2022-05-13 19:15:59,540 INFO [train.py:876] (3/8) Training started
2022-05-13 19:15:59,540 INFO [train.py:886] (3/8) Device: cuda:3
2022-05-13 19:15:59,543 INFO [train.py:895] (3/8) {'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 19:15:59,544 INFO [train.py:897] (3/8) About to create model
2022-05-13 19:16:00,261 INFO [train.py:901] (3/8) Number of model parameters: 116553580
2022-05-13 19:16:07,894 INFO [train.py:916] (3/8) Using DDP
2022-05-13 19:16:09,396 INFO [asr_datamodule.py:391] (3/8) About to get train-clean-100 cuts
2022-05-13 19:16:17,933 INFO [asr_datamodule.py:398] (3/8) About to get train-clean-360 cuts
2022-05-13 19:16:51,517 INFO [asr_datamodule.py:405] (3/8) About to get train-other-500 cuts
2022-05-13 19:17:48,256 INFO [asr_datamodule.py:209] (3/8) Enable MUSAN
2022-05-13 19:17:48,256 INFO [asr_datamodule.py:210] (3/8) About to get Musan cuts
2022-05-13 19:17:50,206 INFO [asr_datamodule.py:238] (3/8) Enable SpecAugment
2022-05-13 19:17:50,206 INFO [asr_datamodule.py:239] (3/8) Time warp factor: 80
2022-05-13 19:17:50,206 INFO [asr_datamodule.py:251] (3/8) Num frame mask: 10
2022-05-13 19:17:50,206 INFO [asr_datamodule.py:264] (3/8) About to create train dataset
2022-05-13 19:17:50,206 INFO [asr_datamodule.py:292] (3/8) Using BucketingSampler.
2022-05-13 19:17:56,080 INFO [asr_datamodule.py:308] (3/8) About to create train dataloader
2022-05-13 19:17:56,081 INFO [asr_datamodule.py:412] (3/8) About to get dev-clean cuts
2022-05-13 19:17:56,430 INFO [asr_datamodule.py:417] (3/8) About to get dev-other cuts
2022-05-13 19:17:56,636 INFO [asr_datamodule.py:339] (3/8) About to create dev dataset
2022-05-13 19:17:56,648 INFO [asr_datamodule.py:358] (3/8) About to create dev dataloader
2022-05-13 19:17:56,648 INFO [train.py:1078] (3/8) 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] (3/8) Reducer buckets have been rebuilt in this iteration.
2022-05-13 19:18:41,987 INFO [train.py:812] (3/8) Epoch 1, batch 0, loss[loss=0.781, simple_loss=1.562, pruned_loss=6.565, over 7286.00 frames.], tot_loss[loss=0.781, simple_loss=1.562, pruned_loss=6.565, over 7286.00 frames.], batch size: 17, lr: 3.00e-03
2022-05-13 19:19:41,267 INFO [train.py:812] (3/8) Epoch 1, batch 50, loss[loss=0.4932, simple_loss=0.9864, pruned_loss=7.017, over 7145.00 frames.], tot_loss[loss=0.5596, simple_loss=1.119, pruned_loss=7.124, over 323403.14 frames.], batch size: 19, lr: 3.00e-03
2022-05-13 19:20:39,812 INFO [train.py:812] (3/8) Epoch 1, batch 100, loss[loss=0.3937, simple_loss=0.7875, pruned_loss=6.65, over 6984.00 frames.], tot_loss[loss=0.499, simple_loss=0.9979, pruned_loss=6.976, over 566246.52 frames.], batch size: 16, lr: 3.00e-03
2022-05-13 19:21:38,639 INFO [train.py:812] (3/8) Epoch 1, batch 150, loss[loss=0.3797, simple_loss=0.7595, pruned_loss=6.71, over 7004.00 frames.], tot_loss[loss=0.4651, simple_loss=0.9302, pruned_loss=6.88, over 757306.73 frames.], batch size: 16, lr: 3.00e-03
2022-05-13 19:22:36,951 INFO [train.py:812] (3/8) Epoch 1, batch 200, loss[loss=0.4016, simple_loss=0.8032, pruned_loss=6.781, over 7266.00 frames.], tot_loss[loss=0.4439, simple_loss=0.8879, pruned_loss=6.847, over 907523.01 frames.], batch size: 25, lr: 3.00e-03
2022-05-13 19:23:35,687 INFO [train.py:812] (3/8) Epoch 1, batch 250, loss[loss=0.422, simple_loss=0.8439, pruned_loss=6.937, over 7310.00 frames.], tot_loss[loss=0.4285, simple_loss=0.8569, pruned_loss=6.832, over 1016093.93 frames.], batch size: 21, lr: 3.00e-03
2022-05-13 19:24:34,035 INFO [train.py:812] (3/8) Epoch 1, batch 300, loss[loss=0.4211, simple_loss=0.8422, pruned_loss=6.938, over 7303.00 frames.], tot_loss[loss=0.4184, simple_loss=0.8369, pruned_loss=6.829, over 1108842.22 frames.], batch size: 25, lr: 3.00e-03
2022-05-13 19:25:33,442 INFO [train.py:812] (3/8) Epoch 1, batch 350, loss[loss=0.4016, simple_loss=0.8033, pruned_loss=6.836, over 7272.00 frames.], tot_loss[loss=0.4095, simple_loss=0.8191, pruned_loss=6.818, over 1178352.97 frames.], batch size: 19, lr: 3.00e-03
2022-05-13 19:26:31,629 INFO [train.py:812] (3/8) Epoch 1, batch 400, loss[loss=0.3926, simple_loss=0.7852, pruned_loss=6.887, over 7426.00 frames.], tot_loss[loss=0.4018, simple_loss=0.8035, pruned_loss=6.802, over 1231098.69 frames.], batch size: 21, lr: 3.00e-03
2022-05-13 19:27:30,036 INFO [train.py:812] (3/8) Epoch 1, batch 450, loss[loss=0.3488, simple_loss=0.6975, pruned_loss=6.798, over 7410.00 frames.], tot_loss[loss=0.3918, simple_loss=0.7836, pruned_loss=6.786, over 1268383.12 frames.], batch size: 21, lr: 2.99e-03
2022-05-13 19:28:29,386 INFO [train.py:812] (3/8) Epoch 1, batch 500, loss[loss=0.3194, simple_loss=0.6388, pruned_loss=6.716, over 7209.00 frames.], tot_loss[loss=0.377, simple_loss=0.754, pruned_loss=6.772, over 1303984.82 frames.], batch size: 22, lr: 2.99e-03
2022-05-13 19:29:27,240 INFO [train.py:812] (3/8) Epoch 1, batch 550, loss[loss=0.3416, simple_loss=0.6833, pruned_loss=6.861, over 7336.00 frames.], tot_loss[loss=0.3627, simple_loss=0.7255, pruned_loss=6.767, over 1330274.69 frames.], batch size: 22, lr: 2.99e-03
2022-05-13 19:30:26,704 INFO [train.py:812] (3/8) Epoch 1, batch 600, loss[loss=0.308, simple_loss=0.6159, pruned_loss=6.77, over 7123.00 frames.], tot_loss[loss=0.3471, simple_loss=0.6942, pruned_loss=6.762, over 1351262.06 frames.], batch size: 21, lr: 2.99e-03
2022-05-13 19:31:24,372 INFO [train.py:812] (3/8) Epoch 1, batch 650, loss[loss=0.2299, simple_loss=0.4597, pruned_loss=6.529, over 6989.00 frames.], tot_loss[loss=0.3314, simple_loss=0.6627, pruned_loss=6.756, over 1369457.65 frames.], batch size: 16, lr: 2.99e-03
2022-05-13 19:32:22,732 INFO [train.py:812] (3/8) Epoch 1, batch 700, loss[loss=0.2672, simple_loss=0.5345, pruned_loss=6.809, over 7191.00 frames.], tot_loss[loss=0.3165, simple_loss=0.6329, pruned_loss=6.746, over 1381348.24 frames.], batch size: 23, lr: 2.99e-03
2022-05-13 19:33:21,780 INFO [train.py:812] (3/8) Epoch 1, batch 750, loss[loss=0.2515, simple_loss=0.5029, pruned_loss=6.629, over 7285.00 frames.], tot_loss[loss=0.303, simple_loss=0.606, pruned_loss=6.74, over 1393501.81 frames.], batch size: 17, lr: 2.98e-03
2022-05-13 19:34:19,630 INFO [train.py:812] (3/8) Epoch 1, batch 800, loss[loss=0.2569, simple_loss=0.5137, pruned_loss=6.751, over 7125.00 frames.], tot_loss[loss=0.2914, simple_loss=0.5827, pruned_loss=6.737, over 1398570.79 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:35:17,941 INFO [train.py:812] (3/8) Epoch 1, batch 850, loss[loss=0.267, simple_loss=0.5339, pruned_loss=6.908, over 7227.00 frames.], tot_loss[loss=0.2807, simple_loss=0.5614, pruned_loss=6.737, over 1403582.62 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:36:17,405 INFO [train.py:812] (3/8) Epoch 1, batch 900, loss[loss=0.2342, simple_loss=0.4684, pruned_loss=6.781, over 7309.00 frames.], tot_loss[loss=0.2709, simple_loss=0.5418, pruned_loss=6.737, over 1409101.19 frames.], batch size: 21, lr: 2.98e-03
2022-05-13 19:37:15,463 INFO [train.py:812] (3/8) Epoch 1, batch 950, loss[loss=0.2019, simple_loss=0.4038, pruned_loss=6.572, over 6992.00 frames.], tot_loss[loss=0.2637, simple_loss=0.5273, pruned_loss=6.74, over 1405256.02 frames.], batch size: 16, lr: 2.97e-03
2022-05-13 19:38:15,210 INFO [train.py:812] (3/8) Epoch 1, batch 1000, loss[loss=0.2004, simple_loss=0.4008, pruned_loss=6.539, over 6986.00 frames.], tot_loss[loss=0.2569, simple_loss=0.5138, pruned_loss=6.74, over 1405591.55 frames.], batch size: 16, lr: 2.97e-03
2022-05-13 19:39:14,103 INFO [train.py:812] (3/8) Epoch 1, batch 1050, loss[loss=0.1982, simple_loss=0.3964, pruned_loss=6.668, over 6981.00 frames.], tot_loss[loss=0.2506, simple_loss=0.5012, pruned_loss=6.745, over 1407974.34 frames.], batch size: 16, lr: 2.97e-03
2022-05-13 19:40:12,426 INFO [train.py:812] (3/8) Epoch 1, batch 1100, loss[loss=0.2456, simple_loss=0.4912, pruned_loss=6.889, over 7189.00 frames.], tot_loss[loss=0.2451, simple_loss=0.4903, pruned_loss=6.75, over 1411438.35 frames.], batch size: 22, lr: 2.96e-03
2022-05-13 19:41:10,362 INFO [train.py:812] (3/8) Epoch 1, batch 1150, loss[loss=0.2266, simple_loss=0.4533, pruned_loss=6.86, over 6718.00 frames.], tot_loss[loss=0.2398, simple_loss=0.4796, pruned_loss=6.749, over 1412961.63 frames.], batch size: 31, lr: 2.96e-03
2022-05-13 19:42:08,514 INFO [train.py:812] (3/8) Epoch 1, batch 1200, loss[loss=0.231, simple_loss=0.4619, pruned_loss=6.944, over 7170.00 frames.], tot_loss[loss=0.2353, simple_loss=0.4705, pruned_loss=6.751, over 1420534.59 frames.], batch size: 26, lr: 2.96e-03
2022-05-13 19:43:07,159 INFO [train.py:812] (3/8) Epoch 1, batch 1250, loss[loss=0.2245, simple_loss=0.4491, pruned_loss=6.8, over 7377.00 frames.], tot_loss[loss=0.2308, simple_loss=0.4616, pruned_loss=6.755, over 1414521.35 frames.], batch size: 23, lr: 2.95e-03
2022-05-13 19:44:06,121 INFO [train.py:812] (3/8) Epoch 1, batch 1300, loss[loss=0.2161, simple_loss=0.4322, pruned_loss=6.814, over 7293.00 frames.], tot_loss[loss=0.2266, simple_loss=0.4532, pruned_loss=6.757, over 1421685.22 frames.], batch size: 24, lr: 2.95e-03
2022-05-13 19:45:04,274 INFO [train.py:812] (3/8) Epoch 1, batch 1350, loss[loss=0.201, simple_loss=0.4021, pruned_loss=6.763, over 7152.00 frames.], tot_loss[loss=0.2223, simple_loss=0.4446, pruned_loss=6.751, over 1422653.87 frames.], batch size: 20, lr: 2.95e-03
2022-05-13 19:46:03,477 INFO [train.py:812] (3/8) Epoch 1, batch 1400, loss[loss=0.2186, simple_loss=0.4372, pruned_loss=6.871, over 7284.00 frames.], tot_loss[loss=0.2206, simple_loss=0.4412, pruned_loss=6.759, over 1418905.51 frames.], batch size: 24, lr: 2.94e-03
2022-05-13 19:47:02,118 INFO [train.py:812] (3/8) Epoch 1, batch 1450, loss[loss=0.1851, simple_loss=0.3702, pruned_loss=6.68, over 7135.00 frames.], tot_loss[loss=0.2178, simple_loss=0.4357, pruned_loss=6.76, over 1419921.19 frames.], batch size: 17, lr: 2.94e-03
2022-05-13 19:48:00,924 INFO [train.py:812] (3/8) Epoch 1, batch 1500, loss[loss=0.1952, simple_loss=0.3905, pruned_loss=6.728, over 7311.00 frames.], tot_loss[loss=0.2154, simple_loss=0.4307, pruned_loss=6.759, over 1422729.33 frames.], batch size: 24, lr: 2.94e-03
2022-05-13 19:48:59,561 INFO [train.py:812] (3/8) Epoch 1, batch 1550, loss[loss=0.2113, simple_loss=0.4226, pruned_loss=6.781, over 7116.00 frames.], tot_loss[loss=0.2131, simple_loss=0.4261, pruned_loss=6.758, over 1423077.22 frames.], batch size: 21, lr: 2.93e-03
2022-05-13 19:49:59,200 INFO [train.py:812] (3/8) Epoch 1, batch 1600, loss[loss=0.2069, simple_loss=0.4139, pruned_loss=6.732, over 7324.00 frames.], tot_loss[loss=0.2106, simple_loss=0.4212, pruned_loss=6.757, over 1421181.38 frames.], batch size: 20, lr: 2.93e-03
2022-05-13 19:50:59,008 INFO [train.py:812] (3/8) Epoch 1, batch 1650, loss[loss=0.1854, simple_loss=0.3708, pruned_loss=6.597, over 7157.00 frames.], tot_loss[loss=0.2081, simple_loss=0.4161, pruned_loss=6.751, over 1422480.46 frames.], batch size: 18, lr: 2.92e-03
2022-05-13 19:51:59,066 INFO [train.py:812] (3/8) Epoch 1, batch 1700, loss[loss=0.1932, simple_loss=0.3865, pruned_loss=6.815, over 6334.00 frames.], tot_loss[loss=0.2065, simple_loss=0.413, pruned_loss=6.754, over 1417828.34 frames.], batch size: 38, lr: 2.92e-03
2022-05-13 19:52:58,901 INFO [train.py:812] (3/8) Epoch 1, batch 1750, loss[loss=0.1977, simple_loss=0.3954, pruned_loss=6.762, over 6621.00 frames.], tot_loss[loss=0.2041, simple_loss=0.4083, pruned_loss=6.753, over 1418934.94 frames.], batch size: 38, lr: 2.91e-03
2022-05-13 19:54:00,194 INFO [train.py:812] (3/8) Epoch 1, batch 1800, loss[loss=0.2051, simple_loss=0.4102, pruned_loss=6.834, over 7116.00 frames.], tot_loss[loss=0.2019, simple_loss=0.4039, pruned_loss=6.755, over 1418714.12 frames.], batch size: 28, lr: 2.91e-03
2022-05-13 19:54:58,673 INFO [train.py:812] (3/8) Epoch 1, batch 1850, loss[loss=0.222, simple_loss=0.4439, pruned_loss=6.818, over 5004.00 frames.], tot_loss[loss=0.1992, simple_loss=0.3983, pruned_loss=6.752, over 1419431.03 frames.], batch size: 52, lr: 2.91e-03
2022-05-13 19:55:57,000 INFO [train.py:812] (3/8) Epoch 1, batch 1900, loss[loss=0.2046, simple_loss=0.4092, pruned_loss=6.764, over 7248.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3967, pruned_loss=6.755, over 1419624.75 frames.], batch size: 19, lr: 2.90e-03
2022-05-13 19:56:55,450 INFO [train.py:812] (3/8) Epoch 1, batch 1950, loss[loss=0.2083, simple_loss=0.4166, pruned_loss=6.761, over 7322.00 frames.], tot_loss[loss=0.1971, simple_loss=0.3942, pruned_loss=6.755, over 1422771.08 frames.], batch size: 21, lr: 2.90e-03
2022-05-13 19:57:54,272 INFO [train.py:812] (3/8) Epoch 1, batch 2000, loss[loss=0.1771, simple_loss=0.3542, pruned_loss=6.672, over 6742.00 frames.], tot_loss[loss=0.196, simple_loss=0.3919, pruned_loss=6.756, over 1422270.75 frames.], batch size: 15, lr: 2.89e-03
2022-05-13 19:58:53,066 INFO [train.py:812] (3/8) Epoch 1, batch 2050, loss[loss=0.1945, simple_loss=0.3889, pruned_loss=6.751, over 7191.00 frames.], tot_loss[loss=0.1944, simple_loss=0.3888, pruned_loss=6.753, over 1420582.21 frames.], batch size: 26, lr: 2.89e-03
2022-05-13 19:59:51,412 INFO [train.py:812] (3/8) Epoch 1, batch 2100, loss[loss=0.1911, simple_loss=0.3822, pruned_loss=6.719, over 7164.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3873, pruned_loss=6.754, over 1417459.10 frames.], batch size: 18, lr: 2.88e-03
2022-05-13 20:00:49,528 INFO [train.py:812] (3/8) Epoch 1, batch 2150, loss[loss=0.2079, simple_loss=0.4157, pruned_loss=6.757, over 7339.00 frames.], tot_loss[loss=0.1924, simple_loss=0.3848, pruned_loss=6.752, over 1421295.59 frames.], batch size: 22, lr: 2.88e-03
2022-05-13 20:01:48,621 INFO [train.py:812] (3/8) Epoch 1, batch 2200, loss[loss=0.1861, simple_loss=0.3723, pruned_loss=6.692, over 7305.00 frames.], tot_loss[loss=0.1923, simple_loss=0.3846, pruned_loss=6.754, over 1421420.28 frames.], batch size: 25, lr: 2.87e-03
2022-05-13 20:02:47,460 INFO [train.py:812] (3/8) Epoch 1, batch 2250, loss[loss=0.1986, simple_loss=0.3973, pruned_loss=6.887, over 7220.00 frames.], tot_loss[loss=0.1914, simple_loss=0.3829, pruned_loss=6.749, over 1420276.68 frames.], batch size: 21, lr: 2.86e-03
2022-05-13 20:03:45,874 INFO [train.py:812] (3/8) Epoch 1, batch 2300, loss[loss=0.1812, simple_loss=0.3623, pruned_loss=6.761, over 7250.00 frames.], tot_loss[loss=0.1905, simple_loss=0.381, pruned_loss=6.746, over 1415383.16 frames.], batch size: 19, lr: 2.86e-03
2022-05-13 20:04:43,213 INFO [train.py:812] (3/8) Epoch 1, batch 2350, loss[loss=0.2179, simple_loss=0.4358, pruned_loss=6.845, over 5102.00 frames.], tot_loss[loss=0.1903, simple_loss=0.3807, pruned_loss=6.757, over 1415362.38 frames.], batch size: 53, lr: 2.85e-03
2022-05-13 20:05:42,790 INFO [train.py:812] (3/8) Epoch 1, batch 2400, loss[loss=0.1723, simple_loss=0.3445, pruned_loss=6.809, over 7420.00 frames.], tot_loss[loss=0.1897, simple_loss=0.3793, pruned_loss=6.759, over 1410723.73 frames.], batch size: 20, lr: 2.85e-03
2022-05-13 20:06:41,410 INFO [train.py:812] (3/8) Epoch 1, batch 2450, loss[loss=0.2007, simple_loss=0.4014, pruned_loss=6.757, over 5040.00 frames.], tot_loss[loss=0.189, simple_loss=0.378, pruned_loss=6.76, over 1411730.22 frames.], batch size: 52, lr: 2.84e-03
2022-05-13 20:07:40,730 INFO [train.py:812] (3/8) Epoch 1, batch 2500, loss[loss=0.1673, simple_loss=0.3346, pruned_loss=6.709, over 7335.00 frames.], tot_loss[loss=0.1878, simple_loss=0.3755, pruned_loss=6.752, over 1418121.25 frames.], batch size: 20, lr: 2.84e-03
2022-05-13 20:08:39,334 INFO [train.py:812] (3/8) Epoch 1, batch 2550, loss[loss=0.171, simple_loss=0.342, pruned_loss=6.714, over 7399.00 frames.], tot_loss[loss=0.1881, simple_loss=0.3761, pruned_loss=6.749, over 1418795.00 frames.], batch size: 18, lr: 2.83e-03
2022-05-13 20:09:37,910 INFO [train.py:812] (3/8) Epoch 1, batch 2600, loss[loss=0.2075, simple_loss=0.415, pruned_loss=6.797, over 7235.00 frames.], tot_loss[loss=0.1862, simple_loss=0.3724, pruned_loss=6.74, over 1421164.74 frames.], batch size: 20, lr: 2.83e-03
2022-05-13 20:10:35,863 INFO [train.py:812] (3/8) Epoch 1, batch 2650, loss[loss=0.1937, simple_loss=0.3875, pruned_loss=6.848, over 7233.00 frames.], tot_loss[loss=0.1854, simple_loss=0.3708, pruned_loss=6.742, over 1422649.81 frames.], batch size: 20, lr: 2.82e-03
2022-05-13 20:11:35,696 INFO [train.py:812] (3/8) Epoch 1, batch 2700, loss[loss=0.1844, simple_loss=0.3688, pruned_loss=6.81, over 7143.00 frames.], tot_loss[loss=0.1853, simple_loss=0.3706, pruned_loss=6.743, over 1422168.41 frames.], batch size: 20, lr: 2.81e-03
2022-05-13 20:12:32,554 INFO [train.py:812] (3/8) Epoch 1, batch 2750, loss[loss=0.1769, simple_loss=0.3538, pruned_loss=6.856, over 7330.00 frames.], tot_loss[loss=0.1849, simple_loss=0.3699, pruned_loss=6.746, over 1423011.67 frames.], batch size: 20, lr: 2.81e-03
2022-05-13 20:13:32,109 INFO [train.py:812] (3/8) Epoch 1, batch 2800, loss[loss=0.1896, simple_loss=0.3792, pruned_loss=6.812, over 7152.00 frames.], tot_loss[loss=0.1848, simple_loss=0.3696, pruned_loss=6.746, over 1422896.90 frames.], batch size: 20, lr: 2.80e-03
2022-05-13 20:14:30,979 INFO [train.py:812] (3/8) Epoch 1, batch 2850, loss[loss=0.1624, simple_loss=0.3248, pruned_loss=6.659, over 7363.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3674, pruned_loss=6.742, over 1425502.37 frames.], batch size: 19, lr: 2.80e-03
2022-05-13 20:15:28,495 INFO [train.py:812] (3/8) Epoch 1, batch 2900, loss[loss=0.1748, simple_loss=0.3496, pruned_loss=6.73, over 7326.00 frames.], tot_loss[loss=0.1845, simple_loss=0.369, pruned_loss=6.743, over 1421114.12 frames.], batch size: 20, lr: 2.79e-03
2022-05-13 20:16:27,581 INFO [train.py:812] (3/8) Epoch 1, batch 2950, loss[loss=0.1907, simple_loss=0.3815, pruned_loss=6.748, over 7154.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3675, pruned_loss=6.74, over 1417170.69 frames.], batch size: 26, lr: 2.78e-03
2022-05-13 20:17:26,747 INFO [train.py:812] (3/8) Epoch 1, batch 3000, loss[loss=0.3151, simple_loss=0.3319, pruned_loss=1.491, over 7277.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3656, pruned_loss=6.713, over 1420734.00 frames.], batch size: 17, lr: 2.78e-03
2022-05-13 20:17:26,748 INFO [train.py:832] (3/8) Computing validation loss
2022-05-13 20:17:34,928 INFO [train.py:841] (3/8) Epoch 1, validation: loss=2.094, simple_loss=0.4148, pruned_loss=1.887, over 698248.00 frames.
2022-05-13 20:18:33,878 INFO [train.py:812] (3/8) Epoch 1, batch 3050, loss[loss=0.2945, simple_loss=0.3939, pruned_loss=0.9752, over 6540.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3749, pruned_loss=5.505, over 1419628.85 frames.], batch size: 38, lr: 2.77e-03
2022-05-13 20:19:33,922 INFO [train.py:812] (3/8) Epoch 1, batch 3100, loss[loss=0.2466, simple_loss=0.3769, pruned_loss=0.5818, over 7415.00 frames.], tot_loss[loss=0.2425, simple_loss=0.3694, pruned_loss=4.428, over 1425455.85 frames.], batch size: 21, lr: 2.77e-03
2022-05-13 20:20:32,559 INFO [train.py:812] (3/8) Epoch 1, batch 3150, loss[loss=0.2336, simple_loss=0.3878, pruned_loss=0.3964, over 7406.00 frames.], tot_loss[loss=0.238, simple_loss=0.3667, pruned_loss=3.54, over 1426568.49 frames.], batch size: 21, lr: 2.76e-03
2022-05-13 20:21:30,565 INFO [train.py:812] (3/8) Epoch 1, batch 3200, loss[loss=0.2394, simple_loss=0.4137, pruned_loss=0.3251, over 7289.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3666, pruned_loss=2.83, over 1423379.09 frames.], batch size: 24, lr: 2.75e-03
2022-05-13 20:22:29,480 INFO [train.py:812] (3/8) Epoch 1, batch 3250, loss[loss=0.2325, simple_loss=0.4049, pruned_loss=0.3001, over 7154.00 frames.], tot_loss[loss=0.2273, simple_loss=0.3659, pruned_loss=2.261, over 1423404.25 frames.], batch size: 20, lr: 2.75e-03
2022-05-13 20:23:28,330 INFO [train.py:812] (3/8) Epoch 1, batch 3300, loss[loss=0.2211, simple_loss=0.3925, pruned_loss=0.2487, over 7376.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3656, pruned_loss=1.817, over 1418291.28 frames.], batch size: 23, lr: 2.74e-03
2022-05-13 20:24:25,737 INFO [train.py:812] (3/8) Epoch 1, batch 3350, loss[loss=0.1899, simple_loss=0.3444, pruned_loss=0.1774, over 7291.00 frames.], tot_loss[loss=0.2175, simple_loss=0.364, pruned_loss=1.456, over 1423372.89 frames.], batch size: 24, lr: 2.73e-03
2022-05-13 20:25:24,234 INFO [train.py:812] (3/8) Epoch 1, batch 3400, loss[loss=0.208, simple_loss=0.3749, pruned_loss=0.2056, over 7251.00 frames.], tot_loss[loss=0.2136, simple_loss=0.363, pruned_loss=1.178, over 1423833.96 frames.], batch size: 19, lr: 2.73e-03
2022-05-13 20:26:22,123 INFO [train.py:812] (3/8) Epoch 1, batch 3450, loss[loss=0.2019, simple_loss=0.368, pruned_loss=0.1788, over 7318.00 frames.], tot_loss[loss=0.2107, simple_loss=0.3627, pruned_loss=0.9604, over 1423510.24 frames.], batch size: 25, lr: 2.72e-03
2022-05-13 20:27:20,221 INFO [train.py:812] (3/8) Epoch 1, batch 3500, loss[loss=0.1982, simple_loss=0.3605, pruned_loss=0.1794, over 7120.00 frames.], tot_loss[loss=0.207, simple_loss=0.3604, pruned_loss=0.7877, over 1421099.69 frames.], batch size: 26, lr: 2.72e-03
2022-05-13 20:28:19,234 INFO [train.py:812] (3/8) Epoch 1, batch 3550, loss[loss=0.2114, simple_loss=0.3835, pruned_loss=0.1963, over 7216.00 frames.], tot_loss[loss=0.2039, simple_loss=0.3584, pruned_loss=0.6515, over 1422566.67 frames.], batch size: 21, lr: 2.71e-03
2022-05-13 20:29:18,095 INFO [train.py:812] (3/8) Epoch 1, batch 3600, loss[loss=0.1935, simple_loss=0.3499, pruned_loss=0.1859, over 7014.00 frames.], tot_loss[loss=0.2017, simple_loss=0.3572, pruned_loss=0.5463, over 1421319.77 frames.], batch size: 16, lr: 2.70e-03
2022-05-13 20:30:25,538 INFO [train.py:812] (3/8) Epoch 1, batch 3650, loss[loss=0.2191, simple_loss=0.3977, pruned_loss=0.2022, over 7223.00 frames.], tot_loss[loss=0.1994, simple_loss=0.3555, pruned_loss=0.4615, over 1422641.22 frames.], batch size: 21, lr: 2.70e-03
2022-05-13 20:32:10,020 INFO [train.py:812] (3/8) Epoch 1, batch 3700, loss[loss=0.2014, simple_loss=0.3676, pruned_loss=0.1762, over 6763.00 frames.], tot_loss[loss=0.1969, simple_loss=0.353, pruned_loss=0.394, over 1426182.49 frames.], batch size: 31, lr: 2.69e-03
2022-05-13 20:33:27,098 INFO [train.py:812] (3/8) Epoch 1, batch 3750, loss[loss=0.1581, simple_loss=0.294, pruned_loss=0.1113, over 7278.00 frames.], tot_loss[loss=0.1956, simple_loss=0.3522, pruned_loss=0.3441, over 1418547.04 frames.], batch size: 18, lr: 2.68e-03
2022-05-13 20:34:26,654 INFO [train.py:812] (3/8) Epoch 1, batch 3800, loss[loss=0.1567, simple_loss=0.2902, pruned_loss=0.1161, over 7129.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3517, pruned_loss=0.3031, over 1418421.52 frames.], batch size: 17, lr: 2.68e-03
2022-05-13 20:35:25,747 INFO [train.py:812] (3/8) Epoch 1, batch 3850, loss[loss=0.189, simple_loss=0.3423, pruned_loss=0.1788, over 7115.00 frames.], tot_loss[loss=0.1935, simple_loss=0.3509, pruned_loss=0.2699, over 1423719.25 frames.], batch size: 17, lr: 2.67e-03
2022-05-13 20:36:24,056 INFO [train.py:812] (3/8) Epoch 1, batch 3900, loss[loss=0.1679, simple_loss=0.3108, pruned_loss=0.125, over 6791.00 frames.], tot_loss[loss=0.193, simple_loss=0.351, pruned_loss=0.2455, over 1420164.38 frames.], batch size: 15, lr: 2.66e-03
2022-05-13 20:37:21,119 INFO [train.py:812] (3/8) Epoch 1, batch 3950, loss[loss=0.1513, simple_loss=0.2823, pruned_loss=0.1014, over 6811.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3493, pruned_loss=0.2244, over 1417660.74 frames.], batch size: 15, lr: 2.66e-03
2022-05-13 20:38:27,953 INFO [train.py:812] (3/8) Epoch 1, batch 4000, loss[loss=0.1939, simple_loss=0.3587, pruned_loss=0.1461, over 7315.00 frames.], tot_loss[loss=0.1912, simple_loss=0.3492, pruned_loss=0.2087, over 1420355.05 frames.], batch size: 21, lr: 2.65e-03
2022-05-13 20:39:26,721 INFO [train.py:812] (3/8) Epoch 1, batch 4050, loss[loss=0.1926, simple_loss=0.3569, pruned_loss=0.1418, over 7080.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3492, pruned_loss=0.196, over 1421153.61 frames.], batch size: 28, lr: 2.64e-03
2022-05-13 20:40:25,271 INFO [train.py:812] (3/8) Epoch 1, batch 4100, loss[loss=0.1731, simple_loss=0.3217, pruned_loss=0.1222, over 7263.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3472, pruned_loss=0.1848, over 1421277.27 frames.], batch size: 19, lr: 2.64e-03
2022-05-13 20:41:23,930 INFO [train.py:812] (3/8) Epoch 1, batch 4150, loss[loss=0.1721, simple_loss=0.3184, pruned_loss=0.1292, over 7053.00 frames.], tot_loss[loss=0.1894, simple_loss=0.3474, pruned_loss=0.1767, over 1425540.50 frames.], batch size: 18, lr: 2.63e-03
2022-05-13 20:42:22,989 INFO [train.py:812] (3/8) Epoch 1, batch 4200, loss[loss=0.1947, simple_loss=0.3565, pruned_loss=0.1644, over 7188.00 frames.], tot_loss[loss=0.1892, simple_loss=0.3474, pruned_loss=0.1702, over 1425353.84 frames.], batch size: 22, lr: 2.63e-03
2022-05-13 20:43:21,440 INFO [train.py:812] (3/8) Epoch 1, batch 4250, loss[loss=0.1755, simple_loss=0.3248, pruned_loss=0.1313, over 7443.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3462, pruned_loss=0.164, over 1422948.95 frames.], batch size: 20, lr: 2.62e-03
2022-05-13 20:44:20,462 INFO [train.py:812] (3/8) Epoch 1, batch 4300, loss[loss=0.2045, simple_loss=0.3766, pruned_loss=0.1617, over 7109.00 frames.], tot_loss[loss=0.1889, simple_loss=0.3474, pruned_loss=0.161, over 1422769.15 frames.], batch size: 28, lr: 2.61e-03
2022-05-13 20:45:19,035 INFO [train.py:812] (3/8) Epoch 1, batch 4350, loss[loss=0.1701, simple_loss=0.3179, pruned_loss=0.1112, over 7429.00 frames.], tot_loss[loss=0.1886, simple_loss=0.3473, pruned_loss=0.1566, over 1426555.38 frames.], batch size: 20, lr: 2.61e-03
2022-05-13 20:46:18,355 INFO [train.py:812] (3/8) Epoch 1, batch 4400, loss[loss=0.1638, simple_loss=0.3032, pruned_loss=0.1217, over 7259.00 frames.], tot_loss[loss=0.1882, simple_loss=0.3469, pruned_loss=0.1531, over 1424384.01 frames.], batch size: 18, lr: 2.60e-03
2022-05-13 20:47:17,358 INFO [train.py:812] (3/8) Epoch 1, batch 4450, loss[loss=0.1833, simple_loss=0.3397, pruned_loss=0.1348, over 7442.00 frames.], tot_loss[loss=0.1881, simple_loss=0.347, pruned_loss=0.1506, over 1423952.19 frames.], batch size: 20, lr: 2.59e-03
2022-05-13 20:48:16,797 INFO [train.py:812] (3/8) Epoch 1, batch 4500, loss[loss=0.2084, simple_loss=0.3788, pruned_loss=0.1905, over 6380.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3474, pruned_loss=0.1494, over 1414028.66 frames.], batch size: 37, lr: 2.59e-03
2022-05-13 20:49:13,803 INFO [train.py:812] (3/8) Epoch 1, batch 4550, loss[loss=0.1974, simple_loss=0.3645, pruned_loss=0.1517, over 4890.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3495, pruned_loss=0.1501, over 1395020.08 frames.], batch size: 52, lr: 2.58e-03
2022-05-13 20:50:25,938 INFO [train.py:812] (3/8) Epoch 2, batch 0, loss[loss=0.2116, simple_loss=0.3869, pruned_loss=0.1814, over 7129.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3869, pruned_loss=0.1814, over 7129.00 frames.], batch size: 26, lr: 2.56e-03
2022-05-13 20:51:25,844 INFO [train.py:812] (3/8) Epoch 2, batch 50, loss[loss=0.1992, simple_loss=0.3697, pruned_loss=0.1439, over 7240.00 frames.], tot_loss[loss=0.1854, simple_loss=0.3429, pruned_loss=0.1393, over 312501.62 frames.], batch size: 20, lr: 2.55e-03
2022-05-13 20:52:24,849 INFO [train.py:812] (3/8) Epoch 2, batch 100, loss[loss=0.1744, simple_loss=0.3267, pruned_loss=0.1103, over 7435.00 frames.], tot_loss[loss=0.1838, simple_loss=0.3406, pruned_loss=0.1347, over 560531.87 frames.], batch size: 20, lr: 2.54e-03
2022-05-13 20:53:23,901 INFO [train.py:812] (3/8) Epoch 2, batch 150, loss[loss=0.1856, simple_loss=0.3479, pruned_loss=0.1164, over 7319.00 frames.], tot_loss[loss=0.1839, simple_loss=0.3408, pruned_loss=0.1348, over 751999.35 frames.], batch size: 20, lr: 2.54e-03
2022-05-13 20:54:21,302 INFO [train.py:812] (3/8) Epoch 2, batch 200, loss[loss=0.1557, simple_loss=0.2932, pruned_loss=0.09066, over 7164.00 frames.], tot_loss[loss=0.1828, simple_loss=0.3391, pruned_loss=0.1331, over 900815.75 frames.], batch size: 19, lr: 2.53e-03
2022-05-13 20:55:19,834 INFO [train.py:812] (3/8) Epoch 2, batch 250, loss[loss=0.1849, simple_loss=0.3427, pruned_loss=0.1358, over 7365.00 frames.], tot_loss[loss=0.1839, simple_loss=0.3409, pruned_loss=0.1345, over 1015868.22 frames.], batch size: 23, lr: 2.53e-03
2022-05-13 20:56:18,126 INFO [train.py:812] (3/8) Epoch 2, batch 300, loss[loss=0.1766, simple_loss=0.3297, pruned_loss=0.1177, over 7248.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3406, pruned_loss=0.1337, over 1104837.50 frames.], batch size: 19, lr: 2.52e-03
2022-05-13 20:57:16,218 INFO [train.py:812] (3/8) Epoch 2, batch 350, loss[loss=0.2004, simple_loss=0.3676, pruned_loss=0.1656, over 7221.00 frames.], tot_loss[loss=0.1833, simple_loss=0.3399, pruned_loss=0.1333, over 1173510.03 frames.], batch size: 21, lr: 2.51e-03
2022-05-13 20:58:14,748 INFO [train.py:812] (3/8) Epoch 2, batch 400, loss[loss=0.1781, simple_loss=0.3306, pruned_loss=0.1275, over 7142.00 frames.], tot_loss[loss=0.1831, simple_loss=0.3396, pruned_loss=0.1331, over 1230998.95 frames.], batch size: 20, lr: 2.51e-03
2022-05-13 20:59:13,913 INFO [train.py:812] (3/8) Epoch 2, batch 450, loss[loss=0.1565, simple_loss=0.2932, pruned_loss=0.09873, over 7159.00 frames.], tot_loss[loss=0.1826, simple_loss=0.3388, pruned_loss=0.1319, over 1276287.79 frames.], batch size: 19, lr: 2.50e-03
2022-05-13 21:00:12,354 INFO [train.py:812] (3/8) Epoch 2, batch 500, loss[loss=0.1613, simple_loss=0.303, pruned_loss=0.09763, over 7159.00 frames.], tot_loss[loss=0.1817, simple_loss=0.3372, pruned_loss=0.1305, over 1308449.04 frames.], batch size: 18, lr: 2.49e-03
2022-05-13 21:01:12,118 INFO [train.py:812] (3/8) Epoch 2, batch 550, loss[loss=0.1781, simple_loss=0.3329, pruned_loss=0.1163, over 7353.00 frames.], tot_loss[loss=0.1816, simple_loss=0.3372, pruned_loss=0.1303, over 1333085.05 frames.], batch size: 19, lr: 2.49e-03
2022-05-13 21:02:10,070 INFO [train.py:812] (3/8) Epoch 2, batch 600, loss[loss=0.2062, simple_loss=0.3767, pruned_loss=0.1783, over 7393.00 frames.], tot_loss[loss=0.1812, simple_loss=0.3366, pruned_loss=0.129, over 1354487.39 frames.], batch size: 23, lr: 2.48e-03
2022-05-13 21:03:08,993 INFO [train.py:812] (3/8) Epoch 2, batch 650, loss[loss=0.1735, simple_loss=0.3228, pruned_loss=0.121, over 7284.00 frames.], tot_loss[loss=0.1816, simple_loss=0.3371, pruned_loss=0.1302, over 1368347.16 frames.], batch size: 18, lr: 2.48e-03
2022-05-13 21:04:08,412 INFO [train.py:812] (3/8) Epoch 2, batch 700, loss[loss=0.2108, simple_loss=0.3821, pruned_loss=0.198, over 4815.00 frames.], tot_loss[loss=0.1814, simple_loss=0.3368, pruned_loss=0.1303, over 1378889.63 frames.], batch size: 52, lr: 2.47e-03
2022-05-13 21:05:07,226 INFO [train.py:812] (3/8) Epoch 2, batch 750, loss[loss=0.1763, simple_loss=0.3273, pruned_loss=0.1266, over 7250.00 frames.], tot_loss[loss=0.1815, simple_loss=0.3371, pruned_loss=0.1297, over 1389699.37 frames.], batch size: 19, lr: 2.46e-03
2022-05-13 21:06:06,453 INFO [train.py:812] (3/8) Epoch 2, batch 800, loss[loss=0.1778, simple_loss=0.3319, pruned_loss=0.1186, over 7067.00 frames.], tot_loss[loss=0.1804, simple_loss=0.3354, pruned_loss=0.1275, over 1399842.22 frames.], batch size: 18, lr: 2.46e-03
2022-05-13 21:07:06,091 INFO [train.py:812] (3/8) Epoch 2, batch 850, loss[loss=0.1595, simple_loss=0.3012, pruned_loss=0.08922, over 7319.00 frames.], tot_loss[loss=0.1802, simple_loss=0.3351, pruned_loss=0.1266, over 1407280.54 frames.], batch size: 20, lr: 2.45e-03
2022-05-13 21:08:05,119 INFO [train.py:812] (3/8) Epoch 2, batch 900, loss[loss=0.1527, simple_loss=0.2879, pruned_loss=0.0871, over 7439.00 frames.], tot_loss[loss=0.1797, simple_loss=0.3344, pruned_loss=0.1256, over 1412767.27 frames.], batch size: 20, lr: 2.45e-03
2022-05-13 21:09:04,129 INFO [train.py:812] (3/8) Epoch 2, batch 950, loss[loss=0.1921, simple_loss=0.3551, pruned_loss=0.1459, over 7258.00 frames.], tot_loss[loss=0.1802, simple_loss=0.3351, pruned_loss=0.1265, over 1415108.49 frames.], batch size: 19, lr: 2.44e-03
2022-05-13 21:10:02,105 INFO [train.py:812] (3/8) Epoch 2, batch 1000, loss[loss=0.1831, simple_loss=0.3426, pruned_loss=0.1182, over 6757.00 frames.], tot_loss[loss=0.1789, simple_loss=0.3328, pruned_loss=0.1246, over 1417402.66 frames.], batch size: 31, lr: 2.43e-03
2022-05-13 21:11:00,256 INFO [train.py:812] (3/8) Epoch 2, batch 1050, loss[loss=0.1933, simple_loss=0.3575, pruned_loss=0.1458, over 7416.00 frames.], tot_loss[loss=0.1788, simple_loss=0.3326, pruned_loss=0.1245, over 1419257.46 frames.], batch size: 20, lr: 2.43e-03
2022-05-13 21:11:59,253 INFO [train.py:812] (3/8) Epoch 2, batch 1100, loss[loss=0.1702, simple_loss=0.3171, pruned_loss=0.1164, over 7162.00 frames.], tot_loss[loss=0.1783, simple_loss=0.3319, pruned_loss=0.1236, over 1420237.86 frames.], batch size: 18, lr: 2.42e-03
2022-05-13 21:12:57,571 INFO [train.py:812] (3/8) Epoch 2, batch 1150, loss[loss=0.1806, simple_loss=0.3356, pruned_loss=0.1275, over 7231.00 frames.], tot_loss[loss=0.1778, simple_loss=0.331, pruned_loss=0.1227, over 1424691.75 frames.], batch size: 20, lr: 2.41e-03
2022-05-13 21:13:56,171 INFO [train.py:812] (3/8) Epoch 2, batch 1200, loss[loss=0.1849, simple_loss=0.3469, pruned_loss=0.1151, over 7075.00 frames.], tot_loss[loss=0.1774, simple_loss=0.3305, pruned_loss=0.1216, over 1423636.08 frames.], batch size: 28, lr: 2.41e-03
2022-05-13 21:14:54,771 INFO [train.py:812] (3/8) Epoch 2, batch 1250, loss[loss=0.1752, simple_loss=0.3244, pruned_loss=0.1302, over 7281.00 frames.], tot_loss[loss=0.1779, simple_loss=0.3314, pruned_loss=0.1218, over 1423222.84 frames.], batch size: 18, lr: 2.40e-03
2022-05-13 21:15:53,347 INFO [train.py:812] (3/8) Epoch 2, batch 1300, loss[loss=0.178, simple_loss=0.3349, pruned_loss=0.105, over 7220.00 frames.], tot_loss[loss=0.1778, simple_loss=0.3313, pruned_loss=0.1216, over 1418053.02 frames.], batch size: 21, lr: 2.40e-03
2022-05-13 21:16:52,354 INFO [train.py:812] (3/8) Epoch 2, batch 1350, loss[loss=0.1521, simple_loss=0.2822, pruned_loss=0.1096, over 7270.00 frames.], tot_loss[loss=0.1771, simple_loss=0.3301, pruned_loss=0.1208, over 1421759.04 frames.], batch size: 17, lr: 2.39e-03
2022-05-13 21:17:49,942 INFO [train.py:812] (3/8) Epoch 2, batch 1400, loss[loss=0.1936, simple_loss=0.3612, pruned_loss=0.13, over 7216.00 frames.], tot_loss[loss=0.1775, simple_loss=0.3309, pruned_loss=0.1212, over 1419586.16 frames.], batch size: 21, lr: 2.39e-03
2022-05-13 21:18:49,266 INFO [train.py:812] (3/8) Epoch 2, batch 1450, loss[loss=0.3009, simple_loss=0.3465, pruned_loss=0.1277, over 7156.00 frames.], tot_loss[loss=0.2006, simple_loss=0.3323, pruned_loss=0.1234, over 1423030.85 frames.], batch size: 26, lr: 2.38e-03
2022-05-13 21:19:47,676 INFO [train.py:812] (3/8) Epoch 2, batch 1500, loss[loss=0.3305, simple_loss=0.3668, pruned_loss=0.1471, over 6254.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3342, pruned_loss=0.1248, over 1422633.09 frames.], batch size: 37, lr: 2.37e-03
2022-05-13 21:20:45,890 INFO [train.py:812] (3/8) Epoch 2, batch 1550, loss[loss=0.2776, simple_loss=0.3279, pruned_loss=0.1136, over 7429.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3348, pruned_loss=0.124, over 1425413.13 frames.], batch size: 20, lr: 2.37e-03
2022-05-13 21:21:43,111 INFO [train.py:812] (3/8) Epoch 2, batch 1600, loss[loss=0.2796, simple_loss=0.3231, pruned_loss=0.118, over 7161.00 frames.], tot_loss[loss=0.2476, simple_loss=0.3337, pruned_loss=0.1226, over 1424012.72 frames.], batch size: 18, lr: 2.36e-03
2022-05-13 21:22:41,916 INFO [train.py:812] (3/8) Epoch 2, batch 1650, loss[loss=0.279, simple_loss=0.3397, pruned_loss=0.1091, over 7434.00 frames.], tot_loss[loss=0.256, simple_loss=0.334, pruned_loss=0.1216, over 1424367.98 frames.], batch size: 20, lr: 2.36e-03
2022-05-13 21:23:40,001 INFO [train.py:812] (3/8) Epoch 2, batch 1700, loss[loss=0.3033, simple_loss=0.3426, pruned_loss=0.132, over 7408.00 frames.], tot_loss[loss=0.2605, simple_loss=0.3324, pruned_loss=0.1197, over 1422976.99 frames.], batch size: 21, lr: 2.35e-03
2022-05-13 21:24:38,974 INFO [train.py:812] (3/8) Epoch 2, batch 1750, loss[loss=0.2695, simple_loss=0.3121, pruned_loss=0.1135, over 7277.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3331, pruned_loss=0.1194, over 1422950.96 frames.], batch size: 18, lr: 2.34e-03
2022-05-13 21:25:38,301 INFO [train.py:812] (3/8) Epoch 2, batch 1800, loss[loss=0.2545, simple_loss=0.3106, pruned_loss=0.09919, over 7359.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3333, pruned_loss=0.119, over 1424332.01 frames.], batch size: 19, lr: 2.34e-03
2022-05-13 21:26:37,479 INFO [train.py:812] (3/8) Epoch 2, batch 1850, loss[loss=0.2249, simple_loss=0.2919, pruned_loss=0.07895, over 7336.00 frames.], tot_loss[loss=0.2713, simple_loss=0.332, pruned_loss=0.1173, over 1424036.70 frames.], batch size: 20, lr: 2.33e-03
2022-05-13 21:27:35,687 INFO [train.py:812] (3/8) Epoch 2, batch 1900, loss[loss=0.2768, simple_loss=0.3111, pruned_loss=0.1212, over 7005.00 frames.], tot_loss[loss=0.275, simple_loss=0.3338, pruned_loss=0.1174, over 1427593.81 frames.], batch size: 16, lr: 2.33e-03
2022-05-13 21:28:33,664 INFO [train.py:812] (3/8) Epoch 2, batch 1950, loss[loss=0.2231, simple_loss=0.2769, pruned_loss=0.08462, over 7275.00 frames.], tot_loss[loss=0.2768, simple_loss=0.334, pruned_loss=0.1171, over 1428309.76 frames.], batch size: 18, lr: 2.32e-03
2022-05-13 21:29:31,780 INFO [train.py:812] (3/8) Epoch 2, batch 2000, loss[loss=0.2314, simple_loss=0.3019, pruned_loss=0.08039, over 7128.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3347, pruned_loss=0.1166, over 1422495.94 frames.], batch size: 21, lr: 2.32e-03
2022-05-13 21:30:31,552 INFO [train.py:812] (3/8) Epoch 2, batch 2050, loss[loss=0.3044, simple_loss=0.3555, pruned_loss=0.1267, over 7043.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3339, pruned_loss=0.1157, over 1423781.57 frames.], batch size: 28, lr: 2.31e-03
2022-05-13 21:31:31,114 INFO [train.py:812] (3/8) Epoch 2, batch 2100, loss[loss=0.305, simple_loss=0.3446, pruned_loss=0.1327, over 7404.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3334, pruned_loss=0.115, over 1424995.42 frames.], batch size: 18, lr: 2.31e-03
2022-05-13 21:32:30,570 INFO [train.py:812] (3/8) Epoch 2, batch 2150, loss[loss=0.2994, simple_loss=0.3547, pruned_loss=0.1221, over 7406.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3327, pruned_loss=0.114, over 1423940.05 frames.], batch size: 21, lr: 2.30e-03
2022-05-13 21:33:29,447 INFO [train.py:812] (3/8) Epoch 2, batch 2200, loss[loss=0.3148, simple_loss=0.3677, pruned_loss=0.1309, over 7127.00 frames.], tot_loss[loss=0.276, simple_loss=0.331, pruned_loss=0.1126, over 1423702.32 frames.], batch size: 21, lr: 2.29e-03
2022-05-13 21:34:29,299 INFO [train.py:812] (3/8) Epoch 2, batch 2250, loss[loss=0.2592, simple_loss=0.3235, pruned_loss=0.09751, over 7213.00 frames.], tot_loss[loss=0.2747, simple_loss=0.33, pruned_loss=0.1113, over 1424254.80 frames.], batch size: 21, lr: 2.29e-03
2022-05-13 21:35:27,778 INFO [train.py:812] (3/8) Epoch 2, batch 2300, loss[loss=0.2918, simple_loss=0.3502, pruned_loss=0.1167, over 7199.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3308, pruned_loss=0.1115, over 1425339.37 frames.], batch size: 22, lr: 2.28e-03
2022-05-13 21:36:26,836 INFO [train.py:812] (3/8) Epoch 2, batch 2350, loss[loss=0.2823, simple_loss=0.3462, pruned_loss=0.1092, over 7235.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3326, pruned_loss=0.1124, over 1422922.03 frames.], batch size: 20, lr: 2.28e-03
2022-05-13 21:37:24,978 INFO [train.py:812] (3/8) Epoch 2, batch 2400, loss[loss=0.2844, simple_loss=0.3451, pruned_loss=0.1118, over 7333.00 frames.], tot_loss[loss=0.277, simple_loss=0.3322, pruned_loss=0.1117, over 1422964.16 frames.], batch size: 21, lr: 2.27e-03
2022-05-13 21:38:23,787 INFO [train.py:812] (3/8) Epoch 2, batch 2450, loss[loss=0.2734, simple_loss=0.3421, pruned_loss=0.1023, over 7312.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3321, pruned_loss=0.1105, over 1426971.41 frames.], batch size: 21, lr: 2.27e-03
2022-05-13 21:39:23,278 INFO [train.py:812] (3/8) Epoch 2, batch 2500, loss[loss=0.3572, simple_loss=0.392, pruned_loss=0.1611, over 7147.00 frames.], tot_loss[loss=0.2758, simple_loss=0.332, pruned_loss=0.1102, over 1427097.79 frames.], batch size: 26, lr: 2.26e-03
2022-05-13 21:40:21,928 INFO [train.py:812] (3/8) Epoch 2, batch 2550, loss[loss=0.2423, simple_loss=0.3004, pruned_loss=0.09213, over 7003.00 frames.], tot_loss[loss=0.2752, simple_loss=0.3312, pruned_loss=0.1099, over 1427392.07 frames.], batch size: 16, lr: 2.26e-03
2022-05-13 21:41:21,065 INFO [train.py:812] (3/8) Epoch 2, batch 2600, loss[loss=0.2663, simple_loss=0.3327, pruned_loss=0.09995, over 7167.00 frames.], tot_loss[loss=0.2739, simple_loss=0.3301, pruned_loss=0.1091, over 1429605.77 frames.], batch size: 26, lr: 2.25e-03
2022-05-13 21:42:20,635 INFO [train.py:812] (3/8) Epoch 2, batch 2650, loss[loss=0.3533, simple_loss=0.3865, pruned_loss=0.1601, over 6252.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3308, pruned_loss=0.1097, over 1427459.31 frames.], batch size: 38, lr: 2.25e-03
2022-05-13 21:43:18,314 INFO [train.py:812] (3/8) Epoch 2, batch 2700, loss[loss=0.3358, simple_loss=0.3769, pruned_loss=0.1473, over 6910.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3298, pruned_loss=0.1085, over 1426874.39 frames.], batch size: 31, lr: 2.24e-03
2022-05-13 21:44:17,956 INFO [train.py:812] (3/8) Epoch 2, batch 2750, loss[loss=0.2836, simple_loss=0.3322, pruned_loss=0.1175, over 7310.00 frames.], tot_loss[loss=0.275, simple_loss=0.3308, pruned_loss=0.1097, over 1423631.50 frames.], batch size: 24, lr: 2.24e-03
2022-05-13 21:45:15,688 INFO [train.py:812] (3/8) Epoch 2, batch 2800, loss[loss=0.3048, simple_loss=0.3533, pruned_loss=0.1281, over 7212.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3294, pruned_loss=0.1077, over 1426147.89 frames.], batch size: 23, lr: 2.23e-03
2022-05-13 21:46:14,854 INFO [train.py:812] (3/8) Epoch 2, batch 2850, loss[loss=0.266, simple_loss=0.3382, pruned_loss=0.09688, over 7306.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3295, pruned_loss=0.1085, over 1425850.38 frames.], batch size: 24, lr: 2.23e-03
2022-05-13 21:47:13,475 INFO [train.py:812] (3/8) Epoch 2, batch 2900, loss[loss=0.237, simple_loss=0.3095, pruned_loss=0.08224, over 7228.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3306, pruned_loss=0.1089, over 1420238.58 frames.], batch size: 20, lr: 2.22e-03
2022-05-13 21:48:11,746 INFO [train.py:812] (3/8) Epoch 2, batch 2950, loss[loss=0.2778, simple_loss=0.3483, pruned_loss=0.1036, over 7241.00 frames.], tot_loss[loss=0.2728, simple_loss=0.33, pruned_loss=0.1079, over 1421146.35 frames.], batch size: 20, lr: 2.22e-03
2022-05-13 21:49:10,833 INFO [train.py:812] (3/8) Epoch 2, batch 3000, loss[loss=0.2089, simple_loss=0.2829, pruned_loss=0.06745, over 7272.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3279, pruned_loss=0.1057, over 1424548.74 frames.], batch size: 17, lr: 2.21e-03
2022-05-13 21:49:10,834 INFO [train.py:832] (3/8) Computing validation loss
2022-05-13 21:49:18,580 INFO [train.py:841] (3/8) Epoch 2, validation: loss=0.2016, simple_loss=0.2977, pruned_loss=0.0527, over 698248.00 frames.
2022-05-13 21:50:17,488 INFO [train.py:812] (3/8) Epoch 2, batch 3050, loss[loss=0.2386, simple_loss=0.2982, pruned_loss=0.0895, over 7280.00 frames.], tot_loss[loss=0.2688, simple_loss=0.3274, pruned_loss=0.1052, over 1420750.64 frames.], batch size: 18, lr: 2.20e-03
2022-05-13 21:51:15,123 INFO [train.py:812] (3/8) Epoch 2, batch 3100, loss[loss=0.3063, simple_loss=0.3421, pruned_loss=0.1352, over 5102.00 frames.], tot_loss[loss=0.268, simple_loss=0.3269, pruned_loss=0.1046, over 1420787.48 frames.], batch size: 53, lr: 2.20e-03
2022-05-13 21:52:13,942 INFO [train.py:812] (3/8) Epoch 2, batch 3150, loss[loss=0.2849, simple_loss=0.314, pruned_loss=0.1279, over 6869.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3267, pruned_loss=0.1039, over 1423414.16 frames.], batch size: 15, lr: 2.19e-03
2022-05-13 21:53:13,035 INFO [train.py:812] (3/8) Epoch 2, batch 3200, loss[loss=0.303, simple_loss=0.3389, pruned_loss=0.1335, over 5050.00 frames.], tot_loss[loss=0.2693, simple_loss=0.3281, pruned_loss=0.1052, over 1412674.07 frames.], batch size: 52, lr: 2.19e-03
2022-05-13 21:54:12,609 INFO [train.py:812] (3/8) Epoch 2, batch 3250, loss[loss=0.3146, simple_loss=0.3598, pruned_loss=0.1347, over 7205.00 frames.], tot_loss[loss=0.2695, simple_loss=0.3283, pruned_loss=0.1054, over 1415152.56 frames.], batch size: 23, lr: 2.18e-03
2022-05-13 21:55:12,229 INFO [train.py:812] (3/8) Epoch 2, batch 3300, loss[loss=0.3898, simple_loss=0.4204, pruned_loss=0.1796, over 7193.00 frames.], tot_loss[loss=0.2692, simple_loss=0.3277, pruned_loss=0.1054, over 1420337.19 frames.], batch size: 22, lr: 2.18e-03
2022-05-13 21:56:11,986 INFO [train.py:812] (3/8) Epoch 2, batch 3350, loss[loss=0.3257, simple_loss=0.3721, pruned_loss=0.1397, over 7147.00 frames.], tot_loss[loss=0.2691, simple_loss=0.3283, pruned_loss=0.1049, over 1423476.62 frames.], batch size: 26, lr: 2.18e-03
2022-05-13 21:57:11,193 INFO [train.py:812] (3/8) Epoch 2, batch 3400, loss[loss=0.233, simple_loss=0.289, pruned_loss=0.08848, over 7130.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3275, pruned_loss=0.104, over 1424628.17 frames.], batch size: 17, lr: 2.17e-03
2022-05-13 21:58:14,496 INFO [train.py:812] (3/8) Epoch 2, batch 3450, loss[loss=0.3231, simple_loss=0.3796, pruned_loss=0.1333, over 7307.00 frames.], tot_loss[loss=0.2678, simple_loss=0.3278, pruned_loss=0.1039, over 1427760.24 frames.], batch size: 24, lr: 2.17e-03
2022-05-13 21:59:13,379 INFO [train.py:812] (3/8) Epoch 2, batch 3500, loss[loss=0.3031, simple_loss=0.3572, pruned_loss=0.1245, over 6506.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3286, pruned_loss=0.1043, over 1424470.04 frames.], batch size: 37, lr: 2.16e-03
2022-05-13 22:00:12,698 INFO [train.py:812] (3/8) Epoch 2, batch 3550, loss[loss=0.2943, simple_loss=0.3473, pruned_loss=0.1206, over 7305.00 frames.], tot_loss[loss=0.268, simple_loss=0.3284, pruned_loss=0.1038, over 1423645.98 frames.], batch size: 25, lr: 2.16e-03
2022-05-13 22:01:11,593 INFO [train.py:812] (3/8) Epoch 2, batch 3600, loss[loss=0.259, simple_loss=0.3277, pruned_loss=0.09516, over 7234.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3277, pruned_loss=0.1026, over 1424839.98 frames.], batch size: 20, lr: 2.15e-03
2022-05-13 22:02:11,494 INFO [train.py:812] (3/8) Epoch 2, batch 3650, loss[loss=0.2699, simple_loss=0.3186, pruned_loss=0.1106, over 6784.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3273, pruned_loss=0.1019, over 1426672.25 frames.], batch size: 15, lr: 2.15e-03
2022-05-13 22:03:10,439 INFO [train.py:812] (3/8) Epoch 2, batch 3700, loss[loss=0.3072, simple_loss=0.351, pruned_loss=0.1317, over 7171.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3291, pruned_loss=0.1028, over 1428183.52 frames.], batch size: 19, lr: 2.14e-03
2022-05-13 22:04:09,796 INFO [train.py:812] (3/8) Epoch 2, batch 3750, loss[loss=0.2644, simple_loss=0.3309, pruned_loss=0.09896, over 7262.00 frames.], tot_loss[loss=0.2657, simple_loss=0.3278, pruned_loss=0.1018, over 1428965.72 frames.], batch size: 24, lr: 2.14e-03
2022-05-13 22:05:09,339 INFO [train.py:812] (3/8) Epoch 2, batch 3800, loss[loss=0.2182, simple_loss=0.2869, pruned_loss=0.07475, over 6825.00 frames.], tot_loss[loss=0.2646, simple_loss=0.3268, pruned_loss=0.1012, over 1428445.87 frames.], batch size: 15, lr: 2.13e-03
2022-05-13 22:06:08,032 INFO [train.py:812] (3/8) Epoch 2, batch 3850, loss[loss=0.2989, simple_loss=0.3654, pruned_loss=0.1162, over 7179.00 frames.], tot_loss[loss=0.2648, simple_loss=0.3269, pruned_loss=0.1013, over 1429883.36 frames.], batch size: 26, lr: 2.13e-03
2022-05-13 22:07:06,192 INFO [train.py:812] (3/8) Epoch 2, batch 3900, loss[loss=0.2648, simple_loss=0.3326, pruned_loss=0.0985, over 7284.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3254, pruned_loss=0.1, over 1429165.40 frames.], batch size: 24, lr: 2.12e-03
2022-05-13 22:08:05,666 INFO [train.py:812] (3/8) Epoch 2, batch 3950, loss[loss=0.3075, simple_loss=0.3558, pruned_loss=0.1296, over 7121.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3251, pruned_loss=0.1004, over 1427113.11 frames.], batch size: 21, lr: 2.12e-03
2022-05-13 22:09:04,837 INFO [train.py:812] (3/8) Epoch 2, batch 4000, loss[loss=0.2675, simple_loss=0.3362, pruned_loss=0.09936, over 7198.00 frames.], tot_loss[loss=0.2623, simple_loss=0.325, pruned_loss=0.09979, over 1427778.52 frames.], batch size: 22, lr: 2.11e-03
2022-05-13 22:10:02,676 INFO [train.py:812] (3/8) Epoch 2, batch 4050, loss[loss=0.2648, simple_loss=0.3265, pruned_loss=0.1015, over 6747.00 frames.], tot_loss[loss=0.262, simple_loss=0.3247, pruned_loss=0.09967, over 1426400.14 frames.], batch size: 31, lr: 2.11e-03
2022-05-13 22:11:01,210 INFO [train.py:812] (3/8) Epoch 2, batch 4100, loss[loss=0.3335, simple_loss=0.3696, pruned_loss=0.1487, over 7212.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3246, pruned_loss=0.09949, over 1420953.05 frames.], batch size: 21, lr: 2.10e-03
2022-05-13 22:11:59,937 INFO [train.py:812] (3/8) Epoch 2, batch 4150, loss[loss=0.2717, simple_loss=0.3317, pruned_loss=0.1058, over 6691.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3235, pruned_loss=0.09865, over 1419702.65 frames.], batch size: 31, lr: 2.10e-03
2022-05-13 22:12:58,513 INFO [train.py:812] (3/8) Epoch 2, batch 4200, loss[loss=0.1979, simple_loss=0.2725, pruned_loss=0.06158, over 7274.00 frames.], tot_loss[loss=0.2594, simple_loss=0.3225, pruned_loss=0.09816, over 1418888.28 frames.], batch size: 18, lr: 2.10e-03
2022-05-13 22:13:58,090 INFO [train.py:812] (3/8) Epoch 2, batch 4250, loss[loss=0.2557, simple_loss=0.3155, pruned_loss=0.09799, over 7275.00 frames.], tot_loss[loss=0.2602, simple_loss=0.323, pruned_loss=0.09864, over 1414619.92 frames.], batch size: 18, lr: 2.09e-03
2022-05-13 22:14:56,717 INFO [train.py:812] (3/8) Epoch 2, batch 4300, loss[loss=0.2967, simple_loss=0.3754, pruned_loss=0.109, over 7319.00 frames.], tot_loss[loss=0.2616, simple_loss=0.3243, pruned_loss=0.09945, over 1413457.47 frames.], batch size: 25, lr: 2.09e-03
2022-05-13 22:15:55,446 INFO [train.py:812] (3/8) Epoch 2, batch 4350, loss[loss=0.2013, simple_loss=0.2729, pruned_loss=0.06485, over 7416.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3249, pruned_loss=0.09992, over 1414018.66 frames.], batch size: 17, lr: 2.08e-03
2022-05-13 22:16:54,200 INFO [train.py:812] (3/8) Epoch 2, batch 4400, loss[loss=0.2788, simple_loss=0.3327, pruned_loss=0.1125, over 7313.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3235, pruned_loss=0.09919, over 1408409.61 frames.], batch size: 21, lr: 2.08e-03
2022-05-13 22:17:52,721 INFO [train.py:812] (3/8) Epoch 2, batch 4450, loss[loss=0.3089, simple_loss=0.346, pruned_loss=0.1359, over 6505.00 frames.], tot_loss[loss=0.262, simple_loss=0.3245, pruned_loss=0.09973, over 1402315.76 frames.], batch size: 38, lr: 2.07e-03
2022-05-13 22:18:50,552 INFO [train.py:812] (3/8) Epoch 2, batch 4500, loss[loss=0.2636, simple_loss=0.3214, pruned_loss=0.1029, over 6309.00 frames.], tot_loss[loss=0.2605, simple_loss=0.323, pruned_loss=0.09896, over 1387904.09 frames.], batch size: 37, lr: 2.07e-03
2022-05-13 22:19:49,238 INFO [train.py:812] (3/8) Epoch 2, batch 4550, loss[loss=0.3386, simple_loss=0.3718, pruned_loss=0.1527, over 5031.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3254, pruned_loss=0.1006, over 1356416.92 frames.], batch size: 52, lr: 2.06e-03
2022-05-13 22:20:58,934 INFO [train.py:812] (3/8) Epoch 3, batch 0, loss[loss=0.2316, simple_loss=0.2973, pruned_loss=0.08301, over 7287.00 frames.], tot_loss[loss=0.2316, simple_loss=0.2973, pruned_loss=0.08301, over 7287.00 frames.], batch size: 17, lr: 2.02e-03
2022-05-13 22:21:58,058 INFO [train.py:812] (3/8) Epoch 3, batch 50, loss[loss=0.2717, simple_loss=0.3288, pruned_loss=0.1073, over 7294.00 frames.], tot_loss[loss=0.26, simple_loss=0.3221, pruned_loss=0.09896, over 323246.44 frames.], batch size: 25, lr: 2.02e-03
2022-05-13 22:22:56,230 INFO [train.py:812] (3/8) Epoch 3, batch 100, loss[loss=0.1931, simple_loss=0.266, pruned_loss=0.0601, over 6994.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3199, pruned_loss=0.09584, over 570552.73 frames.], batch size: 16, lr: 2.01e-03
2022-05-13 22:23:56,092 INFO [train.py:812] (3/8) Epoch 3, batch 150, loss[loss=0.269, simple_loss=0.325, pruned_loss=0.1065, over 6751.00 frames.], tot_loss[loss=0.2543, simple_loss=0.3185, pruned_loss=0.09505, over 763010.74 frames.], batch size: 31, lr: 2.01e-03
2022-05-13 22:24:53,586 INFO [train.py:812] (3/8) Epoch 3, batch 200, loss[loss=0.2875, simple_loss=0.328, pruned_loss=0.1235, over 6793.00 frames.], tot_loss[loss=0.2554, simple_loss=0.3192, pruned_loss=0.09581, over 901224.23 frames.], batch size: 15, lr: 2.00e-03
2022-05-13 22:25:53,015 INFO [train.py:812] (3/8) Epoch 3, batch 250, loss[loss=0.2201, simple_loss=0.2988, pruned_loss=0.0707, over 7362.00 frames.], tot_loss[loss=0.2584, simple_loss=0.3218, pruned_loss=0.09746, over 1012314.16 frames.], batch size: 19, lr: 2.00e-03
2022-05-13 22:26:52,124 INFO [train.py:812] (3/8) Epoch 3, batch 300, loss[loss=0.2484, simple_loss=0.3223, pruned_loss=0.08724, over 6875.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3219, pruned_loss=0.09646, over 1102553.98 frames.], batch size: 31, lr: 2.00e-03
2022-05-13 22:27:51,985 INFO [train.py:812] (3/8) Epoch 3, batch 350, loss[loss=0.2867, simple_loss=0.3479, pruned_loss=0.1128, over 7319.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3222, pruned_loss=0.09628, over 1172913.33 frames.], batch size: 21, lr: 1.99e-03
2022-05-13 22:29:00,803 INFO [train.py:812] (3/8) Epoch 3, batch 400, loss[loss=0.332, simple_loss=0.3634, pruned_loss=0.1503, over 7286.00 frames.], tot_loss[loss=0.258, simple_loss=0.3224, pruned_loss=0.09676, over 1223735.30 frames.], batch size: 24, lr: 1.99e-03
2022-05-13 22:29:59,462 INFO [train.py:812] (3/8) Epoch 3, batch 450, loss[loss=0.2845, simple_loss=0.3447, pruned_loss=0.1121, over 7212.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3222, pruned_loss=0.09635, over 1264029.34 frames.], batch size: 22, lr: 1.98e-03
2022-05-13 22:31:07,391 INFO [train.py:812] (3/8) Epoch 3, batch 500, loss[loss=0.2538, simple_loss=0.3096, pruned_loss=0.09903, over 7008.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3208, pruned_loss=0.09544, over 1301957.86 frames.], batch size: 16, lr: 1.98e-03
2022-05-13 22:32:54,333 INFO [train.py:812] (3/8) Epoch 3, batch 550, loss[loss=0.278, simple_loss=0.3381, pruned_loss=0.109, over 7219.00 frames.], tot_loss[loss=0.2559, simple_loss=0.3209, pruned_loss=0.09541, over 1331694.48 frames.], batch size: 21, lr: 1.98e-03
2022-05-13 22:34:03,100 INFO [train.py:812] (3/8) Epoch 3, batch 600, loss[loss=0.3479, simple_loss=0.4027, pruned_loss=0.1465, over 7285.00 frames.], tot_loss[loss=0.2547, simple_loss=0.3199, pruned_loss=0.09476, over 1352069.80 frames.], batch size: 25, lr: 1.97e-03
2022-05-13 22:35:02,670 INFO [train.py:812] (3/8) Epoch 3, batch 650, loss[loss=0.2449, simple_loss=0.3213, pruned_loss=0.08424, over 7374.00 frames.], tot_loss[loss=0.2546, simple_loss=0.3197, pruned_loss=0.09479, over 1366875.24 frames.], batch size: 19, lr: 1.97e-03
2022-05-13 22:36:02,056 INFO [train.py:812] (3/8) Epoch 3, batch 700, loss[loss=0.2539, simple_loss=0.3331, pruned_loss=0.08731, over 7214.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3191, pruned_loss=0.09416, over 1377307.84 frames.], batch size: 21, lr: 1.96e-03
2022-05-13 22:37:01,823 INFO [train.py:812] (3/8) Epoch 3, batch 750, loss[loss=0.2634, simple_loss=0.3359, pruned_loss=0.09543, over 7191.00 frames.], tot_loss[loss=0.2532, simple_loss=0.3191, pruned_loss=0.09366, over 1390766.76 frames.], batch size: 23, lr: 1.96e-03
2022-05-13 22:38:00,538 INFO [train.py:812] (3/8) Epoch 3, batch 800, loss[loss=0.2415, simple_loss=0.3187, pruned_loss=0.08216, over 7204.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3201, pruned_loss=0.09364, over 1401396.70 frames.], batch size: 23, lr: 1.96e-03
2022-05-13 22:38:59,711 INFO [train.py:812] (3/8) Epoch 3, batch 850, loss[loss=0.2621, simple_loss=0.3361, pruned_loss=0.09404, over 7300.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3183, pruned_loss=0.09208, over 1409380.36 frames.], batch size: 25, lr: 1.95e-03
2022-05-13 22:39:58,498 INFO [train.py:812] (3/8) Epoch 3, batch 900, loss[loss=0.2273, simple_loss=0.2915, pruned_loss=0.08154, over 7064.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3192, pruned_loss=0.09225, over 1412461.02 frames.], batch size: 18, lr: 1.95e-03
2022-05-13 22:40:58,624 INFO [train.py:812] (3/8) Epoch 3, batch 950, loss[loss=0.2656, simple_loss=0.333, pruned_loss=0.09905, over 7145.00 frames.], tot_loss[loss=0.251, simple_loss=0.3184, pruned_loss=0.09178, over 1417775.95 frames.], batch size: 20, lr: 1.94e-03
2022-05-13 22:41:58,349 INFO [train.py:812] (3/8) Epoch 3, batch 1000, loss[loss=0.3122, simple_loss=0.3728, pruned_loss=0.1258, over 6775.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3193, pruned_loss=0.09226, over 1417221.79 frames.], batch size: 31, lr: 1.94e-03
2022-05-13 22:42:57,492 INFO [train.py:812] (3/8) Epoch 3, batch 1050, loss[loss=0.257, simple_loss=0.3304, pruned_loss=0.09181, over 7276.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3196, pruned_loss=0.09235, over 1414728.26 frames.], batch size: 18, lr: 1.94e-03
2022-05-13 22:43:56,784 INFO [train.py:812] (3/8) Epoch 3, batch 1100, loss[loss=0.2485, simple_loss=0.3183, pruned_loss=0.08938, over 7220.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3198, pruned_loss=0.09203, over 1419485.17 frames.], batch size: 21, lr: 1.93e-03
2022-05-13 22:44:56,333 INFO [train.py:812] (3/8) Epoch 3, batch 1150, loss[loss=0.2375, simple_loss=0.3029, pruned_loss=0.08606, over 7232.00 frames.], tot_loss[loss=0.2527, simple_loss=0.3198, pruned_loss=0.09278, over 1420379.86 frames.], batch size: 20, lr: 1.93e-03
2022-05-13 22:45:54,819 INFO [train.py:812] (3/8) Epoch 3, batch 1200, loss[loss=0.245, simple_loss=0.312, pruned_loss=0.08902, over 7425.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3189, pruned_loss=0.09226, over 1424105.19 frames.], batch size: 20, lr: 1.93e-03
2022-05-13 22:46:52,755 INFO [train.py:812] (3/8) Epoch 3, batch 1250, loss[loss=0.305, simple_loss=0.3661, pruned_loss=0.1219, over 7412.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3172, pruned_loss=0.09152, over 1424704.93 frames.], batch size: 21, lr: 1.92e-03
2022-05-13 22:47:52,031 INFO [train.py:812] (3/8) Epoch 3, batch 1300, loss[loss=0.259, simple_loss=0.325, pruned_loss=0.09651, over 7327.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3166, pruned_loss=0.09085, over 1426309.98 frames.], batch size: 21, lr: 1.92e-03
2022-05-13 22:48:50,081 INFO [train.py:812] (3/8) Epoch 3, batch 1350, loss[loss=0.2134, simple_loss=0.2856, pruned_loss=0.07067, over 7410.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3182, pruned_loss=0.09175, over 1425666.14 frames.], batch size: 20, lr: 1.91e-03
2022-05-13 22:49:48,200 INFO [train.py:812] (3/8) Epoch 3, batch 1400, loss[loss=0.263, simple_loss=0.3255, pruned_loss=0.1002, over 7167.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3187, pruned_loss=0.09201, over 1423035.80 frames.], batch size: 19, lr: 1.91e-03
2022-05-13 22:50:48,154 INFO [train.py:812] (3/8) Epoch 3, batch 1450, loss[loss=0.1958, simple_loss=0.2626, pruned_loss=0.06447, over 7149.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3185, pruned_loss=0.09206, over 1419400.92 frames.], batch size: 17, lr: 1.91e-03
2022-05-13 22:51:46,935 INFO [train.py:812] (3/8) Epoch 3, batch 1500, loss[loss=0.2813, simple_loss=0.3464, pruned_loss=0.108, over 7317.00 frames.], tot_loss[loss=0.2517, simple_loss=0.319, pruned_loss=0.09223, over 1416504.42 frames.], batch size: 21, lr: 1.90e-03
2022-05-13 22:52:47,274 INFO [train.py:812] (3/8) Epoch 3, batch 1550, loss[loss=0.1999, simple_loss=0.27, pruned_loss=0.06484, over 7146.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3187, pruned_loss=0.09169, over 1421073.62 frames.], batch size: 19, lr: 1.90e-03
2022-05-13 22:53:45,770 INFO [train.py:812] (3/8) Epoch 3, batch 1600, loss[loss=0.2146, simple_loss=0.2847, pruned_loss=0.07229, over 7143.00 frames.], tot_loss[loss=0.2491, simple_loss=0.3172, pruned_loss=0.09054, over 1423026.72 frames.], batch size: 19, lr: 1.90e-03
2022-05-13 22:54:44,629 INFO [train.py:812] (3/8) Epoch 3, batch 1650, loss[loss=0.2566, simple_loss=0.3197, pruned_loss=0.09678, over 7434.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3169, pruned_loss=0.09112, over 1426578.67 frames.], batch size: 20, lr: 1.89e-03
2022-05-13 22:55:42,296 INFO [train.py:812] (3/8) Epoch 3, batch 1700, loss[loss=0.207, simple_loss=0.2898, pruned_loss=0.06209, over 7151.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3168, pruned_loss=0.09108, over 1417441.84 frames.], batch size: 20, lr: 1.89e-03
2022-05-13 22:56:41,863 INFO [train.py:812] (3/8) Epoch 3, batch 1750, loss[loss=0.193, simple_loss=0.2789, pruned_loss=0.05352, over 7238.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3162, pruned_loss=0.09014, over 1424420.81 frames.], batch size: 20, lr: 1.88e-03
2022-05-13 22:57:40,288 INFO [train.py:812] (3/8) Epoch 3, batch 1800, loss[loss=0.2348, simple_loss=0.3138, pruned_loss=0.07785, over 7122.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3162, pruned_loss=0.09046, over 1417587.95 frames.], batch size: 21, lr: 1.88e-03
2022-05-13 22:58:39,762 INFO [train.py:812] (3/8) Epoch 3, batch 1850, loss[loss=0.2326, simple_loss=0.3103, pruned_loss=0.07752, over 7416.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3157, pruned_loss=0.09003, over 1418937.63 frames.], batch size: 21, lr: 1.88e-03
2022-05-13 22:59:38,875 INFO [train.py:812] (3/8) Epoch 3, batch 1900, loss[loss=0.2196, simple_loss=0.2944, pruned_loss=0.07239, over 7173.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3157, pruned_loss=0.09005, over 1417187.12 frames.], batch size: 18, lr: 1.87e-03
2022-05-13 23:00:38,434 INFO [train.py:812] (3/8) Epoch 3, batch 1950, loss[loss=0.2539, simple_loss=0.3274, pruned_loss=0.09019, over 6927.00 frames.], tot_loss[loss=0.2462, simple_loss=0.314, pruned_loss=0.08915, over 1418027.60 frames.], batch size: 31, lr: 1.87e-03
2022-05-13 23:01:37,608 INFO [train.py:812] (3/8) Epoch 3, batch 2000, loss[loss=0.2399, simple_loss=0.308, pruned_loss=0.08587, over 7155.00 frames.], tot_loss[loss=0.2464, simple_loss=0.314, pruned_loss=0.08934, over 1422289.59 frames.], batch size: 19, lr: 1.87e-03
2022-05-13 23:02:36,930 INFO [train.py:812] (3/8) Epoch 3, batch 2050, loss[loss=0.2723, simple_loss=0.3354, pruned_loss=0.1046, over 5460.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3164, pruned_loss=0.09024, over 1422067.48 frames.], batch size: 53, lr: 1.86e-03
2022-05-13 23:03:35,447 INFO [train.py:812] (3/8) Epoch 3, batch 2100, loss[loss=0.2628, simple_loss=0.3359, pruned_loss=0.0949, over 7316.00 frames.], tot_loss[loss=0.2476, simple_loss=0.316, pruned_loss=0.08964, over 1425034.63 frames.], batch size: 21, lr: 1.86e-03
2022-05-13 23:04:34,072 INFO [train.py:812] (3/8) Epoch 3, batch 2150, loss[loss=0.2549, simple_loss=0.3289, pruned_loss=0.09041, over 7223.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3164, pruned_loss=0.09016, over 1426363.90 frames.], batch size: 20, lr: 1.86e-03
2022-05-13 23:05:32,764 INFO [train.py:812] (3/8) Epoch 3, batch 2200, loss[loss=0.2646, simple_loss=0.3269, pruned_loss=0.1011, over 7153.00 frames.], tot_loss[loss=0.248, simple_loss=0.3159, pruned_loss=0.09002, over 1425028.58 frames.], batch size: 20, lr: 1.85e-03
2022-05-13 23:06:32,195 INFO [train.py:812] (3/8) Epoch 3, batch 2250, loss[loss=0.2417, simple_loss=0.3071, pruned_loss=0.08811, over 7328.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3176, pruned_loss=0.09072, over 1424730.28 frames.], batch size: 20, lr: 1.85e-03
2022-05-13 23:07:31,562 INFO [train.py:812] (3/8) Epoch 3, batch 2300, loss[loss=0.215, simple_loss=0.2849, pruned_loss=0.07257, over 7361.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3163, pruned_loss=0.09054, over 1413465.58 frames.], batch size: 19, lr: 1.85e-03
2022-05-13 23:08:31,265 INFO [train.py:812] (3/8) Epoch 3, batch 2350, loss[loss=0.2152, simple_loss=0.284, pruned_loss=0.07325, over 7258.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3148, pruned_loss=0.08918, over 1415198.47 frames.], batch size: 19, lr: 1.84e-03
2022-05-13 23:09:29,670 INFO [train.py:812] (3/8) Epoch 3, batch 2400, loss[loss=0.2411, simple_loss=0.3061, pruned_loss=0.08812, over 7260.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3154, pruned_loss=0.08968, over 1418363.22 frames.], batch size: 19, lr: 1.84e-03
2022-05-13 23:10:29,108 INFO [train.py:812] (3/8) Epoch 3, batch 2450, loss[loss=0.2323, simple_loss=0.3233, pruned_loss=0.07064, over 7241.00 frames.], tot_loss[loss=0.248, simple_loss=0.3161, pruned_loss=0.08999, over 1415074.53 frames.], batch size: 20, lr: 1.84e-03
2022-05-13 23:11:28,073 INFO [train.py:812] (3/8) Epoch 3, batch 2500, loss[loss=0.2871, simple_loss=0.3515, pruned_loss=0.1114, over 7166.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3144, pruned_loss=0.08914, over 1413412.88 frames.], batch size: 19, lr: 1.83e-03
2022-05-13 23:12:27,740 INFO [train.py:812] (3/8) Epoch 3, batch 2550, loss[loss=0.2449, simple_loss=0.3259, pruned_loss=0.08195, over 7226.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3139, pruned_loss=0.08924, over 1412331.30 frames.], batch size: 21, lr: 1.83e-03
2022-05-13 23:13:27,068 INFO [train.py:812] (3/8) Epoch 3, batch 2600, loss[loss=0.27, simple_loss=0.3315, pruned_loss=0.1043, over 7286.00 frames.], tot_loss[loss=0.244, simple_loss=0.3121, pruned_loss=0.08792, over 1418374.95 frames.], batch size: 18, lr: 1.83e-03
2022-05-13 23:14:26,415 INFO [train.py:812] (3/8) Epoch 3, batch 2650, loss[loss=0.2584, simple_loss=0.3254, pruned_loss=0.09572, over 7335.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3114, pruned_loss=0.08755, over 1418568.30 frames.], batch size: 20, lr: 1.82e-03
2022-05-13 23:15:24,401 INFO [train.py:812] (3/8) Epoch 3, batch 2700, loss[loss=0.2107, simple_loss=0.2816, pruned_loss=0.06986, over 7059.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3116, pruned_loss=0.08683, over 1419745.02 frames.], batch size: 18, lr: 1.82e-03
2022-05-13 23:16:23,942 INFO [train.py:812] (3/8) Epoch 3, batch 2750, loss[loss=0.2909, simple_loss=0.355, pruned_loss=0.1134, over 7201.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3115, pruned_loss=0.08656, over 1419758.89 frames.], batch size: 26, lr: 1.82e-03
2022-05-13 23:17:22,973 INFO [train.py:812] (3/8) Epoch 3, batch 2800, loss[loss=0.3232, simple_loss=0.3589, pruned_loss=0.1438, over 5088.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3117, pruned_loss=0.08692, over 1418844.91 frames.], batch size: 53, lr: 1.81e-03
2022-05-13 23:18:30,780 INFO [train.py:812] (3/8) Epoch 3, batch 2850, loss[loss=0.2507, simple_loss=0.3378, pruned_loss=0.08177, over 7217.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3121, pruned_loss=0.08686, over 1421864.45 frames.], batch size: 21, lr: 1.81e-03
2022-05-13 23:19:29,896 INFO [train.py:812] (3/8) Epoch 3, batch 2900, loss[loss=0.2883, simple_loss=0.3502, pruned_loss=0.1132, over 6367.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3122, pruned_loss=0.08717, over 1418456.20 frames.], batch size: 38, lr: 1.81e-03
2022-05-13 23:20:29,308 INFO [train.py:812] (3/8) Epoch 3, batch 2950, loss[loss=0.2143, simple_loss=0.2883, pruned_loss=0.07012, over 7193.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3139, pruned_loss=0.0882, over 1417829.72 frames.], batch size: 26, lr: 1.80e-03
2022-05-13 23:21:28,550 INFO [train.py:812] (3/8) Epoch 3, batch 3000, loss[loss=0.2465, simple_loss=0.3141, pruned_loss=0.08946, over 7326.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3136, pruned_loss=0.08759, over 1420871.66 frames.], batch size: 22, lr: 1.80e-03
2022-05-13 23:21:28,551 INFO [train.py:832] (3/8) Computing validation loss
2022-05-13 23:21:36,069 INFO [train.py:841] (3/8) Epoch 3, validation: loss=0.1862, simple_loss=0.2867, pruned_loss=0.04278, over 698248.00 frames.
2022-05-13 23:22:33,837 INFO [train.py:812] (3/8) Epoch 3, batch 3050, loss[loss=0.2605, simple_loss=0.3316, pruned_loss=0.09465, over 7410.00 frames.], tot_loss[loss=0.2438, simple_loss=0.3134, pruned_loss=0.08708, over 1425764.70 frames.], batch size: 21, lr: 1.80e-03
2022-05-13 23:23:30,786 INFO [train.py:812] (3/8) Epoch 3, batch 3100, loss[loss=0.2148, simple_loss=0.2883, pruned_loss=0.07061, over 7279.00 frames.], tot_loss[loss=0.243, simple_loss=0.3127, pruned_loss=0.08665, over 1428796.25 frames.], batch size: 18, lr: 1.79e-03
2022-05-13 23:24:30,030 INFO [train.py:812] (3/8) Epoch 3, batch 3150, loss[loss=0.2691, simple_loss=0.3291, pruned_loss=0.1045, over 7220.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3122, pruned_loss=0.08679, over 1423132.96 frames.], batch size: 21, lr: 1.79e-03
2022-05-13 23:25:29,453 INFO [train.py:812] (3/8) Epoch 3, batch 3200, loss[loss=0.2865, simple_loss=0.362, pruned_loss=0.1055, over 7379.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3133, pruned_loss=0.08698, over 1426068.13 frames.], batch size: 23, lr: 1.79e-03
2022-05-13 23:26:29,123 INFO [train.py:812] (3/8) Epoch 3, batch 3250, loss[loss=0.2546, simple_loss=0.3173, pruned_loss=0.09593, over 7161.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3138, pruned_loss=0.08748, over 1427058.96 frames.], batch size: 19, lr: 1.79e-03
2022-05-13 23:27:27,204 INFO [train.py:812] (3/8) Epoch 3, batch 3300, loss[loss=0.2369, simple_loss=0.3115, pruned_loss=0.08115, over 7208.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3123, pruned_loss=0.0864, over 1429553.12 frames.], batch size: 26, lr: 1.78e-03
2022-05-13 23:28:26,177 INFO [train.py:812] (3/8) Epoch 3, batch 3350, loss[loss=0.2313, simple_loss=0.2917, pruned_loss=0.08539, over 7278.00 frames.], tot_loss[loss=0.2436, simple_loss=0.3129, pruned_loss=0.08718, over 1426452.23 frames.], batch size: 18, lr: 1.78e-03
2022-05-13 23:29:23,906 INFO [train.py:812] (3/8) Epoch 3, batch 3400, loss[loss=0.19, simple_loss=0.2543, pruned_loss=0.06287, over 7405.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3125, pruned_loss=0.08654, over 1424298.76 frames.], batch size: 18, lr: 1.78e-03
2022-05-13 23:30:22,226 INFO [train.py:812] (3/8) Epoch 3, batch 3450, loss[loss=0.2359, simple_loss=0.3074, pruned_loss=0.08224, over 7258.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3127, pruned_loss=0.08682, over 1419848.24 frames.], batch size: 19, lr: 1.77e-03
2022-05-13 23:31:20,923 INFO [train.py:812] (3/8) Epoch 3, batch 3500, loss[loss=0.2217, simple_loss=0.3044, pruned_loss=0.06953, over 7312.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3108, pruned_loss=0.0852, over 1420938.55 frames.], batch size: 25, lr: 1.77e-03
2022-05-13 23:32:20,542 INFO [train.py:812] (3/8) Epoch 3, batch 3550, loss[loss=0.2245, simple_loss=0.2948, pruned_loss=0.07713, over 7203.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3113, pruned_loss=0.0855, over 1419299.07 frames.], batch size: 21, lr: 1.77e-03
2022-05-13 23:33:19,836 INFO [train.py:812] (3/8) Epoch 3, batch 3600, loss[loss=0.2569, simple_loss=0.3343, pruned_loss=0.08977, over 7305.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3092, pruned_loss=0.08456, over 1421282.05 frames.], batch size: 24, lr: 1.76e-03
2022-05-13 23:34:19,474 INFO [train.py:812] (3/8) Epoch 3, batch 3650, loss[loss=0.2821, simple_loss=0.3454, pruned_loss=0.1094, over 7373.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3092, pruned_loss=0.08456, over 1421034.58 frames.], batch size: 23, lr: 1.76e-03
2022-05-13 23:35:18,552 INFO [train.py:812] (3/8) Epoch 3, batch 3700, loss[loss=0.2271, simple_loss=0.2895, pruned_loss=0.08232, over 7420.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3095, pruned_loss=0.08436, over 1417434.90 frames.], batch size: 18, lr: 1.76e-03
2022-05-13 23:36:18,204 INFO [train.py:812] (3/8) Epoch 3, batch 3750, loss[loss=0.1981, simple_loss=0.2745, pruned_loss=0.06089, over 7285.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3088, pruned_loss=0.08343, over 1423070.64 frames.], batch size: 18, lr: 1.76e-03
2022-05-13 23:37:16,794 INFO [train.py:812] (3/8) Epoch 3, batch 3800, loss[loss=0.2135, simple_loss=0.2831, pruned_loss=0.07192, over 7173.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3087, pruned_loss=0.08378, over 1422739.13 frames.], batch size: 18, lr: 1.75e-03
2022-05-13 23:38:16,199 INFO [train.py:812] (3/8) Epoch 3, batch 3850, loss[loss=0.2555, simple_loss=0.3287, pruned_loss=0.09113, over 7336.00 frames.], tot_loss[loss=0.2389, simple_loss=0.3092, pruned_loss=0.08425, over 1421009.72 frames.], batch size: 22, lr: 1.75e-03
2022-05-13 23:39:15,474 INFO [train.py:812] (3/8) Epoch 3, batch 3900, loss[loss=0.2442, simple_loss=0.3161, pruned_loss=0.08615, over 7332.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3081, pruned_loss=0.08337, over 1423021.28 frames.], batch size: 20, lr: 1.75e-03
2022-05-13 23:40:14,814 INFO [train.py:812] (3/8) Epoch 3, batch 3950, loss[loss=0.2565, simple_loss=0.33, pruned_loss=0.09148, over 7324.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3089, pruned_loss=0.08369, over 1420704.13 frames.], batch size: 21, lr: 1.74e-03
2022-05-13 23:41:13,966 INFO [train.py:812] (3/8) Epoch 3, batch 4000, loss[loss=0.234, simple_loss=0.3172, pruned_loss=0.0754, over 7339.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3081, pruned_loss=0.08244, over 1425238.82 frames.], batch size: 22, lr: 1.74e-03
2022-05-13 23:42:13,692 INFO [train.py:812] (3/8) Epoch 3, batch 4050, loss[loss=0.261, simple_loss=0.3279, pruned_loss=0.09704, over 7442.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3081, pruned_loss=0.08287, over 1425399.93 frames.], batch size: 20, lr: 1.74e-03
2022-05-13 23:43:12,789 INFO [train.py:812] (3/8) Epoch 3, batch 4100, loss[loss=0.193, simple_loss=0.2636, pruned_loss=0.06119, over 7075.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3083, pruned_loss=0.0834, over 1415821.35 frames.], batch size: 18, lr: 1.73e-03
2022-05-13 23:44:12,466 INFO [train.py:812] (3/8) Epoch 3, batch 4150, loss[loss=0.2458, simple_loss=0.321, pruned_loss=0.08526, over 7109.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3087, pruned_loss=0.08345, over 1420929.66 frames.], batch size: 21, lr: 1.73e-03
2022-05-13 23:45:10,714 INFO [train.py:812] (3/8) Epoch 3, batch 4200, loss[loss=0.273, simple_loss=0.3431, pruned_loss=0.1014, over 7096.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3094, pruned_loss=0.08375, over 1420503.00 frames.], batch size: 28, lr: 1.73e-03
2022-05-13 23:46:09,932 INFO [train.py:812] (3/8) Epoch 3, batch 4250, loss[loss=0.2419, simple_loss=0.3196, pruned_loss=0.08213, over 7207.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3095, pruned_loss=0.08379, over 1420834.87 frames.], batch size: 22, lr: 1.73e-03
2022-05-13 23:47:09,076 INFO [train.py:812] (3/8) Epoch 3, batch 4300, loss[loss=0.2041, simple_loss=0.2801, pruned_loss=0.06403, over 7075.00 frames.], tot_loss[loss=0.2388, simple_loss=0.3102, pruned_loss=0.08371, over 1422622.58 frames.], batch size: 18, lr: 1.72e-03
2022-05-13 23:48:08,220 INFO [train.py:812] (3/8) Epoch 3, batch 4350, loss[loss=0.2579, simple_loss=0.3293, pruned_loss=0.09329, over 7148.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3103, pruned_loss=0.08404, over 1424781.44 frames.], batch size: 20, lr: 1.72e-03
2022-05-13 23:49:06,724 INFO [train.py:812] (3/8) Epoch 3, batch 4400, loss[loss=0.2726, simple_loss=0.3431, pruned_loss=0.1011, over 7281.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3101, pruned_loss=0.08406, over 1419747.74 frames.], batch size: 25, lr: 1.72e-03
2022-05-13 23:50:05,671 INFO [train.py:812] (3/8) Epoch 3, batch 4450, loss[loss=0.2589, simple_loss=0.333, pruned_loss=0.09242, over 7335.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3117, pruned_loss=0.08538, over 1411978.70 frames.], batch size: 22, lr: 1.71e-03
2022-05-13 23:51:04,262 INFO [train.py:812] (3/8) Epoch 3, batch 4500, loss[loss=0.2168, simple_loss=0.2925, pruned_loss=0.07055, over 7122.00 frames.], tot_loss[loss=0.2408, simple_loss=0.3118, pruned_loss=0.08489, over 1405984.40 frames.], batch size: 21, lr: 1.71e-03
2022-05-13 23:52:01,820 INFO [train.py:812] (3/8) Epoch 3, batch 4550, loss[loss=0.2384, simple_loss=0.3072, pruned_loss=0.08479, over 6474.00 frames.], tot_loss[loss=0.2442, simple_loss=0.3149, pruned_loss=0.08674, over 1378709.99 frames.], batch size: 38, lr: 1.71e-03
2022-05-13 23:53:11,479 INFO [train.py:812] (3/8) Epoch 4, batch 0, loss[loss=0.2935, simple_loss=0.365, pruned_loss=0.111, over 7193.00 frames.], tot_loss[loss=0.2935, simple_loss=0.365, pruned_loss=0.111, over 7193.00 frames.], batch size: 23, lr: 1.66e-03
2022-05-13 23:54:10,715 INFO [train.py:812] (3/8) Epoch 4, batch 50, loss[loss=0.1898, simple_loss=0.2552, pruned_loss=0.06218, over 7286.00 frames.], tot_loss[loss=0.233, simple_loss=0.306, pruned_loss=0.07997, over 317772.87 frames.], batch size: 17, lr: 1.66e-03
2022-05-13 23:55:09,485 INFO [train.py:812] (3/8) Epoch 4, batch 100, loss[loss=0.2107, simple_loss=0.2703, pruned_loss=0.07552, over 7282.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3052, pruned_loss=0.08023, over 563897.81 frames.], batch size: 17, lr: 1.65e-03
2022-05-13 23:56:09,350 INFO [train.py:812] (3/8) Epoch 4, batch 150, loss[loss=0.2482, simple_loss=0.3299, pruned_loss=0.08325, over 7313.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3062, pruned_loss=0.0807, over 756021.97 frames.], batch size: 22, lr: 1.65e-03
2022-05-13 23:57:08,450 INFO [train.py:812] (3/8) Epoch 4, batch 200, loss[loss=0.2571, simple_loss=0.3244, pruned_loss=0.09486, over 7206.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3066, pruned_loss=0.08025, over 905394.62 frames.], batch size: 23, lr: 1.65e-03
2022-05-13 23:58:07,152 INFO [train.py:812] (3/8) Epoch 4, batch 250, loss[loss=0.2249, simple_loss=0.2983, pruned_loss=0.07578, over 7342.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3067, pruned_loss=0.08009, over 1016912.78 frames.], batch size: 22, lr: 1.64e-03
2022-05-13 23:59:06,600 INFO [train.py:812] (3/8) Epoch 4, batch 300, loss[loss=0.2711, simple_loss=0.3304, pruned_loss=0.1059, over 7374.00 frames.], tot_loss[loss=0.2325, simple_loss=0.306, pruned_loss=0.07953, over 1111039.37 frames.], batch size: 23, lr: 1.64e-03
2022-05-14 00:00:06,129 INFO [train.py:812] (3/8) Epoch 4, batch 350, loss[loss=0.2581, simple_loss=0.3347, pruned_loss=0.09072, over 7315.00 frames.], tot_loss[loss=0.232, simple_loss=0.3056, pruned_loss=0.07925, over 1182498.00 frames.], batch size: 21, lr: 1.64e-03
2022-05-14 00:01:05,125 INFO [train.py:812] (3/8) Epoch 4, batch 400, loss[loss=0.2379, simple_loss=0.3122, pruned_loss=0.0818, over 7231.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3047, pruned_loss=0.07976, over 1232053.12 frames.], batch size: 20, lr: 1.64e-03
2022-05-14 00:02:04,516 INFO [train.py:812] (3/8) Epoch 4, batch 450, loss[loss=0.2831, simple_loss=0.3355, pruned_loss=0.1153, over 7147.00 frames.], tot_loss[loss=0.2329, simple_loss=0.305, pruned_loss=0.08042, over 1274362.18 frames.], batch size: 20, lr: 1.63e-03
2022-05-14 00:03:03,227 INFO [train.py:812] (3/8) Epoch 4, batch 500, loss[loss=0.213, simple_loss=0.294, pruned_loss=0.06601, over 7151.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3077, pruned_loss=0.08193, over 1303456.41 frames.], batch size: 19, lr: 1.63e-03
2022-05-14 00:04:02,748 INFO [train.py:812] (3/8) Epoch 4, batch 550, loss[loss=0.2193, simple_loss=0.2873, pruned_loss=0.07568, over 7150.00 frames.], tot_loss[loss=0.2358, simple_loss=0.3079, pruned_loss=0.08179, over 1329816.73 frames.], batch size: 18, lr: 1.63e-03
2022-05-14 00:05:01,389 INFO [train.py:812] (3/8) Epoch 4, batch 600, loss[loss=0.2438, simple_loss=0.3085, pruned_loss=0.08954, over 6508.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3076, pruned_loss=0.08188, over 1346996.11 frames.], batch size: 38, lr: 1.63e-03
2022-05-14 00:06:00,846 INFO [train.py:812] (3/8) Epoch 4, batch 650, loss[loss=0.2602, simple_loss=0.345, pruned_loss=0.08764, over 7436.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3073, pruned_loss=0.08075, over 1367544.66 frames.], batch size: 20, lr: 1.62e-03
2022-05-14 00:07:00,177 INFO [train.py:812] (3/8) Epoch 4, batch 700, loss[loss=0.2247, simple_loss=0.3032, pruned_loss=0.07314, over 7269.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3051, pruned_loss=0.07917, over 1384556.92 frames.], batch size: 24, lr: 1.62e-03
2022-05-14 00:07:59,210 INFO [train.py:812] (3/8) Epoch 4, batch 750, loss[loss=0.2369, simple_loss=0.3076, pruned_loss=0.08312, over 7315.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3049, pruned_loss=0.07926, over 1392084.09 frames.], batch size: 24, lr: 1.62e-03
2022-05-14 00:08:58,472 INFO [train.py:812] (3/8) Epoch 4, batch 800, loss[loss=0.2032, simple_loss=0.2846, pruned_loss=0.06091, over 7271.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3057, pruned_loss=0.07958, over 1396751.04 frames.], batch size: 19, lr: 1.62e-03
2022-05-14 00:09:58,461 INFO [train.py:812] (3/8) Epoch 4, batch 850, loss[loss=0.2431, simple_loss=0.3059, pruned_loss=0.09013, over 7064.00 frames.], tot_loss[loss=0.2324, simple_loss=0.306, pruned_loss=0.0794, over 1406741.63 frames.], batch size: 18, lr: 1.61e-03
2022-05-14 00:10:57,737 INFO [train.py:812] (3/8) Epoch 4, batch 900, loss[loss=0.2418, simple_loss=0.325, pruned_loss=0.0793, over 7118.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3052, pruned_loss=0.07868, over 1414678.85 frames.], batch size: 21, lr: 1.61e-03
2022-05-14 00:11:56,764 INFO [train.py:812] (3/8) Epoch 4, batch 950, loss[loss=0.2293, simple_loss=0.3145, pruned_loss=0.07203, over 7179.00 frames.], tot_loss[loss=0.2315, simple_loss=0.3049, pruned_loss=0.079, over 1420087.45 frames.], batch size: 26, lr: 1.61e-03
2022-05-14 00:12:55,420 INFO [train.py:812] (3/8) Epoch 4, batch 1000, loss[loss=0.1743, simple_loss=0.2543, pruned_loss=0.04716, over 7283.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3053, pruned_loss=0.07941, over 1420569.69 frames.], batch size: 18, lr: 1.61e-03
2022-05-14 00:13:54,501 INFO [train.py:812] (3/8) Epoch 4, batch 1050, loss[loss=0.2471, simple_loss=0.3191, pruned_loss=0.08758, over 6759.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3058, pruned_loss=0.07987, over 1419473.49 frames.], batch size: 31, lr: 1.60e-03
2022-05-14 00:14:53,492 INFO [train.py:812] (3/8) Epoch 4, batch 1100, loss[loss=0.2631, simple_loss=0.3351, pruned_loss=0.09555, over 7411.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3049, pruned_loss=0.07964, over 1419923.69 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:15:52,713 INFO [train.py:812] (3/8) Epoch 4, batch 1150, loss[loss=0.225, simple_loss=0.3084, pruned_loss=0.07084, over 7325.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3064, pruned_loss=0.0801, over 1417517.31 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:16:51,390 INFO [train.py:812] (3/8) Epoch 4, batch 1200, loss[loss=0.274, simple_loss=0.3409, pruned_loss=0.1035, over 7324.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3065, pruned_loss=0.08006, over 1415241.81 frames.], batch size: 21, lr: 1.60e-03
2022-05-14 00:17:50,401 INFO [train.py:812] (3/8) Epoch 4, batch 1250, loss[loss=0.1847, simple_loss=0.2581, pruned_loss=0.05563, over 6902.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3055, pruned_loss=0.07941, over 1413492.93 frames.], batch size: 15, lr: 1.59e-03
2022-05-14 00:18:48,726 INFO [train.py:812] (3/8) Epoch 4, batch 1300, loss[loss=0.2598, simple_loss=0.3314, pruned_loss=0.09411, over 7191.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3045, pruned_loss=0.07841, over 1416879.85 frames.], batch size: 23, lr: 1.59e-03
2022-05-14 00:19:47,632 INFO [train.py:812] (3/8) Epoch 4, batch 1350, loss[loss=0.2218, simple_loss=0.3003, pruned_loss=0.0717, over 7232.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3047, pruned_loss=0.07883, over 1416030.62 frames.], batch size: 20, lr: 1.59e-03
2022-05-14 00:20:44,847 INFO [train.py:812] (3/8) Epoch 4, batch 1400, loss[loss=0.2419, simple_loss=0.3157, pruned_loss=0.08408, over 7199.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3034, pruned_loss=0.07815, over 1418969.47 frames.], batch size: 22, lr: 1.59e-03
2022-05-14 00:21:44,656 INFO [train.py:812] (3/8) Epoch 4, batch 1450, loss[loss=0.2459, simple_loss=0.3197, pruned_loss=0.08601, over 7284.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3055, pruned_loss=0.07913, over 1420670.83 frames.], batch size: 24, lr: 1.59e-03
2022-05-14 00:22:43,782 INFO [train.py:812] (3/8) Epoch 4, batch 1500, loss[loss=0.253, simple_loss=0.3258, pruned_loss=0.09014, over 7303.00 frames.], tot_loss[loss=0.231, simple_loss=0.3047, pruned_loss=0.07862, over 1417802.87 frames.], batch size: 24, lr: 1.58e-03
2022-05-14 00:23:43,447 INFO [train.py:812] (3/8) Epoch 4, batch 1550, loss[loss=0.3109, simple_loss=0.3521, pruned_loss=0.1349, over 4985.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3051, pruned_loss=0.07868, over 1416847.88 frames.], batch size: 52, lr: 1.58e-03
2022-05-14 00:24:41,298 INFO [train.py:812] (3/8) Epoch 4, batch 1600, loss[loss=0.2183, simple_loss=0.2972, pruned_loss=0.06967, over 7342.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3062, pruned_loss=0.07915, over 1414398.11 frames.], batch size: 25, lr: 1.58e-03
2022-05-14 00:25:40,740 INFO [train.py:812] (3/8) Epoch 4, batch 1650, loss[loss=0.2243, simple_loss=0.3114, pruned_loss=0.06861, over 7321.00 frames.], tot_loss[loss=0.2311, simple_loss=0.305, pruned_loss=0.07865, over 1416418.40 frames.], batch size: 20, lr: 1.58e-03
2022-05-14 00:26:39,526 INFO [train.py:812] (3/8) Epoch 4, batch 1700, loss[loss=0.2561, simple_loss=0.3251, pruned_loss=0.09355, over 7142.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3058, pruned_loss=0.07866, over 1420088.45 frames.], batch size: 20, lr: 1.57e-03
2022-05-14 00:27:38,787 INFO [train.py:812] (3/8) Epoch 4, batch 1750, loss[loss=0.2572, simple_loss=0.332, pruned_loss=0.09119, over 7209.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3055, pruned_loss=0.07858, over 1420035.36 frames.], batch size: 22, lr: 1.57e-03
2022-05-14 00:28:45,522 INFO [train.py:812] (3/8) Epoch 4, batch 1800, loss[loss=0.233, simple_loss=0.3065, pruned_loss=0.07972, over 7220.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3062, pruned_loss=0.07865, over 1422323.19 frames.], batch size: 21, lr: 1.57e-03
2022-05-14 00:29:45,158 INFO [train.py:812] (3/8) Epoch 4, batch 1850, loss[loss=0.1991, simple_loss=0.2785, pruned_loss=0.05986, over 7135.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3058, pruned_loss=0.07845, over 1420176.01 frames.], batch size: 17, lr: 1.57e-03
2022-05-14 00:30:44,398 INFO [train.py:812] (3/8) Epoch 4, batch 1900, loss[loss=0.2155, simple_loss=0.2811, pruned_loss=0.07497, over 7156.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3067, pruned_loss=0.07913, over 1423502.99 frames.], batch size: 19, lr: 1.56e-03
2022-05-14 00:31:43,799 INFO [train.py:812] (3/8) Epoch 4, batch 1950, loss[loss=0.2563, simple_loss=0.3254, pruned_loss=0.09367, over 6346.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3061, pruned_loss=0.07854, over 1428052.42 frames.], batch size: 37, lr: 1.56e-03
2022-05-14 00:32:40,434 INFO [train.py:812] (3/8) Epoch 4, batch 2000, loss[loss=0.2307, simple_loss=0.3113, pruned_loss=0.0751, over 7109.00 frames.], tot_loss[loss=0.2327, simple_loss=0.307, pruned_loss=0.07924, over 1425444.18 frames.], batch size: 21, lr: 1.56e-03
2022-05-14 00:34:15,587 INFO [train.py:812] (3/8) Epoch 4, batch 2050, loss[loss=0.2538, simple_loss=0.3211, pruned_loss=0.0933, over 6786.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3064, pruned_loss=0.07909, over 1422587.60 frames.], batch size: 31, lr: 1.56e-03
2022-05-14 00:35:41,820 INFO [train.py:812] (3/8) Epoch 4, batch 2100, loss[loss=0.2279, simple_loss=0.3036, pruned_loss=0.07611, over 7317.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3045, pruned_loss=0.07802, over 1420432.28 frames.], batch size: 21, lr: 1.56e-03
2022-05-14 00:36:41,402 INFO [train.py:812] (3/8) Epoch 4, batch 2150, loss[loss=0.201, simple_loss=0.2926, pruned_loss=0.05473, over 7331.00 frames.], tot_loss[loss=0.2299, simple_loss=0.3041, pruned_loss=0.07785, over 1423116.48 frames.], batch size: 22, lr: 1.55e-03
2022-05-14 00:37:40,367 INFO [train.py:812] (3/8) Epoch 4, batch 2200, loss[loss=0.2514, simple_loss=0.3349, pruned_loss=0.08392, over 7224.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3042, pruned_loss=0.07829, over 1424820.71 frames.], batch size: 21, lr: 1.55e-03
2022-05-14 00:38:47,586 INFO [train.py:812] (3/8) Epoch 4, batch 2250, loss[loss=0.294, simple_loss=0.3428, pruned_loss=0.1226, over 4867.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3049, pruned_loss=0.07837, over 1426303.19 frames.], batch size: 52, lr: 1.55e-03
2022-05-14 00:39:45,543 INFO [train.py:812] (3/8) Epoch 4, batch 2300, loss[loss=0.256, simple_loss=0.3278, pruned_loss=0.09208, over 7168.00 frames.], tot_loss[loss=0.2307, simple_loss=0.305, pruned_loss=0.07814, over 1429617.62 frames.], batch size: 19, lr: 1.55e-03
2022-05-14 00:40:45,376 INFO [train.py:812] (3/8) Epoch 4, batch 2350, loss[loss=0.21, simple_loss=0.2825, pruned_loss=0.06874, over 7337.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3041, pruned_loss=0.07766, over 1431407.50 frames.], batch size: 20, lr: 1.54e-03
2022-05-14 00:41:44,129 INFO [train.py:812] (3/8) Epoch 4, batch 2400, loss[loss=0.2485, simple_loss=0.3302, pruned_loss=0.08339, over 7320.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3056, pruned_loss=0.0781, over 1433411.98 frames.], batch size: 25, lr: 1.54e-03
2022-05-14 00:42:43,273 INFO [train.py:812] (3/8) Epoch 4, batch 2450, loss[loss=0.2208, simple_loss=0.3038, pruned_loss=0.06892, over 7375.00 frames.], tot_loss[loss=0.2304, simple_loss=0.3049, pruned_loss=0.07791, over 1436408.36 frames.], batch size: 23, lr: 1.54e-03
2022-05-14 00:43:42,437 INFO [train.py:812] (3/8) Epoch 4, batch 2500, loss[loss=0.2138, simple_loss=0.2944, pruned_loss=0.06663, over 7149.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3039, pruned_loss=0.07678, over 1434830.84 frames.], batch size: 19, lr: 1.54e-03
2022-05-14 00:44:40,437 INFO [train.py:812] (3/8) Epoch 4, batch 2550, loss[loss=0.1982, simple_loss=0.2668, pruned_loss=0.06479, over 7423.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3041, pruned_loss=0.07745, over 1427109.57 frames.], batch size: 18, lr: 1.54e-03
2022-05-14 00:45:38,431 INFO [train.py:812] (3/8) Epoch 4, batch 2600, loss[loss=0.227, simple_loss=0.313, pruned_loss=0.07054, over 7236.00 frames.], tot_loss[loss=0.2307, simple_loss=0.305, pruned_loss=0.07823, over 1426127.13 frames.], batch size: 20, lr: 1.53e-03
2022-05-14 00:46:37,707 INFO [train.py:812] (3/8) Epoch 4, batch 2650, loss[loss=0.1706, simple_loss=0.2441, pruned_loss=0.04852, over 6989.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3063, pruned_loss=0.07872, over 1420386.71 frames.], batch size: 16, lr: 1.53e-03
2022-05-14 00:47:36,747 INFO [train.py:812] (3/8) Epoch 4, batch 2700, loss[loss=0.1782, simple_loss=0.2536, pruned_loss=0.05141, over 6792.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3056, pruned_loss=0.07835, over 1418573.55 frames.], batch size: 15, lr: 1.53e-03
2022-05-14 00:48:35,485 INFO [train.py:812] (3/8) Epoch 4, batch 2750, loss[loss=0.2012, simple_loss=0.2831, pruned_loss=0.05958, over 7267.00 frames.], tot_loss[loss=0.2294, simple_loss=0.3045, pruned_loss=0.07712, over 1421703.83 frames.], batch size: 19, lr: 1.53e-03
2022-05-14 00:49:34,102 INFO [train.py:812] (3/8) Epoch 4, batch 2800, loss[loss=0.2017, simple_loss=0.2849, pruned_loss=0.05931, over 7144.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3031, pruned_loss=0.07616, over 1424263.85 frames.], batch size: 19, lr: 1.53e-03
2022-05-14 00:50:32,963 INFO [train.py:812] (3/8) Epoch 4, batch 2850, loss[loss=0.2765, simple_loss=0.342, pruned_loss=0.1056, over 4873.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3032, pruned_loss=0.07656, over 1423469.41 frames.], batch size: 53, lr: 1.52e-03
2022-05-14 00:51:31,281 INFO [train.py:812] (3/8) Epoch 4, batch 2900, loss[loss=0.2642, simple_loss=0.3414, pruned_loss=0.09355, over 6780.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3018, pruned_loss=0.07578, over 1424057.43 frames.], batch size: 31, lr: 1.52e-03
2022-05-14 00:52:31,091 INFO [train.py:812] (3/8) Epoch 4, batch 2950, loss[loss=0.2177, simple_loss=0.2947, pruned_loss=0.07038, over 7101.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3025, pruned_loss=0.07656, over 1428068.61 frames.], batch size: 28, lr: 1.52e-03
2022-05-14 00:53:30,067 INFO [train.py:812] (3/8) Epoch 4, batch 3000, loss[loss=0.2601, simple_loss=0.3198, pruned_loss=0.1002, over 7152.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3029, pruned_loss=0.07683, over 1426593.01 frames.], batch size: 20, lr: 1.52e-03
2022-05-14 00:53:30,068 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 00:53:37,752 INFO [train.py:841] (3/8) Epoch 4, validation: loss=0.1771, simple_loss=0.279, pruned_loss=0.03761, over 698248.00 frames.
2022-05-14 00:54:36,374 INFO [train.py:812] (3/8) Epoch 4, batch 3050, loss[loss=0.2087, simple_loss=0.2946, pruned_loss=0.06134, over 7117.00 frames.], tot_loss[loss=0.2285, simple_loss=0.303, pruned_loss=0.07703, over 1421560.76 frames.], batch size: 21, lr: 1.51e-03
2022-05-14 00:55:35,276 INFO [train.py:812] (3/8) Epoch 4, batch 3100, loss[loss=0.2488, simple_loss=0.3182, pruned_loss=0.0897, over 7298.00 frames.], tot_loss[loss=0.2282, simple_loss=0.302, pruned_loss=0.07716, over 1418196.02 frames.], batch size: 24, lr: 1.51e-03
2022-05-14 00:56:35,140 INFO [train.py:812] (3/8) Epoch 4, batch 3150, loss[loss=0.2139, simple_loss=0.2907, pruned_loss=0.06849, over 7306.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3024, pruned_loss=0.07713, over 1422882.34 frames.], batch size: 25, lr: 1.51e-03
2022-05-14 00:57:33,588 INFO [train.py:812] (3/8) Epoch 4, batch 3200, loss[loss=0.2105, simple_loss=0.289, pruned_loss=0.06601, over 7060.00 frames.], tot_loss[loss=0.227, simple_loss=0.301, pruned_loss=0.07645, over 1423768.81 frames.], batch size: 18, lr: 1.51e-03
2022-05-14 00:58:32,689 INFO [train.py:812] (3/8) Epoch 4, batch 3250, loss[loss=0.1973, simple_loss=0.2832, pruned_loss=0.05574, over 7260.00 frames.], tot_loss[loss=0.2271, simple_loss=0.3017, pruned_loss=0.07628, over 1423780.11 frames.], batch size: 19, lr: 1.51e-03
2022-05-14 00:59:30,509 INFO [train.py:812] (3/8) Epoch 4, batch 3300, loss[loss=0.2642, simple_loss=0.3379, pruned_loss=0.09528, over 7203.00 frames.], tot_loss[loss=0.228, simple_loss=0.3028, pruned_loss=0.07657, over 1422316.24 frames.], batch size: 23, lr: 1.50e-03
2022-05-14 01:00:29,644 INFO [train.py:812] (3/8) Epoch 4, batch 3350, loss[loss=0.3008, simple_loss=0.3713, pruned_loss=0.1152, over 6369.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3016, pruned_loss=0.07591, over 1420675.88 frames.], batch size: 38, lr: 1.50e-03
2022-05-14 01:01:28,316 INFO [train.py:812] (3/8) Epoch 4, batch 3400, loss[loss=0.23, simple_loss=0.2889, pruned_loss=0.08553, over 6983.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3022, pruned_loss=0.07669, over 1421135.41 frames.], batch size: 16, lr: 1.50e-03
2022-05-14 01:02:28,051 INFO [train.py:812] (3/8) Epoch 4, batch 3450, loss[loss=0.2167, simple_loss=0.2881, pruned_loss=0.07268, over 7166.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3001, pruned_loss=0.07516, over 1426098.07 frames.], batch size: 18, lr: 1.50e-03
2022-05-14 01:03:26,374 INFO [train.py:812] (3/8) Epoch 4, batch 3500, loss[loss=0.2205, simple_loss=0.3005, pruned_loss=0.07027, over 7367.00 frames.], tot_loss[loss=0.2248, simple_loss=0.2995, pruned_loss=0.075, over 1428044.56 frames.], batch size: 23, lr: 1.50e-03
2022-05-14 01:04:26,013 INFO [train.py:812] (3/8) Epoch 4, batch 3550, loss[loss=0.25, simple_loss=0.3158, pruned_loss=0.09208, over 7305.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2998, pruned_loss=0.0755, over 1429470.48 frames.], batch size: 24, lr: 1.49e-03
2022-05-14 01:05:25,242 INFO [train.py:812] (3/8) Epoch 4, batch 3600, loss[loss=0.1692, simple_loss=0.2425, pruned_loss=0.04798, over 6994.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2997, pruned_loss=0.07557, over 1428409.42 frames.], batch size: 16, lr: 1.49e-03
2022-05-14 01:06:24,817 INFO [train.py:812] (3/8) Epoch 4, batch 3650, loss[loss=0.178, simple_loss=0.247, pruned_loss=0.05449, over 7128.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2998, pruned_loss=0.07553, over 1429094.60 frames.], batch size: 17, lr: 1.49e-03
2022-05-14 01:07:24,306 INFO [train.py:812] (3/8) Epoch 4, batch 3700, loss[loss=0.1746, simple_loss=0.246, pruned_loss=0.05158, over 7011.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2996, pruned_loss=0.07528, over 1427542.32 frames.], batch size: 16, lr: 1.49e-03
2022-05-14 01:08:24,367 INFO [train.py:812] (3/8) Epoch 4, batch 3750, loss[loss=0.2282, simple_loss=0.3049, pruned_loss=0.07575, over 7432.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2979, pruned_loss=0.07435, over 1425509.22 frames.], batch size: 20, lr: 1.49e-03
2022-05-14 01:09:22,775 INFO [train.py:812] (3/8) Epoch 4, batch 3800, loss[loss=0.1852, simple_loss=0.2672, pruned_loss=0.05157, over 7060.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2974, pruned_loss=0.07417, over 1422190.91 frames.], batch size: 18, lr: 1.48e-03
2022-05-14 01:10:22,616 INFO [train.py:812] (3/8) Epoch 4, batch 3850, loss[loss=0.218, simple_loss=0.2846, pruned_loss=0.07567, over 7416.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2973, pruned_loss=0.07411, over 1425809.25 frames.], batch size: 18, lr: 1.48e-03
2022-05-14 01:11:21,431 INFO [train.py:812] (3/8) Epoch 4, batch 3900, loss[loss=0.3071, simple_loss=0.3682, pruned_loss=0.123, over 4951.00 frames.], tot_loss[loss=0.2241, simple_loss=0.299, pruned_loss=0.07459, over 1426290.27 frames.], batch size: 52, lr: 1.48e-03
2022-05-14 01:12:20,485 INFO [train.py:812] (3/8) Epoch 4, batch 3950, loss[loss=0.1704, simple_loss=0.2439, pruned_loss=0.04846, over 6831.00 frames.], tot_loss[loss=0.2228, simple_loss=0.2979, pruned_loss=0.07386, over 1423897.64 frames.], batch size: 15, lr: 1.48e-03
2022-05-14 01:13:19,404 INFO [train.py:812] (3/8) Epoch 4, batch 4000, loss[loss=0.2378, simple_loss=0.3151, pruned_loss=0.08028, over 7211.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3, pruned_loss=0.07551, over 1416610.02 frames.], batch size: 21, lr: 1.48e-03
2022-05-14 01:14:18,981 INFO [train.py:812] (3/8) Epoch 4, batch 4050, loss[loss=0.2316, simple_loss=0.3091, pruned_loss=0.07703, over 7412.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3006, pruned_loss=0.07544, over 1419076.35 frames.], batch size: 21, lr: 1.47e-03
2022-05-14 01:15:18,235 INFO [train.py:812] (3/8) Epoch 4, batch 4100, loss[loss=0.2744, simple_loss=0.3403, pruned_loss=0.1043, over 6448.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3009, pruned_loss=0.07592, over 1420862.54 frames.], batch size: 37, lr: 1.47e-03
2022-05-14 01:16:17,171 INFO [train.py:812] (3/8) Epoch 4, batch 4150, loss[loss=0.2006, simple_loss=0.2707, pruned_loss=0.06523, over 7413.00 frames.], tot_loss[loss=0.225, simple_loss=0.2995, pruned_loss=0.07531, over 1423297.51 frames.], batch size: 17, lr: 1.47e-03
2022-05-14 01:17:15,912 INFO [train.py:812] (3/8) Epoch 4, batch 4200, loss[loss=0.2415, simple_loss=0.3085, pruned_loss=0.08721, over 7161.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3008, pruned_loss=0.07615, over 1421376.47 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:18:15,840 INFO [train.py:812] (3/8) Epoch 4, batch 4250, loss[loss=0.1992, simple_loss=0.2718, pruned_loss=0.06329, over 7352.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2992, pruned_loss=0.07552, over 1413751.13 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:19:14,764 INFO [train.py:812] (3/8) Epoch 4, batch 4300, loss[loss=0.2579, simple_loss=0.3347, pruned_loss=0.09059, over 7359.00 frames.], tot_loss[loss=0.2239, simple_loss=0.2975, pruned_loss=0.07513, over 1411651.89 frames.], batch size: 19, lr: 1.47e-03
2022-05-14 01:20:14,297 INFO [train.py:812] (3/8) Epoch 4, batch 4350, loss[loss=0.2088, simple_loss=0.2895, pruned_loss=0.06408, over 6314.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2954, pruned_loss=0.07386, over 1409483.02 frames.], batch size: 37, lr: 1.46e-03
2022-05-14 01:21:13,877 INFO [train.py:812] (3/8) Epoch 4, batch 4400, loss[loss=0.2486, simple_loss=0.3078, pruned_loss=0.09474, over 7080.00 frames.], tot_loss[loss=0.2216, simple_loss=0.295, pruned_loss=0.07409, over 1408074.82 frames.], batch size: 18, lr: 1.46e-03
2022-05-14 01:22:13,435 INFO [train.py:812] (3/8) Epoch 4, batch 4450, loss[loss=0.2425, simple_loss=0.3214, pruned_loss=0.08178, over 7382.00 frames.], tot_loss[loss=0.2209, simple_loss=0.2943, pruned_loss=0.07372, over 1400762.16 frames.], batch size: 23, lr: 1.46e-03
2022-05-14 01:23:11,878 INFO [train.py:812] (3/8) Epoch 4, batch 4500, loss[loss=0.2542, simple_loss=0.3333, pruned_loss=0.08757, over 6353.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2948, pruned_loss=0.07382, over 1395706.18 frames.], batch size: 37, lr: 1.46e-03
2022-05-14 01:24:10,622 INFO [train.py:812] (3/8) Epoch 4, batch 4550, loss[loss=0.2807, simple_loss=0.3357, pruned_loss=0.1128, over 5575.00 frames.], tot_loss[loss=0.226, simple_loss=0.2991, pruned_loss=0.07641, over 1361425.63 frames.], batch size: 52, lr: 1.46e-03
2022-05-14 01:25:17,912 INFO [train.py:812] (3/8) Epoch 5, batch 0, loss[loss=0.248, simple_loss=0.319, pruned_loss=0.08851, over 7202.00 frames.], tot_loss[loss=0.248, simple_loss=0.319, pruned_loss=0.08851, over 7202.00 frames.], batch size: 23, lr: 1.40e-03
2022-05-14 01:26:16,015 INFO [train.py:812] (3/8) Epoch 5, batch 50, loss[loss=0.2652, simple_loss=0.3349, pruned_loss=0.09769, over 7344.00 frames.], tot_loss[loss=0.2223, simple_loss=0.2968, pruned_loss=0.0739, over 320763.36 frames.], batch size: 22, lr: 1.40e-03
2022-05-14 01:27:13,771 INFO [train.py:812] (3/8) Epoch 5, batch 100, loss[loss=0.2216, simple_loss=0.3049, pruned_loss=0.06914, over 7331.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2992, pruned_loss=0.0745, over 566612.13 frames.], batch size: 22, lr: 1.40e-03
2022-05-14 01:28:13,014 INFO [train.py:812] (3/8) Epoch 5, batch 150, loss[loss=0.2239, simple_loss=0.3004, pruned_loss=0.07372, over 4900.00 frames.], tot_loss[loss=0.2231, simple_loss=0.299, pruned_loss=0.0736, over 754758.21 frames.], batch size: 52, lr: 1.40e-03
2022-05-14 01:29:12,385 INFO [train.py:812] (3/8) Epoch 5, batch 200, loss[loss=0.2305, simple_loss=0.2963, pruned_loss=0.08234, over 7158.00 frames.], tot_loss[loss=0.222, simple_loss=0.2981, pruned_loss=0.07296, over 903373.54 frames.], batch size: 19, lr: 1.40e-03
2022-05-14 01:30:11,969 INFO [train.py:812] (3/8) Epoch 5, batch 250, loss[loss=0.2378, simple_loss=0.3108, pruned_loss=0.08239, over 7339.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3005, pruned_loss=0.07355, over 1021318.73 frames.], batch size: 22, lr: 1.39e-03
2022-05-14 01:31:10,333 INFO [train.py:812] (3/8) Epoch 5, batch 300, loss[loss=0.1763, simple_loss=0.252, pruned_loss=0.05028, over 7283.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2985, pruned_loss=0.07249, over 1113029.69 frames.], batch size: 17, lr: 1.39e-03
2022-05-14 01:32:09,254 INFO [train.py:812] (3/8) Epoch 5, batch 350, loss[loss=0.2016, simple_loss=0.2852, pruned_loss=0.059, over 7162.00 frames.], tot_loss[loss=0.2198, simple_loss=0.2964, pruned_loss=0.0716, over 1181009.37 frames.], batch size: 19, lr: 1.39e-03
2022-05-14 01:33:06,922 INFO [train.py:812] (3/8) Epoch 5, batch 400, loss[loss=0.2308, simple_loss=0.3084, pruned_loss=0.07662, over 7038.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2958, pruned_loss=0.07131, over 1232263.26 frames.], batch size: 28, lr: 1.39e-03
2022-05-14 01:34:05,803 INFO [train.py:812] (3/8) Epoch 5, batch 450, loss[loss=0.242, simple_loss=0.3059, pruned_loss=0.08905, over 7101.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2951, pruned_loss=0.07091, over 1274230.78 frames.], batch size: 28, lr: 1.39e-03
2022-05-14 01:35:05,178 INFO [train.py:812] (3/8) Epoch 5, batch 500, loss[loss=0.2043, simple_loss=0.2911, pruned_loss=0.05877, over 7323.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2953, pruned_loss=0.07109, over 1309360.96 frames.], batch size: 21, lr: 1.39e-03
2022-05-14 01:36:04,760 INFO [train.py:812] (3/8) Epoch 5, batch 550, loss[loss=0.2487, simple_loss=0.3216, pruned_loss=0.08785, over 6674.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2944, pruned_loss=0.07056, over 1333520.40 frames.], batch size: 31, lr: 1.38e-03
2022-05-14 01:37:04,098 INFO [train.py:812] (3/8) Epoch 5, batch 600, loss[loss=0.2103, simple_loss=0.2745, pruned_loss=0.07305, over 6977.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2937, pruned_loss=0.07062, over 1355790.06 frames.], batch size: 16, lr: 1.38e-03
2022-05-14 01:38:03,174 INFO [train.py:812] (3/8) Epoch 5, batch 650, loss[loss=0.2229, simple_loss=0.2968, pruned_loss=0.07444, over 7322.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2942, pruned_loss=0.07077, over 1370802.20 frames.], batch size: 20, lr: 1.38e-03
2022-05-14 01:39:02,099 INFO [train.py:812] (3/8) Epoch 5, batch 700, loss[loss=0.2748, simple_loss=0.3513, pruned_loss=0.09912, over 7289.00 frames.], tot_loss[loss=0.2186, simple_loss=0.2952, pruned_loss=0.07102, over 1379760.26 frames.], batch size: 25, lr: 1.38e-03
2022-05-14 01:40:01,979 INFO [train.py:812] (3/8) Epoch 5, batch 750, loss[loss=0.1878, simple_loss=0.2715, pruned_loss=0.05202, over 7059.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2949, pruned_loss=0.07123, over 1384466.95 frames.], batch size: 18, lr: 1.38e-03
2022-05-14 01:40:59,750 INFO [train.py:812] (3/8) Epoch 5, batch 800, loss[loss=0.1929, simple_loss=0.281, pruned_loss=0.05236, over 7058.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2928, pruned_loss=0.07002, over 1396238.00 frames.], batch size: 18, lr: 1.38e-03
2022-05-14 01:41:57,348 INFO [train.py:812] (3/8) Epoch 5, batch 850, loss[loss=0.2066, simple_loss=0.279, pruned_loss=0.06711, over 7064.00 frames.], tot_loss[loss=0.217, simple_loss=0.2932, pruned_loss=0.07037, over 1394678.78 frames.], batch size: 18, lr: 1.37e-03
2022-05-14 01:42:55,832 INFO [train.py:812] (3/8) Epoch 5, batch 900, loss[loss=0.2214, simple_loss=0.2954, pruned_loss=0.07367, over 7309.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2925, pruned_loss=0.07002, over 1402605.66 frames.], batch size: 21, lr: 1.37e-03
2022-05-14 01:43:53,335 INFO [train.py:812] (3/8) Epoch 5, batch 950, loss[loss=0.2404, simple_loss=0.3155, pruned_loss=0.08265, over 7152.00 frames.], tot_loss[loss=0.217, simple_loss=0.2931, pruned_loss=0.07046, over 1406805.82 frames.], batch size: 28, lr: 1.37e-03
2022-05-14 01:44:52,025 INFO [train.py:812] (3/8) Epoch 5, batch 1000, loss[loss=0.2108, simple_loss=0.2894, pruned_loss=0.06607, over 7074.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2931, pruned_loss=0.07053, over 1411488.04 frames.], batch size: 18, lr: 1.37e-03
2022-05-14 01:45:49,411 INFO [train.py:812] (3/8) Epoch 5, batch 1050, loss[loss=0.2388, simple_loss=0.3081, pruned_loss=0.08477, over 7308.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2944, pruned_loss=0.07088, over 1417529.33 frames.], batch size: 24, lr: 1.37e-03
2022-05-14 01:46:47,328 INFO [train.py:812] (3/8) Epoch 5, batch 1100, loss[loss=0.2432, simple_loss=0.3114, pruned_loss=0.08746, over 6207.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2948, pruned_loss=0.071, over 1412824.29 frames.], batch size: 37, lr: 1.37e-03
2022-05-14 01:47:47,032 INFO [train.py:812] (3/8) Epoch 5, batch 1150, loss[loss=0.2513, simple_loss=0.3242, pruned_loss=0.08921, over 7429.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2946, pruned_loss=0.07033, over 1415389.26 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:48:45,950 INFO [train.py:812] (3/8) Epoch 5, batch 1200, loss[loss=0.1992, simple_loss=0.2867, pruned_loss=0.05584, over 6263.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2943, pruned_loss=0.07027, over 1417696.84 frames.], batch size: 37, lr: 1.36e-03
2022-05-14 01:49:45,451 INFO [train.py:812] (3/8) Epoch 5, batch 1250, loss[loss=0.1864, simple_loss=0.2732, pruned_loss=0.04978, over 7266.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2946, pruned_loss=0.07035, over 1413680.34 frames.], batch size: 19, lr: 1.36e-03
2022-05-14 01:50:43,659 INFO [train.py:812] (3/8) Epoch 5, batch 1300, loss[loss=0.2127, simple_loss=0.2831, pruned_loss=0.07116, over 7322.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2948, pruned_loss=0.06981, over 1416933.30 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:51:42,406 INFO [train.py:812] (3/8) Epoch 5, batch 1350, loss[loss=0.1947, simple_loss=0.2677, pruned_loss=0.0609, over 7134.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2952, pruned_loss=0.07013, over 1423181.70 frames.], batch size: 17, lr: 1.36e-03
2022-05-14 01:52:39,812 INFO [train.py:812] (3/8) Epoch 5, batch 1400, loss[loss=0.1818, simple_loss=0.2643, pruned_loss=0.04962, over 7235.00 frames.], tot_loss[loss=0.2195, simple_loss=0.2969, pruned_loss=0.07109, over 1419370.61 frames.], batch size: 20, lr: 1.36e-03
2022-05-14 01:53:37,452 INFO [train.py:812] (3/8) Epoch 5, batch 1450, loss[loss=0.1722, simple_loss=0.247, pruned_loss=0.04869, over 7002.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2971, pruned_loss=0.07116, over 1419477.08 frames.], batch size: 16, lr: 1.35e-03
2022-05-14 01:54:35,088 INFO [train.py:812] (3/8) Epoch 5, batch 1500, loss[loss=0.2334, simple_loss=0.2988, pruned_loss=0.08402, over 7327.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2958, pruned_loss=0.07073, over 1423123.28 frames.], batch size: 20, lr: 1.35e-03
2022-05-14 01:55:34,682 INFO [train.py:812] (3/8) Epoch 5, batch 1550, loss[loss=0.2461, simple_loss=0.3266, pruned_loss=0.08284, over 7390.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2942, pruned_loss=0.06982, over 1425196.25 frames.], batch size: 23, lr: 1.35e-03
2022-05-14 01:56:33,039 INFO [train.py:812] (3/8) Epoch 5, batch 1600, loss[loss=0.2119, simple_loss=0.3018, pruned_loss=0.06098, over 7293.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2948, pruned_loss=0.07031, over 1424451.46 frames.], batch size: 25, lr: 1.35e-03
2022-05-14 01:57:37,178 INFO [train.py:812] (3/8) Epoch 5, batch 1650, loss[loss=0.2218, simple_loss=0.3142, pruned_loss=0.06471, over 7100.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2954, pruned_loss=0.07049, over 1422762.79 frames.], batch size: 21, lr: 1.35e-03
2022-05-14 01:58:36,679 INFO [train.py:812] (3/8) Epoch 5, batch 1700, loss[loss=0.2264, simple_loss=0.3212, pruned_loss=0.06579, over 7340.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2951, pruned_loss=0.07015, over 1424899.92 frames.], batch size: 22, lr: 1.35e-03
2022-05-14 01:59:35,703 INFO [train.py:812] (3/8) Epoch 5, batch 1750, loss[loss=0.2245, simple_loss=0.309, pruned_loss=0.06995, over 7293.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2944, pruned_loss=0.07016, over 1424133.03 frames.], batch size: 24, lr: 1.34e-03
2022-05-14 02:00:34,956 INFO [train.py:812] (3/8) Epoch 5, batch 1800, loss[loss=0.2238, simple_loss=0.3101, pruned_loss=0.06874, over 7321.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2938, pruned_loss=0.06946, over 1426573.99 frames.], batch size: 21, lr: 1.34e-03
2022-05-14 02:01:33,475 INFO [train.py:812] (3/8) Epoch 5, batch 1850, loss[loss=0.2658, simple_loss=0.3471, pruned_loss=0.09223, over 6295.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2946, pruned_loss=0.06956, over 1426523.74 frames.], batch size: 37, lr: 1.34e-03
2022-05-14 02:02:31,901 INFO [train.py:812] (3/8) Epoch 5, batch 1900, loss[loss=0.2037, simple_loss=0.2827, pruned_loss=0.06237, over 7115.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2947, pruned_loss=0.0698, over 1427918.60 frames.], batch size: 21, lr: 1.34e-03
2022-05-14 02:03:30,591 INFO [train.py:812] (3/8) Epoch 5, batch 1950, loss[loss=0.2092, simple_loss=0.2788, pruned_loss=0.06982, over 7162.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2943, pruned_loss=0.06944, over 1428612.73 frames.], batch size: 18, lr: 1.34e-03
2022-05-14 02:04:28,245 INFO [train.py:812] (3/8) Epoch 5, batch 2000, loss[loss=0.2438, simple_loss=0.3223, pruned_loss=0.08262, over 7305.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2953, pruned_loss=0.07045, over 1426267.34 frames.], batch size: 25, lr: 1.34e-03
2022-05-14 02:05:26,860 INFO [train.py:812] (3/8) Epoch 5, batch 2050, loss[loss=0.2344, simple_loss=0.3063, pruned_loss=0.08121, over 7286.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2937, pruned_loss=0.06939, over 1430699.38 frames.], batch size: 24, lr: 1.34e-03
2022-05-14 02:06:25,375 INFO [train.py:812] (3/8) Epoch 5, batch 2100, loss[loss=0.1705, simple_loss=0.2549, pruned_loss=0.04305, over 7395.00 frames.], tot_loss[loss=0.216, simple_loss=0.2934, pruned_loss=0.06935, over 1433763.38 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:07:23,966 INFO [train.py:812] (3/8) Epoch 5, batch 2150, loss[loss=0.2034, simple_loss=0.2822, pruned_loss=0.06229, over 7070.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2941, pruned_loss=0.06937, over 1432502.62 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:08:21,797 INFO [train.py:812] (3/8) Epoch 5, batch 2200, loss[loss=0.2388, simple_loss=0.3215, pruned_loss=0.07811, over 7334.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2935, pruned_loss=0.0695, over 1434485.99 frames.], batch size: 22, lr: 1.33e-03
2022-05-14 02:09:20,781 INFO [train.py:812] (3/8) Epoch 5, batch 2250, loss[loss=0.2416, simple_loss=0.3256, pruned_loss=0.07878, over 7374.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2933, pruned_loss=0.06966, over 1432252.86 frames.], batch size: 23, lr: 1.33e-03
2022-05-14 02:10:20,188 INFO [train.py:812] (3/8) Epoch 5, batch 2300, loss[loss=0.1936, simple_loss=0.2495, pruned_loss=0.06886, over 7282.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2937, pruned_loss=0.06974, over 1430686.53 frames.], batch size: 17, lr: 1.33e-03
2022-05-14 02:11:18,988 INFO [train.py:812] (3/8) Epoch 5, batch 2350, loss[loss=0.1711, simple_loss=0.2576, pruned_loss=0.04233, over 7417.00 frames.], tot_loss[loss=0.217, simple_loss=0.2944, pruned_loss=0.06976, over 1434125.76 frames.], batch size: 18, lr: 1.33e-03
2022-05-14 02:12:18,587 INFO [train.py:812] (3/8) Epoch 5, batch 2400, loss[loss=0.1832, simple_loss=0.2664, pruned_loss=0.04998, over 7213.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2934, pruned_loss=0.06946, over 1435757.90 frames.], batch size: 21, lr: 1.32e-03
2022-05-14 02:13:16,796 INFO [train.py:812] (3/8) Epoch 5, batch 2450, loss[loss=0.2047, simple_loss=0.274, pruned_loss=0.06775, over 7277.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2936, pruned_loss=0.0695, over 1434908.74 frames.], batch size: 18, lr: 1.32e-03
2022-05-14 02:14:14,133 INFO [train.py:812] (3/8) Epoch 5, batch 2500, loss[loss=0.2515, simple_loss=0.3385, pruned_loss=0.08225, over 7216.00 frames.], tot_loss[loss=0.216, simple_loss=0.2931, pruned_loss=0.06947, over 1432697.29 frames.], batch size: 22, lr: 1.32e-03
2022-05-14 02:15:13,112 INFO [train.py:812] (3/8) Epoch 5, batch 2550, loss[loss=0.2218, simple_loss=0.3083, pruned_loss=0.06765, over 7143.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2931, pruned_loss=0.06932, over 1433546.34 frames.], batch size: 20, lr: 1.32e-03
2022-05-14 02:16:11,209 INFO [train.py:812] (3/8) Epoch 5, batch 2600, loss[loss=0.1729, simple_loss=0.2729, pruned_loss=0.03644, over 7314.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2934, pruned_loss=0.06924, over 1431974.10 frames.], batch size: 21, lr: 1.32e-03
2022-05-14 02:17:10,908 INFO [train.py:812] (3/8) Epoch 5, batch 2650, loss[loss=0.1962, simple_loss=0.2629, pruned_loss=0.06477, over 6989.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2935, pruned_loss=0.069, over 1430318.68 frames.], batch size: 16, lr: 1.32e-03
2022-05-14 02:18:10,459 INFO [train.py:812] (3/8) Epoch 5, batch 2700, loss[loss=0.1617, simple_loss=0.243, pruned_loss=0.04021, over 7271.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2925, pruned_loss=0.06826, over 1431837.26 frames.], batch size: 18, lr: 1.32e-03
2022-05-14 02:19:10,225 INFO [train.py:812] (3/8) Epoch 5, batch 2750, loss[loss=0.2104, simple_loss=0.2789, pruned_loss=0.07099, over 7354.00 frames.], tot_loss[loss=0.214, simple_loss=0.2919, pruned_loss=0.06809, over 1432838.68 frames.], batch size: 19, lr: 1.31e-03
2022-05-14 02:20:09,507 INFO [train.py:812] (3/8) Epoch 5, batch 2800, loss[loss=0.2068, simple_loss=0.2789, pruned_loss=0.06739, over 7146.00 frames.], tot_loss[loss=0.213, simple_loss=0.2912, pruned_loss=0.06745, over 1433560.90 frames.], batch size: 17, lr: 1.31e-03
2022-05-14 02:21:07,406 INFO [train.py:812] (3/8) Epoch 5, batch 2850, loss[loss=0.2109, simple_loss=0.2935, pruned_loss=0.06417, over 6708.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2918, pruned_loss=0.0682, over 1430282.89 frames.], batch size: 31, lr: 1.31e-03
2022-05-14 02:22:06,253 INFO [train.py:812] (3/8) Epoch 5, batch 2900, loss[loss=0.2245, simple_loss=0.2948, pruned_loss=0.07707, over 7276.00 frames.], tot_loss[loss=0.214, simple_loss=0.2918, pruned_loss=0.06813, over 1428955.02 frames.], batch size: 24, lr: 1.31e-03
2022-05-14 02:23:05,647 INFO [train.py:812] (3/8) Epoch 5, batch 2950, loss[loss=0.1894, simple_loss=0.2831, pruned_loss=0.0479, over 7349.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2909, pruned_loss=0.06774, over 1429569.13 frames.], batch size: 22, lr: 1.31e-03
2022-05-14 02:24:04,409 INFO [train.py:812] (3/8) Epoch 5, batch 3000, loss[loss=0.2097, simple_loss=0.2938, pruned_loss=0.06282, over 7182.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2911, pruned_loss=0.06799, over 1425911.86 frames.], batch size: 26, lr: 1.31e-03
2022-05-14 02:24:04,410 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 02:24:12,113 INFO [train.py:841] (3/8) Epoch 5, validation: loss=0.1705, simple_loss=0.2732, pruned_loss=0.03391, over 698248.00 frames.
2022-05-14 02:25:11,798 INFO [train.py:812] (3/8) Epoch 5, batch 3050, loss[loss=0.2574, simple_loss=0.3226, pruned_loss=0.09616, over 7208.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2914, pruned_loss=0.06784, over 1430024.83 frames.], batch size: 22, lr: 1.31e-03
2022-05-14 02:26:09,566 INFO [train.py:812] (3/8) Epoch 5, batch 3100, loss[loss=0.2117, simple_loss=0.3013, pruned_loss=0.06098, over 7238.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2917, pruned_loss=0.06794, over 1428603.28 frames.], batch size: 20, lr: 1.30e-03
2022-05-14 02:27:19,072 INFO [train.py:812] (3/8) Epoch 5, batch 3150, loss[loss=0.2053, simple_loss=0.3012, pruned_loss=0.05475, over 7311.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2925, pruned_loss=0.06826, over 1429274.32 frames.], batch size: 25, lr: 1.30e-03
2022-05-14 02:28:18,394 INFO [train.py:812] (3/8) Epoch 5, batch 3200, loss[loss=0.1868, simple_loss=0.265, pruned_loss=0.05429, over 7355.00 frames.], tot_loss[loss=0.214, simple_loss=0.2922, pruned_loss=0.0679, over 1430274.99 frames.], batch size: 19, lr: 1.30e-03
2022-05-14 02:29:17,240 INFO [train.py:812] (3/8) Epoch 5, batch 3250, loss[loss=0.2024, simple_loss=0.2687, pruned_loss=0.06803, over 7165.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2908, pruned_loss=0.06772, over 1427641.99 frames.], batch size: 18, lr: 1.30e-03
2022-05-14 02:30:15,402 INFO [train.py:812] (3/8) Epoch 5, batch 3300, loss[loss=0.232, simple_loss=0.3092, pruned_loss=0.07746, over 7172.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2924, pruned_loss=0.06887, over 1422864.29 frames.], batch size: 26, lr: 1.30e-03
2022-05-14 02:31:14,124 INFO [train.py:812] (3/8) Epoch 5, batch 3350, loss[loss=0.2036, simple_loss=0.2887, pruned_loss=0.05921, over 7111.00 frames.], tot_loss[loss=0.2142, simple_loss=0.292, pruned_loss=0.06821, over 1425610.99 frames.], batch size: 21, lr: 1.30e-03
2022-05-14 02:32:12,545 INFO [train.py:812] (3/8) Epoch 5, batch 3400, loss[loss=0.213, simple_loss=0.2901, pruned_loss=0.06791, over 7227.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2928, pruned_loss=0.06848, over 1427632.91 frames.], batch size: 20, lr: 1.30e-03
2022-05-14 02:33:11,754 INFO [train.py:812] (3/8) Epoch 5, batch 3450, loss[loss=0.2078, simple_loss=0.2967, pruned_loss=0.05944, over 7212.00 frames.], tot_loss[loss=0.2144, simple_loss=0.292, pruned_loss=0.06839, over 1427761.10 frames.], batch size: 23, lr: 1.29e-03
2022-05-14 02:34:10,769 INFO [train.py:812] (3/8) Epoch 5, batch 3500, loss[loss=0.1851, simple_loss=0.2773, pruned_loss=0.04644, over 7322.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2922, pruned_loss=0.06808, over 1430406.49 frames.], batch size: 20, lr: 1.29e-03
2022-05-14 02:35:38,311 INFO [train.py:812] (3/8) Epoch 5, batch 3550, loss[loss=0.203, simple_loss=0.2892, pruned_loss=0.05844, over 7408.00 frames.], tot_loss[loss=0.214, simple_loss=0.2921, pruned_loss=0.06798, over 1425156.27 frames.], batch size: 21, lr: 1.29e-03
2022-05-14 02:36:46,057 INFO [train.py:812] (3/8) Epoch 5, batch 3600, loss[loss=0.1877, simple_loss=0.2656, pruned_loss=0.05494, over 7258.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2907, pruned_loss=0.06756, over 1420663.90 frames.], batch size: 19, lr: 1.29e-03
2022-05-14 02:38:13,343 INFO [train.py:812] (3/8) Epoch 5, batch 3650, loss[loss=0.2247, simple_loss=0.2985, pruned_loss=0.07548, over 6692.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2926, pruned_loss=0.06821, over 1415372.73 frames.], batch size: 31, lr: 1.29e-03
2022-05-14 02:39:12,936 INFO [train.py:812] (3/8) Epoch 5, batch 3700, loss[loss=0.2061, simple_loss=0.2881, pruned_loss=0.06206, over 7169.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2912, pruned_loss=0.06791, over 1420419.42 frames.], batch size: 18, lr: 1.29e-03
2022-05-14 02:40:11,639 INFO [train.py:812] (3/8) Epoch 5, batch 3750, loss[loss=0.1728, simple_loss=0.2454, pruned_loss=0.05014, over 6817.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2926, pruned_loss=0.06816, over 1420678.15 frames.], batch size: 15, lr: 1.29e-03
2022-05-14 02:41:09,954 INFO [train.py:812] (3/8) Epoch 5, batch 3800, loss[loss=0.197, simple_loss=0.2679, pruned_loss=0.06304, over 7281.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2934, pruned_loss=0.06887, over 1422210.29 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:42:07,606 INFO [train.py:812] (3/8) Epoch 5, batch 3850, loss[loss=0.2606, simple_loss=0.3417, pruned_loss=0.08968, over 7416.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2929, pruned_loss=0.06845, over 1421653.53 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:43:06,301 INFO [train.py:812] (3/8) Epoch 5, batch 3900, loss[loss=0.2007, simple_loss=0.2932, pruned_loss=0.05411, over 7179.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2916, pruned_loss=0.06742, over 1418361.02 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:44:04,235 INFO [train.py:812] (3/8) Epoch 5, batch 3950, loss[loss=0.211, simple_loss=0.3041, pruned_loss=0.05893, over 7410.00 frames.], tot_loss[loss=0.2141, simple_loss=0.2924, pruned_loss=0.06793, over 1415305.96 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:45:02,157 INFO [train.py:812] (3/8) Epoch 5, batch 4000, loss[loss=0.2618, simple_loss=0.329, pruned_loss=0.09726, over 7434.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2928, pruned_loss=0.06791, over 1418016.13 frames.], batch size: 20, lr: 1.28e-03
2022-05-14 02:46:01,620 INFO [train.py:812] (3/8) Epoch 5, batch 4050, loss[loss=0.2626, simple_loss=0.3508, pruned_loss=0.08724, over 7206.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2921, pruned_loss=0.0671, over 1420934.69 frames.], batch size: 21, lr: 1.28e-03
2022-05-14 02:46:59,621 INFO [train.py:812] (3/8) Epoch 5, batch 4100, loss[loss=0.1872, simple_loss=0.2657, pruned_loss=0.05432, over 7278.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2943, pruned_loss=0.06813, over 1417595.15 frames.], batch size: 18, lr: 1.28e-03
2022-05-14 02:47:58,847 INFO [train.py:812] (3/8) Epoch 5, batch 4150, loss[loss=0.1871, simple_loss=0.2735, pruned_loss=0.05036, over 7199.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2944, pruned_loss=0.06874, over 1415733.36 frames.], batch size: 22, lr: 1.27e-03
2022-05-14 02:48:57,891 INFO [train.py:812] (3/8) Epoch 5, batch 4200, loss[loss=0.2301, simple_loss=0.2977, pruned_loss=0.08126, over 7121.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2939, pruned_loss=0.06889, over 1413812.16 frames.], batch size: 17, lr: 1.27e-03
2022-05-14 02:49:57,153 INFO [train.py:812] (3/8) Epoch 5, batch 4250, loss[loss=0.1643, simple_loss=0.2459, pruned_loss=0.04136, over 7074.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2938, pruned_loss=0.06888, over 1415145.95 frames.], batch size: 18, lr: 1.27e-03
2022-05-14 02:50:54,438 INFO [train.py:812] (3/8) Epoch 5, batch 4300, loss[loss=0.224, simple_loss=0.3021, pruned_loss=0.07296, over 7135.00 frames.], tot_loss[loss=0.216, simple_loss=0.2942, pruned_loss=0.06891, over 1415383.28 frames.], batch size: 20, lr: 1.27e-03
2022-05-14 02:51:52,657 INFO [train.py:812] (3/8) Epoch 5, batch 4350, loss[loss=0.1869, simple_loss=0.2675, pruned_loss=0.05313, over 7403.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2939, pruned_loss=0.06831, over 1414077.70 frames.], batch size: 21, lr: 1.27e-03
2022-05-14 02:52:52,128 INFO [train.py:812] (3/8) Epoch 5, batch 4400, loss[loss=0.1796, simple_loss=0.2635, pruned_loss=0.04787, over 7254.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2933, pruned_loss=0.06776, over 1410838.88 frames.], batch size: 19, lr: 1.27e-03
2022-05-14 02:53:51,826 INFO [train.py:812] (3/8) Epoch 5, batch 4450, loss[loss=0.2295, simple_loss=0.3069, pruned_loss=0.07608, over 6688.00 frames.], tot_loss[loss=0.2152, simple_loss=0.2938, pruned_loss=0.06834, over 1404177.00 frames.], batch size: 31, lr: 1.27e-03
2022-05-14 02:54:49,592 INFO [train.py:812] (3/8) Epoch 5, batch 4500, loss[loss=0.2279, simple_loss=0.3042, pruned_loss=0.07577, over 5192.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2958, pruned_loss=0.06954, over 1395423.54 frames.], batch size: 52, lr: 1.27e-03
2022-05-14 02:55:48,805 INFO [train.py:812] (3/8) Epoch 5, batch 4550, loss[loss=0.287, simple_loss=0.3463, pruned_loss=0.1139, over 4867.00 frames.], tot_loss[loss=0.2218, simple_loss=0.2987, pruned_loss=0.07245, over 1342688.04 frames.], batch size: 53, lr: 1.26e-03
2022-05-14 02:56:57,101 INFO [train.py:812] (3/8) Epoch 6, batch 0, loss[loss=0.202, simple_loss=0.2789, pruned_loss=0.06254, over 7159.00 frames.], tot_loss[loss=0.202, simple_loss=0.2789, pruned_loss=0.06254, over 7159.00 frames.], batch size: 19, lr: 1.21e-03
2022-05-14 02:57:56,829 INFO [train.py:812] (3/8) Epoch 6, batch 50, loss[loss=0.2638, simple_loss=0.3234, pruned_loss=0.1021, over 5390.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2881, pruned_loss=0.06636, over 319409.40 frames.], batch size: 52, lr: 1.21e-03
2022-05-14 02:58:56,402 INFO [train.py:812] (3/8) Epoch 6, batch 100, loss[loss=0.2015, simple_loss=0.294, pruned_loss=0.05445, over 7142.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2915, pruned_loss=0.06597, over 562526.84 frames.], batch size: 20, lr: 1.21e-03
2022-05-14 02:59:55,386 INFO [train.py:812] (3/8) Epoch 6, batch 150, loss[loss=0.2074, simple_loss=0.2914, pruned_loss=0.06169, over 6830.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2917, pruned_loss=0.06659, over 750142.26 frames.], batch size: 31, lr: 1.21e-03
2022-05-14 03:00:54,856 INFO [train.py:812] (3/8) Epoch 6, batch 200, loss[loss=0.2188, simple_loss=0.2948, pruned_loss=0.07136, over 7410.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2922, pruned_loss=0.06711, over 899810.20 frames.], batch size: 18, lr: 1.21e-03
2022-05-14 03:01:54,419 INFO [train.py:812] (3/8) Epoch 6, batch 250, loss[loss=0.2184, simple_loss=0.3019, pruned_loss=0.06746, over 7334.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2921, pruned_loss=0.06624, over 1020056.72 frames.], batch size: 22, lr: 1.21e-03
2022-05-14 03:02:54,505 INFO [train.py:812] (3/8) Epoch 6, batch 300, loss[loss=0.2015, simple_loss=0.2774, pruned_loss=0.06274, over 7252.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2891, pruned_loss=0.06499, over 1112626.94 frames.], batch size: 20, lr: 1.21e-03
2022-05-14 03:03:51,870 INFO [train.py:812] (3/8) Epoch 6, batch 350, loss[loss=0.2016, simple_loss=0.2756, pruned_loss=0.06387, over 7330.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2878, pruned_loss=0.06544, over 1185944.42 frames.], batch size: 20, lr: 1.20e-03
2022-05-14 03:04:49,931 INFO [train.py:812] (3/8) Epoch 6, batch 400, loss[loss=0.2412, simple_loss=0.3175, pruned_loss=0.08242, over 7384.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2897, pruned_loss=0.0659, over 1237075.85 frames.], batch size: 23, lr: 1.20e-03
2022-05-14 03:05:47,788 INFO [train.py:812] (3/8) Epoch 6, batch 450, loss[loss=0.1795, simple_loss=0.2485, pruned_loss=0.05523, over 6742.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2894, pruned_loss=0.06582, over 1279493.64 frames.], batch size: 15, lr: 1.20e-03
2022-05-14 03:06:47,290 INFO [train.py:812] (3/8) Epoch 6, batch 500, loss[loss=0.2589, simple_loss=0.3248, pruned_loss=0.09649, over 4926.00 frames.], tot_loss[loss=0.211, simple_loss=0.2904, pruned_loss=0.06587, over 1308574.49 frames.], batch size: 52, lr: 1.20e-03
2022-05-14 03:07:45,163 INFO [train.py:812] (3/8) Epoch 6, batch 550, loss[loss=0.2483, simple_loss=0.3306, pruned_loss=0.08307, over 6467.00 frames.], tot_loss[loss=0.2115, simple_loss=0.2908, pruned_loss=0.06613, over 1332343.54 frames.], batch size: 38, lr: 1.20e-03
2022-05-14 03:08:44,001 INFO [train.py:812] (3/8) Epoch 6, batch 600, loss[loss=0.1969, simple_loss=0.2869, pruned_loss=0.05343, over 7140.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2895, pruned_loss=0.0655, over 1352268.64 frames.], batch size: 20, lr: 1.20e-03
2022-05-14 03:09:42,692 INFO [train.py:812] (3/8) Epoch 6, batch 650, loss[loss=0.2133, simple_loss=0.2982, pruned_loss=0.06423, over 7416.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2892, pruned_loss=0.06509, over 1366798.17 frames.], batch size: 21, lr: 1.20e-03
2022-05-14 03:10:42,145 INFO [train.py:812] (3/8) Epoch 6, batch 700, loss[loss=0.2077, simple_loss=0.2839, pruned_loss=0.06571, over 7244.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2892, pruned_loss=0.06466, over 1378845.37 frames.], batch size: 16, lr: 1.20e-03
2022-05-14 03:11:41,235 INFO [train.py:812] (3/8) Epoch 6, batch 750, loss[loss=0.2549, simple_loss=0.324, pruned_loss=0.09291, over 7218.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2911, pruned_loss=0.06602, over 1388515.61 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:12:41,166 INFO [train.py:812] (3/8) Epoch 6, batch 800, loss[loss=0.2251, simple_loss=0.298, pruned_loss=0.0761, over 7219.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2905, pruned_loss=0.06538, over 1398875.18 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:13:40,483 INFO [train.py:812] (3/8) Epoch 6, batch 850, loss[loss=0.2259, simple_loss=0.2995, pruned_loss=0.07612, over 7183.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2897, pruned_loss=0.06503, over 1403858.90 frames.], batch size: 23, lr: 1.19e-03
2022-05-14 03:14:39,812 INFO [train.py:812] (3/8) Epoch 6, batch 900, loss[loss=0.211, simple_loss=0.2926, pruned_loss=0.06467, over 7404.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2894, pruned_loss=0.06449, over 1405419.46 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:15:38,565 INFO [train.py:812] (3/8) Epoch 6, batch 950, loss[loss=0.1766, simple_loss=0.2485, pruned_loss=0.05241, over 7123.00 frames.], tot_loss[loss=0.209, simple_loss=0.2892, pruned_loss=0.06434, over 1406418.79 frames.], batch size: 17, lr: 1.19e-03
2022-05-14 03:16:37,949 INFO [train.py:812] (3/8) Epoch 6, batch 1000, loss[loss=0.2127, simple_loss=0.292, pruned_loss=0.06672, over 7419.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2897, pruned_loss=0.06472, over 1408060.91 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:17:36,234 INFO [train.py:812] (3/8) Epoch 6, batch 1050, loss[loss=0.2052, simple_loss=0.2874, pruned_loss=0.06151, over 7327.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2893, pruned_loss=0.06478, over 1413052.16 frames.], batch size: 20, lr: 1.19e-03
2022-05-14 03:18:39,061 INFO [train.py:812] (3/8) Epoch 6, batch 1100, loss[loss=0.1954, simple_loss=0.2787, pruned_loss=0.05604, over 7314.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2906, pruned_loss=0.06589, over 1408623.15 frames.], batch size: 21, lr: 1.19e-03
2022-05-14 03:19:37,376 INFO [train.py:812] (3/8) Epoch 6, batch 1150, loss[loss=0.207, simple_loss=0.2947, pruned_loss=0.05962, over 7147.00 frames.], tot_loss[loss=0.211, simple_loss=0.2907, pruned_loss=0.06571, over 1413686.10 frames.], batch size: 20, lr: 1.19e-03
2022-05-14 03:20:36,642 INFO [train.py:812] (3/8) Epoch 6, batch 1200, loss[loss=0.246, simple_loss=0.3177, pruned_loss=0.08714, over 7193.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2899, pruned_loss=0.06546, over 1414486.52 frames.], batch size: 26, lr: 1.18e-03
2022-05-14 03:21:34,751 INFO [train.py:812] (3/8) Epoch 6, batch 1250, loss[loss=0.2068, simple_loss=0.2923, pruned_loss=0.06066, over 7145.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2892, pruned_loss=0.065, over 1413785.46 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:22:34,578 INFO [train.py:812] (3/8) Epoch 6, batch 1300, loss[loss=0.1876, simple_loss=0.262, pruned_loss=0.05658, over 7361.00 frames.], tot_loss[loss=0.21, simple_loss=0.2893, pruned_loss=0.06537, over 1412468.20 frames.], batch size: 19, lr: 1.18e-03
2022-05-14 03:23:33,461 INFO [train.py:812] (3/8) Epoch 6, batch 1350, loss[loss=0.2206, simple_loss=0.3005, pruned_loss=0.07038, over 7105.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2885, pruned_loss=0.06529, over 1415747.34 frames.], batch size: 28, lr: 1.18e-03
2022-05-14 03:24:32,547 INFO [train.py:812] (3/8) Epoch 6, batch 1400, loss[loss=0.2278, simple_loss=0.3001, pruned_loss=0.07774, over 7342.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2886, pruned_loss=0.06516, over 1419902.31 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:25:31,685 INFO [train.py:812] (3/8) Epoch 6, batch 1450, loss[loss=0.1833, simple_loss=0.276, pruned_loss=0.0453, over 7427.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2881, pruned_loss=0.06423, over 1420771.79 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:26:31,145 INFO [train.py:812] (3/8) Epoch 6, batch 1500, loss[loss=0.2208, simple_loss=0.3175, pruned_loss=0.06201, over 7144.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2885, pruned_loss=0.06452, over 1422079.09 frames.], batch size: 20, lr: 1.18e-03
2022-05-14 03:27:30,164 INFO [train.py:812] (3/8) Epoch 6, batch 1550, loss[loss=0.1866, simple_loss=0.2624, pruned_loss=0.05545, over 7284.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2887, pruned_loss=0.06495, over 1423644.38 frames.], batch size: 17, lr: 1.18e-03
2022-05-14 03:28:29,752 INFO [train.py:812] (3/8) Epoch 6, batch 1600, loss[loss=0.2311, simple_loss=0.2978, pruned_loss=0.08219, over 7418.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2881, pruned_loss=0.06455, over 1416123.84 frames.], batch size: 20, lr: 1.17e-03
2022-05-14 03:29:29,243 INFO [train.py:812] (3/8) Epoch 6, batch 1650, loss[loss=0.2167, simple_loss=0.3096, pruned_loss=0.06185, over 7295.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2878, pruned_loss=0.0643, over 1415498.06 frames.], batch size: 25, lr: 1.17e-03
2022-05-14 03:30:27,829 INFO [train.py:812] (3/8) Epoch 6, batch 1700, loss[loss=0.2246, simple_loss=0.3096, pruned_loss=0.06979, over 7209.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2882, pruned_loss=0.0647, over 1412836.38 frames.], batch size: 22, lr: 1.17e-03
2022-05-14 03:31:26,904 INFO [train.py:812] (3/8) Epoch 6, batch 1750, loss[loss=0.1914, simple_loss=0.2642, pruned_loss=0.05937, over 7263.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2888, pruned_loss=0.06515, over 1409557.81 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:32:26,449 INFO [train.py:812] (3/8) Epoch 6, batch 1800, loss[loss=0.2609, simple_loss=0.3181, pruned_loss=0.1018, over 5229.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2885, pruned_loss=0.06465, over 1411476.35 frames.], batch size: 53, lr: 1.17e-03
2022-05-14 03:33:25,531 INFO [train.py:812] (3/8) Epoch 6, batch 1850, loss[loss=0.1594, simple_loss=0.2488, pruned_loss=0.035, over 7152.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2878, pruned_loss=0.06423, over 1415392.22 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:34:24,878 INFO [train.py:812] (3/8) Epoch 6, batch 1900, loss[loss=0.202, simple_loss=0.2732, pruned_loss=0.06546, over 7135.00 frames.], tot_loss[loss=0.208, simple_loss=0.2877, pruned_loss=0.06411, over 1414380.01 frames.], batch size: 17, lr: 1.17e-03
2022-05-14 03:35:23,960 INFO [train.py:812] (3/8) Epoch 6, batch 1950, loss[loss=0.1842, simple_loss=0.2708, pruned_loss=0.04879, over 7116.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2879, pruned_loss=0.06365, over 1419652.80 frames.], batch size: 21, lr: 1.17e-03
2022-05-14 03:36:21,520 INFO [train.py:812] (3/8) Epoch 6, batch 2000, loss[loss=0.1897, simple_loss=0.2593, pruned_loss=0.06007, over 7257.00 frames.], tot_loss[loss=0.208, simple_loss=0.2881, pruned_loss=0.06394, over 1423275.66 frames.], batch size: 18, lr: 1.17e-03
2022-05-14 03:37:19,515 INFO [train.py:812] (3/8) Epoch 6, batch 2050, loss[loss=0.207, simple_loss=0.2938, pruned_loss=0.06009, over 7100.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2884, pruned_loss=0.0637, over 1423104.14 frames.], batch size: 28, lr: 1.16e-03
2022-05-14 03:38:19,418 INFO [train.py:812] (3/8) Epoch 6, batch 2100, loss[loss=0.2296, simple_loss=0.3067, pruned_loss=0.07626, over 6504.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2881, pruned_loss=0.06354, over 1424751.19 frames.], batch size: 37, lr: 1.16e-03
2022-05-14 03:39:19,055 INFO [train.py:812] (3/8) Epoch 6, batch 2150, loss[loss=0.2119, simple_loss=0.2968, pruned_loss=0.06343, over 7144.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2875, pruned_loss=0.0631, over 1429939.60 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:40:18,670 INFO [train.py:812] (3/8) Epoch 6, batch 2200, loss[loss=0.2203, simple_loss=0.3094, pruned_loss=0.06555, over 7141.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2874, pruned_loss=0.06297, over 1426532.41 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:41:17,657 INFO [train.py:812] (3/8) Epoch 6, batch 2250, loss[loss=0.2039, simple_loss=0.2847, pruned_loss=0.06153, over 7352.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2872, pruned_loss=0.06326, over 1424673.71 frames.], batch size: 19, lr: 1.16e-03
2022-05-14 03:42:16,655 INFO [train.py:812] (3/8) Epoch 6, batch 2300, loss[loss=0.1904, simple_loss=0.2718, pruned_loss=0.05447, over 7304.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2873, pruned_loss=0.06352, over 1421730.37 frames.], batch size: 24, lr: 1.16e-03
2022-05-14 03:43:15,897 INFO [train.py:812] (3/8) Epoch 6, batch 2350, loss[loss=0.2184, simple_loss=0.3102, pruned_loss=0.06328, over 7214.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2868, pruned_loss=0.06348, over 1421508.20 frames.], batch size: 21, lr: 1.16e-03
2022-05-14 03:44:15,942 INFO [train.py:812] (3/8) Epoch 6, batch 2400, loss[loss=0.2218, simple_loss=0.3076, pruned_loss=0.06797, over 7330.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2862, pruned_loss=0.06341, over 1422548.72 frames.], batch size: 20, lr: 1.16e-03
2022-05-14 03:45:14,485 INFO [train.py:812] (3/8) Epoch 6, batch 2450, loss[loss=0.2043, simple_loss=0.2758, pruned_loss=0.06637, over 7245.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2858, pruned_loss=0.06359, over 1422962.87 frames.], batch size: 16, lr: 1.16e-03
2022-05-14 03:46:13,721 INFO [train.py:812] (3/8) Epoch 6, batch 2500, loss[loss=0.2189, simple_loss=0.3145, pruned_loss=0.06165, over 7318.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2863, pruned_loss=0.06373, over 1422096.22 frames.], batch size: 22, lr: 1.15e-03
2022-05-14 03:47:11,214 INFO [train.py:812] (3/8) Epoch 6, batch 2550, loss[loss=0.2106, simple_loss=0.2918, pruned_loss=0.06474, over 6924.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2862, pruned_loss=0.06349, over 1423501.31 frames.], batch size: 15, lr: 1.15e-03
2022-05-14 03:48:09,669 INFO [train.py:812] (3/8) Epoch 6, batch 2600, loss[loss=0.1849, simple_loss=0.28, pruned_loss=0.04488, over 7316.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2862, pruned_loss=0.0632, over 1425884.88 frames.], batch size: 21, lr: 1.15e-03
2022-05-14 03:49:08,324 INFO [train.py:812] (3/8) Epoch 6, batch 2650, loss[loss=0.2275, simple_loss=0.3208, pruned_loss=0.06708, over 7256.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2875, pruned_loss=0.06339, over 1423993.62 frames.], batch size: 25, lr: 1.15e-03
2022-05-14 03:50:08,411 INFO [train.py:812] (3/8) Epoch 6, batch 2700, loss[loss=0.2172, simple_loss=0.2857, pruned_loss=0.07438, over 6833.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2873, pruned_loss=0.06278, over 1426345.81 frames.], batch size: 15, lr: 1.15e-03
2022-05-14 03:51:06,471 INFO [train.py:812] (3/8) Epoch 6, batch 2750, loss[loss=0.2368, simple_loss=0.3196, pruned_loss=0.07701, over 7241.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2878, pruned_loss=0.06286, over 1424056.77 frames.], batch size: 20, lr: 1.15e-03
2022-05-14 03:52:05,463 INFO [train.py:812] (3/8) Epoch 6, batch 2800, loss[loss=0.1943, simple_loss=0.2818, pruned_loss=0.05336, over 7275.00 frames.], tot_loss[loss=0.2074, simple_loss=0.288, pruned_loss=0.06342, over 1421933.66 frames.], batch size: 18, lr: 1.15e-03
2022-05-14 03:53:03,381 INFO [train.py:812] (3/8) Epoch 6, batch 2850, loss[loss=0.1769, simple_loss=0.2537, pruned_loss=0.05004, over 7287.00 frames.], tot_loss[loss=0.2074, simple_loss=0.288, pruned_loss=0.06337, over 1419142.59 frames.], batch size: 17, lr: 1.15e-03
2022-05-14 03:54:00,909 INFO [train.py:812] (3/8) Epoch 6, batch 2900, loss[loss=0.2149, simple_loss=0.2997, pruned_loss=0.06505, over 6741.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2876, pruned_loss=0.06302, over 1419958.58 frames.], batch size: 31, lr: 1.15e-03
2022-05-14 03:54:58,718 INFO [train.py:812] (3/8) Epoch 6, batch 2950, loss[loss=0.226, simple_loss=0.3213, pruned_loss=0.06538, over 7140.00 frames.], tot_loss[loss=0.2057, simple_loss=0.287, pruned_loss=0.06223, over 1419826.37 frames.], batch size: 20, lr: 1.14e-03
2022-05-14 03:55:55,710 INFO [train.py:812] (3/8) Epoch 6, batch 3000, loss[loss=0.1861, simple_loss=0.2712, pruned_loss=0.0505, over 7242.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2869, pruned_loss=0.06241, over 1420074.66 frames.], batch size: 20, lr: 1.14e-03
2022-05-14 03:55:55,711 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 03:56:03,338 INFO [train.py:841] (3/8) Epoch 6, validation: loss=0.1668, simple_loss=0.2696, pruned_loss=0.03205, over 698248.00 frames.
2022-05-14 03:57:02,144 INFO [train.py:812] (3/8) Epoch 6, batch 3050, loss[loss=0.2123, simple_loss=0.2957, pruned_loss=0.06445, over 7194.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2863, pruned_loss=0.06222, over 1426243.22 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 03:58:01,682 INFO [train.py:812] (3/8) Epoch 6, batch 3100, loss[loss=0.2416, simple_loss=0.3051, pruned_loss=0.08908, over 7335.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2858, pruned_loss=0.0629, over 1423998.86 frames.], batch size: 22, lr: 1.14e-03
2022-05-14 03:58:58,837 INFO [train.py:812] (3/8) Epoch 6, batch 3150, loss[loss=0.2233, simple_loss=0.3075, pruned_loss=0.0696, over 7203.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2862, pruned_loss=0.06257, over 1424261.99 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 03:59:57,535 INFO [train.py:812] (3/8) Epoch 6, batch 3200, loss[loss=0.2059, simple_loss=0.2949, pruned_loss=0.0585, over 7223.00 frames.], tot_loss[loss=0.206, simple_loss=0.2865, pruned_loss=0.06277, over 1425500.81 frames.], batch size: 21, lr: 1.14e-03
2022-05-14 04:00:56,301 INFO [train.py:812] (3/8) Epoch 6, batch 3250, loss[loss=0.2133, simple_loss=0.2848, pruned_loss=0.07092, over 7362.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2871, pruned_loss=0.06322, over 1425071.95 frames.], batch size: 19, lr: 1.14e-03
2022-05-14 04:01:55,490 INFO [train.py:812] (3/8) Epoch 6, batch 3300, loss[loss=0.2856, simple_loss=0.3427, pruned_loss=0.1142, over 7196.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2877, pruned_loss=0.06369, over 1420590.20 frames.], batch size: 23, lr: 1.14e-03
2022-05-14 04:02:54,521 INFO [train.py:812] (3/8) Epoch 6, batch 3350, loss[loss=0.182, simple_loss=0.2697, pruned_loss=0.04712, over 7259.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2868, pruned_loss=0.06332, over 1425112.84 frames.], batch size: 19, lr: 1.14e-03
2022-05-14 04:03:53,902 INFO [train.py:812] (3/8) Epoch 6, batch 3400, loss[loss=0.204, simple_loss=0.2983, pruned_loss=0.05487, over 7294.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2867, pruned_loss=0.06305, over 1425115.90 frames.], batch size: 24, lr: 1.14e-03
2022-05-14 04:04:52,389 INFO [train.py:812] (3/8) Epoch 6, batch 3450, loss[loss=0.236, simple_loss=0.3188, pruned_loss=0.0766, over 7423.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2878, pruned_loss=0.06319, over 1427431.02 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:05:50,776 INFO [train.py:812] (3/8) Epoch 6, batch 3500, loss[loss=0.2154, simple_loss=0.2948, pruned_loss=0.06803, over 7196.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2867, pruned_loss=0.06297, over 1424010.56 frames.], batch size: 22, lr: 1.13e-03
2022-05-14 04:06:49,099 INFO [train.py:812] (3/8) Epoch 6, batch 3550, loss[loss=0.2195, simple_loss=0.2943, pruned_loss=0.07231, over 7322.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2861, pruned_loss=0.06278, over 1426926.50 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:07:47,613 INFO [train.py:812] (3/8) Epoch 6, batch 3600, loss[loss=0.1883, simple_loss=0.2674, pruned_loss=0.05458, over 7178.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2851, pruned_loss=0.06216, over 1428014.36 frames.], batch size: 18, lr: 1.13e-03
2022-05-14 04:08:46,801 INFO [train.py:812] (3/8) Epoch 6, batch 3650, loss[loss=0.1682, simple_loss=0.2592, pruned_loss=0.03857, over 7417.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2847, pruned_loss=0.06202, over 1426720.54 frames.], batch size: 21, lr: 1.13e-03
2022-05-14 04:09:44,219 INFO [train.py:812] (3/8) Epoch 6, batch 3700, loss[loss=0.1907, simple_loss=0.2781, pruned_loss=0.0516, over 7242.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2854, pruned_loss=0.06211, over 1424810.84 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:10:41,350 INFO [train.py:812] (3/8) Epoch 6, batch 3750, loss[loss=0.2198, simple_loss=0.2978, pruned_loss=0.07085, over 7383.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2852, pruned_loss=0.0621, over 1423674.49 frames.], batch size: 23, lr: 1.13e-03
2022-05-14 04:11:40,658 INFO [train.py:812] (3/8) Epoch 6, batch 3800, loss[loss=0.2262, simple_loss=0.3126, pruned_loss=0.06984, over 7230.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2852, pruned_loss=0.06236, over 1420121.15 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:12:39,822 INFO [train.py:812] (3/8) Epoch 6, batch 3850, loss[loss=0.1949, simple_loss=0.2843, pruned_loss=0.05278, over 7434.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2864, pruned_loss=0.06297, over 1420883.75 frames.], batch size: 20, lr: 1.13e-03
2022-05-14 04:13:39,005 INFO [train.py:812] (3/8) Epoch 6, batch 3900, loss[loss=0.1615, simple_loss=0.2352, pruned_loss=0.04386, over 7405.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2861, pruned_loss=0.06278, over 1425236.06 frames.], batch size: 18, lr: 1.13e-03
2022-05-14 04:14:38,338 INFO [train.py:812] (3/8) Epoch 6, batch 3950, loss[loss=0.191, simple_loss=0.2797, pruned_loss=0.0511, over 7318.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2841, pruned_loss=0.06167, over 1425123.90 frames.], batch size: 24, lr: 1.12e-03
2022-05-14 04:15:37,073 INFO [train.py:812] (3/8) Epoch 6, batch 4000, loss[loss=0.2322, simple_loss=0.3181, pruned_loss=0.07313, over 7217.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2849, pruned_loss=0.0619, over 1427337.98 frames.], batch size: 23, lr: 1.12e-03
2022-05-14 04:16:34,892 INFO [train.py:812] (3/8) Epoch 6, batch 4050, loss[loss=0.2329, simple_loss=0.327, pruned_loss=0.06941, over 7295.00 frames.], tot_loss[loss=0.2045, simple_loss=0.285, pruned_loss=0.06204, over 1428195.39 frames.], batch size: 24, lr: 1.12e-03
2022-05-14 04:17:34,623 INFO [train.py:812] (3/8) Epoch 6, batch 4100, loss[loss=0.2072, simple_loss=0.2737, pruned_loss=0.07035, over 7419.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2842, pruned_loss=0.06212, over 1427763.10 frames.], batch size: 18, lr: 1.12e-03
2022-05-14 04:18:33,849 INFO [train.py:812] (3/8) Epoch 6, batch 4150, loss[loss=0.2227, simple_loss=0.3152, pruned_loss=0.06504, over 6783.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2834, pruned_loss=0.06152, over 1427251.51 frames.], batch size: 31, lr: 1.12e-03
2022-05-14 04:19:32,909 INFO [train.py:812] (3/8) Epoch 6, batch 4200, loss[loss=0.1973, simple_loss=0.2963, pruned_loss=0.04918, over 7123.00 frames.], tot_loss[loss=0.2018, simple_loss=0.282, pruned_loss=0.06083, over 1429563.69 frames.], batch size: 21, lr: 1.12e-03
2022-05-14 04:20:33,098 INFO [train.py:812] (3/8) Epoch 6, batch 4250, loss[loss=0.2275, simple_loss=0.3075, pruned_loss=0.07378, over 7378.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2819, pruned_loss=0.06076, over 1430213.47 frames.], batch size: 23, lr: 1.12e-03
2022-05-14 04:21:32,390 INFO [train.py:812] (3/8) Epoch 6, batch 4300, loss[loss=0.2047, simple_loss=0.2769, pruned_loss=0.06627, over 7056.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2828, pruned_loss=0.06152, over 1424919.49 frames.], batch size: 18, lr: 1.12e-03
2022-05-14 04:22:31,726 INFO [train.py:812] (3/8) Epoch 6, batch 4350, loss[loss=0.2173, simple_loss=0.2989, pruned_loss=0.06778, over 7208.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2823, pruned_loss=0.06119, over 1424554.25 frames.], batch size: 21, lr: 1.12e-03
2022-05-14 04:23:31,429 INFO [train.py:812] (3/8) Epoch 6, batch 4400, loss[loss=0.2089, simple_loss=0.2878, pruned_loss=0.06495, over 7434.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2823, pruned_loss=0.06162, over 1422119.60 frames.], batch size: 20, lr: 1.12e-03
2022-05-14 04:24:30,564 INFO [train.py:812] (3/8) Epoch 6, batch 4450, loss[loss=0.1669, simple_loss=0.243, pruned_loss=0.04533, over 7269.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2829, pruned_loss=0.0624, over 1408887.89 frames.], batch size: 17, lr: 1.11e-03
2022-05-14 04:25:38,635 INFO [train.py:812] (3/8) Epoch 6, batch 4500, loss[loss=0.2143, simple_loss=0.3035, pruned_loss=0.06259, over 7234.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2813, pruned_loss=0.06209, over 1408174.23 frames.], batch size: 20, lr: 1.11e-03
2022-05-14 04:26:36,499 INFO [train.py:812] (3/8) Epoch 6, batch 4550, loss[loss=0.2746, simple_loss=0.3398, pruned_loss=0.1047, over 4971.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2844, pruned_loss=0.06462, over 1358900.20 frames.], batch size: 52, lr: 1.11e-03
2022-05-14 04:27:44,578 INFO [train.py:812] (3/8) Epoch 7, batch 0, loss[loss=0.2054, simple_loss=0.2778, pruned_loss=0.06654, over 7411.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2778, pruned_loss=0.06654, over 7411.00 frames.], batch size: 18, lr: 1.07e-03
2022-05-14 04:28:43,245 INFO [train.py:812] (3/8) Epoch 7, batch 50, loss[loss=0.1699, simple_loss=0.2493, pruned_loss=0.04526, over 7407.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2825, pruned_loss=0.06128, over 322484.23 frames.], batch size: 18, lr: 1.07e-03
2022-05-14 04:29:42,452 INFO [train.py:812] (3/8) Epoch 7, batch 100, loss[loss=0.1771, simple_loss=0.2621, pruned_loss=0.04608, over 7151.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2823, pruned_loss=0.06038, over 567527.01 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:30:41,785 INFO [train.py:812] (3/8) Epoch 7, batch 150, loss[loss=0.2068, simple_loss=0.276, pruned_loss=0.06876, over 7143.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2838, pruned_loss=0.06147, over 756775.45 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:31:41,616 INFO [train.py:812] (3/8) Epoch 7, batch 200, loss[loss=0.2363, simple_loss=0.3089, pruned_loss=0.08183, over 7368.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2852, pruned_loss=0.06194, over 905510.79 frames.], batch size: 23, lr: 1.06e-03
2022-05-14 04:32:39,928 INFO [train.py:812] (3/8) Epoch 7, batch 250, loss[loss=0.2235, simple_loss=0.3005, pruned_loss=0.07327, over 7146.00 frames.], tot_loss[loss=0.205, simple_loss=0.2857, pruned_loss=0.06215, over 1019818.21 frames.], batch size: 20, lr: 1.06e-03
2022-05-14 04:33:39,349 INFO [train.py:812] (3/8) Epoch 7, batch 300, loss[loss=0.1639, simple_loss=0.233, pruned_loss=0.0474, over 6810.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2861, pruned_loss=0.06222, over 1105336.52 frames.], batch size: 15, lr: 1.06e-03
2022-05-14 04:34:57,041 INFO [train.py:812] (3/8) Epoch 7, batch 350, loss[loss=0.2031, simple_loss=0.2835, pruned_loss=0.06133, over 7119.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2845, pruned_loss=0.06109, over 1176099.63 frames.], batch size: 21, lr: 1.06e-03
2022-05-14 04:35:53,852 INFO [train.py:812] (3/8) Epoch 7, batch 400, loss[loss=0.1691, simple_loss=0.2529, pruned_loss=0.04263, over 7169.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2855, pruned_loss=0.06099, over 1228714.95 frames.], batch size: 18, lr: 1.06e-03
2022-05-14 04:37:20,597 INFO [train.py:812] (3/8) Epoch 7, batch 450, loss[loss=0.2038, simple_loss=0.2959, pruned_loss=0.0559, over 7350.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2852, pruned_loss=0.06133, over 1274356.42 frames.], batch size: 19, lr: 1.06e-03
2022-05-14 04:38:43,156 INFO [train.py:812] (3/8) Epoch 7, batch 500, loss[loss=0.2218, simple_loss=0.3015, pruned_loss=0.07109, over 6410.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2861, pruned_loss=0.06221, over 1303847.66 frames.], batch size: 38, lr: 1.06e-03
2022-05-14 04:39:42,045 INFO [train.py:812] (3/8) Epoch 7, batch 550, loss[loss=0.2128, simple_loss=0.295, pruned_loss=0.06525, over 7120.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2851, pruned_loss=0.06162, over 1329005.27 frames.], batch size: 21, lr: 1.06e-03
2022-05-14 04:40:39,502 INFO [train.py:812] (3/8) Epoch 7, batch 600, loss[loss=0.2087, simple_loss=0.2901, pruned_loss=0.06365, over 7084.00 frames.], tot_loss[loss=0.204, simple_loss=0.2852, pruned_loss=0.06139, over 1347867.23 frames.], batch size: 28, lr: 1.06e-03
2022-05-14 04:41:38,880 INFO [train.py:812] (3/8) Epoch 7, batch 650, loss[loss=0.2434, simple_loss=0.3063, pruned_loss=0.09026, over 5092.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2833, pruned_loss=0.06069, over 1364662.76 frames.], batch size: 53, lr: 1.05e-03
2022-05-14 04:42:37,554 INFO [train.py:812] (3/8) Epoch 7, batch 700, loss[loss=0.1905, simple_loss=0.2748, pruned_loss=0.05315, over 7176.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2825, pruned_loss=0.06017, over 1379718.38 frames.], batch size: 18, lr: 1.05e-03
2022-05-14 04:43:36,173 INFO [train.py:812] (3/8) Epoch 7, batch 750, loss[loss=0.1993, simple_loss=0.2915, pruned_loss=0.05361, over 6894.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2815, pruned_loss=0.05941, over 1392253.94 frames.], batch size: 31, lr: 1.05e-03
2022-05-14 04:44:33,652 INFO [train.py:812] (3/8) Epoch 7, batch 800, loss[loss=0.2155, simple_loss=0.305, pruned_loss=0.06304, over 7339.00 frames.], tot_loss[loss=0.199, simple_loss=0.2806, pruned_loss=0.05876, over 1392106.89 frames.], batch size: 20, lr: 1.05e-03
2022-05-14 04:45:32,926 INFO [train.py:812] (3/8) Epoch 7, batch 850, loss[loss=0.2221, simple_loss=0.3023, pruned_loss=0.07098, over 7272.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2806, pruned_loss=0.05895, over 1398590.68 frames.], batch size: 24, lr: 1.05e-03
2022-05-14 04:46:32,282 INFO [train.py:812] (3/8) Epoch 7, batch 900, loss[loss=0.2456, simple_loss=0.3223, pruned_loss=0.08444, over 7379.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2818, pruned_loss=0.05958, over 1404096.87 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:47:31,108 INFO [train.py:812] (3/8) Epoch 7, batch 950, loss[loss=0.2175, simple_loss=0.2994, pruned_loss=0.06782, over 7377.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2827, pruned_loss=0.05957, over 1408673.17 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:48:29,682 INFO [train.py:812] (3/8) Epoch 7, batch 1000, loss[loss=0.2123, simple_loss=0.2948, pruned_loss=0.06485, over 7384.00 frames.], tot_loss[loss=0.202, simple_loss=0.2831, pruned_loss=0.06045, over 1408615.57 frames.], batch size: 23, lr: 1.05e-03
2022-05-14 04:49:29,209 INFO [train.py:812] (3/8) Epoch 7, batch 1050, loss[loss=0.2242, simple_loss=0.2953, pruned_loss=0.07652, over 7169.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2834, pruned_loss=0.06043, over 1415101.83 frames.], batch size: 19, lr: 1.05e-03
2022-05-14 04:50:29,134 INFO [train.py:812] (3/8) Epoch 7, batch 1100, loss[loss=0.2229, simple_loss=0.3136, pruned_loss=0.06607, over 7287.00 frames.], tot_loss[loss=0.2016, simple_loss=0.283, pruned_loss=0.06006, over 1418849.86 frames.], batch size: 25, lr: 1.05e-03
2022-05-14 04:51:28,452 INFO [train.py:812] (3/8) Epoch 7, batch 1150, loss[loss=0.1681, simple_loss=0.2553, pruned_loss=0.04048, over 7133.00 frames.], tot_loss[loss=0.201, simple_loss=0.2829, pruned_loss=0.05956, over 1416990.86 frames.], batch size: 17, lr: 1.05e-03
2022-05-14 04:52:28,362 INFO [train.py:812] (3/8) Epoch 7, batch 1200, loss[loss=0.1631, simple_loss=0.2389, pruned_loss=0.0436, over 7276.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2835, pruned_loss=0.06008, over 1413064.51 frames.], batch size: 16, lr: 1.04e-03
2022-05-14 04:53:27,878 INFO [train.py:812] (3/8) Epoch 7, batch 1250, loss[loss=0.1769, simple_loss=0.2727, pruned_loss=0.04051, over 7236.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06019, over 1414784.92 frames.], batch size: 20, lr: 1.04e-03
2022-05-14 04:54:25,609 INFO [train.py:812] (3/8) Epoch 7, batch 1300, loss[loss=0.1612, simple_loss=0.2411, pruned_loss=0.04068, over 7286.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2824, pruned_loss=0.06039, over 1416862.28 frames.], batch size: 17, lr: 1.04e-03
2022-05-14 04:55:24,135 INFO [train.py:812] (3/8) Epoch 7, batch 1350, loss[loss=0.2062, simple_loss=0.2832, pruned_loss=0.0646, over 7420.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2825, pruned_loss=0.06021, over 1422395.80 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 04:56:22,882 INFO [train.py:812] (3/8) Epoch 7, batch 1400, loss[loss=0.2086, simple_loss=0.29, pruned_loss=0.06354, over 7150.00 frames.], tot_loss[loss=0.202, simple_loss=0.2833, pruned_loss=0.06033, over 1420337.53 frames.], batch size: 19, lr: 1.04e-03
2022-05-14 04:57:22,030 INFO [train.py:812] (3/8) Epoch 7, batch 1450, loss[loss=0.187, simple_loss=0.2789, pruned_loss=0.04755, over 6783.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2842, pruned_loss=0.06052, over 1419867.53 frames.], batch size: 31, lr: 1.04e-03
2022-05-14 04:58:20,152 INFO [train.py:812] (3/8) Epoch 7, batch 1500, loss[loss=0.234, simple_loss=0.3083, pruned_loss=0.07989, over 7416.00 frames.], tot_loss[loss=0.2016, simple_loss=0.284, pruned_loss=0.05967, over 1422805.55 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 04:59:18,876 INFO [train.py:812] (3/8) Epoch 7, batch 1550, loss[loss=0.2703, simple_loss=0.3347, pruned_loss=0.1029, over 7153.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2827, pruned_loss=0.05934, over 1417831.94 frames.], batch size: 26, lr: 1.04e-03
2022-05-14 05:00:18,912 INFO [train.py:812] (3/8) Epoch 7, batch 1600, loss[loss=0.2186, simple_loss=0.3091, pruned_loss=0.06407, over 7123.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2826, pruned_loss=0.05935, over 1424094.47 frames.], batch size: 21, lr: 1.04e-03
2022-05-14 05:01:18,241 INFO [train.py:812] (3/8) Epoch 7, batch 1650, loss[loss=0.1931, simple_loss=0.2763, pruned_loss=0.05492, over 7062.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2821, pruned_loss=0.05933, over 1417701.04 frames.], batch size: 18, lr: 1.04e-03
2022-05-14 05:02:16,813 INFO [train.py:812] (3/8) Epoch 7, batch 1700, loss[loss=0.1962, simple_loss=0.2868, pruned_loss=0.05279, over 7209.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2814, pruned_loss=0.05949, over 1417014.76 frames.], batch size: 22, lr: 1.04e-03
2022-05-14 05:03:15,979 INFO [train.py:812] (3/8) Epoch 7, batch 1750, loss[loss=0.1985, simple_loss=0.2892, pruned_loss=0.05386, over 7337.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2816, pruned_loss=0.05985, over 1412083.35 frames.], batch size: 22, lr: 1.04e-03
2022-05-14 05:04:14,635 INFO [train.py:812] (3/8) Epoch 7, batch 1800, loss[loss=0.1915, simple_loss=0.2744, pruned_loss=0.05431, over 7251.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2827, pruned_loss=0.06016, over 1414722.04 frames.], batch size: 25, lr: 1.03e-03
2022-05-14 05:05:13,133 INFO [train.py:812] (3/8) Epoch 7, batch 1850, loss[loss=0.1617, simple_loss=0.2451, pruned_loss=0.03916, over 6999.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2814, pruned_loss=0.05963, over 1416870.31 frames.], batch size: 16, lr: 1.03e-03
2022-05-14 05:06:10,509 INFO [train.py:812] (3/8) Epoch 7, batch 1900, loss[loss=0.217, simple_loss=0.2926, pruned_loss=0.07073, over 7075.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2822, pruned_loss=0.06009, over 1413986.50 frames.], batch size: 18, lr: 1.03e-03
2022-05-14 05:07:08,676 INFO [train.py:812] (3/8) Epoch 7, batch 1950, loss[loss=0.1975, simple_loss=0.274, pruned_loss=0.06049, over 7272.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2811, pruned_loss=0.05993, over 1416859.38 frames.], batch size: 18, lr: 1.03e-03
2022-05-14 05:08:07,324 INFO [train.py:812] (3/8) Epoch 7, batch 2000, loss[loss=0.2394, simple_loss=0.317, pruned_loss=0.08084, over 7328.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2816, pruned_loss=0.06051, over 1417139.16 frames.], batch size: 25, lr: 1.03e-03
2022-05-14 05:09:04,290 INFO [train.py:812] (3/8) Epoch 7, batch 2050, loss[loss=0.1961, simple_loss=0.2818, pruned_loss=0.05521, over 7270.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2827, pruned_loss=0.06121, over 1414930.25 frames.], batch size: 24, lr: 1.03e-03
2022-05-14 05:10:01,680 INFO [train.py:812] (3/8) Epoch 7, batch 2100, loss[loss=0.1733, simple_loss=0.2548, pruned_loss=0.04588, over 7011.00 frames.], tot_loss[loss=0.2018, simple_loss=0.282, pruned_loss=0.06081, over 1418261.81 frames.], batch size: 16, lr: 1.03e-03
2022-05-14 05:11:00,089 INFO [train.py:812] (3/8) Epoch 7, batch 2150, loss[loss=0.1874, simple_loss=0.2895, pruned_loss=0.04263, over 7407.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2821, pruned_loss=0.06008, over 1423738.95 frames.], batch size: 21, lr: 1.03e-03
2022-05-14 05:11:57,907 INFO [train.py:812] (3/8) Epoch 7, batch 2200, loss[loss=0.1625, simple_loss=0.2474, pruned_loss=0.03882, over 7134.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2818, pruned_loss=0.05987, over 1422097.25 frames.], batch size: 17, lr: 1.03e-03
2022-05-14 05:12:56,738 INFO [train.py:812] (3/8) Epoch 7, batch 2250, loss[loss=0.2108, simple_loss=0.2771, pruned_loss=0.07221, over 7280.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2817, pruned_loss=0.05994, over 1416065.24 frames.], batch size: 17, lr: 1.03e-03
2022-05-14 05:13:54,317 INFO [train.py:812] (3/8) Epoch 7, batch 2300, loss[loss=0.2166, simple_loss=0.2901, pruned_loss=0.0716, over 7197.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2813, pruned_loss=0.05966, over 1419019.34 frames.], batch size: 23, lr: 1.03e-03
2022-05-14 05:14:53,745 INFO [train.py:812] (3/8) Epoch 7, batch 2350, loss[loss=0.2376, simple_loss=0.3172, pruned_loss=0.07896, over 7415.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2817, pruned_loss=0.05978, over 1418203.24 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:15:53,760 INFO [train.py:812] (3/8) Epoch 7, batch 2400, loss[loss=0.1802, simple_loss=0.2585, pruned_loss=0.05094, over 7275.00 frames.], tot_loss[loss=0.2, simple_loss=0.2811, pruned_loss=0.05943, over 1421715.37 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:16:51,042 INFO [train.py:812] (3/8) Epoch 7, batch 2450, loss[loss=0.2144, simple_loss=0.2985, pruned_loss=0.06514, over 7421.00 frames.], tot_loss[loss=0.2013, simple_loss=0.282, pruned_loss=0.06029, over 1417968.10 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:17:49,489 INFO [train.py:812] (3/8) Epoch 7, batch 2500, loss[loss=0.2183, simple_loss=0.306, pruned_loss=0.06529, over 7331.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2827, pruned_loss=0.06026, over 1417922.49 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:18:48,409 INFO [train.py:812] (3/8) Epoch 7, batch 2550, loss[loss=0.2061, simple_loss=0.2757, pruned_loss=0.06821, over 7429.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2823, pruned_loss=0.05966, over 1424258.73 frames.], batch size: 20, lr: 1.02e-03
2022-05-14 05:19:47,254 INFO [train.py:812] (3/8) Epoch 7, batch 2600, loss[loss=0.1837, simple_loss=0.2717, pruned_loss=0.0478, over 7166.00 frames.], tot_loss[loss=0.2006, simple_loss=0.2821, pruned_loss=0.05953, over 1418627.83 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:20:45,572 INFO [train.py:812] (3/8) Epoch 7, batch 2650, loss[loss=0.2133, simple_loss=0.2791, pruned_loss=0.07378, over 7169.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2819, pruned_loss=0.05987, over 1417792.43 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:21:44,764 INFO [train.py:812] (3/8) Epoch 7, batch 2700, loss[loss=0.1802, simple_loss=0.2545, pruned_loss=0.05295, over 6784.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2821, pruned_loss=0.05973, over 1419324.67 frames.], batch size: 15, lr: 1.02e-03
2022-05-14 05:22:44,404 INFO [train.py:812] (3/8) Epoch 7, batch 2750, loss[loss=0.1714, simple_loss=0.2503, pruned_loss=0.04624, over 7404.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2822, pruned_loss=0.05968, over 1420077.56 frames.], batch size: 18, lr: 1.02e-03
2022-05-14 05:23:44,349 INFO [train.py:812] (3/8) Epoch 7, batch 2800, loss[loss=0.1593, simple_loss=0.2313, pruned_loss=0.04361, over 6998.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2811, pruned_loss=0.05917, over 1418249.09 frames.], batch size: 16, lr: 1.02e-03
2022-05-14 05:24:43,860 INFO [train.py:812] (3/8) Epoch 7, batch 2850, loss[loss=0.2055, simple_loss=0.2936, pruned_loss=0.05866, over 7316.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2799, pruned_loss=0.05853, over 1423210.24 frames.], batch size: 21, lr: 1.02e-03
2022-05-14 05:25:43,746 INFO [train.py:812] (3/8) Epoch 7, batch 2900, loss[loss=0.2515, simple_loss=0.3187, pruned_loss=0.09212, over 4715.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2795, pruned_loss=0.05786, over 1425139.96 frames.], batch size: 52, lr: 1.02e-03
2022-05-14 05:26:42,756 INFO [train.py:812] (3/8) Epoch 7, batch 2950, loss[loss=0.1927, simple_loss=0.2857, pruned_loss=0.04982, over 7311.00 frames.], tot_loss[loss=0.199, simple_loss=0.2812, pruned_loss=0.0584, over 1425626.68 frames.], batch size: 25, lr: 1.01e-03
2022-05-14 05:27:42,379 INFO [train.py:812] (3/8) Epoch 7, batch 3000, loss[loss=0.2462, simple_loss=0.3275, pruned_loss=0.08248, over 7190.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2821, pruned_loss=0.05876, over 1427093.14 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:27:42,381 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 05:27:49,661 INFO [train.py:841] (3/8) Epoch 7, validation: loss=0.1637, simple_loss=0.2662, pruned_loss=0.03066, over 698248.00 frames.
2022-05-14 05:28:48,978 INFO [train.py:812] (3/8) Epoch 7, batch 3050, loss[loss=0.2071, simple_loss=0.2972, pruned_loss=0.05851, over 7203.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2813, pruned_loss=0.05842, over 1427861.16 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:29:48,820 INFO [train.py:812] (3/8) Epoch 7, batch 3100, loss[loss=0.2006, simple_loss=0.2875, pruned_loss=0.05687, over 7147.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2811, pruned_loss=0.05836, over 1425202.45 frames.], batch size: 26, lr: 1.01e-03
2022-05-14 05:30:48,416 INFO [train.py:812] (3/8) Epoch 7, batch 3150, loss[loss=0.1906, simple_loss=0.2797, pruned_loss=0.05072, over 7117.00 frames.], tot_loss[loss=0.199, simple_loss=0.2813, pruned_loss=0.05838, over 1428601.11 frames.], batch size: 28, lr: 1.01e-03
2022-05-14 05:31:47,451 INFO [train.py:812] (3/8) Epoch 7, batch 3200, loss[loss=0.188, simple_loss=0.2753, pruned_loss=0.05036, over 7338.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2814, pruned_loss=0.05849, over 1425597.50 frames.], batch size: 22, lr: 1.01e-03
2022-05-14 05:32:46,883 INFO [train.py:812] (3/8) Epoch 7, batch 3250, loss[loss=0.2135, simple_loss=0.296, pruned_loss=0.0655, over 6989.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2805, pruned_loss=0.05829, over 1425250.82 frames.], batch size: 28, lr: 1.01e-03
2022-05-14 05:33:46,264 INFO [train.py:812] (3/8) Epoch 7, batch 3300, loss[loss=0.1793, simple_loss=0.2646, pruned_loss=0.04695, over 7143.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2812, pruned_loss=0.05855, over 1419876.24 frames.], batch size: 20, lr: 1.01e-03
2022-05-14 05:34:45,878 INFO [train.py:812] (3/8) Epoch 7, batch 3350, loss[loss=0.1764, simple_loss=0.2597, pruned_loss=0.04656, over 7153.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2807, pruned_loss=0.05806, over 1420345.94 frames.], batch size: 19, lr: 1.01e-03
2022-05-14 05:35:44,956 INFO [train.py:812] (3/8) Epoch 7, batch 3400, loss[loss=0.1918, simple_loss=0.285, pruned_loss=0.04932, over 7105.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2805, pruned_loss=0.05806, over 1422838.68 frames.], batch size: 21, lr: 1.01e-03
2022-05-14 05:36:43,533 INFO [train.py:812] (3/8) Epoch 7, batch 3450, loss[loss=0.227, simple_loss=0.3215, pruned_loss=0.0663, over 7266.00 frames.], tot_loss[loss=0.1988, simple_loss=0.281, pruned_loss=0.0583, over 1420769.19 frames.], batch size: 24, lr: 1.01e-03
2022-05-14 05:37:43,014 INFO [train.py:812] (3/8) Epoch 7, batch 3500, loss[loss=0.2182, simple_loss=0.2979, pruned_loss=0.06927, over 7220.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2811, pruned_loss=0.058, over 1422335.77 frames.], batch size: 21, lr: 1.01e-03
2022-05-14 05:38:41,452 INFO [train.py:812] (3/8) Epoch 7, batch 3550, loss[loss=0.2146, simple_loss=0.3012, pruned_loss=0.06405, over 7377.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2803, pruned_loss=0.05775, over 1424048.60 frames.], batch size: 23, lr: 1.01e-03
2022-05-14 05:39:40,558 INFO [train.py:812] (3/8) Epoch 7, batch 3600, loss[loss=0.2, simple_loss=0.2922, pruned_loss=0.05388, over 7219.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2806, pruned_loss=0.05758, over 1425197.92 frames.], batch size: 21, lr: 1.00e-03
2022-05-14 05:40:39,019 INFO [train.py:812] (3/8) Epoch 7, batch 3650, loss[loss=0.2667, simple_loss=0.3282, pruned_loss=0.1026, over 7070.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2814, pruned_loss=0.05848, over 1422140.89 frames.], batch size: 28, lr: 1.00e-03
2022-05-14 05:41:38,738 INFO [train.py:812] (3/8) Epoch 7, batch 3700, loss[loss=0.1837, simple_loss=0.2668, pruned_loss=0.0503, over 7423.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2802, pruned_loss=0.05812, over 1423427.30 frames.], batch size: 20, lr: 1.00e-03
2022-05-14 05:42:37,960 INFO [train.py:812] (3/8) Epoch 7, batch 3750, loss[loss=0.2289, simple_loss=0.2927, pruned_loss=0.08256, over 5002.00 frames.], tot_loss[loss=0.1982, simple_loss=0.28, pruned_loss=0.0582, over 1424139.94 frames.], batch size: 53, lr: 1.00e-03
2022-05-14 05:43:37,511 INFO [train.py:812] (3/8) Epoch 7, batch 3800, loss[loss=0.2008, simple_loss=0.2861, pruned_loss=0.05774, over 7356.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2802, pruned_loss=0.05809, over 1421989.85 frames.], batch size: 19, lr: 1.00e-03
2022-05-14 05:44:35,594 INFO [train.py:812] (3/8) Epoch 7, batch 3850, loss[loss=0.1592, simple_loss=0.2398, pruned_loss=0.03935, over 7113.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2787, pruned_loss=0.05747, over 1424954.14 frames.], batch size: 17, lr: 1.00e-03
2022-05-14 05:45:34,806 INFO [train.py:812] (3/8) Epoch 7, batch 3900, loss[loss=0.1579, simple_loss=0.238, pruned_loss=0.0389, over 7162.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2778, pruned_loss=0.05687, over 1425879.32 frames.], batch size: 18, lr: 1.00e-03
2022-05-14 05:46:31,674 INFO [train.py:812] (3/8) Epoch 7, batch 3950, loss[loss=0.1921, simple_loss=0.2785, pruned_loss=0.05285, over 7338.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2784, pruned_loss=0.05771, over 1427160.47 frames.], batch size: 22, lr: 9.99e-04
2022-05-14 05:47:30,567 INFO [train.py:812] (3/8) Epoch 7, batch 4000, loss[loss=0.2707, simple_loss=0.3365, pruned_loss=0.1024, over 6727.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2788, pruned_loss=0.05771, over 1431726.03 frames.], batch size: 31, lr: 9.98e-04
2022-05-14 05:48:29,748 INFO [train.py:812] (3/8) Epoch 7, batch 4050, loss[loss=0.2042, simple_loss=0.2894, pruned_loss=0.05951, over 7157.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2782, pruned_loss=0.0576, over 1429464.06 frames.], batch size: 18, lr: 9.98e-04
2022-05-14 05:49:28,784 INFO [train.py:812] (3/8) Epoch 7, batch 4100, loss[loss=0.2182, simple_loss=0.3153, pruned_loss=0.06056, over 7109.00 frames.], tot_loss[loss=0.197, simple_loss=0.2787, pruned_loss=0.05763, over 1424816.24 frames.], batch size: 21, lr: 9.97e-04
2022-05-14 05:50:26,071 INFO [train.py:812] (3/8) Epoch 7, batch 4150, loss[loss=0.1971, simple_loss=0.287, pruned_loss=0.05364, over 7214.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2798, pruned_loss=0.0583, over 1426015.36 frames.], batch size: 23, lr: 9.96e-04
2022-05-14 05:51:25,275 INFO [train.py:812] (3/8) Epoch 7, batch 4200, loss[loss=0.1787, simple_loss=0.2566, pruned_loss=0.05034, over 7286.00 frames.], tot_loss[loss=0.197, simple_loss=0.2791, pruned_loss=0.0575, over 1428057.17 frames.], batch size: 17, lr: 9.95e-04
2022-05-14 05:52:24,621 INFO [train.py:812] (3/8) Epoch 7, batch 4250, loss[loss=0.2065, simple_loss=0.2938, pruned_loss=0.05964, over 7425.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2803, pruned_loss=0.05827, over 1423247.37 frames.], batch size: 20, lr: 9.95e-04
2022-05-14 05:53:23,990 INFO [train.py:812] (3/8) Epoch 7, batch 4300, loss[loss=0.2032, simple_loss=0.2964, pruned_loss=0.05503, over 7234.00 frames.], tot_loss[loss=0.2, simple_loss=0.2819, pruned_loss=0.05909, over 1417864.55 frames.], batch size: 20, lr: 9.94e-04
2022-05-14 05:54:23,294 INFO [train.py:812] (3/8) Epoch 7, batch 4350, loss[loss=0.2022, simple_loss=0.285, pruned_loss=0.05967, over 6336.00 frames.], tot_loss[loss=0.1987, simple_loss=0.281, pruned_loss=0.05821, over 1411951.01 frames.], batch size: 38, lr: 9.93e-04
2022-05-14 05:55:22,363 INFO [train.py:812] (3/8) Epoch 7, batch 4400, loss[loss=0.2449, simple_loss=0.3284, pruned_loss=0.08071, over 6772.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2805, pruned_loss=0.05847, over 1413986.23 frames.], batch size: 31, lr: 9.92e-04
2022-05-14 05:56:20,594 INFO [train.py:812] (3/8) Epoch 7, batch 4450, loss[loss=0.2013, simple_loss=0.2807, pruned_loss=0.061, over 7210.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2811, pruned_loss=0.05858, over 1408421.51 frames.], batch size: 22, lr: 9.92e-04
2022-05-14 05:57:24,426 INFO [train.py:812] (3/8) Epoch 7, batch 4500, loss[loss=0.2136, simple_loss=0.2981, pruned_loss=0.0645, over 7214.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2818, pruned_loss=0.05878, over 1405368.53 frames.], batch size: 22, lr: 9.91e-04
2022-05-14 05:58:22,207 INFO [train.py:812] (3/8) Epoch 7, batch 4550, loss[loss=0.245, simple_loss=0.3078, pruned_loss=0.0911, over 4494.00 frames.], tot_loss[loss=0.2, simple_loss=0.2826, pruned_loss=0.05869, over 1390215.88 frames.], batch size: 52, lr: 9.90e-04
2022-05-14 05:59:32,587 INFO [train.py:812] (3/8) Epoch 8, batch 0, loss[loss=0.1972, simple_loss=0.2935, pruned_loss=0.05042, over 7332.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2935, pruned_loss=0.05042, over 7332.00 frames.], batch size: 22, lr: 9.49e-04
2022-05-14 06:00:31,157 INFO [train.py:812] (3/8) Epoch 8, batch 50, loss[loss=0.1818, simple_loss=0.256, pruned_loss=0.05378, over 7137.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2822, pruned_loss=0.05732, over 320764.07 frames.], batch size: 17, lr: 9.48e-04
2022-05-14 06:01:30,395 INFO [train.py:812] (3/8) Epoch 8, batch 100, loss[loss=0.2068, simple_loss=0.2831, pruned_loss=0.0652, over 7264.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2788, pruned_loss=0.05553, over 568903.63 frames.], batch size: 25, lr: 9.48e-04
2022-05-14 06:02:29,669 INFO [train.py:812] (3/8) Epoch 8, batch 150, loss[loss=0.2053, simple_loss=0.2912, pruned_loss=0.05973, over 7116.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2777, pruned_loss=0.05568, over 758048.30 frames.], batch size: 21, lr: 9.47e-04
2022-05-14 06:03:26,754 INFO [train.py:812] (3/8) Epoch 8, batch 200, loss[loss=0.1878, simple_loss=0.2795, pruned_loss=0.04801, over 7215.00 frames.], tot_loss[loss=0.1944, simple_loss=0.278, pruned_loss=0.05541, over 907014.98 frames.], batch size: 22, lr: 9.46e-04
2022-05-14 06:04:24,364 INFO [train.py:812] (3/8) Epoch 8, batch 250, loss[loss=0.1843, simple_loss=0.2702, pruned_loss=0.04917, over 7121.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2785, pruned_loss=0.05557, over 1020289.29 frames.], batch size: 21, lr: 9.46e-04
2022-05-14 06:05:21,329 INFO [train.py:812] (3/8) Epoch 8, batch 300, loss[loss=0.1786, simple_loss=0.2557, pruned_loss=0.05081, over 7070.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2786, pruned_loss=0.05532, over 1106021.37 frames.], batch size: 18, lr: 9.45e-04
2022-05-14 06:06:19,885 INFO [train.py:812] (3/8) Epoch 8, batch 350, loss[loss=0.2262, simple_loss=0.3143, pruned_loss=0.06906, over 7110.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2778, pruned_loss=0.05589, over 1177793.37 frames.], batch size: 21, lr: 9.44e-04
2022-05-14 06:07:19,503 INFO [train.py:812] (3/8) Epoch 8, batch 400, loss[loss=0.2424, simple_loss=0.3083, pruned_loss=0.08827, over 4856.00 frames.], tot_loss[loss=0.1963, simple_loss=0.279, pruned_loss=0.05676, over 1230569.38 frames.], batch size: 52, lr: 9.43e-04
2022-05-14 06:08:18,799 INFO [train.py:812] (3/8) Epoch 8, batch 450, loss[loss=0.1693, simple_loss=0.2402, pruned_loss=0.04919, over 6711.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2779, pruned_loss=0.05635, over 1271386.13 frames.], batch size: 15, lr: 9.43e-04
2022-05-14 06:09:18,361 INFO [train.py:812] (3/8) Epoch 8, batch 500, loss[loss=0.2089, simple_loss=0.3012, pruned_loss=0.05833, over 7198.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2772, pruned_loss=0.05604, over 1304516.48 frames.], batch size: 23, lr: 9.42e-04
2022-05-14 06:10:17,033 INFO [train.py:812] (3/8) Epoch 8, batch 550, loss[loss=0.2332, simple_loss=0.3124, pruned_loss=0.07699, over 7208.00 frames.], tot_loss[loss=0.1939, simple_loss=0.277, pruned_loss=0.05545, over 1332309.96 frames.], batch size: 23, lr: 9.41e-04
2022-05-14 06:11:16,908 INFO [train.py:812] (3/8) Epoch 8, batch 600, loss[loss=0.22, simple_loss=0.3069, pruned_loss=0.06656, over 7220.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2797, pruned_loss=0.05661, over 1352486.15 frames.], batch size: 21, lr: 9.41e-04
2022-05-14 06:12:15,253 INFO [train.py:812] (3/8) Epoch 8, batch 650, loss[loss=0.1951, simple_loss=0.2734, pruned_loss=0.05845, over 7259.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2787, pruned_loss=0.05618, over 1368026.76 frames.], batch size: 19, lr: 9.40e-04
2022-05-14 06:13:14,186 INFO [train.py:812] (3/8) Epoch 8, batch 700, loss[loss=0.2273, simple_loss=0.2944, pruned_loss=0.08008, over 5277.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2789, pruned_loss=0.05636, over 1377767.63 frames.], batch size: 52, lr: 9.39e-04
2022-05-14 06:14:13,341 INFO [train.py:812] (3/8) Epoch 8, batch 750, loss[loss=0.1699, simple_loss=0.2533, pruned_loss=0.04329, over 7357.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2784, pruned_loss=0.0564, over 1385656.94 frames.], batch size: 19, lr: 9.39e-04
2022-05-14 06:15:12,817 INFO [train.py:812] (3/8) Epoch 8, batch 800, loss[loss=0.1952, simple_loss=0.278, pruned_loss=0.05615, over 6301.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2792, pruned_loss=0.05613, over 1390665.73 frames.], batch size: 37, lr: 9.38e-04
2022-05-14 06:16:12,232 INFO [train.py:812] (3/8) Epoch 8, batch 850, loss[loss=0.1758, simple_loss=0.255, pruned_loss=0.04829, over 7429.00 frames.], tot_loss[loss=0.194, simple_loss=0.2772, pruned_loss=0.05542, over 1398862.29 frames.], batch size: 18, lr: 9.37e-04
2022-05-14 06:17:11,300 INFO [train.py:812] (3/8) Epoch 8, batch 900, loss[loss=0.2031, simple_loss=0.2945, pruned_loss=0.0559, over 6780.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2776, pruned_loss=0.05588, over 1399378.58 frames.], batch size: 31, lr: 9.36e-04
2022-05-14 06:18:09,090 INFO [train.py:812] (3/8) Epoch 8, batch 950, loss[loss=0.1772, simple_loss=0.2709, pruned_loss=0.04176, over 7234.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2782, pruned_loss=0.05625, over 1404811.03 frames.], batch size: 20, lr: 9.36e-04
2022-05-14 06:19:08,064 INFO [train.py:812] (3/8) Epoch 8, batch 1000, loss[loss=0.231, simple_loss=0.3119, pruned_loss=0.07509, over 7225.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2786, pruned_loss=0.05624, over 1408856.36 frames.], batch size: 21, lr: 9.35e-04
2022-05-14 06:20:06,230 INFO [train.py:812] (3/8) Epoch 8, batch 1050, loss[loss=0.1747, simple_loss=0.2515, pruned_loss=0.04897, over 7133.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2789, pruned_loss=0.05644, over 1407484.71 frames.], batch size: 17, lr: 9.34e-04
2022-05-14 06:21:04,771 INFO [train.py:812] (3/8) Epoch 8, batch 1100, loss[loss=0.1802, simple_loss=0.2744, pruned_loss=0.04304, over 7201.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2777, pruned_loss=0.05574, over 1412260.67 frames.], batch size: 22, lr: 9.34e-04
2022-05-14 06:22:02,854 INFO [train.py:812] (3/8) Epoch 8, batch 1150, loss[loss=0.2203, simple_loss=0.2991, pruned_loss=0.0707, over 4713.00 frames.], tot_loss[loss=0.195, simple_loss=0.2784, pruned_loss=0.05583, over 1416709.12 frames.], batch size: 52, lr: 9.33e-04
2022-05-14 06:23:10,858 INFO [train.py:812] (3/8) Epoch 8, batch 1200, loss[loss=0.2045, simple_loss=0.2861, pruned_loss=0.06147, over 7158.00 frames.], tot_loss[loss=0.1957, simple_loss=0.279, pruned_loss=0.0562, over 1419881.51 frames.], batch size: 20, lr: 9.32e-04
2022-05-14 06:24:10,081 INFO [train.py:812] (3/8) Epoch 8, batch 1250, loss[loss=0.1615, simple_loss=0.2502, pruned_loss=0.03643, over 7270.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2776, pruned_loss=0.05567, over 1419410.12 frames.], batch size: 18, lr: 9.32e-04
2022-05-14 06:25:09,382 INFO [train.py:812] (3/8) Epoch 8, batch 1300, loss[loss=0.1844, simple_loss=0.2758, pruned_loss=0.04652, over 7150.00 frames.], tot_loss[loss=0.195, simple_loss=0.2783, pruned_loss=0.05583, over 1416269.74 frames.], batch size: 20, lr: 9.31e-04
2022-05-14 06:26:08,337 INFO [train.py:812] (3/8) Epoch 8, batch 1350, loss[loss=0.1743, simple_loss=0.2661, pruned_loss=0.04122, over 7156.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2794, pruned_loss=0.05638, over 1414935.59 frames.], batch size: 19, lr: 9.30e-04
2022-05-14 06:27:07,999 INFO [train.py:812] (3/8) Epoch 8, batch 1400, loss[loss=0.1652, simple_loss=0.247, pruned_loss=0.04168, over 7266.00 frames.], tot_loss[loss=0.1959, simple_loss=0.279, pruned_loss=0.05639, over 1416084.96 frames.], batch size: 18, lr: 9.30e-04
2022-05-14 06:28:06,826 INFO [train.py:812] (3/8) Epoch 8, batch 1450, loss[loss=0.2089, simple_loss=0.2902, pruned_loss=0.06383, over 7168.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2792, pruned_loss=0.05617, over 1416158.79 frames.], batch size: 18, lr: 9.29e-04
2022-05-14 06:29:06,638 INFO [train.py:812] (3/8) Epoch 8, batch 1500, loss[loss=0.1653, simple_loss=0.2486, pruned_loss=0.04099, over 7411.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2777, pruned_loss=0.0555, over 1416427.03 frames.], batch size: 18, lr: 9.28e-04
2022-05-14 06:30:05,550 INFO [train.py:812] (3/8) Epoch 8, batch 1550, loss[loss=0.206, simple_loss=0.2803, pruned_loss=0.06584, over 7205.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2782, pruned_loss=0.05577, over 1421406.59 frames.], batch size: 22, lr: 9.28e-04
2022-05-14 06:31:05,143 INFO [train.py:812] (3/8) Epoch 8, batch 1600, loss[loss=0.2, simple_loss=0.2877, pruned_loss=0.05619, over 6343.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2793, pruned_loss=0.05643, over 1421615.16 frames.], batch size: 37, lr: 9.27e-04
2022-05-14 06:32:04,299 INFO [train.py:812] (3/8) Epoch 8, batch 1650, loss[loss=0.2041, simple_loss=0.2962, pruned_loss=0.05602, over 7266.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2795, pruned_loss=0.05666, over 1419953.32 frames.], batch size: 24, lr: 9.26e-04
2022-05-14 06:33:04,184 INFO [train.py:812] (3/8) Epoch 8, batch 1700, loss[loss=0.1937, simple_loss=0.2738, pruned_loss=0.05683, over 7316.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2796, pruned_loss=0.05655, over 1420311.58 frames.], batch size: 21, lr: 9.26e-04
2022-05-14 06:34:03,667 INFO [train.py:812] (3/8) Epoch 8, batch 1750, loss[loss=0.2096, simple_loss=0.301, pruned_loss=0.05909, over 7337.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2786, pruned_loss=0.05562, over 1420788.30 frames.], batch size: 22, lr: 9.25e-04
2022-05-14 06:35:12,590 INFO [train.py:812] (3/8) Epoch 8, batch 1800, loss[loss=0.1934, simple_loss=0.2846, pruned_loss=0.05105, over 7331.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2772, pruned_loss=0.05527, over 1421929.54 frames.], batch size: 22, lr: 9.24e-04
2022-05-14 06:36:21,447 INFO [train.py:812] (3/8) Epoch 8, batch 1850, loss[loss=0.1709, simple_loss=0.2643, pruned_loss=0.0388, over 7236.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2774, pruned_loss=0.05501, over 1423384.37 frames.], batch size: 20, lr: 9.24e-04
2022-05-14 06:37:30,718 INFO [train.py:812] (3/8) Epoch 8, batch 1900, loss[loss=0.1914, simple_loss=0.2723, pruned_loss=0.05522, over 7295.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2752, pruned_loss=0.05422, over 1423120.64 frames.], batch size: 25, lr: 9.23e-04
2022-05-14 06:38:48,455 INFO [train.py:812] (3/8) Epoch 8, batch 1950, loss[loss=0.1423, simple_loss=0.2282, pruned_loss=0.02815, over 6995.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2754, pruned_loss=0.05467, over 1427187.77 frames.], batch size: 16, lr: 9.22e-04
2022-05-14 06:40:06,954 INFO [train.py:812] (3/8) Epoch 8, batch 2000, loss[loss=0.2145, simple_loss=0.2958, pruned_loss=0.0666, over 7121.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2768, pruned_loss=0.05506, over 1427472.10 frames.], batch size: 21, lr: 9.22e-04
2022-05-14 06:41:06,016 INFO [train.py:812] (3/8) Epoch 8, batch 2050, loss[loss=0.2506, simple_loss=0.3183, pruned_loss=0.09141, over 5223.00 frames.], tot_loss[loss=0.195, simple_loss=0.2781, pruned_loss=0.05594, over 1422043.50 frames.], batch size: 52, lr: 9.21e-04
2022-05-14 06:42:04,904 INFO [train.py:812] (3/8) Epoch 8, batch 2100, loss[loss=0.2032, simple_loss=0.2907, pruned_loss=0.05785, over 7224.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2783, pruned_loss=0.05605, over 1418439.48 frames.], batch size: 20, lr: 9.20e-04
2022-05-14 06:43:03,992 INFO [train.py:812] (3/8) Epoch 8, batch 2150, loss[loss=0.215, simple_loss=0.2924, pruned_loss=0.06876, over 7196.00 frames.], tot_loss[loss=0.1943, simple_loss=0.277, pruned_loss=0.05578, over 1419933.76 frames.], batch size: 22, lr: 9.20e-04
2022-05-14 06:44:03,047 INFO [train.py:812] (3/8) Epoch 8, batch 2200, loss[loss=0.2032, simple_loss=0.2919, pruned_loss=0.0573, over 7296.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2759, pruned_loss=0.05528, over 1418098.83 frames.], batch size: 24, lr: 9.19e-04
2022-05-14 06:45:01,868 INFO [train.py:812] (3/8) Epoch 8, batch 2250, loss[loss=0.178, simple_loss=0.2598, pruned_loss=0.04814, over 7206.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2749, pruned_loss=0.05492, over 1412833.92 frames.], batch size: 23, lr: 9.18e-04
2022-05-14 06:46:00,787 INFO [train.py:812] (3/8) Epoch 8, batch 2300, loss[loss=0.1866, simple_loss=0.2706, pruned_loss=0.0513, over 7411.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2745, pruned_loss=0.05478, over 1413246.96 frames.], batch size: 18, lr: 9.18e-04
2022-05-14 06:46:59,520 INFO [train.py:812] (3/8) Epoch 8, batch 2350, loss[loss=0.1646, simple_loss=0.254, pruned_loss=0.03757, over 7068.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2749, pruned_loss=0.05477, over 1413293.10 frames.], batch size: 18, lr: 9.17e-04
2022-05-14 06:47:58,460 INFO [train.py:812] (3/8) Epoch 8, batch 2400, loss[loss=0.1591, simple_loss=0.2419, pruned_loss=0.03815, over 7263.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2751, pruned_loss=0.0549, over 1416692.58 frames.], batch size: 19, lr: 9.16e-04
2022-05-14 06:48:57,606 INFO [train.py:812] (3/8) Epoch 8, batch 2450, loss[loss=0.22, simple_loss=0.2967, pruned_loss=0.07165, over 7281.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2755, pruned_loss=0.05483, over 1422886.78 frames.], batch size: 24, lr: 9.16e-04
2022-05-14 06:49:56,999 INFO [train.py:812] (3/8) Epoch 8, batch 2500, loss[loss=0.1904, simple_loss=0.2698, pruned_loss=0.05554, over 7325.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2769, pruned_loss=0.05546, over 1421094.52 frames.], batch size: 21, lr: 9.15e-04
2022-05-14 06:50:55,697 INFO [train.py:812] (3/8) Epoch 8, batch 2550, loss[loss=0.1851, simple_loss=0.2646, pruned_loss=0.05278, over 7364.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2758, pruned_loss=0.05463, over 1425974.82 frames.], batch size: 19, lr: 9.14e-04
2022-05-14 06:51:54,440 INFO [train.py:812] (3/8) Epoch 8, batch 2600, loss[loss=0.2075, simple_loss=0.2769, pruned_loss=0.06907, over 6816.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2757, pruned_loss=0.05479, over 1425646.05 frames.], batch size: 15, lr: 9.14e-04
2022-05-14 06:52:51,845 INFO [train.py:812] (3/8) Epoch 8, batch 2650, loss[loss=0.1742, simple_loss=0.2727, pruned_loss=0.03781, over 7101.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2765, pruned_loss=0.05493, over 1426352.57 frames.], batch size: 21, lr: 9.13e-04
2022-05-14 06:53:49,754 INFO [train.py:812] (3/8) Epoch 8, batch 2700, loss[loss=0.1687, simple_loss=0.2389, pruned_loss=0.04921, over 6781.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2756, pruned_loss=0.05405, over 1428481.82 frames.], batch size: 15, lr: 9.12e-04
2022-05-14 06:54:48,254 INFO [train.py:812] (3/8) Epoch 8, batch 2750, loss[loss=0.1634, simple_loss=0.2383, pruned_loss=0.04425, over 6990.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2751, pruned_loss=0.05442, over 1427034.70 frames.], batch size: 16, lr: 9.12e-04
2022-05-14 06:55:46,851 INFO [train.py:812] (3/8) Epoch 8, batch 2800, loss[loss=0.1941, simple_loss=0.2749, pruned_loss=0.05668, over 7143.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2749, pruned_loss=0.05436, over 1427780.65 frames.], batch size: 20, lr: 9.11e-04
2022-05-14 06:56:44,431 INFO [train.py:812] (3/8) Epoch 8, batch 2850, loss[loss=0.2232, simple_loss=0.308, pruned_loss=0.06916, over 7202.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2761, pruned_loss=0.0549, over 1426617.16 frames.], batch size: 22, lr: 9.11e-04
2022-05-14 06:57:43,808 INFO [train.py:812] (3/8) Epoch 8, batch 2900, loss[loss=0.1775, simple_loss=0.2541, pruned_loss=0.05043, over 7143.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2774, pruned_loss=0.05522, over 1425775.94 frames.], batch size: 17, lr: 9.10e-04
2022-05-14 06:58:42,754 INFO [train.py:812] (3/8) Epoch 8, batch 2950, loss[loss=0.1544, simple_loss=0.2398, pruned_loss=0.03448, over 7070.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2756, pruned_loss=0.0547, over 1425120.82 frames.], batch size: 18, lr: 9.09e-04
2022-05-14 06:59:42,241 INFO [train.py:812] (3/8) Epoch 8, batch 3000, loss[loss=0.2573, simple_loss=0.32, pruned_loss=0.09726, over 5148.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2751, pruned_loss=0.05433, over 1420681.02 frames.], batch size: 52, lr: 9.09e-04
2022-05-14 06:59:42,242 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 06:59:50,552 INFO [train.py:841] (3/8) Epoch 8, validation: loss=0.1612, simple_loss=0.2635, pruned_loss=0.0294, over 698248.00 frames.
2022-05-14 07:00:48,446 INFO [train.py:812] (3/8) Epoch 8, batch 3050, loss[loss=0.2103, simple_loss=0.2948, pruned_loss=0.06288, over 6376.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2754, pruned_loss=0.05481, over 1413917.53 frames.], batch size: 38, lr: 9.08e-04
2022-05-14 07:01:48,157 INFO [train.py:812] (3/8) Epoch 8, batch 3100, loss[loss=0.1548, simple_loss=0.238, pruned_loss=0.03576, over 7261.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2752, pruned_loss=0.0547, over 1419190.63 frames.], batch size: 19, lr: 9.07e-04
2022-05-14 07:02:45,368 INFO [train.py:812] (3/8) Epoch 8, batch 3150, loss[loss=0.1603, simple_loss=0.245, pruned_loss=0.03779, over 7433.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2739, pruned_loss=0.05437, over 1421215.33 frames.], batch size: 20, lr: 9.07e-04
2022-05-14 07:03:44,353 INFO [train.py:812] (3/8) Epoch 8, batch 3200, loss[loss=0.1717, simple_loss=0.2641, pruned_loss=0.0397, over 7430.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2739, pruned_loss=0.05434, over 1424109.20 frames.], batch size: 20, lr: 9.06e-04
2022-05-14 07:04:43,313 INFO [train.py:812] (3/8) Epoch 8, batch 3250, loss[loss=0.1669, simple_loss=0.2589, pruned_loss=0.0375, over 7023.00 frames.], tot_loss[loss=0.192, simple_loss=0.2751, pruned_loss=0.05441, over 1422568.56 frames.], batch size: 28, lr: 9.05e-04
2022-05-14 07:05:41,207 INFO [train.py:812] (3/8) Epoch 8, batch 3300, loss[loss=0.2232, simple_loss=0.3153, pruned_loss=0.0655, over 6712.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2748, pruned_loss=0.05442, over 1421363.24 frames.], batch size: 31, lr: 9.05e-04
2022-05-14 07:06:40,364 INFO [train.py:812] (3/8) Epoch 8, batch 3350, loss[loss=0.1704, simple_loss=0.2583, pruned_loss=0.04128, over 7433.00 frames.], tot_loss[loss=0.1916, simple_loss=0.275, pruned_loss=0.05412, over 1419344.97 frames.], batch size: 20, lr: 9.04e-04
2022-05-14 07:07:39,819 INFO [train.py:812] (3/8) Epoch 8, batch 3400, loss[loss=0.2103, simple_loss=0.2914, pruned_loss=0.06458, over 6804.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2754, pruned_loss=0.05466, over 1417821.72 frames.], batch size: 31, lr: 9.04e-04
2022-05-14 07:08:38,477 INFO [train.py:812] (3/8) Epoch 8, batch 3450, loss[loss=0.2042, simple_loss=0.2824, pruned_loss=0.06298, over 7406.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2768, pruned_loss=0.05519, over 1420938.31 frames.], batch size: 18, lr: 9.03e-04
2022-05-14 07:09:37,923 INFO [train.py:812] (3/8) Epoch 8, batch 3500, loss[loss=0.2239, simple_loss=0.3065, pruned_loss=0.07065, over 7360.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2778, pruned_loss=0.05573, over 1420884.58 frames.], batch size: 23, lr: 9.02e-04
2022-05-14 07:10:37,048 INFO [train.py:812] (3/8) Epoch 8, batch 3550, loss[loss=0.1966, simple_loss=0.2927, pruned_loss=0.05029, over 7259.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2767, pruned_loss=0.05531, over 1422581.75 frames.], batch size: 19, lr: 9.02e-04
2022-05-14 07:11:36,650 INFO [train.py:812] (3/8) Epoch 8, batch 3600, loss[loss=0.175, simple_loss=0.2543, pruned_loss=0.04789, over 7268.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2757, pruned_loss=0.05469, over 1422050.81 frames.], batch size: 17, lr: 9.01e-04
2022-05-14 07:12:33,622 INFO [train.py:812] (3/8) Epoch 8, batch 3650, loss[loss=0.1832, simple_loss=0.2681, pruned_loss=0.04913, over 7410.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2775, pruned_loss=0.05559, over 1416565.97 frames.], batch size: 21, lr: 9.01e-04
2022-05-14 07:13:32,615 INFO [train.py:812] (3/8) Epoch 8, batch 3700, loss[loss=0.2097, simple_loss=0.3056, pruned_loss=0.0569, over 7223.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2767, pruned_loss=0.05503, over 1420122.93 frames.], batch size: 21, lr: 9.00e-04
2022-05-14 07:14:31,408 INFO [train.py:812] (3/8) Epoch 8, batch 3750, loss[loss=0.1943, simple_loss=0.2808, pruned_loss=0.05391, over 7162.00 frames.], tot_loss[loss=0.1937, simple_loss=0.277, pruned_loss=0.0552, over 1416580.73 frames.], batch size: 19, lr: 8.99e-04
2022-05-14 07:15:30,610 INFO [train.py:812] (3/8) Epoch 8, batch 3800, loss[loss=0.2115, simple_loss=0.2985, pruned_loss=0.06226, over 7282.00 frames.], tot_loss[loss=0.195, simple_loss=0.2781, pruned_loss=0.05592, over 1420114.42 frames.], batch size: 24, lr: 8.99e-04
2022-05-14 07:16:28,749 INFO [train.py:812] (3/8) Epoch 8, batch 3850, loss[loss=0.1877, simple_loss=0.2755, pruned_loss=0.04995, over 7212.00 frames.], tot_loss[loss=0.1956, simple_loss=0.279, pruned_loss=0.05606, over 1418290.29 frames.], batch size: 21, lr: 8.98e-04
2022-05-14 07:17:33,251 INFO [train.py:812] (3/8) Epoch 8, batch 3900, loss[loss=0.2335, simple_loss=0.3134, pruned_loss=0.07682, over 7443.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2776, pruned_loss=0.0555, over 1422211.43 frames.], batch size: 20, lr: 8.97e-04
2022-05-14 07:18:32,350 INFO [train.py:812] (3/8) Epoch 8, batch 3950, loss[loss=0.1673, simple_loss=0.2499, pruned_loss=0.04241, over 7001.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2759, pruned_loss=0.05451, over 1424635.18 frames.], batch size: 16, lr: 8.97e-04
2022-05-14 07:19:31,323 INFO [train.py:812] (3/8) Epoch 8, batch 4000, loss[loss=0.1745, simple_loss=0.263, pruned_loss=0.04303, over 7154.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2769, pruned_loss=0.05485, over 1423476.85 frames.], batch size: 20, lr: 8.96e-04
2022-05-14 07:20:29,691 INFO [train.py:812] (3/8) Epoch 8, batch 4050, loss[loss=0.1688, simple_loss=0.2579, pruned_loss=0.03984, over 7418.00 frames.], tot_loss[loss=0.1925, simple_loss=0.276, pruned_loss=0.05451, over 1426051.48 frames.], batch size: 21, lr: 8.96e-04
2022-05-14 07:21:29,486 INFO [train.py:812] (3/8) Epoch 8, batch 4100, loss[loss=0.1674, simple_loss=0.2503, pruned_loss=0.04227, over 7266.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2758, pruned_loss=0.05449, over 1419639.46 frames.], batch size: 17, lr: 8.95e-04
2022-05-14 07:22:28,430 INFO [train.py:812] (3/8) Epoch 8, batch 4150, loss[loss=0.2253, simple_loss=0.3047, pruned_loss=0.07294, over 7335.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2768, pruned_loss=0.05476, over 1413980.50 frames.], batch size: 22, lr: 8.94e-04
2022-05-14 07:23:28,037 INFO [train.py:812] (3/8) Epoch 8, batch 4200, loss[loss=0.1853, simple_loss=0.27, pruned_loss=0.05033, over 7147.00 frames.], tot_loss[loss=0.194, simple_loss=0.2779, pruned_loss=0.05507, over 1416357.55 frames.], batch size: 20, lr: 8.94e-04
2022-05-14 07:24:27,285 INFO [train.py:812] (3/8) Epoch 8, batch 4250, loss[loss=0.22, simple_loss=0.3013, pruned_loss=0.06936, over 7197.00 frames.], tot_loss[loss=0.1932, simple_loss=0.277, pruned_loss=0.05468, over 1420132.83 frames.], batch size: 22, lr: 8.93e-04
2022-05-14 07:25:26,237 INFO [train.py:812] (3/8) Epoch 8, batch 4300, loss[loss=0.1964, simple_loss=0.2839, pruned_loss=0.05443, over 7338.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2762, pruned_loss=0.05451, over 1419487.93 frames.], batch size: 21, lr: 8.93e-04
2022-05-14 07:26:25,415 INFO [train.py:812] (3/8) Epoch 8, batch 4350, loss[loss=0.2177, simple_loss=0.3233, pruned_loss=0.05601, over 7101.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2754, pruned_loss=0.05411, over 1415211.22 frames.], batch size: 21, lr: 8.92e-04
2022-05-14 07:27:24,397 INFO [train.py:812] (3/8) Epoch 8, batch 4400, loss[loss=0.1812, simple_loss=0.2676, pruned_loss=0.04746, over 7120.00 frames.], tot_loss[loss=0.191, simple_loss=0.2743, pruned_loss=0.05388, over 1417543.95 frames.], batch size: 28, lr: 8.91e-04
2022-05-14 07:28:23,669 INFO [train.py:812] (3/8) Epoch 8, batch 4450, loss[loss=0.2109, simple_loss=0.2956, pruned_loss=0.0631, over 7327.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2741, pruned_loss=0.05402, over 1417461.50 frames.], batch size: 20, lr: 8.91e-04
2022-05-14 07:29:23,592 INFO [train.py:812] (3/8) Epoch 8, batch 4500, loss[loss=0.1598, simple_loss=0.2426, pruned_loss=0.03845, over 7150.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2737, pruned_loss=0.05401, over 1415771.81 frames.], batch size: 18, lr: 8.90e-04
2022-05-14 07:30:22,911 INFO [train.py:812] (3/8) Epoch 8, batch 4550, loss[loss=0.1338, simple_loss=0.2154, pruned_loss=0.02608, over 7272.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2732, pruned_loss=0.05476, over 1398004.18 frames.], batch size: 17, lr: 8.90e-04
2022-05-14 07:31:33,240 INFO [train.py:812] (3/8) Epoch 9, batch 0, loss[loss=0.2175, simple_loss=0.2926, pruned_loss=0.0712, over 7209.00 frames.], tot_loss[loss=0.2175, simple_loss=0.2926, pruned_loss=0.0712, over 7209.00 frames.], batch size: 23, lr: 8.54e-04
2022-05-14 07:32:31,235 INFO [train.py:812] (3/8) Epoch 9, batch 50, loss[loss=0.2175, simple_loss=0.2962, pruned_loss=0.06937, over 7138.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2768, pruned_loss=0.05481, over 319899.55 frames.], batch size: 28, lr: 8.53e-04
2022-05-14 07:33:31,078 INFO [train.py:812] (3/8) Epoch 9, batch 100, loss[loss=0.1656, simple_loss=0.2626, pruned_loss=0.03432, over 7231.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2747, pruned_loss=0.05381, over 567553.44 frames.], batch size: 20, lr: 8.53e-04
2022-05-14 07:34:29,321 INFO [train.py:812] (3/8) Epoch 9, batch 150, loss[loss=0.2371, simple_loss=0.3132, pruned_loss=0.08046, over 5320.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2755, pruned_loss=0.05399, over 754762.86 frames.], batch size: 52, lr: 8.52e-04
2022-05-14 07:35:29,135 INFO [train.py:812] (3/8) Epoch 9, batch 200, loss[loss=0.2211, simple_loss=0.3022, pruned_loss=0.07006, over 7216.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2751, pruned_loss=0.0536, over 904272.50 frames.], batch size: 22, lr: 8.51e-04
2022-05-14 07:36:28,012 INFO [train.py:812] (3/8) Epoch 9, batch 250, loss[loss=0.1798, simple_loss=0.2672, pruned_loss=0.04617, over 7430.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2738, pruned_loss=0.05246, over 1020367.28 frames.], batch size: 20, lr: 8.51e-04
2022-05-14 07:37:25,262 INFO [train.py:812] (3/8) Epoch 9, batch 300, loss[loss=0.169, simple_loss=0.2649, pruned_loss=0.03658, over 7328.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2752, pruned_loss=0.05351, over 1106005.68 frames.], batch size: 22, lr: 8.50e-04
2022-05-14 07:38:24,949 INFO [train.py:812] (3/8) Epoch 9, batch 350, loss[loss=0.1855, simple_loss=0.268, pruned_loss=0.05156, over 7154.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2728, pruned_loss=0.05271, over 1180274.35 frames.], batch size: 19, lr: 8.50e-04
2022-05-14 07:39:24,185 INFO [train.py:812] (3/8) Epoch 9, batch 400, loss[loss=0.1888, simple_loss=0.2581, pruned_loss=0.05978, over 7129.00 frames.], tot_loss[loss=0.189, simple_loss=0.2731, pruned_loss=0.0525, over 1239370.10 frames.], batch size: 17, lr: 8.49e-04
2022-05-14 07:40:21,411 INFO [train.py:812] (3/8) Epoch 9, batch 450, loss[loss=0.1568, simple_loss=0.246, pruned_loss=0.03384, over 7247.00 frames.], tot_loss[loss=0.189, simple_loss=0.2727, pruned_loss=0.05263, over 1278917.60 frames.], batch size: 19, lr: 8.49e-04
2022-05-14 07:41:19,781 INFO [train.py:812] (3/8) Epoch 9, batch 500, loss[loss=0.16, simple_loss=0.2364, pruned_loss=0.04182, over 7414.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2741, pruned_loss=0.05306, over 1311890.49 frames.], batch size: 18, lr: 8.48e-04
2022-05-14 07:42:19,041 INFO [train.py:812] (3/8) Epoch 9, batch 550, loss[loss=0.178, simple_loss=0.2635, pruned_loss=0.04624, over 7456.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2741, pruned_loss=0.05275, over 1340114.67 frames.], batch size: 19, lr: 8.48e-04
2022-05-14 07:43:17,527 INFO [train.py:812] (3/8) Epoch 9, batch 600, loss[loss=0.1728, simple_loss=0.261, pruned_loss=0.04229, over 7078.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2741, pruned_loss=0.05303, over 1361587.71 frames.], batch size: 18, lr: 8.47e-04
2022-05-14 07:44:16,645 INFO [train.py:812] (3/8) Epoch 9, batch 650, loss[loss=0.2001, simple_loss=0.2821, pruned_loss=0.05903, over 7358.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2746, pruned_loss=0.05307, over 1374983.32 frames.], batch size: 19, lr: 8.46e-04
2022-05-14 07:45:15,374 INFO [train.py:812] (3/8) Epoch 9, batch 700, loss[loss=0.174, simple_loss=0.2605, pruned_loss=0.04375, over 7441.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2742, pruned_loss=0.053, over 1387061.48 frames.], batch size: 20, lr: 8.46e-04
2022-05-14 07:46:13,741 INFO [train.py:812] (3/8) Epoch 9, batch 750, loss[loss=0.1671, simple_loss=0.256, pruned_loss=0.03908, over 7174.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2737, pruned_loss=0.05328, over 1390520.33 frames.], batch size: 18, lr: 8.45e-04
2022-05-14 07:47:13,054 INFO [train.py:812] (3/8) Epoch 9, batch 800, loss[loss=0.1897, simple_loss=0.2792, pruned_loss=0.05012, over 7399.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2731, pruned_loss=0.05268, over 1396565.97 frames.], batch size: 23, lr: 8.45e-04
2022-05-14 07:48:11,324 INFO [train.py:812] (3/8) Epoch 9, batch 850, loss[loss=0.1798, simple_loss=0.2751, pruned_loss=0.04229, over 7316.00 frames.], tot_loss[loss=0.1891, simple_loss=0.273, pruned_loss=0.05262, over 1402113.76 frames.], batch size: 21, lr: 8.44e-04
2022-05-14 07:49:11,213 INFO [train.py:812] (3/8) Epoch 9, batch 900, loss[loss=0.2061, simple_loss=0.2936, pruned_loss=0.05933, over 7221.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2728, pruned_loss=0.05229, over 1410811.27 frames.], batch size: 21, lr: 8.44e-04
2022-05-14 07:50:10,572 INFO [train.py:812] (3/8) Epoch 9, batch 950, loss[loss=0.2017, simple_loss=0.2831, pruned_loss=0.06015, over 7331.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2727, pruned_loss=0.0523, over 1408278.03 frames.], batch size: 20, lr: 8.43e-04
2022-05-14 07:51:10,569 INFO [train.py:812] (3/8) Epoch 9, batch 1000, loss[loss=0.1856, simple_loss=0.2608, pruned_loss=0.05516, over 7440.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2725, pruned_loss=0.0523, over 1412877.81 frames.], batch size: 20, lr: 8.43e-04
2022-05-14 07:52:08,955 INFO [train.py:812] (3/8) Epoch 9, batch 1050, loss[loss=0.1766, simple_loss=0.2531, pruned_loss=0.05004, over 7251.00 frames.], tot_loss[loss=0.189, simple_loss=0.2731, pruned_loss=0.05244, over 1417717.22 frames.], batch size: 19, lr: 8.42e-04
2022-05-14 07:53:07,740 INFO [train.py:812] (3/8) Epoch 9, batch 1100, loss[loss=0.1534, simple_loss=0.2354, pruned_loss=0.03574, over 7272.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2749, pruned_loss=0.05321, over 1420165.16 frames.], batch size: 17, lr: 8.41e-04
2022-05-14 07:54:04,871 INFO [train.py:812] (3/8) Epoch 9, batch 1150, loss[loss=0.1974, simple_loss=0.2795, pruned_loss=0.05767, over 7296.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2741, pruned_loss=0.05321, over 1420192.14 frames.], batch size: 25, lr: 8.41e-04
2022-05-14 07:55:04,925 INFO [train.py:812] (3/8) Epoch 9, batch 1200, loss[loss=0.19, simple_loss=0.2653, pruned_loss=0.05731, over 7436.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2727, pruned_loss=0.05223, over 1420707.11 frames.], batch size: 20, lr: 8.40e-04
2022-05-14 07:56:02,840 INFO [train.py:812] (3/8) Epoch 9, batch 1250, loss[loss=0.1662, simple_loss=0.2402, pruned_loss=0.04604, over 6792.00 frames.], tot_loss[loss=0.188, simple_loss=0.2717, pruned_loss=0.05216, over 1416180.05 frames.], batch size: 15, lr: 8.40e-04
2022-05-14 07:57:02,080 INFO [train.py:812] (3/8) Epoch 9, batch 1300, loss[loss=0.2486, simple_loss=0.3074, pruned_loss=0.09491, over 7161.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2722, pruned_loss=0.05232, over 1413088.70 frames.], batch size: 19, lr: 8.39e-04
2022-05-14 07:58:01,340 INFO [train.py:812] (3/8) Epoch 9, batch 1350, loss[loss=0.1552, simple_loss=0.2416, pruned_loss=0.03445, over 7411.00 frames.], tot_loss[loss=0.1894, simple_loss=0.273, pruned_loss=0.05284, over 1418502.58 frames.], batch size: 20, lr: 8.39e-04
2022-05-14 07:59:00,867 INFO [train.py:812] (3/8) Epoch 9, batch 1400, loss[loss=0.1891, simple_loss=0.2827, pruned_loss=0.04772, over 7222.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2727, pruned_loss=0.05244, over 1415140.87 frames.], batch size: 21, lr: 8.38e-04
2022-05-14 07:59:57,887 INFO [train.py:812] (3/8) Epoch 9, batch 1450, loss[loss=0.1601, simple_loss=0.255, pruned_loss=0.03265, over 7321.00 frames.], tot_loss[loss=0.187, simple_loss=0.2711, pruned_loss=0.05144, over 1419866.44 frames.], batch size: 21, lr: 8.38e-04
2022-05-14 08:00:55,601 INFO [train.py:812] (3/8) Epoch 9, batch 1500, loss[loss=0.1847, simple_loss=0.2727, pruned_loss=0.04834, over 7234.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2718, pruned_loss=0.05166, over 1422997.63 frames.], batch size: 20, lr: 8.37e-04
2022-05-14 08:01:53,800 INFO [train.py:812] (3/8) Epoch 9, batch 1550, loss[loss=0.1933, simple_loss=0.2774, pruned_loss=0.05458, over 7208.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2715, pruned_loss=0.05171, over 1422444.40 frames.], batch size: 22, lr: 8.37e-04
2022-05-14 08:02:51,997 INFO [train.py:812] (3/8) Epoch 9, batch 1600, loss[loss=0.1685, simple_loss=0.2503, pruned_loss=0.04331, over 7055.00 frames.], tot_loss[loss=0.1887, simple_loss=0.273, pruned_loss=0.05222, over 1420359.31 frames.], batch size: 18, lr: 8.36e-04
2022-05-14 08:03:49,502 INFO [train.py:812] (3/8) Epoch 9, batch 1650, loss[loss=0.1917, simple_loss=0.2741, pruned_loss=0.05464, over 7116.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2733, pruned_loss=0.05245, over 1422013.79 frames.], batch size: 21, lr: 8.35e-04
2022-05-14 08:04:47,909 INFO [train.py:812] (3/8) Epoch 9, batch 1700, loss[loss=0.209, simple_loss=0.2868, pruned_loss=0.06562, over 7148.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.05247, over 1420810.96 frames.], batch size: 20, lr: 8.35e-04
2022-05-14 08:05:46,546 INFO [train.py:812] (3/8) Epoch 9, batch 1750, loss[loss=0.1991, simple_loss=0.292, pruned_loss=0.05311, over 7316.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2732, pruned_loss=0.05214, over 1422840.65 frames.], batch size: 21, lr: 8.34e-04
2022-05-14 08:06:45,595 INFO [train.py:812] (3/8) Epoch 9, batch 1800, loss[loss=0.2179, simple_loss=0.3026, pruned_loss=0.06667, over 7230.00 frames.], tot_loss[loss=0.1897, simple_loss=0.274, pruned_loss=0.05273, over 1419386.31 frames.], batch size: 20, lr: 8.34e-04
2022-05-14 08:07:45,059 INFO [train.py:812] (3/8) Epoch 9, batch 1850, loss[loss=0.188, simple_loss=0.2739, pruned_loss=0.05105, over 7224.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2741, pruned_loss=0.0527, over 1421768.10 frames.], batch size: 20, lr: 8.33e-04
2022-05-14 08:08:44,926 INFO [train.py:812] (3/8) Epoch 9, batch 1900, loss[loss=0.1812, simple_loss=0.2661, pruned_loss=0.0482, over 7160.00 frames.], tot_loss[loss=0.191, simple_loss=0.2752, pruned_loss=0.05336, over 1420030.35 frames.], batch size: 19, lr: 8.33e-04
2022-05-14 08:09:44,294 INFO [train.py:812] (3/8) Epoch 9, batch 1950, loss[loss=0.1878, simple_loss=0.279, pruned_loss=0.04828, over 7111.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2745, pruned_loss=0.05329, over 1421378.35 frames.], batch size: 21, lr: 8.32e-04
2022-05-14 08:10:44,187 INFO [train.py:812] (3/8) Epoch 9, batch 2000, loss[loss=0.2221, simple_loss=0.3008, pruned_loss=0.07174, over 7273.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2737, pruned_loss=0.05277, over 1422643.83 frames.], batch size: 24, lr: 8.32e-04
2022-05-14 08:11:43,643 INFO [train.py:812] (3/8) Epoch 9, batch 2050, loss[loss=0.1691, simple_loss=0.25, pruned_loss=0.04405, over 7283.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2737, pruned_loss=0.05308, over 1420990.67 frames.], batch size: 17, lr: 8.31e-04
2022-05-14 08:12:43,307 INFO [train.py:812] (3/8) Epoch 9, batch 2100, loss[loss=0.1864, simple_loss=0.2581, pruned_loss=0.05733, over 7264.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2739, pruned_loss=0.05328, over 1423188.47 frames.], batch size: 19, lr: 8.31e-04
2022-05-14 08:13:42,060 INFO [train.py:812] (3/8) Epoch 9, batch 2150, loss[loss=0.1613, simple_loss=0.2462, pruned_loss=0.03816, over 7067.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2735, pruned_loss=0.05295, over 1426053.70 frames.], batch size: 18, lr: 8.30e-04
2022-05-14 08:14:40,835 INFO [train.py:812] (3/8) Epoch 9, batch 2200, loss[loss=0.1726, simple_loss=0.2454, pruned_loss=0.04989, over 7295.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2731, pruned_loss=0.05276, over 1424231.28 frames.], batch size: 17, lr: 8.30e-04
2022-05-14 08:15:40,315 INFO [train.py:812] (3/8) Epoch 9, batch 2250, loss[loss=0.1992, simple_loss=0.2766, pruned_loss=0.0609, over 7157.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2737, pruned_loss=0.05302, over 1424714.72 frames.], batch size: 18, lr: 8.29e-04
2022-05-14 08:16:40,193 INFO [train.py:812] (3/8) Epoch 9, batch 2300, loss[loss=0.1765, simple_loss=0.2611, pruned_loss=0.04596, over 7154.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2733, pruned_loss=0.05268, over 1426228.31 frames.], batch size: 20, lr: 8.29e-04
2022-05-14 08:17:37,460 INFO [train.py:812] (3/8) Epoch 9, batch 2350, loss[loss=0.1936, simple_loss=0.2785, pruned_loss=0.05433, over 6728.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2742, pruned_loss=0.05301, over 1424905.36 frames.], batch size: 31, lr: 8.28e-04
2022-05-14 08:18:37,098 INFO [train.py:812] (3/8) Epoch 9, batch 2400, loss[loss=0.1971, simple_loss=0.2689, pruned_loss=0.06265, over 7287.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2742, pruned_loss=0.05298, over 1424967.43 frames.], batch size: 18, lr: 8.28e-04
2022-05-14 08:19:36,151 INFO [train.py:812] (3/8) Epoch 9, batch 2450, loss[loss=0.1729, simple_loss=0.2476, pruned_loss=0.04907, over 7406.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2739, pruned_loss=0.05287, over 1425996.51 frames.], batch size: 18, lr: 8.27e-04
2022-05-14 08:20:34,799 INFO [train.py:812] (3/8) Epoch 9, batch 2500, loss[loss=0.2118, simple_loss=0.3105, pruned_loss=0.05652, over 7206.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2744, pruned_loss=0.05298, over 1423671.70 frames.], batch size: 22, lr: 8.27e-04
2022-05-14 08:21:43,991 INFO [train.py:812] (3/8) Epoch 9, batch 2550, loss[loss=0.1489, simple_loss=0.236, pruned_loss=0.03094, over 7141.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2735, pruned_loss=0.05305, over 1421083.83 frames.], batch size: 17, lr: 8.26e-04
2022-05-14 08:22:42,428 INFO [train.py:812] (3/8) Epoch 9, batch 2600, loss[loss=0.2145, simple_loss=0.3079, pruned_loss=0.06052, over 7365.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2744, pruned_loss=0.05316, over 1418526.56 frames.], batch size: 23, lr: 8.25e-04
2022-05-14 08:23:41,191 INFO [train.py:812] (3/8) Epoch 9, batch 2650, loss[loss=0.2153, simple_loss=0.2907, pruned_loss=0.06995, over 5211.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2736, pruned_loss=0.05278, over 1417279.85 frames.], batch size: 52, lr: 8.25e-04
2022-05-14 08:24:39,447 INFO [train.py:812] (3/8) Epoch 9, batch 2700, loss[loss=0.2012, simple_loss=0.2862, pruned_loss=0.0581, over 7328.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2737, pruned_loss=0.05263, over 1418850.47 frames.], batch size: 22, lr: 8.24e-04
2022-05-14 08:25:38,280 INFO [train.py:812] (3/8) Epoch 9, batch 2750, loss[loss=0.1834, simple_loss=0.2653, pruned_loss=0.05074, over 7324.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2731, pruned_loss=0.0522, over 1423170.22 frames.], batch size: 20, lr: 8.24e-04
2022-05-14 08:26:37,733 INFO [train.py:812] (3/8) Epoch 9, batch 2800, loss[loss=0.222, simple_loss=0.2965, pruned_loss=0.0738, over 7184.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2727, pruned_loss=0.05185, over 1426557.03 frames.], batch size: 22, lr: 8.23e-04
2022-05-14 08:27:35,905 INFO [train.py:812] (3/8) Epoch 9, batch 2850, loss[loss=0.1931, simple_loss=0.2818, pruned_loss=0.05217, over 7155.00 frames.], tot_loss[loss=0.1871, simple_loss=0.272, pruned_loss=0.05114, over 1428849.65 frames.], batch size: 19, lr: 8.23e-04
2022-05-14 08:28:33,956 INFO [train.py:812] (3/8) Epoch 9, batch 2900, loss[loss=0.2011, simple_loss=0.2868, pruned_loss=0.05777, over 7327.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2714, pruned_loss=0.05069, over 1426815.29 frames.], batch size: 21, lr: 8.22e-04
2022-05-14 08:29:31,236 INFO [train.py:812] (3/8) Epoch 9, batch 2950, loss[loss=0.183, simple_loss=0.2545, pruned_loss=0.05572, over 7276.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2731, pruned_loss=0.0519, over 1422571.23 frames.], batch size: 18, lr: 8.22e-04
2022-05-14 08:30:30,199 INFO [train.py:812] (3/8) Epoch 9, batch 3000, loss[loss=0.184, simple_loss=0.2722, pruned_loss=0.04791, over 7305.00 frames.], tot_loss[loss=0.188, simple_loss=0.2728, pruned_loss=0.05164, over 1420768.49 frames.], batch size: 24, lr: 8.21e-04
2022-05-14 08:30:30,200 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 08:30:38,338 INFO [train.py:841] (3/8) Epoch 9, validation: loss=0.1602, simple_loss=0.262, pruned_loss=0.0292, over 698248.00 frames.
2022-05-14 08:31:37,158 INFO [train.py:812] (3/8) Epoch 9, batch 3050, loss[loss=0.185, simple_loss=0.269, pruned_loss=0.05048, over 7325.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2726, pruned_loss=0.0518, over 1417245.41 frames.], batch size: 20, lr: 8.21e-04
2022-05-14 08:32:34,697 INFO [train.py:812] (3/8) Epoch 9, batch 3100, loss[loss=0.2201, simple_loss=0.308, pruned_loss=0.06607, over 6716.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2739, pruned_loss=0.05247, over 1412759.49 frames.], batch size: 31, lr: 8.20e-04
2022-05-14 08:33:32,679 INFO [train.py:812] (3/8) Epoch 9, batch 3150, loss[loss=0.214, simple_loss=0.3006, pruned_loss=0.06369, over 7151.00 frames.], tot_loss[loss=0.189, simple_loss=0.2733, pruned_loss=0.05234, over 1417245.74 frames.], batch size: 19, lr: 8.20e-04
2022-05-14 08:34:32,437 INFO [train.py:812] (3/8) Epoch 9, batch 3200, loss[loss=0.1654, simple_loss=0.2637, pruned_loss=0.03356, over 7148.00 frames.], tot_loss[loss=0.189, simple_loss=0.273, pruned_loss=0.05254, over 1420538.50 frames.], batch size: 20, lr: 8.19e-04
2022-05-14 08:35:31,438 INFO [train.py:812] (3/8) Epoch 9, batch 3250, loss[loss=0.2635, simple_loss=0.3221, pruned_loss=0.1025, over 5133.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2722, pruned_loss=0.05206, over 1418905.65 frames.], batch size: 54, lr: 8.19e-04
2022-05-14 08:36:46,151 INFO [train.py:812] (3/8) Epoch 9, batch 3300, loss[loss=0.1907, simple_loss=0.2758, pruned_loss=0.05279, over 7218.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2715, pruned_loss=0.05155, over 1419169.99 frames.], batch size: 22, lr: 8.18e-04
2022-05-14 08:37:52,672 INFO [train.py:812] (3/8) Epoch 9, batch 3350, loss[loss=0.1714, simple_loss=0.252, pruned_loss=0.04539, over 7247.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2714, pruned_loss=0.05139, over 1423203.03 frames.], batch size: 19, lr: 8.18e-04
2022-05-14 08:38:51,540 INFO [train.py:812] (3/8) Epoch 9, batch 3400, loss[loss=0.208, simple_loss=0.2938, pruned_loss=0.06109, over 6740.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2725, pruned_loss=0.052, over 1421616.06 frames.], batch size: 31, lr: 8.17e-04
2022-05-14 08:39:59,367 INFO [train.py:812] (3/8) Epoch 9, batch 3450, loss[loss=0.1713, simple_loss=0.2531, pruned_loss=0.04479, over 7402.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2728, pruned_loss=0.05215, over 1423832.00 frames.], batch size: 18, lr: 8.17e-04
2022-05-14 08:41:27,464 INFO [train.py:812] (3/8) Epoch 9, batch 3500, loss[loss=0.1804, simple_loss=0.2621, pruned_loss=0.0494, over 7151.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2728, pruned_loss=0.05201, over 1424690.79 frames.], batch size: 19, lr: 8.16e-04
2022-05-14 08:42:35,753 INFO [train.py:812] (3/8) Epoch 9, batch 3550, loss[loss=0.1804, simple_loss=0.2595, pruned_loss=0.05064, over 7174.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2722, pruned_loss=0.05142, over 1426081.22 frames.], batch size: 18, lr: 8.16e-04
2022-05-14 08:43:34,796 INFO [train.py:812] (3/8) Epoch 9, batch 3600, loss[loss=0.1686, simple_loss=0.2491, pruned_loss=0.04404, over 7270.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2728, pruned_loss=0.05176, over 1423985.55 frames.], batch size: 18, lr: 8.15e-04
2022-05-14 08:44:32,169 INFO [train.py:812] (3/8) Epoch 9, batch 3650, loss[loss=0.1685, simple_loss=0.244, pruned_loss=0.04643, over 7147.00 frames.], tot_loss[loss=0.188, simple_loss=0.2723, pruned_loss=0.05184, over 1425997.27 frames.], batch size: 17, lr: 8.15e-04
2022-05-14 08:45:31,305 INFO [train.py:812] (3/8) Epoch 9, batch 3700, loss[loss=0.1932, simple_loss=0.2862, pruned_loss=0.05015, over 7298.00 frames.], tot_loss[loss=0.189, simple_loss=0.2734, pruned_loss=0.05234, over 1426817.84 frames.], batch size: 25, lr: 8.14e-04
2022-05-14 08:46:29,952 INFO [train.py:812] (3/8) Epoch 9, batch 3750, loss[loss=0.1986, simple_loss=0.2795, pruned_loss=0.05885, over 7421.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2737, pruned_loss=0.05244, over 1425021.35 frames.], batch size: 20, lr: 8.14e-04
2022-05-14 08:47:28,945 INFO [train.py:812] (3/8) Epoch 9, batch 3800, loss[loss=0.1595, simple_loss=0.2414, pruned_loss=0.03878, over 7416.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2739, pruned_loss=0.05229, over 1426924.96 frames.], batch size: 18, lr: 8.13e-04
2022-05-14 08:48:27,796 INFO [train.py:812] (3/8) Epoch 9, batch 3850, loss[loss=0.1594, simple_loss=0.242, pruned_loss=0.03838, over 7280.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2734, pruned_loss=0.05186, over 1429016.29 frames.], batch size: 17, lr: 8.13e-04
2022-05-14 08:49:26,888 INFO [train.py:812] (3/8) Epoch 9, batch 3900, loss[loss=0.2316, simple_loss=0.3049, pruned_loss=0.07917, over 4598.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2745, pruned_loss=0.0523, over 1426186.95 frames.], batch size: 52, lr: 8.12e-04
2022-05-14 08:50:26,272 INFO [train.py:812] (3/8) Epoch 9, batch 3950, loss[loss=0.1983, simple_loss=0.2883, pruned_loss=0.05414, over 6658.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2741, pruned_loss=0.05243, over 1427218.16 frames.], batch size: 31, lr: 8.12e-04
2022-05-14 08:51:25,796 INFO [train.py:812] (3/8) Epoch 9, batch 4000, loss[loss=0.1673, simple_loss=0.2597, pruned_loss=0.03751, over 7231.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2749, pruned_loss=0.05289, over 1426724.13 frames.], batch size: 21, lr: 8.11e-04
2022-05-14 08:52:25,217 INFO [train.py:812] (3/8) Epoch 9, batch 4050, loss[loss=0.1577, simple_loss=0.2312, pruned_loss=0.04212, over 7413.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2743, pruned_loss=0.05293, over 1426235.95 frames.], batch size: 18, lr: 8.11e-04
2022-05-14 08:53:24,987 INFO [train.py:812] (3/8) Epoch 9, batch 4100, loss[loss=0.181, simple_loss=0.2487, pruned_loss=0.05665, over 7128.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2741, pruned_loss=0.05286, over 1426476.25 frames.], batch size: 17, lr: 8.10e-04
2022-05-14 08:54:24,671 INFO [train.py:812] (3/8) Epoch 9, batch 4150, loss[loss=0.2346, simple_loss=0.3265, pruned_loss=0.07135, over 7070.00 frames.], tot_loss[loss=0.1888, simple_loss=0.273, pruned_loss=0.05234, over 1421752.82 frames.], batch size: 28, lr: 8.10e-04
2022-05-14 08:55:24,379 INFO [train.py:812] (3/8) Epoch 9, batch 4200, loss[loss=0.1614, simple_loss=0.2466, pruned_loss=0.03805, over 7317.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2713, pruned_loss=0.05163, over 1423844.85 frames.], batch size: 20, lr: 8.09e-04
2022-05-14 08:56:23,001 INFO [train.py:812] (3/8) Epoch 9, batch 4250, loss[loss=0.161, simple_loss=0.2462, pruned_loss=0.03795, over 7140.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2714, pruned_loss=0.05168, over 1419721.92 frames.], batch size: 17, lr: 8.09e-04
2022-05-14 08:57:22,981 INFO [train.py:812] (3/8) Epoch 9, batch 4300, loss[loss=0.1931, simple_loss=0.2798, pruned_loss=0.05322, over 7408.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2704, pruned_loss=0.0517, over 1415378.38 frames.], batch size: 21, lr: 8.08e-04
2022-05-14 08:58:21,477 INFO [train.py:812] (3/8) Epoch 9, batch 4350, loss[loss=0.1716, simple_loss=0.2476, pruned_loss=0.04781, over 7303.00 frames.], tot_loss[loss=0.1864, simple_loss=0.27, pruned_loss=0.05137, over 1420776.33 frames.], batch size: 17, lr: 8.08e-04
2022-05-14 08:59:21,257 INFO [train.py:812] (3/8) Epoch 9, batch 4400, loss[loss=0.1856, simple_loss=0.2735, pruned_loss=0.04888, over 7086.00 frames.], tot_loss[loss=0.1861, simple_loss=0.27, pruned_loss=0.0511, over 1416912.45 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:00:19,275 INFO [train.py:812] (3/8) Epoch 9, batch 4450, loss[loss=0.1998, simple_loss=0.2868, pruned_loss=0.05634, over 7051.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2689, pruned_loss=0.05098, over 1411342.60 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:01:19,088 INFO [train.py:812] (3/8) Epoch 9, batch 4500, loss[loss=0.1973, simple_loss=0.2796, pruned_loss=0.05746, over 7076.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2699, pruned_loss=0.05145, over 1393787.27 frames.], batch size: 28, lr: 8.07e-04
2022-05-14 09:02:17,159 INFO [train.py:812] (3/8) Epoch 9, batch 4550, loss[loss=0.1928, simple_loss=0.278, pruned_loss=0.05381, over 6163.00 frames.], tot_loss[loss=0.191, simple_loss=0.2745, pruned_loss=0.05372, over 1353784.64 frames.], batch size: 37, lr: 8.06e-04
2022-05-14 09:03:24,796 INFO [train.py:812] (3/8) Epoch 10, batch 0, loss[loss=0.1981, simple_loss=0.2862, pruned_loss=0.05495, over 7412.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2862, pruned_loss=0.05495, over 7412.00 frames.], batch size: 21, lr: 7.75e-04
2022-05-14 09:04:24,007 INFO [train.py:812] (3/8) Epoch 10, batch 50, loss[loss=0.1958, simple_loss=0.2913, pruned_loss=0.05019, over 7194.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2735, pruned_loss=0.05189, over 321561.75 frames.], batch size: 23, lr: 7.74e-04
2022-05-14 09:05:23,094 INFO [train.py:812] (3/8) Epoch 10, batch 100, loss[loss=0.2019, simple_loss=0.2711, pruned_loss=0.06638, over 5039.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2713, pruned_loss=0.05147, over 557162.87 frames.], batch size: 52, lr: 7.74e-04
2022-05-14 09:06:22,293 INFO [train.py:812] (3/8) Epoch 10, batch 150, loss[loss=0.1757, simple_loss=0.2679, pruned_loss=0.04169, over 7438.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2724, pruned_loss=0.05132, over 750619.71 frames.], batch size: 20, lr: 7.73e-04
2022-05-14 09:07:20,634 INFO [train.py:812] (3/8) Epoch 10, batch 200, loss[loss=0.1738, simple_loss=0.2657, pruned_loss=0.04092, over 7436.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2725, pruned_loss=0.05089, over 897776.72 frames.], batch size: 20, lr: 7.73e-04
2022-05-14 09:08:19,899 INFO [train.py:812] (3/8) Epoch 10, batch 250, loss[loss=0.1723, simple_loss=0.2561, pruned_loss=0.04426, over 7171.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2741, pruned_loss=0.05211, over 1010016.64 frames.], batch size: 18, lr: 7.72e-04
2022-05-14 09:09:19,089 INFO [train.py:812] (3/8) Epoch 10, batch 300, loss[loss=0.168, simple_loss=0.257, pruned_loss=0.0395, over 7312.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2729, pruned_loss=0.05173, over 1103940.30 frames.], batch size: 20, lr: 7.72e-04
2022-05-14 09:10:16,340 INFO [train.py:812] (3/8) Epoch 10, batch 350, loss[loss=0.1885, simple_loss=0.2779, pruned_loss=0.04952, over 7191.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2717, pruned_loss=0.05067, over 1172625.35 frames.], batch size: 23, lr: 7.71e-04
2022-05-14 09:11:15,058 INFO [train.py:812] (3/8) Epoch 10, batch 400, loss[loss=0.1918, simple_loss=0.2812, pruned_loss=0.05116, over 7172.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2729, pruned_loss=0.05102, over 1222766.80 frames.], batch size: 26, lr: 7.71e-04
2022-05-14 09:12:14,136 INFO [train.py:812] (3/8) Epoch 10, batch 450, loss[loss=0.1842, simple_loss=0.2693, pruned_loss=0.04959, over 6391.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2734, pruned_loss=0.05154, over 1261894.81 frames.], batch size: 38, lr: 7.71e-04
2022-05-14 09:13:13,707 INFO [train.py:812] (3/8) Epoch 10, batch 500, loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03088, over 7148.00 frames.], tot_loss[loss=0.189, simple_loss=0.274, pruned_loss=0.05195, over 1297078.80 frames.], batch size: 19, lr: 7.70e-04
2022-05-14 09:14:12,264 INFO [train.py:812] (3/8) Epoch 10, batch 550, loss[loss=0.1627, simple_loss=0.2551, pruned_loss=0.03517, over 7122.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2733, pruned_loss=0.05154, over 1324718.04 frames.], batch size: 17, lr: 7.70e-04
2022-05-14 09:15:10,133 INFO [train.py:812] (3/8) Epoch 10, batch 600, loss[loss=0.163, simple_loss=0.2474, pruned_loss=0.03932, over 7284.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2718, pruned_loss=0.05066, over 1345649.46 frames.], batch size: 18, lr: 7.69e-04
2022-05-14 09:16:08,399 INFO [train.py:812] (3/8) Epoch 10, batch 650, loss[loss=0.2217, simple_loss=0.3021, pruned_loss=0.07063, over 7176.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2716, pruned_loss=0.05061, over 1362020.64 frames.], batch size: 26, lr: 7.69e-04
2022-05-14 09:17:07,956 INFO [train.py:812] (3/8) Epoch 10, batch 700, loss[loss=0.1718, simple_loss=0.2615, pruned_loss=0.04109, over 7306.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2703, pruned_loss=0.04977, over 1376436.69 frames.], batch size: 25, lr: 7.68e-04
2022-05-14 09:18:07,537 INFO [train.py:812] (3/8) Epoch 10, batch 750, loss[loss=0.1845, simple_loss=0.2645, pruned_loss=0.05224, over 7426.00 frames.], tot_loss[loss=0.184, simple_loss=0.2694, pruned_loss=0.04929, over 1387152.80 frames.], batch size: 20, lr: 7.68e-04
2022-05-14 09:19:06,534 INFO [train.py:812] (3/8) Epoch 10, batch 800, loss[loss=0.2018, simple_loss=0.2884, pruned_loss=0.05762, over 7298.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04905, over 1394104.95 frames.], batch size: 24, lr: 7.67e-04
2022-05-14 09:20:06,000 INFO [train.py:812] (3/8) Epoch 10, batch 850, loss[loss=0.2031, simple_loss=0.2866, pruned_loss=0.05981, over 6484.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2702, pruned_loss=0.04985, over 1396474.27 frames.], batch size: 38, lr: 7.67e-04
2022-05-14 09:21:05,091 INFO [train.py:812] (3/8) Epoch 10, batch 900, loss[loss=0.1837, simple_loss=0.2769, pruned_loss=0.04524, over 7318.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2702, pruned_loss=0.0497, over 1406603.43 frames.], batch size: 21, lr: 7.66e-04
2022-05-14 09:22:03,786 INFO [train.py:812] (3/8) Epoch 10, batch 950, loss[loss=0.2117, simple_loss=0.3006, pruned_loss=0.06138, over 7143.00 frames.], tot_loss[loss=0.1855, simple_loss=0.271, pruned_loss=0.05001, over 1407447.75 frames.], batch size: 26, lr: 7.66e-04
2022-05-14 09:23:02,560 INFO [train.py:812] (3/8) Epoch 10, batch 1000, loss[loss=0.1768, simple_loss=0.2684, pruned_loss=0.04259, over 7330.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2709, pruned_loss=0.04989, over 1414631.14 frames.], batch size: 20, lr: 7.66e-04
2022-05-14 09:24:00,902 INFO [train.py:812] (3/8) Epoch 10, batch 1050, loss[loss=0.1919, simple_loss=0.2756, pruned_loss=0.05408, over 7046.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2712, pruned_loss=0.05026, over 1416716.51 frames.], batch size: 28, lr: 7.65e-04
2022-05-14 09:24:59,369 INFO [train.py:812] (3/8) Epoch 10, batch 1100, loss[loss=0.1773, simple_loss=0.2679, pruned_loss=0.04339, over 7121.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2717, pruned_loss=0.05044, over 1417728.81 frames.], batch size: 28, lr: 7.65e-04
2022-05-14 09:25:57,284 INFO [train.py:812] (3/8) Epoch 10, batch 1150, loss[loss=0.1805, simple_loss=0.2653, pruned_loss=0.04791, over 7324.00 frames.], tot_loss[loss=0.1856, simple_loss=0.271, pruned_loss=0.05011, over 1422086.22 frames.], batch size: 20, lr: 7.64e-04
2022-05-14 09:26:55,696 INFO [train.py:812] (3/8) Epoch 10, batch 1200, loss[loss=0.205, simple_loss=0.2961, pruned_loss=0.05689, over 7198.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2721, pruned_loss=0.05025, over 1420687.40 frames.], batch size: 23, lr: 7.64e-04
2022-05-14 09:27:55,412 INFO [train.py:812] (3/8) Epoch 10, batch 1250, loss[loss=0.151, simple_loss=0.231, pruned_loss=0.03551, over 7275.00 frames.], tot_loss[loss=0.186, simple_loss=0.2717, pruned_loss=0.05017, over 1418361.42 frames.], batch size: 17, lr: 7.63e-04
2022-05-14 09:28:54,708 INFO [train.py:812] (3/8) Epoch 10, batch 1300, loss[loss=0.171, simple_loss=0.2546, pruned_loss=0.04365, over 7004.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2706, pruned_loss=0.05008, over 1415862.83 frames.], batch size: 16, lr: 7.63e-04
2022-05-14 09:29:54,194 INFO [train.py:812] (3/8) Epoch 10, batch 1350, loss[loss=0.1864, simple_loss=0.2796, pruned_loss=0.04659, over 7324.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2712, pruned_loss=0.05047, over 1416537.15 frames.], batch size: 21, lr: 7.62e-04
2022-05-14 09:30:53,025 INFO [train.py:812] (3/8) Epoch 10, batch 1400, loss[loss=0.1834, simple_loss=0.2719, pruned_loss=0.0475, over 7116.00 frames.], tot_loss[loss=0.1863, simple_loss=0.272, pruned_loss=0.0503, over 1419294.23 frames.], batch size: 21, lr: 7.62e-04
2022-05-14 09:31:52,533 INFO [train.py:812] (3/8) Epoch 10, batch 1450, loss[loss=0.2241, simple_loss=0.314, pruned_loss=0.06713, over 7325.00 frames.], tot_loss[loss=0.1859, simple_loss=0.271, pruned_loss=0.05034, over 1420788.26 frames.], batch size: 25, lr: 7.62e-04
2022-05-14 09:32:51,539 INFO [train.py:812] (3/8) Epoch 10, batch 1500, loss[loss=0.2244, simple_loss=0.3069, pruned_loss=0.07093, over 5170.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2716, pruned_loss=0.05052, over 1416172.00 frames.], batch size: 53, lr: 7.61e-04
2022-05-14 09:33:51,502 INFO [train.py:812] (3/8) Epoch 10, batch 1550, loss[loss=0.1566, simple_loss=0.2483, pruned_loss=0.03243, over 7350.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2712, pruned_loss=0.0502, over 1420249.15 frames.], batch size: 19, lr: 7.61e-04
2022-05-14 09:34:49,172 INFO [train.py:812] (3/8) Epoch 10, batch 1600, loss[loss=0.1969, simple_loss=0.2771, pruned_loss=0.05832, over 7266.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2713, pruned_loss=0.0504, over 1419474.28 frames.], batch size: 19, lr: 7.60e-04
2022-05-14 09:35:46,383 INFO [train.py:812] (3/8) Epoch 10, batch 1650, loss[loss=0.1883, simple_loss=0.2739, pruned_loss=0.0513, over 7418.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2713, pruned_loss=0.05049, over 1417564.98 frames.], batch size: 21, lr: 7.60e-04
2022-05-14 09:36:44,421 INFO [train.py:812] (3/8) Epoch 10, batch 1700, loss[loss=0.228, simple_loss=0.3245, pruned_loss=0.06574, over 7293.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2706, pruned_loss=0.05009, over 1414873.83 frames.], batch size: 24, lr: 7.59e-04
2022-05-14 09:37:43,566 INFO [train.py:812] (3/8) Epoch 10, batch 1750, loss[loss=0.1935, simple_loss=0.2636, pruned_loss=0.06166, over 7238.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2715, pruned_loss=0.05104, over 1405919.03 frames.], batch size: 16, lr: 7.59e-04
2022-05-14 09:38:41,641 INFO [train.py:812] (3/8) Epoch 10, batch 1800, loss[loss=0.1851, simple_loss=0.2743, pruned_loss=0.04796, over 7350.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2713, pruned_loss=0.05065, over 1411323.20 frames.], batch size: 19, lr: 7.59e-04
2022-05-14 09:39:39,847 INFO [train.py:812] (3/8) Epoch 10, batch 1850, loss[loss=0.2143, simple_loss=0.2917, pruned_loss=0.0684, over 7366.00 frames.], tot_loss[loss=0.187, simple_loss=0.2719, pruned_loss=0.05101, over 1412125.96 frames.], batch size: 19, lr: 7.58e-04
2022-05-14 09:40:38,491 INFO [train.py:812] (3/8) Epoch 10, batch 1900, loss[loss=0.1806, simple_loss=0.2612, pruned_loss=0.04996, over 7278.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2707, pruned_loss=0.05036, over 1415868.02 frames.], batch size: 18, lr: 7.58e-04
2022-05-14 09:41:37,147 INFO [train.py:812] (3/8) Epoch 10, batch 1950, loss[loss=0.1907, simple_loss=0.2902, pruned_loss=0.04555, over 7218.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2708, pruned_loss=0.05031, over 1414893.19 frames.], batch size: 23, lr: 7.57e-04
2022-05-14 09:42:35,055 INFO [train.py:812] (3/8) Epoch 10, batch 2000, loss[loss=0.2068, simple_loss=0.2977, pruned_loss=0.05797, over 7224.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2701, pruned_loss=0.04999, over 1417720.57 frames.], batch size: 20, lr: 7.57e-04
2022-05-14 09:43:34,860 INFO [train.py:812] (3/8) Epoch 10, batch 2050, loss[loss=0.2111, simple_loss=0.2965, pruned_loss=0.06284, over 7182.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2708, pruned_loss=0.05028, over 1419860.10 frames.], batch size: 23, lr: 7.56e-04
2022-05-14 09:44:34,078 INFO [train.py:812] (3/8) Epoch 10, batch 2100, loss[loss=0.2108, simple_loss=0.2891, pruned_loss=0.06624, over 7152.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2694, pruned_loss=0.04934, over 1424277.29 frames.], batch size: 20, lr: 7.56e-04
2022-05-14 09:45:31,439 INFO [train.py:812] (3/8) Epoch 10, batch 2150, loss[loss=0.1632, simple_loss=0.2355, pruned_loss=0.0455, over 7419.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2674, pruned_loss=0.04823, over 1426126.24 frames.], batch size: 18, lr: 7.56e-04
2022-05-14 09:46:28,653 INFO [train.py:812] (3/8) Epoch 10, batch 2200, loss[loss=0.2075, simple_loss=0.2894, pruned_loss=0.06282, over 6453.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2692, pruned_loss=0.04894, over 1426362.59 frames.], batch size: 38, lr: 7.55e-04
2022-05-14 09:47:27,357 INFO [train.py:812] (3/8) Epoch 10, batch 2250, loss[loss=0.1794, simple_loss=0.2701, pruned_loss=0.04437, over 7321.00 frames.], tot_loss[loss=0.1833, simple_loss=0.269, pruned_loss=0.04885, over 1427930.42 frames.], batch size: 21, lr: 7.55e-04
2022-05-14 09:48:25,598 INFO [train.py:812] (3/8) Epoch 10, batch 2300, loss[loss=0.1796, simple_loss=0.276, pruned_loss=0.04158, over 7140.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2707, pruned_loss=0.0495, over 1425697.66 frames.], batch size: 20, lr: 7.54e-04
2022-05-14 09:49:24,917 INFO [train.py:812] (3/8) Epoch 10, batch 2350, loss[loss=0.1972, simple_loss=0.2861, pruned_loss=0.05415, over 7216.00 frames.], tot_loss[loss=0.184, simple_loss=0.2693, pruned_loss=0.04932, over 1423795.85 frames.], batch size: 22, lr: 7.54e-04
2022-05-14 09:50:22,137 INFO [train.py:812] (3/8) Epoch 10, batch 2400, loss[loss=0.1959, simple_loss=0.2719, pruned_loss=0.05991, over 7288.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2693, pruned_loss=0.04943, over 1426027.39 frames.], batch size: 18, lr: 7.53e-04
2022-05-14 09:51:20,806 INFO [train.py:812] (3/8) Epoch 10, batch 2450, loss[loss=0.1672, simple_loss=0.2388, pruned_loss=0.04777, over 7074.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2688, pruned_loss=0.04919, over 1429672.60 frames.], batch size: 18, lr: 7.53e-04
2022-05-14 09:52:18,415 INFO [train.py:812] (3/8) Epoch 10, batch 2500, loss[loss=0.1791, simple_loss=0.272, pruned_loss=0.04312, over 7318.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2684, pruned_loss=0.04899, over 1428067.52 frames.], batch size: 21, lr: 7.53e-04
2022-05-14 09:53:18,400 INFO [train.py:812] (3/8) Epoch 10, batch 2550, loss[loss=0.1775, simple_loss=0.2708, pruned_loss=0.04208, over 7220.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2688, pruned_loss=0.04913, over 1426288.70 frames.], batch size: 21, lr: 7.52e-04
2022-05-14 09:54:18,146 INFO [train.py:812] (3/8) Epoch 10, batch 2600, loss[loss=0.226, simple_loss=0.3065, pruned_loss=0.07275, over 7177.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2695, pruned_loss=0.04933, over 1429681.75 frames.], batch size: 26, lr: 7.52e-04
2022-05-14 09:55:17,799 INFO [train.py:812] (3/8) Epoch 10, batch 2650, loss[loss=0.1626, simple_loss=0.2601, pruned_loss=0.03256, over 7325.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2702, pruned_loss=0.04935, over 1425316.39 frames.], batch size: 22, lr: 7.51e-04
2022-05-14 09:56:16,816 INFO [train.py:812] (3/8) Epoch 10, batch 2700, loss[loss=0.1747, simple_loss=0.2629, pruned_loss=0.04321, over 6906.00 frames.], tot_loss[loss=0.184, simple_loss=0.2695, pruned_loss=0.04921, over 1425756.39 frames.], batch size: 31, lr: 7.51e-04
2022-05-14 09:57:23,633 INFO [train.py:812] (3/8) Epoch 10, batch 2750, loss[loss=0.1528, simple_loss=0.2493, pruned_loss=0.02812, over 6795.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2688, pruned_loss=0.04894, over 1423769.43 frames.], batch size: 31, lr: 7.50e-04
2022-05-14 09:58:22,149 INFO [train.py:812] (3/8) Epoch 10, batch 2800, loss[loss=0.1806, simple_loss=0.2726, pruned_loss=0.04429, over 7372.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2679, pruned_loss=0.04839, over 1429183.86 frames.], batch size: 23, lr: 7.50e-04
2022-05-14 09:59:21,331 INFO [train.py:812] (3/8) Epoch 10, batch 2850, loss[loss=0.1887, simple_loss=0.2876, pruned_loss=0.04483, over 7336.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2688, pruned_loss=0.04877, over 1426595.97 frames.], batch size: 22, lr: 7.50e-04
2022-05-14 10:00:20,870 INFO [train.py:812] (3/8) Epoch 10, batch 2900, loss[loss=0.1964, simple_loss=0.2883, pruned_loss=0.0522, over 7114.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2688, pruned_loss=0.04916, over 1426350.60 frames.], batch size: 21, lr: 7.49e-04
2022-05-14 10:01:19,217 INFO [train.py:812] (3/8) Epoch 10, batch 2950, loss[loss=0.165, simple_loss=0.246, pruned_loss=0.04197, over 7292.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2686, pruned_loss=0.04916, over 1426165.75 frames.], batch size: 18, lr: 7.49e-04
2022-05-14 10:02:18,291 INFO [train.py:812] (3/8) Epoch 10, batch 3000, loss[loss=0.1842, simple_loss=0.2637, pruned_loss=0.05237, over 7303.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2686, pruned_loss=0.04937, over 1425757.56 frames.], batch size: 17, lr: 7.48e-04
2022-05-14 10:02:18,292 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 10:02:25,810 INFO [train.py:841] (3/8) Epoch 10, validation: loss=0.1584, simple_loss=0.26, pruned_loss=0.0284, over 698248.00 frames.
2022-05-14 10:03:25,424 INFO [train.py:812] (3/8) Epoch 10, batch 3050, loss[loss=0.2235, simple_loss=0.303, pruned_loss=0.07201, over 7153.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2684, pruned_loss=0.04943, over 1426458.93 frames.], batch size: 19, lr: 7.48e-04
2022-05-14 10:04:24,562 INFO [train.py:812] (3/8) Epoch 10, batch 3100, loss[loss=0.1896, simple_loss=0.2796, pruned_loss=0.04976, over 7112.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2694, pruned_loss=0.04939, over 1429176.59 frames.], batch size: 21, lr: 7.47e-04
2022-05-14 10:05:24,317 INFO [train.py:812] (3/8) Epoch 10, batch 3150, loss[loss=0.1784, simple_loss=0.2629, pruned_loss=0.04689, over 7319.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2695, pruned_loss=0.04939, over 1425759.31 frames.], batch size: 21, lr: 7.47e-04
2022-05-14 10:06:23,645 INFO [train.py:812] (3/8) Epoch 10, batch 3200, loss[loss=0.1857, simple_loss=0.2799, pruned_loss=0.04576, over 7242.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04883, over 1425917.03 frames.], batch size: 20, lr: 7.47e-04
2022-05-14 10:07:23,028 INFO [train.py:812] (3/8) Epoch 10, batch 3250, loss[loss=0.1812, simple_loss=0.2684, pruned_loss=0.04705, over 7419.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2693, pruned_loss=0.04923, over 1426589.80 frames.], batch size: 21, lr: 7.46e-04
2022-05-14 10:08:22,145 INFO [train.py:812] (3/8) Epoch 10, batch 3300, loss[loss=0.2123, simple_loss=0.3026, pruned_loss=0.06097, over 7214.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2687, pruned_loss=0.04873, over 1427739.83 frames.], batch size: 22, lr: 7.46e-04
2022-05-14 10:09:21,720 INFO [train.py:812] (3/8) Epoch 10, batch 3350, loss[loss=0.1681, simple_loss=0.2544, pruned_loss=0.04092, over 7197.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2691, pruned_loss=0.0489, over 1428622.50 frames.], batch size: 23, lr: 7.45e-04
2022-05-14 10:10:20,625 INFO [train.py:812] (3/8) Epoch 10, batch 3400, loss[loss=0.1529, simple_loss=0.2298, pruned_loss=0.03801, over 7267.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2685, pruned_loss=0.04883, over 1424815.22 frames.], batch size: 17, lr: 7.45e-04
2022-05-14 10:11:20,096 INFO [train.py:812] (3/8) Epoch 10, batch 3450, loss[loss=0.1669, simple_loss=0.2546, pruned_loss=0.03953, over 7275.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2684, pruned_loss=0.0487, over 1424435.13 frames.], batch size: 24, lr: 7.45e-04
2022-05-14 10:12:19,085 INFO [train.py:812] (3/8) Epoch 10, batch 3500, loss[loss=0.1995, simple_loss=0.2963, pruned_loss=0.05139, over 7403.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2684, pruned_loss=0.04861, over 1424982.43 frames.], batch size: 21, lr: 7.44e-04
2022-05-14 10:13:18,715 INFO [train.py:812] (3/8) Epoch 10, batch 3550, loss[loss=0.2039, simple_loss=0.2886, pruned_loss=0.05959, over 7063.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2678, pruned_loss=0.04841, over 1427518.85 frames.], batch size: 28, lr: 7.44e-04
2022-05-14 10:14:16,927 INFO [train.py:812] (3/8) Epoch 10, batch 3600, loss[loss=0.1915, simple_loss=0.2722, pruned_loss=0.05535, over 7132.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2679, pruned_loss=0.04858, over 1427744.25 frames.], batch size: 28, lr: 7.43e-04
2022-05-14 10:15:16,461 INFO [train.py:812] (3/8) Epoch 10, batch 3650, loss[loss=0.1529, simple_loss=0.2406, pruned_loss=0.03263, over 7060.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2671, pruned_loss=0.04814, over 1423120.04 frames.], batch size: 18, lr: 7.43e-04
2022-05-14 10:16:15,503 INFO [train.py:812] (3/8) Epoch 10, batch 3700, loss[loss=0.1307, simple_loss=0.2168, pruned_loss=0.02232, over 7282.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2671, pruned_loss=0.04768, over 1425178.30 frames.], batch size: 17, lr: 7.43e-04
2022-05-14 10:17:15,204 INFO [train.py:812] (3/8) Epoch 10, batch 3750, loss[loss=0.1645, simple_loss=0.2547, pruned_loss=0.03711, over 7166.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04779, over 1427638.16 frames.], batch size: 19, lr: 7.42e-04
2022-05-14 10:18:14,389 INFO [train.py:812] (3/8) Epoch 10, batch 3800, loss[loss=0.186, simple_loss=0.2766, pruned_loss=0.04777, over 7436.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2672, pruned_loss=0.04771, over 1425752.59 frames.], batch size: 20, lr: 7.42e-04
2022-05-14 10:19:12,953 INFO [train.py:812] (3/8) Epoch 10, batch 3850, loss[loss=0.1589, simple_loss=0.244, pruned_loss=0.03691, over 7059.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2693, pruned_loss=0.04878, over 1425191.43 frames.], batch size: 18, lr: 7.41e-04
2022-05-14 10:20:21,764 INFO [train.py:812] (3/8) Epoch 10, batch 3900, loss[loss=0.1814, simple_loss=0.2609, pruned_loss=0.05096, over 7162.00 frames.], tot_loss[loss=0.183, simple_loss=0.2686, pruned_loss=0.04873, over 1426933.65 frames.], batch size: 19, lr: 7.41e-04
2022-05-14 10:21:21,321 INFO [train.py:812] (3/8) Epoch 10, batch 3950, loss[loss=0.2124, simple_loss=0.2803, pruned_loss=0.07227, over 5072.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2691, pruned_loss=0.04908, over 1421676.77 frames.], batch size: 52, lr: 7.41e-04
2022-05-14 10:22:19,907 INFO [train.py:812] (3/8) Epoch 10, batch 4000, loss[loss=0.175, simple_loss=0.2811, pruned_loss=0.03445, over 7250.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2697, pruned_loss=0.0496, over 1422893.05 frames.], batch size: 19, lr: 7.40e-04
2022-05-14 10:23:18,818 INFO [train.py:812] (3/8) Epoch 10, batch 4050, loss[loss=0.2093, simple_loss=0.2846, pruned_loss=0.06703, over 7120.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2697, pruned_loss=0.04975, over 1423021.14 frames.], batch size: 17, lr: 7.40e-04
2022-05-14 10:24:16,984 INFO [train.py:812] (3/8) Epoch 10, batch 4100, loss[loss=0.197, simple_loss=0.2876, pruned_loss=0.05316, over 7313.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2694, pruned_loss=0.04918, over 1425298.93 frames.], batch size: 21, lr: 7.39e-04
2022-05-14 10:25:16,581 INFO [train.py:812] (3/8) Epoch 10, batch 4150, loss[loss=0.1639, simple_loss=0.2437, pruned_loss=0.04204, over 7398.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2694, pruned_loss=0.04885, over 1425070.06 frames.], batch size: 18, lr: 7.39e-04
2022-05-14 10:26:14,794 INFO [train.py:812] (3/8) Epoch 10, batch 4200, loss[loss=0.1929, simple_loss=0.2789, pruned_loss=0.0534, over 7289.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2692, pruned_loss=0.04891, over 1426593.90 frames.], batch size: 24, lr: 7.39e-04
2022-05-14 10:27:13,958 INFO [train.py:812] (3/8) Epoch 10, batch 4250, loss[loss=0.1591, simple_loss=0.2411, pruned_loss=0.0386, over 7267.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2703, pruned_loss=0.04971, over 1422375.39 frames.], batch size: 17, lr: 7.38e-04
2022-05-14 10:28:13,113 INFO [train.py:812] (3/8) Epoch 10, batch 4300, loss[loss=0.1994, simple_loss=0.2992, pruned_loss=0.04979, over 7288.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2703, pruned_loss=0.04943, over 1416453.54 frames.], batch size: 24, lr: 7.38e-04
2022-05-14 10:29:10,971 INFO [train.py:812] (3/8) Epoch 10, batch 4350, loss[loss=0.2373, simple_loss=0.3147, pruned_loss=0.07992, over 5170.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2726, pruned_loss=0.0506, over 1407817.37 frames.], batch size: 52, lr: 7.37e-04
2022-05-14 10:30:10,247 INFO [train.py:812] (3/8) Epoch 10, batch 4400, loss[loss=0.161, simple_loss=0.2505, pruned_loss=0.03579, over 7208.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2732, pruned_loss=0.05077, over 1411019.72 frames.], batch size: 22, lr: 7.37e-04
2022-05-14 10:31:10,027 INFO [train.py:812] (3/8) Epoch 10, batch 4450, loss[loss=0.2349, simple_loss=0.3014, pruned_loss=0.08423, over 5307.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2737, pruned_loss=0.05104, over 1395854.63 frames.], batch size: 52, lr: 7.37e-04
2022-05-14 10:32:09,141 INFO [train.py:812] (3/8) Epoch 10, batch 4500, loss[loss=0.1822, simple_loss=0.2696, pruned_loss=0.04743, over 7143.00 frames.], tot_loss[loss=0.1878, simple_loss=0.273, pruned_loss=0.05133, over 1391851.50 frames.], batch size: 20, lr: 7.36e-04
2022-05-14 10:33:08,617 INFO [train.py:812] (3/8) Epoch 10, batch 4550, loss[loss=0.198, simple_loss=0.2818, pruned_loss=0.05714, over 7179.00 frames.], tot_loss[loss=0.188, simple_loss=0.2726, pruned_loss=0.05169, over 1370304.42 frames.], batch size: 26, lr: 7.36e-04
2022-05-14 10:34:22,336 INFO [train.py:812] (3/8) Epoch 11, batch 0, loss[loss=0.1701, simple_loss=0.2505, pruned_loss=0.04482, over 7434.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2505, pruned_loss=0.04482, over 7434.00 frames.], batch size: 20, lr: 7.08e-04
2022-05-14 10:35:21,211 INFO [train.py:812] (3/8) Epoch 11, batch 50, loss[loss=0.1781, simple_loss=0.2654, pruned_loss=0.04535, over 7427.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2698, pruned_loss=0.04799, over 322750.35 frames.], batch size: 20, lr: 7.08e-04
2022-05-14 10:36:19,851 INFO [train.py:812] (3/8) Epoch 11, batch 100, loss[loss=0.1749, simple_loss=0.2541, pruned_loss=0.04781, over 7280.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2694, pruned_loss=0.04856, over 567033.27 frames.], batch size: 18, lr: 7.08e-04
2022-05-14 10:37:28,461 INFO [train.py:812] (3/8) Epoch 11, batch 150, loss[loss=0.1754, simple_loss=0.2509, pruned_loss=0.04996, over 6782.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2717, pruned_loss=0.04989, over 759735.15 frames.], batch size: 15, lr: 7.07e-04
2022-05-14 10:38:36,327 INFO [train.py:812] (3/8) Epoch 11, batch 200, loss[loss=0.1673, simple_loss=0.2498, pruned_loss=0.04239, over 7430.00 frames.], tot_loss[loss=0.184, simple_loss=0.2701, pruned_loss=0.04892, over 907386.09 frames.], batch size: 18, lr: 7.07e-04
2022-05-14 10:39:34,522 INFO [train.py:812] (3/8) Epoch 11, batch 250, loss[loss=0.1729, simple_loss=0.2632, pruned_loss=0.04124, over 6273.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2687, pruned_loss=0.04796, over 1023497.28 frames.], batch size: 38, lr: 7.06e-04
2022-05-14 10:40:50,465 INFO [train.py:812] (3/8) Epoch 11, batch 300, loss[loss=0.2008, simple_loss=0.2883, pruned_loss=0.05662, over 4987.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2681, pruned_loss=0.04785, over 1114221.35 frames.], batch size: 52, lr: 7.06e-04
2022-05-14 10:41:47,783 INFO [train.py:812] (3/8) Epoch 11, batch 350, loss[loss=0.1915, simple_loss=0.2829, pruned_loss=0.05007, over 6681.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2682, pruned_loss=0.04759, over 1186938.82 frames.], batch size: 31, lr: 7.06e-04
2022-05-14 10:43:03,922 INFO [train.py:812] (3/8) Epoch 11, batch 400, loss[loss=0.1916, simple_loss=0.28, pruned_loss=0.05162, over 7433.00 frames.], tot_loss[loss=0.1816, simple_loss=0.268, pruned_loss=0.04761, over 1241109.49 frames.], batch size: 20, lr: 7.05e-04
2022-05-14 10:44:13,173 INFO [train.py:812] (3/8) Epoch 11, batch 450, loss[loss=0.187, simple_loss=0.2758, pruned_loss=0.04912, over 7239.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2663, pruned_loss=0.04724, over 1280538.39 frames.], batch size: 20, lr: 7.05e-04
2022-05-14 10:45:12,653 INFO [train.py:812] (3/8) Epoch 11, batch 500, loss[loss=0.185, simple_loss=0.2705, pruned_loss=0.04976, over 7331.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2664, pruned_loss=0.04719, over 1315238.30 frames.], batch size: 20, lr: 7.04e-04
2022-05-14 10:46:12,010 INFO [train.py:812] (3/8) Epoch 11, batch 550, loss[loss=0.2032, simple_loss=0.2883, pruned_loss=0.05909, over 7072.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2664, pruned_loss=0.04714, over 1340685.35 frames.], batch size: 18, lr: 7.04e-04
2022-05-14 10:47:11,312 INFO [train.py:812] (3/8) Epoch 11, batch 600, loss[loss=0.15, simple_loss=0.2258, pruned_loss=0.03709, over 6993.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2667, pruned_loss=0.04726, over 1359558.93 frames.], batch size: 16, lr: 7.04e-04
2022-05-14 10:48:09,755 INFO [train.py:812] (3/8) Epoch 11, batch 650, loss[loss=0.1797, simple_loss=0.2502, pruned_loss=0.05455, over 7159.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2676, pruned_loss=0.04797, over 1364980.90 frames.], batch size: 17, lr: 7.03e-04
2022-05-14 10:49:08,417 INFO [train.py:812] (3/8) Epoch 11, batch 700, loss[loss=0.1777, simple_loss=0.2617, pruned_loss=0.04683, over 7198.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2685, pruned_loss=0.0483, over 1375654.92 frames.], batch size: 16, lr: 7.03e-04
2022-05-14 10:50:07,687 INFO [train.py:812] (3/8) Epoch 11, batch 750, loss[loss=0.1821, simple_loss=0.2684, pruned_loss=0.04795, over 7141.00 frames.], tot_loss[loss=0.182, simple_loss=0.2683, pruned_loss=0.04783, over 1382755.11 frames.], batch size: 20, lr: 7.03e-04
2022-05-14 10:51:05,913 INFO [train.py:812] (3/8) Epoch 11, batch 800, loss[loss=0.1893, simple_loss=0.2814, pruned_loss=0.04861, over 7115.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2679, pruned_loss=0.04752, over 1394075.19 frames.], batch size: 26, lr: 7.02e-04
2022-05-14 10:52:03,630 INFO [train.py:812] (3/8) Epoch 11, batch 850, loss[loss=0.1874, simple_loss=0.2857, pruned_loss=0.04451, over 7335.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2682, pruned_loss=0.04739, over 1398461.98 frames.], batch size: 20, lr: 7.02e-04
2022-05-14 10:53:01,756 INFO [train.py:812] (3/8) Epoch 11, batch 900, loss[loss=0.1788, simple_loss=0.268, pruned_loss=0.04476, over 7433.00 frames.], tot_loss[loss=0.1804, simple_loss=0.267, pruned_loss=0.04688, over 1406864.46 frames.], batch size: 20, lr: 7.02e-04
2022-05-14 10:54:00,388 INFO [train.py:812] (3/8) Epoch 11, batch 950, loss[loss=0.1651, simple_loss=0.2593, pruned_loss=0.03551, over 7000.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2664, pruned_loss=0.04664, over 1408762.86 frames.], batch size: 16, lr: 7.01e-04
2022-05-14 10:54:58,947 INFO [train.py:812] (3/8) Epoch 11, batch 1000, loss[loss=0.1741, simple_loss=0.2647, pruned_loss=0.0418, over 7351.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2669, pruned_loss=0.04689, over 1413414.88 frames.], batch size: 25, lr: 7.01e-04
2022-05-14 10:55:58,045 INFO [train.py:812] (3/8) Epoch 11, batch 1050, loss[loss=0.1842, simple_loss=0.2671, pruned_loss=0.05062, over 7265.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2683, pruned_loss=0.04756, over 1409098.29 frames.], batch size: 19, lr: 7.00e-04
2022-05-14 10:56:57,221 INFO [train.py:812] (3/8) Epoch 11, batch 1100, loss[loss=0.1602, simple_loss=0.2397, pruned_loss=0.04035, over 7168.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2677, pruned_loss=0.04727, over 1413361.07 frames.], batch size: 18, lr: 7.00e-04
2022-05-14 10:57:56,853 INFO [train.py:812] (3/8) Epoch 11, batch 1150, loss[loss=0.2115, simple_loss=0.2706, pruned_loss=0.07617, over 7071.00 frames.], tot_loss[loss=0.181, simple_loss=0.2673, pruned_loss=0.04731, over 1417273.01 frames.], batch size: 18, lr: 7.00e-04
2022-05-14 10:58:55,529 INFO [train.py:812] (3/8) Epoch 11, batch 1200, loss[loss=0.1592, simple_loss=0.2384, pruned_loss=0.03999, over 7239.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2655, pruned_loss=0.04685, over 1419943.09 frames.], batch size: 16, lr: 6.99e-04
2022-05-14 10:59:53,782 INFO [train.py:812] (3/8) Epoch 11, batch 1250, loss[loss=0.1608, simple_loss=0.247, pruned_loss=0.03736, over 7144.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2649, pruned_loss=0.04616, over 1424252.03 frames.], batch size: 17, lr: 6.99e-04
2022-05-14 11:00:50,424 INFO [train.py:812] (3/8) Epoch 11, batch 1300, loss[loss=0.2084, simple_loss=0.2982, pruned_loss=0.05931, over 7323.00 frames.], tot_loss[loss=0.1789, simple_loss=0.265, pruned_loss=0.0464, over 1421429.68 frames.], batch size: 21, lr: 6.99e-04
2022-05-14 11:01:49,334 INFO [train.py:812] (3/8) Epoch 11, batch 1350, loss[loss=0.1878, simple_loss=0.2804, pruned_loss=0.04764, over 7321.00 frames.], tot_loss[loss=0.1801, simple_loss=0.266, pruned_loss=0.04709, over 1424786.01 frames.], batch size: 21, lr: 6.98e-04
2022-05-14 11:02:46,389 INFO [train.py:812] (3/8) Epoch 11, batch 1400, loss[loss=0.1634, simple_loss=0.2483, pruned_loss=0.03927, over 7156.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2657, pruned_loss=0.0472, over 1428090.87 frames.], batch size: 19, lr: 6.98e-04
2022-05-14 11:03:44,643 INFO [train.py:812] (3/8) Epoch 11, batch 1450, loss[loss=0.1768, simple_loss=0.2641, pruned_loss=0.04473, over 7275.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2666, pruned_loss=0.04712, over 1428283.80 frames.], batch size: 17, lr: 6.97e-04
2022-05-14 11:04:41,556 INFO [train.py:812] (3/8) Epoch 11, batch 1500, loss[loss=0.1665, simple_loss=0.2656, pruned_loss=0.03371, over 7039.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2657, pruned_loss=0.04694, over 1425948.82 frames.], batch size: 28, lr: 6.97e-04
2022-05-14 11:05:41,358 INFO [train.py:812] (3/8) Epoch 11, batch 1550, loss[loss=0.1532, simple_loss=0.2345, pruned_loss=0.03595, over 7447.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2666, pruned_loss=0.04756, over 1424219.95 frames.], batch size: 20, lr: 6.97e-04
2022-05-14 11:06:38,923 INFO [train.py:812] (3/8) Epoch 11, batch 1600, loss[loss=0.2139, simple_loss=0.3048, pruned_loss=0.06156, over 6796.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2668, pruned_loss=0.04741, over 1418572.90 frames.], batch size: 31, lr: 6.96e-04
2022-05-14 11:07:38,255 INFO [train.py:812] (3/8) Epoch 11, batch 1650, loss[loss=0.1496, simple_loss=0.2227, pruned_loss=0.03822, over 6765.00 frames.], tot_loss[loss=0.1801, simple_loss=0.266, pruned_loss=0.04711, over 1418140.81 frames.], batch size: 15, lr: 6.96e-04
2022-05-14 11:08:37,023 INFO [train.py:812] (3/8) Epoch 11, batch 1700, loss[loss=0.1724, simple_loss=0.2559, pruned_loss=0.04448, over 7188.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2655, pruned_loss=0.04648, over 1417824.88 frames.], batch size: 16, lr: 6.96e-04
2022-05-14 11:09:36,813 INFO [train.py:812] (3/8) Epoch 11, batch 1750, loss[loss=0.1906, simple_loss=0.2796, pruned_loss=0.05079, over 7118.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2654, pruned_loss=0.04662, over 1414543.49 frames.], batch size: 21, lr: 6.95e-04
2022-05-14 11:10:35,674 INFO [train.py:812] (3/8) Epoch 11, batch 1800, loss[loss=0.2125, simple_loss=0.2892, pruned_loss=0.06787, over 5156.00 frames.], tot_loss[loss=0.181, simple_loss=0.267, pruned_loss=0.04753, over 1415097.10 frames.], batch size: 53, lr: 6.95e-04
2022-05-14 11:11:35,348 INFO [train.py:812] (3/8) Epoch 11, batch 1850, loss[loss=0.2022, simple_loss=0.2855, pruned_loss=0.05947, over 6353.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2662, pruned_loss=0.04678, over 1418700.40 frames.], batch size: 37, lr: 6.95e-04
2022-05-14 11:12:33,303 INFO [train.py:812] (3/8) Epoch 11, batch 1900, loss[loss=0.1978, simple_loss=0.3007, pruned_loss=0.04741, over 7316.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2658, pruned_loss=0.04659, over 1423181.22 frames.], batch size: 21, lr: 6.94e-04
2022-05-14 11:13:32,936 INFO [train.py:812] (3/8) Epoch 11, batch 1950, loss[loss=0.1807, simple_loss=0.2665, pruned_loss=0.04744, over 7361.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2656, pruned_loss=0.04641, over 1422719.87 frames.], batch size: 19, lr: 6.94e-04
2022-05-14 11:14:32,018 INFO [train.py:812] (3/8) Epoch 11, batch 2000, loss[loss=0.1479, simple_loss=0.238, pruned_loss=0.0289, over 7157.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2661, pruned_loss=0.04643, over 1423785.71 frames.], batch size: 18, lr: 6.93e-04
2022-05-14 11:15:30,886 INFO [train.py:812] (3/8) Epoch 11, batch 2050, loss[loss=0.1787, simple_loss=0.254, pruned_loss=0.05175, over 7265.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2662, pruned_loss=0.04661, over 1425686.94 frames.], batch size: 17, lr: 6.93e-04
2022-05-14 11:16:30,463 INFO [train.py:812] (3/8) Epoch 11, batch 2100, loss[loss=0.1934, simple_loss=0.284, pruned_loss=0.05142, over 7379.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2665, pruned_loss=0.04659, over 1426077.08 frames.], batch size: 23, lr: 6.93e-04
2022-05-14 11:17:37,594 INFO [train.py:812] (3/8) Epoch 11, batch 2150, loss[loss=0.1637, simple_loss=0.2491, pruned_loss=0.03916, over 7160.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2664, pruned_loss=0.04642, over 1425799.85 frames.], batch size: 18, lr: 6.92e-04
2022-05-14 11:18:36,030 INFO [train.py:812] (3/8) Epoch 11, batch 2200, loss[loss=0.1861, simple_loss=0.28, pruned_loss=0.0461, over 7234.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2664, pruned_loss=0.04668, over 1423544.50 frames.], batch size: 20, lr: 6.92e-04
2022-05-14 11:19:35,021 INFO [train.py:812] (3/8) Epoch 11, batch 2250, loss[loss=0.178, simple_loss=0.2732, pruned_loss=0.04139, over 7327.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2677, pruned_loss=0.04748, over 1426975.08 frames.], batch size: 22, lr: 6.92e-04
2022-05-14 11:20:34,380 INFO [train.py:812] (3/8) Epoch 11, batch 2300, loss[loss=0.1537, simple_loss=0.247, pruned_loss=0.03024, over 7146.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2675, pruned_loss=0.04751, over 1427502.75 frames.], batch size: 26, lr: 6.91e-04
2022-05-14 11:21:33,291 INFO [train.py:812] (3/8) Epoch 11, batch 2350, loss[loss=0.1876, simple_loss=0.277, pruned_loss=0.04912, over 6802.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2665, pruned_loss=0.04742, over 1429985.88 frames.], batch size: 31, lr: 6.91e-04
2022-05-14 11:22:32,006 INFO [train.py:812] (3/8) Epoch 11, batch 2400, loss[loss=0.1667, simple_loss=0.264, pruned_loss=0.0347, over 7315.00 frames.], tot_loss[loss=0.18, simple_loss=0.2661, pruned_loss=0.04699, over 1423556.28 frames.], batch size: 21, lr: 6.91e-04
2022-05-14 11:23:31,120 INFO [train.py:812] (3/8) Epoch 11, batch 2450, loss[loss=0.1846, simple_loss=0.2551, pruned_loss=0.05705, over 7008.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2645, pruned_loss=0.04641, over 1423890.94 frames.], batch size: 16, lr: 6.90e-04
2022-05-14 11:24:30,209 INFO [train.py:812] (3/8) Epoch 11, batch 2500, loss[loss=0.1532, simple_loss=0.2392, pruned_loss=0.03359, over 7150.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2656, pruned_loss=0.04687, over 1422937.09 frames.], batch size: 19, lr: 6.90e-04
2022-05-14 11:25:29,308 INFO [train.py:812] (3/8) Epoch 11, batch 2550, loss[loss=0.1519, simple_loss=0.2361, pruned_loss=0.03389, over 6770.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2653, pruned_loss=0.04661, over 1426701.89 frames.], batch size: 15, lr: 6.90e-04
2022-05-14 11:26:27,797 INFO [train.py:812] (3/8) Epoch 11, batch 2600, loss[loss=0.1989, simple_loss=0.2815, pruned_loss=0.05817, over 7381.00 frames.], tot_loss[loss=0.179, simple_loss=0.2653, pruned_loss=0.04634, over 1428152.98 frames.], batch size: 23, lr: 6.89e-04
2022-05-14 11:27:26,100 INFO [train.py:812] (3/8) Epoch 11, batch 2650, loss[loss=0.1662, simple_loss=0.2505, pruned_loss=0.04093, over 7005.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2663, pruned_loss=0.04698, over 1423822.27 frames.], batch size: 16, lr: 6.89e-04
2022-05-14 11:28:23,546 INFO [train.py:812] (3/8) Epoch 11, batch 2700, loss[loss=0.1853, simple_loss=0.2703, pruned_loss=0.05016, over 7409.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2664, pruned_loss=0.04658, over 1426848.60 frames.], batch size: 21, lr: 6.89e-04
2022-05-14 11:29:20,989 INFO [train.py:812] (3/8) Epoch 11, batch 2750, loss[loss=0.1628, simple_loss=0.2475, pruned_loss=0.03904, over 7278.00 frames.], tot_loss[loss=0.1799, simple_loss=0.266, pruned_loss=0.04691, over 1426048.70 frames.], batch size: 18, lr: 6.88e-04
2022-05-14 11:30:17,968 INFO [train.py:812] (3/8) Epoch 11, batch 2800, loss[loss=0.1994, simple_loss=0.2905, pruned_loss=0.05419, over 7163.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2662, pruned_loss=0.04668, over 1424668.22 frames.], batch size: 19, lr: 6.88e-04
2022-05-14 11:31:17,644 INFO [train.py:812] (3/8) Epoch 11, batch 2850, loss[loss=0.2005, simple_loss=0.2804, pruned_loss=0.06034, over 7317.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2657, pruned_loss=0.04674, over 1424318.77 frames.], batch size: 21, lr: 6.87e-04
2022-05-14 11:32:14,480 INFO [train.py:812] (3/8) Epoch 11, batch 2900, loss[loss=0.2093, simple_loss=0.2921, pruned_loss=0.06327, over 7176.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2653, pruned_loss=0.04658, over 1427288.01 frames.], batch size: 23, lr: 6.87e-04
2022-05-14 11:33:13,345 INFO [train.py:812] (3/8) Epoch 11, batch 2950, loss[loss=0.1754, simple_loss=0.2642, pruned_loss=0.04336, over 7203.00 frames.], tot_loss[loss=0.1797, simple_loss=0.266, pruned_loss=0.04672, over 1424753.40 frames.], batch size: 22, lr: 6.87e-04
2022-05-14 11:34:12,260 INFO [train.py:812] (3/8) Epoch 11, batch 3000, loss[loss=0.1753, simple_loss=0.2553, pruned_loss=0.04761, over 7172.00 frames.], tot_loss[loss=0.1806, simple_loss=0.267, pruned_loss=0.04712, over 1423474.49 frames.], batch size: 18, lr: 6.86e-04
2022-05-14 11:34:12,261 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 11:34:19,823 INFO [train.py:841] (3/8) Epoch 11, validation: loss=0.1564, simple_loss=0.2581, pruned_loss=0.02737, over 698248.00 frames.
2022-05-14 11:35:18,269 INFO [train.py:812] (3/8) Epoch 11, batch 3050, loss[loss=0.2065, simple_loss=0.2791, pruned_loss=0.06696, over 7157.00 frames.], tot_loss[loss=0.1797, simple_loss=0.266, pruned_loss=0.04668, over 1428212.91 frames.], batch size: 26, lr: 6.86e-04
2022-05-14 11:36:16,728 INFO [train.py:812] (3/8) Epoch 11, batch 3100, loss[loss=0.149, simple_loss=0.2334, pruned_loss=0.03235, over 7423.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04745, over 1425626.13 frames.], batch size: 18, lr: 6.86e-04
2022-05-14 11:37:16,184 INFO [train.py:812] (3/8) Epoch 11, batch 3150, loss[loss=0.1458, simple_loss=0.2373, pruned_loss=0.02717, over 7275.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2668, pruned_loss=0.04749, over 1428306.88 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:38:15,162 INFO [train.py:812] (3/8) Epoch 11, batch 3200, loss[loss=0.1454, simple_loss=0.2294, pruned_loss=0.03066, over 7165.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2653, pruned_loss=0.04689, over 1430087.55 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:39:14,893 INFO [train.py:812] (3/8) Epoch 11, batch 3250, loss[loss=0.1655, simple_loss=0.248, pruned_loss=0.04157, over 7062.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2657, pruned_loss=0.04705, over 1431547.13 frames.], batch size: 18, lr: 6.85e-04
2022-05-14 11:40:14,275 INFO [train.py:812] (3/8) Epoch 11, batch 3300, loss[loss=0.1789, simple_loss=0.2592, pruned_loss=0.04926, over 6517.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2661, pruned_loss=0.04733, over 1431543.33 frames.], batch size: 38, lr: 6.84e-04
2022-05-14 11:41:13,840 INFO [train.py:812] (3/8) Epoch 11, batch 3350, loss[loss=0.1948, simple_loss=0.2761, pruned_loss=0.05675, over 7126.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2666, pruned_loss=0.04745, over 1425109.36 frames.], batch size: 21, lr: 6.84e-04
2022-05-14 11:42:12,398 INFO [train.py:812] (3/8) Epoch 11, batch 3400, loss[loss=0.1815, simple_loss=0.2502, pruned_loss=0.05642, over 7005.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2673, pruned_loss=0.04774, over 1421354.29 frames.], batch size: 16, lr: 6.84e-04
2022-05-14 11:43:11,478 INFO [train.py:812] (3/8) Epoch 11, batch 3450, loss[loss=0.1842, simple_loss=0.2747, pruned_loss=0.04685, over 7114.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2676, pruned_loss=0.04781, over 1424015.71 frames.], batch size: 21, lr: 6.83e-04
2022-05-14 11:44:10,236 INFO [train.py:812] (3/8) Epoch 11, batch 3500, loss[loss=0.177, simple_loss=0.2527, pruned_loss=0.05066, over 7413.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2671, pruned_loss=0.04805, over 1424828.79 frames.], batch size: 18, lr: 6.83e-04
2022-05-14 11:45:10,094 INFO [train.py:812] (3/8) Epoch 11, batch 3550, loss[loss=0.1892, simple_loss=0.273, pruned_loss=0.05269, over 6546.00 frames.], tot_loss[loss=0.182, simple_loss=0.2678, pruned_loss=0.04813, over 1424027.39 frames.], batch size: 38, lr: 6.83e-04
2022-05-14 11:46:08,780 INFO [train.py:812] (3/8) Epoch 11, batch 3600, loss[loss=0.1586, simple_loss=0.2459, pruned_loss=0.03565, over 6523.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2679, pruned_loss=0.04826, over 1419434.68 frames.], batch size: 38, lr: 6.82e-04
2022-05-14 11:47:07,765 INFO [train.py:812] (3/8) Epoch 11, batch 3650, loss[loss=0.2072, simple_loss=0.3009, pruned_loss=0.05679, over 7115.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2683, pruned_loss=0.04813, over 1421788.34 frames.], batch size: 21, lr: 6.82e-04
2022-05-14 11:48:06,835 INFO [train.py:812] (3/8) Epoch 11, batch 3700, loss[loss=0.1881, simple_loss=0.2789, pruned_loss=0.04858, over 7114.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2687, pruned_loss=0.04833, over 1417654.60 frames.], batch size: 21, lr: 6.82e-04
2022-05-14 11:49:06,463 INFO [train.py:812] (3/8) Epoch 11, batch 3750, loss[loss=0.204, simple_loss=0.2795, pruned_loss=0.06425, over 7428.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2698, pruned_loss=0.04881, over 1424091.78 frames.], batch size: 20, lr: 6.81e-04
2022-05-14 11:50:05,387 INFO [train.py:812] (3/8) Epoch 11, batch 3800, loss[loss=0.1966, simple_loss=0.2886, pruned_loss=0.05226, over 7254.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2697, pruned_loss=0.04881, over 1422662.48 frames.], batch size: 24, lr: 6.81e-04
2022-05-14 11:51:04,548 INFO [train.py:812] (3/8) Epoch 11, batch 3850, loss[loss=0.1745, simple_loss=0.2706, pruned_loss=0.03917, over 7213.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2687, pruned_loss=0.04795, over 1426801.18 frames.], batch size: 22, lr: 6.81e-04
2022-05-14 11:52:01,418 INFO [train.py:812] (3/8) Epoch 11, batch 3900, loss[loss=0.1812, simple_loss=0.2734, pruned_loss=0.04448, over 7384.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2682, pruned_loss=0.04772, over 1428108.34 frames.], batch size: 23, lr: 6.80e-04
2022-05-14 11:53:00,850 INFO [train.py:812] (3/8) Epoch 11, batch 3950, loss[loss=0.1812, simple_loss=0.2692, pruned_loss=0.04663, over 7424.00 frames.], tot_loss[loss=0.181, simple_loss=0.2672, pruned_loss=0.04739, over 1426725.01 frames.], batch size: 20, lr: 6.80e-04
2022-05-14 11:53:59,461 INFO [train.py:812] (3/8) Epoch 11, batch 4000, loss[loss=0.1937, simple_loss=0.2935, pruned_loss=0.04698, over 7220.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2674, pruned_loss=0.0479, over 1418318.36 frames.], batch size: 21, lr: 6.80e-04
2022-05-14 11:54:58,918 INFO [train.py:812] (3/8) Epoch 11, batch 4050, loss[loss=0.1906, simple_loss=0.2719, pruned_loss=0.0547, over 7196.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2674, pruned_loss=0.04804, over 1418631.24 frames.], batch size: 22, lr: 6.79e-04
2022-05-14 11:55:57,977 INFO [train.py:812] (3/8) Epoch 11, batch 4100, loss[loss=0.2112, simple_loss=0.3002, pruned_loss=0.06107, over 7202.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2685, pruned_loss=0.04857, over 1417721.70 frames.], batch size: 22, lr: 6.79e-04
2022-05-14 11:56:56,025 INFO [train.py:812] (3/8) Epoch 11, batch 4150, loss[loss=0.1924, simple_loss=0.2845, pruned_loss=0.05018, over 6801.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2696, pruned_loss=0.04889, over 1415431.22 frames.], batch size: 31, lr: 6.79e-04
2022-05-14 11:57:54,852 INFO [train.py:812] (3/8) Epoch 11, batch 4200, loss[loss=0.1904, simple_loss=0.2726, pruned_loss=0.05406, over 7019.00 frames.], tot_loss[loss=0.183, simple_loss=0.2688, pruned_loss=0.0486, over 1415944.62 frames.], batch size: 28, lr: 6.78e-04
2022-05-14 11:58:54,362 INFO [train.py:812] (3/8) Epoch 11, batch 4250, loss[loss=0.2185, simple_loss=0.2868, pruned_loss=0.07507, over 5091.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2682, pruned_loss=0.04811, over 1415098.24 frames.], batch size: 52, lr: 6.78e-04
2022-05-14 11:59:53,049 INFO [train.py:812] (3/8) Epoch 11, batch 4300, loss[loss=0.2389, simple_loss=0.3184, pruned_loss=0.07975, over 5047.00 frames.], tot_loss[loss=0.182, simple_loss=0.2678, pruned_loss=0.0481, over 1411350.47 frames.], batch size: 52, lr: 6.78e-04
2022-05-14 12:00:52,208 INFO [train.py:812] (3/8) Epoch 11, batch 4350, loss[loss=0.1606, simple_loss=0.2527, pruned_loss=0.03426, over 7230.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2693, pruned_loss=0.04878, over 1410391.61 frames.], batch size: 20, lr: 6.77e-04
2022-05-14 12:01:50,106 INFO [train.py:812] (3/8) Epoch 11, batch 4400, loss[loss=0.1987, simple_loss=0.2831, pruned_loss=0.05714, over 7208.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2695, pruned_loss=0.04854, over 1416203.13 frames.], batch size: 22, lr: 6.77e-04
2022-05-14 12:02:49,119 INFO [train.py:812] (3/8) Epoch 11, batch 4450, loss[loss=0.1638, simple_loss=0.2533, pruned_loss=0.03717, over 7241.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2708, pruned_loss=0.04918, over 1418592.07 frames.], batch size: 20, lr: 6.77e-04
2022-05-14 12:03:48,062 INFO [train.py:812] (3/8) Epoch 11, batch 4500, loss[loss=0.2623, simple_loss=0.3207, pruned_loss=0.1019, over 5335.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2715, pruned_loss=0.04936, over 1410805.69 frames.], batch size: 52, lr: 6.76e-04
2022-05-14 12:04:46,785 INFO [train.py:812] (3/8) Epoch 11, batch 4550, loss[loss=0.2175, simple_loss=0.2953, pruned_loss=0.0698, over 5504.00 frames.], tot_loss[loss=0.1878, simple_loss=0.273, pruned_loss=0.0513, over 1346643.32 frames.], batch size: 53, lr: 6.76e-04
2022-05-14 12:05:54,959 INFO [train.py:812] (3/8) Epoch 12, batch 0, loss[loss=0.173, simple_loss=0.2646, pruned_loss=0.04066, over 7410.00 frames.], tot_loss[loss=0.173, simple_loss=0.2646, pruned_loss=0.04066, over 7410.00 frames.], batch size: 21, lr: 6.52e-04
2022-05-14 12:06:54,813 INFO [train.py:812] (3/8) Epoch 12, batch 50, loss[loss=0.229, simple_loss=0.2982, pruned_loss=0.07992, over 4928.00 frames.], tot_loss[loss=0.1795, simple_loss=0.266, pruned_loss=0.04648, over 319368.90 frames.], batch size: 53, lr: 6.52e-04
2022-05-14 12:07:53,900 INFO [train.py:812] (3/8) Epoch 12, batch 100, loss[loss=0.1571, simple_loss=0.2439, pruned_loss=0.03511, over 6407.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2679, pruned_loss=0.04743, over 559314.75 frames.], batch size: 37, lr: 6.51e-04
2022-05-14 12:08:53,462 INFO [train.py:812] (3/8) Epoch 12, batch 150, loss[loss=0.1556, simple_loss=0.2351, pruned_loss=0.03807, over 7271.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2694, pruned_loss=0.04795, over 749657.30 frames.], batch size: 17, lr: 6.51e-04
2022-05-14 12:09:52,488 INFO [train.py:812] (3/8) Epoch 12, batch 200, loss[loss=0.1916, simple_loss=0.2909, pruned_loss=0.04611, over 7204.00 frames.], tot_loss[loss=0.1821, simple_loss=0.269, pruned_loss=0.04766, over 897370.64 frames.], batch size: 22, lr: 6.51e-04
2022-05-14 12:10:51,851 INFO [train.py:812] (3/8) Epoch 12, batch 250, loss[loss=0.1535, simple_loss=0.2434, pruned_loss=0.03173, over 6692.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2681, pruned_loss=0.0473, over 1014252.58 frames.], batch size: 31, lr: 6.50e-04
2022-05-14 12:11:51,030 INFO [train.py:812] (3/8) Epoch 12, batch 300, loss[loss=0.2033, simple_loss=0.2919, pruned_loss=0.0574, over 7211.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2677, pruned_loss=0.04649, over 1099657.36 frames.], batch size: 22, lr: 6.50e-04
2022-05-14 12:12:50,774 INFO [train.py:812] (3/8) Epoch 12, batch 350, loss[loss=0.1848, simple_loss=0.2821, pruned_loss=0.04375, over 7340.00 frames.], tot_loss[loss=0.1789, simple_loss=0.266, pruned_loss=0.04592, over 1166668.55 frames.], batch size: 22, lr: 6.50e-04
2022-05-14 12:13:50,250 INFO [train.py:812] (3/8) Epoch 12, batch 400, loss[loss=0.1957, simple_loss=0.2859, pruned_loss=0.05271, over 7347.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2658, pruned_loss=0.0456, over 1220987.53 frames.], batch size: 22, lr: 6.49e-04
2022-05-14 12:14:48,368 INFO [train.py:812] (3/8) Epoch 12, batch 450, loss[loss=0.1696, simple_loss=0.2549, pruned_loss=0.04216, over 7166.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2653, pruned_loss=0.0458, over 1269346.26 frames.], batch size: 19, lr: 6.49e-04
2022-05-14 12:15:47,353 INFO [train.py:812] (3/8) Epoch 12, batch 500, loss[loss=0.2266, simple_loss=0.3089, pruned_loss=0.07212, over 7373.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2655, pruned_loss=0.04598, over 1303302.84 frames.], batch size: 23, lr: 6.49e-04
2022-05-14 12:16:45,608 INFO [train.py:812] (3/8) Epoch 12, batch 550, loss[loss=0.1726, simple_loss=0.2632, pruned_loss=0.04096, over 7410.00 frames.], tot_loss[loss=0.1785, simple_loss=0.265, pruned_loss=0.04596, over 1329725.98 frames.], batch size: 21, lr: 6.48e-04
2022-05-14 12:17:43,508 INFO [train.py:812] (3/8) Epoch 12, batch 600, loss[loss=0.1708, simple_loss=0.2801, pruned_loss=0.03069, over 7323.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2651, pruned_loss=0.04591, over 1348862.10 frames.], batch size: 22, lr: 6.48e-04
2022-05-14 12:18:41,731 INFO [train.py:812] (3/8) Epoch 12, batch 650, loss[loss=0.2035, simple_loss=0.2911, pruned_loss=0.058, over 7378.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2633, pruned_loss=0.04491, over 1370202.07 frames.], batch size: 23, lr: 6.48e-04
2022-05-14 12:19:49,853 INFO [train.py:812] (3/8) Epoch 12, batch 700, loss[loss=0.1873, simple_loss=0.2756, pruned_loss=0.04951, over 7282.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2641, pruned_loss=0.04536, over 1381103.82 frames.], batch size: 24, lr: 6.47e-04
2022-05-14 12:20:48,660 INFO [train.py:812] (3/8) Epoch 12, batch 750, loss[loss=0.1358, simple_loss=0.231, pruned_loss=0.02028, over 7325.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2647, pruned_loss=0.04545, over 1386389.72 frames.], batch size: 20, lr: 6.47e-04
2022-05-14 12:21:47,964 INFO [train.py:812] (3/8) Epoch 12, batch 800, loss[loss=0.1704, simple_loss=0.2541, pruned_loss=0.04332, over 7405.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2643, pruned_loss=0.04536, over 1398338.69 frames.], batch size: 18, lr: 6.47e-04
2022-05-14 12:22:46,121 INFO [train.py:812] (3/8) Epoch 12, batch 850, loss[loss=0.1782, simple_loss=0.2635, pruned_loss=0.04646, over 6691.00 frames.], tot_loss[loss=0.179, simple_loss=0.266, pruned_loss=0.04594, over 1402815.12 frames.], batch size: 31, lr: 6.46e-04
2022-05-14 12:23:43,968 INFO [train.py:812] (3/8) Epoch 12, batch 900, loss[loss=0.205, simple_loss=0.2868, pruned_loss=0.06155, over 7337.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2659, pruned_loss=0.04585, over 1407805.23 frames.], batch size: 22, lr: 6.46e-04
2022-05-14 12:24:43,684 INFO [train.py:812] (3/8) Epoch 12, batch 950, loss[loss=0.1631, simple_loss=0.2516, pruned_loss=0.03733, over 7425.00 frames.], tot_loss[loss=0.1793, simple_loss=0.266, pruned_loss=0.04632, over 1413019.48 frames.], batch size: 20, lr: 6.46e-04
2022-05-14 12:25:42,164 INFO [train.py:812] (3/8) Epoch 12, batch 1000, loss[loss=0.1649, simple_loss=0.2571, pruned_loss=0.03634, over 7154.00 frames.], tot_loss[loss=0.18, simple_loss=0.2666, pruned_loss=0.04665, over 1415885.08 frames.], batch size: 19, lr: 6.46e-04
2022-05-14 12:26:41,693 INFO [train.py:812] (3/8) Epoch 12, batch 1050, loss[loss=0.1484, simple_loss=0.2237, pruned_loss=0.03656, over 7003.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2666, pruned_loss=0.047, over 1415344.97 frames.], batch size: 16, lr: 6.45e-04
2022-05-14 12:27:40,714 INFO [train.py:812] (3/8) Epoch 12, batch 1100, loss[loss=0.1823, simple_loss=0.2601, pruned_loss=0.05227, over 7151.00 frames.], tot_loss[loss=0.1815, simple_loss=0.268, pruned_loss=0.04751, over 1417779.09 frames.], batch size: 19, lr: 6.45e-04
2022-05-14 12:28:40,253 INFO [train.py:812] (3/8) Epoch 12, batch 1150, loss[loss=0.2213, simple_loss=0.2923, pruned_loss=0.07513, over 5114.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2669, pruned_loss=0.04676, over 1420568.38 frames.], batch size: 53, lr: 6.45e-04
2022-05-14 12:29:38,127 INFO [train.py:812] (3/8) Epoch 12, batch 1200, loss[loss=0.1735, simple_loss=0.2645, pruned_loss=0.04119, over 7114.00 frames.], tot_loss[loss=0.18, simple_loss=0.2666, pruned_loss=0.04668, over 1423428.16 frames.], batch size: 21, lr: 6.44e-04
2022-05-14 12:30:37,014 INFO [train.py:812] (3/8) Epoch 12, batch 1250, loss[loss=0.1754, simple_loss=0.2574, pruned_loss=0.04674, over 7001.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2662, pruned_loss=0.04669, over 1424543.17 frames.], batch size: 16, lr: 6.44e-04
2022-05-14 12:31:36,635 INFO [train.py:812] (3/8) Epoch 12, batch 1300, loss[loss=0.1631, simple_loss=0.2492, pruned_loss=0.03853, over 7319.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2659, pruned_loss=0.04617, over 1426378.55 frames.], batch size: 20, lr: 6.44e-04
2022-05-14 12:32:34,807 INFO [train.py:812] (3/8) Epoch 12, batch 1350, loss[loss=0.1961, simple_loss=0.2827, pruned_loss=0.05472, over 7324.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2657, pruned_loss=0.04604, over 1424306.88 frames.], batch size: 21, lr: 6.43e-04
2022-05-14 12:33:34,081 INFO [train.py:812] (3/8) Epoch 12, batch 1400, loss[loss=0.2039, simple_loss=0.2949, pruned_loss=0.0565, over 7325.00 frames.], tot_loss[loss=0.1784, simple_loss=0.265, pruned_loss=0.04595, over 1421634.74 frames.], batch size: 21, lr: 6.43e-04
2022-05-14 12:34:33,347 INFO [train.py:812] (3/8) Epoch 12, batch 1450, loss[loss=0.1598, simple_loss=0.2438, pruned_loss=0.03795, over 7073.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2651, pruned_loss=0.04595, over 1422000.20 frames.], batch size: 18, lr: 6.43e-04
2022-05-14 12:35:32,026 INFO [train.py:812] (3/8) Epoch 12, batch 1500, loss[loss=0.2149, simple_loss=0.2948, pruned_loss=0.06751, over 7193.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2649, pruned_loss=0.04603, over 1425593.18 frames.], batch size: 23, lr: 6.42e-04
2022-05-14 12:36:36,803 INFO [train.py:812] (3/8) Epoch 12, batch 1550, loss[loss=0.1772, simple_loss=0.2748, pruned_loss=0.03977, over 7231.00 frames.], tot_loss[loss=0.1776, simple_loss=0.264, pruned_loss=0.04565, over 1424429.92 frames.], batch size: 20, lr: 6.42e-04
2022-05-14 12:37:35,854 INFO [train.py:812] (3/8) Epoch 12, batch 1600, loss[loss=0.1789, simple_loss=0.2544, pruned_loss=0.05167, over 7359.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2651, pruned_loss=0.04602, over 1424814.85 frames.], batch size: 19, lr: 6.42e-04
2022-05-14 12:38:44,921 INFO [train.py:812] (3/8) Epoch 12, batch 1650, loss[loss=0.1633, simple_loss=0.2563, pruned_loss=0.03511, over 7375.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2648, pruned_loss=0.04611, over 1425851.96 frames.], batch size: 23, lr: 6.42e-04
2022-05-14 12:39:52,047 INFO [train.py:812] (3/8) Epoch 12, batch 1700, loss[loss=0.1692, simple_loss=0.2598, pruned_loss=0.03931, over 7222.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2647, pruned_loss=0.04555, over 1426769.99 frames.], batch size: 21, lr: 6.41e-04
2022-05-14 12:40:51,340 INFO [train.py:812] (3/8) Epoch 12, batch 1750, loss[loss=0.1958, simple_loss=0.2829, pruned_loss=0.05437, over 7144.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2647, pruned_loss=0.04593, over 1428217.91 frames.], batch size: 26, lr: 6.41e-04
2022-05-14 12:41:58,739 INFO [train.py:812] (3/8) Epoch 12, batch 1800, loss[loss=0.1598, simple_loss=0.2333, pruned_loss=0.04317, over 7003.00 frames.], tot_loss[loss=0.1779, simple_loss=0.264, pruned_loss=0.04588, over 1428562.96 frames.], batch size: 16, lr: 6.41e-04
2022-05-14 12:43:07,986 INFO [train.py:812] (3/8) Epoch 12, batch 1850, loss[loss=0.2043, simple_loss=0.2906, pruned_loss=0.05898, over 7181.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2641, pruned_loss=0.04566, over 1426731.56 frames.], batch size: 26, lr: 6.40e-04
2022-05-14 12:44:16,790 INFO [train.py:812] (3/8) Epoch 12, batch 1900, loss[loss=0.158, simple_loss=0.2532, pruned_loss=0.03137, over 7433.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2635, pruned_loss=0.04537, over 1429239.69 frames.], batch size: 20, lr: 6.40e-04
2022-05-14 12:45:34,900 INFO [train.py:812] (3/8) Epoch 12, batch 1950, loss[loss=0.1694, simple_loss=0.2431, pruned_loss=0.04784, over 6992.00 frames.], tot_loss[loss=0.1767, simple_loss=0.263, pruned_loss=0.04516, over 1428248.07 frames.], batch size: 16, lr: 6.40e-04
2022-05-14 12:46:34,651 INFO [train.py:812] (3/8) Epoch 12, batch 2000, loss[loss=0.1749, simple_loss=0.2603, pruned_loss=0.04472, over 6554.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2635, pruned_loss=0.04529, over 1426508.48 frames.], batch size: 38, lr: 6.39e-04
2022-05-14 12:47:34,772 INFO [train.py:812] (3/8) Epoch 12, batch 2050, loss[loss=0.1822, simple_loss=0.2697, pruned_loss=0.04733, over 7376.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2639, pruned_loss=0.04544, over 1424370.78 frames.], batch size: 23, lr: 6.39e-04
2022-05-14 12:48:34,242 INFO [train.py:812] (3/8) Epoch 12, batch 2100, loss[loss=0.1846, simple_loss=0.2796, pruned_loss=0.04473, over 6778.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2636, pruned_loss=0.04545, over 1428106.74 frames.], batch size: 31, lr: 6.39e-04
2022-05-14 12:49:34,262 INFO [train.py:812] (3/8) Epoch 12, batch 2150, loss[loss=0.163, simple_loss=0.2489, pruned_loss=0.03855, over 6789.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2642, pruned_loss=0.04567, over 1422337.50 frames.], batch size: 15, lr: 6.38e-04
2022-05-14 12:50:33,510 INFO [train.py:812] (3/8) Epoch 12, batch 2200, loss[loss=0.1713, simple_loss=0.2596, pruned_loss=0.04154, over 7425.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2635, pruned_loss=0.04514, over 1426740.29 frames.], batch size: 20, lr: 6.38e-04
2022-05-14 12:51:31,622 INFO [train.py:812] (3/8) Epoch 12, batch 2250, loss[loss=0.1602, simple_loss=0.2539, pruned_loss=0.03327, over 7137.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2634, pruned_loss=0.04499, over 1426163.22 frames.], batch size: 17, lr: 6.38e-04
2022-05-14 12:52:29,469 INFO [train.py:812] (3/8) Epoch 12, batch 2300, loss[loss=0.1547, simple_loss=0.2415, pruned_loss=0.03391, over 7361.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2643, pruned_loss=0.04531, over 1424385.67 frames.], batch size: 19, lr: 6.38e-04
2022-05-14 12:53:28,555 INFO [train.py:812] (3/8) Epoch 12, batch 2350, loss[loss=0.181, simple_loss=0.2681, pruned_loss=0.04689, over 7280.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2649, pruned_loss=0.04579, over 1426176.92 frames.], batch size: 24, lr: 6.37e-04
2022-05-14 12:54:27,655 INFO [train.py:812] (3/8) Epoch 12, batch 2400, loss[loss=0.1523, simple_loss=0.2476, pruned_loss=0.02846, over 7117.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2649, pruned_loss=0.04547, over 1428076.17 frames.], batch size: 21, lr: 6.37e-04
2022-05-14 12:55:26,370 INFO [train.py:812] (3/8) Epoch 12, batch 2450, loss[loss=0.2055, simple_loss=0.2992, pruned_loss=0.05585, over 7235.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2658, pruned_loss=0.04591, over 1425751.12 frames.], batch size: 20, lr: 6.37e-04
2022-05-14 12:56:25,363 INFO [train.py:812] (3/8) Epoch 12, batch 2500, loss[loss=0.1611, simple_loss=0.2417, pruned_loss=0.04021, over 7058.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2642, pruned_loss=0.04527, over 1425406.97 frames.], batch size: 18, lr: 6.36e-04
2022-05-14 12:57:24,980 INFO [train.py:812] (3/8) Epoch 12, batch 2550, loss[loss=0.1489, simple_loss=0.2244, pruned_loss=0.03675, over 7282.00 frames.], tot_loss[loss=0.178, simple_loss=0.265, pruned_loss=0.04556, over 1428248.01 frames.], batch size: 17, lr: 6.36e-04
2022-05-14 12:58:23,568 INFO [train.py:812] (3/8) Epoch 12, batch 2600, loss[loss=0.1831, simple_loss=0.2788, pruned_loss=0.04374, over 7291.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2638, pruned_loss=0.04516, over 1422572.05 frames.], batch size: 24, lr: 6.36e-04
2022-05-14 12:59:22,467 INFO [train.py:812] (3/8) Epoch 12, batch 2650, loss[loss=0.1844, simple_loss=0.2688, pruned_loss=0.04996, over 7262.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2651, pruned_loss=0.04554, over 1418986.95 frames.], batch size: 19, lr: 6.36e-04
2022-05-14 13:00:21,646 INFO [train.py:812] (3/8) Epoch 12, batch 2700, loss[loss=0.1875, simple_loss=0.2787, pruned_loss=0.04818, over 7309.00 frames.], tot_loss[loss=0.177, simple_loss=0.2643, pruned_loss=0.04488, over 1422710.23 frames.], batch size: 25, lr: 6.35e-04
2022-05-14 13:01:21,318 INFO [train.py:812] (3/8) Epoch 12, batch 2750, loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03351, over 7435.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2637, pruned_loss=0.04454, over 1425323.65 frames.], batch size: 20, lr: 6.35e-04
2022-05-14 13:02:20,428 INFO [train.py:812] (3/8) Epoch 12, batch 2800, loss[loss=0.2038, simple_loss=0.2909, pruned_loss=0.05829, over 7111.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2641, pruned_loss=0.04524, over 1426319.55 frames.], batch size: 21, lr: 6.35e-04
2022-05-14 13:03:19,810 INFO [train.py:812] (3/8) Epoch 12, batch 2850, loss[loss=0.1856, simple_loss=0.282, pruned_loss=0.04464, over 7327.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2635, pruned_loss=0.04501, over 1428473.58 frames.], batch size: 21, lr: 6.34e-04
2022-05-14 13:04:18,946 INFO [train.py:812] (3/8) Epoch 12, batch 2900, loss[loss=0.1721, simple_loss=0.2681, pruned_loss=0.03807, over 7297.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2642, pruned_loss=0.04519, over 1424949.66 frames.], batch size: 24, lr: 6.34e-04
2022-05-14 13:05:18,606 INFO [train.py:812] (3/8) Epoch 12, batch 2950, loss[loss=0.1961, simple_loss=0.2862, pruned_loss=0.053, over 7227.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2639, pruned_loss=0.04526, over 1421156.92 frames.], batch size: 21, lr: 6.34e-04
2022-05-14 13:06:17,597 INFO [train.py:812] (3/8) Epoch 12, batch 3000, loss[loss=0.1773, simple_loss=0.2595, pruned_loss=0.04752, over 7279.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2634, pruned_loss=0.04494, over 1422846.71 frames.], batch size: 25, lr: 6.33e-04
2022-05-14 13:06:17,598 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 13:06:26,032 INFO [train.py:841] (3/8) Epoch 12, validation: loss=0.1553, simple_loss=0.2571, pruned_loss=0.02678, over 698248.00 frames.
2022-05-14 13:07:25,168 INFO [train.py:812] (3/8) Epoch 12, batch 3050, loss[loss=0.1986, simple_loss=0.288, pruned_loss=0.05456, over 7370.00 frames.], tot_loss[loss=0.178, simple_loss=0.2649, pruned_loss=0.04562, over 1420554.21 frames.], batch size: 23, lr: 6.33e-04
2022-05-14 13:08:24,673 INFO [train.py:812] (3/8) Epoch 12, batch 3100, loss[loss=0.2004, simple_loss=0.2764, pruned_loss=0.06224, over 7324.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2642, pruned_loss=0.04523, over 1422351.31 frames.], batch size: 20, lr: 6.33e-04
2022-05-14 13:09:23,899 INFO [train.py:812] (3/8) Epoch 12, batch 3150, loss[loss=0.1901, simple_loss=0.2743, pruned_loss=0.05291, over 7366.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2647, pruned_loss=0.04547, over 1424817.51 frames.], batch size: 23, lr: 6.33e-04
2022-05-14 13:10:22,790 INFO [train.py:812] (3/8) Epoch 12, batch 3200, loss[loss=0.1687, simple_loss=0.2592, pruned_loss=0.03908, over 7118.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2652, pruned_loss=0.04605, over 1424747.12 frames.], batch size: 21, lr: 6.32e-04
2022-05-14 13:11:22,081 INFO [train.py:812] (3/8) Epoch 12, batch 3250, loss[loss=0.1804, simple_loss=0.2694, pruned_loss=0.04575, over 7422.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2645, pruned_loss=0.04564, over 1425496.13 frames.], batch size: 21, lr: 6.32e-04
2022-05-14 13:12:21,121 INFO [train.py:812] (3/8) Epoch 12, batch 3300, loss[loss=0.1807, simple_loss=0.2598, pruned_loss=0.05076, over 7006.00 frames.], tot_loss[loss=0.179, simple_loss=0.2656, pruned_loss=0.04621, over 1425806.24 frames.], batch size: 16, lr: 6.32e-04
2022-05-14 13:13:18,553 INFO [train.py:812] (3/8) Epoch 12, batch 3350, loss[loss=0.1639, simple_loss=0.2413, pruned_loss=0.04325, over 7283.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2657, pruned_loss=0.04603, over 1426566.41 frames.], batch size: 18, lr: 6.31e-04
2022-05-14 13:14:17,030 INFO [train.py:812] (3/8) Epoch 12, batch 3400, loss[loss=0.1812, simple_loss=0.2596, pruned_loss=0.05135, over 6611.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2666, pruned_loss=0.04644, over 1421170.59 frames.], batch size: 38, lr: 6.31e-04
2022-05-14 13:15:16,592 INFO [train.py:812] (3/8) Epoch 12, batch 3450, loss[loss=0.1957, simple_loss=0.2841, pruned_loss=0.05363, over 7111.00 frames.], tot_loss[loss=0.1795, simple_loss=0.266, pruned_loss=0.04645, over 1419760.84 frames.], batch size: 21, lr: 6.31e-04
2022-05-14 13:16:15,024 INFO [train.py:812] (3/8) Epoch 12, batch 3500, loss[loss=0.148, simple_loss=0.2416, pruned_loss=0.02716, over 7308.00 frames.], tot_loss[loss=0.1788, simple_loss=0.266, pruned_loss=0.04583, over 1425366.44 frames.], batch size: 21, lr: 6.31e-04
2022-05-14 13:17:13,843 INFO [train.py:812] (3/8) Epoch 12, batch 3550, loss[loss=0.1633, simple_loss=0.2408, pruned_loss=0.04289, over 7015.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2654, pruned_loss=0.04537, over 1423614.81 frames.], batch size: 16, lr: 6.30e-04
2022-05-14 13:18:12,620 INFO [train.py:812] (3/8) Epoch 12, batch 3600, loss[loss=0.2003, simple_loss=0.2884, pruned_loss=0.05604, over 7235.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2661, pruned_loss=0.04548, over 1425165.22 frames.], batch size: 20, lr: 6.30e-04
2022-05-14 13:19:11,470 INFO [train.py:812] (3/8) Epoch 12, batch 3650, loss[loss=0.2054, simple_loss=0.2872, pruned_loss=0.06179, over 7440.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2656, pruned_loss=0.04506, over 1425087.73 frames.], batch size: 20, lr: 6.30e-04
2022-05-14 13:20:08,347 INFO [train.py:812] (3/8) Epoch 12, batch 3700, loss[loss=0.1694, simple_loss=0.2645, pruned_loss=0.03717, over 6858.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2649, pruned_loss=0.04493, over 1421768.85 frames.], batch size: 31, lr: 6.29e-04
2022-05-14 13:21:06,281 INFO [train.py:812] (3/8) Epoch 12, batch 3750, loss[loss=0.1806, simple_loss=0.2841, pruned_loss=0.03851, over 7369.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2644, pruned_loss=0.04472, over 1425965.90 frames.], batch size: 23, lr: 6.29e-04
2022-05-14 13:22:05,715 INFO [train.py:812] (3/8) Epoch 12, batch 3800, loss[loss=0.1733, simple_loss=0.272, pruned_loss=0.0373, over 7129.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2644, pruned_loss=0.04465, over 1428242.19 frames.], batch size: 26, lr: 6.29e-04
2022-05-14 13:23:04,540 INFO [train.py:812] (3/8) Epoch 12, batch 3850, loss[loss=0.1585, simple_loss=0.2569, pruned_loss=0.03005, over 7121.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2647, pruned_loss=0.04472, over 1430049.42 frames.], batch size: 21, lr: 6.29e-04
2022-05-14 13:24:03,544 INFO [train.py:812] (3/8) Epoch 12, batch 3900, loss[loss=0.1941, simple_loss=0.2702, pruned_loss=0.059, over 7441.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2651, pruned_loss=0.0453, over 1431160.04 frames.], batch size: 20, lr: 6.28e-04
2022-05-14 13:25:02,799 INFO [train.py:812] (3/8) Epoch 12, batch 3950, loss[loss=0.1835, simple_loss=0.2772, pruned_loss=0.04488, over 7229.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2641, pruned_loss=0.04513, over 1432445.10 frames.], batch size: 20, lr: 6.28e-04
2022-05-14 13:26:01,748 INFO [train.py:812] (3/8) Epoch 12, batch 4000, loss[loss=0.1519, simple_loss=0.2515, pruned_loss=0.02618, over 7408.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2643, pruned_loss=0.04522, over 1427433.95 frames.], batch size: 21, lr: 6.28e-04
2022-05-14 13:27:01,236 INFO [train.py:812] (3/8) Epoch 12, batch 4050, loss[loss=0.1712, simple_loss=0.2686, pruned_loss=0.03693, over 7426.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2651, pruned_loss=0.04574, over 1425471.83 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:28:00,396 INFO [train.py:812] (3/8) Epoch 12, batch 4100, loss[loss=0.163, simple_loss=0.2503, pruned_loss=0.03789, over 7333.00 frames.], tot_loss[loss=0.1785, simple_loss=0.265, pruned_loss=0.04601, over 1421234.62 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:28:59,994 INFO [train.py:812] (3/8) Epoch 12, batch 4150, loss[loss=0.1509, simple_loss=0.2358, pruned_loss=0.03305, over 7233.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2659, pruned_loss=0.04631, over 1421841.75 frames.], batch size: 20, lr: 6.27e-04
2022-05-14 13:29:59,304 INFO [train.py:812] (3/8) Epoch 12, batch 4200, loss[loss=0.1683, simple_loss=0.2661, pruned_loss=0.03527, over 7330.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2662, pruned_loss=0.04624, over 1420674.34 frames.], batch size: 22, lr: 6.27e-04
2022-05-14 13:30:59,189 INFO [train.py:812] (3/8) Epoch 12, batch 4250, loss[loss=0.178, simple_loss=0.2552, pruned_loss=0.05043, over 7409.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2649, pruned_loss=0.04588, over 1424606.81 frames.], batch size: 18, lr: 6.26e-04
2022-05-14 13:31:58,490 INFO [train.py:812] (3/8) Epoch 12, batch 4300, loss[loss=0.1789, simple_loss=0.2748, pruned_loss=0.04149, over 7241.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2648, pruned_loss=0.04606, over 1418266.09 frames.], batch size: 20, lr: 6.26e-04
2022-05-14 13:32:57,463 INFO [train.py:812] (3/8) Epoch 12, batch 4350, loss[loss=0.2102, simple_loss=0.2944, pruned_loss=0.06299, over 7219.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2631, pruned_loss=0.0455, over 1419899.56 frames.], batch size: 22, lr: 6.26e-04
2022-05-14 13:33:56,667 INFO [train.py:812] (3/8) Epoch 12, batch 4400, loss[loss=0.1953, simple_loss=0.2948, pruned_loss=0.04792, over 7309.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2631, pruned_loss=0.04558, over 1417940.88 frames.], batch size: 21, lr: 6.25e-04
2022-05-14 13:34:56,720 INFO [train.py:812] (3/8) Epoch 12, batch 4450, loss[loss=0.1829, simple_loss=0.2661, pruned_loss=0.04981, over 6114.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2621, pruned_loss=0.04545, over 1406034.88 frames.], batch size: 37, lr: 6.25e-04
2022-05-14 13:35:55,750 INFO [train.py:812] (3/8) Epoch 12, batch 4500, loss[loss=0.1977, simple_loss=0.289, pruned_loss=0.05319, over 6301.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2625, pruned_loss=0.04599, over 1389160.14 frames.], batch size: 37, lr: 6.25e-04
2022-05-14 13:36:54,579 INFO [train.py:812] (3/8) Epoch 12, batch 4550, loss[loss=0.2054, simple_loss=0.2821, pruned_loss=0.06437, over 4926.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2645, pruned_loss=0.04734, over 1349856.65 frames.], batch size: 52, lr: 6.25e-04
2022-05-14 13:38:08,546 INFO [train.py:812] (3/8) Epoch 13, batch 0, loss[loss=0.1878, simple_loss=0.2779, pruned_loss=0.04886, over 7150.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2779, pruned_loss=0.04886, over 7150.00 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:39:08,079 INFO [train.py:812] (3/8) Epoch 13, batch 50, loss[loss=0.1545, simple_loss=0.255, pruned_loss=0.02705, over 7234.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2641, pruned_loss=0.04423, over 319090.60 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:40:06,262 INFO [train.py:812] (3/8) Epoch 13, batch 100, loss[loss=0.1981, simple_loss=0.283, pruned_loss=0.05657, over 7185.00 frames.], tot_loss[loss=0.1761, simple_loss=0.265, pruned_loss=0.04365, over 565148.95 frames.], batch size: 23, lr: 6.03e-04
2022-05-14 13:41:05,018 INFO [train.py:812] (3/8) Epoch 13, batch 150, loss[loss=0.1604, simple_loss=0.2445, pruned_loss=0.03817, over 7146.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2659, pruned_loss=0.04443, over 754598.50 frames.], batch size: 20, lr: 6.03e-04
2022-05-14 13:42:04,234 INFO [train.py:812] (3/8) Epoch 13, batch 200, loss[loss=0.1722, simple_loss=0.2687, pruned_loss=0.03783, over 7136.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2642, pruned_loss=0.04445, over 900051.56 frames.], batch size: 20, lr: 6.02e-04
2022-05-14 13:43:03,735 INFO [train.py:812] (3/8) Epoch 13, batch 250, loss[loss=0.1528, simple_loss=0.2312, pruned_loss=0.03722, over 7219.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2634, pruned_loss=0.04433, over 1014152.92 frames.], batch size: 16, lr: 6.02e-04
2022-05-14 13:44:02,527 INFO [train.py:812] (3/8) Epoch 13, batch 300, loss[loss=0.1774, simple_loss=0.2755, pruned_loss=0.03961, over 7152.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2627, pruned_loss=0.04388, over 1103088.56 frames.], batch size: 20, lr: 6.02e-04
2022-05-14 13:45:01,884 INFO [train.py:812] (3/8) Epoch 13, batch 350, loss[loss=0.1955, simple_loss=0.2799, pruned_loss=0.05555, over 7063.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2634, pruned_loss=0.04405, over 1175320.09 frames.], batch size: 28, lr: 6.01e-04
2022-05-14 13:46:00,661 INFO [train.py:812] (3/8) Epoch 13, batch 400, loss[loss=0.1648, simple_loss=0.2556, pruned_loss=0.03701, over 7358.00 frames.], tot_loss[loss=0.1751, simple_loss=0.263, pruned_loss=0.04356, over 1232494.79 frames.], batch size: 19, lr: 6.01e-04
2022-05-14 13:46:57,910 INFO [train.py:812] (3/8) Epoch 13, batch 450, loss[loss=0.1619, simple_loss=0.2572, pruned_loss=0.03329, over 7325.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2618, pruned_loss=0.04321, over 1276109.12 frames.], batch size: 21, lr: 6.01e-04
2022-05-14 13:47:55,552 INFO [train.py:812] (3/8) Epoch 13, batch 500, loss[loss=0.172, simple_loss=0.2632, pruned_loss=0.04037, over 6390.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2607, pruned_loss=0.04314, over 1309883.07 frames.], batch size: 37, lr: 6.01e-04
2022-05-14 13:48:55,155 INFO [train.py:812] (3/8) Epoch 13, batch 550, loss[loss=0.2049, simple_loss=0.2837, pruned_loss=0.06304, over 7388.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2609, pruned_loss=0.04372, over 1332619.58 frames.], batch size: 23, lr: 6.00e-04
2022-05-14 13:49:53,967 INFO [train.py:812] (3/8) Epoch 13, batch 600, loss[loss=0.1565, simple_loss=0.2392, pruned_loss=0.03692, over 6789.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2599, pruned_loss=0.04374, over 1346407.32 frames.], batch size: 15, lr: 6.00e-04
2022-05-14 13:50:53,008 INFO [train.py:812] (3/8) Epoch 13, batch 650, loss[loss=0.1694, simple_loss=0.2509, pruned_loss=0.04399, over 7290.00 frames.], tot_loss[loss=0.175, simple_loss=0.2616, pruned_loss=0.04423, over 1366602.52 frames.], batch size: 18, lr: 6.00e-04
2022-05-14 13:51:52,317 INFO [train.py:812] (3/8) Epoch 13, batch 700, loss[loss=0.1703, simple_loss=0.241, pruned_loss=0.04978, over 6774.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2624, pruned_loss=0.04406, over 1383657.70 frames.], batch size: 15, lr: 6.00e-04
2022-05-14 13:52:51,777 INFO [train.py:812] (3/8) Epoch 13, batch 750, loss[loss=0.2109, simple_loss=0.2897, pruned_loss=0.06604, over 7181.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2625, pruned_loss=0.04398, over 1395552.26 frames.], batch size: 23, lr: 5.99e-04
2022-05-14 13:53:50,410 INFO [train.py:812] (3/8) Epoch 13, batch 800, loss[loss=0.1859, simple_loss=0.2712, pruned_loss=0.05029, over 7226.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2627, pruned_loss=0.04385, over 1404982.32 frames.], batch size: 22, lr: 5.99e-04
2022-05-14 13:54:49,217 INFO [train.py:812] (3/8) Epoch 13, batch 850, loss[loss=0.1522, simple_loss=0.2375, pruned_loss=0.03351, over 7138.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2631, pruned_loss=0.04407, over 1411039.88 frames.], batch size: 17, lr: 5.99e-04
2022-05-14 13:55:48,278 INFO [train.py:812] (3/8) Epoch 13, batch 900, loss[loss=0.158, simple_loss=0.2462, pruned_loss=0.03489, over 7322.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2621, pruned_loss=0.04376, over 1413876.40 frames.], batch size: 20, lr: 5.99e-04
2022-05-14 13:56:52,995 INFO [train.py:812] (3/8) Epoch 13, batch 950, loss[loss=0.1819, simple_loss=0.2689, pruned_loss=0.04745, over 7198.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2627, pruned_loss=0.0442, over 1414701.95 frames.], batch size: 26, lr: 5.98e-04
2022-05-14 13:57:52,231 INFO [train.py:812] (3/8) Epoch 13, batch 1000, loss[loss=0.2326, simple_loss=0.3175, pruned_loss=0.07385, over 6323.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2634, pruned_loss=0.04473, over 1415056.48 frames.], batch size: 37, lr: 5.98e-04
2022-05-14 13:58:51,873 INFO [train.py:812] (3/8) Epoch 13, batch 1050, loss[loss=0.1866, simple_loss=0.2708, pruned_loss=0.05123, over 7265.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2625, pruned_loss=0.04452, over 1416536.99 frames.], batch size: 19, lr: 5.98e-04
2022-05-14 13:59:49,634 INFO [train.py:812] (3/8) Epoch 13, batch 1100, loss[loss=0.2227, simple_loss=0.3038, pruned_loss=0.07078, over 7383.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2633, pruned_loss=0.04474, over 1422180.56 frames.], batch size: 23, lr: 5.97e-04
2022-05-14 14:00:49,263 INFO [train.py:812] (3/8) Epoch 13, batch 1150, loss[loss=0.1473, simple_loss=0.2302, pruned_loss=0.0322, over 7328.00 frames.], tot_loss[loss=0.1749, simple_loss=0.262, pruned_loss=0.04393, over 1425019.71 frames.], batch size: 20, lr: 5.97e-04
2022-05-14 14:01:48,645 INFO [train.py:812] (3/8) Epoch 13, batch 1200, loss[loss=0.2256, simple_loss=0.294, pruned_loss=0.07863, over 4797.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2623, pruned_loss=0.04443, over 1420856.24 frames.], batch size: 54, lr: 5.97e-04
2022-05-14 14:02:48,259 INFO [train.py:812] (3/8) Epoch 13, batch 1250, loss[loss=0.1768, simple_loss=0.27, pruned_loss=0.04176, over 7154.00 frames.], tot_loss[loss=0.1752, simple_loss=0.262, pruned_loss=0.0442, over 1418950.75 frames.], batch size: 19, lr: 5.97e-04
2022-05-14 14:03:47,346 INFO [train.py:812] (3/8) Epoch 13, batch 1300, loss[loss=0.1727, simple_loss=0.2524, pruned_loss=0.04653, over 7068.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2616, pruned_loss=0.04377, over 1418472.10 frames.], batch size: 18, lr: 5.96e-04
2022-05-14 14:04:46,574 INFO [train.py:812] (3/8) Epoch 13, batch 1350, loss[loss=0.172, simple_loss=0.2569, pruned_loss=0.04359, over 5303.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2628, pruned_loss=0.0445, over 1416062.73 frames.], batch size: 53, lr: 5.96e-04
2022-05-14 14:05:45,493 INFO [train.py:812] (3/8) Epoch 13, batch 1400, loss[loss=0.2007, simple_loss=0.2784, pruned_loss=0.06146, over 7295.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2632, pruned_loss=0.04459, over 1415420.03 frames.], batch size: 25, lr: 5.96e-04
2022-05-14 14:06:43,974 INFO [train.py:812] (3/8) Epoch 13, batch 1450, loss[loss=0.1677, simple_loss=0.2673, pruned_loss=0.034, over 7317.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2633, pruned_loss=0.0442, over 1413551.86 frames.], batch size: 21, lr: 5.96e-04
2022-05-14 14:07:42,545 INFO [train.py:812] (3/8) Epoch 13, batch 1500, loss[loss=0.2023, simple_loss=0.2848, pruned_loss=0.05988, over 7198.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2633, pruned_loss=0.0443, over 1417518.08 frames.], batch size: 23, lr: 5.95e-04
2022-05-14 14:08:42,621 INFO [train.py:812] (3/8) Epoch 13, batch 1550, loss[loss=0.1836, simple_loss=0.2924, pruned_loss=0.0374, over 7152.00 frames.], tot_loss[loss=0.1756, simple_loss=0.263, pruned_loss=0.04414, over 1419251.56 frames.], batch size: 28, lr: 5.95e-04
2022-05-14 14:09:41,279 INFO [train.py:812] (3/8) Epoch 13, batch 1600, loss[loss=0.1806, simple_loss=0.265, pruned_loss=0.0481, over 7299.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2631, pruned_loss=0.04419, over 1418705.95 frames.], batch size: 25, lr: 5.95e-04
2022-05-14 14:10:39,359 INFO [train.py:812] (3/8) Epoch 13, batch 1650, loss[loss=0.1974, simple_loss=0.2779, pruned_loss=0.05848, over 7285.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2628, pruned_loss=0.04403, over 1422389.24 frames.], batch size: 24, lr: 5.95e-04
2022-05-14 14:11:36,537 INFO [train.py:812] (3/8) Epoch 13, batch 1700, loss[loss=0.1693, simple_loss=0.25, pruned_loss=0.04431, over 7120.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2625, pruned_loss=0.04417, over 1417712.41 frames.], batch size: 17, lr: 5.94e-04
2022-05-14 14:12:34,772 INFO [train.py:812] (3/8) Epoch 13, batch 1750, loss[loss=0.1909, simple_loss=0.2798, pruned_loss=0.05098, over 7134.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2613, pruned_loss=0.04357, over 1422103.49 frames.], batch size: 26, lr: 5.94e-04
2022-05-14 14:13:34,266 INFO [train.py:812] (3/8) Epoch 13, batch 1800, loss[loss=0.1737, simple_loss=0.2482, pruned_loss=0.04962, over 6981.00 frames.], tot_loss[loss=0.175, simple_loss=0.2624, pruned_loss=0.04385, over 1427266.37 frames.], batch size: 16, lr: 5.94e-04
2022-05-14 14:14:33,806 INFO [train.py:812] (3/8) Epoch 13, batch 1850, loss[loss=0.1824, simple_loss=0.2724, pruned_loss=0.04621, over 7331.00 frames.], tot_loss[loss=0.1746, simple_loss=0.262, pruned_loss=0.04363, over 1427934.03 frames.], batch size: 22, lr: 5.94e-04
2022-05-14 14:15:33,201 INFO [train.py:812] (3/8) Epoch 13, batch 1900, loss[loss=0.1669, simple_loss=0.2564, pruned_loss=0.03869, over 7238.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2634, pruned_loss=0.04439, over 1428204.87 frames.], batch size: 20, lr: 5.93e-04
2022-05-14 14:16:32,242 INFO [train.py:812] (3/8) Epoch 13, batch 1950, loss[loss=0.1883, simple_loss=0.2656, pruned_loss=0.05548, over 7271.00 frames.], tot_loss[loss=0.1757, simple_loss=0.263, pruned_loss=0.04422, over 1428133.49 frames.], batch size: 17, lr: 5.93e-04
2022-05-14 14:17:31,533 INFO [train.py:812] (3/8) Epoch 13, batch 2000, loss[loss=0.1423, simple_loss=0.2233, pruned_loss=0.03059, over 6992.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2614, pruned_loss=0.04353, over 1427993.61 frames.], batch size: 16, lr: 5.93e-04
2022-05-14 14:18:40,070 INFO [train.py:812] (3/8) Epoch 13, batch 2050, loss[loss=0.1532, simple_loss=0.242, pruned_loss=0.03222, over 7161.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2613, pruned_loss=0.04372, over 1421297.90 frames.], batch size: 19, lr: 5.93e-04
2022-05-14 14:19:39,659 INFO [train.py:812] (3/8) Epoch 13, batch 2100, loss[loss=0.1778, simple_loss=0.261, pruned_loss=0.04725, over 7154.00 frames.], tot_loss[loss=0.1749, simple_loss=0.262, pruned_loss=0.04393, over 1420998.37 frames.], batch size: 19, lr: 5.92e-04
2022-05-14 14:20:39,506 INFO [train.py:812] (3/8) Epoch 13, batch 2150, loss[loss=0.1381, simple_loss=0.2261, pruned_loss=0.02508, over 7279.00 frames.], tot_loss[loss=0.175, simple_loss=0.2621, pruned_loss=0.04391, over 1421381.26 frames.], batch size: 18, lr: 5.92e-04
2022-05-14 14:21:36,889 INFO [train.py:812] (3/8) Epoch 13, batch 2200, loss[loss=0.1866, simple_loss=0.2737, pruned_loss=0.04975, over 7335.00 frames.], tot_loss[loss=0.175, simple_loss=0.262, pruned_loss=0.04399, over 1422539.17 frames.], batch size: 20, lr: 5.92e-04
2022-05-14 14:22:35,521 INFO [train.py:812] (3/8) Epoch 13, batch 2250, loss[loss=0.171, simple_loss=0.2555, pruned_loss=0.04319, over 7032.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2618, pruned_loss=0.0439, over 1420746.05 frames.], batch size: 28, lr: 5.91e-04
2022-05-14 14:23:34,261 INFO [train.py:812] (3/8) Epoch 13, batch 2300, loss[loss=0.149, simple_loss=0.2448, pruned_loss=0.02655, over 7107.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2625, pruned_loss=0.04409, over 1423940.11 frames.], batch size: 21, lr: 5.91e-04
2022-05-14 14:24:34,065 INFO [train.py:812] (3/8) Epoch 13, batch 2350, loss[loss=0.1671, simple_loss=0.2434, pruned_loss=0.0454, over 7160.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2624, pruned_loss=0.04419, over 1425287.20 frames.], batch size: 19, lr: 5.91e-04
2022-05-14 14:25:33,546 INFO [train.py:812] (3/8) Epoch 13, batch 2400, loss[loss=0.1683, simple_loss=0.2497, pruned_loss=0.04344, over 7129.00 frames.], tot_loss[loss=0.1747, simple_loss=0.262, pruned_loss=0.04369, over 1426420.66 frames.], batch size: 17, lr: 5.91e-04
2022-05-14 14:26:31,967 INFO [train.py:812] (3/8) Epoch 13, batch 2450, loss[loss=0.1848, simple_loss=0.2874, pruned_loss=0.04114, over 7224.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2622, pruned_loss=0.04354, over 1425893.50 frames.], batch size: 21, lr: 5.90e-04
2022-05-14 14:27:30,754 INFO [train.py:812] (3/8) Epoch 13, batch 2500, loss[loss=0.167, simple_loss=0.2495, pruned_loss=0.04227, over 7272.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2639, pruned_loss=0.04436, over 1426931.44 frames.], batch size: 18, lr: 5.90e-04
2022-05-14 14:28:30,420 INFO [train.py:812] (3/8) Epoch 13, batch 2550, loss[loss=0.1578, simple_loss=0.2381, pruned_loss=0.03874, over 6790.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2631, pruned_loss=0.04418, over 1428740.04 frames.], batch size: 15, lr: 5.90e-04
2022-05-14 14:29:29,632 INFO [train.py:812] (3/8) Epoch 13, batch 2600, loss[loss=0.1465, simple_loss=0.2364, pruned_loss=0.02825, over 6794.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2626, pruned_loss=0.04401, over 1424695.23 frames.], batch size: 15, lr: 5.90e-04
2022-05-14 14:30:29,049 INFO [train.py:812] (3/8) Epoch 13, batch 2650, loss[loss=0.1579, simple_loss=0.2461, pruned_loss=0.03483, over 7007.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2636, pruned_loss=0.04414, over 1422747.42 frames.], batch size: 16, lr: 5.89e-04
2022-05-14 14:31:27,714 INFO [train.py:812] (3/8) Epoch 13, batch 2700, loss[loss=0.1575, simple_loss=0.2366, pruned_loss=0.03919, over 7002.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2623, pruned_loss=0.04379, over 1424222.47 frames.], batch size: 16, lr: 5.89e-04
2022-05-14 14:32:27,061 INFO [train.py:812] (3/8) Epoch 13, batch 2750, loss[loss=0.2147, simple_loss=0.299, pruned_loss=0.06522, over 7109.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2623, pruned_loss=0.04397, over 1421572.90 frames.], batch size: 21, lr: 5.89e-04
2022-05-14 14:33:24,950 INFO [train.py:812] (3/8) Epoch 13, batch 2800, loss[loss=0.1442, simple_loss=0.2237, pruned_loss=0.03233, over 7114.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2634, pruned_loss=0.04412, over 1420944.01 frames.], batch size: 17, lr: 5.89e-04
2022-05-14 14:34:24,902 INFO [train.py:812] (3/8) Epoch 13, batch 2850, loss[loss=0.1916, simple_loss=0.2767, pruned_loss=0.05325, over 7398.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2633, pruned_loss=0.04393, over 1427301.15 frames.], batch size: 23, lr: 5.88e-04
2022-05-14 14:35:22,586 INFO [train.py:812] (3/8) Epoch 13, batch 2900, loss[loss=0.151, simple_loss=0.2408, pruned_loss=0.03059, over 7357.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2647, pruned_loss=0.04421, over 1424903.86 frames.], batch size: 19, lr: 5.88e-04
2022-05-14 14:36:21,962 INFO [train.py:812] (3/8) Epoch 13, batch 2950, loss[loss=0.1621, simple_loss=0.2516, pruned_loss=0.03632, over 7115.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2637, pruned_loss=0.04387, over 1426784.53 frames.], batch size: 21, lr: 5.88e-04
2022-05-14 14:37:20,805 INFO [train.py:812] (3/8) Epoch 13, batch 3000, loss[loss=0.1614, simple_loss=0.2403, pruned_loss=0.04126, over 7281.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2634, pruned_loss=0.0431, over 1427613.48 frames.], batch size: 17, lr: 5.88e-04
2022-05-14 14:37:20,807 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 14:37:28,227 INFO [train.py:841] (3/8) Epoch 13, validation: loss=0.1549, simple_loss=0.2559, pruned_loss=0.02694, over 698248.00 frames.
2022-05-14 14:38:28,393 INFO [train.py:812] (3/8) Epoch 13, batch 3050, loss[loss=0.1562, simple_loss=0.2437, pruned_loss=0.03431, over 7131.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2626, pruned_loss=0.04258, over 1428380.07 frames.], batch size: 17, lr: 5.87e-04
2022-05-14 14:39:27,922 INFO [train.py:812] (3/8) Epoch 13, batch 3100, loss[loss=0.16, simple_loss=0.2557, pruned_loss=0.0322, over 7106.00 frames.], tot_loss[loss=0.1737, simple_loss=0.262, pruned_loss=0.04268, over 1427301.64 frames.], batch size: 21, lr: 5.87e-04
2022-05-14 14:40:36,450 INFO [train.py:812] (3/8) Epoch 13, batch 3150, loss[loss=0.2252, simple_loss=0.3127, pruned_loss=0.0688, over 7306.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2634, pruned_loss=0.04343, over 1424448.53 frames.], batch size: 25, lr: 5.87e-04
2022-05-14 14:41:35,460 INFO [train.py:812] (3/8) Epoch 13, batch 3200, loss[loss=0.2149, simple_loss=0.294, pruned_loss=0.06792, over 5257.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2635, pruned_loss=0.04357, over 1425861.00 frames.], batch size: 52, lr: 5.87e-04
2022-05-14 14:42:44,514 INFO [train.py:812] (3/8) Epoch 13, batch 3250, loss[loss=0.1362, simple_loss=0.2192, pruned_loss=0.02661, over 7286.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2622, pruned_loss=0.04307, over 1428591.16 frames.], batch size: 17, lr: 5.86e-04
2022-05-14 14:43:53,093 INFO [train.py:812] (3/8) Epoch 13, batch 3300, loss[loss=0.1585, simple_loss=0.2564, pruned_loss=0.03031, over 7334.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2623, pruned_loss=0.04341, over 1427905.41 frames.], batch size: 20, lr: 5.86e-04
2022-05-14 14:44:51,613 INFO [train.py:812] (3/8) Epoch 13, batch 3350, loss[loss=0.1598, simple_loss=0.2377, pruned_loss=0.04094, over 7417.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2625, pruned_loss=0.04341, over 1421287.19 frames.], batch size: 17, lr: 5.86e-04
2022-05-14 14:46:18,933 INFO [train.py:812] (3/8) Epoch 13, batch 3400, loss[loss=0.2094, simple_loss=0.2837, pruned_loss=0.06752, over 7364.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2632, pruned_loss=0.04393, over 1424661.56 frames.], batch size: 23, lr: 5.86e-04
2022-05-14 14:47:27,726 INFO [train.py:812] (3/8) Epoch 13, batch 3450, loss[loss=0.1401, simple_loss=0.2276, pruned_loss=0.02634, over 7410.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2637, pruned_loss=0.04443, over 1413498.10 frames.], batch size: 18, lr: 5.85e-04
2022-05-14 14:48:26,581 INFO [train.py:812] (3/8) Epoch 13, batch 3500, loss[loss=0.183, simple_loss=0.2776, pruned_loss=0.04419, over 6798.00 frames.], tot_loss[loss=0.177, simple_loss=0.2645, pruned_loss=0.04475, over 1415882.45 frames.], batch size: 31, lr: 5.85e-04
2022-05-14 14:49:26,038 INFO [train.py:812] (3/8) Epoch 13, batch 3550, loss[loss=0.164, simple_loss=0.2412, pruned_loss=0.04337, over 6996.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2636, pruned_loss=0.04446, over 1420943.10 frames.], batch size: 16, lr: 5.85e-04
2022-05-14 14:50:24,009 INFO [train.py:812] (3/8) Epoch 13, batch 3600, loss[loss=0.1394, simple_loss=0.2263, pruned_loss=0.02625, over 7273.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2627, pruned_loss=0.04385, over 1420793.84 frames.], batch size: 18, lr: 5.85e-04
2022-05-14 14:51:22,199 INFO [train.py:812] (3/8) Epoch 13, batch 3650, loss[loss=0.2081, simple_loss=0.2936, pruned_loss=0.06126, over 7407.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2633, pruned_loss=0.04404, over 1423538.30 frames.], batch size: 21, lr: 5.84e-04
2022-05-14 14:52:20,915 INFO [train.py:812] (3/8) Epoch 13, batch 3700, loss[loss=0.1608, simple_loss=0.2517, pruned_loss=0.03494, over 7256.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2629, pruned_loss=0.04419, over 1424679.39 frames.], batch size: 19, lr: 5.84e-04
2022-05-14 14:53:20,281 INFO [train.py:812] (3/8) Epoch 13, batch 3750, loss[loss=0.1815, simple_loss=0.2799, pruned_loss=0.04156, over 7417.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2629, pruned_loss=0.04418, over 1425058.13 frames.], batch size: 21, lr: 5.84e-04
2022-05-14 14:54:19,184 INFO [train.py:812] (3/8) Epoch 13, batch 3800, loss[loss=0.192, simple_loss=0.2842, pruned_loss=0.04995, over 7105.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2637, pruned_loss=0.04438, over 1428741.61 frames.], batch size: 28, lr: 5.84e-04
2022-05-14 14:55:18,394 INFO [train.py:812] (3/8) Epoch 13, batch 3850, loss[loss=0.1836, simple_loss=0.2755, pruned_loss=0.04584, over 7205.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2645, pruned_loss=0.04456, over 1426863.06 frames.], batch size: 22, lr: 5.83e-04
2022-05-14 14:56:16,994 INFO [train.py:812] (3/8) Epoch 13, batch 3900, loss[loss=0.1843, simple_loss=0.2772, pruned_loss=0.04568, over 7292.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2639, pruned_loss=0.04428, over 1425862.84 frames.], batch size: 24, lr: 5.83e-04
2022-05-14 14:57:16,815 INFO [train.py:812] (3/8) Epoch 13, batch 3950, loss[loss=0.2073, simple_loss=0.2935, pruned_loss=0.06052, over 7203.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2641, pruned_loss=0.04445, over 1424683.04 frames.], batch size: 23, lr: 5.83e-04
2022-05-14 14:58:15,066 INFO [train.py:812] (3/8) Epoch 13, batch 4000, loss[loss=0.1628, simple_loss=0.2458, pruned_loss=0.03994, over 7147.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2633, pruned_loss=0.04407, over 1422986.01 frames.], batch size: 17, lr: 5.83e-04
2022-05-14 14:59:14,567 INFO [train.py:812] (3/8) Epoch 13, batch 4050, loss[loss=0.1683, simple_loss=0.2543, pruned_loss=0.04111, over 7232.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2627, pruned_loss=0.04406, over 1424915.90 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:00:14,085 INFO [train.py:812] (3/8) Epoch 13, batch 4100, loss[loss=0.2085, simple_loss=0.3104, pruned_loss=0.05333, over 7141.00 frames.], tot_loss[loss=0.174, simple_loss=0.2612, pruned_loss=0.04344, over 1424751.62 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:01:13,273 INFO [train.py:812] (3/8) Epoch 13, batch 4150, loss[loss=0.1403, simple_loss=0.2286, pruned_loss=0.02605, over 7439.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2625, pruned_loss=0.04382, over 1421014.14 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:02:11,341 INFO [train.py:812] (3/8) Epoch 13, batch 4200, loss[loss=0.1744, simple_loss=0.2728, pruned_loss=0.03796, over 7146.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2619, pruned_loss=0.04361, over 1421957.78 frames.], batch size: 20, lr: 5.82e-04
2022-05-14 15:03:10,124 INFO [train.py:812] (3/8) Epoch 13, batch 4250, loss[loss=0.1876, simple_loss=0.2736, pruned_loss=0.05082, over 7173.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2614, pruned_loss=0.04322, over 1418904.35 frames.], batch size: 26, lr: 5.81e-04
2022-05-14 15:04:08,184 INFO [train.py:812] (3/8) Epoch 13, batch 4300, loss[loss=0.1581, simple_loss=0.2509, pruned_loss=0.0327, over 7431.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2616, pruned_loss=0.04329, over 1416329.14 frames.], batch size: 20, lr: 5.81e-04
2022-05-14 15:05:06,780 INFO [train.py:812] (3/8) Epoch 13, batch 4350, loss[loss=0.1701, simple_loss=0.2514, pruned_loss=0.04436, over 7000.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2617, pruned_loss=0.04352, over 1410501.42 frames.], batch size: 16, lr: 5.81e-04
2022-05-14 15:06:06,048 INFO [train.py:812] (3/8) Epoch 13, batch 4400, loss[loss=0.185, simple_loss=0.2641, pruned_loss=0.05296, over 4715.00 frames.], tot_loss[loss=0.1728, simple_loss=0.26, pruned_loss=0.0428, over 1408916.47 frames.], batch size: 52, lr: 5.81e-04
2022-05-14 15:07:04,935 INFO [train.py:812] (3/8) Epoch 13, batch 4450, loss[loss=0.1852, simple_loss=0.276, pruned_loss=0.04713, over 7272.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2592, pruned_loss=0.04248, over 1406676.39 frames.], batch size: 24, lr: 5.81e-04
2022-05-14 15:08:03,267 INFO [train.py:812] (3/8) Epoch 13, batch 4500, loss[loss=0.1721, simple_loss=0.2715, pruned_loss=0.03636, over 7409.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2608, pruned_loss=0.04321, over 1389118.60 frames.], batch size: 21, lr: 5.80e-04
2022-05-14 15:09:01,456 INFO [train.py:812] (3/8) Epoch 13, batch 4550, loss[loss=0.1767, simple_loss=0.2597, pruned_loss=0.04691, over 5204.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2637, pruned_loss=0.04471, over 1355687.60 frames.], batch size: 53, lr: 5.80e-04
2022-05-14 15:10:14,182 INFO [train.py:812] (3/8) Epoch 14, batch 0, loss[loss=0.1864, simple_loss=0.2649, pruned_loss=0.05393, over 7372.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2649, pruned_loss=0.05393, over 7372.00 frames.], batch size: 23, lr: 5.61e-04
2022-05-14 15:11:14,040 INFO [train.py:812] (3/8) Epoch 14, batch 50, loss[loss=0.1665, simple_loss=0.2594, pruned_loss=0.03681, over 7128.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2589, pruned_loss=0.04374, over 322832.62 frames.], batch size: 21, lr: 5.61e-04
2022-05-14 15:12:13,747 INFO [train.py:812] (3/8) Epoch 14, batch 100, loss[loss=0.1709, simple_loss=0.2584, pruned_loss=0.04172, over 7157.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2606, pruned_loss=0.04328, over 572516.28 frames.], batch size: 20, lr: 5.61e-04
2022-05-14 15:13:13,277 INFO [train.py:812] (3/8) Epoch 14, batch 150, loss[loss=0.1473, simple_loss=0.2241, pruned_loss=0.03523, over 6970.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2593, pruned_loss=0.04265, over 762723.50 frames.], batch size: 16, lr: 5.61e-04
2022-05-14 15:14:11,613 INFO [train.py:812] (3/8) Epoch 14, batch 200, loss[loss=0.1752, simple_loss=0.2669, pruned_loss=0.04179, over 7210.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2595, pruned_loss=0.04213, over 910092.89 frames.], batch size: 22, lr: 5.60e-04
2022-05-14 15:15:09,280 INFO [train.py:812] (3/8) Epoch 14, batch 250, loss[loss=0.1768, simple_loss=0.2732, pruned_loss=0.04024, over 7204.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2608, pruned_loss=0.04237, over 1026340.24 frames.], batch size: 22, lr: 5.60e-04
2022-05-14 15:16:07,594 INFO [train.py:812] (3/8) Epoch 14, batch 300, loss[loss=0.1782, simple_loss=0.2624, pruned_loss=0.04696, over 7408.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2629, pruned_loss=0.04289, over 1113087.03 frames.], batch size: 21, lr: 5.60e-04
2022-05-14 15:17:06,816 INFO [train.py:812] (3/8) Epoch 14, batch 350, loss[loss=0.1648, simple_loss=0.2512, pruned_loss=0.0392, over 7439.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2613, pruned_loss=0.04295, over 1180950.21 frames.], batch size: 20, lr: 5.60e-04
2022-05-14 15:18:11,721 INFO [train.py:812] (3/8) Epoch 14, batch 400, loss[loss=0.1728, simple_loss=0.2715, pruned_loss=0.03705, over 7066.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2602, pruned_loss=0.04238, over 1231303.58 frames.], batch size: 28, lr: 5.59e-04
2022-05-14 15:19:10,167 INFO [train.py:812] (3/8) Epoch 14, batch 450, loss[loss=0.2171, simple_loss=0.2989, pruned_loss=0.06761, over 6513.00 frames.], tot_loss[loss=0.173, simple_loss=0.2612, pruned_loss=0.04244, over 1273270.46 frames.], batch size: 37, lr: 5.59e-04
2022-05-14 15:20:09,606 INFO [train.py:812] (3/8) Epoch 14, batch 500, loss[loss=0.1982, simple_loss=0.2857, pruned_loss=0.05535, over 7094.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2597, pruned_loss=0.04162, over 1301910.85 frames.], batch size: 28, lr: 5.59e-04
2022-05-14 15:21:08,779 INFO [train.py:812] (3/8) Epoch 14, batch 550, loss[loss=0.1699, simple_loss=0.2658, pruned_loss=0.03698, over 6254.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.0413, over 1326667.79 frames.], batch size: 37, lr: 5.59e-04
2022-05-14 15:22:08,315 INFO [train.py:812] (3/8) Epoch 14, batch 600, loss[loss=0.1709, simple_loss=0.2622, pruned_loss=0.03981, over 7321.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2595, pruned_loss=0.04135, over 1348789.35 frames.], batch size: 21, lr: 5.59e-04
2022-05-14 15:23:07,038 INFO [train.py:812] (3/8) Epoch 14, batch 650, loss[loss=0.1588, simple_loss=0.2392, pruned_loss=0.03919, over 7069.00 frames.], tot_loss[loss=0.172, simple_loss=0.2604, pruned_loss=0.04177, over 1361942.71 frames.], batch size: 18, lr: 5.58e-04
2022-05-14 15:24:06,625 INFO [train.py:812] (3/8) Epoch 14, batch 700, loss[loss=0.1569, simple_loss=0.2401, pruned_loss=0.03682, over 7263.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2598, pruned_loss=0.04153, over 1377272.19 frames.], batch size: 18, lr: 5.58e-04
2022-05-14 15:25:05,442 INFO [train.py:812] (3/8) Epoch 14, batch 750, loss[loss=0.1777, simple_loss=0.2738, pruned_loss=0.04076, over 7194.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04151, over 1383395.77 frames.], batch size: 23, lr: 5.58e-04
2022-05-14 15:26:04,459 INFO [train.py:812] (3/8) Epoch 14, batch 800, loss[loss=0.1878, simple_loss=0.2721, pruned_loss=0.05181, over 7311.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2597, pruned_loss=0.0417, over 1392901.47 frames.], batch size: 25, lr: 5.58e-04
2022-05-14 15:27:03,671 INFO [train.py:812] (3/8) Epoch 14, batch 850, loss[loss=0.174, simple_loss=0.2686, pruned_loss=0.03971, over 7219.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2596, pruned_loss=0.04197, over 1400825.09 frames.], batch size: 21, lr: 5.57e-04
2022-05-14 15:28:02,927 INFO [train.py:812] (3/8) Epoch 14, batch 900, loss[loss=0.1554, simple_loss=0.2423, pruned_loss=0.03422, over 7169.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2603, pruned_loss=0.04235, over 1403732.07 frames.], batch size: 18, lr: 5.57e-04
2022-05-14 15:29:01,737 INFO [train.py:812] (3/8) Epoch 14, batch 950, loss[loss=0.1699, simple_loss=0.2655, pruned_loss=0.0371, over 7227.00 frames.], tot_loss[loss=0.173, simple_loss=0.261, pruned_loss=0.04254, over 1403900.50 frames.], batch size: 21, lr: 5.57e-04
2022-05-14 15:30:01,401 INFO [train.py:812] (3/8) Epoch 14, batch 1000, loss[loss=0.1889, simple_loss=0.2748, pruned_loss=0.05145, over 7217.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2602, pruned_loss=0.04222, over 1410604.79 frames.], batch size: 22, lr: 5.57e-04
2022-05-14 15:31:00,112 INFO [train.py:812] (3/8) Epoch 14, batch 1050, loss[loss=0.1753, simple_loss=0.2624, pruned_loss=0.04414, over 7414.00 frames.], tot_loss[loss=0.1713, simple_loss=0.259, pruned_loss=0.04177, over 1411015.47 frames.], batch size: 21, lr: 5.56e-04
2022-05-14 15:31:57,355 INFO [train.py:812] (3/8) Epoch 14, batch 1100, loss[loss=0.1856, simple_loss=0.2731, pruned_loss=0.04905, over 6804.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.04149, over 1410268.80 frames.], batch size: 31, lr: 5.56e-04
2022-05-14 15:32:55,035 INFO [train.py:812] (3/8) Epoch 14, batch 1150, loss[loss=0.2048, simple_loss=0.2941, pruned_loss=0.05777, over 7337.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2601, pruned_loss=0.04169, over 1410315.50 frames.], batch size: 22, lr: 5.56e-04
2022-05-14 15:33:54,463 INFO [train.py:812] (3/8) Epoch 14, batch 1200, loss[loss=0.2368, simple_loss=0.3016, pruned_loss=0.08604, over 4719.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2608, pruned_loss=0.04196, over 1409694.47 frames.], batch size: 54, lr: 5.56e-04
2022-05-14 15:34:52,744 INFO [train.py:812] (3/8) Epoch 14, batch 1250, loss[loss=0.1893, simple_loss=0.2748, pruned_loss=0.05185, over 7440.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2613, pruned_loss=0.04222, over 1413959.31 frames.], batch size: 20, lr: 5.56e-04
2022-05-14 15:35:51,072 INFO [train.py:812] (3/8) Epoch 14, batch 1300, loss[loss=0.1384, simple_loss=0.2278, pruned_loss=0.02444, over 7262.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2603, pruned_loss=0.0415, over 1417326.71 frames.], batch size: 19, lr: 5.55e-04
2022-05-14 15:36:49,464 INFO [train.py:812] (3/8) Epoch 14, batch 1350, loss[loss=0.1364, simple_loss=0.2173, pruned_loss=0.02774, over 7273.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2596, pruned_loss=0.04134, over 1421083.74 frames.], batch size: 18, lr: 5.55e-04
2022-05-14 15:37:48,218 INFO [train.py:812] (3/8) Epoch 14, batch 1400, loss[loss=0.1691, simple_loss=0.2462, pruned_loss=0.04602, over 7185.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2603, pruned_loss=0.04159, over 1417119.37 frames.], batch size: 18, lr: 5.55e-04
2022-05-14 15:38:45,042 INFO [train.py:812] (3/8) Epoch 14, batch 1450, loss[loss=0.1442, simple_loss=0.2311, pruned_loss=0.02871, over 7286.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2599, pruned_loss=0.0415, over 1420721.02 frames.], batch size: 17, lr: 5.55e-04
2022-05-14 15:39:43,863 INFO [train.py:812] (3/8) Epoch 14, batch 1500, loss[loss=0.1647, simple_loss=0.2437, pruned_loss=0.04283, over 7264.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2589, pruned_loss=0.04145, over 1423113.72 frames.], batch size: 17, lr: 5.54e-04
2022-05-14 15:40:41,999 INFO [train.py:812] (3/8) Epoch 14, batch 1550, loss[loss=0.1726, simple_loss=0.2636, pruned_loss=0.04084, over 6510.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2595, pruned_loss=0.04185, over 1417856.95 frames.], batch size: 38, lr: 5.54e-04
2022-05-14 15:41:40,133 INFO [train.py:812] (3/8) Epoch 14, batch 1600, loss[loss=0.1904, simple_loss=0.2866, pruned_loss=0.04715, over 7414.00 frames.], tot_loss[loss=0.173, simple_loss=0.261, pruned_loss=0.04251, over 1416280.03 frames.], batch size: 21, lr: 5.54e-04
2022-05-14 15:42:38,933 INFO [train.py:812] (3/8) Epoch 14, batch 1650, loss[loss=0.1789, simple_loss=0.2698, pruned_loss=0.04403, over 7237.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2617, pruned_loss=0.04276, over 1418541.42 frames.], batch size: 20, lr: 5.54e-04
2022-05-14 15:43:38,138 INFO [train.py:812] (3/8) Epoch 14, batch 1700, loss[loss=0.1592, simple_loss=0.25, pruned_loss=0.03421, over 6451.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2615, pruned_loss=0.04248, over 1418537.20 frames.], batch size: 38, lr: 5.54e-04
2022-05-14 15:44:37,209 INFO [train.py:812] (3/8) Epoch 14, batch 1750, loss[loss=0.14, simple_loss=0.2183, pruned_loss=0.03089, over 7272.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2612, pruned_loss=0.04236, over 1421649.52 frames.], batch size: 17, lr: 5.53e-04
2022-05-14 15:45:37,401 INFO [train.py:812] (3/8) Epoch 14, batch 1800, loss[loss=0.2122, simple_loss=0.2963, pruned_loss=0.06408, over 7136.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2606, pruned_loss=0.0422, over 1426583.75 frames.], batch size: 20, lr: 5.53e-04
2022-05-14 15:46:35,081 INFO [train.py:812] (3/8) Epoch 14, batch 1850, loss[loss=0.1779, simple_loss=0.2732, pruned_loss=0.04134, over 7315.00 frames.], tot_loss[loss=0.173, simple_loss=0.2611, pruned_loss=0.04243, over 1426173.16 frames.], batch size: 25, lr: 5.53e-04
2022-05-14 15:47:33,722 INFO [train.py:812] (3/8) Epoch 14, batch 1900, loss[loss=0.1922, simple_loss=0.2889, pruned_loss=0.0478, over 6492.00 frames.], tot_loss[loss=0.174, simple_loss=0.2621, pruned_loss=0.043, over 1421300.73 frames.], batch size: 38, lr: 5.53e-04
2022-05-14 15:48:32,633 INFO [train.py:812] (3/8) Epoch 14, batch 1950, loss[loss=0.1484, simple_loss=0.2365, pruned_loss=0.03016, over 7247.00 frames.], tot_loss[loss=0.1737, simple_loss=0.262, pruned_loss=0.04265, over 1423050.46 frames.], batch size: 19, lr: 5.52e-04
2022-05-14 15:49:32,350 INFO [train.py:812] (3/8) Epoch 14, batch 2000, loss[loss=0.2009, simple_loss=0.2967, pruned_loss=0.05257, over 7340.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2619, pruned_loss=0.04273, over 1424430.77 frames.], batch size: 22, lr: 5.52e-04
2022-05-14 15:50:31,354 INFO [train.py:812] (3/8) Epoch 14, batch 2050, loss[loss=0.1863, simple_loss=0.2858, pruned_loss=0.04341, over 7383.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04281, over 1425749.71 frames.], batch size: 23, lr: 5.52e-04
2022-05-14 15:51:31,089 INFO [train.py:812] (3/8) Epoch 14, batch 2100, loss[loss=0.1622, simple_loss=0.257, pruned_loss=0.03373, over 7249.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2619, pruned_loss=0.04273, over 1425090.33 frames.], batch size: 20, lr: 5.52e-04
2022-05-14 15:52:30,509 INFO [train.py:812] (3/8) Epoch 14, batch 2150, loss[loss=0.1606, simple_loss=0.2575, pruned_loss=0.03183, over 7127.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2609, pruned_loss=0.04194, over 1427722.38 frames.], batch size: 26, lr: 5.52e-04
2022-05-14 15:53:29,976 INFO [train.py:812] (3/8) Epoch 14, batch 2200, loss[loss=0.1864, simple_loss=0.2809, pruned_loss=0.04595, over 7438.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2611, pruned_loss=0.04219, over 1426616.52 frames.], batch size: 20, lr: 5.51e-04
2022-05-14 15:54:28,286 INFO [train.py:812] (3/8) Epoch 14, batch 2250, loss[loss=0.1911, simple_loss=0.2798, pruned_loss=0.05122, over 7222.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2605, pruned_loss=0.04216, over 1427892.66 frames.], batch size: 20, lr: 5.51e-04
2022-05-14 15:55:26,895 INFO [train.py:812] (3/8) Epoch 14, batch 2300, loss[loss=0.1879, simple_loss=0.2751, pruned_loss=0.05038, over 7062.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2596, pruned_loss=0.04201, over 1427752.34 frames.], batch size: 28, lr: 5.51e-04
2022-05-14 15:56:25,082 INFO [train.py:812] (3/8) Epoch 14, batch 2350, loss[loss=0.2184, simple_loss=0.2866, pruned_loss=0.07514, over 5173.00 frames.], tot_loss[loss=0.1723, simple_loss=0.26, pruned_loss=0.04232, over 1427329.92 frames.], batch size: 52, lr: 5.51e-04
2022-05-14 15:57:24,248 INFO [train.py:812] (3/8) Epoch 14, batch 2400, loss[loss=0.1607, simple_loss=0.2389, pruned_loss=0.04123, over 7290.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2595, pruned_loss=0.04195, over 1427777.65 frames.], batch size: 17, lr: 5.50e-04
2022-05-14 15:58:23,293 INFO [train.py:812] (3/8) Epoch 14, batch 2450, loss[loss=0.1751, simple_loss=0.28, pruned_loss=0.03508, over 6728.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2609, pruned_loss=0.04239, over 1429996.81 frames.], batch size: 31, lr: 5.50e-04
2022-05-14 15:59:21,590 INFO [train.py:812] (3/8) Epoch 14, batch 2500, loss[loss=0.1642, simple_loss=0.242, pruned_loss=0.0432, over 7277.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2613, pruned_loss=0.04262, over 1426156.54 frames.], batch size: 17, lr: 5.50e-04
2022-05-14 16:00:19,957 INFO [train.py:812] (3/8) Epoch 14, batch 2550, loss[loss=0.1995, simple_loss=0.295, pruned_loss=0.05197, over 7320.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2623, pruned_loss=0.0432, over 1422708.99 frames.], batch size: 25, lr: 5.50e-04
2022-05-14 16:01:19,223 INFO [train.py:812] (3/8) Epoch 14, batch 2600, loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03185, over 7404.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04284, over 1419183.25 frames.], batch size: 21, lr: 5.50e-04
2022-05-14 16:02:16,423 INFO [train.py:812] (3/8) Epoch 14, batch 2650, loss[loss=0.1758, simple_loss=0.2771, pruned_loss=0.0372, over 7102.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2621, pruned_loss=0.04311, over 1416528.52 frames.], batch size: 21, lr: 5.49e-04
2022-05-14 16:03:15,380 INFO [train.py:812] (3/8) Epoch 14, batch 2700, loss[loss=0.132, simple_loss=0.2159, pruned_loss=0.02404, over 7008.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2627, pruned_loss=0.0435, over 1421282.17 frames.], batch size: 16, lr: 5.49e-04
2022-05-14 16:04:13,413 INFO [train.py:812] (3/8) Epoch 14, batch 2750, loss[loss=0.1825, simple_loss=0.2746, pruned_loss=0.04519, over 7283.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2613, pruned_loss=0.04277, over 1426627.49 frames.], batch size: 24, lr: 5.49e-04
2022-05-14 16:05:11,586 INFO [train.py:812] (3/8) Epoch 14, batch 2800, loss[loss=0.1546, simple_loss=0.2328, pruned_loss=0.03817, over 7146.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2606, pruned_loss=0.04242, over 1425699.61 frames.], batch size: 17, lr: 5.49e-04
2022-05-14 16:06:10,653 INFO [train.py:812] (3/8) Epoch 14, batch 2850, loss[loss=0.1587, simple_loss=0.252, pruned_loss=0.03272, over 7420.00 frames.], tot_loss[loss=0.1722, simple_loss=0.26, pruned_loss=0.04222, over 1426746.47 frames.], batch size: 21, lr: 5.48e-04
2022-05-14 16:07:10,183 INFO [train.py:812] (3/8) Epoch 14, batch 2900, loss[loss=0.1626, simple_loss=0.2606, pruned_loss=0.03228, over 7124.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2603, pruned_loss=0.04214, over 1427962.68 frames.], batch size: 21, lr: 5.48e-04
2022-05-14 16:08:08,880 INFO [train.py:812] (3/8) Epoch 14, batch 2950, loss[loss=0.1691, simple_loss=0.2573, pruned_loss=0.04041, over 7183.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2606, pruned_loss=0.04208, over 1429047.23 frames.], batch size: 23, lr: 5.48e-04
2022-05-14 16:09:07,577 INFO [train.py:812] (3/8) Epoch 14, batch 3000, loss[loss=0.196, simple_loss=0.2779, pruned_loss=0.05706, over 7298.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2587, pruned_loss=0.04141, over 1430502.82 frames.], batch size: 24, lr: 5.48e-04
2022-05-14 16:09:07,578 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 16:09:15,054 INFO [train.py:841] (3/8) Epoch 14, validation: loss=0.1549, simple_loss=0.2556, pruned_loss=0.02713, over 698248.00 frames.
2022-05-14 16:10:14,214 INFO [train.py:812] (3/8) Epoch 14, batch 3050, loss[loss=0.1465, simple_loss=0.2256, pruned_loss=0.03368, over 7288.00 frames.], tot_loss[loss=0.1712, simple_loss=0.259, pruned_loss=0.04164, over 1430541.77 frames.], batch size: 17, lr: 5.48e-04
2022-05-14 16:11:13,763 INFO [train.py:812] (3/8) Epoch 14, batch 3100, loss[loss=0.1813, simple_loss=0.2701, pruned_loss=0.04629, over 7183.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2602, pruned_loss=0.0426, over 1431428.69 frames.], batch size: 23, lr: 5.47e-04
2022-05-14 16:12:13,361 INFO [train.py:812] (3/8) Epoch 14, batch 3150, loss[loss=0.1949, simple_loss=0.2755, pruned_loss=0.05719, over 5340.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2589, pruned_loss=0.04204, over 1430617.57 frames.], batch size: 52, lr: 5.47e-04
2022-05-14 16:13:13,789 INFO [train.py:812] (3/8) Epoch 14, batch 3200, loss[loss=0.1733, simple_loss=0.2643, pruned_loss=0.04117, over 7332.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2594, pruned_loss=0.04193, over 1429881.59 frames.], batch size: 22, lr: 5.47e-04
2022-05-14 16:14:11,595 INFO [train.py:812] (3/8) Epoch 14, batch 3250, loss[loss=0.1982, simple_loss=0.2934, pruned_loss=0.05149, over 7149.00 frames.], tot_loss[loss=0.1721, simple_loss=0.26, pruned_loss=0.04206, over 1427095.58 frames.], batch size: 26, lr: 5.47e-04
2022-05-14 16:15:10,524 INFO [train.py:812] (3/8) Epoch 14, batch 3300, loss[loss=0.1684, simple_loss=0.2535, pruned_loss=0.04169, over 7154.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2597, pruned_loss=0.04168, over 1423418.60 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:16:09,531 INFO [train.py:812] (3/8) Epoch 14, batch 3350, loss[loss=0.1604, simple_loss=0.2421, pruned_loss=0.03937, over 7408.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2592, pruned_loss=0.04183, over 1425667.85 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:17:08,391 INFO [train.py:812] (3/8) Epoch 14, batch 3400, loss[loss=0.1789, simple_loss=0.2728, pruned_loss=0.04249, over 7157.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2601, pruned_loss=0.04178, over 1426341.11 frames.], batch size: 18, lr: 5.46e-04
2022-05-14 16:18:17,665 INFO [train.py:812] (3/8) Epoch 14, batch 3450, loss[loss=0.1538, simple_loss=0.259, pruned_loss=0.02428, over 7124.00 frames.], tot_loss[loss=0.172, simple_loss=0.2606, pruned_loss=0.04174, over 1425636.18 frames.], batch size: 21, lr: 5.46e-04
2022-05-14 16:19:16,722 INFO [train.py:812] (3/8) Epoch 14, batch 3500, loss[loss=0.1634, simple_loss=0.2659, pruned_loss=0.03042, over 7332.00 frames.], tot_loss[loss=0.172, simple_loss=0.2603, pruned_loss=0.04186, over 1428579.55 frames.], batch size: 22, lr: 5.46e-04
2022-05-14 16:20:15,507 INFO [train.py:812] (3/8) Epoch 14, batch 3550, loss[loss=0.179, simple_loss=0.2666, pruned_loss=0.04567, over 7320.00 frames.], tot_loss[loss=0.1718, simple_loss=0.26, pruned_loss=0.04181, over 1428419.79 frames.], batch size: 21, lr: 5.45e-04
2022-05-14 16:21:14,190 INFO [train.py:812] (3/8) Epoch 14, batch 3600, loss[loss=0.1837, simple_loss=0.2592, pruned_loss=0.05403, over 7341.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2589, pruned_loss=0.04171, over 1431555.31 frames.], batch size: 19, lr: 5.45e-04
2022-05-14 16:22:13,044 INFO [train.py:812] (3/8) Epoch 14, batch 3650, loss[loss=0.1661, simple_loss=0.2626, pruned_loss=0.03476, over 7233.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2593, pruned_loss=0.04187, over 1430336.50 frames.], batch size: 20, lr: 5.45e-04
2022-05-14 16:23:12,477 INFO [train.py:812] (3/8) Epoch 14, batch 3700, loss[loss=0.1996, simple_loss=0.2938, pruned_loss=0.05268, over 7287.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2598, pruned_loss=0.04229, over 1422469.84 frames.], batch size: 24, lr: 5.45e-04
2022-05-14 16:24:11,507 INFO [train.py:812] (3/8) Epoch 14, batch 3750, loss[loss=0.2081, simple_loss=0.2906, pruned_loss=0.06276, over 5284.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2604, pruned_loss=0.04261, over 1421329.90 frames.], batch size: 52, lr: 5.45e-04
2022-05-14 16:25:11,054 INFO [train.py:812] (3/8) Epoch 14, batch 3800, loss[loss=0.1488, simple_loss=0.2313, pruned_loss=0.03312, over 6999.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2605, pruned_loss=0.04253, over 1419982.19 frames.], batch size: 16, lr: 5.44e-04
2022-05-14 16:26:09,751 INFO [train.py:812] (3/8) Epoch 14, batch 3850, loss[loss=0.209, simple_loss=0.2972, pruned_loss=0.06046, over 7210.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2613, pruned_loss=0.0428, over 1419900.38 frames.], batch size: 22, lr: 5.44e-04
2022-05-14 16:27:08,434 INFO [train.py:812] (3/8) Epoch 14, batch 3900, loss[loss=0.177, simple_loss=0.2667, pruned_loss=0.04361, over 7319.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2613, pruned_loss=0.04258, over 1422099.42 frames.], batch size: 21, lr: 5.44e-04
2022-05-14 16:28:07,615 INFO [train.py:812] (3/8) Epoch 14, batch 3950, loss[loss=0.2309, simple_loss=0.3008, pruned_loss=0.08049, over 5049.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2602, pruned_loss=0.04228, over 1419773.71 frames.], batch size: 53, lr: 5.44e-04
2022-05-14 16:29:06,374 INFO [train.py:812] (3/8) Epoch 14, batch 4000, loss[loss=0.1888, simple_loss=0.2832, pruned_loss=0.04721, over 7334.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2605, pruned_loss=0.04218, over 1421248.26 frames.], batch size: 22, lr: 5.43e-04
2022-05-14 16:30:03,970 INFO [train.py:812] (3/8) Epoch 14, batch 4050, loss[loss=0.1584, simple_loss=0.244, pruned_loss=0.03646, over 7268.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2593, pruned_loss=0.04176, over 1423474.05 frames.], batch size: 16, lr: 5.43e-04
2022-05-14 16:31:03,485 INFO [train.py:812] (3/8) Epoch 14, batch 4100, loss[loss=0.2067, simple_loss=0.2837, pruned_loss=0.06484, over 6946.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2595, pruned_loss=0.04213, over 1421016.26 frames.], batch size: 32, lr: 5.43e-04
2022-05-14 16:32:02,252 INFO [train.py:812] (3/8) Epoch 14, batch 4150, loss[loss=0.1605, simple_loss=0.2617, pruned_loss=0.02969, over 7214.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2594, pruned_loss=0.04222, over 1420250.72 frames.], batch size: 21, lr: 5.43e-04
2022-05-14 16:33:01,712 INFO [train.py:812] (3/8) Epoch 14, batch 4200, loss[loss=0.142, simple_loss=0.2192, pruned_loss=0.03242, over 7276.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2577, pruned_loss=0.04161, over 1422366.65 frames.], batch size: 17, lr: 5.43e-04
2022-05-14 16:34:00,229 INFO [train.py:812] (3/8) Epoch 14, batch 4250, loss[loss=0.1849, simple_loss=0.2703, pruned_loss=0.04972, over 6348.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2582, pruned_loss=0.04197, over 1416189.82 frames.], batch size: 37, lr: 5.42e-04
2022-05-14 16:34:59,081 INFO [train.py:812] (3/8) Epoch 14, batch 4300, loss[loss=0.1571, simple_loss=0.251, pruned_loss=0.03159, over 7220.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2595, pruned_loss=0.04252, over 1411570.74 frames.], batch size: 21, lr: 5.42e-04
2022-05-14 16:35:56,837 INFO [train.py:812] (3/8) Epoch 14, batch 4350, loss[loss=0.1313, simple_loss=0.2104, pruned_loss=0.02609, over 7238.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2588, pruned_loss=0.04218, over 1408809.26 frames.], batch size: 16, lr: 5.42e-04
2022-05-14 16:37:01,587 INFO [train.py:812] (3/8) Epoch 14, batch 4400, loss[loss=0.1709, simple_loss=0.271, pruned_loss=0.03541, over 7137.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2591, pruned_loss=0.04217, over 1403677.41 frames.], batch size: 20, lr: 5.42e-04
2022-05-14 16:38:00,472 INFO [train.py:812] (3/8) Epoch 14, batch 4450, loss[loss=0.2011, simple_loss=0.2834, pruned_loss=0.05935, over 5241.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2605, pruned_loss=0.04256, over 1394241.28 frames.], batch size: 52, lr: 5.42e-04
2022-05-14 16:38:59,695 INFO [train.py:812] (3/8) Epoch 14, batch 4500, loss[loss=0.2268, simple_loss=0.3029, pruned_loss=0.0753, over 4564.00 frames.], tot_loss[loss=0.1737, simple_loss=0.261, pruned_loss=0.04322, over 1378340.69 frames.], batch size: 52, lr: 5.41e-04
2022-05-14 16:40:07,821 INFO [train.py:812] (3/8) Epoch 14, batch 4550, loss[loss=0.1611, simple_loss=0.2451, pruned_loss=0.03857, over 6792.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2616, pruned_loss=0.04355, over 1368359.36 frames.], batch size: 31, lr: 5.41e-04
2022-05-14 16:41:16,674 INFO [train.py:812] (3/8) Epoch 15, batch 0, loss[loss=0.1826, simple_loss=0.273, pruned_loss=0.04606, over 7022.00 frames.], tot_loss[loss=0.1826, simple_loss=0.273, pruned_loss=0.04606, over 7022.00 frames.], batch size: 28, lr: 5.25e-04
2022-05-14 16:42:15,551 INFO [train.py:812] (3/8) Epoch 15, batch 50, loss[loss=0.1959, simple_loss=0.2736, pruned_loss=0.05906, over 5037.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2626, pruned_loss=0.04378, over 322042.74 frames.], batch size: 52, lr: 5.24e-04
2022-05-14 16:43:15,416 INFO [train.py:812] (3/8) Epoch 15, batch 100, loss[loss=0.175, simple_loss=0.272, pruned_loss=0.03901, over 7174.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2602, pruned_loss=0.04167, over 568673.93 frames.], batch size: 18, lr: 5.24e-04
2022-05-14 16:44:31,174 INFO [train.py:812] (3/8) Epoch 15, batch 150, loss[loss=0.1465, simple_loss=0.2381, pruned_loss=0.0274, over 7118.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04152, over 758912.12 frames.], batch size: 21, lr: 5.24e-04
2022-05-14 16:45:31,053 INFO [train.py:812] (3/8) Epoch 15, batch 200, loss[loss=0.1768, simple_loss=0.2606, pruned_loss=0.04653, over 7331.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2619, pruned_loss=0.04233, over 903442.69 frames.], batch size: 20, lr: 5.24e-04
2022-05-14 16:46:49,218 INFO [train.py:812] (3/8) Epoch 15, batch 250, loss[loss=0.1817, simple_loss=0.2671, pruned_loss=0.04815, over 6399.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2617, pruned_loss=0.042, over 1020110.19 frames.], batch size: 38, lr: 5.24e-04
2022-05-14 16:48:07,490 INFO [train.py:812] (3/8) Epoch 15, batch 300, loss[loss=0.1514, simple_loss=0.2332, pruned_loss=0.03477, over 7130.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2596, pruned_loss=0.04109, over 1110433.74 frames.], batch size: 17, lr: 5.23e-04
2022-05-14 16:49:06,735 INFO [train.py:812] (3/8) Epoch 15, batch 350, loss[loss=0.1447, simple_loss=0.2229, pruned_loss=0.03324, over 6803.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2588, pruned_loss=0.041, over 1171838.01 frames.], batch size: 15, lr: 5.23e-04
2022-05-14 16:50:06,782 INFO [train.py:812] (3/8) Epoch 15, batch 400, loss[loss=0.1819, simple_loss=0.2739, pruned_loss=0.04499, over 7156.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2587, pruned_loss=0.04133, over 1227426.98 frames.], batch size: 20, lr: 5.23e-04
2022-05-14 16:51:05,892 INFO [train.py:812] (3/8) Epoch 15, batch 450, loss[loss=0.1782, simple_loss=0.2583, pruned_loss=0.04908, over 7164.00 frames.], tot_loss[loss=0.17, simple_loss=0.2582, pruned_loss=0.04094, over 1272081.73 frames.], batch size: 19, lr: 5.23e-04
2022-05-14 16:52:05,390 INFO [train.py:812] (3/8) Epoch 15, batch 500, loss[loss=0.1622, simple_loss=0.2502, pruned_loss=0.03708, over 7441.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2583, pruned_loss=0.04108, over 1303848.69 frames.], batch size: 20, lr: 5.23e-04
2022-05-14 16:53:04,816 INFO [train.py:812] (3/8) Epoch 15, batch 550, loss[loss=0.1586, simple_loss=0.2433, pruned_loss=0.03702, over 7289.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2584, pruned_loss=0.04102, over 1332242.30 frames.], batch size: 18, lr: 5.22e-04
2022-05-14 16:54:04,509 INFO [train.py:812] (3/8) Epoch 15, batch 600, loss[loss=0.1418, simple_loss=0.2368, pruned_loss=0.02337, over 7229.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2581, pruned_loss=0.04068, over 1355348.80 frames.], batch size: 20, lr: 5.22e-04
2022-05-14 16:55:03,721 INFO [train.py:812] (3/8) Epoch 15, batch 650, loss[loss=0.1895, simple_loss=0.28, pruned_loss=0.04947, over 7343.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2582, pruned_loss=0.04048, over 1370008.08 frames.], batch size: 22, lr: 5.22e-04
2022-05-14 16:56:03,037 INFO [train.py:812] (3/8) Epoch 15, batch 700, loss[loss=0.1533, simple_loss=0.2559, pruned_loss=0.02536, over 7320.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2584, pruned_loss=0.04054, over 1382897.49 frames.], batch size: 20, lr: 5.22e-04
2022-05-14 16:57:02,251 INFO [train.py:812] (3/8) Epoch 15, batch 750, loss[loss=0.1647, simple_loss=0.2605, pruned_loss=0.03443, over 7331.00 frames.], tot_loss[loss=0.1702, simple_loss=0.259, pruned_loss=0.04072, over 1391447.73 frames.], batch size: 22, lr: 5.22e-04
2022-05-14 16:58:01,661 INFO [train.py:812] (3/8) Epoch 15, batch 800, loss[loss=0.165, simple_loss=0.2575, pruned_loss=0.03625, over 7341.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2591, pruned_loss=0.04063, over 1399422.21 frames.], batch size: 22, lr: 5.21e-04
2022-05-14 16:59:01,062 INFO [train.py:812] (3/8) Epoch 15, batch 850, loss[loss=0.1531, simple_loss=0.2394, pruned_loss=0.03339, over 7152.00 frames.], tot_loss[loss=0.1702, simple_loss=0.259, pruned_loss=0.04075, over 1401281.07 frames.], batch size: 17, lr: 5.21e-04
2022-05-14 17:00:00,532 INFO [train.py:812] (3/8) Epoch 15, batch 900, loss[loss=0.1759, simple_loss=0.2653, pruned_loss=0.04322, over 7276.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2588, pruned_loss=0.04093, over 1396011.85 frames.], batch size: 19, lr: 5.21e-04
2022-05-14 17:00:59,819 INFO [train.py:812] (3/8) Epoch 15, batch 950, loss[loss=0.1559, simple_loss=0.2502, pruned_loss=0.03082, over 7334.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2597, pruned_loss=0.04122, over 1404889.85 frames.], batch size: 22, lr: 5.21e-04
2022-05-14 17:01:59,701 INFO [train.py:812] (3/8) Epoch 15, batch 1000, loss[loss=0.1824, simple_loss=0.2723, pruned_loss=0.04622, over 7070.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2601, pruned_loss=0.04131, over 1406703.77 frames.], batch size: 28, lr: 5.21e-04
2022-05-14 17:02:57,915 INFO [train.py:812] (3/8) Epoch 15, batch 1050, loss[loss=0.1456, simple_loss=0.2364, pruned_loss=0.02744, over 7283.00 frames.], tot_loss[loss=0.171, simple_loss=0.2595, pruned_loss=0.04121, over 1412978.68 frames.], batch size: 18, lr: 5.20e-04
2022-05-14 17:03:56,822 INFO [train.py:812] (3/8) Epoch 15, batch 1100, loss[loss=0.1689, simple_loss=0.2478, pruned_loss=0.04503, over 7273.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2599, pruned_loss=0.04134, over 1416977.49 frames.], batch size: 17, lr: 5.20e-04
2022-05-14 17:04:54,405 INFO [train.py:812] (3/8) Epoch 15, batch 1150, loss[loss=0.1683, simple_loss=0.2643, pruned_loss=0.03613, over 7408.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2591, pruned_loss=0.0409, over 1421482.95 frames.], batch size: 21, lr: 5.20e-04
2022-05-14 17:05:54,079 INFO [train.py:812] (3/8) Epoch 15, batch 1200, loss[loss=0.1738, simple_loss=0.26, pruned_loss=0.04379, over 7443.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2584, pruned_loss=0.04094, over 1423118.39 frames.], batch size: 20, lr: 5.20e-04
2022-05-14 17:06:52,027 INFO [train.py:812] (3/8) Epoch 15, batch 1250, loss[loss=0.154, simple_loss=0.2343, pruned_loss=0.03683, over 7352.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2586, pruned_loss=0.04085, over 1426342.19 frames.], batch size: 19, lr: 5.20e-04
2022-05-14 17:07:51,279 INFO [train.py:812] (3/8) Epoch 15, batch 1300, loss[loss=0.1776, simple_loss=0.2705, pruned_loss=0.04238, over 6551.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2588, pruned_loss=0.04111, over 1420253.91 frames.], batch size: 38, lr: 5.19e-04
2022-05-14 17:08:51,291 INFO [train.py:812] (3/8) Epoch 15, batch 1350, loss[loss=0.1595, simple_loss=0.2355, pruned_loss=0.04172, over 7005.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04139, over 1422177.91 frames.], batch size: 16, lr: 5.19e-04
2022-05-14 17:09:50,456 INFO [train.py:812] (3/8) Epoch 15, batch 1400, loss[loss=0.1835, simple_loss=0.2725, pruned_loss=0.04731, over 7275.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2589, pruned_loss=0.04124, over 1421426.91 frames.], batch size: 24, lr: 5.19e-04
2022-05-14 17:10:49,133 INFO [train.py:812] (3/8) Epoch 15, batch 1450, loss[loss=0.1816, simple_loss=0.2679, pruned_loss=0.04761, over 7374.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2588, pruned_loss=0.04131, over 1418863.23 frames.], batch size: 23, lr: 5.19e-04
2022-05-14 17:11:46,392 INFO [train.py:812] (3/8) Epoch 15, batch 1500, loss[loss=0.1745, simple_loss=0.2594, pruned_loss=0.0448, over 7147.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2592, pruned_loss=0.04161, over 1412495.10 frames.], batch size: 20, lr: 5.19e-04
2022-05-14 17:12:45,416 INFO [train.py:812] (3/8) Epoch 15, batch 1550, loss[loss=0.1611, simple_loss=0.2515, pruned_loss=0.03533, over 7115.00 frames.], tot_loss[loss=0.17, simple_loss=0.2582, pruned_loss=0.0409, over 1417381.52 frames.], batch size: 21, lr: 5.18e-04
2022-05-14 17:13:44,588 INFO [train.py:812] (3/8) Epoch 15, batch 1600, loss[loss=0.1854, simple_loss=0.2732, pruned_loss=0.04883, over 7419.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2578, pruned_loss=0.04042, over 1418884.95 frames.], batch size: 21, lr: 5.18e-04
2022-05-14 17:14:43,358 INFO [train.py:812] (3/8) Epoch 15, batch 1650, loss[loss=0.1756, simple_loss=0.2653, pruned_loss=0.04293, over 7190.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.0403, over 1424188.23 frames.], batch size: 23, lr: 5.18e-04
2022-05-14 17:15:42,311 INFO [train.py:812] (3/8) Epoch 15, batch 1700, loss[loss=0.201, simple_loss=0.2865, pruned_loss=0.05774, over 7307.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2573, pruned_loss=0.04011, over 1427830.60 frames.], batch size: 25, lr: 5.18e-04
2022-05-14 17:16:41,861 INFO [train.py:812] (3/8) Epoch 15, batch 1750, loss[loss=0.1871, simple_loss=0.2833, pruned_loss=0.04544, over 7035.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2577, pruned_loss=0.04062, over 1431018.25 frames.], batch size: 28, lr: 5.18e-04
2022-05-14 17:17:41,418 INFO [train.py:812] (3/8) Epoch 15, batch 1800, loss[loss=0.1408, simple_loss=0.222, pruned_loss=0.02982, over 7289.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2575, pruned_loss=0.04037, over 1428406.69 frames.], batch size: 17, lr: 5.17e-04
2022-05-14 17:18:41,018 INFO [train.py:812] (3/8) Epoch 15, batch 1850, loss[loss=0.153, simple_loss=0.2377, pruned_loss=0.03413, over 7159.00 frames.], tot_loss[loss=0.169, simple_loss=0.2574, pruned_loss=0.04028, over 1432668.56 frames.], batch size: 18, lr: 5.17e-04
2022-05-14 17:19:40,982 INFO [train.py:812] (3/8) Epoch 15, batch 1900, loss[loss=0.1624, simple_loss=0.2643, pruned_loss=0.03027, over 7104.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2577, pruned_loss=0.04038, over 1432411.72 frames.], batch size: 21, lr: 5.17e-04
2022-05-14 17:20:40,333 INFO [train.py:812] (3/8) Epoch 15, batch 1950, loss[loss=0.1637, simple_loss=0.2569, pruned_loss=0.03522, over 7290.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2574, pruned_loss=0.04064, over 1432711.21 frames.], batch size: 18, lr: 5.17e-04
2022-05-14 17:21:39,010 INFO [train.py:812] (3/8) Epoch 15, batch 2000, loss[loss=0.1886, simple_loss=0.2776, pruned_loss=0.04973, over 6512.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2577, pruned_loss=0.04097, over 1427801.20 frames.], batch size: 38, lr: 5.17e-04
2022-05-14 17:22:38,285 INFO [train.py:812] (3/8) Epoch 15, batch 2050, loss[loss=0.1643, simple_loss=0.2577, pruned_loss=0.03546, over 7276.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2577, pruned_loss=0.04057, over 1429030.03 frames.], batch size: 25, lr: 5.16e-04
2022-05-14 17:23:37,394 INFO [train.py:812] (3/8) Epoch 15, batch 2100, loss[loss=0.1611, simple_loss=0.2433, pruned_loss=0.03945, over 7438.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2577, pruned_loss=0.04103, over 1422526.73 frames.], batch size: 18, lr: 5.16e-04
2022-05-14 17:24:36,096 INFO [train.py:812] (3/8) Epoch 15, batch 2150, loss[loss=0.192, simple_loss=0.2815, pruned_loss=0.05124, over 7202.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2576, pruned_loss=0.04102, over 1421403.99 frames.], batch size: 22, lr: 5.16e-04
2022-05-14 17:25:35,461 INFO [train.py:812] (3/8) Epoch 15, batch 2200, loss[loss=0.1722, simple_loss=0.2611, pruned_loss=0.04163, over 7427.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2582, pruned_loss=0.04123, over 1420463.95 frames.], batch size: 20, lr: 5.16e-04
2022-05-14 17:26:33,943 INFO [train.py:812] (3/8) Epoch 15, batch 2250, loss[loss=0.2037, simple_loss=0.2856, pruned_loss=0.0609, over 7085.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2581, pruned_loss=0.041, over 1420867.72 frames.], batch size: 28, lr: 5.16e-04
2022-05-14 17:27:32,328 INFO [train.py:812] (3/8) Epoch 15, batch 2300, loss[loss=0.1553, simple_loss=0.2383, pruned_loss=0.03616, over 6798.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2582, pruned_loss=0.04082, over 1420570.05 frames.], batch size: 15, lr: 5.15e-04
2022-05-14 17:28:30,863 INFO [train.py:812] (3/8) Epoch 15, batch 2350, loss[loss=0.1262, simple_loss=0.2164, pruned_loss=0.01795, over 7410.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2578, pruned_loss=0.04029, over 1423468.34 frames.], batch size: 18, lr: 5.15e-04
2022-05-14 17:29:30,880 INFO [train.py:812] (3/8) Epoch 15, batch 2400, loss[loss=0.1555, simple_loss=0.2385, pruned_loss=0.03625, over 7423.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2593, pruned_loss=0.04101, over 1421421.88 frames.], batch size: 18, lr: 5.15e-04
2022-05-14 17:30:30,102 INFO [train.py:812] (3/8) Epoch 15, batch 2450, loss[loss=0.173, simple_loss=0.2651, pruned_loss=0.04044, over 7408.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2601, pruned_loss=0.04129, over 1422739.51 frames.], batch size: 21, lr: 5.15e-04
2022-05-14 17:31:29,570 INFO [train.py:812] (3/8) Epoch 15, batch 2500, loss[loss=0.1492, simple_loss=0.238, pruned_loss=0.03023, over 7316.00 frames.], tot_loss[loss=0.171, simple_loss=0.2599, pruned_loss=0.04101, over 1423996.58 frames.], batch size: 21, lr: 5.15e-04
2022-05-14 17:32:27,883 INFO [train.py:812] (3/8) Epoch 15, batch 2550, loss[loss=0.1667, simple_loss=0.2525, pruned_loss=0.04044, over 7169.00 frames.], tot_loss[loss=0.1714, simple_loss=0.26, pruned_loss=0.04141, over 1426651.63 frames.], batch size: 18, lr: 5.14e-04
2022-05-14 17:33:27,552 INFO [train.py:812] (3/8) Epoch 15, batch 2600, loss[loss=0.1789, simple_loss=0.2652, pruned_loss=0.04633, over 7192.00 frames.], tot_loss[loss=0.172, simple_loss=0.2606, pruned_loss=0.04176, over 1420731.58 frames.], batch size: 23, lr: 5.14e-04
2022-05-14 17:34:25,793 INFO [train.py:812] (3/8) Epoch 15, batch 2650, loss[loss=0.1824, simple_loss=0.2724, pruned_loss=0.04623, over 7283.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2601, pruned_loss=0.04145, over 1421290.55 frames.], batch size: 25, lr: 5.14e-04
2022-05-14 17:35:25,138 INFO [train.py:812] (3/8) Epoch 15, batch 2700, loss[loss=0.1759, simple_loss=0.2685, pruned_loss=0.04169, over 7324.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2608, pruned_loss=0.04151, over 1423980.75 frames.], batch size: 21, lr: 5.14e-04
2022-05-14 17:36:24,195 INFO [train.py:812] (3/8) Epoch 15, batch 2750, loss[loss=0.2073, simple_loss=0.2948, pruned_loss=0.05989, over 7261.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04141, over 1424839.55 frames.], batch size: 24, lr: 5.14e-04
2022-05-14 17:37:23,469 INFO [train.py:812] (3/8) Epoch 15, batch 2800, loss[loss=0.1783, simple_loss=0.2707, pruned_loss=0.04295, over 7155.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2598, pruned_loss=0.04074, over 1428382.70 frames.], batch size: 20, lr: 5.14e-04
2022-05-14 17:38:20,794 INFO [train.py:812] (3/8) Epoch 15, batch 2850, loss[loss=0.1671, simple_loss=0.2495, pruned_loss=0.04236, over 6830.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2601, pruned_loss=0.04117, over 1427997.21 frames.], batch size: 15, lr: 5.13e-04
2022-05-14 17:39:21,008 INFO [train.py:812] (3/8) Epoch 15, batch 2900, loss[loss=0.1731, simple_loss=0.2668, pruned_loss=0.03964, over 7388.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2603, pruned_loss=0.04152, over 1422676.19 frames.], batch size: 23, lr: 5.13e-04
2022-05-14 17:40:20,072 INFO [train.py:812] (3/8) Epoch 15, batch 2950, loss[loss=0.1526, simple_loss=0.2464, pruned_loss=0.02942, over 7426.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2598, pruned_loss=0.04129, over 1424070.87 frames.], batch size: 20, lr: 5.13e-04
2022-05-14 17:41:19,151 INFO [train.py:812] (3/8) Epoch 15, batch 3000, loss[loss=0.1574, simple_loss=0.2547, pruned_loss=0.03004, over 7158.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2588, pruned_loss=0.04082, over 1421940.06 frames.], batch size: 19, lr: 5.13e-04
2022-05-14 17:41:19,152 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 17:41:26,767 INFO [train.py:841] (3/8) Epoch 15, validation: loss=0.1543, simple_loss=0.2544, pruned_loss=0.02713, over 698248.00 frames.
2022-05-14 17:42:25,644 INFO [train.py:812] (3/8) Epoch 15, batch 3050, loss[loss=0.1651, simple_loss=0.2479, pruned_loss=0.04117, over 7218.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2586, pruned_loss=0.04039, over 1424986.43 frames.], batch size: 16, lr: 5.13e-04
2022-05-14 17:43:23,111 INFO [train.py:812] (3/8) Epoch 15, batch 3100, loss[loss=0.1565, simple_loss=0.2498, pruned_loss=0.03162, over 7334.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2597, pruned_loss=0.04108, over 1422001.41 frames.], batch size: 20, lr: 5.12e-04
2022-05-14 17:44:21,946 INFO [train.py:812] (3/8) Epoch 15, batch 3150, loss[loss=0.1634, simple_loss=0.244, pruned_loss=0.04141, over 7276.00 frames.], tot_loss[loss=0.1706, simple_loss=0.259, pruned_loss=0.04112, over 1426803.47 frames.], batch size: 17, lr: 5.12e-04
2022-05-14 17:45:20,563 INFO [train.py:812] (3/8) Epoch 15, batch 3200, loss[loss=0.1703, simple_loss=0.2627, pruned_loss=0.03897, over 7090.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2589, pruned_loss=0.04131, over 1427426.94 frames.], batch size: 28, lr: 5.12e-04
2022-05-14 17:46:20,195 INFO [train.py:812] (3/8) Epoch 15, batch 3250, loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03065, over 7440.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2591, pruned_loss=0.04137, over 1428190.21 frames.], batch size: 19, lr: 5.12e-04
2022-05-14 17:47:18,745 INFO [train.py:812] (3/8) Epoch 15, batch 3300, loss[loss=0.1559, simple_loss=0.241, pruned_loss=0.03544, over 7281.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2581, pruned_loss=0.04115, over 1426835.49 frames.], batch size: 17, lr: 5.12e-04
2022-05-14 17:48:17,414 INFO [train.py:812] (3/8) Epoch 15, batch 3350, loss[loss=0.1639, simple_loss=0.2654, pruned_loss=0.03119, over 7192.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2589, pruned_loss=0.04114, over 1426317.16 frames.], batch size: 23, lr: 5.11e-04
2022-05-14 17:49:14,688 INFO [train.py:812] (3/8) Epoch 15, batch 3400, loss[loss=0.1777, simple_loss=0.2757, pruned_loss=0.03987, over 7224.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2597, pruned_loss=0.04105, over 1423203.67 frames.], batch size: 21, lr: 5.11e-04
2022-05-14 17:50:13,360 INFO [train.py:812] (3/8) Epoch 15, batch 3450, loss[loss=0.2029, simple_loss=0.2916, pruned_loss=0.05704, over 7031.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2606, pruned_loss=0.04143, over 1420548.47 frames.], batch size: 28, lr: 5.11e-04
2022-05-14 17:51:13,182 INFO [train.py:812] (3/8) Epoch 15, batch 3500, loss[loss=0.1771, simple_loss=0.2765, pruned_loss=0.0388, over 7174.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2594, pruned_loss=0.04079, over 1426413.85 frames.], batch size: 26, lr: 5.11e-04
2022-05-14 17:52:12,887 INFO [train.py:812] (3/8) Epoch 15, batch 3550, loss[loss=0.1732, simple_loss=0.2655, pruned_loss=0.04041, over 7227.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2592, pruned_loss=0.04076, over 1428545.76 frames.], batch size: 20, lr: 5.11e-04
2022-05-14 17:53:11,377 INFO [train.py:812] (3/8) Epoch 15, batch 3600, loss[loss=0.1674, simple_loss=0.26, pruned_loss=0.03741, over 7323.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2593, pruned_loss=0.04113, over 1425337.55 frames.], batch size: 21, lr: 5.11e-04
2022-05-14 17:54:10,562 INFO [train.py:812] (3/8) Epoch 15, batch 3650, loss[loss=0.171, simple_loss=0.2654, pruned_loss=0.03828, over 7268.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2583, pruned_loss=0.04059, over 1425628.47 frames.], batch size: 19, lr: 5.10e-04
2022-05-14 17:55:10,191 INFO [train.py:812] (3/8) Epoch 15, batch 3700, loss[loss=0.1394, simple_loss=0.2289, pruned_loss=0.02499, over 7423.00 frames.], tot_loss[loss=0.1704, simple_loss=0.259, pruned_loss=0.04096, over 1422712.44 frames.], batch size: 20, lr: 5.10e-04
2022-05-14 17:56:09,468 INFO [train.py:812] (3/8) Epoch 15, batch 3750, loss[loss=0.2444, simple_loss=0.3091, pruned_loss=0.08982, over 5320.00 frames.], tot_loss[loss=0.1707, simple_loss=0.259, pruned_loss=0.04119, over 1424039.82 frames.], batch size: 52, lr: 5.10e-04
2022-05-14 17:57:14,304 INFO [train.py:812] (3/8) Epoch 15, batch 3800, loss[loss=0.1924, simple_loss=0.2683, pruned_loss=0.05826, over 7062.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2592, pruned_loss=0.0406, over 1426210.60 frames.], batch size: 18, lr: 5.10e-04
2022-05-14 17:58:12,037 INFO [train.py:812] (3/8) Epoch 15, batch 3850, loss[loss=0.1536, simple_loss=0.2491, pruned_loss=0.02905, over 7234.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2593, pruned_loss=0.04056, over 1428853.99 frames.], batch size: 20, lr: 5.10e-04
2022-05-14 17:59:11,810 INFO [train.py:812] (3/8) Epoch 15, batch 3900, loss[loss=0.1722, simple_loss=0.2569, pruned_loss=0.0438, over 7259.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2581, pruned_loss=0.04027, over 1426465.14 frames.], batch size: 19, lr: 5.09e-04
2022-05-14 18:00:10,981 INFO [train.py:812] (3/8) Epoch 15, batch 3950, loss[loss=0.1813, simple_loss=0.2697, pruned_loss=0.04648, over 7373.00 frames.], tot_loss[loss=0.17, simple_loss=0.2584, pruned_loss=0.04084, over 1423439.83 frames.], batch size: 19, lr: 5.09e-04
2022-05-14 18:01:10,520 INFO [train.py:812] (3/8) Epoch 15, batch 4000, loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03243, over 7208.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2575, pruned_loss=0.04011, over 1423034.09 frames.], batch size: 21, lr: 5.09e-04
2022-05-14 18:02:09,512 INFO [train.py:812] (3/8) Epoch 15, batch 4050, loss[loss=0.1611, simple_loss=0.2528, pruned_loss=0.03469, over 7221.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2574, pruned_loss=0.03975, over 1427236.13 frames.], batch size: 21, lr: 5.09e-04
2022-05-14 18:03:08,713 INFO [train.py:812] (3/8) Epoch 15, batch 4100, loss[loss=0.1824, simple_loss=0.2753, pruned_loss=0.04478, over 7203.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2581, pruned_loss=0.04068, over 1418167.15 frames.], batch size: 23, lr: 5.09e-04
2022-05-14 18:04:07,539 INFO [train.py:812] (3/8) Epoch 15, batch 4150, loss[loss=0.2139, simple_loss=0.2861, pruned_loss=0.07082, over 5030.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2582, pruned_loss=0.04127, over 1412506.79 frames.], batch size: 52, lr: 5.08e-04
2022-05-14 18:05:07,016 INFO [train.py:812] (3/8) Epoch 15, batch 4200, loss[loss=0.1678, simple_loss=0.2659, pruned_loss=0.03481, over 7231.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2578, pruned_loss=0.04118, over 1411014.77 frames.], batch size: 20, lr: 5.08e-04
2022-05-14 18:06:05,959 INFO [train.py:812] (3/8) Epoch 15, batch 4250, loss[loss=0.1523, simple_loss=0.2386, pruned_loss=0.03304, over 7060.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2575, pruned_loss=0.0406, over 1408460.76 frames.], batch size: 18, lr: 5.08e-04
2022-05-14 18:07:05,132 INFO [train.py:812] (3/8) Epoch 15, batch 4300, loss[loss=0.129, simple_loss=0.215, pruned_loss=0.0215, over 6807.00 frames.], tot_loss[loss=0.17, simple_loss=0.2583, pruned_loss=0.04086, over 1405161.97 frames.], batch size: 15, lr: 5.08e-04
2022-05-14 18:08:04,065 INFO [train.py:812] (3/8) Epoch 15, batch 4350, loss[loss=0.1735, simple_loss=0.2651, pruned_loss=0.04091, over 7320.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2589, pruned_loss=0.04125, over 1408606.39 frames.], batch size: 21, lr: 5.08e-04
2022-05-14 18:09:03,506 INFO [train.py:812] (3/8) Epoch 15, batch 4400, loss[loss=0.15, simple_loss=0.2318, pruned_loss=0.03413, over 7163.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2582, pruned_loss=0.04073, over 1410962.36 frames.], batch size: 19, lr: 5.08e-04
2022-05-14 18:10:02,438 INFO [train.py:812] (3/8) Epoch 15, batch 4450, loss[loss=0.1659, simple_loss=0.2501, pruned_loss=0.0408, over 7168.00 frames.], tot_loss[loss=0.169, simple_loss=0.2568, pruned_loss=0.04058, over 1403355.85 frames.], batch size: 18, lr: 5.07e-04
2022-05-14 18:11:01,295 INFO [train.py:812] (3/8) Epoch 15, batch 4500, loss[loss=0.1688, simple_loss=0.2482, pruned_loss=0.04467, over 7061.00 frames.], tot_loss[loss=0.17, simple_loss=0.2577, pruned_loss=0.04114, over 1395204.41 frames.], batch size: 18, lr: 5.07e-04
2022-05-14 18:11:59,582 INFO [train.py:812] (3/8) Epoch 15, batch 4550, loss[loss=0.1967, simple_loss=0.2928, pruned_loss=0.05028, over 4729.00 frames.], tot_loss[loss=0.1716, simple_loss=0.259, pruned_loss=0.04213, over 1367583.40 frames.], batch size: 53, lr: 5.07e-04
2022-05-14 18:13:08,744 INFO [train.py:812] (3/8) Epoch 16, batch 0, loss[loss=0.1802, simple_loss=0.2703, pruned_loss=0.04502, over 7286.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2703, pruned_loss=0.04502, over 7286.00 frames.], batch size: 24, lr: 4.92e-04
2022-05-14 18:14:07,989 INFO [train.py:812] (3/8) Epoch 16, batch 50, loss[loss=0.145, simple_loss=0.2223, pruned_loss=0.03381, over 7411.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2587, pruned_loss=0.04071, over 320950.99 frames.], batch size: 18, lr: 4.92e-04
2022-05-14 18:15:07,114 INFO [train.py:812] (3/8) Epoch 16, batch 100, loss[loss=0.1817, simple_loss=0.2714, pruned_loss=0.04603, over 7331.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2569, pruned_loss=0.03992, over 564900.20 frames.], batch size: 20, lr: 4.92e-04
2022-05-14 18:16:06,273 INFO [train.py:812] (3/8) Epoch 16, batch 150, loss[loss=0.1698, simple_loss=0.2665, pruned_loss=0.03657, over 7154.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2567, pruned_loss=0.04, over 754730.49 frames.], batch size: 20, lr: 4.92e-04
2022-05-14 18:17:15,042 INFO [train.py:812] (3/8) Epoch 16, batch 200, loss[loss=0.1659, simple_loss=0.263, pruned_loss=0.03442, over 7107.00 frames.], tot_loss[loss=0.168, simple_loss=0.2564, pruned_loss=0.03976, over 898003.38 frames.], batch size: 21, lr: 4.91e-04
2022-05-14 18:18:13,142 INFO [train.py:812] (3/8) Epoch 16, batch 250, loss[loss=0.1486, simple_loss=0.2279, pruned_loss=0.03467, over 7157.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2569, pruned_loss=0.03996, over 1015154.59 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:19:12,324 INFO [train.py:812] (3/8) Epoch 16, batch 300, loss[loss=0.1808, simple_loss=0.2619, pruned_loss=0.04983, over 7143.00 frames.], tot_loss[loss=0.1673, simple_loss=0.256, pruned_loss=0.03934, over 1109476.30 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:20:11,379 INFO [train.py:812] (3/8) Epoch 16, batch 350, loss[loss=0.1398, simple_loss=0.2291, pruned_loss=0.02524, over 7272.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2567, pruned_loss=0.03988, over 1180576.11 frames.], batch size: 18, lr: 4.91e-04
2022-05-14 18:21:11,294 INFO [train.py:812] (3/8) Epoch 16, batch 400, loss[loss=0.1723, simple_loss=0.2615, pruned_loss=0.04151, over 7265.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2579, pruned_loss=0.04019, over 1233680.10 frames.], batch size: 19, lr: 4.91e-04
2022-05-14 18:22:10,136 INFO [train.py:812] (3/8) Epoch 16, batch 450, loss[loss=0.1478, simple_loss=0.2305, pruned_loss=0.03255, over 7430.00 frames.], tot_loss[loss=0.1705, simple_loss=0.259, pruned_loss=0.04096, over 1280592.40 frames.], batch size: 20, lr: 4.91e-04
2022-05-14 18:23:09,255 INFO [train.py:812] (3/8) Epoch 16, batch 500, loss[loss=0.2044, simple_loss=0.2888, pruned_loss=0.06003, over 7199.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2596, pruned_loss=0.0409, over 1317530.43 frames.], batch size: 23, lr: 4.90e-04
2022-05-14 18:24:07,719 INFO [train.py:812] (3/8) Epoch 16, batch 550, loss[loss=0.1489, simple_loss=0.2259, pruned_loss=0.03601, over 7284.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2576, pruned_loss=0.0403, over 1344623.99 frames.], batch size: 18, lr: 4.90e-04
2022-05-14 18:25:07,647 INFO [train.py:812] (3/8) Epoch 16, batch 600, loss[loss=0.155, simple_loss=0.2483, pruned_loss=0.03081, over 7167.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2565, pruned_loss=0.03958, over 1360517.33 frames.], batch size: 19, lr: 4.90e-04
2022-05-14 18:26:06,737 INFO [train.py:812] (3/8) Epoch 16, batch 650, loss[loss=0.1557, simple_loss=0.2477, pruned_loss=0.03186, over 6418.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2567, pruned_loss=0.03939, over 1373420.77 frames.], batch size: 37, lr: 4.90e-04
2022-05-14 18:27:05,466 INFO [train.py:812] (3/8) Epoch 16, batch 700, loss[loss=0.1811, simple_loss=0.274, pruned_loss=0.04408, over 7042.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2569, pruned_loss=0.04007, over 1385108.54 frames.], batch size: 28, lr: 4.90e-04
2022-05-14 18:28:04,352 INFO [train.py:812] (3/8) Epoch 16, batch 750, loss[loss=0.1597, simple_loss=0.2406, pruned_loss=0.03938, over 7146.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2559, pruned_loss=0.03927, over 1393695.98 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:29:03,807 INFO [train.py:812] (3/8) Epoch 16, batch 800, loss[loss=0.1572, simple_loss=0.2403, pruned_loss=0.03707, over 7256.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2564, pruned_loss=0.03938, over 1401761.88 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:30:02,503 INFO [train.py:812] (3/8) Epoch 16, batch 850, loss[loss=0.1465, simple_loss=0.2411, pruned_loss=0.02595, over 7151.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2569, pruned_loss=0.03925, over 1403849.69 frames.], batch size: 20, lr: 4.89e-04
2022-05-14 18:31:02,361 INFO [train.py:812] (3/8) Epoch 16, batch 900, loss[loss=0.1563, simple_loss=0.243, pruned_loss=0.03475, over 7339.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03952, over 1402965.34 frames.], batch size: 19, lr: 4.89e-04
2022-05-14 18:32:01,905 INFO [train.py:812] (3/8) Epoch 16, batch 950, loss[loss=0.1638, simple_loss=0.2531, pruned_loss=0.03723, over 7423.00 frames.], tot_loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03958, over 1406983.03 frames.], batch size: 20, lr: 4.89e-04
2022-05-14 18:33:00,788 INFO [train.py:812] (3/8) Epoch 16, batch 1000, loss[loss=0.1864, simple_loss=0.275, pruned_loss=0.04892, over 7285.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2558, pruned_loss=0.03921, over 1412796.45 frames.], batch size: 25, lr: 4.89e-04
2022-05-14 18:33:59,599 INFO [train.py:812] (3/8) Epoch 16, batch 1050, loss[loss=0.1935, simple_loss=0.2833, pruned_loss=0.05189, over 7319.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2571, pruned_loss=0.03976, over 1417866.11 frames.], batch size: 20, lr: 4.88e-04
2022-05-14 18:34:59,554 INFO [train.py:812] (3/8) Epoch 16, batch 1100, loss[loss=0.195, simple_loss=0.2745, pruned_loss=0.05771, over 7351.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2572, pruned_loss=0.03967, over 1420091.09 frames.], batch size: 19, lr: 4.88e-04
2022-05-14 18:35:59,301 INFO [train.py:812] (3/8) Epoch 16, batch 1150, loss[loss=0.1849, simple_loss=0.2708, pruned_loss=0.04952, over 5306.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2564, pruned_loss=0.03916, over 1420325.18 frames.], batch size: 52, lr: 4.88e-04
2022-05-14 18:36:59,221 INFO [train.py:812] (3/8) Epoch 16, batch 1200, loss[loss=0.1595, simple_loss=0.2571, pruned_loss=0.03093, over 7120.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2566, pruned_loss=0.03911, over 1417385.39 frames.], batch size: 21, lr: 4.88e-04
2022-05-14 18:37:58,847 INFO [train.py:812] (3/8) Epoch 16, batch 1250, loss[loss=0.1457, simple_loss=0.2284, pruned_loss=0.03149, over 6811.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2566, pruned_loss=0.03958, over 1418309.09 frames.], batch size: 15, lr: 4.88e-04
2022-05-14 18:38:58,776 INFO [train.py:812] (3/8) Epoch 16, batch 1300, loss[loss=0.1941, simple_loss=0.28, pruned_loss=0.0541, over 7211.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2577, pruned_loss=0.03993, over 1424766.56 frames.], batch size: 22, lr: 4.88e-04
2022-05-14 18:39:58,299 INFO [train.py:812] (3/8) Epoch 16, batch 1350, loss[loss=0.1618, simple_loss=0.2457, pruned_loss=0.03894, over 7163.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2572, pruned_loss=0.03995, over 1417624.64 frames.], batch size: 19, lr: 4.87e-04
2022-05-14 18:40:58,002 INFO [train.py:812] (3/8) Epoch 16, batch 1400, loss[loss=0.173, simple_loss=0.2787, pruned_loss=0.03368, over 7338.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2568, pruned_loss=0.03987, over 1415649.16 frames.], batch size: 22, lr: 4.87e-04
2022-05-14 18:41:57,514 INFO [train.py:812] (3/8) Epoch 16, batch 1450, loss[loss=0.1877, simple_loss=0.2787, pruned_loss=0.04835, over 7419.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2573, pruned_loss=0.04006, over 1422211.04 frames.], batch size: 21, lr: 4.87e-04
2022-05-14 18:43:06,577 INFO [train.py:812] (3/8) Epoch 16, batch 1500, loss[loss=0.1893, simple_loss=0.2764, pruned_loss=0.05111, over 7208.00 frames.], tot_loss[loss=0.1693, simple_loss=0.258, pruned_loss=0.04027, over 1421842.29 frames.], batch size: 23, lr: 4.87e-04
2022-05-14 18:44:06,043 INFO [train.py:812] (3/8) Epoch 16, batch 1550, loss[loss=0.1514, simple_loss=0.2268, pruned_loss=0.03802, over 6760.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2567, pruned_loss=0.03939, over 1419813.51 frames.], batch size: 15, lr: 4.87e-04
2022-05-14 18:45:05,964 INFO [train.py:812] (3/8) Epoch 16, batch 1600, loss[loss=0.1501, simple_loss=0.2351, pruned_loss=0.03254, over 6833.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2573, pruned_loss=0.03961, over 1421959.49 frames.], batch size: 15, lr: 4.87e-04
2022-05-14 18:46:05,454 INFO [train.py:812] (3/8) Epoch 16, batch 1650, loss[loss=0.1872, simple_loss=0.2705, pruned_loss=0.05198, over 7148.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2578, pruned_loss=0.04003, over 1424195.50 frames.], batch size: 20, lr: 4.86e-04
2022-05-14 18:47:14,893 INFO [train.py:812] (3/8) Epoch 16, batch 1700, loss[loss=0.1776, simple_loss=0.2553, pruned_loss=0.0499, over 7394.00 frames.], tot_loss[loss=0.168, simple_loss=0.2568, pruned_loss=0.03963, over 1424451.42 frames.], batch size: 18, lr: 4.86e-04
2022-05-14 18:48:31,554 INFO [train.py:812] (3/8) Epoch 16, batch 1750, loss[loss=0.1718, simple_loss=0.2599, pruned_loss=0.04184, over 7376.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2581, pruned_loss=0.04033, over 1424067.99 frames.], batch size: 23, lr: 4.86e-04
2022-05-14 18:49:49,343 INFO [train.py:812] (3/8) Epoch 16, batch 1800, loss[loss=0.1626, simple_loss=0.2559, pruned_loss=0.03462, over 7368.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2581, pruned_loss=0.04029, over 1421965.58 frames.], batch size: 19, lr: 4.86e-04
2022-05-14 18:50:57,661 INFO [train.py:812] (3/8) Epoch 16, batch 1850, loss[loss=0.1661, simple_loss=0.2608, pruned_loss=0.03565, over 7145.00 frames.], tot_loss[loss=0.1685, simple_loss=0.257, pruned_loss=0.04002, over 1424632.74 frames.], batch size: 20, lr: 4.86e-04
2022-05-14 18:51:57,512 INFO [train.py:812] (3/8) Epoch 16, batch 1900, loss[loss=0.1776, simple_loss=0.2728, pruned_loss=0.04121, over 7301.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2566, pruned_loss=0.03952, over 1428408.51 frames.], batch size: 25, lr: 4.86e-04
2022-05-14 18:52:55,102 INFO [train.py:812] (3/8) Epoch 16, batch 1950, loss[loss=0.2119, simple_loss=0.3129, pruned_loss=0.05549, over 7204.00 frames.], tot_loss[loss=0.169, simple_loss=0.2577, pruned_loss=0.04013, over 1429955.03 frames.], batch size: 23, lr: 4.85e-04
2022-05-14 18:53:54,398 INFO [train.py:812] (3/8) Epoch 16, batch 2000, loss[loss=0.2119, simple_loss=0.2985, pruned_loss=0.0627, over 4843.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2581, pruned_loss=0.04018, over 1423731.91 frames.], batch size: 52, lr: 4.85e-04
2022-05-14 18:54:53,349 INFO [train.py:812] (3/8) Epoch 16, batch 2050, loss[loss=0.1565, simple_loss=0.2419, pruned_loss=0.03559, over 6462.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2589, pruned_loss=0.04061, over 1421846.09 frames.], batch size: 38, lr: 4.85e-04
2022-05-14 18:55:52,713 INFO [train.py:812] (3/8) Epoch 16, batch 2100, loss[loss=0.1662, simple_loss=0.2592, pruned_loss=0.03665, over 7115.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2593, pruned_loss=0.04084, over 1422888.23 frames.], batch size: 21, lr: 4.85e-04
2022-05-14 18:56:51,652 INFO [train.py:812] (3/8) Epoch 16, batch 2150, loss[loss=0.1571, simple_loss=0.2584, pruned_loss=0.02789, over 7256.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2587, pruned_loss=0.0404, over 1418883.83 frames.], batch size: 19, lr: 4.85e-04
2022-05-14 18:57:50,988 INFO [train.py:812] (3/8) Epoch 16, batch 2200, loss[loss=0.1708, simple_loss=0.2734, pruned_loss=0.03406, over 7226.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2588, pruned_loss=0.04031, over 1415938.89 frames.], batch size: 22, lr: 4.84e-04
2022-05-14 18:58:50,175 INFO [train.py:812] (3/8) Epoch 16, batch 2250, loss[loss=0.1987, simple_loss=0.2883, pruned_loss=0.05455, over 7405.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2581, pruned_loss=0.0398, over 1418284.32 frames.], batch size: 21, lr: 4.84e-04
2022-05-14 18:59:49,553 INFO [train.py:812] (3/8) Epoch 16, batch 2300, loss[loss=0.1815, simple_loss=0.2672, pruned_loss=0.0479, over 7223.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2584, pruned_loss=0.03999, over 1420104.97 frames.], batch size: 23, lr: 4.84e-04
2022-05-14 19:00:48,681 INFO [train.py:812] (3/8) Epoch 16, batch 2350, loss[loss=0.2158, simple_loss=0.3059, pruned_loss=0.06282, over 7299.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2578, pruned_loss=0.03993, over 1422514.65 frames.], batch size: 25, lr: 4.84e-04
2022-05-14 19:01:48,348 INFO [train.py:812] (3/8) Epoch 16, batch 2400, loss[loss=0.189, simple_loss=0.2803, pruned_loss=0.04881, over 7259.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2576, pruned_loss=0.03996, over 1425897.40 frames.], batch size: 25, lr: 4.84e-04
2022-05-14 19:02:47,248 INFO [train.py:812] (3/8) Epoch 16, batch 2450, loss[loss=0.1944, simple_loss=0.2841, pruned_loss=0.05239, over 6755.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2575, pruned_loss=0.03989, over 1424660.03 frames.], batch size: 31, lr: 4.84e-04
2022-05-14 19:03:46,833 INFO [train.py:812] (3/8) Epoch 16, batch 2500, loss[loss=0.1699, simple_loss=0.2554, pruned_loss=0.04218, over 7219.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2566, pruned_loss=0.03944, over 1428062.01 frames.], batch size: 21, lr: 4.83e-04
2022-05-14 19:04:46,105 INFO [train.py:812] (3/8) Epoch 16, batch 2550, loss[loss=0.1385, simple_loss=0.2286, pruned_loss=0.02422, over 7144.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2556, pruned_loss=0.03934, over 1424893.43 frames.], batch size: 20, lr: 4.83e-04
2022-05-14 19:05:45,581 INFO [train.py:812] (3/8) Epoch 16, batch 2600, loss[loss=0.1437, simple_loss=0.2372, pruned_loss=0.02514, over 7360.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2562, pruned_loss=0.03959, over 1423516.32 frames.], batch size: 19, lr: 4.83e-04
2022-05-14 19:06:45,268 INFO [train.py:812] (3/8) Epoch 16, batch 2650, loss[loss=0.1776, simple_loss=0.2657, pruned_loss=0.04475, over 7375.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2562, pruned_loss=0.03959, over 1424356.27 frames.], batch size: 23, lr: 4.83e-04
2022-05-14 19:07:45,241 INFO [train.py:812] (3/8) Epoch 16, batch 2700, loss[loss=0.1874, simple_loss=0.2812, pruned_loss=0.04679, over 7188.00 frames.], tot_loss[loss=0.168, simple_loss=0.2567, pruned_loss=0.03963, over 1421460.54 frames.], batch size: 26, lr: 4.83e-04
2022-05-14 19:08:44,236 INFO [train.py:812] (3/8) Epoch 16, batch 2750, loss[loss=0.1356, simple_loss=0.23, pruned_loss=0.02057, over 7276.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2573, pruned_loss=0.03967, over 1425705.41 frames.], batch size: 18, lr: 4.83e-04
2022-05-14 19:09:44,119 INFO [train.py:812] (3/8) Epoch 16, batch 2800, loss[loss=0.1837, simple_loss=0.2783, pruned_loss=0.04452, over 7231.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.03983, over 1427582.38 frames.], batch size: 21, lr: 4.82e-04
2022-05-14 19:10:43,374 INFO [train.py:812] (3/8) Epoch 16, batch 2850, loss[loss=0.1634, simple_loss=0.2444, pruned_loss=0.04122, over 7154.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.03979, over 1426517.57 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:11:42,827 INFO [train.py:812] (3/8) Epoch 16, batch 2900, loss[loss=0.1765, simple_loss=0.2628, pruned_loss=0.04507, over 7158.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2574, pruned_loss=0.03955, over 1428856.45 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:12:41,624 INFO [train.py:812] (3/8) Epoch 16, batch 2950, loss[loss=0.1798, simple_loss=0.2705, pruned_loss=0.04449, over 7330.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2574, pruned_loss=0.03968, over 1424888.30 frames.], batch size: 22, lr: 4.82e-04
2022-05-14 19:13:40,831 INFO [train.py:812] (3/8) Epoch 16, batch 3000, loss[loss=0.1886, simple_loss=0.2818, pruned_loss=0.04769, over 7416.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2574, pruned_loss=0.03958, over 1428825.50 frames.], batch size: 21, lr: 4.82e-04
2022-05-14 19:13:40,832 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 19:13:48,992 INFO [train.py:841] (3/8) Epoch 16, validation: loss=0.1537, simple_loss=0.2535, pruned_loss=0.02695, over 698248.00 frames.
2022-05-14 19:14:47,137 INFO [train.py:812] (3/8) Epoch 16, batch 3050, loss[loss=0.1506, simple_loss=0.2293, pruned_loss=0.03601, over 7399.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2571, pruned_loss=0.03963, over 1427590.08 frames.], batch size: 18, lr: 4.82e-04
2022-05-14 19:15:46,675 INFO [train.py:812] (3/8) Epoch 16, batch 3100, loss[loss=0.1688, simple_loss=0.2601, pruned_loss=0.03873, over 7198.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2558, pruned_loss=0.03913, over 1426980.90 frames.], batch size: 23, lr: 4.81e-04
2022-05-14 19:16:44,968 INFO [train.py:812] (3/8) Epoch 16, batch 3150, loss[loss=0.1488, simple_loss=0.2357, pruned_loss=0.03093, over 7165.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2561, pruned_loss=0.03911, over 1423986.72 frames.], batch size: 18, lr: 4.81e-04
2022-05-14 19:17:47,867 INFO [train.py:812] (3/8) Epoch 16, batch 3200, loss[loss=0.1661, simple_loss=0.264, pruned_loss=0.03407, over 7282.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2578, pruned_loss=0.03978, over 1423831.31 frames.], batch size: 24, lr: 4.81e-04
2022-05-14 19:18:47,167 INFO [train.py:812] (3/8) Epoch 16, batch 3250, loss[loss=0.1619, simple_loss=0.2608, pruned_loss=0.03151, over 7329.00 frames.], tot_loss[loss=0.168, simple_loss=0.2569, pruned_loss=0.03956, over 1425334.08 frames.], batch size: 21, lr: 4.81e-04
2022-05-14 19:19:45,408 INFO [train.py:812] (3/8) Epoch 16, batch 3300, loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03203, over 7301.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2579, pruned_loss=0.03961, over 1429229.53 frames.], batch size: 25, lr: 4.81e-04
2022-05-14 19:20:42,558 INFO [train.py:812] (3/8) Epoch 16, batch 3350, loss[loss=0.1656, simple_loss=0.2554, pruned_loss=0.03784, over 7237.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2562, pruned_loss=0.03903, over 1430806.36 frames.], batch size: 20, lr: 4.81e-04
2022-05-14 19:21:41,196 INFO [train.py:812] (3/8) Epoch 16, batch 3400, loss[loss=0.1776, simple_loss=0.2673, pruned_loss=0.04398, over 7113.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2573, pruned_loss=0.03924, over 1428611.68 frames.], batch size: 28, lr: 4.80e-04
2022-05-14 19:22:40,323 INFO [train.py:812] (3/8) Epoch 16, batch 3450, loss[loss=0.1477, simple_loss=0.2365, pruned_loss=0.02948, over 7355.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2576, pruned_loss=0.03942, over 1429814.39 frames.], batch size: 19, lr: 4.80e-04
2022-05-14 19:23:40,278 INFO [train.py:812] (3/8) Epoch 16, batch 3500, loss[loss=0.1772, simple_loss=0.2691, pruned_loss=0.04258, over 7316.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2573, pruned_loss=0.03949, over 1427936.98 frames.], batch size: 21, lr: 4.80e-04
2022-05-14 19:24:39,219 INFO [train.py:812] (3/8) Epoch 16, batch 3550, loss[loss=0.1999, simple_loss=0.2965, pruned_loss=0.05165, over 7163.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2579, pruned_loss=0.03964, over 1424387.52 frames.], batch size: 26, lr: 4.80e-04
2022-05-14 19:25:38,823 INFO [train.py:812] (3/8) Epoch 16, batch 3600, loss[loss=0.1595, simple_loss=0.2544, pruned_loss=0.03234, over 7313.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2567, pruned_loss=0.03891, over 1425886.02 frames.], batch size: 21, lr: 4.80e-04
2022-05-14 19:26:37,927 INFO [train.py:812] (3/8) Epoch 16, batch 3650, loss[loss=0.1544, simple_loss=0.2381, pruned_loss=0.03541, over 7276.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2571, pruned_loss=0.03924, over 1426053.72 frames.], batch size: 18, lr: 4.80e-04
2022-05-14 19:27:36,138 INFO [train.py:812] (3/8) Epoch 16, batch 3700, loss[loss=0.1457, simple_loss=0.2316, pruned_loss=0.02991, over 7259.00 frames.], tot_loss[loss=0.1669, simple_loss=0.256, pruned_loss=0.03889, over 1424136.55 frames.], batch size: 16, lr: 4.79e-04
2022-05-14 19:28:35,312 INFO [train.py:812] (3/8) Epoch 16, batch 3750, loss[loss=0.2069, simple_loss=0.2966, pruned_loss=0.05854, over 7320.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2562, pruned_loss=0.03913, over 1421351.90 frames.], batch size: 25, lr: 4.79e-04
2022-05-14 19:29:33,344 INFO [train.py:812] (3/8) Epoch 16, batch 3800, loss[loss=0.1663, simple_loss=0.243, pruned_loss=0.04479, over 7117.00 frames.], tot_loss[loss=0.168, simple_loss=0.257, pruned_loss=0.03951, over 1425118.58 frames.], batch size: 17, lr: 4.79e-04
2022-05-14 19:30:31,492 INFO [train.py:812] (3/8) Epoch 16, batch 3850, loss[loss=0.1494, simple_loss=0.24, pruned_loss=0.02942, over 7280.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2574, pruned_loss=0.03997, over 1420657.90 frames.], batch size: 18, lr: 4.79e-04
2022-05-14 19:31:29,777 INFO [train.py:812] (3/8) Epoch 16, batch 3900, loss[loss=0.1533, simple_loss=0.2487, pruned_loss=0.02898, over 7216.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2576, pruned_loss=0.03993, over 1422236.81 frames.], batch size: 21, lr: 4.79e-04
2022-05-14 19:32:28,908 INFO [train.py:812] (3/8) Epoch 16, batch 3950, loss[loss=0.1564, simple_loss=0.2412, pruned_loss=0.03578, over 7237.00 frames.], tot_loss[loss=0.169, simple_loss=0.2581, pruned_loss=0.03998, over 1421140.67 frames.], batch size: 20, lr: 4.79e-04
2022-05-14 19:33:27,630 INFO [train.py:812] (3/8) Epoch 16, batch 4000, loss[loss=0.1562, simple_loss=0.2487, pruned_loss=0.03179, over 7322.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2578, pruned_loss=0.03958, over 1419611.72 frames.], batch size: 21, lr: 4.79e-04
2022-05-14 19:34:27,158 INFO [train.py:812] (3/8) Epoch 16, batch 4050, loss[loss=0.167, simple_loss=0.2474, pruned_loss=0.04325, over 7162.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2581, pruned_loss=0.03983, over 1418481.67 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:35:27,339 INFO [train.py:812] (3/8) Epoch 16, batch 4100, loss[loss=0.16, simple_loss=0.2454, pruned_loss=0.03726, over 7161.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2573, pruned_loss=0.03967, over 1424117.41 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:36:26,214 INFO [train.py:812] (3/8) Epoch 16, batch 4150, loss[loss=0.1755, simple_loss=0.2709, pruned_loss=0.04008, over 7094.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2578, pruned_loss=0.03972, over 1418564.93 frames.], batch size: 28, lr: 4.78e-04
2022-05-14 19:37:25,121 INFO [train.py:812] (3/8) Epoch 16, batch 4200, loss[loss=0.1611, simple_loss=0.2366, pruned_loss=0.04277, over 6998.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03924, over 1418602.16 frames.], batch size: 16, lr: 4.78e-04
2022-05-14 19:38:24,439 INFO [train.py:812] (3/8) Epoch 16, batch 4250, loss[loss=0.1307, simple_loss=0.2155, pruned_loss=0.02294, over 7168.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2558, pruned_loss=0.03931, over 1417973.45 frames.], batch size: 18, lr: 4.78e-04
2022-05-14 19:39:23,839 INFO [train.py:812] (3/8) Epoch 16, batch 4300, loss[loss=0.1652, simple_loss=0.2544, pruned_loss=0.03801, over 6752.00 frames.], tot_loss[loss=0.167, simple_loss=0.2555, pruned_loss=0.03928, over 1413506.28 frames.], batch size: 31, lr: 4.78e-04
2022-05-14 19:40:22,737 INFO [train.py:812] (3/8) Epoch 16, batch 4350, loss[loss=0.1452, simple_loss=0.2371, pruned_loss=0.02671, over 7165.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2558, pruned_loss=0.03882, over 1416199.90 frames.], batch size: 18, lr: 4.77e-04
2022-05-14 19:41:21,972 INFO [train.py:812] (3/8) Epoch 16, batch 4400, loss[loss=0.1731, simple_loss=0.2841, pruned_loss=0.03103, over 7111.00 frames.], tot_loss[loss=0.1668, simple_loss=0.256, pruned_loss=0.03879, over 1415679.64 frames.], batch size: 21, lr: 4.77e-04
2022-05-14 19:42:18,613 INFO [train.py:812] (3/8) Epoch 16, batch 4450, loss[loss=0.1806, simple_loss=0.2708, pruned_loss=0.04522, over 7198.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2565, pruned_loss=0.03906, over 1410791.35 frames.], batch size: 22, lr: 4.77e-04
2022-05-14 19:43:16,028 INFO [train.py:812] (3/8) Epoch 16, batch 4500, loss[loss=0.1638, simple_loss=0.2545, pruned_loss=0.0366, over 7121.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.039, over 1401362.05 frames.], batch size: 17, lr: 4.77e-04
2022-05-14 19:44:12,834 INFO [train.py:812] (3/8) Epoch 16, batch 4550, loss[loss=0.1823, simple_loss=0.2682, pruned_loss=0.04816, over 4996.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2591, pruned_loss=0.04127, over 1350665.94 frames.], batch size: 52, lr: 4.77e-04
2022-05-14 19:45:27,028 INFO [train.py:812] (3/8) Epoch 17, batch 0, loss[loss=0.1948, simple_loss=0.2864, pruned_loss=0.05161, over 7102.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2864, pruned_loss=0.05161, over 7102.00 frames.], batch size: 21, lr: 4.63e-04
2022-05-14 19:46:26,097 INFO [train.py:812] (3/8) Epoch 17, batch 50, loss[loss=0.184, simple_loss=0.2868, pruned_loss=0.04062, over 7313.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2623, pruned_loss=0.04075, over 316507.97 frames.], batch size: 21, lr: 4.63e-04
2022-05-14 19:47:25,010 INFO [train.py:812] (3/8) Epoch 17, batch 100, loss[loss=0.1812, simple_loss=0.2622, pruned_loss=0.05011, over 7146.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2591, pruned_loss=0.03999, over 559010.00 frames.], batch size: 20, lr: 4.63e-04
2022-05-14 19:48:23,524 INFO [train.py:812] (3/8) Epoch 17, batch 150, loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04022, over 6978.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2568, pruned_loss=0.03945, over 747502.64 frames.], batch size: 16, lr: 4.63e-04
2022-05-14 19:49:23,016 INFO [train.py:812] (3/8) Epoch 17, batch 200, loss[loss=0.1628, simple_loss=0.2453, pruned_loss=0.04015, over 7138.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2585, pruned_loss=0.03965, over 896596.68 frames.], batch size: 17, lr: 4.63e-04
2022-05-14 19:50:21,383 INFO [train.py:812] (3/8) Epoch 17, batch 250, loss[loss=0.1411, simple_loss=0.2245, pruned_loss=0.02889, over 7261.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2585, pruned_loss=0.03958, over 1016265.38 frames.], batch size: 19, lr: 4.63e-04
2022-05-14 19:51:20,292 INFO [train.py:812] (3/8) Epoch 17, batch 300, loss[loss=0.1615, simple_loss=0.2409, pruned_loss=0.04104, over 7066.00 frames.], tot_loss[loss=0.169, simple_loss=0.2588, pruned_loss=0.03962, over 1102434.02 frames.], batch size: 18, lr: 4.62e-04
2022-05-14 19:52:19,505 INFO [train.py:812] (3/8) Epoch 17, batch 350, loss[loss=0.1705, simple_loss=0.2459, pruned_loss=0.04753, over 7216.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2575, pruned_loss=0.03951, over 1172353.01 frames.], batch size: 16, lr: 4.62e-04
2022-05-14 19:53:18,616 INFO [train.py:812] (3/8) Epoch 17, batch 400, loss[loss=0.2262, simple_loss=0.2946, pruned_loss=0.07894, over 5340.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2586, pruned_loss=0.03962, over 1228819.74 frames.], batch size: 52, lr: 4.62e-04
2022-05-14 19:54:16,193 INFO [train.py:812] (3/8) Epoch 17, batch 450, loss[loss=0.148, simple_loss=0.2377, pruned_loss=0.02919, over 7353.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2576, pruned_loss=0.03953, over 1268591.94 frames.], batch size: 19, lr: 4.62e-04
2022-05-14 19:55:14,833 INFO [train.py:812] (3/8) Epoch 17, batch 500, loss[loss=0.1468, simple_loss=0.2287, pruned_loss=0.03241, over 7177.00 frames.], tot_loss[loss=0.1678, simple_loss=0.257, pruned_loss=0.03927, over 1302134.45 frames.], batch size: 18, lr: 4.62e-04
2022-05-14 19:56:13,701 INFO [train.py:812] (3/8) Epoch 17, batch 550, loss[loss=0.1499, simple_loss=0.2262, pruned_loss=0.03683, over 7122.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2566, pruned_loss=0.03962, over 1328225.54 frames.], batch size: 17, lr: 4.62e-04
2022-05-14 19:57:12,589 INFO [train.py:812] (3/8) Epoch 17, batch 600, loss[loss=0.1797, simple_loss=0.2752, pruned_loss=0.04213, over 7004.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2561, pruned_loss=0.039, over 1342969.95 frames.], batch size: 28, lr: 4.62e-04
2022-05-14 19:58:11,566 INFO [train.py:812] (3/8) Epoch 17, batch 650, loss[loss=0.1565, simple_loss=0.2551, pruned_loss=0.02899, over 7337.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2567, pruned_loss=0.03887, over 1360847.81 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 19:59:10,294 INFO [train.py:812] (3/8) Epoch 17, batch 700, loss[loss=0.155, simple_loss=0.2437, pruned_loss=0.03322, over 7261.00 frames.], tot_loss[loss=0.168, simple_loss=0.2575, pruned_loss=0.03931, over 1367871.74 frames.], batch size: 19, lr: 4.61e-04
2022-05-14 20:00:09,353 INFO [train.py:812] (3/8) Epoch 17, batch 750, loss[loss=0.1663, simple_loss=0.2592, pruned_loss=0.03672, over 7146.00 frames.], tot_loss[loss=0.1685, simple_loss=0.258, pruned_loss=0.03947, over 1376184.57 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 20:01:08,205 INFO [train.py:812] (3/8) Epoch 17, batch 800, loss[loss=0.1642, simple_loss=0.2531, pruned_loss=0.03763, over 7161.00 frames.], tot_loss[loss=0.167, simple_loss=0.2567, pruned_loss=0.03867, over 1388309.35 frames.], batch size: 19, lr: 4.61e-04
2022-05-14 20:02:07,162 INFO [train.py:812] (3/8) Epoch 17, batch 850, loss[loss=0.1744, simple_loss=0.2656, pruned_loss=0.04156, over 6260.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2557, pruned_loss=0.03885, over 1396694.67 frames.], batch size: 37, lr: 4.61e-04
2022-05-14 20:03:05,135 INFO [train.py:812] (3/8) Epoch 17, batch 900, loss[loss=0.1636, simple_loss=0.2475, pruned_loss=0.03985, over 7329.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.03874, over 1408524.84 frames.], batch size: 20, lr: 4.61e-04
2022-05-14 20:04:03,139 INFO [train.py:812] (3/8) Epoch 17, batch 950, loss[loss=0.1669, simple_loss=0.2392, pruned_loss=0.04728, over 7135.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2554, pruned_loss=0.03865, over 1412464.92 frames.], batch size: 17, lr: 4.60e-04
2022-05-14 20:05:01,741 INFO [train.py:812] (3/8) Epoch 17, batch 1000, loss[loss=0.1569, simple_loss=0.2615, pruned_loss=0.02616, over 7117.00 frames.], tot_loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03835, over 1417016.00 frames.], batch size: 21, lr: 4.60e-04
2022-05-14 20:06:00,353 INFO [train.py:812] (3/8) Epoch 17, batch 1050, loss[loss=0.1839, simple_loss=0.286, pruned_loss=0.04087, over 7338.00 frames.], tot_loss[loss=0.166, simple_loss=0.2552, pruned_loss=0.03838, over 1421238.77 frames.], batch size: 22, lr: 4.60e-04
2022-05-14 20:06:59,640 INFO [train.py:812] (3/8) Epoch 17, batch 1100, loss[loss=0.1887, simple_loss=0.2677, pruned_loss=0.0548, over 7305.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2559, pruned_loss=0.03854, over 1421625.96 frames.], batch size: 24, lr: 4.60e-04
2022-05-14 20:07:58,271 INFO [train.py:812] (3/8) Epoch 17, batch 1150, loss[loss=0.196, simple_loss=0.2906, pruned_loss=0.05072, over 7312.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2565, pruned_loss=0.03916, over 1422947.43 frames.], batch size: 24, lr: 4.60e-04
2022-05-14 20:08:57,627 INFO [train.py:812] (3/8) Epoch 17, batch 1200, loss[loss=0.2597, simple_loss=0.3534, pruned_loss=0.08303, over 7291.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2575, pruned_loss=0.03979, over 1419086.20 frames.], batch size: 25, lr: 4.60e-04
2022-05-14 20:09:55,622 INFO [train.py:812] (3/8) Epoch 17, batch 1250, loss[loss=0.182, simple_loss=0.2732, pruned_loss=0.04543, over 7276.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2576, pruned_loss=0.03973, over 1415153.30 frames.], batch size: 18, lr: 4.60e-04
2022-05-14 20:10:53,524 INFO [train.py:812] (3/8) Epoch 17, batch 1300, loss[loss=0.1872, simple_loss=0.2854, pruned_loss=0.04447, over 7350.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.03949, over 1413828.90 frames.], batch size: 22, lr: 4.59e-04
2022-05-14 20:11:51,652 INFO [train.py:812] (3/8) Epoch 17, batch 1350, loss[loss=0.1781, simple_loss=0.2585, pruned_loss=0.0489, over 6996.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2572, pruned_loss=0.0395, over 1419219.71 frames.], batch size: 16, lr: 4.59e-04
2022-05-14 20:12:51,094 INFO [train.py:812] (3/8) Epoch 17, batch 1400, loss[loss=0.1891, simple_loss=0.272, pruned_loss=0.05311, over 7139.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2558, pruned_loss=0.03923, over 1420483.05 frames.], batch size: 20, lr: 4.59e-04
2022-05-14 20:13:49,598 INFO [train.py:812] (3/8) Epoch 17, batch 1450, loss[loss=0.1734, simple_loss=0.2649, pruned_loss=0.04095, over 7343.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2563, pruned_loss=0.03931, over 1419381.06 frames.], batch size: 22, lr: 4.59e-04
2022-05-14 20:14:48,947 INFO [train.py:812] (3/8) Epoch 17, batch 1500, loss[loss=0.1357, simple_loss=0.2223, pruned_loss=0.02457, over 7249.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2547, pruned_loss=0.0385, over 1425014.51 frames.], batch size: 19, lr: 4.59e-04
2022-05-14 20:15:57,360 INFO [train.py:812] (3/8) Epoch 17, batch 1550, loss[loss=0.1728, simple_loss=0.2655, pruned_loss=0.04008, over 7211.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2551, pruned_loss=0.03902, over 1423079.44 frames.], batch size: 21, lr: 4.59e-04
2022-05-14 20:16:56,749 INFO [train.py:812] (3/8) Epoch 17, batch 1600, loss[loss=0.1618, simple_loss=0.2447, pruned_loss=0.03943, over 7424.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2548, pruned_loss=0.0387, over 1427576.29 frames.], batch size: 20, lr: 4.58e-04
2022-05-14 20:17:55,347 INFO [train.py:812] (3/8) Epoch 17, batch 1650, loss[loss=0.1466, simple_loss=0.2407, pruned_loss=0.02622, over 7418.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2549, pruned_loss=0.03859, over 1428964.81 frames.], batch size: 21, lr: 4.58e-04
2022-05-14 20:18:53,710 INFO [train.py:812] (3/8) Epoch 17, batch 1700, loss[loss=0.1795, simple_loss=0.279, pruned_loss=0.04002, over 5361.00 frames.], tot_loss[loss=0.167, simple_loss=0.256, pruned_loss=0.039, over 1423487.35 frames.], batch size: 52, lr: 4.58e-04
2022-05-14 20:19:52,402 INFO [train.py:812] (3/8) Epoch 17, batch 1750, loss[loss=0.2043, simple_loss=0.2934, pruned_loss=0.05757, over 7380.00 frames.], tot_loss[loss=0.1677, simple_loss=0.257, pruned_loss=0.03924, over 1414531.29 frames.], batch size: 23, lr: 4.58e-04
2022-05-14 20:20:51,552 INFO [train.py:812] (3/8) Epoch 17, batch 1800, loss[loss=0.1651, simple_loss=0.2636, pruned_loss=0.03331, over 7204.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2568, pruned_loss=0.03878, over 1415278.88 frames.], batch size: 23, lr: 4.58e-04
2022-05-14 20:21:48,757 INFO [train.py:812] (3/8) Epoch 17, batch 1850, loss[loss=0.1794, simple_loss=0.2636, pruned_loss=0.04758, over 6393.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2571, pruned_loss=0.03907, over 1416272.47 frames.], batch size: 37, lr: 4.58e-04
2022-05-14 20:22:47,369 INFO [train.py:812] (3/8) Epoch 17, batch 1900, loss[loss=0.1848, simple_loss=0.2719, pruned_loss=0.04889, over 7443.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2571, pruned_loss=0.03919, over 1420386.67 frames.], batch size: 20, lr: 4.58e-04
2022-05-14 20:23:46,069 INFO [train.py:812] (3/8) Epoch 17, batch 1950, loss[loss=0.1757, simple_loss=0.2666, pruned_loss=0.04239, over 7313.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2566, pruned_loss=0.03899, over 1422363.60 frames.], batch size: 21, lr: 4.57e-04
2022-05-14 20:24:44,691 INFO [train.py:812] (3/8) Epoch 17, batch 2000, loss[loss=0.15, simple_loss=0.2377, pruned_loss=0.03116, over 7268.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2569, pruned_loss=0.03902, over 1424539.52 frames.], batch size: 19, lr: 4.57e-04
2022-05-14 20:25:43,667 INFO [train.py:812] (3/8) Epoch 17, batch 2050, loss[loss=0.1475, simple_loss=0.2332, pruned_loss=0.03093, over 7417.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2559, pruned_loss=0.03871, over 1427281.76 frames.], batch size: 18, lr: 4.57e-04
2022-05-14 20:26:43,428 INFO [train.py:812] (3/8) Epoch 17, batch 2100, loss[loss=0.1672, simple_loss=0.2577, pruned_loss=0.03839, over 7415.00 frames.], tot_loss[loss=0.1667, simple_loss=0.256, pruned_loss=0.03867, over 1428754.35 frames.], batch size: 21, lr: 4.57e-04
2022-05-14 20:27:42,668 INFO [train.py:812] (3/8) Epoch 17, batch 2150, loss[loss=0.1769, simple_loss=0.2642, pruned_loss=0.04482, over 7358.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2563, pruned_loss=0.03895, over 1424554.86 frames.], batch size: 19, lr: 4.57e-04
2022-05-14 20:28:40,063 INFO [train.py:812] (3/8) Epoch 17, batch 2200, loss[loss=0.1646, simple_loss=0.2646, pruned_loss=0.03226, over 7338.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2563, pruned_loss=0.03879, over 1422207.89 frames.], batch size: 22, lr: 4.57e-04
2022-05-14 20:29:39,220 INFO [train.py:812] (3/8) Epoch 17, batch 2250, loss[loss=0.1645, simple_loss=0.2637, pruned_loss=0.03269, over 7405.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2562, pruned_loss=0.03872, over 1424316.39 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:30:37,971 INFO [train.py:812] (3/8) Epoch 17, batch 2300, loss[loss=0.1896, simple_loss=0.2796, pruned_loss=0.0498, over 7298.00 frames.], tot_loss[loss=0.167, simple_loss=0.2567, pruned_loss=0.03866, over 1423255.60 frames.], batch size: 24, lr: 4.56e-04
2022-05-14 20:31:36,782 INFO [train.py:812] (3/8) Epoch 17, batch 2350, loss[loss=0.1727, simple_loss=0.2615, pruned_loss=0.04192, over 7381.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2555, pruned_loss=0.03795, over 1427007.22 frames.], batch size: 23, lr: 4.56e-04
2022-05-14 20:32:36,095 INFO [train.py:812] (3/8) Epoch 17, batch 2400, loss[loss=0.1479, simple_loss=0.2234, pruned_loss=0.03621, over 6998.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2552, pruned_loss=0.03795, over 1424613.64 frames.], batch size: 16, lr: 4.56e-04
2022-05-14 20:33:34,598 INFO [train.py:812] (3/8) Epoch 17, batch 2450, loss[loss=0.153, simple_loss=0.2492, pruned_loss=0.02837, over 7329.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2545, pruned_loss=0.03757, over 1424256.78 frames.], batch size: 22, lr: 4.56e-04
2022-05-14 20:34:34,265 INFO [train.py:812] (3/8) Epoch 17, batch 2500, loss[loss=0.1739, simple_loss=0.2662, pruned_loss=0.0408, over 7213.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2532, pruned_loss=0.03722, over 1423513.19 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:35:31,565 INFO [train.py:812] (3/8) Epoch 17, batch 2550, loss[loss=0.1682, simple_loss=0.2701, pruned_loss=0.03313, over 7223.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2531, pruned_loss=0.03731, over 1418454.31 frames.], batch size: 21, lr: 4.56e-04
2022-05-14 20:36:37,624 INFO [train.py:812] (3/8) Epoch 17, batch 2600, loss[loss=0.1678, simple_loss=0.2604, pruned_loss=0.03762, over 7062.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2549, pruned_loss=0.038, over 1421102.89 frames.], batch size: 28, lr: 4.55e-04
2022-05-14 20:37:36,696 INFO [train.py:812] (3/8) Epoch 17, batch 2650, loss[loss=0.1566, simple_loss=0.2378, pruned_loss=0.03771, over 7363.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2549, pruned_loss=0.03799, over 1419971.65 frames.], batch size: 19, lr: 4.55e-04
2022-05-14 20:38:34,780 INFO [train.py:812] (3/8) Epoch 17, batch 2700, loss[loss=0.1809, simple_loss=0.2843, pruned_loss=0.03874, over 7318.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2543, pruned_loss=0.03771, over 1422545.95 frames.], batch size: 22, lr: 4.55e-04
2022-05-14 20:39:32,808 INFO [train.py:812] (3/8) Epoch 17, batch 2750, loss[loss=0.1554, simple_loss=0.2451, pruned_loss=0.03285, over 7148.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2536, pruned_loss=0.03761, over 1421631.46 frames.], batch size: 19, lr: 4.55e-04
2022-05-14 20:40:31,885 INFO [train.py:812] (3/8) Epoch 17, batch 2800, loss[loss=0.204, simple_loss=0.2761, pruned_loss=0.06593, over 5298.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2537, pruned_loss=0.0376, over 1421762.83 frames.], batch size: 52, lr: 4.55e-04
2022-05-14 20:41:30,546 INFO [train.py:812] (3/8) Epoch 17, batch 2850, loss[loss=0.1543, simple_loss=0.2531, pruned_loss=0.02777, over 7317.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2543, pruned_loss=0.0379, over 1422229.22 frames.], batch size: 21, lr: 4.55e-04
2022-05-14 20:42:28,889 INFO [train.py:812] (3/8) Epoch 17, batch 2900, loss[loss=0.1688, simple_loss=0.2745, pruned_loss=0.03152, over 7237.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2545, pruned_loss=0.03816, over 1418527.16 frames.], batch size: 20, lr: 4.55e-04
2022-05-14 20:43:27,754 INFO [train.py:812] (3/8) Epoch 17, batch 2950, loss[loss=0.1361, simple_loss=0.2271, pruned_loss=0.0225, over 7274.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2551, pruned_loss=0.0385, over 1419287.62 frames.], batch size: 18, lr: 4.54e-04
2022-05-14 20:44:36,159 INFO [train.py:812] (3/8) Epoch 17, batch 3000, loss[loss=0.173, simple_loss=0.2754, pruned_loss=0.0353, over 7144.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2557, pruned_loss=0.03845, over 1423893.38 frames.], batch size: 20, lr: 4.54e-04
2022-05-14 20:44:36,159 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 20:44:43,902 INFO [train.py:841] (3/8) Epoch 17, validation: loss=0.1538, simple_loss=0.2534, pruned_loss=0.02708, over 698248.00 frames.
2022-05-14 20:45:42,769 INFO [train.py:812] (3/8) Epoch 17, batch 3050, loss[loss=0.1557, simple_loss=0.2528, pruned_loss=0.02929, over 6269.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2553, pruned_loss=0.03815, over 1423667.82 frames.], batch size: 37, lr: 4.54e-04
2022-05-14 20:46:41,070 INFO [train.py:812] (3/8) Epoch 17, batch 3100, loss[loss=0.1814, simple_loss=0.2691, pruned_loss=0.04684, over 7301.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2558, pruned_loss=0.03837, over 1420455.57 frames.], batch size: 25, lr: 4.54e-04
2022-05-14 20:47:58,623 INFO [train.py:812] (3/8) Epoch 17, batch 3150, loss[loss=0.1569, simple_loss=0.2429, pruned_loss=0.03547, over 7332.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2559, pruned_loss=0.03869, over 1419588.01 frames.], batch size: 20, lr: 4.54e-04
2022-05-14 20:49:07,274 INFO [train.py:812] (3/8) Epoch 17, batch 3200, loss[loss=0.1571, simple_loss=0.2493, pruned_loss=0.03243, over 7367.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2548, pruned_loss=0.03855, over 1418910.11 frames.], batch size: 19, lr: 4.54e-04
2022-05-14 20:50:25,523 INFO [train.py:812] (3/8) Epoch 17, batch 3250, loss[loss=0.1824, simple_loss=0.2545, pruned_loss=0.05518, over 7056.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2553, pruned_loss=0.03879, over 1424581.30 frames.], batch size: 18, lr: 4.54e-04
2022-05-14 20:51:34,403 INFO [train.py:812] (3/8) Epoch 17, batch 3300, loss[loss=0.2074, simple_loss=0.2944, pruned_loss=0.06024, over 7149.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2561, pruned_loss=0.03908, over 1425754.68 frames.], batch size: 19, lr: 4.53e-04
2022-05-14 20:52:33,317 INFO [train.py:812] (3/8) Epoch 17, batch 3350, loss[loss=0.187, simple_loss=0.2754, pruned_loss=0.04931, over 7340.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2563, pruned_loss=0.039, over 1426494.96 frames.], batch size: 22, lr: 4.53e-04
2022-05-14 20:53:32,492 INFO [train.py:812] (3/8) Epoch 17, batch 3400, loss[loss=0.1725, simple_loss=0.258, pruned_loss=0.04349, over 7141.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2551, pruned_loss=0.03837, over 1423804.02 frames.], batch size: 20, lr: 4.53e-04
2022-05-14 20:54:31,686 INFO [train.py:812] (3/8) Epoch 17, batch 3450, loss[loss=0.1487, simple_loss=0.2424, pruned_loss=0.02748, over 7330.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2532, pruned_loss=0.03816, over 1424677.22 frames.], batch size: 20, lr: 4.53e-04
2022-05-14 20:55:30,336 INFO [train.py:812] (3/8) Epoch 17, batch 3500, loss[loss=0.1665, simple_loss=0.2583, pruned_loss=0.03732, over 7214.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2536, pruned_loss=0.03805, over 1424372.08 frames.], batch size: 22, lr: 4.53e-04
2022-05-14 20:56:29,291 INFO [train.py:812] (3/8) Epoch 17, batch 3550, loss[loss=0.1722, simple_loss=0.2676, pruned_loss=0.03842, over 7107.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2542, pruned_loss=0.03785, over 1426698.54 frames.], batch size: 21, lr: 4.53e-04
2022-05-14 20:57:28,812 INFO [train.py:812] (3/8) Epoch 17, batch 3600, loss[loss=0.1373, simple_loss=0.2263, pruned_loss=0.02418, over 7277.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03797, over 1427555.97 frames.], batch size: 18, lr: 4.52e-04
2022-05-14 20:58:27,773 INFO [train.py:812] (3/8) Epoch 17, batch 3650, loss[loss=0.1705, simple_loss=0.2607, pruned_loss=0.04016, over 7320.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2547, pruned_loss=0.03784, over 1431062.89 frames.], batch size: 21, lr: 4.52e-04
2022-05-14 20:59:27,705 INFO [train.py:812] (3/8) Epoch 17, batch 3700, loss[loss=0.1556, simple_loss=0.2533, pruned_loss=0.02894, over 7142.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2542, pruned_loss=0.03762, over 1431244.09 frames.], batch size: 20, lr: 4.52e-04
2022-05-14 21:00:26,369 INFO [train.py:812] (3/8) Epoch 17, batch 3750, loss[loss=0.1851, simple_loss=0.284, pruned_loss=0.04315, over 6452.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2544, pruned_loss=0.03757, over 1428141.54 frames.], batch size: 38, lr: 4.52e-04
2022-05-14 21:01:24,374 INFO [train.py:812] (3/8) Epoch 17, batch 3800, loss[loss=0.1701, simple_loss=0.2613, pruned_loss=0.03948, over 6462.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2551, pruned_loss=0.03783, over 1426845.33 frames.], batch size: 38, lr: 4.52e-04
2022-05-14 21:02:23,092 INFO [train.py:812] (3/8) Epoch 17, batch 3850, loss[loss=0.1272, simple_loss=0.2143, pruned_loss=0.02002, over 6991.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03784, over 1426202.37 frames.], batch size: 16, lr: 4.52e-04
2022-05-14 21:03:22,480 INFO [train.py:812] (3/8) Epoch 17, batch 3900, loss[loss=0.1777, simple_loss=0.2606, pruned_loss=0.04734, over 7205.00 frames.], tot_loss[loss=0.165, simple_loss=0.2543, pruned_loss=0.03786, over 1428196.25 frames.], batch size: 22, lr: 4.52e-04
2022-05-14 21:04:21,494 INFO [train.py:812] (3/8) Epoch 17, batch 3950, loss[loss=0.1705, simple_loss=0.2676, pruned_loss=0.03674, over 7187.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2554, pruned_loss=0.0381, over 1427541.96 frames.], batch size: 23, lr: 4.51e-04
2022-05-14 21:05:20,839 INFO [train.py:812] (3/8) Epoch 17, batch 4000, loss[loss=0.1427, simple_loss=0.2272, pruned_loss=0.02916, over 7290.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2552, pruned_loss=0.03822, over 1427732.73 frames.], batch size: 18, lr: 4.51e-04
2022-05-14 21:06:19,927 INFO [train.py:812] (3/8) Epoch 17, batch 4050, loss[loss=0.1755, simple_loss=0.2666, pruned_loss=0.0422, over 6850.00 frames.], tot_loss[loss=0.166, simple_loss=0.255, pruned_loss=0.03851, over 1424406.29 frames.], batch size: 31, lr: 4.51e-04
2022-05-14 21:07:18,998 INFO [train.py:812] (3/8) Epoch 17, batch 4100, loss[loss=0.1653, simple_loss=0.2616, pruned_loss=0.03453, over 6378.00 frames.], tot_loss[loss=0.1671, simple_loss=0.256, pruned_loss=0.03912, over 1423592.36 frames.], batch size: 37, lr: 4.51e-04
2022-05-14 21:08:18,273 INFO [train.py:812] (3/8) Epoch 17, batch 4150, loss[loss=0.1426, simple_loss=0.2301, pruned_loss=0.02761, over 7136.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2553, pruned_loss=0.03897, over 1423428.63 frames.], batch size: 17, lr: 4.51e-04
2022-05-14 21:09:17,053 INFO [train.py:812] (3/8) Epoch 17, batch 4200, loss[loss=0.1743, simple_loss=0.2712, pruned_loss=0.03869, over 7163.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2562, pruned_loss=0.03928, over 1422172.27 frames.], batch size: 26, lr: 4.51e-04
2022-05-14 21:10:16,228 INFO [train.py:812] (3/8) Epoch 17, batch 4250, loss[loss=0.151, simple_loss=0.2454, pruned_loss=0.02832, over 7271.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2569, pruned_loss=0.03942, over 1423034.39 frames.], batch size: 18, lr: 4.51e-04
2022-05-14 21:11:15,271 INFO [train.py:812] (3/8) Epoch 17, batch 4300, loss[loss=0.1449, simple_loss=0.2379, pruned_loss=0.026, over 7067.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2563, pruned_loss=0.03898, over 1422013.00 frames.], batch size: 18, lr: 4.50e-04
2022-05-14 21:12:14,024 INFO [train.py:812] (3/8) Epoch 17, batch 4350, loss[loss=0.1708, simple_loss=0.2567, pruned_loss=0.04248, over 7166.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2553, pruned_loss=0.03869, over 1421419.02 frames.], batch size: 18, lr: 4.50e-04
2022-05-14 21:13:12,932 INFO [train.py:812] (3/8) Epoch 17, batch 4400, loss[loss=0.1515, simple_loss=0.2483, pruned_loss=0.02733, over 7222.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2555, pruned_loss=0.03878, over 1419404.82 frames.], batch size: 21, lr: 4.50e-04
2022-05-14 21:14:12,271 INFO [train.py:812] (3/8) Epoch 17, batch 4450, loss[loss=0.1529, simple_loss=0.2329, pruned_loss=0.03644, over 7122.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2565, pruned_loss=0.0389, over 1414879.15 frames.], batch size: 17, lr: 4.50e-04
2022-05-14 21:15:12,247 INFO [train.py:812] (3/8) Epoch 17, batch 4500, loss[loss=0.1756, simple_loss=0.2645, pruned_loss=0.04336, over 7239.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2553, pruned_loss=0.03865, over 1413613.28 frames.], batch size: 20, lr: 4.50e-04
2022-05-14 21:16:11,537 INFO [train.py:812] (3/8) Epoch 17, batch 4550, loss[loss=0.1773, simple_loss=0.2601, pruned_loss=0.04721, over 5102.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2546, pruned_loss=0.03949, over 1376662.09 frames.], batch size: 53, lr: 4.50e-04
2022-05-14 21:17:18,356 INFO [train.py:812] (3/8) Epoch 18, batch 0, loss[loss=0.1838, simple_loss=0.2651, pruned_loss=0.0513, over 7238.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2651, pruned_loss=0.0513, over 7238.00 frames.], batch size: 20, lr: 4.38e-04
2022-05-14 21:18:18,229 INFO [train.py:812] (3/8) Epoch 18, batch 50, loss[loss=0.1594, simple_loss=0.2419, pruned_loss=0.03843, over 7006.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2541, pruned_loss=0.03842, over 323622.16 frames.], batch size: 16, lr: 4.38e-04
2022-05-14 21:19:17,370 INFO [train.py:812] (3/8) Epoch 18, batch 100, loss[loss=0.1666, simple_loss=0.2552, pruned_loss=0.03902, over 7153.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2549, pruned_loss=0.03867, over 565413.99 frames.], batch size: 18, lr: 4.37e-04
2022-05-14 21:20:15,729 INFO [train.py:812] (3/8) Epoch 18, batch 150, loss[loss=0.169, simple_loss=0.2618, pruned_loss=0.03809, over 7142.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2567, pruned_loss=0.0399, over 752276.03 frames.], batch size: 20, lr: 4.37e-04
2022-05-14 21:21:13,523 INFO [train.py:812] (3/8) Epoch 18, batch 200, loss[loss=0.1659, simple_loss=0.2505, pruned_loss=0.04068, over 7168.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2564, pruned_loss=0.03936, over 903349.68 frames.], batch size: 18, lr: 4.37e-04
2022-05-14 21:22:12,912 INFO [train.py:812] (3/8) Epoch 18, batch 250, loss[loss=0.1571, simple_loss=0.2492, pruned_loss=0.03252, over 6822.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2568, pruned_loss=0.03924, over 1020865.66 frames.], batch size: 31, lr: 4.37e-04
2022-05-14 21:23:11,923 INFO [train.py:812] (3/8) Epoch 18, batch 300, loss[loss=0.1811, simple_loss=0.267, pruned_loss=0.04766, over 7045.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2562, pruned_loss=0.03863, over 1104183.98 frames.], batch size: 28, lr: 4.37e-04
2022-05-14 21:24:11,080 INFO [train.py:812] (3/8) Epoch 18, batch 350, loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04297, over 7337.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03795, over 1172271.06 frames.], batch size: 22, lr: 4.37e-04
2022-05-14 21:25:08,900 INFO [train.py:812] (3/8) Epoch 18, batch 400, loss[loss=0.1371, simple_loss=0.2201, pruned_loss=0.02702, over 7247.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2546, pruned_loss=0.03717, over 1232698.16 frames.], batch size: 16, lr: 4.37e-04
2022-05-14 21:26:06,606 INFO [train.py:812] (3/8) Epoch 18, batch 450, loss[loss=0.1629, simple_loss=0.2476, pruned_loss=0.03912, over 7214.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2558, pruned_loss=0.03783, over 1275635.90 frames.], batch size: 22, lr: 4.36e-04
2022-05-14 21:27:06,218 INFO [train.py:812] (3/8) Epoch 18, batch 500, loss[loss=0.1618, simple_loss=0.2591, pruned_loss=0.03224, over 7337.00 frames.], tot_loss[loss=0.1659, simple_loss=0.256, pruned_loss=0.03787, over 1312227.82 frames.], batch size: 22, lr: 4.36e-04
2022-05-14 21:28:04,684 INFO [train.py:812] (3/8) Epoch 18, batch 550, loss[loss=0.1312, simple_loss=0.2249, pruned_loss=0.01876, over 7135.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2551, pruned_loss=0.03755, over 1338684.31 frames.], batch size: 17, lr: 4.36e-04
2022-05-14 21:29:02,257 INFO [train.py:812] (3/8) Epoch 18, batch 600, loss[loss=0.1682, simple_loss=0.2592, pruned_loss=0.03862, over 6427.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2566, pruned_loss=0.03854, over 1356410.62 frames.], batch size: 38, lr: 4.36e-04
2022-05-14 21:30:01,242 INFO [train.py:812] (3/8) Epoch 18, batch 650, loss[loss=0.19, simple_loss=0.2697, pruned_loss=0.05514, over 4944.00 frames.], tot_loss[loss=0.166, simple_loss=0.2558, pruned_loss=0.03807, over 1369181.40 frames.], batch size: 52, lr: 4.36e-04
2022-05-14 21:30:59,697 INFO [train.py:812] (3/8) Epoch 18, batch 700, loss[loss=0.177, simple_loss=0.2691, pruned_loss=0.04246, over 7318.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2549, pruned_loss=0.03799, over 1380370.78 frames.], batch size: 21, lr: 4.36e-04
2022-05-14 21:31:59,636 INFO [train.py:812] (3/8) Epoch 18, batch 750, loss[loss=0.1618, simple_loss=0.2507, pruned_loss=0.0364, over 7428.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2539, pruned_loss=0.03781, over 1390921.97 frames.], batch size: 18, lr: 4.36e-04
2022-05-14 21:32:57,566 INFO [train.py:812] (3/8) Epoch 18, batch 800, loss[loss=0.1867, simple_loss=0.2798, pruned_loss=0.04679, over 7321.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2536, pruned_loss=0.03743, over 1403512.57 frames.], batch size: 21, lr: 4.36e-04
2022-05-14 21:33:57,275 INFO [train.py:812] (3/8) Epoch 18, batch 850, loss[loss=0.1506, simple_loss=0.2516, pruned_loss=0.02484, over 7409.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2535, pruned_loss=0.03754, over 1406851.92 frames.], batch size: 21, lr: 4.35e-04
2022-05-14 21:34:56,180 INFO [train.py:812] (3/8) Epoch 18, batch 900, loss[loss=0.1979, simple_loss=0.2887, pruned_loss=0.0536, over 7203.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2545, pruned_loss=0.03816, over 1406847.82 frames.], batch size: 22, lr: 4.35e-04
2022-05-14 21:35:54,622 INFO [train.py:812] (3/8) Epoch 18, batch 950, loss[loss=0.1485, simple_loss=0.2463, pruned_loss=0.02534, over 7252.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2554, pruned_loss=0.03816, over 1408938.95 frames.], batch size: 19, lr: 4.35e-04
2022-05-14 21:36:52,271 INFO [train.py:812] (3/8) Epoch 18, batch 1000, loss[loss=0.1702, simple_loss=0.2645, pruned_loss=0.03796, over 7287.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2548, pruned_loss=0.03772, over 1413311.03 frames.], batch size: 24, lr: 4.35e-04
2022-05-14 21:37:51,922 INFO [train.py:812] (3/8) Epoch 18, batch 1050, loss[loss=0.174, simple_loss=0.2542, pruned_loss=0.04685, over 7281.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2536, pruned_loss=0.03726, over 1414986.55 frames.], batch size: 17, lr: 4.35e-04
2022-05-14 21:38:50,480 INFO [train.py:812] (3/8) Epoch 18, batch 1100, loss[loss=0.2405, simple_loss=0.3131, pruned_loss=0.08392, over 7279.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2541, pruned_loss=0.03745, over 1419539.55 frames.], batch size: 25, lr: 4.35e-04
2022-05-14 21:39:48,085 INFO [train.py:812] (3/8) Epoch 18, batch 1150, loss[loss=0.1741, simple_loss=0.2701, pruned_loss=0.0391, over 7377.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03773, over 1418323.11 frames.], batch size: 23, lr: 4.35e-04
2022-05-14 21:40:45,341 INFO [train.py:812] (3/8) Epoch 18, batch 1200, loss[loss=0.1792, simple_loss=0.2611, pruned_loss=0.04864, over 7286.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2545, pruned_loss=0.03799, over 1415952.91 frames.], batch size: 18, lr: 4.34e-04
2022-05-14 21:41:44,615 INFO [train.py:812] (3/8) Epoch 18, batch 1250, loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.03072, over 7407.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2548, pruned_loss=0.03803, over 1417960.18 frames.], batch size: 21, lr: 4.34e-04
2022-05-14 21:42:42,160 INFO [train.py:812] (3/8) Epoch 18, batch 1300, loss[loss=0.153, simple_loss=0.2391, pruned_loss=0.03347, over 7160.00 frames.], tot_loss[loss=0.1649, simple_loss=0.254, pruned_loss=0.0379, over 1419223.04 frames.], batch size: 26, lr: 4.34e-04
2022-05-14 21:43:41,332 INFO [train.py:812] (3/8) Epoch 18, batch 1350, loss[loss=0.1508, simple_loss=0.2338, pruned_loss=0.03391, over 7000.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2545, pruned_loss=0.03796, over 1421743.17 frames.], batch size: 16, lr: 4.34e-04
2022-05-14 21:44:39,588 INFO [train.py:812] (3/8) Epoch 18, batch 1400, loss[loss=0.1494, simple_loss=0.2474, pruned_loss=0.02576, over 7118.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2553, pruned_loss=0.03807, over 1423743.48 frames.], batch size: 21, lr: 4.34e-04
2022-05-14 21:45:38,203 INFO [train.py:812] (3/8) Epoch 18, batch 1450, loss[loss=0.1726, simple_loss=0.2645, pruned_loss=0.04033, over 7149.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2557, pruned_loss=0.03828, over 1421742.09 frames.], batch size: 20, lr: 4.34e-04
2022-05-14 21:46:36,910 INFO [train.py:812] (3/8) Epoch 18, batch 1500, loss[loss=0.1527, simple_loss=0.2447, pruned_loss=0.03031, over 7288.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2556, pruned_loss=0.03829, over 1413339.49 frames.], batch size: 25, lr: 4.34e-04
2022-05-14 21:47:35,825 INFO [train.py:812] (3/8) Epoch 18, batch 1550, loss[loss=0.1767, simple_loss=0.2603, pruned_loss=0.04649, over 7156.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03797, over 1420524.97 frames.], batch size: 19, lr: 4.33e-04
2022-05-14 21:48:33,674 INFO [train.py:812] (3/8) Epoch 18, batch 1600, loss[loss=0.146, simple_loss=0.2384, pruned_loss=0.02676, over 7432.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2554, pruned_loss=0.03811, over 1421184.26 frames.], batch size: 20, lr: 4.33e-04
2022-05-14 21:49:33,290 INFO [train.py:812] (3/8) Epoch 18, batch 1650, loss[loss=0.1386, simple_loss=0.2211, pruned_loss=0.02806, over 7283.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2545, pruned_loss=0.03757, over 1421008.87 frames.], batch size: 17, lr: 4.33e-04
2022-05-14 21:50:30,803 INFO [train.py:812] (3/8) Epoch 18, batch 1700, loss[loss=0.1597, simple_loss=0.2466, pruned_loss=0.03643, over 7362.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2554, pruned_loss=0.03798, over 1423734.14 frames.], batch size: 19, lr: 4.33e-04
2022-05-14 21:51:29,625 INFO [train.py:812] (3/8) Epoch 18, batch 1750, loss[loss=0.19, simple_loss=0.2716, pruned_loss=0.0542, over 7323.00 frames.], tot_loss[loss=0.166, simple_loss=0.2555, pruned_loss=0.0382, over 1424000.89 frames.], batch size: 21, lr: 4.33e-04
2022-05-14 21:52:27,478 INFO [train.py:812] (3/8) Epoch 18, batch 1800, loss[loss=0.1575, simple_loss=0.2453, pruned_loss=0.03483, over 7235.00 frames.], tot_loss[loss=0.165, simple_loss=0.2546, pruned_loss=0.03776, over 1427958.50 frames.], batch size: 20, lr: 4.33e-04
2022-05-14 21:53:27,315 INFO [train.py:812] (3/8) Epoch 18, batch 1850, loss[loss=0.1835, simple_loss=0.2694, pruned_loss=0.04876, over 4792.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2531, pruned_loss=0.03753, over 1426224.65 frames.], batch size: 53, lr: 4.33e-04
2022-05-14 21:54:25,903 INFO [train.py:812] (3/8) Epoch 18, batch 1900, loss[loss=0.1848, simple_loss=0.2882, pruned_loss=0.04074, over 7325.00 frames.], tot_loss[loss=0.1654, simple_loss=0.255, pruned_loss=0.03792, over 1426270.43 frames.], batch size: 21, lr: 4.33e-04
2022-05-14 21:55:25,268 INFO [train.py:812] (3/8) Epoch 18, batch 1950, loss[loss=0.1683, simple_loss=0.2655, pruned_loss=0.0355, over 7326.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2561, pruned_loss=0.03825, over 1423490.33 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 21:56:23,559 INFO [train.py:812] (3/8) Epoch 18, batch 2000, loss[loss=0.1792, simple_loss=0.2552, pruned_loss=0.05164, over 4976.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2552, pruned_loss=0.03817, over 1423940.51 frames.], batch size: 52, lr: 4.32e-04
2022-05-14 21:57:27,187 INFO [train.py:812] (3/8) Epoch 18, batch 2050, loss[loss=0.179, simple_loss=0.2637, pruned_loss=0.04717, over 7126.00 frames.], tot_loss[loss=0.166, simple_loss=0.2553, pruned_loss=0.03832, over 1421010.25 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 21:58:25,629 INFO [train.py:812] (3/8) Epoch 18, batch 2100, loss[loss=0.198, simple_loss=0.3016, pruned_loss=0.04725, over 6860.00 frames.], tot_loss[loss=0.1658, simple_loss=0.255, pruned_loss=0.03829, over 1416866.44 frames.], batch size: 32, lr: 4.32e-04
2022-05-14 21:59:24,608 INFO [train.py:812] (3/8) Epoch 18, batch 2150, loss[loss=0.146, simple_loss=0.2384, pruned_loss=0.02683, over 7230.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2547, pruned_loss=0.03807, over 1418481.79 frames.], batch size: 21, lr: 4.32e-04
2022-05-14 22:00:22,625 INFO [train.py:812] (3/8) Epoch 18, batch 2200, loss[loss=0.1713, simple_loss=0.2489, pruned_loss=0.04683, over 7269.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2545, pruned_loss=0.03798, over 1420985.50 frames.], batch size: 16, lr: 4.32e-04
2022-05-14 22:01:21,995 INFO [train.py:812] (3/8) Epoch 18, batch 2250, loss[loss=0.1424, simple_loss=0.2249, pruned_loss=0.02999, over 7011.00 frames.], tot_loss[loss=0.1647, simple_loss=0.254, pruned_loss=0.03767, over 1424298.56 frames.], batch size: 16, lr: 4.32e-04
2022-05-14 22:02:21,443 INFO [train.py:812] (3/8) Epoch 18, batch 2300, loss[loss=0.1787, simple_loss=0.267, pruned_loss=0.04516, over 7144.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2555, pruned_loss=0.03841, over 1426203.90 frames.], batch size: 20, lr: 4.31e-04
2022-05-14 22:03:21,214 INFO [train.py:812] (3/8) Epoch 18, batch 2350, loss[loss=0.2169, simple_loss=0.3143, pruned_loss=0.05972, over 7174.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2554, pruned_loss=0.03813, over 1425951.20 frames.], batch size: 26, lr: 4.31e-04
2022-05-14 22:04:20,401 INFO [train.py:812] (3/8) Epoch 18, batch 2400, loss[loss=0.1899, simple_loss=0.28, pruned_loss=0.0499, over 6360.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03845, over 1425095.24 frames.], batch size: 37, lr: 4.31e-04
2022-05-14 22:05:18,776 INFO [train.py:812] (3/8) Epoch 18, batch 2450, loss[loss=0.1379, simple_loss=0.232, pruned_loss=0.02185, over 7148.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2552, pruned_loss=0.03785, over 1426223.45 frames.], batch size: 19, lr: 4.31e-04
2022-05-14 22:06:16,636 INFO [train.py:812] (3/8) Epoch 18, batch 2500, loss[loss=0.1705, simple_loss=0.2713, pruned_loss=0.03487, over 7119.00 frames.], tot_loss[loss=0.1663, simple_loss=0.256, pruned_loss=0.03833, over 1418583.18 frames.], batch size: 21, lr: 4.31e-04
2022-05-14 22:07:15,269 INFO [train.py:812] (3/8) Epoch 18, batch 2550, loss[loss=0.1659, simple_loss=0.2629, pruned_loss=0.03447, over 7323.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2553, pruned_loss=0.03816, over 1419343.36 frames.], batch size: 21, lr: 4.31e-04
2022-05-14 22:08:14,633 INFO [train.py:812] (3/8) Epoch 18, batch 2600, loss[loss=0.1317, simple_loss=0.2079, pruned_loss=0.02774, over 6815.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2553, pruned_loss=0.03814, over 1418700.25 frames.], batch size: 15, lr: 4.31e-04
2022-05-14 22:09:14,624 INFO [train.py:812] (3/8) Epoch 18, batch 2650, loss[loss=0.1598, simple_loss=0.2474, pruned_loss=0.03611, over 7363.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03781, over 1419275.78 frames.], batch size: 19, lr: 4.31e-04
2022-05-14 22:10:13,359 INFO [train.py:812] (3/8) Epoch 18, batch 2700, loss[loss=0.1628, simple_loss=0.2371, pruned_loss=0.04422, over 7272.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2537, pruned_loss=0.03782, over 1419311.77 frames.], batch size: 18, lr: 4.30e-04
2022-05-14 22:11:12,898 INFO [train.py:812] (3/8) Epoch 18, batch 2750, loss[loss=0.1783, simple_loss=0.2643, pruned_loss=0.04614, over 7149.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2539, pruned_loss=0.03799, over 1416879.16 frames.], batch size: 20, lr: 4.30e-04
2022-05-14 22:12:10,443 INFO [train.py:812] (3/8) Epoch 18, batch 2800, loss[loss=0.1457, simple_loss=0.2442, pruned_loss=0.02355, over 7318.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2531, pruned_loss=0.03782, over 1416371.23 frames.], batch size: 21, lr: 4.30e-04
2022-05-14 22:13:09,212 INFO [train.py:812] (3/8) Epoch 18, batch 2850, loss[loss=0.1797, simple_loss=0.2701, pruned_loss=0.04464, over 7308.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2529, pruned_loss=0.03729, over 1419418.81 frames.], batch size: 25, lr: 4.30e-04
2022-05-14 22:14:17,875 INFO [train.py:812] (3/8) Epoch 18, batch 2900, loss[loss=0.1916, simple_loss=0.2897, pruned_loss=0.04676, over 7187.00 frames.], tot_loss[loss=0.165, simple_loss=0.2539, pruned_loss=0.03809, over 1421765.89 frames.], batch size: 22, lr: 4.30e-04
2022-05-14 22:15:17,305 INFO [train.py:812] (3/8) Epoch 18, batch 2950, loss[loss=0.1869, simple_loss=0.2853, pruned_loss=0.04419, over 6398.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2541, pruned_loss=0.03822, over 1418739.57 frames.], batch size: 38, lr: 4.30e-04
2022-05-14 22:16:16,199 INFO [train.py:812] (3/8) Epoch 18, batch 3000, loss[loss=0.1868, simple_loss=0.2697, pruned_loss=0.05194, over 7299.00 frames.], tot_loss[loss=0.1647, simple_loss=0.254, pruned_loss=0.03769, over 1417729.17 frames.], batch size: 25, lr: 4.30e-04
2022-05-14 22:16:16,200 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 22:16:23,834 INFO [train.py:841] (3/8) Epoch 18, validation: loss=0.153, simple_loss=0.2523, pruned_loss=0.02686, over 698248.00 frames.
2022-05-14 22:17:22,908 INFO [train.py:812] (3/8) Epoch 18, batch 3050, loss[loss=0.1932, simple_loss=0.2876, pruned_loss=0.04938, over 7123.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2544, pruned_loss=0.03813, over 1417547.35 frames.], batch size: 21, lr: 4.29e-04
2022-05-14 22:18:21,080 INFO [train.py:812] (3/8) Epoch 18, batch 3100, loss[loss=0.1423, simple_loss=0.2296, pruned_loss=0.02749, over 7233.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2542, pruned_loss=0.03809, over 1419362.25 frames.], batch size: 20, lr: 4.29e-04
2022-05-14 22:19:19,566 INFO [train.py:812] (3/8) Epoch 18, batch 3150, loss[loss=0.1646, simple_loss=0.2495, pruned_loss=0.03982, over 7253.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2542, pruned_loss=0.03823, over 1421361.33 frames.], batch size: 19, lr: 4.29e-04
2022-05-14 22:20:18,606 INFO [train.py:812] (3/8) Epoch 18, batch 3200, loss[loss=0.1937, simple_loss=0.2891, pruned_loss=0.04921, over 6800.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2543, pruned_loss=0.0382, over 1419338.16 frames.], batch size: 31, lr: 4.29e-04
2022-05-14 22:21:17,361 INFO [train.py:812] (3/8) Epoch 18, batch 3250, loss[loss=0.1666, simple_loss=0.2619, pruned_loss=0.03562, over 7381.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2538, pruned_loss=0.03774, over 1422010.24 frames.], batch size: 23, lr: 4.29e-04
2022-05-14 22:22:16,089 INFO [train.py:812] (3/8) Epoch 18, batch 3300, loss[loss=0.1385, simple_loss=0.2309, pruned_loss=0.02305, over 7150.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2531, pruned_loss=0.03705, over 1425908.85 frames.], batch size: 18, lr: 4.29e-04
2022-05-14 22:23:15,275 INFO [train.py:812] (3/8) Epoch 18, batch 3350, loss[loss=0.1546, simple_loss=0.2395, pruned_loss=0.03481, over 7406.00 frames.], tot_loss[loss=0.164, simple_loss=0.2538, pruned_loss=0.03708, over 1425984.21 frames.], batch size: 18, lr: 4.29e-04
2022-05-14 22:24:13,567 INFO [train.py:812] (3/8) Epoch 18, batch 3400, loss[loss=0.1905, simple_loss=0.2808, pruned_loss=0.05011, over 7375.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2536, pruned_loss=0.03742, over 1429421.79 frames.], batch size: 23, lr: 4.29e-04
2022-05-14 22:25:13,419 INFO [train.py:812] (3/8) Epoch 18, batch 3450, loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02876, over 7411.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2541, pruned_loss=0.03745, over 1430388.13 frames.], batch size: 18, lr: 4.28e-04
2022-05-14 22:26:12,106 INFO [train.py:812] (3/8) Epoch 18, batch 3500, loss[loss=0.2088, simple_loss=0.2937, pruned_loss=0.06196, over 6376.00 frames.], tot_loss[loss=0.1655, simple_loss=0.255, pruned_loss=0.03796, over 1432783.08 frames.], batch size: 38, lr: 4.28e-04
2022-05-14 22:27:09,543 INFO [train.py:812] (3/8) Epoch 18, batch 3550, loss[loss=0.1817, simple_loss=0.2681, pruned_loss=0.04769, over 7191.00 frames.], tot_loss[loss=0.166, simple_loss=0.2553, pruned_loss=0.03832, over 1431303.72 frames.], batch size: 23, lr: 4.28e-04
2022-05-14 22:28:09,169 INFO [train.py:812] (3/8) Epoch 18, batch 3600, loss[loss=0.1885, simple_loss=0.2811, pruned_loss=0.04798, over 7217.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2554, pruned_loss=0.03802, over 1432384.12 frames.], batch size: 21, lr: 4.28e-04
2022-05-14 22:29:08,000 INFO [train.py:812] (3/8) Epoch 18, batch 3650, loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02897, over 7337.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2553, pruned_loss=0.03803, over 1424533.74 frames.], batch size: 22, lr: 4.28e-04
2022-05-14 22:30:06,372 INFO [train.py:812] (3/8) Epoch 18, batch 3700, loss[loss=0.1591, simple_loss=0.2384, pruned_loss=0.03989, over 7011.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2556, pruned_loss=0.03813, over 1425924.18 frames.], batch size: 16, lr: 4.28e-04
2022-05-14 22:31:03,773 INFO [train.py:812] (3/8) Epoch 18, batch 3750, loss[loss=0.1786, simple_loss=0.2664, pruned_loss=0.04543, over 7294.00 frames.], tot_loss[loss=0.166, simple_loss=0.2561, pruned_loss=0.03797, over 1428223.26 frames.], batch size: 25, lr: 4.28e-04
2022-05-14 22:32:02,174 INFO [train.py:812] (3/8) Epoch 18, batch 3800, loss[loss=0.1846, simple_loss=0.2794, pruned_loss=0.04492, over 7349.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2553, pruned_loss=0.03749, over 1427374.62 frames.], batch size: 19, lr: 4.28e-04
2022-05-14 22:33:01,935 INFO [train.py:812] (3/8) Epoch 18, batch 3850, loss[loss=0.1504, simple_loss=0.2417, pruned_loss=0.02949, over 7400.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2545, pruned_loss=0.03723, over 1425677.87 frames.], batch size: 18, lr: 4.27e-04
2022-05-14 22:34:00,991 INFO [train.py:812] (3/8) Epoch 18, batch 3900, loss[loss=0.2286, simple_loss=0.304, pruned_loss=0.07663, over 7112.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2546, pruned_loss=0.03774, over 1421962.68 frames.], batch size: 21, lr: 4.27e-04
2022-05-14 22:35:00,678 INFO [train.py:812] (3/8) Epoch 18, batch 3950, loss[loss=0.1681, simple_loss=0.2576, pruned_loss=0.03927, over 7056.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2536, pruned_loss=0.03756, over 1423428.58 frames.], batch size: 28, lr: 4.27e-04
2022-05-14 22:35:58,134 INFO [train.py:812] (3/8) Epoch 18, batch 4000, loss[loss=0.1328, simple_loss=0.2158, pruned_loss=0.02492, over 7238.00 frames.], tot_loss[loss=0.164, simple_loss=0.2535, pruned_loss=0.0373, over 1424113.45 frames.], batch size: 16, lr: 4.27e-04
2022-05-14 22:36:56,550 INFO [train.py:812] (3/8) Epoch 18, batch 4050, loss[loss=0.1874, simple_loss=0.2726, pruned_loss=0.05115, over 6996.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2542, pruned_loss=0.0376, over 1427345.84 frames.], batch size: 28, lr: 4.27e-04
2022-05-14 22:37:55,338 INFO [train.py:812] (3/8) Epoch 18, batch 4100, loss[loss=0.1844, simple_loss=0.2652, pruned_loss=0.05178, over 7142.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2541, pruned_loss=0.03783, over 1423200.17 frames.], batch size: 20, lr: 4.27e-04
2022-05-14 22:38:54,560 INFO [train.py:812] (3/8) Epoch 18, batch 4150, loss[loss=0.1516, simple_loss=0.2381, pruned_loss=0.03257, over 7341.00 frames.], tot_loss[loss=0.165, simple_loss=0.2544, pruned_loss=0.03779, over 1422027.88 frames.], batch size: 20, lr: 4.27e-04
2022-05-14 22:39:53,847 INFO [train.py:812] (3/8) Epoch 18, batch 4200, loss[loss=0.1388, simple_loss=0.2281, pruned_loss=0.02477, over 6993.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2537, pruned_loss=0.03747, over 1421929.58 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:40:53,074 INFO [train.py:812] (3/8) Epoch 18, batch 4250, loss[loss=0.1696, simple_loss=0.2646, pruned_loss=0.03729, over 6845.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2539, pruned_loss=0.03785, over 1416882.00 frames.], batch size: 31, lr: 4.26e-04
2022-05-14 22:41:52,046 INFO [train.py:812] (3/8) Epoch 18, batch 4300, loss[loss=0.1466, simple_loss=0.2208, pruned_loss=0.03619, over 7019.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2528, pruned_loss=0.03764, over 1417920.05 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:42:51,532 INFO [train.py:812] (3/8) Epoch 18, batch 4350, loss[loss=0.1703, simple_loss=0.2669, pruned_loss=0.03687, over 7223.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2533, pruned_loss=0.0382, over 1406429.39 frames.], batch size: 21, lr: 4.26e-04
2022-05-14 22:43:50,335 INFO [train.py:812] (3/8) Epoch 18, batch 4400, loss[loss=0.1418, simple_loss=0.2297, pruned_loss=0.02699, over 7061.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2545, pruned_loss=0.03848, over 1401603.86 frames.], batch size: 18, lr: 4.26e-04
2022-05-14 22:44:47,949 INFO [train.py:812] (3/8) Epoch 18, batch 4450, loss[loss=0.1765, simple_loss=0.271, pruned_loss=0.04103, over 6355.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2563, pruned_loss=0.039, over 1393654.07 frames.], batch size: 37, lr: 4.26e-04
2022-05-14 22:45:55,940 INFO [train.py:812] (3/8) Epoch 18, batch 4500, loss[loss=0.146, simple_loss=0.2219, pruned_loss=0.03499, over 7012.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2566, pruned_loss=0.03889, over 1382232.57 frames.], batch size: 16, lr: 4.26e-04
2022-05-14 22:46:55,058 INFO [train.py:812] (3/8) Epoch 18, batch 4550, loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02904, over 7155.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2555, pruned_loss=0.03852, over 1371534.84 frames.], batch size: 19, lr: 4.26e-04
2022-05-14 22:48:10,079 INFO [train.py:812] (3/8) Epoch 19, batch 0, loss[loss=0.1756, simple_loss=0.2672, pruned_loss=0.04198, over 7285.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2672, pruned_loss=0.04198, over 7285.00 frames.], batch size: 25, lr: 4.15e-04
2022-05-14 22:49:27,402 INFO [train.py:812] (3/8) Epoch 19, batch 50, loss[loss=0.162, simple_loss=0.2572, pruned_loss=0.03342, over 7342.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2545, pruned_loss=0.03714, over 325119.20 frames.], batch size: 22, lr: 4.15e-04
2022-05-14 22:50:35,548 INFO [train.py:812] (3/8) Epoch 19, batch 100, loss[loss=0.1844, simple_loss=0.276, pruned_loss=0.04642, over 7348.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2539, pruned_loss=0.03675, over 575182.50 frames.], batch size: 22, lr: 4.14e-04
2022-05-14 22:51:34,800 INFO [train.py:812] (3/8) Epoch 19, batch 150, loss[loss=0.1821, simple_loss=0.2848, pruned_loss=0.03975, over 7211.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2535, pruned_loss=0.03701, over 764273.09 frames.], batch size: 21, lr: 4.14e-04
2022-05-14 22:53:02,387 INFO [train.py:812] (3/8) Epoch 19, batch 200, loss[loss=0.1379, simple_loss=0.2271, pruned_loss=0.02439, over 7291.00 frames.], tot_loss[loss=0.1629, simple_loss=0.253, pruned_loss=0.03644, over 910367.38 frames.], batch size: 17, lr: 4.14e-04
2022-05-14 22:54:01,870 INFO [train.py:812] (3/8) Epoch 19, batch 250, loss[loss=0.1702, simple_loss=0.2602, pruned_loss=0.04014, over 6796.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2526, pruned_loss=0.0368, over 1025819.17 frames.], batch size: 31, lr: 4.14e-04
2022-05-14 22:55:01,082 INFO [train.py:812] (3/8) Epoch 19, batch 300, loss[loss=0.1591, simple_loss=0.2453, pruned_loss=0.03649, over 7237.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2522, pruned_loss=0.03682, over 1115574.70 frames.], batch size: 20, lr: 4.14e-04
2022-05-14 22:56:00,982 INFO [train.py:812] (3/8) Epoch 19, batch 350, loss[loss=0.1728, simple_loss=0.2708, pruned_loss=0.03736, over 6721.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2514, pruned_loss=0.03665, over 1182319.32 frames.], batch size: 31, lr: 4.14e-04
2022-05-14 22:56:59,177 INFO [train.py:812] (3/8) Epoch 19, batch 400, loss[loss=0.1348, simple_loss=0.2174, pruned_loss=0.02612, over 7064.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2525, pruned_loss=0.03691, over 1234299.15 frames.], batch size: 18, lr: 4.14e-04
2022-05-14 22:57:58,724 INFO [train.py:812] (3/8) Epoch 19, batch 450, loss[loss=0.1661, simple_loss=0.2722, pruned_loss=0.03, over 7338.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2532, pruned_loss=0.03724, over 1276357.92 frames.], batch size: 22, lr: 4.14e-04
2022-05-14 22:58:57,676 INFO [train.py:812] (3/8) Epoch 19, batch 500, loss[loss=0.144, simple_loss=0.2293, pruned_loss=0.02935, over 7129.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2536, pruned_loss=0.03736, over 1306842.96 frames.], batch size: 17, lr: 4.13e-04
2022-05-14 22:59:57,484 INFO [train.py:812] (3/8) Epoch 19, batch 550, loss[loss=0.1565, simple_loss=0.2347, pruned_loss=0.03917, over 7266.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2532, pruned_loss=0.03716, over 1336300.81 frames.], batch size: 17, lr: 4.13e-04
2022-05-14 23:00:56,149 INFO [train.py:812] (3/8) Epoch 19, batch 600, loss[loss=0.1454, simple_loss=0.2307, pruned_loss=0.03001, over 7267.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2532, pruned_loss=0.03703, over 1356946.76 frames.], batch size: 18, lr: 4.13e-04
2022-05-14 23:01:55,595 INFO [train.py:812] (3/8) Epoch 19, batch 650, loss[loss=0.1557, simple_loss=0.2482, pruned_loss=0.03158, over 7114.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2524, pruned_loss=0.03654, over 1376687.64 frames.], batch size: 21, lr: 4.13e-04
2022-05-14 23:02:54,269 INFO [train.py:812] (3/8) Epoch 19, batch 700, loss[loss=0.1999, simple_loss=0.2834, pruned_loss=0.05822, over 4835.00 frames.], tot_loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03676, over 1386217.02 frames.], batch size: 52, lr: 4.13e-04
2022-05-14 23:03:53,342 INFO [train.py:812] (3/8) Epoch 19, batch 750, loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02863, over 7147.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2524, pruned_loss=0.03665, over 1394843.62 frames.], batch size: 19, lr: 4.13e-04
2022-05-14 23:04:52,297 INFO [train.py:812] (3/8) Epoch 19, batch 800, loss[loss=0.1692, simple_loss=0.258, pruned_loss=0.0402, over 6634.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2532, pruned_loss=0.03684, over 1397616.23 frames.], batch size: 31, lr: 4.13e-04
2022-05-14 23:05:50,873 INFO [train.py:812] (3/8) Epoch 19, batch 850, loss[loss=0.1474, simple_loss=0.2276, pruned_loss=0.03364, over 7069.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2541, pruned_loss=0.03701, over 1405290.93 frames.], batch size: 18, lr: 4.13e-04
2022-05-14 23:06:49,951 INFO [train.py:812] (3/8) Epoch 19, batch 900, loss[loss=0.1992, simple_loss=0.27, pruned_loss=0.06419, over 6853.00 frames.], tot_loss[loss=0.164, simple_loss=0.2543, pruned_loss=0.03681, over 1410517.82 frames.], batch size: 15, lr: 4.12e-04
2022-05-14 23:07:49,372 INFO [train.py:812] (3/8) Epoch 19, batch 950, loss[loss=0.1871, simple_loss=0.2737, pruned_loss=0.0503, over 7392.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2542, pruned_loss=0.03678, over 1412929.24 frames.], batch size: 23, lr: 4.12e-04
2022-05-14 23:08:48,635 INFO [train.py:812] (3/8) Epoch 19, batch 1000, loss[loss=0.1464, simple_loss=0.2417, pruned_loss=0.02557, over 7145.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2546, pruned_loss=0.03686, over 1420220.78 frames.], batch size: 20, lr: 4.12e-04
2022-05-14 23:09:47,742 INFO [train.py:812] (3/8) Epoch 19, batch 1050, loss[loss=0.1769, simple_loss=0.2779, pruned_loss=0.03797, over 7307.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2538, pruned_loss=0.03676, over 1417438.83 frames.], batch size: 25, lr: 4.12e-04
2022-05-14 23:10:45,902 INFO [train.py:812] (3/8) Epoch 19, batch 1100, loss[loss=0.1462, simple_loss=0.2382, pruned_loss=0.02714, over 7341.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2527, pruned_loss=0.0366, over 1418592.80 frames.], batch size: 20, lr: 4.12e-04
2022-05-14 23:11:43,621 INFO [train.py:812] (3/8) Epoch 19, batch 1150, loss[loss=0.1731, simple_loss=0.2652, pruned_loss=0.04048, over 7306.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2533, pruned_loss=0.03703, over 1419640.32 frames.], batch size: 24, lr: 4.12e-04
2022-05-14 23:12:42,320 INFO [train.py:812] (3/8) Epoch 19, batch 1200, loss[loss=0.1903, simple_loss=0.2632, pruned_loss=0.05874, over 4976.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2534, pruned_loss=0.03742, over 1413153.00 frames.], batch size: 52, lr: 4.12e-04
2022-05-14 23:13:40,372 INFO [train.py:812] (3/8) Epoch 19, batch 1250, loss[loss=0.1527, simple_loss=0.2579, pruned_loss=0.02374, over 7120.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2528, pruned_loss=0.03738, over 1414814.21 frames.], batch size: 21, lr: 4.12e-04
2022-05-14 23:14:39,564 INFO [train.py:812] (3/8) Epoch 19, batch 1300, loss[loss=0.1328, simple_loss=0.224, pruned_loss=0.02075, over 7157.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2543, pruned_loss=0.03776, over 1415960.04 frames.], batch size: 19, lr: 4.12e-04
2022-05-14 23:15:38,859 INFO [train.py:812] (3/8) Epoch 19, batch 1350, loss[loss=0.2023, simple_loss=0.2924, pruned_loss=0.05613, over 7060.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2554, pruned_loss=0.03788, over 1413758.14 frames.], batch size: 28, lr: 4.11e-04
2022-05-14 23:16:38,068 INFO [train.py:812] (3/8) Epoch 19, batch 1400, loss[loss=0.1535, simple_loss=0.2401, pruned_loss=0.0335, over 7075.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2539, pruned_loss=0.03746, over 1412014.56 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:17:42,352 INFO [train.py:812] (3/8) Epoch 19, batch 1450, loss[loss=0.172, simple_loss=0.2626, pruned_loss=0.04071, over 7308.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2526, pruned_loss=0.03676, over 1418666.51 frames.], batch size: 21, lr: 4.11e-04
2022-05-14 23:18:41,290 INFO [train.py:812] (3/8) Epoch 19, batch 1500, loss[loss=0.1717, simple_loss=0.2557, pruned_loss=0.04381, over 7259.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03692, over 1421962.94 frames.], batch size: 19, lr: 4.11e-04
2022-05-14 23:19:40,443 INFO [train.py:812] (3/8) Epoch 19, batch 1550, loss[loss=0.1552, simple_loss=0.2437, pruned_loss=0.03335, over 7414.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2528, pruned_loss=0.03678, over 1425203.00 frames.], batch size: 21, lr: 4.11e-04
2022-05-14 23:20:39,977 INFO [train.py:812] (3/8) Epoch 19, batch 1600, loss[loss=0.1893, simple_loss=0.2804, pruned_loss=0.04913, over 7207.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2533, pruned_loss=0.03759, over 1424071.09 frames.], batch size: 22, lr: 4.11e-04
2022-05-14 23:21:39,519 INFO [train.py:812] (3/8) Epoch 19, batch 1650, loss[loss=0.1606, simple_loss=0.2468, pruned_loss=0.03721, over 7165.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2539, pruned_loss=0.03815, over 1423178.32 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:22:38,860 INFO [train.py:812] (3/8) Epoch 19, batch 1700, loss[loss=0.1332, simple_loss=0.2219, pruned_loss=0.02225, over 7158.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2543, pruned_loss=0.03791, over 1423374.98 frames.], batch size: 18, lr: 4.11e-04
2022-05-14 23:23:37,792 INFO [train.py:812] (3/8) Epoch 19, batch 1750, loss[loss=0.1758, simple_loss=0.2664, pruned_loss=0.04263, over 7143.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2551, pruned_loss=0.03816, over 1416232.56 frames.], batch size: 20, lr: 4.10e-04
2022-05-14 23:24:36,351 INFO [train.py:812] (3/8) Epoch 19, batch 1800, loss[loss=0.1602, simple_loss=0.2552, pruned_loss=0.03254, over 7255.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2561, pruned_loss=0.0381, over 1417165.01 frames.], batch size: 19, lr: 4.10e-04
2022-05-14 23:25:35,792 INFO [train.py:812] (3/8) Epoch 19, batch 1850, loss[loss=0.1723, simple_loss=0.2721, pruned_loss=0.03623, over 7320.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2556, pruned_loss=0.03759, over 1422908.37 frames.], batch size: 24, lr: 4.10e-04
2022-05-14 23:26:34,569 INFO [train.py:812] (3/8) Epoch 19, batch 1900, loss[loss=0.1741, simple_loss=0.2642, pruned_loss=0.04202, over 7032.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2556, pruned_loss=0.03784, over 1419659.96 frames.], batch size: 28, lr: 4.10e-04
2022-05-14 23:27:34,107 INFO [train.py:812] (3/8) Epoch 19, batch 1950, loss[loss=0.1366, simple_loss=0.2129, pruned_loss=0.03015, over 7450.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2551, pruned_loss=0.03775, over 1420970.26 frames.], batch size: 17, lr: 4.10e-04
2022-05-14 23:28:32,902 INFO [train.py:812] (3/8) Epoch 19, batch 2000, loss[loss=0.1639, simple_loss=0.2569, pruned_loss=0.03544, over 7147.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2548, pruned_loss=0.03767, over 1424594.08 frames.], batch size: 20, lr: 4.10e-04
2022-05-14 23:29:32,680 INFO [train.py:812] (3/8) Epoch 19, batch 2050, loss[loss=0.1568, simple_loss=0.25, pruned_loss=0.03184, over 7294.00 frames.], tot_loss[loss=0.1644, simple_loss=0.254, pruned_loss=0.03733, over 1424716.97 frames.], batch size: 25, lr: 4.10e-04
2022-05-14 23:30:30,650 INFO [train.py:812] (3/8) Epoch 19, batch 2100, loss[loss=0.169, simple_loss=0.2548, pruned_loss=0.04155, over 7160.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2542, pruned_loss=0.03704, over 1425190.83 frames.], batch size: 19, lr: 4.10e-04
2022-05-14 23:31:30,648 INFO [train.py:812] (3/8) Epoch 19, batch 2150, loss[loss=0.1572, simple_loss=0.2518, pruned_loss=0.03133, over 7214.00 frames.], tot_loss[loss=0.163, simple_loss=0.2529, pruned_loss=0.03654, over 1421929.59 frames.], batch size: 21, lr: 4.09e-04
2022-05-14 23:32:29,957 INFO [train.py:812] (3/8) Epoch 19, batch 2200, loss[loss=0.1725, simple_loss=0.2716, pruned_loss=0.03671, over 7104.00 frames.], tot_loss[loss=0.162, simple_loss=0.2521, pruned_loss=0.03595, over 1426021.95 frames.], batch size: 21, lr: 4.09e-04
2022-05-14 23:33:29,285 INFO [train.py:812] (3/8) Epoch 19, batch 2250, loss[loss=0.1921, simple_loss=0.285, pruned_loss=0.04959, over 6444.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2534, pruned_loss=0.03651, over 1424626.39 frames.], batch size: 38, lr: 4.09e-04
2022-05-14 23:34:27,801 INFO [train.py:812] (3/8) Epoch 19, batch 2300, loss[loss=0.1834, simple_loss=0.2747, pruned_loss=0.04605, over 7354.00 frames.], tot_loss[loss=0.1628, simple_loss=0.253, pruned_loss=0.03628, over 1425943.04 frames.], batch size: 23, lr: 4.09e-04
2022-05-14 23:35:25,960 INFO [train.py:812] (3/8) Epoch 19, batch 2350, loss[loss=0.1425, simple_loss=0.2246, pruned_loss=0.03015, over 7271.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2525, pruned_loss=0.03608, over 1423569.03 frames.], batch size: 17, lr: 4.09e-04
2022-05-14 23:36:25,342 INFO [train.py:812] (3/8) Epoch 19, batch 2400, loss[loss=0.175, simple_loss=0.2605, pruned_loss=0.04477, over 7153.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2536, pruned_loss=0.03695, over 1420309.52 frames.], batch size: 20, lr: 4.09e-04
2022-05-14 23:37:24,203 INFO [train.py:812] (3/8) Epoch 19, batch 2450, loss[loss=0.173, simple_loss=0.2675, pruned_loss=0.03922, over 7139.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2524, pruned_loss=0.03642, over 1422818.07 frames.], batch size: 20, lr: 4.09e-04
2022-05-14 23:38:23,509 INFO [train.py:812] (3/8) Epoch 19, batch 2500, loss[loss=0.1846, simple_loss=0.2733, pruned_loss=0.04793, over 7190.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2527, pruned_loss=0.03675, over 1421832.64 frames.], batch size: 26, lr: 4.09e-04
2022-05-14 23:39:22,980 INFO [train.py:812] (3/8) Epoch 19, batch 2550, loss[loss=0.1814, simple_loss=0.2798, pruned_loss=0.04144, over 7311.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03696, over 1421381.42 frames.], batch size: 24, lr: 4.08e-04
2022-05-14 23:40:21,741 INFO [train.py:812] (3/8) Epoch 19, batch 2600, loss[loss=0.1591, simple_loss=0.2398, pruned_loss=0.03918, over 6992.00 frames.], tot_loss[loss=0.165, simple_loss=0.2549, pruned_loss=0.03758, over 1424940.04 frames.], batch size: 16, lr: 4.08e-04
2022-05-14 23:41:20,964 INFO [train.py:812] (3/8) Epoch 19, batch 2650, loss[loss=0.188, simple_loss=0.266, pruned_loss=0.05505, over 7282.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2547, pruned_loss=0.03732, over 1426794.61 frames.], batch size: 24, lr: 4.08e-04
2022-05-14 23:42:20,837 INFO [train.py:812] (3/8) Epoch 19, batch 2700, loss[loss=0.1716, simple_loss=0.2661, pruned_loss=0.03853, over 7286.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2542, pruned_loss=0.03702, over 1430118.15 frames.], batch size: 25, lr: 4.08e-04
2022-05-14 23:43:20,346 INFO [train.py:812] (3/8) Epoch 19, batch 2750, loss[loss=0.1685, simple_loss=0.2642, pruned_loss=0.0364, over 7417.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2545, pruned_loss=0.03711, over 1429384.45 frames.], batch size: 21, lr: 4.08e-04
2022-05-14 23:44:19,811 INFO [train.py:812] (3/8) Epoch 19, batch 2800, loss[loss=0.1569, simple_loss=0.2557, pruned_loss=0.02908, over 7069.00 frames.], tot_loss[loss=0.164, simple_loss=0.2542, pruned_loss=0.03689, over 1430133.53 frames.], batch size: 18, lr: 4.08e-04
2022-05-14 23:45:18,635 INFO [train.py:812] (3/8) Epoch 19, batch 2850, loss[loss=0.1481, simple_loss=0.2541, pruned_loss=0.02102, over 7163.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03654, over 1427158.65 frames.], batch size: 19, lr: 4.08e-04
2022-05-14 23:46:17,147 INFO [train.py:812] (3/8) Epoch 19, batch 2900, loss[loss=0.1659, simple_loss=0.2525, pruned_loss=0.03965, over 7145.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03609, over 1424041.20 frames.], batch size: 26, lr: 4.08e-04
2022-05-14 23:47:15,890 INFO [train.py:812] (3/8) Epoch 19, batch 2950, loss[loss=0.1446, simple_loss=0.2192, pruned_loss=0.03505, over 7264.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2534, pruned_loss=0.03639, over 1429958.72 frames.], batch size: 17, lr: 4.08e-04
2022-05-14 23:48:15,115 INFO [train.py:812] (3/8) Epoch 19, batch 3000, loss[loss=0.2382, simple_loss=0.3061, pruned_loss=0.08511, over 5174.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2532, pruned_loss=0.03659, over 1429709.19 frames.], batch size: 52, lr: 4.07e-04
2022-05-14 23:48:15,115 INFO [train.py:832] (3/8) Computing validation loss
2022-05-14 23:48:22,685 INFO [train.py:841] (3/8) Epoch 19, validation: loss=0.1531, simple_loss=0.2523, pruned_loss=0.02694, over 698248.00 frames.
2022-05-14 23:49:22,391 INFO [train.py:812] (3/8) Epoch 19, batch 3050, loss[loss=0.1875, simple_loss=0.287, pruned_loss=0.04404, over 7181.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2538, pruned_loss=0.0366, over 1431245.90 frames.], batch size: 23, lr: 4.07e-04
2022-05-14 23:50:21,358 INFO [train.py:812] (3/8) Epoch 19, batch 3100, loss[loss=0.1772, simple_loss=0.2718, pruned_loss=0.04133, over 6375.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2541, pruned_loss=0.03672, over 1432083.87 frames.], batch size: 38, lr: 4.07e-04
2022-05-14 23:51:20,039 INFO [train.py:812] (3/8) Epoch 19, batch 3150, loss[loss=0.1394, simple_loss=0.2263, pruned_loss=0.02622, over 7278.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2549, pruned_loss=0.03706, over 1429026.55 frames.], batch size: 18, lr: 4.07e-04
2022-05-14 23:52:18,557 INFO [train.py:812] (3/8) Epoch 19, batch 3200, loss[loss=0.1375, simple_loss=0.2353, pruned_loss=0.01983, over 7157.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2544, pruned_loss=0.03715, over 1427260.66 frames.], batch size: 19, lr: 4.07e-04
2022-05-14 23:53:18,013 INFO [train.py:812] (3/8) Epoch 19, batch 3250, loss[loss=0.1929, simple_loss=0.279, pruned_loss=0.05339, over 7367.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2548, pruned_loss=0.03735, over 1424950.14 frames.], batch size: 19, lr: 4.07e-04
2022-05-14 23:54:16,312 INFO [train.py:812] (3/8) Epoch 19, batch 3300, loss[loss=0.1626, simple_loss=0.2481, pruned_loss=0.03854, over 6262.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2551, pruned_loss=0.03762, over 1424746.07 frames.], batch size: 37, lr: 4.07e-04
2022-05-14 23:55:15,323 INFO [train.py:812] (3/8) Epoch 19, batch 3350, loss[loss=0.1529, simple_loss=0.2379, pruned_loss=0.03399, over 7122.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2536, pruned_loss=0.03695, over 1424691.80 frames.], batch size: 21, lr: 4.07e-04
2022-05-14 23:56:14,426 INFO [train.py:812] (3/8) Epoch 19, batch 3400, loss[loss=0.1648, simple_loss=0.2508, pruned_loss=0.03943, over 7280.00 frames.], tot_loss[loss=0.164, simple_loss=0.2543, pruned_loss=0.03685, over 1425864.94 frames.], batch size: 18, lr: 4.06e-04
2022-05-14 23:57:14,016 INFO [train.py:812] (3/8) Epoch 19, batch 3450, loss[loss=0.1439, simple_loss=0.2378, pruned_loss=0.02505, over 7358.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2537, pruned_loss=0.03691, over 1421659.28 frames.], batch size: 19, lr: 4.06e-04
2022-05-14 23:58:13,020 INFO [train.py:812] (3/8) Epoch 19, batch 3500, loss[loss=0.1566, simple_loss=0.2408, pruned_loss=0.03624, over 7268.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2536, pruned_loss=0.03696, over 1423531.75 frames.], batch size: 18, lr: 4.06e-04
2022-05-14 23:59:12,612 INFO [train.py:812] (3/8) Epoch 19, batch 3550, loss[loss=0.149, simple_loss=0.2242, pruned_loss=0.03688, over 7149.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2529, pruned_loss=0.03661, over 1423941.28 frames.], batch size: 17, lr: 4.06e-04
2022-05-15 00:00:11,601 INFO [train.py:812] (3/8) Epoch 19, batch 3600, loss[loss=0.2008, simple_loss=0.2882, pruned_loss=0.05667, over 7194.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2537, pruned_loss=0.03682, over 1421555.65 frames.], batch size: 23, lr: 4.06e-04
2022-05-15 00:01:11,005 INFO [train.py:812] (3/8) Epoch 19, batch 3650, loss[loss=0.1681, simple_loss=0.252, pruned_loss=0.04212, over 7327.00 frames.], tot_loss[loss=0.1637, simple_loss=0.254, pruned_loss=0.03671, over 1414446.81 frames.], batch size: 20, lr: 4.06e-04
2022-05-15 00:02:10,016 INFO [train.py:812] (3/8) Epoch 19, batch 3700, loss[loss=0.1902, simple_loss=0.2734, pruned_loss=0.05352, over 7413.00 frames.], tot_loss[loss=0.1647, simple_loss=0.255, pruned_loss=0.03719, over 1415911.46 frames.], batch size: 21, lr: 4.06e-04
2022-05-15 00:03:09,354 INFO [train.py:812] (3/8) Epoch 19, batch 3750, loss[loss=0.171, simple_loss=0.2674, pruned_loss=0.03731, over 7380.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2547, pruned_loss=0.03731, over 1411839.35 frames.], batch size: 23, lr: 4.06e-04
2022-05-15 00:04:08,160 INFO [train.py:812] (3/8) Epoch 19, batch 3800, loss[loss=0.1799, simple_loss=0.2584, pruned_loss=0.05073, over 7361.00 frames.], tot_loss[loss=0.1649, simple_loss=0.255, pruned_loss=0.03741, over 1417766.74 frames.], batch size: 19, lr: 4.06e-04
2022-05-15 00:05:06,746 INFO [train.py:812] (3/8) Epoch 19, batch 3850, loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03251, over 7176.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2548, pruned_loss=0.03745, over 1415752.93 frames.], batch size: 18, lr: 4.05e-04
2022-05-15 00:06:04,369 INFO [train.py:812] (3/8) Epoch 19, batch 3900, loss[loss=0.1707, simple_loss=0.2686, pruned_loss=0.03641, over 7121.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2561, pruned_loss=0.03787, over 1413599.68 frames.], batch size: 21, lr: 4.05e-04
2022-05-15 00:07:04,139 INFO [train.py:812] (3/8) Epoch 19, batch 3950, loss[loss=0.1983, simple_loss=0.2837, pruned_loss=0.05641, over 7155.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2555, pruned_loss=0.03762, over 1416292.82 frames.], batch size: 18, lr: 4.05e-04
2022-05-15 00:08:03,271 INFO [train.py:812] (3/8) Epoch 19, batch 4000, loss[loss=0.1721, simple_loss=0.2614, pruned_loss=0.04144, over 5488.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2546, pruned_loss=0.03726, over 1417832.73 frames.], batch size: 53, lr: 4.05e-04
2022-05-15 00:09:00,791 INFO [train.py:812] (3/8) Epoch 19, batch 4050, loss[loss=0.1527, simple_loss=0.2317, pruned_loss=0.03684, over 7250.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2538, pruned_loss=0.03686, over 1416173.23 frames.], batch size: 16, lr: 4.05e-04
2022-05-15 00:09:59,473 INFO [train.py:812] (3/8) Epoch 19, batch 4100, loss[loss=0.1873, simple_loss=0.2749, pruned_loss=0.04981, over 4813.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2539, pruned_loss=0.03716, over 1416572.76 frames.], batch size: 53, lr: 4.05e-04
2022-05-15 00:10:57,143 INFO [train.py:812] (3/8) Epoch 19, batch 4150, loss[loss=0.1711, simple_loss=0.2598, pruned_loss=0.04114, over 7393.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2534, pruned_loss=0.0369, over 1421702.91 frames.], batch size: 23, lr: 4.05e-04
2022-05-15 00:11:56,833 INFO [train.py:812] (3/8) Epoch 19, batch 4200, loss[loss=0.1593, simple_loss=0.2442, pruned_loss=0.0372, over 7204.00 frames.], tot_loss[loss=0.1632, simple_loss=0.253, pruned_loss=0.03672, over 1420133.32 frames.], batch size: 23, lr: 4.05e-04
2022-05-15 00:12:56,145 INFO [train.py:812] (3/8) Epoch 19, batch 4250, loss[loss=0.1328, simple_loss=0.2224, pruned_loss=0.02161, over 6827.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2523, pruned_loss=0.03617, over 1419972.05 frames.], batch size: 15, lr: 4.04e-04
2022-05-15 00:14:05,100 INFO [train.py:812] (3/8) Epoch 19, batch 4300, loss[loss=0.1552, simple_loss=0.2487, pruned_loss=0.03086, over 7099.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.03598, over 1420033.34 frames.], batch size: 26, lr: 4.04e-04
2022-05-15 00:15:04,943 INFO [train.py:812] (3/8) Epoch 19, batch 4350, loss[loss=0.1551, simple_loss=0.2405, pruned_loss=0.03486, over 7158.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2517, pruned_loss=0.03585, over 1417291.25 frames.], batch size: 18, lr: 4.04e-04
2022-05-15 00:16:03,309 INFO [train.py:812] (3/8) Epoch 19, batch 4400, loss[loss=0.1727, simple_loss=0.2659, pruned_loss=0.03975, over 6287.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2525, pruned_loss=0.03625, over 1412771.92 frames.], batch size: 37, lr: 4.04e-04
2022-05-15 00:17:02,484 INFO [train.py:812] (3/8) Epoch 19, batch 4450, loss[loss=0.1611, simple_loss=0.245, pruned_loss=0.03858, over 6778.00 frames.], tot_loss[loss=0.1626, simple_loss=0.252, pruned_loss=0.03659, over 1407423.05 frames.], batch size: 15, lr: 4.04e-04
2022-05-15 00:18:02,035 INFO [train.py:812] (3/8) Epoch 19, batch 4500, loss[loss=0.152, simple_loss=0.2522, pruned_loss=0.02588, over 7142.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2533, pruned_loss=0.03724, over 1394443.30 frames.], batch size: 20, lr: 4.04e-04
2022-05-15 00:19:01,146 INFO [train.py:812] (3/8) Epoch 19, batch 4550, loss[loss=0.1941, simple_loss=0.2902, pruned_loss=0.049, over 6475.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2532, pruned_loss=0.03787, over 1366970.07 frames.], batch size: 38, lr: 4.04e-04
2022-05-15 00:20:09,399 INFO [train.py:812] (3/8) Epoch 20, batch 0, loss[loss=0.1472, simple_loss=0.2426, pruned_loss=0.02592, over 7365.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2426, pruned_loss=0.02592, over 7365.00 frames.], batch size: 19, lr: 3.94e-04
2022-05-15 00:21:09,542 INFO [train.py:812] (3/8) Epoch 20, batch 50, loss[loss=0.1499, simple_loss=0.2389, pruned_loss=0.03048, over 7282.00 frames.], tot_loss[loss=0.163, simple_loss=0.2553, pruned_loss=0.03536, over 320425.31 frames.], batch size: 18, lr: 3.94e-04
2022-05-15 00:22:08,905 INFO [train.py:812] (3/8) Epoch 20, batch 100, loss[loss=0.1993, simple_loss=0.2887, pruned_loss=0.05494, over 5046.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2549, pruned_loss=0.03598, over 565831.53 frames.], batch size: 54, lr: 3.94e-04
2022-05-15 00:23:08,479 INFO [train.py:812] (3/8) Epoch 20, batch 150, loss[loss=0.1575, simple_loss=0.2591, pruned_loss=0.02796, over 7312.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2562, pruned_loss=0.03654, over 755818.70 frames.], batch size: 21, lr: 3.94e-04
2022-05-15 00:24:07,822 INFO [train.py:812] (3/8) Epoch 20, batch 200, loss[loss=0.1862, simple_loss=0.2805, pruned_loss=0.04598, over 7344.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2553, pruned_loss=0.03618, over 903378.55 frames.], batch size: 22, lr: 3.93e-04
2022-05-15 00:25:08,075 INFO [train.py:812] (3/8) Epoch 20, batch 250, loss[loss=0.1526, simple_loss=0.2487, pruned_loss=0.02829, over 7334.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2543, pruned_loss=0.03603, over 1022482.91 frames.], batch size: 22, lr: 3.93e-04
2022-05-15 00:26:07,340 INFO [train.py:812] (3/8) Epoch 20, batch 300, loss[loss=0.1749, simple_loss=0.2698, pruned_loss=0.03995, over 7202.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2546, pruned_loss=0.036, over 1112062.55 frames.], batch size: 23, lr: 3.93e-04
2022-05-15 00:27:07,246 INFO [train.py:812] (3/8) Epoch 20, batch 350, loss[loss=0.1656, simple_loss=0.2593, pruned_loss=0.03601, over 7151.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2549, pruned_loss=0.03616, over 1184474.74 frames.], batch size: 20, lr: 3.93e-04
2022-05-15 00:28:05,117 INFO [train.py:812] (3/8) Epoch 20, batch 400, loss[loss=0.1778, simple_loss=0.2718, pruned_loss=0.04196, over 7158.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2545, pruned_loss=0.03614, over 1238001.23 frames.], batch size: 20, lr: 3.93e-04
2022-05-15 00:29:03,584 INFO [train.py:812] (3/8) Epoch 20, batch 450, loss[loss=0.1768, simple_loss=0.2768, pruned_loss=0.03839, over 7387.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2548, pruned_loss=0.03611, over 1276364.13 frames.], batch size: 23, lr: 3.93e-04
2022-05-15 00:30:01,853 INFO [train.py:812] (3/8) Epoch 20, batch 500, loss[loss=0.148, simple_loss=0.2427, pruned_loss=0.02669, over 7220.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2552, pruned_loss=0.03649, over 1308156.20 frames.], batch size: 21, lr: 3.93e-04
2022-05-15 00:31:00,460 INFO [train.py:812] (3/8) Epoch 20, batch 550, loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.0325, over 6732.00 frames.], tot_loss[loss=0.1632, simple_loss=0.254, pruned_loss=0.0362, over 1334495.93 frames.], batch size: 31, lr: 3.93e-04
2022-05-15 00:32:00,099 INFO [train.py:812] (3/8) Epoch 20, batch 600, loss[loss=0.1536, simple_loss=0.2386, pruned_loss=0.03427, over 7171.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2527, pruned_loss=0.03574, over 1355818.49 frames.], batch size: 18, lr: 3.93e-04
2022-05-15 00:32:59,169 INFO [train.py:812] (3/8) Epoch 20, batch 650, loss[loss=0.1601, simple_loss=0.2477, pruned_loss=0.03623, over 7170.00 frames.], tot_loss[loss=0.162, simple_loss=0.2525, pruned_loss=0.03573, over 1369709.84 frames.], batch size: 18, lr: 3.92e-04
2022-05-15 00:33:55,657 INFO [train.py:812] (3/8) Epoch 20, batch 700, loss[loss=0.1723, simple_loss=0.2678, pruned_loss=0.03839, over 7223.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2531, pruned_loss=0.03589, over 1383019.65 frames.], batch size: 20, lr: 3.92e-04
2022-05-15 00:34:54,545 INFO [train.py:812] (3/8) Epoch 20, batch 750, loss[loss=0.204, simple_loss=0.3046, pruned_loss=0.0517, over 7297.00 frames.], tot_loss[loss=0.1627, simple_loss=0.253, pruned_loss=0.03616, over 1393862.55 frames.], batch size: 25, lr: 3.92e-04
2022-05-15 00:35:51,666 INFO [train.py:812] (3/8) Epoch 20, batch 800, loss[loss=0.1521, simple_loss=0.2353, pruned_loss=0.03443, over 7404.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03603, over 1403185.82 frames.], batch size: 18, lr: 3.92e-04
2022-05-15 00:36:56,563 INFO [train.py:812] (3/8) Epoch 20, batch 850, loss[loss=0.1655, simple_loss=0.2613, pruned_loss=0.0348, over 7057.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2523, pruned_loss=0.03579, over 1410997.00 frames.], batch size: 28, lr: 3.92e-04
2022-05-15 00:37:55,360 INFO [train.py:812] (3/8) Epoch 20, batch 900, loss[loss=0.1394, simple_loss=0.2284, pruned_loss=0.02519, over 7350.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2515, pruned_loss=0.03562, over 1416491.09 frames.], batch size: 19, lr: 3.92e-04
2022-05-15 00:38:53,704 INFO [train.py:812] (3/8) Epoch 20, batch 950, loss[loss=0.1429, simple_loss=0.2399, pruned_loss=0.02291, over 7236.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2522, pruned_loss=0.03576, over 1419624.54 frames.], batch size: 20, lr: 3.92e-04
2022-05-15 00:39:52,436 INFO [train.py:812] (3/8) Epoch 20, batch 1000, loss[loss=0.2013, simple_loss=0.2984, pruned_loss=0.05205, over 7294.00 frames.], tot_loss[loss=0.162, simple_loss=0.2526, pruned_loss=0.03574, over 1420716.41 frames.], batch size: 24, lr: 3.92e-04
2022-05-15 00:40:51,838 INFO [train.py:812] (3/8) Epoch 20, batch 1050, loss[loss=0.2019, simple_loss=0.2859, pruned_loss=0.05896, over 7220.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2529, pruned_loss=0.03621, over 1419905.86 frames.], batch size: 22, lr: 3.92e-04
2022-05-15 00:41:50,551 INFO [train.py:812] (3/8) Epoch 20, batch 1100, loss[loss=0.2137, simple_loss=0.2913, pruned_loss=0.06804, over 7200.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2534, pruned_loss=0.03697, over 1415504.83 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:42:49,020 INFO [train.py:812] (3/8) Epoch 20, batch 1150, loss[loss=0.1845, simple_loss=0.2798, pruned_loss=0.04456, over 7315.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2543, pruned_loss=0.03712, over 1419971.63 frames.], batch size: 24, lr: 3.91e-04
2022-05-15 00:43:48,225 INFO [train.py:812] (3/8) Epoch 20, batch 1200, loss[loss=0.1626, simple_loss=0.2528, pruned_loss=0.03624, over 7347.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2528, pruned_loss=0.0363, over 1424822.70 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:44:47,697 INFO [train.py:812] (3/8) Epoch 20, batch 1250, loss[loss=0.1289, simple_loss=0.222, pruned_loss=0.01784, over 7151.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2526, pruned_loss=0.03627, over 1425595.71 frames.], batch size: 17, lr: 3.91e-04
2022-05-15 00:45:46,805 INFO [train.py:812] (3/8) Epoch 20, batch 1300, loss[loss=0.1733, simple_loss=0.2657, pruned_loss=0.04042, over 7124.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2517, pruned_loss=0.03602, over 1427376.46 frames.], batch size: 21, lr: 3.91e-04
2022-05-15 00:46:46,847 INFO [train.py:812] (3/8) Epoch 20, batch 1350, loss[loss=0.1797, simple_loss=0.2692, pruned_loss=0.04516, over 7211.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2533, pruned_loss=0.03671, over 1429519.41 frames.], batch size: 22, lr: 3.91e-04
2022-05-15 00:47:55,895 INFO [train.py:812] (3/8) Epoch 20, batch 1400, loss[loss=0.1724, simple_loss=0.2612, pruned_loss=0.04181, over 7184.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2533, pruned_loss=0.03663, over 1431087.93 frames.], batch size: 26, lr: 3.91e-04
2022-05-15 00:48:55,553 INFO [train.py:812] (3/8) Epoch 20, batch 1450, loss[loss=0.1743, simple_loss=0.262, pruned_loss=0.04328, over 7178.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2539, pruned_loss=0.03698, over 1429092.86 frames.], batch size: 26, lr: 3.91e-04
2022-05-15 00:49:54,736 INFO [train.py:812] (3/8) Epoch 20, batch 1500, loss[loss=0.1805, simple_loss=0.2717, pruned_loss=0.04467, over 7369.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2548, pruned_loss=0.03731, over 1427251.71 frames.], batch size: 23, lr: 3.91e-04
2022-05-15 00:51:04,074 INFO [train.py:812] (3/8) Epoch 20, batch 1550, loss[loss=0.154, simple_loss=0.2487, pruned_loss=0.02964, over 7438.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2542, pruned_loss=0.03666, over 1429980.88 frames.], batch size: 20, lr: 3.91e-04
2022-05-15 00:52:22,067 INFO [train.py:812] (3/8) Epoch 20, batch 1600, loss[loss=0.156, simple_loss=0.2514, pruned_loss=0.03031, over 7347.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2547, pruned_loss=0.03685, over 1424679.40 frames.], batch size: 22, lr: 3.90e-04
2022-05-15 00:53:19,528 INFO [train.py:812] (3/8) Epoch 20, batch 1650, loss[loss=0.1764, simple_loss=0.2705, pruned_loss=0.04114, over 7204.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2545, pruned_loss=0.03647, over 1421116.46 frames.], batch size: 23, lr: 3.90e-04
2022-05-15 00:54:36,072 INFO [train.py:812] (3/8) Epoch 20, batch 1700, loss[loss=0.1463, simple_loss=0.2401, pruned_loss=0.02625, over 7163.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2538, pruned_loss=0.03643, over 1419413.48 frames.], batch size: 19, lr: 3.90e-04
2022-05-15 00:55:43,690 INFO [train.py:812] (3/8) Epoch 20, batch 1750, loss[loss=0.1607, simple_loss=0.2508, pruned_loss=0.03532, over 7339.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2543, pruned_loss=0.03661, over 1424793.18 frames.], batch size: 22, lr: 3.90e-04
2022-05-15 00:56:42,597 INFO [train.py:812] (3/8) Epoch 20, batch 1800, loss[loss=0.1909, simple_loss=0.2854, pruned_loss=0.04823, over 7311.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2543, pruned_loss=0.0363, over 1424065.19 frames.], batch size: 25, lr: 3.90e-04
2022-05-15 00:57:42,321 INFO [train.py:812] (3/8) Epoch 20, batch 1850, loss[loss=0.1493, simple_loss=0.2331, pruned_loss=0.03271, over 7065.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2544, pruned_loss=0.03659, over 1426783.48 frames.], batch size: 18, lr: 3.90e-04
2022-05-15 00:58:41,673 INFO [train.py:812] (3/8) Epoch 20, batch 1900, loss[loss=0.1528, simple_loss=0.2334, pruned_loss=0.03608, over 7233.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2543, pruned_loss=0.03656, over 1427894.94 frames.], batch size: 20, lr: 3.90e-04
2022-05-15 00:59:40,056 INFO [train.py:812] (3/8) Epoch 20, batch 1950, loss[loss=0.1729, simple_loss=0.2577, pruned_loss=0.04404, over 6320.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2528, pruned_loss=0.03629, over 1428296.20 frames.], batch size: 37, lr: 3.90e-04
2022-05-15 01:00:37,503 INFO [train.py:812] (3/8) Epoch 20, batch 2000, loss[loss=0.1699, simple_loss=0.2587, pruned_loss=0.04051, over 7228.00 frames.], tot_loss[loss=0.162, simple_loss=0.252, pruned_loss=0.03604, over 1429189.86 frames.], batch size: 20, lr: 3.90e-04
2022-05-15 01:01:35,460 INFO [train.py:812] (3/8) Epoch 20, batch 2050, loss[loss=0.1431, simple_loss=0.2378, pruned_loss=0.02422, over 7223.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2519, pruned_loss=0.03613, over 1428800.86 frames.], batch size: 21, lr: 3.89e-04
2022-05-15 01:02:33,044 INFO [train.py:812] (3/8) Epoch 20, batch 2100, loss[loss=0.1558, simple_loss=0.2447, pruned_loss=0.03341, over 7429.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2524, pruned_loss=0.0364, over 1431293.24 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:03:30,904 INFO [train.py:812] (3/8) Epoch 20, batch 2150, loss[loss=0.2102, simple_loss=0.2823, pruned_loss=0.06904, over 7207.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2528, pruned_loss=0.03674, over 1425269.15 frames.], batch size: 22, lr: 3.89e-04
2022-05-15 01:04:30,267 INFO [train.py:812] (3/8) Epoch 20, batch 2200, loss[loss=0.1666, simple_loss=0.25, pruned_loss=0.04161, over 7241.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2516, pruned_loss=0.03607, over 1420999.13 frames.], batch size: 16, lr: 3.89e-04
2022-05-15 01:05:28,870 INFO [train.py:812] (3/8) Epoch 20, batch 2250, loss[loss=0.151, simple_loss=0.2467, pruned_loss=0.02768, over 7144.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2514, pruned_loss=0.03561, over 1423220.36 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:06:27,814 INFO [train.py:812] (3/8) Epoch 20, batch 2300, loss[loss=0.1769, simple_loss=0.272, pruned_loss=0.04095, over 7399.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2514, pruned_loss=0.03577, over 1424661.07 frames.], batch size: 23, lr: 3.89e-04
2022-05-15 01:07:25,541 INFO [train.py:812] (3/8) Epoch 20, batch 2350, loss[loss=0.167, simple_loss=0.2579, pruned_loss=0.03807, over 7314.00 frames.], tot_loss[loss=0.161, simple_loss=0.2512, pruned_loss=0.0354, over 1422342.00 frames.], batch size: 21, lr: 3.89e-04
2022-05-15 01:08:24,200 INFO [train.py:812] (3/8) Epoch 20, batch 2400, loss[loss=0.1583, simple_loss=0.2474, pruned_loss=0.03456, over 7435.00 frames.], tot_loss[loss=0.161, simple_loss=0.2511, pruned_loss=0.03546, over 1423468.61 frames.], batch size: 20, lr: 3.89e-04
2022-05-15 01:09:23,901 INFO [train.py:812] (3/8) Epoch 20, batch 2450, loss[loss=0.1749, simple_loss=0.2608, pruned_loss=0.04451, over 7056.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2504, pruned_loss=0.0354, over 1425993.58 frames.], batch size: 28, lr: 3.89e-04
2022-05-15 01:10:23,008 INFO [train.py:812] (3/8) Epoch 20, batch 2500, loss[loss=0.1758, simple_loss=0.2666, pruned_loss=0.04251, over 7193.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2501, pruned_loss=0.03564, over 1424728.20 frames.], batch size: 26, lr: 3.88e-04
2022-05-15 01:11:22,810 INFO [train.py:812] (3/8) Epoch 20, batch 2550, loss[loss=0.1702, simple_loss=0.2594, pruned_loss=0.04054, over 7340.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2512, pruned_loss=0.03576, over 1424077.34 frames.], batch size: 20, lr: 3.88e-04
2022-05-15 01:12:22,062 INFO [train.py:812] (3/8) Epoch 20, batch 2600, loss[loss=0.1694, simple_loss=0.2634, pruned_loss=0.03771, over 6742.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2522, pruned_loss=0.03612, over 1425103.51 frames.], batch size: 31, lr: 3.88e-04
2022-05-15 01:13:22,169 INFO [train.py:812] (3/8) Epoch 20, batch 2650, loss[loss=0.1458, simple_loss=0.2241, pruned_loss=0.03373, over 7007.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2518, pruned_loss=0.03607, over 1426435.02 frames.], batch size: 16, lr: 3.88e-04
2022-05-15 01:14:21,650 INFO [train.py:812] (3/8) Epoch 20, batch 2700, loss[loss=0.1656, simple_loss=0.2616, pruned_loss=0.03479, over 7379.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.03596, over 1427261.50 frames.], batch size: 23, lr: 3.88e-04
2022-05-15 01:15:21,498 INFO [train.py:812] (3/8) Epoch 20, batch 2750, loss[loss=0.1521, simple_loss=0.2457, pruned_loss=0.02928, over 7201.00 frames.], tot_loss[loss=0.162, simple_loss=0.2519, pruned_loss=0.03608, over 1425725.17 frames.], batch size: 23, lr: 3.88e-04
2022-05-15 01:16:20,979 INFO [train.py:812] (3/8) Epoch 20, batch 2800, loss[loss=0.1477, simple_loss=0.2417, pruned_loss=0.02684, over 7167.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2526, pruned_loss=0.03606, over 1430028.44 frames.], batch size: 18, lr: 3.88e-04
2022-05-15 01:17:20,825 INFO [train.py:812] (3/8) Epoch 20, batch 2850, loss[loss=0.1709, simple_loss=0.2618, pruned_loss=0.03995, over 7407.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2523, pruned_loss=0.03628, over 1432696.38 frames.], batch size: 21, lr: 3.88e-04
2022-05-15 01:18:20,011 INFO [train.py:812] (3/8) Epoch 20, batch 2900, loss[loss=0.1612, simple_loss=0.2532, pruned_loss=0.03458, over 7171.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2516, pruned_loss=0.03604, over 1428095.01 frames.], batch size: 26, lr: 3.88e-04
2022-05-15 01:19:19,614 INFO [train.py:812] (3/8) Epoch 20, batch 2950, loss[loss=0.1693, simple_loss=0.2586, pruned_loss=0.04003, over 7231.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2525, pruned_loss=0.03601, over 1431660.54 frames.], batch size: 20, lr: 3.87e-04
2022-05-15 01:20:18,527 INFO [train.py:812] (3/8) Epoch 20, batch 3000, loss[loss=0.1878, simple_loss=0.2853, pruned_loss=0.04514, over 7375.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2535, pruned_loss=0.03634, over 1430393.27 frames.], batch size: 23, lr: 3.87e-04
2022-05-15 01:20:18,528 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 01:20:27,134 INFO [train.py:841] (3/8) Epoch 20, validation: loss=0.1532, simple_loss=0.2519, pruned_loss=0.02723, over 698248.00 frames.
2022-05-15 01:21:26,365 INFO [train.py:812] (3/8) Epoch 20, batch 3050, loss[loss=0.1723, simple_loss=0.2636, pruned_loss=0.04046, over 7162.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2536, pruned_loss=0.03648, over 1431960.84 frames.], batch size: 19, lr: 3.87e-04
2022-05-15 01:22:25,321 INFO [train.py:812] (3/8) Epoch 20, batch 3100, loss[loss=0.1555, simple_loss=0.2378, pruned_loss=0.03664, over 7117.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2532, pruned_loss=0.03636, over 1430745.76 frames.], batch size: 21, lr: 3.87e-04
2022-05-15 01:23:24,547 INFO [train.py:812] (3/8) Epoch 20, batch 3150, loss[loss=0.1357, simple_loss=0.2212, pruned_loss=0.02512, over 7273.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2531, pruned_loss=0.03635, over 1431303.34 frames.], batch size: 18, lr: 3.87e-04
2022-05-15 01:24:21,333 INFO [train.py:812] (3/8) Epoch 20, batch 3200, loss[loss=0.1586, simple_loss=0.2523, pruned_loss=0.03245, over 6825.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2527, pruned_loss=0.03612, over 1431831.60 frames.], batch size: 31, lr: 3.87e-04
2022-05-15 01:25:18,745 INFO [train.py:812] (3/8) Epoch 20, batch 3250, loss[loss=0.1575, simple_loss=0.2399, pruned_loss=0.03761, over 7061.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2524, pruned_loss=0.03605, over 1428280.45 frames.], batch size: 18, lr: 3.87e-04
2022-05-15 01:26:16,474 INFO [train.py:812] (3/8) Epoch 20, batch 3300, loss[loss=0.1687, simple_loss=0.2556, pruned_loss=0.04089, over 7128.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.03585, over 1426539.68 frames.], batch size: 17, lr: 3.87e-04
2022-05-15 01:27:14,067 INFO [train.py:812] (3/8) Epoch 20, batch 3350, loss[loss=0.1776, simple_loss=0.2674, pruned_loss=0.04396, over 7151.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2514, pruned_loss=0.0354, over 1427117.15 frames.], batch size: 20, lr: 3.87e-04
2022-05-15 01:28:13,189 INFO [train.py:812] (3/8) Epoch 20, batch 3400, loss[loss=0.137, simple_loss=0.2249, pruned_loss=0.02453, over 7253.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2507, pruned_loss=0.03518, over 1426361.18 frames.], batch size: 17, lr: 3.87e-04
2022-05-15 01:29:12,303 INFO [train.py:812] (3/8) Epoch 20, batch 3450, loss[loss=0.1713, simple_loss=0.263, pruned_loss=0.0398, over 7230.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03546, over 1424989.06 frames.], batch size: 20, lr: 3.86e-04
2022-05-15 01:30:11,785 INFO [train.py:812] (3/8) Epoch 20, batch 3500, loss[loss=0.1699, simple_loss=0.2597, pruned_loss=0.04012, over 7262.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2525, pruned_loss=0.03568, over 1424010.44 frames.], batch size: 19, lr: 3.86e-04
2022-05-15 01:31:11,572 INFO [train.py:812] (3/8) Epoch 20, batch 3550, loss[loss=0.1468, simple_loss=0.2468, pruned_loss=0.0234, over 7112.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2521, pruned_loss=0.03574, over 1426603.08 frames.], batch size: 21, lr: 3.86e-04
2022-05-15 01:32:11,071 INFO [train.py:812] (3/8) Epoch 20, batch 3600, loss[loss=0.185, simple_loss=0.2745, pruned_loss=0.04774, over 7226.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2519, pruned_loss=0.03573, over 1429374.72 frames.], batch size: 23, lr: 3.86e-04
2022-05-15 01:33:11,042 INFO [train.py:812] (3/8) Epoch 20, batch 3650, loss[loss=0.1736, simple_loss=0.2706, pruned_loss=0.03827, over 7317.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2517, pruned_loss=0.03567, over 1430884.40 frames.], batch size: 21, lr: 3.86e-04
2022-05-15 01:34:09,111 INFO [train.py:812] (3/8) Epoch 20, batch 3700, loss[loss=0.1538, simple_loss=0.2392, pruned_loss=0.03417, over 7164.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.03591, over 1432903.92 frames.], batch size: 18, lr: 3.86e-04
2022-05-15 01:35:08,008 INFO [train.py:812] (3/8) Epoch 20, batch 3750, loss[loss=0.1899, simple_loss=0.2692, pruned_loss=0.0553, over 7067.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2516, pruned_loss=0.03571, over 1427653.18 frames.], batch size: 28, lr: 3.86e-04
2022-05-15 01:36:06,428 INFO [train.py:812] (3/8) Epoch 20, batch 3800, loss[loss=0.1377, simple_loss=0.2342, pruned_loss=0.02061, over 7332.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2513, pruned_loss=0.03605, over 1423407.11 frames.], batch size: 20, lr: 3.86e-04
2022-05-15 01:37:04,400 INFO [train.py:812] (3/8) Epoch 20, batch 3850, loss[loss=0.1554, simple_loss=0.2425, pruned_loss=0.03418, over 7267.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2509, pruned_loss=0.03593, over 1421281.58 frames.], batch size: 17, lr: 3.86e-04
2022-05-15 01:38:02,156 INFO [train.py:812] (3/8) Epoch 20, batch 3900, loss[loss=0.1773, simple_loss=0.2709, pruned_loss=0.04179, over 7116.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2521, pruned_loss=0.03618, over 1418286.78 frames.], batch size: 21, lr: 3.85e-04
2022-05-15 01:39:01,287 INFO [train.py:812] (3/8) Epoch 20, batch 3950, loss[loss=0.1543, simple_loss=0.2508, pruned_loss=0.02892, over 7331.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2521, pruned_loss=0.03617, over 1411918.27 frames.], batch size: 20, lr: 3.85e-04
2022-05-15 01:39:59,103 INFO [train.py:812] (3/8) Epoch 20, batch 4000, loss[loss=0.1454, simple_loss=0.2296, pruned_loss=0.03057, over 7158.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2512, pruned_loss=0.03586, over 1409716.56 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:40:58,251 INFO [train.py:812] (3/8) Epoch 20, batch 4050, loss[loss=0.1463, simple_loss=0.2399, pruned_loss=0.02635, over 7325.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2518, pruned_loss=0.03614, over 1407387.10 frames.], batch size: 20, lr: 3.85e-04
2022-05-15 01:41:57,206 INFO [train.py:812] (3/8) Epoch 20, batch 4100, loss[loss=0.1496, simple_loss=0.2298, pruned_loss=0.03469, over 7280.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2511, pruned_loss=0.03634, over 1407576.40 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:42:56,561 INFO [train.py:812] (3/8) Epoch 20, batch 4150, loss[loss=0.1423, simple_loss=0.2336, pruned_loss=0.02557, over 7059.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2507, pruned_loss=0.03609, over 1411564.58 frames.], batch size: 18, lr: 3.85e-04
2022-05-15 01:43:53,656 INFO [train.py:812] (3/8) Epoch 20, batch 4200, loss[loss=0.1566, simple_loss=0.2323, pruned_loss=0.04048, over 6782.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2509, pruned_loss=0.03635, over 1405022.54 frames.], batch size: 15, lr: 3.85e-04
2022-05-15 01:44:52,589 INFO [train.py:812] (3/8) Epoch 20, batch 4250, loss[loss=0.1698, simple_loss=0.2687, pruned_loss=0.03544, over 7176.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2502, pruned_loss=0.03626, over 1403653.56 frames.], batch size: 23, lr: 3.85e-04
2022-05-15 01:45:49,896 INFO [train.py:812] (3/8) Epoch 20, batch 4300, loss[loss=0.1941, simple_loss=0.295, pruned_loss=0.04666, over 7221.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2513, pruned_loss=0.03656, over 1401154.02 frames.], batch size: 21, lr: 3.85e-04
2022-05-15 01:46:48,979 INFO [train.py:812] (3/8) Epoch 20, batch 4350, loss[loss=0.1925, simple_loss=0.2756, pruned_loss=0.05472, over 5282.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2497, pruned_loss=0.03606, over 1404627.16 frames.], batch size: 52, lr: 3.84e-04
2022-05-15 01:47:48,041 INFO [train.py:812] (3/8) Epoch 20, batch 4400, loss[loss=0.1784, simple_loss=0.2673, pruned_loss=0.04475, over 7156.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2496, pruned_loss=0.03609, over 1398267.33 frames.], batch size: 19, lr: 3.84e-04
2022-05-15 01:48:47,108 INFO [train.py:812] (3/8) Epoch 20, batch 4450, loss[loss=0.1428, simple_loss=0.2263, pruned_loss=0.0296, over 6842.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2493, pruned_loss=0.03598, over 1389200.52 frames.], batch size: 15, lr: 3.84e-04
2022-05-15 01:49:45,780 INFO [train.py:812] (3/8) Epoch 20, batch 4500, loss[loss=0.2164, simple_loss=0.3027, pruned_loss=0.06503, over 7186.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2512, pruned_loss=0.0366, over 1383858.65 frames.], batch size: 23, lr: 3.84e-04
2022-05-15 01:50:44,396 INFO [train.py:812] (3/8) Epoch 20, batch 4550, loss[loss=0.1524, simple_loss=0.2493, pruned_loss=0.02771, over 6567.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2536, pruned_loss=0.03788, over 1339574.56 frames.], batch size: 39, lr: 3.84e-04
2022-05-15 01:51:55,156 INFO [train.py:812] (3/8) Epoch 21, batch 0, loss[loss=0.1571, simple_loss=0.2542, pruned_loss=0.02999, over 7010.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2542, pruned_loss=0.02999, over 7010.00 frames.], batch size: 16, lr: 3.75e-04
2022-05-15 01:52:54,962 INFO [train.py:812] (3/8) Epoch 21, batch 50, loss[loss=0.1414, simple_loss=0.2342, pruned_loss=0.02434, over 6287.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2528, pruned_loss=0.03635, over 322962.62 frames.], batch size: 37, lr: 3.75e-04
2022-05-15 01:53:53,826 INFO [train.py:812] (3/8) Epoch 21, batch 100, loss[loss=0.1493, simple_loss=0.2327, pruned_loss=0.03297, over 6801.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2525, pruned_loss=0.03685, over 566916.91 frames.], batch size: 15, lr: 3.75e-04
2022-05-15 01:54:52,686 INFO [train.py:812] (3/8) Epoch 21, batch 150, loss[loss=0.1457, simple_loss=0.2243, pruned_loss=0.03353, over 7166.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2531, pruned_loss=0.03693, over 755587.93 frames.], batch size: 18, lr: 3.75e-04
2022-05-15 01:55:51,315 INFO [train.py:812] (3/8) Epoch 21, batch 200, loss[loss=0.1863, simple_loss=0.2808, pruned_loss=0.04588, over 6839.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03655, over 900047.27 frames.], batch size: 31, lr: 3.75e-04
2022-05-15 01:56:53,955 INFO [train.py:812] (3/8) Epoch 21, batch 250, loss[loss=0.1428, simple_loss=0.2336, pruned_loss=0.02597, over 7162.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2529, pruned_loss=0.0364, over 1012645.53 frames.], batch size: 19, lr: 3.75e-04
2022-05-15 01:57:52,819 INFO [train.py:812] (3/8) Epoch 21, batch 300, loss[loss=0.1517, simple_loss=0.2395, pruned_loss=0.032, over 7270.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2529, pruned_loss=0.03631, over 1101309.98 frames.], batch size: 18, lr: 3.75e-04
2022-05-15 01:58:49,819 INFO [train.py:812] (3/8) Epoch 21, batch 350, loss[loss=0.1422, simple_loss=0.2329, pruned_loss=0.02573, over 7269.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2537, pruned_loss=0.03624, over 1169480.81 frames.], batch size: 19, lr: 3.74e-04
2022-05-15 01:59:47,323 INFO [train.py:812] (3/8) Epoch 21, batch 400, loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03238, over 7070.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03593, over 1228974.79 frames.], batch size: 18, lr: 3.74e-04
2022-05-15 02:00:46,709 INFO [train.py:812] (3/8) Epoch 21, batch 450, loss[loss=0.1549, simple_loss=0.2476, pruned_loss=0.03107, over 7066.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2519, pruned_loss=0.03565, over 1271267.59 frames.], batch size: 18, lr: 3.74e-04
2022-05-15 02:01:45,874 INFO [train.py:812] (3/8) Epoch 21, batch 500, loss[loss=0.1742, simple_loss=0.2601, pruned_loss=0.04414, over 7016.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2515, pruned_loss=0.03558, over 1309660.49 frames.], batch size: 28, lr: 3.74e-04
2022-05-15 02:02:44,631 INFO [train.py:812] (3/8) Epoch 21, batch 550, loss[loss=0.1481, simple_loss=0.2337, pruned_loss=0.03123, over 6764.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2508, pruned_loss=0.03505, over 1335918.90 frames.], batch size: 15, lr: 3.74e-04
2022-05-15 02:03:42,715 INFO [train.py:812] (3/8) Epoch 21, batch 600, loss[loss=0.1988, simple_loss=0.3, pruned_loss=0.04885, over 7199.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2504, pruned_loss=0.03485, over 1355588.17 frames.], batch size: 22, lr: 3.74e-04
2022-05-15 02:04:42,153 INFO [train.py:812] (3/8) Epoch 21, batch 650, loss[loss=0.1388, simple_loss=0.2175, pruned_loss=0.03001, over 7140.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2493, pruned_loss=0.03487, over 1369801.87 frames.], batch size: 17, lr: 3.74e-04
2022-05-15 02:05:41,122 INFO [train.py:812] (3/8) Epoch 21, batch 700, loss[loss=0.1771, simple_loss=0.2828, pruned_loss=0.03571, over 7232.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2504, pruned_loss=0.03523, over 1379659.16 frames.], batch size: 20, lr: 3.74e-04
2022-05-15 02:06:40,201 INFO [train.py:812] (3/8) Epoch 21, batch 750, loss[loss=0.1551, simple_loss=0.2407, pruned_loss=0.03475, over 7416.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2508, pruned_loss=0.03523, over 1384685.65 frames.], batch size: 18, lr: 3.74e-04
2022-05-15 02:07:37,522 INFO [train.py:812] (3/8) Epoch 21, batch 800, loss[loss=0.1682, simple_loss=0.262, pruned_loss=0.03718, over 7232.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2508, pruned_loss=0.03547, over 1382902.41 frames.], batch size: 20, lr: 3.73e-04
2022-05-15 02:08:37,326 INFO [train.py:812] (3/8) Epoch 21, batch 850, loss[loss=0.1838, simple_loss=0.2715, pruned_loss=0.04808, over 7318.00 frames.], tot_loss[loss=0.16, simple_loss=0.2497, pruned_loss=0.03511, over 1389713.39 frames.], batch size: 25, lr: 3.73e-04
2022-05-15 02:09:36,930 INFO [train.py:812] (3/8) Epoch 21, batch 900, loss[loss=0.1678, simple_loss=0.2539, pruned_loss=0.04086, over 7232.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2494, pruned_loss=0.03513, over 1398558.05 frames.], batch size: 20, lr: 3.73e-04
2022-05-15 02:10:36,776 INFO [train.py:812] (3/8) Epoch 21, batch 950, loss[loss=0.1501, simple_loss=0.2449, pruned_loss=0.02767, over 7347.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2502, pruned_loss=0.03551, over 1405355.09 frames.], batch size: 22, lr: 3.73e-04
2022-05-15 02:11:34,903 INFO [train.py:812] (3/8) Epoch 21, batch 1000, loss[loss=0.1636, simple_loss=0.269, pruned_loss=0.02913, over 7209.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2506, pruned_loss=0.03538, over 1405284.02 frames.], batch size: 23, lr: 3.73e-04
2022-05-15 02:12:42,574 INFO [train.py:812] (3/8) Epoch 21, batch 1050, loss[loss=0.1669, simple_loss=0.2662, pruned_loss=0.03377, over 7399.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2514, pruned_loss=0.03546, over 1406081.02 frames.], batch size: 21, lr: 3.73e-04
2022-05-15 02:13:41,812 INFO [train.py:812] (3/8) Epoch 21, batch 1100, loss[loss=0.165, simple_loss=0.2464, pruned_loss=0.04181, over 6810.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2512, pruned_loss=0.03565, over 1406639.41 frames.], batch size: 15, lr: 3.73e-04
2022-05-15 02:14:40,534 INFO [train.py:812] (3/8) Epoch 21, batch 1150, loss[loss=0.1806, simple_loss=0.2744, pruned_loss=0.04342, over 7325.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2516, pruned_loss=0.03598, over 1412161.92 frames.], batch size: 24, lr: 3.73e-04
2022-05-15 02:15:37,793 INFO [train.py:812] (3/8) Epoch 21, batch 1200, loss[loss=0.1434, simple_loss=0.2301, pruned_loss=0.02834, over 7281.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2524, pruned_loss=0.03566, over 1414390.79 frames.], batch size: 18, lr: 3.73e-04
2022-05-15 02:16:37,333 INFO [train.py:812] (3/8) Epoch 21, batch 1250, loss[loss=0.1828, simple_loss=0.2803, pruned_loss=0.04266, over 7297.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03537, over 1417019.86 frames.], batch size: 24, lr: 3.73e-04
2022-05-15 02:17:36,468 INFO [train.py:812] (3/8) Epoch 21, batch 1300, loss[loss=0.1399, simple_loss=0.228, pruned_loss=0.02594, over 7068.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.03527, over 1415810.98 frames.], batch size: 18, lr: 3.72e-04
2022-05-15 02:18:34,031 INFO [train.py:812] (3/8) Epoch 21, batch 1350, loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.0401, over 7341.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03514, over 1422957.07 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:19:32,908 INFO [train.py:812] (3/8) Epoch 21, batch 1400, loss[loss=0.1649, simple_loss=0.265, pruned_loss=0.03243, over 7380.00 frames.], tot_loss[loss=0.1606, simple_loss=0.251, pruned_loss=0.03508, over 1426009.08 frames.], batch size: 23, lr: 3.72e-04
2022-05-15 02:20:31,870 INFO [train.py:812] (3/8) Epoch 21, batch 1450, loss[loss=0.2022, simple_loss=0.2756, pruned_loss=0.0644, over 4839.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2506, pruned_loss=0.03533, over 1420009.69 frames.], batch size: 52, lr: 3.72e-04
2022-05-15 02:21:30,170 INFO [train.py:812] (3/8) Epoch 21, batch 1500, loss[loss=0.1692, simple_loss=0.2624, pruned_loss=0.038, over 7327.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2516, pruned_loss=0.03586, over 1417346.87 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:22:29,834 INFO [train.py:812] (3/8) Epoch 21, batch 1550, loss[loss=0.1648, simple_loss=0.2573, pruned_loss=0.03615, over 6762.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2522, pruned_loss=0.03619, over 1420371.41 frames.], batch size: 31, lr: 3.72e-04
2022-05-15 02:23:26,743 INFO [train.py:812] (3/8) Epoch 21, batch 1600, loss[loss=0.1763, simple_loss=0.2793, pruned_loss=0.03665, over 7337.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2525, pruned_loss=0.03583, over 1421518.18 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:24:25,713 INFO [train.py:812] (3/8) Epoch 21, batch 1650, loss[loss=0.148, simple_loss=0.2501, pruned_loss=0.02292, over 7331.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2522, pruned_loss=0.03562, over 1423373.08 frames.], batch size: 20, lr: 3.72e-04
2022-05-15 02:25:24,252 INFO [train.py:812] (3/8) Epoch 21, batch 1700, loss[loss=0.1651, simple_loss=0.263, pruned_loss=0.03363, over 7328.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2517, pruned_loss=0.03561, over 1423630.87 frames.], batch size: 22, lr: 3.72e-04
2022-05-15 02:26:22,310 INFO [train.py:812] (3/8) Epoch 21, batch 1750, loss[loss=0.1435, simple_loss=0.2326, pruned_loss=0.02719, over 7425.00 frames.], tot_loss[loss=0.1617, simple_loss=0.252, pruned_loss=0.03571, over 1423829.39 frames.], batch size: 18, lr: 3.72e-04
2022-05-15 02:27:21,185 INFO [train.py:812] (3/8) Epoch 21, batch 1800, loss[loss=0.1579, simple_loss=0.2536, pruned_loss=0.0311, over 7217.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2509, pruned_loss=0.03517, over 1424788.52 frames.], batch size: 23, lr: 3.71e-04
2022-05-15 02:28:20,356 INFO [train.py:812] (3/8) Epoch 21, batch 1850, loss[loss=0.1533, simple_loss=0.2332, pruned_loss=0.03674, over 7413.00 frames.], tot_loss[loss=0.161, simple_loss=0.251, pruned_loss=0.03545, over 1422972.26 frames.], batch size: 18, lr: 3.71e-04
2022-05-15 02:29:19,107 INFO [train.py:812] (3/8) Epoch 21, batch 1900, loss[loss=0.1561, simple_loss=0.2479, pruned_loss=0.03219, over 7156.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2519, pruned_loss=0.03581, over 1424509.89 frames.], batch size: 19, lr: 3.71e-04
2022-05-15 02:30:19,014 INFO [train.py:812] (3/8) Epoch 21, batch 1950, loss[loss=0.1599, simple_loss=0.2448, pruned_loss=0.03746, over 7273.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2514, pruned_loss=0.03591, over 1427812.67 frames.], batch size: 19, lr: 3.71e-04
2022-05-15 02:31:18,514 INFO [train.py:812] (3/8) Epoch 21, batch 2000, loss[loss=0.1826, simple_loss=0.2783, pruned_loss=0.04344, over 6771.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2503, pruned_loss=0.03537, over 1423670.13 frames.], batch size: 31, lr: 3.71e-04
2022-05-15 02:32:18,153 INFO [train.py:812] (3/8) Epoch 21, batch 2050, loss[loss=0.158, simple_loss=0.2527, pruned_loss=0.03162, over 7224.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2512, pruned_loss=0.03596, over 1424472.38 frames.], batch size: 21, lr: 3.71e-04
2022-05-15 02:33:17,366 INFO [train.py:812] (3/8) Epoch 21, batch 2100, loss[loss=0.1588, simple_loss=0.244, pruned_loss=0.03682, over 7066.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2509, pruned_loss=0.03575, over 1422970.20 frames.], batch size: 18, lr: 3.71e-04
2022-05-15 02:34:16,879 INFO [train.py:812] (3/8) Epoch 21, batch 2150, loss[loss=0.1612, simple_loss=0.2407, pruned_loss=0.04084, over 6842.00 frames.], tot_loss[loss=0.1611, simple_loss=0.251, pruned_loss=0.03561, over 1422314.68 frames.], batch size: 15, lr: 3.71e-04
2022-05-15 02:35:14,475 INFO [train.py:812] (3/8) Epoch 21, batch 2200, loss[loss=0.1956, simple_loss=0.2999, pruned_loss=0.0456, over 7195.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2503, pruned_loss=0.03538, over 1423641.08 frames.], batch size: 22, lr: 3.71e-04
2022-05-15 02:36:12,362 INFO [train.py:812] (3/8) Epoch 21, batch 2250, loss[loss=0.1679, simple_loss=0.2604, pruned_loss=0.03767, over 7212.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2508, pruned_loss=0.03544, over 1424899.58 frames.], batch size: 22, lr: 3.71e-04
2022-05-15 02:37:12,523 INFO [train.py:812] (3/8) Epoch 21, batch 2300, loss[loss=0.2148, simple_loss=0.2878, pruned_loss=0.07088, over 5170.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2506, pruned_loss=0.0356, over 1422989.48 frames.], batch size: 53, lr: 3.71e-04
2022-05-15 02:38:11,392 INFO [train.py:812] (3/8) Epoch 21, batch 2350, loss[loss=0.1651, simple_loss=0.2582, pruned_loss=0.03602, over 7296.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2523, pruned_loss=0.0362, over 1417725.65 frames.], batch size: 24, lr: 3.70e-04
2022-05-15 02:39:10,808 INFO [train.py:812] (3/8) Epoch 21, batch 2400, loss[loss=0.1539, simple_loss=0.2436, pruned_loss=0.03213, over 7215.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2513, pruned_loss=0.03573, over 1420638.48 frames.], batch size: 23, lr: 3.70e-04
2022-05-15 02:40:10,440 INFO [train.py:812] (3/8) Epoch 21, batch 2450, loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03886, over 7168.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2516, pruned_loss=0.03544, over 1422089.75 frames.], batch size: 19, lr: 3.70e-04
2022-05-15 02:41:09,423 INFO [train.py:812] (3/8) Epoch 21, batch 2500, loss[loss=0.1761, simple_loss=0.2696, pruned_loss=0.04132, over 7415.00 frames.], tot_loss[loss=0.161, simple_loss=0.2516, pruned_loss=0.03525, over 1422989.40 frames.], batch size: 21, lr: 3.70e-04
2022-05-15 02:42:07,847 INFO [train.py:812] (3/8) Epoch 21, batch 2550, loss[loss=0.2111, simple_loss=0.2931, pruned_loss=0.06455, over 4625.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2527, pruned_loss=0.03579, over 1420296.52 frames.], batch size: 52, lr: 3.70e-04
2022-05-15 02:43:06,152 INFO [train.py:812] (3/8) Epoch 21, batch 2600, loss[loss=0.1508, simple_loss=0.2361, pruned_loss=0.03271, over 7087.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2531, pruned_loss=0.03584, over 1421519.31 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:44:05,922 INFO [train.py:812] (3/8) Epoch 21, batch 2650, loss[loss=0.143, simple_loss=0.2386, pruned_loss=0.02373, over 7331.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2537, pruned_loss=0.03662, over 1416381.17 frames.], batch size: 20, lr: 3.70e-04
2022-05-15 02:45:04,656 INFO [train.py:812] (3/8) Epoch 21, batch 2700, loss[loss=0.146, simple_loss=0.2273, pruned_loss=0.03239, over 7414.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2528, pruned_loss=0.03604, over 1420585.16 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:46:03,779 INFO [train.py:812] (3/8) Epoch 21, batch 2750, loss[loss=0.1663, simple_loss=0.2519, pruned_loss=0.04032, over 7176.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2532, pruned_loss=0.03615, over 1422727.99 frames.], batch size: 18, lr: 3.70e-04
2022-05-15 02:47:03,049 INFO [train.py:812] (3/8) Epoch 21, batch 2800, loss[loss=0.1468, simple_loss=0.2378, pruned_loss=0.02786, over 7373.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2522, pruned_loss=0.03555, over 1426186.55 frames.], batch size: 23, lr: 3.70e-04
2022-05-15 02:48:12,152 INFO [train.py:812] (3/8) Epoch 21, batch 2850, loss[loss=0.1602, simple_loss=0.2557, pruned_loss=0.03231, over 7215.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2518, pruned_loss=0.0354, over 1421571.61 frames.], batch size: 23, lr: 3.69e-04
2022-05-15 02:49:11,140 INFO [train.py:812] (3/8) Epoch 21, batch 2900, loss[loss=0.1774, simple_loss=0.2648, pruned_loss=0.045, over 7090.00 frames.], tot_loss[loss=0.1613, simple_loss=0.252, pruned_loss=0.03532, over 1417249.58 frames.], batch size: 28, lr: 3.69e-04
2022-05-15 02:50:09,892 INFO [train.py:812] (3/8) Epoch 21, batch 2950, loss[loss=0.1514, simple_loss=0.2362, pruned_loss=0.03333, over 7367.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2519, pruned_loss=0.0352, over 1415688.14 frames.], batch size: 19, lr: 3.69e-04
2022-05-15 02:51:09,038 INFO [train.py:812] (3/8) Epoch 21, batch 3000, loss[loss=0.1835, simple_loss=0.2738, pruned_loss=0.04658, over 6774.00 frames.], tot_loss[loss=0.1614, simple_loss=0.252, pruned_loss=0.03545, over 1415409.99 frames.], batch size: 31, lr: 3.69e-04
2022-05-15 02:51:09,039 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 02:51:16,350 INFO [train.py:841] (3/8) Epoch 21, validation: loss=0.153, simple_loss=0.2519, pruned_loss=0.02704, over 698248.00 frames.
2022-05-15 02:52:35,373 INFO [train.py:812] (3/8) Epoch 21, batch 3050, loss[loss=0.1407, simple_loss=0.2196, pruned_loss=0.03088, over 7303.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2514, pruned_loss=0.03541, over 1416122.24 frames.], batch size: 18, lr: 3.69e-04
2022-05-15 02:53:32,962 INFO [train.py:812] (3/8) Epoch 21, batch 3100, loss[loss=0.1864, simple_loss=0.2778, pruned_loss=0.04754, over 7364.00 frames.], tot_loss[loss=0.1616, simple_loss=0.252, pruned_loss=0.03558, over 1414144.29 frames.], batch size: 23, lr: 3.69e-04
2022-05-15 02:55:01,531 INFO [train.py:812] (3/8) Epoch 21, batch 3150, loss[loss=0.2043, simple_loss=0.2978, pruned_loss=0.05541, over 7306.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2523, pruned_loss=0.0359, over 1418693.73 frames.], batch size: 24, lr: 3.69e-04
2022-05-15 02:56:00,661 INFO [train.py:812] (3/8) Epoch 21, batch 3200, loss[loss=0.1604, simple_loss=0.2621, pruned_loss=0.02931, over 7310.00 frames.], tot_loss[loss=0.163, simple_loss=0.2536, pruned_loss=0.03625, over 1423030.15 frames.], batch size: 21, lr: 3.69e-04
2022-05-15 02:57:00,390 INFO [train.py:812] (3/8) Epoch 21, batch 3250, loss[loss=0.1691, simple_loss=0.2644, pruned_loss=0.03692, over 7065.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2534, pruned_loss=0.03619, over 1421868.03 frames.], batch size: 18, lr: 3.69e-04
2022-05-15 02:58:08,763 INFO [train.py:812] (3/8) Epoch 21, batch 3300, loss[loss=0.1359, simple_loss=0.2189, pruned_loss=0.02644, over 7140.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2529, pruned_loss=0.0358, over 1423389.77 frames.], batch size: 17, lr: 3.69e-04
2022-05-15 02:59:08,383 INFO [train.py:812] (3/8) Epoch 21, batch 3350, loss[loss=0.1462, simple_loss=0.2336, pruned_loss=0.0294, over 7231.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2521, pruned_loss=0.03561, over 1419212.33 frames.], batch size: 20, lr: 3.68e-04
2022-05-15 03:00:06,809 INFO [train.py:812] (3/8) Epoch 21, batch 3400, loss[loss=0.1854, simple_loss=0.2773, pruned_loss=0.0467, over 6516.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2528, pruned_loss=0.03593, over 1416330.03 frames.], batch size: 38, lr: 3.68e-04
2022-05-15 03:01:06,184 INFO [train.py:812] (3/8) Epoch 21, batch 3450, loss[loss=0.1675, simple_loss=0.2596, pruned_loss=0.03772, over 7321.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2536, pruned_loss=0.03634, over 1414850.02 frames.], batch size: 21, lr: 3.68e-04
2022-05-15 03:02:05,063 INFO [train.py:812] (3/8) Epoch 21, batch 3500, loss[loss=0.167, simple_loss=0.2623, pruned_loss=0.03585, over 7063.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2537, pruned_loss=0.03626, over 1411068.46 frames.], batch size: 28, lr: 3.68e-04
2022-05-15 03:03:04,135 INFO [train.py:812] (3/8) Epoch 21, batch 3550, loss[loss=0.1445, simple_loss=0.2255, pruned_loss=0.03173, over 7302.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2521, pruned_loss=0.03574, over 1415388.59 frames.], batch size: 17, lr: 3.68e-04
2022-05-15 03:04:02,908 INFO [train.py:812] (3/8) Epoch 21, batch 3600, loss[loss=0.1735, simple_loss=0.2681, pruned_loss=0.03947, over 7366.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2521, pruned_loss=0.03577, over 1412215.91 frames.], batch size: 23, lr: 3.68e-04
2022-05-15 03:05:02,951 INFO [train.py:812] (3/8) Epoch 21, batch 3650, loss[loss=0.1583, simple_loss=0.2545, pruned_loss=0.03098, over 7208.00 frames.], tot_loss[loss=0.1615, simple_loss=0.252, pruned_loss=0.03548, over 1413850.76 frames.], batch size: 26, lr: 3.68e-04
2022-05-15 03:06:01,336 INFO [train.py:812] (3/8) Epoch 21, batch 3700, loss[loss=0.137, simple_loss=0.2365, pruned_loss=0.01878, over 7308.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2516, pruned_loss=0.03511, over 1414830.66 frames.], batch size: 21, lr: 3.68e-04
2022-05-15 03:07:01,116 INFO [train.py:812] (3/8) Epoch 21, batch 3750, loss[loss=0.1588, simple_loss=0.251, pruned_loss=0.03328, over 7315.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2515, pruned_loss=0.03514, over 1418139.50 frames.], batch size: 25, lr: 3.68e-04
2022-05-15 03:07:59,608 INFO [train.py:812] (3/8) Epoch 21, batch 3800, loss[loss=0.1696, simple_loss=0.2632, pruned_loss=0.03801, over 7176.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03495, over 1417850.34 frames.], batch size: 26, lr: 3.68e-04
2022-05-15 03:08:58,683 INFO [train.py:812] (3/8) Epoch 21, batch 3850, loss[loss=0.1546, simple_loss=0.2504, pruned_loss=0.02937, over 7321.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2512, pruned_loss=0.03503, over 1419125.79 frames.], batch size: 20, lr: 3.68e-04
2022-05-15 03:09:55,530 INFO [train.py:812] (3/8) Epoch 21, batch 3900, loss[loss=0.1324, simple_loss=0.2186, pruned_loss=0.02311, over 7261.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2511, pruned_loss=0.03477, over 1422634.77 frames.], batch size: 19, lr: 3.67e-04
2022-05-15 03:10:53,482 INFO [train.py:812] (3/8) Epoch 21, batch 3950, loss[loss=0.1653, simple_loss=0.2382, pruned_loss=0.04618, over 7408.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2524, pruned_loss=0.03543, over 1418348.72 frames.], batch size: 18, lr: 3.67e-04
2022-05-15 03:11:51,918 INFO [train.py:812] (3/8) Epoch 21, batch 4000, loss[loss=0.1549, simple_loss=0.2465, pruned_loss=0.03162, over 7355.00 frames.], tot_loss[loss=0.161, simple_loss=0.252, pruned_loss=0.03495, over 1422183.05 frames.], batch size: 19, lr: 3.67e-04
2022-05-15 03:12:50,956 INFO [train.py:812] (3/8) Epoch 21, batch 4050, loss[loss=0.2263, simple_loss=0.2883, pruned_loss=0.08213, over 5025.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2511, pruned_loss=0.03484, over 1419083.29 frames.], batch size: 52, lr: 3.67e-04
2022-05-15 03:13:49,279 INFO [train.py:812] (3/8) Epoch 21, batch 4100, loss[loss=0.1558, simple_loss=0.2517, pruned_loss=0.02993, over 7215.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2522, pruned_loss=0.03555, over 1411484.48 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:14:46,152 INFO [train.py:812] (3/8) Epoch 21, batch 4150, loss[loss=0.1458, simple_loss=0.23, pruned_loss=0.03081, over 7073.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2531, pruned_loss=0.03594, over 1412753.96 frames.], batch size: 18, lr: 3.67e-04
2022-05-15 03:15:43,924 INFO [train.py:812] (3/8) Epoch 21, batch 4200, loss[loss=0.1555, simple_loss=0.2496, pruned_loss=0.0307, over 6657.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2528, pruned_loss=0.03568, over 1412327.70 frames.], batch size: 31, lr: 3.67e-04
2022-05-15 03:16:47,805 INFO [train.py:812] (3/8) Epoch 21, batch 4250, loss[loss=0.1709, simple_loss=0.2666, pruned_loss=0.03758, over 7230.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2516, pruned_loss=0.03504, over 1417057.30 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:17:46,897 INFO [train.py:812] (3/8) Epoch 21, batch 4300, loss[loss=0.1838, simple_loss=0.2697, pruned_loss=0.04893, over 7316.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2509, pruned_loss=0.03486, over 1417152.78 frames.], batch size: 24, lr: 3.67e-04
2022-05-15 03:18:45,855 INFO [train.py:812] (3/8) Epoch 21, batch 4350, loss[loss=0.1598, simple_loss=0.2519, pruned_loss=0.03387, over 7226.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2501, pruned_loss=0.03442, over 1415728.13 frames.], batch size: 21, lr: 3.67e-04
2022-05-15 03:19:43,044 INFO [train.py:812] (3/8) Epoch 21, batch 4400, loss[loss=0.1411, simple_loss=0.2261, pruned_loss=0.02809, over 7157.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03452, over 1415808.61 frames.], batch size: 18, lr: 3.66e-04
2022-05-15 03:20:42,006 INFO [train.py:812] (3/8) Epoch 21, batch 4450, loss[loss=0.1366, simple_loss=0.2157, pruned_loss=0.02878, over 7014.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2505, pruned_loss=0.03443, over 1407618.15 frames.], batch size: 16, lr: 3.66e-04
2022-05-15 03:21:40,280 INFO [train.py:812] (3/8) Epoch 21, batch 4500, loss[loss=0.148, simple_loss=0.2282, pruned_loss=0.03387, over 7005.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2507, pruned_loss=0.03435, over 1410546.73 frames.], batch size: 16, lr: 3.66e-04
2022-05-15 03:22:39,944 INFO [train.py:812] (3/8) Epoch 21, batch 4550, loss[loss=0.1671, simple_loss=0.2567, pruned_loss=0.03874, over 5097.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03508, over 1395300.42 frames.], batch size: 52, lr: 3.66e-04
2022-05-15 03:23:52,231 INFO [train.py:812] (3/8) Epoch 22, batch 0, loss[loss=0.1682, simple_loss=0.2721, pruned_loss=0.03218, over 7284.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2721, pruned_loss=0.03218, over 7284.00 frames.], batch size: 25, lr: 3.58e-04
2022-05-15 03:24:50,138 INFO [train.py:812] (3/8) Epoch 22, batch 50, loss[loss=0.1324, simple_loss=0.2303, pruned_loss=0.01728, over 7163.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2519, pruned_loss=0.03514, over 317776.90 frames.], batch size: 18, lr: 3.58e-04
2022-05-15 03:25:49,145 INFO [train.py:812] (3/8) Epoch 22, batch 100, loss[loss=0.1591, simple_loss=0.2519, pruned_loss=0.03311, over 7118.00 frames.], tot_loss[loss=0.161, simple_loss=0.2507, pruned_loss=0.03567, over 563466.43 frames.], batch size: 21, lr: 3.58e-04
2022-05-15 03:26:47,183 INFO [train.py:812] (3/8) Epoch 22, batch 150, loss[loss=0.1653, simple_loss=0.2565, pruned_loss=0.03704, over 7310.00 frames.], tot_loss[loss=0.16, simple_loss=0.2499, pruned_loss=0.0351, over 753393.26 frames.], batch size: 21, lr: 3.58e-04
2022-05-15 03:27:46,006 INFO [train.py:812] (3/8) Epoch 22, batch 200, loss[loss=0.1532, simple_loss=0.2513, pruned_loss=0.02753, over 7335.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2489, pruned_loss=0.03438, over 901299.23 frames.], batch size: 22, lr: 3.58e-04
2022-05-15 03:28:43,575 INFO [train.py:812] (3/8) Epoch 22, batch 250, loss[loss=0.151, simple_loss=0.2393, pruned_loss=0.03132, over 7252.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03432, over 1014418.92 frames.], batch size: 19, lr: 3.57e-04
2022-05-15 03:29:41,559 INFO [train.py:812] (3/8) Epoch 22, batch 300, loss[loss=0.1427, simple_loss=0.229, pruned_loss=0.0282, over 7228.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2511, pruned_loss=0.03526, over 1106575.92 frames.], batch size: 20, lr: 3.57e-04
2022-05-15 03:30:39,459 INFO [train.py:812] (3/8) Epoch 22, batch 350, loss[loss=0.1428, simple_loss=0.2316, pruned_loss=0.02704, over 7157.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2503, pruned_loss=0.03477, over 1176782.80 frames.], batch size: 19, lr: 3.57e-04
2022-05-15 03:31:38,288 INFO [train.py:812] (3/8) Epoch 22, batch 400, loss[loss=0.1616, simple_loss=0.2638, pruned_loss=0.02972, over 7222.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.03443, over 1229513.56 frames.], batch size: 21, lr: 3.57e-04
2022-05-15 03:32:37,205 INFO [train.py:812] (3/8) Epoch 22, batch 450, loss[loss=0.187, simple_loss=0.2754, pruned_loss=0.04931, over 4735.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2491, pruned_loss=0.03409, over 1272480.46 frames.], batch size: 52, lr: 3.57e-04
2022-05-15 03:33:36,429 INFO [train.py:812] (3/8) Epoch 22, batch 500, loss[loss=0.1951, simple_loss=0.292, pruned_loss=0.04912, over 7317.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03455, over 1308151.36 frames.], batch size: 25, lr: 3.57e-04
2022-05-15 03:34:33,231 INFO [train.py:812] (3/8) Epoch 22, batch 550, loss[loss=0.1487, simple_loss=0.2385, pruned_loss=0.02942, over 7432.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2522, pruned_loss=0.03511, over 1331325.03 frames.], batch size: 20, lr: 3.57e-04
2022-05-15 03:35:32,148 INFO [train.py:812] (3/8) Epoch 22, batch 600, loss[loss=0.1699, simple_loss=0.2632, pruned_loss=0.03825, over 7331.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2502, pruned_loss=0.03447, over 1353154.19 frames.], batch size: 22, lr: 3.57e-04
2022-05-15 03:36:30,999 INFO [train.py:812] (3/8) Epoch 22, batch 650, loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02953, over 7333.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2518, pruned_loss=0.03499, over 1368663.23 frames.], batch size: 22, lr: 3.57e-04
2022-05-15 03:37:30,482 INFO [train.py:812] (3/8) Epoch 22, batch 700, loss[loss=0.2107, simple_loss=0.293, pruned_loss=0.06421, over 7267.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03545, over 1378642.46 frames.], batch size: 25, lr: 3.57e-04
2022-05-15 03:38:28,392 INFO [train.py:812] (3/8) Epoch 22, batch 750, loss[loss=0.1473, simple_loss=0.236, pruned_loss=0.02927, over 7165.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2515, pruned_loss=0.03534, over 1386512.74 frames.], batch size: 18, lr: 3.57e-04
2022-05-15 03:39:28,258 INFO [train.py:812] (3/8) Epoch 22, batch 800, loss[loss=0.1644, simple_loss=0.2615, pruned_loss=0.03366, over 7285.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2516, pruned_loss=0.03536, over 1399548.32 frames.], batch size: 25, lr: 3.56e-04
2022-05-15 03:40:27,681 INFO [train.py:812] (3/8) Epoch 22, batch 850, loss[loss=0.1607, simple_loss=0.2484, pruned_loss=0.03647, over 7419.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03519, over 1404580.35 frames.], batch size: 18, lr: 3.56e-04
2022-05-15 03:41:26,083 INFO [train.py:812] (3/8) Epoch 22, batch 900, loss[loss=0.1838, simple_loss=0.2776, pruned_loss=0.04503, over 6395.00 frames.], tot_loss[loss=0.161, simple_loss=0.2515, pruned_loss=0.03524, over 1408492.61 frames.], batch size: 38, lr: 3.56e-04
2022-05-15 03:42:25,446 INFO [train.py:812] (3/8) Epoch 22, batch 950, loss[loss=0.142, simple_loss=0.2244, pruned_loss=0.02984, over 7270.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2513, pruned_loss=0.03542, over 1410867.29 frames.], batch size: 18, lr: 3.56e-04
2022-05-15 03:43:24,201 INFO [train.py:812] (3/8) Epoch 22, batch 1000, loss[loss=0.152, simple_loss=0.2475, pruned_loss=0.02825, over 7144.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2521, pruned_loss=0.0357, over 1411421.58 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:44:23,449 INFO [train.py:812] (3/8) Epoch 22, batch 1050, loss[loss=0.1438, simple_loss=0.2337, pruned_loss=0.02698, over 7338.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2506, pruned_loss=0.03523, over 1414774.24 frames.], batch size: 22, lr: 3.56e-04
2022-05-15 03:45:22,999 INFO [train.py:812] (3/8) Epoch 22, batch 1100, loss[loss=0.1768, simple_loss=0.2777, pruned_loss=0.03797, over 6403.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2496, pruned_loss=0.03417, over 1418924.81 frames.], batch size: 37, lr: 3.56e-04
2022-05-15 03:46:20,328 INFO [train.py:812] (3/8) Epoch 22, batch 1150, loss[loss=0.1398, simple_loss=0.2315, pruned_loss=0.02403, over 7263.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2493, pruned_loss=0.03428, over 1419971.69 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:47:19,430 INFO [train.py:812] (3/8) Epoch 22, batch 1200, loss[loss=0.1624, simple_loss=0.2501, pruned_loss=0.03737, over 7329.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2492, pruned_loss=0.03453, over 1421818.54 frames.], batch size: 25, lr: 3.56e-04
2022-05-15 03:48:18,941 INFO [train.py:812] (3/8) Epoch 22, batch 1250, loss[loss=0.1371, simple_loss=0.2215, pruned_loss=0.0264, over 7025.00 frames.], tot_loss[loss=0.16, simple_loss=0.2501, pruned_loss=0.03498, over 1420814.57 frames.], batch size: 16, lr: 3.56e-04
2022-05-15 03:49:19,101 INFO [train.py:812] (3/8) Epoch 22, batch 1300, loss[loss=0.1469, simple_loss=0.2307, pruned_loss=0.03157, over 7174.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2498, pruned_loss=0.03503, over 1419758.21 frames.], batch size: 19, lr: 3.56e-04
2022-05-15 03:50:16,169 INFO [train.py:812] (3/8) Epoch 22, batch 1350, loss[loss=0.172, simple_loss=0.2692, pruned_loss=0.03735, over 7406.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2496, pruned_loss=0.03483, over 1423597.81 frames.], batch size: 21, lr: 3.55e-04
2022-05-15 03:51:15,326 INFO [train.py:812] (3/8) Epoch 22, batch 1400, loss[loss=0.1689, simple_loss=0.2702, pruned_loss=0.0338, over 7204.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2492, pruned_loss=0.03472, over 1419976.91 frames.], batch size: 22, lr: 3.55e-04
2022-05-15 03:52:14,158 INFO [train.py:812] (3/8) Epoch 22, batch 1450, loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02859, over 7428.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2506, pruned_loss=0.03527, over 1425204.22 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:53:13,818 INFO [train.py:812] (3/8) Epoch 22, batch 1500, loss[loss=0.1665, simple_loss=0.2604, pruned_loss=0.03627, over 7230.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2499, pruned_loss=0.03541, over 1427008.39 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:54:13,338 INFO [train.py:812] (3/8) Epoch 22, batch 1550, loss[loss=0.169, simple_loss=0.2638, pruned_loss=0.03708, over 7238.00 frames.], tot_loss[loss=0.16, simple_loss=0.2497, pruned_loss=0.03509, over 1429445.13 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:55:12,240 INFO [train.py:812] (3/8) Epoch 22, batch 1600, loss[loss=0.1243, simple_loss=0.2113, pruned_loss=0.01868, over 6802.00 frames.], tot_loss[loss=0.159, simple_loss=0.2489, pruned_loss=0.03456, over 1429929.83 frames.], batch size: 15, lr: 3.55e-04
2022-05-15 03:56:08,988 INFO [train.py:812] (3/8) Epoch 22, batch 1650, loss[loss=0.1666, simple_loss=0.2707, pruned_loss=0.03124, over 6663.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2496, pruned_loss=0.03462, over 1431454.91 frames.], batch size: 31, lr: 3.55e-04
2022-05-15 03:57:06,971 INFO [train.py:812] (3/8) Epoch 22, batch 1700, loss[loss=0.1573, simple_loss=0.2516, pruned_loss=0.03154, over 7336.00 frames.], tot_loss[loss=0.159, simple_loss=0.249, pruned_loss=0.03448, over 1433328.49 frames.], batch size: 22, lr: 3.55e-04
2022-05-15 03:58:03,871 INFO [train.py:812] (3/8) Epoch 22, batch 1750, loss[loss=0.1509, simple_loss=0.2486, pruned_loss=0.02656, over 7229.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2494, pruned_loss=0.03437, over 1432676.13 frames.], batch size: 20, lr: 3.55e-04
2022-05-15 03:59:03,639 INFO [train.py:812] (3/8) Epoch 22, batch 1800, loss[loss=0.1287, simple_loss=0.2188, pruned_loss=0.01935, over 7274.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2495, pruned_loss=0.03476, over 1429760.24 frames.], batch size: 17, lr: 3.55e-04
2022-05-15 04:00:02,102 INFO [train.py:812] (3/8) Epoch 22, batch 1850, loss[loss=0.1581, simple_loss=0.2514, pruned_loss=0.03238, over 6455.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2498, pruned_loss=0.03499, over 1425860.39 frames.], batch size: 38, lr: 3.55e-04
2022-05-15 04:01:00,876 INFO [train.py:812] (3/8) Epoch 22, batch 1900, loss[loss=0.1748, simple_loss=0.259, pruned_loss=0.04533, over 5010.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2505, pruned_loss=0.03546, over 1424269.37 frames.], batch size: 52, lr: 3.54e-04
2022-05-15 04:02:00,144 INFO [train.py:812] (3/8) Epoch 22, batch 1950, loss[loss=0.1563, simple_loss=0.232, pruned_loss=0.0403, over 7278.00 frames.], tot_loss[loss=0.1601, simple_loss=0.25, pruned_loss=0.03507, over 1425201.75 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:02:59,640 INFO [train.py:812] (3/8) Epoch 22, batch 2000, loss[loss=0.2068, simple_loss=0.304, pruned_loss=0.05487, over 7330.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03496, over 1427703.59 frames.], batch size: 20, lr: 3.54e-04
2022-05-15 04:03:58,502 INFO [train.py:812] (3/8) Epoch 22, batch 2050, loss[loss=0.1357, simple_loss=0.2139, pruned_loss=0.0288, over 7271.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2514, pruned_loss=0.03502, over 1428080.54 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:04:58,099 INFO [train.py:812] (3/8) Epoch 22, batch 2100, loss[loss=0.1371, simple_loss=0.2175, pruned_loss=0.02838, over 7412.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2507, pruned_loss=0.0345, over 1427006.75 frames.], batch size: 18, lr: 3.54e-04
2022-05-15 04:05:56,571 INFO [train.py:812] (3/8) Epoch 22, batch 2150, loss[loss=0.1338, simple_loss=0.2222, pruned_loss=0.02273, over 7164.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2494, pruned_loss=0.03406, over 1422465.78 frames.], batch size: 18, lr: 3.54e-04
2022-05-15 04:06:54,938 INFO [train.py:812] (3/8) Epoch 22, batch 2200, loss[loss=0.1664, simple_loss=0.2516, pruned_loss=0.04063, over 7121.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03431, over 1425110.73 frames.], batch size: 21, lr: 3.54e-04
2022-05-15 04:07:52,614 INFO [train.py:812] (3/8) Epoch 22, batch 2250, loss[loss=0.1273, simple_loss=0.2082, pruned_loss=0.02327, over 6777.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03464, over 1422886.41 frames.], batch size: 15, lr: 3.54e-04
2022-05-15 04:08:49,578 INFO [train.py:812] (3/8) Epoch 22, batch 2300, loss[loss=0.1965, simple_loss=0.2688, pruned_loss=0.06209, over 4904.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2502, pruned_loss=0.03451, over 1424393.98 frames.], batch size: 52, lr: 3.54e-04
2022-05-15 04:09:47,978 INFO [train.py:812] (3/8) Epoch 22, batch 2350, loss[loss=0.1506, simple_loss=0.2525, pruned_loss=0.02433, over 6284.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2504, pruned_loss=0.03454, over 1426875.17 frames.], batch size: 37, lr: 3.54e-04
2022-05-15 04:10:57,210 INFO [train.py:812] (3/8) Epoch 22, batch 2400, loss[loss=0.1398, simple_loss=0.2277, pruned_loss=0.02596, over 7135.00 frames.], tot_loss[loss=0.16, simple_loss=0.2501, pruned_loss=0.03499, over 1426709.28 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:11:56,417 INFO [train.py:812] (3/8) Epoch 22, batch 2450, loss[loss=0.1386, simple_loss=0.2263, pruned_loss=0.02541, over 7283.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2509, pruned_loss=0.03516, over 1425393.51 frames.], batch size: 17, lr: 3.54e-04
2022-05-15 04:12:56,178 INFO [train.py:812] (3/8) Epoch 22, batch 2500, loss[loss=0.1788, simple_loss=0.2747, pruned_loss=0.04146, over 7420.00 frames.], tot_loss[loss=0.161, simple_loss=0.2513, pruned_loss=0.03536, over 1423059.42 frames.], batch size: 21, lr: 3.53e-04
2022-05-15 04:13:55,270 INFO [train.py:812] (3/8) Epoch 22, batch 2550, loss[loss=0.1919, simple_loss=0.274, pruned_loss=0.05495, over 7067.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03522, over 1421639.14 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:14:54,427 INFO [train.py:812] (3/8) Epoch 22, batch 2600, loss[loss=0.1567, simple_loss=0.2382, pruned_loss=0.03759, over 7154.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2522, pruned_loss=0.03547, over 1417451.14 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:15:53,309 INFO [train.py:812] (3/8) Epoch 22, batch 2650, loss[loss=0.144, simple_loss=0.2339, pruned_loss=0.02703, over 7251.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2508, pruned_loss=0.03493, over 1421370.41 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:16:52,316 INFO [train.py:812] (3/8) Epoch 22, batch 2700, loss[loss=0.1443, simple_loss=0.2314, pruned_loss=0.02859, over 7159.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2495, pruned_loss=0.03454, over 1420506.69 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:17:51,004 INFO [train.py:812] (3/8) Epoch 22, batch 2750, loss[loss=0.1339, simple_loss=0.2249, pruned_loss=0.02141, over 7068.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03431, over 1420063.49 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:18:49,821 INFO [train.py:812] (3/8) Epoch 22, batch 2800, loss[loss=0.1419, simple_loss=0.2259, pruned_loss=0.02895, over 7282.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03454, over 1421412.11 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:19:48,481 INFO [train.py:812] (3/8) Epoch 22, batch 2850, loss[loss=0.1348, simple_loss=0.2247, pruned_loss=0.02249, over 7155.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03475, over 1419524.11 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:20:47,848 INFO [train.py:812] (3/8) Epoch 22, batch 2900, loss[loss=0.1512, simple_loss=0.239, pruned_loss=0.03168, over 7158.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2507, pruned_loss=0.03483, over 1421422.20 frames.], batch size: 19, lr: 3.53e-04
2022-05-15 04:21:47,228 INFO [train.py:812] (3/8) Epoch 22, batch 2950, loss[loss=0.1451, simple_loss=0.2482, pruned_loss=0.02095, over 7409.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2509, pruned_loss=0.03499, over 1421747.04 frames.], batch size: 21, lr: 3.53e-04
2022-05-15 04:22:47,049 INFO [train.py:812] (3/8) Epoch 22, batch 3000, loss[loss=0.1671, simple_loss=0.2564, pruned_loss=0.03887, over 7158.00 frames.], tot_loss[loss=0.1598, simple_loss=0.25, pruned_loss=0.03481, over 1426075.57 frames.], batch size: 18, lr: 3.53e-04
2022-05-15 04:22:47,050 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 04:22:54,482 INFO [train.py:841] (3/8) Epoch 22, validation: loss=0.1529, simple_loss=0.2512, pruned_loss=0.02731, over 698248.00 frames.
2022-05-15 04:23:53,732 INFO [train.py:812] (3/8) Epoch 22, batch 3050, loss[loss=0.1872, simple_loss=0.2764, pruned_loss=0.04901, over 7068.00 frames.], tot_loss[loss=0.16, simple_loss=0.2502, pruned_loss=0.03492, over 1427686.07 frames.], batch size: 28, lr: 3.52e-04
2022-05-15 04:24:53,786 INFO [train.py:812] (3/8) Epoch 22, batch 3100, loss[loss=0.2195, simple_loss=0.2901, pruned_loss=0.07449, over 4966.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2494, pruned_loss=0.03484, over 1428000.12 frames.], batch size: 52, lr: 3.52e-04
2022-05-15 04:25:52,319 INFO [train.py:812] (3/8) Epoch 22, batch 3150, loss[loss=0.155, simple_loss=0.2517, pruned_loss=0.02912, over 7421.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2492, pruned_loss=0.03465, over 1426458.09 frames.], batch size: 21, lr: 3.52e-04
2022-05-15 04:26:51,022 INFO [train.py:812] (3/8) Epoch 22, batch 3200, loss[loss=0.1672, simple_loss=0.2668, pruned_loss=0.03378, over 7443.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2498, pruned_loss=0.0349, over 1427984.27 frames.], batch size: 19, lr: 3.52e-04
2022-05-15 04:27:50,206 INFO [train.py:812] (3/8) Epoch 22, batch 3250, loss[loss=0.1411, simple_loss=0.2236, pruned_loss=0.02926, over 7001.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2506, pruned_loss=0.03487, over 1429135.06 frames.], batch size: 16, lr: 3.52e-04
2022-05-15 04:28:47,776 INFO [train.py:812] (3/8) Epoch 22, batch 3300, loss[loss=0.1676, simple_loss=0.2521, pruned_loss=0.04159, over 7428.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2519, pruned_loss=0.03553, over 1432023.62 frames.], batch size: 20, lr: 3.52e-04
2022-05-15 04:29:46,913 INFO [train.py:812] (3/8) Epoch 22, batch 3350, loss[loss=0.1377, simple_loss=0.2297, pruned_loss=0.02282, over 7353.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2519, pruned_loss=0.03518, over 1430369.10 frames.], batch size: 19, lr: 3.52e-04
2022-05-15 04:30:46,412 INFO [train.py:812] (3/8) Epoch 22, batch 3400, loss[loss=0.1613, simple_loss=0.2503, pruned_loss=0.03611, over 7140.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2519, pruned_loss=0.03509, over 1426504.77 frames.], batch size: 17, lr: 3.52e-04
2022-05-15 04:31:45,549 INFO [train.py:812] (3/8) Epoch 22, batch 3450, loss[loss=0.1611, simple_loss=0.2588, pruned_loss=0.03177, over 7320.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2526, pruned_loss=0.03565, over 1428431.09 frames.], batch size: 22, lr: 3.52e-04
2022-05-15 04:32:45,140 INFO [train.py:812] (3/8) Epoch 22, batch 3500, loss[loss=0.153, simple_loss=0.2602, pruned_loss=0.02286, over 7339.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2515, pruned_loss=0.03505, over 1431399.76 frames.], batch size: 22, lr: 3.52e-04
2022-05-15 04:33:44,166 INFO [train.py:812] (3/8) Epoch 22, batch 3550, loss[loss=0.1617, simple_loss=0.2513, pruned_loss=0.03606, over 6600.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2523, pruned_loss=0.03548, over 1428646.73 frames.], batch size: 31, lr: 3.52e-04
2022-05-15 04:34:43,569 INFO [train.py:812] (3/8) Epoch 22, batch 3600, loss[loss=0.1363, simple_loss=0.2183, pruned_loss=0.0272, over 7271.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2511, pruned_loss=0.03512, over 1424201.26 frames.], batch size: 17, lr: 3.51e-04
2022-05-15 04:35:42,253 INFO [train.py:812] (3/8) Epoch 22, batch 3650, loss[loss=0.1732, simple_loss=0.266, pruned_loss=0.04019, over 7368.00 frames.], tot_loss[loss=0.161, simple_loss=0.2514, pruned_loss=0.0353, over 1425906.23 frames.], batch size: 23, lr: 3.51e-04
2022-05-15 04:36:47,194 INFO [train.py:812] (3/8) Epoch 22, batch 3700, loss[loss=0.1556, simple_loss=0.2445, pruned_loss=0.03332, over 7209.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2508, pruned_loss=0.03493, over 1427685.34 frames.], batch size: 21, lr: 3.51e-04
2022-05-15 04:37:46,503 INFO [train.py:812] (3/8) Epoch 22, batch 3750, loss[loss=0.1473, simple_loss=0.2366, pruned_loss=0.02895, over 6991.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03495, over 1431221.22 frames.], batch size: 16, lr: 3.51e-04
2022-05-15 04:38:46,197 INFO [train.py:812] (3/8) Epoch 22, batch 3800, loss[loss=0.1754, simple_loss=0.2595, pruned_loss=0.04568, over 5348.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2497, pruned_loss=0.03464, over 1425000.42 frames.], batch size: 52, lr: 3.51e-04
2022-05-15 04:39:43,941 INFO [train.py:812] (3/8) Epoch 22, batch 3850, loss[loss=0.2115, simple_loss=0.2927, pruned_loss=0.06515, over 7229.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2504, pruned_loss=0.03466, over 1427405.22 frames.], batch size: 20, lr: 3.51e-04
2022-05-15 04:40:43,465 INFO [train.py:812] (3/8) Epoch 22, batch 3900, loss[loss=0.159, simple_loss=0.2552, pruned_loss=0.03142, over 6462.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2503, pruned_loss=0.03457, over 1427483.54 frames.], batch size: 38, lr: 3.51e-04
2022-05-15 04:41:41,330 INFO [train.py:812] (3/8) Epoch 22, batch 3950, loss[loss=0.1324, simple_loss=0.2099, pruned_loss=0.02741, over 7282.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.0344, over 1425968.25 frames.], batch size: 17, lr: 3.51e-04
2022-05-15 04:42:39,859 INFO [train.py:812] (3/8) Epoch 22, batch 4000, loss[loss=0.1759, simple_loss=0.2791, pruned_loss=0.03636, over 7327.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2506, pruned_loss=0.03462, over 1425682.62 frames.], batch size: 21, lr: 3.51e-04
2022-05-15 04:43:37,305 INFO [train.py:812] (3/8) Epoch 22, batch 4050, loss[loss=0.1486, simple_loss=0.2419, pruned_loss=0.02769, over 7366.00 frames.], tot_loss[loss=0.16, simple_loss=0.2506, pruned_loss=0.03468, over 1423162.69 frames.], batch size: 19, lr: 3.51e-04
2022-05-15 04:44:35,620 INFO [train.py:812] (3/8) Epoch 22, batch 4100, loss[loss=0.1379, simple_loss=0.2304, pruned_loss=0.02273, over 7336.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2501, pruned_loss=0.03429, over 1423950.38 frames.], batch size: 20, lr: 3.51e-04
2022-05-15 04:45:34,806 INFO [train.py:812] (3/8) Epoch 22, batch 4150, loss[loss=0.1687, simple_loss=0.2521, pruned_loss=0.04265, over 7066.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03423, over 1419382.41 frames.], batch size: 18, lr: 3.51e-04
2022-05-15 04:46:33,508 INFO [train.py:812] (3/8) Epoch 22, batch 4200, loss[loss=0.1854, simple_loss=0.2694, pruned_loss=0.05074, over 7150.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2502, pruned_loss=0.03442, over 1414848.42 frames.], batch size: 20, lr: 3.50e-04
2022-05-15 04:47:30,290 INFO [train.py:812] (3/8) Epoch 22, batch 4250, loss[loss=0.176, simple_loss=0.2723, pruned_loss=0.03987, over 6739.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2517, pruned_loss=0.03534, over 1408751.75 frames.], batch size: 31, lr: 3.50e-04
2022-05-15 04:48:27,308 INFO [train.py:812] (3/8) Epoch 22, batch 4300, loss[loss=0.1682, simple_loss=0.2693, pruned_loss=0.03355, over 7277.00 frames.], tot_loss[loss=0.1613, simple_loss=0.252, pruned_loss=0.03526, over 1411517.15 frames.], batch size: 24, lr: 3.50e-04
2022-05-15 04:49:26,470 INFO [train.py:812] (3/8) Epoch 22, batch 4350, loss[loss=0.167, simple_loss=0.2634, pruned_loss=0.03532, over 7339.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2529, pruned_loss=0.03564, over 1408424.40 frames.], batch size: 22, lr: 3.50e-04
2022-05-15 04:50:35,273 INFO [train.py:812] (3/8) Epoch 22, batch 4400, loss[loss=0.1494, simple_loss=0.239, pruned_loss=0.02985, over 7109.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2533, pruned_loss=0.03596, over 1402040.53 frames.], batch size: 21, lr: 3.50e-04
2022-05-15 04:51:33,775 INFO [train.py:812] (3/8) Epoch 22, batch 4450, loss[loss=0.1865, simple_loss=0.2761, pruned_loss=0.04843, over 7341.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2544, pruned_loss=0.0366, over 1398227.16 frames.], batch size: 22, lr: 3.50e-04
2022-05-15 04:52:33,291 INFO [train.py:812] (3/8) Epoch 22, batch 4500, loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03254, over 7077.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2553, pruned_loss=0.03729, over 1388007.05 frames.], batch size: 28, lr: 3.50e-04
2022-05-15 04:53:50,569 INFO [train.py:812] (3/8) Epoch 22, batch 4550, loss[loss=0.2064, simple_loss=0.2857, pruned_loss=0.06354, over 5306.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2564, pruned_loss=0.03821, over 1346417.32 frames.], batch size: 52, lr: 3.50e-04
2022-05-15 04:55:29,962 INFO [train.py:812] (3/8) Epoch 23, batch 0, loss[loss=0.1423, simple_loss=0.2325, pruned_loss=0.02607, over 7229.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2325, pruned_loss=0.02607, over 7229.00 frames.], batch size: 16, lr: 3.42e-04
2022-05-15 04:56:28,536 INFO [train.py:812] (3/8) Epoch 23, batch 50, loss[loss=0.1448, simple_loss=0.2333, pruned_loss=0.02812, over 7159.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2494, pruned_loss=0.03295, over 318866.97 frames.], batch size: 19, lr: 3.42e-04
2022-05-15 04:57:26,780 INFO [train.py:812] (3/8) Epoch 23, batch 100, loss[loss=0.1555, simple_loss=0.2452, pruned_loss=0.03285, over 7292.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2501, pruned_loss=0.03327, over 565150.47 frames.], batch size: 18, lr: 3.42e-04
2022-05-15 04:58:25,155 INFO [train.py:812] (3/8) Epoch 23, batch 150, loss[loss=0.1753, simple_loss=0.2688, pruned_loss=0.04088, over 7305.00 frames.], tot_loss[loss=0.16, simple_loss=0.2513, pruned_loss=0.03437, over 753243.47 frames.], batch size: 24, lr: 3.42e-04
2022-05-15 04:59:34,119 INFO [train.py:812] (3/8) Epoch 23, batch 200, loss[loss=0.1551, simple_loss=0.2566, pruned_loss=0.02679, over 6512.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2516, pruned_loss=0.03486, over 901946.34 frames.], batch size: 38, lr: 3.42e-04
2022-05-15 05:00:33,212 INFO [train.py:812] (3/8) Epoch 23, batch 250, loss[loss=0.1844, simple_loss=0.2735, pruned_loss=0.04767, over 7185.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2513, pruned_loss=0.03494, over 1016862.28 frames.], batch size: 23, lr: 3.42e-04
2022-05-15 05:01:30,500 INFO [train.py:812] (3/8) Epoch 23, batch 300, loss[loss=0.1407, simple_loss=0.2282, pruned_loss=0.02658, over 7162.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2514, pruned_loss=0.03513, over 1102179.31 frames.], batch size: 19, lr: 3.42e-04
2022-05-15 05:02:29,200 INFO [train.py:812] (3/8) Epoch 23, batch 350, loss[loss=0.1816, simple_loss=0.2742, pruned_loss=0.04449, over 7336.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2506, pruned_loss=0.03487, over 1176665.59 frames.], batch size: 22, lr: 3.42e-04
2022-05-15 05:03:27,246 INFO [train.py:812] (3/8) Epoch 23, batch 400, loss[loss=0.1556, simple_loss=0.2463, pruned_loss=0.03247, over 7186.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2507, pruned_loss=0.0346, over 1229734.12 frames.], batch size: 23, lr: 3.42e-04
2022-05-15 05:04:26,524 INFO [train.py:812] (3/8) Epoch 23, batch 450, loss[loss=0.1619, simple_loss=0.2504, pruned_loss=0.03667, over 7247.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2521, pruned_loss=0.03542, over 1271303.03 frames.], batch size: 24, lr: 3.42e-04
2022-05-15 05:05:24,823 INFO [train.py:812] (3/8) Epoch 23, batch 500, loss[loss=0.1667, simple_loss=0.2478, pruned_loss=0.0428, over 6778.00 frames.], tot_loss[loss=0.1613, simple_loss=0.252, pruned_loss=0.03527, over 1306184.39 frames.], batch size: 15, lr: 3.41e-04
2022-05-15 05:06:21,986 INFO [train.py:812] (3/8) Epoch 23, batch 550, loss[loss=0.1616, simple_loss=0.2506, pruned_loss=0.0363, over 7307.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2511, pruned_loss=0.03509, over 1336534.76 frames.], batch size: 24, lr: 3.41e-04
2022-05-15 05:07:20,816 INFO [train.py:812] (3/8) Epoch 23, batch 600, loss[loss=0.1804, simple_loss=0.2656, pruned_loss=0.04763, over 7119.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2513, pruned_loss=0.0349, over 1358629.56 frames.], batch size: 21, lr: 3.41e-04
2022-05-15 05:08:19,866 INFO [train.py:812] (3/8) Epoch 23, batch 650, loss[loss=0.1522, simple_loss=0.2569, pruned_loss=0.02375, over 6847.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2515, pruned_loss=0.0347, over 1373955.28 frames.], batch size: 31, lr: 3.41e-04
2022-05-15 05:09:19,440 INFO [train.py:812] (3/8) Epoch 23, batch 700, loss[loss=0.189, simple_loss=0.275, pruned_loss=0.0515, over 4899.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2516, pruned_loss=0.03471, over 1379747.86 frames.], batch size: 52, lr: 3.41e-04
2022-05-15 05:10:18,451 INFO [train.py:812] (3/8) Epoch 23, batch 750, loss[loss=0.1673, simple_loss=0.2653, pruned_loss=0.03463, over 7194.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2516, pruned_loss=0.03446, over 1392239.25 frames.], batch size: 23, lr: 3.41e-04
2022-05-15 05:11:17,820 INFO [train.py:812] (3/8) Epoch 23, batch 800, loss[loss=0.1649, simple_loss=0.2544, pruned_loss=0.03766, over 7368.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2512, pruned_loss=0.0345, over 1395892.76 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:12:15,507 INFO [train.py:812] (3/8) Epoch 23, batch 850, loss[loss=0.144, simple_loss=0.2437, pruned_loss=0.02215, over 7436.00 frames.], tot_loss[loss=0.16, simple_loss=0.2511, pruned_loss=0.03443, over 1403493.40 frames.], batch size: 20, lr: 3.41e-04
2022-05-15 05:13:14,530 INFO [train.py:812] (3/8) Epoch 23, batch 900, loss[loss=0.1621, simple_loss=0.2455, pruned_loss=0.03931, over 7160.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2524, pruned_loss=0.03491, over 1408203.46 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:14:13,163 INFO [train.py:812] (3/8) Epoch 23, batch 950, loss[loss=0.187, simple_loss=0.2881, pruned_loss=0.04298, over 7039.00 frames.], tot_loss[loss=0.1617, simple_loss=0.253, pruned_loss=0.03522, over 1410175.07 frames.], batch size: 28, lr: 3.41e-04
2022-05-15 05:15:13,121 INFO [train.py:812] (3/8) Epoch 23, batch 1000, loss[loss=0.1493, simple_loss=0.2521, pruned_loss=0.02325, over 7360.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2524, pruned_loss=0.03466, over 1417500.78 frames.], batch size: 19, lr: 3.41e-04
2022-05-15 05:16:12,063 INFO [train.py:812] (3/8) Epoch 23, batch 1050, loss[loss=0.1726, simple_loss=0.2555, pruned_loss=0.04488, over 5286.00 frames.], tot_loss[loss=0.1609, simple_loss=0.252, pruned_loss=0.03488, over 1418126.30 frames.], batch size: 53, lr: 3.41e-04
2022-05-15 05:17:11,003 INFO [train.py:812] (3/8) Epoch 23, batch 1100, loss[loss=0.1161, simple_loss=0.2009, pruned_loss=0.01561, over 7283.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2515, pruned_loss=0.03441, over 1418237.64 frames.], batch size: 17, lr: 3.40e-04
2022-05-15 05:18:09,896 INFO [train.py:812] (3/8) Epoch 23, batch 1150, loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03517, over 7429.00 frames.], tot_loss[loss=0.16, simple_loss=0.2516, pruned_loss=0.03418, over 1422256.47 frames.], batch size: 20, lr: 3.40e-04
2022-05-15 05:19:09,542 INFO [train.py:812] (3/8) Epoch 23, batch 1200, loss[loss=0.1586, simple_loss=0.2375, pruned_loss=0.03983, over 7286.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2508, pruned_loss=0.03411, over 1421174.80 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:20:07,295 INFO [train.py:812] (3/8) Epoch 23, batch 1250, loss[loss=0.1447, simple_loss=0.2196, pruned_loss=0.0349, over 6829.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2499, pruned_loss=0.0339, over 1424515.23 frames.], batch size: 15, lr: 3.40e-04
2022-05-15 05:21:05,549 INFO [train.py:812] (3/8) Epoch 23, batch 1300, loss[loss=0.1821, simple_loss=0.2807, pruned_loss=0.04168, over 7215.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2494, pruned_loss=0.03377, over 1427649.20 frames.], batch size: 23, lr: 3.40e-04
2022-05-15 05:22:03,019 INFO [train.py:812] (3/8) Epoch 23, batch 1350, loss[loss=0.1274, simple_loss=0.2124, pruned_loss=0.02121, over 7263.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2489, pruned_loss=0.03374, over 1427473.48 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:23:02,495 INFO [train.py:812] (3/8) Epoch 23, batch 1400, loss[loss=0.1554, simple_loss=0.251, pruned_loss=0.02992, over 7117.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2488, pruned_loss=0.03352, over 1427525.74 frames.], batch size: 21, lr: 3.40e-04
2022-05-15 05:24:01,071 INFO [train.py:812] (3/8) Epoch 23, batch 1450, loss[loss=0.1429, simple_loss=0.2283, pruned_loss=0.02877, over 7399.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2491, pruned_loss=0.03381, over 1420895.35 frames.], batch size: 18, lr: 3.40e-04
2022-05-15 05:24:59,741 INFO [train.py:812] (3/8) Epoch 23, batch 1500, loss[loss=0.1617, simple_loss=0.2577, pruned_loss=0.03281, over 7091.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2481, pruned_loss=0.03361, over 1422742.02 frames.], batch size: 28, lr: 3.40e-04
2022-05-15 05:25:58,345 INFO [train.py:812] (3/8) Epoch 23, batch 1550, loss[loss=0.1443, simple_loss=0.2394, pruned_loss=0.02459, over 7346.00 frames.], tot_loss[loss=0.1585, simple_loss=0.249, pruned_loss=0.03398, over 1414651.91 frames.], batch size: 19, lr: 3.40e-04
2022-05-15 05:26:57,175 INFO [train.py:812] (3/8) Epoch 23, batch 1600, loss[loss=0.1653, simple_loss=0.253, pruned_loss=0.03881, over 7212.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2499, pruned_loss=0.03438, over 1412612.89 frames.], batch size: 21, lr: 3.40e-04
2022-05-15 05:27:55,177 INFO [train.py:812] (3/8) Epoch 23, batch 1650, loss[loss=0.1871, simple_loss=0.2727, pruned_loss=0.05077, over 7363.00 frames.], tot_loss[loss=0.159, simple_loss=0.2492, pruned_loss=0.03435, over 1415757.46 frames.], batch size: 23, lr: 3.40e-04
2022-05-15 05:28:54,099 INFO [train.py:812] (3/8) Epoch 23, batch 1700, loss[loss=0.1365, simple_loss=0.2205, pruned_loss=0.02627, over 7395.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03422, over 1416560.56 frames.], batch size: 18, lr: 3.39e-04
2022-05-15 05:29:50,560 INFO [train.py:812] (3/8) Epoch 23, batch 1750, loss[loss=0.1786, simple_loss=0.267, pruned_loss=0.04512, over 7150.00 frames.], tot_loss[loss=0.16, simple_loss=0.2508, pruned_loss=0.03459, over 1414983.09 frames.], batch size: 26, lr: 3.39e-04
2022-05-15 05:30:48,706 INFO [train.py:812] (3/8) Epoch 23, batch 1800, loss[loss=0.2269, simple_loss=0.3082, pruned_loss=0.07284, over 4815.00 frames.], tot_loss[loss=0.1603, simple_loss=0.251, pruned_loss=0.03483, over 1412290.11 frames.], batch size: 52, lr: 3.39e-04
2022-05-15 05:31:46,090 INFO [train.py:812] (3/8) Epoch 23, batch 1850, loss[loss=0.1317, simple_loss=0.2203, pruned_loss=0.02157, over 7419.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2503, pruned_loss=0.03424, over 1417900.51 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:32:43,996 INFO [train.py:812] (3/8) Epoch 23, batch 1900, loss[loss=0.156, simple_loss=0.2528, pruned_loss=0.02966, over 7143.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2501, pruned_loss=0.03413, over 1421700.96 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:33:42,348 INFO [train.py:812] (3/8) Epoch 23, batch 1950, loss[loss=0.151, simple_loss=0.2498, pruned_loss=0.02605, over 7148.00 frames.], tot_loss[loss=0.1593, simple_loss=0.25, pruned_loss=0.03424, over 1419119.81 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:34:41,195 INFO [train.py:812] (3/8) Epoch 23, batch 2000, loss[loss=0.137, simple_loss=0.2317, pruned_loss=0.02116, over 7256.00 frames.], tot_loss[loss=0.1598, simple_loss=0.251, pruned_loss=0.03427, over 1422088.51 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:35:40,289 INFO [train.py:812] (3/8) Epoch 23, batch 2050, loss[loss=0.145, simple_loss=0.2357, pruned_loss=0.02712, over 7235.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2505, pruned_loss=0.03422, over 1426003.39 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:36:39,468 INFO [train.py:812] (3/8) Epoch 23, batch 2100, loss[loss=0.2005, simple_loss=0.2854, pruned_loss=0.0578, over 7184.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2505, pruned_loss=0.03464, over 1420543.17 frames.], batch size: 23, lr: 3.39e-04
2022-05-15 05:37:38,018 INFO [train.py:812] (3/8) Epoch 23, batch 2150, loss[loss=0.1364, simple_loss=0.2324, pruned_loss=0.02023, over 7157.00 frames.], tot_loss[loss=0.1603, simple_loss=0.251, pruned_loss=0.03477, over 1421318.54 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:38:37,635 INFO [train.py:812] (3/8) Epoch 23, batch 2200, loss[loss=0.1711, simple_loss=0.2644, pruned_loss=0.03893, over 7152.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2512, pruned_loss=0.03494, over 1416050.79 frames.], batch size: 20, lr: 3.39e-04
2022-05-15 05:39:36,693 INFO [train.py:812] (3/8) Epoch 23, batch 2250, loss[loss=0.1374, simple_loss=0.2356, pruned_loss=0.01957, over 7156.00 frames.], tot_loss[loss=0.16, simple_loss=0.2507, pruned_loss=0.03468, over 1412341.51 frames.], batch size: 19, lr: 3.39e-04
2022-05-15 05:40:35,579 INFO [train.py:812] (3/8) Epoch 23, batch 2300, loss[loss=0.1727, simple_loss=0.2629, pruned_loss=0.04125, over 7319.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2495, pruned_loss=0.03446, over 1414013.00 frames.], batch size: 21, lr: 3.38e-04
2022-05-15 05:41:34,381 INFO [train.py:812] (3/8) Epoch 23, batch 2350, loss[loss=0.1587, simple_loss=0.2529, pruned_loss=0.03228, over 7352.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2493, pruned_loss=0.0342, over 1415833.31 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:42:33,285 INFO [train.py:812] (3/8) Epoch 23, batch 2400, loss[loss=0.1584, simple_loss=0.2527, pruned_loss=0.03201, over 7311.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2501, pruned_loss=0.03416, over 1418545.72 frames.], batch size: 24, lr: 3.38e-04
2022-05-15 05:43:31,220 INFO [train.py:812] (3/8) Epoch 23, batch 2450, loss[loss=0.1686, simple_loss=0.2599, pruned_loss=0.03861, over 7194.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2506, pruned_loss=0.03434, over 1422425.63 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:44:30,336 INFO [train.py:812] (3/8) Epoch 23, batch 2500, loss[loss=0.1487, simple_loss=0.2452, pruned_loss=0.02614, over 6238.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2489, pruned_loss=0.0341, over 1419767.03 frames.], batch size: 37, lr: 3.38e-04
2022-05-15 05:45:29,326 INFO [train.py:812] (3/8) Epoch 23, batch 2550, loss[loss=0.2018, simple_loss=0.2937, pruned_loss=0.05495, over 7361.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2488, pruned_loss=0.03391, over 1420390.09 frames.], batch size: 23, lr: 3.38e-04
2022-05-15 05:46:26,769 INFO [train.py:812] (3/8) Epoch 23, batch 2600, loss[loss=0.1444, simple_loss=0.2475, pruned_loss=0.02067, over 7330.00 frames.], tot_loss[loss=0.159, simple_loss=0.2493, pruned_loss=0.03437, over 1424743.22 frames.], batch size: 22, lr: 3.38e-04
2022-05-15 05:47:25,381 INFO [train.py:812] (3/8) Epoch 23, batch 2650, loss[loss=0.1867, simple_loss=0.2652, pruned_loss=0.05416, over 7270.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2486, pruned_loss=0.03425, over 1422090.05 frames.], batch size: 25, lr: 3.38e-04
2022-05-15 05:48:25,396 INFO [train.py:812] (3/8) Epoch 23, batch 2700, loss[loss=0.1565, simple_loss=0.2533, pruned_loss=0.02981, over 7158.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2488, pruned_loss=0.03415, over 1421848.89 frames.], batch size: 19, lr: 3.38e-04
2022-05-15 05:49:24,343 INFO [train.py:812] (3/8) Epoch 23, batch 2750, loss[loss=0.1545, simple_loss=0.2412, pruned_loss=0.03389, over 7168.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2494, pruned_loss=0.03494, over 1419792.73 frames.], batch size: 18, lr: 3.38e-04
2022-05-15 05:50:23,647 INFO [train.py:812] (3/8) Epoch 23, batch 2800, loss[loss=0.1558, simple_loss=0.2392, pruned_loss=0.03621, over 7169.00 frames.], tot_loss[loss=0.16, simple_loss=0.2497, pruned_loss=0.03519, over 1419449.28 frames.], batch size: 18, lr: 3.38e-04
2022-05-15 05:51:22,632 INFO [train.py:812] (3/8) Epoch 23, batch 2850, loss[loss=0.1505, simple_loss=0.2498, pruned_loss=0.02557, over 7054.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2495, pruned_loss=0.03493, over 1421191.23 frames.], batch size: 28, lr: 3.38e-04
2022-05-15 05:52:22,311 INFO [train.py:812] (3/8) Epoch 23, batch 2900, loss[loss=0.1521, simple_loss=0.2472, pruned_loss=0.02847, over 7280.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2491, pruned_loss=0.03451, over 1422923.57 frames.], batch size: 25, lr: 3.37e-04
2022-05-15 05:53:20,360 INFO [train.py:812] (3/8) Epoch 23, batch 2950, loss[loss=0.1812, simple_loss=0.2739, pruned_loss=0.04421, over 7199.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2495, pruned_loss=0.03438, over 1423749.30 frames.], batch size: 22, lr: 3.37e-04
2022-05-15 05:54:18,732 INFO [train.py:812] (3/8) Epoch 23, batch 3000, loss[loss=0.1321, simple_loss=0.217, pruned_loss=0.02365, over 7004.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2497, pruned_loss=0.03422, over 1424053.69 frames.], batch size: 16, lr: 3.37e-04
2022-05-15 05:54:18,733 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 05:54:28,115 INFO [train.py:841] (3/8) 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] (3/8) Epoch 23, batch 3050, loss[loss=0.1539, simple_loss=0.2426, pruned_loss=0.03265, over 7166.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2492, pruned_loss=0.03387, over 1426815.87 frames.], batch size: 19, lr: 3.37e-04
2022-05-15 05:56:31,536 INFO [train.py:812] (3/8) Epoch 23, batch 3100, loss[loss=0.1407, simple_loss=0.2267, pruned_loss=0.02731, over 7247.00 frames.], tot_loss[loss=0.1582, simple_loss=0.249, pruned_loss=0.03377, over 1425583.25 frames.], batch size: 20, lr: 3.37e-04
2022-05-15 05:57:30,932 INFO [train.py:812] (3/8) Epoch 23, batch 3150, loss[loss=0.169, simple_loss=0.2668, pruned_loss=0.03559, over 7333.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2493, pruned_loss=0.03396, over 1426921.34 frames.], batch size: 20, lr: 3.37e-04
2022-05-15 05:58:30,529 INFO [train.py:812] (3/8) Epoch 23, batch 3200, loss[loss=0.1668, simple_loss=0.2724, pruned_loss=0.03055, over 7109.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2492, pruned_loss=0.03372, over 1427536.61 frames.], batch size: 21, lr: 3.37e-04
2022-05-15 05:59:29,571 INFO [train.py:812] (3/8) Epoch 23, batch 3250, loss[loss=0.1702, simple_loss=0.2549, pruned_loss=0.0428, over 6530.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2507, pruned_loss=0.03428, over 1422060.79 frames.], batch size: 39, lr: 3.37e-04
2022-05-15 06:00:29,698 INFO [train.py:812] (3/8) Epoch 23, batch 3300, loss[loss=0.188, simple_loss=0.2849, pruned_loss=0.04554, over 7281.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2504, pruned_loss=0.03414, over 1423408.32 frames.], batch size: 24, lr: 3.37e-04
2022-05-15 06:01:29,019 INFO [train.py:812] (3/8) Epoch 23, batch 3350, loss[loss=0.1412, simple_loss=0.2328, pruned_loss=0.02482, over 7168.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03366, over 1428162.26 frames.], batch size: 26, lr: 3.37e-04
2022-05-15 06:02:28,580 INFO [train.py:812] (3/8) Epoch 23, batch 3400, loss[loss=0.1371, simple_loss=0.2325, pruned_loss=0.02088, over 7171.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2487, pruned_loss=0.03345, over 1429492.49 frames.], batch size: 19, lr: 3.37e-04
2022-05-15 06:03:27,785 INFO [train.py:812] (3/8) Epoch 23, batch 3450, loss[loss=0.1569, simple_loss=0.2468, pruned_loss=0.03352, over 6863.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2483, pruned_loss=0.03371, over 1430405.19 frames.], batch size: 15, lr: 3.37e-04
2022-05-15 06:04:27,369 INFO [train.py:812] (3/8) Epoch 23, batch 3500, loss[loss=0.1443, simple_loss=0.2286, pruned_loss=0.03001, over 7174.00 frames.], tot_loss[loss=0.1564, simple_loss=0.247, pruned_loss=0.0329, over 1431474.13 frames.], batch size: 16, lr: 3.37e-04
2022-05-15 06:05:25,896 INFO [train.py:812] (3/8) Epoch 23, batch 3550, loss[loss=0.152, simple_loss=0.2322, pruned_loss=0.03591, over 7414.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2469, pruned_loss=0.03267, over 1430867.12 frames.], batch size: 18, lr: 3.36e-04
2022-05-15 06:06:25,039 INFO [train.py:812] (3/8) Epoch 23, batch 3600, loss[loss=0.132, simple_loss=0.2173, pruned_loss=0.0234, over 7273.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03281, over 1432267.50 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:07:24,127 INFO [train.py:812] (3/8) Epoch 23, batch 3650, loss[loss=0.1704, simple_loss=0.2565, pruned_loss=0.04218, over 6413.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03288, over 1431694.82 frames.], batch size: 38, lr: 3.36e-04
2022-05-15 06:08:33,458 INFO [train.py:812] (3/8) Epoch 23, batch 3700, loss[loss=0.1771, simple_loss=0.2734, pruned_loss=0.04036, over 7160.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2494, pruned_loss=0.03373, over 1430944.93 frames.], batch size: 19, lr: 3.36e-04
2022-05-15 06:09:32,119 INFO [train.py:812] (3/8) Epoch 23, batch 3750, loss[loss=0.1432, simple_loss=0.227, pruned_loss=0.02964, over 7273.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2497, pruned_loss=0.03393, over 1428276.95 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:10:31,402 INFO [train.py:812] (3/8) Epoch 23, batch 3800, loss[loss=0.1755, simple_loss=0.27, pruned_loss=0.04044, over 7392.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2498, pruned_loss=0.03397, over 1429433.81 frames.], batch size: 23, lr: 3.36e-04
2022-05-15 06:11:30,123 INFO [train.py:812] (3/8) Epoch 23, batch 3850, loss[loss=0.1464, simple_loss=0.2473, pruned_loss=0.0227, over 7048.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2489, pruned_loss=0.03374, over 1429330.36 frames.], batch size: 28, lr: 3.36e-04
2022-05-15 06:12:28,357 INFO [train.py:812] (3/8) Epoch 23, batch 3900, loss[loss=0.1558, simple_loss=0.2524, pruned_loss=0.02961, over 7125.00 frames.], tot_loss[loss=0.1596, simple_loss=0.25, pruned_loss=0.03462, over 1429472.75 frames.], batch size: 21, lr: 3.36e-04
2022-05-15 06:13:25,760 INFO [train.py:812] (3/8) Epoch 23, batch 3950, loss[loss=0.1533, simple_loss=0.2401, pruned_loss=0.03324, over 7159.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2505, pruned_loss=0.03454, over 1429097.25 frames.], batch size: 19, lr: 3.36e-04
2022-05-15 06:14:23,058 INFO [train.py:812] (3/8) Epoch 23, batch 4000, loss[loss=0.1375, simple_loss=0.2174, pruned_loss=0.02877, over 7287.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2502, pruned_loss=0.0341, over 1426042.43 frames.], batch size: 17, lr: 3.36e-04
2022-05-15 06:15:21,541 INFO [train.py:812] (3/8) Epoch 23, batch 4050, loss[loss=0.1669, simple_loss=0.2488, pruned_loss=0.0425, over 7248.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2511, pruned_loss=0.0345, over 1421013.01 frames.], batch size: 16, lr: 3.36e-04
2022-05-15 06:16:21,791 INFO [train.py:812] (3/8) Epoch 23, batch 4100, loss[loss=0.1576, simple_loss=0.239, pruned_loss=0.03816, over 6796.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2507, pruned_loss=0.03436, over 1418873.89 frames.], batch size: 15, lr: 3.36e-04
2022-05-15 06:17:19,467 INFO [train.py:812] (3/8) Epoch 23, batch 4150, loss[loss=0.1405, simple_loss=0.2385, pruned_loss=0.02131, over 7324.00 frames.], tot_loss[loss=0.1596, simple_loss=0.251, pruned_loss=0.03415, over 1418683.26 frames.], batch size: 21, lr: 3.35e-04
2022-05-15 06:18:18,886 INFO [train.py:812] (3/8) Epoch 23, batch 4200, loss[loss=0.131, simple_loss=0.2147, pruned_loss=0.02368, over 7016.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2509, pruned_loss=0.0339, over 1422501.91 frames.], batch size: 16, lr: 3.35e-04
2022-05-15 06:19:17,842 INFO [train.py:812] (3/8) Epoch 23, batch 4250, loss[loss=0.1742, simple_loss=0.2652, pruned_loss=0.04163, over 7232.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2504, pruned_loss=0.03368, over 1423202.93 frames.], batch size: 20, lr: 3.35e-04
2022-05-15 06:20:16,267 INFO [train.py:812] (3/8) Epoch 23, batch 4300, loss[loss=0.1366, simple_loss=0.226, pruned_loss=0.02359, over 7155.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03338, over 1420062.69 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:21:15,777 INFO [train.py:812] (3/8) Epoch 23, batch 4350, loss[loss=0.1453, simple_loss=0.2273, pruned_loss=0.03166, over 6804.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03319, over 1421145.09 frames.], batch size: 15, lr: 3.35e-04
2022-05-15 06:22:15,638 INFO [train.py:812] (3/8) Epoch 23, batch 4400, loss[loss=0.1584, simple_loss=0.2432, pruned_loss=0.03678, over 7059.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2477, pruned_loss=0.03323, over 1418591.51 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:23:14,860 INFO [train.py:812] (3/8) Epoch 23, batch 4450, loss[loss=0.2041, simple_loss=0.2844, pruned_loss=0.0619, over 4955.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2482, pruned_loss=0.03366, over 1412942.34 frames.], batch size: 52, lr: 3.35e-04
2022-05-15 06:24:12,957 INFO [train.py:812] (3/8) Epoch 23, batch 4500, loss[loss=0.1485, simple_loss=0.2332, pruned_loss=0.03185, over 7062.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2489, pruned_loss=0.03362, over 1412081.80 frames.], batch size: 18, lr: 3.35e-04
2022-05-15 06:25:11,004 INFO [train.py:812] (3/8) Epoch 23, batch 4550, loss[loss=0.2033, simple_loss=0.2802, pruned_loss=0.06319, over 5151.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2518, pruned_loss=0.03548, over 1355279.06 frames.], batch size: 52, lr: 3.35e-04
2022-05-15 06:26:16,434 INFO [train.py:812] (3/8) Epoch 24, batch 0, loss[loss=0.1419, simple_loss=0.2171, pruned_loss=0.03338, over 6844.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2171, pruned_loss=0.03338, over 6844.00 frames.], batch size: 15, lr: 3.28e-04
2022-05-15 06:27:14,045 INFO [train.py:812] (3/8) Epoch 24, batch 50, loss[loss=0.1422, simple_loss=0.2229, pruned_loss=0.03077, over 7272.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.03349, over 316762.67 frames.], batch size: 17, lr: 3.28e-04
2022-05-15 06:28:13,407 INFO [train.py:812] (3/8) Epoch 24, batch 100, loss[loss=0.1788, simple_loss=0.2815, pruned_loss=0.03805, over 7332.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2499, pruned_loss=0.03328, over 568049.26 frames.], batch size: 20, lr: 3.28e-04
2022-05-15 06:29:11,050 INFO [train.py:812] (3/8) Epoch 24, batch 150, loss[loss=0.1823, simple_loss=0.2782, pruned_loss=0.04318, over 7379.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2502, pruned_loss=0.03423, over 753495.41 frames.], batch size: 23, lr: 3.28e-04
2022-05-15 06:30:10,076 INFO [train.py:812] (3/8) Epoch 24, batch 200, loss[loss=0.1725, simple_loss=0.2594, pruned_loss=0.0428, over 7195.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2485, pruned_loss=0.03343, over 903947.49 frames.], batch size: 22, lr: 3.28e-04
2022-05-15 06:31:07,643 INFO [train.py:812] (3/8) Epoch 24, batch 250, loss[loss=0.1673, simple_loss=0.2606, pruned_loss=0.03699, over 7414.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2478, pruned_loss=0.03316, over 1016293.16 frames.], batch size: 21, lr: 3.28e-04
2022-05-15 06:32:07,184 INFO [train.py:812] (3/8) Epoch 24, batch 300, loss[loss=0.1523, simple_loss=0.2447, pruned_loss=0.02994, over 7150.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2481, pruned_loss=0.03327, over 1107245.45 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:33:03,993 INFO [train.py:812] (3/8) Epoch 24, batch 350, loss[loss=0.1904, simple_loss=0.2811, pruned_loss=0.04989, over 7294.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2484, pruned_loss=0.03314, over 1178596.11 frames.], batch size: 25, lr: 3.27e-04
2022-05-15 06:34:01,082 INFO [train.py:812] (3/8) Epoch 24, batch 400, loss[loss=0.1895, simple_loss=0.2754, pruned_loss=0.05178, over 7274.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03327, over 1228660.81 frames.], batch size: 24, lr: 3.27e-04
2022-05-15 06:34:58,902 INFO [train.py:812] (3/8) Epoch 24, batch 450, loss[loss=0.1519, simple_loss=0.2466, pruned_loss=0.0286, over 7149.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2499, pruned_loss=0.03338, over 1274417.70 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:35:57,362 INFO [train.py:812] (3/8) Epoch 24, batch 500, loss[loss=0.1426, simple_loss=0.2338, pruned_loss=0.02575, over 7355.00 frames.], tot_loss[loss=0.1582, simple_loss=0.25, pruned_loss=0.03321, over 1306061.69 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:36:55,889 INFO [train.py:812] (3/8) Epoch 24, batch 550, loss[loss=0.1687, simple_loss=0.2607, pruned_loss=0.03834, over 7211.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2494, pruned_loss=0.03316, over 1335181.08 frames.], batch size: 22, lr: 3.27e-04
2022-05-15 06:37:55,361 INFO [train.py:812] (3/8) Epoch 24, batch 600, loss[loss=0.1661, simple_loss=0.2597, pruned_loss=0.03631, over 7369.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03286, over 1353004.55 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:38:54,592 INFO [train.py:812] (3/8) Epoch 24, batch 650, loss[loss=0.1339, simple_loss=0.2171, pruned_loss=0.02533, over 7359.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03293, over 1363791.51 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:39:54,785 INFO [train.py:812] (3/8) Epoch 24, batch 700, loss[loss=0.1718, simple_loss=0.2609, pruned_loss=0.04137, over 7128.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2467, pruned_loss=0.03285, over 1380423.58 frames.], batch size: 26, lr: 3.27e-04
2022-05-15 06:40:53,828 INFO [train.py:812] (3/8) Epoch 24, batch 750, loss[loss=0.1302, simple_loss=0.2147, pruned_loss=0.02288, over 6982.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03285, over 1391610.29 frames.], batch size: 16, lr: 3.27e-04
2022-05-15 06:41:53,040 INFO [train.py:812] (3/8) Epoch 24, batch 800, loss[loss=0.1284, simple_loss=0.2136, pruned_loss=0.02154, over 7255.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03285, over 1399010.39 frames.], batch size: 19, lr: 3.27e-04
2022-05-15 06:42:52,215 INFO [train.py:812] (3/8) Epoch 24, batch 850, loss[loss=0.1699, simple_loss=0.2646, pruned_loss=0.03757, over 6771.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2472, pruned_loss=0.03271, over 1405513.06 frames.], batch size: 31, lr: 3.27e-04
2022-05-15 06:43:51,471 INFO [train.py:812] (3/8) Epoch 24, batch 900, loss[loss=0.1291, simple_loss=0.2219, pruned_loss=0.01818, over 7424.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2466, pruned_loss=0.03239, over 1410729.17 frames.], batch size: 20, lr: 3.27e-04
2022-05-15 06:44:50,514 INFO [train.py:812] (3/8) Epoch 24, batch 950, loss[loss=0.1531, simple_loss=0.2513, pruned_loss=0.02745, over 6498.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2459, pruned_loss=0.03256, over 1415294.61 frames.], batch size: 38, lr: 3.26e-04
2022-05-15 06:45:49,544 INFO [train.py:812] (3/8) Epoch 24, batch 1000, loss[loss=0.1734, simple_loss=0.2727, pruned_loss=0.03702, over 7319.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2466, pruned_loss=0.03295, over 1417183.53 frames.], batch size: 21, lr: 3.26e-04
2022-05-15 06:46:47,306 INFO [train.py:812] (3/8) Epoch 24, batch 1050, loss[loss=0.1453, simple_loss=0.2405, pruned_loss=0.02501, over 7232.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2475, pruned_loss=0.0336, over 1411224.24 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:47:46,416 INFO [train.py:812] (3/8) Epoch 24, batch 1100, loss[loss=0.1612, simple_loss=0.2581, pruned_loss=0.03211, over 7140.00 frames.], tot_loss[loss=0.1574, simple_loss=0.248, pruned_loss=0.03346, over 1411629.52 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:48:44,908 INFO [train.py:812] (3/8) Epoch 24, batch 1150, loss[loss=0.1482, simple_loss=0.249, pruned_loss=0.02366, over 6505.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2479, pruned_loss=0.03364, over 1415276.43 frames.], batch size: 38, lr: 3.26e-04
2022-05-15 06:49:42,947 INFO [train.py:812] (3/8) Epoch 24, batch 1200, loss[loss=0.1597, simple_loss=0.2466, pruned_loss=0.03642, over 7169.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2489, pruned_loss=0.03395, over 1417498.23 frames.], batch size: 18, lr: 3.26e-04
2022-05-15 06:50:50,708 INFO [train.py:812] (3/8) Epoch 24, batch 1250, loss[loss=0.1411, simple_loss=0.2388, pruned_loss=0.02167, over 7334.00 frames.], tot_loss[loss=0.1578, simple_loss=0.248, pruned_loss=0.03377, over 1417910.64 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:51:49,896 INFO [train.py:812] (3/8) Epoch 24, batch 1300, loss[loss=0.164, simple_loss=0.2654, pruned_loss=0.03134, over 6780.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2477, pruned_loss=0.03324, over 1419738.92 frames.], batch size: 31, lr: 3.26e-04
2022-05-15 06:52:48,840 INFO [train.py:812] (3/8) Epoch 24, batch 1350, loss[loss=0.1517, simple_loss=0.2341, pruned_loss=0.03466, over 7407.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2489, pruned_loss=0.03382, over 1425469.46 frames.], batch size: 18, lr: 3.26e-04
2022-05-15 06:53:46,293 INFO [train.py:812] (3/8) Epoch 24, batch 1400, loss[loss=0.1731, simple_loss=0.2757, pruned_loss=0.03528, over 7182.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2489, pruned_loss=0.0335, over 1424065.71 frames.], batch size: 26, lr: 3.26e-04
2022-05-15 06:55:13,447 INFO [train.py:812] (3/8) Epoch 24, batch 1450, loss[loss=0.1685, simple_loss=0.2588, pruned_loss=0.03916, over 7144.00 frames.], tot_loss[loss=0.1581, simple_loss=0.249, pruned_loss=0.03361, over 1421917.90 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:56:21,948 INFO [train.py:812] (3/8) Epoch 24, batch 1500, loss[loss=0.1695, simple_loss=0.2572, pruned_loss=0.04095, over 7147.00 frames.], tot_loss[loss=0.1584, simple_loss=0.249, pruned_loss=0.03392, over 1421015.42 frames.], batch size: 20, lr: 3.26e-04
2022-05-15 06:57:21,235 INFO [train.py:812] (3/8) Epoch 24, batch 1550, loss[loss=0.1744, simple_loss=0.2752, pruned_loss=0.03684, over 6639.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2485, pruned_loss=0.03391, over 1421112.91 frames.], batch size: 31, lr: 3.26e-04
2022-05-15 06:58:39,392 INFO [train.py:812] (3/8) Epoch 24, batch 1600, loss[loss=0.1437, simple_loss=0.2469, pruned_loss=0.02031, over 7322.00 frames.], tot_loss[loss=0.1585, simple_loss=0.249, pruned_loss=0.03402, over 1422473.26 frames.], batch size: 20, lr: 3.25e-04
2022-05-15 06:59:37,754 INFO [train.py:812] (3/8) Epoch 24, batch 1650, loss[loss=0.1491, simple_loss=0.2285, pruned_loss=0.03488, over 7237.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2494, pruned_loss=0.03417, over 1414632.61 frames.], batch size: 16, lr: 3.25e-04
2022-05-15 07:00:36,790 INFO [train.py:812] (3/8) Epoch 24, batch 1700, loss[loss=0.1709, simple_loss=0.2691, pruned_loss=0.03637, over 7322.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2492, pruned_loss=0.03394, over 1419161.90 frames.], batch size: 21, lr: 3.25e-04
2022-05-15 07:01:34,454 INFO [train.py:812] (3/8) Epoch 24, batch 1750, loss[loss=0.1486, simple_loss=0.2332, pruned_loss=0.03199, over 7072.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2495, pruned_loss=0.03397, over 1421327.88 frames.], batch size: 18, lr: 3.25e-04
2022-05-15 07:02:33,276 INFO [train.py:812] (3/8) Epoch 24, batch 1800, loss[loss=0.1682, simple_loss=0.265, pruned_loss=0.03565, over 7331.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2496, pruned_loss=0.03385, over 1421828.36 frames.], batch size: 22, lr: 3.25e-04
2022-05-15 07:03:31,325 INFO [train.py:812] (3/8) Epoch 24, batch 1850, loss[loss=0.1674, simple_loss=0.2635, pruned_loss=0.03569, over 7295.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.03381, over 1425628.89 frames.], batch size: 24, lr: 3.25e-04
2022-05-15 07:04:30,221 INFO [train.py:812] (3/8) Epoch 24, batch 1900, loss[loss=0.1536, simple_loss=0.2539, pruned_loss=0.02661, over 7096.00 frames.], tot_loss[loss=0.159, simple_loss=0.2498, pruned_loss=0.03415, over 1423240.97 frames.], batch size: 28, lr: 3.25e-04
2022-05-15 07:05:29,175 INFO [train.py:812] (3/8) Epoch 24, batch 1950, loss[loss=0.153, simple_loss=0.2495, pruned_loss=0.02827, over 7448.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03407, over 1424622.93 frames.], batch size: 22, lr: 3.25e-04
2022-05-15 07:06:27,357 INFO [train.py:812] (3/8) Epoch 24, batch 2000, loss[loss=0.1494, simple_loss=0.234, pruned_loss=0.03243, over 5364.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2505, pruned_loss=0.03428, over 1422959.00 frames.], batch size: 52, lr: 3.25e-04
2022-05-15 07:07:25,813 INFO [train.py:812] (3/8) Epoch 24, batch 2050, loss[loss=0.1357, simple_loss=0.2237, pruned_loss=0.0238, over 7442.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2508, pruned_loss=0.03441, over 1421831.87 frames.], batch size: 20, lr: 3.25e-04
2022-05-15 07:08:23,725 INFO [train.py:812] (3/8) Epoch 24, batch 2100, loss[loss=0.1395, simple_loss=0.2294, pruned_loss=0.02478, over 7021.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2505, pruned_loss=0.03423, over 1422960.08 frames.], batch size: 16, lr: 3.25e-04
2022-05-15 07:09:22,543 INFO [train.py:812] (3/8) Epoch 24, batch 2150, loss[loss=0.1768, simple_loss=0.2514, pruned_loss=0.05108, over 4884.00 frames.], tot_loss[loss=0.159, simple_loss=0.2498, pruned_loss=0.03412, over 1420580.89 frames.], batch size: 52, lr: 3.25e-04
2022-05-15 07:10:21,849 INFO [train.py:812] (3/8) Epoch 24, batch 2200, loss[loss=0.1256, simple_loss=0.2139, pruned_loss=0.01862, over 7150.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2486, pruned_loss=0.03341, over 1419625.24 frames.], batch size: 17, lr: 3.25e-04
2022-05-15 07:11:20,861 INFO [train.py:812] (3/8) Epoch 24, batch 2250, loss[loss=0.1573, simple_loss=0.2524, pruned_loss=0.03107, over 7303.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.0336, over 1409999.10 frames.], batch size: 25, lr: 3.24e-04
2022-05-15 07:12:19,948 INFO [train.py:812] (3/8) Epoch 24, batch 2300, loss[loss=0.1198, simple_loss=0.2056, pruned_loss=0.01701, over 7299.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2472, pruned_loss=0.03293, over 1416437.90 frames.], batch size: 17, lr: 3.24e-04
2022-05-15 07:13:18,782 INFO [train.py:812] (3/8) Epoch 24, batch 2350, loss[loss=0.1472, simple_loss=0.242, pruned_loss=0.02617, over 7345.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2486, pruned_loss=0.0333, over 1417851.80 frames.], batch size: 22, lr: 3.24e-04
2022-05-15 07:14:18,465 INFO [train.py:812] (3/8) Epoch 24, batch 2400, loss[loss=0.136, simple_loss=0.2217, pruned_loss=0.02518, over 7224.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2491, pruned_loss=0.03297, over 1421138.95 frames.], batch size: 16, lr: 3.24e-04
2022-05-15 07:15:15,754 INFO [train.py:812] (3/8) Epoch 24, batch 2450, loss[loss=0.1631, simple_loss=0.2569, pruned_loss=0.03463, over 7226.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2491, pruned_loss=0.03305, over 1417199.37 frames.], batch size: 20, lr: 3.24e-04
2022-05-15 07:16:21,376 INFO [train.py:812] (3/8) Epoch 24, batch 2500, loss[loss=0.1629, simple_loss=0.2482, pruned_loss=0.0388, over 7324.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2483, pruned_loss=0.03296, over 1417831.75 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:17:19,924 INFO [train.py:812] (3/8) Epoch 24, batch 2550, loss[loss=0.1867, simple_loss=0.276, pruned_loss=0.04877, over 5096.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.03308, over 1413703.77 frames.], batch size: 52, lr: 3.24e-04
2022-05-15 07:18:18,694 INFO [train.py:812] (3/8) Epoch 24, batch 2600, loss[loss=0.162, simple_loss=0.2517, pruned_loss=0.03614, over 7288.00 frames.], tot_loss[loss=0.1579, simple_loss=0.249, pruned_loss=0.03342, over 1417022.44 frames.], batch size: 18, lr: 3.24e-04
2022-05-15 07:19:17,318 INFO [train.py:812] (3/8) Epoch 24, batch 2650, loss[loss=0.1541, simple_loss=0.2574, pruned_loss=0.02546, over 7327.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2482, pruned_loss=0.03342, over 1417697.15 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:20:16,532 INFO [train.py:812] (3/8) Epoch 24, batch 2700, loss[loss=0.1589, simple_loss=0.2575, pruned_loss=0.0301, over 7342.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03356, over 1422370.82 frames.], batch size: 22, lr: 3.24e-04
2022-05-15 07:21:15,972 INFO [train.py:812] (3/8) Epoch 24, batch 2750, loss[loss=0.1618, simple_loss=0.259, pruned_loss=0.03231, over 7412.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2483, pruned_loss=0.03336, over 1425740.34 frames.], batch size: 21, lr: 3.24e-04
2022-05-15 07:22:15,053 INFO [train.py:812] (3/8) Epoch 24, batch 2800, loss[loss=0.1456, simple_loss=0.239, pruned_loss=0.02607, over 7248.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03358, over 1422107.51 frames.], batch size: 20, lr: 3.24e-04
2022-05-15 07:23:13,162 INFO [train.py:812] (3/8) Epoch 24, batch 2850, loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.03262, over 7360.00 frames.], tot_loss[loss=0.1595, simple_loss=0.251, pruned_loss=0.03401, over 1422749.82 frames.], batch size: 19, lr: 3.24e-04
2022-05-15 07:24:12,086 INFO [train.py:812] (3/8) Epoch 24, batch 2900, loss[loss=0.155, simple_loss=0.2429, pruned_loss=0.03356, over 7335.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2508, pruned_loss=0.03397, over 1422536.82 frames.], batch size: 25, lr: 3.24e-04
2022-05-15 07:25:09,863 INFO [train.py:812] (3/8) Epoch 24, batch 2950, loss[loss=0.1507, simple_loss=0.2248, pruned_loss=0.03833, over 7316.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2496, pruned_loss=0.03358, over 1426055.43 frames.], batch size: 17, lr: 3.23e-04
2022-05-15 07:26:08,033 INFO [train.py:812] (3/8) Epoch 24, batch 3000, loss[loss=0.1644, simple_loss=0.2519, pruned_loss=0.03844, over 7117.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2493, pruned_loss=0.03359, over 1421785.34 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:26:08,034 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 07:26:15,602 INFO [train.py:841] (3/8) Epoch 24, validation: loss=0.1537, simple_loss=0.2513, pruned_loss=0.02802, over 698248.00 frames.
2022-05-15 07:27:14,997 INFO [train.py:812] (3/8) Epoch 24, batch 3050, loss[loss=0.1499, simple_loss=0.2362, pruned_loss=0.03181, over 7272.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2502, pruned_loss=0.03406, over 1416857.16 frames.], batch size: 18, lr: 3.23e-04
2022-05-15 07:28:13,634 INFO [train.py:812] (3/8) Epoch 24, batch 3100, loss[loss=0.1744, simple_loss=0.2648, pruned_loss=0.04195, over 6853.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2497, pruned_loss=0.03409, over 1420859.59 frames.], batch size: 31, lr: 3.23e-04
2022-05-15 07:29:12,208 INFO [train.py:812] (3/8) Epoch 24, batch 3150, loss[loss=0.1218, simple_loss=0.2042, pruned_loss=0.01966, over 7424.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.03382, over 1422731.49 frames.], batch size: 17, lr: 3.23e-04
2022-05-15 07:30:11,682 INFO [train.py:812] (3/8) Epoch 24, batch 3200, loss[loss=0.1485, simple_loss=0.248, pruned_loss=0.02452, over 7320.00 frames.], tot_loss[loss=0.158, simple_loss=0.2491, pruned_loss=0.03344, over 1426902.78 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:31:10,163 INFO [train.py:812] (3/8) Epoch 24, batch 3250, loss[loss=0.1385, simple_loss=0.2313, pruned_loss=0.0229, over 7158.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03358, over 1428659.35 frames.], batch size: 18, lr: 3.23e-04
2022-05-15 07:32:09,048 INFO [train.py:812] (3/8) Epoch 24, batch 3300, loss[loss=0.1797, simple_loss=0.2629, pruned_loss=0.04825, over 7298.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03364, over 1428402.25 frames.], batch size: 24, lr: 3.23e-04
2022-05-15 07:33:06,611 INFO [train.py:812] (3/8) Epoch 24, batch 3350, loss[loss=0.1594, simple_loss=0.2481, pruned_loss=0.03538, over 7268.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.03376, over 1424679.68 frames.], batch size: 24, lr: 3.23e-04
2022-05-15 07:34:04,973 INFO [train.py:812] (3/8) Epoch 24, batch 3400, loss[loss=0.1486, simple_loss=0.2341, pruned_loss=0.03156, over 7353.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2496, pruned_loss=0.03366, over 1428322.65 frames.], batch size: 19, lr: 3.23e-04
2022-05-15 07:35:03,132 INFO [train.py:812] (3/8) Epoch 24, batch 3450, loss[loss=0.1416, simple_loss=0.2411, pruned_loss=0.02103, over 7326.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2498, pruned_loss=0.03334, over 1423373.50 frames.], batch size: 22, lr: 3.23e-04
2022-05-15 07:36:01,800 INFO [train.py:812] (3/8) Epoch 24, batch 3500, loss[loss=0.1434, simple_loss=0.2257, pruned_loss=0.03054, over 7204.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2488, pruned_loss=0.03328, over 1421730.93 frames.], batch size: 16, lr: 3.23e-04
2022-05-15 07:37:00,363 INFO [train.py:812] (3/8) Epoch 24, batch 3550, loss[loss=0.1849, simple_loss=0.2801, pruned_loss=0.04487, over 7124.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2489, pruned_loss=0.03308, over 1423021.77 frames.], batch size: 21, lr: 3.23e-04
2022-05-15 07:38:00,103 INFO [train.py:812] (3/8) Epoch 24, batch 3600, loss[loss=0.1598, simple_loss=0.2517, pruned_loss=0.03396, over 7065.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2498, pruned_loss=0.03318, over 1422936.26 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:38:57,458 INFO [train.py:812] (3/8) Epoch 24, batch 3650, loss[loss=0.1483, simple_loss=0.2335, pruned_loss=0.03152, over 7362.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2504, pruned_loss=0.03351, over 1423102.07 frames.], batch size: 19, lr: 3.22e-04
2022-05-15 07:39:55,861 INFO [train.py:812] (3/8) Epoch 24, batch 3700, loss[loss=0.1664, simple_loss=0.2567, pruned_loss=0.0381, over 6340.00 frames.], tot_loss[loss=0.159, simple_loss=0.2506, pruned_loss=0.03367, over 1420648.03 frames.], batch size: 38, lr: 3.22e-04
2022-05-15 07:40:52,806 INFO [train.py:812] (3/8) Epoch 24, batch 3750, loss[loss=0.1404, simple_loss=0.2257, pruned_loss=0.02751, over 7278.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2503, pruned_loss=0.03357, over 1421485.17 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:41:51,834 INFO [train.py:812] (3/8) Epoch 24, batch 3800, loss[loss=0.1676, simple_loss=0.2586, pruned_loss=0.03828, over 7426.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2499, pruned_loss=0.03365, over 1423496.51 frames.], batch size: 20, lr: 3.22e-04
2022-05-15 07:42:51,142 INFO [train.py:812] (3/8) Epoch 24, batch 3850, loss[loss=0.1749, simple_loss=0.2624, pruned_loss=0.04368, over 5007.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2495, pruned_loss=0.03339, over 1419582.83 frames.], batch size: 52, lr: 3.22e-04
2022-05-15 07:43:50,681 INFO [train.py:812] (3/8) Epoch 24, batch 3900, loss[loss=0.1644, simple_loss=0.2463, pruned_loss=0.04127, over 6761.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2492, pruned_loss=0.03359, over 1417099.66 frames.], batch size: 31, lr: 3.22e-04
2022-05-15 07:44:49,677 INFO [train.py:812] (3/8) Epoch 24, batch 3950, loss[loss=0.1421, simple_loss=0.2176, pruned_loss=0.03333, over 7141.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03356, over 1417096.54 frames.], batch size: 17, lr: 3.22e-04
2022-05-15 07:45:48,713 INFO [train.py:812] (3/8) Epoch 24, batch 4000, loss[loss=0.1906, simple_loss=0.2729, pruned_loss=0.05419, over 7207.00 frames.], tot_loss[loss=0.1589, simple_loss=0.25, pruned_loss=0.03387, over 1415795.78 frames.], batch size: 22, lr: 3.22e-04
2022-05-15 07:46:47,062 INFO [train.py:812] (3/8) Epoch 24, batch 4050, loss[loss=0.1762, simple_loss=0.2641, pruned_loss=0.04413, over 5001.00 frames.], tot_loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03415, over 1416665.62 frames.], batch size: 52, lr: 3.22e-04
2022-05-15 07:47:46,725 INFO [train.py:812] (3/8) Epoch 24, batch 4100, loss[loss=0.1608, simple_loss=0.244, pruned_loss=0.03881, over 7271.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2491, pruned_loss=0.0337, over 1417293.61 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:48:45,779 INFO [train.py:812] (3/8) Epoch 24, batch 4150, loss[loss=0.1392, simple_loss=0.2297, pruned_loss=0.02438, over 7422.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2487, pruned_loss=0.03377, over 1419470.11 frames.], batch size: 17, lr: 3.22e-04
2022-05-15 07:49:44,867 INFO [train.py:812] (3/8) Epoch 24, batch 4200, loss[loss=0.1462, simple_loss=0.2364, pruned_loss=0.02795, over 7281.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2498, pruned_loss=0.03376, over 1420210.94 frames.], batch size: 18, lr: 3.22e-04
2022-05-15 07:50:44,176 INFO [train.py:812] (3/8) Epoch 24, batch 4250, loss[loss=0.1568, simple_loss=0.2471, pruned_loss=0.03323, over 7392.00 frames.], tot_loss[loss=0.158, simple_loss=0.2489, pruned_loss=0.03356, over 1417878.08 frames.], batch size: 23, lr: 3.22e-04
2022-05-15 07:51:43,374 INFO [train.py:812] (3/8) Epoch 24, batch 4300, loss[loss=0.1776, simple_loss=0.2576, pruned_loss=0.04887, over 7262.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2479, pruned_loss=0.03358, over 1418190.60 frames.], batch size: 16, lr: 3.21e-04
2022-05-15 07:52:41,809 INFO [train.py:812] (3/8) Epoch 24, batch 4350, loss[loss=0.1563, simple_loss=0.2503, pruned_loss=0.03112, over 6827.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2487, pruned_loss=0.03399, over 1415227.08 frames.], batch size: 31, lr: 3.21e-04
2022-05-15 07:53:40,606 INFO [train.py:812] (3/8) Epoch 24, batch 4400, loss[loss=0.1573, simple_loss=0.2645, pruned_loss=0.02506, over 6442.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2496, pruned_loss=0.03426, over 1408747.70 frames.], batch size: 38, lr: 3.21e-04
2022-05-15 07:54:38,513 INFO [train.py:812] (3/8) Epoch 24, batch 4450, loss[loss=0.1744, simple_loss=0.2682, pruned_loss=0.04029, over 6440.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2489, pruned_loss=0.03431, over 1410498.65 frames.], batch size: 38, lr: 3.21e-04
2022-05-15 07:55:37,552 INFO [train.py:812] (3/8) Epoch 24, batch 4500, loss[loss=0.1594, simple_loss=0.2501, pruned_loss=0.03433, over 6378.00 frames.], tot_loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03477, over 1396044.29 frames.], batch size: 37, lr: 3.21e-04
2022-05-15 07:56:36,603 INFO [train.py:812] (3/8) Epoch 24, batch 4550, loss[loss=0.179, simple_loss=0.2752, pruned_loss=0.04144, over 7270.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2507, pruned_loss=0.03499, over 1383720.87 frames.], batch size: 24, lr: 3.21e-04
2022-05-15 07:57:47,756 INFO [train.py:812] (3/8) Epoch 25, batch 0, loss[loss=0.1887, simple_loss=0.2778, pruned_loss=0.04986, over 7059.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2778, pruned_loss=0.04986, over 7059.00 frames.], batch size: 18, lr: 3.15e-04
2022-05-15 07:58:47,071 INFO [train.py:812] (3/8) Epoch 25, batch 50, loss[loss=0.157, simple_loss=0.2482, pruned_loss=0.03287, over 7272.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2543, pruned_loss=0.03613, over 321764.34 frames.], batch size: 19, lr: 3.15e-04
2022-05-15 07:59:46,724 INFO [train.py:812] (3/8) Epoch 25, batch 100, loss[loss=0.1494, simple_loss=0.2413, pruned_loss=0.02877, over 7325.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2508, pruned_loss=0.03468, over 569247.89 frames.], batch size: 20, lr: 3.15e-04
2022-05-15 08:00:45,691 INFO [train.py:812] (3/8) Epoch 25, batch 150, loss[loss=0.1532, simple_loss=0.2487, pruned_loss=0.02888, over 7312.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2505, pruned_loss=0.03418, over 760797.64 frames.], batch size: 21, lr: 3.14e-04
2022-05-15 08:01:45,476 INFO [train.py:812] (3/8) Epoch 25, batch 200, loss[loss=0.1639, simple_loss=0.2471, pruned_loss=0.0403, over 6846.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2505, pruned_loss=0.03413, over 906316.26 frames.], batch size: 15, lr: 3.14e-04
2022-05-15 08:02:44,400 INFO [train.py:812] (3/8) Epoch 25, batch 250, loss[loss=0.169, simple_loss=0.2672, pruned_loss=0.03545, over 7233.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2495, pruned_loss=0.03347, over 1018564.83 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:03:43,896 INFO [train.py:812] (3/8) Epoch 25, batch 300, loss[loss=0.1784, simple_loss=0.2665, pruned_loss=0.04522, over 7151.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2497, pruned_loss=0.03359, over 1112340.12 frames.], batch size: 19, lr: 3.14e-04
2022-05-15 08:04:42,714 INFO [train.py:812] (3/8) Epoch 25, batch 350, loss[loss=0.1597, simple_loss=0.2583, pruned_loss=0.03059, over 7196.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2492, pruned_loss=0.03371, over 1180934.71 frames.], batch size: 23, lr: 3.14e-04
2022-05-15 08:05:50,916 INFO [train.py:812] (3/8) Epoch 25, batch 400, loss[loss=0.1751, simple_loss=0.2671, pruned_loss=0.04152, over 7250.00 frames.], tot_loss[loss=0.1578, simple_loss=0.249, pruned_loss=0.03326, over 1236047.88 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:06:49,139 INFO [train.py:812] (3/8) Epoch 25, batch 450, loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03218, over 7146.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2485, pruned_loss=0.03345, over 1276953.21 frames.], batch size: 28, lr: 3.14e-04
2022-05-15 08:07:48,543 INFO [train.py:812] (3/8) Epoch 25, batch 500, loss[loss=0.1433, simple_loss=0.2336, pruned_loss=0.02653, over 7170.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03358, over 1312530.87 frames.], batch size: 18, lr: 3.14e-04
2022-05-15 08:08:47,653 INFO [train.py:812] (3/8) Epoch 25, batch 550, loss[loss=0.1331, simple_loss=0.2235, pruned_loss=0.02131, over 7169.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2486, pruned_loss=0.0335, over 1339662.81 frames.], batch size: 18, lr: 3.14e-04
2022-05-15 08:09:45,616 INFO [train.py:812] (3/8) Epoch 25, batch 600, loss[loss=0.1617, simple_loss=0.2626, pruned_loss=0.0304, over 7187.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2486, pruned_loss=0.03354, over 1358555.23 frames.], batch size: 23, lr: 3.14e-04
2022-05-15 08:10:45,002 INFO [train.py:812] (3/8) Epoch 25, batch 650, loss[loss=0.1222, simple_loss=0.2015, pruned_loss=0.02148, over 7270.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2472, pruned_loss=0.03333, over 1370406.96 frames.], batch size: 17, lr: 3.14e-04
2022-05-15 08:11:43,796 INFO [train.py:812] (3/8) Epoch 25, batch 700, loss[loss=0.1354, simple_loss=0.2154, pruned_loss=0.0277, over 7222.00 frames.], tot_loss[loss=0.1568, simple_loss=0.247, pruned_loss=0.03329, over 1386722.25 frames.], batch size: 16, lr: 3.14e-04
2022-05-15 08:12:42,957 INFO [train.py:812] (3/8) Epoch 25, batch 750, loss[loss=0.1773, simple_loss=0.2659, pruned_loss=0.04432, over 7235.00 frames.], tot_loss[loss=0.1577, simple_loss=0.248, pruned_loss=0.03366, over 1397506.20 frames.], batch size: 20, lr: 3.14e-04
2022-05-15 08:13:42,683 INFO [train.py:812] (3/8) Epoch 25, batch 800, loss[loss=0.1757, simple_loss=0.2744, pruned_loss=0.03849, over 7410.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2484, pruned_loss=0.03355, over 1405546.69 frames.], batch size: 21, lr: 3.14e-04
2022-05-15 08:14:42,181 INFO [train.py:812] (3/8) Epoch 25, batch 850, loss[loss=0.1514, simple_loss=0.2563, pruned_loss=0.02327, over 7311.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03309, over 1407052.77 frames.], batch size: 21, lr: 3.13e-04
2022-05-15 08:15:39,810 INFO [train.py:812] (3/8) Epoch 25, batch 900, loss[loss=0.2, simple_loss=0.297, pruned_loss=0.05148, over 7289.00 frames.], tot_loss[loss=0.158, simple_loss=0.2491, pruned_loss=0.03344, over 1409959.06 frames.], batch size: 25, lr: 3.13e-04
2022-05-15 08:16:38,337 INFO [train.py:812] (3/8) Epoch 25, batch 950, loss[loss=0.1795, simple_loss=0.2625, pruned_loss=0.04831, over 4898.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2486, pruned_loss=0.03332, over 1405229.20 frames.], batch size: 52, lr: 3.13e-04
2022-05-15 08:17:38,345 INFO [train.py:812] (3/8) Epoch 25, batch 1000, loss[loss=0.1491, simple_loss=0.2434, pruned_loss=0.02739, over 7422.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03287, over 1412521.17 frames.], batch size: 21, lr: 3.13e-04
2022-05-15 08:18:37,736 INFO [train.py:812] (3/8) Epoch 25, batch 1050, loss[loss=0.1481, simple_loss=0.237, pruned_loss=0.02955, over 7328.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2483, pruned_loss=0.03323, over 1419144.66 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:19:35,300 INFO [train.py:812] (3/8) Epoch 25, batch 1100, loss[loss=0.1678, simple_loss=0.266, pruned_loss=0.03476, over 7343.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03261, over 1421203.36 frames.], batch size: 22, lr: 3.13e-04
2022-05-15 08:20:32,126 INFO [train.py:812] (3/8) Epoch 25, batch 1150, loss[loss=0.1574, simple_loss=0.2516, pruned_loss=0.03157, over 7190.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03264, over 1424447.30 frames.], batch size: 23, lr: 3.13e-04
2022-05-15 08:21:31,791 INFO [train.py:812] (3/8) Epoch 25, batch 1200, loss[loss=0.153, simple_loss=0.2493, pruned_loss=0.02832, over 7369.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2479, pruned_loss=0.03298, over 1424061.89 frames.], batch size: 23, lr: 3.13e-04
2022-05-15 08:22:29,879 INFO [train.py:812] (3/8) Epoch 25, batch 1250, loss[loss=0.142, simple_loss=0.2364, pruned_loss=0.02375, over 7149.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2478, pruned_loss=0.03321, over 1422295.69 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:23:28,260 INFO [train.py:812] (3/8) Epoch 25, batch 1300, loss[loss=0.1516, simple_loss=0.2325, pruned_loss=0.03538, over 7210.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2468, pruned_loss=0.03285, over 1421698.76 frames.], batch size: 16, lr: 3.13e-04
2022-05-15 08:24:27,533 INFO [train.py:812] (3/8) Epoch 25, batch 1350, loss[loss=0.1458, simple_loss=0.2446, pruned_loss=0.02351, over 6358.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03266, over 1420970.78 frames.], batch size: 38, lr: 3.13e-04
2022-05-15 08:25:26,988 INFO [train.py:812] (3/8) Epoch 25, batch 1400, loss[loss=0.1303, simple_loss=0.218, pruned_loss=0.02128, over 7272.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2476, pruned_loss=0.03261, over 1426120.66 frames.], batch size: 17, lr: 3.13e-04
2022-05-15 08:26:25,996 INFO [train.py:812] (3/8) Epoch 25, batch 1450, loss[loss=0.1602, simple_loss=0.2642, pruned_loss=0.0281, over 7137.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2476, pruned_loss=0.03274, over 1422838.31 frames.], batch size: 20, lr: 3.13e-04
2022-05-15 08:27:24,395 INFO [train.py:812] (3/8) Epoch 25, batch 1500, loss[loss=0.1273, simple_loss=0.2193, pruned_loss=0.01764, over 6759.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2473, pruned_loss=0.03281, over 1421182.81 frames.], batch size: 31, lr: 3.13e-04
2022-05-15 08:28:23,108 INFO [train.py:812] (3/8) Epoch 25, batch 1550, loss[loss=0.1314, simple_loss=0.22, pruned_loss=0.02139, over 7294.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2481, pruned_loss=0.03254, over 1422407.09 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:29:22,783 INFO [train.py:812] (3/8) Epoch 25, batch 1600, loss[loss=0.1504, simple_loss=0.2332, pruned_loss=0.0338, over 7164.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2481, pruned_loss=0.03274, over 1421791.25 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:30:21,915 INFO [train.py:812] (3/8) Epoch 25, batch 1650, loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03149, over 7213.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03287, over 1422705.18 frames.], batch size: 21, lr: 3.12e-04
2022-05-15 08:31:21,075 INFO [train.py:812] (3/8) Epoch 25, batch 1700, loss[loss=0.184, simple_loss=0.2747, pruned_loss=0.04666, over 7375.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03342, over 1420546.92 frames.], batch size: 23, lr: 3.12e-04
2022-05-15 08:32:19,165 INFO [train.py:812] (3/8) Epoch 25, batch 1750, loss[loss=0.1442, simple_loss=0.2308, pruned_loss=0.02879, over 7134.00 frames.], tot_loss[loss=0.158, simple_loss=0.2492, pruned_loss=0.03345, over 1423188.92 frames.], batch size: 17, lr: 3.12e-04
2022-05-15 08:33:18,557 INFO [train.py:812] (3/8) Epoch 25, batch 1800, loss[loss=0.1435, simple_loss=0.2263, pruned_loss=0.03034, over 7010.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2492, pruned_loss=0.03275, over 1423814.27 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:34:17,256 INFO [train.py:812] (3/8) Epoch 25, batch 1850, loss[loss=0.1487, simple_loss=0.2387, pruned_loss=0.02935, over 7242.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2489, pruned_loss=0.03263, over 1420882.85 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:35:20,954 INFO [train.py:812] (3/8) Epoch 25, batch 1900, loss[loss=0.1604, simple_loss=0.2474, pruned_loss=0.0367, over 7292.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2498, pruned_loss=0.03359, over 1421995.34 frames.], batch size: 25, lr: 3.12e-04
2022-05-15 08:36:19,548 INFO [train.py:812] (3/8) Epoch 25, batch 1950, loss[loss=0.1356, simple_loss=0.2305, pruned_loss=0.02034, over 7256.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2497, pruned_loss=0.03384, over 1424242.40 frames.], batch size: 19, lr: 3.12e-04
2022-05-15 08:37:18,262 INFO [train.py:812] (3/8) Epoch 25, batch 2000, loss[loss=0.1872, simple_loss=0.279, pruned_loss=0.04769, over 7146.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2493, pruned_loss=0.03404, over 1424281.63 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:38:16,607 INFO [train.py:812] (3/8) Epoch 25, batch 2050, loss[loss=0.183, simple_loss=0.2876, pruned_loss=0.03916, over 7325.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2475, pruned_loss=0.03338, over 1427562.59 frames.], batch size: 21, lr: 3.12e-04
2022-05-15 08:39:15,898 INFO [train.py:812] (3/8) Epoch 25, batch 2100, loss[loss=0.1445, simple_loss=0.2302, pruned_loss=0.0294, over 7260.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2472, pruned_loss=0.03315, over 1424022.88 frames.], batch size: 19, lr: 3.12e-04
2022-05-15 08:40:13,579 INFO [train.py:812] (3/8) Epoch 25, batch 2150, loss[loss=0.1424, simple_loss=0.2481, pruned_loss=0.01833, over 7437.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2482, pruned_loss=0.03346, over 1422982.46 frames.], batch size: 20, lr: 3.12e-04
2022-05-15 08:41:13,388 INFO [train.py:812] (3/8) Epoch 25, batch 2200, loss[loss=0.1544, simple_loss=0.2407, pruned_loss=0.03405, over 7225.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2482, pruned_loss=0.03331, over 1421903.23 frames.], batch size: 16, lr: 3.12e-04
2022-05-15 08:42:11,777 INFO [train.py:812] (3/8) Epoch 25, batch 2250, loss[loss=0.1595, simple_loss=0.2423, pruned_loss=0.03833, over 7067.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.03324, over 1417229.21 frames.], batch size: 18, lr: 3.12e-04
2022-05-15 08:43:09,219 INFO [train.py:812] (3/8) Epoch 25, batch 2300, loss[loss=0.1305, simple_loss=0.2069, pruned_loss=0.02705, over 7240.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2474, pruned_loss=0.03281, over 1418211.22 frames.], batch size: 16, lr: 3.11e-04
2022-05-15 08:44:06,008 INFO [train.py:812] (3/8) Epoch 25, batch 2350, loss[loss=0.1683, simple_loss=0.2599, pruned_loss=0.03838, over 7317.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03287, over 1419252.38 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:45:05,367 INFO [train.py:812] (3/8) Epoch 25, batch 2400, loss[loss=0.1651, simple_loss=0.2563, pruned_loss=0.03695, over 7360.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2491, pruned_loss=0.03324, over 1423799.34 frames.], batch size: 19, lr: 3.11e-04
2022-05-15 08:46:04,715 INFO [train.py:812] (3/8) Epoch 25, batch 2450, loss[loss=0.1485, simple_loss=0.2305, pruned_loss=0.03326, over 7142.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03309, over 1423157.65 frames.], batch size: 17, lr: 3.11e-04
2022-05-15 08:47:04,378 INFO [train.py:812] (3/8) Epoch 25, batch 2500, loss[loss=0.1669, simple_loss=0.256, pruned_loss=0.03891, over 7404.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2488, pruned_loss=0.03311, over 1423322.15 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:48:03,388 INFO [train.py:812] (3/8) Epoch 25, batch 2550, loss[loss=0.1537, simple_loss=0.2595, pruned_loss=0.0239, over 7417.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2489, pruned_loss=0.0327, over 1424350.94 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:49:03,053 INFO [train.py:812] (3/8) Epoch 25, batch 2600, loss[loss=0.1508, simple_loss=0.2255, pruned_loss=0.03806, over 7152.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2486, pruned_loss=0.03293, over 1421192.01 frames.], batch size: 17, lr: 3.11e-04
2022-05-15 08:50:01,903 INFO [train.py:812] (3/8) Epoch 25, batch 2650, loss[loss=0.1538, simple_loss=0.2354, pruned_loss=0.03616, over 7206.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2489, pruned_loss=0.03293, over 1423020.17 frames.], batch size: 22, lr: 3.11e-04
2022-05-15 08:51:09,490 INFO [train.py:812] (3/8) Epoch 25, batch 2700, loss[loss=0.1638, simple_loss=0.2434, pruned_loss=0.04215, over 7059.00 frames.], tot_loss[loss=0.156, simple_loss=0.2477, pruned_loss=0.03213, over 1425646.09 frames.], batch size: 18, lr: 3.11e-04
2022-05-15 08:52:06,913 INFO [train.py:812] (3/8) Epoch 25, batch 2750, loss[loss=0.1646, simple_loss=0.2591, pruned_loss=0.03508, over 7140.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2472, pruned_loss=0.03212, over 1420729.18 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:53:06,509 INFO [train.py:812] (3/8) Epoch 25, batch 2800, loss[loss=0.1583, simple_loss=0.2489, pruned_loss=0.03385, over 7251.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03224, over 1421249.60 frames.], batch size: 19, lr: 3.11e-04
2022-05-15 08:54:05,457 INFO [train.py:812] (3/8) Epoch 25, batch 2850, loss[loss=0.1442, simple_loss=0.24, pruned_loss=0.02418, over 7435.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.0321, over 1419966.95 frames.], batch size: 20, lr: 3.11e-04
2022-05-15 08:55:04,575 INFO [train.py:812] (3/8) Epoch 25, batch 2900, loss[loss=0.1807, simple_loss=0.2645, pruned_loss=0.04851, over 7216.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03236, over 1420562.27 frames.], batch size: 23, lr: 3.11e-04
2022-05-15 08:56:02,074 INFO [train.py:812] (3/8) Epoch 25, batch 2950, loss[loss=0.1566, simple_loss=0.2551, pruned_loss=0.02905, over 7115.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2484, pruned_loss=0.03252, over 1425445.10 frames.], batch size: 21, lr: 3.11e-04
2022-05-15 08:57:29,014 INFO [train.py:812] (3/8) Epoch 25, batch 3000, loss[loss=0.1433, simple_loss=0.2449, pruned_loss=0.0208, over 6729.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03207, over 1429029.18 frames.], batch size: 31, lr: 3.10e-04
2022-05-15 08:57:29,015 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 08:57:46,642 INFO [train.py:841] (3/8) Epoch 25, validation: loss=0.1532, simple_loss=0.2507, pruned_loss=0.02787, over 698248.00 frames.
2022-05-15 08:58:45,936 INFO [train.py:812] (3/8) Epoch 25, batch 3050, loss[loss=0.1498, simple_loss=0.2526, pruned_loss=0.02347, over 7117.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.0319, over 1429657.15 frames.], batch size: 21, lr: 3.10e-04
2022-05-15 08:59:53,863 INFO [train.py:812] (3/8) Epoch 25, batch 3100, loss[loss=0.1449, simple_loss=0.2361, pruned_loss=0.02679, over 6802.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03251, over 1429701.49 frames.], batch size: 15, lr: 3.10e-04
2022-05-15 09:01:01,527 INFO [train.py:812] (3/8) Epoch 25, batch 3150, loss[loss=0.1462, simple_loss=0.2304, pruned_loss=0.03105, over 7251.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2481, pruned_loss=0.03267, over 1430511.34 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:02:01,509 INFO [train.py:812] (3/8) Epoch 25, batch 3200, loss[loss=0.1665, simple_loss=0.2516, pruned_loss=0.04073, over 5218.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2473, pruned_loss=0.03257, over 1429135.96 frames.], batch size: 54, lr: 3.10e-04
2022-05-15 09:03:00,344 INFO [train.py:812] (3/8) Epoch 25, batch 3250, loss[loss=0.1813, simple_loss=0.2747, pruned_loss=0.04402, over 7235.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03275, over 1427170.90 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:03:59,272 INFO [train.py:812] (3/8) Epoch 25, batch 3300, loss[loss=0.1522, simple_loss=0.2411, pruned_loss=0.03162, over 7152.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.0327, over 1425771.99 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:04:58,424 INFO [train.py:812] (3/8) Epoch 25, batch 3350, loss[loss=0.1393, simple_loss=0.2342, pruned_loss=0.02214, over 7255.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2471, pruned_loss=0.03232, over 1422791.33 frames.], batch size: 19, lr: 3.10e-04
2022-05-15 09:05:57,553 INFO [train.py:812] (3/8) Epoch 25, batch 3400, loss[loss=0.136, simple_loss=0.215, pruned_loss=0.02849, over 7282.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2466, pruned_loss=0.03221, over 1424432.32 frames.], batch size: 17, lr: 3.10e-04
2022-05-15 09:06:55,957 INFO [train.py:812] (3/8) Epoch 25, batch 3450, loss[loss=0.1489, simple_loss=0.2528, pruned_loss=0.02251, over 7234.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2473, pruned_loss=0.03264, over 1421844.40 frames.], batch size: 21, lr: 3.10e-04
2022-05-15 09:07:54,088 INFO [train.py:812] (3/8) Epoch 25, batch 3500, loss[loss=0.1362, simple_loss=0.2171, pruned_loss=0.02764, over 7132.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03293, over 1423432.99 frames.], batch size: 17, lr: 3.10e-04
2022-05-15 09:08:53,607 INFO [train.py:812] (3/8) Epoch 25, batch 3550, loss[loss=0.1466, simple_loss=0.244, pruned_loss=0.02459, over 7322.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2488, pruned_loss=0.03344, over 1424578.95 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:09:52,739 INFO [train.py:812] (3/8) Epoch 25, batch 3600, loss[loss=0.1899, simple_loss=0.2779, pruned_loss=0.05097, over 7200.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2494, pruned_loss=0.03361, over 1422920.04 frames.], batch size: 23, lr: 3.10e-04
2022-05-15 09:10:51,694 INFO [train.py:812] (3/8) Epoch 25, batch 3650, loss[loss=0.192, simple_loss=0.2821, pruned_loss=0.05095, over 6424.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2486, pruned_loss=0.033, over 1419281.40 frames.], batch size: 37, lr: 3.10e-04
2022-05-15 09:11:51,257 INFO [train.py:812] (3/8) Epoch 25, batch 3700, loss[loss=0.1401, simple_loss=0.2383, pruned_loss=0.02092, over 7429.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2478, pruned_loss=0.03292, over 1422320.53 frames.], batch size: 20, lr: 3.10e-04
2022-05-15 09:12:50,498 INFO [train.py:812] (3/8) Epoch 25, batch 3750, loss[loss=0.1615, simple_loss=0.2521, pruned_loss=0.03547, over 7395.00 frames.], tot_loss[loss=0.157, simple_loss=0.2477, pruned_loss=0.03319, over 1424383.14 frames.], batch size: 23, lr: 3.09e-04
2022-05-15 09:13:50,123 INFO [train.py:812] (3/8) Epoch 25, batch 3800, loss[loss=0.1859, simple_loss=0.2645, pruned_loss=0.05364, over 5089.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2472, pruned_loss=0.03319, over 1422212.70 frames.], batch size: 52, lr: 3.09e-04
2022-05-15 09:14:48,006 INFO [train.py:812] (3/8) Epoch 25, batch 3850, loss[loss=0.141, simple_loss=0.2324, pruned_loss=0.02475, over 7276.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2478, pruned_loss=0.03326, over 1421939.58 frames.], batch size: 18, lr: 3.09e-04
2022-05-15 09:15:47,061 INFO [train.py:812] (3/8) Epoch 25, batch 3900, loss[loss=0.1534, simple_loss=0.2433, pruned_loss=0.03173, over 7254.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2483, pruned_loss=0.03342, over 1421700.47 frames.], batch size: 19, lr: 3.09e-04
2022-05-15 09:16:44,709 INFO [train.py:812] (3/8) Epoch 25, batch 3950, loss[loss=0.1335, simple_loss=0.2176, pruned_loss=0.02472, over 7420.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2487, pruned_loss=0.0335, over 1424188.31 frames.], batch size: 18, lr: 3.09e-04
2022-05-15 09:17:43,602 INFO [train.py:812] (3/8) Epoch 25, batch 4000, loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02923, over 7323.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03336, over 1423019.17 frames.], batch size: 21, lr: 3.09e-04
2022-05-15 09:18:42,639 INFO [train.py:812] (3/8) Epoch 25, batch 4050, loss[loss=0.1421, simple_loss=0.2296, pruned_loss=0.02732, over 7430.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2479, pruned_loss=0.03278, over 1421878.69 frames.], batch size: 20, lr: 3.09e-04
2022-05-15 09:19:41,934 INFO [train.py:812] (3/8) Epoch 25, batch 4100, loss[loss=0.189, simple_loss=0.2721, pruned_loss=0.05299, over 6454.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2485, pruned_loss=0.03317, over 1422402.07 frames.], batch size: 38, lr: 3.09e-04
2022-05-15 09:20:41,043 INFO [train.py:812] (3/8) Epoch 25, batch 4150, loss[loss=0.1627, simple_loss=0.262, pruned_loss=0.03168, over 7220.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2479, pruned_loss=0.03282, over 1418626.17 frames.], batch size: 21, lr: 3.09e-04
2022-05-15 09:21:39,839 INFO [train.py:812] (3/8) Epoch 25, batch 4200, loss[loss=0.183, simple_loss=0.2715, pruned_loss=0.04721, over 7193.00 frames.], tot_loss[loss=0.1584, simple_loss=0.25, pruned_loss=0.03343, over 1420486.53 frames.], batch size: 23, lr: 3.09e-04
2022-05-15 09:22:38,421 INFO [train.py:812] (3/8) Epoch 25, batch 4250, loss[loss=0.1707, simple_loss=0.264, pruned_loss=0.03871, over 6163.00 frames.], tot_loss[loss=0.158, simple_loss=0.2493, pruned_loss=0.03336, over 1415306.46 frames.], batch size: 37, lr: 3.09e-04
2022-05-15 09:23:37,025 INFO [train.py:812] (3/8) Epoch 25, batch 4300, loss[loss=0.1431, simple_loss=0.239, pruned_loss=0.02365, over 7155.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03305, over 1414737.00 frames.], batch size: 19, lr: 3.09e-04
2022-05-15 09:24:36,170 INFO [train.py:812] (3/8) Epoch 25, batch 4350, loss[loss=0.1652, simple_loss=0.2571, pruned_loss=0.03662, over 7325.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2473, pruned_loss=0.03306, over 1414731.09 frames.], batch size: 25, lr: 3.09e-04
2022-05-15 09:25:35,368 INFO [train.py:812] (3/8) Epoch 25, batch 4400, loss[loss=0.1685, simple_loss=0.2566, pruned_loss=0.04017, over 7291.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2494, pruned_loss=0.03351, over 1413081.87 frames.], batch size: 24, lr: 3.09e-04
2022-05-15 09:26:34,027 INFO [train.py:812] (3/8) Epoch 25, batch 4450, loss[loss=0.1637, simple_loss=0.2583, pruned_loss=0.03458, over 7287.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2497, pruned_loss=0.03303, over 1403697.95 frames.], batch size: 25, lr: 3.09e-04
2022-05-15 09:27:33,085 INFO [train.py:812] (3/8) Epoch 25, batch 4500, loss[loss=0.1582, simple_loss=0.246, pruned_loss=0.03525, over 5242.00 frames.], tot_loss[loss=0.1593, simple_loss=0.251, pruned_loss=0.03378, over 1388376.17 frames.], batch size: 52, lr: 3.08e-04
2022-05-15 09:28:30,315 INFO [train.py:812] (3/8) Epoch 25, batch 4550, loss[loss=0.1853, simple_loss=0.2718, pruned_loss=0.04942, over 5096.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2528, pruned_loss=0.03475, over 1349918.35 frames.], batch size: 52, lr: 3.08e-04
2022-05-15 09:29:36,547 INFO [train.py:812] (3/8) Epoch 26, batch 0, loss[loss=0.1719, simple_loss=0.2654, pruned_loss=0.03923, over 7217.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2654, pruned_loss=0.03923, over 7217.00 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:30:35,845 INFO [train.py:812] (3/8) Epoch 26, batch 50, loss[loss=0.1386, simple_loss=0.2314, pruned_loss=0.02289, over 7323.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02932, over 322597.04 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:31:35,589 INFO [train.py:812] (3/8) Epoch 26, batch 100, loss[loss=0.1636, simple_loss=0.2583, pruned_loss=0.03449, over 5037.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2458, pruned_loss=0.03053, over 566612.50 frames.], batch size: 52, lr: 3.02e-04
2022-05-15 09:32:35,329 INFO [train.py:812] (3/8) Epoch 26, batch 150, loss[loss=0.1409, simple_loss=0.2264, pruned_loss=0.0277, over 7290.00 frames.], tot_loss[loss=0.154, simple_loss=0.2465, pruned_loss=0.0307, over 760092.24 frames.], batch size: 17, lr: 3.02e-04
2022-05-15 09:33:34,908 INFO [train.py:812] (3/8) Epoch 26, batch 200, loss[loss=0.1867, simple_loss=0.2722, pruned_loss=0.05059, over 7371.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03099, over 906395.18 frames.], batch size: 23, lr: 3.02e-04
2022-05-15 09:34:32,548 INFO [train.py:812] (3/8) Epoch 26, batch 250, loss[loss=0.1774, simple_loss=0.2739, pruned_loss=0.04043, over 7196.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03181, over 1018974.60 frames.], batch size: 22, lr: 3.02e-04
2022-05-15 09:35:31,868 INFO [train.py:812] (3/8) Epoch 26, batch 300, loss[loss=0.1648, simple_loss=0.2582, pruned_loss=0.03567, over 7326.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.03229, over 1105366.89 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:36:29,845 INFO [train.py:812] (3/8) Epoch 26, batch 350, loss[loss=0.1332, simple_loss=0.2163, pruned_loss=0.02503, over 7157.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2468, pruned_loss=0.03199, over 1174778.59 frames.], batch size: 18, lr: 3.02e-04
2022-05-15 09:37:29,648 INFO [train.py:812] (3/8) Epoch 26, batch 400, loss[loss=0.1343, simple_loss=0.2142, pruned_loss=0.0272, over 7422.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2471, pruned_loss=0.03201, over 1232630.36 frames.], batch size: 18, lr: 3.02e-04
2022-05-15 09:38:28,198 INFO [train.py:812] (3/8) Epoch 26, batch 450, loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02989, over 7416.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03176, over 1273486.63 frames.], batch size: 21, lr: 3.02e-04
2022-05-15 09:39:25,642 INFO [train.py:812] (3/8) Epoch 26, batch 500, loss[loss=0.1697, simple_loss=0.2625, pruned_loss=0.03843, over 7365.00 frames.], tot_loss[loss=0.156, simple_loss=0.2476, pruned_loss=0.03223, over 1302952.21 frames.], batch size: 23, lr: 3.02e-04
2022-05-15 09:40:22,330 INFO [train.py:812] (3/8) Epoch 26, batch 550, loss[loss=0.1727, simple_loss=0.2693, pruned_loss=0.03807, over 7231.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03222, over 1329459.58 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:41:20,608 INFO [train.py:812] (3/8) Epoch 26, batch 600, loss[loss=0.1752, simple_loss=0.2722, pruned_loss=0.03905, over 7104.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03228, over 1348226.22 frames.], batch size: 28, lr: 3.02e-04
2022-05-15 09:42:19,340 INFO [train.py:812] (3/8) Epoch 26, batch 650, loss[loss=0.1464, simple_loss=0.2366, pruned_loss=0.02815, over 7337.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03208, over 1362408.22 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:43:17,904 INFO [train.py:812] (3/8) Epoch 26, batch 700, loss[loss=0.1584, simple_loss=0.2528, pruned_loss=0.03204, over 7143.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03174, over 1375363.45 frames.], batch size: 20, lr: 3.02e-04
2022-05-15 09:44:17,488 INFO [train.py:812] (3/8) Epoch 26, batch 750, loss[loss=0.1556, simple_loss=0.2455, pruned_loss=0.03291, over 7430.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.032, over 1390907.08 frames.], batch size: 20, lr: 3.01e-04
2022-05-15 09:45:17,293 INFO [train.py:812] (3/8) Epoch 26, batch 800, loss[loss=0.1765, simple_loss=0.2658, pruned_loss=0.04357, over 6868.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03239, over 1396229.21 frames.], batch size: 31, lr: 3.01e-04
2022-05-15 09:46:14,899 INFO [train.py:812] (3/8) Epoch 26, batch 850, loss[loss=0.1728, simple_loss=0.2641, pruned_loss=0.04075, over 7123.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2476, pruned_loss=0.03199, over 1407111.64 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:47:13,166 INFO [train.py:812] (3/8) Epoch 26, batch 900, loss[loss=0.1406, simple_loss=0.2269, pruned_loss=0.0272, over 7240.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03221, over 1406599.08 frames.], batch size: 16, lr: 3.01e-04
2022-05-15 09:48:12,077 INFO [train.py:812] (3/8) Epoch 26, batch 950, loss[loss=0.1678, simple_loss=0.2472, pruned_loss=0.0442, over 7299.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03244, over 1412861.83 frames.], batch size: 17, lr: 3.01e-04
2022-05-15 09:49:11,023 INFO [train.py:812] (3/8) Epoch 26, batch 1000, loss[loss=0.2039, simple_loss=0.286, pruned_loss=0.06086, over 7119.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2481, pruned_loss=0.03276, over 1412244.54 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:50:10,502 INFO [train.py:812] (3/8) Epoch 26, batch 1050, loss[loss=0.1765, simple_loss=0.2554, pruned_loss=0.04876, over 4913.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03253, over 1412501.89 frames.], batch size: 53, lr: 3.01e-04
2022-05-15 09:51:08,590 INFO [train.py:812] (3/8) Epoch 26, batch 1100, loss[loss=0.1738, simple_loss=0.2717, pruned_loss=0.03799, over 7125.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2485, pruned_loss=0.03257, over 1413888.27 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:52:08,216 INFO [train.py:812] (3/8) Epoch 26, batch 1150, loss[loss=0.1691, simple_loss=0.2515, pruned_loss=0.04338, over 7380.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2479, pruned_loss=0.0325, over 1417233.97 frames.], batch size: 23, lr: 3.01e-04
2022-05-15 09:53:08,270 INFO [train.py:812] (3/8) Epoch 26, batch 1200, loss[loss=0.132, simple_loss=0.2144, pruned_loss=0.02478, over 7152.00 frames.], tot_loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03271, over 1421602.55 frames.], batch size: 17, lr: 3.01e-04
2022-05-15 09:54:07,366 INFO [train.py:812] (3/8) Epoch 26, batch 1250, loss[loss=0.1539, simple_loss=0.2502, pruned_loss=0.02886, over 7328.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03303, over 1424005.39 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:55:11,133 INFO [train.py:812] (3/8) Epoch 26, batch 1300, loss[loss=0.1945, simple_loss=0.2825, pruned_loss=0.05322, over 7435.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03244, over 1427602.39 frames.], batch size: 20, lr: 3.01e-04
2022-05-15 09:56:09,544 INFO [train.py:812] (3/8) Epoch 26, batch 1350, loss[loss=0.1435, simple_loss=0.2421, pruned_loss=0.02245, over 7309.00 frames.], tot_loss[loss=0.1566, simple_loss=0.248, pruned_loss=0.03265, over 1427354.87 frames.], batch size: 21, lr: 3.01e-04
2022-05-15 09:57:07,827 INFO [train.py:812] (3/8) Epoch 26, batch 1400, loss[loss=0.184, simple_loss=0.2795, pruned_loss=0.04424, over 7343.00 frames.], tot_loss[loss=0.1569, simple_loss=0.248, pruned_loss=0.03287, over 1427482.21 frames.], batch size: 22, lr: 3.01e-04
2022-05-15 09:58:05,645 INFO [train.py:812] (3/8) Epoch 26, batch 1450, loss[loss=0.141, simple_loss=0.2276, pruned_loss=0.02717, over 7006.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2481, pruned_loss=0.03276, over 1429224.71 frames.], batch size: 16, lr: 3.01e-04
2022-05-15 09:59:03,797 INFO [train.py:812] (3/8) Epoch 26, batch 1500, loss[loss=0.182, simple_loss=0.278, pruned_loss=0.04302, over 7232.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2476, pruned_loss=0.03267, over 1428073.88 frames.], batch size: 21, lr: 3.00e-04
2022-05-15 10:00:02,487 INFO [train.py:812] (3/8) Epoch 26, batch 1550, loss[loss=0.1355, simple_loss=0.2213, pruned_loss=0.02486, over 7140.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2472, pruned_loss=0.03268, over 1427676.92 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:01:01,588 INFO [train.py:812] (3/8) Epoch 26, batch 1600, loss[loss=0.1414, simple_loss=0.2346, pruned_loss=0.02411, over 7147.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2488, pruned_loss=0.03303, over 1425381.20 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:02:00,515 INFO [train.py:812] (3/8) Epoch 26, batch 1650, loss[loss=0.1534, simple_loss=0.2469, pruned_loss=0.02989, over 7044.00 frames.], tot_loss[loss=0.1557, simple_loss=0.247, pruned_loss=0.03217, over 1425927.69 frames.], batch size: 28, lr: 3.00e-04
2022-05-15 10:02:59,718 INFO [train.py:812] (3/8) Epoch 26, batch 1700, loss[loss=0.1635, simple_loss=0.2539, pruned_loss=0.03657, over 7331.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2461, pruned_loss=0.0316, over 1425922.28 frames.], batch size: 21, lr: 3.00e-04
2022-05-15 10:04:07,533 INFO [train.py:812] (3/8) Epoch 26, batch 1750, loss[loss=0.1589, simple_loss=0.2383, pruned_loss=0.03977, over 7132.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2465, pruned_loss=0.03153, over 1425274.93 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:05:06,532 INFO [train.py:812] (3/8) Epoch 26, batch 1800, loss[loss=0.153, simple_loss=0.2498, pruned_loss=0.02814, over 7137.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03158, over 1421270.87 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:06:05,265 INFO [train.py:812] (3/8) Epoch 26, batch 1850, loss[loss=0.1633, simple_loss=0.2696, pruned_loss=0.02846, over 7422.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03169, over 1422129.12 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:07:04,828 INFO [train.py:812] (3/8) Epoch 26, batch 1900, loss[loss=0.1393, simple_loss=0.2245, pruned_loss=0.02707, over 7151.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2464, pruned_loss=0.03165, over 1422360.15 frames.], batch size: 17, lr: 3.00e-04
2022-05-15 10:08:02,585 INFO [train.py:812] (3/8) Epoch 26, batch 1950, loss[loss=0.1752, simple_loss=0.2648, pruned_loss=0.04283, over 4857.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03249, over 1419668.83 frames.], batch size: 52, lr: 3.00e-04
2022-05-15 10:09:00,919 INFO [train.py:812] (3/8) Epoch 26, batch 2000, loss[loss=0.1398, simple_loss=0.22, pruned_loss=0.02976, over 7161.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2473, pruned_loss=0.03295, over 1416920.74 frames.], batch size: 19, lr: 3.00e-04
2022-05-15 10:10:00,120 INFO [train.py:812] (3/8) Epoch 26, batch 2050, loss[loss=0.1548, simple_loss=0.2456, pruned_loss=0.03196, over 7322.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2464, pruned_loss=0.03254, over 1418361.44 frames.], batch size: 20, lr: 3.00e-04
2022-05-15 10:10:59,344 INFO [train.py:812] (3/8) Epoch 26, batch 2100, loss[loss=0.1565, simple_loss=0.2448, pruned_loss=0.03408, over 7196.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2475, pruned_loss=0.03302, over 1417141.44 frames.], batch size: 22, lr: 3.00e-04
2022-05-15 10:11:58,141 INFO [train.py:812] (3/8) Epoch 26, batch 2150, loss[loss=0.1476, simple_loss=0.2385, pruned_loss=0.02832, over 7156.00 frames.], tot_loss[loss=0.1568, simple_loss=0.248, pruned_loss=0.03282, over 1419170.46 frames.], batch size: 18, lr: 3.00e-04
2022-05-15 10:12:57,683 INFO [train.py:812] (3/8) Epoch 26, batch 2200, loss[loss=0.1684, simple_loss=0.2558, pruned_loss=0.04051, over 7108.00 frames.], tot_loss[loss=0.157, simple_loss=0.2484, pruned_loss=0.03283, over 1421739.47 frames.], batch size: 28, lr: 3.00e-04
2022-05-15 10:13:56,434 INFO [train.py:812] (3/8) Epoch 26, batch 2250, loss[loss=0.1571, simple_loss=0.2571, pruned_loss=0.02855, over 7369.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2477, pruned_loss=0.03269, over 1424322.45 frames.], batch size: 23, lr: 3.00e-04
2022-05-15 10:14:54,801 INFO [train.py:812] (3/8) Epoch 26, batch 2300, loss[loss=0.1384, simple_loss=0.2224, pruned_loss=0.02719, over 7063.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03289, over 1424587.51 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:15:54,089 INFO [train.py:812] (3/8) Epoch 26, batch 2350, loss[loss=0.1374, simple_loss=0.2252, pruned_loss=0.0248, over 7258.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03257, over 1424223.54 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:16:53,778 INFO [train.py:812] (3/8) Epoch 26, batch 2400, loss[loss=0.2021, simple_loss=0.2933, pruned_loss=0.05552, over 7368.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2466, pruned_loss=0.03286, over 1422576.81 frames.], batch size: 23, lr: 2.99e-04
2022-05-15 10:17:52,717 INFO [train.py:812] (3/8) Epoch 26, batch 2450, loss[loss=0.1484, simple_loss=0.2439, pruned_loss=0.02646, over 6765.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2474, pruned_loss=0.03325, over 1421631.99 frames.], batch size: 31, lr: 2.99e-04
2022-05-15 10:18:50,826 INFO [train.py:812] (3/8) Epoch 26, batch 2500, loss[loss=0.1458, simple_loss=0.2378, pruned_loss=0.02695, over 7363.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2466, pruned_loss=0.03252, over 1422690.70 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:19:48,014 INFO [train.py:812] (3/8) Epoch 26, batch 2550, loss[loss=0.127, simple_loss=0.2086, pruned_loss=0.02269, over 7414.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03217, over 1425587.74 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:20:46,863 INFO [train.py:812] (3/8) Epoch 26, batch 2600, loss[loss=0.1616, simple_loss=0.2484, pruned_loss=0.03743, over 7156.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2464, pruned_loss=0.03229, over 1423846.54 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:21:44,649 INFO [train.py:812] (3/8) Epoch 26, batch 2650, loss[loss=0.169, simple_loss=0.2582, pruned_loss=0.03985, over 7111.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2475, pruned_loss=0.03267, over 1418975.23 frames.], batch size: 28, lr: 2.99e-04
2022-05-15 10:22:43,728 INFO [train.py:812] (3/8) Epoch 26, batch 2700, loss[loss=0.1436, simple_loss=0.2341, pruned_loss=0.02659, over 7266.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2479, pruned_loss=0.03254, over 1419732.49 frames.], batch size: 19, lr: 2.99e-04
2022-05-15 10:23:42,367 INFO [train.py:812] (3/8) Epoch 26, batch 2750, loss[loss=0.199, simple_loss=0.295, pruned_loss=0.0515, over 7304.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2483, pruned_loss=0.03302, over 1413989.76 frames.], batch size: 25, lr: 2.99e-04
2022-05-15 10:24:40,489 INFO [train.py:812] (3/8) Epoch 26, batch 2800, loss[loss=0.1732, simple_loss=0.2668, pruned_loss=0.03979, over 7281.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2476, pruned_loss=0.03276, over 1416580.12 frames.], batch size: 18, lr: 2.99e-04
2022-05-15 10:25:38,072 INFO [train.py:812] (3/8) Epoch 26, batch 2850, loss[loss=0.1469, simple_loss=0.2425, pruned_loss=0.02565, over 7413.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2472, pruned_loss=0.03285, over 1412322.63 frames.], batch size: 21, lr: 2.99e-04
2022-05-15 10:26:37,767 INFO [train.py:812] (3/8) Epoch 26, batch 2900, loss[loss=0.1697, simple_loss=0.2585, pruned_loss=0.04045, over 7151.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2465, pruned_loss=0.03246, over 1418754.27 frames.], batch size: 20, lr: 2.99e-04
2022-05-15 10:27:35,291 INFO [train.py:812] (3/8) Epoch 26, batch 2950, loss[loss=0.1426, simple_loss=0.2422, pruned_loss=0.0215, over 7324.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03251, over 1419284.89 frames.], batch size: 20, lr: 2.99e-04
2022-05-15 10:28:33,136 INFO [train.py:812] (3/8) Epoch 26, batch 3000, loss[loss=0.1682, simple_loss=0.2592, pruned_loss=0.03861, over 6254.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03226, over 1423064.68 frames.], batch size: 37, lr: 2.99e-04
2022-05-15 10:28:33,137 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 10:28:40,784 INFO [train.py:841] (3/8) Epoch 26, validation: loss=0.1534, simple_loss=0.2507, pruned_loss=0.02805, over 698248.00 frames.
2022-05-15 10:29:38,768 INFO [train.py:812] (3/8) Epoch 26, batch 3050, loss[loss=0.182, simple_loss=0.284, pruned_loss=0.04003, over 7339.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2486, pruned_loss=0.03265, over 1421765.28 frames.], batch size: 22, lr: 2.99e-04
2022-05-15 10:30:38,723 INFO [train.py:812] (3/8) Epoch 26, batch 3100, loss[loss=0.136, simple_loss=0.2225, pruned_loss=0.02475, over 7265.00 frames.], tot_loss[loss=0.1561, simple_loss=0.248, pruned_loss=0.03211, over 1419851.54 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:31:36,303 INFO [train.py:812] (3/8) Epoch 26, batch 3150, loss[loss=0.1275, simple_loss=0.2198, pruned_loss=0.0176, over 7134.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03255, over 1419133.24 frames.], batch size: 17, lr: 2.98e-04
2022-05-15 10:32:35,703 INFO [train.py:812] (3/8) Epoch 26, batch 3200, loss[loss=0.1541, simple_loss=0.2437, pruned_loss=0.03225, over 7160.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2482, pruned_loss=0.03234, over 1422035.04 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:33:35,059 INFO [train.py:812] (3/8) Epoch 26, batch 3250, loss[loss=0.1607, simple_loss=0.2487, pruned_loss=0.03629, over 7273.00 frames.], tot_loss[loss=0.156, simple_loss=0.247, pruned_loss=0.03247, over 1425479.19 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:34:33,012 INFO [train.py:812] (3/8) Epoch 26, batch 3300, loss[loss=0.1544, simple_loss=0.2516, pruned_loss=0.02863, over 7160.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03233, over 1418368.37 frames.], batch size: 26, lr: 2.98e-04
2022-05-15 10:35:31,810 INFO [train.py:812] (3/8) Epoch 26, batch 3350, loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02859, over 7328.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2475, pruned_loss=0.03253, over 1415046.74 frames.], batch size: 21, lr: 2.98e-04
2022-05-15 10:36:31,892 INFO [train.py:812] (3/8) Epoch 26, batch 3400, loss[loss=0.1631, simple_loss=0.2542, pruned_loss=0.03603, over 6284.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.03248, over 1419920.11 frames.], batch size: 37, lr: 2.98e-04
2022-05-15 10:37:30,432 INFO [train.py:812] (3/8) Epoch 26, batch 3450, loss[loss=0.1389, simple_loss=0.2279, pruned_loss=0.02497, over 7167.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03235, over 1419707.41 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:38:29,759 INFO [train.py:812] (3/8) Epoch 26, batch 3500, loss[loss=0.1454, simple_loss=0.2514, pruned_loss=0.01975, over 7390.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03239, over 1419539.24 frames.], batch size: 23, lr: 2.98e-04
2022-05-15 10:39:28,312 INFO [train.py:812] (3/8) Epoch 26, batch 3550, loss[loss=0.1442, simple_loss=0.2341, pruned_loss=0.0272, over 7416.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.03234, over 1421862.41 frames.], batch size: 21, lr: 2.98e-04
2022-05-15 10:40:26,266 INFO [train.py:812] (3/8) Epoch 26, batch 3600, loss[loss=0.2056, simple_loss=0.2842, pruned_loss=0.06352, over 7206.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2463, pruned_loss=0.03222, over 1426145.77 frames.], batch size: 23, lr: 2.98e-04
2022-05-15 10:41:25,803 INFO [train.py:812] (3/8) Epoch 26, batch 3650, loss[loss=0.1463, simple_loss=0.2311, pruned_loss=0.03072, over 7262.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.03251, over 1426630.15 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:42:23,892 INFO [train.py:812] (3/8) Epoch 26, batch 3700, loss[loss=0.1743, simple_loss=0.2579, pruned_loss=0.04532, over 7071.00 frames.], tot_loss[loss=0.1562, simple_loss=0.247, pruned_loss=0.03272, over 1423928.58 frames.], batch size: 18, lr: 2.98e-04
2022-05-15 10:43:22,974 INFO [train.py:812] (3/8) Epoch 26, batch 3750, loss[loss=0.1563, simple_loss=0.2495, pruned_loss=0.03161, over 7160.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2476, pruned_loss=0.03286, over 1422107.44 frames.], batch size: 19, lr: 2.98e-04
2022-05-15 10:44:21,256 INFO [train.py:812] (3/8) Epoch 26, batch 3800, loss[loss=0.1511, simple_loss=0.2475, pruned_loss=0.02734, over 6593.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2469, pruned_loss=0.03237, over 1419718.18 frames.], batch size: 38, lr: 2.98e-04
2022-05-15 10:45:20,421 INFO [train.py:812] (3/8) Epoch 26, batch 3850, loss[loss=0.1638, simple_loss=0.2555, pruned_loss=0.03606, over 7146.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03249, over 1417900.30 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:46:19,968 INFO [train.py:812] (3/8) Epoch 26, batch 3900, loss[loss=0.1312, simple_loss=0.2195, pruned_loss=0.02146, over 7421.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2472, pruned_loss=0.03216, over 1420591.46 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:47:17,430 INFO [train.py:812] (3/8) Epoch 26, batch 3950, loss[loss=0.1677, simple_loss=0.2697, pruned_loss=0.03279, over 7223.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2469, pruned_loss=0.03218, over 1424972.58 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:48:16,829 INFO [train.py:812] (3/8) Epoch 26, batch 4000, loss[loss=0.1466, simple_loss=0.2393, pruned_loss=0.02696, over 7430.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2471, pruned_loss=0.0326, over 1418438.18 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:49:15,500 INFO [train.py:812] (3/8) Epoch 26, batch 4050, loss[loss=0.1609, simple_loss=0.2554, pruned_loss=0.03318, over 7426.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03241, over 1420039.00 frames.], batch size: 21, lr: 2.97e-04
2022-05-15 10:50:15,017 INFO [train.py:812] (3/8) Epoch 26, batch 4100, loss[loss=0.1482, simple_loss=0.2417, pruned_loss=0.0273, over 7408.00 frames.], tot_loss[loss=0.157, simple_loss=0.2478, pruned_loss=0.03305, over 1417972.14 frames.], batch size: 21, lr: 2.97e-04
2022-05-15 10:51:14,786 INFO [train.py:812] (3/8) Epoch 26, batch 4150, loss[loss=0.174, simple_loss=0.2639, pruned_loss=0.04208, over 7254.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2468, pruned_loss=0.0325, over 1423048.63 frames.], batch size: 19, lr: 2.97e-04
2022-05-15 10:52:13,189 INFO [train.py:812] (3/8) Epoch 26, batch 4200, loss[loss=0.166, simple_loss=0.2672, pruned_loss=0.03244, over 6999.00 frames.], tot_loss[loss=0.156, simple_loss=0.2469, pruned_loss=0.03248, over 1419352.58 frames.], batch size: 28, lr: 2.97e-04
2022-05-15 10:53:19,329 INFO [train.py:812] (3/8) Epoch 26, batch 4250, loss[loss=0.1475, simple_loss=0.2401, pruned_loss=0.02743, over 7168.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2475, pruned_loss=0.03284, over 1419946.07 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:54:17,966 INFO [train.py:812] (3/8) Epoch 26, batch 4300, loss[loss=0.1873, simple_loss=0.2856, pruned_loss=0.04454, over 7176.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2482, pruned_loss=0.0332, over 1422545.85 frames.], batch size: 26, lr: 2.97e-04
2022-05-15 10:55:15,845 INFO [train.py:812] (3/8) Epoch 26, batch 4350, loss[loss=0.1454, simple_loss=0.2426, pruned_loss=0.0241, over 7239.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2487, pruned_loss=0.03316, over 1415865.95 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:56:15,063 INFO [train.py:812] (3/8) Epoch 26, batch 4400, loss[loss=0.1668, simple_loss=0.2512, pruned_loss=0.04122, over 7072.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2487, pruned_loss=0.0329, over 1415532.24 frames.], batch size: 18, lr: 2.97e-04
2022-05-15 10:57:23,155 INFO [train.py:812] (3/8) Epoch 26, batch 4450, loss[loss=0.1699, simple_loss=0.2632, pruned_loss=0.03834, over 7283.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2492, pruned_loss=0.03313, over 1413421.02 frames.], batch size: 24, lr: 2.97e-04
2022-05-15 10:58:40,619 INFO [train.py:812] (3/8) Epoch 26, batch 4500, loss[loss=0.1581, simple_loss=0.2497, pruned_loss=0.03323, over 7329.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2484, pruned_loss=0.03298, over 1396504.23 frames.], batch size: 20, lr: 2.97e-04
2022-05-15 10:59:48,365 INFO [train.py:812] (3/8) Epoch 26, batch 4550, loss[loss=0.188, simple_loss=0.2868, pruned_loss=0.04458, over 5009.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2485, pruned_loss=0.03328, over 1387550.74 frames.], batch size: 52, lr: 2.97e-04
2022-05-15 11:01:05,797 INFO [train.py:812] (3/8) Epoch 27, batch 0, loss[loss=0.1591, simple_loss=0.2434, pruned_loss=0.0374, over 7164.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2434, pruned_loss=0.0374, over 7164.00 frames.], batch size: 18, lr: 2.91e-04
2022-05-15 11:02:14,197 INFO [train.py:812] (3/8) Epoch 27, batch 50, loss[loss=0.1343, simple_loss=0.2144, pruned_loss=0.02714, over 7288.00 frames.], tot_loss[loss=0.1564, simple_loss=0.247, pruned_loss=0.03292, over 318517.66 frames.], batch size: 17, lr: 2.91e-04
2022-05-15 11:03:12,400 INFO [train.py:812] (3/8) Epoch 27, batch 100, loss[loss=0.1397, simple_loss=0.2185, pruned_loss=0.03047, over 7282.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2481, pruned_loss=0.03305, over 562473.89 frames.], batch size: 17, lr: 2.91e-04
2022-05-15 11:04:11,547 INFO [train.py:812] (3/8) Epoch 27, batch 150, loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03096, over 6355.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03249, over 749976.92 frames.], batch size: 37, lr: 2.91e-04
2022-05-15 11:05:08,305 INFO [train.py:812] (3/8) Epoch 27, batch 200, loss[loss=0.1512, simple_loss=0.2443, pruned_loss=0.02912, over 7210.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03255, over 893133.86 frames.], batch size: 26, lr: 2.91e-04
2022-05-15 11:06:06,618 INFO [train.py:812] (3/8) Epoch 27, batch 250, loss[loss=0.1648, simple_loss=0.2573, pruned_loss=0.03611, over 6310.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2475, pruned_loss=0.0327, over 1006162.28 frames.], batch size: 38, lr: 2.91e-04
2022-05-15 11:07:05,728 INFO [train.py:812] (3/8) Epoch 27, batch 300, loss[loss=0.171, simple_loss=0.2781, pruned_loss=0.032, over 6400.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.0323, over 1100116.37 frames.], batch size: 37, lr: 2.91e-04
2022-05-15 11:08:04,250 INFO [train.py:812] (3/8) Epoch 27, batch 350, loss[loss=0.1619, simple_loss=0.259, pruned_loss=0.03241, over 6807.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03174, over 1169068.42 frames.], batch size: 31, lr: 2.91e-04
2022-05-15 11:09:03,269 INFO [train.py:812] (3/8) Epoch 27, batch 400, loss[loss=0.1636, simple_loss=0.2529, pruned_loss=0.0371, over 7148.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03211, over 1229065.72 frames.], batch size: 20, lr: 2.91e-04
2022-05-15 11:10:01,847 INFO [train.py:812] (3/8) Epoch 27, batch 450, loss[loss=0.1533, simple_loss=0.2433, pruned_loss=0.03168, over 7245.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2469, pruned_loss=0.03221, over 1276193.79 frames.], batch size: 20, lr: 2.91e-04
2022-05-15 11:10:59,671 INFO [train.py:812] (3/8) Epoch 27, batch 500, loss[loss=0.1686, simple_loss=0.2535, pruned_loss=0.04184, over 5293.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2467, pruned_loss=0.03201, over 1308174.00 frames.], batch size: 52, lr: 2.91e-04
2022-05-15 11:11:59,569 INFO [train.py:812] (3/8) Epoch 27, batch 550, loss[loss=0.1969, simple_loss=0.2809, pruned_loss=0.05647, over 7209.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.03248, over 1332598.66 frames.], batch size: 22, lr: 2.90e-04
2022-05-15 11:12:59,032 INFO [train.py:812] (3/8) Epoch 27, batch 600, loss[loss=0.1485, simple_loss=0.2317, pruned_loss=0.0327, over 7256.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2472, pruned_loss=0.0325, over 1355215.01 frames.], batch size: 19, lr: 2.90e-04
2022-05-15 11:13:58,663 INFO [train.py:812] (3/8) Epoch 27, batch 650, loss[loss=0.1177, simple_loss=0.204, pruned_loss=0.01576, over 7278.00 frames.], tot_loss[loss=0.155, simple_loss=0.2461, pruned_loss=0.03195, over 1372132.88 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:14:57,640 INFO [train.py:812] (3/8) Epoch 27, batch 700, loss[loss=0.1539, simple_loss=0.2529, pruned_loss=0.02746, over 7117.00 frames.], tot_loss[loss=0.1557, simple_loss=0.247, pruned_loss=0.0322, over 1380861.55 frames.], batch size: 21, lr: 2.90e-04
2022-05-15 11:16:01,091 INFO [train.py:812] (3/8) Epoch 27, batch 750, loss[loss=0.1494, simple_loss=0.2483, pruned_loss=0.02528, over 7146.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2464, pruned_loss=0.03172, over 1388937.45 frames.], batch size: 20, lr: 2.90e-04
2022-05-15 11:17:00,044 INFO [train.py:812] (3/8) Epoch 27, batch 800, loss[loss=0.1552, simple_loss=0.246, pruned_loss=0.0322, over 7231.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2457, pruned_loss=0.03157, over 1395142.65 frames.], batch size: 20, lr: 2.90e-04
2022-05-15 11:17:59,351 INFO [train.py:812] (3/8) Epoch 27, batch 850, loss[loss=0.1894, simple_loss=0.2605, pruned_loss=0.05913, over 5021.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03185, over 1397565.10 frames.], batch size: 52, lr: 2.90e-04
2022-05-15 11:18:57,702 INFO [train.py:812] (3/8) Epoch 27, batch 900, loss[loss=0.1491, simple_loss=0.2358, pruned_loss=0.03121, over 7398.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2458, pruned_loss=0.03162, over 1407272.33 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:19:56,346 INFO [train.py:812] (3/8) Epoch 27, batch 950, loss[loss=0.1315, simple_loss=0.2212, pruned_loss=0.02091, over 6778.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03208, over 1408173.61 frames.], batch size: 15, lr: 2.90e-04
2022-05-15 11:20:55,288 INFO [train.py:812] (3/8) Epoch 27, batch 1000, loss[loss=0.1738, simple_loss=0.2623, pruned_loss=0.04271, over 7298.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2476, pruned_loss=0.0325, over 1411970.43 frames.], batch size: 24, lr: 2.90e-04
2022-05-15 11:21:53,179 INFO [train.py:812] (3/8) Epoch 27, batch 1050, loss[loss=0.1617, simple_loss=0.2568, pruned_loss=0.03333, over 7199.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03218, over 1417403.56 frames.], batch size: 23, lr: 2.90e-04
2022-05-15 11:22:52,383 INFO [train.py:812] (3/8) Epoch 27, batch 1100, loss[loss=0.1753, simple_loss=0.2665, pruned_loss=0.04203, over 7206.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2467, pruned_loss=0.03193, over 1422045.60 frames.], batch size: 22, lr: 2.90e-04
2022-05-15 11:23:52,138 INFO [train.py:812] (3/8) Epoch 27, batch 1150, loss[loss=0.1396, simple_loss=0.2239, pruned_loss=0.02762, over 7163.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2478, pruned_loss=0.03234, over 1423104.61 frames.], batch size: 19, lr: 2.90e-04
2022-05-15 11:24:50,276 INFO [train.py:812] (3/8) Epoch 27, batch 1200, loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03129, over 7301.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2472, pruned_loss=0.03199, over 1427022.13 frames.], batch size: 24, lr: 2.90e-04
2022-05-15 11:25:49,797 INFO [train.py:812] (3/8) Epoch 27, batch 1250, loss[loss=0.1569, simple_loss=0.2505, pruned_loss=0.03164, over 6348.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03183, over 1427095.06 frames.], batch size: 37, lr: 2.90e-04
2022-05-15 11:26:48,354 INFO [train.py:812] (3/8) Epoch 27, batch 1300, loss[loss=0.1263, simple_loss=0.2126, pruned_loss=0.02001, over 7287.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2467, pruned_loss=0.03213, over 1423652.67 frames.], batch size: 18, lr: 2.90e-04
2022-05-15 11:27:46,492 INFO [train.py:812] (3/8) Epoch 27, batch 1350, loss[loss=0.123, simple_loss=0.2122, pruned_loss=0.01688, over 7416.00 frames.], tot_loss[loss=0.1541, simple_loss=0.245, pruned_loss=0.03156, over 1427348.37 frames.], batch size: 18, lr: 2.89e-04
2022-05-15 11:28:44,270 INFO [train.py:812] (3/8) Epoch 27, batch 1400, loss[loss=0.1702, simple_loss=0.2581, pruned_loss=0.04122, over 7205.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2447, pruned_loss=0.03175, over 1419380.96 frames.], batch size: 23, lr: 2.89e-04
2022-05-15 11:29:43,175 INFO [train.py:812] (3/8) Epoch 27, batch 1450, loss[loss=0.1332, simple_loss=0.2241, pruned_loss=0.02112, over 7274.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2449, pruned_loss=0.03186, over 1422053.09 frames.], batch size: 18, lr: 2.89e-04
2022-05-15 11:30:41,589 INFO [train.py:812] (3/8) Epoch 27, batch 1500, loss[loss=0.1665, simple_loss=0.2493, pruned_loss=0.04189, over 5547.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2446, pruned_loss=0.03147, over 1418014.02 frames.], batch size: 52, lr: 2.89e-04
2022-05-15 11:31:41,140 INFO [train.py:812] (3/8) Epoch 27, batch 1550, loss[loss=0.1655, simple_loss=0.2567, pruned_loss=0.03712, over 7115.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.03169, over 1421193.34 frames.], batch size: 21, lr: 2.89e-04
2022-05-15 11:32:40,458 INFO [train.py:812] (3/8) Epoch 27, batch 1600, loss[loss=0.1292, simple_loss=0.2187, pruned_loss=0.01988, over 7256.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2439, pruned_loss=0.03143, over 1424377.70 frames.], batch size: 19, lr: 2.89e-04
2022-05-15 11:33:39,615 INFO [train.py:812] (3/8) Epoch 27, batch 1650, loss[loss=0.1585, simple_loss=0.2615, pruned_loss=0.02777, over 7159.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2449, pruned_loss=0.03134, over 1428182.02 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:34:37,986 INFO [train.py:812] (3/8) Epoch 27, batch 1700, loss[loss=0.1559, simple_loss=0.2576, pruned_loss=0.02712, over 7351.00 frames.], tot_loss[loss=0.154, simple_loss=0.2452, pruned_loss=0.03142, over 1429914.06 frames.], batch size: 22, lr: 2.89e-04
2022-05-15 11:35:35,782 INFO [train.py:812] (3/8) Epoch 27, batch 1750, loss[loss=0.1598, simple_loss=0.257, pruned_loss=0.03129, over 7137.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03144, over 1430499.04 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:36:34,355 INFO [train.py:812] (3/8) Epoch 27, batch 1800, loss[loss=0.162, simple_loss=0.2587, pruned_loss=0.03262, over 7107.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2458, pruned_loss=0.03156, over 1428494.01 frames.], batch size: 21, lr: 2.89e-04
2022-05-15 11:37:32,431 INFO [train.py:812] (3/8) Epoch 27, batch 1850, loss[loss=0.1572, simple_loss=0.2494, pruned_loss=0.0325, over 4933.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2465, pruned_loss=0.03201, over 1429077.75 frames.], batch size: 52, lr: 2.89e-04
2022-05-15 11:38:30,737 INFO [train.py:812] (3/8) Epoch 27, batch 1900, loss[loss=0.1361, simple_loss=0.2211, pruned_loss=0.02558, over 7360.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2457, pruned_loss=0.03168, over 1428313.11 frames.], batch size: 19, lr: 2.89e-04
2022-05-15 11:39:30,044 INFO [train.py:812] (3/8) Epoch 27, batch 1950, loss[loss=0.1554, simple_loss=0.2525, pruned_loss=0.02913, over 6313.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2459, pruned_loss=0.03195, over 1424897.36 frames.], batch size: 37, lr: 2.89e-04
2022-05-15 11:40:29,355 INFO [train.py:812] (3/8) Epoch 27, batch 2000, loss[loss=0.1581, simple_loss=0.2559, pruned_loss=0.03016, over 6777.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2457, pruned_loss=0.03203, over 1423165.97 frames.], batch size: 31, lr: 2.89e-04
2022-05-15 11:41:28,616 INFO [train.py:812] (3/8) Epoch 27, batch 2050, loss[loss=0.1678, simple_loss=0.2573, pruned_loss=0.03919, over 7123.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2467, pruned_loss=0.03257, over 1425966.19 frames.], batch size: 26, lr: 2.89e-04
2022-05-15 11:42:27,675 INFO [train.py:812] (3/8) Epoch 27, batch 2100, loss[loss=0.1666, simple_loss=0.2649, pruned_loss=0.03413, over 7192.00 frames.], tot_loss[loss=0.156, simple_loss=0.2471, pruned_loss=0.03249, over 1424379.48 frames.], batch size: 22, lr: 2.89e-04
2022-05-15 11:43:25,350 INFO [train.py:812] (3/8) Epoch 27, batch 2150, loss[loss=0.182, simple_loss=0.2729, pruned_loss=0.04556, over 7313.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2483, pruned_loss=0.03257, over 1427677.09 frames.], batch size: 25, lr: 2.89e-04
2022-05-15 11:44:23,717 INFO [train.py:812] (3/8) Epoch 27, batch 2200, loss[loss=0.1562, simple_loss=0.2535, pruned_loss=0.02948, over 7225.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2474, pruned_loss=0.03243, over 1425962.15 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:45:23,009 INFO [train.py:812] (3/8) Epoch 27, batch 2250, loss[loss=0.1427, simple_loss=0.2271, pruned_loss=0.02915, over 6998.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2475, pruned_loss=0.0323, over 1431077.00 frames.], batch size: 16, lr: 2.88e-04
2022-05-15 11:46:21,528 INFO [train.py:812] (3/8) Epoch 27, batch 2300, loss[loss=0.1252, simple_loss=0.2117, pruned_loss=0.01936, over 7137.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2475, pruned_loss=0.03213, over 1433315.30 frames.], batch size: 17, lr: 2.88e-04
2022-05-15 11:47:19,554 INFO [train.py:812] (3/8) Epoch 27, batch 2350, loss[loss=0.1716, simple_loss=0.2759, pruned_loss=0.0336, over 7139.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2476, pruned_loss=0.03228, over 1431156.09 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:48:16,531 INFO [train.py:812] (3/8) Epoch 27, batch 2400, loss[loss=0.1636, simple_loss=0.2525, pruned_loss=0.03734, over 7296.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03248, over 1432882.38 frames.], batch size: 24, lr: 2.88e-04
2022-05-15 11:49:16,161 INFO [train.py:812] (3/8) Epoch 27, batch 2450, loss[loss=0.1577, simple_loss=0.2536, pruned_loss=0.03092, over 7226.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03197, over 1435364.18 frames.], batch size: 20, lr: 2.88e-04
2022-05-15 11:50:15,240 INFO [train.py:812] (3/8) Epoch 27, batch 2500, loss[loss=0.1669, simple_loss=0.2552, pruned_loss=0.03931, over 7211.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03185, over 1437471.13 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 11:51:13,610 INFO [train.py:812] (3/8) Epoch 27, batch 2550, loss[loss=0.1583, simple_loss=0.2565, pruned_loss=0.03002, over 6823.00 frames.], tot_loss[loss=0.154, simple_loss=0.2456, pruned_loss=0.03124, over 1435007.49 frames.], batch size: 31, lr: 2.88e-04
2022-05-15 11:52:12,823 INFO [train.py:812] (3/8) Epoch 27, batch 2600, loss[loss=0.1406, simple_loss=0.2359, pruned_loss=0.02264, over 7229.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2464, pruned_loss=0.03169, over 1434966.21 frames.], batch size: 16, lr: 2.88e-04
2022-05-15 11:53:12,307 INFO [train.py:812] (3/8) Epoch 27, batch 2650, loss[loss=0.1527, simple_loss=0.2539, pruned_loss=0.02573, over 7268.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03185, over 1431176.91 frames.], batch size: 24, lr: 2.88e-04
2022-05-15 11:54:11,600 INFO [train.py:812] (3/8) Epoch 27, batch 2700, loss[loss=0.1564, simple_loss=0.2497, pruned_loss=0.03149, over 7337.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03174, over 1429115.58 frames.], batch size: 22, lr: 2.88e-04
2022-05-15 11:55:10,407 INFO [train.py:812] (3/8) Epoch 27, batch 2750, loss[loss=0.1447, simple_loss=0.2397, pruned_loss=0.02486, over 7164.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03137, over 1428239.44 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:56:08,578 INFO [train.py:812] (3/8) Epoch 27, batch 2800, loss[loss=0.1594, simple_loss=0.2522, pruned_loss=0.0333, over 7305.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2456, pruned_loss=0.03113, over 1427436.74 frames.], batch size: 25, lr: 2.88e-04
2022-05-15 11:57:08,031 INFO [train.py:812] (3/8) Epoch 27, batch 2850, loss[loss=0.1482, simple_loss=0.2419, pruned_loss=0.02723, over 7246.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03125, over 1426982.58 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:58:06,919 INFO [train.py:812] (3/8) Epoch 27, batch 2900, loss[loss=0.1343, simple_loss=0.2194, pruned_loss=0.02456, over 7156.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.03152, over 1426513.53 frames.], batch size: 19, lr: 2.88e-04
2022-05-15 11:59:06,482 INFO [train.py:812] (3/8) Epoch 27, batch 2950, loss[loss=0.1519, simple_loss=0.2502, pruned_loss=0.02674, over 7112.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2467, pruned_loss=0.03157, over 1420205.99 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 12:00:05,427 INFO [train.py:812] (3/8) Epoch 27, batch 3000, loss[loss=0.1729, simple_loss=0.2651, pruned_loss=0.04037, over 7415.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2464, pruned_loss=0.03146, over 1419055.52 frames.], batch size: 21, lr: 2.88e-04
2022-05-15 12:00:05,428 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 12:00:12,945 INFO [train.py:841] (3/8) Epoch 27, validation: loss=0.1528, simple_loss=0.25, pruned_loss=0.02785, over 698248.00 frames.
2022-05-15 12:01:11,833 INFO [train.py:812] (3/8) Epoch 27, batch 3050, loss[loss=0.1525, simple_loss=0.2531, pruned_loss=0.02598, over 7113.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03138, over 1411405.60 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:02:10,771 INFO [train.py:812] (3/8) Epoch 27, batch 3100, loss[loss=0.1548, simple_loss=0.257, pruned_loss=0.02624, over 7319.00 frames.], tot_loss[loss=0.1549, simple_loss=0.247, pruned_loss=0.03141, over 1417236.85 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:03:20,252 INFO [train.py:812] (3/8) Epoch 27, batch 3150, loss[loss=0.1544, simple_loss=0.2508, pruned_loss=0.02894, over 7213.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2471, pruned_loss=0.03158, over 1417895.17 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:04:19,260 INFO [train.py:812] (3/8) Epoch 27, batch 3200, loss[loss=0.1676, simple_loss=0.2566, pruned_loss=0.03931, over 7184.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2478, pruned_loss=0.0325, over 1418751.29 frames.], batch size: 23, lr: 2.87e-04
2022-05-15 12:05:18,852 INFO [train.py:812] (3/8) Epoch 27, batch 3250, loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03444, over 6449.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2468, pruned_loss=0.03222, over 1420424.88 frames.], batch size: 37, lr: 2.87e-04
2022-05-15 12:06:17,727 INFO [train.py:812] (3/8) Epoch 27, batch 3300, loss[loss=0.159, simple_loss=0.2502, pruned_loss=0.03391, over 6668.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2465, pruned_loss=0.03225, over 1419445.63 frames.], batch size: 31, lr: 2.87e-04
2022-05-15 12:07:17,124 INFO [train.py:812] (3/8) Epoch 27, batch 3350, loss[loss=0.1528, simple_loss=0.2559, pruned_loss=0.02485, over 7329.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2476, pruned_loss=0.03234, over 1420234.84 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:08:16,173 INFO [train.py:812] (3/8) Epoch 27, batch 3400, loss[loss=0.1287, simple_loss=0.2246, pruned_loss=0.01646, over 7144.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03247, over 1417538.66 frames.], batch size: 20, lr: 2.87e-04
2022-05-15 12:09:14,980 INFO [train.py:812] (3/8) Epoch 27, batch 3450, loss[loss=0.1462, simple_loss=0.2453, pruned_loss=0.02355, over 7332.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2477, pruned_loss=0.03227, over 1421255.59 frames.], batch size: 22, lr: 2.87e-04
2022-05-15 12:10:13,329 INFO [train.py:812] (3/8) Epoch 27, batch 3500, loss[loss=0.138, simple_loss=0.2239, pruned_loss=0.02605, over 6840.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03184, over 1423466.54 frames.], batch size: 15, lr: 2.87e-04
2022-05-15 12:11:13,072 INFO [train.py:812] (3/8) Epoch 27, batch 3550, loss[loss=0.1798, simple_loss=0.2636, pruned_loss=0.048, over 5060.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2459, pruned_loss=0.03145, over 1417185.12 frames.], batch size: 52, lr: 2.87e-04
2022-05-15 12:12:10,926 INFO [train.py:812] (3/8) Epoch 27, batch 3600, loss[loss=0.1471, simple_loss=0.2403, pruned_loss=0.02695, over 7156.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2463, pruned_loss=0.03122, over 1415474.10 frames.], batch size: 19, lr: 2.87e-04
2022-05-15 12:13:10,317 INFO [train.py:812] (3/8) Epoch 27, batch 3650, loss[loss=0.147, simple_loss=0.2383, pruned_loss=0.02789, over 7072.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03139, over 1414126.68 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:14:09,323 INFO [train.py:812] (3/8) Epoch 27, batch 3700, loss[loss=0.1492, simple_loss=0.2337, pruned_loss=0.03238, over 7282.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03189, over 1413224.71 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:15:08,394 INFO [train.py:812] (3/8) Epoch 27, batch 3750, loss[loss=0.1519, simple_loss=0.2513, pruned_loss=0.02629, over 7205.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2468, pruned_loss=0.03239, over 1416803.91 frames.], batch size: 21, lr: 2.87e-04
2022-05-15 12:16:08,126 INFO [train.py:812] (3/8) Epoch 27, batch 3800, loss[loss=0.1499, simple_loss=0.2307, pruned_loss=0.03456, over 7319.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03171, over 1420751.04 frames.], batch size: 20, lr: 2.87e-04
2022-05-15 12:17:07,774 INFO [train.py:812] (3/8) Epoch 27, batch 3850, loss[loss=0.1479, simple_loss=0.2393, pruned_loss=0.02828, over 7407.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2479, pruned_loss=0.03247, over 1414619.95 frames.], batch size: 18, lr: 2.87e-04
2022-05-15 12:18:06,242 INFO [train.py:812] (3/8) Epoch 27, batch 3900, loss[loss=0.1843, simple_loss=0.2724, pruned_loss=0.0481, over 7120.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2482, pruned_loss=0.03265, over 1415733.38 frames.], batch size: 28, lr: 2.86e-04
2022-05-15 12:19:04,961 INFO [train.py:812] (3/8) Epoch 27, batch 3950, loss[loss=0.1419, simple_loss=0.2198, pruned_loss=0.03194, over 7352.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03251, over 1420515.81 frames.], batch size: 19, lr: 2.86e-04
2022-05-15 12:20:04,222 INFO [train.py:812] (3/8) Epoch 27, batch 4000, loss[loss=0.1606, simple_loss=0.2519, pruned_loss=0.03464, over 7106.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2474, pruned_loss=0.0325, over 1425319.02 frames.], batch size: 28, lr: 2.86e-04
2022-05-15 12:21:04,105 INFO [train.py:812] (3/8) Epoch 27, batch 4050, loss[loss=0.1608, simple_loss=0.2482, pruned_loss=0.03675, over 7330.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2473, pruned_loss=0.03245, over 1426118.25 frames.], batch size: 20, lr: 2.86e-04
2022-05-15 12:22:03,540 INFO [train.py:812] (3/8) Epoch 27, batch 4100, loss[loss=0.1356, simple_loss=0.2229, pruned_loss=0.02417, over 7338.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.03193, over 1424903.83 frames.], batch size: 20, lr: 2.86e-04
2022-05-15 12:23:02,354 INFO [train.py:812] (3/8) Epoch 27, batch 4150, loss[loss=0.1607, simple_loss=0.2619, pruned_loss=0.02971, over 7107.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2471, pruned_loss=0.03219, over 1422501.53 frames.], batch size: 21, lr: 2.86e-04
2022-05-15 12:23:59,497 INFO [train.py:812] (3/8) Epoch 27, batch 4200, loss[loss=0.1483, simple_loss=0.2563, pruned_loss=0.02018, over 7335.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03215, over 1423836.14 frames.], batch size: 22, lr: 2.86e-04
2022-05-15 12:24:57,508 INFO [train.py:812] (3/8) Epoch 27, batch 4250, loss[loss=0.164, simple_loss=0.2642, pruned_loss=0.03183, over 7423.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2473, pruned_loss=0.03221, over 1417097.81 frames.], batch size: 21, lr: 2.86e-04
2022-05-15 12:25:55,492 INFO [train.py:812] (3/8) Epoch 27, batch 4300, loss[loss=0.1461, simple_loss=0.2442, pruned_loss=0.02397, over 6812.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2483, pruned_loss=0.03242, over 1416430.83 frames.], batch size: 31, lr: 2.86e-04
2022-05-15 12:26:54,771 INFO [train.py:812] (3/8) Epoch 27, batch 4350, loss[loss=0.1228, simple_loss=0.2093, pruned_loss=0.01816, over 6998.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2484, pruned_loss=0.03229, over 1415950.91 frames.], batch size: 16, lr: 2.86e-04
2022-05-15 12:27:53,340 INFO [train.py:812] (3/8) Epoch 27, batch 4400, loss[loss=0.1718, simple_loss=0.2731, pruned_loss=0.03526, over 6350.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2493, pruned_loss=0.03302, over 1402637.15 frames.], batch size: 38, lr: 2.86e-04
2022-05-15 12:28:51,263 INFO [train.py:812] (3/8) Epoch 27, batch 4450, loss[loss=0.1603, simple_loss=0.2569, pruned_loss=0.03183, over 7333.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2488, pruned_loss=0.03337, over 1397162.58 frames.], batch size: 22, lr: 2.86e-04
2022-05-15 12:29:50,404 INFO [train.py:812] (3/8) Epoch 27, batch 4500, loss[loss=0.1714, simple_loss=0.2665, pruned_loss=0.03813, over 7154.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2483, pruned_loss=0.03318, over 1387707.82 frames.], batch size: 18, lr: 2.86e-04
2022-05-15 12:30:49,285 INFO [train.py:812] (3/8) Epoch 27, batch 4550, loss[loss=0.1879, simple_loss=0.2767, pruned_loss=0.04954, over 5036.00 frames.], tot_loss[loss=0.1568, simple_loss=0.247, pruned_loss=0.03326, over 1370609.90 frames.], batch size: 52, lr: 2.86e-04
2022-05-15 12:32:00,087 INFO [train.py:812] (3/8) Epoch 28, batch 0, loss[loss=0.1479, simple_loss=0.2336, pruned_loss=0.03105, over 7263.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2336, pruned_loss=0.03105, over 7263.00 frames.], batch size: 19, lr: 2.81e-04
2022-05-15 12:32:59,356 INFO [train.py:812] (3/8) Epoch 28, batch 50, loss[loss=0.1366, simple_loss=0.2254, pruned_loss=0.02394, over 7256.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2458, pruned_loss=0.03188, over 321702.64 frames.], batch size: 19, lr: 2.81e-04
2022-05-15 12:33:58,530 INFO [train.py:812] (3/8) Epoch 28, batch 100, loss[loss=0.1701, simple_loss=0.2722, pruned_loss=0.03396, over 7150.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2468, pruned_loss=0.03167, over 565290.18 frames.], batch size: 20, lr: 2.80e-04
2022-05-15 12:35:03,237 INFO [train.py:812] (3/8) Epoch 28, batch 150, loss[loss=0.1433, simple_loss=0.2378, pruned_loss=0.02437, over 6463.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.03121, over 753903.81 frames.], batch size: 38, lr: 2.80e-04
2022-05-15 12:36:01,533 INFO [train.py:812] (3/8) Epoch 28, batch 200, loss[loss=0.1943, simple_loss=0.2804, pruned_loss=0.05415, over 7181.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2473, pruned_loss=0.0315, over 899776.13 frames.], batch size: 23, lr: 2.80e-04
2022-05-15 12:36:59,616 INFO [train.py:812] (3/8) Epoch 28, batch 250, loss[loss=0.1572, simple_loss=0.2501, pruned_loss=0.03215, over 7299.00 frames.], tot_loss[loss=0.155, simple_loss=0.2469, pruned_loss=0.03152, over 1015515.71 frames.], batch size: 24, lr: 2.80e-04
2022-05-15 12:37:58,302 INFO [train.py:812] (3/8) Epoch 28, batch 300, loss[loss=0.1444, simple_loss=0.2315, pruned_loss=0.02862, over 6807.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03116, over 1105034.66 frames.], batch size: 31, lr: 2.80e-04
2022-05-15 12:38:57,242 INFO [train.py:812] (3/8) Epoch 28, batch 350, loss[loss=0.1448, simple_loss=0.2368, pruned_loss=0.02643, over 7170.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03079, over 1177103.03 frames.], batch size: 19, lr: 2.80e-04
2022-05-15 12:39:55,229 INFO [train.py:812] (3/8) Epoch 28, batch 400, loss[loss=0.1453, simple_loss=0.2326, pruned_loss=0.02898, over 7125.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03106, over 1233410.67 frames.], batch size: 17, lr: 2.80e-04
2022-05-15 12:40:54,572 INFO [train.py:812] (3/8) Epoch 28, batch 450, loss[loss=0.1574, simple_loss=0.2499, pruned_loss=0.03251, over 7277.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.03109, over 1270591.34 frames.], batch size: 25, lr: 2.80e-04
2022-05-15 12:41:53,058 INFO [train.py:812] (3/8) Epoch 28, batch 500, loss[loss=0.1433, simple_loss=0.2416, pruned_loss=0.02252, over 7315.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2464, pruned_loss=0.03093, over 1307705.52 frames.], batch size: 21, lr: 2.80e-04
2022-05-15 12:42:52,279 INFO [train.py:812] (3/8) Epoch 28, batch 550, loss[loss=0.1488, simple_loss=0.2332, pruned_loss=0.03221, over 7077.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03068, over 1330189.37 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:43:51,382 INFO [train.py:812] (3/8) Epoch 28, batch 600, loss[loss=0.1518, simple_loss=0.2552, pruned_loss=0.02423, over 7328.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.03088, over 1348415.59 frames.], batch size: 20, lr: 2.80e-04
2022-05-15 12:44:49,180 INFO [train.py:812] (3/8) Epoch 28, batch 650, loss[loss=0.1678, simple_loss=0.2834, pruned_loss=0.02607, over 6982.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2466, pruned_loss=0.03106, over 1366051.40 frames.], batch size: 28, lr: 2.80e-04
2022-05-15 12:45:47,935 INFO [train.py:812] (3/8) Epoch 28, batch 700, loss[loss=0.1489, simple_loss=0.2397, pruned_loss=0.0291, over 7066.00 frames.], tot_loss[loss=0.1536, simple_loss=0.246, pruned_loss=0.03061, over 1379566.74 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:46:48,080 INFO [train.py:812] (3/8) Epoch 28, batch 750, loss[loss=0.1476, simple_loss=0.2539, pruned_loss=0.02066, over 7213.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03032, over 1390346.22 frames.], batch size: 21, lr: 2.80e-04
2022-05-15 12:47:47,179 INFO [train.py:812] (3/8) Epoch 28, batch 800, loss[loss=0.1712, simple_loss=0.2521, pruned_loss=0.04518, over 7119.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2458, pruned_loss=0.03066, over 1397378.88 frames.], batch size: 28, lr: 2.80e-04
2022-05-15 12:48:46,808 INFO [train.py:812] (3/8) Epoch 28, batch 850, loss[loss=0.1505, simple_loss=0.2551, pruned_loss=0.02294, over 7295.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2458, pruned_loss=0.03061, over 1406000.75 frames.], batch size: 25, lr: 2.80e-04
2022-05-15 12:49:45,701 INFO [train.py:812] (3/8) Epoch 28, batch 900, loss[loss=0.1347, simple_loss=0.2251, pruned_loss=0.02217, over 7007.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2471, pruned_loss=0.0312, over 1408627.28 frames.], batch size: 16, lr: 2.80e-04
2022-05-15 12:50:44,993 INFO [train.py:812] (3/8) Epoch 28, batch 950, loss[loss=0.1439, simple_loss=0.2341, pruned_loss=0.02686, over 7160.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2478, pruned_loss=0.03155, over 1410559.41 frames.], batch size: 18, lr: 2.80e-04
2022-05-15 12:51:43,943 INFO [train.py:812] (3/8) Epoch 28, batch 1000, loss[loss=0.1531, simple_loss=0.2412, pruned_loss=0.03246, over 7428.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2476, pruned_loss=0.03173, over 1415820.94 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 12:52:42,541 INFO [train.py:812] (3/8) Epoch 28, batch 1050, loss[loss=0.1378, simple_loss=0.2386, pruned_loss=0.01848, over 7414.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2478, pruned_loss=0.03185, over 1415566.98 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 12:53:50,420 INFO [train.py:812] (3/8) Epoch 28, batch 1100, loss[loss=0.1512, simple_loss=0.2409, pruned_loss=0.03076, over 7071.00 frames.], tot_loss[loss=0.156, simple_loss=0.2477, pruned_loss=0.03217, over 1415070.44 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 12:54:49,777 INFO [train.py:812] (3/8) Epoch 28, batch 1150, loss[loss=0.1708, simple_loss=0.264, pruned_loss=0.03883, over 7201.00 frames.], tot_loss[loss=0.1559, simple_loss=0.247, pruned_loss=0.03239, over 1420181.10 frames.], batch size: 23, lr: 2.79e-04
2022-05-15 12:55:48,177 INFO [train.py:812] (3/8) Epoch 28, batch 1200, loss[loss=0.1719, simple_loss=0.2667, pruned_loss=0.03861, over 7129.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2468, pruned_loss=0.03236, over 1424597.32 frames.], batch size: 17, lr: 2.79e-04
2022-05-15 12:56:47,570 INFO [train.py:812] (3/8) Epoch 28, batch 1250, loss[loss=0.1296, simple_loss=0.2152, pruned_loss=0.02207, over 7154.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2472, pruned_loss=0.03229, over 1422019.19 frames.], batch size: 17, lr: 2.79e-04
2022-05-15 12:57:56,206 INFO [train.py:812] (3/8) Epoch 28, batch 1300, loss[loss=0.1435, simple_loss=0.2245, pruned_loss=0.03122, over 7290.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2471, pruned_loss=0.03222, over 1418090.83 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 12:58:55,694 INFO [train.py:812] (3/8) Epoch 28, batch 1350, loss[loss=0.1609, simple_loss=0.2385, pruned_loss=0.04163, over 7364.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2466, pruned_loss=0.03185, over 1418536.09 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:00:02,714 INFO [train.py:812] (3/8) Epoch 28, batch 1400, loss[loss=0.1475, simple_loss=0.2258, pruned_loss=0.03461, over 7075.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03167, over 1418856.10 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 13:01:30,482 INFO [train.py:812] (3/8) Epoch 28, batch 1450, loss[loss=0.1445, simple_loss=0.2421, pruned_loss=0.02345, over 7325.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2445, pruned_loss=0.03154, over 1420807.95 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 13:02:27,760 INFO [train.py:812] (3/8) Epoch 28, batch 1500, loss[loss=0.1673, simple_loss=0.2712, pruned_loss=0.03171, over 7129.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2458, pruned_loss=0.03198, over 1422976.76 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 13:03:25,221 INFO [train.py:812] (3/8) Epoch 28, batch 1550, loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02965, over 7197.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2456, pruned_loss=0.03176, over 1420368.18 frames.], batch size: 16, lr: 2.79e-04
2022-05-15 13:04:33,685 INFO [train.py:812] (3/8) Epoch 28, batch 1600, loss[loss=0.1457, simple_loss=0.246, pruned_loss=0.02273, over 7398.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2449, pruned_loss=0.03124, over 1424516.48 frames.], batch size: 21, lr: 2.79e-04
2022-05-15 13:05:32,118 INFO [train.py:812] (3/8) Epoch 28, batch 1650, loss[loss=0.1573, simple_loss=0.2369, pruned_loss=0.03888, over 7067.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2447, pruned_loss=0.0312, over 1425722.56 frames.], batch size: 18, lr: 2.79e-04
2022-05-15 13:06:30,575 INFO [train.py:812] (3/8) Epoch 28, batch 1700, loss[loss=0.1396, simple_loss=0.2332, pruned_loss=0.02304, over 7344.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2447, pruned_loss=0.03119, over 1427010.51 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:07:29,547 INFO [train.py:812] (3/8) Epoch 28, batch 1750, loss[loss=0.1572, simple_loss=0.2472, pruned_loss=0.03356, over 6877.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03154, over 1428822.88 frames.], batch size: 31, lr: 2.79e-04
2022-05-15 13:08:28,868 INFO [train.py:812] (3/8) Epoch 28, batch 1800, loss[loss=0.1908, simple_loss=0.2823, pruned_loss=0.04966, over 7238.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2451, pruned_loss=0.03161, over 1427930.06 frames.], batch size: 20, lr: 2.79e-04
2022-05-15 13:09:27,169 INFO [train.py:812] (3/8) Epoch 28, batch 1850, loss[loss=0.1588, simple_loss=0.243, pruned_loss=0.03728, over 7149.00 frames.], tot_loss[loss=0.154, simple_loss=0.2451, pruned_loss=0.03143, over 1430347.19 frames.], batch size: 19, lr: 2.79e-04
2022-05-15 13:10:26,321 INFO [train.py:812] (3/8) Epoch 28, batch 1900, loss[loss=0.1614, simple_loss=0.2445, pruned_loss=0.03912, over 7279.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2461, pruned_loss=0.03162, over 1430169.05 frames.], batch size: 17, lr: 2.78e-04
2022-05-15 13:11:24,507 INFO [train.py:812] (3/8) Epoch 28, batch 1950, loss[loss=0.152, simple_loss=0.2395, pruned_loss=0.03221, over 6560.00 frames.], tot_loss[loss=0.155, simple_loss=0.2463, pruned_loss=0.03185, over 1426011.25 frames.], batch size: 39, lr: 2.78e-04
2022-05-15 13:12:23,334 INFO [train.py:812] (3/8) Epoch 28, batch 2000, loss[loss=0.1503, simple_loss=0.245, pruned_loss=0.02779, over 7218.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2462, pruned_loss=0.03175, over 1425295.19 frames.], batch size: 21, lr: 2.78e-04
2022-05-15 13:13:21,604 INFO [train.py:812] (3/8) Epoch 28, batch 2050, loss[loss=0.1592, simple_loss=0.2566, pruned_loss=0.0309, over 7208.00 frames.], tot_loss[loss=0.1556, simple_loss=0.247, pruned_loss=0.03215, over 1423907.85 frames.], batch size: 23, lr: 2.78e-04
2022-05-15 13:14:20,999 INFO [train.py:812] (3/8) Epoch 28, batch 2100, loss[loss=0.1719, simple_loss=0.2687, pruned_loss=0.03752, over 7306.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2468, pruned_loss=0.03192, over 1423402.42 frames.], batch size: 25, lr: 2.78e-04
2022-05-15 13:15:20,652 INFO [train.py:812] (3/8) Epoch 28, batch 2150, loss[loss=0.1421, simple_loss=0.2314, pruned_loss=0.02635, over 7131.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2473, pruned_loss=0.03188, over 1422280.17 frames.], batch size: 17, lr: 2.78e-04
2022-05-15 13:16:19,064 INFO [train.py:812] (3/8) Epoch 28, batch 2200, loss[loss=0.1636, simple_loss=0.2516, pruned_loss=0.03775, over 7268.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2474, pruned_loss=0.03195, over 1420581.20 frames.], batch size: 24, lr: 2.78e-04
2022-05-15 13:17:18,194 INFO [train.py:812] (3/8) Epoch 28, batch 2250, loss[loss=0.1608, simple_loss=0.2545, pruned_loss=0.03352, over 7330.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2466, pruned_loss=0.03144, over 1423544.13 frames.], batch size: 22, lr: 2.78e-04
2022-05-15 13:18:16,759 INFO [train.py:812] (3/8) Epoch 28, batch 2300, loss[loss=0.1592, simple_loss=0.2447, pruned_loss=0.03682, over 7146.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2468, pruned_loss=0.03151, over 1421629.72 frames.], batch size: 20, lr: 2.78e-04
2022-05-15 13:19:16,301 INFO [train.py:812] (3/8) Epoch 28, batch 2350, loss[loss=0.1305, simple_loss=0.2265, pruned_loss=0.01719, over 7169.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2464, pruned_loss=0.03154, over 1419425.43 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:20:14,306 INFO [train.py:812] (3/8) Epoch 28, batch 2400, loss[loss=0.1658, simple_loss=0.2559, pruned_loss=0.03781, over 7207.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2471, pruned_loss=0.03156, over 1422540.49 frames.], batch size: 23, lr: 2.78e-04
2022-05-15 13:21:14,086 INFO [train.py:812] (3/8) Epoch 28, batch 2450, loss[loss=0.143, simple_loss=0.2346, pruned_loss=0.02571, over 6444.00 frames.], tot_loss[loss=0.154, simple_loss=0.246, pruned_loss=0.03094, over 1423300.04 frames.], batch size: 38, lr: 2.78e-04
2022-05-15 13:22:13,072 INFO [train.py:812] (3/8) Epoch 28, batch 2500, loss[loss=0.1435, simple_loss=0.2316, pruned_loss=0.0277, over 6771.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03147, over 1420393.94 frames.], batch size: 15, lr: 2.78e-04
2022-05-15 13:23:12,405 INFO [train.py:812] (3/8) Epoch 28, batch 2550, loss[loss=0.1657, simple_loss=0.2447, pruned_loss=0.04331, over 7256.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03179, over 1421658.29 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:24:10,660 INFO [train.py:812] (3/8) Epoch 28, batch 2600, loss[loss=0.1426, simple_loss=0.2398, pruned_loss=0.02268, over 7231.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2468, pruned_loss=0.03171, over 1421556.68 frames.], batch size: 20, lr: 2.78e-04
2022-05-15 13:25:09,881 INFO [train.py:812] (3/8) Epoch 28, batch 2650, loss[loss=0.135, simple_loss=0.2236, pruned_loss=0.02317, over 7006.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2469, pruned_loss=0.03173, over 1420246.89 frames.], batch size: 16, lr: 2.78e-04
2022-05-15 13:26:08,939 INFO [train.py:812] (3/8) Epoch 28, batch 2700, loss[loss=0.1435, simple_loss=0.242, pruned_loss=0.02255, over 7324.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2469, pruned_loss=0.03142, over 1421881.30 frames.], batch size: 21, lr: 2.78e-04
2022-05-15 13:27:07,531 INFO [train.py:812] (3/8) Epoch 28, batch 2750, loss[loss=0.1606, simple_loss=0.2583, pruned_loss=0.03148, over 7249.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03117, over 1420642.80 frames.], batch size: 19, lr: 2.78e-04
2022-05-15 13:28:05,898 INFO [train.py:812] (3/8) Epoch 28, batch 2800, loss[loss=0.1384, simple_loss=0.2351, pruned_loss=0.02081, over 7231.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.03122, over 1416766.48 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:29:05,085 INFO [train.py:812] (3/8) Epoch 28, batch 2850, loss[loss=0.1518, simple_loss=0.2414, pruned_loss=0.03113, over 7144.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03166, over 1420894.78 frames.], batch size: 17, lr: 2.77e-04
2022-05-15 13:30:03,000 INFO [train.py:812] (3/8) Epoch 28, batch 2900, loss[loss=0.177, simple_loss=0.2796, pruned_loss=0.03716, over 7283.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2478, pruned_loss=0.03182, over 1420592.57 frames.], batch size: 25, lr: 2.77e-04
2022-05-15 13:31:01,397 INFO [train.py:812] (3/8) Epoch 28, batch 2950, loss[loss=0.1673, simple_loss=0.2589, pruned_loss=0.03782, over 7197.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03201, over 1423148.79 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:32:00,607 INFO [train.py:812] (3/8) Epoch 28, batch 3000, loss[loss=0.1583, simple_loss=0.2468, pruned_loss=0.03488, over 7013.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2475, pruned_loss=0.03199, over 1425379.76 frames.], batch size: 28, lr: 2.77e-04
2022-05-15 13:32:00,608 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 13:32:08,092 INFO [train.py:841] (3/8) Epoch 28, validation: loss=0.1523, simple_loss=0.2496, pruned_loss=0.02748, over 698248.00 frames.
2022-05-15 13:33:05,913 INFO [train.py:812] (3/8) Epoch 28, batch 3050, loss[loss=0.1399, simple_loss=0.2272, pruned_loss=0.0263, over 7123.00 frames.], tot_loss[loss=0.1553, simple_loss=0.247, pruned_loss=0.03179, over 1426398.82 frames.], batch size: 17, lr: 2.77e-04
2022-05-15 13:34:04,041 INFO [train.py:812] (3/8) Epoch 28, batch 3100, loss[loss=0.1497, simple_loss=0.2447, pruned_loss=0.02736, over 7371.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2457, pruned_loss=0.03128, over 1425523.99 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:35:03,610 INFO [train.py:812] (3/8) Epoch 28, batch 3150, loss[loss=0.1616, simple_loss=0.2515, pruned_loss=0.03583, over 7421.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2459, pruned_loss=0.03173, over 1424707.88 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:36:02,619 INFO [train.py:812] (3/8) Epoch 28, batch 3200, loss[loss=0.1487, simple_loss=0.2417, pruned_loss=0.02782, over 7324.00 frames.], tot_loss[loss=0.155, simple_loss=0.2465, pruned_loss=0.03175, over 1424983.65 frames.], batch size: 21, lr: 2.77e-04
2022-05-15 13:37:02,637 INFO [train.py:812] (3/8) Epoch 28, batch 3250, loss[loss=0.1333, simple_loss=0.2243, pruned_loss=0.02109, over 7160.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2453, pruned_loss=0.03151, over 1425652.52 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:37:59,656 INFO [train.py:812] (3/8) Epoch 28, batch 3300, loss[loss=0.1394, simple_loss=0.2266, pruned_loss=0.02614, over 7000.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.0314, over 1424391.65 frames.], batch size: 16, lr: 2.77e-04
2022-05-15 13:38:57,848 INFO [train.py:812] (3/8) Epoch 28, batch 3350, loss[loss=0.1555, simple_loss=0.2493, pruned_loss=0.03089, over 7368.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03146, over 1421150.49 frames.], batch size: 23, lr: 2.77e-04
2022-05-15 13:39:56,927 INFO [train.py:812] (3/8) Epoch 28, batch 3400, loss[loss=0.1367, simple_loss=0.2249, pruned_loss=0.02426, over 7318.00 frames.], tot_loss[loss=0.1555, simple_loss=0.247, pruned_loss=0.03198, over 1422912.20 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:40:56,498 INFO [train.py:812] (3/8) Epoch 28, batch 3450, loss[loss=0.1494, simple_loss=0.2428, pruned_loss=0.02803, over 7193.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2463, pruned_loss=0.03154, over 1424323.99 frames.], batch size: 22, lr: 2.77e-04
2022-05-15 13:41:55,468 INFO [train.py:812] (3/8) Epoch 28, batch 3500, loss[loss=0.1399, simple_loss=0.2295, pruned_loss=0.02512, over 7064.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.0311, over 1423085.65 frames.], batch size: 18, lr: 2.77e-04
2022-05-15 13:42:54,601 INFO [train.py:812] (3/8) Epoch 28, batch 3550, loss[loss=0.1627, simple_loss=0.2565, pruned_loss=0.0345, over 7340.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03102, over 1423572.18 frames.], batch size: 22, lr: 2.77e-04
2022-05-15 13:43:53,666 INFO [train.py:812] (3/8) Epoch 28, batch 3600, loss[loss=0.1407, simple_loss=0.2235, pruned_loss=0.02898, over 7452.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03099, over 1423072.48 frames.], batch size: 19, lr: 2.77e-04
2022-05-15 13:44:53,077 INFO [train.py:812] (3/8) Epoch 28, batch 3650, loss[loss=0.1847, simple_loss=0.2723, pruned_loss=0.04861, over 7417.00 frames.], tot_loss[loss=0.154, simple_loss=0.2455, pruned_loss=0.03127, over 1424263.83 frames.], batch size: 21, lr: 2.77e-04
2022-05-15 13:45:51,500 INFO [train.py:812] (3/8) Epoch 28, batch 3700, loss[loss=0.1564, simple_loss=0.2503, pruned_loss=0.03124, over 7427.00 frames.], tot_loss[loss=0.1533, simple_loss=0.245, pruned_loss=0.03085, over 1424397.56 frames.], batch size: 20, lr: 2.77e-04
2022-05-15 13:46:50,230 INFO [train.py:812] (3/8) Epoch 28, batch 3750, loss[loss=0.1925, simple_loss=0.2708, pruned_loss=0.05711, over 4883.00 frames.], tot_loss[loss=0.154, simple_loss=0.2458, pruned_loss=0.03113, over 1418685.95 frames.], batch size: 52, lr: 2.76e-04
2022-05-15 13:47:49,324 INFO [train.py:812] (3/8) Epoch 28, batch 3800, loss[loss=0.1434, simple_loss=0.2265, pruned_loss=0.03018, over 7263.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2459, pruned_loss=0.03123, over 1421740.59 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:48:48,434 INFO [train.py:812] (3/8) Epoch 28, batch 3850, loss[loss=0.1681, simple_loss=0.2628, pruned_loss=0.03663, over 7153.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2462, pruned_loss=0.03105, over 1426493.09 frames.], batch size: 19, lr: 2.76e-04
2022-05-15 13:49:47,464 INFO [train.py:812] (3/8) Epoch 28, batch 3900, loss[loss=0.1548, simple_loss=0.2478, pruned_loss=0.03091, over 7214.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03114, over 1425404.80 frames.], batch size: 22, lr: 2.76e-04
2022-05-15 13:50:47,234 INFO [train.py:812] (3/8) Epoch 28, batch 3950, loss[loss=0.1861, simple_loss=0.2771, pruned_loss=0.04758, over 7202.00 frames.], tot_loss[loss=0.154, simple_loss=0.246, pruned_loss=0.03094, over 1426409.96 frames.], batch size: 22, lr: 2.76e-04
2022-05-15 13:51:46,168 INFO [train.py:812] (3/8) Epoch 28, batch 4000, loss[loss=0.1651, simple_loss=0.2529, pruned_loss=0.03862, over 6662.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03095, over 1422953.78 frames.], batch size: 31, lr: 2.76e-04
2022-05-15 13:52:45,722 INFO [train.py:812] (3/8) Epoch 28, batch 4050, loss[loss=0.1545, simple_loss=0.2476, pruned_loss=0.03072, over 5058.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2461, pruned_loss=0.03131, over 1417394.19 frames.], batch size: 52, lr: 2.76e-04
2022-05-15 13:53:44,802 INFO [train.py:812] (3/8) Epoch 28, batch 4100, loss[loss=0.1326, simple_loss=0.2165, pruned_loss=0.02437, over 7137.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03126, over 1419724.71 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:54:49,280 INFO [train.py:812] (3/8) Epoch 28, batch 4150, loss[loss=0.136, simple_loss=0.2247, pruned_loss=0.02365, over 7165.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2454, pruned_loss=0.0311, over 1424991.65 frames.], batch size: 19, lr: 2.76e-04
2022-05-15 13:55:47,964 INFO [train.py:812] (3/8) Epoch 28, batch 4200, loss[loss=0.1765, simple_loss=0.269, pruned_loss=0.042, over 5022.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2466, pruned_loss=0.03181, over 1418126.72 frames.], batch size: 54, lr: 2.76e-04
2022-05-15 13:56:46,298 INFO [train.py:812] (3/8) Epoch 28, batch 4250, loss[loss=0.1378, simple_loss=0.2153, pruned_loss=0.03016, over 7070.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2469, pruned_loss=0.03187, over 1416106.81 frames.], batch size: 18, lr: 2.76e-04
2022-05-15 13:57:45,190 INFO [train.py:812] (3/8) Epoch 28, batch 4300, loss[loss=0.1457, simple_loss=0.2346, pruned_loss=0.02836, over 7136.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2468, pruned_loss=0.03206, over 1417466.68 frames.], batch size: 17, lr: 2.76e-04
2022-05-15 13:58:44,133 INFO [train.py:812] (3/8) Epoch 28, batch 4350, loss[loss=0.1731, simple_loss=0.2702, pruned_loss=0.03798, over 7212.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2474, pruned_loss=0.03224, over 1417697.67 frames.], batch size: 21, lr: 2.76e-04
2022-05-15 13:59:42,364 INFO [train.py:812] (3/8) Epoch 28, batch 4400, loss[loss=0.1486, simple_loss=0.2475, pruned_loss=0.02483, over 6411.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2469, pruned_loss=0.03203, over 1409549.45 frames.], batch size: 38, lr: 2.76e-04
2022-05-15 14:00:51,450 INFO [train.py:812] (3/8) Epoch 28, batch 4450, loss[loss=0.1238, simple_loss=0.211, pruned_loss=0.01831, over 6830.00 frames.], tot_loss[loss=0.156, simple_loss=0.2472, pruned_loss=0.03241, over 1403163.91 frames.], batch size: 15, lr: 2.76e-04
2022-05-15 14:01:50,402 INFO [train.py:812] (3/8) Epoch 28, batch 4500, loss[loss=0.1427, simple_loss=0.2448, pruned_loss=0.02027, over 7215.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2474, pruned_loss=0.03217, over 1391049.47 frames.], batch size: 21, lr: 2.76e-04
2022-05-15 14:02:49,720 INFO [train.py:812] (3/8) Epoch 28, batch 4550, loss[loss=0.1669, simple_loss=0.2591, pruned_loss=0.03736, over 6450.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2478, pruned_loss=0.03269, over 1361387.22 frames.], batch size: 38, lr: 2.76e-04
2022-05-15 14:04:01,542 INFO [train.py:812] (3/8) Epoch 29, batch 0, loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03101, over 6986.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03101, over 6986.00 frames.], batch size: 28, lr: 2.71e-04
2022-05-15 14:05:00,932 INFO [train.py:812] (3/8) Epoch 29, batch 50, loss[loss=0.1546, simple_loss=0.2572, pruned_loss=0.02596, over 7282.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2462, pruned_loss=0.03141, over 323098.20 frames.], batch size: 24, lr: 2.71e-04
2022-05-15 14:05:59,929 INFO [train.py:812] (3/8) Epoch 29, batch 100, loss[loss=0.1843, simple_loss=0.2726, pruned_loss=0.04795, over 7309.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03135, over 568899.43 frames.], batch size: 21, lr: 2.71e-04
2022-05-15 14:06:58,554 INFO [train.py:812] (3/8) Epoch 29, batch 150, loss[loss=0.1577, simple_loss=0.2521, pruned_loss=0.03166, over 7233.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03181, over 759328.41 frames.], batch size: 20, lr: 2.71e-04
2022-05-15 14:07:56,831 INFO [train.py:812] (3/8) Epoch 29, batch 200, loss[loss=0.1542, simple_loss=0.2401, pruned_loss=0.03413, over 7071.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03118, over 909211.70 frames.], batch size: 18, lr: 2.71e-04
2022-05-15 14:08:56,085 INFO [train.py:812] (3/8) Epoch 29, batch 250, loss[loss=0.1756, simple_loss=0.2544, pruned_loss=0.04839, over 4886.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2449, pruned_loss=0.0314, over 1020028.34 frames.], batch size: 53, lr: 2.71e-04
2022-05-15 14:09:54,908 INFO [train.py:812] (3/8) Epoch 29, batch 300, loss[loss=0.1601, simple_loss=0.2417, pruned_loss=0.03924, over 7159.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2459, pruned_loss=0.03169, over 1109589.45 frames.], batch size: 18, lr: 2.70e-04
2022-05-15 14:10:53,112 INFO [train.py:812] (3/8) Epoch 29, batch 350, loss[loss=0.1629, simple_loss=0.2566, pruned_loss=0.03455, over 7065.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2467, pruned_loss=0.03187, over 1181051.67 frames.], batch size: 18, lr: 2.70e-04
2022-05-15 14:11:51,403 INFO [train.py:812] (3/8) Epoch 29, batch 400, loss[loss=0.1572, simple_loss=0.2591, pruned_loss=0.02761, over 7129.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2468, pruned_loss=0.0318, over 1236960.41 frames.], batch size: 20, lr: 2.70e-04
2022-05-15 14:12:49,824 INFO [train.py:812] (3/8) Epoch 29, batch 450, loss[loss=0.1626, simple_loss=0.2618, pruned_loss=0.03167, over 7118.00 frames.], tot_loss[loss=0.1552, simple_loss=0.247, pruned_loss=0.03174, over 1282646.52 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:13:47,245 INFO [train.py:812] (3/8) Epoch 29, batch 500, loss[loss=0.1775, simple_loss=0.2679, pruned_loss=0.04356, over 5264.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2466, pruned_loss=0.03199, over 1309240.86 frames.], batch size: 52, lr: 2.70e-04
2022-05-15 14:14:46,089 INFO [train.py:812] (3/8) Epoch 29, batch 550, loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.0297, over 7218.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2465, pruned_loss=0.03216, over 1331613.66 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:15:44,274 INFO [train.py:812] (3/8) Epoch 29, batch 600, loss[loss=0.1273, simple_loss=0.2215, pruned_loss=0.01657, over 7273.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2462, pruned_loss=0.03195, over 1347834.00 frames.], batch size: 19, lr: 2.70e-04
2022-05-15 14:16:43,597 INFO [train.py:812] (3/8) Epoch 29, batch 650, loss[loss=0.1377, simple_loss=0.2171, pruned_loss=0.02914, over 7055.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2452, pruned_loss=0.03145, over 1367172.39 frames.], batch size: 18, lr: 2.70e-04
2022-05-15 14:17:43,339 INFO [train.py:812] (3/8) Epoch 29, batch 700, loss[loss=0.1732, simple_loss=0.2661, pruned_loss=0.04013, over 5169.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2457, pruned_loss=0.03166, over 1375163.46 frames.], batch size: 52, lr: 2.70e-04
2022-05-15 14:18:41,551 INFO [train.py:812] (3/8) Epoch 29, batch 750, loss[loss=0.1306, simple_loss=0.2179, pruned_loss=0.02159, over 7433.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2456, pruned_loss=0.03174, over 1381401.73 frames.], batch size: 20, lr: 2.70e-04
2022-05-15 14:19:40,347 INFO [train.py:812] (3/8) Epoch 29, batch 800, loss[loss=0.1491, simple_loss=0.2534, pruned_loss=0.02242, over 7114.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2464, pruned_loss=0.0319, over 1387512.70 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:20:39,289 INFO [train.py:812] (3/8) Epoch 29, batch 850, loss[loss=0.1648, simple_loss=0.2573, pruned_loss=0.03615, over 6278.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2463, pruned_loss=0.03175, over 1392177.70 frames.], batch size: 37, lr: 2.70e-04
2022-05-15 14:21:38,037 INFO [train.py:812] (3/8) Epoch 29, batch 900, loss[loss=0.1506, simple_loss=0.2416, pruned_loss=0.02983, over 6729.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2456, pruned_loss=0.03133, over 1399355.42 frames.], batch size: 31, lr: 2.70e-04
2022-05-15 14:22:37,037 INFO [train.py:812] (3/8) Epoch 29, batch 950, loss[loss=0.1664, simple_loss=0.2553, pruned_loss=0.03878, over 7202.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.0315, over 1408583.61 frames.], batch size: 22, lr: 2.70e-04
2022-05-15 14:23:36,643 INFO [train.py:812] (3/8) Epoch 29, batch 1000, loss[loss=0.1381, simple_loss=0.2147, pruned_loss=0.03076, over 6827.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2449, pruned_loss=0.03112, over 1414320.77 frames.], batch size: 15, lr: 2.70e-04
2022-05-15 14:24:36,138 INFO [train.py:812] (3/8) Epoch 29, batch 1050, loss[loss=0.1572, simple_loss=0.2645, pruned_loss=0.02495, over 7406.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.03118, over 1419767.55 frames.], batch size: 21, lr: 2.70e-04
2022-05-15 14:25:35,346 INFO [train.py:812] (3/8) Epoch 29, batch 1100, loss[loss=0.1607, simple_loss=0.2423, pruned_loss=0.03958, over 7276.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2458, pruned_loss=0.03154, over 1422589.04 frames.], batch size: 17, lr: 2.70e-04
2022-05-15 14:26:34,881 INFO [train.py:812] (3/8) Epoch 29, batch 1150, loss[loss=0.1711, simple_loss=0.2657, pruned_loss=0.03827, over 7101.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2458, pruned_loss=0.0313, over 1421328.77 frames.], batch size: 28, lr: 2.70e-04
2022-05-15 14:27:33,681 INFO [train.py:812] (3/8) Epoch 29, batch 1200, loss[loss=0.1575, simple_loss=0.2507, pruned_loss=0.0322, over 7093.00 frames.], tot_loss[loss=0.155, simple_loss=0.2467, pruned_loss=0.03166, over 1423193.74 frames.], batch size: 28, lr: 2.70e-04
2022-05-15 14:28:32,479 INFO [train.py:812] (3/8) Epoch 29, batch 1250, loss[loss=0.1675, simple_loss=0.2561, pruned_loss=0.03941, over 7217.00 frames.], tot_loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03174, over 1417083.12 frames.], batch size: 22, lr: 2.70e-04
2022-05-15 14:29:29,504 INFO [train.py:812] (3/8) Epoch 29, batch 1300, loss[loss=0.1764, simple_loss=0.2716, pruned_loss=0.04064, over 7148.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.03158, over 1420193.30 frames.], batch size: 20, lr: 2.69e-04
2022-05-15 14:30:28,434 INFO [train.py:812] (3/8) Epoch 29, batch 1350, loss[loss=0.1627, simple_loss=0.2575, pruned_loss=0.03391, over 7110.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2449, pruned_loss=0.03072, over 1426073.67 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:31:27,376 INFO [train.py:812] (3/8) Epoch 29, batch 1400, loss[loss=0.1424, simple_loss=0.2248, pruned_loss=0.02999, over 7289.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03066, over 1427051.33 frames.], batch size: 17, lr: 2.69e-04
2022-05-15 14:32:26,336 INFO [train.py:812] (3/8) Epoch 29, batch 1450, loss[loss=0.1496, simple_loss=0.2425, pruned_loss=0.02834, over 7282.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2441, pruned_loss=0.03028, over 1431117.48 frames.], batch size: 24, lr: 2.69e-04
2022-05-15 14:33:24,389 INFO [train.py:812] (3/8) Epoch 29, batch 1500, loss[loss=0.1439, simple_loss=0.2411, pruned_loss=0.02329, over 7332.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2445, pruned_loss=0.03037, over 1427654.13 frames.], batch size: 20, lr: 2.69e-04
2022-05-15 14:34:23,839 INFO [train.py:812] (3/8) Epoch 29, batch 1550, loss[loss=0.1499, simple_loss=0.2392, pruned_loss=0.03029, over 7220.00 frames.], tot_loss[loss=0.153, simple_loss=0.2448, pruned_loss=0.03064, over 1430243.58 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:35:22,637 INFO [train.py:812] (3/8) Epoch 29, batch 1600, loss[loss=0.1583, simple_loss=0.2372, pruned_loss=0.03967, over 6827.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03072, over 1427449.99 frames.], batch size: 15, lr: 2.69e-04
2022-05-15 14:36:22,713 INFO [train.py:812] (3/8) Epoch 29, batch 1650, loss[loss=0.1279, simple_loss=0.2156, pruned_loss=0.02011, over 7220.00 frames.], tot_loss[loss=0.153, simple_loss=0.2445, pruned_loss=0.03072, over 1429325.15 frames.], batch size: 16, lr: 2.69e-04
2022-05-15 14:37:22,121 INFO [train.py:812] (3/8) Epoch 29, batch 1700, loss[loss=0.1511, simple_loss=0.2478, pruned_loss=0.02723, over 7267.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2452, pruned_loss=0.03101, over 1431611.50 frames.], batch size: 19, lr: 2.69e-04
2022-05-15 14:38:21,732 INFO [train.py:812] (3/8) Epoch 29, batch 1750, loss[loss=0.1455, simple_loss=0.25, pruned_loss=0.0205, over 7115.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2456, pruned_loss=0.03085, over 1433145.28 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:39:20,904 INFO [train.py:812] (3/8) Epoch 29, batch 1800, loss[loss=0.1431, simple_loss=0.2193, pruned_loss=0.03344, over 6991.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03076, over 1423246.41 frames.], batch size: 16, lr: 2.69e-04
2022-05-15 14:40:20,347 INFO [train.py:812] (3/8) Epoch 29, batch 1850, loss[loss=0.1219, simple_loss=0.2083, pruned_loss=0.01775, over 7410.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03114, over 1425477.83 frames.], batch size: 18, lr: 2.69e-04
2022-05-15 14:41:18,738 INFO [train.py:812] (3/8) Epoch 29, batch 1900, loss[loss=0.1568, simple_loss=0.2488, pruned_loss=0.03236, over 7177.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03104, over 1425866.44 frames.], batch size: 26, lr: 2.69e-04
2022-05-15 14:42:17,745 INFO [train.py:812] (3/8) Epoch 29, batch 1950, loss[loss=0.1859, simple_loss=0.2731, pruned_loss=0.04932, over 7286.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.03091, over 1428986.90 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:43:16,653 INFO [train.py:812] (3/8) Epoch 29, batch 2000, loss[loss=0.1482, simple_loss=0.2444, pruned_loss=0.02602, over 7195.00 frames.], tot_loss[loss=0.1535, simple_loss=0.245, pruned_loss=0.03094, over 1431282.26 frames.], batch size: 23, lr: 2.69e-04
2022-05-15 14:44:14,138 INFO [train.py:812] (3/8) Epoch 29, batch 2050, loss[loss=0.1498, simple_loss=0.2382, pruned_loss=0.03072, over 7320.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2456, pruned_loss=0.03158, over 1423669.19 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:45:11,934 INFO [train.py:812] (3/8) Epoch 29, batch 2100, loss[loss=0.1482, simple_loss=0.2402, pruned_loss=0.02811, over 7336.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2449, pruned_loss=0.03135, over 1425408.42 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:46:11,708 INFO [train.py:812] (3/8) Epoch 29, batch 2150, loss[loss=0.1604, simple_loss=0.2611, pruned_loss=0.02981, over 7226.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03116, over 1426421.36 frames.], batch size: 21, lr: 2.69e-04
2022-05-15 14:47:09,926 INFO [train.py:812] (3/8) Epoch 29, batch 2200, loss[loss=0.1544, simple_loss=0.2507, pruned_loss=0.02903, over 7265.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03104, over 1420707.30 frames.], batch size: 25, lr: 2.69e-04
2022-05-15 14:48:08,319 INFO [train.py:812] (3/8) Epoch 29, batch 2250, loss[loss=0.1552, simple_loss=0.2492, pruned_loss=0.03061, over 7123.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03085, over 1424770.21 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:49:05,774 INFO [train.py:812] (3/8) Epoch 29, batch 2300, loss[loss=0.1669, simple_loss=0.2561, pruned_loss=0.03886, over 7279.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03081, over 1426308.44 frames.], batch size: 24, lr: 2.68e-04
2022-05-15 14:50:03,886 INFO [train.py:812] (3/8) Epoch 29, batch 2350, loss[loss=0.1265, simple_loss=0.2169, pruned_loss=0.01807, over 7055.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2449, pruned_loss=0.03082, over 1423885.01 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:51:02,203 INFO [train.py:812] (3/8) Epoch 29, batch 2400, loss[loss=0.1542, simple_loss=0.2466, pruned_loss=0.03091, over 7368.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2439, pruned_loss=0.03068, over 1425854.66 frames.], batch size: 19, lr: 2.68e-04
2022-05-15 14:51:59,591 INFO [train.py:812] (3/8) Epoch 29, batch 2450, loss[loss=0.1707, simple_loss=0.2757, pruned_loss=0.03284, over 7099.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03121, over 1416701.31 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:52:57,607 INFO [train.py:812] (3/8) Epoch 29, batch 2500, loss[loss=0.1443, simple_loss=0.2233, pruned_loss=0.03263, over 7401.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2441, pruned_loss=0.03104, over 1419629.60 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:53:56,775 INFO [train.py:812] (3/8) Epoch 29, batch 2550, loss[loss=0.1375, simple_loss=0.2132, pruned_loss=0.0309, over 7167.00 frames.], tot_loss[loss=0.153, simple_loss=0.2439, pruned_loss=0.03105, over 1417197.53 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:54:55,311 INFO [train.py:812] (3/8) Epoch 29, batch 2600, loss[loss=0.1827, simple_loss=0.2684, pruned_loss=0.04854, over 7212.00 frames.], tot_loss[loss=0.1531, simple_loss=0.244, pruned_loss=0.03112, over 1415308.56 frames.], batch size: 23, lr: 2.68e-04
2022-05-15 14:56:04,281 INFO [train.py:812] (3/8) Epoch 29, batch 2650, loss[loss=0.1301, simple_loss=0.2163, pruned_loss=0.02198, over 7419.00 frames.], tot_loss[loss=0.153, simple_loss=0.2438, pruned_loss=0.03106, over 1417840.29 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 14:57:02,545 INFO [train.py:812] (3/8) Epoch 29, batch 2700, loss[loss=0.1634, simple_loss=0.245, pruned_loss=0.04083, over 5085.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2438, pruned_loss=0.0313, over 1418133.13 frames.], batch size: 53, lr: 2.68e-04
2022-05-15 14:58:00,029 INFO [train.py:812] (3/8) Epoch 29, batch 2750, loss[loss=0.1428, simple_loss=0.2387, pruned_loss=0.02341, over 7325.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2446, pruned_loss=0.03127, over 1414619.45 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 14:59:07,975 INFO [train.py:812] (3/8) Epoch 29, batch 2800, loss[loss=0.1292, simple_loss=0.2274, pruned_loss=0.01552, over 7330.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2453, pruned_loss=0.03149, over 1417221.07 frames.], batch size: 22, lr: 2.68e-04
2022-05-15 15:00:06,425 INFO [train.py:812] (3/8) Epoch 29, batch 2850, loss[loss=0.1816, simple_loss=0.2685, pruned_loss=0.04731, over 7268.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2452, pruned_loss=0.0317, over 1418247.12 frames.], batch size: 19, lr: 2.68e-04
2022-05-15 15:01:14,245 INFO [train.py:812] (3/8) Epoch 29, batch 2900, loss[loss=0.143, simple_loss=0.2263, pruned_loss=0.0298, over 7275.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2455, pruned_loss=0.03169, over 1417238.87 frames.], batch size: 17, lr: 2.68e-04
2022-05-15 15:02:42,658 INFO [train.py:812] (3/8) Epoch 29, batch 2950, loss[loss=0.1226, simple_loss=0.2117, pruned_loss=0.01672, over 7136.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2446, pruned_loss=0.03149, over 1418219.95 frames.], batch size: 17, lr: 2.68e-04
2022-05-15 15:03:40,342 INFO [train.py:812] (3/8) Epoch 29, batch 3000, loss[loss=0.1374, simple_loss=0.2334, pruned_loss=0.02073, over 7239.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03146, over 1419683.60 frames.], batch size: 20, lr: 2.68e-04
2022-05-15 15:03:40,343 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 15:03:47,851 INFO [train.py:841] (3/8) Epoch 29, validation: loss=0.153, simple_loss=0.2498, pruned_loss=0.02809, over 698248.00 frames.
2022-05-15 15:04:46,935 INFO [train.py:812] (3/8) Epoch 29, batch 3050, loss[loss=0.133, simple_loss=0.2259, pruned_loss=0.02001, over 7161.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2447, pruned_loss=0.03118, over 1422190.44 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 15:05:54,527 INFO [train.py:812] (3/8) Epoch 29, batch 3100, loss[loss=0.1287, simple_loss=0.2168, pruned_loss=0.02025, over 7289.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2446, pruned_loss=0.03108, over 1419361.12 frames.], batch size: 18, lr: 2.68e-04
2022-05-15 15:06:53,662 INFO [train.py:812] (3/8) Epoch 29, batch 3150, loss[loss=0.1728, simple_loss=0.2698, pruned_loss=0.03788, over 7221.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2456, pruned_loss=0.03135, over 1422807.29 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 15:07:52,378 INFO [train.py:812] (3/8) Epoch 29, batch 3200, loss[loss=0.1565, simple_loss=0.2556, pruned_loss=0.02871, over 7109.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03081, over 1422554.82 frames.], batch size: 21, lr: 2.68e-04
2022-05-15 15:08:52,059 INFO [train.py:812] (3/8) Epoch 29, batch 3250, loss[loss=0.1253, simple_loss=0.2069, pruned_loss=0.02188, over 6790.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2443, pruned_loss=0.03058, over 1421692.54 frames.], batch size: 15, lr: 2.67e-04
2022-05-15 15:09:50,367 INFO [train.py:812] (3/8) Epoch 29, batch 3300, loss[loss=0.1495, simple_loss=0.2517, pruned_loss=0.02367, over 7222.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03092, over 1421650.58 frames.], batch size: 21, lr: 2.67e-04
2022-05-15 15:10:48,348 INFO [train.py:812] (3/8) Epoch 29, batch 3350, loss[loss=0.1426, simple_loss=0.2366, pruned_loss=0.02427, over 7020.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03099, over 1419766.83 frames.], batch size: 28, lr: 2.67e-04
2022-05-15 15:11:47,200 INFO [train.py:812] (3/8) Epoch 29, batch 3400, loss[loss=0.1271, simple_loss=0.2169, pruned_loss=0.01869, over 7067.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2448, pruned_loss=0.03097, over 1416853.11 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:12:46,907 INFO [train.py:812] (3/8) Epoch 29, batch 3450, loss[loss=0.1349, simple_loss=0.2151, pruned_loss=0.02736, over 7275.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2451, pruned_loss=0.03135, over 1419722.57 frames.], batch size: 17, lr: 2.67e-04
2022-05-15 15:13:45,905 INFO [train.py:812] (3/8) Epoch 29, batch 3500, loss[loss=0.1639, simple_loss=0.2657, pruned_loss=0.03105, over 6810.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2447, pruned_loss=0.03103, over 1418996.38 frames.], batch size: 31, lr: 2.67e-04
2022-05-15 15:14:51,721 INFO [train.py:812] (3/8) Epoch 29, batch 3550, loss[loss=0.1413, simple_loss=0.2372, pruned_loss=0.02266, over 7285.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03117, over 1422522.36 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:15:51,093 INFO [train.py:812] (3/8) Epoch 29, batch 3600, loss[loss=0.1447, simple_loss=0.2244, pruned_loss=0.03244, over 6792.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03124, over 1422889.58 frames.], batch size: 15, lr: 2.67e-04
2022-05-15 15:16:50,814 INFO [train.py:812] (3/8) Epoch 29, batch 3650, loss[loss=0.1591, simple_loss=0.2545, pruned_loss=0.03186, over 7321.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03093, over 1426505.28 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:17:49,907 INFO [train.py:812] (3/8) Epoch 29, batch 3700, loss[loss=0.1828, simple_loss=0.2696, pruned_loss=0.04797, over 7210.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2448, pruned_loss=0.03132, over 1425992.62 frames.], batch size: 23, lr: 2.67e-04
2022-05-15 15:18:49,039 INFO [train.py:812] (3/8) Epoch 29, batch 3750, loss[loss=0.1986, simple_loss=0.2845, pruned_loss=0.05635, over 4543.00 frames.], tot_loss[loss=0.1537, simple_loss=0.245, pruned_loss=0.03123, over 1424608.68 frames.], batch size: 52, lr: 2.67e-04
2022-05-15 15:19:48,071 INFO [train.py:812] (3/8) Epoch 29, batch 3800, loss[loss=0.1388, simple_loss=0.2337, pruned_loss=0.02192, over 7432.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2457, pruned_loss=0.0313, over 1425200.33 frames.], batch size: 20, lr: 2.67e-04
2022-05-15 15:20:46,934 INFO [train.py:812] (3/8) Epoch 29, batch 3850, loss[loss=0.1577, simple_loss=0.2549, pruned_loss=0.03028, over 7389.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03106, over 1426285.95 frames.], batch size: 23, lr: 2.67e-04
2022-05-15 15:21:44,959 INFO [train.py:812] (3/8) Epoch 29, batch 3900, loss[loss=0.1662, simple_loss=0.2612, pruned_loss=0.03559, over 7315.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2468, pruned_loss=0.0312, over 1429404.36 frames.], batch size: 24, lr: 2.67e-04
2022-05-15 15:22:44,167 INFO [train.py:812] (3/8) Epoch 29, batch 3950, loss[loss=0.1222, simple_loss=0.2123, pruned_loss=0.01602, over 7408.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2476, pruned_loss=0.03128, over 1430936.39 frames.], batch size: 18, lr: 2.67e-04
2022-05-15 15:23:43,018 INFO [train.py:812] (3/8) Epoch 29, batch 4000, loss[loss=0.166, simple_loss=0.2579, pruned_loss=0.03708, over 7324.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2478, pruned_loss=0.03159, over 1430125.21 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:24:42,295 INFO [train.py:812] (3/8) Epoch 29, batch 4050, loss[loss=0.1389, simple_loss=0.2217, pruned_loss=0.02808, over 7266.00 frames.], tot_loss[loss=0.1559, simple_loss=0.248, pruned_loss=0.03188, over 1429756.12 frames.], batch size: 17, lr: 2.67e-04
2022-05-15 15:25:40,978 INFO [train.py:812] (3/8) Epoch 29, batch 4100, loss[loss=0.168, simple_loss=0.2575, pruned_loss=0.0393, over 7357.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2468, pruned_loss=0.03134, over 1430224.34 frames.], batch size: 22, lr: 2.67e-04
2022-05-15 15:26:40,400 INFO [train.py:812] (3/8) Epoch 29, batch 4150, loss[loss=0.1502, simple_loss=0.2387, pruned_loss=0.03084, over 7320.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2461, pruned_loss=0.03125, over 1424566.04 frames.], batch size: 21, lr: 2.67e-04
2022-05-15 15:27:39,252 INFO [train.py:812] (3/8) Epoch 29, batch 4200, loss[loss=0.1441, simple_loss=0.2455, pruned_loss=0.02139, over 7252.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2474, pruned_loss=0.03143, over 1421520.47 frames.], batch size: 19, lr: 2.66e-04
2022-05-15 15:28:38,674 INFO [train.py:812] (3/8) Epoch 29, batch 4250, loss[loss=0.1693, simple_loss=0.2647, pruned_loss=0.03694, over 6725.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2469, pruned_loss=0.03137, over 1421695.37 frames.], batch size: 31, lr: 2.66e-04
2022-05-15 15:29:36,800 INFO [train.py:812] (3/8) Epoch 29, batch 4300, loss[loss=0.1513, simple_loss=0.2415, pruned_loss=0.03051, over 7170.00 frames.], tot_loss[loss=0.154, simple_loss=0.2461, pruned_loss=0.03092, over 1417458.16 frames.], batch size: 18, lr: 2.66e-04
2022-05-15 15:30:35,753 INFO [train.py:812] (3/8) Epoch 29, batch 4350, loss[loss=0.1615, simple_loss=0.2558, pruned_loss=0.03362, over 7318.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03078, over 1417972.15 frames.], batch size: 21, lr: 2.66e-04
2022-05-15 15:31:34,528 INFO [train.py:812] (3/8) Epoch 29, batch 4400, loss[loss=0.1688, simple_loss=0.2648, pruned_loss=0.03643, over 7292.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.03089, over 1410148.79 frames.], batch size: 24, lr: 2.66e-04
2022-05-15 15:32:33,479 INFO [train.py:812] (3/8) Epoch 29, batch 4450, loss[loss=0.1575, simple_loss=0.2575, pruned_loss=0.02878, over 6443.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03124, over 1401273.94 frames.], batch size: 38, lr: 2.66e-04
2022-05-15 15:33:31,922 INFO [train.py:812] (3/8) Epoch 29, batch 4500, loss[loss=0.1798, simple_loss=0.2798, pruned_loss=0.03986, over 7197.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2459, pruned_loss=0.03151, over 1378330.86 frames.], batch size: 22, lr: 2.66e-04
2022-05-15 15:34:29,703 INFO [train.py:812] (3/8) Epoch 29, batch 4550, loss[loss=0.1811, simple_loss=0.2614, pruned_loss=0.05045, over 4873.00 frames.], tot_loss[loss=0.157, simple_loss=0.2483, pruned_loss=0.03281, over 1359749.28 frames.], batch size: 52, lr: 2.66e-04
2022-05-15 15:35:40,748 INFO [train.py:812] (3/8) Epoch 30, batch 0, loss[loss=0.1489, simple_loss=0.244, pruned_loss=0.02697, over 7326.00 frames.], tot_loss[loss=0.1489, simple_loss=0.244, pruned_loss=0.02697, over 7326.00 frames.], batch size: 20, lr: 2.62e-04
2022-05-15 15:36:39,953 INFO [train.py:812] (3/8) Epoch 30, batch 50, loss[loss=0.1286, simple_loss=0.2167, pruned_loss=0.02023, over 7270.00 frames.], tot_loss[loss=0.152, simple_loss=0.2437, pruned_loss=0.0302, over 323547.71 frames.], batch size: 18, lr: 2.62e-04
2022-05-15 15:37:39,027 INFO [train.py:812] (3/8) Epoch 30, batch 100, loss[loss=0.1321, simple_loss=0.2175, pruned_loss=0.02334, over 7275.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2439, pruned_loss=0.03075, over 571714.68 frames.], batch size: 17, lr: 2.62e-04
2022-05-15 15:38:38,756 INFO [train.py:812] (3/8) Epoch 30, batch 150, loss[loss=0.1425, simple_loss=0.2426, pruned_loss=0.02121, over 7309.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2438, pruned_loss=0.03036, over 750140.42 frames.], batch size: 24, lr: 2.62e-04
2022-05-15 15:39:36,193 INFO [train.py:812] (3/8) Epoch 30, batch 200, loss[loss=0.1793, simple_loss=0.2566, pruned_loss=0.051, over 7351.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03072, over 900510.66 frames.], batch size: 19, lr: 2.61e-04
2022-05-15 15:40:35,787 INFO [train.py:812] (3/8) Epoch 30, batch 250, loss[loss=0.1396, simple_loss=0.2202, pruned_loss=0.02947, over 6813.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03052, over 1016507.13 frames.], batch size: 15, lr: 2.61e-04
2022-05-15 15:41:34,904 INFO [train.py:812] (3/8) Epoch 30, batch 300, loss[loss=0.1528, simple_loss=0.2404, pruned_loss=0.03258, over 7289.00 frames.], tot_loss[loss=0.1537, simple_loss=0.246, pruned_loss=0.03068, over 1108820.18 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:42:33,922 INFO [train.py:812] (3/8) Epoch 30, batch 350, loss[loss=0.1589, simple_loss=0.2505, pruned_loss=0.03369, over 7327.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2454, pruned_loss=0.03107, over 1181539.21 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:43:32,157 INFO [train.py:812] (3/8) Epoch 30, batch 400, loss[loss=0.1622, simple_loss=0.2567, pruned_loss=0.03383, over 7292.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03091, over 1237498.55 frames.], batch size: 24, lr: 2.61e-04
2022-05-15 15:44:30,897 INFO [train.py:812] (3/8) Epoch 30, batch 450, loss[loss=0.1547, simple_loss=0.249, pruned_loss=0.03017, over 7416.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03058, over 1280002.96 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:45:28,621 INFO [train.py:812] (3/8) Epoch 30, batch 500, loss[loss=0.1571, simple_loss=0.249, pruned_loss=0.03265, over 7323.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2449, pruned_loss=0.031, over 1309453.78 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:46:27,329 INFO [train.py:812] (3/8) Epoch 30, batch 550, loss[loss=0.1743, simple_loss=0.2562, pruned_loss=0.04618, over 7271.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.031, over 1337193.75 frames.], batch size: 24, lr: 2.61e-04
2022-05-15 15:47:24,866 INFO [train.py:812] (3/8) Epoch 30, batch 600, loss[loss=0.1543, simple_loss=0.2474, pruned_loss=0.03059, over 7208.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03112, over 1352098.24 frames.], batch size: 22, lr: 2.61e-04
2022-05-15 15:48:22,515 INFO [train.py:812] (3/8) Epoch 30, batch 650, loss[loss=0.1533, simple_loss=0.2387, pruned_loss=0.03396, over 7062.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03111, over 1366830.76 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:49:20,298 INFO [train.py:812] (3/8) Epoch 30, batch 700, loss[loss=0.1451, simple_loss=0.2472, pruned_loss=0.02153, over 7333.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03098, over 1375298.61 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:50:18,871 INFO [train.py:812] (3/8) Epoch 30, batch 750, loss[loss=0.1645, simple_loss=0.2556, pruned_loss=0.03671, over 7232.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2466, pruned_loss=0.03128, over 1381240.51 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:51:17,427 INFO [train.py:812] (3/8) Epoch 30, batch 800, loss[loss=0.1524, simple_loss=0.2586, pruned_loss=0.02307, over 7334.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2462, pruned_loss=0.03136, over 1387692.17 frames.], batch size: 22, lr: 2.61e-04
2022-05-15 15:52:16,536 INFO [train.py:812] (3/8) Epoch 30, batch 850, loss[loss=0.1446, simple_loss=0.2301, pruned_loss=0.02953, over 7070.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03061, over 1397129.72 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:53:14,179 INFO [train.py:812] (3/8) Epoch 30, batch 900, loss[loss=0.1613, simple_loss=0.2558, pruned_loss=0.03339, over 7214.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2454, pruned_loss=0.03089, over 1400761.79 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:54:13,174 INFO [train.py:812] (3/8) Epoch 30, batch 950, loss[loss=0.1548, simple_loss=0.2523, pruned_loss=0.02868, over 7113.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2458, pruned_loss=0.03063, over 1407167.06 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:55:11,577 INFO [train.py:812] (3/8) Epoch 30, batch 1000, loss[loss=0.1673, simple_loss=0.2627, pruned_loss=0.036, over 7149.00 frames.], tot_loss[loss=0.1542, simple_loss=0.247, pruned_loss=0.03075, over 1410395.07 frames.], batch size: 20, lr: 2.61e-04
2022-05-15 15:56:10,075 INFO [train.py:812] (3/8) Epoch 30, batch 1050, loss[loss=0.152, simple_loss=0.2382, pruned_loss=0.03286, over 7295.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2476, pruned_loss=0.03136, over 1406145.44 frames.], batch size: 18, lr: 2.61e-04
2022-05-15 15:57:08,265 INFO [train.py:812] (3/8) Epoch 30, batch 1100, loss[loss=0.1597, simple_loss=0.254, pruned_loss=0.03268, over 7319.00 frames.], tot_loss[loss=0.1556, simple_loss=0.248, pruned_loss=0.03167, over 1415835.74 frames.], batch size: 21, lr: 2.61e-04
2022-05-15 15:58:07,682 INFO [train.py:812] (3/8) Epoch 30, batch 1150, loss[loss=0.1321, simple_loss=0.2148, pruned_loss=0.02471, over 6991.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03146, over 1416572.06 frames.], batch size: 16, lr: 2.61e-04
2022-05-15 15:59:06,100 INFO [train.py:812] (3/8) Epoch 30, batch 1200, loss[loss=0.1499, simple_loss=0.2492, pruned_loss=0.02531, over 7160.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2466, pruned_loss=0.03089, over 1421277.23 frames.], batch size: 19, lr: 2.61e-04
2022-05-15 16:00:14,950 INFO [train.py:812] (3/8) Epoch 30, batch 1250, loss[loss=0.1863, simple_loss=0.2741, pruned_loss=0.04929, over 4693.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03098, over 1416464.38 frames.], batch size: 53, lr: 2.60e-04
2022-05-15 16:01:13,721 INFO [train.py:812] (3/8) Epoch 30, batch 1300, loss[loss=0.1584, simple_loss=0.2572, pruned_loss=0.02983, over 7344.00 frames.], tot_loss[loss=0.154, simple_loss=0.2457, pruned_loss=0.03114, over 1417499.57 frames.], batch size: 22, lr: 2.60e-04
2022-05-15 16:02:13,360 INFO [train.py:812] (3/8) Epoch 30, batch 1350, loss[loss=0.1248, simple_loss=0.216, pruned_loss=0.01683, over 6457.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2462, pruned_loss=0.03163, over 1418603.68 frames.], batch size: 37, lr: 2.60e-04
2022-05-15 16:03:12,426 INFO [train.py:812] (3/8) Epoch 30, batch 1400, loss[loss=0.1603, simple_loss=0.2401, pruned_loss=0.04028, over 6790.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2457, pruned_loss=0.03186, over 1419442.51 frames.], batch size: 15, lr: 2.60e-04
2022-05-15 16:04:10,797 INFO [train.py:812] (3/8) Epoch 30, batch 1450, loss[loss=0.1358, simple_loss=0.2394, pruned_loss=0.01608, over 7122.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2458, pruned_loss=0.03168, over 1417628.99 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:05:09,032 INFO [train.py:812] (3/8) Epoch 30, batch 1500, loss[loss=0.1469, simple_loss=0.2388, pruned_loss=0.02753, over 7251.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2457, pruned_loss=0.03148, over 1416674.73 frames.], batch size: 19, lr: 2.60e-04
2022-05-15 16:06:06,408 INFO [train.py:812] (3/8) Epoch 30, batch 1550, loss[loss=0.1743, simple_loss=0.2637, pruned_loss=0.04248, over 7206.00 frames.], tot_loss[loss=0.1545, simple_loss=0.246, pruned_loss=0.03148, over 1417330.69 frames.], batch size: 23, lr: 2.60e-04
2022-05-15 16:07:03,143 INFO [train.py:812] (3/8) Epoch 30, batch 1600, loss[loss=0.1387, simple_loss=0.2329, pruned_loss=0.02229, over 7317.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2468, pruned_loss=0.0317, over 1418459.31 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:08:02,732 INFO [train.py:812] (3/8) Epoch 30, batch 1650, loss[loss=0.1406, simple_loss=0.237, pruned_loss=0.02213, over 7142.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2451, pruned_loss=0.03098, over 1422317.53 frames.], batch size: 26, lr: 2.60e-04
2022-05-15 16:09:00,138 INFO [train.py:812] (3/8) Epoch 30, batch 1700, loss[loss=0.1743, simple_loss=0.2594, pruned_loss=0.04461, over 7135.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2455, pruned_loss=0.03113, over 1425435.10 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:09:58,742 INFO [train.py:812] (3/8) Epoch 30, batch 1750, loss[loss=0.1452, simple_loss=0.2425, pruned_loss=0.02398, over 7144.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2447, pruned_loss=0.03081, over 1422420.62 frames.], batch size: 20, lr: 2.60e-04
2022-05-15 16:10:56,854 INFO [train.py:812] (3/8) Epoch 30, batch 1800, loss[loss=0.1927, simple_loss=0.2946, pruned_loss=0.04545, over 5192.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03053, over 1419572.45 frames.], batch size: 53, lr: 2.60e-04
2022-05-15 16:11:55,134 INFO [train.py:812] (3/8) Epoch 30, batch 1850, loss[loss=0.1707, simple_loss=0.2668, pruned_loss=0.03732, over 7129.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03042, over 1423864.58 frames.], batch size: 21, lr: 2.60e-04
2022-05-15 16:12:53,272 INFO [train.py:812] (3/8) Epoch 30, batch 1900, loss[loss=0.1311, simple_loss=0.2129, pruned_loss=0.0247, over 7234.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03043, over 1426872.87 frames.], batch size: 16, lr: 2.60e-04
2022-05-15 16:13:52,792 INFO [train.py:812] (3/8) Epoch 30, batch 1950, loss[loss=0.1476, simple_loss=0.2326, pruned_loss=0.03129, over 7279.00 frames.], tot_loss[loss=0.153, simple_loss=0.2447, pruned_loss=0.03064, over 1428349.46 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:14:51,457 INFO [train.py:812] (3/8) Epoch 30, batch 2000, loss[loss=0.155, simple_loss=0.255, pruned_loss=0.02749, over 7334.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2453, pruned_loss=0.03084, over 1430126.75 frames.], batch size: 22, lr: 2.60e-04
2022-05-15 16:15:50,975 INFO [train.py:812] (3/8) Epoch 30, batch 2050, loss[loss=0.1921, simple_loss=0.2776, pruned_loss=0.05326, over 7223.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.03098, over 1430670.49 frames.], batch size: 23, lr: 2.60e-04
2022-05-15 16:16:49,856 INFO [train.py:812] (3/8) Epoch 30, batch 2100, loss[loss=0.1628, simple_loss=0.2569, pruned_loss=0.0344, over 7146.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.03098, over 1429811.69 frames.], batch size: 20, lr: 2.60e-04
2022-05-15 16:17:48,132 INFO [train.py:812] (3/8) Epoch 30, batch 2150, loss[loss=0.1443, simple_loss=0.2243, pruned_loss=0.0322, over 7135.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2461, pruned_loss=0.03143, over 1427990.68 frames.], batch size: 17, lr: 2.60e-04
2022-05-15 16:18:47,072 INFO [train.py:812] (3/8) Epoch 30, batch 2200, loss[loss=0.1797, simple_loss=0.277, pruned_loss=0.04119, over 7293.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2455, pruned_loss=0.03166, over 1423342.67 frames.], batch size: 24, lr: 2.60e-04
2022-05-15 16:19:45,888 INFO [train.py:812] (3/8) Epoch 30, batch 2250, loss[loss=0.1636, simple_loss=0.2584, pruned_loss=0.03442, over 7215.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2455, pruned_loss=0.03147, over 1422255.00 frames.], batch size: 26, lr: 2.59e-04
2022-05-15 16:20:43,586 INFO [train.py:812] (3/8) Epoch 30, batch 2300, loss[loss=0.1493, simple_loss=0.2461, pruned_loss=0.02627, over 7327.00 frames.], tot_loss[loss=0.154, simple_loss=0.2454, pruned_loss=0.03126, over 1418977.07 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:21:42,628 INFO [train.py:812] (3/8) Epoch 30, batch 2350, loss[loss=0.1783, simple_loss=0.2715, pruned_loss=0.04251, over 7341.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2451, pruned_loss=0.03113, over 1420229.93 frames.], batch size: 22, lr: 2.59e-04
2022-05-15 16:22:41,690 INFO [train.py:812] (3/8) Epoch 30, batch 2400, loss[loss=0.1749, simple_loss=0.2647, pruned_loss=0.04255, over 7276.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2459, pruned_loss=0.03113, over 1421630.33 frames.], batch size: 25, lr: 2.59e-04
2022-05-15 16:23:41,338 INFO [train.py:812] (3/8) Epoch 30, batch 2450, loss[loss=0.1687, simple_loss=0.2632, pruned_loss=0.03708, over 7157.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2446, pruned_loss=0.03057, over 1426171.32 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:24:39,655 INFO [train.py:812] (3/8) Epoch 30, batch 2500, loss[loss=0.1411, simple_loss=0.2266, pruned_loss=0.02782, over 6763.00 frames.], tot_loss[loss=0.1528, simple_loss=0.244, pruned_loss=0.03075, over 1430031.53 frames.], batch size: 15, lr: 2.59e-04
2022-05-15 16:25:38,968 INFO [train.py:812] (3/8) Epoch 30, batch 2550, loss[loss=0.1331, simple_loss=0.2161, pruned_loss=0.02506, over 7433.00 frames.], tot_loss[loss=0.153, simple_loss=0.2442, pruned_loss=0.03089, over 1428028.98 frames.], batch size: 18, lr: 2.59e-04
2022-05-15 16:26:37,725 INFO [train.py:812] (3/8) Epoch 30, batch 2600, loss[loss=0.1578, simple_loss=0.2572, pruned_loss=0.02921, over 7113.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03059, over 1427906.06 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:27:37,214 INFO [train.py:812] (3/8) Epoch 30, batch 2650, loss[loss=0.1473, simple_loss=0.2408, pruned_loss=0.02692, over 7145.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2442, pruned_loss=0.03051, over 1429398.64 frames.], batch size: 17, lr: 2.59e-04
2022-05-15 16:28:36,178 INFO [train.py:812] (3/8) Epoch 30, batch 2700, loss[loss=0.1645, simple_loss=0.255, pruned_loss=0.03697, over 7114.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2455, pruned_loss=0.0309, over 1429370.37 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:29:34,403 INFO [train.py:812] (3/8) Epoch 30, batch 2750, loss[loss=0.1577, simple_loss=0.2603, pruned_loss=0.02757, over 7236.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2457, pruned_loss=0.03069, over 1426224.75 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:30:32,046 INFO [train.py:812] (3/8) Epoch 30, batch 2800, loss[loss=0.1442, simple_loss=0.2441, pruned_loss=0.02219, over 7329.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2455, pruned_loss=0.03052, over 1424835.92 frames.], batch size: 22, lr: 2.59e-04
2022-05-15 16:31:31,640 INFO [train.py:812] (3/8) Epoch 30, batch 2850, loss[loss=0.1492, simple_loss=0.247, pruned_loss=0.02573, over 7239.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.03047, over 1419239.64 frames.], batch size: 20, lr: 2.59e-04
2022-05-15 16:32:29,823 INFO [train.py:812] (3/8) Epoch 30, batch 2900, loss[loss=0.1334, simple_loss=0.2174, pruned_loss=0.02467, over 6988.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.0304, over 1421633.50 frames.], batch size: 16, lr: 2.59e-04
2022-05-15 16:33:36,391 INFO [train.py:812] (3/8) Epoch 30, batch 2950, loss[loss=0.1627, simple_loss=0.2564, pruned_loss=0.03445, over 6239.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.03064, over 1422607.02 frames.], batch size: 37, lr: 2.59e-04
2022-05-15 16:34:35,499 INFO [train.py:812] (3/8) Epoch 30, batch 3000, loss[loss=0.142, simple_loss=0.2321, pruned_loss=0.0259, over 7108.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2437, pruned_loss=0.03057, over 1425072.08 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:34:35,500 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 16:34:43,057 INFO [train.py:841] (3/8) Epoch 30, validation: loss=0.1528, simple_loss=0.2494, pruned_loss=0.02809, over 698248.00 frames.
2022-05-15 16:35:41,799 INFO [train.py:812] (3/8) Epoch 30, batch 3050, loss[loss=0.1413, simple_loss=0.2443, pruned_loss=0.01915, over 7113.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03046, over 1427003.80 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:36:40,849 INFO [train.py:812] (3/8) Epoch 30, batch 3100, loss[loss=0.1514, simple_loss=0.2489, pruned_loss=0.02696, over 7422.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03048, over 1427216.51 frames.], batch size: 21, lr: 2.59e-04
2022-05-15 16:37:40,496 INFO [train.py:812] (3/8) Epoch 30, batch 3150, loss[loss=0.1288, simple_loss=0.2196, pruned_loss=0.01896, over 7152.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03036, over 1423129.90 frames.], batch size: 18, lr: 2.59e-04
2022-05-15 16:38:39,677 INFO [train.py:812] (3/8) Epoch 30, batch 3200, loss[loss=0.1601, simple_loss=0.25, pruned_loss=0.03508, over 7263.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2439, pruned_loss=0.03073, over 1425481.64 frames.], batch size: 19, lr: 2.59e-04
2022-05-15 16:39:38,875 INFO [train.py:812] (3/8) Epoch 30, batch 3250, loss[loss=0.1449, simple_loss=0.2434, pruned_loss=0.02315, over 7049.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2438, pruned_loss=0.03065, over 1420433.82 frames.], batch size: 28, lr: 2.59e-04
2022-05-15 16:40:36,554 INFO [train.py:812] (3/8) Epoch 30, batch 3300, loss[loss=0.1416, simple_loss=0.2363, pruned_loss=0.02348, over 7326.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03093, over 1423605.68 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 16:41:35,374 INFO [train.py:812] (3/8) Epoch 30, batch 3350, loss[loss=0.1433, simple_loss=0.2263, pruned_loss=0.03021, over 7278.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03041, over 1427552.26 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:42:33,349 INFO [train.py:812] (3/8) Epoch 30, batch 3400, loss[loss=0.1619, simple_loss=0.2472, pruned_loss=0.03833, over 4910.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2438, pruned_loss=0.03061, over 1424829.47 frames.], batch size: 52, lr: 2.58e-04
2022-05-15 16:43:31,885 INFO [train.py:812] (3/8) Epoch 30, batch 3450, loss[loss=0.1594, simple_loss=0.2499, pruned_loss=0.0344, over 7306.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.03079, over 1420925.46 frames.], batch size: 24, lr: 2.58e-04
2022-05-15 16:44:30,295 INFO [train.py:812] (3/8) Epoch 30, batch 3500, loss[loss=0.1866, simple_loss=0.289, pruned_loss=0.0421, over 7150.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2445, pruned_loss=0.03097, over 1423008.69 frames.], batch size: 26, lr: 2.58e-04
2022-05-15 16:45:29,355 INFO [train.py:812] (3/8) Epoch 30, batch 3550, loss[loss=0.1521, simple_loss=0.2403, pruned_loss=0.03189, over 7150.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03071, over 1422527.78 frames.], batch size: 18, lr: 2.58e-04
2022-05-15 16:46:28,176 INFO [train.py:812] (3/8) Epoch 30, batch 3600, loss[loss=0.1502, simple_loss=0.2357, pruned_loss=0.03237, over 7247.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.0304, over 1427081.41 frames.], batch size: 19, lr: 2.58e-04
2022-05-15 16:47:27,375 INFO [train.py:812] (3/8) Epoch 30, batch 3650, loss[loss=0.1684, simple_loss=0.2587, pruned_loss=0.03906, over 6742.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2448, pruned_loss=0.03082, over 1429030.37 frames.], batch size: 31, lr: 2.58e-04
2022-05-15 16:48:25,023 INFO [train.py:812] (3/8) Epoch 30, batch 3700, loss[loss=0.1357, simple_loss=0.2195, pruned_loss=0.02591, over 7262.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2446, pruned_loss=0.03103, over 1429693.79 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:49:23,810 INFO [train.py:812] (3/8) Epoch 30, batch 3750, loss[loss=0.1688, simple_loss=0.2743, pruned_loss=0.03168, over 7121.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03044, over 1432779.41 frames.], batch size: 28, lr: 2.58e-04
2022-05-15 16:50:21,210 INFO [train.py:812] (3/8) Epoch 30, batch 3800, loss[loss=0.1811, simple_loss=0.2841, pruned_loss=0.03905, over 7203.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03063, over 1424999.14 frames.], batch size: 22, lr: 2.58e-04
2022-05-15 16:51:18,889 INFO [train.py:812] (3/8) Epoch 30, batch 3850, loss[loss=0.135, simple_loss=0.2277, pruned_loss=0.02117, over 6838.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02999, over 1425909.15 frames.], batch size: 15, lr: 2.58e-04
2022-05-15 16:52:16,865 INFO [train.py:812] (3/8) Epoch 30, batch 3900, loss[loss=0.1596, simple_loss=0.2378, pruned_loss=0.04073, over 7150.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02983, over 1426725.75 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 16:53:15,072 INFO [train.py:812] (3/8) Epoch 30, batch 3950, loss[loss=0.1796, simple_loss=0.2637, pruned_loss=0.04772, over 7378.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2451, pruned_loss=0.03015, over 1420635.68 frames.], batch size: 23, lr: 2.58e-04
2022-05-15 16:54:13,798 INFO [train.py:812] (3/8) Epoch 30, batch 4000, loss[loss=0.1716, simple_loss=0.258, pruned_loss=0.0426, over 7284.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2465, pruned_loss=0.03088, over 1419378.99 frames.], batch size: 25, lr: 2.58e-04
2022-05-15 16:55:12,883 INFO [train.py:812] (3/8) Epoch 30, batch 4050, loss[loss=0.1667, simple_loss=0.2616, pruned_loss=0.03591, over 7039.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2453, pruned_loss=0.0305, over 1418832.49 frames.], batch size: 28, lr: 2.58e-04
2022-05-15 16:56:10,886 INFO [train.py:812] (3/8) Epoch 30, batch 4100, loss[loss=0.1479, simple_loss=0.2456, pruned_loss=0.02509, over 7323.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03022, over 1420871.97 frames.], batch size: 21, lr: 2.58e-04
2022-05-15 16:57:19,268 INFO [train.py:812] (3/8) Epoch 30, batch 4150, loss[loss=0.1478, simple_loss=0.2522, pruned_loss=0.02174, over 7226.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2445, pruned_loss=0.0302, over 1421031.05 frames.], batch size: 21, lr: 2.58e-04
2022-05-15 16:58:17,925 INFO [train.py:812] (3/8) Epoch 30, batch 4200, loss[loss=0.163, simple_loss=0.2529, pruned_loss=0.03654, over 7439.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2447, pruned_loss=0.03021, over 1421356.30 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 16:59:24,883 INFO [train.py:812] (3/8) Epoch 30, batch 4250, loss[loss=0.1773, simple_loss=0.281, pruned_loss=0.03678, over 7372.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2466, pruned_loss=0.03108, over 1415650.40 frames.], batch size: 23, lr: 2.58e-04
2022-05-15 17:00:23,126 INFO [train.py:812] (3/8) Epoch 30, batch 4300, loss[loss=0.1533, simple_loss=0.2339, pruned_loss=0.03634, over 7277.00 frames.], tot_loss[loss=0.1542, simple_loss=0.246, pruned_loss=0.0312, over 1420087.02 frames.], batch size: 17, lr: 2.58e-04
2022-05-15 17:01:31,761 INFO [train.py:812] (3/8) Epoch 30, batch 4350, loss[loss=0.1432, simple_loss=0.2372, pruned_loss=0.02462, over 7243.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2458, pruned_loss=0.03144, over 1421739.79 frames.], batch size: 20, lr: 2.58e-04
2022-05-15 17:02:30,811 INFO [train.py:812] (3/8) Epoch 30, batch 4400, loss[loss=0.1651, simple_loss=0.2635, pruned_loss=0.03338, over 7226.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2449, pruned_loss=0.03134, over 1418613.34 frames.], batch size: 20, lr: 2.57e-04
2022-05-15 17:03:47,890 INFO [train.py:812] (3/8) Epoch 30, batch 4450, loss[loss=0.1686, simple_loss=0.262, pruned_loss=0.0376, over 6547.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2448, pruned_loss=0.03134, over 1413533.32 frames.], batch size: 38, lr: 2.57e-04
2022-05-15 17:04:54,627 INFO [train.py:812] (3/8) Epoch 30, batch 4500, loss[loss=0.182, simple_loss=0.2786, pruned_loss=0.04267, over 4836.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2457, pruned_loss=0.03136, over 1399151.63 frames.], batch size: 52, lr: 2.57e-04
2022-05-15 17:05:52,207 INFO [train.py:812] (3/8) Epoch 30, batch 4550, loss[loss=0.174, simple_loss=0.2526, pruned_loss=0.04772, over 5247.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2478, pruned_loss=0.03233, over 1359713.84 frames.], batch size: 52, lr: 2.57e-04
2022-05-15 17:07:08,072 INFO [train.py:812] (3/8) Epoch 31, batch 0, loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03239, over 7328.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2464, pruned_loss=0.03239, over 7328.00 frames.], batch size: 20, lr: 2.53e-04
2022-05-15 17:08:07,408 INFO [train.py:812] (3/8) Epoch 31, batch 50, loss[loss=0.1505, simple_loss=0.247, pruned_loss=0.02701, over 7249.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2435, pruned_loss=0.03094, over 317286.77 frames.], batch size: 19, lr: 2.53e-04
2022-05-15 17:09:06,191 INFO [train.py:812] (3/8) Epoch 31, batch 100, loss[loss=0.1601, simple_loss=0.2589, pruned_loss=0.03069, over 7384.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.0309, over 561743.99 frames.], batch size: 23, lr: 2.53e-04
2022-05-15 17:10:05,002 INFO [train.py:812] (3/8) Epoch 31, batch 150, loss[loss=0.1793, simple_loss=0.2672, pruned_loss=0.04566, over 7217.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2446, pruned_loss=0.03118, over 756903.69 frames.], batch size: 22, lr: 2.53e-04
2022-05-15 17:11:03,886 INFO [train.py:812] (3/8) Epoch 31, batch 200, loss[loss=0.1742, simple_loss=0.2646, pruned_loss=0.04194, over 5058.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2429, pruned_loss=0.03019, over 902018.28 frames.], batch size: 53, lr: 2.53e-04
2022-05-15 17:12:02,391 INFO [train.py:812] (3/8) Epoch 31, batch 250, loss[loss=0.1498, simple_loss=0.2447, pruned_loss=0.0275, over 7294.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03036, over 1016303.14 frames.], batch size: 25, lr: 2.53e-04
2022-05-15 17:13:01,764 INFO [train.py:812] (3/8) Epoch 31, batch 300, loss[loss=0.1477, simple_loss=0.2504, pruned_loss=0.02252, over 7335.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2441, pruned_loss=0.03058, over 1107841.85 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:13:59,730 INFO [train.py:812] (3/8) Epoch 31, batch 350, loss[loss=0.138, simple_loss=0.2196, pruned_loss=0.02821, over 7176.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2441, pruned_loss=0.03073, over 1175590.59 frames.], batch size: 18, lr: 2.53e-04
2022-05-15 17:14:57,251 INFO [train.py:812] (3/8) Epoch 31, batch 400, loss[loss=0.1278, simple_loss=0.2276, pruned_loss=0.01395, over 7213.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2446, pruned_loss=0.03075, over 1225669.29 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:15:56,106 INFO [train.py:812] (3/8) Epoch 31, batch 450, loss[loss=0.1831, simple_loss=0.2761, pruned_loss=0.04504, over 7186.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03058, over 1266826.21 frames.], batch size: 26, lr: 2.53e-04
2022-05-15 17:16:55,632 INFO [train.py:812] (3/8) Epoch 31, batch 500, loss[loss=0.1385, simple_loss=0.224, pruned_loss=0.02646, over 7286.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03036, over 1302053.70 frames.], batch size: 17, lr: 2.53e-04
2022-05-15 17:17:54,442 INFO [train.py:812] (3/8) Epoch 31, batch 550, loss[loss=0.1701, simple_loss=0.2694, pruned_loss=0.03535, over 7407.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2452, pruned_loss=0.03058, over 1328144.66 frames.], batch size: 21, lr: 2.53e-04
2022-05-15 17:18:53,062 INFO [train.py:812] (3/8) Epoch 31, batch 600, loss[loss=0.1304, simple_loss=0.216, pruned_loss=0.02243, over 7057.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03052, over 1348160.17 frames.], batch size: 18, lr: 2.53e-04
2022-05-15 17:19:50,588 INFO [train.py:812] (3/8) Epoch 31, batch 650, loss[loss=0.1753, simple_loss=0.2751, pruned_loss=0.0378, over 7140.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.0305, over 1369636.52 frames.], batch size: 20, lr: 2.53e-04
2022-05-15 17:20:49,369 INFO [train.py:812] (3/8) Epoch 31, batch 700, loss[loss=0.1089, simple_loss=0.1957, pruned_loss=0.01107, over 7183.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2448, pruned_loss=0.03063, over 1379252.37 frames.], batch size: 16, lr: 2.52e-04
2022-05-15 17:21:47,445 INFO [train.py:812] (3/8) Epoch 31, batch 750, loss[loss=0.1439, simple_loss=0.2371, pruned_loss=0.02539, over 7232.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2444, pruned_loss=0.03021, over 1387389.52 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:22:46,106 INFO [train.py:812] (3/8) Epoch 31, batch 800, loss[loss=0.1468, simple_loss=0.2465, pruned_loss=0.02351, over 7340.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2449, pruned_loss=0.03016, over 1396496.90 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:23:44,743 INFO [train.py:812] (3/8) Epoch 31, batch 850, loss[loss=0.1472, simple_loss=0.2453, pruned_loss=0.02456, over 7435.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02991, over 1399769.42 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:24:43,349 INFO [train.py:812] (3/8) Epoch 31, batch 900, loss[loss=0.145, simple_loss=0.2237, pruned_loss=0.03314, over 6808.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03014, over 1404351.64 frames.], batch size: 15, lr: 2.52e-04
2022-05-15 17:25:42,289 INFO [train.py:812] (3/8) Epoch 31, batch 950, loss[loss=0.1529, simple_loss=0.2431, pruned_loss=0.0313, over 7124.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2438, pruned_loss=0.03031, over 1405456.03 frames.], batch size: 28, lr: 2.52e-04
2022-05-15 17:26:41,337 INFO [train.py:812] (3/8) Epoch 31, batch 1000, loss[loss=0.1536, simple_loss=0.2523, pruned_loss=0.0274, over 7342.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03061, over 1408546.36 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:27:40,666 INFO [train.py:812] (3/8) Epoch 31, batch 1050, loss[loss=0.15, simple_loss=0.2398, pruned_loss=0.0301, over 7119.00 frames.], tot_loss[loss=0.153, simple_loss=0.2444, pruned_loss=0.03079, over 1410538.09 frames.], batch size: 28, lr: 2.52e-04
2022-05-15 17:28:39,407 INFO [train.py:812] (3/8) Epoch 31, batch 1100, loss[loss=0.1511, simple_loss=0.2307, pruned_loss=0.0358, over 7072.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2441, pruned_loss=0.03083, over 1414756.45 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:29:38,119 INFO [train.py:812] (3/8) Epoch 31, batch 1150, loss[loss=0.15, simple_loss=0.244, pruned_loss=0.028, over 7065.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2436, pruned_loss=0.03059, over 1416979.29 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:30:36,852 INFO [train.py:812] (3/8) Epoch 31, batch 1200, loss[loss=0.1602, simple_loss=0.2527, pruned_loss=0.03382, over 7192.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2437, pruned_loss=0.03069, over 1419633.27 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:31:36,209 INFO [train.py:812] (3/8) Epoch 31, batch 1250, loss[loss=0.1483, simple_loss=0.2297, pruned_loss=0.03348, over 7410.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2442, pruned_loss=0.03082, over 1418674.25 frames.], batch size: 18, lr: 2.52e-04
2022-05-15 17:32:35,745 INFO [train.py:812] (3/8) Epoch 31, batch 1300, loss[loss=0.1615, simple_loss=0.2663, pruned_loss=0.02837, over 7164.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2443, pruned_loss=0.03041, over 1418775.65 frames.], batch size: 26, lr: 2.52e-04
2022-05-15 17:33:34,081 INFO [train.py:812] (3/8) Epoch 31, batch 1350, loss[loss=0.1298, simple_loss=0.2197, pruned_loss=0.01995, over 7149.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03048, over 1415631.22 frames.], batch size: 17, lr: 2.52e-04
2022-05-15 17:34:32,636 INFO [train.py:812] (3/8) Epoch 31, batch 1400, loss[loss=0.1805, simple_loss=0.2833, pruned_loss=0.03884, over 7339.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2461, pruned_loss=0.03053, over 1419608.78 frames.], batch size: 22, lr: 2.52e-04
2022-05-15 17:35:31,418 INFO [train.py:812] (3/8) Epoch 31, batch 1450, loss[loss=0.1416, simple_loss=0.2445, pruned_loss=0.01931, over 7145.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.03038, over 1420612.47 frames.], batch size: 20, lr: 2.52e-04
2022-05-15 17:36:30,345 INFO [train.py:812] (3/8) Epoch 31, batch 1500, loss[loss=0.159, simple_loss=0.2496, pruned_loss=0.03414, over 7325.00 frames.], tot_loss[loss=0.154, simple_loss=0.2466, pruned_loss=0.03068, over 1426167.17 frames.], batch size: 25, lr: 2.52e-04
2022-05-15 17:37:27,926 INFO [train.py:812] (3/8) Epoch 31, batch 1550, loss[loss=0.1548, simple_loss=0.2575, pruned_loss=0.0261, over 7331.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2455, pruned_loss=0.0307, over 1427422.56 frames.], batch size: 25, lr: 2.52e-04
2022-05-15 17:38:27,319 INFO [train.py:812] (3/8) Epoch 31, batch 1600, loss[loss=0.138, simple_loss=0.2214, pruned_loss=0.02731, over 7251.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03041, over 1428534.36 frames.], batch size: 19, lr: 2.52e-04
2022-05-15 17:39:26,037 INFO [train.py:812] (3/8) Epoch 31, batch 1650, loss[loss=0.1632, simple_loss=0.2548, pruned_loss=0.03581, over 7122.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2454, pruned_loss=0.03041, over 1428765.89 frames.], batch size: 21, lr: 2.52e-04
2022-05-15 17:40:24,535 INFO [train.py:812] (3/8) Epoch 31, batch 1700, loss[loss=0.1457, simple_loss=0.2469, pruned_loss=0.02223, over 7312.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03, over 1426445.69 frames.], batch size: 24, lr: 2.52e-04
2022-05-15 17:41:22,648 INFO [train.py:812] (3/8) Epoch 31, batch 1750, loss[loss=0.1649, simple_loss=0.2488, pruned_loss=0.04048, over 7375.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03002, over 1428678.93 frames.], batch size: 23, lr: 2.52e-04
2022-05-15 17:42:21,640 INFO [train.py:812] (3/8) Epoch 31, batch 1800, loss[loss=0.1254, simple_loss=0.2202, pruned_loss=0.01531, over 7424.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03016, over 1425483.26 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 17:43:20,028 INFO [train.py:812] (3/8) Epoch 31, batch 1850, loss[loss=0.138, simple_loss=0.225, pruned_loss=0.02551, over 7141.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03024, over 1423587.01 frames.], batch size: 17, lr: 2.51e-04
2022-05-15 17:44:19,005 INFO [train.py:812] (3/8) Epoch 31, batch 1900, loss[loss=0.1474, simple_loss=0.2405, pruned_loss=0.02715, over 7336.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03048, over 1426453.20 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 17:45:17,768 INFO [train.py:812] (3/8) Epoch 31, batch 1950, loss[loss=0.1632, simple_loss=0.258, pruned_loss=0.03416, over 7369.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03028, over 1426806.44 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:46:16,483 INFO [train.py:812] (3/8) Epoch 31, batch 2000, loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.03125, over 7161.00 frames.], tot_loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.03002, over 1428749.08 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:47:15,228 INFO [train.py:812] (3/8) Epoch 31, batch 2050, loss[loss=0.1665, simple_loss=0.2619, pruned_loss=0.03556, over 7190.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2425, pruned_loss=0.02993, over 1426417.03 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 17:48:13,812 INFO [train.py:812] (3/8) Epoch 31, batch 2100, loss[loss=0.1571, simple_loss=0.2415, pruned_loss=0.0363, over 7148.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2434, pruned_loss=0.03017, over 1424322.37 frames.], batch size: 19, lr: 2.51e-04
2022-05-15 17:49:12,917 INFO [train.py:812] (3/8) Epoch 31, batch 2150, loss[loss=0.1637, simple_loss=0.2475, pruned_loss=0.04001, over 7158.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02977, over 1427567.03 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:50:11,062 INFO [train.py:812] (3/8) Epoch 31, batch 2200, loss[loss=0.1559, simple_loss=0.2329, pruned_loss=0.03948, over 7064.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03015, over 1429325.70 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:51:08,600 INFO [train.py:812] (3/8) Epoch 31, batch 2250, loss[loss=0.1797, simple_loss=0.2776, pruned_loss=0.04089, over 7208.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2459, pruned_loss=0.0305, over 1428324.43 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:52:08,114 INFO [train.py:812] (3/8) Epoch 31, batch 2300, loss[loss=0.1303, simple_loss=0.2208, pruned_loss=0.0199, over 7251.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2461, pruned_loss=0.03061, over 1431095.71 frames.], batch size: 19, lr: 2.51e-04
2022-05-15 17:53:06,337 INFO [train.py:812] (3/8) Epoch 31, batch 2350, loss[loss=0.1285, simple_loss=0.2203, pruned_loss=0.01835, over 7063.00 frames.], tot_loss[loss=0.153, simple_loss=0.2453, pruned_loss=0.03037, over 1430369.99 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:54:10,963 INFO [train.py:812] (3/8) Epoch 31, batch 2400, loss[loss=0.1813, simple_loss=0.2701, pruned_loss=0.04621, over 7220.00 frames.], tot_loss[loss=0.1538, simple_loss=0.246, pruned_loss=0.03079, over 1428935.44 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 17:55:08,412 INFO [train.py:812] (3/8) Epoch 31, batch 2450, loss[loss=0.1562, simple_loss=0.2541, pruned_loss=0.02919, over 7225.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2457, pruned_loss=0.03064, over 1425101.17 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 17:56:07,145 INFO [train.py:812] (3/8) Epoch 31, batch 2500, loss[loss=0.1568, simple_loss=0.26, pruned_loss=0.02677, over 7340.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2446, pruned_loss=0.03025, over 1427562.95 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 17:57:05,826 INFO [train.py:812] (3/8) Epoch 31, batch 2550, loss[loss=0.1594, simple_loss=0.2464, pruned_loss=0.0362, over 7169.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2444, pruned_loss=0.03035, over 1429170.60 frames.], batch size: 23, lr: 2.51e-04
2022-05-15 17:58:14,113 INFO [train.py:812] (3/8) Epoch 31, batch 2600, loss[loss=0.1285, simple_loss=0.2197, pruned_loss=0.01863, over 7402.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2442, pruned_loss=0.03059, over 1428530.53 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 17:59:11,562 INFO [train.py:812] (3/8) Epoch 31, batch 2650, loss[loss=0.1566, simple_loss=0.2501, pruned_loss=0.03157, over 7400.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2447, pruned_loss=0.03049, over 1425859.72 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 18:00:10,461 INFO [train.py:812] (3/8) Epoch 31, batch 2700, loss[loss=0.1855, simple_loss=0.2612, pruned_loss=0.05489, over 7235.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.0304, over 1419626.90 frames.], batch size: 25, lr: 2.51e-04
2022-05-15 18:01:09,682 INFO [train.py:812] (3/8) Epoch 31, batch 2750, loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.0296, over 7145.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03047, over 1420189.84 frames.], batch size: 20, lr: 2.51e-04
2022-05-15 18:02:08,951 INFO [train.py:812] (3/8) Epoch 31, batch 2800, loss[loss=0.1499, simple_loss=0.2259, pruned_loss=0.03695, over 7163.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03068, over 1422166.57 frames.], batch size: 18, lr: 2.51e-04
2022-05-15 18:03:06,864 INFO [train.py:812] (3/8) Epoch 31, batch 2850, loss[loss=0.1643, simple_loss=0.2605, pruned_loss=0.03406, over 7187.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2455, pruned_loss=0.0309, over 1419737.09 frames.], batch size: 22, lr: 2.51e-04
2022-05-15 18:04:06,617 INFO [train.py:812] (3/8) Epoch 31, batch 2900, loss[loss=0.1478, simple_loss=0.2526, pruned_loss=0.02153, over 7119.00 frames.], tot_loss[loss=0.1541, simple_loss=0.246, pruned_loss=0.03107, over 1423546.89 frames.], batch size: 21, lr: 2.51e-04
2022-05-15 18:05:04,888 INFO [train.py:812] (3/8) Epoch 31, batch 2950, loss[loss=0.1583, simple_loss=0.2453, pruned_loss=0.03563, over 7266.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2454, pruned_loss=0.03057, over 1422825.57 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:06:03,446 INFO [train.py:812] (3/8) Epoch 31, batch 3000, loss[loss=0.1442, simple_loss=0.2317, pruned_loss=0.02834, over 7332.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.0305, over 1422380.46 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:06:03,447 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 18:06:10,972 INFO [train.py:841] (3/8) Epoch 31, validation: loss=0.1541, simple_loss=0.25, pruned_loss=0.02913, over 698248.00 frames.
2022-05-15 18:07:09,520 INFO [train.py:812] (3/8) Epoch 31, batch 3050, loss[loss=0.1229, simple_loss=0.2075, pruned_loss=0.01915, over 7001.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2451, pruned_loss=0.03063, over 1422286.71 frames.], batch size: 16, lr: 2.50e-04
2022-05-15 18:08:09,158 INFO [train.py:812] (3/8) Epoch 31, batch 3100, loss[loss=0.1678, simple_loss=0.2579, pruned_loss=0.0388, over 7313.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2448, pruned_loss=0.03055, over 1425379.89 frames.], batch size: 25, lr: 2.50e-04
2022-05-15 18:09:08,136 INFO [train.py:812] (3/8) Epoch 31, batch 3150, loss[loss=0.1509, simple_loss=0.2354, pruned_loss=0.03314, over 6991.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2445, pruned_loss=0.03057, over 1424248.62 frames.], batch size: 16, lr: 2.50e-04
2022-05-15 18:10:05,063 INFO [train.py:812] (3/8) Epoch 31, batch 3200, loss[loss=0.1586, simple_loss=0.25, pruned_loss=0.0336, over 7205.00 frames.], tot_loss[loss=0.153, simple_loss=0.2446, pruned_loss=0.03071, over 1416361.59 frames.], batch size: 23, lr: 2.50e-04
2022-05-15 18:11:03,062 INFO [train.py:812] (3/8) Epoch 31, batch 3250, loss[loss=0.2085, simple_loss=0.2875, pruned_loss=0.06472, over 7145.00 frames.], tot_loss[loss=0.1532, simple_loss=0.245, pruned_loss=0.03065, over 1415935.33 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:12:02,654 INFO [train.py:812] (3/8) Epoch 31, batch 3300, loss[loss=0.118, simple_loss=0.1958, pruned_loss=0.02005, over 7270.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03056, over 1422257.02 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:13:01,583 INFO [train.py:812] (3/8) Epoch 31, batch 3350, loss[loss=0.1509, simple_loss=0.2517, pruned_loss=0.0251, over 7217.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2438, pruned_loss=0.03053, over 1421451.40 frames.], batch size: 21, lr: 2.50e-04
2022-05-15 18:14:00,865 INFO [train.py:812] (3/8) Epoch 31, batch 3400, loss[loss=0.1711, simple_loss=0.2649, pruned_loss=0.03871, over 7289.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2431, pruned_loss=0.02999, over 1420942.10 frames.], batch size: 25, lr: 2.50e-04
2022-05-15 18:14:57,860 INFO [train.py:812] (3/8) Epoch 31, batch 3450, loss[loss=0.1392, simple_loss=0.2357, pruned_loss=0.02137, over 6255.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02981, over 1424996.64 frames.], batch size: 37, lr: 2.50e-04
2022-05-15 18:15:56,016 INFO [train.py:812] (3/8) Epoch 31, batch 3500, loss[loss=0.1773, simple_loss=0.2722, pruned_loss=0.04115, over 7380.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02985, over 1427191.45 frames.], batch size: 23, lr: 2.50e-04
2022-05-15 18:16:54,984 INFO [train.py:812] (3/8) Epoch 31, batch 3550, loss[loss=0.1618, simple_loss=0.2482, pruned_loss=0.03776, over 7432.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03038, over 1428377.46 frames.], batch size: 20, lr: 2.50e-04
2022-05-15 18:17:52,448 INFO [train.py:812] (3/8) Epoch 31, batch 3600, loss[loss=0.1671, simple_loss=0.2557, pruned_loss=0.03925, over 7278.00 frames.], tot_loss[loss=0.1529, simple_loss=0.245, pruned_loss=0.03034, over 1422909.19 frames.], batch size: 24, lr: 2.50e-04
2022-05-15 18:18:51,245 INFO [train.py:812] (3/8) Epoch 31, batch 3650, loss[loss=0.14, simple_loss=0.2264, pruned_loss=0.02676, over 7135.00 frames.], tot_loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03057, over 1421839.72 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:19:50,481 INFO [train.py:812] (3/8) Epoch 31, batch 3700, loss[loss=0.1306, simple_loss=0.2287, pruned_loss=0.01625, over 7302.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03043, over 1425497.01 frames.], batch size: 17, lr: 2.50e-04
2022-05-15 18:20:49,304 INFO [train.py:812] (3/8) Epoch 31, batch 3750, loss[loss=0.1387, simple_loss=0.2367, pruned_loss=0.02037, over 7255.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03034, over 1423470.91 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:21:49,295 INFO [train.py:812] (3/8) Epoch 31, batch 3800, loss[loss=0.1227, simple_loss=0.2092, pruned_loss=0.01813, over 7286.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.0304, over 1425985.14 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:22:47,399 INFO [train.py:812] (3/8) Epoch 31, batch 3850, loss[loss=0.1326, simple_loss=0.2243, pruned_loss=0.02046, over 7064.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.03046, over 1425126.76 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:23:45,721 INFO [train.py:812] (3/8) Epoch 31, batch 3900, loss[loss=0.1522, simple_loss=0.2537, pruned_loss=0.0254, over 7280.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2446, pruned_loss=0.03009, over 1428309.79 frames.], batch size: 24, lr: 2.50e-04
2022-05-15 18:24:43,600 INFO [train.py:812] (3/8) Epoch 31, batch 3950, loss[loss=0.1546, simple_loss=0.2447, pruned_loss=0.03226, over 7343.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03008, over 1428616.24 frames.], batch size: 19, lr: 2.50e-04
2022-05-15 18:25:41,729 INFO [train.py:812] (3/8) Epoch 31, batch 4000, loss[loss=0.1386, simple_loss=0.2347, pruned_loss=0.02121, over 7167.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2446, pruned_loss=0.03042, over 1426301.96 frames.], batch size: 18, lr: 2.50e-04
2022-05-15 18:26:41,002 INFO [train.py:812] (3/8) Epoch 31, batch 4050, loss[loss=0.1866, simple_loss=0.2805, pruned_loss=0.04638, over 7280.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.0308, over 1425521.07 frames.], batch size: 24, lr: 2.49e-04
2022-05-15 18:27:40,601 INFO [train.py:812] (3/8) Epoch 31, batch 4100, loss[loss=0.128, simple_loss=0.2268, pruned_loss=0.01455, over 7160.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2456, pruned_loss=0.03087, over 1427747.73 frames.], batch size: 19, lr: 2.49e-04
2022-05-15 18:28:39,531 INFO [train.py:812] (3/8) Epoch 31, batch 4150, loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03133, over 7113.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03013, over 1430205.48 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:29:38,554 INFO [train.py:812] (3/8) Epoch 31, batch 4200, loss[loss=0.1385, simple_loss=0.225, pruned_loss=0.02602, over 6810.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03003, over 1431141.41 frames.], batch size: 15, lr: 2.49e-04
2022-05-15 18:30:36,491 INFO [train.py:812] (3/8) Epoch 31, batch 4250, loss[loss=0.1683, simple_loss=0.2624, pruned_loss=0.03712, over 7154.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2439, pruned_loss=0.02999, over 1427628.07 frames.], batch size: 26, lr: 2.49e-04
2022-05-15 18:31:35,773 INFO [train.py:812] (3/8) Epoch 31, batch 4300, loss[loss=0.1431, simple_loss=0.2382, pruned_loss=0.02395, over 7303.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02979, over 1431155.24 frames.], batch size: 24, lr: 2.49e-04
2022-05-15 18:32:33,414 INFO [train.py:812] (3/8) Epoch 31, batch 4350, loss[loss=0.1517, simple_loss=0.2499, pruned_loss=0.0268, over 7109.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02979, over 1422053.87 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:33:32,237 INFO [train.py:812] (3/8) Epoch 31, batch 4400, loss[loss=0.1568, simple_loss=0.2421, pruned_loss=0.03573, over 7111.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2442, pruned_loss=0.03027, over 1412296.46 frames.], batch size: 21, lr: 2.49e-04
2022-05-15 18:34:30,882 INFO [train.py:812] (3/8) Epoch 31, batch 4450, loss[loss=0.1356, simple_loss=0.2322, pruned_loss=0.01952, over 6402.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03033, over 1411769.77 frames.], batch size: 38, lr: 2.49e-04
2022-05-15 18:35:30,074 INFO [train.py:812] (3/8) Epoch 31, batch 4500, loss[loss=0.1578, simple_loss=0.2481, pruned_loss=0.03375, over 6563.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2455, pruned_loss=0.03105, over 1385931.15 frames.], batch size: 38, lr: 2.49e-04
2022-05-15 18:36:28,940 INFO [train.py:812] (3/8) Epoch 31, batch 4550, loss[loss=0.1782, simple_loss=0.2763, pruned_loss=0.04003, over 4918.00 frames.], tot_loss[loss=0.155, simple_loss=0.2468, pruned_loss=0.03164, over 1355358.28 frames.], batch size: 52, lr: 2.49e-04
2022-05-15 18:37:36,649 INFO [train.py:812] (3/8) Epoch 32, batch 0, loss[loss=0.1564, simple_loss=0.2463, pruned_loss=0.03328, over 5085.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2463, pruned_loss=0.03328, over 5085.00 frames.], batch size: 52, lr: 2.45e-04
2022-05-15 18:38:34,886 INFO [train.py:812] (3/8) Epoch 32, batch 50, loss[loss=0.1588, simple_loss=0.2496, pruned_loss=0.03402, over 6428.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2499, pruned_loss=0.03195, over 319323.88 frames.], batch size: 38, lr: 2.45e-04
2022-05-15 18:39:33,414 INFO [train.py:812] (3/8) Epoch 32, batch 100, loss[loss=0.1538, simple_loss=0.2552, pruned_loss=0.02616, over 7288.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2469, pruned_loss=0.0307, over 566393.36 frames.], batch size: 25, lr: 2.45e-04
2022-05-15 18:40:32,488 INFO [train.py:812] (3/8) Epoch 32, batch 150, loss[loss=0.1828, simple_loss=0.2808, pruned_loss=0.04242, over 7154.00 frames.], tot_loss[loss=0.1534, simple_loss=0.246, pruned_loss=0.03043, over 758174.47 frames.], batch size: 26, lr: 2.45e-04
2022-05-15 18:41:31,067 INFO [train.py:812] (3/8) Epoch 32, batch 200, loss[loss=0.1269, simple_loss=0.2044, pruned_loss=0.02467, over 7011.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2443, pruned_loss=0.02979, over 902865.58 frames.], batch size: 16, lr: 2.45e-04
2022-05-15 18:42:29,491 INFO [train.py:812] (3/8) Epoch 32, batch 250, loss[loss=0.1422, simple_loss=0.2372, pruned_loss=0.02361, over 7285.00 frames.], tot_loss[loss=0.152, simple_loss=0.2442, pruned_loss=0.02991, over 1022567.77 frames.], batch size: 24, lr: 2.45e-04
2022-05-15 18:43:28,934 INFO [train.py:812] (3/8) Epoch 32, batch 300, loss[loss=0.1783, simple_loss=0.2647, pruned_loss=0.04596, over 7305.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2448, pruned_loss=0.02982, over 1113333.35 frames.], batch size: 24, lr: 2.45e-04
2022-05-15 18:44:28,377 INFO [train.py:812] (3/8) Epoch 32, batch 350, loss[loss=0.1544, simple_loss=0.2514, pruned_loss=0.02869, over 7111.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02988, over 1181025.33 frames.], batch size: 28, lr: 2.45e-04
2022-05-15 18:45:27,075 INFO [train.py:812] (3/8) Epoch 32, batch 400, loss[loss=0.1645, simple_loss=0.2528, pruned_loss=0.03808, over 7170.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2449, pruned_loss=0.03036, over 1236141.77 frames.], batch size: 26, lr: 2.45e-04
2022-05-15 18:46:25,919 INFO [train.py:812] (3/8) Epoch 32, batch 450, loss[loss=0.1388, simple_loss=0.2359, pruned_loss=0.0208, over 7323.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03047, over 1276432.13 frames.], batch size: 21, lr: 2.45e-04
2022-05-15 18:47:25,083 INFO [train.py:812] (3/8) Epoch 32, batch 500, loss[loss=0.1687, simple_loss=0.2618, pruned_loss=0.03785, over 7330.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2431, pruned_loss=0.03015, over 1312758.48 frames.], batch size: 22, lr: 2.45e-04
2022-05-15 18:48:23,090 INFO [train.py:812] (3/8) Epoch 32, batch 550, loss[loss=0.1462, simple_loss=0.2462, pruned_loss=0.02308, over 7335.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02985, over 1340992.30 frames.], batch size: 22, lr: 2.45e-04
2022-05-15 18:49:22,848 INFO [train.py:812] (3/8) Epoch 32, batch 600, loss[loss=0.1136, simple_loss=0.2044, pruned_loss=0.01138, over 7134.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2425, pruned_loss=0.0295, over 1363936.42 frames.], batch size: 17, lr: 2.45e-04
2022-05-15 18:50:21,223 INFO [train.py:812] (3/8) Epoch 32, batch 650, loss[loss=0.1294, simple_loss=0.2164, pruned_loss=0.02118, over 6997.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2425, pruned_loss=0.02954, over 1379345.87 frames.], batch size: 16, lr: 2.45e-04
2022-05-15 18:51:18,831 INFO [train.py:812] (3/8) Epoch 32, batch 700, loss[loss=0.1563, simple_loss=0.2505, pruned_loss=0.03109, over 7208.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02947, over 1387659.79 frames.], batch size: 23, lr: 2.45e-04
2022-05-15 18:52:17,781 INFO [train.py:812] (3/8) Epoch 32, batch 750, loss[loss=0.1439, simple_loss=0.2393, pruned_loss=0.02424, over 7114.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02963, over 1395391.87 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 18:53:17,322 INFO [train.py:812] (3/8) Epoch 32, batch 800, loss[loss=0.1323, simple_loss=0.2242, pruned_loss=0.02023, over 7270.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02918, over 1400094.42 frames.], batch size: 18, lr: 2.44e-04
2022-05-15 18:54:15,844 INFO [train.py:812] (3/8) Epoch 32, batch 850, loss[loss=0.1683, simple_loss=0.2649, pruned_loss=0.03585, over 7290.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03001, over 1407604.67 frames.], batch size: 25, lr: 2.44e-04
2022-05-15 18:55:14,214 INFO [train.py:812] (3/8) Epoch 32, batch 900, loss[loss=0.1516, simple_loss=0.241, pruned_loss=0.03106, over 7338.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.02994, over 1410010.21 frames.], batch size: 22, lr: 2.44e-04
2022-05-15 18:56:22,062 INFO [train.py:812] (3/8) Epoch 32, batch 950, loss[loss=0.139, simple_loss=0.2232, pruned_loss=0.02743, over 6831.00 frames.], tot_loss[loss=0.1523, simple_loss=0.244, pruned_loss=0.03026, over 1412214.49 frames.], batch size: 15, lr: 2.44e-04
2022-05-15 18:57:31,072 INFO [train.py:812] (3/8) Epoch 32, batch 1000, loss[loss=0.1431, simple_loss=0.2333, pruned_loss=0.02639, over 7430.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03, over 1415717.33 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 18:58:30,364 INFO [train.py:812] (3/8) Epoch 32, batch 1050, loss[loss=0.1954, simple_loss=0.2851, pruned_loss=0.05284, over 7236.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2432, pruned_loss=0.03018, over 1419760.01 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 18:59:29,286 INFO [train.py:812] (3/8) Epoch 32, batch 1100, loss[loss=0.1397, simple_loss=0.2388, pruned_loss=0.02031, over 7202.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2426, pruned_loss=0.02975, over 1418541.86 frames.], batch size: 22, lr: 2.44e-04
2022-05-15 19:00:36,742 INFO [train.py:812] (3/8) Epoch 32, batch 1150, loss[loss=0.1479, simple_loss=0.2317, pruned_loss=0.03205, over 7133.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2431, pruned_loss=0.02988, over 1421920.69 frames.], batch size: 17, lr: 2.44e-04
2022-05-15 19:01:36,496 INFO [train.py:812] (3/8) Epoch 32, batch 1200, loss[loss=0.1657, simple_loss=0.2606, pruned_loss=0.03543, over 7407.00 frames.], tot_loss[loss=0.151, simple_loss=0.2425, pruned_loss=0.02978, over 1423640.22 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:02:45,178 INFO [train.py:812] (3/8) Epoch 32, batch 1250, loss[loss=0.1656, simple_loss=0.2556, pruned_loss=0.03773, over 7213.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03036, over 1417464.82 frames.], batch size: 23, lr: 2.44e-04
2022-05-15 19:03:53,735 INFO [train.py:812] (3/8) Epoch 32, batch 1300, loss[loss=0.1777, simple_loss=0.28, pruned_loss=0.03768, over 7141.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2446, pruned_loss=0.0305, over 1422961.96 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:05:00,952 INFO [train.py:812] (3/8) Epoch 32, batch 1350, loss[loss=0.1391, simple_loss=0.2283, pruned_loss=0.02492, over 7333.00 frames.], tot_loss[loss=0.1534, simple_loss=0.245, pruned_loss=0.03086, over 1421559.22 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:05:59,742 INFO [train.py:812] (3/8) Epoch 32, batch 1400, loss[loss=0.1311, simple_loss=0.2237, pruned_loss=0.01919, over 7248.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03013, over 1422054.87 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:06:57,259 INFO [train.py:812] (3/8) Epoch 32, batch 1450, loss[loss=0.1508, simple_loss=0.2366, pruned_loss=0.03248, over 7335.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2443, pruned_loss=0.03073, over 1423840.23 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:08:05,674 INFO [train.py:812] (3/8) Epoch 32, batch 1500, loss[loss=0.176, simple_loss=0.2566, pruned_loss=0.04766, over 4964.00 frames.], tot_loss[loss=0.1524, simple_loss=0.244, pruned_loss=0.03047, over 1422527.37 frames.], batch size: 52, lr: 2.44e-04
2022-05-15 19:09:04,131 INFO [train.py:812] (3/8) Epoch 32, batch 1550, loss[loss=0.1402, simple_loss=0.2244, pruned_loss=0.02802, over 7397.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03019, over 1421741.51 frames.], batch size: 18, lr: 2.44e-04
2022-05-15 19:10:03,416 INFO [train.py:812] (3/8) Epoch 32, batch 1600, loss[loss=0.186, simple_loss=0.2652, pruned_loss=0.05342, over 7207.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2437, pruned_loss=0.03056, over 1417571.25 frames.], batch size: 23, lr: 2.44e-04
2022-05-15 19:11:01,504 INFO [train.py:812] (3/8) Epoch 32, batch 1650, loss[loss=0.152, simple_loss=0.2514, pruned_loss=0.02632, over 7413.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03049, over 1416974.32 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:12:00,717 INFO [train.py:812] (3/8) Epoch 32, batch 1700, loss[loss=0.1384, simple_loss=0.2394, pruned_loss=0.01871, over 7126.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.03016, over 1412668.80 frames.], batch size: 21, lr: 2.44e-04
2022-05-15 19:12:59,704 INFO [train.py:812] (3/8) Epoch 32, batch 1750, loss[loss=0.1797, simple_loss=0.2668, pruned_loss=0.04631, over 5093.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2441, pruned_loss=0.03033, over 1410449.60 frames.], batch size: 52, lr: 2.44e-04
2022-05-15 19:14:04,613 INFO [train.py:812] (3/8) Epoch 32, batch 1800, loss[loss=0.1337, simple_loss=0.2234, pruned_loss=0.02198, over 7234.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2452, pruned_loss=0.03051, over 1411986.72 frames.], batch size: 20, lr: 2.44e-04
2022-05-15 19:15:03,150 INFO [train.py:812] (3/8) Epoch 32, batch 1850, loss[loss=0.1189, simple_loss=0.2033, pruned_loss=0.01722, over 6990.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2451, pruned_loss=0.03056, over 1405802.28 frames.], batch size: 16, lr: 2.44e-04
2022-05-15 19:16:02,093 INFO [train.py:812] (3/8) Epoch 32, batch 1900, loss[loss=0.1395, simple_loss=0.2297, pruned_loss=0.02468, over 7360.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03042, over 1412510.09 frames.], batch size: 19, lr: 2.44e-04
2022-05-15 19:17:00,604 INFO [train.py:812] (3/8) Epoch 32, batch 1950, loss[loss=0.1327, simple_loss=0.2261, pruned_loss=0.01969, over 7360.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03041, over 1418294.72 frames.], batch size: 19, lr: 2.43e-04
2022-05-15 19:18:00,427 INFO [train.py:812] (3/8) Epoch 32, batch 2000, loss[loss=0.1433, simple_loss=0.2304, pruned_loss=0.02809, over 7281.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.03031, over 1420207.03 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:18:57,520 INFO [train.py:812] (3/8) Epoch 32, batch 2050, loss[loss=0.141, simple_loss=0.2377, pruned_loss=0.02209, over 7155.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03045, over 1416722.88 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:19:56,208 INFO [train.py:812] (3/8) Epoch 32, batch 2100, loss[loss=0.135, simple_loss=0.2232, pruned_loss=0.02346, over 7264.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2452, pruned_loss=0.03074, over 1417055.60 frames.], batch size: 16, lr: 2.43e-04
2022-05-15 19:20:54,970 INFO [train.py:812] (3/8) Epoch 32, batch 2150, loss[loss=0.1631, simple_loss=0.2648, pruned_loss=0.03076, over 7225.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2455, pruned_loss=0.0304, over 1420727.91 frames.], batch size: 21, lr: 2.43e-04
2022-05-15 19:21:53,739 INFO [train.py:812] (3/8) Epoch 32, batch 2200, loss[loss=0.1673, simple_loss=0.2631, pruned_loss=0.03579, over 7184.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03012, over 1423234.92 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:22:52,759 INFO [train.py:812] (3/8) Epoch 32, batch 2250, loss[loss=0.1361, simple_loss=0.2301, pruned_loss=0.02106, over 7056.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2441, pruned_loss=0.03006, over 1424934.81 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:23:52,309 INFO [train.py:812] (3/8) Epoch 32, batch 2300, loss[loss=0.1422, simple_loss=0.2403, pruned_loss=0.02203, over 7338.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.03011, over 1421178.14 frames.], batch size: 22, lr: 2.43e-04
2022-05-15 19:24:49,710 INFO [train.py:812] (3/8) Epoch 32, batch 2350, loss[loss=0.1511, simple_loss=0.2296, pruned_loss=0.03627, over 7279.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.0305, over 1425004.79 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:25:48,460 INFO [train.py:812] (3/8) Epoch 32, batch 2400, loss[loss=0.1475, simple_loss=0.2383, pruned_loss=0.02835, over 7328.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2456, pruned_loss=0.031, over 1420601.12 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:26:47,797 INFO [train.py:812] (3/8) Epoch 32, batch 2450, loss[loss=0.193, simple_loss=0.2879, pruned_loss=0.04902, over 7145.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2452, pruned_loss=0.0311, over 1422338.74 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:27:46,267 INFO [train.py:812] (3/8) Epoch 32, batch 2500, loss[loss=0.1334, simple_loss=0.2156, pruned_loss=0.02564, over 7279.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2445, pruned_loss=0.03082, over 1424620.02 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:28:44,156 INFO [train.py:812] (3/8) Epoch 32, batch 2550, loss[loss=0.1523, simple_loss=0.2465, pruned_loss=0.02909, over 7327.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2441, pruned_loss=0.03042, over 1423259.31 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:29:41,341 INFO [train.py:812] (3/8) Epoch 32, batch 2600, loss[loss=0.1505, simple_loss=0.2323, pruned_loss=0.0343, over 7139.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2439, pruned_loss=0.03041, over 1421347.40 frames.], batch size: 17, lr: 2.43e-04
2022-05-15 19:30:39,890 INFO [train.py:812] (3/8) Epoch 32, batch 2650, loss[loss=0.168, simple_loss=0.2689, pruned_loss=0.03353, over 7162.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.02999, over 1423809.43 frames.], batch size: 26, lr: 2.43e-04
2022-05-15 19:31:39,423 INFO [train.py:812] (3/8) Epoch 32, batch 2700, loss[loss=0.1309, simple_loss=0.2256, pruned_loss=0.01809, over 7321.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2433, pruned_loss=0.02975, over 1422553.36 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:32:37,295 INFO [train.py:812] (3/8) Epoch 32, batch 2750, loss[loss=0.1445, simple_loss=0.2399, pruned_loss=0.02453, over 7118.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02996, over 1424588.89 frames.], batch size: 28, lr: 2.43e-04
2022-05-15 19:33:35,485 INFO [train.py:812] (3/8) Epoch 32, batch 2800, loss[loss=0.1308, simple_loss=0.2143, pruned_loss=0.02362, over 7418.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02997, over 1424338.10 frames.], batch size: 18, lr: 2.43e-04
2022-05-15 19:34:34,368 INFO [train.py:812] (3/8) Epoch 32, batch 2850, loss[loss=0.1758, simple_loss=0.2726, pruned_loss=0.03953, over 6486.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02964, over 1421318.64 frames.], batch size: 38, lr: 2.43e-04
2022-05-15 19:35:32,676 INFO [train.py:812] (3/8) Epoch 32, batch 2900, loss[loss=0.1543, simple_loss=0.2553, pruned_loss=0.02665, over 7226.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2437, pruned_loss=0.0298, over 1425353.90 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:36:30,947 INFO [train.py:812] (3/8) Epoch 32, batch 2950, loss[loss=0.1395, simple_loss=0.2372, pruned_loss=0.02088, over 7205.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02963, over 1418143.66 frames.], batch size: 23, lr: 2.43e-04
2022-05-15 19:37:29,680 INFO [train.py:812] (3/8) Epoch 32, batch 3000, loss[loss=0.1572, simple_loss=0.2446, pruned_loss=0.03483, over 7414.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.02953, over 1419465.25 frames.], batch size: 20, lr: 2.43e-04
2022-05-15 19:37:29,681 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 19:37:37,095 INFO [train.py:841] (3/8) 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] (3/8) Epoch 32, batch 3050, loss[loss=0.1788, simple_loss=0.2705, pruned_loss=0.04359, over 7293.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02976, over 1423013.05 frames.], batch size: 25, lr: 2.43e-04
2022-05-15 19:39:34,755 INFO [train.py:812] (3/8) Epoch 32, batch 3100, loss[loss=0.1742, simple_loss=0.2754, pruned_loss=0.03647, over 7102.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02991, over 1426500.63 frames.], batch size: 28, lr: 2.42e-04
2022-05-15 19:40:34,124 INFO [train.py:812] (3/8) Epoch 32, batch 3150, loss[loss=0.131, simple_loss=0.213, pruned_loss=0.02446, over 7294.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2429, pruned_loss=0.02987, over 1423957.18 frames.], batch size: 17, lr: 2.42e-04
2022-05-15 19:41:32,533 INFO [train.py:812] (3/8) Epoch 32, batch 3200, loss[loss=0.1606, simple_loss=0.2621, pruned_loss=0.02955, over 7120.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2445, pruned_loss=0.0301, over 1426136.13 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:42:31,652 INFO [train.py:812] (3/8) Epoch 32, batch 3250, loss[loss=0.1363, simple_loss=0.235, pruned_loss=0.01877, over 7331.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2443, pruned_loss=0.02993, over 1428125.74 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 19:43:31,267 INFO [train.py:812] (3/8) Epoch 32, batch 3300, loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02787, over 7435.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03013, over 1424326.70 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:44:30,517 INFO [train.py:812] (3/8) Epoch 32, batch 3350, loss[loss=0.1514, simple_loss=0.2521, pruned_loss=0.02532, over 7313.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02966, over 1425846.39 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:45:29,637 INFO [train.py:812] (3/8) Epoch 32, batch 3400, loss[loss=0.1345, simple_loss=0.2232, pruned_loss=0.02292, over 7333.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2436, pruned_loss=0.0303, over 1422670.94 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:46:27,576 INFO [train.py:812] (3/8) Epoch 32, batch 3450, loss[loss=0.1876, simple_loss=0.2822, pruned_loss=0.0465, over 7219.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2449, pruned_loss=0.03041, over 1425913.93 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 19:47:26,345 INFO [train.py:812] (3/8) Epoch 32, batch 3500, loss[loss=0.158, simple_loss=0.2666, pruned_loss=0.02466, over 7302.00 frames.], tot_loss[loss=0.153, simple_loss=0.2451, pruned_loss=0.0304, over 1428708.07 frames.], batch size: 24, lr: 2.42e-04
2022-05-15 19:48:25,221 INFO [train.py:812] (3/8) Epoch 32, batch 3550, loss[loss=0.1545, simple_loss=0.2406, pruned_loss=0.03421, over 7367.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2441, pruned_loss=0.03017, over 1431882.00 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:49:24,686 INFO [train.py:812] (3/8) Epoch 32, batch 3600, loss[loss=0.147, simple_loss=0.2447, pruned_loss=0.02461, over 6290.00 frames.], tot_loss[loss=0.152, simple_loss=0.2436, pruned_loss=0.03015, over 1428321.63 frames.], batch size: 37, lr: 2.42e-04
2022-05-15 19:50:24,024 INFO [train.py:812] (3/8) Epoch 32, batch 3650, loss[loss=0.1465, simple_loss=0.2383, pruned_loss=0.02736, over 7243.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2442, pruned_loss=0.03014, over 1427994.51 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:51:24,134 INFO [train.py:812] (3/8) Epoch 32, batch 3700, loss[loss=0.1619, simple_loss=0.2383, pruned_loss=0.04277, over 7133.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2429, pruned_loss=0.02976, over 1430043.73 frames.], batch size: 17, lr: 2.42e-04
2022-05-15 19:52:22,797 INFO [train.py:812] (3/8) Epoch 32, batch 3750, loss[loss=0.1702, simple_loss=0.2572, pruned_loss=0.04164, over 7193.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02962, over 1424616.25 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:53:21,638 INFO [train.py:812] (3/8) Epoch 32, batch 3800, loss[loss=0.1628, simple_loss=0.2522, pruned_loss=0.03669, over 7370.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02951, over 1425948.24 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:54:19,345 INFO [train.py:812] (3/8) Epoch 32, batch 3850, loss[loss=0.1566, simple_loss=0.2565, pruned_loss=0.02838, over 7437.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02935, over 1428616.04 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 19:55:28,026 INFO [train.py:812] (3/8) Epoch 32, batch 3900, loss[loss=0.1463, simple_loss=0.2279, pruned_loss=0.03236, over 7162.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02941, over 1429610.71 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 19:56:25,325 INFO [train.py:812] (3/8) Epoch 32, batch 3950, loss[loss=0.1702, simple_loss=0.2689, pruned_loss=0.03571, over 7214.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02996, over 1425958.03 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 19:57:24,487 INFO [train.py:812] (3/8) Epoch 32, batch 4000, loss[loss=0.1247, simple_loss=0.2136, pruned_loss=0.01786, over 7408.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.02997, over 1421624.30 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 19:58:22,814 INFO [train.py:812] (3/8) Epoch 32, batch 4050, loss[loss=0.1954, simple_loss=0.2945, pruned_loss=0.04813, over 7368.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2442, pruned_loss=0.03036, over 1419293.73 frames.], batch size: 23, lr: 2.42e-04
2022-05-15 19:59:20,967 INFO [train.py:812] (3/8) Epoch 32, batch 4100, loss[loss=0.167, simple_loss=0.2569, pruned_loss=0.03851, over 7193.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03064, over 1417525.48 frames.], batch size: 22, lr: 2.42e-04
2022-05-15 20:00:19,816 INFO [train.py:812] (3/8) Epoch 32, batch 4150, loss[loss=0.1491, simple_loss=0.237, pruned_loss=0.0306, over 7224.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2444, pruned_loss=0.03047, over 1420903.53 frames.], batch size: 21, lr: 2.42e-04
2022-05-15 20:01:19,551 INFO [train.py:812] (3/8) Epoch 32, batch 4200, loss[loss=0.1425, simple_loss=0.2335, pruned_loss=0.02573, over 7323.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2427, pruned_loss=0.03016, over 1419934.69 frames.], batch size: 20, lr: 2.42e-04
2022-05-15 20:02:17,845 INFO [train.py:812] (3/8) Epoch 32, batch 4250, loss[loss=0.1188, simple_loss=0.2034, pruned_loss=0.01714, over 7255.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2433, pruned_loss=0.03022, over 1418869.29 frames.], batch size: 19, lr: 2.42e-04
2022-05-15 20:03:17,421 INFO [train.py:812] (3/8) Epoch 32, batch 4300, loss[loss=0.1306, simple_loss=0.2177, pruned_loss=0.02178, over 7411.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2428, pruned_loss=0.02988, over 1418369.97 frames.], batch size: 18, lr: 2.42e-04
2022-05-15 20:04:16,082 INFO [train.py:812] (3/8) Epoch 32, batch 4350, loss[loss=0.1368, simple_loss=0.2316, pruned_loss=0.02105, over 7166.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.03006, over 1418296.14 frames.], batch size: 18, lr: 2.41e-04
2022-05-15 20:05:14,967 INFO [train.py:812] (3/8) Epoch 32, batch 4400, loss[loss=0.1586, simple_loss=0.2488, pruned_loss=0.03416, over 7354.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2436, pruned_loss=0.03042, over 1405054.96 frames.], batch size: 25, lr: 2.41e-04
2022-05-15 20:06:12,565 INFO [train.py:812] (3/8) Epoch 32, batch 4450, loss[loss=0.1313, simple_loss=0.2136, pruned_loss=0.02447, over 7239.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2446, pruned_loss=0.0309, over 1402864.20 frames.], batch size: 16, lr: 2.41e-04
2022-05-15 20:07:11,450 INFO [train.py:812] (3/8) Epoch 32, batch 4500, loss[loss=0.1607, simple_loss=0.2542, pruned_loss=0.03355, over 6917.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2447, pruned_loss=0.03101, over 1395687.03 frames.], batch size: 31, lr: 2.41e-04
2022-05-15 20:08:09,898 INFO [train.py:812] (3/8) Epoch 32, batch 4550, loss[loss=0.1692, simple_loss=0.2548, pruned_loss=0.04176, over 5276.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2443, pruned_loss=0.03136, over 1357340.76 frames.], batch size: 52, lr: 2.41e-04
2022-05-15 20:09:17,615 INFO [train.py:812] (3/8) Epoch 33, batch 0, loss[loss=0.145, simple_loss=0.2351, pruned_loss=0.02751, over 6808.00 frames.], tot_loss[loss=0.145, simple_loss=0.2351, pruned_loss=0.02751, over 6808.00 frames.], batch size: 31, lr: 2.38e-04
2022-05-15 20:10:15,653 INFO [train.py:812] (3/8) Epoch 33, batch 50, loss[loss=0.1398, simple_loss=0.236, pruned_loss=0.02178, over 5272.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2463, pruned_loss=0.02919, over 314604.74 frames.], batch size: 52, lr: 2.38e-04
2022-05-15 20:11:14,587 INFO [train.py:812] (3/8) Epoch 33, batch 100, loss[loss=0.1358, simple_loss=0.224, pruned_loss=0.02383, over 6242.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2457, pruned_loss=0.02987, over 559147.43 frames.], batch size: 37, lr: 2.38e-04
2022-05-15 20:12:13,173 INFO [train.py:812] (3/8) Epoch 33, batch 150, loss[loss=0.1738, simple_loss=0.2728, pruned_loss=0.03742, over 7219.00 frames.], tot_loss[loss=0.1533, simple_loss=0.247, pruned_loss=0.02978, over 751233.82 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:13:12,831 INFO [train.py:812] (3/8) Epoch 33, batch 200, loss[loss=0.1375, simple_loss=0.213, pruned_loss=0.03094, over 7002.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2454, pruned_loss=0.02989, over 893860.67 frames.], batch size: 16, lr: 2.37e-04
2022-05-15 20:14:10,194 INFO [train.py:812] (3/8) Epoch 33, batch 250, loss[loss=0.149, simple_loss=0.2555, pruned_loss=0.02124, over 7232.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2455, pruned_loss=0.03, over 1008740.05 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:15:08,982 INFO [train.py:812] (3/8) Epoch 33, batch 300, loss[loss=0.1627, simple_loss=0.2636, pruned_loss=0.03087, over 6929.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2472, pruned_loss=0.03103, over 1091911.52 frames.], batch size: 31, lr: 2.37e-04
2022-05-15 20:16:07,549 INFO [train.py:812] (3/8) Epoch 33, batch 350, loss[loss=0.1257, simple_loss=0.2124, pruned_loss=0.01947, over 7398.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2472, pruned_loss=0.03153, over 1162832.65 frames.], batch size: 18, lr: 2.37e-04
2022-05-15 20:17:07,043 INFO [train.py:812] (3/8) Epoch 33, batch 400, loss[loss=0.1493, simple_loss=0.2391, pruned_loss=0.0297, over 7423.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2453, pruned_loss=0.03077, over 1220170.06 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:18:06,481 INFO [train.py:812] (3/8) Epoch 33, batch 450, loss[loss=0.1537, simple_loss=0.2491, pruned_loss=0.02915, over 6804.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2449, pruned_loss=0.03064, over 1262714.79 frames.], batch size: 31, lr: 2.37e-04
2022-05-15 20:19:06,088 INFO [train.py:812] (3/8) Epoch 33, batch 500, loss[loss=0.1657, simple_loss=0.2518, pruned_loss=0.03987, over 7189.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03076, over 1300763.65 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:20:04,295 INFO [train.py:812] (3/8) Epoch 33, batch 550, loss[loss=0.1614, simple_loss=0.2463, pruned_loss=0.03824, over 7317.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2458, pruned_loss=0.03073, over 1329641.82 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:21:03,114 INFO [train.py:812] (3/8) Epoch 33, batch 600, loss[loss=0.1603, simple_loss=0.2534, pruned_loss=0.03362, over 7298.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2458, pruned_loss=0.0307, over 1347892.17 frames.], batch size: 24, lr: 2.37e-04
2022-05-15 20:22:00,731 INFO [train.py:812] (3/8) Epoch 33, batch 650, loss[loss=0.1574, simple_loss=0.2479, pruned_loss=0.03343, over 7167.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2461, pruned_loss=0.03055, over 1364675.19 frames.], batch size: 26, lr: 2.37e-04
2022-05-15 20:23:00,265 INFO [train.py:812] (3/8) Epoch 33, batch 700, loss[loss=0.1284, simple_loss=0.2123, pruned_loss=0.02229, over 7121.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2462, pruned_loss=0.03069, over 1375088.65 frames.], batch size: 17, lr: 2.37e-04
2022-05-15 20:23:58,666 INFO [train.py:812] (3/8) Epoch 33, batch 750, loss[loss=0.1364, simple_loss=0.2367, pruned_loss=0.01807, over 7206.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2451, pruned_loss=0.03025, over 1380671.88 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:24:57,941 INFO [train.py:812] (3/8) Epoch 33, batch 800, loss[loss=0.1331, simple_loss=0.2232, pruned_loss=0.02153, over 7424.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2439, pruned_loss=0.03013, over 1392656.65 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:25:55,910 INFO [train.py:812] (3/8) Epoch 33, batch 850, loss[loss=0.1636, simple_loss=0.2556, pruned_loss=0.03583, over 7366.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03, over 1399711.19 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:26:54,543 INFO [train.py:812] (3/8) Epoch 33, batch 900, loss[loss=0.1504, simple_loss=0.2388, pruned_loss=0.03101, over 7170.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02943, over 1409705.06 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:27:51,769 INFO [train.py:812] (3/8) Epoch 33, batch 950, loss[loss=0.1382, simple_loss=0.2334, pruned_loss=0.02147, over 7429.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02978, over 1413959.18 frames.], batch size: 20, lr: 2.37e-04
2022-05-15 20:28:51,356 INFO [train.py:812] (3/8) Epoch 33, batch 1000, loss[loss=0.1691, simple_loss=0.2659, pruned_loss=0.03618, over 7227.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02932, over 1413536.04 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:29:49,401 INFO [train.py:812] (3/8) Epoch 33, batch 1050, loss[loss=0.157, simple_loss=0.2476, pruned_loss=0.03326, over 7117.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02929, over 1412457.08 frames.], batch size: 28, lr: 2.37e-04
2022-05-15 20:30:48,565 INFO [train.py:812] (3/8) Epoch 33, batch 1100, loss[loss=0.1517, simple_loss=0.2493, pruned_loss=0.02705, over 7271.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02934, over 1417385.87 frames.], batch size: 24, lr: 2.37e-04
2022-05-15 20:31:47,035 INFO [train.py:812] (3/8) Epoch 33, batch 1150, loss[loss=0.1821, simple_loss=0.2814, pruned_loss=0.04141, over 7223.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02953, over 1418951.82 frames.], batch size: 23, lr: 2.37e-04
2022-05-15 20:32:51,443 INFO [train.py:812] (3/8) Epoch 33, batch 1200, loss[loss=0.1856, simple_loss=0.2758, pruned_loss=0.0477, over 7177.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02971, over 1421436.77 frames.], batch size: 26, lr: 2.37e-04
2022-05-15 20:33:50,514 INFO [train.py:812] (3/8) Epoch 33, batch 1250, loss[loss=0.1398, simple_loss=0.2423, pruned_loss=0.01867, over 6542.00 frames.], tot_loss[loss=0.1521, simple_loss=0.244, pruned_loss=0.03005, over 1420401.97 frames.], batch size: 38, lr: 2.37e-04
2022-05-15 20:34:50,219 INFO [train.py:812] (3/8) Epoch 33, batch 1300, loss[loss=0.1399, simple_loss=0.2411, pruned_loss=0.0194, over 7221.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2434, pruned_loss=0.02995, over 1421163.68 frames.], batch size: 21, lr: 2.37e-04
2022-05-15 20:35:49,534 INFO [train.py:812] (3/8) Epoch 33, batch 1350, loss[loss=0.1331, simple_loss=0.2057, pruned_loss=0.03018, over 7286.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.02996, over 1420763.64 frames.], batch size: 17, lr: 2.37e-04
2022-05-15 20:36:48,933 INFO [train.py:812] (3/8) Epoch 33, batch 1400, loss[loss=0.1555, simple_loss=0.2589, pruned_loss=0.02608, over 7142.00 frames.], tot_loss[loss=0.1514, simple_loss=0.243, pruned_loss=0.02994, over 1422309.34 frames.], batch size: 20, lr: 2.36e-04
2022-05-15 20:37:47,490 INFO [train.py:812] (3/8) Epoch 33, batch 1450, loss[loss=0.1443, simple_loss=0.2463, pruned_loss=0.02121, over 6690.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03001, over 1425343.76 frames.], batch size: 31, lr: 2.36e-04
2022-05-15 20:38:46,327 INFO [train.py:812] (3/8) Epoch 33, batch 1500, loss[loss=0.144, simple_loss=0.2377, pruned_loss=0.02511, over 5027.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2444, pruned_loss=0.03061, over 1422369.69 frames.], batch size: 52, lr: 2.36e-04
2022-05-15 20:39:44,946 INFO [train.py:812] (3/8) Epoch 33, batch 1550, loss[loss=0.1462, simple_loss=0.2401, pruned_loss=0.02611, over 7219.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2444, pruned_loss=0.03036, over 1419017.27 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:40:43,839 INFO [train.py:812] (3/8) Epoch 33, batch 1600, loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03184, over 7408.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2443, pruned_loss=0.03046, over 1420892.07 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:41:42,714 INFO [train.py:812] (3/8) Epoch 33, batch 1650, loss[loss=0.1452, simple_loss=0.2492, pruned_loss=0.02065, over 7219.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03008, over 1421824.72 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:42:41,756 INFO [train.py:812] (3/8) Epoch 33, batch 1700, loss[loss=0.1671, simple_loss=0.2645, pruned_loss=0.03481, over 7299.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02973, over 1423516.72 frames.], batch size: 24, lr: 2.36e-04
2022-05-15 20:43:40,824 INFO [train.py:812] (3/8) Epoch 33, batch 1750, loss[loss=0.1554, simple_loss=0.2538, pruned_loss=0.02851, over 6956.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2448, pruned_loss=0.03031, over 1416726.22 frames.], batch size: 28, lr: 2.36e-04
2022-05-15 20:44:40,008 INFO [train.py:812] (3/8) Epoch 33, batch 1800, loss[loss=0.1321, simple_loss=0.2214, pruned_loss=0.02141, over 7251.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2442, pruned_loss=0.03008, over 1420376.62 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:45:38,884 INFO [train.py:812] (3/8) Epoch 33, batch 1850, loss[loss=0.1518, simple_loss=0.2517, pruned_loss=0.02591, over 7309.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02974, over 1422766.47 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:46:37,358 INFO [train.py:812] (3/8) Epoch 33, batch 1900, loss[loss=0.1641, simple_loss=0.2584, pruned_loss=0.03485, over 7376.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02935, over 1425357.57 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 20:47:35,887 INFO [train.py:812] (3/8) Epoch 33, batch 1950, loss[loss=0.1516, simple_loss=0.2425, pruned_loss=0.03042, over 7273.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02965, over 1424119.53 frames.], batch size: 24, lr: 2.36e-04
2022-05-15 20:48:34,894 INFO [train.py:812] (3/8) Epoch 33, batch 2000, loss[loss=0.1483, simple_loss=0.2449, pruned_loss=0.02586, over 6407.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02997, over 1425163.67 frames.], batch size: 37, lr: 2.36e-04
2022-05-15 20:49:32,708 INFO [train.py:812] (3/8) Epoch 33, batch 2050, loss[loss=0.1371, simple_loss=0.2282, pruned_loss=0.02301, over 7166.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2426, pruned_loss=0.02945, over 1426019.26 frames.], batch size: 18, lr: 2.36e-04
2022-05-15 20:50:32,327 INFO [train.py:812] (3/8) Epoch 33, batch 2100, loss[loss=0.151, simple_loss=0.2428, pruned_loss=0.02954, over 7148.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02934, over 1427558.33 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:51:30,308 INFO [train.py:812] (3/8) Epoch 33, batch 2150, loss[loss=0.1285, simple_loss=0.2166, pruned_loss=0.02017, over 7413.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02959, over 1429253.12 frames.], batch size: 18, lr: 2.36e-04
2022-05-15 20:52:28,371 INFO [train.py:812] (3/8) Epoch 33, batch 2200, loss[loss=0.2264, simple_loss=0.3042, pruned_loss=0.07434, over 5250.00 frames.], tot_loss[loss=0.152, simple_loss=0.2437, pruned_loss=0.03017, over 1423239.60 frames.], batch size: 52, lr: 2.36e-04
2022-05-15 20:53:26,612 INFO [train.py:812] (3/8) Epoch 33, batch 2250, loss[loss=0.1815, simple_loss=0.2799, pruned_loss=0.04151, over 7222.00 frames.], tot_loss[loss=0.1526, simple_loss=0.244, pruned_loss=0.0306, over 1421401.41 frames.], batch size: 26, lr: 2.36e-04
2022-05-15 20:54:25,526 INFO [train.py:812] (3/8) Epoch 33, batch 2300, loss[loss=0.184, simple_loss=0.2679, pruned_loss=0.05004, over 7194.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2437, pruned_loss=0.03072, over 1419994.27 frames.], batch size: 22, lr: 2.36e-04
2022-05-15 20:55:24,363 INFO [train.py:812] (3/8) Epoch 33, batch 2350, loss[loss=0.1602, simple_loss=0.2458, pruned_loss=0.0373, over 6775.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2425, pruned_loss=0.03039, over 1422649.81 frames.], batch size: 15, lr: 2.36e-04
2022-05-15 20:56:22,964 INFO [train.py:812] (3/8) Epoch 33, batch 2400, loss[loss=0.1578, simple_loss=0.2555, pruned_loss=0.03007, over 7446.00 frames.], tot_loss[loss=0.151, simple_loss=0.2419, pruned_loss=0.03004, over 1424260.87 frames.], batch size: 20, lr: 2.36e-04
2022-05-15 20:57:40,446 INFO [train.py:812] (3/8) Epoch 33, batch 2450, loss[loss=0.1459, simple_loss=0.2356, pruned_loss=0.02811, over 7261.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2417, pruned_loss=0.02973, over 1427026.39 frames.], batch size: 19, lr: 2.36e-04
2022-05-15 20:58:40,019 INFO [train.py:812] (3/8) Epoch 33, batch 2500, loss[loss=0.1329, simple_loss=0.2313, pruned_loss=0.01728, over 7316.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2421, pruned_loss=0.02976, over 1428093.33 frames.], batch size: 21, lr: 2.36e-04
2022-05-15 20:59:48,289 INFO [train.py:812] (3/8) Epoch 33, batch 2550, loss[loss=0.1449, simple_loss=0.2387, pruned_loss=0.02558, over 7368.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2415, pruned_loss=0.02962, over 1427336.68 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 21:00:46,754 INFO [train.py:812] (3/8) Epoch 33, batch 2600, loss[loss=0.1676, simple_loss=0.2634, pruned_loss=0.03593, over 7205.00 frames.], tot_loss[loss=0.1506, simple_loss=0.242, pruned_loss=0.02962, over 1427450.63 frames.], batch size: 23, lr: 2.36e-04
2022-05-15 21:01:44,981 INFO [train.py:812] (3/8) Epoch 33, batch 2650, loss[loss=0.1686, simple_loss=0.2427, pruned_loss=0.04723, over 7215.00 frames.], tot_loss[loss=0.151, simple_loss=0.2427, pruned_loss=0.02971, over 1423515.32 frames.], batch size: 16, lr: 2.35e-04
2022-05-15 21:02:52,794 INFO [train.py:812] (3/8) Epoch 33, batch 2700, loss[loss=0.1427, simple_loss=0.2343, pruned_loss=0.0256, over 7423.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2432, pruned_loss=0.02989, over 1425453.23 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:04:10,613 INFO [train.py:812] (3/8) Epoch 33, batch 2750, loss[loss=0.1206, simple_loss=0.2014, pruned_loss=0.0199, over 7278.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.03004, over 1426383.81 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:05:09,532 INFO [train.py:812] (3/8) Epoch 33, batch 2800, loss[loss=0.1623, simple_loss=0.2588, pruned_loss=0.0329, over 7207.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02982, over 1425565.77 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:06:07,217 INFO [train.py:812] (3/8) Epoch 33, batch 2850, loss[loss=0.1642, simple_loss=0.2667, pruned_loss=0.03087, over 7331.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02995, over 1427225.23 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:07:06,431 INFO [train.py:812] (3/8) Epoch 33, batch 2900, loss[loss=0.1453, simple_loss=0.2468, pruned_loss=0.02193, over 7286.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.03008, over 1425992.05 frames.], batch size: 25, lr: 2.35e-04
2022-05-15 21:08:04,491 INFO [train.py:812] (3/8) Epoch 33, batch 2950, loss[loss=0.1473, simple_loss=0.2359, pruned_loss=0.02934, over 7433.00 frames.], tot_loss[loss=0.152, simple_loss=0.2445, pruned_loss=0.02971, over 1428586.76 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:09:12,202 INFO [train.py:812] (3/8) Epoch 33, batch 3000, loss[loss=0.1476, simple_loss=0.2313, pruned_loss=0.03197, over 7062.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02998, over 1427080.05 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:09:12,203 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 21:09:19,691 INFO [train.py:841] (3/8) Epoch 33, validation: loss=0.1535, simple_loss=0.2493, pruned_loss=0.02886, over 698248.00 frames.
2022-05-15 21:10:18,083 INFO [train.py:812] (3/8) Epoch 33, batch 3050, loss[loss=0.1507, simple_loss=0.244, pruned_loss=0.02867, over 6556.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2435, pruned_loss=0.02994, over 1423343.68 frames.], batch size: 38, lr: 2.35e-04
2022-05-15 21:11:15,941 INFO [train.py:812] (3/8) Epoch 33, batch 3100, loss[loss=0.1489, simple_loss=0.2542, pruned_loss=0.02185, over 7360.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2427, pruned_loss=0.02953, over 1423527.99 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:12:14,886 INFO [train.py:812] (3/8) Epoch 33, batch 3150, loss[loss=0.1418, simple_loss=0.2334, pruned_loss=0.02512, over 7070.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2429, pruned_loss=0.02998, over 1421771.96 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:13:13,033 INFO [train.py:812] (3/8) Epoch 33, batch 3200, loss[loss=0.1306, simple_loss=0.2111, pruned_loss=0.02504, over 7184.00 frames.], tot_loss[loss=0.1516, simple_loss=0.243, pruned_loss=0.03006, over 1421751.88 frames.], batch size: 16, lr: 2.35e-04
2022-05-15 21:14:11,775 INFO [train.py:812] (3/8) Epoch 33, batch 3250, loss[loss=0.1335, simple_loss=0.2237, pruned_loss=0.02164, over 7268.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2428, pruned_loss=0.03009, over 1419412.70 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:15:11,681 INFO [train.py:812] (3/8) Epoch 33, batch 3300, loss[loss=0.1393, simple_loss=0.2366, pruned_loss=0.02097, over 7226.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2415, pruned_loss=0.02965, over 1424171.57 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:16:10,456 INFO [train.py:812] (3/8) Epoch 33, batch 3350, loss[loss=0.1507, simple_loss=0.2454, pruned_loss=0.02802, over 7319.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2416, pruned_loss=0.02926, over 1428080.44 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:17:10,016 INFO [train.py:812] (3/8) Epoch 33, batch 3400, loss[loss=0.1309, simple_loss=0.2181, pruned_loss=0.02182, over 7276.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02946, over 1427974.01 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:18:09,753 INFO [train.py:812] (3/8) Epoch 33, batch 3450, loss[loss=0.1476, simple_loss=0.246, pruned_loss=0.0246, over 7329.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02964, over 1432277.31 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:19:07,578 INFO [train.py:812] (3/8) Epoch 33, batch 3500, loss[loss=0.1711, simple_loss=0.2593, pruned_loss=0.04139, over 7389.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03001, over 1428799.34 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:20:05,730 INFO [train.py:812] (3/8) Epoch 33, batch 3550, loss[loss=0.151, simple_loss=0.2371, pruned_loss=0.03246, over 7416.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02983, over 1427264.86 frames.], batch size: 18, lr: 2.35e-04
2022-05-15 21:21:04,475 INFO [train.py:812] (3/8) Epoch 33, batch 3600, loss[loss=0.139, simple_loss=0.2368, pruned_loss=0.02054, over 7332.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03011, over 1423033.14 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:22:03,600 INFO [train.py:812] (3/8) Epoch 33, batch 3650, loss[loss=0.1686, simple_loss=0.2504, pruned_loss=0.04341, over 7333.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2436, pruned_loss=0.02997, over 1422646.83 frames.], batch size: 20, lr: 2.35e-04
2022-05-15 21:23:02,533 INFO [train.py:812] (3/8) Epoch 33, batch 3700, loss[loss=0.1468, simple_loss=0.2341, pruned_loss=0.02973, over 7282.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02978, over 1426123.51 frames.], batch size: 17, lr: 2.35e-04
2022-05-15 21:24:01,169 INFO [train.py:812] (3/8) Epoch 33, batch 3750, loss[loss=0.1756, simple_loss=0.2648, pruned_loss=0.04318, over 7222.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.02971, over 1426797.59 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:25:00,735 INFO [train.py:812] (3/8) Epoch 33, batch 3800, loss[loss=0.1618, simple_loss=0.2598, pruned_loss=0.03188, over 7208.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2424, pruned_loss=0.02995, over 1427478.37 frames.], batch size: 23, lr: 2.35e-04
2022-05-15 21:25:58,521 INFO [train.py:812] (3/8) Epoch 33, batch 3850, loss[loss=0.1675, simple_loss=0.2669, pruned_loss=0.03407, over 7324.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02996, over 1428275.31 frames.], batch size: 21, lr: 2.35e-04
2022-05-15 21:26:57,084 INFO [train.py:812] (3/8) Epoch 33, batch 3900, loss[loss=0.142, simple_loss=0.2216, pruned_loss=0.03123, over 6817.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.0299, over 1428517.88 frames.], batch size: 15, lr: 2.35e-04
2022-05-15 21:27:55,699 INFO [train.py:812] (3/8) Epoch 33, batch 3950, loss[loss=0.1478, simple_loss=0.2286, pruned_loss=0.03347, over 7412.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2453, pruned_loss=0.03069, over 1431378.23 frames.], batch size: 18, lr: 2.34e-04
2022-05-15 21:28:55,471 INFO [train.py:812] (3/8) Epoch 33, batch 4000, loss[loss=0.1556, simple_loss=0.2495, pruned_loss=0.03088, over 6324.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2439, pruned_loss=0.03028, over 1430887.82 frames.], batch size: 37, lr: 2.34e-04
2022-05-15 21:29:54,335 INFO [train.py:812] (3/8) Epoch 33, batch 4050, loss[loss=0.1304, simple_loss=0.2169, pruned_loss=0.02195, over 7278.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2437, pruned_loss=0.03007, over 1427406.60 frames.], batch size: 18, lr: 2.34e-04
2022-05-15 21:30:52,684 INFO [train.py:812] (3/8) Epoch 33, batch 4100, loss[loss=0.1358, simple_loss=0.2349, pruned_loss=0.01834, over 7138.00 frames.], tot_loss[loss=0.152, simple_loss=0.2435, pruned_loss=0.03023, over 1421007.53 frames.], batch size: 26, lr: 2.34e-04
2022-05-15 21:31:50,613 INFO [train.py:812] (3/8) Epoch 33, batch 4150, loss[loss=0.1462, simple_loss=0.224, pruned_loss=0.03427, over 6828.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.02995, over 1420960.87 frames.], batch size: 15, lr: 2.34e-04
2022-05-15 21:32:49,106 INFO [train.py:812] (3/8) Epoch 33, batch 4200, loss[loss=0.1633, simple_loss=0.2578, pruned_loss=0.03444, over 7259.00 frames.], tot_loss[loss=0.151, simple_loss=0.2429, pruned_loss=0.0296, over 1418595.84 frames.], batch size: 19, lr: 2.34e-04
2022-05-15 21:33:48,263 INFO [train.py:812] (3/8) Epoch 33, batch 4250, loss[loss=0.1414, simple_loss=0.2343, pruned_loss=0.02428, over 7423.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.0292, over 1420008.19 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:34:46,553 INFO [train.py:812] (3/8) Epoch 33, batch 4300, loss[loss=0.1546, simple_loss=0.2494, pruned_loss=0.02995, over 6722.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02915, over 1418717.64 frames.], batch size: 31, lr: 2.34e-04
2022-05-15 21:35:44,808 INFO [train.py:812] (3/8) Epoch 33, batch 4350, loss[loss=0.1367, simple_loss=0.2374, pruned_loss=0.018, over 7224.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02948, over 1414632.29 frames.], batch size: 21, lr: 2.34e-04
2022-05-15 21:36:43,619 INFO [train.py:812] (3/8) Epoch 33, batch 4400, loss[loss=0.1459, simple_loss=0.2459, pruned_loss=0.02301, over 7142.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02927, over 1413886.70 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:37:42,030 INFO [train.py:812] (3/8) Epoch 33, batch 4450, loss[loss=0.148, simple_loss=0.2411, pruned_loss=0.02749, over 7322.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02932, over 1406141.10 frames.], batch size: 22, lr: 2.34e-04
2022-05-15 21:38:41,152 INFO [train.py:812] (3/8) Epoch 33, batch 4500, loss[loss=0.1477, simple_loss=0.2411, pruned_loss=0.02718, over 7147.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02914, over 1396594.52 frames.], batch size: 20, lr: 2.34e-04
2022-05-15 21:39:39,859 INFO [train.py:812] (3/8) Epoch 33, batch 4550, loss[loss=0.1671, simple_loss=0.252, pruned_loss=0.04111, over 4859.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2445, pruned_loss=0.02999, over 1373994.71 frames.], batch size: 52, lr: 2.34e-04
2022-05-15 21:40:52,122 INFO [train.py:812] (3/8) Epoch 34, batch 0, loss[loss=0.1495, simple_loss=0.2437, pruned_loss=0.02767, over 7436.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2437, pruned_loss=0.02767, over 7436.00 frames.], batch size: 20, lr: 2.31e-04
2022-05-15 21:41:51,397 INFO [train.py:812] (3/8) Epoch 34, batch 50, loss[loss=0.1544, simple_loss=0.2605, pruned_loss=0.02418, over 7077.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2425, pruned_loss=0.02943, over 324499.02 frames.], batch size: 28, lr: 2.30e-04
2022-05-15 21:42:51,066 INFO [train.py:812] (3/8) Epoch 34, batch 100, loss[loss=0.1753, simple_loss=0.2814, pruned_loss=0.03466, over 7106.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2444, pruned_loss=0.02951, over 565487.94 frames.], batch size: 21, lr: 2.30e-04
2022-05-15 21:43:50,309 INFO [train.py:812] (3/8) Epoch 34, batch 150, loss[loss=0.1269, simple_loss=0.215, pruned_loss=0.01938, over 7055.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02901, over 755519.82 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:44:49,637 INFO [train.py:812] (3/8) Epoch 34, batch 200, loss[loss=0.1446, simple_loss=0.2241, pruned_loss=0.03252, over 7250.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02933, over 906248.30 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:45:48,787 INFO [train.py:812] (3/8) Epoch 34, batch 250, loss[loss=0.1912, simple_loss=0.2736, pruned_loss=0.05438, over 5147.00 frames.], tot_loss[loss=0.1504, simple_loss=0.242, pruned_loss=0.02941, over 1013330.07 frames.], batch size: 53, lr: 2.30e-04
2022-05-15 21:46:48,755 INFO [train.py:812] (3/8) Epoch 34, batch 300, loss[loss=0.1646, simple_loss=0.2512, pruned_loss=0.03898, over 7390.00 frames.], tot_loss[loss=0.15, simple_loss=0.2417, pruned_loss=0.02912, over 1103297.29 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 21:47:46,306 INFO [train.py:812] (3/8) Epoch 34, batch 350, loss[loss=0.1252, simple_loss=0.2097, pruned_loss=0.02037, over 7150.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2432, pruned_loss=0.02951, over 1168529.39 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:48:46,227 INFO [train.py:812] (3/8) Epoch 34, batch 400, loss[loss=0.1603, simple_loss=0.2626, pruned_loss=0.02897, over 7404.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.0295, over 1229032.79 frames.], batch size: 21, lr: 2.30e-04
2022-05-15 21:49:44,740 INFO [train.py:812] (3/8) Epoch 34, batch 450, loss[loss=0.1392, simple_loss=0.2217, pruned_loss=0.02839, over 7423.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02973, over 1273903.45 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:50:44,149 INFO [train.py:812] (3/8) Epoch 34, batch 500, loss[loss=0.1477, simple_loss=0.2532, pruned_loss=0.02109, over 7310.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2432, pruned_loss=0.02999, over 1307309.63 frames.], batch size: 24, lr: 2.30e-04
2022-05-15 21:51:42,495 INFO [train.py:812] (3/8) Epoch 34, batch 550, loss[loss=0.1659, simple_loss=0.2662, pruned_loss=0.03284, over 6468.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02956, over 1331424.37 frames.], batch size: 38, lr: 2.30e-04
2022-05-15 21:52:57,370 INFO [train.py:812] (3/8) Epoch 34, batch 600, loss[loss=0.1652, simple_loss=0.2563, pruned_loss=0.03701, over 7297.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02934, over 1353004.77 frames.], batch size: 25, lr: 2.30e-04
2022-05-15 21:53:56,005 INFO [train.py:812] (3/8) Epoch 34, batch 650, loss[loss=0.1538, simple_loss=0.2415, pruned_loss=0.03308, over 7163.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2435, pruned_loss=0.02938, over 1371227.19 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:54:54,867 INFO [train.py:812] (3/8) Epoch 34, batch 700, loss[loss=0.1323, simple_loss=0.214, pruned_loss=0.02524, over 7117.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.0291, over 1378541.49 frames.], batch size: 17, lr: 2.30e-04
2022-05-15 21:55:51,391 INFO [train.py:812] (3/8) Epoch 34, batch 750, loss[loss=0.1812, simple_loss=0.2708, pruned_loss=0.04579, over 7204.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02938, over 1390252.52 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 21:56:50,459 INFO [train.py:812] (3/8) Epoch 34, batch 800, loss[loss=0.1508, simple_loss=0.2342, pruned_loss=0.03365, over 7272.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02978, over 1395514.32 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 21:57:49,840 INFO [train.py:812] (3/8) Epoch 34, batch 850, loss[loss=0.1507, simple_loss=0.2512, pruned_loss=0.02506, over 6414.00 frames.], tot_loss[loss=0.152, simple_loss=0.2443, pruned_loss=0.02987, over 1404332.64 frames.], batch size: 37, lr: 2.30e-04
2022-05-15 21:58:48,159 INFO [train.py:812] (3/8) Epoch 34, batch 900, loss[loss=0.1594, simple_loss=0.2447, pruned_loss=0.03703, over 4980.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2433, pruned_loss=0.03, over 1409172.79 frames.], batch size: 53, lr: 2.30e-04
2022-05-15 21:59:45,336 INFO [train.py:812] (3/8) Epoch 34, batch 950, loss[loss=0.1411, simple_loss=0.2344, pruned_loss=0.02389, over 7274.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2429, pruned_loss=0.03011, over 1407957.69 frames.], batch size: 18, lr: 2.30e-04
2022-05-15 22:00:43,723 INFO [train.py:812] (3/8) Epoch 34, batch 1000, loss[loss=0.1416, simple_loss=0.2362, pruned_loss=0.02348, over 7426.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2425, pruned_loss=0.02986, over 1409108.20 frames.], batch size: 20, lr: 2.30e-04
2022-05-15 22:01:41,767 INFO [train.py:812] (3/8) Epoch 34, batch 1050, loss[loss=0.1259, simple_loss=0.2313, pruned_loss=0.01021, over 7169.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02965, over 1415030.16 frames.], batch size: 19, lr: 2.30e-04
2022-05-15 22:02:40,794 INFO [train.py:812] (3/8) Epoch 34, batch 1100, loss[loss=0.177, simple_loss=0.2608, pruned_loss=0.04662, over 6354.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2431, pruned_loss=0.02972, over 1413162.76 frames.], batch size: 38, lr: 2.30e-04
2022-05-15 22:03:39,416 INFO [train.py:812] (3/8) Epoch 34, batch 1150, loss[loss=0.1567, simple_loss=0.2491, pruned_loss=0.03214, over 7437.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02959, over 1416372.32 frames.], batch size: 20, lr: 2.30e-04
2022-05-15 22:04:38,157 INFO [train.py:812] (3/8) Epoch 34, batch 1200, loss[loss=0.1842, simple_loss=0.2709, pruned_loss=0.04869, over 7191.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2429, pruned_loss=0.02974, over 1420235.43 frames.], batch size: 23, lr: 2.30e-04
2022-05-15 22:05:35,683 INFO [train.py:812] (3/8) Epoch 34, batch 1250, loss[loss=0.1429, simple_loss=0.2392, pruned_loss=0.02328, over 7336.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2435, pruned_loss=0.03006, over 1417082.18 frames.], batch size: 22, lr: 2.30e-04
2022-05-15 22:06:34,731 INFO [train.py:812] (3/8) Epoch 34, batch 1300, loss[loss=0.1683, simple_loss=0.2622, pruned_loss=0.0372, over 7182.00 frames.], tot_loss[loss=0.1514, simple_loss=0.243, pruned_loss=0.02987, over 1417638.24 frames.], batch size: 26, lr: 2.30e-04
2022-05-15 22:07:33,173 INFO [train.py:812] (3/8) Epoch 34, batch 1350, loss[loss=0.1373, simple_loss=0.2387, pruned_loss=0.01791, over 7217.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02962, over 1418651.07 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:08:32,150 INFO [train.py:812] (3/8) Epoch 34, batch 1400, loss[loss=0.1423, simple_loss=0.2387, pruned_loss=0.02299, over 7261.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2426, pruned_loss=0.02953, over 1421570.31 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:09:31,077 INFO [train.py:812] (3/8) Epoch 34, batch 1450, loss[loss=0.1744, simple_loss=0.2774, pruned_loss=0.03575, over 7415.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02944, over 1425622.51 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:10:29,323 INFO [train.py:812] (3/8) Epoch 34, batch 1500, loss[loss=0.1679, simple_loss=0.2572, pruned_loss=0.03936, over 7373.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2432, pruned_loss=0.02969, over 1423894.07 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:11:28,517 INFO [train.py:812] (3/8) Epoch 34, batch 1550, loss[loss=0.1643, simple_loss=0.2589, pruned_loss=0.03482, over 7310.00 frames.], tot_loss[loss=0.152, simple_loss=0.2438, pruned_loss=0.03009, over 1420992.99 frames.], batch size: 24, lr: 2.29e-04
2022-05-15 22:12:27,926 INFO [train.py:812] (3/8) Epoch 34, batch 1600, loss[loss=0.1471, simple_loss=0.2378, pruned_loss=0.02813, over 7328.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2433, pruned_loss=0.02984, over 1422340.23 frames.], batch size: 20, lr: 2.29e-04
2022-05-15 22:13:26,007 INFO [train.py:812] (3/8) Epoch 34, batch 1650, loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03022, over 7198.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.02996, over 1421959.24 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:14:25,177 INFO [train.py:812] (3/8) Epoch 34, batch 1700, loss[loss=0.1742, simple_loss=0.2658, pruned_loss=0.04129, over 7385.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2443, pruned_loss=0.02971, over 1425981.29 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:15:24,020 INFO [train.py:812] (3/8) Epoch 34, batch 1750, loss[loss=0.1486, simple_loss=0.2391, pruned_loss=0.02904, over 7054.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02983, over 1421511.13 frames.], batch size: 28, lr: 2.29e-04
2022-05-15 22:16:22,617 INFO [train.py:812] (3/8) Epoch 34, batch 1800, loss[loss=0.1328, simple_loss=0.2176, pruned_loss=0.02395, over 7266.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02963, over 1423259.85 frames.], batch size: 17, lr: 2.29e-04
2022-05-15 22:17:21,598 INFO [train.py:812] (3/8) Epoch 34, batch 1850, loss[loss=0.1524, simple_loss=0.2518, pruned_loss=0.02648, over 7310.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02926, over 1416106.03 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:18:20,748 INFO [train.py:812] (3/8) Epoch 34, batch 1900, loss[loss=0.1386, simple_loss=0.2367, pruned_loss=0.02023, over 6752.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02914, over 1410572.99 frames.], batch size: 31, lr: 2.29e-04
2022-05-15 22:19:17,928 INFO [train.py:812] (3/8) Epoch 34, batch 1950, loss[loss=0.1456, simple_loss=0.2298, pruned_loss=0.03072, over 7004.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02912, over 1416267.36 frames.], batch size: 16, lr: 2.29e-04
2022-05-15 22:20:16,770 INFO [train.py:812] (3/8) Epoch 34, batch 2000, loss[loss=0.1412, simple_loss=0.2251, pruned_loss=0.02868, over 7418.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.0293, over 1421975.00 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:21:15,731 INFO [train.py:812] (3/8) Epoch 34, batch 2050, loss[loss=0.1716, simple_loss=0.2602, pruned_loss=0.0415, over 7122.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02938, over 1421068.62 frames.], batch size: 26, lr: 2.29e-04
2022-05-15 22:22:14,731 INFO [train.py:812] (3/8) Epoch 34, batch 2100, loss[loss=0.1763, simple_loss=0.2695, pruned_loss=0.04159, over 7202.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02922, over 1423794.39 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:23:12,297 INFO [train.py:812] (3/8) Epoch 34, batch 2150, loss[loss=0.1666, simple_loss=0.2625, pruned_loss=0.03534, over 7297.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02905, over 1423446.97 frames.], batch size: 24, lr: 2.29e-04
2022-05-15 22:24:11,546 INFO [train.py:812] (3/8) Epoch 34, batch 2200, loss[loss=0.16, simple_loss=0.2566, pruned_loss=0.03167, over 7314.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02947, over 1426020.69 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:25:10,887 INFO [train.py:812] (3/8) Epoch 34, batch 2250, loss[loss=0.1397, simple_loss=0.2261, pruned_loss=0.02664, over 7278.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02945, over 1423225.25 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:26:09,577 INFO [train.py:812] (3/8) Epoch 34, batch 2300, loss[loss=0.1372, simple_loss=0.2207, pruned_loss=0.02685, over 7159.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2436, pruned_loss=0.02927, over 1424619.20 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:27:07,995 INFO [train.py:812] (3/8) Epoch 34, batch 2350, loss[loss=0.1385, simple_loss=0.2348, pruned_loss=0.02111, over 7173.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02894, over 1426297.95 frames.], batch size: 19, lr: 2.29e-04
2022-05-15 22:28:06,478 INFO [train.py:812] (3/8) Epoch 34, batch 2400, loss[loss=0.1648, simple_loss=0.2511, pruned_loss=0.03926, over 7386.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2418, pruned_loss=0.02885, over 1427055.01 frames.], batch size: 23, lr: 2.29e-04
2022-05-15 22:29:04,718 INFO [train.py:812] (3/8) Epoch 34, batch 2450, loss[loss=0.1612, simple_loss=0.2602, pruned_loss=0.0311, over 7218.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02916, over 1421050.53 frames.], batch size: 21, lr: 2.29e-04
2022-05-15 22:30:04,436 INFO [train.py:812] (3/8) Epoch 34, batch 2500, loss[loss=0.1328, simple_loss=0.2132, pruned_loss=0.02621, over 6998.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02921, over 1418831.79 frames.], batch size: 16, lr: 2.29e-04
2022-05-15 22:31:02,341 INFO [train.py:812] (3/8) Epoch 34, batch 2550, loss[loss=0.1544, simple_loss=0.249, pruned_loss=0.02988, over 7337.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02928, over 1420915.27 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:32:00,055 INFO [train.py:812] (3/8) Epoch 34, batch 2600, loss[loss=0.1416, simple_loss=0.2308, pruned_loss=0.02622, over 7083.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02951, over 1420373.07 frames.], batch size: 18, lr: 2.29e-04
2022-05-15 22:32:58,085 INFO [train.py:812] (3/8) Epoch 34, batch 2650, loss[loss=0.1379, simple_loss=0.2328, pruned_loss=0.02154, over 7346.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.02928, over 1421504.28 frames.], batch size: 22, lr: 2.29e-04
2022-05-15 22:33:56,974 INFO [train.py:812] (3/8) Epoch 34, batch 2700, loss[loss=0.1359, simple_loss=0.2227, pruned_loss=0.02454, over 7265.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02938, over 1426076.43 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 22:34:55,309 INFO [train.py:812] (3/8) Epoch 34, batch 2750, loss[loss=0.1437, simple_loss=0.2357, pruned_loss=0.02586, over 7320.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2428, pruned_loss=0.02971, over 1424197.69 frames.], batch size: 21, lr: 2.28e-04
2022-05-15 22:35:54,057 INFO [train.py:812] (3/8) Epoch 34, batch 2800, loss[loss=0.1284, simple_loss=0.2151, pruned_loss=0.0209, over 7400.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02969, over 1429463.51 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 22:36:52,780 INFO [train.py:812] (3/8) Epoch 34, batch 2850, loss[loss=0.1521, simple_loss=0.2462, pruned_loss=0.02901, over 7195.00 frames.], tot_loss[loss=0.152, simple_loss=0.2441, pruned_loss=0.02993, over 1430941.74 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:37:50,504 INFO [train.py:812] (3/8) Epoch 34, batch 2900, loss[loss=0.154, simple_loss=0.2383, pruned_loss=0.03489, over 7143.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2435, pruned_loss=0.0296, over 1427289.12 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:38:49,627 INFO [train.py:812] (3/8) Epoch 34, batch 2950, loss[loss=0.1547, simple_loss=0.2508, pruned_loss=0.02925, over 7147.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.02962, over 1427308.39 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:39:49,324 INFO [train.py:812] (3/8) Epoch 34, batch 3000, loss[loss=0.1286, simple_loss=0.2193, pruned_loss=0.01895, over 7351.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2434, pruned_loss=0.02975, over 1428013.34 frames.], batch size: 19, lr: 2.28e-04
2022-05-15 22:39:49,325 INFO [train.py:832] (3/8) Computing validation loss
2022-05-15 22:39:56,835 INFO [train.py:841] (3/8) Epoch 34, validation: loss=0.1534, simple_loss=0.2492, pruned_loss=0.02878, over 698248.00 frames.
2022-05-15 22:40:55,231 INFO [train.py:812] (3/8) Epoch 34, batch 3050, loss[loss=0.1565, simple_loss=0.2562, pruned_loss=0.02842, over 7358.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02992, over 1428036.30 frames.], batch size: 19, lr: 2.28e-04
2022-05-15 22:41:53,721 INFO [train.py:812] (3/8) Epoch 34, batch 3100, loss[loss=0.1389, simple_loss=0.2243, pruned_loss=0.02671, over 6806.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.0297, over 1428802.01 frames.], batch size: 15, lr: 2.28e-04
2022-05-15 22:42:52,703 INFO [train.py:812] (3/8) Epoch 34, batch 3150, loss[loss=0.1264, simple_loss=0.212, pruned_loss=0.02044, over 7280.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02971, over 1428146.47 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:43:51,472 INFO [train.py:812] (3/8) Epoch 34, batch 3200, loss[loss=0.1738, simple_loss=0.2661, pruned_loss=0.04081, over 4774.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2427, pruned_loss=0.02979, over 1423628.79 frames.], batch size: 52, lr: 2.28e-04
2022-05-15 22:44:49,451 INFO [train.py:812] (3/8) Epoch 34, batch 3250, loss[loss=0.1571, simple_loss=0.2364, pruned_loss=0.03887, over 7131.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02936, over 1421093.31 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:45:48,017 INFO [train.py:812] (3/8) Epoch 34, batch 3300, loss[loss=0.1854, simple_loss=0.2733, pruned_loss=0.04876, over 7104.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2427, pruned_loss=0.02991, over 1417799.06 frames.], batch size: 28, lr: 2.28e-04
2022-05-15 22:46:47,343 INFO [train.py:812] (3/8) Epoch 34, batch 3350, loss[loss=0.1385, simple_loss=0.2352, pruned_loss=0.02089, over 7145.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2416, pruned_loss=0.02949, over 1420557.36 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:47:45,296 INFO [train.py:812] (3/8) Epoch 34, batch 3400, loss[loss=0.1635, simple_loss=0.2512, pruned_loss=0.03792, over 7206.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2418, pruned_loss=0.02968, over 1421595.46 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:48:43,925 INFO [train.py:812] (3/8) Epoch 34, batch 3450, loss[loss=0.1489, simple_loss=0.236, pruned_loss=0.03088, over 7000.00 frames.], tot_loss[loss=0.151, simple_loss=0.2425, pruned_loss=0.02973, over 1427258.71 frames.], batch size: 16, lr: 2.28e-04
2022-05-15 22:49:41,429 INFO [train.py:812] (3/8) Epoch 34, batch 3500, loss[loss=0.1591, simple_loss=0.2581, pruned_loss=0.03005, over 7198.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.0296, over 1429052.40 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:50:38,736 INFO [train.py:812] (3/8) Epoch 34, batch 3550, loss[loss=0.1192, simple_loss=0.2054, pruned_loss=0.01651, over 7276.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02903, over 1431002.53 frames.], batch size: 17, lr: 2.28e-04
2022-05-15 22:51:37,871 INFO [train.py:812] (3/8) Epoch 34, batch 3600, loss[loss=0.1527, simple_loss=0.2554, pruned_loss=0.02504, over 7320.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2423, pruned_loss=0.02913, over 1432512.74 frames.], batch size: 21, lr: 2.28e-04
2022-05-15 22:52:35,094 INFO [train.py:812] (3/8) Epoch 34, batch 3650, loss[loss=0.1634, simple_loss=0.2623, pruned_loss=0.03227, over 6418.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02942, over 1427365.81 frames.], batch size: 38, lr: 2.28e-04
2022-05-15 22:53:34,811 INFO [train.py:812] (3/8) Epoch 34, batch 3700, loss[loss=0.1417, simple_loss=0.2338, pruned_loss=0.02483, over 7241.00 frames.], tot_loss[loss=0.15, simple_loss=0.2414, pruned_loss=0.0293, over 1423014.05 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:54:33,352 INFO [train.py:812] (3/8) Epoch 34, batch 3750, loss[loss=0.1604, simple_loss=0.2535, pruned_loss=0.0337, over 7278.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2415, pruned_loss=0.02936, over 1420463.69 frames.], batch size: 24, lr: 2.28e-04
2022-05-15 22:55:32,404 INFO [train.py:812] (3/8) Epoch 34, batch 3800, loss[loss=0.1583, simple_loss=0.2529, pruned_loss=0.0319, over 7142.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02895, over 1424895.05 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:56:31,647 INFO [train.py:812] (3/8) Epoch 34, batch 3850, loss[loss=0.1679, simple_loss=0.2587, pruned_loss=0.03859, over 7220.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.02886, over 1427445.03 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:57:28,731 INFO [train.py:812] (3/8) Epoch 34, batch 3900, loss[loss=0.1604, simple_loss=0.2586, pruned_loss=0.0311, over 7198.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.02924, over 1425365.19 frames.], batch size: 23, lr: 2.28e-04
2022-05-15 22:58:46,461 INFO [train.py:812] (3/8) Epoch 34, batch 3950, loss[loss=0.1459, simple_loss=0.2458, pruned_loss=0.02299, over 7326.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02884, over 1422624.54 frames.], batch size: 20, lr: 2.28e-04
2022-05-15 22:59:45,595 INFO [train.py:812] (3/8) Epoch 34, batch 4000, loss[loss=0.1461, simple_loss=0.234, pruned_loss=0.02915, over 7075.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02914, over 1423098.46 frames.], batch size: 18, lr: 2.28e-04
2022-05-15 23:00:53,164 INFO [train.py:812] (3/8) Epoch 34, batch 4050, loss[loss=0.1555, simple_loss=0.251, pruned_loss=0.03002, over 7205.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2433, pruned_loss=0.02941, over 1417280.04 frames.], batch size: 26, lr: 2.27e-04
2022-05-15 23:01:51,474 INFO [train.py:812] (3/8) Epoch 34, batch 4100, loss[loss=0.1919, simple_loss=0.2777, pruned_loss=0.05302, over 6342.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2435, pruned_loss=0.02972, over 1417799.14 frames.], batch size: 37, lr: 2.27e-04
2022-05-15 23:02:49,333 INFO [train.py:812] (3/8) Epoch 34, batch 4150, loss[loss=0.1401, simple_loss=0.2314, pruned_loss=0.02441, over 7404.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2436, pruned_loss=0.03013, over 1417525.86 frames.], batch size: 18, lr: 2.27e-04
2022-05-15 23:03:57,823 INFO [train.py:812] (3/8) Epoch 34, batch 4200, loss[loss=0.1502, simple_loss=0.2412, pruned_loss=0.02955, over 7234.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02947, over 1419982.01 frames.], batch size: 20, lr: 2.27e-04
2022-05-15 23:05:06,366 INFO [train.py:812] (3/8) Epoch 34, batch 4250, loss[loss=0.1434, simple_loss=0.2197, pruned_loss=0.03359, over 7146.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2438, pruned_loss=0.02968, over 1420065.98 frames.], batch size: 17, lr: 2.27e-04
2022-05-15 23:06:05,057 INFO [train.py:812] (3/8) Epoch 34, batch 4300, loss[loss=0.14, simple_loss=0.22, pruned_loss=0.02998, over 6990.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2449, pruned_loss=0.03013, over 1420887.39 frames.], batch size: 16, lr: 2.27e-04
2022-05-15 23:07:13,183 INFO [train.py:812] (3/8) Epoch 34, batch 4350, loss[loss=0.1226, simple_loss=0.2054, pruned_loss=0.01987, over 6762.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2456, pruned_loss=0.03044, over 1415794.42 frames.], batch size: 15, lr: 2.27e-04
2022-05-15 23:08:12,771 INFO [train.py:812] (3/8) Epoch 34, batch 4400, loss[loss=0.1484, simple_loss=0.2314, pruned_loss=0.03264, over 7150.00 frames.], tot_loss[loss=0.153, simple_loss=0.2452, pruned_loss=0.03045, over 1415965.52 frames.], batch size: 18, lr: 2.27e-04
2022-05-15 23:09:11,159 INFO [train.py:812] (3/8) Epoch 34, batch 4450, loss[loss=0.1532, simple_loss=0.2433, pruned_loss=0.03159, over 7208.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2454, pruned_loss=0.03053, over 1402176.61 frames.], batch size: 23, lr: 2.27e-04
2022-05-15 23:10:19,462 INFO [train.py:812] (3/8) Epoch 34, batch 4500, loss[loss=0.1745, simple_loss=0.2758, pruned_loss=0.03663, over 5156.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2446, pruned_loss=0.03029, over 1393300.05 frames.], batch size: 52, lr: 2.27e-04
2022-05-15 23:11:16,030 INFO [train.py:812] (3/8) Epoch 34, batch 4550, loss[loss=0.1601, simple_loss=0.2581, pruned_loss=0.03103, over 5116.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2465, pruned_loss=0.03109, over 1351844.91 frames.], batch size: 52, lr: 2.27e-04
2022-05-15 23:12:20,541 INFO [train.py:812] (3/8) Epoch 35, batch 0, loss[loss=0.1498, simple_loss=0.2469, pruned_loss=0.02641, over 7229.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2469, pruned_loss=0.02641, over 7229.00 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:13:24,589 INFO [train.py:812] (3/8) Epoch 35, batch 50, loss[loss=0.1701, simple_loss=0.2644, pruned_loss=0.03785, over 7289.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2474, pruned_loss=0.03049, over 318876.94 frames.], batch size: 24, lr: 2.24e-04
2022-05-15 23:14:23,114 INFO [train.py:812] (3/8) Epoch 35, batch 100, loss[loss=0.141, simple_loss=0.2421, pruned_loss=0.0199, over 7137.00 frames.], tot_loss[loss=0.15, simple_loss=0.2434, pruned_loss=0.02831, over 567564.95 frames.], batch size: 26, lr: 2.24e-04
2022-05-15 23:15:22,486 INFO [train.py:812] (3/8) Epoch 35, batch 150, loss[loss=0.1698, simple_loss=0.2562, pruned_loss=0.04169, over 7374.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02858, over 760678.01 frames.], batch size: 23, lr: 2.24e-04
2022-05-15 23:16:21,265 INFO [train.py:812] (3/8) Epoch 35, batch 200, loss[loss=0.1385, simple_loss=0.2227, pruned_loss=0.02717, over 7073.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02857, over 910699.16 frames.], batch size: 18, lr: 2.24e-04
2022-05-15 23:17:21,129 INFO [train.py:812] (3/8) Epoch 35, batch 250, loss[loss=0.1634, simple_loss=0.2587, pruned_loss=0.03402, over 7236.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02905, over 1027695.26 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:18:18,845 INFO [train.py:812] (3/8) Epoch 35, batch 300, loss[loss=0.1517, simple_loss=0.2484, pruned_loss=0.02751, over 7161.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2424, pruned_loss=0.02888, over 1113716.00 frames.], batch size: 19, lr: 2.24e-04
2022-05-15 23:19:18,517 INFO [train.py:812] (3/8) Epoch 35, batch 350, loss[loss=0.1676, simple_loss=0.2582, pruned_loss=0.03848, over 7194.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02943, over 1185518.35 frames.], batch size: 23, lr: 2.24e-04
2022-05-15 23:20:16,879 INFO [train.py:812] (3/8) Epoch 35, batch 400, loss[loss=0.1372, simple_loss=0.2385, pruned_loss=0.01794, over 7320.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.02935, over 1239665.22 frames.], batch size: 20, lr: 2.24e-04
2022-05-15 23:21:15,059 INFO [train.py:812] (3/8) Epoch 35, batch 450, loss[loss=0.1624, simple_loss=0.2606, pruned_loss=0.03216, over 6864.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02932, over 1284190.53 frames.], batch size: 31, lr: 2.24e-04
2022-05-15 23:22:13,117 INFO [train.py:812] (3/8) Epoch 35, batch 500, loss[loss=0.1492, simple_loss=0.2406, pruned_loss=0.02888, over 7323.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02897, over 1314408.97 frames.], batch size: 20, lr: 2.23e-04
2022-05-15 23:23:12,698 INFO [train.py:812] (3/8) Epoch 35, batch 550, loss[loss=0.1445, simple_loss=0.2251, pruned_loss=0.03198, over 7057.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2406, pruned_loss=0.02888, over 1335239.30 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:24:10,898 INFO [train.py:812] (3/8) Epoch 35, batch 600, loss[loss=0.1494, simple_loss=0.2505, pruned_loss=0.02409, over 7333.00 frames.], tot_loss[loss=0.1504, simple_loss=0.242, pruned_loss=0.02936, over 1353613.03 frames.], batch size: 22, lr: 2.23e-04
2022-05-15 23:25:10,089 INFO [train.py:812] (3/8) Epoch 35, batch 650, loss[loss=0.1476, simple_loss=0.2318, pruned_loss=0.03173, over 7167.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2423, pruned_loss=0.0293, over 1372259.00 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:26:08,923 INFO [train.py:812] (3/8) Epoch 35, batch 700, loss[loss=0.1465, simple_loss=0.2358, pruned_loss=0.02854, over 7285.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2421, pruned_loss=0.02933, over 1386476.42 frames.], batch size: 17, lr: 2.23e-04
2022-05-15 23:27:08,851 INFO [train.py:812] (3/8) Epoch 35, batch 750, loss[loss=0.1439, simple_loss=0.2265, pruned_loss=0.03068, over 7255.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2417, pruned_loss=0.02945, over 1394503.44 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:28:07,088 INFO [train.py:812] (3/8) Epoch 35, batch 800, loss[loss=0.1502, simple_loss=0.2509, pruned_loss=0.02475, over 7211.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02952, over 1403251.50 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:29:06,741 INFO [train.py:812] (3/8) Epoch 35, batch 850, loss[loss=0.1616, simple_loss=0.2663, pruned_loss=0.02848, over 7286.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2434, pruned_loss=0.02967, over 1403716.61 frames.], batch size: 24, lr: 2.23e-04
2022-05-15 23:30:05,619 INFO [train.py:812] (3/8) Epoch 35, batch 900, loss[loss=0.1649, simple_loss=0.2606, pruned_loss=0.03461, over 5062.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02959, over 1407283.18 frames.], batch size: 52, lr: 2.23e-04
2022-05-15 23:31:04,514 INFO [train.py:812] (3/8) Epoch 35, batch 950, loss[loss=0.1505, simple_loss=0.2448, pruned_loss=0.02804, over 7252.00 frames.], tot_loss[loss=0.1511, simple_loss=0.243, pruned_loss=0.0296, over 1410282.32 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:32:02,586 INFO [train.py:812] (3/8) Epoch 35, batch 1000, loss[loss=0.166, simple_loss=0.2585, pruned_loss=0.03679, over 6739.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2437, pruned_loss=0.0299, over 1411710.04 frames.], batch size: 31, lr: 2.23e-04
2022-05-15 23:33:01,146 INFO [train.py:812] (3/8) Epoch 35, batch 1050, loss[loss=0.1442, simple_loss=0.2359, pruned_loss=0.02625, over 7416.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02935, over 1416122.99 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:33:59,687 INFO [train.py:812] (3/8) Epoch 35, batch 1100, loss[loss=0.1509, simple_loss=0.2461, pruned_loss=0.02789, over 7363.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02924, over 1420143.48 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:34:58,668 INFO [train.py:812] (3/8) Epoch 35, batch 1150, loss[loss=0.1651, simple_loss=0.2481, pruned_loss=0.04106, over 7225.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02908, over 1422465.94 frames.], batch size: 23, lr: 2.23e-04
2022-05-15 23:35:56,582 INFO [train.py:812] (3/8) Epoch 35, batch 1200, loss[loss=0.1531, simple_loss=0.2345, pruned_loss=0.03583, over 7280.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.02874, over 1425488.16 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:36:55,065 INFO [train.py:812] (3/8) Epoch 35, batch 1250, loss[loss=0.1583, simple_loss=0.2673, pruned_loss=0.02464, over 7332.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02901, over 1424333.70 frames.], batch size: 22, lr: 2.23e-04
2022-05-15 23:37:53,432 INFO [train.py:812] (3/8) Epoch 35, batch 1300, loss[loss=0.1415, simple_loss=0.235, pruned_loss=0.02402, over 7038.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2438, pruned_loss=0.02931, over 1419850.78 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:38:52,775 INFO [train.py:812] (3/8) Epoch 35, batch 1350, loss[loss=0.161, simple_loss=0.252, pruned_loss=0.03503, over 7182.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2441, pruned_loss=0.02952, over 1423281.46 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:39:51,286 INFO [train.py:812] (3/8) Epoch 35, batch 1400, loss[loss=0.1449, simple_loss=0.2433, pruned_loss=0.02331, over 7321.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2442, pruned_loss=0.02959, over 1421380.39 frames.], batch size: 20, lr: 2.23e-04
2022-05-15 23:40:50,632 INFO [train.py:812] (3/8) Epoch 35, batch 1450, loss[loss=0.1463, simple_loss=0.2345, pruned_loss=0.029, over 7254.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02983, over 1419473.00 frames.], batch size: 19, lr: 2.23e-04
2022-05-15 23:41:50,092 INFO [train.py:812] (3/8) Epoch 35, batch 1500, loss[loss=0.1435, simple_loss=0.2319, pruned_loss=0.02755, over 7147.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2439, pruned_loss=0.02967, over 1420425.32 frames.], batch size: 17, lr: 2.23e-04
2022-05-15 23:42:48,890 INFO [train.py:812] (3/8) Epoch 35, batch 1550, loss[loss=0.1728, simple_loss=0.2774, pruned_loss=0.0341, over 7220.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2444, pruned_loss=0.02971, over 1420549.05 frames.], batch size: 21, lr: 2.23e-04
2022-05-15 23:43:47,280 INFO [train.py:812] (3/8) Epoch 35, batch 1600, loss[loss=0.152, simple_loss=0.2476, pruned_loss=0.02816, over 7081.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2441, pruned_loss=0.02966, over 1422993.39 frames.], batch size: 28, lr: 2.23e-04
2022-05-15 23:44:46,437 INFO [train.py:812] (3/8) Epoch 35, batch 1650, loss[loss=0.1398, simple_loss=0.2305, pruned_loss=0.0245, over 7408.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02933, over 1427716.01 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:45:45,299 INFO [train.py:812] (3/8) Epoch 35, batch 1700, loss[loss=0.1734, simple_loss=0.2562, pruned_loss=0.04533, over 5049.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02931, over 1426289.22 frames.], batch size: 52, lr: 2.23e-04
2022-05-15 23:46:45,347 INFO [train.py:812] (3/8) Epoch 35, batch 1750, loss[loss=0.1296, simple_loss=0.2204, pruned_loss=0.01945, over 7161.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2422, pruned_loss=0.0292, over 1426149.01 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:47:44,618 INFO [train.py:812] (3/8) Epoch 35, batch 1800, loss[loss=0.1559, simple_loss=0.2453, pruned_loss=0.03326, over 7274.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02871, over 1430465.44 frames.], batch size: 25, lr: 2.23e-04
2022-05-15 23:48:43,742 INFO [train.py:812] (3/8) Epoch 35, batch 1850, loss[loss=0.1404, simple_loss=0.2282, pruned_loss=0.02634, over 7053.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02882, over 1426356.18 frames.], batch size: 18, lr: 2.23e-04
2022-05-15 23:49:42,138 INFO [train.py:812] (3/8) Epoch 35, batch 1900, loss[loss=0.1635, simple_loss=0.2569, pruned_loss=0.03507, over 7377.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2414, pruned_loss=0.02884, over 1425880.47 frames.], batch size: 23, lr: 2.22e-04
2022-05-15 23:50:50,957 INFO [train.py:812] (3/8) Epoch 35, batch 1950, loss[loss=0.1323, simple_loss=0.2218, pruned_loss=0.02139, over 7180.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02891, over 1424544.27 frames.], batch size: 18, lr: 2.22e-04
2022-05-15 23:51:48,104 INFO [train.py:812] (3/8) Epoch 35, batch 2000, loss[loss=0.1639, simple_loss=0.2612, pruned_loss=0.03327, over 6502.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02908, over 1420236.95 frames.], batch size: 38, lr: 2.22e-04
2022-05-15 23:52:46,840 INFO [train.py:812] (3/8) Epoch 35, batch 2050, loss[loss=0.1493, simple_loss=0.2438, pruned_loss=0.02738, over 7115.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02947, over 1421169.97 frames.], batch size: 21, lr: 2.22e-04
2022-05-15 23:53:45,612 INFO [train.py:812] (3/8) Epoch 35, batch 2100, loss[loss=0.169, simple_loss=0.2624, pruned_loss=0.03781, over 7410.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2427, pruned_loss=0.02938, over 1424779.34 frames.], batch size: 21, lr: 2.22e-04
2022-05-15 23:54:43,310 INFO [train.py:812] (3/8) Epoch 35, batch 2150, loss[loss=0.1582, simple_loss=0.2602, pruned_loss=0.02805, over 6118.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02898, over 1428074.04 frames.], batch size: 37, lr: 2.22e-04
2022-05-15 23:55:40,404 INFO [train.py:812] (3/8) Epoch 35, batch 2200, loss[loss=0.1498, simple_loss=0.244, pruned_loss=0.02778, over 7439.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02928, over 1424647.65 frames.], batch size: 20, lr: 2.22e-04
2022-05-15 23:56:39,589 INFO [train.py:812] (3/8) Epoch 35, batch 2250, loss[loss=0.1672, simple_loss=0.2509, pruned_loss=0.04172, over 7276.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02934, over 1422568.69 frames.], batch size: 18, lr: 2.22e-04
2022-05-15 23:57:38,206 INFO [train.py:812] (3/8) Epoch 35, batch 2300, loss[loss=0.1402, simple_loss=0.2355, pruned_loss=0.02248, over 7112.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2413, pruned_loss=0.02887, over 1419459.09 frames.], batch size: 26, lr: 2.22e-04
2022-05-15 23:58:36,528 INFO [train.py:812] (3/8) Epoch 35, batch 2350, loss[loss=0.1475, simple_loss=0.2483, pruned_loss=0.02334, over 7009.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02873, over 1416956.29 frames.], batch size: 28, lr: 2.22e-04
2022-05-15 23:59:34,365 INFO [train.py:812] (3/8) Epoch 35, batch 2400, loss[loss=0.124, simple_loss=0.2106, pruned_loss=0.01872, over 7006.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02887, over 1423028.49 frames.], batch size: 16, lr: 2.22e-04
2022-05-16 00:00:32,008 INFO [train.py:812] (3/8) Epoch 35, batch 2450, loss[loss=0.1407, simple_loss=0.2359, pruned_loss=0.02272, over 7428.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2413, pruned_loss=0.02887, over 1422804.53 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:01:31,441 INFO [train.py:812] (3/8) Epoch 35, batch 2500, loss[loss=0.2013, simple_loss=0.2971, pruned_loss=0.05272, over 6334.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.029, over 1424453.76 frames.], batch size: 37, lr: 2.22e-04
2022-05-16 00:02:30,458 INFO [train.py:812] (3/8) Epoch 35, batch 2550, loss[loss=0.1497, simple_loss=0.244, pruned_loss=0.0277, over 7115.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2417, pruned_loss=0.02895, over 1423993.11 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:03:28,740 INFO [train.py:812] (3/8) Epoch 35, batch 2600, loss[loss=0.1568, simple_loss=0.2506, pruned_loss=0.03149, over 7209.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2412, pruned_loss=0.02902, over 1423893.63 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:04:26,532 INFO [train.py:812] (3/8) Epoch 35, batch 2650, loss[loss=0.1538, simple_loss=0.2535, pruned_loss=0.02702, over 7194.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2417, pruned_loss=0.02936, over 1422751.93 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:05:25,221 INFO [train.py:812] (3/8) Epoch 35, batch 2700, loss[loss=0.1461, simple_loss=0.2404, pruned_loss=0.02592, over 7116.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2415, pruned_loss=0.02929, over 1424606.70 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:06:24,233 INFO [train.py:812] (3/8) Epoch 35, batch 2750, loss[loss=0.1408, simple_loss=0.2394, pruned_loss=0.0211, over 7310.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2421, pruned_loss=0.02953, over 1424670.36 frames.], batch size: 21, lr: 2.22e-04
2022-05-16 00:07:23,087 INFO [train.py:812] (3/8) Epoch 35, batch 2800, loss[loss=0.1572, simple_loss=0.2497, pruned_loss=0.03233, over 7335.00 frames.], tot_loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02975, over 1425838.64 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:08:20,730 INFO [train.py:812] (3/8) Epoch 35, batch 2850, loss[loss=0.171, simple_loss=0.2632, pruned_loss=0.03937, over 7159.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2428, pruned_loss=0.0294, over 1424253.22 frames.], batch size: 19, lr: 2.22e-04
2022-05-16 00:09:20,162 INFO [train.py:812] (3/8) Epoch 35, batch 2900, loss[loss=0.1532, simple_loss=0.2471, pruned_loss=0.02958, over 6347.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2432, pruned_loss=0.02978, over 1423122.79 frames.], batch size: 37, lr: 2.22e-04
2022-05-16 00:10:18,328 INFO [train.py:812] (3/8) Epoch 35, batch 2950, loss[loss=0.1404, simple_loss=0.2253, pruned_loss=0.02779, over 7209.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2442, pruned_loss=0.03, over 1416940.65 frames.], batch size: 16, lr: 2.22e-04
2022-05-16 00:11:17,558 INFO [train.py:812] (3/8) Epoch 35, batch 3000, loss[loss=0.1591, simple_loss=0.2486, pruned_loss=0.03478, over 7377.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02926, over 1420607.06 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:11:17,560 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 00:11:25,088 INFO [train.py:841] (3/8) Epoch 35, validation: loss=0.1528, simple_loss=0.2485, pruned_loss=0.02851, over 698248.00 frames.
2022-05-16 00:12:24,397 INFO [train.py:812] (3/8) Epoch 35, batch 3050, loss[loss=0.1517, simple_loss=0.2449, pruned_loss=0.02928, over 7234.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02937, over 1423449.88 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:13:22,721 INFO [train.py:812] (3/8) Epoch 35, batch 3100, loss[loss=0.144, simple_loss=0.2473, pruned_loss=0.02035, over 7389.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2426, pruned_loss=0.02914, over 1419640.64 frames.], batch size: 23, lr: 2.22e-04
2022-05-16 00:14:22,594 INFO [train.py:812] (3/8) Epoch 35, batch 3150, loss[loss=0.1914, simple_loss=0.275, pruned_loss=0.05395, over 7215.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2424, pruned_loss=0.02928, over 1422160.35 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:15:21,756 INFO [train.py:812] (3/8) Epoch 35, batch 3200, loss[loss=0.1577, simple_loss=0.2473, pruned_loss=0.03405, over 7198.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02986, over 1427259.20 frames.], batch size: 22, lr: 2.22e-04
2022-05-16 00:16:21,591 INFO [train.py:812] (3/8) Epoch 35, batch 3250, loss[loss=0.1496, simple_loss=0.2385, pruned_loss=0.03034, over 7428.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2436, pruned_loss=0.02968, over 1425110.63 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:17:21,153 INFO [train.py:812] (3/8) Epoch 35, batch 3300, loss[loss=0.1454, simple_loss=0.2381, pruned_loss=0.0263, over 7424.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02945, over 1425962.85 frames.], batch size: 20, lr: 2.22e-04
2022-05-16 00:18:19,924 INFO [train.py:812] (3/8) Epoch 35, batch 3350, loss[loss=0.1459, simple_loss=0.2386, pruned_loss=0.02664, over 7428.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2439, pruned_loss=0.02948, over 1429352.29 frames.], batch size: 20, lr: 2.21e-04
2022-05-16 00:19:17,063 INFO [train.py:812] (3/8) Epoch 35, batch 3400, loss[loss=0.159, simple_loss=0.2419, pruned_loss=0.03803, over 7278.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 1425674.26 frames.], batch size: 18, lr: 2.21e-04
2022-05-16 00:20:15,987 INFO [train.py:812] (3/8) Epoch 35, batch 3450, loss[loss=0.1164, simple_loss=0.1994, pruned_loss=0.01667, over 6990.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2438, pruned_loss=0.02995, over 1428732.71 frames.], batch size: 16, lr: 2.21e-04
2022-05-16 00:21:14,729 INFO [train.py:812] (3/8) Epoch 35, batch 3500, loss[loss=0.133, simple_loss=0.2302, pruned_loss=0.0179, over 7339.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02961, over 1427666.97 frames.], batch size: 22, lr: 2.21e-04
2022-05-16 00:22:12,838 INFO [train.py:812] (3/8) Epoch 35, batch 3550, loss[loss=0.1674, simple_loss=0.2587, pruned_loss=0.03808, over 6851.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.0293, over 1419949.88 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:23:10,728 INFO [train.py:812] (3/8) Epoch 35, batch 3600, loss[loss=0.167, simple_loss=0.2567, pruned_loss=0.03864, over 7215.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02913, over 1419701.99 frames.], batch size: 22, lr: 2.21e-04
2022-05-16 00:24:08,627 INFO [train.py:812] (3/8) Epoch 35, batch 3650, loss[loss=0.1701, simple_loss=0.2675, pruned_loss=0.03638, over 7300.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02939, over 1421576.36 frames.], batch size: 25, lr: 2.21e-04
2022-05-16 00:25:06,925 INFO [train.py:812] (3/8) Epoch 35, batch 3700, loss[loss=0.1413, simple_loss=0.2403, pruned_loss=0.02113, over 6334.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.0293, over 1421021.68 frames.], batch size: 37, lr: 2.21e-04
2022-05-16 00:26:05,697 INFO [train.py:812] (3/8) Epoch 35, batch 3750, loss[loss=0.159, simple_loss=0.2445, pruned_loss=0.03673, over 5106.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02932, over 1418290.97 frames.], batch size: 52, lr: 2.21e-04
2022-05-16 00:27:04,266 INFO [train.py:812] (3/8) Epoch 35, batch 3800, loss[loss=0.1575, simple_loss=0.2453, pruned_loss=0.03486, over 6794.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2436, pruned_loss=0.02959, over 1418648.70 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:28:02,101 INFO [train.py:812] (3/8) Epoch 35, batch 3850, loss[loss=0.1773, simple_loss=0.2691, pruned_loss=0.04276, over 7289.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02952, over 1420870.97 frames.], batch size: 24, lr: 2.21e-04
2022-05-16 00:29:00,960 INFO [train.py:812] (3/8) Epoch 35, batch 3900, loss[loss=0.1591, simple_loss=0.2381, pruned_loss=0.04011, over 6808.00 frames.], tot_loss[loss=0.151, simple_loss=0.2432, pruned_loss=0.02944, over 1417288.90 frames.], batch size: 15, lr: 2.21e-04
2022-05-16 00:30:00,064 INFO [train.py:812] (3/8) Epoch 35, batch 3950, loss[loss=0.1245, simple_loss=0.2156, pruned_loss=0.01675, over 7125.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2426, pruned_loss=0.02896, over 1418236.71 frames.], batch size: 17, lr: 2.21e-04
2022-05-16 00:30:58,309 INFO [train.py:812] (3/8) Epoch 35, batch 4000, loss[loss=0.1391, simple_loss=0.2331, pruned_loss=0.02261, over 6978.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02886, over 1417558.03 frames.], batch size: 16, lr: 2.21e-04
2022-05-16 00:32:02,098 INFO [train.py:812] (3/8) Epoch 35, batch 4050, loss[loss=0.1393, simple_loss=0.247, pruned_loss=0.0158, over 6353.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2428, pruned_loss=0.02874, over 1420150.22 frames.], batch size: 38, lr: 2.21e-04
2022-05-16 00:33:00,877 INFO [train.py:812] (3/8) Epoch 35, batch 4100, loss[loss=0.1507, simple_loss=0.2486, pruned_loss=0.02642, over 7227.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2423, pruned_loss=0.02838, over 1425101.00 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:33:59,514 INFO [train.py:812] (3/8) Epoch 35, batch 4150, loss[loss=0.1471, simple_loss=0.2556, pruned_loss=0.01935, over 7312.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02838, over 1423932.85 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:34:58,414 INFO [train.py:812] (3/8) Epoch 35, batch 4200, loss[loss=0.1338, simple_loss=0.2412, pruned_loss=0.01321, over 7326.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2419, pruned_loss=0.02863, over 1422620.53 frames.], batch size: 21, lr: 2.21e-04
2022-05-16 00:35:57,140 INFO [train.py:812] (3/8) Epoch 35, batch 4250, loss[loss=0.133, simple_loss=0.2232, pruned_loss=0.02146, over 7273.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02885, over 1427182.20 frames.], batch size: 17, lr: 2.21e-04
2022-05-16 00:36:55,266 INFO [train.py:812] (3/8) Epoch 35, batch 4300, loss[loss=0.1475, simple_loss=0.2387, pruned_loss=0.02812, over 7138.00 frames.], tot_loss[loss=0.149, simple_loss=0.2411, pruned_loss=0.02849, over 1418246.89 frames.], batch size: 26, lr: 2.21e-04
2022-05-16 00:37:53,241 INFO [train.py:812] (3/8) Epoch 35, batch 4350, loss[loss=0.2037, simple_loss=0.2888, pruned_loss=0.05926, over 7301.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02921, over 1413608.53 frames.], batch size: 24, lr: 2.21e-04
2022-05-16 00:38:52,031 INFO [train.py:812] (3/8) Epoch 35, batch 4400, loss[loss=0.1389, simple_loss=0.2387, pruned_loss=0.01951, over 7157.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2429, pruned_loss=0.02965, over 1408393.29 frames.], batch size: 19, lr: 2.21e-04
2022-05-16 00:39:50,126 INFO [train.py:812] (3/8) Epoch 35, batch 4450, loss[loss=0.1554, simple_loss=0.2583, pruned_loss=0.02624, over 6794.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2434, pruned_loss=0.02965, over 1392681.75 frames.], batch size: 31, lr: 2.21e-04
2022-05-16 00:40:48,510 INFO [train.py:812] (3/8) Epoch 35, batch 4500, loss[loss=0.1454, simple_loss=0.2481, pruned_loss=0.02137, over 7166.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2438, pruned_loss=0.03003, over 1378846.70 frames.], batch size: 26, lr: 2.21e-04
2022-05-16 00:41:45,663 INFO [train.py:812] (3/8) Epoch 35, batch 4550, loss[loss=0.1678, simple_loss=0.2514, pruned_loss=0.04208, over 4761.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2466, pruned_loss=0.0312, over 1355288.04 frames.], batch size: 52, lr: 2.21e-04
2022-05-16 00:42:50,990 INFO [train.py:812] (3/8) Epoch 36, batch 0, loss[loss=0.1395, simple_loss=0.2444, pruned_loss=0.01729, over 7328.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2444, pruned_loss=0.01729, over 7328.00 frames.], batch size: 20, lr: 2.18e-04
2022-05-16 00:43:50,522 INFO [train.py:812] (3/8) Epoch 36, batch 50, loss[loss=0.1702, simple_loss=0.26, pruned_loss=0.04016, over 7433.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02947, over 316265.55 frames.], batch size: 20, lr: 2.18e-04
2022-05-16 00:44:48,780 INFO [train.py:812] (3/8) Epoch 36, batch 100, loss[loss=0.1637, simple_loss=0.2538, pruned_loss=0.03674, over 5436.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2415, pruned_loss=0.02741, over 562432.93 frames.], batch size: 54, lr: 2.17e-04
2022-05-16 00:45:47,236 INFO [train.py:812] (3/8) Epoch 36, batch 150, loss[loss=0.1337, simple_loss=0.2232, pruned_loss=0.02213, over 7232.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2406, pruned_loss=0.02837, over 751609.70 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:46:46,269 INFO [train.py:812] (3/8) Epoch 36, batch 200, loss[loss=0.1544, simple_loss=0.2485, pruned_loss=0.03018, over 7315.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2418, pruned_loss=0.02901, over 901705.24 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 00:47:45,331 INFO [train.py:812] (3/8) Epoch 36, batch 250, loss[loss=0.1343, simple_loss=0.2322, pruned_loss=0.01816, over 7165.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02849, over 1020418.36 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:48:43,643 INFO [train.py:812] (3/8) Epoch 36, batch 300, loss[loss=0.1761, simple_loss=0.263, pruned_loss=0.04457, over 7192.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02906, over 1105604.73 frames.], batch size: 26, lr: 2.17e-04
2022-05-16 00:49:42,218 INFO [train.py:812] (3/8) Epoch 36, batch 350, loss[loss=0.1392, simple_loss=0.2308, pruned_loss=0.02375, over 6821.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02941, over 1174810.45 frames.], batch size: 31, lr: 2.17e-04
2022-05-16 00:50:40,189 INFO [train.py:812] (3/8) Epoch 36, batch 400, loss[loss=0.1696, simple_loss=0.2595, pruned_loss=0.03985, over 7214.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.0294, over 1230852.86 frames.], batch size: 22, lr: 2.17e-04
2022-05-16 00:51:39,738 INFO [train.py:812] (3/8) Epoch 36, batch 450, loss[loss=0.1739, simple_loss=0.2648, pruned_loss=0.0415, over 7158.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2444, pruned_loss=0.02969, over 1278731.70 frames.], batch size: 26, lr: 2.17e-04
2022-05-16 00:52:38,616 INFO [train.py:812] (3/8) Epoch 36, batch 500, loss[loss=0.1954, simple_loss=0.2856, pruned_loss=0.0526, over 7195.00 frames.], tot_loss[loss=0.152, simple_loss=0.2447, pruned_loss=0.0296, over 1309313.19 frames.], batch size: 23, lr: 2.17e-04
2022-05-16 00:53:37,429 INFO [train.py:812] (3/8) Epoch 36, batch 550, loss[loss=0.1501, simple_loss=0.2393, pruned_loss=0.03044, over 7433.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2448, pruned_loss=0.02975, over 1335690.52 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:54:35,753 INFO [train.py:812] (3/8) Epoch 36, batch 600, loss[loss=0.1726, simple_loss=0.275, pruned_loss=0.03509, over 7215.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2446, pruned_loss=0.02992, over 1357913.93 frames.], batch size: 23, lr: 2.17e-04
2022-05-16 00:55:34,860 INFO [train.py:812] (3/8) Epoch 36, batch 650, loss[loss=0.1535, simple_loss=0.2473, pruned_loss=0.02986, over 7144.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2429, pruned_loss=0.02933, over 1372614.58 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:56:33,803 INFO [train.py:812] (3/8) Epoch 36, batch 700, loss[loss=0.1328, simple_loss=0.2264, pruned_loss=0.01967, over 7247.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2421, pruned_loss=0.02908, over 1384085.47 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 00:57:42,570 INFO [train.py:812] (3/8) Epoch 36, batch 750, loss[loss=0.1354, simple_loss=0.2269, pruned_loss=0.02189, over 7330.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02881, over 1385327.83 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 00:58:59,888 INFO [train.py:812] (3/8) Epoch 36, batch 800, loss[loss=0.1517, simple_loss=0.252, pruned_loss=0.02567, over 7401.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.02869, over 1392955.30 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 00:59:58,235 INFO [train.py:812] (3/8) Epoch 36, batch 850, loss[loss=0.1666, simple_loss=0.2674, pruned_loss=0.03294, over 7225.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.0289, over 1393141.63 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 01:00:57,366 INFO [train.py:812] (3/8) Epoch 36, batch 900, loss[loss=0.155, simple_loss=0.2451, pruned_loss=0.0324, over 6756.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.02901, over 1400356.90 frames.], batch size: 31, lr: 2.17e-04
2022-05-16 01:01:55,206 INFO [train.py:812] (3/8) Epoch 36, batch 950, loss[loss=0.1363, simple_loss=0.2167, pruned_loss=0.02793, over 6998.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2434, pruned_loss=0.02919, over 1404272.75 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:03:03,143 INFO [train.py:812] (3/8) Epoch 36, batch 1000, loss[loss=0.1268, simple_loss=0.2092, pruned_loss=0.0222, over 7281.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2429, pruned_loss=0.02913, over 1406734.61 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:04:02,096 INFO [train.py:812] (3/8) Epoch 36, batch 1050, loss[loss=0.1408, simple_loss=0.2324, pruned_loss=0.02459, over 7365.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2434, pruned_loss=0.02913, over 1406432.40 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 01:05:09,913 INFO [train.py:812] (3/8) Epoch 36, batch 1100, loss[loss=0.1729, simple_loss=0.2855, pruned_loss=0.03017, over 7207.00 frames.], tot_loss[loss=0.151, simple_loss=0.2438, pruned_loss=0.02911, over 1407006.92 frames.], batch size: 22, lr: 2.17e-04
2022-05-16 01:06:19,088 INFO [train.py:812] (3/8) Epoch 36, batch 1150, loss[loss=0.1609, simple_loss=0.2576, pruned_loss=0.03214, over 7265.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02899, over 1412114.08 frames.], batch size: 24, lr: 2.17e-04
2022-05-16 01:07:18,003 INFO [train.py:812] (3/8) Epoch 36, batch 1200, loss[loss=0.1233, simple_loss=0.2118, pruned_loss=0.01737, over 7300.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.02901, over 1408113.15 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:08:16,987 INFO [train.py:812] (3/8) Epoch 36, batch 1250, loss[loss=0.1359, simple_loss=0.2133, pruned_loss=0.02922, over 7011.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02896, over 1410158.39 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:09:23,822 INFO [train.py:812] (3/8) Epoch 36, batch 1300, loss[loss=0.1304, simple_loss=0.2106, pruned_loss=0.02512, over 7143.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2422, pruned_loss=0.02899, over 1414546.46 frames.], batch size: 17, lr: 2.17e-04
2022-05-16 01:10:23,373 INFO [train.py:812] (3/8) Epoch 36, batch 1350, loss[loss=0.123, simple_loss=0.2185, pruned_loss=0.01372, over 7260.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1419550.22 frames.], batch size: 19, lr: 2.17e-04
2022-05-16 01:11:21,654 INFO [train.py:812] (3/8) Epoch 36, batch 1400, loss[loss=0.1439, simple_loss=0.2219, pruned_loss=0.03297, over 7001.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2426, pruned_loss=0.02934, over 1417806.57 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:12:20,397 INFO [train.py:812] (3/8) Epoch 36, batch 1450, loss[loss=0.1388, simple_loss=0.2243, pruned_loss=0.02666, over 7206.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02904, over 1415492.22 frames.], batch size: 16, lr: 2.17e-04
2022-05-16 01:13:19,133 INFO [train.py:812] (3/8) Epoch 36, batch 1500, loss[loss=0.1349, simple_loss=0.23, pruned_loss=0.01988, over 7314.00 frames.], tot_loss[loss=0.1501, simple_loss=0.242, pruned_loss=0.02911, over 1418878.75 frames.], batch size: 21, lr: 2.17e-04
2022-05-16 01:14:17,128 INFO [train.py:812] (3/8) Epoch 36, batch 1550, loss[loss=0.1487, simple_loss=0.2487, pruned_loss=0.02431, over 7241.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2416, pruned_loss=0.0288, over 1420657.56 frames.], batch size: 20, lr: 2.17e-04
2022-05-16 01:15:14,897 INFO [train.py:812] (3/8) Epoch 36, batch 1600, loss[loss=0.1537, simple_loss=0.2534, pruned_loss=0.02699, over 7372.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2408, pruned_loss=0.02867, over 1420491.79 frames.], batch size: 23, lr: 2.16e-04
2022-05-16 01:16:13,256 INFO [train.py:812] (3/8) Epoch 36, batch 1650, loss[loss=0.1399, simple_loss=0.2345, pruned_loss=0.02264, over 7150.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2412, pruned_loss=0.02903, over 1422479.67 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:17:10,693 INFO [train.py:812] (3/8) Epoch 36, batch 1700, loss[loss=0.1505, simple_loss=0.2522, pruned_loss=0.02446, over 7291.00 frames.], tot_loss[loss=0.15, simple_loss=0.2419, pruned_loss=0.02903, over 1424319.77 frames.], batch size: 25, lr: 2.16e-04
2022-05-16 01:18:09,637 INFO [train.py:812] (3/8) Epoch 36, batch 1750, loss[loss=0.1317, simple_loss=0.2197, pruned_loss=0.02187, over 7290.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02913, over 1420572.89 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:19:07,102 INFO [train.py:812] (3/8) Epoch 36, batch 1800, loss[loss=0.1897, simple_loss=0.2803, pruned_loss=0.04951, over 7190.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2436, pruned_loss=0.0295, over 1422077.75 frames.], batch size: 23, lr: 2.16e-04
2022-05-16 01:20:05,568 INFO [train.py:812] (3/8) Epoch 36, batch 1850, loss[loss=0.1617, simple_loss=0.2576, pruned_loss=0.03289, over 7118.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02945, over 1425164.10 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:21:04,164 INFO [train.py:812] (3/8) Epoch 36, batch 1900, loss[loss=0.1604, simple_loss=0.2513, pruned_loss=0.03471, over 6938.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02937, over 1426603.52 frames.], batch size: 32, lr: 2.16e-04
2022-05-16 01:22:03,016 INFO [train.py:812] (3/8) Epoch 36, batch 1950, loss[loss=0.1553, simple_loss=0.2418, pruned_loss=0.03433, over 7232.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02921, over 1424273.05 frames.], batch size: 20, lr: 2.16e-04
2022-05-16 01:23:01,518 INFO [train.py:812] (3/8) Epoch 36, batch 2000, loss[loss=0.1273, simple_loss=0.2116, pruned_loss=0.02154, over 7010.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02956, over 1421089.06 frames.], batch size: 16, lr: 2.16e-04
2022-05-16 01:24:00,271 INFO [train.py:812] (3/8) Epoch 36, batch 2050, loss[loss=0.1464, simple_loss=0.2489, pruned_loss=0.02194, over 7312.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2437, pruned_loss=0.02948, over 1425593.75 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:24:59,359 INFO [train.py:812] (3/8) Epoch 36, batch 2100, loss[loss=0.1565, simple_loss=0.248, pruned_loss=0.03245, over 7419.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02924, over 1423932.13 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:25:59,143 INFO [train.py:812] (3/8) Epoch 36, batch 2150, loss[loss=0.1459, simple_loss=0.2257, pruned_loss=0.03308, over 7259.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02925, over 1425965.48 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:26:58,702 INFO [train.py:812] (3/8) Epoch 36, batch 2200, loss[loss=0.1324, simple_loss=0.2191, pruned_loss=0.02284, over 7411.00 frames.], tot_loss[loss=0.151, simple_loss=0.2435, pruned_loss=0.02925, over 1425601.65 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:27:57,335 INFO [train.py:812] (3/8) Epoch 36, batch 2250, loss[loss=0.1592, simple_loss=0.2547, pruned_loss=0.03187, over 7337.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2444, pruned_loss=0.02939, over 1421984.52 frames.], batch size: 22, lr: 2.16e-04
2022-05-16 01:28:55,644 INFO [train.py:812] (3/8) Epoch 36, batch 2300, loss[loss=0.1512, simple_loss=0.2322, pruned_loss=0.03516, over 7127.00 frames.], tot_loss[loss=0.151, simple_loss=0.2433, pruned_loss=0.02934, over 1424835.32 frames.], batch size: 17, lr: 2.16e-04
2022-05-16 01:29:55,108 INFO [train.py:812] (3/8) Epoch 36, batch 2350, loss[loss=0.1591, simple_loss=0.251, pruned_loss=0.03356, over 5330.00 frames.], tot_loss[loss=0.1519, simple_loss=0.244, pruned_loss=0.02989, over 1422920.48 frames.], batch size: 53, lr: 2.16e-04
2022-05-16 01:30:54,428 INFO [train.py:812] (3/8) Epoch 36, batch 2400, loss[loss=0.137, simple_loss=0.2208, pruned_loss=0.02655, over 7405.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2435, pruned_loss=0.02949, over 1426243.75 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:31:54,037 INFO [train.py:812] (3/8) Epoch 36, batch 2450, loss[loss=0.1377, simple_loss=0.228, pruned_loss=0.02372, over 7158.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.0291, over 1422382.89 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:32:52,233 INFO [train.py:812] (3/8) Epoch 36, batch 2500, loss[loss=0.143, simple_loss=0.2311, pruned_loss=0.02743, over 7144.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02892, over 1425669.76 frames.], batch size: 20, lr: 2.16e-04
2022-05-16 01:33:51,369 INFO [train.py:812] (3/8) Epoch 36, batch 2550, loss[loss=0.1666, simple_loss=0.2562, pruned_loss=0.03851, over 7349.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02916, over 1422055.51 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:34:50,094 INFO [train.py:812] (3/8) Epoch 36, batch 2600, loss[loss=0.143, simple_loss=0.2281, pruned_loss=0.02893, over 7155.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.02894, over 1423282.02 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:35:48,592 INFO [train.py:812] (3/8) Epoch 36, batch 2650, loss[loss=0.2041, simple_loss=0.2876, pruned_loss=0.06027, over 5158.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02932, over 1422209.30 frames.], batch size: 52, lr: 2.16e-04
2022-05-16 01:36:46,989 INFO [train.py:812] (3/8) Epoch 36, batch 2700, loss[loss=0.1438, simple_loss=0.2418, pruned_loss=0.02287, over 7302.00 frames.], tot_loss[loss=0.151, simple_loss=0.2431, pruned_loss=0.02947, over 1422520.90 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:37:45,862 INFO [train.py:812] (3/8) Epoch 36, batch 2750, loss[loss=0.1459, simple_loss=0.246, pruned_loss=0.02289, over 7113.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02919, over 1425479.38 frames.], batch size: 21, lr: 2.16e-04
2022-05-16 01:38:44,972 INFO [train.py:812] (3/8) Epoch 36, batch 2800, loss[loss=0.1729, simple_loss=0.2783, pruned_loss=0.03375, over 7202.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2421, pruned_loss=0.0293, over 1426771.41 frames.], batch size: 22, lr: 2.16e-04
2022-05-16 01:39:44,897 INFO [train.py:812] (3/8) Epoch 36, batch 2850, loss[loss=0.1379, simple_loss=0.2249, pruned_loss=0.02548, over 7263.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2413, pruned_loss=0.02894, over 1427958.84 frames.], batch size: 17, lr: 2.16e-04
2022-05-16 01:40:43,912 INFO [train.py:812] (3/8) Epoch 36, batch 2900, loss[loss=0.1307, simple_loss=0.2261, pruned_loss=0.01764, over 7254.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2405, pruned_loss=0.02902, over 1426008.75 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:41:42,644 INFO [train.py:812] (3/8) Epoch 36, batch 2950, loss[loss=0.1382, simple_loss=0.2367, pruned_loss=0.01979, over 7162.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2418, pruned_loss=0.02921, over 1424156.14 frames.], batch size: 18, lr: 2.16e-04
2022-05-16 01:42:41,187 INFO [train.py:812] (3/8) Epoch 36, batch 3000, loss[loss=0.1413, simple_loss=0.2327, pruned_loss=0.02495, over 7171.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02945, over 1421832.25 frames.], batch size: 19, lr: 2.16e-04
2022-05-16 01:42:41,188 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 01:42:48,528 INFO [train.py:841] (3/8) Epoch 36, validation: loss=0.1533, simple_loss=0.2487, pruned_loss=0.02893, over 698248.00 frames.
2022-05-16 01:43:48,491 INFO [train.py:812] (3/8) Epoch 36, batch 3050, loss[loss=0.1625, simple_loss=0.2559, pruned_loss=0.03448, over 7306.00 frames.], tot_loss[loss=0.1509, simple_loss=0.243, pruned_loss=0.02939, over 1424345.60 frames.], batch size: 24, lr: 2.16e-04
2022-05-16 01:44:47,695 INFO [train.py:812] (3/8) Epoch 36, batch 3100, loss[loss=0.1835, simple_loss=0.2723, pruned_loss=0.04734, over 7284.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2441, pruned_loss=0.02977, over 1428582.03 frames.], batch size: 25, lr: 2.15e-04
2022-05-16 01:45:47,527 INFO [train.py:812] (3/8) Epoch 36, batch 3150, loss[loss=0.1417, simple_loss=0.2461, pruned_loss=0.01867, over 7392.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.0293, over 1425800.35 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:46:46,128 INFO [train.py:812] (3/8) Epoch 36, batch 3200, loss[loss=0.1311, simple_loss=0.2142, pruned_loss=0.02403, over 7137.00 frames.], tot_loss[loss=0.152, simple_loss=0.244, pruned_loss=0.03001, over 1419959.30 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 01:47:45,908 INFO [train.py:812] (3/8) Epoch 36, batch 3250, loss[loss=0.1759, simple_loss=0.2681, pruned_loss=0.04188, over 5303.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2438, pruned_loss=0.02954, over 1417183.25 frames.], batch size: 53, lr: 2.15e-04
2022-05-16 01:48:53,218 INFO [train.py:812] (3/8) Epoch 36, batch 3300, loss[loss=0.1749, simple_loss=0.2694, pruned_loss=0.04026, over 7191.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2445, pruned_loss=0.02986, over 1421059.59 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:49:52,241 INFO [train.py:812] (3/8) Epoch 36, batch 3350, loss[loss=0.1441, simple_loss=0.2318, pruned_loss=0.02822, over 7194.00 frames.], tot_loss[loss=0.1515, simple_loss=0.244, pruned_loss=0.0295, over 1425307.81 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 01:50:50,250 INFO [train.py:812] (3/8) Epoch 36, batch 3400, loss[loss=0.1481, simple_loss=0.2294, pruned_loss=0.03342, over 7256.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02909, over 1424443.71 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 01:51:53,843 INFO [train.py:812] (3/8) Epoch 36, batch 3450, loss[loss=0.1176, simple_loss=0.2042, pruned_loss=0.01549, over 7282.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2425, pruned_loss=0.02886, over 1422185.56 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 01:52:52,273 INFO [train.py:812] (3/8) Epoch 36, batch 3500, loss[loss=0.1413, simple_loss=0.2404, pruned_loss=0.02114, over 7416.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02882, over 1418737.20 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 01:53:50,961 INFO [train.py:812] (3/8) Epoch 36, batch 3550, loss[loss=0.1576, simple_loss=0.2531, pruned_loss=0.03109, over 6999.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02843, over 1421897.16 frames.], batch size: 28, lr: 2.15e-04
2022-05-16 01:54:49,008 INFO [train.py:812] (3/8) Epoch 36, batch 3600, loss[loss=0.1609, simple_loss=0.2517, pruned_loss=0.0351, over 7336.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2425, pruned_loss=0.02868, over 1420861.00 frames.], batch size: 25, lr: 2.15e-04
2022-05-16 01:55:48,143 INFO [train.py:812] (3/8) Epoch 36, batch 3650, loss[loss=0.1627, simple_loss=0.2614, pruned_loss=0.03197, over 7291.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2424, pruned_loss=0.02859, over 1422400.57 frames.], batch size: 24, lr: 2.15e-04
2022-05-16 01:56:46,024 INFO [train.py:812] (3/8) Epoch 36, batch 3700, loss[loss=0.1522, simple_loss=0.2467, pruned_loss=0.02885, over 7107.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2419, pruned_loss=0.02816, over 1425164.83 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 01:57:44,749 INFO [train.py:812] (3/8) Epoch 36, batch 3750, loss[loss=0.1551, simple_loss=0.2525, pruned_loss=0.02889, over 7332.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02824, over 1424568.56 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 01:58:43,587 INFO [train.py:812] (3/8) Epoch 36, batch 3800, loss[loss=0.1398, simple_loss=0.2329, pruned_loss=0.0234, over 7358.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2429, pruned_loss=0.02869, over 1426791.12 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 01:59:42,774 INFO [train.py:812] (3/8) Epoch 36, batch 3850, loss[loss=0.1384, simple_loss=0.2284, pruned_loss=0.02421, over 6997.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2433, pruned_loss=0.02912, over 1423640.06 frames.], batch size: 16, lr: 2.15e-04
2022-05-16 02:00:41,780 INFO [train.py:812] (3/8) Epoch 36, batch 3900, loss[loss=0.1523, simple_loss=0.251, pruned_loss=0.02679, over 7205.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2427, pruned_loss=0.02896, over 1425166.82 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 02:01:40,129 INFO [train.py:812] (3/8) Epoch 36, batch 3950, loss[loss=0.1652, simple_loss=0.2621, pruned_loss=0.0341, over 6795.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2433, pruned_loss=0.02899, over 1423405.70 frames.], batch size: 31, lr: 2.15e-04
2022-05-16 02:02:38,476 INFO [train.py:812] (3/8) Epoch 36, batch 4000, loss[loss=0.1484, simple_loss=0.2427, pruned_loss=0.02702, over 7044.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2434, pruned_loss=0.02894, over 1423676.68 frames.], batch size: 28, lr: 2.15e-04
2022-05-16 02:03:36,276 INFO [train.py:812] (3/8) Epoch 36, batch 4050, loss[loss=0.1584, simple_loss=0.2558, pruned_loss=0.03054, over 7216.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2436, pruned_loss=0.0288, over 1426331.82 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:04:34,903 INFO [train.py:812] (3/8) Epoch 36, batch 4100, loss[loss=0.1648, simple_loss=0.2408, pruned_loss=0.04444, over 7126.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2432, pruned_loss=0.02884, over 1426277.05 frames.], batch size: 17, lr: 2.15e-04
2022-05-16 02:05:34,542 INFO [train.py:812] (3/8) Epoch 36, batch 4150, loss[loss=0.1839, simple_loss=0.2818, pruned_loss=0.04304, over 7199.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02903, over 1418597.31 frames.], batch size: 23, lr: 2.15e-04
2022-05-16 02:06:32,904 INFO [train.py:812] (3/8) Epoch 36, batch 4200, loss[loss=0.1408, simple_loss=0.2254, pruned_loss=0.02806, over 7242.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.02903, over 1416658.84 frames.], batch size: 20, lr: 2.15e-04
2022-05-16 02:07:31,853 INFO [train.py:812] (3/8) Epoch 36, batch 4250, loss[loss=0.1712, simple_loss=0.257, pruned_loss=0.04266, over 7218.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2426, pruned_loss=0.029, over 1415988.29 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 02:08:31,008 INFO [train.py:812] (3/8) Epoch 36, batch 4300, loss[loss=0.143, simple_loss=0.235, pruned_loss=0.02552, over 7201.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2424, pruned_loss=0.02911, over 1411796.02 frames.], batch size: 22, lr: 2.15e-04
2022-05-16 02:09:30,581 INFO [train.py:812] (3/8) Epoch 36, batch 4350, loss[loss=0.1488, simple_loss=0.2427, pruned_loss=0.02749, over 7439.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02858, over 1410400.34 frames.], batch size: 20, lr: 2.15e-04
2022-05-16 02:10:29,634 INFO [train.py:812] (3/8) Epoch 36, batch 4400, loss[loss=0.141, simple_loss=0.2199, pruned_loss=0.03106, over 7351.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2403, pruned_loss=0.02829, over 1414809.52 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 02:11:29,746 INFO [train.py:812] (3/8) Epoch 36, batch 4450, loss[loss=0.1384, simple_loss=0.2361, pruned_loss=0.02036, over 7213.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2404, pruned_loss=0.02848, over 1405657.58 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:12:28,157 INFO [train.py:812] (3/8) Epoch 36, batch 4500, loss[loss=0.1384, simple_loss=0.2427, pruned_loss=0.01709, over 7228.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2405, pruned_loss=0.02829, over 1394622.77 frames.], batch size: 21, lr: 2.15e-04
2022-05-16 02:13:26,413 INFO [train.py:812] (3/8) Epoch 36, batch 4550, loss[loss=0.1544, simple_loss=0.2381, pruned_loss=0.0354, over 7255.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2412, pruned_loss=0.02867, over 1355543.76 frames.], batch size: 19, lr: 2.15e-04
2022-05-16 02:14:35,968 INFO [train.py:812] (3/8) Epoch 37, batch 0, loss[loss=0.1463, simple_loss=0.2444, pruned_loss=0.0241, over 7328.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2444, pruned_loss=0.0241, over 7328.00 frames.], batch size: 22, lr: 2.12e-04
2022-05-16 02:15:34,999 INFO [train.py:812] (3/8) Epoch 37, batch 50, loss[loss=0.1536, simple_loss=0.2472, pruned_loss=0.03003, over 7070.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2433, pruned_loss=0.03004, over 321531.10 frames.], batch size: 18, lr: 2.12e-04
2022-05-16 02:16:33,775 INFO [train.py:812] (3/8) Epoch 37, batch 100, loss[loss=0.13, simple_loss=0.2254, pruned_loss=0.01736, over 7348.00 frames.], tot_loss[loss=0.152, simple_loss=0.2444, pruned_loss=0.02984, over 566770.16 frames.], batch size: 20, lr: 2.12e-04
2022-05-16 02:17:32,742 INFO [train.py:812] (3/8) Epoch 37, batch 150, loss[loss=0.1551, simple_loss=0.2567, pruned_loss=0.02674, over 7035.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2447, pruned_loss=0.02988, over 753994.98 frames.], batch size: 28, lr: 2.11e-04
2022-05-16 02:18:31,117 INFO [train.py:812] (3/8) Epoch 37, batch 200, loss[loss=0.1424, simple_loss=0.236, pruned_loss=0.02438, over 7317.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2472, pruned_loss=0.03053, over 905753.24 frames.], batch size: 21, lr: 2.11e-04
2022-05-16 02:19:29,641 INFO [train.py:812] (3/8) Epoch 37, batch 250, loss[loss=0.1385, simple_loss=0.2247, pruned_loss=0.02612, over 7253.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2452, pruned_loss=0.02994, over 1017295.48 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:20:28,586 INFO [train.py:812] (3/8) Epoch 37, batch 300, loss[loss=0.169, simple_loss=0.2681, pruned_loss=0.03499, over 7317.00 frames.], tot_loss[loss=0.1526, simple_loss=0.245, pruned_loss=0.03013, over 1103815.24 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:21:27,115 INFO [train.py:812] (3/8) Epoch 37, batch 350, loss[loss=0.1305, simple_loss=0.2233, pruned_loss=0.0188, over 7179.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2448, pruned_loss=0.02997, over 1172276.81 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:22:25,667 INFO [train.py:812] (3/8) Epoch 37, batch 400, loss[loss=0.1649, simple_loss=0.2601, pruned_loss=0.03484, over 7222.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2436, pruned_loss=0.02938, over 1231807.61 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:23:24,618 INFO [train.py:812] (3/8) Epoch 37, batch 450, loss[loss=0.1537, simple_loss=0.2503, pruned_loss=0.02854, over 7145.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2439, pruned_loss=0.0292, over 1276152.85 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:24:21,868 INFO [train.py:812] (3/8) Epoch 37, batch 500, loss[loss=0.1402, simple_loss=0.2407, pruned_loss=0.01984, over 7232.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.02914, over 1306329.71 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:25:21,111 INFO [train.py:812] (3/8) Epoch 37, batch 550, loss[loss=0.1356, simple_loss=0.2332, pruned_loss=0.01903, over 7071.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2436, pruned_loss=0.02906, over 1321757.82 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:26:19,450 INFO [train.py:812] (3/8) Epoch 37, batch 600, loss[loss=0.1433, simple_loss=0.2397, pruned_loss=0.0235, over 7433.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2426, pruned_loss=0.02879, over 1346692.51 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:27:18,100 INFO [train.py:812] (3/8) Epoch 37, batch 650, loss[loss=0.1166, simple_loss=0.2074, pruned_loss=0.01293, over 7114.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.02851, over 1366551.43 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:28:16,810 INFO [train.py:812] (3/8) Epoch 37, batch 700, loss[loss=0.1403, simple_loss=0.2275, pruned_loss=0.02655, over 7235.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02854, over 1380100.00 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:29:16,835 INFO [train.py:812] (3/8) Epoch 37, batch 750, loss[loss=0.1363, simple_loss=0.2227, pruned_loss=0.02495, over 7141.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2424, pruned_loss=0.02868, over 1389141.08 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:30:15,264 INFO [train.py:812] (3/8) Epoch 37, batch 800, loss[loss=0.1354, simple_loss=0.2179, pruned_loss=0.0264, over 7397.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2422, pruned_loss=0.02859, over 1399181.31 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:31:14,053 INFO [train.py:812] (3/8) Epoch 37, batch 850, loss[loss=0.1249, simple_loss=0.2144, pruned_loss=0.01766, over 7265.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2431, pruned_loss=0.02932, over 1398518.99 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:32:12,869 INFO [train.py:812] (3/8) Epoch 37, batch 900, loss[loss=0.1394, simple_loss=0.2317, pruned_loss=0.0235, over 7063.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02898, over 1407184.13 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:33:11,830 INFO [train.py:812] (3/8) Epoch 37, batch 950, loss[loss=0.1181, simple_loss=0.2048, pruned_loss=0.01567, over 7281.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02873, over 1411003.00 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:34:09,861 INFO [train.py:812] (3/8) Epoch 37, batch 1000, loss[loss=0.1639, simple_loss=0.2773, pruned_loss=0.02526, over 6741.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02884, over 1413212.03 frames.], batch size: 31, lr: 2.11e-04
2022-05-16 02:35:08,721 INFO [train.py:812] (3/8) Epoch 37, batch 1050, loss[loss=0.1587, simple_loss=0.2475, pruned_loss=0.03493, over 7371.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2417, pruned_loss=0.02901, over 1417486.88 frames.], batch size: 23, lr: 2.11e-04
2022-05-16 02:36:07,864 INFO [train.py:812] (3/8) Epoch 37, batch 1100, loss[loss=0.1585, simple_loss=0.2642, pruned_loss=0.02636, over 7221.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02878, over 1419792.70 frames.], batch size: 21, lr: 2.11e-04
2022-05-16 02:37:06,617 INFO [train.py:812] (3/8) Epoch 37, batch 1150, loss[loss=0.1804, simple_loss=0.2659, pruned_loss=0.04746, over 5355.00 frames.], tot_loss[loss=0.15, simple_loss=0.2418, pruned_loss=0.02909, over 1419639.49 frames.], batch size: 52, lr: 2.11e-04
2022-05-16 02:38:04,301 INFO [train.py:812] (3/8) Epoch 37, batch 1200, loss[loss=0.1466, simple_loss=0.2483, pruned_loss=0.02246, over 7143.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02925, over 1421994.96 frames.], batch size: 20, lr: 2.11e-04
2022-05-16 02:39:03,398 INFO [train.py:812] (3/8) Epoch 37, batch 1250, loss[loss=0.1417, simple_loss=0.2383, pruned_loss=0.02252, over 7199.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2437, pruned_loss=0.02929, over 1421287.46 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:40:01,883 INFO [train.py:812] (3/8) Epoch 37, batch 1300, loss[loss=0.1402, simple_loss=0.2279, pruned_loss=0.02629, over 7130.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2439, pruned_loss=0.02937, over 1423852.20 frames.], batch size: 17, lr: 2.11e-04
2022-05-16 02:41:00,940 INFO [train.py:812] (3/8) Epoch 37, batch 1350, loss[loss=0.1505, simple_loss=0.2439, pruned_loss=0.02856, over 7072.00 frames.], tot_loss[loss=0.151, simple_loss=0.2436, pruned_loss=0.02918, over 1418450.75 frames.], batch size: 18, lr: 2.11e-04
2022-05-16 02:41:59,956 INFO [train.py:812] (3/8) Epoch 37, batch 1400, loss[loss=0.1298, simple_loss=0.219, pruned_loss=0.02028, over 6988.00 frames.], tot_loss[loss=0.1507, simple_loss=0.243, pruned_loss=0.02919, over 1417936.17 frames.], batch size: 16, lr: 2.11e-04
2022-05-16 02:42:58,499 INFO [train.py:812] (3/8) Epoch 37, batch 1450, loss[loss=0.1572, simple_loss=0.2498, pruned_loss=0.03232, over 7312.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2437, pruned_loss=0.02953, over 1420447.63 frames.], batch size: 24, lr: 2.11e-04
2022-05-16 02:43:56,623 INFO [train.py:812] (3/8) Epoch 37, batch 1500, loss[loss=0.1613, simple_loss=0.262, pruned_loss=0.03028, over 7302.00 frames.], tot_loss[loss=0.151, simple_loss=0.2434, pruned_loss=0.02932, over 1416613.41 frames.], batch size: 24, lr: 2.11e-04
2022-05-16 02:44:55,820 INFO [train.py:812] (3/8) Epoch 37, batch 1550, loss[loss=0.188, simple_loss=0.2746, pruned_loss=0.05068, over 6838.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2438, pruned_loss=0.02944, over 1411561.68 frames.], batch size: 31, lr: 2.11e-04
2022-05-16 02:45:53,996 INFO [train.py:812] (3/8) Epoch 37, batch 1600, loss[loss=0.1728, simple_loss=0.2726, pruned_loss=0.03654, over 7388.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2431, pruned_loss=0.02963, over 1412398.16 frames.], batch size: 23, lr: 2.11e-04
2022-05-16 02:46:52,089 INFO [train.py:812] (3/8) Epoch 37, batch 1650, loss[loss=0.177, simple_loss=0.2672, pruned_loss=0.04341, over 7196.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2432, pruned_loss=0.02958, over 1415428.21 frames.], batch size: 22, lr: 2.11e-04
2022-05-16 02:47:50,727 INFO [train.py:812] (3/8) Epoch 37, batch 1700, loss[loss=0.138, simple_loss=0.2317, pruned_loss=0.02211, over 7156.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2432, pruned_loss=0.02932, over 1414208.92 frames.], batch size: 19, lr: 2.11e-04
2022-05-16 02:48:48,826 INFO [train.py:812] (3/8) Epoch 37, batch 1750, loss[loss=0.1362, simple_loss=0.2239, pruned_loss=0.0242, over 7355.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2423, pruned_loss=0.02922, over 1409412.24 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:49:47,207 INFO [train.py:812] (3/8) Epoch 37, batch 1800, loss[loss=0.1733, simple_loss=0.2593, pruned_loss=0.04362, over 7305.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2431, pruned_loss=0.02957, over 1411040.57 frames.], batch size: 24, lr: 2.10e-04
2022-05-16 02:50:46,412 INFO [train.py:812] (3/8) Epoch 37, batch 1850, loss[loss=0.1378, simple_loss=0.2285, pruned_loss=0.02356, over 7269.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2424, pruned_loss=0.02962, over 1411341.25 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:51:45,048 INFO [train.py:812] (3/8) Epoch 37, batch 1900, loss[loss=0.1893, simple_loss=0.2868, pruned_loss=0.0459, over 6856.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2436, pruned_loss=0.02978, over 1417288.52 frames.], batch size: 31, lr: 2.10e-04
2022-05-16 02:52:44,039 INFO [train.py:812] (3/8) Epoch 37, batch 1950, loss[loss=0.1424, simple_loss=0.2467, pruned_loss=0.01909, over 7210.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02921, over 1420337.93 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:53:42,345 INFO [train.py:812] (3/8) Epoch 37, batch 2000, loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03279, over 7422.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2424, pruned_loss=0.02924, over 1417456.08 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:54:41,769 INFO [train.py:812] (3/8) Epoch 37, batch 2050, loss[loss=0.1512, simple_loss=0.2533, pruned_loss=0.02453, over 7238.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02859, over 1420421.59 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 02:55:38,575 INFO [train.py:812] (3/8) Epoch 37, batch 2100, loss[loss=0.1604, simple_loss=0.2571, pruned_loss=0.03181, over 7158.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2417, pruned_loss=0.02884, over 1419916.00 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 02:56:46,890 INFO [train.py:812] (3/8) Epoch 37, batch 2150, loss[loss=0.1335, simple_loss=0.2316, pruned_loss=0.01769, over 7417.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02896, over 1417589.29 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 02:57:45,126 INFO [train.py:812] (3/8) Epoch 37, batch 2200, loss[loss=0.1308, simple_loss=0.2182, pruned_loss=0.02174, over 7266.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02848, over 1418910.67 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 02:58:53,440 INFO [train.py:812] (3/8) Epoch 37, batch 2250, loss[loss=0.1557, simple_loss=0.2648, pruned_loss=0.02333, over 7143.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02884, over 1419878.25 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 03:00:01,413 INFO [train.py:812] (3/8) Epoch 37, batch 2300, loss[loss=0.1587, simple_loss=0.2595, pruned_loss=0.02891, over 7214.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2424, pruned_loss=0.02894, over 1419315.68 frames.], batch size: 23, lr: 2.10e-04
2022-05-16 03:01:01,004 INFO [train.py:812] (3/8) Epoch 37, batch 2350, loss[loss=0.1303, simple_loss=0.2147, pruned_loss=0.02295, over 7276.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02949, over 1413442.75 frames.], batch size: 17, lr: 2.10e-04
2022-05-16 03:01:59,214 INFO [train.py:812] (3/8) Epoch 37, batch 2400, loss[loss=0.1632, simple_loss=0.2671, pruned_loss=0.02969, over 7334.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02912, over 1419533.36 frames.], batch size: 25, lr: 2.10e-04
2022-05-16 03:02:57,113 INFO [train.py:812] (3/8) Epoch 37, batch 2450, loss[loss=0.1543, simple_loss=0.241, pruned_loss=0.0338, over 7100.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2422, pruned_loss=0.02909, over 1424876.52 frames.], batch size: 26, lr: 2.10e-04
2022-05-16 03:04:04,663 INFO [train.py:812] (3/8) Epoch 37, batch 2500, loss[loss=0.1343, simple_loss=0.2248, pruned_loss=0.02187, over 7152.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.0289, over 1427769.58 frames.], batch size: 19, lr: 2.10e-04
2022-05-16 03:05:04,381 INFO [train.py:812] (3/8) Epoch 37, batch 2550, loss[loss=0.1741, simple_loss=0.27, pruned_loss=0.03916, over 7290.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02909, over 1428918.49 frames.], batch size: 24, lr: 2.10e-04
2022-05-16 03:06:02,648 INFO [train.py:812] (3/8) Epoch 37, batch 2600, loss[loss=0.1352, simple_loss=0.2222, pruned_loss=0.02406, over 7300.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02874, over 1426074.63 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:07:21,594 INFO [train.py:812] (3/8) Epoch 37, batch 2650, loss[loss=0.1707, simple_loss=0.2596, pruned_loss=0.04092, over 7204.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2426, pruned_loss=0.02915, over 1429603.00 frames.], batch size: 22, lr: 2.10e-04
2022-05-16 03:08:19,629 INFO [train.py:812] (3/8) Epoch 37, batch 2700, loss[loss=0.1392, simple_loss=0.2393, pruned_loss=0.01955, over 6235.00 frames.], tot_loss[loss=0.151, simple_loss=0.243, pruned_loss=0.02952, over 1425424.73 frames.], batch size: 37, lr: 2.10e-04
2022-05-16 03:09:18,857 INFO [train.py:812] (3/8) Epoch 37, batch 2750, loss[loss=0.1635, simple_loss=0.2498, pruned_loss=0.03859, over 4999.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2428, pruned_loss=0.02903, over 1425528.53 frames.], batch size: 52, lr: 2.10e-04
2022-05-16 03:10:16,994 INFO [train.py:812] (3/8) Epoch 37, batch 2800, loss[loss=0.1255, simple_loss=0.2119, pruned_loss=0.01957, over 7281.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02877, over 1430444.95 frames.], batch size: 18, lr: 2.10e-04
2022-05-16 03:11:34,304 INFO [train.py:812] (3/8) Epoch 37, batch 2850, loss[loss=0.1654, simple_loss=0.2569, pruned_loss=0.03696, over 6564.00 frames.], tot_loss[loss=0.1495, simple_loss=0.242, pruned_loss=0.02852, over 1429168.10 frames.], batch size: 37, lr: 2.10e-04
2022-05-16 03:12:32,631 INFO [train.py:812] (3/8) Epoch 37, batch 2900, loss[loss=0.1229, simple_loss=0.2082, pruned_loss=0.01881, over 6998.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.0285, over 1429485.87 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:13:31,851 INFO [train.py:812] (3/8) Epoch 37, batch 2950, loss[loss=0.1333, simple_loss=0.2205, pruned_loss=0.02304, over 7430.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02841, over 1425728.89 frames.], batch size: 20, lr: 2.10e-04
2022-05-16 03:14:30,575 INFO [train.py:812] (3/8) Epoch 37, batch 3000, loss[loss=0.1549, simple_loss=0.2524, pruned_loss=0.02866, over 7214.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02885, over 1422623.08 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 03:14:30,576 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 03:14:38,087 INFO [train.py:841] (3/8) Epoch 37, validation: loss=0.1539, simple_loss=0.2491, pruned_loss=0.02931, over 698248.00 frames.
2022-05-16 03:15:37,672 INFO [train.py:812] (3/8) Epoch 37, batch 3050, loss[loss=0.1294, simple_loss=0.211, pruned_loss=0.0239, over 7223.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2428, pruned_loss=0.02948, over 1422226.75 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:16:36,459 INFO [train.py:812] (3/8) Epoch 37, batch 3100, loss[loss=0.1662, simple_loss=0.2537, pruned_loss=0.03936, over 7070.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2427, pruned_loss=0.02943, over 1419562.59 frames.], batch size: 18, lr: 2.10e-04
2022-05-16 03:17:34,873 INFO [train.py:812] (3/8) Epoch 37, batch 3150, loss[loss=0.1381, simple_loss=0.2219, pruned_loss=0.02708, over 6995.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2424, pruned_loss=0.02947, over 1418134.28 frames.], batch size: 16, lr: 2.10e-04
2022-05-16 03:18:33,949 INFO [train.py:812] (3/8) Epoch 37, batch 3200, loss[loss=0.1571, simple_loss=0.2471, pruned_loss=0.03359, over 4958.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2425, pruned_loss=0.02936, over 1418597.73 frames.], batch size: 52, lr: 2.10e-04
2022-05-16 03:19:33,580 INFO [train.py:812] (3/8) Epoch 37, batch 3250, loss[loss=0.1689, simple_loss=0.2658, pruned_loss=0.03599, over 7201.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2424, pruned_loss=0.02936, over 1417939.40 frames.], batch size: 22, lr: 2.10e-04
2022-05-16 03:20:31,423 INFO [train.py:812] (3/8) Epoch 37, batch 3300, loss[loss=0.148, simple_loss=0.243, pruned_loss=0.02651, over 7408.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2425, pruned_loss=0.02923, over 1415214.28 frames.], batch size: 21, lr: 2.10e-04
2022-05-16 03:21:29,408 INFO [train.py:812] (3/8) Epoch 37, batch 3350, loss[loss=0.1568, simple_loss=0.2502, pruned_loss=0.03169, over 7384.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2435, pruned_loss=0.02953, over 1411407.64 frames.], batch size: 23, lr: 2.09e-04
2022-05-16 03:22:27,820 INFO [train.py:812] (3/8) Epoch 37, batch 3400, loss[loss=0.1381, simple_loss=0.2186, pruned_loss=0.02883, over 7125.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2433, pruned_loss=0.02967, over 1416753.43 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:23:27,198 INFO [train.py:812] (3/8) Epoch 37, batch 3450, loss[loss=0.1272, simple_loss=0.2075, pruned_loss=0.02344, over 7294.00 frames.], tot_loss[loss=0.15, simple_loss=0.242, pruned_loss=0.02899, over 1419785.05 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:24:25,214 INFO [train.py:812] (3/8) Epoch 37, batch 3500, loss[loss=0.1363, simple_loss=0.23, pruned_loss=0.02135, over 7351.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2419, pruned_loss=0.02892, over 1417102.91 frames.], batch size: 19, lr: 2.09e-04
2022-05-16 03:25:24,374 INFO [train.py:812] (3/8) Epoch 37, batch 3550, loss[loss=0.1455, simple_loss=0.2321, pruned_loss=0.02948, over 6826.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2415, pruned_loss=0.02913, over 1414005.13 frames.], batch size: 15, lr: 2.09e-04
2022-05-16 03:26:23,184 INFO [train.py:812] (3/8) Epoch 37, batch 3600, loss[loss=0.13, simple_loss=0.2183, pruned_loss=0.02092, over 7008.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2406, pruned_loss=0.02874, over 1420337.99 frames.], batch size: 16, lr: 2.09e-04
2022-05-16 03:27:22,037 INFO [train.py:812] (3/8) Epoch 37, batch 3650, loss[loss=0.1316, simple_loss=0.2299, pruned_loss=0.0166, over 7151.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2403, pruned_loss=0.02847, over 1422643.51 frames.], batch size: 19, lr: 2.09e-04
2022-05-16 03:28:20,581 INFO [train.py:812] (3/8) Epoch 37, batch 3700, loss[loss=0.1384, simple_loss=0.2345, pruned_loss=0.02115, over 7245.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2407, pruned_loss=0.02847, over 1426011.85 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:29:19,681 INFO [train.py:812] (3/8) Epoch 37, batch 3750, loss[loss=0.1525, simple_loss=0.2429, pruned_loss=0.03106, over 7302.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2416, pruned_loss=0.02863, over 1423449.81 frames.], batch size: 24, lr: 2.09e-04
2022-05-16 03:30:17,095 INFO [train.py:812] (3/8) Epoch 37, batch 3800, loss[loss=0.1206, simple_loss=0.202, pruned_loss=0.01961, over 7268.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.02832, over 1425423.98 frames.], batch size: 17, lr: 2.09e-04
2022-05-16 03:31:15,864 INFO [train.py:812] (3/8) Epoch 37, batch 3850, loss[loss=0.1687, simple_loss=0.2602, pruned_loss=0.03859, over 5271.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02871, over 1424878.29 frames.], batch size: 54, lr: 2.09e-04
2022-05-16 03:32:12,577 INFO [train.py:812] (3/8) Epoch 37, batch 3900, loss[loss=0.1517, simple_loss=0.2529, pruned_loss=0.02526, over 7316.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02853, over 1426814.54 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:33:11,484 INFO [train.py:812] (3/8) Epoch 37, batch 3950, loss[loss=0.1388, simple_loss=0.2295, pruned_loss=0.02407, over 7275.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02889, over 1428451.87 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:34:09,785 INFO [train.py:812] (3/8) Epoch 37, batch 4000, loss[loss=0.1711, simple_loss=0.2587, pruned_loss=0.04171, over 7148.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02889, over 1428669.36 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:35:09,214 INFO [train.py:812] (3/8) Epoch 37, batch 4050, loss[loss=0.1584, simple_loss=0.2537, pruned_loss=0.0315, over 7148.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02872, over 1428131.66 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:36:06,893 INFO [train.py:812] (3/8) Epoch 37, batch 4100, loss[loss=0.1587, simple_loss=0.2598, pruned_loss=0.02879, over 7282.00 frames.], tot_loss[loss=0.15, simple_loss=0.2428, pruned_loss=0.02862, over 1425593.62 frames.], batch size: 25, lr: 2.09e-04
2022-05-16 03:37:05,680 INFO [train.py:812] (3/8) Epoch 37, batch 4150, loss[loss=0.1639, simple_loss=0.2529, pruned_loss=0.03747, over 7213.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02843, over 1426817.02 frames.], batch size: 21, lr: 2.09e-04
2022-05-16 03:38:02,986 INFO [train.py:812] (3/8) Epoch 37, batch 4200, loss[loss=0.1687, simple_loss=0.2694, pruned_loss=0.03399, over 7339.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.02855, over 1429022.05 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:39:02,452 INFO [train.py:812] (3/8) Epoch 37, batch 4250, loss[loss=0.1775, simple_loss=0.2668, pruned_loss=0.04405, over 7193.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02854, over 1431533.32 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:40:00,864 INFO [train.py:812] (3/8) Epoch 37, batch 4300, loss[loss=0.1438, simple_loss=0.242, pruned_loss=0.0228, over 7315.00 frames.], tot_loss[loss=0.15, simple_loss=0.2426, pruned_loss=0.02877, over 1425320.26 frames.], batch size: 20, lr: 2.09e-04
2022-05-16 03:41:00,630 INFO [train.py:812] (3/8) Epoch 37, batch 4350, loss[loss=0.1522, simple_loss=0.2572, pruned_loss=0.02363, over 7326.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2428, pruned_loss=0.02845, over 1429536.43 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:41:59,219 INFO [train.py:812] (3/8) Epoch 37, batch 4400, loss[loss=0.1534, simple_loss=0.254, pruned_loss=0.02643, over 7331.00 frames.], tot_loss[loss=0.1499, simple_loss=0.243, pruned_loss=0.02841, over 1421561.22 frames.], batch size: 22, lr: 2.09e-04
2022-05-16 03:42:59,058 INFO [train.py:812] (3/8) Epoch 37, batch 4450, loss[loss=0.1234, simple_loss=0.2101, pruned_loss=0.01839, over 7416.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2434, pruned_loss=0.02854, over 1420370.03 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:43:58,022 INFO [train.py:812] (3/8) Epoch 37, batch 4500, loss[loss=0.1298, simple_loss=0.2217, pruned_loss=0.01899, over 7292.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.02846, over 1415284.81 frames.], batch size: 18, lr: 2.09e-04
2022-05-16 03:44:56,301 INFO [train.py:812] (3/8) Epoch 37, batch 4550, loss[loss=0.1491, simple_loss=0.2464, pruned_loss=0.02591, over 6453.00 frames.], tot_loss[loss=0.1511, simple_loss=0.244, pruned_loss=0.02905, over 1391457.19 frames.], batch size: 37, lr: 2.09e-04
2022-05-16 03:46:01,487 INFO [train.py:812] (3/8) Epoch 38, batch 0, loss[loss=0.1486, simple_loss=0.2416, pruned_loss=0.02778, over 7357.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2416, pruned_loss=0.02778, over 7357.00 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:47:10,792 INFO [train.py:812] (3/8) Epoch 38, batch 50, loss[loss=0.1544, simple_loss=0.2479, pruned_loss=0.03045, over 6355.00 frames.], tot_loss[loss=0.149, simple_loss=0.2404, pruned_loss=0.02883, over 322423.02 frames.], batch size: 37, lr: 2.06e-04
2022-05-16 03:48:09,438 INFO [train.py:812] (3/8) Epoch 38, batch 100, loss[loss=0.1296, simple_loss=0.22, pruned_loss=0.01963, over 7255.00 frames.], tot_loss[loss=0.1495, simple_loss=0.241, pruned_loss=0.029, over 559896.72 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:49:08,228 INFO [train.py:812] (3/8) Epoch 38, batch 150, loss[loss=0.1478, simple_loss=0.2473, pruned_loss=0.02408, over 7383.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02934, over 747820.24 frames.], batch size: 23, lr: 2.06e-04
2022-05-16 03:50:07,469 INFO [train.py:812] (3/8) Epoch 38, batch 200, loss[loss=0.1471, simple_loss=0.2472, pruned_loss=0.02347, over 7405.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2414, pruned_loss=0.02861, over 896490.77 frames.], batch size: 21, lr: 2.06e-04
2022-05-16 03:51:06,653 INFO [train.py:812] (3/8) Epoch 38, batch 250, loss[loss=0.139, simple_loss=0.2251, pruned_loss=0.02649, over 7358.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02814, over 1015283.67 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:52:05,095 INFO [train.py:812] (3/8) Epoch 38, batch 300, loss[loss=0.1628, simple_loss=0.2579, pruned_loss=0.03386, over 7236.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2423, pruned_loss=0.02899, over 1104712.77 frames.], batch size: 20, lr: 2.06e-04
2022-05-16 03:53:04,633 INFO [train.py:812] (3/8) Epoch 38, batch 350, loss[loss=0.1302, simple_loss=0.2237, pruned_loss=0.01836, over 7259.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2425, pruned_loss=0.02891, over 1172031.12 frames.], batch size: 19, lr: 2.06e-04
2022-05-16 03:54:02,519 INFO [train.py:812] (3/8) Epoch 38, batch 400, loss[loss=0.1332, simple_loss=0.2129, pruned_loss=0.02673, over 7279.00 frames.], tot_loss[loss=0.15, simple_loss=0.2428, pruned_loss=0.02856, over 1232192.49 frames.], batch size: 17, lr: 2.06e-04
2022-05-16 03:55:02,079 INFO [train.py:812] (3/8) Epoch 38, batch 450, loss[loss=0.1543, simple_loss=0.2563, pruned_loss=0.02617, over 7106.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02851, over 1275110.27 frames.], batch size: 21, lr: 2.06e-04
2022-05-16 03:56:00,717 INFO [train.py:812] (3/8) Epoch 38, batch 500, loss[loss=0.1318, simple_loss=0.2289, pruned_loss=0.01732, over 7288.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02853, over 1311756.58 frames.], batch size: 18, lr: 2.06e-04
2022-05-16 03:56:58,593 INFO [train.py:812] (3/8) Epoch 38, batch 550, loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02849, over 7333.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02882, over 1335979.40 frames.], batch size: 20, lr: 2.06e-04
2022-05-16 03:57:56,242 INFO [train.py:812] (3/8) Epoch 38, batch 600, loss[loss=0.1715, simple_loss=0.2579, pruned_loss=0.04258, over 7388.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2429, pruned_loss=0.02892, over 1357366.04 frames.], batch size: 23, lr: 2.06e-04
2022-05-16 03:58:54,201 INFO [train.py:812] (3/8) Epoch 38, batch 650, loss[loss=0.1563, simple_loss=0.2566, pruned_loss=0.02795, over 7343.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02881, over 1374174.89 frames.], batch size: 22, lr: 2.06e-04
2022-05-16 03:59:53,351 INFO [train.py:812] (3/8) Epoch 38, batch 700, loss[loss=0.1527, simple_loss=0.246, pruned_loss=0.02966, over 7170.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2428, pruned_loss=0.02877, over 1386843.87 frames.], batch size: 18, lr: 2.06e-04
2022-05-16 04:00:52,136 INFO [train.py:812] (3/8) Epoch 38, batch 750, loss[loss=0.1586, simple_loss=0.2514, pruned_loss=0.03289, over 7397.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2433, pruned_loss=0.02847, over 1401265.29 frames.], batch size: 23, lr: 2.05e-04
2022-05-16 04:01:50,304 INFO [train.py:812] (3/8) Epoch 38, batch 800, loss[loss=0.1288, simple_loss=0.2138, pruned_loss=0.02194, over 7402.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2435, pruned_loss=0.02841, over 1409107.05 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:02:49,119 INFO [train.py:812] (3/8) Epoch 38, batch 850, loss[loss=0.1334, simple_loss=0.2144, pruned_loss=0.02618, over 7366.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2429, pruned_loss=0.02808, over 1411556.32 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:03:47,718 INFO [train.py:812] (3/8) Epoch 38, batch 900, loss[loss=0.1529, simple_loss=0.2545, pruned_loss=0.02561, over 7292.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2425, pruned_loss=0.02802, over 1413045.61 frames.], batch size: 24, lr: 2.05e-04
2022-05-16 04:04:46,169 INFO [train.py:812] (3/8) Epoch 38, batch 950, loss[loss=0.1336, simple_loss=0.2215, pruned_loss=0.02284, over 7253.00 frames.], tot_loss[loss=0.15, simple_loss=0.2432, pruned_loss=0.0284, over 1418169.83 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:05:44,613 INFO [train.py:812] (3/8) Epoch 38, batch 1000, loss[loss=0.1621, simple_loss=0.2509, pruned_loss=0.03667, over 7203.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2427, pruned_loss=0.02818, over 1421200.31 frames.], batch size: 22, lr: 2.05e-04
2022-05-16 04:06:43,937 INFO [train.py:812] (3/8) Epoch 38, batch 1050, loss[loss=0.149, simple_loss=0.2415, pruned_loss=0.02824, over 7334.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2432, pruned_loss=0.02826, over 1422162.61 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:07:41,755 INFO [train.py:812] (3/8) Epoch 38, batch 1100, loss[loss=0.1347, simple_loss=0.2208, pruned_loss=0.02434, over 7226.00 frames.], tot_loss[loss=0.1495, simple_loss=0.243, pruned_loss=0.02795, over 1426477.29 frames.], batch size: 16, lr: 2.05e-04
2022-05-16 04:08:41,047 INFO [train.py:812] (3/8) Epoch 38, batch 1150, loss[loss=0.1423, simple_loss=0.2289, pruned_loss=0.02783, over 7256.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2427, pruned_loss=0.02833, over 1423410.64 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:09:40,636 INFO [train.py:812] (3/8) Epoch 38, batch 1200, loss[loss=0.146, simple_loss=0.2471, pruned_loss=0.02247, over 7204.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2425, pruned_loss=0.02821, over 1425256.09 frames.], batch size: 26, lr: 2.05e-04
2022-05-16 04:10:39,684 INFO [train.py:812] (3/8) Epoch 38, batch 1250, loss[loss=0.186, simple_loss=0.2855, pruned_loss=0.04323, over 6319.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2423, pruned_loss=0.02819, over 1428530.06 frames.], batch size: 37, lr: 2.05e-04
2022-05-16 04:11:38,489 INFO [train.py:812] (3/8) Epoch 38, batch 1300, loss[loss=0.1339, simple_loss=0.2128, pruned_loss=0.02748, over 7281.00 frames.], tot_loss[loss=0.1503, simple_loss=0.243, pruned_loss=0.02881, over 1427398.29 frames.], batch size: 17, lr: 2.05e-04
2022-05-16 04:12:36,172 INFO [train.py:812] (3/8) Epoch 38, batch 1350, loss[loss=0.1375, simple_loss=0.2375, pruned_loss=0.01878, over 7115.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02869, over 1421532.29 frames.], batch size: 21, lr: 2.05e-04
2022-05-16 04:13:33,876 INFO [train.py:812] (3/8) Epoch 38, batch 1400, loss[loss=0.1568, simple_loss=0.2461, pruned_loss=0.03375, over 7313.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02885, over 1421657.56 frames.], batch size: 24, lr: 2.05e-04
2022-05-16 04:14:32,882 INFO [train.py:812] (3/8) Epoch 38, batch 1450, loss[loss=0.1798, simple_loss=0.2665, pruned_loss=0.04648, over 7189.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2431, pruned_loss=0.02923, over 1425855.30 frames.], batch size: 22, lr: 2.05e-04
2022-05-16 04:15:31,394 INFO [train.py:812] (3/8) Epoch 38, batch 1500, loss[loss=0.1619, simple_loss=0.255, pruned_loss=0.03442, over 7274.00 frames.], tot_loss[loss=0.1506, simple_loss=0.243, pruned_loss=0.02907, over 1425683.65 frames.], batch size: 25, lr: 2.05e-04
2022-05-16 04:16:30,117 INFO [train.py:812] (3/8) Epoch 38, batch 1550, loss[loss=0.1426, simple_loss=0.2391, pruned_loss=0.02309, over 7231.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2432, pruned_loss=0.02924, over 1422925.90 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:17:27,390 INFO [train.py:812] (3/8) Epoch 38, batch 1600, loss[loss=0.1504, simple_loss=0.236, pruned_loss=0.0324, over 7267.00 frames.], tot_loss[loss=0.1505, simple_loss=0.243, pruned_loss=0.029, over 1425799.69 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:18:25,547 INFO [train.py:812] (3/8) Epoch 38, batch 1650, loss[loss=0.1537, simple_loss=0.2558, pruned_loss=0.02581, over 7109.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.029, over 1425491.94 frames.], batch size: 28, lr: 2.05e-04
2022-05-16 04:19:24,088 INFO [train.py:812] (3/8) Epoch 38, batch 1700, loss[loss=0.1385, simple_loss=0.2252, pruned_loss=0.02594, over 7164.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02872, over 1424310.89 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:20:24,537 INFO [train.py:812] (3/8) Epoch 38, batch 1750, loss[loss=0.1815, simple_loss=0.263, pruned_loss=0.05003, over 5103.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02867, over 1422859.98 frames.], batch size: 52, lr: 2.05e-04
2022-05-16 04:21:23,204 INFO [train.py:812] (3/8) Epoch 38, batch 1800, loss[loss=0.153, simple_loss=0.2538, pruned_loss=0.02611, over 7335.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02896, over 1419690.39 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:22:21,139 INFO [train.py:812] (3/8) Epoch 38, batch 1850, loss[loss=0.171, simple_loss=0.2622, pruned_loss=0.0399, over 7271.00 frames.], tot_loss[loss=0.1491, simple_loss=0.241, pruned_loss=0.02858, over 1422395.83 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:23:20,137 INFO [train.py:812] (3/8) Epoch 38, batch 1900, loss[loss=0.1542, simple_loss=0.2392, pruned_loss=0.03457, over 6885.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02881, over 1424952.94 frames.], batch size: 15, lr: 2.05e-04
2022-05-16 04:24:18,760 INFO [train.py:812] (3/8) Epoch 38, batch 1950, loss[loss=0.1451, simple_loss=0.2347, pruned_loss=0.0278, over 7259.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02863, over 1427761.63 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:25:17,610 INFO [train.py:812] (3/8) Epoch 38, batch 2000, loss[loss=0.1374, simple_loss=0.2308, pruned_loss=0.02199, over 7395.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2427, pruned_loss=0.02885, over 1426362.91 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:26:16,384 INFO [train.py:812] (3/8) Epoch 38, batch 2050, loss[loss=0.1361, simple_loss=0.2368, pruned_loss=0.01775, over 7246.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2429, pruned_loss=0.02888, over 1423246.04 frames.], batch size: 19, lr: 2.05e-04
2022-05-16 04:27:14,048 INFO [train.py:812] (3/8) Epoch 38, batch 2100, loss[loss=0.1623, simple_loss=0.2536, pruned_loss=0.03547, over 7182.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2441, pruned_loss=0.02953, over 1418094.64 frames.], batch size: 26, lr: 2.05e-04
2022-05-16 04:28:12,418 INFO [train.py:812] (3/8) Epoch 38, batch 2150, loss[loss=0.1155, simple_loss=0.2104, pruned_loss=0.01026, over 7059.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2437, pruned_loss=0.02936, over 1418239.96 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:29:11,129 INFO [train.py:812] (3/8) Epoch 38, batch 2200, loss[loss=0.1302, simple_loss=0.2164, pruned_loss=0.022, over 7077.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2441, pruned_loss=0.02935, over 1419698.48 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:30:15,088 INFO [train.py:812] (3/8) Epoch 38, batch 2250, loss[loss=0.1624, simple_loss=0.2525, pruned_loss=0.03611, over 6490.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2441, pruned_loss=0.02939, over 1418672.76 frames.], batch size: 38, lr: 2.05e-04
2022-05-16 04:31:14,143 INFO [train.py:812] (3/8) Epoch 38, batch 2300, loss[loss=0.1289, simple_loss=0.2181, pruned_loss=0.01987, over 7063.00 frames.], tot_loss[loss=0.1511, simple_loss=0.244, pruned_loss=0.02908, over 1422756.39 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:32:13,302 INFO [train.py:812] (3/8) Epoch 38, batch 2350, loss[loss=0.1479, simple_loss=0.2419, pruned_loss=0.02702, over 7329.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2437, pruned_loss=0.02896, over 1421008.12 frames.], batch size: 20, lr: 2.05e-04
2022-05-16 04:33:12,147 INFO [train.py:812] (3/8) Epoch 38, batch 2400, loss[loss=0.1345, simple_loss=0.218, pruned_loss=0.02549, over 7410.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2427, pruned_loss=0.02852, over 1425857.86 frames.], batch size: 18, lr: 2.05e-04
2022-05-16 04:34:10,722 INFO [train.py:812] (3/8) Epoch 38, batch 2450, loss[loss=0.1313, simple_loss=0.2286, pruned_loss=0.01698, over 7326.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2427, pruned_loss=0.02817, over 1428246.96 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:35:08,787 INFO [train.py:812] (3/8) Epoch 38, batch 2500, loss[loss=0.1367, simple_loss=0.2281, pruned_loss=0.02263, over 7168.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2424, pruned_loss=0.02815, over 1428059.21 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:36:06,690 INFO [train.py:812] (3/8) Epoch 38, batch 2550, loss[loss=0.1333, simple_loss=0.2178, pruned_loss=0.02436, over 7169.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2415, pruned_loss=0.02777, over 1425310.84 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:37:05,279 INFO [train.py:812] (3/8) Epoch 38, batch 2600, loss[loss=0.1461, simple_loss=0.2384, pruned_loss=0.02692, over 7429.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2414, pruned_loss=0.02813, over 1424309.69 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:38:03,415 INFO [train.py:812] (3/8) Epoch 38, batch 2650, loss[loss=0.1562, simple_loss=0.2529, pruned_loss=0.02975, over 7203.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02876, over 1425285.76 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:39:01,023 INFO [train.py:812] (3/8) Epoch 38, batch 2700, loss[loss=0.1557, simple_loss=0.2443, pruned_loss=0.0335, over 7231.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02858, over 1424685.05 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:39:59,838 INFO [train.py:812] (3/8) Epoch 38, batch 2750, loss[loss=0.1428, simple_loss=0.2404, pruned_loss=0.02258, over 7353.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.02851, over 1425909.84 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 04:40:57,546 INFO [train.py:812] (3/8) Epoch 38, batch 2800, loss[loss=0.1665, simple_loss=0.2644, pruned_loss=0.03431, over 7295.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2422, pruned_loss=0.0287, over 1423919.34 frames.], batch size: 24, lr: 2.04e-04
2022-05-16 04:41:55,555 INFO [train.py:812] (3/8) Epoch 38, batch 2850, loss[loss=0.1341, simple_loss=0.2257, pruned_loss=0.02121, over 7414.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2419, pruned_loss=0.02891, over 1424046.62 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 04:42:54,121 INFO [train.py:812] (3/8) Epoch 38, batch 2900, loss[loss=0.1251, simple_loss=0.2154, pruned_loss=0.01738, over 7144.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2409, pruned_loss=0.02861, over 1424262.64 frames.], batch size: 17, lr: 2.04e-04
2022-05-16 04:43:53,031 INFO [train.py:812] (3/8) Epoch 38, batch 2950, loss[loss=0.1244, simple_loss=0.205, pruned_loss=0.02191, over 7415.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.02834, over 1428692.15 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:44:52,016 INFO [train.py:812] (3/8) Epoch 38, batch 3000, loss[loss=0.1667, simple_loss=0.2623, pruned_loss=0.03556, over 7224.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02847, over 1428402.19 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:44:52,017 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 04:44:59,416 INFO [train.py:841] (3/8) Epoch 38, validation: loss=0.1532, simple_loss=0.2484, pruned_loss=0.02898, over 698248.00 frames.
2022-05-16 04:45:58,530 INFO [train.py:812] (3/8) Epoch 38, batch 3050, loss[loss=0.1392, simple_loss=0.2282, pruned_loss=0.02515, over 7166.00 frames.], tot_loss[loss=0.15, simple_loss=0.2423, pruned_loss=0.0289, over 1428490.12 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:46:56,199 INFO [train.py:812] (3/8) Epoch 38, batch 3100, loss[loss=0.1557, simple_loss=0.2467, pruned_loss=0.03231, over 7206.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2428, pruned_loss=0.02931, over 1421955.82 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 04:47:54,532 INFO [train.py:812] (3/8) Epoch 38, batch 3150, loss[loss=0.1567, simple_loss=0.2505, pruned_loss=0.03146, over 7381.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2427, pruned_loss=0.02918, over 1421290.82 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 04:48:52,453 INFO [train.py:812] (3/8) Epoch 38, batch 3200, loss[loss=0.1558, simple_loss=0.2507, pruned_loss=0.03048, over 7121.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2428, pruned_loss=0.02924, over 1425441.10 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 04:49:51,332 INFO [train.py:812] (3/8) Epoch 38, batch 3250, loss[loss=0.1316, simple_loss=0.2149, pruned_loss=0.02414, over 7302.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02912, over 1426434.58 frames.], batch size: 18, lr: 2.04e-04
2022-05-16 04:50:49,196 INFO [train.py:812] (3/8) Epoch 38, batch 3300, loss[loss=0.1436, simple_loss=0.2394, pruned_loss=0.0239, over 7233.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2418, pruned_loss=0.02931, over 1425789.99 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:51:47,389 INFO [train.py:812] (3/8) Epoch 38, batch 3350, loss[loss=0.1625, simple_loss=0.2571, pruned_loss=0.03392, over 7190.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2426, pruned_loss=0.02931, over 1426325.52 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 04:52:45,589 INFO [train.py:812] (3/8) Epoch 38, batch 3400, loss[loss=0.1446, simple_loss=0.2412, pruned_loss=0.024, over 6815.00 frames.], tot_loss[loss=0.15, simple_loss=0.2422, pruned_loss=0.02888, over 1430310.03 frames.], batch size: 31, lr: 2.04e-04
2022-05-16 04:53:45,206 INFO [train.py:812] (3/8) Epoch 38, batch 3450, loss[loss=0.1477, simple_loss=0.2439, pruned_loss=0.02571, over 7430.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2422, pruned_loss=0.02885, over 1431417.60 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:54:43,562 INFO [train.py:812] (3/8) Epoch 38, batch 3500, loss[loss=0.1346, simple_loss=0.2326, pruned_loss=0.01829, over 7227.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2421, pruned_loss=0.02887, over 1430596.39 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:55:41,794 INFO [train.py:812] (3/8) Epoch 38, batch 3550, loss[loss=0.1726, simple_loss=0.2609, pruned_loss=0.04213, over 7141.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2431, pruned_loss=0.02898, over 1430871.40 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 04:56:49,698 INFO [train.py:812] (3/8) Epoch 38, batch 3600, loss[loss=0.1774, simple_loss=0.2691, pruned_loss=0.04285, over 6659.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2432, pruned_loss=0.02888, over 1428919.40 frames.], batch size: 31, lr: 2.04e-04
2022-05-16 04:57:48,349 INFO [train.py:812] (3/8) Epoch 38, batch 3650, loss[loss=0.1471, simple_loss=0.2453, pruned_loss=0.0245, over 7149.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2432, pruned_loss=0.02909, over 1431359.99 frames.], batch size: 28, lr: 2.04e-04
2022-05-16 04:58:46,155 INFO [train.py:812] (3/8) Epoch 38, batch 3700, loss[loss=0.1458, simple_loss=0.2535, pruned_loss=0.01906, over 7278.00 frames.], tot_loss[loss=0.1508, simple_loss=0.243, pruned_loss=0.02925, over 1422844.46 frames.], batch size: 24, lr: 2.04e-04
2022-05-16 05:00:03,396 INFO [train.py:812] (3/8) Epoch 38, batch 3750, loss[loss=0.1576, simple_loss=0.2442, pruned_loss=0.03552, over 7164.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2427, pruned_loss=0.02909, over 1418805.62 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 05:01:01,771 INFO [train.py:812] (3/8) Epoch 38, batch 3800, loss[loss=0.1546, simple_loss=0.2448, pruned_loss=0.03217, over 7374.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2413, pruned_loss=0.02858, over 1419530.54 frames.], batch size: 23, lr: 2.04e-04
2022-05-16 05:02:01,372 INFO [train.py:812] (3/8) Epoch 38, batch 3850, loss[loss=0.1543, simple_loss=0.2577, pruned_loss=0.02549, over 7111.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2411, pruned_loss=0.02858, over 1422210.25 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 05:03:01,108 INFO [train.py:812] (3/8) Epoch 38, batch 3900, loss[loss=0.1303, simple_loss=0.2247, pruned_loss=0.01795, over 7328.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2416, pruned_loss=0.02891, over 1423560.19 frames.], batch size: 20, lr: 2.04e-04
2022-05-16 05:03:59,298 INFO [train.py:812] (3/8) Epoch 38, batch 3950, loss[loss=0.1453, simple_loss=0.2433, pruned_loss=0.02363, over 7214.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.02849, over 1418886.63 frames.], batch size: 22, lr: 2.04e-04
2022-05-16 05:04:56,830 INFO [train.py:812] (3/8) Epoch 38, batch 4000, loss[loss=0.1576, simple_loss=0.2462, pruned_loss=0.03456, over 7163.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02851, over 1419402.47 frames.], batch size: 19, lr: 2.04e-04
2022-05-16 05:06:06,116 INFO [train.py:812] (3/8) Epoch 38, batch 4050, loss[loss=0.1388, simple_loss=0.2237, pruned_loss=0.02696, over 7264.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02853, over 1413208.03 frames.], batch size: 17, lr: 2.04e-04
2022-05-16 05:07:14,549 INFO [train.py:812] (3/8) Epoch 38, batch 4100, loss[loss=0.1572, simple_loss=0.2531, pruned_loss=0.03064, over 7212.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2421, pruned_loss=0.02871, over 1414994.12 frames.], batch size: 21, lr: 2.04e-04
2022-05-16 05:08:13,991 INFO [train.py:812] (3/8) Epoch 38, batch 4150, loss[loss=0.164, simple_loss=0.248, pruned_loss=0.03996, over 7255.00 frames.], tot_loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02852, over 1414485.32 frames.], batch size: 19, lr: 2.03e-04
2022-05-16 05:09:21,218 INFO [train.py:812] (3/8) Epoch 38, batch 4200, loss[loss=0.1762, simple_loss=0.2624, pruned_loss=0.04504, over 7289.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2409, pruned_loss=0.02841, over 1415632.61 frames.], batch size: 24, lr: 2.03e-04
2022-05-16 05:10:29,490 INFO [train.py:812] (3/8) Epoch 38, batch 4250, loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03073, over 7242.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2416, pruned_loss=0.02866, over 1416191.82 frames.], batch size: 20, lr: 2.03e-04
2022-05-16 05:11:27,939 INFO [train.py:812] (3/8) Epoch 38, batch 4300, loss[loss=0.1553, simple_loss=0.2516, pruned_loss=0.02945, over 4777.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2409, pruned_loss=0.02888, over 1413715.55 frames.], batch size: 52, lr: 2.03e-04
2022-05-16 05:12:26,641 INFO [train.py:812] (3/8) Epoch 38, batch 4350, loss[loss=0.1309, simple_loss=0.2194, pruned_loss=0.02125, over 6998.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2396, pruned_loss=0.0285, over 1415631.46 frames.], batch size: 16, lr: 2.03e-04
2022-05-16 05:13:26,088 INFO [train.py:812] (3/8) Epoch 38, batch 4400, loss[loss=0.1316, simple_loss=0.2169, pruned_loss=0.02316, over 6771.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2391, pruned_loss=0.02795, over 1416061.03 frames.], batch size: 15, lr: 2.03e-04
2022-05-16 05:14:25,870 INFO [train.py:812] (3/8) Epoch 38, batch 4450, loss[loss=0.1576, simple_loss=0.2456, pruned_loss=0.03485, over 6857.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2382, pruned_loss=0.02814, over 1407966.87 frames.], batch size: 15, lr: 2.03e-04
2022-05-16 05:15:24,205 INFO [train.py:812] (3/8) Epoch 38, batch 4500, loss[loss=0.1445, simple_loss=0.2442, pruned_loss=0.02239, over 6401.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2387, pruned_loss=0.0287, over 1382590.92 frames.], batch size: 37, lr: 2.03e-04
2022-05-16 05:16:23,035 INFO [train.py:812] (3/8) Epoch 38, batch 4550, loss[loss=0.1626, simple_loss=0.2486, pruned_loss=0.03833, over 5026.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2379, pruned_loss=0.02882, over 1356862.25 frames.], batch size: 53, lr: 2.03e-04
2022-05-16 05:17:28,541 INFO [train.py:812] (3/8) Epoch 39, batch 0, loss[loss=0.1482, simple_loss=0.2463, pruned_loss=0.02509, over 7266.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2463, pruned_loss=0.02509, over 7266.00 frames.], batch size: 19, lr: 2.01e-04
2022-05-16 05:18:26,906 INFO [train.py:812] (3/8) Epoch 39, batch 50, loss[loss=0.1574, simple_loss=0.2591, pruned_loss=0.02789, over 7151.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2423, pruned_loss=0.02675, over 320683.32 frames.], batch size: 20, lr: 2.01e-04
2022-05-16 05:19:25,801 INFO [train.py:812] (3/8) Epoch 39, batch 100, loss[loss=0.1754, simple_loss=0.2675, pruned_loss=0.04165, over 6725.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2434, pruned_loss=0.02854, over 565749.13 frames.], batch size: 31, lr: 2.01e-04
2022-05-16 05:20:24,082 INFO [train.py:812] (3/8) Epoch 39, batch 150, loss[loss=0.1278, simple_loss=0.2183, pruned_loss=0.01863, over 7159.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.0289, over 754410.52 frames.], batch size: 18, lr: 2.01e-04
2022-05-16 05:21:22,503 INFO [train.py:812] (3/8) Epoch 39, batch 200, loss[loss=0.1448, simple_loss=0.2412, pruned_loss=0.02425, over 7444.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2426, pruned_loss=0.02863, over 901541.45 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:22:20,446 INFO [train.py:812] (3/8) Epoch 39, batch 250, loss[loss=0.15, simple_loss=0.2452, pruned_loss=0.02738, over 6378.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02826, over 1017062.11 frames.], batch size: 37, lr: 2.00e-04
2022-05-16 05:23:19,144 INFO [train.py:812] (3/8) Epoch 39, batch 300, loss[loss=0.1488, simple_loss=0.2382, pruned_loss=0.02963, over 7436.00 frames.], tot_loss[loss=0.1494, simple_loss=0.242, pruned_loss=0.02842, over 1111971.16 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:24:17,709 INFO [train.py:812] (3/8) Epoch 39, batch 350, loss[loss=0.1526, simple_loss=0.2488, pruned_loss=0.02823, over 7308.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02818, over 1178370.31 frames.], batch size: 24, lr: 2.00e-04
2022-05-16 05:25:17,160 INFO [train.py:812] (3/8) Epoch 39, batch 400, loss[loss=0.1543, simple_loss=0.2532, pruned_loss=0.02768, over 7221.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2414, pruned_loss=0.02794, over 1227908.15 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:26:16,266 INFO [train.py:812] (3/8) Epoch 39, batch 450, loss[loss=0.1749, simple_loss=0.2647, pruned_loss=0.04252, over 7190.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02857, over 1273219.62 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:27:15,058 INFO [train.py:812] (3/8) Epoch 39, batch 500, loss[loss=0.1534, simple_loss=0.2507, pruned_loss=0.02799, over 7146.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2419, pruned_loss=0.02874, over 1300184.55 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:28:14,642 INFO [train.py:812] (3/8) Epoch 39, batch 550, loss[loss=0.1473, simple_loss=0.242, pruned_loss=0.02627, over 7432.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02872, over 1325802.79 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:29:14,827 INFO [train.py:812] (3/8) Epoch 39, batch 600, loss[loss=0.1517, simple_loss=0.2386, pruned_loss=0.03245, over 7160.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2419, pruned_loss=0.02853, over 1344600.90 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:30:14,577 INFO [train.py:812] (3/8) Epoch 39, batch 650, loss[loss=0.1216, simple_loss=0.2019, pruned_loss=0.02068, over 7271.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2413, pruned_loss=0.02855, over 1364330.05 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:31:13,689 INFO [train.py:812] (3/8) Epoch 39, batch 700, loss[loss=0.1192, simple_loss=0.2026, pruned_loss=0.01789, over 6800.00 frames.], tot_loss[loss=0.1481, simple_loss=0.24, pruned_loss=0.02809, over 1377018.08 frames.], batch size: 15, lr: 2.00e-04
2022-05-16 05:32:12,659 INFO [train.py:812] (3/8) Epoch 39, batch 750, loss[loss=0.1488, simple_loss=0.2463, pruned_loss=0.02566, over 6350.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2402, pruned_loss=0.02785, over 1386249.83 frames.], batch size: 38, lr: 2.00e-04
2022-05-16 05:33:12,266 INFO [train.py:812] (3/8) Epoch 39, batch 800, loss[loss=0.1527, simple_loss=0.2441, pruned_loss=0.03064, over 7247.00 frames.], tot_loss[loss=0.148, simple_loss=0.2404, pruned_loss=0.02785, over 1399477.52 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:34:10,577 INFO [train.py:812] (3/8) Epoch 39, batch 850, loss[loss=0.1703, simple_loss=0.2672, pruned_loss=0.03671, over 7117.00 frames.], tot_loss[loss=0.1478, simple_loss=0.24, pruned_loss=0.02784, over 1405484.09 frames.], batch size: 28, lr: 2.00e-04
2022-05-16 05:35:08,786 INFO [train.py:812] (3/8) Epoch 39, batch 900, loss[loss=0.1661, simple_loss=0.2645, pruned_loss=0.03385, over 7413.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2407, pruned_loss=0.02829, over 1404450.82 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:36:07,915 INFO [train.py:812] (3/8) Epoch 39, batch 950, loss[loss=0.1352, simple_loss=0.2204, pruned_loss=0.02497, over 7127.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.02846, over 1405765.68 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:37:07,606 INFO [train.py:812] (3/8) Epoch 39, batch 1000, loss[loss=0.147, simple_loss=0.2419, pruned_loss=0.02602, over 7352.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.02826, over 1408728.05 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:38:06,537 INFO [train.py:812] (3/8) Epoch 39, batch 1050, loss[loss=0.1485, simple_loss=0.2472, pruned_loss=0.02493, over 6686.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2409, pruned_loss=0.02845, over 1411522.84 frames.], batch size: 31, lr: 2.00e-04
2022-05-16 05:39:05,050 INFO [train.py:812] (3/8) Epoch 39, batch 1100, loss[loss=0.1835, simple_loss=0.2708, pruned_loss=0.0481, over 7387.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2407, pruned_loss=0.02836, over 1415597.17 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:40:03,842 INFO [train.py:812] (3/8) Epoch 39, batch 1150, loss[loss=0.1297, simple_loss=0.2191, pruned_loss=0.02016, over 7290.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2397, pruned_loss=0.02791, over 1418933.52 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:41:02,387 INFO [train.py:812] (3/8) Epoch 39, batch 1200, loss[loss=0.1668, simple_loss=0.2635, pruned_loss=0.03504, over 6823.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2408, pruned_loss=0.02845, over 1420426.95 frames.], batch size: 31, lr: 2.00e-04
2022-05-16 05:42:00,508 INFO [train.py:812] (3/8) Epoch 39, batch 1250, loss[loss=0.1386, simple_loss=0.2319, pruned_loss=0.02259, over 7432.00 frames.], tot_loss[loss=0.1491, simple_loss=0.241, pruned_loss=0.02856, over 1421323.09 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:42:59,391 INFO [train.py:812] (3/8) Epoch 39, batch 1300, loss[loss=0.1259, simple_loss=0.2125, pruned_loss=0.01968, over 7286.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2405, pruned_loss=0.02824, over 1425576.84 frames.], batch size: 17, lr: 2.00e-04
2022-05-16 05:43:56,601 INFO [train.py:812] (3/8) Epoch 39, batch 1350, loss[loss=0.145, simple_loss=0.2403, pruned_loss=0.02487, over 7334.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.02813, over 1425530.31 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:45:05,768 INFO [train.py:812] (3/8) Epoch 39, batch 1400, loss[loss=0.1364, simple_loss=0.2297, pruned_loss=0.02151, over 7156.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2405, pruned_loss=0.02841, over 1425032.02 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:46:03,939 INFO [train.py:812] (3/8) Epoch 39, batch 1450, loss[loss=0.1606, simple_loss=0.2513, pruned_loss=0.03498, over 7294.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2404, pruned_loss=0.02803, over 1425565.95 frames.], batch size: 25, lr: 2.00e-04
2022-05-16 05:47:01,535 INFO [train.py:812] (3/8) Epoch 39, batch 1500, loss[loss=0.1644, simple_loss=0.2666, pruned_loss=0.03109, over 7108.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02804, over 1424164.36 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:48:00,116 INFO [train.py:812] (3/8) Epoch 39, batch 1550, loss[loss=0.1601, simple_loss=0.2654, pruned_loss=0.02739, over 7210.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2399, pruned_loss=0.02825, over 1423729.43 frames.], batch size: 22, lr: 2.00e-04
2022-05-16 05:48:59,840 INFO [train.py:812] (3/8) Epoch 39, batch 1600, loss[loss=0.1475, simple_loss=0.2382, pruned_loss=0.02834, over 6748.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2399, pruned_loss=0.02832, over 1426019.39 frames.], batch size: 31, lr: 2.00e-04
2022-05-16 05:49:57,809 INFO [train.py:812] (3/8) Epoch 39, batch 1650, loss[loss=0.1442, simple_loss=0.2333, pruned_loss=0.0275, over 7214.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2407, pruned_loss=0.02886, over 1425184.16 frames.], batch size: 21, lr: 2.00e-04
2022-05-16 05:51:01,152 INFO [train.py:812] (3/8) Epoch 39, batch 1700, loss[loss=0.163, simple_loss=0.2514, pruned_loss=0.03733, over 7062.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2415, pruned_loss=0.02896, over 1427184.93 frames.], batch size: 28, lr: 2.00e-04
2022-05-16 05:51:59,355 INFO [train.py:812] (3/8) Epoch 39, batch 1750, loss[loss=0.146, simple_loss=0.2475, pruned_loss=0.02228, over 7425.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2418, pruned_loss=0.02895, over 1427693.29 frames.], batch size: 20, lr: 2.00e-04
2022-05-16 05:52:58,528 INFO [train.py:812] (3/8) Epoch 39, batch 1800, loss[loss=0.1677, simple_loss=0.2546, pruned_loss=0.04043, over 7193.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2422, pruned_loss=0.02924, over 1425208.41 frames.], batch size: 23, lr: 2.00e-04
2022-05-16 05:53:57,514 INFO [train.py:812] (3/8) Epoch 39, batch 1850, loss[loss=0.1291, simple_loss=0.2198, pruned_loss=0.01916, over 7155.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2412, pruned_loss=0.0286, over 1421870.70 frames.], batch size: 19, lr: 2.00e-04
2022-05-16 05:54:55,915 INFO [train.py:812] (3/8) Epoch 39, batch 1900, loss[loss=0.137, simple_loss=0.2284, pruned_loss=0.02279, over 7269.00 frames.], tot_loss[loss=0.1491, simple_loss=0.241, pruned_loss=0.02859, over 1424751.59 frames.], batch size: 18, lr: 2.00e-04
2022-05-16 05:55:54,022 INFO [train.py:812] (3/8) Epoch 39, batch 1950, loss[loss=0.1401, simple_loss=0.2386, pruned_loss=0.02087, over 7318.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2411, pruned_loss=0.02835, over 1424684.75 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 05:56:52,300 INFO [train.py:812] (3/8) Epoch 39, batch 2000, loss[loss=0.1371, simple_loss=0.2284, pruned_loss=0.02287, over 7271.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2414, pruned_loss=0.02865, over 1423762.59 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 05:57:50,324 INFO [train.py:812] (3/8) Epoch 39, batch 2050, loss[loss=0.1361, simple_loss=0.2287, pruned_loss=0.02178, over 7320.00 frames.], tot_loss[loss=0.15, simple_loss=0.2424, pruned_loss=0.02877, over 1421709.30 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 05:58:49,535 INFO [train.py:812] (3/8) Epoch 39, batch 2100, loss[loss=0.1658, simple_loss=0.2454, pruned_loss=0.04311, over 6803.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02837, over 1422278.99 frames.], batch size: 15, lr: 1.99e-04
2022-05-16 05:59:47,691 INFO [train.py:812] (3/8) Epoch 39, batch 2150, loss[loss=0.1494, simple_loss=0.2444, pruned_loss=0.02716, over 7271.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02803, over 1420255.54 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:00:46,901 INFO [train.py:812] (3/8) Epoch 39, batch 2200, loss[loss=0.1686, simple_loss=0.2636, pruned_loss=0.03679, over 7198.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2415, pruned_loss=0.02837, over 1420788.24 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:01:45,967 INFO [train.py:812] (3/8) Epoch 39, batch 2250, loss[loss=0.1605, simple_loss=0.2629, pruned_loss=0.02901, over 7149.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2407, pruned_loss=0.02811, over 1423827.03 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:02:45,396 INFO [train.py:812] (3/8) Epoch 39, batch 2300, loss[loss=0.1408, simple_loss=0.2343, pruned_loss=0.02368, over 7162.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2414, pruned_loss=0.02825, over 1423843.80 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:03:45,424 INFO [train.py:812] (3/8) Epoch 39, batch 2350, loss[loss=0.1619, simple_loss=0.2544, pruned_loss=0.03474, over 7235.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2411, pruned_loss=0.02808, over 1425884.04 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:04:43,836 INFO [train.py:812] (3/8) Epoch 39, batch 2400, loss[loss=0.1619, simple_loss=0.2561, pruned_loss=0.03383, over 7151.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.0282, over 1428251.99 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:05:41,778 INFO [train.py:812] (3/8) Epoch 39, batch 2450, loss[loss=0.1404, simple_loss=0.2238, pruned_loss=0.02849, over 7418.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02788, over 1428426.22 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:06:40,887 INFO [train.py:812] (3/8) Epoch 39, batch 2500, loss[loss=0.1305, simple_loss=0.2161, pruned_loss=0.02241, over 7403.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2402, pruned_loss=0.02753, over 1426594.43 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:07:38,147 INFO [train.py:812] (3/8) Epoch 39, batch 2550, loss[loss=0.1376, simple_loss=0.2375, pruned_loss=0.01891, over 7435.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2401, pruned_loss=0.02782, over 1431217.28 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:08:37,355 INFO [train.py:812] (3/8) Epoch 39, batch 2600, loss[loss=0.172, simple_loss=0.2584, pruned_loss=0.04275, over 7152.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.0282, over 1429545.60 frames.], batch size: 26, lr: 1.99e-04
2022-05-16 06:09:36,142 INFO [train.py:812] (3/8) Epoch 39, batch 2650, loss[loss=0.1527, simple_loss=0.2555, pruned_loss=0.02499, over 7069.00 frames.], tot_loss[loss=0.1483, simple_loss=0.241, pruned_loss=0.02786, over 1429982.49 frames.], batch size: 28, lr: 1.99e-04
2022-05-16 06:10:34,083 INFO [train.py:812] (3/8) Epoch 39, batch 2700, loss[loss=0.1674, simple_loss=0.2637, pruned_loss=0.03557, over 7354.00 frames.], tot_loss[loss=0.1483, simple_loss=0.241, pruned_loss=0.02782, over 1428529.49 frames.], batch size: 25, lr: 1.99e-04
2022-05-16 06:11:32,682 INFO [train.py:812] (3/8) Epoch 39, batch 2750, loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02812, over 7158.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.0282, over 1428605.95 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:12:31,341 INFO [train.py:812] (3/8) Epoch 39, batch 2800, loss[loss=0.1435, simple_loss=0.245, pruned_loss=0.02099, over 7335.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2423, pruned_loss=0.0286, over 1425732.62 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:13:29,192 INFO [train.py:812] (3/8) Epoch 39, batch 2850, loss[loss=0.1457, simple_loss=0.2408, pruned_loss=0.02533, over 6345.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.0284, over 1425792.91 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:14:28,575 INFO [train.py:812] (3/8) Epoch 39, batch 2900, loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03041, over 7321.00 frames.], tot_loss[loss=0.1492, simple_loss=0.242, pruned_loss=0.02824, over 1425233.84 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 06:15:27,562 INFO [train.py:812] (3/8) Epoch 39, batch 2950, loss[loss=0.1341, simple_loss=0.2307, pruned_loss=0.01872, over 7330.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2408, pruned_loss=0.02774, over 1428485.23 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:16:26,915 INFO [train.py:812] (3/8) Epoch 39, batch 3000, loss[loss=0.139, simple_loss=0.2367, pruned_loss=0.02071, over 7222.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2413, pruned_loss=0.02787, over 1428862.67 frames.], batch size: 20, lr: 1.99e-04
2022-05-16 06:16:26,916 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 06:16:34,437 INFO [train.py:841] (3/8) Epoch 39, validation: loss=0.153, simple_loss=0.2484, pruned_loss=0.02885, over 698248.00 frames.
2022-05-16 06:17:33,449 INFO [train.py:812] (3/8) Epoch 39, batch 3050, loss[loss=0.1398, simple_loss=0.2252, pruned_loss=0.0272, over 7125.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2411, pruned_loss=0.02815, over 1426227.32 frames.], batch size: 17, lr: 1.99e-04
2022-05-16 06:18:32,181 INFO [train.py:812] (3/8) Epoch 39, batch 3100, loss[loss=0.1471, simple_loss=0.2465, pruned_loss=0.02387, over 6456.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2413, pruned_loss=0.02844, over 1418310.65 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:19:30,259 INFO [train.py:812] (3/8) Epoch 39, batch 3150, loss[loss=0.1544, simple_loss=0.2526, pruned_loss=0.02813, over 7416.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2416, pruned_loss=0.02846, over 1423850.82 frames.], batch size: 21, lr: 1.99e-04
2022-05-16 06:20:28,878 INFO [train.py:812] (3/8) Epoch 39, batch 3200, loss[loss=0.1397, simple_loss=0.236, pruned_loss=0.0217, over 6427.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2416, pruned_loss=0.0285, over 1424018.22 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:21:26,200 INFO [train.py:812] (3/8) Epoch 39, batch 3250, loss[loss=0.1511, simple_loss=0.2544, pruned_loss=0.02394, over 6437.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.0281, over 1423901.62 frames.], batch size: 38, lr: 1.99e-04
2022-05-16 06:22:25,453 INFO [train.py:812] (3/8) Epoch 39, batch 3300, loss[loss=0.1646, simple_loss=0.2544, pruned_loss=0.03739, over 7160.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2417, pruned_loss=0.028, over 1423746.87 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:23:24,304 INFO [train.py:812] (3/8) Epoch 39, batch 3350, loss[loss=0.148, simple_loss=0.2373, pruned_loss=0.02933, over 7135.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2407, pruned_loss=0.02756, over 1426353.65 frames.], batch size: 17, lr: 1.99e-04
2022-05-16 06:24:23,010 INFO [train.py:812] (3/8) Epoch 39, batch 3400, loss[loss=0.1384, simple_loss=0.231, pruned_loss=0.02291, over 7364.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2399, pruned_loss=0.02738, over 1427057.24 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:25:22,169 INFO [train.py:812] (3/8) Epoch 39, batch 3450, loss[loss=0.1592, simple_loss=0.2547, pruned_loss=0.03186, over 7196.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.02786, over 1418597.55 frames.], batch size: 23, lr: 1.99e-04
2022-05-16 06:26:21,435 INFO [train.py:812] (3/8) Epoch 39, batch 3500, loss[loss=0.1492, simple_loss=0.2471, pruned_loss=0.0256, over 7153.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2411, pruned_loss=0.02789, over 1419895.00 frames.], batch size: 19, lr: 1.99e-04
2022-05-16 06:27:20,316 INFO [train.py:812] (3/8) Epoch 39, batch 3550, loss[loss=0.1631, simple_loss=0.2649, pruned_loss=0.03066, over 7331.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02848, over 1422387.92 frames.], batch size: 22, lr: 1.99e-04
2022-05-16 06:28:19,532 INFO [train.py:812] (3/8) Epoch 39, batch 3600, loss[loss=0.1332, simple_loss=0.2183, pruned_loss=0.02405, over 7287.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2417, pruned_loss=0.0285, over 1423160.16 frames.], batch size: 18, lr: 1.99e-04
2022-05-16 06:29:17,985 INFO [train.py:812] (3/8) Epoch 39, batch 3650, loss[loss=0.1715, simple_loss=0.2656, pruned_loss=0.03868, over 7021.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2419, pruned_loss=0.02842, over 1425062.29 frames.], batch size: 28, lr: 1.99e-04
2022-05-16 06:30:16,951 INFO [train.py:812] (3/8) Epoch 39, batch 3700, loss[loss=0.1666, simple_loss=0.2633, pruned_loss=0.03494, over 6310.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2417, pruned_loss=0.02828, over 1421763.69 frames.], batch size: 37, lr: 1.99e-04
2022-05-16 06:31:16,255 INFO [train.py:812] (3/8) Epoch 39, batch 3750, loss[loss=0.1605, simple_loss=0.2579, pruned_loss=0.03153, over 7204.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02859, over 1416646.11 frames.], batch size: 23, lr: 1.98e-04
2022-05-16 06:32:15,554 INFO [train.py:812] (3/8) Epoch 39, batch 3800, loss[loss=0.1502, simple_loss=0.2484, pruned_loss=0.02596, over 7359.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2409, pruned_loss=0.02819, over 1422637.93 frames.], batch size: 19, lr: 1.98e-04
2022-05-16 06:33:12,750 INFO [train.py:812] (3/8) Epoch 39, batch 3850, loss[loss=0.1616, simple_loss=0.2483, pruned_loss=0.03744, over 5167.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.02823, over 1419467.77 frames.], batch size: 52, lr: 1.98e-04
2022-05-16 06:34:10,686 INFO [train.py:812] (3/8) Epoch 39, batch 3900, loss[loss=0.1772, simple_loss=0.2698, pruned_loss=0.04235, over 7094.00 frames.], tot_loss[loss=0.1487, simple_loss=0.241, pruned_loss=0.02822, over 1420316.65 frames.], batch size: 28, lr: 1.98e-04
2022-05-16 06:35:09,064 INFO [train.py:812] (3/8) Epoch 39, batch 3950, loss[loss=0.1577, simple_loss=0.2529, pruned_loss=0.03121, over 7339.00 frames.], tot_loss[loss=0.148, simple_loss=0.2408, pruned_loss=0.02767, over 1422508.85 frames.], batch size: 25, lr: 1.98e-04
2022-05-16 06:36:07,264 INFO [train.py:812] (3/8) Epoch 39, batch 4000, loss[loss=0.1445, simple_loss=0.2457, pruned_loss=0.02164, over 6702.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2404, pruned_loss=0.02753, over 1425165.30 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:37:03,579 INFO [train.py:812] (3/8) Epoch 39, batch 4050, loss[loss=0.1469, simple_loss=0.2318, pruned_loss=0.03105, over 6863.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.02793, over 1424221.03 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:38:02,733 INFO [train.py:812] (3/8) Epoch 39, batch 4100, loss[loss=0.1462, simple_loss=0.2402, pruned_loss=0.02609, over 7211.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2407, pruned_loss=0.02817, over 1422695.04 frames.], batch size: 21, lr: 1.98e-04
2022-05-16 06:39:01,696 INFO [train.py:812] (3/8) Epoch 39, batch 4150, loss[loss=0.1517, simple_loss=0.2531, pruned_loss=0.02517, over 7216.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2406, pruned_loss=0.0281, over 1420787.92 frames.], batch size: 21, lr: 1.98e-04
2022-05-16 06:40:00,317 INFO [train.py:812] (3/8) Epoch 39, batch 4200, loss[loss=0.1659, simple_loss=0.2617, pruned_loss=0.03508, over 6714.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.02783, over 1419333.40 frames.], batch size: 31, lr: 1.98e-04
2022-05-16 06:40:58,797 INFO [train.py:812] (3/8) Epoch 39, batch 4250, loss[loss=0.138, simple_loss=0.2295, pruned_loss=0.02323, over 7154.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2403, pruned_loss=0.02775, over 1416252.71 frames.], batch size: 17, lr: 1.98e-04
2022-05-16 06:41:58,205 INFO [train.py:812] (3/8) Epoch 39, batch 4300, loss[loss=0.1591, simple_loss=0.2563, pruned_loss=0.03094, over 7295.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2413, pruned_loss=0.02808, over 1417296.77 frames.], batch size: 25, lr: 1.98e-04
2022-05-16 06:42:56,998 INFO [train.py:812] (3/8) Epoch 39, batch 4350, loss[loss=0.1468, simple_loss=0.2421, pruned_loss=0.02574, over 7445.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2425, pruned_loss=0.02845, over 1413534.62 frames.], batch size: 20, lr: 1.98e-04
2022-05-16 06:43:56,254 INFO [train.py:812] (3/8) Epoch 39, batch 4400, loss[loss=0.1609, simple_loss=0.2619, pruned_loss=0.02993, over 7348.00 frames.], tot_loss[loss=0.1512, simple_loss=0.244, pruned_loss=0.02922, over 1410636.95 frames.], batch size: 22, lr: 1.98e-04
2022-05-16 06:44:54,112 INFO [train.py:812] (3/8) Epoch 39, batch 4450, loss[loss=0.1248, simple_loss=0.2091, pruned_loss=0.02031, over 7401.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2443, pruned_loss=0.02941, over 1398972.29 frames.], batch size: 17, lr: 1.98e-04
2022-05-16 06:45:52,450 INFO [train.py:812] (3/8) Epoch 39, batch 4500, loss[loss=0.1344, simple_loss=0.2298, pruned_loss=0.01949, over 7166.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2449, pruned_loss=0.02968, over 1388161.17 frames.], batch size: 18, lr: 1.98e-04
2022-05-16 06:46:49,719 INFO [train.py:812] (3/8) Epoch 39, batch 4550, loss[loss=0.212, simple_loss=0.3001, pruned_loss=0.06194, over 5190.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2473, pruned_loss=0.03119, over 1349998.29 frames.], batch size: 52, lr: 1.98e-04
2022-05-16 06:47:54,890 INFO [train.py:812] (3/8) Epoch 40, batch 0, loss[loss=0.2219, simple_loss=0.3243, pruned_loss=0.05977, over 7286.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3243, pruned_loss=0.05977, over 7286.00 frames.], batch size: 24, lr: 1.96e-04
2022-05-16 06:48:53,197 INFO [train.py:812] (3/8) Epoch 40, batch 50, loss[loss=0.114, simple_loss=0.1962, pruned_loss=0.01591, over 7273.00 frames.], tot_loss[loss=0.1497, simple_loss=0.243, pruned_loss=0.02817, over 316480.18 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 06:49:52,153 INFO [train.py:812] (3/8) Epoch 40, batch 100, loss[loss=0.1488, simple_loss=0.2496, pruned_loss=0.02396, over 7355.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2417, pruned_loss=0.02786, over 562105.99 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 06:50:51,450 INFO [train.py:812] (3/8) Epoch 40, batch 150, loss[loss=0.1544, simple_loss=0.2586, pruned_loss=0.02512, over 7234.00 frames.], tot_loss[loss=0.1479, simple_loss=0.24, pruned_loss=0.02792, over 754518.24 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:51:50,330 INFO [train.py:812] (3/8) Epoch 40, batch 200, loss[loss=0.1304, simple_loss=0.2194, pruned_loss=0.02071, over 7418.00 frames.], tot_loss[loss=0.1496, simple_loss=0.242, pruned_loss=0.02855, over 903543.54 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 06:52:48,875 INFO [train.py:812] (3/8) Epoch 40, batch 250, loss[loss=0.1546, simple_loss=0.2503, pruned_loss=0.02943, over 7113.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2417, pruned_loss=0.02833, over 1017189.48 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 06:53:47,826 INFO [train.py:812] (3/8) Epoch 40, batch 300, loss[loss=0.1653, simple_loss=0.2565, pruned_loss=0.03702, over 7288.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02819, over 1107918.14 frames.], batch size: 24, lr: 1.95e-04
2022-05-16 06:54:46,901 INFO [train.py:812] (3/8) Epoch 40, batch 350, loss[loss=0.163, simple_loss=0.258, pruned_loss=0.03399, over 7140.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2415, pruned_loss=0.02857, over 1171657.01 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:55:45,287 INFO [train.py:812] (3/8) Epoch 40, batch 400, loss[loss=0.153, simple_loss=0.2496, pruned_loss=0.02817, over 7165.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2427, pruned_loss=0.02879, over 1228455.78 frames.], batch size: 26, lr: 1.95e-04
2022-05-16 06:56:53,569 INFO [train.py:812] (3/8) Epoch 40, batch 450, loss[loss=0.1526, simple_loss=0.2409, pruned_loss=0.03217, over 7307.00 frames.], tot_loss[loss=0.1498, simple_loss=0.242, pruned_loss=0.02883, over 1272660.16 frames.], batch size: 25, lr: 1.95e-04
2022-05-16 06:57:52,470 INFO [train.py:812] (3/8) Epoch 40, batch 500, loss[loss=0.1347, simple_loss=0.2372, pruned_loss=0.01608, over 7321.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02872, over 1304841.52 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 06:58:59,574 INFO [train.py:812] (3/8) Epoch 40, batch 550, loss[loss=0.1433, simple_loss=0.239, pruned_loss=0.02385, over 7223.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2425, pruned_loss=0.02908, over 1326054.36 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 06:59:58,458 INFO [train.py:812] (3/8) Epoch 40, batch 600, loss[loss=0.1242, simple_loss=0.2196, pruned_loss=0.01438, over 7256.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2417, pruned_loss=0.02864, over 1348255.80 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 07:01:07,557 INFO [train.py:812] (3/8) Epoch 40, batch 650, loss[loss=0.1633, simple_loss=0.2567, pruned_loss=0.03499, over 7228.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02878, over 1367393.43 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 07:02:07,006 INFO [train.py:812] (3/8) Epoch 40, batch 700, loss[loss=0.1251, simple_loss=0.2105, pruned_loss=0.01982, over 7293.00 frames.], tot_loss[loss=0.15, simple_loss=0.2421, pruned_loss=0.02892, over 1380293.36 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:03:06,183 INFO [train.py:812] (3/8) Epoch 40, batch 750, loss[loss=0.128, simple_loss=0.2198, pruned_loss=0.01808, over 7349.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2415, pruned_loss=0.02877, over 1385564.79 frames.], batch size: 19, lr: 1.95e-04
2022-05-16 07:04:05,444 INFO [train.py:812] (3/8) Epoch 40, batch 800, loss[loss=0.1472, simple_loss=0.2444, pruned_loss=0.02501, over 7111.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2409, pruned_loss=0.02839, over 1394542.77 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:05:03,693 INFO [train.py:812] (3/8) Epoch 40, batch 850, loss[loss=0.1165, simple_loss=0.2025, pruned_loss=0.01527, over 7126.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2417, pruned_loss=0.02874, over 1400747.87 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:06:12,332 INFO [train.py:812] (3/8) Epoch 40, batch 900, loss[loss=0.1799, simple_loss=0.2769, pruned_loss=0.04149, over 7190.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2423, pruned_loss=0.02842, over 1407436.40 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:07:10,688 INFO [train.py:812] (3/8) Epoch 40, batch 950, loss[loss=0.1529, simple_loss=0.2441, pruned_loss=0.03082, over 5005.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.02849, over 1410609.87 frames.], batch size: 52, lr: 1.95e-04
2022-05-16 07:08:20,191 INFO [train.py:812] (3/8) Epoch 40, batch 1000, loss[loss=0.1287, simple_loss=0.2229, pruned_loss=0.0172, over 7112.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2424, pruned_loss=0.02845, over 1409119.19 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:09:19,152 INFO [train.py:812] (3/8) Epoch 40, batch 1050, loss[loss=0.1465, simple_loss=0.2465, pruned_loss=0.02326, over 7212.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2427, pruned_loss=0.0284, over 1408021.28 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:10:42,486 INFO [train.py:812] (3/8) Epoch 40, batch 1100, loss[loss=0.1394, simple_loss=0.2289, pruned_loss=0.025, over 7169.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2429, pruned_loss=0.02851, over 1407158.66 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:11:40,911 INFO [train.py:812] (3/8) Epoch 40, batch 1150, loss[loss=0.1536, simple_loss=0.2443, pruned_loss=0.03143, over 6732.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2427, pruned_loss=0.02834, over 1414380.09 frames.], batch size: 31, lr: 1.95e-04
2022-05-16 07:12:38,506 INFO [train.py:812] (3/8) Epoch 40, batch 1200, loss[loss=0.1615, simple_loss=0.2588, pruned_loss=0.03206, over 6475.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2429, pruned_loss=0.02824, over 1417472.49 frames.], batch size: 38, lr: 1.95e-04
2022-05-16 07:13:37,112 INFO [train.py:812] (3/8) Epoch 40, batch 1250, loss[loss=0.1748, simple_loss=0.2686, pruned_loss=0.04052, over 7304.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02823, over 1421820.33 frames.], batch size: 25, lr: 1.95e-04
2022-05-16 07:14:35,224 INFO [train.py:812] (3/8) Epoch 40, batch 1300, loss[loss=0.1731, simple_loss=0.2785, pruned_loss=0.03389, over 7435.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2424, pruned_loss=0.02832, over 1422400.36 frames.], batch size: 20, lr: 1.95e-04
2022-05-16 07:15:33,954 INFO [train.py:812] (3/8) Epoch 40, batch 1350, loss[loss=0.1409, simple_loss=0.2281, pruned_loss=0.02683, over 6286.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2418, pruned_loss=0.0285, over 1421591.83 frames.], batch size: 37, lr: 1.95e-04
2022-05-16 07:16:32,344 INFO [train.py:812] (3/8) Epoch 40, batch 1400, loss[loss=0.149, simple_loss=0.2496, pruned_loss=0.02422, over 6452.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2422, pruned_loss=0.02841, over 1423261.67 frames.], batch size: 38, lr: 1.95e-04
2022-05-16 07:17:30,726 INFO [train.py:812] (3/8) Epoch 40, batch 1450, loss[loss=0.154, simple_loss=0.2522, pruned_loss=0.02789, over 7180.00 frames.], tot_loss[loss=0.149, simple_loss=0.2416, pruned_loss=0.02825, over 1424670.21 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:18:29,821 INFO [train.py:812] (3/8) Epoch 40, batch 1500, loss[loss=0.1264, simple_loss=0.2221, pruned_loss=0.01537, over 7142.00 frames.], tot_loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.02811, over 1425719.46 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:19:28,056 INFO [train.py:812] (3/8) Epoch 40, batch 1550, loss[loss=0.1777, simple_loss=0.2675, pruned_loss=0.04395, over 7189.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.02817, over 1423492.66 frames.], batch size: 23, lr: 1.95e-04
2022-05-16 07:20:27,062 INFO [train.py:812] (3/8) Epoch 40, batch 1600, loss[loss=0.1365, simple_loss=0.2332, pruned_loss=0.01992, over 7098.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2419, pruned_loss=0.02827, over 1427060.72 frames.], batch size: 28, lr: 1.95e-04
2022-05-16 07:21:25,470 INFO [train.py:812] (3/8) Epoch 40, batch 1650, loss[loss=0.2026, simple_loss=0.2767, pruned_loss=0.06425, over 5002.00 frames.], tot_loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.0283, over 1421589.77 frames.], batch size: 53, lr: 1.95e-04
2022-05-16 07:22:23,892 INFO [train.py:812] (3/8) Epoch 40, batch 1700, loss[loss=0.1331, simple_loss=0.2188, pruned_loss=0.0237, over 7428.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2418, pruned_loss=0.02842, over 1415145.47 frames.], batch size: 17, lr: 1.95e-04
2022-05-16 07:23:23,267 INFO [train.py:812] (3/8) Epoch 40, batch 1750, loss[loss=0.1551, simple_loss=0.2439, pruned_loss=0.03315, over 7320.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2409, pruned_loss=0.0283, over 1416947.91 frames.], batch size: 21, lr: 1.95e-04
2022-05-16 07:24:22,401 INFO [train.py:812] (3/8) Epoch 40, batch 1800, loss[loss=0.1634, simple_loss=0.2588, pruned_loss=0.03396, over 7350.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2419, pruned_loss=0.02836, over 1418996.96 frames.], batch size: 22, lr: 1.95e-04
2022-05-16 07:25:21,046 INFO [train.py:812] (3/8) Epoch 40, batch 1850, loss[loss=0.1473, simple_loss=0.2335, pruned_loss=0.03057, over 7065.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2414, pruned_loss=0.02798, over 1421898.49 frames.], batch size: 18, lr: 1.95e-04
2022-05-16 07:26:20,237 INFO [train.py:812] (3/8) Epoch 40, batch 1900, loss[loss=0.1598, simple_loss=0.2566, pruned_loss=0.03146, over 7175.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2419, pruned_loss=0.02784, over 1425044.45 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:27:17,893 INFO [train.py:812] (3/8) Epoch 40, batch 1950, loss[loss=0.1619, simple_loss=0.2548, pruned_loss=0.0345, over 5053.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2425, pruned_loss=0.02797, over 1418894.23 frames.], batch size: 52, lr: 1.94e-04
2022-05-16 07:28:16,407 INFO [train.py:812] (3/8) Epoch 40, batch 2000, loss[loss=0.1445, simple_loss=0.2286, pruned_loss=0.03018, over 7077.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.0282, over 1422245.93 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:29:15,090 INFO [train.py:812] (3/8) Epoch 40, batch 2050, loss[loss=0.1359, simple_loss=0.2307, pruned_loss=0.02053, over 7426.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2423, pruned_loss=0.02852, over 1426795.19 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:30:14,379 INFO [train.py:812] (3/8) Epoch 40, batch 2100, loss[loss=0.1437, simple_loss=0.2359, pruned_loss=0.0257, over 7386.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02858, over 1424892.22 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:31:12,655 INFO [train.py:812] (3/8) Epoch 40, batch 2150, loss[loss=0.1444, simple_loss=0.2458, pruned_loss=0.02156, over 7148.00 frames.], tot_loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02867, over 1429008.25 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:32:11,382 INFO [train.py:812] (3/8) Epoch 40, batch 2200, loss[loss=0.1886, simple_loss=0.2826, pruned_loss=0.04732, over 7238.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2422, pruned_loss=0.02833, over 1431521.35 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:33:10,318 INFO [train.py:812] (3/8) Epoch 40, batch 2250, loss[loss=0.1806, simple_loss=0.2692, pruned_loss=0.046, over 7191.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.02832, over 1429600.59 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:34:08,376 INFO [train.py:812] (3/8) Epoch 40, batch 2300, loss[loss=0.1386, simple_loss=0.2226, pruned_loss=0.02724, over 7444.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2405, pruned_loss=0.02817, over 1425937.65 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:35:07,172 INFO [train.py:812] (3/8) Epoch 40, batch 2350, loss[loss=0.1416, simple_loss=0.2379, pruned_loss=0.0227, over 7337.00 frames.], tot_loss[loss=0.148, simple_loss=0.2394, pruned_loss=0.02828, over 1426006.81 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:36:06,631 INFO [train.py:812] (3/8) Epoch 40, batch 2400, loss[loss=0.1744, simple_loss=0.264, pruned_loss=0.0424, over 7194.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2395, pruned_loss=0.02843, over 1427637.58 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:37:04,710 INFO [train.py:812] (3/8) Epoch 40, batch 2450, loss[loss=0.1537, simple_loss=0.2504, pruned_loss=0.02854, over 7029.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2405, pruned_loss=0.02833, over 1422639.85 frames.], batch size: 28, lr: 1.94e-04
2022-05-16 07:38:03,593 INFO [train.py:812] (3/8) Epoch 40, batch 2500, loss[loss=0.1387, simple_loss=0.2314, pruned_loss=0.02297, over 7412.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2401, pruned_loss=0.02821, over 1419852.79 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:39:02,629 INFO [train.py:812] (3/8) Epoch 40, batch 2550, loss[loss=0.1519, simple_loss=0.2441, pruned_loss=0.02987, over 7023.00 frames.], tot_loss[loss=0.148, simple_loss=0.2403, pruned_loss=0.02789, over 1419531.23 frames.], batch size: 28, lr: 1.94e-04
2022-05-16 07:40:02,264 INFO [train.py:812] (3/8) Epoch 40, batch 2600, loss[loss=0.1442, simple_loss=0.2369, pruned_loss=0.02575, over 7334.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2399, pruned_loss=0.02787, over 1419500.74 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:40:59,594 INFO [train.py:812] (3/8) Epoch 40, batch 2650, loss[loss=0.1538, simple_loss=0.242, pruned_loss=0.03282, over 7157.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2403, pruned_loss=0.02802, over 1421703.99 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:42:08,102 INFO [train.py:812] (3/8) Epoch 40, batch 2700, loss[loss=0.1478, simple_loss=0.2411, pruned_loss=0.02724, over 7211.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2405, pruned_loss=0.02798, over 1423331.26 frames.], batch size: 26, lr: 1.94e-04
2022-05-16 07:43:06,193 INFO [train.py:812] (3/8) Epoch 40, batch 2750, loss[loss=0.175, simple_loss=0.2791, pruned_loss=0.03546, over 7281.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2408, pruned_loss=0.02798, over 1426418.90 frames.], batch size: 24, lr: 1.94e-04
2022-05-16 07:44:05,710 INFO [train.py:812] (3/8) Epoch 40, batch 2800, loss[loss=0.1387, simple_loss=0.2343, pruned_loss=0.02158, over 7446.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2412, pruned_loss=0.02824, over 1423809.19 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:45:02,887 INFO [train.py:812] (3/8) Epoch 40, batch 2850, loss[loss=0.1302, simple_loss=0.2273, pruned_loss=0.01659, over 6207.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2418, pruned_loss=0.0283, over 1420161.60 frames.], batch size: 37, lr: 1.94e-04
2022-05-16 07:46:01,161 INFO [train.py:812] (3/8) Epoch 40, batch 2900, loss[loss=0.1274, simple_loss=0.21, pruned_loss=0.02241, over 7059.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2413, pruned_loss=0.02789, over 1420392.32 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:46:58,666 INFO [train.py:812] (3/8) Epoch 40, batch 2950, loss[loss=0.1626, simple_loss=0.2537, pruned_loss=0.03573, over 7272.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2422, pruned_loss=0.02786, over 1420358.81 frames.], batch size: 24, lr: 1.94e-04
2022-05-16 07:47:56,498 INFO [train.py:812] (3/8) Epoch 40, batch 3000, loss[loss=0.1849, simple_loss=0.2788, pruned_loss=0.04555, over 7337.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2429, pruned_loss=0.02837, over 1414262.11 frames.], batch size: 22, lr: 1.94e-04
2022-05-16 07:47:56,499 INFO [train.py:832] (3/8) Computing validation loss
2022-05-16 07:48:04,107 INFO [train.py:841] (3/8) 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] (3/8) Epoch 40, batch 3050, loss[loss=0.129, simple_loss=0.2276, pruned_loss=0.01518, over 7354.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2424, pruned_loss=0.02812, over 1416498.66 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:50:01,906 INFO [train.py:812] (3/8) Epoch 40, batch 3100, loss[loss=0.1713, simple_loss=0.2623, pruned_loss=0.04011, over 7205.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2431, pruned_loss=0.02857, over 1418318.01 frames.], batch size: 26, lr: 1.94e-04
2022-05-16 07:51:00,380 INFO [train.py:812] (3/8) Epoch 40, batch 3150, loss[loss=0.1567, simple_loss=0.2552, pruned_loss=0.02904, over 7140.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2436, pruned_loss=0.02892, over 1421845.30 frames.], batch size: 20, lr: 1.94e-04
2022-05-16 07:51:59,401 INFO [train.py:812] (3/8) Epoch 40, batch 3200, loss[loss=0.1509, simple_loss=0.2379, pruned_loss=0.03195, over 4938.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2434, pruned_loss=0.02871, over 1421749.70 frames.], batch size: 52, lr: 1.94e-04
2022-05-16 07:52:57,348 INFO [train.py:812] (3/8) Epoch 40, batch 3250, loss[loss=0.154, simple_loss=0.2557, pruned_loss=0.02618, over 7391.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2437, pruned_loss=0.02867, over 1420649.12 frames.], batch size: 23, lr: 1.94e-04
2022-05-16 07:53:57,055 INFO [train.py:812] (3/8) Epoch 40, batch 3300, loss[loss=0.1551, simple_loss=0.2545, pruned_loss=0.02785, over 7121.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2425, pruned_loss=0.02858, over 1419692.84 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:54:55,913 INFO [train.py:812] (3/8) Epoch 40, batch 3350, loss[loss=0.1518, simple_loss=0.2484, pruned_loss=0.02755, over 7127.00 frames.], tot_loss[loss=0.15, simple_loss=0.2427, pruned_loss=0.02868, over 1417770.21 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:55:55,661 INFO [train.py:812] (3/8) Epoch 40, batch 3400, loss[loss=0.1572, simple_loss=0.2523, pruned_loss=0.03106, over 7162.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02835, over 1418769.83 frames.], batch size: 19, lr: 1.94e-04
2022-05-16 07:56:54,767 INFO [train.py:812] (3/8) Epoch 40, batch 3450, loss[loss=0.1148, simple_loss=0.1937, pruned_loss=0.01792, over 7270.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2416, pruned_loss=0.02812, over 1417213.60 frames.], batch size: 17, lr: 1.94e-04
2022-05-16 07:57:54,427 INFO [train.py:812] (3/8) Epoch 40, batch 3500, loss[loss=0.154, simple_loss=0.2506, pruned_loss=0.02871, over 7325.00 frames.], tot_loss[loss=0.1491, simple_loss=0.242, pruned_loss=0.02807, over 1418675.41 frames.], batch size: 21, lr: 1.94e-04
2022-05-16 07:58:53,141 INFO [train.py:812] (3/8) Epoch 40, batch 3550, loss[loss=0.1449, simple_loss=0.2276, pruned_loss=0.0311, over 7056.00 frames.], tot_loss[loss=0.1484, simple_loss=0.241, pruned_loss=0.0279, over 1420502.99 frames.], batch size: 18, lr: 1.94e-04
2022-05-16 07:59:51,351 INFO [train.py:812] (3/8) Epoch 40, batch 3600, loss[loss=0.1621, simple_loss=0.2457, pruned_loss=0.03924, over 5134.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2409, pruned_loss=0.028, over 1416756.44 frames.], batch size: 52, lr: 1.94e-04
2022-05-16 08:00:51,216 INFO [train.py:812] (3/8) Epoch 40, batch 3650, loss[loss=0.1551, simple_loss=0.2499, pruned_loss=0.03011, over 6328.00 frames.], tot_loss[loss=0.1483, simple_loss=0.241, pruned_loss=0.02786, over 1418601.39 frames.], batch size: 37, lr: 1.94e-04
2022-05-16 08:01:49,908 INFO [train.py:812] (3/8) Epoch 40, batch 3700, loss[loss=0.1483, simple_loss=0.2294, pruned_loss=0.03361, over 7130.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2411, pruned_loss=0.02773, over 1422702.79 frames.], batch size: 17, lr: 1.94e-04
2022-05-16 08:02:46,988 INFO [train.py:812] (3/8) Epoch 40, batch 3750, loss[loss=0.132, simple_loss=0.2241, pruned_loss=0.01995, over 7345.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2417, pruned_loss=0.02796, over 1420050.77 frames.], batch size: 19, lr: 1.93e-04
2022-05-16 08:03:45,476 INFO [train.py:812] (3/8) Epoch 40, batch 3800, loss[loss=0.1373, simple_loss=0.2244, pruned_loss=0.02505, over 6996.00 frames.], tot_loss[loss=0.149, simple_loss=0.2419, pruned_loss=0.02799, over 1424154.47 frames.], batch size: 16, lr: 1.93e-04
2022-05-16 08:04:42,355 INFO [train.py:812] (3/8) Epoch 40, batch 3850, loss[loss=0.1484, simple_loss=0.2502, pruned_loss=0.02331, over 7418.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2413, pruned_loss=0.02791, over 1420293.51 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:05:41,382 INFO [train.py:812] (3/8) Epoch 40, batch 3900, loss[loss=0.1721, simple_loss=0.268, pruned_loss=0.03811, over 7199.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2415, pruned_loss=0.02784, over 1421035.98 frames.], batch size: 23, lr: 1.93e-04
2022-05-16 08:06:40,237 INFO [train.py:812] (3/8) Epoch 40, batch 3950, loss[loss=0.1362, simple_loss=0.2205, pruned_loss=0.02599, over 7057.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2412, pruned_loss=0.02834, over 1416631.30 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:07:38,721 INFO [train.py:812] (3/8) Epoch 40, batch 4000, loss[loss=0.1574, simple_loss=0.2286, pruned_loss=0.04308, over 7147.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2414, pruned_loss=0.0285, over 1416198.52 frames.], batch size: 17, lr: 1.93e-04
2022-05-16 08:08:36,091 INFO [train.py:812] (3/8) Epoch 40, batch 4050, loss[loss=0.1706, simple_loss=0.2584, pruned_loss=0.04144, over 7214.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2418, pruned_loss=0.0286, over 1420752.86 frames.], batch size: 22, lr: 1.93e-04
2022-05-16 08:09:35,654 INFO [train.py:812] (3/8) Epoch 40, batch 4100, loss[loss=0.14, simple_loss=0.2357, pruned_loss=0.02213, over 7224.00 frames.], tot_loss[loss=0.1486, simple_loss=0.241, pruned_loss=0.02811, over 1421163.02 frames.], batch size: 20, lr: 1.93e-04
2022-05-16 08:10:34,192 INFO [train.py:812] (3/8) Epoch 40, batch 4150, loss[loss=0.1443, simple_loss=0.2331, pruned_loss=0.0277, over 7266.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2407, pruned_loss=0.02785, over 1423140.76 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:11:32,974 INFO [train.py:812] (3/8) Epoch 40, batch 4200, loss[loss=0.1402, simple_loss=0.2268, pruned_loss=0.02683, over 7163.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2406, pruned_loss=0.02778, over 1423945.93 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:12:31,937 INFO [train.py:812] (3/8) Epoch 40, batch 4250, loss[loss=0.141, simple_loss=0.2389, pruned_loss=0.02156, over 7317.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2407, pruned_loss=0.02801, over 1419379.12 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:13:30,179 INFO [train.py:812] (3/8) Epoch 40, batch 4300, loss[loss=0.1355, simple_loss=0.2222, pruned_loss=0.02438, over 7169.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2408, pruned_loss=0.02829, over 1419000.58 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:14:29,476 INFO [train.py:812] (3/8) Epoch 40, batch 4350, loss[loss=0.1403, simple_loss=0.2315, pruned_loss=0.02448, over 7328.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2406, pruned_loss=0.02796, over 1420377.66 frames.], batch size: 20, lr: 1.93e-04
2022-05-16 08:15:29,013 INFO [train.py:812] (3/8) Epoch 40, batch 4400, loss[loss=0.1494, simple_loss=0.2433, pruned_loss=0.02778, over 6684.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2415, pruned_loss=0.02818, over 1420320.41 frames.], batch size: 31, lr: 1.93e-04
2022-05-16 08:16:26,686 INFO [train.py:812] (3/8) Epoch 40, batch 4450, loss[loss=0.1519, simple_loss=0.2389, pruned_loss=0.03242, over 7159.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2414, pruned_loss=0.02843, over 1408928.97 frames.], batch size: 18, lr: 1.93e-04
2022-05-16 08:17:25,841 INFO [train.py:812] (3/8) Epoch 40, batch 4500, loss[loss=0.1583, simple_loss=0.2609, pruned_loss=0.02783, over 7223.00 frames.], tot_loss[loss=0.1497, simple_loss=0.242, pruned_loss=0.02866, over 1401367.61 frames.], batch size: 21, lr: 1.93e-04
2022-05-16 08:18:25,894 INFO [train.py:812] (3/8) Epoch 40, batch 4550, loss[loss=0.127, simple_loss=0.2146, pruned_loss=0.01969, over 7259.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2394, pruned_loss=0.02819, over 1392088.26 frames.], batch size: 16, lr: 1.93e-04
2022-05-16 08:19:10,531 INFO [train.py:1030] (3/8) Done!