2022-04-28 06:39:03,117 INFO [train.py:827] (5/8) Training started
2022-04-28 06:39:03,117 INFO [train.py:837] (5/8) Device: cuda:5
2022-04-28 06:39:03,161 INFO [train.py:846] (5/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '3b83183234d0f1d8391872630551c5af7c491ed2', 'k2-git-date': 'Tue Apr 12 08:26:41 2022', 'lhotse-version': '1.1.0.dev+missing.version.file', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'deeper-conformer', 'icefall-git-sha1': 'd79f5fe-dirty', 'icefall-git-date': 'Mon Apr 25 17:26:43 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0309102938-68688b4cbd-xhtcg', 'IP address': '10.48.32.137'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless4/exp-L'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 20, 'use_fp16': False, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
2022-04-28 06:39:03,161 INFO [train.py:848] (5/8) About to create model
2022-04-28 06:39:03,685 INFO [train.py:852] (5/8) Number of model parameters: 118129516
2022-04-28 06:39:09,620 INFO [train.py:858] (5/8) Using DDP
2022-04-28 06:39:10,515 INFO [asr_datamodule.py:391] (5/8) About to get train-clean-100 cuts
2022-04-28 06:39:17,546 INFO [asr_datamodule.py:398] (5/8) About to get train-clean-360 cuts
2022-04-28 06:39:44,193 INFO [asr_datamodule.py:405] (5/8) About to get train-other-500 cuts
2022-04-28 06:40:26,739 INFO [asr_datamodule.py:209] (5/8) Enable MUSAN
2022-04-28 06:40:26,740 INFO [asr_datamodule.py:210] (5/8) About to get Musan cuts
2022-04-28 06:40:28,062 INFO [asr_datamodule.py:238] (5/8) Enable SpecAugment
2022-04-28 06:40:28,063 INFO [asr_datamodule.py:239] (5/8) Time warp factor: 80
2022-04-28 06:40:28,063 INFO [asr_datamodule.py:251] (5/8) Num frame mask: 10
2022-04-28 06:40:28,063 INFO [asr_datamodule.py:264] (5/8) About to create train dataset
2022-04-28 06:40:28,063 INFO [asr_datamodule.py:292] (5/8) Using BucketingSampler.
2022-04-28 06:40:32,487 INFO [asr_datamodule.py:308] (5/8) About to create train dataloader
2022-04-28 06:40:32,487 INFO [asr_datamodule.py:412] (5/8) About to get dev-clean cuts
2022-04-28 06:40:32,755 INFO [asr_datamodule.py:417] (5/8) About to get dev-other cuts
2022-04-28 06:40:32,884 INFO [asr_datamodule.py:339] (5/8) About to create dev dataset
2022-04-28 06:40:32,893 INFO [asr_datamodule.py:358] (5/8) About to create dev dataloader
2022-04-28 06:40:32,894 INFO [train.py:987] (5/8) Sanity check -- see if any of the batches in epoch 0 would cause OOM.
2022-04-28 06:40:42,725 INFO [distributed.py:874] (5/8) Reducer buckets have been rebuilt in this iteration.
2022-04-28 06:41:17,067 INFO [train.py:763] (5/8) Epoch 0, batch 0, loss[loss=0.6327, simple_loss=1.265, pruned_loss=7.023, over 7273.00 frames.], tot_loss[loss=0.6327, simple_loss=1.265, pruned_loss=7.023, over 7273.00 frames.], batch size: 17, lr: 3.00e-03
2022-04-28 06:42:23,611 INFO [train.py:763] (5/8) Epoch 0, batch 50, loss[loss=0.4911, simple_loss=0.9822, pruned_loss=6.615, over 7159.00 frames.], tot_loss[loss=0.5656, simple_loss=1.131, pruned_loss=6.942, over 323165.15 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:43:30,302 INFO [train.py:763] (5/8) Epoch 0, batch 100, loss[loss=0.4097, simple_loss=0.8195, pruned_loss=6.677, over 7014.00 frames.], tot_loss[loss=0.5104, simple_loss=1.021, pruned_loss=6.87, over 566707.79 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:44:37,540 INFO [train.py:763] (5/8) Epoch 0, batch 150, loss[loss=0.3649, simple_loss=0.7298, pruned_loss=6.553, over 7014.00 frames.], tot_loss[loss=0.477, simple_loss=0.9539, pruned_loss=6.857, over 758707.81 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:45:44,963 INFO [train.py:763] (5/8) Epoch 0, batch 200, loss[loss=0.4055, simple_loss=0.811, pruned_loss=6.767, over 7298.00 frames.], tot_loss[loss=0.4536, simple_loss=0.9072, pruned_loss=6.836, over 908711.24 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:46:50,983 INFO [train.py:763] (5/8) Epoch 0, batch 250, loss[loss=0.4406, simple_loss=0.8813, pruned_loss=6.759, over 7332.00 frames.], tot_loss[loss=0.4367, simple_loss=0.8733, pruned_loss=6.797, over 1017284.57 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:47:58,729 INFO [train.py:763] (5/8) Epoch 0, batch 300, loss[loss=0.4006, simple_loss=0.8011, pruned_loss=6.72, over 7307.00 frames.], tot_loss[loss=0.4245, simple_loss=0.849, pruned_loss=6.768, over 1109663.75 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:49:06,201 INFO [train.py:763] (5/8) Epoch 0, batch 350, loss[loss=0.3892, simple_loss=0.7785, pruned_loss=6.646, over 7260.00 frames.], tot_loss[loss=0.4149, simple_loss=0.8298, pruned_loss=6.732, over 1178939.80 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:50:12,120 INFO [train.py:763] (5/8) Epoch 0, batch 400, loss[loss=0.3638, simple_loss=0.7275, pruned_loss=6.614, over 7410.00 frames.], tot_loss[loss=0.4049, simple_loss=0.8097, pruned_loss=6.703, over 1231027.84 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:51:17,835 INFO [train.py:763] (5/8) Epoch 0, batch 450, loss[loss=0.3382, simple_loss=0.6764, pruned_loss=6.604, over 7421.00 frames.], tot_loss[loss=0.3919, simple_loss=0.7838, pruned_loss=6.684, over 1267472.88 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:52:24,503 INFO [train.py:763] (5/8) Epoch 0, batch 500, loss[loss=0.3171, simple_loss=0.6341, pruned_loss=6.745, over 7195.00 frames.], tot_loss[loss=0.3753, simple_loss=0.7507, pruned_loss=6.672, over 1303749.18 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:53:30,000 INFO [train.py:763] (5/8) Epoch 0, batch 550, loss[loss=0.2933, simple_loss=0.5867, pruned_loss=6.639, over 7341.00 frames.], tot_loss[loss=0.3605, simple_loss=0.721, pruned_loss=6.674, over 1330646.29 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:54:36,577 INFO [train.py:763] (5/8) Epoch 0, batch 600, loss[loss=0.306, simple_loss=0.612, pruned_loss=6.676, over 7116.00 frames.], tot_loss[loss=0.3452, simple_loss=0.6904, pruned_loss=6.665, over 1351560.91 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:55:42,128 INFO [train.py:763] (5/8) Epoch 0, batch 650, loss[loss=0.2504, simple_loss=0.5008, pruned_loss=6.456, over 6998.00 frames.], tot_loss[loss=0.3321, simple_loss=0.6642, pruned_loss=6.657, over 1369585.21 frames.], batch size: 16, lr: 2.99e-03
2022-04-28 06:56:47,776 INFO [train.py:763] (5/8) Epoch 0, batch 700, loss[loss=0.3006, simple_loss=0.6012, pruned_loss=6.702, over 7222.00 frames.], tot_loss[loss=0.3171, simple_loss=0.6343, pruned_loss=6.639, over 1381417.14 frames.], batch size: 23, lr: 2.99e-03
2022-04-28 06:57:54,533 INFO [train.py:763] (5/8) Epoch 0, batch 750, loss[loss=0.2447, simple_loss=0.4895, pruned_loss=6.546, over 7263.00 frames.], tot_loss[loss=0.3041, simple_loss=0.6081, pruned_loss=6.623, over 1392615.01 frames.], batch size: 17, lr: 2.98e-03
2022-04-28 06:59:01,271 INFO [train.py:763] (5/8) Epoch 0, batch 800, loss[loss=0.2571, simple_loss=0.5143, pruned_loss=6.588, over 7117.00 frames.], tot_loss[loss=0.2937, simple_loss=0.5874, pruned_loss=6.614, over 1397517.41 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:00:07,436 INFO [train.py:763] (5/8) Epoch 0, batch 850, loss[loss=0.2588, simple_loss=0.5176, pruned_loss=6.637, over 7233.00 frames.], tot_loss[loss=0.2843, simple_loss=0.5686, pruned_loss=6.598, over 1402481.34 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:01:13,437 INFO [train.py:763] (5/8) Epoch 0, batch 900, loss[loss=0.2515, simple_loss=0.503, pruned_loss=6.715, over 7322.00 frames.], tot_loss[loss=0.275, simple_loss=0.5501, pruned_loss=6.586, over 1407372.65 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:02:19,020 INFO [train.py:763] (5/8) Epoch 0, batch 950, loss[loss=0.2284, simple_loss=0.4567, pruned_loss=6.511, over 7014.00 frames.], tot_loss[loss=0.2691, simple_loss=0.5383, pruned_loss=6.581, over 1403749.14 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:03:26,145 INFO [train.py:763] (5/8) Epoch 0, batch 1000, loss[loss=0.215, simple_loss=0.4299, pruned_loss=6.53, over 6997.00 frames.], tot_loss[loss=0.2633, simple_loss=0.5267, pruned_loss=6.579, over 1404078.82 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:04:32,985 INFO [train.py:763] (5/8) Epoch 0, batch 1050, loss[loss=0.2025, simple_loss=0.405, pruned_loss=6.412, over 6998.00 frames.], tot_loss[loss=0.2574, simple_loss=0.5149, pruned_loss=6.573, over 1406437.23 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:05:39,533 INFO [train.py:763] (5/8) Epoch 0, batch 1100, loss[loss=0.2539, simple_loss=0.5077, pruned_loss=6.65, over 7217.00 frames.], tot_loss[loss=0.2525, simple_loss=0.505, pruned_loss=6.578, over 1409802.92 frames.], batch size: 22, lr: 2.96e-03
2022-04-28 07:06:46,915 INFO [train.py:763] (5/8) Epoch 0, batch 1150, loss[loss=0.243, simple_loss=0.486, pruned_loss=6.502, over 6786.00 frames.], tot_loss[loss=0.2472, simple_loss=0.4943, pruned_loss=6.57, over 1411342.29 frames.], batch size: 31, lr: 2.96e-03
2022-04-28 07:07:52,786 INFO [train.py:763] (5/8) Epoch 0, batch 1200, loss[loss=0.2237, simple_loss=0.4474, pruned_loss=6.609, over 7208.00 frames.], tot_loss[loss=0.2425, simple_loss=0.4849, pruned_loss=6.573, over 1419478.84 frames.], batch size: 26, lr: 2.96e-03
2022-04-28 07:08:58,134 INFO [train.py:763] (5/8) Epoch 0, batch 1250, loss[loss=0.2334, simple_loss=0.4668, pruned_loss=6.619, over 7372.00 frames.], tot_loss[loss=0.2394, simple_loss=0.4788, pruned_loss=6.576, over 1413079.34 frames.], batch size: 23, lr: 2.95e-03
2022-04-28 07:10:04,047 INFO [train.py:763] (5/8) Epoch 0, batch 1300, loss[loss=0.226, simple_loss=0.452, pruned_loss=6.733, over 7299.00 frames.], tot_loss[loss=0.2355, simple_loss=0.471, pruned_loss=6.58, over 1420490.03 frames.], batch size: 24, lr: 2.95e-03
2022-04-28 07:11:09,807 INFO [train.py:763] (5/8) Epoch 0, batch 1350, loss[loss=0.2231, simple_loss=0.4462, pruned_loss=6.526, over 7149.00 frames.], tot_loss[loss=0.2326, simple_loss=0.4653, pruned_loss=6.579, over 1421684.21 frames.], batch size: 20, lr: 2.95e-03
2022-04-28 07:12:15,118 INFO [train.py:763] (5/8) Epoch 0, batch 1400, loss[loss=0.235, simple_loss=0.4701, pruned_loss=6.667, over 7266.00 frames.], tot_loss[loss=0.2305, simple_loss=0.4609, pruned_loss=6.589, over 1418266.41 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:13:21,025 INFO [train.py:763] (5/8) Epoch 0, batch 1450, loss[loss=0.1818, simple_loss=0.3636, pruned_loss=6.435, over 7132.00 frames.], tot_loss[loss=0.2271, simple_loss=0.4541, pruned_loss=6.583, over 1418947.32 frames.], batch size: 17, lr: 2.94e-03
2022-04-28 07:14:26,718 INFO [train.py:763] (5/8) Epoch 0, batch 1500, loss[loss=0.2093, simple_loss=0.4185, pruned_loss=6.611, over 7286.00 frames.], tot_loss[loss=0.2249, simple_loss=0.4498, pruned_loss=6.579, over 1422010.64 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:15:32,251 INFO [train.py:763] (5/8) Epoch 0, batch 1550, loss[loss=0.2352, simple_loss=0.4704, pruned_loss=6.619, over 7109.00 frames.], tot_loss[loss=0.2226, simple_loss=0.4451, pruned_loss=6.574, over 1422038.66 frames.], batch size: 21, lr: 2.93e-03
2022-04-28 07:16:38,331 INFO [train.py:763] (5/8) Epoch 0, batch 1600, loss[loss=0.2222, simple_loss=0.4443, pruned_loss=6.601, over 7331.00 frames.], tot_loss[loss=0.2205, simple_loss=0.441, pruned_loss=6.571, over 1419947.73 frames.], batch size: 20, lr: 2.93e-03
2022-04-28 07:17:45,341 INFO [train.py:763] (5/8) Epoch 0, batch 1650, loss[loss=0.2037, simple_loss=0.4075, pruned_loss=6.519, over 7162.00 frames.], tot_loss[loss=0.2185, simple_loss=0.4369, pruned_loss=6.567, over 1422039.04 frames.], batch size: 18, lr: 2.92e-03
2022-04-28 07:18:52,038 INFO [train.py:763] (5/8) Epoch 0, batch 1700, loss[loss=0.2197, simple_loss=0.4393, pruned_loss=6.539, over 6309.00 frames.], tot_loss[loss=0.2169, simple_loss=0.4338, pruned_loss=6.569, over 1416658.07 frames.], batch size: 38, lr: 2.92e-03
2022-04-28 07:19:58,700 INFO [train.py:763] (5/8) Epoch 0, batch 1750, loss[loss=0.2085, simple_loss=0.417, pruned_loss=6.432, over 6285.00 frames.], tot_loss[loss=0.2141, simple_loss=0.4283, pruned_loss=6.565, over 1416741.43 frames.], batch size: 37, lr: 2.91e-03
2022-04-28 07:21:06,373 INFO [train.py:763] (5/8) Epoch 0, batch 1800, loss[loss=0.2216, simple_loss=0.4432, pruned_loss=6.634, over 7099.00 frames.], tot_loss[loss=0.2138, simple_loss=0.4276, pruned_loss=6.568, over 1417824.57 frames.], batch size: 28, lr: 2.91e-03
2022-04-28 07:22:12,431 INFO [train.py:763] (5/8) Epoch 0, batch 1850, loss[loss=0.2433, simple_loss=0.4866, pruned_loss=6.476, over 4863.00 frames.], tot_loss[loss=0.2123, simple_loss=0.4246, pruned_loss=6.569, over 1420006.01 frames.], batch size: 52, lr: 2.91e-03
2022-04-28 07:23:18,922 INFO [train.py:763] (5/8) Epoch 0, batch 1900, loss[loss=0.1979, simple_loss=0.3959, pruned_loss=6.625, over 7258.00 frames.], tot_loss[loss=0.2105, simple_loss=0.421, pruned_loss=6.573, over 1420108.23 frames.], batch size: 19, lr: 2.90e-03
2022-04-28 07:24:26,530 INFO [train.py:763] (5/8) Epoch 0, batch 1950, loss[loss=0.1973, simple_loss=0.3947, pruned_loss=6.466, over 7328.00 frames.], tot_loss[loss=0.209, simple_loss=0.418, pruned_loss=6.567, over 1422956.42 frames.], batch size: 21, lr: 2.90e-03
2022-04-28 07:25:34,074 INFO [train.py:763] (5/8) Epoch 0, batch 2000, loss[loss=0.2142, simple_loss=0.4285, pruned_loss=6.477, over 7196.00 frames.], tot_loss[loss=0.2072, simple_loss=0.4144, pruned_loss=6.561, over 1423589.12 frames.], batch size: 16, lr: 2.89e-03
2022-04-28 07:26:39,965 INFO [train.py:763] (5/8) Epoch 0, batch 2050, loss[loss=0.2069, simple_loss=0.4138, pruned_loss=6.649, over 7192.00 frames.], tot_loss[loss=0.2064, simple_loss=0.4128, pruned_loss=6.562, over 1421559.87 frames.], batch size: 26, lr: 2.89e-03
2022-04-28 07:27:45,825 INFO [train.py:763] (5/8) Epoch 0, batch 2100, loss[loss=0.1963, simple_loss=0.3927, pruned_loss=6.475, over 7174.00 frames.], tot_loss[loss=0.2056, simple_loss=0.4111, pruned_loss=6.564, over 1418813.93 frames.], batch size: 18, lr: 2.88e-03
2022-04-28 07:28:51,559 INFO [train.py:763] (5/8) Epoch 0, batch 2150, loss[loss=0.2319, simple_loss=0.4638, pruned_loss=6.684, over 7347.00 frames.], tot_loss[loss=0.2044, simple_loss=0.4088, pruned_loss=6.57, over 1422357.03 frames.], batch size: 22, lr: 2.88e-03
2022-04-28 07:29:57,488 INFO [train.py:763] (5/8) Epoch 0, batch 2200, loss[loss=0.2078, simple_loss=0.4155, pruned_loss=6.565, over 7294.00 frames.], tot_loss[loss=0.2038, simple_loss=0.4076, pruned_loss=6.578, over 1421459.40 frames.], batch size: 25, lr: 2.87e-03
2022-04-28 07:31:03,292 INFO [train.py:763] (5/8) Epoch 0, batch 2250, loss[loss=0.1841, simple_loss=0.3682, pruned_loss=6.572, over 7230.00 frames.], tot_loss[loss=0.2024, simple_loss=0.4048, pruned_loss=6.577, over 1420032.64 frames.], batch size: 21, lr: 2.86e-03
2022-04-28 07:32:08,993 INFO [train.py:763] (5/8) Epoch 0, batch 2300, loss[loss=0.2005, simple_loss=0.4009, pruned_loss=6.569, over 7268.00 frames.], tot_loss[loss=0.202, simple_loss=0.404, pruned_loss=6.574, over 1414782.55 frames.], batch size: 19, lr: 2.86e-03
2022-04-28 07:33:14,411 INFO [train.py:763] (5/8) Epoch 0, batch 2350, loss[loss=0.2246, simple_loss=0.4492, pruned_loss=6.574, over 5111.00 frames.], tot_loss[loss=0.2013, simple_loss=0.4026, pruned_loss=6.581, over 1414756.69 frames.], batch size: 52, lr: 2.85e-03
2022-04-28 07:34:20,290 INFO [train.py:763] (5/8) Epoch 0, batch 2400, loss[loss=0.1801, simple_loss=0.3603, pruned_loss=6.547, over 7431.00 frames.], tot_loss[loss=0.2012, simple_loss=0.4024, pruned_loss=6.581, over 1411552.78 frames.], batch size: 20, lr: 2.85e-03
2022-04-28 07:35:25,719 INFO [train.py:763] (5/8) Epoch 0, batch 2450, loss[loss=0.2372, simple_loss=0.4744, pruned_loss=6.725, over 4810.00 frames.], tot_loss[loss=0.2007, simple_loss=0.4013, pruned_loss=6.582, over 1411276.09 frames.], batch size: 52, lr: 2.84e-03
2022-04-28 07:36:32,812 INFO [train.py:763] (5/8) Epoch 0, batch 2500, loss[loss=0.1981, simple_loss=0.3961, pruned_loss=6.7, over 7338.00 frames.], tot_loss[loss=0.2, simple_loss=0.4, pruned_loss=6.584, over 1417579.93 frames.], batch size: 20, lr: 2.84e-03
2022-04-28 07:37:40,502 INFO [train.py:763] (5/8) Epoch 0, batch 2550, loss[loss=0.1841, simple_loss=0.3682, pruned_loss=6.487, over 7383.00 frames.], tot_loss[loss=0.1995, simple_loss=0.399, pruned_loss=6.589, over 1418376.06 frames.], batch size: 18, lr: 2.83e-03
2022-04-28 07:38:46,548 INFO [train.py:763] (5/8) Epoch 0, batch 2600, loss[loss=0.2183, simple_loss=0.4366, pruned_loss=6.591, over 7235.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3965, pruned_loss=6.591, over 1421147.50 frames.], batch size: 20, lr: 2.83e-03
2022-04-28 07:39:52,340 INFO [train.py:763] (5/8) Epoch 0, batch 2650, loss[loss=0.1989, simple_loss=0.3979, pruned_loss=6.629, over 7230.00 frames.], tot_loss[loss=0.1973, simple_loss=0.3946, pruned_loss=6.59, over 1422588.03 frames.], batch size: 20, lr: 2.82e-03
2022-04-28 07:40:58,207 INFO [train.py:763] (5/8) Epoch 0, batch 2700, loss[loss=0.2038, simple_loss=0.4076, pruned_loss=6.73, over 7147.00 frames.], tot_loss[loss=0.1963, simple_loss=0.3925, pruned_loss=6.59, over 1422262.71 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:42:03,324 INFO [train.py:763] (5/8) Epoch 0, batch 2750, loss[loss=0.2037, simple_loss=0.4073, pruned_loss=6.644, over 7319.00 frames.], tot_loss[loss=0.1962, simple_loss=0.3925, pruned_loss=6.599, over 1423478.64 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:43:09,951 INFO [train.py:763] (5/8) Epoch 0, batch 2800, loss[loss=0.1803, simple_loss=0.3606, pruned_loss=6.569, over 7152.00 frames.], tot_loss[loss=0.1955, simple_loss=0.391, pruned_loss=6.6, over 1422544.55 frames.], batch size: 20, lr: 2.80e-03
2022-04-28 07:44:16,836 INFO [train.py:763] (5/8) Epoch 0, batch 2850, loss[loss=0.1784, simple_loss=0.3568, pruned_loss=6.509, over 7362.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3903, pruned_loss=6.601, over 1425559.87 frames.], batch size: 19, lr: 2.80e-03
2022-04-28 07:45:22,341 INFO [train.py:763] (5/8) Epoch 0, batch 2900, loss[loss=0.1724, simple_loss=0.3449, pruned_loss=6.584, over 7325.00 frames.], tot_loss[loss=0.1957, simple_loss=0.3914, pruned_loss=6.609, over 1421492.94 frames.], batch size: 20, lr: 2.79e-03
2022-04-28 07:46:27,658 INFO [train.py:763] (5/8) Epoch 0, batch 2950, loss[loss=0.1964, simple_loss=0.3928, pruned_loss=6.552, over 7144.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3892, pruned_loss=6.607, over 1417375.63 frames.], batch size: 26, lr: 2.78e-03
2022-04-28 07:47:32,892 INFO [train.py:763] (5/8) Epoch 0, batch 3000, loss[loss=0.3299, simple_loss=0.3773, pruned_loss=1.413, over 7293.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3872, pruned_loss=6.581, over 1420995.67 frames.], batch size: 17, lr: 2.78e-03
2022-04-28 07:47:32,893 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 07:47:50,998 INFO [train.py:792] (5/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
2022-04-28 07:48:57,679 INFO [train.py:763] (5/8) Epoch 0, batch 3050, loss[loss=0.3017, simple_loss=0.4187, pruned_loss=0.9235, over 6380.00 frames.], tot_loss[loss=0.251, simple_loss=0.3963, pruned_loss=5.397, over 1419996.99 frames.], batch size: 38, lr: 2.77e-03
2022-04-28 07:50:04,088 INFO [train.py:763] (5/8) Epoch 0, batch 3100, loss[loss=0.2624, simple_loss=0.4087, pruned_loss=0.5804, over 7416.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3919, pruned_loss=4.337, over 1425647.36 frames.], batch size: 21, lr: 2.77e-03
2022-04-28 07:51:10,059 INFO [train.py:763] (5/8) Epoch 0, batch 3150, loss[loss=0.2433, simple_loss=0.4107, pruned_loss=0.3796, over 7397.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3891, pruned_loss=3.465, over 1426684.51 frames.], batch size: 21, lr: 2.76e-03
2022-04-28 07:52:16,822 INFO [train.py:763] (5/8) Epoch 0, batch 3200, loss[loss=0.2268, simple_loss=0.3965, pruned_loss=0.2854, over 7297.00 frames.], tot_loss[loss=0.2421, simple_loss=0.388, pruned_loss=2.771, over 1423777.62 frames.], batch size: 24, lr: 2.75e-03
2022-04-28 07:53:24,325 INFO [train.py:763] (5/8) Epoch 0, batch 3250, loss[loss=0.2108, simple_loss=0.3723, pruned_loss=0.2464, over 7145.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3861, pruned_loss=2.215, over 1423657.45 frames.], batch size: 20, lr: 2.75e-03
2022-04-28 07:54:30,951 INFO [train.py:763] (5/8) Epoch 0, batch 3300, loss[loss=0.2294, simple_loss=0.407, pruned_loss=0.2591, over 7385.00 frames.], tot_loss[loss=0.2322, simple_loss=0.386, pruned_loss=1.784, over 1418525.74 frames.], batch size: 23, lr: 2.74e-03
2022-04-28 07:55:37,622 INFO [train.py:763] (5/8) Epoch 0, batch 3350, loss[loss=0.2214, simple_loss=0.3984, pruned_loss=0.2221, over 7286.00 frames.], tot_loss[loss=0.2278, simple_loss=0.3849, pruned_loss=1.433, over 1423304.58 frames.], batch size: 24, lr: 2.73e-03
2022-04-28 07:56:43,239 INFO [train.py:763] (5/8) Epoch 0, batch 3400, loss[loss=0.2194, simple_loss=0.3958, pruned_loss=0.215, over 7259.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3849, pruned_loss=1.163, over 1423706.77 frames.], batch size: 19, lr: 2.73e-03
2022-04-28 07:57:49,076 INFO [train.py:763] (5/8) Epoch 0, batch 3450, loss[loss=0.2286, simple_loss=0.4134, pruned_loss=0.2193, over 7291.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3846, pruned_loss=0.9524, over 1423518.25 frames.], batch size: 25, lr: 2.72e-03
2022-04-28 07:58:54,335 INFO [train.py:763] (5/8) Epoch 0, batch 3500, loss[loss=0.2158, simple_loss=0.3914, pruned_loss=0.2013, over 7157.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3844, pruned_loss=0.7859, over 1420971.26 frames.], batch size: 26, lr: 2.72e-03
2022-04-28 08:00:00,016 INFO [train.py:763] (5/8) Epoch 0, batch 3550, loss[loss=0.2347, simple_loss=0.4239, pruned_loss=0.2273, over 7221.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3815, pruned_loss=0.6527, over 1422831.02 frames.], batch size: 21, lr: 2.71e-03
2022-04-28 08:01:06,053 INFO [train.py:763] (5/8) Epoch 0, batch 3600, loss[loss=0.2016, simple_loss=0.363, pruned_loss=0.2007, over 6985.00 frames.], tot_loss[loss=0.2141, simple_loss=0.38, pruned_loss=0.5499, over 1421084.27 frames.], batch size: 16, lr: 2.70e-03
2022-04-28 08:02:21,064 INFO [train.py:763] (5/8) Epoch 0, batch 3650, loss[loss=0.2323, simple_loss=0.4235, pruned_loss=0.2058, over 7217.00 frames.], tot_loss[loss=0.2117, simple_loss=0.3781, pruned_loss=0.4674, over 1421168.42 frames.], batch size: 21, lr: 2.70e-03
2022-04-28 08:04:03,469 INFO [train.py:763] (5/8) Epoch 0, batch 3700, loss[loss=0.24, simple_loss=0.4313, pruned_loss=0.2439, over 6778.00 frames.], tot_loss[loss=0.2097, simple_loss=0.3764, pruned_loss=0.4016, over 1426350.53 frames.], batch size: 31, lr: 2.69e-03
2022-04-28 08:05:34,891 INFO [train.py:763] (5/8) Epoch 0, batch 3750, loss[loss=0.2086, simple_loss=0.379, pruned_loss=0.1909, over 7283.00 frames.], tot_loss[loss=0.2078, simple_loss=0.3746, pruned_loss=0.3514, over 1418565.44 frames.], batch size: 18, lr: 2.68e-03
2022-04-28 08:06:40,600 INFO [train.py:763] (5/8) Epoch 0, batch 3800, loss[loss=0.1866, simple_loss=0.3441, pruned_loss=0.1451, over 7138.00 frames.], tot_loss[loss=0.2062, simple_loss=0.373, pruned_loss=0.3108, over 1417995.08 frames.], batch size: 17, lr: 2.68e-03
2022-04-28 08:07:46,194 INFO [train.py:763] (5/8) Epoch 0, batch 3850, loss[loss=0.1804, simple_loss=0.3333, pruned_loss=0.1373, over 7127.00 frames.], tot_loss[loss=0.2053, simple_loss=0.3724, pruned_loss=0.2789, over 1423280.69 frames.], batch size: 17, lr: 2.67e-03
2022-04-28 08:08:52,450 INFO [train.py:763] (5/8) Epoch 0, batch 3900, loss[loss=0.1876, simple_loss=0.3457, pruned_loss=0.148, over 6783.00 frames.], tot_loss[loss=0.2056, simple_loss=0.3738, pruned_loss=0.2564, over 1419532.25 frames.], batch size: 15, lr: 2.66e-03
2022-04-28 08:09:58,862 INFO [train.py:763] (5/8) Epoch 0, batch 3950, loss[loss=0.1951, simple_loss=0.355, pruned_loss=0.1759, over 6784.00 frames.], tot_loss[loss=0.2037, simple_loss=0.3711, pruned_loss=0.2348, over 1417371.66 frames.], batch size: 15, lr: 2.66e-03
2022-04-28 08:11:04,212 INFO [train.py:763] (5/8) Epoch 0, batch 4000, loss[loss=0.1734, simple_loss=0.3232, pruned_loss=0.1184, over 7311.00 frames.], tot_loss[loss=0.2042, simple_loss=0.3727, pruned_loss=0.2199, over 1420110.39 frames.], batch size: 21, lr: 2.65e-03
2022-04-28 08:12:09,512 INFO [train.py:763] (5/8) Epoch 0, batch 4050, loss[loss=0.2208, simple_loss=0.4049, pruned_loss=0.1833, over 7077.00 frames.], tot_loss[loss=0.203, simple_loss=0.3712, pruned_loss=0.2061, over 1420525.25 frames.], batch size: 28, lr: 2.64e-03
2022-04-28 08:13:15,847 INFO [train.py:763] (5/8) Epoch 0, batch 4100, loss[loss=0.1962, simple_loss=0.3608, pruned_loss=0.1583, over 7256.00 frames.], tot_loss[loss=0.2017, simple_loss=0.3694, pruned_loss=0.1956, over 1420733.32 frames.], batch size: 19, lr: 2.64e-03
2022-04-28 08:14:22,423 INFO [train.py:763] (5/8) Epoch 0, batch 4150, loss[loss=0.193, simple_loss=0.3576, pruned_loss=0.1426, over 7071.00 frames.], tot_loss[loss=0.201, simple_loss=0.3686, pruned_loss=0.1866, over 1425343.30 frames.], batch size: 18, lr: 2.63e-03
2022-04-28 08:15:27,432 INFO [train.py:763] (5/8) Epoch 0, batch 4200, loss[loss=0.2039, simple_loss=0.3785, pruned_loss=0.1463, over 7205.00 frames.], tot_loss[loss=0.2005, simple_loss=0.3681, pruned_loss=0.1793, over 1424762.06 frames.], batch size: 22, lr: 2.63e-03
2022-04-28 08:16:32,487 INFO [train.py:763] (5/8) Epoch 0, batch 4250, loss[loss=0.1949, simple_loss=0.3628, pruned_loss=0.1345, over 7422.00 frames.], tot_loss[loss=0.2008, simple_loss=0.3689, pruned_loss=0.1752, over 1423074.46 frames.], batch size: 20, lr: 2.62e-03
2022-04-28 08:17:38,268 INFO [train.py:763] (5/8) Epoch 0, batch 4300, loss[loss=0.1926, simple_loss=0.3573, pruned_loss=0.1398, over 7107.00 frames.], tot_loss[loss=0.2008, simple_loss=0.3691, pruned_loss=0.1716, over 1422591.06 frames.], batch size: 28, lr: 2.61e-03
2022-04-28 08:18:43,773 INFO [train.py:763] (5/8) Epoch 0, batch 4350, loss[loss=0.1949, simple_loss=0.3604, pruned_loss=0.1469, over 7440.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3699, pruned_loss=0.1686, over 1426524.82 frames.], batch size: 20, lr: 2.61e-03
2022-04-28 08:19:48,921 INFO [train.py:763] (5/8) Epoch 0, batch 4400, loss[loss=0.1902, simple_loss=0.3493, pruned_loss=0.1557, over 7283.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3697, pruned_loss=0.1658, over 1423973.58 frames.], batch size: 18, lr: 2.60e-03
2022-04-28 08:20:54,086 INFO [train.py:763] (5/8) Epoch 0, batch 4450, loss[loss=0.1858, simple_loss=0.3472, pruned_loss=0.1217, over 7430.00 frames.], tot_loss[loss=0.2014, simple_loss=0.3709, pruned_loss=0.1641, over 1423480.68 frames.], batch size: 20, lr: 2.59e-03
2022-04-28 08:21:59,575 INFO [train.py:763] (5/8) Epoch 0, batch 4500, loss[loss=0.2085, simple_loss=0.3814, pruned_loss=0.1784, over 6339.00 frames.], tot_loss[loss=0.2016, simple_loss=0.3713, pruned_loss=0.1626, over 1413963.02 frames.], batch size: 37, lr: 2.59e-03
2022-04-28 08:23:05,619 INFO [train.py:763] (5/8) Epoch 0, batch 4550, loss[loss=0.2043, simple_loss=0.3733, pruned_loss=0.1764, over 4767.00 frames.], tot_loss[loss=0.2025, simple_loss=0.3729, pruned_loss=0.1631, over 1394447.31 frames.], batch size: 52, lr: 2.58e-03
2022-04-28 08:24:44,868 INFO [train.py:763] (5/8) Epoch 1, batch 0, loss[loss=0.2048, simple_loss=0.377, pruned_loss=0.163, over 7148.00 frames.], tot_loss[loss=0.2048, simple_loss=0.377, pruned_loss=0.163, over 7148.00 frames.], batch size: 26, lr: 2.56e-03
2022-04-28 08:25:50,521 INFO [train.py:763] (5/8) Epoch 1, batch 50, loss[loss=0.2019, simple_loss=0.374, pruned_loss=0.1489, over 7234.00 frames.], tot_loss[loss=0.2005, simple_loss=0.3694, pruned_loss=0.1576, over 311774.24 frames.], batch size: 20, lr: 2.55e-03
2022-04-28 08:26:56,241 INFO [train.py:763] (5/8) Epoch 1, batch 100, loss[loss=0.1901, simple_loss=0.3503, pruned_loss=0.1493, over 7424.00 frames.], tot_loss[loss=0.1971, simple_loss=0.3639, pruned_loss=0.1517, over 560155.24 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:28:01,399 INFO [train.py:763] (5/8) Epoch 1, batch 150, loss[loss=0.1872, simple_loss=0.3466, pruned_loss=0.1391, over 7330.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3635, pruned_loss=0.1489, over 751178.15 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:29:06,953 INFO [train.py:763] (5/8) Epoch 1, batch 200, loss[loss=0.176, simple_loss=0.3268, pruned_loss=0.1257, over 7160.00 frames.], tot_loss[loss=0.1955, simple_loss=0.3615, pruned_loss=0.1474, over 901251.69 frames.], batch size: 19, lr: 2.53e-03
2022-04-28 08:30:12,408 INFO [train.py:763] (5/8) Epoch 1, batch 250, loss[loss=0.1906, simple_loss=0.3554, pruned_loss=0.1291, over 7375.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3605, pruned_loss=0.146, over 1015711.86 frames.], batch size: 23, lr: 2.53e-03
2022-04-28 08:31:17,608 INFO [train.py:763] (5/8) Epoch 1, batch 300, loss[loss=0.1943, simple_loss=0.3587, pruned_loss=0.149, over 7268.00 frames.], tot_loss[loss=0.1958, simple_loss=0.3623, pruned_loss=0.1464, over 1104806.40 frames.], batch size: 19, lr: 2.52e-03
2022-04-28 08:32:23,182 INFO [train.py:763] (5/8) Epoch 1, batch 350, loss[loss=0.1904, simple_loss=0.3563, pruned_loss=0.1223, over 7226.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3612, pruned_loss=0.1448, over 1173896.30 frames.], batch size: 21, lr: 2.51e-03
2022-04-28 08:33:29,299 INFO [train.py:763] (5/8) Epoch 1, batch 400, loss[loss=0.2196, simple_loss=0.4073, pruned_loss=0.1597, over 7145.00 frames.], tot_loss[loss=0.1955, simple_loss=0.362, pruned_loss=0.1451, over 1230795.64 frames.], batch size: 20, lr: 2.51e-03
2022-04-28 08:34:36,150 INFO [train.py:763] (5/8) Epoch 1, batch 450, loss[loss=0.1859, simple_loss=0.3451, pruned_loss=0.1329, over 7144.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3619, pruned_loss=0.1443, over 1275552.33 frames.], batch size: 19, lr: 2.50e-03
2022-04-28 08:35:42,355 INFO [train.py:763] (5/8) Epoch 1, batch 500, loss[loss=0.1938, simple_loss=0.3576, pruned_loss=0.1495, over 7168.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3615, pruned_loss=0.1438, over 1307750.66 frames.], batch size: 18, lr: 2.49e-03
2022-04-28 08:36:48,885 INFO [train.py:763] (5/8) Epoch 1, batch 550, loss[loss=0.2013, simple_loss=0.3716, pruned_loss=0.1547, over 7360.00 frames.], tot_loss[loss=0.1949, simple_loss=0.361, pruned_loss=0.1437, over 1333000.77 frames.], batch size: 19, lr: 2.49e-03
2022-04-28 08:37:55,734 INFO [train.py:763] (5/8) Epoch 1, batch 600, loss[loss=0.1959, simple_loss=0.3656, pruned_loss=0.1312, over 7387.00 frames.], tot_loss[loss=0.1953, simple_loss=0.3619, pruned_loss=0.1437, over 1354088.84 frames.], batch size: 23, lr: 2.48e-03
2022-04-28 08:39:01,287 INFO [train.py:763] (5/8) Epoch 1, batch 650, loss[loss=0.1791, simple_loss=0.33, pruned_loss=0.1412, over 7281.00 frames.], tot_loss[loss=0.1945, simple_loss=0.3605, pruned_loss=0.1428, over 1367837.83 frames.], batch size: 18, lr: 2.48e-03
2022-04-28 08:40:06,983 INFO [train.py:763] (5/8) Epoch 1, batch 700, loss[loss=0.2205, simple_loss=0.4019, pruned_loss=0.196, over 4716.00 frames.], tot_loss[loss=0.1941, simple_loss=0.3598, pruned_loss=0.1422, over 1379699.69 frames.], batch size: 52, lr: 2.47e-03
2022-04-28 08:41:12,400 INFO [train.py:763] (5/8) Epoch 1, batch 750, loss[loss=0.184, simple_loss=0.3428, pruned_loss=0.1261, over 7257.00 frames.], tot_loss[loss=0.1933, simple_loss=0.3586, pruned_loss=0.1404, over 1391532.21 frames.], batch size: 19, lr: 2.46e-03
2022-04-28 08:42:18,209 INFO [train.py:763] (5/8) Epoch 1, batch 800, loss[loss=0.1644, simple_loss=0.3096, pruned_loss=0.09654, over 7074.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3577, pruned_loss=0.14, over 1400742.66 frames.], batch size: 18, lr: 2.46e-03
2022-04-28 08:43:24,118 INFO [train.py:763] (5/8) Epoch 1, batch 850, loss[loss=0.18, simple_loss=0.3368, pruned_loss=0.1163, over 7329.00 frames.], tot_loss[loss=0.192, simple_loss=0.3563, pruned_loss=0.1385, over 1408578.70 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:44:29,833 INFO [train.py:763] (5/8) Epoch 1, batch 900, loss[loss=0.1793, simple_loss=0.3366, pruned_loss=0.1105, over 7426.00 frames.], tot_loss[loss=0.1919, simple_loss=0.3563, pruned_loss=0.1379, over 1412806.71 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:45:35,253 INFO [train.py:763] (5/8) Epoch 1, batch 950, loss[loss=0.1447, simple_loss=0.276, pruned_loss=0.06695, over 7261.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3557, pruned_loss=0.1369, over 1415459.05 frames.], batch size: 19, lr: 2.44e-03
2022-04-28 08:46:40,820 INFO [train.py:763] (5/8) Epoch 1, batch 1000, loss[loss=0.2072, simple_loss=0.3833, pruned_loss=0.1558, over 6657.00 frames.], tot_loss[loss=0.1909, simple_loss=0.3546, pruned_loss=0.1362, over 1417254.07 frames.], batch size: 31, lr: 2.43e-03
2022-04-28 08:47:46,481 INFO [train.py:763] (5/8) Epoch 1, batch 1050, loss[loss=0.1704, simple_loss=0.3201, pruned_loss=0.1031, over 7420.00 frames.], tot_loss[loss=0.1905, simple_loss=0.354, pruned_loss=0.1349, over 1418574.01 frames.], batch size: 20, lr: 2.43e-03
2022-04-28 08:48:51,696 INFO [train.py:763] (5/8) Epoch 1, batch 1100, loss[loss=0.1757, simple_loss=0.3263, pruned_loss=0.1252, over 7154.00 frames.], tot_loss[loss=0.1902, simple_loss=0.3537, pruned_loss=0.1337, over 1419554.26 frames.], batch size: 18, lr: 2.42e-03
2022-04-28 08:49:57,307 INFO [train.py:763] (5/8) Epoch 1, batch 1150, loss[loss=0.1956, simple_loss=0.3629, pruned_loss=0.1414, over 7245.00 frames.], tot_loss[loss=0.1893, simple_loss=0.3522, pruned_loss=0.1321, over 1423261.01 frames.], batch size: 20, lr: 2.41e-03
2022-04-28 08:51:02,493 INFO [train.py:763] (5/8) Epoch 1, batch 1200, loss[loss=0.18, simple_loss=0.3381, pruned_loss=0.1091, over 6980.00 frames.], tot_loss[loss=0.1892, simple_loss=0.352, pruned_loss=0.132, over 1422761.11 frames.], batch size: 28, lr: 2.41e-03
2022-04-28 08:52:07,808 INFO [train.py:763] (5/8) Epoch 1, batch 1250, loss[loss=0.1781, simple_loss=0.3319, pruned_loss=0.1217, over 7283.00 frames.], tot_loss[loss=0.1898, simple_loss=0.353, pruned_loss=0.1326, over 1422930.91 frames.], batch size: 18, lr: 2.40e-03
2022-04-28 08:53:12,963 INFO [train.py:763] (5/8) Epoch 1, batch 1300, loss[loss=0.2061, simple_loss=0.3843, pruned_loss=0.1399, over 7220.00 frames.], tot_loss[loss=0.1909, simple_loss=0.355, pruned_loss=0.1342, over 1417377.23 frames.], batch size: 21, lr: 2.40e-03
2022-04-28 08:54:18,353 INFO [train.py:763] (5/8) Epoch 1, batch 1350, loss[loss=0.1673, simple_loss=0.3135, pruned_loss=0.1057, over 7291.00 frames.], tot_loss[loss=0.1892, simple_loss=0.3521, pruned_loss=0.1313, over 1420716.34 frames.], batch size: 17, lr: 2.39e-03
2022-04-28 08:55:23,450 INFO [train.py:763] (5/8) Epoch 1, batch 1400, loss[loss=0.2055, simple_loss=0.3808, pruned_loss=0.1509, over 7236.00 frames.], tot_loss[loss=0.1892, simple_loss=0.352, pruned_loss=0.1316, over 1419266.27 frames.], batch size: 21, lr: 2.39e-03
2022-04-28 08:56:28,952 INFO [train.py:763] (5/8) Epoch 1, batch 1450, loss[loss=0.3981, simple_loss=0.4198, pruned_loss=0.1882, over 7196.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3536, pruned_loss=0.1345, over 1422633.72 frames.], batch size: 26, lr: 2.38e-03
2022-04-28 08:57:34,416 INFO [train.py:763] (5/8) Epoch 1, batch 1500, loss[loss=0.3426, simple_loss=0.3754, pruned_loss=0.1549, over 6607.00 frames.], tot_loss[loss=0.2383, simple_loss=0.3557, pruned_loss=0.1354, over 1423247.05 frames.], batch size: 38, lr: 2.37e-03
2022-04-28 08:58:40,151 INFO [train.py:763] (5/8) Epoch 1, batch 1550, loss[loss=0.2923, simple_loss=0.3447, pruned_loss=0.1199, over 7432.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3578, pruned_loss=0.1363, over 1426495.67 frames.], batch size: 20, lr: 2.37e-03
2022-04-28 08:59:47,371 INFO [train.py:763] (5/8) Epoch 1, batch 1600, loss[loss=0.2905, simple_loss=0.345, pruned_loss=0.118, over 7167.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3572, pruned_loss=0.1353, over 1425473.04 frames.], batch size: 18, lr: 2.36e-03
2022-04-28 09:00:52,896 INFO [train.py:763] (5/8) Epoch 1, batch 1650, loss[loss=0.3002, simple_loss=0.3602, pruned_loss=0.1201, over 7420.00 frames.], tot_loss[loss=0.2764, simple_loss=0.3563, pruned_loss=0.1336, over 1425295.00 frames.], batch size: 20, lr: 2.36e-03
2022-04-28 09:01:59,218 INFO [train.py:763] (5/8) Epoch 1, batch 1700, loss[loss=0.3357, simple_loss=0.3844, pruned_loss=0.1435, over 7416.00 frames.], tot_loss[loss=0.2837, simple_loss=0.3567, pruned_loss=0.1329, over 1424122.91 frames.], batch size: 21, lr: 2.35e-03
2022-04-28 09:03:06,116 INFO [train.py:763] (5/8) Epoch 1, batch 1750, loss[loss=0.2375, simple_loss=0.3032, pruned_loss=0.08595, over 7286.00 frames.], tot_loss[loss=0.2896, simple_loss=0.3579, pruned_loss=0.132, over 1424349.27 frames.], batch size: 18, lr: 2.34e-03
2022-04-28 09:04:13,397 INFO [train.py:763] (5/8) Epoch 1, batch 1800, loss[loss=0.2656, simple_loss=0.3185, pruned_loss=0.1063, over 7361.00 frames.], tot_loss[loss=0.2947, simple_loss=0.3584, pruned_loss=0.1322, over 1424973.01 frames.], batch size: 19, lr: 2.34e-03
2022-04-28 09:05:20,646 INFO [train.py:763] (5/8) Epoch 1, batch 1850, loss[loss=0.2831, simple_loss=0.3474, pruned_loss=0.1094, over 7321.00 frames.], tot_loss[loss=0.2973, simple_loss=0.3576, pruned_loss=0.1314, over 1426199.60 frames.], batch size: 20, lr: 2.33e-03
2022-04-28 09:06:26,268 INFO [train.py:763] (5/8) Epoch 1, batch 1900, loss[loss=0.2428, simple_loss=0.3021, pruned_loss=0.09173, over 7008.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3569, pruned_loss=0.1293, over 1429286.43 frames.], batch size: 16, lr: 2.33e-03
2022-04-28 09:07:32,761 INFO [train.py:763] (5/8) Epoch 1, batch 1950, loss[loss=0.2615, simple_loss=0.3235, pruned_loss=0.0997, over 7276.00 frames.], tot_loss[loss=0.2995, simple_loss=0.3571, pruned_loss=0.1287, over 1429429.93 frames.], batch size: 18, lr: 2.32e-03
2022-04-28 09:08:38,164 INFO [train.py:763] (5/8) Epoch 1, batch 2000, loss[loss=0.2659, simple_loss=0.3339, pruned_loss=0.099, over 7123.00 frames.], tot_loss[loss=0.3007, simple_loss=0.3575, pruned_loss=0.1281, over 1423593.32 frames.], batch size: 21, lr: 2.32e-03
2022-04-28 09:09:44,443 INFO [train.py:763] (5/8) Epoch 1, batch 2050, loss[loss=0.3179, simple_loss=0.3741, pruned_loss=0.1308, over 7060.00 frames.], tot_loss[loss=0.3, simple_loss=0.3562, pruned_loss=0.1266, over 1424699.21 frames.], batch size: 28, lr: 2.31e-03
2022-04-28 09:10:49,772 INFO [train.py:763] (5/8) Epoch 1, batch 2100, loss[loss=0.24, simple_loss=0.3021, pruned_loss=0.08897, over 7406.00 frames.], tot_loss[loss=0.2996, simple_loss=0.3553, pruned_loss=0.1257, over 1424696.86 frames.], batch size: 18, lr: 2.31e-03
2022-04-28 09:11:55,367 INFO [train.py:763] (5/8) Epoch 1, batch 2150, loss[loss=0.2409, simple_loss=0.3128, pruned_loss=0.08449, over 7409.00 frames.], tot_loss[loss=0.298, simple_loss=0.3535, pruned_loss=0.1241, over 1423926.51 frames.], batch size: 21, lr: 2.30e-03
2022-04-28 09:13:01,259 INFO [train.py:763] (5/8) Epoch 1, batch 2200, loss[loss=0.3414, simple_loss=0.3835, pruned_loss=0.1497, over 7134.00 frames.], tot_loss[loss=0.2978, simple_loss=0.3532, pruned_loss=0.1235, over 1423096.21 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:14:06,872 INFO [train.py:763] (5/8) Epoch 1, batch 2250, loss[loss=0.2669, simple_loss=0.3401, pruned_loss=0.09685, over 7223.00 frames.], tot_loss[loss=0.2954, simple_loss=0.3515, pruned_loss=0.1214, over 1424521.84 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:15:14,114 INFO [train.py:763] (5/8) Epoch 1, batch 2300, loss[loss=0.3125, simple_loss=0.3686, pruned_loss=0.1282, over 7219.00 frames.], tot_loss[loss=0.2957, simple_loss=0.3518, pruned_loss=0.1211, over 1425331.17 frames.], batch size: 22, lr: 2.28e-03
2022-04-28 09:16:21,362 INFO [train.py:763] (5/8) Epoch 1, batch 2350, loss[loss=0.2684, simple_loss=0.3499, pruned_loss=0.09347, over 7237.00 frames.], tot_loss[loss=0.2969, simple_loss=0.3528, pruned_loss=0.1215, over 1424084.81 frames.], batch size: 20, lr: 2.28e-03
2022-04-28 09:17:26,502 INFO [train.py:763] (5/8) Epoch 1, batch 2400, loss[loss=0.2971, simple_loss=0.3628, pruned_loss=0.1156, over 7313.00 frames.], tot_loss[loss=0.2968, simple_loss=0.3534, pruned_loss=0.121, over 1423164.51 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:18:31,933 INFO [train.py:763] (5/8) Epoch 1, batch 2450, loss[loss=0.3054, simple_loss=0.371, pruned_loss=0.12, over 7333.00 frames.], tot_loss[loss=0.2963, simple_loss=0.3531, pruned_loss=0.1204, over 1426579.13 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:19:37,102 INFO [train.py:763] (5/8) Epoch 1, batch 2500, loss[loss=0.3047, simple_loss=0.3628, pruned_loss=0.1233, over 7172.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3541, pruned_loss=0.1206, over 1426985.51 frames.], batch size: 26, lr: 2.26e-03
2022-04-28 09:20:43,303 INFO [train.py:763] (5/8) Epoch 1, batch 2550, loss[loss=0.263, simple_loss=0.3166, pruned_loss=0.1047, over 6990.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3538, pruned_loss=0.1206, over 1427184.23 frames.], batch size: 16, lr: 2.26e-03
2022-04-28 09:21:48,830 INFO [train.py:763] (5/8) Epoch 1, batch 2600, loss[loss=0.3508, simple_loss=0.4012, pruned_loss=0.1502, over 7190.00 frames.], tot_loss[loss=0.2966, simple_loss=0.3534, pruned_loss=0.1201, over 1429088.41 frames.], batch size: 26, lr: 2.25e-03
2022-04-28 09:22:54,018 INFO [train.py:763] (5/8) Epoch 1, batch 2650, loss[loss=0.3262, simple_loss=0.3808, pruned_loss=0.1358, over 6490.00 frames.], tot_loss[loss=0.2964, simple_loss=0.3532, pruned_loss=0.12, over 1428164.98 frames.], batch size: 37, lr: 2.25e-03
2022-04-28 09:24:00,444 INFO [train.py:763] (5/8) Epoch 1, batch 2700, loss[loss=0.3756, simple_loss=0.4225, pruned_loss=0.1644, over 6828.00 frames.], tot_loss[loss=0.2952, simple_loss=0.3527, pruned_loss=0.119, over 1428014.58 frames.], batch size: 31, lr: 2.24e-03
2022-04-28 09:25:06,558 INFO [train.py:763] (5/8) Epoch 1, batch 2750, loss[loss=0.2994, simple_loss=0.3622, pruned_loss=0.1183, over 7292.00 frames.], tot_loss[loss=0.2951, simple_loss=0.3523, pruned_loss=0.1191, over 1424059.22 frames.], batch size: 24, lr: 2.24e-03
2022-04-28 09:26:12,254 INFO [train.py:763] (5/8) Epoch 1, batch 2800, loss[loss=0.3122, simple_loss=0.3764, pruned_loss=0.124, over 7187.00 frames.], tot_loss[loss=0.2947, simple_loss=0.3524, pruned_loss=0.1186, over 1427157.17 frames.], batch size: 23, lr: 2.23e-03
2022-04-28 09:27:17,553 INFO [train.py:763] (5/8) Epoch 1, batch 2850, loss[loss=0.2853, simple_loss=0.3432, pruned_loss=0.1137, over 7302.00 frames.], tot_loss[loss=0.2931, simple_loss=0.3515, pruned_loss=0.1174, over 1426939.53 frames.], batch size: 24, lr: 2.23e-03
2022-04-28 09:28:22,524 INFO [train.py:763] (5/8) Epoch 1, batch 2900, loss[loss=0.2627, simple_loss=0.3364, pruned_loss=0.09453, over 7228.00 frames.], tot_loss[loss=0.2939, simple_loss=0.3527, pruned_loss=0.1176, over 1421064.84 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:29:27,939 INFO [train.py:763] (5/8) Epoch 1, batch 2950, loss[loss=0.2663, simple_loss=0.3241, pruned_loss=0.1042, over 7234.00 frames.], tot_loss[loss=0.2932, simple_loss=0.3522, pruned_loss=0.1172, over 1421738.02 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:30:33,556 INFO [train.py:763] (5/8) Epoch 1, batch 3000, loss[loss=0.2594, simple_loss=0.3164, pruned_loss=0.1012, over 7292.00 frames.], tot_loss[loss=0.292, simple_loss=0.3511, pruned_loss=0.1164, over 1425123.16 frames.], batch size: 17, lr: 2.21e-03
2022-04-28 09:30:33,557 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 09:30:49,512 INFO [train.py:792] (5/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
2022-04-28 09:31:55,924 INFO [train.py:763] (5/8) Epoch 1, batch 3050, loss[loss=0.2787, simple_loss=0.3402, pruned_loss=0.1086, over 7284.00 frames.], tot_loss[loss=0.2918, simple_loss=0.3509, pruned_loss=0.1164, over 1420794.91 frames.], batch size: 18, lr: 2.20e-03
2022-04-28 09:33:01,971 INFO [train.py:763] (5/8) Epoch 1, batch 3100, loss[loss=0.3439, simple_loss=0.3737, pruned_loss=0.157, over 4893.00 frames.], tot_loss[loss=0.2939, simple_loss=0.3523, pruned_loss=0.1178, over 1420481.61 frames.], batch size: 52, lr: 2.20e-03
2022-04-28 09:34:07,387 INFO [train.py:763] (5/8) Epoch 1, batch 3150, loss[loss=0.2523, simple_loss=0.3179, pruned_loss=0.09334, over 6759.00 frames.], tot_loss[loss=0.2931, simple_loss=0.352, pruned_loss=0.1171, over 1422692.60 frames.], batch size: 15, lr: 2.19e-03
2022-04-28 09:35:13,550 INFO [train.py:763] (5/8) Epoch 1, batch 3200, loss[loss=0.3102, simple_loss=0.3606, pruned_loss=0.1299, over 4951.00 frames.], tot_loss[loss=0.2937, simple_loss=0.3531, pruned_loss=0.1171, over 1413066.31 frames.], batch size: 53, lr: 2.19e-03
2022-04-28 09:36:19,400 INFO [train.py:763] (5/8) Epoch 1, batch 3250, loss[loss=0.3015, simple_loss=0.3715, pruned_loss=0.1157, over 7214.00 frames.], tot_loss[loss=0.2933, simple_loss=0.3532, pruned_loss=0.1167, over 1415696.94 frames.], batch size: 23, lr: 2.18e-03
2022-04-28 09:37:26,025 INFO [train.py:763] (5/8) Epoch 1, batch 3300, loss[loss=0.3419, simple_loss=0.3796, pruned_loss=0.1521, over 7195.00 frames.], tot_loss[loss=0.2906, simple_loss=0.3515, pruned_loss=0.1149, over 1420005.41 frames.], batch size: 22, lr: 2.18e-03
2022-04-28 09:38:31,143 INFO [train.py:763] (5/8) Epoch 1, batch 3350, loss[loss=0.2944, simple_loss=0.3676, pruned_loss=0.1106, over 7184.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3515, pruned_loss=0.1146, over 1423022.70 frames.], batch size: 26, lr: 2.18e-03
2022-04-28 09:39:36,462 INFO [train.py:763] (5/8) Epoch 1, batch 3400, loss[loss=0.2659, simple_loss=0.3261, pruned_loss=0.1029, over 7116.00 frames.], tot_loss[loss=0.2894, simple_loss=0.3505, pruned_loss=0.1141, over 1424989.96 frames.], batch size: 17, lr: 2.17e-03
2022-04-28 09:40:52,300 INFO [train.py:763] (5/8) Epoch 1, batch 3450, loss[loss=0.3056, simple_loss=0.374, pruned_loss=0.1186, over 7321.00 frames.], tot_loss[loss=0.2896, simple_loss=0.351, pruned_loss=0.1141, over 1427437.39 frames.], batch size: 24, lr: 2.17e-03
2022-04-28 09:41:59,074 INFO [train.py:763] (5/8) Epoch 1, batch 3500, loss[loss=0.3154, simple_loss=0.3632, pruned_loss=0.1338, over 6372.00 frames.], tot_loss[loss=0.29, simple_loss=0.3514, pruned_loss=0.1143, over 1423612.69 frames.], batch size: 37, lr: 2.16e-03
2022-04-28 09:43:05,805 INFO [train.py:763] (5/8) Epoch 1, batch 3550, loss[loss=0.3058, simple_loss=0.3734, pruned_loss=0.1191, over 7307.00 frames.], tot_loss[loss=0.2887, simple_loss=0.3506, pruned_loss=0.1134, over 1423777.99 frames.], batch size: 25, lr: 2.16e-03
2022-04-28 09:44:12,976 INFO [train.py:763] (5/8) Epoch 1, batch 3600, loss[loss=0.3131, simple_loss=0.3678, pruned_loss=0.1293, over 7244.00 frames.], tot_loss[loss=0.2888, simple_loss=0.3509, pruned_loss=0.1133, over 1425173.49 frames.], batch size: 20, lr: 2.15e-03
2022-04-28 09:45:20,596 INFO [train.py:763] (5/8) Epoch 1, batch 3650, loss[loss=0.278, simple_loss=0.3241, pruned_loss=0.116, over 6802.00 frames.], tot_loss[loss=0.2878, simple_loss=0.3501, pruned_loss=0.1127, over 1426592.07 frames.], batch size: 15, lr: 2.15e-03
2022-04-28 09:46:27,942 INFO [train.py:763] (5/8) Epoch 1, batch 3700, loss[loss=0.2523, simple_loss=0.3203, pruned_loss=0.09216, over 7163.00 frames.], tot_loss[loss=0.2876, simple_loss=0.3501, pruned_loss=0.1126, over 1428630.84 frames.], batch size: 19, lr: 2.14e-03
2022-04-28 09:47:33,414 INFO [train.py:763] (5/8) Epoch 1, batch 3750, loss[loss=0.3371, simple_loss=0.3937, pruned_loss=0.1403, over 7286.00 frames.], tot_loss[loss=0.2882, simple_loss=0.351, pruned_loss=0.1127, over 1429581.37 frames.], batch size: 24, lr: 2.14e-03
2022-04-28 09:48:38,889 INFO [train.py:763] (5/8) Epoch 1, batch 3800, loss[loss=0.2391, simple_loss=0.3001, pruned_loss=0.08911, over 6737.00 frames.], tot_loss[loss=0.2873, simple_loss=0.3505, pruned_loss=0.1121, over 1428980.26 frames.], batch size: 15, lr: 2.13e-03
2022-04-28 09:49:44,150 INFO [train.py:763] (5/8) Epoch 1, batch 3850, loss[loss=0.3266, simple_loss=0.3869, pruned_loss=0.1331, over 7099.00 frames.], tot_loss[loss=0.2888, simple_loss=0.3521, pruned_loss=0.1128, over 1430631.26 frames.], batch size: 26, lr: 2.13e-03
2022-04-28 09:50:49,554 INFO [train.py:763] (5/8) Epoch 1, batch 3900, loss[loss=0.2624, simple_loss=0.333, pruned_loss=0.09586, over 7319.00 frames.], tot_loss[loss=0.2864, simple_loss=0.3503, pruned_loss=0.1113, over 1429662.76 frames.], batch size: 24, lr: 2.12e-03
2022-04-28 09:51:55,502 INFO [train.py:763] (5/8) Epoch 1, batch 3950, loss[loss=0.2998, simple_loss=0.3664, pruned_loss=0.1166, over 7104.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3491, pruned_loss=0.1106, over 1427311.84 frames.], batch size: 21, lr: 2.12e-03
2022-04-28 09:53:01,246 INFO [train.py:763] (5/8) Epoch 1, batch 4000, loss[loss=0.3238, simple_loss=0.3792, pruned_loss=0.1342, over 7200.00 frames.], tot_loss[loss=0.2851, simple_loss=0.3491, pruned_loss=0.1106, over 1428001.64 frames.], batch size: 22, lr: 2.11e-03
2022-04-28 09:54:07,053 INFO [train.py:763] (5/8) Epoch 1, batch 4050, loss[loss=0.3394, simple_loss=0.3941, pruned_loss=0.1423, over 6819.00 frames.], tot_loss[loss=0.2855, simple_loss=0.3493, pruned_loss=0.1108, over 1426597.60 frames.], batch size: 31, lr: 2.11e-03
2022-04-28 09:55:12,320 INFO [train.py:763] (5/8) Epoch 1, batch 4100, loss[loss=0.2751, simple_loss=0.3519, pruned_loss=0.09913, over 7217.00 frames.], tot_loss[loss=0.2867, simple_loss=0.3497, pruned_loss=0.1119, over 1420661.03 frames.], batch size: 21, lr: 2.10e-03
2022-04-28 09:56:17,397 INFO [train.py:763] (5/8) Epoch 1, batch 4150, loss[loss=0.3593, simple_loss=0.4181, pruned_loss=0.1502, over 6774.00 frames.], tot_loss[loss=0.2854, simple_loss=0.3487, pruned_loss=0.1111, over 1419856.02 frames.], batch size: 31, lr: 2.10e-03
2022-04-28 09:57:22,848 INFO [train.py:763] (5/8) Epoch 1, batch 4200, loss[loss=0.2418, simple_loss=0.3086, pruned_loss=0.08754, over 7283.00 frames.], tot_loss[loss=0.2848, simple_loss=0.3479, pruned_loss=0.1108, over 1417283.87 frames.], batch size: 18, lr: 2.10e-03
2022-04-28 09:58:27,895 INFO [train.py:763] (5/8) Epoch 1, batch 4250, loss[loss=0.2545, simple_loss=0.318, pruned_loss=0.09546, over 7291.00 frames.], tot_loss[loss=0.2852, simple_loss=0.348, pruned_loss=0.1112, over 1413199.71 frames.], batch size: 18, lr: 2.09e-03
2022-04-28 09:59:34,316 INFO [train.py:763] (5/8) Epoch 1, batch 4300, loss[loss=0.2896, simple_loss=0.3525, pruned_loss=0.1134, over 7277.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3478, pruned_loss=0.1104, over 1413434.86 frames.], batch size: 25, lr: 2.09e-03
2022-04-28 10:00:39,974 INFO [train.py:763] (5/8) Epoch 1, batch 4350, loss[loss=0.1993, simple_loss=0.2788, pruned_loss=0.05989, over 6993.00 frames.], tot_loss[loss=0.284, simple_loss=0.3474, pruned_loss=0.1103, over 1414208.50 frames.], batch size: 16, lr: 2.08e-03
2022-04-28 10:01:45,340 INFO [train.py:763] (5/8) Epoch 1, batch 4400, loss[loss=0.2937, simple_loss=0.3672, pruned_loss=0.1101, over 7312.00 frames.], tot_loss[loss=0.2837, simple_loss=0.3472, pruned_loss=0.1101, over 1409167.01 frames.], batch size: 21, lr: 2.08e-03
2022-04-28 10:02:50,270 INFO [train.py:763] (5/8) Epoch 1, batch 4450, loss[loss=0.3023, simple_loss=0.3605, pruned_loss=0.122, over 6412.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3479, pruned_loss=0.1103, over 1401692.57 frames.], batch size: 37, lr: 2.07e-03
2022-04-28 10:03:55,339 INFO [train.py:763] (5/8) Epoch 1, batch 4500, loss[loss=0.3018, simple_loss=0.3684, pruned_loss=0.1175, over 6211.00 frames.], tot_loss[loss=0.2856, simple_loss=0.3482, pruned_loss=0.1115, over 1386690.91 frames.], batch size: 37, lr: 2.07e-03
2022-04-28 10:04:59,438 INFO [train.py:763] (5/8) Epoch 1, batch 4550, loss[loss=0.3733, simple_loss=0.3926, pruned_loss=0.177, over 5041.00 frames.], tot_loss[loss=0.2891, simple_loss=0.3506, pruned_loss=0.1138, over 1356199.21 frames.], batch size: 52, lr: 2.06e-03
2022-04-28 10:06:27,060 INFO [train.py:763] (5/8) Epoch 2, batch 0, loss[loss=0.2589, simple_loss=0.326, pruned_loss=0.09591, over 7301.00 frames.], tot_loss[loss=0.2589, simple_loss=0.326, pruned_loss=0.09591, over 7301.00 frames.], batch size: 17, lr: 2.02e-03
2022-04-28 10:07:33,523 INFO [train.py:763] (5/8) Epoch 2, batch 50, loss[loss=0.3094, simple_loss=0.3761, pruned_loss=0.1214, over 7285.00 frames.], tot_loss[loss=0.2827, simple_loss=0.3459, pruned_loss=0.1097, over 321707.03 frames.], batch size: 25, lr: 2.02e-03
2022-04-28 10:08:39,168 INFO [train.py:763] (5/8) Epoch 2, batch 100, loss[loss=0.2769, simple_loss=0.3214, pruned_loss=0.1163, over 6988.00 frames.], tot_loss[loss=0.2795, simple_loss=0.3457, pruned_loss=0.1066, over 568912.89 frames.], batch size: 16, lr: 2.01e-03
2022-04-28 10:09:45,127 INFO [train.py:763] (5/8) Epoch 2, batch 150, loss[loss=0.3153, simple_loss=0.3743, pruned_loss=0.1282, over 6715.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3402, pruned_loss=0.1032, over 760970.38 frames.], batch size: 31, lr: 2.01e-03
2022-04-28 10:10:50,702 INFO [train.py:763] (5/8) Epoch 2, batch 200, loss[loss=0.2515, simple_loss=0.312, pruned_loss=0.09547, over 6762.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3395, pruned_loss=0.103, over 900128.61 frames.], batch size: 15, lr: 2.00e-03
2022-04-28 10:11:56,045 INFO [train.py:763] (5/8) Epoch 2, batch 250, loss[loss=0.2541, simple_loss=0.3282, pruned_loss=0.08996, over 7366.00 frames.], tot_loss[loss=0.2751, simple_loss=0.3418, pruned_loss=0.1042, over 1011166.49 frames.], batch size: 19, lr: 2.00e-03
2022-04-28 10:13:01,580 INFO [train.py:763] (5/8) Epoch 2, batch 300, loss[loss=0.3069, simple_loss=0.3724, pruned_loss=0.1207, over 6804.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3434, pruned_loss=0.1052, over 1101059.51 frames.], batch size: 31, lr: 2.00e-03
2022-04-28 10:14:07,030 INFO [train.py:763] (5/8) Epoch 2, batch 350, loss[loss=0.2881, simple_loss=0.3646, pruned_loss=0.1058, over 7316.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3444, pruned_loss=0.1061, over 1171755.43 frames.], batch size: 21, lr: 1.99e-03
2022-04-28 10:15:12,742 INFO [train.py:763] (5/8) Epoch 2, batch 400, loss[loss=0.2803, simple_loss=0.3414, pruned_loss=0.1096, over 7296.00 frames.], tot_loss[loss=0.2804, simple_loss=0.3459, pruned_loss=0.1074, over 1223138.63 frames.], batch size: 24, lr: 1.99e-03
2022-04-28 10:16:17,707 INFO [train.py:763] (5/8) Epoch 2, batch 450, loss[loss=0.2767, simple_loss=0.341, pruned_loss=0.1062, over 7199.00 frames.], tot_loss[loss=0.2797, simple_loss=0.3458, pruned_loss=0.1068, over 1263362.17 frames.], batch size: 22, lr: 1.98e-03
2022-04-28 10:17:41,020 INFO [train.py:763] (5/8) Epoch 2, batch 500, loss[loss=0.2299, simple_loss=0.3039, pruned_loss=0.07792, over 6994.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3445, pruned_loss=0.1055, over 1302115.88 frames.], batch size: 16, lr: 1.98e-03
2022-04-28 10:19:24,532 INFO [train.py:763] (5/8) Epoch 2, batch 550, loss[loss=0.2755, simple_loss=0.3508, pruned_loss=0.1001, over 7222.00 frames.], tot_loss[loss=0.2762, simple_loss=0.3439, pruned_loss=0.1042, over 1331971.79 frames.], batch size: 21, lr: 1.98e-03
2022-04-28 10:20:31,151 INFO [train.py:763] (5/8) Epoch 2, batch 600, loss[loss=0.3091, simple_loss=0.3875, pruned_loss=0.1154, over 7297.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3427, pruned_loss=0.1036, over 1352497.30 frames.], batch size: 25, lr: 1.97e-03
2022-04-28 10:21:56,823 INFO [train.py:763] (5/8) Epoch 2, batch 650, loss[loss=0.2719, simple_loss=0.3329, pruned_loss=0.1054, over 7351.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3423, pruned_loss=0.1038, over 1367415.98 frames.], batch size: 19, lr: 1.97e-03
2022-04-28 10:23:03,995 INFO [train.py:763] (5/8) Epoch 2, batch 700, loss[loss=0.253, simple_loss=0.3415, pruned_loss=0.08218, over 7220.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3429, pruned_loss=0.1042, over 1378148.72 frames.], batch size: 21, lr: 1.96e-03
2022-04-28 10:24:09,352 INFO [train.py:763] (5/8) Epoch 2, batch 750, loss[loss=0.2693, simple_loss=0.3562, pruned_loss=0.09116, over 7197.00 frames.], tot_loss[loss=0.276, simple_loss=0.3433, pruned_loss=0.1044, over 1391329.14 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:25:14,627 INFO [train.py:763] (5/8) Epoch 2, batch 800, loss[loss=0.3145, simple_loss=0.3649, pruned_loss=0.1321, over 7205.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3436, pruned_loss=0.1039, over 1402492.25 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:26:20,186 INFO [train.py:763] (5/8) Epoch 2, batch 850, loss[loss=0.3154, simple_loss=0.3748, pruned_loss=0.1281, over 7300.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3426, pruned_loss=0.1033, over 1409804.18 frames.], batch size: 25, lr: 1.95e-03
2022-04-28 10:27:26,319 INFO [train.py:763] (5/8) Epoch 2, batch 900, loss[loss=0.239, simple_loss=0.3146, pruned_loss=0.08172, over 7077.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3433, pruned_loss=0.104, over 1411818.73 frames.], batch size: 18, lr: 1.95e-03
2022-04-28 10:28:31,604 INFO [train.py:763] (5/8) Epoch 2, batch 950, loss[loss=0.2512, simple_loss=0.3352, pruned_loss=0.08363, over 7142.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3426, pruned_loss=0.1031, over 1417028.19 frames.], batch size: 20, lr: 1.94e-03
2022-04-28 10:29:36,676 INFO [train.py:763] (5/8) Epoch 2, batch 1000, loss[loss=0.3469, simple_loss=0.4029, pruned_loss=0.1455, over 6830.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3439, pruned_loss=0.1036, over 1417160.71 frames.], batch size: 31, lr: 1.94e-03
2022-04-28 10:30:41,960 INFO [train.py:763] (5/8) Epoch 2, batch 1050, loss[loss=0.2145, simple_loss=0.2885, pruned_loss=0.0702, over 7295.00 frames.], tot_loss[loss=0.2748, simple_loss=0.3429, pruned_loss=0.1033, over 1414898.47 frames.], batch size: 18, lr: 1.94e-03
2022-04-28 10:31:48,324 INFO [train.py:763] (5/8) Epoch 2, batch 1100, loss[loss=0.266, simple_loss=0.334, pruned_loss=0.09895, over 7219.00 frames.], tot_loss[loss=0.2756, simple_loss=0.3439, pruned_loss=0.1036, over 1419539.80 frames.], batch size: 21, lr: 1.93e-03
2022-04-28 10:32:55,822 INFO [train.py:763] (5/8) Epoch 2, batch 1150, loss[loss=0.3526, simple_loss=0.3994, pruned_loss=0.1529, over 7226.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3425, pruned_loss=0.1031, over 1421008.77 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:34:03,567 INFO [train.py:763] (5/8) Epoch 2, batch 1200, loss[loss=0.2984, simple_loss=0.3568, pruned_loss=0.1199, over 7419.00 frames.], tot_loss[loss=0.2742, simple_loss=0.3425, pruned_loss=0.103, over 1424496.33 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:35:11,229 INFO [train.py:763] (5/8) Epoch 2, batch 1250, loss[loss=0.2877, simple_loss=0.3666, pruned_loss=0.1045, over 7408.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3422, pruned_loss=0.1024, over 1425283.30 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:36:17,280 INFO [train.py:763] (5/8) Epoch 2, batch 1300, loss[loss=0.2647, simple_loss=0.3399, pruned_loss=0.09471, over 7334.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3408, pruned_loss=0.1013, over 1426990.70 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:37:22,334 INFO [train.py:763] (5/8) Epoch 2, batch 1350, loss[loss=0.2886, simple_loss=0.3471, pruned_loss=0.1151, over 7430.00 frames.], tot_loss[loss=0.2732, simple_loss=0.342, pruned_loss=0.1022, over 1426659.07 frames.], batch size: 20, lr: 1.91e-03
2022-04-28 10:38:27,406 INFO [train.py:763] (5/8) Epoch 2, batch 1400, loss[loss=0.2492, simple_loss=0.3338, pruned_loss=0.08235, over 7159.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3422, pruned_loss=0.1022, over 1423438.33 frames.], batch size: 19, lr: 1.91e-03
2022-04-28 10:39:32,825 INFO [train.py:763] (5/8) Epoch 2, batch 1450, loss[loss=0.2586, simple_loss=0.303, pruned_loss=0.107, over 7114.00 frames.], tot_loss[loss=0.2722, simple_loss=0.341, pruned_loss=0.1017, over 1420103.32 frames.], batch size: 17, lr: 1.91e-03
2022-04-28 10:40:38,393 INFO [train.py:763] (5/8) Epoch 2, batch 1500, loss[loss=0.3572, simple_loss=0.4019, pruned_loss=0.1563, over 7313.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3419, pruned_loss=0.1024, over 1419309.19 frames.], batch size: 21, lr: 1.90e-03
2022-04-28 10:41:43,977 INFO [train.py:763] (5/8) Epoch 2, batch 1550, loss[loss=0.2454, simple_loss=0.3228, pruned_loss=0.08395, over 7165.00 frames.], tot_loss[loss=0.2708, simple_loss=0.3404, pruned_loss=0.1006, over 1423273.34 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:42:49,545 INFO [train.py:763] (5/8) Epoch 2, batch 1600, loss[loss=0.2479, simple_loss=0.3288, pruned_loss=0.08353, over 7162.00 frames.], tot_loss[loss=0.2699, simple_loss=0.3397, pruned_loss=0.1001, over 1424197.00 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:43:56,347 INFO [train.py:763] (5/8) Epoch 2, batch 1650, loss[loss=0.2076, simple_loss=0.2887, pruned_loss=0.06329, over 7433.00 frames.], tot_loss[loss=0.268, simple_loss=0.3384, pruned_loss=0.09877, over 1426322.33 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:45:02,863 INFO [train.py:763] (5/8) Epoch 2, batch 1700, loss[loss=0.2491, simple_loss=0.3198, pruned_loss=0.08915, over 7141.00 frames.], tot_loss[loss=0.269, simple_loss=0.339, pruned_loss=0.09947, over 1416350.49 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:46:08,593 INFO [train.py:763] (5/8) Epoch 2, batch 1750, loss[loss=0.2637, simple_loss=0.3488, pruned_loss=0.08935, over 7226.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3387, pruned_loss=0.09874, over 1423661.09 frames.], batch size: 20, lr: 1.88e-03
2022-04-28 10:47:13,952 INFO [train.py:763] (5/8) Epoch 2, batch 1800, loss[loss=0.2899, simple_loss=0.3515, pruned_loss=0.1142, over 7110.00 frames.], tot_loss[loss=0.2691, simple_loss=0.339, pruned_loss=0.09958, over 1417201.89 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:48:20,972 INFO [train.py:763] (5/8) Epoch 2, batch 1850, loss[loss=0.2831, simple_loss=0.3465, pruned_loss=0.1098, over 7415.00 frames.], tot_loss[loss=0.2677, simple_loss=0.338, pruned_loss=0.09869, over 1418882.58 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:49:26,581 INFO [train.py:763] (5/8) Epoch 2, batch 1900, loss[loss=0.2405, simple_loss=0.3182, pruned_loss=0.08145, over 7156.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3386, pruned_loss=0.09928, over 1416358.78 frames.], batch size: 18, lr: 1.87e-03
2022-04-28 10:50:31,925 INFO [train.py:763] (5/8) Epoch 2, batch 1950, loss[loss=0.3296, simple_loss=0.383, pruned_loss=0.1381, over 6778.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3379, pruned_loss=0.09938, over 1418212.53 frames.], batch size: 31, lr: 1.87e-03
2022-04-28 10:51:37,338 INFO [train.py:763] (5/8) Epoch 2, batch 2000, loss[loss=0.2611, simple_loss=0.3346, pruned_loss=0.09377, over 7164.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3369, pruned_loss=0.09848, over 1422109.59 frames.], batch size: 19, lr: 1.87e-03
2022-04-28 10:52:43,681 INFO [train.py:763] (5/8) Epoch 2, batch 2050, loss[loss=0.3739, simple_loss=0.3883, pruned_loss=0.1797, over 5066.00 frames.], tot_loss[loss=0.2695, simple_loss=0.339, pruned_loss=0.09998, over 1421591.67 frames.], batch size: 52, lr: 1.86e-03
2022-04-28 10:53:49,754 INFO [train.py:763] (5/8) Epoch 2, batch 2100, loss[loss=0.2523, simple_loss=0.3255, pruned_loss=0.08955, over 7323.00 frames.], tot_loss[loss=0.2686, simple_loss=0.3385, pruned_loss=0.09939, over 1424838.71 frames.], batch size: 21, lr: 1.86e-03
2022-04-28 10:54:55,198 INFO [train.py:763] (5/8) Epoch 2, batch 2150, loss[loss=0.3057, simple_loss=0.3555, pruned_loss=0.128, over 7227.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3383, pruned_loss=0.09858, over 1425845.77 frames.], batch size: 20, lr: 1.86e-03
2022-04-28 10:56:00,719 INFO [train.py:763] (5/8) Epoch 2, batch 2200, loss[loss=0.2568, simple_loss=0.3349, pruned_loss=0.08933, over 7133.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3373, pruned_loss=0.09808, over 1424927.63 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:57:05,942 INFO [train.py:763] (5/8) Epoch 2, batch 2250, loss[loss=0.2756, simple_loss=0.3543, pruned_loss=0.09849, over 7328.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3382, pruned_loss=0.09818, over 1424912.89 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:58:11,388 INFO [train.py:763] (5/8) Epoch 2, batch 2300, loss[loss=0.26, simple_loss=0.3389, pruned_loss=0.09059, over 7355.00 frames.], tot_loss[loss=0.2663, simple_loss=0.3369, pruned_loss=0.09781, over 1413505.44 frames.], batch size: 19, lr: 1.85e-03
2022-04-28 10:59:16,569 INFO [train.py:763] (5/8) Epoch 2, batch 2350, loss[loss=0.2204, simple_loss=0.3015, pruned_loss=0.06961, over 7257.00 frames.], tot_loss[loss=0.2657, simple_loss=0.3364, pruned_loss=0.09747, over 1415317.98 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:00:21,744 INFO [train.py:763] (5/8) Epoch 2, batch 2400, loss[loss=0.2141, simple_loss=0.2939, pruned_loss=0.06717, over 7249.00 frames.], tot_loss[loss=0.2675, simple_loss=0.3381, pruned_loss=0.09849, over 1418741.56 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:01:26,808 INFO [train.py:763] (5/8) Epoch 2, batch 2450, loss[loss=0.2909, simple_loss=0.3541, pruned_loss=0.1139, over 7223.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3382, pruned_loss=0.09834, over 1415968.05 frames.], batch size: 20, lr: 1.84e-03
2022-04-28 11:02:32,500 INFO [train.py:763] (5/8) Epoch 2, batch 2500, loss[loss=0.2577, simple_loss=0.3306, pruned_loss=0.09241, over 7152.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3377, pruned_loss=0.09783, over 1414628.59 frames.], batch size: 19, lr: 1.83e-03
2022-04-28 11:03:38,317 INFO [train.py:763] (5/8) Epoch 2, batch 2550, loss[loss=0.2629, simple_loss=0.3538, pruned_loss=0.08603, over 7210.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3366, pruned_loss=0.09732, over 1413921.09 frames.], batch size: 21, lr: 1.83e-03
2022-04-28 11:04:44,225 INFO [train.py:763] (5/8) Epoch 2, batch 2600, loss[loss=0.23, simple_loss=0.3113, pruned_loss=0.07432, over 7274.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3363, pruned_loss=0.09672, over 1419599.00 frames.], batch size: 18, lr: 1.83e-03
2022-04-28 11:05:50,137 INFO [train.py:763] (5/8) Epoch 2, batch 2650, loss[loss=0.2594, simple_loss=0.3281, pruned_loss=0.09532, over 7325.00 frames.], tot_loss[loss=0.2644, simple_loss=0.3357, pruned_loss=0.09653, over 1419374.59 frames.], batch size: 20, lr: 1.82e-03
2022-04-28 11:06:55,496 INFO [train.py:763] (5/8) Epoch 2, batch 2700, loss[loss=0.1953, simple_loss=0.2878, pruned_loss=0.05143, over 7068.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3354, pruned_loss=0.09573, over 1420084.99 frames.], batch size: 18, lr: 1.82e-03
2022-04-28 11:08:01,953 INFO [train.py:763] (5/8) Epoch 2, batch 2750, loss[loss=0.305, simple_loss=0.3781, pruned_loss=0.1159, over 7227.00 frames.], tot_loss[loss=0.2626, simple_loss=0.335, pruned_loss=0.09514, over 1419491.09 frames.], batch size: 26, lr: 1.82e-03
2022-04-28 11:09:07,554 INFO [train.py:763] (5/8) Epoch 2, batch 2800, loss[loss=0.4051, simple_loss=0.4296, pruned_loss=0.1903, over 5120.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3353, pruned_loss=0.09544, over 1418565.77 frames.], batch size: 53, lr: 1.81e-03
2022-04-28 11:10:13,394 INFO [train.py:763] (5/8) Epoch 2, batch 2850, loss[loss=0.2884, simple_loss=0.3702, pruned_loss=0.1033, over 7214.00 frames.], tot_loss[loss=0.2621, simple_loss=0.3347, pruned_loss=0.09476, over 1422013.51 frames.], batch size: 21, lr: 1.81e-03
2022-04-28 11:11:19,194 INFO [train.py:763] (5/8) Epoch 2, batch 2900, loss[loss=0.292, simple_loss=0.3612, pruned_loss=0.1114, over 6521.00 frames.], tot_loss[loss=0.2617, simple_loss=0.3342, pruned_loss=0.09457, over 1418947.88 frames.], batch size: 37, lr: 1.81e-03
2022-04-28 11:12:24,873 INFO [train.py:763] (5/8) Epoch 2, batch 2950, loss[loss=0.2684, simple_loss=0.3363, pruned_loss=0.1003, over 7174.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3352, pruned_loss=0.0957, over 1417264.45 frames.], batch size: 26, lr: 1.80e-03
2022-04-28 11:13:30,381 INFO [train.py:763] (5/8) Epoch 2, batch 3000, loss[loss=0.2474, simple_loss=0.3238, pruned_loss=0.08546, over 7331.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3348, pruned_loss=0.09533, over 1420805.31 frames.], batch size: 22, lr: 1.80e-03
2022-04-28 11:13:30,382 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 11:13:45,774 INFO [train.py:792] (5/8) Epoch 2, validation: loss=0.2017, simple_loss=0.3052, pruned_loss=0.04915, over 698248.00 frames.
2022-04-28 11:14:51,529 INFO [train.py:763] (5/8) Epoch 2, batch 3050, loss[loss=0.2662, simple_loss=0.3426, pruned_loss=0.0949, over 7418.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3356, pruned_loss=0.09612, over 1425700.70 frames.], batch size: 21, lr: 1.80e-03
2022-04-28 11:15:57,119 INFO [train.py:763] (5/8) Epoch 2, batch 3100, loss[loss=0.2053, simple_loss=0.292, pruned_loss=0.05927, over 7291.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3354, pruned_loss=0.09566, over 1428968.95 frames.], batch size: 18, lr: 1.79e-03
2022-04-28 11:17:02,759 INFO [train.py:763] (5/8) Epoch 2, batch 3150, loss[loss=0.272, simple_loss=0.3545, pruned_loss=0.0948, over 7219.00 frames.], tot_loss[loss=0.263, simple_loss=0.3349, pruned_loss=0.09555, over 1423871.94 frames.], batch size: 21, lr: 1.79e-03
2022-04-28 11:18:08,974 INFO [train.py:763] (5/8) Epoch 2, batch 3200, loss[loss=0.2762, simple_loss=0.3556, pruned_loss=0.09841, over 7390.00 frames.], tot_loss[loss=0.263, simple_loss=0.3355, pruned_loss=0.09521, over 1426391.56 frames.], batch size: 23, lr: 1.79e-03
2022-04-28 11:19:14,940 INFO [train.py:763] (5/8) Epoch 2, batch 3250, loss[loss=0.2738, simple_loss=0.3385, pruned_loss=0.1045, over 7158.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3356, pruned_loss=0.09495, over 1426637.33 frames.], batch size: 19, lr: 1.79e-03
2022-04-28 11:20:20,956 INFO [train.py:763] (5/8) Epoch 2, batch 3300, loss[loss=0.2452, simple_loss=0.3291, pruned_loss=0.08067, over 7209.00 frames.], tot_loss[loss=0.2612, simple_loss=0.3342, pruned_loss=0.09412, over 1428717.65 frames.], batch size: 26, lr: 1.78e-03
2022-04-28 11:21:25,813 INFO [train.py:763] (5/8) Epoch 2, batch 3350, loss[loss=0.2037, simple_loss=0.2939, pruned_loss=0.05675, over 7278.00 frames.], tot_loss[loss=0.2627, simple_loss=0.3354, pruned_loss=0.09503, over 1425547.93 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:22:30,855 INFO [train.py:763] (5/8) Epoch 2, batch 3400, loss[loss=0.2105, simple_loss=0.2833, pruned_loss=0.06886, over 7422.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3359, pruned_loss=0.09531, over 1423323.38 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:23:36,221 INFO [train.py:763] (5/8) Epoch 2, batch 3450, loss[loss=0.2517, simple_loss=0.3377, pruned_loss=0.08287, over 7265.00 frames.], tot_loss[loss=0.2638, simple_loss=0.336, pruned_loss=0.0958, over 1419631.83 frames.], batch size: 19, lr: 1.77e-03
2022-04-28 11:24:41,584 INFO [train.py:763] (5/8) Epoch 2, batch 3500, loss[loss=0.2641, simple_loss=0.3452, pruned_loss=0.09147, over 7317.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3348, pruned_loss=0.09547, over 1420959.03 frames.], batch size: 25, lr: 1.77e-03
2022-04-28 11:25:47,029 INFO [train.py:763] (5/8) Epoch 2, batch 3550, loss[loss=0.2568, simple_loss=0.3247, pruned_loss=0.09445, over 7208.00 frames.], tot_loss[loss=0.2643, simple_loss=0.3359, pruned_loss=0.09637, over 1419775.99 frames.], batch size: 21, lr: 1.77e-03
2022-04-28 11:26:52,373 INFO [train.py:763] (5/8) Epoch 2, batch 3600, loss[loss=0.2255, simple_loss=0.3135, pruned_loss=0.06871, over 7284.00 frames.], tot_loss[loss=0.2619, simple_loss=0.3336, pruned_loss=0.09511, over 1421002.07 frames.], batch size: 24, lr: 1.76e-03
2022-04-28 11:27:57,958 INFO [train.py:763] (5/8) Epoch 2, batch 3650, loss[loss=0.3159, simple_loss=0.3779, pruned_loss=0.1269, over 7383.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3329, pruned_loss=0.09439, over 1421412.17 frames.], batch size: 23, lr: 1.76e-03
2022-04-28 11:29:03,183 INFO [train.py:763] (5/8) Epoch 2, batch 3700, loss[loss=0.2321, simple_loss=0.3086, pruned_loss=0.07785, over 7418.00 frames.], tot_loss[loss=0.26, simple_loss=0.3325, pruned_loss=0.09372, over 1416586.27 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:30:08,703 INFO [train.py:763] (5/8) Epoch 2, batch 3750, loss[loss=0.2023, simple_loss=0.2784, pruned_loss=0.06314, over 7279.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3309, pruned_loss=0.09226, over 1422251.38 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:31:14,668 INFO [train.py:763] (5/8) Epoch 2, batch 3800, loss[loss=0.2014, simple_loss=0.2856, pruned_loss=0.05856, over 7168.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3311, pruned_loss=0.0926, over 1423268.09 frames.], batch size: 18, lr: 1.75e-03
2022-04-28 11:32:20,651 INFO [train.py:763] (5/8) Epoch 2, batch 3850, loss[loss=0.2748, simple_loss=0.3652, pruned_loss=0.09217, over 7336.00 frames.], tot_loss[loss=0.2599, simple_loss=0.332, pruned_loss=0.0939, over 1422166.25 frames.], batch size: 22, lr: 1.75e-03
2022-04-28 11:33:26,580 INFO [train.py:763] (5/8) Epoch 2, batch 3900, loss[loss=0.2767, simple_loss=0.338, pruned_loss=0.1077, over 7329.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3303, pruned_loss=0.09259, over 1423926.48 frames.], batch size: 20, lr: 1.75e-03
2022-04-28 11:34:31,998 INFO [train.py:763] (5/8) Epoch 2, batch 3950, loss[loss=0.2472, simple_loss=0.3323, pruned_loss=0.08106, over 7319.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3306, pruned_loss=0.09263, over 1421214.16 frames.], batch size: 21, lr: 1.74e-03
2022-04-28 11:35:37,644 INFO [train.py:763] (5/8) Epoch 2, batch 4000, loss[loss=0.2443, simple_loss=0.3259, pruned_loss=0.08137, over 7342.00 frames.], tot_loss[loss=0.2575, simple_loss=0.3308, pruned_loss=0.09211, over 1425845.56 frames.], batch size: 22, lr: 1.74e-03
2022-04-28 11:36:44,083 INFO [train.py:763] (5/8) Epoch 2, batch 4050, loss[loss=0.3101, simple_loss=0.3929, pruned_loss=0.1136, over 7428.00 frames.], tot_loss[loss=0.2569, simple_loss=0.3305, pruned_loss=0.09166, over 1425677.52 frames.], batch size: 20, lr: 1.74e-03
2022-04-28 11:37:49,246 INFO [train.py:763] (5/8) Epoch 2, batch 4100, loss[loss=0.227, simple_loss=0.3043, pruned_loss=0.07481, over 7054.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3314, pruned_loss=0.09233, over 1416209.24 frames.], batch size: 18, lr: 1.73e-03
2022-04-28 11:38:54,192 INFO [train.py:763] (5/8) Epoch 2, batch 4150, loss[loss=0.2478, simple_loss=0.3266, pruned_loss=0.08445, over 7112.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3315, pruned_loss=0.09204, over 1421482.15 frames.], batch size: 21, lr: 1.73e-03
2022-04-28 11:40:00,907 INFO [train.py:763] (5/8) Epoch 2, batch 4200, loss[loss=0.3004, simple_loss=0.3601, pruned_loss=0.1204, over 6975.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3314, pruned_loss=0.09188, over 1420801.99 frames.], batch size: 28, lr: 1.73e-03
2022-04-28 11:41:08,032 INFO [train.py:763] (5/8) Epoch 2, batch 4250, loss[loss=0.2387, simple_loss=0.3284, pruned_loss=0.07452, over 7197.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3299, pruned_loss=0.09058, over 1420857.91 frames.], batch size: 22, lr: 1.73e-03
2022-04-28 11:42:14,796 INFO [train.py:763] (5/8) Epoch 2, batch 4300, loss[loss=0.2258, simple_loss=0.3063, pruned_loss=0.07264, over 7437.00 frames.], tot_loss[loss=0.2558, simple_loss=0.3304, pruned_loss=0.09058, over 1423557.80 frames.], batch size: 19, lr: 1.72e-03
2022-04-28 11:43:21,904 INFO [train.py:763] (5/8) Epoch 2, batch 4350, loss[loss=0.2578, simple_loss=0.3465, pruned_loss=0.0846, over 7141.00 frames.], tot_loss[loss=0.2559, simple_loss=0.3307, pruned_loss=0.09062, over 1425112.80 frames.], batch size: 20, lr: 1.72e-03
2022-04-28 11:44:27,748 INFO [train.py:763] (5/8) Epoch 2, batch 4400, loss[loss=0.2467, simple_loss=0.3302, pruned_loss=0.08163, over 7278.00 frames.], tot_loss[loss=0.2555, simple_loss=0.3299, pruned_loss=0.09052, over 1419927.09 frames.], batch size: 25, lr: 1.72e-03
2022-04-28 11:45:33,254 INFO [train.py:763] (5/8) Epoch 2, batch 4450, loss[loss=0.2558, simple_loss=0.3434, pruned_loss=0.08403, over 7335.00 frames.], tot_loss[loss=0.2571, simple_loss=0.3315, pruned_loss=0.09138, over 1411939.76 frames.], batch size: 22, lr: 1.71e-03
2022-04-28 11:46:38,407 INFO [train.py:763] (5/8) Epoch 2, batch 4500, loss[loss=0.2356, simple_loss=0.3192, pruned_loss=0.07605, over 7132.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3334, pruned_loss=0.0926, over 1405192.60 frames.], batch size: 21, lr: 1.71e-03
2022-04-28 11:47:42,637 INFO [train.py:763] (5/8) Epoch 2, batch 4550, loss[loss=0.2556, simple_loss=0.3305, pruned_loss=0.09031, over 6499.00 frames.], tot_loss[loss=0.2618, simple_loss=0.3355, pruned_loss=0.09405, over 1378616.61 frames.], batch size: 38, lr: 1.71e-03
2022-04-28 11:49:10,867 INFO [train.py:763] (5/8) Epoch 3, batch 0, loss[loss=0.2628, simple_loss=0.3483, pruned_loss=0.08863, over 7188.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3483, pruned_loss=0.08863, over 7188.00 frames.], batch size: 23, lr: 1.66e-03
2022-04-28 11:50:17,408 INFO [train.py:763] (5/8) Epoch 3, batch 50, loss[loss=0.2206, simple_loss=0.2929, pruned_loss=0.07418, over 7282.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3269, pruned_loss=0.08913, over 317629.10 frames.], batch size: 17, lr: 1.66e-03
2022-04-28 11:51:23,925 INFO [train.py:763] (5/8) Epoch 3, batch 100, loss[loss=0.2111, simple_loss=0.2841, pruned_loss=0.06903, over 7288.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3249, pruned_loss=0.0874, over 564299.49 frames.], batch size: 17, lr: 1.65e-03
2022-04-28 11:52:29,499 INFO [train.py:763] (5/8) Epoch 3, batch 150, loss[loss=0.247, simple_loss=0.3358, pruned_loss=0.07914, over 7343.00 frames.], tot_loss[loss=0.2481, simple_loss=0.325, pruned_loss=0.08554, over 755309.63 frames.], batch size: 22, lr: 1.65e-03
2022-04-28 11:53:34,978 INFO [train.py:763] (5/8) Epoch 3, batch 200, loss[loss=0.2386, simple_loss=0.3199, pruned_loss=0.07864, over 7206.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3266, pruned_loss=0.08647, over 904354.38 frames.], batch size: 23, lr: 1.65e-03
2022-04-28 11:54:40,986 INFO [train.py:763] (5/8) Epoch 3, batch 250, loss[loss=0.2684, simple_loss=0.352, pruned_loss=0.0924, over 7323.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3285, pruned_loss=0.0874, over 1016178.86 frames.], batch size: 22, lr: 1.64e-03
2022-04-28 11:55:46,616 INFO [train.py:763] (5/8) Epoch 3, batch 300, loss[loss=0.252, simple_loss=0.3393, pruned_loss=0.08236, over 7382.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3278, pruned_loss=0.08697, over 1110523.92 frames.], batch size: 23, lr: 1.64e-03
2022-04-28 11:56:52,031 INFO [train.py:763] (5/8) Epoch 3, batch 350, loss[loss=0.2468, simple_loss=0.3395, pruned_loss=0.07709, over 7320.00 frames.], tot_loss[loss=0.2524, simple_loss=0.3291, pruned_loss=0.08781, over 1182166.58 frames.], batch size: 21, lr: 1.64e-03
2022-04-28 11:57:57,849 INFO [train.py:763] (5/8) Epoch 3, batch 400, loss[loss=0.2715, simple_loss=0.3472, pruned_loss=0.09793, over 7237.00 frames.], tot_loss[loss=0.252, simple_loss=0.3284, pruned_loss=0.08778, over 1232260.52 frames.], batch size: 20, lr: 1.64e-03
2022-04-28 11:59:03,274 INFO [train.py:763] (5/8) Epoch 3, batch 450, loss[loss=0.2751, simple_loss=0.3482, pruned_loss=0.101, over 7148.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3273, pruned_loss=0.08759, over 1273822.63 frames.], batch size: 20, lr: 1.63e-03
2022-04-28 12:00:09,029 INFO [train.py:763] (5/8) Epoch 3, batch 500, loss[loss=0.215, simple_loss=0.3036, pruned_loss=0.06325, over 7170.00 frames.], tot_loss[loss=0.253, simple_loss=0.3291, pruned_loss=0.08848, over 1304250.13 frames.], batch size: 19, lr: 1.63e-03
2022-04-28 12:01:14,930 INFO [train.py:763] (5/8) Epoch 3, batch 550, loss[loss=0.1899, simple_loss=0.2784, pruned_loss=0.05073, over 7157.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3289, pruned_loss=0.08821, over 1330040.93 frames.], batch size: 18, lr: 1.63e-03
2022-04-28 12:02:20,885 INFO [train.py:763] (5/8) Epoch 3, batch 600, loss[loss=0.2758, simple_loss=0.3494, pruned_loss=0.1011, over 6435.00 frames.], tot_loss[loss=0.2521, simple_loss=0.3282, pruned_loss=0.08796, over 1347668.01 frames.], batch size: 38, lr: 1.63e-03
2022-04-28 12:03:27,827 INFO [train.py:763] (5/8) Epoch 3, batch 650, loss[loss=0.2058, simple_loss=0.2979, pruned_loss=0.05684, over 7421.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3272, pruned_loss=0.08695, over 1368630.43 frames.], batch size: 20, lr: 1.62e-03
2022-04-28 12:04:35,159 INFO [train.py:763] (5/8) Epoch 3, batch 700, loss[loss=0.2841, simple_loss=0.3632, pruned_loss=0.1025, over 7305.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3264, pruned_loss=0.08652, over 1385533.94 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:05:41,313 INFO [train.py:763] (5/8) Epoch 3, batch 750, loss[loss=0.2811, simple_loss=0.3601, pruned_loss=0.1011, over 7301.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3265, pruned_loss=0.08716, over 1393623.13 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:06:46,996 INFO [train.py:763] (5/8) Epoch 3, batch 800, loss[loss=0.2202, simple_loss=0.2966, pruned_loss=0.07185, over 7258.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3269, pruned_loss=0.0872, over 1397495.87 frames.], batch size: 19, lr: 1.62e-03
2022-04-28 12:07:53,463 INFO [train.py:763] (5/8) Epoch 3, batch 850, loss[loss=0.2518, simple_loss=0.3256, pruned_loss=0.08895, over 7050.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3279, pruned_loss=0.08741, over 1407491.52 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:09:00,231 INFO [train.py:763] (5/8) Epoch 3, batch 900, loss[loss=0.2522, simple_loss=0.3368, pruned_loss=0.0838, over 7109.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3271, pruned_loss=0.08668, over 1415166.60 frames.], batch size: 21, lr: 1.61e-03
2022-04-28 12:10:06,508 INFO [train.py:763] (5/8) Epoch 3, batch 950, loss[loss=0.2977, simple_loss=0.3724, pruned_loss=0.1116, over 7177.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3274, pruned_loss=0.08706, over 1420234.62 frames.], batch size: 26, lr: 1.61e-03
2022-04-28 12:11:12,751 INFO [train.py:763] (5/8) Epoch 3, batch 1000, loss[loss=0.2163, simple_loss=0.2878, pruned_loss=0.07236, over 7276.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3269, pruned_loss=0.08693, over 1420513.66 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:12:18,776 INFO [train.py:763] (5/8) Epoch 3, batch 1050, loss[loss=0.3198, simple_loss=0.3803, pruned_loss=0.1296, over 6669.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3277, pruned_loss=0.08692, over 1418597.04 frames.], batch size: 31, lr: 1.60e-03
2022-04-28 12:13:24,401 INFO [train.py:763] (5/8) Epoch 3, batch 1100, loss[loss=0.2548, simple_loss=0.3399, pruned_loss=0.08481, over 7414.00 frames.], tot_loss[loss=0.251, simple_loss=0.3273, pruned_loss=0.08737, over 1419837.77 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:14:28,841 INFO [train.py:763] (5/8) Epoch 3, batch 1150, loss[loss=0.2685, simple_loss=0.3593, pruned_loss=0.08883, over 7321.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3281, pruned_loss=0.08763, over 1417558.12 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:15:35,091 INFO [train.py:763] (5/8) Epoch 3, batch 1200, loss[loss=0.266, simple_loss=0.3368, pruned_loss=0.09764, over 7313.00 frames.], tot_loss[loss=0.2525, simple_loss=0.3291, pruned_loss=0.08794, over 1415972.26 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:16:40,634 INFO [train.py:763] (5/8) Epoch 3, batch 1250, loss[loss=0.2428, simple_loss=0.3075, pruned_loss=0.08904, over 6782.00 frames.], tot_loss[loss=0.2512, simple_loss=0.328, pruned_loss=0.08718, over 1414236.93 frames.], batch size: 15, lr: 1.59e-03
2022-04-28 12:17:46,149 INFO [train.py:763] (5/8) Epoch 3, batch 1300, loss[loss=0.2749, simple_loss=0.3502, pruned_loss=0.0998, over 7222.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3272, pruned_loss=0.08664, over 1417013.77 frames.], batch size: 23, lr: 1.59e-03
2022-04-28 12:18:51,894 INFO [train.py:763] (5/8) Epoch 3, batch 1350, loss[loss=0.2519, simple_loss=0.3319, pruned_loss=0.08593, over 7240.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3273, pruned_loss=0.08717, over 1416191.13 frames.], batch size: 20, lr: 1.59e-03
2022-04-28 12:19:57,905 INFO [train.py:763] (5/8) Epoch 3, batch 1400, loss[loss=0.2707, simple_loss=0.3606, pruned_loss=0.09038, over 7212.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3266, pruned_loss=0.08691, over 1419066.02 frames.], batch size: 22, lr: 1.59e-03
2022-04-28 12:21:03,061 INFO [train.py:763] (5/8) Epoch 3, batch 1450, loss[loss=0.294, simple_loss=0.3748, pruned_loss=0.1066, over 7282.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3279, pruned_loss=0.08743, over 1421356.33 frames.], batch size: 24, lr: 1.59e-03
2022-04-28 12:22:08,506 INFO [train.py:763] (5/8) Epoch 3, batch 1500, loss[loss=0.2907, simple_loss=0.3665, pruned_loss=0.1074, over 7279.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3274, pruned_loss=0.08674, over 1418566.64 frames.], batch size: 24, lr: 1.58e-03
2022-04-28 12:23:14,003 INFO [train.py:763] (5/8) Epoch 3, batch 1550, loss[loss=0.3563, simple_loss=0.3952, pruned_loss=0.1587, over 5179.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3276, pruned_loss=0.08663, over 1418310.91 frames.], batch size: 53, lr: 1.58e-03
2022-04-28 12:24:20,152 INFO [train.py:763] (5/8) Epoch 3, batch 1600, loss[loss=0.2665, simple_loss=0.3514, pruned_loss=0.09084, over 7292.00 frames.], tot_loss[loss=0.253, simple_loss=0.3298, pruned_loss=0.08813, over 1415225.14 frames.], batch size: 25, lr: 1.58e-03
2022-04-28 12:25:26,872 INFO [train.py:763] (5/8) Epoch 3, batch 1650, loss[loss=0.238, simple_loss=0.3266, pruned_loss=0.07472, over 7323.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3281, pruned_loss=0.08735, over 1416912.29 frames.], batch size: 20, lr: 1.58e-03
2022-04-28 12:26:34,042 INFO [train.py:763] (5/8) Epoch 3, batch 1700, loss[loss=0.2766, simple_loss=0.3361, pruned_loss=0.1086, over 7138.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3278, pruned_loss=0.08666, over 1420158.45 frames.], batch size: 20, lr: 1.57e-03
2022-04-28 12:27:40,154 INFO [train.py:763] (5/8) Epoch 3, batch 1750, loss[loss=0.2415, simple_loss=0.3217, pruned_loss=0.08062, over 7209.00 frames.], tot_loss[loss=0.251, simple_loss=0.3279, pruned_loss=0.08702, over 1419481.92 frames.], batch size: 22, lr: 1.57e-03
2022-04-28 12:28:45,191 INFO [train.py:763] (5/8) Epoch 3, batch 1800, loss[loss=0.3163, simple_loss=0.3838, pruned_loss=0.1244, over 7223.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3292, pruned_loss=0.08759, over 1421691.36 frames.], batch size: 21, lr: 1.57e-03
2022-04-28 12:29:50,463 INFO [train.py:763] (5/8) Epoch 3, batch 1850, loss[loss=0.239, simple_loss=0.3038, pruned_loss=0.08709, over 7135.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3286, pruned_loss=0.08695, over 1420615.88 frames.], batch size: 17, lr: 1.57e-03
2022-04-28 12:30:57,299 INFO [train.py:763] (5/8) Epoch 3, batch 1900, loss[loss=0.2605, simple_loss=0.3255, pruned_loss=0.09772, over 7150.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3294, pruned_loss=0.0876, over 1423568.45 frames.], batch size: 19, lr: 1.56e-03
2022-04-28 12:32:03,223 INFO [train.py:763] (5/8) Epoch 3, batch 1950, loss[loss=0.2458, simple_loss=0.3323, pruned_loss=0.07962, over 6553.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3281, pruned_loss=0.08635, over 1428613.21 frames.], batch size: 38, lr: 1.56e-03
2022-04-28 12:33:17,828 INFO [train.py:763] (5/8) Epoch 3, batch 2000, loss[loss=0.2382, simple_loss=0.3237, pruned_loss=0.07634, over 7111.00 frames.], tot_loss[loss=0.2505, simple_loss=0.3284, pruned_loss=0.08627, over 1425933.43 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:35:10,050 INFO [train.py:763] (5/8) Epoch 3, batch 2050, loss[loss=0.269, simple_loss=0.346, pruned_loss=0.09599, over 6805.00 frames.], tot_loss[loss=0.251, simple_loss=0.3285, pruned_loss=0.08676, over 1422980.62 frames.], batch size: 31, lr: 1.56e-03
2022-04-28 12:36:15,502 INFO [train.py:763] (5/8) Epoch 3, batch 2100, loss[loss=0.2542, simple_loss=0.3344, pruned_loss=0.087, over 7317.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3269, pruned_loss=0.08596, over 1421240.84 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:37:29,644 INFO [train.py:763] (5/8) Epoch 3, batch 2150, loss[loss=0.2775, simple_loss=0.3484, pruned_loss=0.1033, over 7332.00 frames.], tot_loss[loss=0.249, simple_loss=0.3266, pruned_loss=0.08567, over 1423888.78 frames.], batch size: 22, lr: 1.55e-03
2022-04-28 12:38:44,723 INFO [train.py:763] (5/8) Epoch 3, batch 2200, loss[loss=0.2437, simple_loss=0.323, pruned_loss=0.08221, over 7221.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3253, pruned_loss=0.08516, over 1426162.84 frames.], batch size: 21, lr: 1.55e-03
2022-04-28 12:40:02,467 INFO [train.py:763] (5/8) Epoch 3, batch 2250, loss[loss=0.314, simple_loss=0.3602, pruned_loss=0.1339, over 5229.00 frames.], tot_loss[loss=0.2481, simple_loss=0.326, pruned_loss=0.08511, over 1427881.53 frames.], batch size: 52, lr: 1.55e-03
2022-04-28 12:41:07,756 INFO [train.py:763] (5/8) Epoch 3, batch 2300, loss[loss=0.2404, simple_loss=0.3275, pruned_loss=0.07665, over 7144.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3263, pruned_loss=0.08506, over 1430364.80 frames.], batch size: 19, lr: 1.55e-03
2022-04-28 12:42:14,645 INFO [train.py:763] (5/8) Epoch 3, batch 2350, loss[loss=0.2466, simple_loss=0.3292, pruned_loss=0.08203, over 7328.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3251, pruned_loss=0.08415, over 1431082.12 frames.], batch size: 20, lr: 1.54e-03
2022-04-28 12:43:19,983 INFO [train.py:763] (5/8) Epoch 3, batch 2400, loss[loss=0.2527, simple_loss=0.3327, pruned_loss=0.08641, over 7287.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3249, pruned_loss=0.08275, over 1433379.41 frames.], batch size: 25, lr: 1.54e-03
2022-04-28 12:44:25,918 INFO [train.py:763] (5/8) Epoch 3, batch 2450, loss[loss=0.2845, simple_loss=0.3513, pruned_loss=0.1089, over 7360.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3253, pruned_loss=0.08362, over 1436533.08 frames.], batch size: 23, lr: 1.54e-03
2022-04-28 12:45:31,564 INFO [train.py:763] (5/8) Epoch 3, batch 2500, loss[loss=0.2401, simple_loss=0.3175, pruned_loss=0.08136, over 7152.00 frames.], tot_loss[loss=0.246, simple_loss=0.3247, pruned_loss=0.08361, over 1434352.46 frames.], batch size: 19, lr: 1.54e-03
2022-04-28 12:46:36,897 INFO [train.py:763] (5/8) Epoch 3, batch 2550, loss[loss=0.218, simple_loss=0.2905, pruned_loss=0.07275, over 7405.00 frames.], tot_loss[loss=0.2468, simple_loss=0.325, pruned_loss=0.08428, over 1425864.23 frames.], batch size: 18, lr: 1.54e-03
2022-04-28 12:47:42,412 INFO [train.py:763] (5/8) Epoch 3, batch 2600, loss[loss=0.27, simple_loss=0.3522, pruned_loss=0.0939, over 7226.00 frames.], tot_loss[loss=0.2493, simple_loss=0.3271, pruned_loss=0.08573, over 1425462.49 frames.], batch size: 20, lr: 1.53e-03
2022-04-28 12:48:47,825 INFO [train.py:763] (5/8) Epoch 3, batch 2650, loss[loss=0.1711, simple_loss=0.2572, pruned_loss=0.04256, over 6988.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3277, pruned_loss=0.08568, over 1418954.97 frames.], batch size: 16, lr: 1.53e-03
2022-04-28 12:49:52,905 INFO [train.py:763] (5/8) Epoch 3, batch 2700, loss[loss=0.2167, simple_loss=0.284, pruned_loss=0.0747, over 6775.00 frames.], tot_loss[loss=0.2482, simple_loss=0.3268, pruned_loss=0.08483, over 1417637.32 frames.], batch size: 15, lr: 1.53e-03
2022-04-28 12:50:58,283 INFO [train.py:763] (5/8) Epoch 3, batch 2750, loss[loss=0.3133, simple_loss=0.3689, pruned_loss=0.1289, over 7260.00 frames.], tot_loss[loss=0.2477, simple_loss=0.3269, pruned_loss=0.08424, over 1421323.14 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:52:03,630 INFO [train.py:763] (5/8) Epoch 3, batch 2800, loss[loss=0.2828, simple_loss=0.3506, pruned_loss=0.1076, over 7165.00 frames.], tot_loss[loss=0.2467, simple_loss=0.326, pruned_loss=0.08365, over 1423613.46 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:53:09,255 INFO [train.py:763] (5/8) Epoch 3, batch 2850, loss[loss=0.3013, simple_loss=0.3637, pruned_loss=0.1195, over 5174.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3249, pruned_loss=0.08275, over 1422781.38 frames.], batch size: 52, lr: 1.52e-03
2022-04-28 12:54:14,539 INFO [train.py:763] (5/8) Epoch 3, batch 2900, loss[loss=0.2621, simple_loss=0.3377, pruned_loss=0.09324, over 6708.00 frames.], tot_loss[loss=0.245, simple_loss=0.3246, pruned_loss=0.08275, over 1423271.08 frames.], batch size: 31, lr: 1.52e-03
2022-04-28 12:55:20,291 INFO [train.py:763] (5/8) Epoch 3, batch 2950, loss[loss=0.2921, simple_loss=0.3594, pruned_loss=0.1124, over 7050.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3235, pruned_loss=0.0826, over 1427345.10 frames.], batch size: 28, lr: 1.52e-03
2022-04-28 12:56:25,614 INFO [train.py:763] (5/8) Epoch 3, batch 3000, loss[loss=0.2461, simple_loss=0.328, pruned_loss=0.08212, over 7155.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3242, pruned_loss=0.08309, over 1425369.11 frames.], batch size: 20, lr: 1.52e-03
2022-04-28 12:56:25,615 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 12:56:40,878 INFO [train.py:792] (5/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
2022-04-28 12:57:46,584 INFO [train.py:763] (5/8) Epoch 3, batch 3050, loss[loss=0.2561, simple_loss=0.3377, pruned_loss=0.08728, over 7113.00 frames.], tot_loss[loss=0.2464, simple_loss=0.3248, pruned_loss=0.08403, over 1419857.42 frames.], batch size: 21, lr: 1.51e-03
2022-04-28 12:58:52,516 INFO [train.py:763] (5/8) Epoch 3, batch 3100, loss[loss=0.2558, simple_loss=0.3349, pruned_loss=0.08837, over 7272.00 frames.], tot_loss[loss=0.2462, simple_loss=0.3241, pruned_loss=0.08414, over 1416259.11 frames.], batch size: 24, lr: 1.51e-03
2022-04-28 12:59:58,119 INFO [train.py:763] (5/8) Epoch 3, batch 3150, loss[loss=0.2809, simple_loss=0.3528, pruned_loss=0.1045, over 7313.00 frames.], tot_loss[loss=0.2444, simple_loss=0.3226, pruned_loss=0.08308, over 1421017.07 frames.], batch size: 25, lr: 1.51e-03
2022-04-28 13:01:03,466 INFO [train.py:763] (5/8) Epoch 3, batch 3200, loss[loss=0.2398, simple_loss=0.3269, pruned_loss=0.07634, over 7075.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3213, pruned_loss=0.08226, over 1422223.17 frames.], batch size: 18, lr: 1.51e-03
2022-04-28 13:02:09,498 INFO [train.py:763] (5/8) Epoch 3, batch 3250, loss[loss=0.2447, simple_loss=0.3215, pruned_loss=0.08392, over 7251.00 frames.], tot_loss[loss=0.245, simple_loss=0.3228, pruned_loss=0.08361, over 1423886.22 frames.], batch size: 19, lr: 1.51e-03
2022-04-28 13:03:16,273 INFO [train.py:763] (5/8) Epoch 3, batch 3300, loss[loss=0.2851, simple_loss=0.347, pruned_loss=0.1115, over 7209.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3238, pruned_loss=0.08371, over 1422573.73 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:04:22,930 INFO [train.py:763] (5/8) Epoch 3, batch 3350, loss[loss=0.2633, simple_loss=0.3335, pruned_loss=0.09658, over 6201.00 frames.], tot_loss[loss=0.2446, simple_loss=0.3227, pruned_loss=0.08325, over 1419863.92 frames.], batch size: 37, lr: 1.50e-03
2022-04-28 13:05:28,645 INFO [train.py:763] (5/8) Epoch 3, batch 3400, loss[loss=0.2147, simple_loss=0.2847, pruned_loss=0.07233, over 7005.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3229, pruned_loss=0.0835, over 1420893.33 frames.], batch size: 16, lr: 1.50e-03
2022-04-28 13:06:35,049 INFO [train.py:763] (5/8) Epoch 3, batch 3450, loss[loss=0.1856, simple_loss=0.2651, pruned_loss=0.05306, over 7167.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3208, pruned_loss=0.08239, over 1426111.60 frames.], batch size: 18, lr: 1.50e-03
2022-04-28 13:07:42,234 INFO [train.py:763] (5/8) Epoch 3, batch 3500, loss[loss=0.2889, simple_loss=0.3578, pruned_loss=0.11, over 7392.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3207, pruned_loss=0.08246, over 1428117.08 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:08:48,567 INFO [train.py:763] (5/8) Epoch 3, batch 3550, loss[loss=0.2458, simple_loss=0.3303, pruned_loss=0.08061, over 7280.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3202, pruned_loss=0.08199, over 1429099.44 frames.], batch size: 24, lr: 1.49e-03
2022-04-28 13:09:55,568 INFO [train.py:763] (5/8) Epoch 3, batch 3600, loss[loss=0.2122, simple_loss=0.2946, pruned_loss=0.06486, over 7002.00 frames.], tot_loss[loss=0.2432, simple_loss=0.321, pruned_loss=0.08272, over 1427442.09 frames.], batch size: 16, lr: 1.49e-03
2022-04-28 13:11:02,053 INFO [train.py:763] (5/8) Epoch 3, batch 3650, loss[loss=0.2239, simple_loss=0.2988, pruned_loss=0.07451, over 7132.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3212, pruned_loss=0.08246, over 1428411.34 frames.], batch size: 17, lr: 1.49e-03
2022-04-28 13:12:07,946 INFO [train.py:763] (5/8) Epoch 3, batch 3700, loss[loss=0.1999, simple_loss=0.2667, pruned_loss=0.0666, over 6987.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3209, pruned_loss=0.082, over 1427053.87 frames.], batch size: 16, lr: 1.49e-03
2022-04-28 13:13:15,401 INFO [train.py:763] (5/8) Epoch 3, batch 3750, loss[loss=0.2602, simple_loss=0.3369, pruned_loss=0.09179, over 7425.00 frames.], tot_loss[loss=0.2412, simple_loss=0.3198, pruned_loss=0.08124, over 1424522.41 frames.], batch size: 20, lr: 1.49e-03
2022-04-28 13:14:22,399 INFO [train.py:763] (5/8) Epoch 3, batch 3800, loss[loss=0.2249, simple_loss=0.3091, pruned_loss=0.0703, over 7059.00 frames.], tot_loss[loss=0.242, simple_loss=0.3207, pruned_loss=0.08161, over 1421068.26 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:15:29,716 INFO [train.py:763] (5/8) Epoch 3, batch 3850, loss[loss=0.2209, simple_loss=0.3, pruned_loss=0.07089, over 7424.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3205, pruned_loss=0.08161, over 1425006.08 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:16:35,241 INFO [train.py:763] (5/8) Epoch 3, batch 3900, loss[loss=0.2727, simple_loss=0.3498, pruned_loss=0.09783, over 5201.00 frames.], tot_loss[loss=0.2405, simple_loss=0.3198, pruned_loss=0.08056, over 1426986.88 frames.], batch size: 52, lr: 1.48e-03
2022-04-28 13:17:41,255 INFO [train.py:763] (5/8) Epoch 3, batch 3950, loss[loss=0.1973, simple_loss=0.2728, pruned_loss=0.0609, over 7216.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3198, pruned_loss=0.08041, over 1425351.74 frames.], batch size: 16, lr: 1.48e-03
2022-04-28 13:18:46,789 INFO [train.py:763] (5/8) Epoch 3, batch 4000, loss[loss=0.29, simple_loss=0.3658, pruned_loss=0.1071, over 7210.00 frames.], tot_loss[loss=0.2409, simple_loss=0.32, pruned_loss=0.08087, over 1417835.57 frames.], batch size: 21, lr: 1.48e-03
2022-04-28 13:19:52,134 INFO [train.py:763] (5/8) Epoch 3, batch 4050, loss[loss=0.2473, simple_loss=0.3248, pruned_loss=0.08487, over 7407.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3211, pruned_loss=0.08177, over 1419637.71 frames.], batch size: 21, lr: 1.47e-03
2022-04-28 13:20:58,246 INFO [train.py:763] (5/8) Epoch 3, batch 4100, loss[loss=0.2629, simple_loss=0.3397, pruned_loss=0.09307, over 6458.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3212, pruned_loss=0.08197, over 1422029.28 frames.], batch size: 38, lr: 1.47e-03
2022-04-28 13:22:04,112 INFO [train.py:763] (5/8) Epoch 3, batch 4150, loss[loss=0.2302, simple_loss=0.2992, pruned_loss=0.08054, over 7004.00 frames.], tot_loss[loss=0.2416, simple_loss=0.3205, pruned_loss=0.08132, over 1424454.55 frames.], batch size: 16, lr: 1.47e-03
2022-04-28 13:23:11,086 INFO [train.py:763] (5/8) Epoch 3, batch 4200, loss[loss=0.2292, simple_loss=0.3143, pruned_loss=0.07206, over 7150.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3201, pruned_loss=0.08103, over 1422560.69 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:24:18,326 INFO [train.py:763] (5/8) Epoch 3, batch 4250, loss[loss=0.1983, simple_loss=0.2785, pruned_loss=0.05908, over 7363.00 frames.], tot_loss[loss=0.2409, simple_loss=0.3193, pruned_loss=0.0812, over 1413808.85 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:25:24,095 INFO [train.py:763] (5/8) Epoch 3, batch 4300, loss[loss=0.2197, simple_loss=0.3043, pruned_loss=0.06755, over 7359.00 frames.], tot_loss[loss=0.2395, simple_loss=0.3176, pruned_loss=0.08071, over 1412239.91 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:26:29,899 INFO [train.py:763] (5/8) Epoch 3, batch 4350, loss[loss=0.262, simple_loss=0.3411, pruned_loss=0.09148, over 6603.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3159, pruned_loss=0.08064, over 1410399.06 frames.], batch size: 38, lr: 1.46e-03
2022-04-28 13:27:35,686 INFO [train.py:763] (5/8) Epoch 3, batch 4400, loss[loss=0.2183, simple_loss=0.2954, pruned_loss=0.07059, over 7058.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3153, pruned_loss=0.08043, over 1409983.55 frames.], batch size: 18, lr: 1.46e-03
2022-04-28 13:28:41,566 INFO [train.py:763] (5/8) Epoch 3, batch 4450, loss[loss=0.2382, simple_loss=0.3264, pruned_loss=0.07497, over 7376.00 frames.], tot_loss[loss=0.239, simple_loss=0.3162, pruned_loss=0.08086, over 1400731.83 frames.], batch size: 23, lr: 1.46e-03
2022-04-28 13:29:46,953 INFO [train.py:763] (5/8) Epoch 3, batch 4500, loss[loss=0.2585, simple_loss=0.3417, pruned_loss=0.08766, over 6492.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3168, pruned_loss=0.08094, over 1396426.83 frames.], batch size: 38, lr: 1.46e-03
2022-04-28 13:30:51,043 INFO [train.py:763] (5/8) Epoch 3, batch 4550, loss[loss=0.2882, simple_loss=0.3512, pruned_loss=0.1126, over 5338.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3208, pruned_loss=0.08357, over 1363078.50 frames.], batch size: 53, lr: 1.46e-03
2022-04-28 13:32:20,228 INFO [train.py:763] (5/8) Epoch 4, batch 0, loss[loss=0.2587, simple_loss=0.3509, pruned_loss=0.08325, over 7212.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3509, pruned_loss=0.08325, over 7212.00 frames.], batch size: 23, lr: 1.40e-03
2022-04-28 13:33:26,506 INFO [train.py:763] (5/8) Epoch 4, batch 50, loss[loss=0.2469, simple_loss=0.333, pruned_loss=0.0804, over 7341.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3199, pruned_loss=0.0802, over 320885.32 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:34:31,943 INFO [train.py:763] (5/8) Epoch 4, batch 100, loss[loss=0.2356, simple_loss=0.3243, pruned_loss=0.07347, over 7334.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3195, pruned_loss=0.07887, over 566740.25 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:35:37,389 INFO [train.py:763] (5/8) Epoch 4, batch 150, loss[loss=0.2894, simple_loss=0.3552, pruned_loss=0.1117, over 5186.00 frames.], tot_loss[loss=0.24, simple_loss=0.321, pruned_loss=0.07948, over 756319.69 frames.], batch size: 52, lr: 1.40e-03
2022-04-28 13:36:43,016 INFO [train.py:763] (5/8) Epoch 4, batch 200, loss[loss=0.2138, simple_loss=0.3023, pruned_loss=0.06263, over 7167.00 frames.], tot_loss[loss=0.2421, simple_loss=0.3231, pruned_loss=0.08054, over 904209.76 frames.], batch size: 19, lr: 1.40e-03
2022-04-28 13:37:48,982 INFO [train.py:763] (5/8) Epoch 4, batch 250, loss[loss=0.308, simple_loss=0.3872, pruned_loss=0.1144, over 7352.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3246, pruned_loss=0.08084, over 1021580.19 frames.], batch size: 22, lr: 1.39e-03
2022-04-28 13:38:55,699 INFO [train.py:763] (5/8) Epoch 4, batch 300, loss[loss=0.1935, simple_loss=0.2754, pruned_loss=0.05583, over 7285.00 frames.], tot_loss[loss=0.2402, simple_loss=0.322, pruned_loss=0.07922, over 1114136.69 frames.], batch size: 17, lr: 1.39e-03
2022-04-28 13:40:02,835 INFO [train.py:763] (5/8) Epoch 4, batch 350, loss[loss=0.2259, simple_loss=0.3115, pruned_loss=0.07019, over 7160.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3204, pruned_loss=0.07904, over 1182262.25 frames.], batch size: 19, lr: 1.39e-03
2022-04-28 13:41:09,523 INFO [train.py:763] (5/8) Epoch 4, batch 400, loss[loss=0.2362, simple_loss=0.3106, pruned_loss=0.08095, over 7100.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3195, pruned_loss=0.0789, over 1232794.85 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:42:15,469 INFO [train.py:763] (5/8) Epoch 4, batch 450, loss[loss=0.2578, simple_loss=0.3338, pruned_loss=0.09094, over 7094.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3186, pruned_loss=0.07827, over 1274330.45 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:43:21,275 INFO [train.py:763] (5/8) Epoch 4, batch 500, loss[loss=0.2241, simple_loss=0.3145, pruned_loss=0.06691, over 7307.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3173, pruned_loss=0.0772, over 1308469.67 frames.], batch size: 21, lr: 1.39e-03
2022-04-28 13:44:28,343 INFO [train.py:763] (5/8) Epoch 4, batch 550, loss[loss=0.2461, simple_loss=0.3292, pruned_loss=0.08144, over 6777.00 frames.], tot_loss[loss=0.236, simple_loss=0.3175, pruned_loss=0.07725, over 1333235.97 frames.], batch size: 31, lr: 1.38e-03
2022-04-28 13:45:33,799 INFO [train.py:763] (5/8) Epoch 4, batch 600, loss[loss=0.2483, simple_loss=0.3166, pruned_loss=0.08994, over 7009.00 frames.], tot_loss[loss=0.2361, simple_loss=0.3174, pruned_loss=0.0774, over 1355441.91 frames.], batch size: 16, lr: 1.38e-03
2022-04-28 13:46:39,065 INFO [train.py:763] (5/8) Epoch 4, batch 650, loss[loss=0.2272, simple_loss=0.3125, pruned_loss=0.07094, over 7340.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3173, pruned_loss=0.07749, over 1370872.20 frames.], batch size: 20, lr: 1.38e-03
2022-04-28 13:47:44,008 INFO [train.py:763] (5/8) Epoch 4, batch 700, loss[loss=0.2644, simple_loss=0.3523, pruned_loss=0.08828, over 7314.00 frames.], tot_loss[loss=0.2377, simple_loss=0.3186, pruned_loss=0.07837, over 1380294.00 frames.], batch size: 25, lr: 1.38e-03
2022-04-28 13:48:49,488 INFO [train.py:763] (5/8) Epoch 4, batch 750, loss[loss=0.2123, simple_loss=0.2909, pruned_loss=0.06687, over 7070.00 frames.], tot_loss[loss=0.238, simple_loss=0.3182, pruned_loss=0.07887, over 1384643.88 frames.], batch size: 18, lr: 1.38e-03
2022-04-28 13:49:55,006 INFO [train.py:763] (5/8) Epoch 4, batch 800, loss[loss=0.2232, simple_loss=0.3, pruned_loss=0.07318, over 7444.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3158, pruned_loss=0.07764, over 1396780.92 frames.], batch size: 19, lr: 1.38e-03
2022-04-28 13:50:59,970 INFO [train.py:763] (5/8) Epoch 4, batch 850, loss[loss=0.2124, simple_loss=0.2943, pruned_loss=0.06532, over 7063.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3155, pruned_loss=0.07744, over 1395693.90 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:52:05,798 INFO [train.py:763] (5/8) Epoch 4, batch 900, loss[loss=0.2845, simple_loss=0.3489, pruned_loss=0.11, over 7316.00 frames.], tot_loss[loss=0.2353, simple_loss=0.3155, pruned_loss=0.07756, over 1403415.50 frames.], batch size: 21, lr: 1.37e-03
2022-04-28 13:53:12,235 INFO [train.py:763] (5/8) Epoch 4, batch 950, loss[loss=0.2134, simple_loss=0.3023, pruned_loss=0.06231, over 6975.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3157, pruned_loss=0.07781, over 1407888.98 frames.], batch size: 28, lr: 1.37e-03
2022-04-28 13:54:19,387 INFO [train.py:763] (5/8) Epoch 4, batch 1000, loss[loss=0.2336, simple_loss=0.3204, pruned_loss=0.07341, over 7082.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3147, pruned_loss=0.07719, over 1412039.75 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:55:24,911 INFO [train.py:763] (5/8) Epoch 4, batch 1050, loss[loss=0.2716, simple_loss=0.3575, pruned_loss=0.09285, over 7285.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3159, pruned_loss=0.07746, over 1417217.78 frames.], batch size: 24, lr: 1.37e-03
2022-04-28 13:56:29,984 INFO [train.py:763] (5/8) Epoch 4, batch 1100, loss[loss=0.2579, simple_loss=0.3337, pruned_loss=0.09107, over 6285.00 frames.], tot_loss[loss=0.2371, simple_loss=0.3176, pruned_loss=0.07834, over 1413190.70 frames.], batch size: 37, lr: 1.37e-03
2022-04-28 13:57:36,095 INFO [train.py:763] (5/8) Epoch 4, batch 1150, loss[loss=0.2924, simple_loss=0.3636, pruned_loss=0.1106, over 7427.00 frames.], tot_loss[loss=0.2372, simple_loss=0.318, pruned_loss=0.07814, over 1415700.45 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 13:58:41,147 INFO [train.py:763] (5/8) Epoch 4, batch 1200, loss[loss=0.2527, simple_loss=0.3332, pruned_loss=0.0861, over 6224.00 frames.], tot_loss[loss=0.2362, simple_loss=0.317, pruned_loss=0.07773, over 1417297.10 frames.], batch size: 37, lr: 1.36e-03
2022-04-28 13:59:46,362 INFO [train.py:763] (5/8) Epoch 4, batch 1250, loss[loss=0.2699, simple_loss=0.3371, pruned_loss=0.1014, over 7262.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3166, pruned_loss=0.07756, over 1412190.36 frames.], batch size: 19, lr: 1.36e-03
2022-04-28 14:00:51,533 INFO [train.py:763] (5/8) Epoch 4, batch 1300, loss[loss=0.2311, simple_loss=0.3172, pruned_loss=0.07246, over 7335.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3168, pruned_loss=0.07715, over 1415452.87 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:01:57,426 INFO [train.py:763] (5/8) Epoch 4, batch 1350, loss[loss=0.202, simple_loss=0.2886, pruned_loss=0.05767, over 7141.00 frames.], tot_loss[loss=0.2356, simple_loss=0.317, pruned_loss=0.07704, over 1422289.00 frames.], batch size: 17, lr: 1.36e-03
2022-04-28 14:03:02,793 INFO [train.py:763] (5/8) Epoch 4, batch 1400, loss[loss=0.1805, simple_loss=0.2763, pruned_loss=0.04236, over 7241.00 frames.], tot_loss[loss=0.238, simple_loss=0.3193, pruned_loss=0.07834, over 1419123.79 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:04:07,967 INFO [train.py:763] (5/8) Epoch 4, batch 1450, loss[loss=0.2199, simple_loss=0.2993, pruned_loss=0.07023, over 7001.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3195, pruned_loss=0.07835, over 1419703.47 frames.], batch size: 16, lr: 1.35e-03
2022-04-28 14:05:14,095 INFO [train.py:763] (5/8) Epoch 4, batch 1500, loss[loss=0.2018, simple_loss=0.2955, pruned_loss=0.05409, over 7315.00 frames.], tot_loss[loss=0.2368, simple_loss=0.3181, pruned_loss=0.07774, over 1422476.91 frames.], batch size: 20, lr: 1.35e-03
2022-04-28 14:06:19,710 INFO [train.py:763] (5/8) Epoch 4, batch 1550, loss[loss=0.2555, simple_loss=0.3404, pruned_loss=0.08525, over 7371.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3165, pruned_loss=0.07702, over 1424580.74 frames.], batch size: 23, lr: 1.35e-03
2022-04-28 14:07:24,982 INFO [train.py:763] (5/8) Epoch 4, batch 1600, loss[loss=0.2108, simple_loss=0.3051, pruned_loss=0.05829, over 7293.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3162, pruned_loss=0.07638, over 1424006.58 frames.], batch size: 25, lr: 1.35e-03
2022-04-28 14:08:30,212 INFO [train.py:763] (5/8) Epoch 4, batch 1650, loss[loss=0.2343, simple_loss=0.3305, pruned_loss=0.06907, over 7111.00 frames.], tot_loss[loss=0.2344, simple_loss=0.3164, pruned_loss=0.07619, over 1422185.81 frames.], batch size: 21, lr: 1.35e-03
2022-04-28 14:09:35,808 INFO [train.py:763] (5/8) Epoch 4, batch 1700, loss[loss=0.2028, simple_loss=0.2971, pruned_loss=0.05424, over 7336.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3154, pruned_loss=0.07567, over 1423956.10 frames.], batch size: 22, lr: 1.35e-03
2022-04-28 14:10:42,773 INFO [train.py:763] (5/8) Epoch 4, batch 1750, loss[loss=0.2328, simple_loss=0.3176, pruned_loss=0.07402, over 7287.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3153, pruned_loss=0.07578, over 1423494.54 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:11:49,096 INFO [train.py:763] (5/8) Epoch 4, batch 1800, loss[loss=0.2659, simple_loss=0.356, pruned_loss=0.08787, over 7326.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3157, pruned_loss=0.07593, over 1426186.79 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:12:54,653 INFO [train.py:763] (5/8) Epoch 4, batch 1850, loss[loss=0.2562, simple_loss=0.3438, pruned_loss=0.08425, over 6209.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3165, pruned_loss=0.07625, over 1426352.93 frames.], batch size: 37, lr: 1.34e-03
2022-04-28 14:13:59,954 INFO [train.py:763] (5/8) Epoch 4, batch 1900, loss[loss=0.2344, simple_loss=0.3317, pruned_loss=0.06859, over 7105.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3163, pruned_loss=0.0759, over 1427202.51 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:15:05,365 INFO [train.py:763] (5/8) Epoch 4, batch 1950, loss[loss=0.208, simple_loss=0.2843, pruned_loss=0.06581, over 7160.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3152, pruned_loss=0.07506, over 1427257.19 frames.], batch size: 18, lr: 1.34e-03
2022-04-28 14:16:10,986 INFO [train.py:763] (5/8) Epoch 4, batch 2000, loss[loss=0.2419, simple_loss=0.3284, pruned_loss=0.07771, over 7295.00 frames.], tot_loss[loss=0.2327, simple_loss=0.315, pruned_loss=0.07516, over 1424084.16 frames.], batch size: 25, lr: 1.34e-03
2022-04-28 14:17:16,778 INFO [train.py:763] (5/8) Epoch 4, batch 2050, loss[loss=0.2317, simple_loss=0.3152, pruned_loss=0.07408, over 7295.00 frames.], tot_loss[loss=0.2319, simple_loss=0.3142, pruned_loss=0.07478, over 1429134.23 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:18:22,262 INFO [train.py:763] (5/8) Epoch 4, batch 2100, loss[loss=0.2554, simple_loss=0.3261, pruned_loss=0.09236, over 7410.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3143, pruned_loss=0.07496, over 1432115.73 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:19:27,840 INFO [train.py:763] (5/8) Epoch 4, batch 2150, loss[loss=0.2322, simple_loss=0.3133, pruned_loss=0.07555, over 7064.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3159, pruned_loss=0.07551, over 1431014.71 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:20:34,215 INFO [train.py:763] (5/8) Epoch 4, batch 2200, loss[loss=0.2257, simple_loss=0.3206, pruned_loss=0.06536, over 7338.00 frames.], tot_loss[loss=0.2326, simple_loss=0.315, pruned_loss=0.07512, over 1433521.64 frames.], batch size: 22, lr: 1.33e-03
2022-04-28 14:21:39,768 INFO [train.py:763] (5/8) Epoch 4, batch 2250, loss[loss=0.2251, simple_loss=0.3157, pruned_loss=0.06724, over 7390.00 frames.], tot_loss[loss=0.233, simple_loss=0.315, pruned_loss=0.07548, over 1431421.71 frames.], batch size: 23, lr: 1.33e-03
2022-04-28 14:22:45,302 INFO [train.py:763] (5/8) Epoch 4, batch 2300, loss[loss=0.1993, simple_loss=0.2668, pruned_loss=0.06592, over 7258.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3149, pruned_loss=0.07593, over 1430302.81 frames.], batch size: 17, lr: 1.33e-03
2022-04-28 14:23:50,812 INFO [train.py:763] (5/8) Epoch 4, batch 2350, loss[loss=0.2132, simple_loss=0.2964, pruned_loss=0.06506, over 7399.00 frames.], tot_loss[loss=0.235, simple_loss=0.3165, pruned_loss=0.07669, over 1433371.19 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:24:56,461 INFO [train.py:763] (5/8) Epoch 4, batch 2400, loss[loss=0.2348, simple_loss=0.3239, pruned_loss=0.07283, over 7206.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3158, pruned_loss=0.07622, over 1434921.23 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:26:01,957 INFO [train.py:763] (5/8) Epoch 4, batch 2450, loss[loss=0.1805, simple_loss=0.2658, pruned_loss=0.04759, over 7283.00 frames.], tot_loss[loss=0.2358, simple_loss=0.317, pruned_loss=0.07732, over 1435292.02 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:27:09,072 INFO [train.py:763] (5/8) Epoch 4, batch 2500, loss[loss=0.2652, simple_loss=0.3512, pruned_loss=0.08957, over 7206.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3168, pruned_loss=0.07704, over 1433130.63 frames.], batch size: 22, lr: 1.32e-03
2022-04-28 14:28:15,005 INFO [train.py:763] (5/8) Epoch 4, batch 2550, loss[loss=0.2855, simple_loss=0.3703, pruned_loss=0.1003, over 7144.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3167, pruned_loss=0.07706, over 1433677.21 frames.], batch size: 20, lr: 1.32e-03
2022-04-28 14:29:20,321 INFO [train.py:763] (5/8) Epoch 4, batch 2600, loss[loss=0.2978, simple_loss=0.3737, pruned_loss=0.1109, over 7314.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3171, pruned_loss=0.07719, over 1431677.00 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:30:26,104 INFO [train.py:763] (5/8) Epoch 4, batch 2650, loss[loss=0.1946, simple_loss=0.2828, pruned_loss=0.0532, over 7003.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3164, pruned_loss=0.07635, over 1429762.62 frames.], batch size: 16, lr: 1.32e-03
2022-04-28 14:31:31,748 INFO [train.py:763] (5/8) Epoch 4, batch 2700, loss[loss=0.1946, simple_loss=0.2863, pruned_loss=0.05142, over 7287.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3154, pruned_loss=0.07543, over 1431672.28 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:32:38,283 INFO [train.py:763] (5/8) Epoch 4, batch 2750, loss[loss=0.231, simple_loss=0.3105, pruned_loss=0.07576, over 7358.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3146, pruned_loss=0.07538, over 1432263.03 frames.], batch size: 19, lr: 1.31e-03
2022-04-28 14:33:43,922 INFO [train.py:763] (5/8) Epoch 4, batch 2800, loss[loss=0.2066, simple_loss=0.2816, pruned_loss=0.06584, over 7124.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3139, pruned_loss=0.07516, over 1433239.29 frames.], batch size: 17, lr: 1.31e-03
2022-04-28 14:34:49,330 INFO [train.py:763] (5/8) Epoch 4, batch 2850, loss[loss=0.2516, simple_loss=0.3332, pruned_loss=0.08495, over 6809.00 frames.], tot_loss[loss=0.233, simple_loss=0.315, pruned_loss=0.07549, over 1430488.57 frames.], batch size: 31, lr: 1.31e-03
2022-04-28 14:35:55,990 INFO [train.py:763] (5/8) Epoch 4, batch 2900, loss[loss=0.2811, simple_loss=0.3573, pruned_loss=0.1025, over 7284.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3166, pruned_loss=0.07677, over 1428562.04 frames.], batch size: 24, lr: 1.31e-03
2022-04-28 14:37:01,949 INFO [train.py:763] (5/8) Epoch 4, batch 2950, loss[loss=0.2296, simple_loss=0.3225, pruned_loss=0.06834, over 7346.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3143, pruned_loss=0.07518, over 1428943.10 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:38:07,797 INFO [train.py:763] (5/8) Epoch 4, batch 3000, loss[loss=0.227, simple_loss=0.316, pruned_loss=0.06904, over 7171.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3144, pruned_loss=0.07531, over 1425418.94 frames.], batch size: 26, lr: 1.31e-03
2022-04-28 14:38:07,798 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 14:38:23,247 INFO [train.py:792] (5/8) Epoch 4, validation: loss=0.1809, simple_loss=0.2865, pruned_loss=0.03766, over 698248.00 frames.
2022-04-28 14:39:28,682 INFO [train.py:763] (5/8) Epoch 4, batch 3050, loss[loss=0.2343, simple_loss=0.3243, pruned_loss=0.07209, over 7191.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3152, pruned_loss=0.07569, over 1428788.99 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:40:34,118 INFO [train.py:763] (5/8) Epoch 4, batch 3100, loss[loss=0.2371, simple_loss=0.3254, pruned_loss=0.07435, over 7230.00 frames.], tot_loss[loss=0.2341, simple_loss=0.316, pruned_loss=0.07609, over 1427209.55 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:41:39,922 INFO [train.py:763] (5/8) Epoch 4, batch 3150, loss[loss=0.2207, simple_loss=0.307, pruned_loss=0.06717, over 7287.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3164, pruned_loss=0.07606, over 1427749.75 frames.], batch size: 25, lr: 1.30e-03
2022-04-28 14:42:46,517 INFO [train.py:763] (5/8) Epoch 4, batch 3200, loss[loss=0.232, simple_loss=0.3138, pruned_loss=0.07516, over 7355.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3159, pruned_loss=0.07568, over 1428998.24 frames.], batch size: 19, lr: 1.30e-03
2022-04-28 14:43:52,381 INFO [train.py:763] (5/8) Epoch 4, batch 3250, loss[loss=0.2326, simple_loss=0.3119, pruned_loss=0.07669, over 7156.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3147, pruned_loss=0.07551, over 1427296.41 frames.], batch size: 18, lr: 1.30e-03
2022-04-28 14:44:57,969 INFO [train.py:763] (5/8) Epoch 4, batch 3300, loss[loss=0.2549, simple_loss=0.346, pruned_loss=0.08192, over 7195.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3156, pruned_loss=0.07615, over 1422999.04 frames.], batch size: 26, lr: 1.30e-03
2022-04-28 14:46:03,558 INFO [train.py:763] (5/8) Epoch 4, batch 3350, loss[loss=0.333, simple_loss=0.388, pruned_loss=0.139, over 7110.00 frames.], tot_loss[loss=0.2336, simple_loss=0.3154, pruned_loss=0.07587, over 1425416.98 frames.], batch size: 21, lr: 1.30e-03
2022-04-28 14:47:08,822 INFO [train.py:763] (5/8) Epoch 4, batch 3400, loss[loss=0.2446, simple_loss=0.3344, pruned_loss=0.07741, over 7226.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3164, pruned_loss=0.07604, over 1427236.27 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:48:14,161 INFO [train.py:763] (5/8) Epoch 4, batch 3450, loss[loss=0.253, simple_loss=0.3201, pruned_loss=0.09298, over 7190.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3156, pruned_loss=0.07572, over 1426903.30 frames.], batch size: 23, lr: 1.29e-03
2022-04-28 14:49:37,453 INFO [train.py:763] (5/8) Epoch 4, batch 3500, loss[loss=0.2328, simple_loss=0.3022, pruned_loss=0.08168, over 7331.00 frames.], tot_loss[loss=0.2338, simple_loss=0.316, pruned_loss=0.07577, over 1429184.44 frames.], batch size: 20, lr: 1.29e-03
2022-04-28 14:50:52,153 INFO [train.py:763] (5/8) Epoch 4, batch 3550, loss[loss=0.2462, simple_loss=0.3198, pruned_loss=0.08625, over 7404.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3163, pruned_loss=0.07606, over 1423814.53 frames.], batch size: 21, lr: 1.29e-03
2022-04-28 14:51:57,844 INFO [train.py:763] (5/8) Epoch 4, batch 3600, loss[loss=0.2153, simple_loss=0.2858, pruned_loss=0.0724, over 7258.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3159, pruned_loss=0.0762, over 1420329.02 frames.], batch size: 19, lr: 1.29e-03
2022-04-28 14:53:23,239 INFO [train.py:763] (5/8) Epoch 4, batch 3650, loss[loss=0.2352, simple_loss=0.3225, pruned_loss=0.07397, over 6807.00 frames.], tot_loss[loss=0.2341, simple_loss=0.316, pruned_loss=0.07613, over 1414920.62 frames.], batch size: 31, lr: 1.29e-03
2022-04-28 14:54:39,017 INFO [train.py:763] (5/8) Epoch 4, batch 3700, loss[loss=0.209, simple_loss=0.2907, pruned_loss=0.06366, over 7163.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3135, pruned_loss=0.07481, over 1418532.78 frames.], batch size: 18, lr: 1.29e-03
2022-04-28 14:55:53,485 INFO [train.py:763] (5/8) Epoch 4, batch 3750, loss[loss=0.1918, simple_loss=0.2764, pruned_loss=0.0536, over 7203.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3152, pruned_loss=0.07549, over 1420213.42 frames.], batch size: 16, lr: 1.29e-03
2022-04-28 14:56:59,181 INFO [train.py:763] (5/8) Epoch 4, batch 3800, loss[loss=0.2045, simple_loss=0.2839, pruned_loss=0.06255, over 7278.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3147, pruned_loss=0.07523, over 1421500.50 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 14:58:05,508 INFO [train.py:763] (5/8) Epoch 4, batch 3850, loss[loss=0.2454, simple_loss=0.3321, pruned_loss=0.07934, over 7414.00 frames.], tot_loss[loss=0.2319, simple_loss=0.314, pruned_loss=0.07487, over 1421028.01 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 14:59:11,128 INFO [train.py:763] (5/8) Epoch 4, batch 3900, loss[loss=0.2081, simple_loss=0.2974, pruned_loss=0.05937, over 7163.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3132, pruned_loss=0.07449, over 1417693.54 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:00:16,496 INFO [train.py:763] (5/8) Epoch 4, batch 3950, loss[loss=0.2249, simple_loss=0.3148, pruned_loss=0.06744, over 7421.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3134, pruned_loss=0.0749, over 1414903.04 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:01:21,852 INFO [train.py:763] (5/8) Epoch 4, batch 4000, loss[loss=0.2224, simple_loss=0.3153, pruned_loss=0.06479, over 7436.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3131, pruned_loss=0.0741, over 1418250.73 frames.], batch size: 20, lr: 1.28e-03
2022-04-28 15:02:27,499 INFO [train.py:763] (5/8) Epoch 4, batch 4050, loss[loss=0.2151, simple_loss=0.3081, pruned_loss=0.061, over 7218.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3121, pruned_loss=0.07368, over 1420352.12 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:03:34,100 INFO [train.py:763] (5/8) Epoch 4, batch 4100, loss[loss=0.2369, simple_loss=0.3139, pruned_loss=0.07993, over 7274.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3141, pruned_loss=0.07467, over 1417532.87 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:04:40,957 INFO [train.py:763] (5/8) Epoch 4, batch 4150, loss[loss=0.2378, simple_loss=0.3225, pruned_loss=0.0766, over 7193.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3148, pruned_loss=0.07499, over 1415569.25 frames.], batch size: 22, lr: 1.27e-03
2022-04-28 15:05:47,263 INFO [train.py:763] (5/8) Epoch 4, batch 4200, loss[loss=0.2142, simple_loss=0.2886, pruned_loss=0.0699, over 7133.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3151, pruned_loss=0.07513, over 1414276.40 frames.], batch size: 17, lr: 1.27e-03
2022-04-28 15:06:53,144 INFO [train.py:763] (5/8) Epoch 4, batch 4250, loss[loss=0.2022, simple_loss=0.2988, pruned_loss=0.05286, over 7067.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3143, pruned_loss=0.07424, over 1414643.45 frames.], batch size: 18, lr: 1.27e-03
2022-04-28 15:07:59,472 INFO [train.py:763] (5/8) Epoch 4, batch 4300, loss[loss=0.1987, simple_loss=0.291, pruned_loss=0.05321, over 7150.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3151, pruned_loss=0.07457, over 1415416.58 frames.], batch size: 20, lr: 1.27e-03
2022-04-28 15:09:04,577 INFO [train.py:763] (5/8) Epoch 4, batch 4350, loss[loss=0.2416, simple_loss=0.3226, pruned_loss=0.08032, over 7421.00 frames.], tot_loss[loss=0.2321, simple_loss=0.3153, pruned_loss=0.07445, over 1414703.56 frames.], batch size: 21, lr: 1.27e-03
2022-04-28 15:10:09,737 INFO [train.py:763] (5/8) Epoch 4, batch 4400, loss[loss=0.2081, simple_loss=0.2964, pruned_loss=0.05986, over 7263.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3144, pruned_loss=0.0737, over 1410085.12 frames.], batch size: 19, lr: 1.27e-03
2022-04-28 15:11:14,757 INFO [train.py:763] (5/8) Epoch 4, batch 4450, loss[loss=0.2223, simple_loss=0.3148, pruned_loss=0.06486, over 6845.00 frames.], tot_loss[loss=0.231, simple_loss=0.3146, pruned_loss=0.07372, over 1403640.04 frames.], batch size: 31, lr: 1.27e-03
2022-04-28 15:12:19,727 INFO [train.py:763] (5/8) Epoch 4, batch 4500, loss[loss=0.2852, simple_loss=0.3448, pruned_loss=0.1128, over 5207.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3178, pruned_loss=0.07581, over 1394002.91 frames.], batch size: 53, lr: 1.27e-03
2022-04-28 15:13:25,336 INFO [train.py:763] (5/8) Epoch 4, batch 4550, loss[loss=0.3125, simple_loss=0.3689, pruned_loss=0.1281, over 5283.00 frames.], tot_loss[loss=0.2399, simple_loss=0.3211, pruned_loss=0.07933, over 1337773.26 frames.], batch size: 53, lr: 1.26e-03
2022-04-28 15:14:53,622 INFO [train.py:763] (5/8) Epoch 5, batch 0, loss[loss=0.2168, simple_loss=0.2967, pruned_loss=0.06842, over 7157.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2967, pruned_loss=0.06842, over 7157.00 frames.], batch size: 19, lr: 1.21e-03
2022-04-28 15:15:59,881 INFO [train.py:763] (5/8) Epoch 5, batch 50, loss[loss=0.2598, simple_loss=0.3302, pruned_loss=0.09466, over 5005.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3132, pruned_loss=0.07173, over 318596.10 frames.], batch size: 52, lr: 1.21e-03
2022-04-28 15:17:05,494 INFO [train.py:763] (5/8) Epoch 5, batch 100, loss[loss=0.2455, simple_loss=0.3338, pruned_loss=0.07855, over 7144.00 frames.], tot_loss[loss=0.229, simple_loss=0.3142, pruned_loss=0.07195, over 562286.52 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:18:11,212 INFO [train.py:763] (5/8) Epoch 5, batch 150, loss[loss=0.2684, simple_loss=0.346, pruned_loss=0.09542, over 6668.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3132, pruned_loss=0.07111, over 750570.13 frames.], batch size: 31, lr: 1.21e-03
2022-04-28 15:19:17,541 INFO [train.py:763] (5/8) Epoch 5, batch 200, loss[loss=0.1979, simple_loss=0.2807, pruned_loss=0.0576, over 7408.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3122, pruned_loss=0.07043, over 899918.11 frames.], batch size: 18, lr: 1.21e-03
2022-04-28 15:20:23,017 INFO [train.py:763] (5/8) Epoch 5, batch 250, loss[loss=0.2596, simple_loss=0.3503, pruned_loss=0.08449, over 7318.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3116, pruned_loss=0.06945, over 1019885.66 frames.], batch size: 22, lr: 1.21e-03
2022-04-28 15:21:29,019 INFO [train.py:763] (5/8) Epoch 5, batch 300, loss[loss=0.1872, simple_loss=0.2836, pruned_loss=0.04547, over 7242.00 frames.], tot_loss[loss=0.2256, simple_loss=0.311, pruned_loss=0.07009, over 1112227.15 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:22:35,200 INFO [train.py:763] (5/8) Epoch 5, batch 350, loss[loss=0.2204, simple_loss=0.3038, pruned_loss=0.06853, over 7320.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3093, pruned_loss=0.06914, over 1185241.17 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:23:40,942 INFO [train.py:763] (5/8) Epoch 5, batch 400, loss[loss=0.2207, simple_loss=0.3137, pruned_loss=0.06389, over 7367.00 frames.], tot_loss[loss=0.2255, simple_loss=0.3108, pruned_loss=0.07007, over 1236553.02 frames.], batch size: 23, lr: 1.20e-03
2022-04-28 15:24:46,942 INFO [train.py:763] (5/8) Epoch 5, batch 450, loss[loss=0.2222, simple_loss=0.3121, pruned_loss=0.06611, over 7243.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3103, pruned_loss=0.06966, over 1279300.57 frames.], batch size: 16, lr: 1.20e-03
2022-04-28 15:25:52,445 INFO [train.py:763] (5/8) Epoch 5, batch 500, loss[loss=0.3005, simple_loss=0.3603, pruned_loss=0.1204, over 5037.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3109, pruned_loss=0.07021, over 1307600.28 frames.], batch size: 52, lr: 1.20e-03
2022-04-28 15:26:57,647 INFO [train.py:763] (5/8) Epoch 5, batch 550, loss[loss=0.3183, simple_loss=0.3822, pruned_loss=0.1272, over 6502.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3106, pruned_loss=0.06942, over 1332207.39 frames.], batch size: 38, lr: 1.20e-03
2022-04-28 15:28:04,525 INFO [train.py:763] (5/8) Epoch 5, batch 600, loss[loss=0.212, simple_loss=0.3066, pruned_loss=0.05867, over 7154.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3095, pruned_loss=0.06945, over 1351357.41 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:29:09,669 INFO [train.py:763] (5/8) Epoch 5, batch 650, loss[loss=0.205, simple_loss=0.307, pruned_loss=0.05153, over 7408.00 frames.], tot_loss[loss=0.2237, simple_loss=0.309, pruned_loss=0.06915, over 1365910.20 frames.], batch size: 21, lr: 1.20e-03
2022-04-28 15:30:15,014 INFO [train.py:763] (5/8) Epoch 5, batch 700, loss[loss=0.2205, simple_loss=0.2968, pruned_loss=0.07206, over 6745.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3103, pruned_loss=0.06961, over 1377364.29 frames.], batch size: 15, lr: 1.20e-03
2022-04-28 15:31:20,307 INFO [train.py:763] (5/8) Epoch 5, batch 750, loss[loss=0.1936, simple_loss=0.2952, pruned_loss=0.046, over 7219.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3107, pruned_loss=0.06946, over 1387970.94 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:32:25,895 INFO [train.py:763] (5/8) Epoch 5, batch 800, loss[loss=0.2919, simple_loss=0.3636, pruned_loss=0.1101, over 7221.00 frames.], tot_loss[loss=0.224, simple_loss=0.3095, pruned_loss=0.06921, over 1397808.45 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:33:31,260 INFO [train.py:763] (5/8) Epoch 5, batch 850, loss[loss=0.2239, simple_loss=0.3095, pruned_loss=0.06911, over 7201.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3096, pruned_loss=0.0696, over 1403018.32 frames.], batch size: 23, lr: 1.19e-03
2022-04-28 15:34:36,546 INFO [train.py:763] (5/8) Epoch 5, batch 900, loss[loss=0.2575, simple_loss=0.3561, pruned_loss=0.07946, over 7416.00 frames.], tot_loss[loss=0.227, simple_loss=0.3116, pruned_loss=0.0712, over 1405730.65 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:35:42,340 INFO [train.py:763] (5/8) Epoch 5, batch 950, loss[loss=0.2239, simple_loss=0.2937, pruned_loss=0.07702, over 7130.00 frames.], tot_loss[loss=0.227, simple_loss=0.3114, pruned_loss=0.07134, over 1406585.43 frames.], batch size: 17, lr: 1.19e-03
2022-04-28 15:36:47,766 INFO [train.py:763] (5/8) Epoch 5, batch 1000, loss[loss=0.2255, simple_loss=0.3307, pruned_loss=0.06012, over 7399.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3122, pruned_loss=0.07219, over 1408521.47 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:37:53,895 INFO [train.py:763] (5/8) Epoch 5, batch 1050, loss[loss=0.2538, simple_loss=0.3299, pruned_loss=0.08884, over 7332.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3118, pruned_loss=0.07154, over 1414154.52 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:39:10,235 INFO [train.py:763] (5/8) Epoch 5, batch 1100, loss[loss=0.2612, simple_loss=0.3419, pruned_loss=0.09025, over 7313.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3123, pruned_loss=0.07202, over 1409083.77 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:40:16,766 INFO [train.py:763] (5/8) Epoch 5, batch 1150, loss[loss=0.2087, simple_loss=0.3008, pruned_loss=0.05834, over 7145.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3118, pruned_loss=0.07093, over 1413375.48 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:41:22,543 INFO [train.py:763] (5/8) Epoch 5, batch 1200, loss[loss=0.1952, simple_loss=0.2912, pruned_loss=0.04955, over 7192.00 frames.], tot_loss[loss=0.226, simple_loss=0.3108, pruned_loss=0.07061, over 1414138.69 frames.], batch size: 26, lr: 1.18e-03
2022-04-28 15:42:29,036 INFO [train.py:763] (5/8) Epoch 5, batch 1250, loss[loss=0.2008, simple_loss=0.2882, pruned_loss=0.05674, over 7138.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3111, pruned_loss=0.0712, over 1414400.78 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:43:35,964 INFO [train.py:763] (5/8) Epoch 5, batch 1300, loss[loss=0.189, simple_loss=0.2882, pruned_loss=0.04491, over 7364.00 frames.], tot_loss[loss=0.2269, simple_loss=0.311, pruned_loss=0.07142, over 1411869.71 frames.], batch size: 19, lr: 1.18e-03
2022-04-28 15:44:42,297 INFO [train.py:763] (5/8) Epoch 5, batch 1350, loss[loss=0.2211, simple_loss=0.3197, pruned_loss=0.06126, over 7122.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3104, pruned_loss=0.07122, over 1416394.13 frames.], batch size: 28, lr: 1.18e-03
2022-04-28 15:45:48,513 INFO [train.py:763] (5/8) Epoch 5, batch 1400, loss[loss=0.2054, simple_loss=0.2924, pruned_loss=0.05918, over 7321.00 frames.], tot_loss[loss=0.2254, simple_loss=0.31, pruned_loss=0.07037, over 1419966.17 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:46:53,775 INFO [train.py:763] (5/8) Epoch 5, batch 1450, loss[loss=0.2569, simple_loss=0.3323, pruned_loss=0.09079, over 7432.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3095, pruned_loss=0.07, over 1421191.22 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:47:59,052 INFO [train.py:763] (5/8) Epoch 5, batch 1500, loss[loss=0.2138, simple_loss=0.3045, pruned_loss=0.06154, over 7145.00 frames.], tot_loss[loss=0.2241, simple_loss=0.309, pruned_loss=0.06963, over 1421333.34 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:49:04,611 INFO [train.py:763] (5/8) Epoch 5, batch 1550, loss[loss=0.1946, simple_loss=0.2817, pruned_loss=0.05374, over 7270.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3093, pruned_loss=0.07001, over 1422793.95 frames.], batch size: 17, lr: 1.18e-03
2022-04-28 15:50:09,903 INFO [train.py:763] (5/8) Epoch 5, batch 1600, loss[loss=0.2027, simple_loss=0.2907, pruned_loss=0.05736, over 7424.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3089, pruned_loss=0.07034, over 1417231.87 frames.], batch size: 20, lr: 1.17e-03
2022-04-28 15:51:15,390 INFO [train.py:763] (5/8) Epoch 5, batch 1650, loss[loss=0.2687, simple_loss=0.3438, pruned_loss=0.09678, over 7241.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3081, pruned_loss=0.06981, over 1416761.54 frames.], batch size: 25, lr: 1.17e-03
2022-04-28 15:52:21,482 INFO [train.py:763] (5/8) Epoch 5, batch 1700, loss[loss=0.2159, simple_loss=0.3092, pruned_loss=0.06132, over 7199.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3086, pruned_loss=0.07031, over 1414570.52 frames.], batch size: 22, lr: 1.17e-03
2022-04-28 15:53:26,978 INFO [train.py:763] (5/8) Epoch 5, batch 1750, loss[loss=0.2687, simple_loss=0.3331, pruned_loss=0.1021, over 7269.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3101, pruned_loss=0.07132, over 1411916.56 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:54:32,256 INFO [train.py:763] (5/8) Epoch 5, batch 1800, loss[loss=0.2688, simple_loss=0.3408, pruned_loss=0.09836, over 4941.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3097, pruned_loss=0.07099, over 1412448.83 frames.], batch size: 53, lr: 1.17e-03
2022-04-28 15:55:37,885 INFO [train.py:763] (5/8) Epoch 5, batch 1850, loss[loss=0.2291, simple_loss=0.2939, pruned_loss=0.08215, over 7158.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3089, pruned_loss=0.0704, over 1415870.50 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:56:43,244 INFO [train.py:763] (5/8) Epoch 5, batch 1900, loss[loss=0.2133, simple_loss=0.2834, pruned_loss=0.0716, over 7149.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3088, pruned_loss=0.06981, over 1414928.69 frames.], batch size: 17, lr: 1.17e-03
2022-04-28 15:57:48,607 INFO [train.py:763] (5/8) Epoch 5, batch 1950, loss[loss=0.1985, simple_loss=0.2966, pruned_loss=0.05018, over 7106.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3092, pruned_loss=0.06987, over 1420237.22 frames.], batch size: 21, lr: 1.17e-03
2022-04-28 15:58:54,747 INFO [train.py:763] (5/8) Epoch 5, batch 2000, loss[loss=0.2009, simple_loss=0.2797, pruned_loss=0.06107, over 7282.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3089, pruned_loss=0.06917, over 1424016.88 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:59:59,957 INFO [train.py:763] (5/8) Epoch 5, batch 2050, loss[loss=0.2233, simple_loss=0.3087, pruned_loss=0.06892, over 7057.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3091, pruned_loss=0.06883, over 1423912.19 frames.], batch size: 28, lr: 1.16e-03
2022-04-28 16:01:06,588 INFO [train.py:763] (5/8) Epoch 5, batch 2100, loss[loss=0.2487, simple_loss=0.3327, pruned_loss=0.08238, over 6415.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3091, pruned_loss=0.06913, over 1426215.29 frames.], batch size: 38, lr: 1.16e-03
2022-04-28 16:02:12,127 INFO [train.py:763] (5/8) Epoch 5, batch 2150, loss[loss=0.2108, simple_loss=0.3094, pruned_loss=0.0561, over 7154.00 frames.], tot_loss[loss=0.223, simple_loss=0.3088, pruned_loss=0.0686, over 1431077.64 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:03:17,462 INFO [train.py:763] (5/8) Epoch 5, batch 2200, loss[loss=0.2333, simple_loss=0.3153, pruned_loss=0.07565, over 7152.00 frames.], tot_loss[loss=0.2223, simple_loss=0.308, pruned_loss=0.06832, over 1427429.40 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:04:22,917 INFO [train.py:763] (5/8) Epoch 5, batch 2250, loss[loss=0.1888, simple_loss=0.2778, pruned_loss=0.04988, over 7355.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3084, pruned_loss=0.06905, over 1426135.11 frames.], batch size: 19, lr: 1.16e-03
2022-04-28 16:05:29,066 INFO [train.py:763] (5/8) Epoch 5, batch 2300, loss[loss=0.2667, simple_loss=0.3539, pruned_loss=0.08979, over 7277.00 frames.], tot_loss[loss=0.2241, simple_loss=0.3092, pruned_loss=0.06948, over 1422781.89 frames.], batch size: 24, lr: 1.16e-03
2022-04-28 16:06:35,255 INFO [train.py:763] (5/8) Epoch 5, batch 2350, loss[loss=0.2362, simple_loss=0.3278, pruned_loss=0.07225, over 7219.00 frames.], tot_loss[loss=0.2243, simple_loss=0.309, pruned_loss=0.06974, over 1421976.45 frames.], batch size: 21, lr: 1.16e-03
2022-04-28 16:07:41,518 INFO [train.py:763] (5/8) Epoch 5, batch 2400, loss[loss=0.2026, simple_loss=0.2874, pruned_loss=0.05891, over 7323.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3071, pruned_loss=0.0689, over 1421653.64 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:08:47,669 INFO [train.py:763] (5/8) Epoch 5, batch 2450, loss[loss=0.1931, simple_loss=0.2795, pruned_loss=0.05339, over 6843.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3064, pruned_loss=0.06898, over 1420975.04 frames.], batch size: 15, lr: 1.16e-03
2022-04-28 16:09:52,917 INFO [train.py:763] (5/8) Epoch 5, batch 2500, loss[loss=0.2294, simple_loss=0.3191, pruned_loss=0.06987, over 7326.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3079, pruned_loss=0.06966, over 1420288.65 frames.], batch size: 22, lr: 1.15e-03
2022-04-28 16:10:59,314 INFO [train.py:763] (5/8) Epoch 5, batch 2550, loss[loss=0.2253, simple_loss=0.3, pruned_loss=0.07527, over 7240.00 frames.], tot_loss[loss=0.2237, simple_loss=0.308, pruned_loss=0.06973, over 1422161.49 frames.], batch size: 16, lr: 1.15e-03
2022-04-28 16:12:05,359 INFO [train.py:763] (5/8) Epoch 5, batch 2600, loss[loss=0.2576, simple_loss=0.3523, pruned_loss=0.08149, over 7314.00 frames.], tot_loss[loss=0.2247, simple_loss=0.309, pruned_loss=0.07013, over 1425463.92 frames.], batch size: 21, lr: 1.15e-03
2022-04-28 16:13:10,881 INFO [train.py:763] (5/8) Epoch 5, batch 2650, loss[loss=0.224, simple_loss=0.3192, pruned_loss=0.0644, over 7279.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3091, pruned_loss=0.06968, over 1424942.91 frames.], batch size: 25, lr: 1.15e-03
2022-04-28 16:14:16,442 INFO [train.py:763] (5/8) Epoch 5, batch 2700, loss[loss=0.2173, simple_loss=0.292, pruned_loss=0.07131, over 6818.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3079, pruned_loss=0.06885, over 1426654.58 frames.], batch size: 15, lr: 1.15e-03
2022-04-28 16:15:15,071 INFO [train.py:763] (5/8) Epoch 5, batch 2750, loss[loss=0.2012, simple_loss=0.2959, pruned_loss=0.05326, over 7244.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3083, pruned_loss=0.06897, over 1424331.51 frames.], batch size: 20, lr: 1.15e-03
2022-04-28 16:16:11,920 INFO [train.py:763] (5/8) Epoch 5, batch 2800, loss[loss=0.1958, simple_loss=0.2804, pruned_loss=0.0556, over 7279.00 frames.], tot_loss[loss=0.223, simple_loss=0.3082, pruned_loss=0.06891, over 1421875.99 frames.], batch size: 18, lr: 1.15e-03
2022-04-28 16:17:08,602 INFO [train.py:763] (5/8) Epoch 5, batch 2850, loss[loss=0.1941, simple_loss=0.2781, pruned_loss=0.05504, over 7284.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3078, pruned_loss=0.06862, over 1418471.03 frames.], batch size: 17, lr: 1.15e-03
2022-04-28 16:18:06,401 INFO [train.py:763] (5/8) Epoch 5, batch 2900, loss[loss=0.2366, simple_loss=0.3215, pruned_loss=0.07581, over 6742.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3082, pruned_loss=0.06884, over 1420081.33 frames.], batch size: 31, lr: 1.15e-03
2022-04-28 16:19:04,272 INFO [train.py:763] (5/8) Epoch 5, batch 2950, loss[loss=0.241, simple_loss=0.3302, pruned_loss=0.07591, over 7140.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3069, pruned_loss=0.06812, over 1420117.87 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,115 INFO [train.py:763] (5/8) Epoch 5, batch 3000, loss[loss=0.2223, simple_loss=0.3061, pruned_loss=0.06928, over 7234.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3071, pruned_loss=0.0679, over 1419500.39 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,116 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 16:20:13,357 INFO [train.py:792] (5/8) Epoch 5, validation: loss=0.1791, simple_loss=0.2847, pruned_loss=0.03677, over 698248.00 frames.
2022-04-28 16:21:19,344 INFO [train.py:763] (5/8) Epoch 5, batch 3050, loss[loss=0.2595, simple_loss=0.3343, pruned_loss=0.09236, over 7212.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3064, pruned_loss=0.0679, over 1425292.91 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:22:24,948 INFO [train.py:763] (5/8) Epoch 5, batch 3100, loss[loss=0.2147, simple_loss=0.316, pruned_loss=0.0567, over 7343.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3052, pruned_loss=0.06767, over 1423575.39 frames.], batch size: 22, lr: 1.14e-03
2022-04-28 16:23:30,179 INFO [train.py:763] (5/8) Epoch 5, batch 3150, loss[loss=0.2262, simple_loss=0.3137, pruned_loss=0.06939, over 7167.00 frames.], tot_loss[loss=0.2209, simple_loss=0.306, pruned_loss=0.06785, over 1423331.74 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:24:36,731 INFO [train.py:763] (5/8) Epoch 5, batch 3200, loss[loss=0.221, simple_loss=0.3067, pruned_loss=0.06764, over 7233.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3073, pruned_loss=0.06842, over 1424137.68 frames.], batch size: 21, lr: 1.14e-03
2022-04-28 16:25:42,634 INFO [train.py:763] (5/8) Epoch 5, batch 3250, loss[loss=0.1945, simple_loss=0.2847, pruned_loss=0.05211, over 7361.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3081, pruned_loss=0.06814, over 1424149.24 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:26:48,952 INFO [train.py:763] (5/8) Epoch 5, batch 3300, loss[loss=0.2468, simple_loss=0.3344, pruned_loss=0.07963, over 7200.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3093, pruned_loss=0.06855, over 1420077.15 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:27:54,268 INFO [train.py:763] (5/8) Epoch 5, batch 3350, loss[loss=0.2252, simple_loss=0.3122, pruned_loss=0.06906, over 7256.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3081, pruned_loss=0.06809, over 1424422.18 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:28:59,516 INFO [train.py:763] (5/8) Epoch 5, batch 3400, loss[loss=0.2559, simple_loss=0.3381, pruned_loss=0.08687, over 7292.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3073, pruned_loss=0.06797, over 1424336.50 frames.], batch size: 24, lr: 1.14e-03
2022-04-28 16:30:05,198 INFO [train.py:763] (5/8) Epoch 5, batch 3450, loss[loss=0.2097, simple_loss=0.3088, pruned_loss=0.05531, over 7406.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3082, pruned_loss=0.0678, over 1427203.05 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:31:11,009 INFO [train.py:763] (5/8) Epoch 5, batch 3500, loss[loss=0.2374, simple_loss=0.3212, pruned_loss=0.07676, over 7189.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3067, pruned_loss=0.06775, over 1424384.49 frames.], batch size: 22, lr: 1.13e-03
2022-04-28 16:32:16,134 INFO [train.py:763] (5/8) Epoch 5, batch 3550, loss[loss=0.2494, simple_loss=0.3319, pruned_loss=0.08346, over 7323.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3063, pruned_loss=0.06761, over 1427765.39 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:33:21,411 INFO [train.py:763] (5/8) Epoch 5, batch 3600, loss[loss=0.192, simple_loss=0.2666, pruned_loss=0.05871, over 7160.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3064, pruned_loss=0.06771, over 1428623.63 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:34:27,119 INFO [train.py:763] (5/8) Epoch 5, batch 3650, loss[loss=0.2181, simple_loss=0.3109, pruned_loss=0.06265, over 7423.00 frames.], tot_loss[loss=0.2207, simple_loss=0.3065, pruned_loss=0.06751, over 1427834.96 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:35:34,080 INFO [train.py:763] (5/8) Epoch 5, batch 3700, loss[loss=0.1971, simple_loss=0.2967, pruned_loss=0.04881, over 7235.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3066, pruned_loss=0.06801, over 1426144.72 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:36:39,418 INFO [train.py:763] (5/8) Epoch 5, batch 3750, loss[loss=0.2298, simple_loss=0.3178, pruned_loss=0.07086, over 7377.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3071, pruned_loss=0.06873, over 1424343.42 frames.], batch size: 23, lr: 1.13e-03
2022-04-28 16:37:46,380 INFO [train.py:763] (5/8) Epoch 5, batch 3800, loss[loss=0.2025, simple_loss=0.2837, pruned_loss=0.06065, over 7232.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3068, pruned_loss=0.06837, over 1420731.19 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:38:51,774 INFO [train.py:763] (5/8) Epoch 5, batch 3850, loss[loss=0.2056, simple_loss=0.2925, pruned_loss=0.05937, over 7419.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3079, pruned_loss=0.0688, over 1420898.97 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:39:57,108 INFO [train.py:763] (5/8) Epoch 5, batch 3900, loss[loss=0.2082, simple_loss=0.2899, pruned_loss=0.06323, over 7404.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3073, pruned_loss=0.06816, over 1425503.22 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:41:04,046 INFO [train.py:763] (5/8) Epoch 5, batch 3950, loss[loss=0.2462, simple_loss=0.3243, pruned_loss=0.08409, over 7318.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3066, pruned_loss=0.06783, over 1424766.07 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:42:11,004 INFO [train.py:763] (5/8) Epoch 5, batch 4000, loss[loss=0.2237, simple_loss=0.3086, pruned_loss=0.06939, over 7195.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3074, pruned_loss=0.06812, over 1426621.41 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:43:18,253 INFO [train.py:763] (5/8) Epoch 5, batch 4050, loss[loss=0.2527, simple_loss=0.3245, pruned_loss=0.09051, over 7281.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3068, pruned_loss=0.06813, over 1427222.47 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:44:25,538 INFO [train.py:763] (5/8) Epoch 5, batch 4100, loss[loss=0.2014, simple_loss=0.2869, pruned_loss=0.05799, over 7414.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3055, pruned_loss=0.06752, over 1427763.65 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:45:32,381 INFO [train.py:763] (5/8) Epoch 5, batch 4150, loss[loss=0.2656, simple_loss=0.3491, pruned_loss=0.09108, over 6628.00 frames.], tot_loss[loss=0.2204, simple_loss=0.3057, pruned_loss=0.06757, over 1427888.34 frames.], batch size: 31, lr: 1.12e-03
2022-04-28 16:46:39,137 INFO [train.py:763] (5/8) Epoch 5, batch 4200, loss[loss=0.2846, simple_loss=0.3577, pruned_loss=0.1058, over 7117.00 frames.], tot_loss[loss=0.2198, simple_loss=0.3047, pruned_loss=0.06745, over 1429314.29 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:47:45,475 INFO [train.py:763] (5/8) Epoch 5, batch 4250, loss[loss=0.2266, simple_loss=0.3261, pruned_loss=0.06351, over 7373.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3053, pruned_loss=0.06757, over 1430352.43 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:48:52,199 INFO [train.py:763] (5/8) Epoch 5, batch 4300, loss[loss=0.1863, simple_loss=0.2638, pruned_loss=0.05439, over 7074.00 frames.], tot_loss[loss=0.2198, simple_loss=0.305, pruned_loss=0.06732, over 1425367.74 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:49:59,892 INFO [train.py:763] (5/8) Epoch 5, batch 4350, loss[loss=0.2036, simple_loss=0.296, pruned_loss=0.05563, over 7213.00 frames.], tot_loss[loss=0.219, simple_loss=0.3042, pruned_loss=0.06693, over 1424934.81 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:51:07,558 INFO [train.py:763] (5/8) Epoch 5, batch 4400, loss[loss=0.2271, simple_loss=0.3093, pruned_loss=0.07241, over 7430.00 frames.], tot_loss[loss=0.218, simple_loss=0.3033, pruned_loss=0.06636, over 1423161.69 frames.], batch size: 20, lr: 1.12e-03
2022-04-28 16:52:13,253 INFO [train.py:763] (5/8) Epoch 5, batch 4450, loss[loss=0.1925, simple_loss=0.2747, pruned_loss=0.0552, over 7281.00 frames.], tot_loss[loss=0.2188, simple_loss=0.3037, pruned_loss=0.06694, over 1409707.94 frames.], batch size: 17, lr: 1.11e-03
2022-04-28 16:53:19,259 INFO [train.py:763] (5/8) Epoch 5, batch 4500, loss[loss=0.1984, simple_loss=0.2951, pruned_loss=0.05085, over 7234.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3013, pruned_loss=0.06658, over 1409578.62 frames.], batch size: 20, lr: 1.11e-03
2022-04-28 16:54:23,903 INFO [train.py:763] (5/8) Epoch 5, batch 4550, loss[loss=0.3285, simple_loss=0.3876, pruned_loss=0.1347, over 5110.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3058, pruned_loss=0.07031, over 1360227.44 frames.], batch size: 52, lr: 1.11e-03
2022-04-28 16:55:51,902 INFO [train.py:763] (5/8) Epoch 6, batch 0, loss[loss=0.223, simple_loss=0.3072, pruned_loss=0.06945, over 7402.00 frames.], tot_loss[loss=0.223, simple_loss=0.3072, pruned_loss=0.06945, over 7402.00 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:56:58,098 INFO [train.py:763] (5/8) Epoch 6, batch 50, loss[loss=0.1673, simple_loss=0.2534, pruned_loss=0.04057, over 7422.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3034, pruned_loss=0.06494, over 322748.78 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:58:04,030 INFO [train.py:763] (5/8) Epoch 6, batch 100, loss[loss=0.2426, simple_loss=0.329, pruned_loss=0.07808, over 7149.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3014, pruned_loss=0.06303, over 567106.69 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 16:59:09,772 INFO [train.py:763] (5/8) Epoch 6, batch 150, loss[loss=0.1838, simple_loss=0.2795, pruned_loss=0.04408, over 7143.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3022, pruned_loss=0.06381, over 756220.48 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:00:15,503 INFO [train.py:763] (5/8) Epoch 6, batch 200, loss[loss=0.1976, simple_loss=0.295, pruned_loss=0.05009, over 7391.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3024, pruned_loss=0.0635, over 907156.55 frames.], batch size: 23, lr: 1.06e-03
2022-04-28 17:01:29,831 INFO [train.py:763] (5/8) Epoch 6, batch 250, loss[loss=0.2461, simple_loss=0.3288, pruned_loss=0.08167, over 7147.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3027, pruned_loss=0.06333, over 1020927.74 frames.], batch size: 20, lr: 1.06e-03
2022-04-28 17:02:45,517 INFO [train.py:763] (5/8) Epoch 6, batch 300, loss[loss=0.2429, simple_loss=0.3058, pruned_loss=0.08996, over 7221.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3045, pruned_loss=0.06449, over 1107289.29 frames.], batch size: 16, lr: 1.06e-03
2022-04-28 17:03:59,809 INFO [train.py:763] (5/8) Epoch 6, batch 350, loss[loss=0.208, simple_loss=0.3036, pruned_loss=0.05625, over 7110.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3038, pruned_loss=0.06373, over 1177894.80 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:05:05,105 INFO [train.py:763] (5/8) Epoch 6, batch 400, loss[loss=0.1746, simple_loss=0.2517, pruned_loss=0.04873, over 7162.00 frames.], tot_loss[loss=0.216, simple_loss=0.3035, pruned_loss=0.06421, over 1230318.01 frames.], batch size: 18, lr: 1.06e-03
2022-04-28 17:06:20,542 INFO [train.py:763] (5/8) Epoch 6, batch 450, loss[loss=0.1946, simple_loss=0.2758, pruned_loss=0.05672, over 7357.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3027, pruned_loss=0.06393, over 1276075.10 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:07:44,119 INFO [train.py:763] (5/8) Epoch 6, batch 500, loss[loss=0.245, simple_loss=0.327, pruned_loss=0.08154, over 6524.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3048, pruned_loss=0.06512, over 1305407.44 frames.], batch size: 37, lr: 1.06e-03
2022-04-28 17:08:59,116 INFO [train.py:763] (5/8) Epoch 6, batch 550, loss[loss=0.2049, simple_loss=0.2981, pruned_loss=0.0558, over 7107.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3041, pruned_loss=0.06521, over 1330586.70 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:10:13,645 INFO [train.py:763] (5/8) Epoch 6, batch 600, loss[loss=0.2404, simple_loss=0.3231, pruned_loss=0.07888, over 7004.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3049, pruned_loss=0.06571, over 1348352.65 frames.], batch size: 28, lr: 1.06e-03
2022-04-28 17:11:19,494 INFO [train.py:763] (5/8) Epoch 6, batch 650, loss[loss=0.2813, simple_loss=0.3436, pruned_loss=0.1095, over 5099.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3027, pruned_loss=0.06447, over 1364114.89 frames.], batch size: 53, lr: 1.05e-03
2022-04-28 17:12:25,181 INFO [train.py:763] (5/8) Epoch 6, batch 700, loss[loss=0.1819, simple_loss=0.2736, pruned_loss=0.0451, over 7160.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3013, pruned_loss=0.06365, over 1378207.15 frames.], batch size: 18, lr: 1.05e-03
2022-04-28 17:13:31,501 INFO [train.py:763] (5/8) Epoch 6, batch 750, loss[loss=0.2481, simple_loss=0.3299, pruned_loss=0.08314, over 6772.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3014, pruned_loss=0.06384, over 1391677.78 frames.], batch size: 31, lr: 1.05e-03
2022-04-28 17:14:37,097 INFO [train.py:763] (5/8) Epoch 6, batch 800, loss[loss=0.1842, simple_loss=0.2732, pruned_loss=0.04759, over 7335.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2999, pruned_loss=0.06293, over 1391555.68 frames.], batch size: 20, lr: 1.05e-03
2022-04-28 17:15:43,496 INFO [train.py:763] (5/8) Epoch 6, batch 850, loss[loss=0.2002, simple_loss=0.294, pruned_loss=0.05317, over 7290.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2998, pruned_loss=0.06316, over 1397798.01 frames.], batch size: 24, lr: 1.05e-03
2022-04-28 17:16:48,956 INFO [train.py:763] (5/8) Epoch 6, batch 900, loss[loss=0.222, simple_loss=0.314, pruned_loss=0.06496, over 7383.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3005, pruned_loss=0.06335, over 1403207.39 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:17:54,048 INFO [train.py:763] (5/8) Epoch 6, batch 950, loss[loss=0.2552, simple_loss=0.3458, pruned_loss=0.0823, over 7382.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3018, pruned_loss=0.06343, over 1407618.35 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:18:59,566 INFO [train.py:763] (5/8) Epoch 6, batch 1000, loss[loss=0.187, simple_loss=0.2763, pruned_loss=0.04884, over 7384.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3022, pruned_loss=0.0637, over 1408574.77 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:20:06,062 INFO [train.py:763] (5/8) Epoch 6, batch 1050, loss[loss=0.2002, simple_loss=0.2876, pruned_loss=0.05643, over 7148.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3015, pruned_loss=0.0634, over 1415912.31 frames.], batch size: 19, lr: 1.05e-03
2022-04-28 17:21:12,154 INFO [train.py:763] (5/8) Epoch 6, batch 1100, loss[loss=0.2657, simple_loss=0.3558, pruned_loss=0.08778, over 7285.00 frames.], tot_loss[loss=0.2149, simple_loss=0.302, pruned_loss=0.06388, over 1418664.73 frames.], batch size: 25, lr: 1.05e-03
2022-04-28 17:22:18,730 INFO [train.py:763] (5/8) Epoch 6, batch 1150, loss[loss=0.2189, simple_loss=0.2926, pruned_loss=0.07257, over 7135.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3034, pruned_loss=0.06447, over 1417315.87 frames.], batch size: 17, lr: 1.05e-03
2022-04-28 17:23:26,116 INFO [train.py:763] (5/8) Epoch 6, batch 1200, loss[loss=0.231, simple_loss=0.3063, pruned_loss=0.07779, over 6825.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3035, pruned_loss=0.06436, over 1412338.70 frames.], batch size: 15, lr: 1.04e-03
2022-04-28 17:24:33,319 INFO [train.py:763] (5/8) Epoch 6, batch 1250, loss[loss=0.2029, simple_loss=0.3023, pruned_loss=0.05174, over 7234.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3027, pruned_loss=0.06421, over 1413548.52 frames.], batch size: 20, lr: 1.04e-03
2022-04-28 17:25:39,231 INFO [train.py:763] (5/8) Epoch 6, batch 1300, loss[loss=0.1782, simple_loss=0.2645, pruned_loss=0.04595, over 7273.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3027, pruned_loss=0.06438, over 1414917.83 frames.], batch size: 17, lr: 1.04e-03
2022-04-28 17:26:44,447 INFO [train.py:763] (5/8) Epoch 6, batch 1350, loss[loss=0.2119, simple_loss=0.303, pruned_loss=0.06042, over 7416.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3027, pruned_loss=0.06392, over 1420650.88 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:27:49,621 INFO [train.py:763] (5/8) Epoch 6, batch 1400, loss[loss=0.1954, simple_loss=0.2852, pruned_loss=0.0528, over 7163.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3044, pruned_loss=0.0647, over 1419134.63 frames.], batch size: 19, lr: 1.04e-03
2022-04-28 17:28:55,367 INFO [train.py:763] (5/8) Epoch 6, batch 1450, loss[loss=0.2299, simple_loss=0.3162, pruned_loss=0.07185, over 6746.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3045, pruned_loss=0.06499, over 1418922.70 frames.], batch size: 31, lr: 1.04e-03
2022-04-28 17:30:00,752 INFO [train.py:763] (5/8) Epoch 6, batch 1500, loss[loss=0.2315, simple_loss=0.3165, pruned_loss=0.07323, over 7419.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3031, pruned_loss=0.06388, over 1422864.33 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:31:05,973 INFO [train.py:763] (5/8) Epoch 6, batch 1550, loss[loss=0.2666, simple_loss=0.336, pruned_loss=0.09862, over 7166.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3029, pruned_loss=0.06409, over 1417374.08 frames.], batch size: 26, lr: 1.04e-03
2022-04-28 17:32:11,542 INFO [train.py:763] (5/8) Epoch 6, batch 1600, loss[loss=0.2505, simple_loss=0.3409, pruned_loss=0.08004, over 7103.00 frames.], tot_loss[loss=0.2143, simple_loss=0.302, pruned_loss=0.0633, over 1424279.06 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:33:16,941 INFO [train.py:763] (5/8) Epoch 6, batch 1650, loss[loss=0.2369, simple_loss=0.3106, pruned_loss=0.08162, over 7065.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3018, pruned_loss=0.06373, over 1418493.09 frames.], batch size: 18, lr: 1.04e-03
2022-04-28 17:34:24,088 INFO [train.py:763] (5/8) Epoch 6, batch 1700, loss[loss=0.2351, simple_loss=0.3206, pruned_loss=0.07484, over 7215.00 frames.], tot_loss[loss=0.2143, simple_loss=0.301, pruned_loss=0.06383, over 1416683.13 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:35:30,124 INFO [train.py:763] (5/8) Epoch 6, batch 1750, loss[loss=0.2397, simple_loss=0.333, pruned_loss=0.07318, over 7336.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3022, pruned_loss=0.06466, over 1411788.57 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:36:35,228 INFO [train.py:763] (5/8) Epoch 6, batch 1800, loss[loss=0.2526, simple_loss=0.3365, pruned_loss=0.08436, over 7300.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3027, pruned_loss=0.06452, over 1414979.46 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:37:41,014 INFO [train.py:763] (5/8) Epoch 6, batch 1850, loss[loss=0.187, simple_loss=0.2622, pruned_loss=0.05592, over 7006.00 frames.], tot_loss[loss=0.216, simple_loss=0.3029, pruned_loss=0.06451, over 1417169.23 frames.], batch size: 16, lr: 1.03e-03
2022-04-28 17:38:46,206 INFO [train.py:763] (5/8) Epoch 6, batch 1900, loss[loss=0.2106, simple_loss=0.2994, pruned_loss=0.06093, over 7062.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3039, pruned_loss=0.06533, over 1413528.20 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:39:52,671 INFO [train.py:763] (5/8) Epoch 6, batch 1950, loss[loss=0.221, simple_loss=0.2914, pruned_loss=0.07535, over 7276.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3026, pruned_loss=0.06518, over 1417363.41 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:40:59,185 INFO [train.py:763] (5/8) Epoch 6, batch 2000, loss[loss=0.2468, simple_loss=0.3182, pruned_loss=0.08773, over 7278.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3022, pruned_loss=0.06502, over 1418096.44 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:42:06,059 INFO [train.py:763] (5/8) Epoch 6, batch 2050, loss[loss=0.2226, simple_loss=0.3126, pruned_loss=0.06627, over 7296.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3032, pruned_loss=0.06558, over 1414897.26 frames.], batch size: 24, lr: 1.03e-03
2022-04-28 17:43:12,556 INFO [train.py:763] (5/8) Epoch 6, batch 2100, loss[loss=0.1776, simple_loss=0.2665, pruned_loss=0.04435, over 6994.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3031, pruned_loss=0.06493, over 1417765.30 frames.], batch size: 16, lr: 1.03e-03
2022-04-28 17:44:19,364 INFO [train.py:763] (5/8) Epoch 6, batch 2150, loss[loss=0.2329, simple_loss=0.3224, pruned_loss=0.07172, over 7407.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3029, pruned_loss=0.06437, over 1423364.52 frames.], batch size: 21, lr: 1.03e-03
2022-04-28 17:45:25,698 INFO [train.py:763] (5/8) Epoch 6, batch 2200, loss[loss=0.2145, simple_loss=0.2919, pruned_loss=0.06857, over 7136.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3018, pruned_loss=0.06364, over 1421783.60 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:46:32,102 INFO [train.py:763] (5/8) Epoch 6, batch 2250, loss[loss=0.2061, simple_loss=0.2853, pruned_loss=0.06348, over 7274.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3025, pruned_loss=0.06434, over 1416104.40 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:47:38,691 INFO [train.py:763] (5/8) Epoch 6, batch 2300, loss[loss=0.2452, simple_loss=0.3379, pruned_loss=0.07628, over 7172.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3015, pruned_loss=0.06368, over 1419276.94 frames.], batch size: 23, lr: 1.03e-03
2022-04-28 17:48:44,946 INFO [train.py:763] (5/8) Epoch 6, batch 2350, loss[loss=0.2525, simple_loss=0.3437, pruned_loss=0.08065, over 7405.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3024, pruned_loss=0.06406, over 1416555.55 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:49:50,853 INFO [train.py:763] (5/8) Epoch 6, batch 2400, loss[loss=0.216, simple_loss=0.2984, pruned_loss=0.0668, over 7278.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3029, pruned_loss=0.06425, over 1420972.13 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:50:56,973 INFO [train.py:763] (5/8) Epoch 6, batch 2450, loss[loss=0.2441, simple_loss=0.3343, pruned_loss=0.07698, over 7417.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3037, pruned_loss=0.06511, over 1417112.45 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:52:02,805 INFO [train.py:763] (5/8) Epoch 6, batch 2500, loss[loss=0.244, simple_loss=0.3343, pruned_loss=0.07684, over 7316.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3042, pruned_loss=0.06528, over 1417281.67 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:53:08,646 INFO [train.py:763] (5/8) Epoch 6, batch 2550, loss[loss=0.2493, simple_loss=0.3225, pruned_loss=0.0881, over 7423.00 frames.], tot_loss[loss=0.216, simple_loss=0.3031, pruned_loss=0.06444, over 1423610.94 frames.], batch size: 20, lr: 1.02e-03
2022-04-28 17:54:14,772 INFO [train.py:763] (5/8) Epoch 6, batch 2600, loss[loss=0.159, simple_loss=0.2508, pruned_loss=0.03367, over 7160.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3023, pruned_loss=0.06417, over 1417943.08 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:55:21,049 INFO [train.py:763] (5/8) Epoch 6, batch 2650, loss[loss=0.1874, simple_loss=0.2762, pruned_loss=0.04927, over 7155.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3022, pruned_loss=0.06442, over 1417509.50 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:56:26,534 INFO [train.py:763] (5/8) Epoch 6, batch 2700, loss[loss=0.1975, simple_loss=0.2788, pruned_loss=0.05808, over 6822.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3027, pruned_loss=0.0646, over 1418815.67 frames.], batch size: 15, lr: 1.02e-03
2022-04-28 17:57:32,674 INFO [train.py:763] (5/8) Epoch 6, batch 2750, loss[loss=0.1954, simple_loss=0.2847, pruned_loss=0.05301, over 7409.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3026, pruned_loss=0.06424, over 1419116.51 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:58:39,125 INFO [train.py:763] (5/8) Epoch 6, batch 2800, loss[loss=0.1901, simple_loss=0.2784, pruned_loss=0.05089, over 6991.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3015, pruned_loss=0.06387, over 1417992.12 frames.], batch size: 16, lr: 1.02e-03
2022-04-28 17:59:46,052 INFO [train.py:763] (5/8) Epoch 6, batch 2850, loss[loss=0.219, simple_loss=0.3077, pruned_loss=0.06512, over 7311.00 frames.], tot_loss[loss=0.2129, simple_loss=0.2996, pruned_loss=0.06312, over 1423311.04 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 18:00:52,211 INFO [train.py:763] (5/8) Epoch 6, batch 2900, loss[loss=0.2518, simple_loss=0.3216, pruned_loss=0.09107, over 5202.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3005, pruned_loss=0.06294, over 1425753.94 frames.], batch size: 53, lr: 1.02e-03
2022-04-28 18:01:57,565 INFO [train.py:763] (5/8) Epoch 6, batch 2950, loss[loss=0.2437, simple_loss=0.3231, pruned_loss=0.08211, over 7305.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3019, pruned_loss=0.06337, over 1426057.65 frames.], batch size: 25, lr: 1.01e-03
2022-04-28 18:03:03,522 INFO [train.py:763] (5/8) Epoch 6, batch 3000, loss[loss=0.2367, simple_loss=0.3192, pruned_loss=0.07707, over 7175.00 frames.], tot_loss[loss=0.215, simple_loss=0.3022, pruned_loss=0.06391, over 1427634.85 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:03:03,523 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 18:03:18,817 INFO [train.py:792] (5/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
2022-04-28 18:04:24,352 INFO [train.py:763] (5/8) Epoch 6, batch 3050, loss[loss=0.2175, simple_loss=0.3005, pruned_loss=0.06721, over 7170.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3025, pruned_loss=0.06413, over 1427512.82 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:05:30,261 INFO [train.py:763] (5/8) Epoch 6, batch 3100, loss[loss=0.206, simple_loss=0.2931, pruned_loss=0.05942, over 7087.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3031, pruned_loss=0.06427, over 1425286.52 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:06:36,924 INFO [train.py:763] (5/8) Epoch 6, batch 3150, loss[loss=0.2286, simple_loss=0.3128, pruned_loss=0.07217, over 7117.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3021, pruned_loss=0.06349, over 1428844.62 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:07:42,736 INFO [train.py:763] (5/8) Epoch 6, batch 3200, loss[loss=0.219, simple_loss=0.3142, pruned_loss=0.06186, over 7337.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3032, pruned_loss=0.06428, over 1425078.55 frames.], batch size: 22, lr: 1.01e-03
2022-04-28 18:08:48,611 INFO [train.py:763] (5/8) Epoch 6, batch 3250, loss[loss=0.2065, simple_loss=0.3038, pruned_loss=0.05458, over 7038.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3021, pruned_loss=0.0642, over 1424748.74 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:09:54,860 INFO [train.py:763] (5/8) Epoch 6, batch 3300, loss[loss=0.2113, simple_loss=0.3063, pruned_loss=0.05819, over 7149.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3022, pruned_loss=0.06399, over 1419391.61 frames.], batch size: 20, lr: 1.01e-03
2022-04-28 18:11:00,644 INFO [train.py:763] (5/8) Epoch 6, batch 3350, loss[loss=0.2173, simple_loss=0.3032, pruned_loss=0.06567, over 7155.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3024, pruned_loss=0.06394, over 1420697.90 frames.], batch size: 19, lr: 1.01e-03
2022-04-28 18:12:05,977 INFO [train.py:763] (5/8) Epoch 6, batch 3400, loss[loss=0.2244, simple_loss=0.3112, pruned_loss=0.06882, over 7125.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3029, pruned_loss=0.06404, over 1422706.65 frames.], batch size: 21, lr: 1.01e-03
2022-04-28 18:13:11,474 INFO [train.py:763] (5/8) Epoch 6, batch 3450, loss[loss=0.2163, simple_loss=0.3087, pruned_loss=0.06196, over 7302.00 frames.], tot_loss[loss=0.215, simple_loss=0.3027, pruned_loss=0.0637, over 1420029.90 frames.], batch size: 24, lr: 1.01e-03
2022-04-28 18:14:16,744 INFO [train.py:763] (5/8) Epoch 6, batch 3500, loss[loss=0.2341, simple_loss=0.3252, pruned_loss=0.07147, over 7224.00 frames.], tot_loss[loss=0.2157, simple_loss=0.3032, pruned_loss=0.06408, over 1421675.28 frames.], batch size: 21, lr: 1.01e-03
2022-04-28 18:15:22,310 INFO [train.py:763] (5/8) Epoch 6, batch 3550, loss[loss=0.2353, simple_loss=0.3265, pruned_loss=0.07201, over 7373.00 frames.], tot_loss[loss=0.2155, simple_loss=0.303, pruned_loss=0.06403, over 1423213.94 frames.], batch size: 23, lr: 1.01e-03
2022-04-28 18:16:27,538 INFO [train.py:763] (5/8) Epoch 6, batch 3600, loss[loss=0.2306, simple_loss=0.3257, pruned_loss=0.06768, over 7213.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3029, pruned_loss=0.06396, over 1424754.62 frames.], batch size: 21, lr: 1.00e-03
2022-04-28 18:17:32,795 INFO [train.py:763] (5/8) Epoch 6, batch 3650, loss[loss=0.2473, simple_loss=0.3347, pruned_loss=0.07996, over 7040.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3026, pruned_loss=0.06344, over 1421179.61 frames.], batch size: 28, lr: 1.00e-03
2022-04-28 18:18:39,448 INFO [train.py:763] (5/8) Epoch 6, batch 3700, loss[loss=0.2087, simple_loss=0.2854, pruned_loss=0.06598, over 7432.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3014, pruned_loss=0.06303, over 1422838.94 frames.], batch size: 20, lr: 1.00e-03
2022-04-28 18:19:44,876 INFO [train.py:763] (5/8) Epoch 6, batch 3750, loss[loss=0.2538, simple_loss=0.3242, pruned_loss=0.09169, over 5176.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3022, pruned_loss=0.06383, over 1423757.84 frames.], batch size: 55, lr: 1.00e-03
2022-04-28 18:20:50,225 INFO [train.py:763] (5/8) Epoch 6, batch 3800, loss[loss=0.2024, simple_loss=0.2911, pruned_loss=0.05684, over 7361.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3018, pruned_loss=0.06336, over 1420777.55 frames.], batch size: 19, lr: 1.00e-03
2022-04-28 18:21:56,434 INFO [train.py:763] (5/8) Epoch 6, batch 3850, loss[loss=0.215, simple_loss=0.2929, pruned_loss=0.06856, over 7144.00 frames.], tot_loss[loss=0.214, simple_loss=0.3012, pruned_loss=0.06339, over 1423990.98 frames.], batch size: 17, lr: 1.00e-03
2022-04-28 18:23:02,795 INFO [train.py:763] (5/8) Epoch 6, batch 3900, loss[loss=0.2044, simple_loss=0.2903, pruned_loss=0.05921, over 7154.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3005, pruned_loss=0.06293, over 1424341.61 frames.], batch size: 18, lr: 1.00e-03
2022-04-28 18:24:08,628 INFO [train.py:763] (5/8) Epoch 6, batch 3950, loss[loss=0.2239, simple_loss=0.3108, pruned_loss=0.06845, over 7333.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3003, pruned_loss=0.06275, over 1425815.63 frames.], batch size: 22, lr: 9.99e-04
2022-04-28 18:25:14,073 INFO [train.py:763] (5/8) Epoch 6, batch 4000, loss[loss=0.2284, simple_loss=0.3099, pruned_loss=0.07345, over 6773.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3007, pruned_loss=0.06302, over 1430277.97 frames.], batch size: 31, lr: 9.98e-04
2022-04-28 18:26:19,664 INFO [train.py:763] (5/8) Epoch 6, batch 4050, loss[loss=0.1984, simple_loss=0.2895, pruned_loss=0.05368, over 7163.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3003, pruned_loss=0.0626, over 1428718.33 frames.], batch size: 18, lr: 9.98e-04
2022-04-28 18:27:25,501 INFO [train.py:763] (5/8) Epoch 6, batch 4100, loss[loss=0.2344, simple_loss=0.3178, pruned_loss=0.07547, over 7103.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3006, pruned_loss=0.06321, over 1423857.25 frames.], batch size: 21, lr: 9.97e-04
2022-04-28 18:28:32,065 INFO [train.py:763] (5/8) Epoch 6, batch 4150, loss[loss=0.2358, simple_loss=0.3199, pruned_loss=0.07585, over 7192.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2997, pruned_loss=0.06289, over 1424548.99 frames.], batch size: 23, lr: 9.96e-04
2022-04-28 18:29:37,834 INFO [train.py:763] (5/8) Epoch 6, batch 4200, loss[loss=0.1833, simple_loss=0.2616, pruned_loss=0.05251, over 7280.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2988, pruned_loss=0.06195, over 1428029.00 frames.], batch size: 17, lr: 9.95e-04
2022-04-28 18:30:43,253 INFO [train.py:763] (5/8) Epoch 6, batch 4250, loss[loss=0.2175, simple_loss=0.3025, pruned_loss=0.06624, over 7422.00 frames.], tot_loss[loss=0.213, simple_loss=0.3003, pruned_loss=0.06281, over 1422272.76 frames.], batch size: 20, lr: 9.95e-04
2022-04-28 18:31:48,732 INFO [train.py:763] (5/8) Epoch 6, batch 4300, loss[loss=0.2, simple_loss=0.2889, pruned_loss=0.05553, over 7239.00 frames.], tot_loss[loss=0.2148, simple_loss=0.302, pruned_loss=0.06375, over 1417517.32 frames.], batch size: 20, lr: 9.94e-04
2022-04-28 18:32:54,889 INFO [train.py:763] (5/8) Epoch 6, batch 4350, loss[loss=0.2431, simple_loss=0.3281, pruned_loss=0.079, over 6452.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3015, pruned_loss=0.06341, over 1409728.28 frames.], batch size: 37, lr: 9.93e-04
2022-04-28 18:34:00,601 INFO [train.py:763] (5/8) Epoch 6, batch 4400, loss[loss=0.2345, simple_loss=0.3298, pruned_loss=0.06956, over 6788.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3007, pruned_loss=0.06274, over 1411502.53 frames.], batch size: 31, lr: 9.92e-04
2022-04-28 18:35:07,316 INFO [train.py:763] (5/8) Epoch 6, batch 4450, loss[loss=0.2439, simple_loss=0.3228, pruned_loss=0.08245, over 7208.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3018, pruned_loss=0.06326, over 1406104.53 frames.], batch size: 22, lr: 9.92e-04
2022-04-28 18:36:23,325 INFO [train.py:763] (5/8) Epoch 6, batch 4500, loss[loss=0.2617, simple_loss=0.3417, pruned_loss=0.09081, over 7200.00 frames.], tot_loss[loss=0.2154, simple_loss=0.303, pruned_loss=0.06391, over 1404020.49 frames.], batch size: 22, lr: 9.91e-04
2022-04-28 18:37:28,297 INFO [train.py:763] (5/8) Epoch 6, batch 4550, loss[loss=0.293, simple_loss=0.3656, pruned_loss=0.1102, over 5156.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3051, pruned_loss=0.06464, over 1389023.21 frames.], batch size: 52, lr: 9.90e-04
2022-04-28 18:38:57,448 INFO [train.py:763] (5/8) Epoch 7, batch 0, loss[loss=0.2237, simple_loss=0.3247, pruned_loss=0.06136, over 7336.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3247, pruned_loss=0.06136, over 7336.00 frames.], batch size: 22, lr: 9.49e-04
2022-04-28 18:40:02,644 INFO [train.py:763] (5/8) Epoch 7, batch 50, loss[loss=0.24, simple_loss=0.3022, pruned_loss=0.08885, over 7145.00 frames.], tot_loss[loss=0.216, simple_loss=0.3067, pruned_loss=0.06268, over 320501.34 frames.], batch size: 17, lr: 9.48e-04
2022-04-28 18:41:07,861 INFO [train.py:763] (5/8) Epoch 7, batch 100, loss[loss=0.2617, simple_loss=0.3509, pruned_loss=0.08625, over 7264.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3047, pruned_loss=0.06246, over 569096.56 frames.], batch size: 25, lr: 9.48e-04
2022-04-28 18:42:13,277 INFO [train.py:763] (5/8) Epoch 7, batch 150, loss[loss=0.178, simple_loss=0.2735, pruned_loss=0.04126, over 7114.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2995, pruned_loss=0.05987, over 758781.89 frames.], batch size: 21, lr: 9.47e-04
2022-04-28 18:43:19,114 INFO [train.py:763] (5/8) Epoch 7, batch 200, loss[loss=0.2144, simple_loss=0.3196, pruned_loss=0.05463, over 7204.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2992, pruned_loss=0.06018, over 907317.16 frames.], batch size: 22, lr: 9.46e-04
2022-04-28 18:44:24,618 INFO [train.py:763] (5/8) Epoch 7, batch 250, loss[loss=0.2202, simple_loss=0.321, pruned_loss=0.05969, over 7111.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3011, pruned_loss=0.06137, over 1020623.77 frames.], batch size: 21, lr: 9.46e-04
2022-04-28 18:45:29,828 INFO [train.py:763] (5/8) Epoch 7, batch 300, loss[loss=0.2141, simple_loss=0.2952, pruned_loss=0.0665, over 7070.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3006, pruned_loss=0.06109, over 1106526.31 frames.], batch size: 18, lr: 9.45e-04
2022-04-28 18:46:35,552 INFO [train.py:763] (5/8) Epoch 7, batch 350, loss[loss=0.222, simple_loss=0.3224, pruned_loss=0.06085, over 7108.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2998, pruned_loss=0.06103, over 1178305.48 frames.], batch size: 21, lr: 9.44e-04
2022-04-28 18:47:40,832 INFO [train.py:763] (5/8) Epoch 7, batch 400, loss[loss=0.3023, simple_loss=0.3468, pruned_loss=0.1289, over 4745.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3008, pruned_loss=0.06141, over 1230831.07 frames.], batch size: 52, lr: 9.43e-04
2022-04-28 18:48:46,401 INFO [train.py:763] (5/8) Epoch 7, batch 450, loss[loss=0.1955, simple_loss=0.2751, pruned_loss=0.05797, over 6790.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3014, pruned_loss=0.06234, over 1272136.36 frames.], batch size: 15, lr: 9.43e-04
2022-04-28 18:49:51,768 INFO [train.py:763] (5/8) Epoch 7, batch 500, loss[loss=0.2438, simple_loss=0.3279, pruned_loss=0.07991, over 7205.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2999, pruned_loss=0.06163, over 1304878.41 frames.], batch size: 23, lr: 9.42e-04
2022-04-28 18:50:57,364 INFO [train.py:763] (5/8) Epoch 7, batch 550, loss[loss=0.2216, simple_loss=0.3151, pruned_loss=0.06399, over 7205.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2999, pruned_loss=0.06096, over 1332634.06 frames.], batch size: 23, lr: 9.41e-04
2022-04-28 18:52:02,636 INFO [train.py:763] (5/8) Epoch 7, batch 600, loss[loss=0.1895, simple_loss=0.2888, pruned_loss=0.04515, over 7225.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3003, pruned_loss=0.06144, over 1353284.70 frames.], batch size: 21, lr: 9.41e-04
2022-04-28 18:53:08,466 INFO [train.py:763] (5/8) Epoch 7, batch 650, loss[loss=0.2065, simple_loss=0.3016, pruned_loss=0.05568, over 7263.00 frames.], tot_loss[loss=0.21, simple_loss=0.299, pruned_loss=0.06047, over 1368053.53 frames.], batch size: 19, lr: 9.40e-04
2022-04-28 18:54:13,821 INFO [train.py:763] (5/8) Epoch 7, batch 700, loss[loss=0.252, simple_loss=0.3177, pruned_loss=0.09312, over 5294.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2999, pruned_loss=0.06116, over 1377064.87 frames.], batch size: 52, lr: 9.39e-04
2022-04-28 18:55:19,485 INFO [train.py:763] (5/8) Epoch 7, batch 750, loss[loss=0.2212, simple_loss=0.304, pruned_loss=0.06922, over 7359.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2987, pruned_loss=0.06079, over 1384804.95 frames.], batch size: 19, lr: 9.39e-04
2022-04-28 18:56:26,112 INFO [train.py:763] (5/8) Epoch 7, batch 800, loss[loss=0.232, simple_loss=0.3228, pruned_loss=0.07059, over 6396.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3008, pruned_loss=0.0612, over 1390141.65 frames.], batch size: 37, lr: 9.38e-04
2022-04-28 18:57:33,285 INFO [train.py:763] (5/8) Epoch 7, batch 850, loss[loss=0.1971, simple_loss=0.2815, pruned_loss=0.05636, over 7404.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2982, pruned_loss=0.06017, over 1399122.67 frames.], batch size: 18, lr: 9.37e-04
2022-04-28 18:58:40,236 INFO [train.py:763] (5/8) Epoch 7, batch 900, loss[loss=0.2267, simple_loss=0.313, pruned_loss=0.07023, over 6745.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2995, pruned_loss=0.061, over 1398991.63 frames.], batch size: 31, lr: 9.36e-04
2022-04-28 18:59:46,950 INFO [train.py:763] (5/8) Epoch 7, batch 950, loss[loss=0.173, simple_loss=0.2776, pruned_loss=0.03424, over 7230.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2999, pruned_loss=0.06122, over 1405033.82 frames.], batch size: 20, lr: 9.36e-04
2022-04-28 19:00:52,056 INFO [train.py:763] (5/8) Epoch 7, batch 1000, loss[loss=0.2277, simple_loss=0.3129, pruned_loss=0.07125, over 7227.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2996, pruned_loss=0.0611, over 1409133.73 frames.], batch size: 21, lr: 9.35e-04
2022-04-28 19:01:58,582 INFO [train.py:763] (5/8) Epoch 7, batch 1050, loss[loss=0.1739, simple_loss=0.263, pruned_loss=0.0424, over 7116.00 frames.], tot_loss[loss=0.2101, simple_loss=0.299, pruned_loss=0.06063, over 1407114.54 frames.], batch size: 17, lr: 9.34e-04
2022-04-28 19:03:05,231 INFO [train.py:763] (5/8) Epoch 7, batch 1100, loss[loss=0.201, simple_loss=0.2862, pruned_loss=0.05792, over 7201.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2991, pruned_loss=0.06102, over 1412229.13 frames.], batch size: 22, lr: 9.34e-04
2022-04-28 19:04:11,933 INFO [train.py:763] (5/8) Epoch 7, batch 1150, loss[loss=0.2442, simple_loss=0.3244, pruned_loss=0.08204, over 4990.00 frames.], tot_loss[loss=0.2117, simple_loss=0.3008, pruned_loss=0.0613, over 1417523.36 frames.], batch size: 52, lr: 9.33e-04
2022-04-28 19:05:18,442 INFO [train.py:763] (5/8) Epoch 7, batch 1200, loss[loss=0.1989, simple_loss=0.2997, pruned_loss=0.04901, over 7137.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2996, pruned_loss=0.06068, over 1420656.80 frames.], batch size: 20, lr: 9.32e-04
2022-04-28 19:06:24,034 INFO [train.py:763] (5/8) Epoch 7, batch 1250, loss[loss=0.1869, simple_loss=0.2725, pruned_loss=0.05064, over 7290.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2989, pruned_loss=0.06072, over 1419250.67 frames.], batch size: 18, lr: 9.32e-04
2022-04-28 19:07:30,161 INFO [train.py:763] (5/8) Epoch 7, batch 1300, loss[loss=0.2086, simple_loss=0.3045, pruned_loss=0.05634, over 7140.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2993, pruned_loss=0.061, over 1415536.29 frames.], batch size: 20, lr: 9.31e-04
2022-04-28 19:08:35,484 INFO [train.py:763] (5/8) Epoch 7, batch 1350, loss[loss=0.2155, simple_loss=0.3051, pruned_loss=0.06294, over 7164.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2998, pruned_loss=0.06174, over 1414372.71 frames.], batch size: 19, lr: 9.30e-04
2022-04-28 19:09:41,322 INFO [train.py:763] (5/8) Epoch 7, batch 1400, loss[loss=0.174, simple_loss=0.2715, pruned_loss=0.03822, over 7280.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2993, pruned_loss=0.06079, over 1416453.60 frames.], batch size: 18, lr: 9.30e-04
2022-04-28 19:10:48,156 INFO [train.py:763] (5/8) Epoch 7, batch 1450, loss[loss=0.1798, simple_loss=0.2742, pruned_loss=0.04273, over 7158.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2989, pruned_loss=0.06031, over 1416113.09 frames.], batch size: 18, lr: 9.29e-04
2022-04-28 19:11:54,403 INFO [train.py:763] (5/8) Epoch 7, batch 1500, loss[loss=0.2041, simple_loss=0.2877, pruned_loss=0.06023, over 7417.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2982, pruned_loss=0.06049, over 1416194.28 frames.], batch size: 18, lr: 9.28e-04
2022-04-28 19:12:59,479 INFO [train.py:763] (5/8) Epoch 7, batch 1550, loss[loss=0.1993, simple_loss=0.2947, pruned_loss=0.05196, over 7202.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2979, pruned_loss=0.05995, over 1421046.72 frames.], batch size: 22, lr: 9.28e-04
2022-04-28 19:14:04,518 INFO [train.py:763] (5/8) Epoch 7, batch 1600, loss[loss=0.2155, simple_loss=0.2983, pruned_loss=0.06638, over 6485.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2986, pruned_loss=0.0603, over 1421111.67 frames.], batch size: 38, lr: 9.27e-04
2022-04-28 19:15:09,647 INFO [train.py:763] (5/8) Epoch 7, batch 1650, loss[loss=0.1839, simple_loss=0.2835, pruned_loss=0.04217, over 7309.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2986, pruned_loss=0.06031, over 1419934.10 frames.], batch size: 24, lr: 9.26e-04
2022-04-28 19:16:15,826 INFO [train.py:763] (5/8) Epoch 7, batch 1700, loss[loss=0.1993, simple_loss=0.2912, pruned_loss=0.05366, over 7314.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2979, pruned_loss=0.05977, over 1420197.26 frames.], batch size: 21, lr: 9.26e-04
2022-04-28 19:17:22,177 INFO [train.py:763] (5/8) Epoch 7, batch 1750, loss[loss=0.2295, simple_loss=0.3191, pruned_loss=0.07001, over 7317.00 frames.], tot_loss[loss=0.209, simple_loss=0.2984, pruned_loss=0.05978, over 1420444.62 frames.], batch size: 22, lr: 9.25e-04
2022-04-28 19:18:45,821 INFO [train.py:763] (5/8) Epoch 7, batch 1800, loss[loss=0.2042, simple_loss=0.3125, pruned_loss=0.04795, over 7339.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2969, pruned_loss=0.05924, over 1421111.65 frames.], batch size: 22, lr: 9.24e-04
2022-04-28 19:19:59,994 INFO [train.py:763] (5/8) Epoch 7, batch 1850, loss[loss=0.2223, simple_loss=0.3139, pruned_loss=0.06531, over 7245.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2977, pruned_loss=0.05967, over 1422857.61 frames.], batch size: 20, lr: 9.24e-04
2022-04-28 19:21:23,370 INFO [train.py:763] (5/8) Epoch 7, batch 1900, loss[loss=0.2739, simple_loss=0.3603, pruned_loss=0.09373, over 7295.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2972, pruned_loss=0.0598, over 1421778.53 frames.], batch size: 25, lr: 9.23e-04
2022-04-28 19:22:40,071 INFO [train.py:763] (5/8) Epoch 7, batch 1950, loss[loss=0.1518, simple_loss=0.243, pruned_loss=0.03026, over 7002.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2973, pruned_loss=0.05979, over 1425843.97 frames.], batch size: 16, lr: 9.22e-04
2022-04-28 19:23:47,456 INFO [train.py:763] (5/8) Epoch 7, batch 2000, loss[loss=0.2064, simple_loss=0.2968, pruned_loss=0.05794, over 7105.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2971, pruned_loss=0.05952, over 1425873.74 frames.], batch size: 21, lr: 9.22e-04
2022-04-28 19:25:02,873 INFO [train.py:763] (5/8) Epoch 7, batch 2050, loss[loss=0.2554, simple_loss=0.3208, pruned_loss=0.095, over 5077.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2983, pruned_loss=0.06024, over 1420229.23 frames.], batch size: 52, lr: 9.21e-04
2022-04-28 19:26:07,941 INFO [train.py:763] (5/8) Epoch 7, batch 2100, loss[loss=0.1921, simple_loss=0.2941, pruned_loss=0.04501, over 7240.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2987, pruned_loss=0.06027, over 1417604.44 frames.], batch size: 20, lr: 9.20e-04
2022-04-28 19:27:22,251 INFO [train.py:763] (5/8) Epoch 7, batch 2150, loss[loss=0.2232, simple_loss=0.3151, pruned_loss=0.06569, over 7190.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2978, pruned_loss=0.05973, over 1418468.85 frames.], batch size: 22, lr: 9.20e-04
2022-04-28 19:28:27,691 INFO [train.py:763] (5/8) Epoch 7, batch 2200, loss[loss=0.2369, simple_loss=0.3353, pruned_loss=0.06922, over 7298.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2967, pruned_loss=0.05936, over 1415795.54 frames.], batch size: 24, lr: 9.19e-04
2022-04-28 19:29:32,847 INFO [train.py:763] (5/8) Epoch 7, batch 2250, loss[loss=0.2437, simple_loss=0.3318, pruned_loss=0.07785, over 7200.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2967, pruned_loss=0.05997, over 1410615.20 frames.], batch size: 23, lr: 9.18e-04
2022-04-28 19:30:38,174 INFO [train.py:763] (5/8) Epoch 7, batch 2300, loss[loss=0.1674, simple_loss=0.2503, pruned_loss=0.04226, over 7420.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2971, pruned_loss=0.06006, over 1411248.00 frames.], batch size: 18, lr: 9.18e-04
2022-04-28 19:31:43,955 INFO [train.py:763] (5/8) Epoch 7, batch 2350, loss[loss=0.2086, simple_loss=0.3008, pruned_loss=0.05822, over 7067.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2984, pruned_loss=0.06073, over 1411249.15 frames.], batch size: 18, lr: 9.17e-04
2022-04-28 19:32:50,596 INFO [train.py:763] (5/8) Epoch 7, batch 2400, loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03158, over 7251.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2978, pruned_loss=0.06018, over 1415401.21 frames.], batch size: 19, lr: 9.16e-04
2022-04-28 19:33:55,905 INFO [train.py:763] (5/8) Epoch 7, batch 2450, loss[loss=0.192, simple_loss=0.2987, pruned_loss=0.04268, over 7308.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2985, pruned_loss=0.06016, over 1422495.95 frames.], batch size: 24, lr: 9.16e-04
2022-04-28 19:35:01,305 INFO [train.py:763] (5/8) Epoch 7, batch 2500, loss[loss=0.2137, simple_loss=0.3166, pruned_loss=0.05539, over 7319.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2994, pruned_loss=0.06044, over 1420642.51 frames.], batch size: 21, lr: 9.15e-04
2022-04-28 19:36:06,929 INFO [train.py:763] (5/8) Epoch 7, batch 2550, loss[loss=0.26, simple_loss=0.3352, pruned_loss=0.09241, over 7357.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2984, pruned_loss=0.06022, over 1425009.77 frames.], batch size: 19, lr: 9.14e-04
2022-04-28 19:37:12,487 INFO [train.py:763] (5/8) Epoch 7, batch 2600, loss[loss=0.1703, simple_loss=0.2553, pruned_loss=0.04265, over 7226.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2975, pruned_loss=0.05977, over 1425540.41 frames.], batch size: 16, lr: 9.14e-04
2022-04-28 19:38:17,717 INFO [train.py:763] (5/8) Epoch 7, batch 2650, loss[loss=0.2207, simple_loss=0.3015, pruned_loss=0.06997, over 7115.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2965, pruned_loss=0.0592, over 1426477.11 frames.], batch size: 21, lr: 9.13e-04
2022-04-28 19:39:23,653 INFO [train.py:763] (5/8) Epoch 7, batch 2700, loss[loss=0.1679, simple_loss=0.2614, pruned_loss=0.03723, over 6767.00 frames.], tot_loss[loss=0.2059, simple_loss=0.295, pruned_loss=0.05843, over 1428610.68 frames.], batch size: 15, lr: 9.12e-04
2022-04-28 19:40:30,723 INFO [train.py:763] (5/8) Epoch 7, batch 2750, loss[loss=0.1705, simple_loss=0.2595, pruned_loss=0.04079, over 7407.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2952, pruned_loss=0.05903, over 1428382.63 frames.], batch size: 17, lr: 9.12e-04
2022-04-28 19:41:36,698 INFO [train.py:763] (5/8) Epoch 7, batch 2800, loss[loss=0.2175, simple_loss=0.3063, pruned_loss=0.06432, over 7145.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2959, pruned_loss=0.05874, over 1427995.25 frames.], batch size: 20, lr: 9.11e-04
2022-04-28 19:42:43,489 INFO [train.py:763] (5/8) Epoch 7, batch 2850, loss[loss=0.2298, simple_loss=0.3225, pruned_loss=0.06859, over 7214.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2961, pruned_loss=0.05844, over 1426393.31 frames.], batch size: 22, lr: 9.11e-04
2022-04-28 19:43:49,297 INFO [train.py:763] (5/8) Epoch 7, batch 2900, loss[loss=0.1814, simple_loss=0.2701, pruned_loss=0.04636, over 7152.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2973, pruned_loss=0.05889, over 1425758.79 frames.], batch size: 17, lr: 9.10e-04
2022-04-28 19:44:55,759 INFO [train.py:763] (5/8) Epoch 7, batch 2950, loss[loss=0.2018, simple_loss=0.2847, pruned_loss=0.05942, over 7054.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2961, pruned_loss=0.05882, over 1425143.58 frames.], batch size: 18, lr: 9.09e-04
2022-04-28 19:46:01,163 INFO [train.py:763] (5/8) Epoch 7, batch 3000, loss[loss=0.2515, simple_loss=0.3182, pruned_loss=0.09243, over 5155.00 frames.], tot_loss[loss=0.207, simple_loss=0.2965, pruned_loss=0.05876, over 1421400.84 frames.], batch size: 52, lr: 9.09e-04
2022-04-28 19:46:01,164 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 19:46:16,423 INFO [train.py:792] (5/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
2022-04-28 19:47:23,042 INFO [train.py:763] (5/8) Epoch 7, batch 3050, loss[loss=0.2104, simple_loss=0.3026, pruned_loss=0.05915, over 6306.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2964, pruned_loss=0.05934, over 1414982.72 frames.], batch size: 37, lr: 9.08e-04
2022-04-28 19:48:28,737 INFO [train.py:763] (5/8) Epoch 7, batch 3100, loss[loss=0.1763, simple_loss=0.27, pruned_loss=0.0413, over 7258.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2959, pruned_loss=0.05858, over 1418914.14 frames.], batch size: 19, lr: 9.07e-04
2022-04-28 19:49:34,318 INFO [train.py:763] (5/8) Epoch 7, batch 3150, loss[loss=0.1912, simple_loss=0.2866, pruned_loss=0.04794, over 7433.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2946, pruned_loss=0.05825, over 1421203.86 frames.], batch size: 20, lr: 9.07e-04
2022-04-28 19:50:39,923 INFO [train.py:763] (5/8) Epoch 7, batch 3200, loss[loss=0.2042, simple_loss=0.3059, pruned_loss=0.05121, over 7438.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2952, pruned_loss=0.05822, over 1424047.29 frames.], batch size: 20, lr: 9.06e-04
2022-04-28 19:51:45,170 INFO [train.py:763] (5/8) Epoch 7, batch 3250, loss[loss=0.2378, simple_loss=0.3191, pruned_loss=0.07824, over 7030.00 frames.], tot_loss[loss=0.207, simple_loss=0.2961, pruned_loss=0.05892, over 1422675.68 frames.], batch size: 28, lr: 9.05e-04
2022-04-28 19:52:50,679 INFO [train.py:763] (5/8) Epoch 7, batch 3300, loss[loss=0.2172, simple_loss=0.3102, pruned_loss=0.0621, over 6779.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2957, pruned_loss=0.05865, over 1422688.06 frames.], batch size: 31, lr: 9.05e-04
2022-04-28 19:53:56,160 INFO [train.py:763] (5/8) Epoch 7, batch 3350, loss[loss=0.1736, simple_loss=0.2663, pruned_loss=0.04052, over 7432.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2968, pruned_loss=0.05939, over 1421126.02 frames.], batch size: 20, lr: 9.04e-04
2022-04-28 19:55:01,745 INFO [train.py:763] (5/8) Epoch 7, batch 3400, loss[loss=0.2244, simple_loss=0.3171, pruned_loss=0.06584, over 6831.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2961, pruned_loss=0.05923, over 1419149.11 frames.], batch size: 31, lr: 9.04e-04
2022-04-28 19:56:08,389 INFO [train.py:763] (5/8) Epoch 7, batch 3450, loss[loss=0.2017, simple_loss=0.2776, pruned_loss=0.06296, over 7418.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2975, pruned_loss=0.06006, over 1421884.05 frames.], batch size: 18, lr: 9.03e-04
2022-04-28 19:57:15,791 INFO [train.py:763] (5/8) Epoch 7, batch 3500, loss[loss=0.1961, simple_loss=0.2901, pruned_loss=0.05102, over 7380.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2977, pruned_loss=0.05988, over 1421635.27 frames.], batch size: 23, lr: 9.02e-04
2022-04-28 19:58:22,828 INFO [train.py:763] (5/8) Epoch 7, batch 3550, loss[loss=0.1873, simple_loss=0.2848, pruned_loss=0.0449, over 7260.00 frames.], tot_loss[loss=0.2092, simple_loss=0.298, pruned_loss=0.06022, over 1422691.42 frames.], batch size: 19, lr: 9.02e-04
2022-04-28 19:59:29,960 INFO [train.py:763] (5/8) Epoch 7, batch 3600, loss[loss=0.179, simple_loss=0.2633, pruned_loss=0.04732, over 7262.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2967, pruned_loss=0.05939, over 1421595.67 frames.], batch size: 17, lr: 9.01e-04
2022-04-28 20:00:37,041 INFO [train.py:763] (5/8) Epoch 7, batch 3650, loss[loss=0.196, simple_loss=0.3003, pruned_loss=0.0459, over 7407.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2975, pruned_loss=0.05968, over 1415718.87 frames.], batch size: 21, lr: 9.01e-04
2022-04-28 20:01:42,545 INFO [train.py:763] (5/8) Epoch 7, batch 3700, loss[loss=0.2168, simple_loss=0.3174, pruned_loss=0.0581, over 7220.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2972, pruned_loss=0.05909, over 1419355.87 frames.], batch size: 21, lr: 9.00e-04
2022-04-28 20:02:49,194 INFO [train.py:763] (5/8) Epoch 7, batch 3750, loss[loss=0.196, simple_loss=0.2858, pruned_loss=0.05306, over 7159.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2959, pruned_loss=0.0584, over 1416351.81 frames.], batch size: 19, lr: 8.99e-04
2022-04-28 20:03:54,765 INFO [train.py:763] (5/8) Epoch 7, batch 3800, loss[loss=0.2737, simple_loss=0.3537, pruned_loss=0.09681, over 7273.00 frames.], tot_loss[loss=0.2071, simple_loss=0.297, pruned_loss=0.05858, over 1419963.89 frames.], batch size: 24, lr: 8.99e-04
2022-04-28 20:05:00,511 INFO [train.py:763] (5/8) Epoch 7, batch 3850, loss[loss=0.2133, simple_loss=0.3106, pruned_loss=0.05801, over 7219.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2983, pruned_loss=0.05917, over 1418068.26 frames.], batch size: 21, lr: 8.98e-04
2022-04-28 20:06:06,739 INFO [train.py:763] (5/8) Epoch 7, batch 3900, loss[loss=0.1956, simple_loss=0.2915, pruned_loss=0.04987, over 7434.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2971, pruned_loss=0.05832, over 1421796.89 frames.], batch size: 20, lr: 8.97e-04
2022-04-28 20:07:13,251 INFO [train.py:763] (5/8) Epoch 7, batch 3950, loss[loss=0.1821, simple_loss=0.2673, pruned_loss=0.04847, over 6995.00 frames.], tot_loss[loss=0.2055, simple_loss=0.296, pruned_loss=0.05754, over 1425135.46 frames.], batch size: 16, lr: 8.97e-04
2022-04-28 20:08:18,740 INFO [train.py:763] (5/8) Epoch 7, batch 4000, loss[loss=0.2087, simple_loss=0.3057, pruned_loss=0.0558, over 7143.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2969, pruned_loss=0.0579, over 1423699.24 frames.], batch size: 20, lr: 8.96e-04
2022-04-28 20:09:23,873 INFO [train.py:763] (5/8) Epoch 7, batch 4050, loss[loss=0.2617, simple_loss=0.3586, pruned_loss=0.08241, over 7406.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2961, pruned_loss=0.05757, over 1425833.92 frames.], batch size: 21, lr: 8.96e-04
2022-04-28 20:10:29,416 INFO [train.py:763] (5/8) Epoch 7, batch 4100, loss[loss=0.2062, simple_loss=0.2848, pruned_loss=0.06383, over 7273.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2961, pruned_loss=0.05772, over 1419269.64 frames.], batch size: 17, lr: 8.95e-04
2022-04-28 20:11:34,145 INFO [train.py:763] (5/8) Epoch 7, batch 4150, loss[loss=0.2016, simple_loss=0.3049, pruned_loss=0.04913, over 7341.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2966, pruned_loss=0.0578, over 1412281.20 frames.], batch size: 22, lr: 8.94e-04
2022-04-28 20:12:39,369 INFO [train.py:763] (5/8) Epoch 7, batch 4200, loss[loss=0.214, simple_loss=0.3083, pruned_loss=0.0599, over 7146.00 frames.], tot_loss[loss=0.2062, simple_loss=0.297, pruned_loss=0.05768, over 1415039.58 frames.], batch size: 20, lr: 8.94e-04
2022-04-28 20:13:44,898 INFO [train.py:763] (5/8) Epoch 7, batch 4250, loss[loss=0.2097, simple_loss=0.3111, pruned_loss=0.05413, over 7213.00 frames.], tot_loss[loss=0.2054, simple_loss=0.296, pruned_loss=0.05737, over 1419677.88 frames.], batch size: 22, lr: 8.93e-04
2022-04-28 20:14:50,392 INFO [train.py:763] (5/8) Epoch 7, batch 4300, loss[loss=0.2302, simple_loss=0.3112, pruned_loss=0.07459, over 7311.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2951, pruned_loss=0.05785, over 1418335.75 frames.], batch size: 21, lr: 8.93e-04
2022-04-28 20:15:55,692 INFO [train.py:763] (5/8) Epoch 7, batch 4350, loss[loss=0.2021, simple_loss=0.3087, pruned_loss=0.04777, over 7109.00 frames.], tot_loss[loss=0.205, simple_loss=0.2945, pruned_loss=0.05779, over 1414322.66 frames.], batch size: 21, lr: 8.92e-04
2022-04-28 20:17:01,784 INFO [train.py:763] (5/8) Epoch 7, batch 4400, loss[loss=0.1966, simple_loss=0.2929, pruned_loss=0.05017, over 7010.00 frames.], tot_loss[loss=0.205, simple_loss=0.2943, pruned_loss=0.05779, over 1416888.14 frames.], batch size: 28, lr: 8.91e-04
2022-04-28 20:18:08,983 INFO [train.py:763] (5/8) Epoch 7, batch 4450, loss[loss=0.2193, simple_loss=0.3058, pruned_loss=0.06641, over 7332.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2946, pruned_loss=0.05801, over 1417028.88 frames.], batch size: 20, lr: 8.91e-04
2022-04-28 20:19:16,359 INFO [train.py:763] (5/8) Epoch 7, batch 4500, loss[loss=0.2247, simple_loss=0.2992, pruned_loss=0.07511, over 7161.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2942, pruned_loss=0.05872, over 1414286.78 frames.], batch size: 18, lr: 8.90e-04
2022-04-28 20:20:24,255 INFO [train.py:763] (5/8) Epoch 7, batch 4550, loss[loss=0.2142, simple_loss=0.2882, pruned_loss=0.07016, over 7298.00 frames.], tot_loss[loss=0.206, simple_loss=0.2935, pruned_loss=0.05925, over 1398369.30 frames.], batch size: 17, lr: 8.90e-04
2022-04-28 20:21:52,814 INFO [train.py:763] (5/8) Epoch 8, batch 0, loss[loss=0.2479, simple_loss=0.3474, pruned_loss=0.07417, over 7204.00 frames.], tot_loss[loss=0.2479, simple_loss=0.3474, pruned_loss=0.07417, over 7204.00 frames.], batch size: 23, lr: 8.54e-04
2022-04-28 20:22:58,565 INFO [train.py:763] (5/8) Epoch 8, batch 50, loss[loss=0.2022, simple_loss=0.3052, pruned_loss=0.04964, over 7093.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3006, pruned_loss=0.0602, over 319535.94 frames.], batch size: 28, lr: 8.53e-04
2022-04-28 20:24:03,947 INFO [train.py:763] (5/8) Epoch 8, batch 100, loss[loss=0.196, simple_loss=0.2845, pruned_loss=0.05374, over 7237.00 frames.], tot_loss[loss=0.2059, simple_loss=0.296, pruned_loss=0.05786, over 566721.51 frames.], batch size: 20, lr: 8.53e-04
2022-04-28 20:25:10,094 INFO [train.py:763] (5/8) Epoch 8, batch 150, loss[loss=0.2428, simple_loss=0.3196, pruned_loss=0.083, over 5099.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2948, pruned_loss=0.05715, over 753259.72 frames.], batch size: 52, lr: 8.52e-04
2022-04-28 20:26:16,008 INFO [train.py:763] (5/8) Epoch 8, batch 200, loss[loss=0.2185, simple_loss=0.3065, pruned_loss=0.06529, over 7178.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2954, pruned_loss=0.0568, over 902196.55 frames.], batch size: 22, lr: 8.51e-04
2022-04-28 20:27:21,277 INFO [train.py:763] (5/8) Epoch 8, batch 250, loss[loss=0.2034, simple_loss=0.2888, pruned_loss=0.05895, over 7438.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2946, pruned_loss=0.05639, over 1018488.57 frames.], batch size: 20, lr: 8.51e-04
2022-04-28 20:28:27,037 INFO [train.py:763] (5/8) Epoch 8, batch 300, loss[loss=0.1931, simple_loss=0.2955, pruned_loss=0.04529, over 7339.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2953, pruned_loss=0.05701, over 1105022.95 frames.], batch size: 22, lr: 8.50e-04
2022-04-28 20:29:32,800 INFO [train.py:763] (5/8) Epoch 8, batch 350, loss[loss=0.1835, simple_loss=0.2774, pruned_loss=0.04484, over 7159.00 frames.], tot_loss[loss=0.2027, simple_loss=0.293, pruned_loss=0.05615, over 1178962.59 frames.], batch size: 19, lr: 8.50e-04
2022-04-28 20:30:38,288 INFO [train.py:763] (5/8) Epoch 8, batch 400, loss[loss=0.1655, simple_loss=0.2488, pruned_loss=0.04108, over 7143.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2924, pruned_loss=0.05572, over 1237942.69 frames.], batch size: 17, lr: 8.49e-04
2022-04-28 20:31:43,715 INFO [train.py:763] (5/8) Epoch 8, batch 450, loss[loss=0.1792, simple_loss=0.2712, pruned_loss=0.04361, over 7255.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2923, pruned_loss=0.05559, over 1278242.08 frames.], batch size: 19, lr: 8.49e-04
2022-04-28 20:32:50,565 INFO [train.py:763] (5/8) Epoch 8, batch 500, loss[loss=0.2014, simple_loss=0.2884, pruned_loss=0.0572, over 7426.00 frames.], tot_loss[loss=0.2032, simple_loss=0.294, pruned_loss=0.05621, over 1311295.24 frames.], batch size: 18, lr: 8.48e-04
2022-04-28 20:33:57,715 INFO [train.py:763] (5/8) Epoch 8, batch 550, loss[loss=0.1816, simple_loss=0.2834, pruned_loss=0.03989, over 7073.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2935, pruned_loss=0.05579, over 1338692.40 frames.], batch size: 18, lr: 8.48e-04
2022-04-28 20:35:03,802 INFO [train.py:763] (5/8) Epoch 8, batch 600, loss[loss=0.2293, simple_loss=0.3104, pruned_loss=0.0741, over 7056.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2932, pruned_loss=0.0558, over 1360370.90 frames.], batch size: 18, lr: 8.47e-04
2022-04-28 20:36:09,116 INFO [train.py:763] (5/8) Epoch 8, batch 650, loss[loss=0.2186, simple_loss=0.294, pruned_loss=0.07165, over 7355.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2938, pruned_loss=0.05634, over 1373748.00 frames.], batch size: 19, lr: 8.46e-04
2022-04-28 20:37:14,556 INFO [train.py:763] (5/8) Epoch 8, batch 700, loss[loss=0.2014, simple_loss=0.2921, pruned_loss=0.05536, over 7429.00 frames.], tot_loss[loss=0.2035, simple_loss=0.294, pruned_loss=0.05652, over 1386542.20 frames.], batch size: 20, lr: 8.46e-04
2022-04-28 20:38:20,317 INFO [train.py:763] (5/8) Epoch 8, batch 750, loss[loss=0.1677, simple_loss=0.2622, pruned_loss=0.03662, over 7172.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2948, pruned_loss=0.05673, over 1390053.93 frames.], batch size: 18, lr: 8.45e-04
2022-04-28 20:39:25,916 INFO [train.py:763] (5/8) Epoch 8, batch 800, loss[loss=0.2309, simple_loss=0.3211, pruned_loss=0.07042, over 7390.00 frames.], tot_loss[loss=0.204, simple_loss=0.2945, pruned_loss=0.05672, over 1395777.54 frames.], batch size: 23, lr: 8.45e-04
2022-04-28 20:40:32,532 INFO [train.py:763] (5/8) Epoch 8, batch 850, loss[loss=0.2098, simple_loss=0.2983, pruned_loss=0.06066, over 7314.00 frames.], tot_loss[loss=0.2044, simple_loss=0.295, pruned_loss=0.05692, over 1400327.16 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:41:39,530 INFO [train.py:763] (5/8) Epoch 8, batch 900, loss[loss=0.2161, simple_loss=0.3034, pruned_loss=0.0644, over 7222.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2941, pruned_loss=0.0564, over 1410320.92 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:42:46,681 INFO [train.py:763] (5/8) Epoch 8, batch 950, loss[loss=0.2144, simple_loss=0.2958, pruned_loss=0.06654, over 7351.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2943, pruned_loss=0.05702, over 1409274.99 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:43:53,796 INFO [train.py:763] (5/8) Epoch 8, batch 1000, loss[loss=0.204, simple_loss=0.2916, pruned_loss=0.05822, over 7426.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2932, pruned_loss=0.05646, over 1413116.86 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:45:00,941 INFO [train.py:763] (5/8) Epoch 8, batch 1050, loss[loss=0.1945, simple_loss=0.2905, pruned_loss=0.04928, over 7254.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2928, pruned_loss=0.05603, over 1418689.65 frames.], batch size: 19, lr: 8.42e-04
2022-04-28 20:46:07,163 INFO [train.py:763] (5/8) Epoch 8, batch 1100, loss[loss=0.1756, simple_loss=0.2541, pruned_loss=0.04852, over 7273.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2937, pruned_loss=0.05633, over 1421811.43 frames.], batch size: 17, lr: 8.41e-04
2022-04-28 20:47:12,903 INFO [train.py:763] (5/8) Epoch 8, batch 1150, loss[loss=0.2145, simple_loss=0.3026, pruned_loss=0.06319, over 7297.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2935, pruned_loss=0.05607, over 1421888.35 frames.], batch size: 25, lr: 8.41e-04
2022-04-28 20:48:18,245 INFO [train.py:763] (5/8) Epoch 8, batch 1200, loss[loss=0.1803, simple_loss=0.2672, pruned_loss=0.04667, over 7432.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2934, pruned_loss=0.05617, over 1422137.67 frames.], batch size: 20, lr: 8.40e-04
2022-04-28 20:49:23,431 INFO [train.py:763] (5/8) Epoch 8, batch 1250, loss[loss=0.1775, simple_loss=0.2609, pruned_loss=0.04706, over 6847.00 frames.], tot_loss[loss=0.2016, simple_loss=0.292, pruned_loss=0.0556, over 1418702.66 frames.], batch size: 15, lr: 8.40e-04
2022-04-28 20:50:29,963 INFO [train.py:763] (5/8) Epoch 8, batch 1300, loss[loss=0.2153, simple_loss=0.3135, pruned_loss=0.05857, over 7148.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2926, pruned_loss=0.05591, over 1415018.45 frames.], batch size: 19, lr: 8.39e-04
2022-04-28 20:51:37,190 INFO [train.py:763] (5/8) Epoch 8, batch 1350, loss[loss=0.2022, simple_loss=0.2869, pruned_loss=0.05874, over 7436.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2935, pruned_loss=0.0566, over 1419216.48 frames.], batch size: 20, lr: 8.39e-04
2022-04-28 20:52:43,215 INFO [train.py:763] (5/8) Epoch 8, batch 1400, loss[loss=0.2296, simple_loss=0.3215, pruned_loss=0.06886, over 7225.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2936, pruned_loss=0.05695, over 1415675.17 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:53:48,897 INFO [train.py:763] (5/8) Epoch 8, batch 1450, loss[loss=0.2232, simple_loss=0.3133, pruned_loss=0.06652, over 7319.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2922, pruned_loss=0.05599, over 1420424.39 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:54:55,566 INFO [train.py:763] (5/8) Epoch 8, batch 1500, loss[loss=0.2029, simple_loss=0.3025, pruned_loss=0.05168, over 7226.00 frames.], tot_loss[loss=0.2015, simple_loss=0.292, pruned_loss=0.05553, over 1423017.14 frames.], batch size: 20, lr: 8.37e-04
2022-04-28 20:56:02,364 INFO [train.py:763] (5/8) Epoch 8, batch 1550, loss[loss=0.2439, simple_loss=0.336, pruned_loss=0.0759, over 7217.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2919, pruned_loss=0.05574, over 1422711.25 frames.], batch size: 22, lr: 8.37e-04
2022-04-28 20:57:08,626 INFO [train.py:763] (5/8) Epoch 8, batch 1600, loss[loss=0.2057, simple_loss=0.2896, pruned_loss=0.06089, over 7067.00 frames.], tot_loss[loss=0.202, simple_loss=0.2925, pruned_loss=0.05576, over 1420581.42 frames.], batch size: 18, lr: 8.36e-04
2022-04-28 20:58:15,622 INFO [train.py:763] (5/8) Epoch 8, batch 1650, loss[loss=0.2404, simple_loss=0.3254, pruned_loss=0.07772, over 7113.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2926, pruned_loss=0.05606, over 1422373.10 frames.], batch size: 21, lr: 8.35e-04
2022-04-28 20:59:22,377 INFO [train.py:763] (5/8) Epoch 8, batch 1700, loss[loss=0.2106, simple_loss=0.3084, pruned_loss=0.05647, over 7150.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2935, pruned_loss=0.05607, over 1421083.84 frames.], batch size: 20, lr: 8.35e-04
2022-04-28 21:00:28,781 INFO [train.py:763] (5/8) Epoch 8, batch 1750, loss[loss=0.2115, simple_loss=0.3088, pruned_loss=0.05709, over 7322.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2929, pruned_loss=0.05582, over 1422607.94 frames.], batch size: 21, lr: 8.34e-04
2022-04-28 21:01:33,982 INFO [train.py:763] (5/8) Epoch 8, batch 1800, loss[loss=0.1837, simple_loss=0.282, pruned_loss=0.04272, over 7226.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2938, pruned_loss=0.05636, over 1419302.74 frames.], batch size: 20, lr: 8.34e-04
2022-04-28 21:02:39,285 INFO [train.py:763] (5/8) Epoch 8, batch 1850, loss[loss=0.191, simple_loss=0.2894, pruned_loss=0.04635, over 7221.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2946, pruned_loss=0.05633, over 1422131.71 frames.], batch size: 20, lr: 8.33e-04
2022-04-28 21:03:44,677 INFO [train.py:763] (5/8) Epoch 8, batch 1900, loss[loss=0.1868, simple_loss=0.2809, pruned_loss=0.04631, over 7158.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2951, pruned_loss=0.05625, over 1420533.42 frames.], batch size: 19, lr: 8.33e-04
2022-04-28 21:04:50,209 INFO [train.py:763] (5/8) Epoch 8, batch 1950, loss[loss=0.1921, simple_loss=0.2946, pruned_loss=0.04484, over 7125.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2935, pruned_loss=0.05566, over 1422003.45 frames.], batch size: 21, lr: 8.32e-04
2022-04-28 21:05:55,506 INFO [train.py:763] (5/8) Epoch 8, batch 2000, loss[loss=0.2151, simple_loss=0.3018, pruned_loss=0.06423, over 7318.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2927, pruned_loss=0.05533, over 1422447.09 frames.], batch size: 24, lr: 8.32e-04
2022-04-28 21:07:00,733 INFO [train.py:763] (5/8) Epoch 8, batch 2050, loss[loss=0.1678, simple_loss=0.2498, pruned_loss=0.04289, over 7284.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2936, pruned_loss=0.05598, over 1421899.70 frames.], batch size: 17, lr: 8.31e-04
2022-04-28 21:08:05,944 INFO [train.py:763] (5/8) Epoch 8, batch 2100, loss[loss=0.2359, simple_loss=0.3224, pruned_loss=0.0747, over 7253.00 frames.], tot_loss[loss=0.202, simple_loss=0.293, pruned_loss=0.05551, over 1423297.56 frames.], batch size: 19, lr: 8.31e-04
2022-04-28 21:09:08,028 INFO [train.py:763] (5/8) Epoch 8, batch 2150, loss[loss=0.2118, simple_loss=0.2947, pruned_loss=0.0644, over 7073.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2925, pruned_loss=0.05497, over 1425250.99 frames.], batch size: 18, lr: 8.30e-04
2022-04-28 21:10:14,599 INFO [train.py:763] (5/8) Epoch 8, batch 2200, loss[loss=0.1659, simple_loss=0.2617, pruned_loss=0.035, over 7255.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2925, pruned_loss=0.05533, over 1423444.97 frames.], batch size: 17, lr: 8.30e-04
2022-04-28 21:11:21,400 INFO [train.py:763] (5/8) Epoch 8, batch 2250, loss[loss=0.1908, simple_loss=0.2751, pruned_loss=0.05327, over 7155.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2922, pruned_loss=0.05528, over 1423782.32 frames.], batch size: 18, lr: 8.29e-04
2022-04-28 21:12:26,811 INFO [train.py:763] (5/8) Epoch 8, batch 2300, loss[loss=0.1568, simple_loss=0.2521, pruned_loss=0.03076, over 7155.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2931, pruned_loss=0.0558, over 1424989.65 frames.], batch size: 20, lr: 8.29e-04
2022-04-28 21:13:32,129 INFO [train.py:763] (5/8) Epoch 8, batch 2350, loss[loss=0.2347, simple_loss=0.3168, pruned_loss=0.07629, over 6811.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2937, pruned_loss=0.05634, over 1422920.30 frames.], batch size: 31, lr: 8.28e-04
2022-04-28 21:14:37,454 INFO [train.py:763] (5/8) Epoch 8, batch 2400, loss[loss=0.1682, simple_loss=0.2651, pruned_loss=0.03567, over 7276.00 frames.], tot_loss[loss=0.2037, simple_loss=0.294, pruned_loss=0.05664, over 1424216.25 frames.], batch size: 18, lr: 8.28e-04
2022-04-28 21:15:42,881 INFO [train.py:763] (5/8) Epoch 8, batch 2450, loss[loss=0.2028, simple_loss=0.2859, pruned_loss=0.05987, over 7410.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2935, pruned_loss=0.05602, over 1425282.90 frames.], batch size: 18, lr: 8.27e-04
2022-04-28 21:16:48,168 INFO [train.py:763] (5/8) Epoch 8, batch 2500, loss[loss=0.1949, simple_loss=0.2816, pruned_loss=0.05408, over 7205.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2934, pruned_loss=0.05611, over 1423608.83 frames.], batch size: 22, lr: 8.27e-04
2022-04-28 21:17:53,466 INFO [train.py:763] (5/8) Epoch 8, batch 2550, loss[loss=0.1791, simple_loss=0.2545, pruned_loss=0.05189, over 7136.00 frames.], tot_loss[loss=0.202, simple_loss=0.2925, pruned_loss=0.05574, over 1421232.81 frames.], batch size: 17, lr: 8.26e-04
2022-04-28 21:18:58,786 INFO [train.py:763] (5/8) Epoch 8, batch 2600, loss[loss=0.2223, simple_loss=0.3125, pruned_loss=0.06599, over 7371.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2933, pruned_loss=0.05589, over 1418884.30 frames.], batch size: 23, lr: 8.25e-04
2022-04-28 21:20:03,883 INFO [train.py:763] (5/8) Epoch 8, batch 2650, loss[loss=0.2536, simple_loss=0.3238, pruned_loss=0.09169, over 5323.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2924, pruned_loss=0.05539, over 1417758.30 frames.], batch size: 53, lr: 8.25e-04
2022-04-28 21:21:09,318 INFO [train.py:763] (5/8) Epoch 8, batch 2700, loss[loss=0.1988, simple_loss=0.2967, pruned_loss=0.05041, over 7336.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2927, pruned_loss=0.0552, over 1419372.24 frames.], batch size: 22, lr: 8.24e-04
2022-04-28 21:22:14,622 INFO [train.py:763] (5/8) Epoch 8, batch 2750, loss[loss=0.1934, simple_loss=0.2766, pruned_loss=0.0551, over 7318.00 frames.], tot_loss[loss=0.201, simple_loss=0.2923, pruned_loss=0.05487, over 1423740.92 frames.], batch size: 20, lr: 8.24e-04
2022-04-28 21:23:20,620 INFO [train.py:763] (5/8) Epoch 8, batch 2800, loss[loss=0.2182, simple_loss=0.3135, pruned_loss=0.06141, over 7205.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2931, pruned_loss=0.0552, over 1426948.90 frames.], batch size: 22, lr: 8.23e-04
2022-04-28 21:24:26,776 INFO [train.py:763] (5/8) Epoch 8, batch 2850, loss[loss=0.1856, simple_loss=0.2832, pruned_loss=0.04402, over 7163.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2927, pruned_loss=0.05509, over 1429315.22 frames.], batch size: 19, lr: 8.23e-04
2022-04-28 21:25:32,047 INFO [train.py:763] (5/8) Epoch 8, batch 2900, loss[loss=0.2423, simple_loss=0.3308, pruned_loss=0.0769, over 7313.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2927, pruned_loss=0.05494, over 1428351.75 frames.], batch size: 21, lr: 8.22e-04
2022-04-28 21:26:37,473 INFO [train.py:763] (5/8) Epoch 8, batch 2950, loss[loss=0.1687, simple_loss=0.258, pruned_loss=0.0397, over 7303.00 frames.], tot_loss[loss=0.202, simple_loss=0.2931, pruned_loss=0.05544, over 1425056.39 frames.], batch size: 18, lr: 8.22e-04
2022-04-28 21:27:43,089 INFO [train.py:763] (5/8) Epoch 8, batch 3000, loss[loss=0.2264, simple_loss=0.3181, pruned_loss=0.06732, over 7312.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2919, pruned_loss=0.05516, over 1423246.56 frames.], batch size: 24, lr: 8.21e-04
2022-04-28 21:27:43,090 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 21:27:58,489 INFO [train.py:792] (5/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 21:29:04,159 INFO [train.py:763] (5/8) Epoch 8, batch 3050, loss[loss=0.2142, simple_loss=0.2972, pruned_loss=0.06556, over 7322.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2929, pruned_loss=0.0563, over 1419708.54 frames.], batch size: 20, lr: 8.21e-04
2022-04-28 21:30:09,338 INFO [train.py:763] (5/8) Epoch 8, batch 3100, loss[loss=0.2179, simple_loss=0.3196, pruned_loss=0.0581, over 6761.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2948, pruned_loss=0.05714, over 1414463.77 frames.], batch size: 31, lr: 8.20e-04
2022-04-28 21:31:14,880 INFO [train.py:763] (5/8) Epoch 8, batch 3150, loss[loss=0.207, simple_loss=0.3, pruned_loss=0.05702, over 7156.00 frames.], tot_loss[loss=0.2036, simple_loss=0.294, pruned_loss=0.05663, over 1417967.79 frames.], batch size: 19, lr: 8.20e-04
2022-04-28 21:32:20,537 INFO [train.py:763] (5/8) Epoch 8, batch 3200, loss[loss=0.1805, simple_loss=0.2824, pruned_loss=0.03927, over 7145.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2934, pruned_loss=0.056, over 1422255.56 frames.], batch size: 20, lr: 8.19e-04
2022-04-28 21:33:34,634 INFO [train.py:763] (5/8) Epoch 8, batch 3250, loss[loss=0.2306, simple_loss=0.3131, pruned_loss=0.07406, over 4953.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2938, pruned_loss=0.05642, over 1420142.90 frames.], batch size: 52, lr: 8.19e-04
2022-04-28 21:34:51,675 INFO [train.py:763] (5/8) Epoch 8, batch 3300, loss[loss=0.2076, simple_loss=0.3063, pruned_loss=0.0544, over 7193.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2928, pruned_loss=0.05596, over 1420635.33 frames.], batch size: 22, lr: 8.18e-04
2022-04-28 21:36:05,892 INFO [train.py:763] (5/8) Epoch 8, batch 3350, loss[loss=0.206, simple_loss=0.295, pruned_loss=0.05852, over 7264.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2929, pruned_loss=0.05608, over 1424018.98 frames.], batch size: 19, lr: 8.18e-04
2022-04-28 21:37:39,081 INFO [train.py:763] (5/8) Epoch 8, batch 3400, loss[loss=0.1971, simple_loss=0.3013, pruned_loss=0.04639, over 6791.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2938, pruned_loss=0.05656, over 1421601.68 frames.], batch size: 31, lr: 8.17e-04
2022-04-28 21:38:45,189 INFO [train.py:763] (5/8) Epoch 8, batch 3450, loss[loss=0.1578, simple_loss=0.2464, pruned_loss=0.0346, over 7426.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2939, pruned_loss=0.05631, over 1423764.47 frames.], batch size: 18, lr: 8.17e-04
2022-04-28 21:40:00,478 INFO [train.py:763] (5/8) Epoch 8, batch 3500, loss[loss=0.1995, simple_loss=0.2848, pruned_loss=0.0571, over 7151.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2931, pruned_loss=0.05599, over 1423878.46 frames.], batch size: 19, lr: 8.16e-04
2022-04-28 21:41:15,121 INFO [train.py:763] (5/8) Epoch 8, batch 3550, loss[loss=0.1703, simple_loss=0.2577, pruned_loss=0.0414, over 7172.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2924, pruned_loss=0.0557, over 1425890.23 frames.], batch size: 18, lr: 8.16e-04
2022-04-28 21:42:20,510 INFO [train.py:763] (5/8) Epoch 8, batch 3600, loss[loss=0.1975, simple_loss=0.2829, pruned_loss=0.05605, over 7278.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2933, pruned_loss=0.05609, over 1423997.62 frames.], batch size: 18, lr: 8.15e-04
2022-04-28 21:43:26,016 INFO [train.py:763] (5/8) Epoch 8, batch 3650, loss[loss=0.1869, simple_loss=0.2671, pruned_loss=0.0534, over 7138.00 frames.], tot_loss[loss=0.2025, simple_loss=0.293, pruned_loss=0.05596, over 1425292.41 frames.], batch size: 17, lr: 8.15e-04
2022-04-28 21:44:39,940 INFO [train.py:763] (5/8) Epoch 8, batch 3700, loss[loss=0.1858, simple_loss=0.2756, pruned_loss=0.04794, over 7282.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2929, pruned_loss=0.05539, over 1426375.02 frames.], batch size: 25, lr: 8.14e-04
2022-04-28 21:45:45,263 INFO [train.py:763] (5/8) Epoch 8, batch 3750, loss[loss=0.2059, simple_loss=0.294, pruned_loss=0.05895, over 7440.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2935, pruned_loss=0.05585, over 1425267.85 frames.], batch size: 20, lr: 8.14e-04
2022-04-28 21:46:51,553 INFO [train.py:763] (5/8) Epoch 8, batch 3800, loss[loss=0.1823, simple_loss=0.2682, pruned_loss=0.04817, over 7407.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2933, pruned_loss=0.0554, over 1426885.23 frames.], batch size: 18, lr: 8.13e-04
2022-04-28 21:47:57,465 INFO [train.py:763] (5/8) Epoch 8, batch 3850, loss[loss=0.2146, simple_loss=0.2885, pruned_loss=0.0704, over 7263.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2933, pruned_loss=0.05567, over 1429185.43 frames.], batch size: 17, lr: 8.13e-04
2022-04-28 21:49:03,320 INFO [train.py:763] (5/8) Epoch 8, batch 3900, loss[loss=0.2558, simple_loss=0.3375, pruned_loss=0.08706, over 5383.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2942, pruned_loss=0.05595, over 1427566.14 frames.], batch size: 52, lr: 8.12e-04
2022-04-28 21:50:08,724 INFO [train.py:763] (5/8) Epoch 8, batch 3950, loss[loss=0.1998, simple_loss=0.2971, pruned_loss=0.05128, over 6813.00 frames.], tot_loss[loss=0.2016, simple_loss=0.293, pruned_loss=0.05513, over 1428878.52 frames.], batch size: 31, lr: 8.12e-04
2022-04-28 21:51:14,800 INFO [train.py:763] (5/8) Epoch 8, batch 4000, loss[loss=0.1821, simple_loss=0.2782, pruned_loss=0.04301, over 7232.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2937, pruned_loss=0.05571, over 1428500.58 frames.], batch size: 21, lr: 8.11e-04
2022-04-28 21:52:21,956 INFO [train.py:763] (5/8) Epoch 8, batch 4050, loss[loss=0.1698, simple_loss=0.2656, pruned_loss=0.037, over 7396.00 frames.], tot_loss[loss=0.2008, simple_loss=0.292, pruned_loss=0.0548, over 1427411.91 frames.], batch size: 18, lr: 8.11e-04
2022-04-28 21:53:28,739 INFO [train.py:763] (5/8) Epoch 8, batch 4100, loss[loss=0.2384, simple_loss=0.297, pruned_loss=0.08995, over 7154.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2925, pruned_loss=0.05512, over 1428022.76 frames.], batch size: 17, lr: 8.10e-04
2022-04-28 21:54:34,092 INFO [train.py:763] (5/8) Epoch 8, batch 4150, loss[loss=0.2378, simple_loss=0.3385, pruned_loss=0.06852, over 7062.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2926, pruned_loss=0.05531, over 1422918.00 frames.], batch size: 28, lr: 8.10e-04
2022-04-28 21:55:39,792 INFO [train.py:763] (5/8) Epoch 8, batch 4200, loss[loss=0.18, simple_loss=0.2827, pruned_loss=0.03863, over 7322.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2909, pruned_loss=0.05485, over 1423842.38 frames.], batch size: 20, lr: 8.09e-04
2022-04-28 21:56:45,199 INFO [train.py:763] (5/8) Epoch 8, batch 4250, loss[loss=0.1808, simple_loss=0.266, pruned_loss=0.04786, over 7120.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2903, pruned_loss=0.05461, over 1419519.24 frames.], batch size: 17, lr: 8.09e-04
2022-04-28 21:57:50,935 INFO [train.py:763] (5/8) Epoch 8, batch 4300, loss[loss=0.2076, simple_loss=0.2967, pruned_loss=0.05924, over 7422.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2896, pruned_loss=0.05448, over 1416426.58 frames.], batch size: 21, lr: 8.08e-04
2022-04-28 21:58:56,625 INFO [train.py:763] (5/8) Epoch 8, batch 4350, loss[loss=0.2103, simple_loss=0.2808, pruned_loss=0.06989, over 7280.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2891, pruned_loss=0.05422, over 1422223.02 frames.], batch size: 17, lr: 8.08e-04
2022-04-28 22:00:02,326 INFO [train.py:763] (5/8) Epoch 8, batch 4400, loss[loss=0.21, simple_loss=0.3045, pruned_loss=0.05778, over 7068.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2885, pruned_loss=0.0542, over 1418618.70 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:01:09,622 INFO [train.py:763] (5/8) Epoch 8, batch 4450, loss[loss=0.1871, simple_loss=0.2868, pruned_loss=0.04374, over 7036.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2874, pruned_loss=0.05386, over 1413932.52 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:02:15,957 INFO [train.py:763] (5/8) Epoch 8, batch 4500, loss[loss=0.2143, simple_loss=0.3077, pruned_loss=0.06042, over 7044.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2888, pruned_loss=0.05471, over 1397229.12 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:03:19,883 INFO [train.py:763] (5/8) Epoch 8, batch 4550, loss[loss=0.2126, simple_loss=0.298, pruned_loss=0.06357, over 6445.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2935, pruned_loss=0.05761, over 1356932.32 frames.], batch size: 38, lr: 8.06e-04
2022-04-28 22:04:39,800 INFO [train.py:763] (5/8) Epoch 9, batch 0, loss[loss=0.1689, simple_loss=0.269, pruned_loss=0.03438, over 7420.00 frames.], tot_loss[loss=0.1689, simple_loss=0.269, pruned_loss=0.03438, over 7420.00 frames.], batch size: 21, lr: 7.75e-04
2022-04-28 22:05:45,915 INFO [train.py:763] (5/8) Epoch 9, batch 50, loss[loss=0.2141, simple_loss=0.3093, pruned_loss=0.05948, over 7234.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2927, pruned_loss=0.05574, over 321451.96 frames.], batch size: 23, lr: 7.74e-04
2022-04-28 22:06:51,606 INFO [train.py:763] (5/8) Epoch 9, batch 100, loss[loss=0.2324, simple_loss=0.315, pruned_loss=0.07488, over 4669.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2903, pruned_loss=0.0548, over 556955.02 frames.], batch size: 52, lr: 7.74e-04
2022-04-28 22:07:57,283 INFO [train.py:763] (5/8) Epoch 9, batch 150, loss[loss=0.1985, simple_loss=0.2879, pruned_loss=0.05459, over 7430.00 frames.], tot_loss[loss=0.198, simple_loss=0.2893, pruned_loss=0.05334, over 751043.89 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:09:03,723 INFO [train.py:763] (5/8) Epoch 9, batch 200, loss[loss=0.2002, simple_loss=0.298, pruned_loss=0.05117, over 7432.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2891, pruned_loss=0.05281, over 898198.72 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:10:10,402 INFO [train.py:763] (5/8) Epoch 9, batch 250, loss[loss=0.1834, simple_loss=0.2785, pruned_loss=0.04414, over 7163.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2911, pruned_loss=0.05385, over 1010392.88 frames.], batch size: 18, lr: 7.72e-04
2022-04-28 22:11:16,232 INFO [train.py:763] (5/8) Epoch 9, batch 300, loss[loss=0.155, simple_loss=0.2525, pruned_loss=0.02879, over 7329.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2908, pruned_loss=0.05395, over 1104368.38 frames.], batch size: 20, lr: 7.72e-04
2022-04-28 22:12:21,613 INFO [train.py:763] (5/8) Epoch 9, batch 350, loss[loss=0.1998, simple_loss=0.3094, pruned_loss=0.04513, over 7197.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2903, pruned_loss=0.05315, over 1173290.06 frames.], batch size: 23, lr: 7.71e-04
2022-04-28 22:13:26,948 INFO [train.py:763] (5/8) Epoch 9, batch 400, loss[loss=0.2108, simple_loss=0.3077, pruned_loss=0.05693, over 7176.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2919, pruned_loss=0.05378, over 1223193.14 frames.], batch size: 26, lr: 7.71e-04
2022-04-28 22:14:32,129 INFO [train.py:763] (5/8) Epoch 9, batch 450, loss[loss=0.2146, simple_loss=0.2988, pruned_loss=0.06515, over 6257.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2922, pruned_loss=0.05385, over 1261722.40 frames.], batch size: 37, lr: 7.71e-04
2022-04-28 22:15:37,760 INFO [train.py:763] (5/8) Epoch 9, batch 500, loss[loss=0.2057, simple_loss=0.3023, pruned_loss=0.05456, over 7158.00 frames.], tot_loss[loss=0.1999, simple_loss=0.292, pruned_loss=0.05389, over 1297047.67 frames.], batch size: 19, lr: 7.70e-04
2022-04-28 22:16:43,434 INFO [train.py:763] (5/8) Epoch 9, batch 550, loss[loss=0.1613, simple_loss=0.2513, pruned_loss=0.03567, over 7134.00 frames.], tot_loss[loss=0.1998, simple_loss=0.292, pruned_loss=0.05384, over 1325509.23 frames.], batch size: 17, lr: 7.70e-04
2022-04-28 22:17:49,467 INFO [train.py:763] (5/8) Epoch 9, batch 600, loss[loss=0.1817, simple_loss=0.2633, pruned_loss=0.05004, over 7270.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2921, pruned_loss=0.05414, over 1347221.94 frames.], batch size: 18, lr: 7.69e-04
2022-04-28 22:18:54,916 INFO [train.py:763] (5/8) Epoch 9, batch 650, loss[loss=0.211, simple_loss=0.2987, pruned_loss=0.06162, over 7143.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2922, pruned_loss=0.05439, over 1363688.33 frames.], batch size: 26, lr: 7.69e-04
2022-04-28 22:20:00,527 INFO [train.py:763] (5/8) Epoch 9, batch 700, loss[loss=0.2196, simple_loss=0.3101, pruned_loss=0.06456, over 7255.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2917, pruned_loss=0.05409, over 1377416.37 frames.], batch size: 25, lr: 7.68e-04
2022-04-28 22:21:06,845 INFO [train.py:763] (5/8) Epoch 9, batch 750, loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05592, over 7431.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2919, pruned_loss=0.05431, over 1387402.73 frames.], batch size: 20, lr: 7.68e-04
2022-04-28 22:22:12,202 INFO [train.py:763] (5/8) Epoch 9, batch 800, loss[loss=0.2005, simple_loss=0.2982, pruned_loss=0.05139, over 7259.00 frames.], tot_loss[loss=0.2, simple_loss=0.2915, pruned_loss=0.05428, over 1394684.72 frames.], batch size: 24, lr: 7.67e-04
2022-04-28 22:23:17,416 INFO [train.py:763] (5/8) Epoch 9, batch 850, loss[loss=0.2354, simple_loss=0.3163, pruned_loss=0.07721, over 6503.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2915, pruned_loss=0.05462, over 1396900.47 frames.], batch size: 38, lr: 7.67e-04
2022-04-28 22:24:22,802 INFO [train.py:763] (5/8) Epoch 9, batch 900, loss[loss=0.1813, simple_loss=0.2823, pruned_loss=0.04016, over 7317.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2918, pruned_loss=0.05442, over 1406504.75 frames.], batch size: 21, lr: 7.66e-04
2022-04-28 22:25:27,957 INFO [train.py:763] (5/8) Epoch 9, batch 950, loss[loss=0.1994, simple_loss=0.2933, pruned_loss=0.05276, over 7144.00 frames.], tot_loss[loss=0.2003, simple_loss=0.292, pruned_loss=0.05431, over 1406208.46 frames.], batch size: 26, lr: 7.66e-04
2022-04-28 22:26:34,002 INFO [train.py:763] (5/8) Epoch 9, batch 1000, loss[loss=0.1747, simple_loss=0.2632, pruned_loss=0.04309, over 7336.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2908, pruned_loss=0.05336, over 1413787.04 frames.], batch size: 20, lr: 7.66e-04
2022-04-28 22:27:40,366 INFO [train.py:763] (5/8) Epoch 9, batch 1050, loss[loss=0.2022, simple_loss=0.3017, pruned_loss=0.05138, over 7025.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2908, pruned_loss=0.05318, over 1417042.12 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:28:46,009 INFO [train.py:763] (5/8) Epoch 9, batch 1100, loss[loss=0.206, simple_loss=0.3046, pruned_loss=0.05374, over 7008.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2918, pruned_loss=0.05402, over 1418483.49 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:29:52,333 INFO [train.py:763] (5/8) Epoch 9, batch 1150, loss[loss=0.1673, simple_loss=0.2743, pruned_loss=0.03018, over 7339.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2916, pruned_loss=0.05368, over 1422343.91 frames.], batch size: 20, lr: 7.64e-04
2022-04-28 22:30:57,649 INFO [train.py:763] (5/8) Epoch 9, batch 1200, loss[loss=0.2168, simple_loss=0.3072, pruned_loss=0.06321, over 7211.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2918, pruned_loss=0.05354, over 1421191.96 frames.], batch size: 23, lr: 7.64e-04
2022-04-28 22:32:04,407 INFO [train.py:763] (5/8) Epoch 9, batch 1250, loss[loss=0.1868, simple_loss=0.2712, pruned_loss=0.05124, over 7283.00 frames.], tot_loss[loss=0.2, simple_loss=0.2923, pruned_loss=0.05385, over 1419139.84 frames.], batch size: 17, lr: 7.63e-04
2022-04-28 22:33:11,159 INFO [train.py:763] (5/8) Epoch 9, batch 1300, loss[loss=0.1642, simple_loss=0.2435, pruned_loss=0.04245, over 6997.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2905, pruned_loss=0.05336, over 1416103.86 frames.], batch size: 16, lr: 7.63e-04
2022-04-28 22:34:16,575 INFO [train.py:763] (5/8) Epoch 9, batch 1350, loss[loss=0.2069, simple_loss=0.3043, pruned_loss=0.05479, over 7319.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2911, pruned_loss=0.0541, over 1416081.46 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:35:21,686 INFO [train.py:763] (5/8) Epoch 9, batch 1400, loss[loss=0.1951, simple_loss=0.301, pruned_loss=0.04458, over 7128.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2931, pruned_loss=0.0549, over 1419022.54 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:36:27,463 INFO [train.py:763] (5/8) Epoch 9, batch 1450, loss[loss=0.2142, simple_loss=0.3028, pruned_loss=0.06285, over 7317.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2915, pruned_loss=0.05421, over 1420563.87 frames.], batch size: 25, lr: 7.62e-04
2022-04-28 22:37:33,364 INFO [train.py:763] (5/8) Epoch 9, batch 1500, loss[loss=0.222, simple_loss=0.3138, pruned_loss=0.06505, over 5189.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2919, pruned_loss=0.05385, over 1417273.02 frames.], batch size: 53, lr: 7.61e-04
2022-04-28 22:38:38,712 INFO [train.py:763] (5/8) Epoch 9, batch 1550, loss[loss=0.1761, simple_loss=0.2798, pruned_loss=0.03622, over 7353.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2916, pruned_loss=0.05331, over 1421243.99 frames.], batch size: 19, lr: 7.61e-04
2022-04-28 22:39:43,992 INFO [train.py:763] (5/8) Epoch 9, batch 1600, loss[loss=0.1858, simple_loss=0.2813, pruned_loss=0.04518, over 7259.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2919, pruned_loss=0.05347, over 1419919.38 frames.], batch size: 19, lr: 7.60e-04
2022-04-28 22:40:50,100 INFO [train.py:763] (5/8) Epoch 9, batch 1650, loss[loss=0.1683, simple_loss=0.265, pruned_loss=0.03583, over 7413.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2908, pruned_loss=0.05314, over 1417857.07 frames.], batch size: 21, lr: 7.60e-04
2022-04-28 22:41:56,345 INFO [train.py:763] (5/8) Epoch 9, batch 1700, loss[loss=0.2568, simple_loss=0.3421, pruned_loss=0.08578, over 7295.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2907, pruned_loss=0.05327, over 1415369.63 frames.], batch size: 24, lr: 7.59e-04
2022-04-28 22:43:01,522 INFO [train.py:763] (5/8) Epoch 9, batch 1750, loss[loss=0.2148, simple_loss=0.2807, pruned_loss=0.07444, over 6822.00 frames.], tot_loss[loss=0.2, simple_loss=0.2918, pruned_loss=0.05408, over 1406609.81 frames.], batch size: 15, lr: 7.59e-04
2022-04-28 22:44:07,090 INFO [train.py:763] (5/8) Epoch 9, batch 1800, loss[loss=0.181, simple_loss=0.2792, pruned_loss=0.0414, over 7369.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2911, pruned_loss=0.05393, over 1410700.18 frames.], batch size: 19, lr: 7.59e-04
2022-04-28 22:45:14,107 INFO [train.py:763] (5/8) Epoch 9, batch 1850, loss[loss=0.1778, simple_loss=0.261, pruned_loss=0.04728, over 7360.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2919, pruned_loss=0.05451, over 1411891.89 frames.], batch size: 19, lr: 7.58e-04
2022-04-28 22:46:21,657 INFO [train.py:763] (5/8) Epoch 9, batch 1900, loss[loss=0.1913, simple_loss=0.2824, pruned_loss=0.05009, over 7269.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2904, pruned_loss=0.05376, over 1416739.19 frames.], batch size: 18, lr: 7.58e-04
2022-04-28 22:47:28,657 INFO [train.py:763] (5/8) Epoch 9, batch 1950, loss[loss=0.2291, simple_loss=0.3172, pruned_loss=0.07049, over 7200.00 frames.], tot_loss[loss=0.1986, simple_loss=0.29, pruned_loss=0.05355, over 1416095.03 frames.], batch size: 23, lr: 7.57e-04
2022-04-28 22:48:34,059 INFO [train.py:763] (5/8) Epoch 9, batch 2000, loss[loss=0.1957, simple_loss=0.2938, pruned_loss=0.04881, over 7237.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2897, pruned_loss=0.05321, over 1419113.69 frames.], batch size: 20, lr: 7.57e-04
2022-04-28 22:49:39,703 INFO [train.py:763] (5/8) Epoch 9, batch 2050, loss[loss=0.2103, simple_loss=0.3025, pruned_loss=0.05905, over 7220.00 frames.], tot_loss[loss=0.198, simple_loss=0.2895, pruned_loss=0.05327, over 1420760.12 frames.], batch size: 23, lr: 7.56e-04
2022-04-28 22:50:45,171 INFO [train.py:763] (5/8) Epoch 9, batch 2100, loss[loss=0.2439, simple_loss=0.3406, pruned_loss=0.07363, over 7150.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2901, pruned_loss=0.05368, over 1424971.70 frames.], batch size: 20, lr: 7.56e-04
2022-04-28 22:51:50,840 INFO [train.py:763] (5/8) Epoch 9, batch 2150, loss[loss=0.1654, simple_loss=0.2553, pruned_loss=0.03775, over 7413.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2887, pruned_loss=0.05311, over 1426711.65 frames.], batch size: 18, lr: 7.56e-04
2022-04-28 22:52:56,061 INFO [train.py:763] (5/8) Epoch 9, batch 2200, loss[loss=0.2157, simple_loss=0.3093, pruned_loss=0.06101, over 6421.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2893, pruned_loss=0.0532, over 1427185.15 frames.], batch size: 38, lr: 7.55e-04
2022-04-28 22:54:01,590 INFO [train.py:763] (5/8) Epoch 9, batch 2250, loss[loss=0.1904, simple_loss=0.2795, pruned_loss=0.0506, over 7318.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2896, pruned_loss=0.05371, over 1429453.04 frames.], batch size: 21, lr: 7.55e-04
2022-04-28 22:55:07,222 INFO [train.py:763] (5/8) Epoch 9, batch 2300, loss[loss=0.1945, simple_loss=0.2939, pruned_loss=0.04752, over 7157.00 frames.], tot_loss[loss=0.199, simple_loss=0.2904, pruned_loss=0.05382, over 1426468.74 frames.], batch size: 20, lr: 7.54e-04
2022-04-28 22:56:13,150 INFO [train.py:763] (5/8) Epoch 9, batch 2350, loss[loss=0.2256, simple_loss=0.3157, pruned_loss=0.0677, over 7214.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2901, pruned_loss=0.05381, over 1424427.79 frames.], batch size: 22, lr: 7.54e-04
2022-04-28 22:57:18,406 INFO [train.py:763] (5/8) Epoch 9, batch 2400, loss[loss=0.1922, simple_loss=0.28, pruned_loss=0.05221, over 7282.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2893, pruned_loss=0.05307, over 1426820.83 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:58:24,898 INFO [train.py:763] (5/8) Epoch 9, batch 2450, loss[loss=0.2062, simple_loss=0.2909, pruned_loss=0.06074, over 7073.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2887, pruned_loss=0.05306, over 1430094.79 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:59:30,591 INFO [train.py:763] (5/8) Epoch 9, batch 2500, loss[loss=0.2011, simple_loss=0.2931, pruned_loss=0.05456, over 7310.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2895, pruned_loss=0.05358, over 1428556.05 frames.], batch size: 21, lr: 7.53e-04
2022-04-28 23:00:35,853 INFO [train.py:763] (5/8) Epoch 9, batch 2550, loss[loss=0.1865, simple_loss=0.2877, pruned_loss=0.04266, over 7207.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2898, pruned_loss=0.05358, over 1425842.29 frames.], batch size: 21, lr: 7.52e-04
2022-04-28 23:01:42,065 INFO [train.py:763] (5/8) Epoch 9, batch 2600, loss[loss=0.2606, simple_loss=0.3482, pruned_loss=0.08654, over 7137.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2906, pruned_loss=0.05413, over 1428494.93 frames.], batch size: 26, lr: 7.52e-04
2022-04-28 23:02:47,162 INFO [train.py:763] (5/8) Epoch 9, batch 2650, loss[loss=0.1937, simple_loss=0.2915, pruned_loss=0.048, over 7352.00 frames.], tot_loss[loss=0.199, simple_loss=0.2905, pruned_loss=0.05373, over 1425320.11 frames.], batch size: 22, lr: 7.51e-04
2022-04-28 23:03:53,486 INFO [train.py:763] (5/8) Epoch 9, batch 2700, loss[loss=0.2139, simple_loss=0.3019, pruned_loss=0.06299, over 6780.00 frames.], tot_loss[loss=0.198, simple_loss=0.2896, pruned_loss=0.05324, over 1426894.84 frames.], batch size: 31, lr: 7.51e-04
2022-04-28 23:04:58,887 INFO [train.py:763] (5/8) Epoch 9, batch 2750, loss[loss=0.1788, simple_loss=0.2847, pruned_loss=0.03646, over 6805.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2894, pruned_loss=0.0532, over 1424112.43 frames.], batch size: 31, lr: 7.50e-04
2022-04-28 23:06:04,508 INFO [train.py:763] (5/8) Epoch 9, batch 2800, loss[loss=0.2252, simple_loss=0.3078, pruned_loss=0.07131, over 7377.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2894, pruned_loss=0.05354, over 1429474.31 frames.], batch size: 23, lr: 7.50e-04
2022-04-28 23:07:09,874 INFO [train.py:763] (5/8) Epoch 9, batch 2850, loss[loss=0.1936, simple_loss=0.2902, pruned_loss=0.04845, over 7346.00 frames.], tot_loss[loss=0.1978, simple_loss=0.289, pruned_loss=0.05328, over 1427439.50 frames.], batch size: 22, lr: 7.50e-04
2022-04-28 23:08:15,558 INFO [train.py:763] (5/8) Epoch 9, batch 2900, loss[loss=0.2016, simple_loss=0.3013, pruned_loss=0.05091, over 7121.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2894, pruned_loss=0.05313, over 1426362.68 frames.], batch size: 21, lr: 7.49e-04
2022-04-28 23:09:22,019 INFO [train.py:763] (5/8) Epoch 9, batch 2950, loss[loss=0.1681, simple_loss=0.2611, pruned_loss=0.03758, over 7300.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2893, pruned_loss=0.05319, over 1425740.55 frames.], batch size: 18, lr: 7.49e-04
2022-04-28 23:10:28,994 INFO [train.py:763] (5/8) Epoch 9, batch 3000, loss[loss=0.1397, simple_loss=0.226, pruned_loss=0.02671, over 7277.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2889, pruned_loss=0.05313, over 1425858.87 frames.], batch size: 17, lr: 7.48e-04
2022-04-28 23:10:28,995 INFO [train.py:783] (5/8) Computing validation loss
2022-04-28 23:10:44,551 INFO [train.py:792] (5/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 23:11:50,381 INFO [train.py:763] (5/8) Epoch 9, batch 3050, loss[loss=0.1796, simple_loss=0.2769, pruned_loss=0.04118, over 7165.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2887, pruned_loss=0.05286, over 1426033.90 frames.], batch size: 19, lr: 7.48e-04
2022-04-28 23:12:55,858 INFO [train.py:763] (5/8) Epoch 9, batch 3100, loss[loss=0.1869, simple_loss=0.2803, pruned_loss=0.04672, over 7123.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2886, pruned_loss=0.05232, over 1429212.30 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:14:01,352 INFO [train.py:763] (5/8) Epoch 9, batch 3150, loss[loss=0.2373, simple_loss=0.3196, pruned_loss=0.0775, over 7313.00 frames.], tot_loss[loss=0.197, simple_loss=0.2884, pruned_loss=0.05278, over 1425577.96 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:15:07,619 INFO [train.py:763] (5/8) Epoch 9, batch 3200, loss[loss=0.1731, simple_loss=0.2684, pruned_loss=0.0389, over 7242.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2864, pruned_loss=0.05166, over 1425962.70 frames.], batch size: 20, lr: 7.47e-04
2022-04-28 23:16:13,890 INFO [train.py:763] (5/8) Epoch 9, batch 3250, loss[loss=0.1922, simple_loss=0.2946, pruned_loss=0.04491, over 7419.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2879, pruned_loss=0.05232, over 1426619.61 frames.], batch size: 21, lr: 7.46e-04
2022-04-28 23:17:19,394 INFO [train.py:763] (5/8) Epoch 9, batch 3300, loss[loss=0.2282, simple_loss=0.3161, pruned_loss=0.07021, over 7216.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2877, pruned_loss=0.05221, over 1427545.29 frames.], batch size: 22, lr: 7.46e-04
2022-04-28 23:18:25,195 INFO [train.py:763] (5/8) Epoch 9, batch 3350, loss[loss=0.2058, simple_loss=0.3008, pruned_loss=0.05544, over 7207.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2884, pruned_loss=0.05236, over 1428644.17 frames.], batch size: 23, lr: 7.45e-04
2022-04-28 23:19:31,233 INFO [train.py:763] (5/8) Epoch 9, batch 3400, loss[loss=0.1831, simple_loss=0.2599, pruned_loss=0.05316, over 7281.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2879, pruned_loss=0.05222, over 1425165.08 frames.], batch size: 17, lr: 7.45e-04
2022-04-28 23:20:36,545 INFO [train.py:763] (5/8) Epoch 9, batch 3450, loss[loss=0.2143, simple_loss=0.3111, pruned_loss=0.0588, over 7291.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2881, pruned_loss=0.05215, over 1424458.80 frames.], batch size: 24, lr: 7.45e-04
2022-04-28 23:21:42,134 INFO [train.py:763] (5/8) Epoch 9, batch 3500, loss[loss=0.2107, simple_loss=0.3148, pruned_loss=0.05331, over 7414.00 frames.], tot_loss[loss=0.1968, simple_loss=0.289, pruned_loss=0.05234, over 1424417.62 frames.], batch size: 21, lr: 7.44e-04
2022-04-28 23:22:49,856 INFO [train.py:763] (5/8) Epoch 9, batch 3550, loss[loss=0.2037, simple_loss=0.2969, pruned_loss=0.05523, over 7111.00 frames.], tot_loss[loss=0.1957, simple_loss=0.288, pruned_loss=0.05171, over 1427397.89 frames.], batch size: 28, lr: 7.44e-04
2022-04-28 23:23:55,523 INFO [train.py:763] (5/8) Epoch 9, batch 3600, loss[loss=0.1812, simple_loss=0.2815, pruned_loss=0.0404, over 7038.00 frames.], tot_loss[loss=0.1956, simple_loss=0.288, pruned_loss=0.05157, over 1427498.92 frames.], batch size: 28, lr: 7.43e-04
2022-04-28 23:25:02,076 INFO [train.py:763] (5/8) Epoch 9, batch 3650, loss[loss=0.1905, simple_loss=0.2794, pruned_loss=0.05081, over 7075.00 frames.], tot_loss[loss=0.1965, simple_loss=0.289, pruned_loss=0.05202, over 1423545.01 frames.], batch size: 18, lr: 7.43e-04
2022-04-28 23:26:07,310 INFO [train.py:763] (5/8) Epoch 9, batch 3700, loss[loss=0.1797, simple_loss=0.2682, pruned_loss=0.0456, over 7279.00 frames.], tot_loss[loss=0.197, simple_loss=0.2894, pruned_loss=0.05228, over 1425360.83 frames.], batch size: 17, lr: 7.43e-04
2022-04-28 23:27:12,608 INFO [train.py:763] (5/8) Epoch 9, batch 3750, loss[loss=0.1935, simple_loss=0.2803, pruned_loss=0.05335, over 7142.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2898, pruned_loss=0.05237, over 1428091.54 frames.], batch size: 19, lr: 7.42e-04
2022-04-28 23:28:17,831 INFO [train.py:763] (5/8) Epoch 9, batch 3800, loss[loss=0.1714, simple_loss=0.2656, pruned_loss=0.03864, over 7441.00 frames.], tot_loss[loss=0.1979, simple_loss=0.29, pruned_loss=0.05295, over 1425591.99 frames.], batch size: 20, lr: 7.42e-04
2022-04-28 23:29:23,013 INFO [train.py:763] (5/8) Epoch 9, batch 3850, loss[loss=0.2054, simple_loss=0.2897, pruned_loss=0.06057, over 7067.00 frames.], tot_loss[loss=0.1989, simple_loss=0.291, pruned_loss=0.0534, over 1425195.16 frames.], batch size: 18, lr: 7.41e-04
2022-04-28 23:30:28,556 INFO [train.py:763] (5/8) Epoch 9, batch 3900, loss[loss=0.1815, simple_loss=0.2681, pruned_loss=0.04741, over 7167.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2899, pruned_loss=0.05264, over 1426857.65 frames.], batch size: 19, lr: 7.41e-04
2022-04-28 23:31:35,180 INFO [train.py:763] (5/8) Epoch 9, batch 3950, loss[loss=0.2395, simple_loss=0.3158, pruned_loss=0.08154, over 5273.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2896, pruned_loss=0.05251, over 1421306.37 frames.], batch size: 52, lr: 7.41e-04
2022-04-28 23:32:42,035 INFO [train.py:763] (5/8) Epoch 9, batch 4000, loss[loss=0.1821, simple_loss=0.2711, pruned_loss=0.04656, over 7257.00 frames.], tot_loss[loss=0.198, simple_loss=0.2899, pruned_loss=0.05302, over 1421748.06 frames.], batch size: 19, lr: 7.40e-04
2022-04-28 23:33:47,291 INFO [train.py:763] (5/8) Epoch 9, batch 4050, loss[loss=0.1648, simple_loss=0.2476, pruned_loss=0.041, over 7131.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2893, pruned_loss=0.05287, over 1422389.44 frames.], batch size: 17, lr: 7.40e-04
2022-04-28 23:34:53,530 INFO [train.py:763] (5/8) Epoch 9, batch 4100, loss[loss=0.1839, simple_loss=0.277, pruned_loss=0.04544, over 7330.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2892, pruned_loss=0.05262, over 1424914.41 frames.], batch size: 21, lr: 7.39e-04
2022-04-28 23:35:59,484 INFO [train.py:763] (5/8) Epoch 9, batch 4150, loss[loss=0.1934, simple_loss=0.272, pruned_loss=0.05742, over 7408.00 frames.], tot_loss[loss=0.197, simple_loss=0.2892, pruned_loss=0.05242, over 1424963.65 frames.], batch size: 18, lr: 7.39e-04
2022-04-28 23:37:04,702 INFO [train.py:763] (5/8) Epoch 9, batch 4200, loss[loss=0.1946, simple_loss=0.2844, pruned_loss=0.05235, over 7278.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2891, pruned_loss=0.05209, over 1426793.48 frames.], batch size: 24, lr: 7.39e-04
2022-04-28 23:38:10,558 INFO [train.py:763] (5/8) Epoch 9, batch 4250, loss[loss=0.173, simple_loss=0.2617, pruned_loss=0.04214, over 7287.00 frames.], tot_loss[loss=0.198, simple_loss=0.2903, pruned_loss=0.05288, over 1422588.70 frames.], batch size: 17, lr: 7.38e-04
2022-04-28 23:39:16,468 INFO [train.py:763] (5/8) Epoch 9, batch 4300, loss[loss=0.1867, simple_loss=0.2949, pruned_loss=0.03921, over 7313.00 frames.], tot_loss[loss=0.1986, simple_loss=0.291, pruned_loss=0.0531, over 1417464.20 frames.], batch size: 24, lr: 7.38e-04
2022-04-28 23:40:22,456 INFO [train.py:763] (5/8) Epoch 9, batch 4350, loss[loss=0.2408, simple_loss=0.3295, pruned_loss=0.07608, over 4968.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2925, pruned_loss=0.05362, over 1407209.68 frames.], batch size: 54, lr: 7.37e-04
2022-04-28 23:41:28,516 INFO [train.py:763] (5/8) Epoch 9, batch 4400, loss[loss=0.2056, simple_loss=0.2982, pruned_loss=0.05651, over 7205.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2929, pruned_loss=0.05395, over 1410153.03 frames.], batch size: 22, lr: 7.37e-04
2022-04-28 23:42:35,264 INFO [train.py:763] (5/8) Epoch 9, batch 4450, loss[loss=0.2354, simple_loss=0.3184, pruned_loss=0.07622, over 4531.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2935, pruned_loss=0.05449, over 1395247.33 frames.], batch size: 52, lr: 7.37e-04
2022-04-28 23:43:41,396 INFO [train.py:763] (5/8) Epoch 9, batch 4500, loss[loss=0.2263, simple_loss=0.3239, pruned_loss=0.06431, over 7145.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2927, pruned_loss=0.05458, over 1392058.08 frames.], batch size: 20, lr: 7.36e-04
2022-04-28 23:44:48,037 INFO [train.py:763] (5/8) Epoch 9, batch 4550, loss[loss=0.2229, simple_loss=0.3114, pruned_loss=0.06723, over 7175.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2923, pruned_loss=0.05524, over 1372424.69 frames.], batch size: 26, lr: 7.36e-04
2022-04-28 23:46:26,287 INFO [train.py:763] (5/8) Epoch 10, batch 0, loss[loss=0.1978, simple_loss=0.281, pruned_loss=0.05727, over 7432.00 frames.], tot_loss[loss=0.1978, simple_loss=0.281, pruned_loss=0.05727, over 7432.00 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:47:32,328 INFO [train.py:763] (5/8) Epoch 10, batch 50, loss[loss=0.1614, simple_loss=0.2533, pruned_loss=0.03476, over 7438.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2885, pruned_loss=0.0489, over 322211.17 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:48:38,937 INFO [train.py:763] (5/8) Epoch 10, batch 100, loss[loss=0.1696, simple_loss=0.2587, pruned_loss=0.04027, over 7279.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2872, pruned_loss=0.04992, over 566285.89 frames.], batch size: 18, lr: 7.08e-04
2022-04-28 23:49:55,137 INFO [train.py:763] (5/8) Epoch 10, batch 150, loss[loss=0.1858, simple_loss=0.2721, pruned_loss=0.04977, over 6816.00 frames.], tot_loss[loss=0.195, simple_loss=0.2891, pruned_loss=0.0505, over 759293.75 frames.], batch size: 15, lr: 7.07e-04
2022-04-28 23:51:18,550 INFO [train.py:763] (5/8) Epoch 10, batch 200, loss[loss=0.1614, simple_loss=0.2577, pruned_loss=0.03261, over 7403.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2875, pruned_loss=0.04964, over 907326.76 frames.], batch size: 18, lr: 7.07e-04
2022-04-28 23:52:32,866 INFO [train.py:763] (5/8) Epoch 10, batch 250, loss[loss=0.237, simple_loss=0.3221, pruned_loss=0.076, over 6424.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2875, pruned_loss=0.0504, over 1022683.39 frames.], batch size: 37, lr: 7.06e-04
2022-04-28 23:53:48,230 INFO [train.py:763] (5/8) Epoch 10, batch 300, loss[loss=0.2148, simple_loss=0.2982, pruned_loss=0.06573, over 5041.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2866, pruned_loss=0.05021, over 1114362.81 frames.], batch size: 52, lr: 7.06e-04
2022-04-28 23:54:53,620 INFO [train.py:763] (5/8) Epoch 10, batch 350, loss[loss=0.1989, simple_loss=0.3005, pruned_loss=0.04861, over 6668.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2866, pruned_loss=0.05017, over 1186592.32 frames.], batch size: 31, lr: 7.06e-04
2022-04-28 23:56:17,504 INFO [train.py:763] (5/8) Epoch 10, batch 400, loss[loss=0.1878, simple_loss=0.2666, pruned_loss=0.0545, over 7415.00 frames.], tot_loss[loss=0.1925, simple_loss=0.286, pruned_loss=0.04953, over 1240760.78 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:57:23,255 INFO [train.py:763] (5/8) Epoch 10, batch 450, loss[loss=0.1967, simple_loss=0.2947, pruned_loss=0.04932, over 7231.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2843, pruned_loss=0.04894, over 1280348.42 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:58:37,641 INFO [train.py:763] (5/8) Epoch 10, batch 500, loss[loss=0.2021, simple_loss=0.3038, pruned_loss=0.05016, over 7317.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2848, pruned_loss=0.04921, over 1315439.40 frames.], batch size: 20, lr: 7.04e-04
2022-04-28 23:59:42,727 INFO [train.py:763] (5/8) Epoch 10, batch 550, loss[loss=0.1976, simple_loss=0.2848, pruned_loss=0.05515, over 7067.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2856, pruned_loss=0.04933, over 1341127.37 frames.], batch size: 18, lr: 7.04e-04
2022-04-29 00:00:47,815 INFO [train.py:763] (5/8) Epoch 10, batch 600, loss[loss=0.1734, simple_loss=0.253, pruned_loss=0.04692, over 7015.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2862, pruned_loss=0.04963, over 1359954.83 frames.], batch size: 16, lr: 7.04e-04
2022-04-29 00:01:53,011 INFO [train.py:763] (5/8) Epoch 10, batch 650, loss[loss=0.1837, simple_loss=0.2712, pruned_loss=0.04814, over 7131.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2873, pruned_loss=0.05072, over 1366079.78 frames.], batch size: 17, lr: 7.03e-04
2022-04-29 00:02:58,040 INFO [train.py:763] (5/8) Epoch 10, batch 700, loss[loss=0.1773, simple_loss=0.2593, pruned_loss=0.04763, over 7243.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2886, pruned_loss=0.05141, over 1376150.64 frames.], batch size: 16, lr: 7.03e-04
2022-04-29 00:04:03,198 INFO [train.py:763] (5/8) Epoch 10, batch 750, loss[loss=0.196, simple_loss=0.3032, pruned_loss=0.04443, over 7147.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2883, pruned_loss=0.05145, over 1382875.26 frames.], batch size: 20, lr: 7.03e-04
2022-04-29 00:05:08,476 INFO [train.py:763] (5/8) Epoch 10, batch 800, loss[loss=0.2185, simple_loss=0.3224, pruned_loss=0.05733, over 7179.00 frames.], tot_loss[loss=0.195, simple_loss=0.288, pruned_loss=0.05103, over 1394522.20 frames.], batch size: 26, lr: 7.02e-04
2022-04-29 00:06:13,828 INFO [train.py:763] (5/8) Epoch 10, batch 850, loss[loss=0.1755, simple_loss=0.2707, pruned_loss=0.04011, over 7323.00 frames.], tot_loss[loss=0.1949, simple_loss=0.288, pruned_loss=0.05092, over 1399247.09 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:07:19,245 INFO [train.py:763] (5/8) Epoch 10, batch 900, loss[loss=0.1861, simple_loss=0.2828, pruned_loss=0.04471, over 7433.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2877, pruned_loss=0.05096, over 1407740.89 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:08:24,543 INFO [train.py:763] (5/8) Epoch 10, batch 950, loss[loss=0.1682, simple_loss=0.2599, pruned_loss=0.03829, over 6997.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2875, pruned_loss=0.05101, over 1409647.59 frames.], batch size: 16, lr: 7.01e-04
2022-04-29 00:09:29,923 INFO [train.py:763] (5/8) Epoch 10, batch 1000, loss[loss=0.2025, simple_loss=0.3081, pruned_loss=0.04848, over 7329.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2871, pruned_loss=0.05099, over 1414001.97 frames.], batch size: 25, lr: 7.01e-04
2022-04-29 00:10:35,521 INFO [train.py:763] (5/8) Epoch 10, batch 1050, loss[loss=0.1836, simple_loss=0.27, pruned_loss=0.04861, over 7259.00 frames.], tot_loss[loss=0.1961, simple_loss=0.289, pruned_loss=0.05165, over 1409345.92 frames.], batch size: 19, lr: 7.00e-04
2022-04-29 00:11:41,114 INFO [train.py:763] (5/8) Epoch 10, batch 1100, loss[loss=0.19, simple_loss=0.272, pruned_loss=0.05402, over 7168.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2881, pruned_loss=0.05143, over 1414198.85 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:12:46,627 INFO [train.py:763] (5/8) Epoch 10, batch 1150, loss[loss=0.196, simple_loss=0.286, pruned_loss=0.05302, over 7068.00 frames.], tot_loss[loss=0.1944, simple_loss=0.287, pruned_loss=0.05087, over 1417767.20 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:13:53,263 INFO [train.py:763] (5/8) Epoch 10, batch 1200, loss[loss=0.1766, simple_loss=0.2616, pruned_loss=0.04581, over 7235.00 frames.], tot_loss[loss=0.1934, simple_loss=0.286, pruned_loss=0.05045, over 1420492.88 frames.], batch size: 16, lr: 6.99e-04
2022-04-29 00:14:59,022 INFO [train.py:763] (5/8) Epoch 10, batch 1250, loss[loss=0.159, simple_loss=0.2401, pruned_loss=0.03892, over 7125.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2859, pruned_loss=0.05022, over 1424864.21 frames.], batch size: 17, lr: 6.99e-04
2022-04-29 00:16:04,767 INFO [train.py:763] (5/8) Epoch 10, batch 1300, loss[loss=0.2056, simple_loss=0.3005, pruned_loss=0.05533, over 7322.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2856, pruned_loss=0.05044, over 1420651.60 frames.], batch size: 21, lr: 6.99e-04
2022-04-29 00:17:11,809 INFO [train.py:763] (5/8) Epoch 10, batch 1350, loss[loss=0.1978, simple_loss=0.2956, pruned_loss=0.04997, over 7328.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2867, pruned_loss=0.0511, over 1424435.17 frames.], batch size: 21, lr: 6.98e-04
2022-04-29 00:18:18,358 INFO [train.py:763] (5/8) Epoch 10, batch 1400, loss[loss=0.1854, simple_loss=0.2784, pruned_loss=0.04624, over 7162.00 frames.], tot_loss[loss=0.1946, simple_loss=0.287, pruned_loss=0.05108, over 1427676.74 frames.], batch size: 19, lr: 6.98e-04
2022-04-29 00:19:25,287 INFO [train.py:763] (5/8) Epoch 10, batch 1450, loss[loss=0.1676, simple_loss=0.2569, pruned_loss=0.03917, over 7277.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2874, pruned_loss=0.05103, over 1427626.34 frames.], batch size: 17, lr: 6.97e-04
2022-04-29 00:20:30,754 INFO [train.py:763] (5/8) Epoch 10, batch 1500, loss[loss=0.2098, simple_loss=0.2952, pruned_loss=0.06223, over 7058.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2879, pruned_loss=0.05122, over 1425211.93 frames.], batch size: 28, lr: 6.97e-04
2022-04-29 00:21:36,432 INFO [train.py:763] (5/8) Epoch 10, batch 1550, loss[loss=0.183, simple_loss=0.2691, pruned_loss=0.04848, over 7424.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2875, pruned_loss=0.05091, over 1423686.10 frames.], batch size: 20, lr: 6.97e-04
2022-04-29 00:22:41,610 INFO [train.py:763] (5/8) Epoch 10, batch 1600, loss[loss=0.2185, simple_loss=0.3097, pruned_loss=0.06359, over 6686.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2869, pruned_loss=0.05073, over 1417953.66 frames.], batch size: 31, lr: 6.96e-04
2022-04-29 00:23:47,731 INFO [train.py:763] (5/8) Epoch 10, batch 1650, loss[loss=0.166, simple_loss=0.248, pruned_loss=0.04198, over 7255.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2869, pruned_loss=0.05097, over 1417409.83 frames.], batch size: 16, lr: 6.96e-04
2022-04-29 00:24:52,740 INFO [train.py:763] (5/8) Epoch 10, batch 1700, loss[loss=0.1661, simple_loss=0.2612, pruned_loss=0.03555, over 6830.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2868, pruned_loss=0.05115, over 1416706.28 frames.], batch size: 15, lr: 6.96e-04
2022-04-29 00:25:58,400 INFO [train.py:763] (5/8) Epoch 10, batch 1750, loss[loss=0.1976, simple_loss=0.2975, pruned_loss=0.04885, over 7115.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2856, pruned_loss=0.05071, over 1412587.65 frames.], batch size: 21, lr: 6.95e-04
2022-04-29 00:27:03,853 INFO [train.py:763] (5/8) Epoch 10, batch 1800, loss[loss=0.2508, simple_loss=0.3265, pruned_loss=0.08748, over 5503.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2856, pruned_loss=0.05055, over 1413014.62 frames.], batch size: 52, lr: 6.95e-04
2022-04-29 00:28:10,769 INFO [train.py:763] (5/8) Epoch 10, batch 1850, loss[loss=0.1835, simple_loss=0.2757, pruned_loss=0.04571, over 6444.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2856, pruned_loss=0.0506, over 1417565.58 frames.], batch size: 37, lr: 6.95e-04
2022-04-29 00:29:17,866 INFO [train.py:763] (5/8) Epoch 10, batch 1900, loss[loss=0.2184, simple_loss=0.3136, pruned_loss=0.06159, over 7326.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2858, pruned_loss=0.05022, over 1421829.04 frames.], batch size: 21, lr: 6.94e-04
2022-04-29 00:30:24,854 INFO [train.py:763] (5/8) Epoch 10, batch 1950, loss[loss=0.1739, simple_loss=0.2825, pruned_loss=0.03261, over 7355.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2854, pruned_loss=0.04991, over 1421159.63 frames.], batch size: 19, lr: 6.94e-04
2022-04-29 00:31:31,836 INFO [train.py:763] (5/8) Epoch 10, batch 2000, loss[loss=0.1447, simple_loss=0.2338, pruned_loss=0.02784, over 7181.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2856, pruned_loss=0.05005, over 1422966.17 frames.], batch size: 18, lr: 6.93e-04
2022-04-29 00:32:38,702 INFO [train.py:763] (5/8) Epoch 10, batch 2050, loss[loss=0.1533, simple_loss=0.2481, pruned_loss=0.02923, over 7277.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2849, pruned_loss=0.04919, over 1425170.58 frames.], batch size: 17, lr: 6.93e-04
2022-04-29 00:33:45,458 INFO [train.py:763] (5/8) Epoch 10, batch 2100, loss[loss=0.2083, simple_loss=0.2961, pruned_loss=0.0603, over 7368.00 frames.], tot_loss[loss=0.1928, simple_loss=0.286, pruned_loss=0.04986, over 1425014.92 frames.], batch size: 23, lr: 6.93e-04
2022-04-29 00:35:01,074 INFO [train.py:763] (5/8) Epoch 10, batch 2150, loss[loss=0.1701, simple_loss=0.2578, pruned_loss=0.04124, over 7177.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2853, pruned_loss=0.0495, over 1425982.32 frames.], batch size: 18, lr: 6.92e-04
2022-04-29 00:36:06,568 INFO [train.py:763] (5/8) Epoch 10, batch 2200, loss[loss=0.2064, simple_loss=0.2974, pruned_loss=0.05772, over 7226.00 frames.], tot_loss[loss=0.192, simple_loss=0.2848, pruned_loss=0.04958, over 1424369.34 frames.], batch size: 20, lr: 6.92e-04
2022-04-29 00:37:11,929 INFO [train.py:763] (5/8) Epoch 10, batch 2250, loss[loss=0.1659, simple_loss=0.2624, pruned_loss=0.03469, over 7342.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2859, pruned_loss=0.0498, over 1427074.98 frames.], batch size: 22, lr: 6.92e-04
2022-04-29 00:38:17,413 INFO [train.py:763] (5/8) Epoch 10, batch 2300, loss[loss=0.1835, simple_loss=0.2851, pruned_loss=0.04089, over 7153.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2855, pruned_loss=0.04984, over 1427291.44 frames.], batch size: 26, lr: 6.91e-04
2022-04-29 00:39:22,706 INFO [train.py:763] (5/8) Epoch 10, batch 2350, loss[loss=0.1894, simple_loss=0.2888, pruned_loss=0.04501, over 6737.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2851, pruned_loss=0.04948, over 1429709.16 frames.], batch size: 31, lr: 6.91e-04
2022-04-29 00:40:27,869 INFO [train.py:763] (5/8) Epoch 10, batch 2400, loss[loss=0.1919, simple_loss=0.289, pruned_loss=0.04743, over 7307.00 frames.], tot_loss[loss=0.192, simple_loss=0.2848, pruned_loss=0.04957, over 1423473.13 frames.], batch size: 21, lr: 6.91e-04
2022-04-29 00:41:33,302 INFO [train.py:763] (5/8) Epoch 10, batch 2450, loss[loss=0.1973, simple_loss=0.2832, pruned_loss=0.0557, over 7002.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2842, pruned_loss=0.04973, over 1423387.22 frames.], batch size: 16, lr: 6.90e-04
2022-04-29 00:42:38,517 INFO [train.py:763] (5/8) Epoch 10, batch 2500, loss[loss=0.2055, simple_loss=0.2941, pruned_loss=0.05845, over 7147.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2845, pruned_loss=0.04969, over 1422876.33 frames.], batch size: 19, lr: 6.90e-04
2022-04-29 00:43:44,259 INFO [train.py:763] (5/8) Epoch 10, batch 2550, loss[loss=0.1899, simple_loss=0.2792, pruned_loss=0.05032, over 6811.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2845, pruned_loss=0.04922, over 1426639.89 frames.], batch size: 15, lr: 6.90e-04
2022-04-29 00:44:51,074 INFO [train.py:763] (5/8) Epoch 10, batch 2600, loss[loss=0.1803, simple_loss=0.2817, pruned_loss=0.03941, over 7398.00 frames.], tot_loss[loss=0.1921, simple_loss=0.285, pruned_loss=0.04959, over 1428404.69 frames.], batch size: 23, lr: 6.89e-04
2022-04-29 00:45:56,186 INFO [train.py:763] (5/8) Epoch 10, batch 2650, loss[loss=0.175, simple_loss=0.266, pruned_loss=0.04195, over 7001.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05026, over 1424063.68 frames.], batch size: 16, lr: 6.89e-04
2022-04-29 00:47:01,616 INFO [train.py:763] (5/8) Epoch 10, batch 2700, loss[loss=0.2221, simple_loss=0.3112, pruned_loss=0.06648, over 7409.00 frames.], tot_loss[loss=0.194, simple_loss=0.287, pruned_loss=0.05052, over 1426925.26 frames.], batch size: 21, lr: 6.89e-04
2022-04-29 00:48:08,169 INFO [train.py:763] (5/8) Epoch 10, batch 2750, loss[loss=0.1881, simple_loss=0.272, pruned_loss=0.05215, over 7265.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2856, pruned_loss=0.05017, over 1426028.72 frames.], batch size: 18, lr: 6.88e-04
2022-04-29 00:49:13,517 INFO [train.py:763] (5/8) Epoch 10, batch 2800, loss[loss=0.1777, simple_loss=0.2835, pruned_loss=0.03593, over 7150.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2861, pruned_loss=0.05053, over 1424378.92 frames.], batch size: 19, lr: 6.88e-04
2022-04-29 00:50:19,055 INFO [train.py:763] (5/8) Epoch 10, batch 2850, loss[loss=0.2311, simple_loss=0.3145, pruned_loss=0.07379, over 7321.00 frames.], tot_loss[loss=0.193, simple_loss=0.2854, pruned_loss=0.05032, over 1424858.35 frames.], batch size: 21, lr: 6.87e-04
2022-04-29 00:51:24,561 INFO [train.py:763] (5/8) Epoch 10, batch 2900, loss[loss=0.1981, simple_loss=0.2989, pruned_loss=0.04866, over 7193.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2854, pruned_loss=0.05009, over 1427606.82 frames.], batch size: 23, lr: 6.87e-04
2022-04-29 00:52:30,310 INFO [train.py:763] (5/8) Epoch 10, batch 2950, loss[loss=0.195, simple_loss=0.2882, pruned_loss=0.05093, over 7194.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2859, pruned_loss=0.04993, over 1425292.86 frames.], batch size: 22, lr: 6.87e-04
2022-04-29 00:53:36,016 INFO [train.py:763] (5/8) Epoch 10, batch 3000, loss[loss=0.1785, simple_loss=0.2603, pruned_loss=0.04834, over 7163.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2864, pruned_loss=0.04986, over 1424549.16 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:53:36,017 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 00:53:51,272 INFO [train.py:792] (5/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
2022-04-29 00:54:57,777 INFO [train.py:763] (5/8) Epoch 10, batch 3050, loss[loss=0.1966, simple_loss=0.2905, pruned_loss=0.05137, over 7155.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2857, pruned_loss=0.04963, over 1428429.22 frames.], batch size: 26, lr: 6.86e-04
2022-04-29 00:56:03,589 INFO [train.py:763] (5/8) Epoch 10, batch 3100, loss[loss=0.1682, simple_loss=0.2667, pruned_loss=0.03481, over 7424.00 frames.], tot_loss[loss=0.194, simple_loss=0.2867, pruned_loss=0.05064, over 1425830.93 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:57:10,798 INFO [train.py:763] (5/8) Epoch 10, batch 3150, loss[loss=0.1816, simple_loss=0.2672, pruned_loss=0.04794, over 7306.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2853, pruned_loss=0.0499, over 1427870.95 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:58:16,976 INFO [train.py:763] (5/8) Epoch 10, batch 3200, loss[loss=0.1524, simple_loss=0.2432, pruned_loss=0.03076, over 7172.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2845, pruned_loss=0.0496, over 1429467.35 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:59:22,564 INFO [train.py:763] (5/8) Epoch 10, batch 3250, loss[loss=0.1839, simple_loss=0.2692, pruned_loss=0.04924, over 7065.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2842, pruned_loss=0.04969, over 1430822.36 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 01:00:29,380 INFO [train.py:763] (5/8) Epoch 10, batch 3300, loss[loss=0.2035, simple_loss=0.2974, pruned_loss=0.0548, over 6246.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2847, pruned_loss=0.05005, over 1429603.72 frames.], batch size: 37, lr: 6.84e-04
2022-04-29 01:01:36,451 INFO [train.py:763] (5/8) Epoch 10, batch 3350, loss[loss=0.1914, simple_loss=0.2917, pruned_loss=0.04559, over 7099.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2856, pruned_loss=0.05045, over 1423655.13 frames.], batch size: 21, lr: 6.84e-04
2022-04-29 01:02:41,925 INFO [train.py:763] (5/8) Epoch 10, batch 3400, loss[loss=0.1659, simple_loss=0.2474, pruned_loss=0.04219, over 7016.00 frames.], tot_loss[loss=0.1938, simple_loss=0.286, pruned_loss=0.05081, over 1420811.74 frames.], batch size: 16, lr: 6.84e-04
2022-04-29 01:03:47,415 INFO [train.py:763] (5/8) Epoch 10, batch 3450, loss[loss=0.2084, simple_loss=0.2988, pruned_loss=0.05907, over 7115.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2856, pruned_loss=0.0504, over 1423336.83 frames.], batch size: 21, lr: 6.83e-04
2022-04-29 01:04:52,725 INFO [train.py:763] (5/8) Epoch 10, batch 3500, loss[loss=0.1772, simple_loss=0.26, pruned_loss=0.04714, over 7428.00 frames.], tot_loss[loss=0.193, simple_loss=0.2855, pruned_loss=0.0502, over 1424648.14 frames.], batch size: 18, lr: 6.83e-04
2022-04-29 01:05:58,215 INFO [train.py:763] (5/8) Epoch 10, batch 3550, loss[loss=0.2148, simple_loss=0.3096, pruned_loss=0.05995, over 6347.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2851, pruned_loss=0.05008, over 1423526.34 frames.], batch size: 37, lr: 6.83e-04
2022-04-29 01:07:03,435 INFO [train.py:763] (5/8) Epoch 10, batch 3600, loss[loss=0.2144, simple_loss=0.305, pruned_loss=0.0619, over 6486.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2873, pruned_loss=0.05145, over 1419325.05 frames.], batch size: 37, lr: 6.82e-04
2022-04-29 01:08:09,038 INFO [train.py:763] (5/8) Epoch 10, batch 3650, loss[loss=0.1766, simple_loss=0.2793, pruned_loss=0.03694, over 7115.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2875, pruned_loss=0.05093, over 1421455.48 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:09:14,321 INFO [train.py:763] (5/8) Epoch 10, batch 3700, loss[loss=0.2205, simple_loss=0.315, pruned_loss=0.06301, over 7115.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2872, pruned_loss=0.05075, over 1418118.80 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:10:20,245 INFO [train.py:763] (5/8) Epoch 10, batch 3750, loss[loss=0.1561, simple_loss=0.2519, pruned_loss=0.03011, over 7425.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2876, pruned_loss=0.05072, over 1424364.68 frames.], batch size: 20, lr: 6.81e-04
2022-04-29 01:11:26,044 INFO [train.py:763] (5/8) Epoch 10, batch 3800, loss[loss=0.1962, simple_loss=0.2876, pruned_loss=0.05239, over 7295.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2874, pruned_loss=0.0506, over 1422685.85 frames.], batch size: 24, lr: 6.81e-04
2022-04-29 01:12:32,921 INFO [train.py:763] (5/8) Epoch 10, batch 3850, loss[loss=0.1965, simple_loss=0.2904, pruned_loss=0.05126, over 7221.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2864, pruned_loss=0.05006, over 1426768.86 frames.], batch size: 22, lr: 6.81e-04
2022-04-29 01:13:40,347 INFO [train.py:763] (5/8) Epoch 10, batch 3900, loss[loss=0.2179, simple_loss=0.3138, pruned_loss=0.06098, over 7363.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2858, pruned_loss=0.04979, over 1427218.94 frames.], batch size: 23, lr: 6.80e-04
2022-04-29 01:14:47,720 INFO [train.py:763] (5/8) Epoch 10, batch 3950, loss[loss=0.1768, simple_loss=0.2745, pruned_loss=0.03957, over 7440.00 frames.], tot_loss[loss=0.192, simple_loss=0.2851, pruned_loss=0.04946, over 1425867.16 frames.], batch size: 20, lr: 6.80e-04
2022-04-29 01:15:53,655 INFO [train.py:763] (5/8) Epoch 10, batch 4000, loss[loss=0.1981, simple_loss=0.2969, pruned_loss=0.04968, over 7217.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2857, pruned_loss=0.04968, over 1417434.08 frames.], batch size: 21, lr: 6.80e-04
2022-04-29 01:17:00,584 INFO [train.py:763] (5/8) Epoch 10, batch 4050, loss[loss=0.1941, simple_loss=0.2875, pruned_loss=0.05032, over 7211.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2858, pruned_loss=0.04982, over 1416954.09 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:18:07,405 INFO [train.py:763] (5/8) Epoch 10, batch 4100, loss[loss=0.2219, simple_loss=0.308, pruned_loss=0.06789, over 7200.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2856, pruned_loss=0.04966, over 1416728.05 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:19:14,072 INFO [train.py:763] (5/8) Epoch 10, batch 4150, loss[loss=0.2284, simple_loss=0.3164, pruned_loss=0.07017, over 6790.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2867, pruned_loss=0.05008, over 1414718.66 frames.], batch size: 31, lr: 6.79e-04
2022-04-29 01:20:19,805 INFO [train.py:763] (5/8) Epoch 10, batch 4200, loss[loss=0.17, simple_loss=0.2729, pruned_loss=0.03358, over 7098.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2872, pruned_loss=0.05018, over 1415957.72 frames.], batch size: 28, lr: 6.78e-04
2022-04-29 01:21:26,035 INFO [train.py:763] (5/8) Epoch 10, batch 4250, loss[loss=0.2389, simple_loss=0.3229, pruned_loss=0.07744, over 4854.00 frames.], tot_loss[loss=0.194, simple_loss=0.2871, pruned_loss=0.05046, over 1415387.32 frames.], batch size: 52, lr: 6.78e-04
2022-04-29 01:22:31,079 INFO [train.py:763] (5/8) Epoch 10, batch 4300, loss[loss=0.2423, simple_loss=0.3229, pruned_loss=0.0809, over 4795.00 frames.], tot_loss[loss=0.195, simple_loss=0.2876, pruned_loss=0.05117, over 1410529.07 frames.], batch size: 52, lr: 6.78e-04
2022-04-29 01:23:36,200 INFO [train.py:763] (5/8) Epoch 10, batch 4350, loss[loss=0.1593, simple_loss=0.2544, pruned_loss=0.03206, over 7233.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2872, pruned_loss=0.05057, over 1409288.02 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:24:41,263 INFO [train.py:763] (5/8) Epoch 10, batch 4400, loss[loss=0.1885, simple_loss=0.2792, pruned_loss=0.04893, over 7195.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2876, pruned_loss=0.05028, over 1415064.51 frames.], batch size: 22, lr: 6.77e-04
2022-04-29 01:25:46,580 INFO [train.py:763] (5/8) Epoch 10, batch 4450, loss[loss=0.1698, simple_loss=0.2719, pruned_loss=0.03385, over 7228.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2896, pruned_loss=0.05085, over 1418012.31 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:26:52,305 INFO [train.py:763] (5/8) Epoch 10, batch 4500, loss[loss=0.2219, simple_loss=0.3004, pruned_loss=0.07166, over 5099.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2905, pruned_loss=0.05154, over 1409083.17 frames.], batch size: 52, lr: 6.76e-04
2022-04-29 01:27:57,105 INFO [train.py:763] (5/8) Epoch 10, batch 4550, loss[loss=0.2266, simple_loss=0.304, pruned_loss=0.07455, over 5061.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2936, pruned_loss=0.05468, over 1347203.66 frames.], batch size: 52, lr: 6.76e-04
2022-04-29 01:29:26,059 INFO [train.py:763] (5/8) Epoch 11, batch 0, loss[loss=0.1925, simple_loss=0.295, pruned_loss=0.04502, over 7411.00 frames.], tot_loss[loss=0.1925, simple_loss=0.295, pruned_loss=0.04502, over 7411.00 frames.], batch size: 21, lr: 6.52e-04
2022-04-29 01:30:32,269 INFO [train.py:763] (5/8) Epoch 11, batch 50, loss[loss=0.2205, simple_loss=0.3015, pruned_loss=0.06972, over 4644.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2878, pruned_loss=0.05023, over 317966.78 frames.], batch size: 53, lr: 6.52e-04
2022-04-29 01:31:38,381 INFO [train.py:763] (5/8) Epoch 11, batch 100, loss[loss=0.178, simple_loss=0.2645, pruned_loss=0.0458, over 6301.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2875, pruned_loss=0.04982, over 557264.69 frames.], batch size: 37, lr: 6.51e-04
2022-04-29 01:32:44,340 INFO [train.py:763] (5/8) Epoch 11, batch 150, loss[loss=0.1683, simple_loss=0.2476, pruned_loss=0.04451, over 7288.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2869, pruned_loss=0.04939, over 747823.16 frames.], batch size: 17, lr: 6.51e-04
2022-04-29 01:33:50,252 INFO [train.py:763] (5/8) Epoch 11, batch 200, loss[loss=0.214, simple_loss=0.311, pruned_loss=0.05854, over 7204.00 frames.], tot_loss[loss=0.1941, simple_loss=0.288, pruned_loss=0.0501, over 895746.78 frames.], batch size: 22, lr: 6.51e-04
2022-04-29 01:34:55,812 INFO [train.py:763] (5/8) Epoch 11, batch 250, loss[loss=0.2042, simple_loss=0.303, pruned_loss=0.05267, over 6959.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2885, pruned_loss=0.05037, over 1013794.01 frames.], batch size: 32, lr: 6.50e-04
2022-04-29 01:36:01,206 INFO [train.py:763] (5/8) Epoch 11, batch 300, loss[loss=0.1776, simple_loss=0.2674, pruned_loss=0.04391, over 7192.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2881, pruned_loss=0.05015, over 1098637.92 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:37:06,910 INFO [train.py:763] (5/8) Epoch 11, batch 350, loss[loss=0.178, simple_loss=0.276, pruned_loss=0.04003, over 7330.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2868, pruned_loss=0.04953, over 1164838.69 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:38:12,679 INFO [train.py:763] (5/8) Epoch 11, batch 400, loss[loss=0.1996, simple_loss=0.2931, pruned_loss=0.05301, over 7323.00 frames.], tot_loss[loss=0.1925, simple_loss=0.286, pruned_loss=0.04953, over 1220366.71 frames.], batch size: 22, lr: 6.49e-04
2022-04-29 01:39:18,306 INFO [train.py:763] (5/8) Epoch 11, batch 450, loss[loss=0.1702, simple_loss=0.2602, pruned_loss=0.04013, over 7151.00 frames.], tot_loss[loss=0.1914, simple_loss=0.285, pruned_loss=0.04894, over 1268478.67 frames.], batch size: 19, lr: 6.49e-04
2022-04-29 01:40:24,058 INFO [train.py:763] (5/8) Epoch 11, batch 500, loss[loss=0.223, simple_loss=0.3228, pruned_loss=0.06156, over 7396.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2856, pruned_loss=0.04963, over 1302397.09 frames.], batch size: 23, lr: 6.49e-04
2022-04-29 01:41:30,083 INFO [train.py:763] (5/8) Epoch 11, batch 550, loss[loss=0.2047, simple_loss=0.3131, pruned_loss=0.04817, over 7419.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2846, pruned_loss=0.04883, over 1329362.66 frames.], batch size: 21, lr: 6.48e-04
2022-04-29 01:42:36,760 INFO [train.py:763] (5/8) Epoch 11, batch 600, loss[loss=0.1921, simple_loss=0.3032, pruned_loss=0.04051, over 7330.00 frames.], tot_loss[loss=0.191, simple_loss=0.2845, pruned_loss=0.04878, over 1348699.09 frames.], batch size: 22, lr: 6.48e-04
2022-04-29 01:43:44,105 INFO [train.py:763] (5/8) Epoch 11, batch 650, loss[loss=0.1937, simple_loss=0.2934, pruned_loss=0.04697, over 7384.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2835, pruned_loss=0.04789, over 1369876.98 frames.], batch size: 23, lr: 6.48e-04
2022-04-29 01:44:51,109 INFO [train.py:763] (5/8) Epoch 11, batch 700, loss[loss=0.1963, simple_loss=0.2868, pruned_loss=0.05288, over 7297.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2841, pruned_loss=0.04809, over 1380076.58 frames.], batch size: 24, lr: 6.47e-04
2022-04-29 01:45:57,540 INFO [train.py:763] (5/8) Epoch 11, batch 750, loss[loss=0.1676, simple_loss=0.2685, pruned_loss=0.03339, over 7325.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2838, pruned_loss=0.04801, over 1385539.16 frames.], batch size: 20, lr: 6.47e-04
2022-04-29 01:47:03,482 INFO [train.py:763] (5/8) Epoch 11, batch 800, loss[loss=0.1644, simple_loss=0.2485, pruned_loss=0.04015, over 7403.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2836, pruned_loss=0.04808, over 1398439.69 frames.], batch size: 18, lr: 6.47e-04
2022-04-29 01:48:08,967 INFO [train.py:763] (5/8) Epoch 11, batch 850, loss[loss=0.2151, simple_loss=0.3027, pruned_loss=0.06376, over 6726.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2844, pruned_loss=0.04872, over 1402991.64 frames.], batch size: 31, lr: 6.46e-04
2022-04-29 01:49:14,793 INFO [train.py:763] (5/8) Epoch 11, batch 900, loss[loss=0.1749, simple_loss=0.282, pruned_loss=0.03385, over 7325.00 frames.], tot_loss[loss=0.1905, simple_loss=0.284, pruned_loss=0.04851, over 1407737.40 frames.], batch size: 22, lr: 6.46e-04
2022-04-29 01:50:20,607 INFO [train.py:763] (5/8) Epoch 11, batch 950, loss[loss=0.1621, simple_loss=0.2609, pruned_loss=0.03169, over 7432.00 frames.], tot_loss[loss=0.1905, simple_loss=0.284, pruned_loss=0.0485, over 1413211.71 frames.], batch size: 20, lr: 6.46e-04
2022-04-29 01:51:27,140 INFO [train.py:763] (5/8) Epoch 11, batch 1000, loss[loss=0.2509, simple_loss=0.3264, pruned_loss=0.08775, over 7165.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2854, pruned_loss=0.04882, over 1416229.31 frames.], batch size: 19, lr: 6.46e-04
2022-04-29 01:52:32,492 INFO [train.py:763] (5/8) Epoch 11, batch 1050, loss[loss=0.175, simple_loss=0.2646, pruned_loss=0.04271, over 7004.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2856, pruned_loss=0.04882, over 1416590.54 frames.], batch size: 16, lr: 6.45e-04
2022-04-29 01:53:38,692 INFO [train.py:763] (5/8) Epoch 11, batch 1100, loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03538, over 7166.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2862, pruned_loss=0.04884, over 1419804.79 frames.], batch size: 19, lr: 6.45e-04
2022-04-29 01:54:45,840 INFO [train.py:763] (5/8) Epoch 11, batch 1150, loss[loss=0.2343, simple_loss=0.3144, pruned_loss=0.07709, over 4963.00 frames.], tot_loss[loss=0.191, simple_loss=0.2852, pruned_loss=0.04844, over 1421924.92 frames.], batch size: 52, lr: 6.45e-04
2022-04-29 01:55:51,961 INFO [train.py:763] (5/8) Epoch 11, batch 1200, loss[loss=0.2404, simple_loss=0.3278, pruned_loss=0.07649, over 7109.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2855, pruned_loss=0.04844, over 1424972.98 frames.], batch size: 21, lr: 6.44e-04
2022-04-29 01:56:57,801 INFO [train.py:763] (5/8) Epoch 11, batch 1250, loss[loss=0.1476, simple_loss=0.2436, pruned_loss=0.02581, over 7007.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2848, pruned_loss=0.04835, over 1425911.61 frames.], batch size: 16, lr: 6.44e-04
2022-04-29 01:58:03,707 INFO [train.py:763] (5/8) Epoch 11, batch 1300, loss[loss=0.1739, simple_loss=0.2705, pruned_loss=0.03861, over 7323.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2844, pruned_loss=0.04803, over 1427660.39 frames.], batch size: 20, lr: 6.44e-04
2022-04-29 01:59:10,168 INFO [train.py:763] (5/8) Epoch 11, batch 1350, loss[loss=0.1825, simple_loss=0.2764, pruned_loss=0.04425, over 7325.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2842, pruned_loss=0.0482, over 1424668.01 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:00:15,531 INFO [train.py:763] (5/8) Epoch 11, batch 1400, loss[loss=0.204, simple_loss=0.312, pruned_loss=0.04804, over 7316.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2838, pruned_loss=0.04805, over 1421662.07 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:01:21,169 INFO [train.py:763] (5/8) Epoch 11, batch 1450, loss[loss=0.1565, simple_loss=0.248, pruned_loss=0.03246, over 7068.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2838, pruned_loss=0.04796, over 1421977.37 frames.], batch size: 18, lr: 6.43e-04
2022-04-29 02:02:28,458 INFO [train.py:763] (5/8) Epoch 11, batch 1500, loss[loss=0.2248, simple_loss=0.3116, pruned_loss=0.06903, over 7223.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2834, pruned_loss=0.04806, over 1425355.76 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:03:33,962 INFO [train.py:763] (5/8) Epoch 11, batch 1550, loss[loss=0.2127, simple_loss=0.31, pruned_loss=0.05773, over 7227.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2831, pruned_loss=0.04826, over 1424862.59 frames.], batch size: 20, lr: 6.42e-04
2022-04-29 02:04:39,639 INFO [train.py:763] (5/8) Epoch 11, batch 1600, loss[loss=0.2042, simple_loss=0.2896, pruned_loss=0.05942, over 7349.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2848, pruned_loss=0.04885, over 1425554.89 frames.], batch size: 19, lr: 6.42e-04
2022-04-29 02:06:04,019 INFO [train.py:763] (5/8) Epoch 11, batch 1650, loss[loss=0.1852, simple_loss=0.286, pruned_loss=0.0422, over 7380.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2845, pruned_loss=0.04862, over 1426357.06 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:07:17,970 INFO [train.py:763] (5/8) Epoch 11, batch 1700, loss[loss=0.2329, simple_loss=0.3204, pruned_loss=0.07273, over 7215.00 frames.], tot_loss[loss=0.1909, simple_loss=0.285, pruned_loss=0.04839, over 1427547.44 frames.], batch size: 21, lr: 6.41e-04
2022-04-29 02:08:33,277 INFO [train.py:763] (5/8) Epoch 11, batch 1750, loss[loss=0.2037, simple_loss=0.2982, pruned_loss=0.05462, over 7155.00 frames.], tot_loss[loss=0.192, simple_loss=0.2861, pruned_loss=0.04893, over 1428263.99 frames.], batch size: 26, lr: 6.41e-04
2022-04-29 02:09:47,988 INFO [train.py:763] (5/8) Epoch 11, batch 1800, loss[loss=0.1576, simple_loss=0.2537, pruned_loss=0.03078, over 6999.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2863, pruned_loss=0.04915, over 1428783.87 frames.], batch size: 16, lr: 6.41e-04
2022-04-29 02:11:03,174 INFO [train.py:763] (5/8) Epoch 11, batch 1850, loss[loss=0.1884, simple_loss=0.2895, pruned_loss=0.04364, over 7188.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2853, pruned_loss=0.04878, over 1426964.53 frames.], batch size: 26, lr: 6.40e-04
2022-04-29 02:12:18,081 INFO [train.py:763] (5/8) Epoch 11, batch 1900, loss[loss=0.1706, simple_loss=0.2633, pruned_loss=0.03897, over 7423.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2846, pruned_loss=0.0484, over 1429675.03 frames.], batch size: 20, lr: 6.40e-04
2022-04-29 02:13:32,352 INFO [train.py:763] (5/8) Epoch 11, batch 1950, loss[loss=0.1961, simple_loss=0.2825, pruned_loss=0.05492, over 7009.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2851, pruned_loss=0.04884, over 1428441.75 frames.], batch size: 16, lr: 6.40e-04
2022-04-29 02:14:38,167 INFO [train.py:763] (5/8) Epoch 11, batch 2000, loss[loss=0.1928, simple_loss=0.2849, pruned_loss=0.05038, over 6533.00 frames.], tot_loss[loss=0.193, simple_loss=0.2861, pruned_loss=0.04994, over 1427330.19 frames.], batch size: 38, lr: 6.39e-04
2022-04-29 02:15:44,450 INFO [train.py:763] (5/8) Epoch 11, batch 2050, loss[loss=0.1758, simple_loss=0.2728, pruned_loss=0.03939, over 7364.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2835, pruned_loss=0.04883, over 1424886.33 frames.], batch size: 23, lr: 6.39e-04
2022-04-29 02:16:50,755 INFO [train.py:763] (5/8) Epoch 11, batch 2100, loss[loss=0.1939, simple_loss=0.2862, pruned_loss=0.05076, over 6729.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2835, pruned_loss=0.04858, over 1428331.52 frames.], batch size: 31, lr: 6.39e-04
2022-04-29 02:17:57,127 INFO [train.py:763] (5/8) Epoch 11, batch 2150, loss[loss=0.1798, simple_loss=0.2532, pruned_loss=0.0532, over 6809.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2838, pruned_loss=0.04869, over 1422479.98 frames.], batch size: 15, lr: 6.38e-04
2022-04-29 02:19:03,275 INFO [train.py:763] (5/8) Epoch 11, batch 2200, loss[loss=0.2007, simple_loss=0.2916, pruned_loss=0.05491, over 7426.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2835, pruned_loss=0.04867, over 1426632.50 frames.], batch size: 20, lr: 6.38e-04
2022-04-29 02:20:09,576 INFO [train.py:763] (5/8) Epoch 11, batch 2250, loss[loss=0.1769, simple_loss=0.2674, pruned_loss=0.04316, over 7152.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2834, pruned_loss=0.04857, over 1426200.16 frames.], batch size: 17, lr: 6.38e-04
2022-04-29 02:21:16,349 INFO [train.py:763] (5/8) Epoch 11, batch 2300, loss[loss=0.1662, simple_loss=0.2637, pruned_loss=0.03434, over 7359.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2844, pruned_loss=0.04845, over 1424363.87 frames.], batch size: 19, lr: 6.38e-04
2022-04-29 02:22:22,093 INFO [train.py:763] (5/8) Epoch 11, batch 2350, loss[loss=0.2319, simple_loss=0.32, pruned_loss=0.07195, over 7281.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2844, pruned_loss=0.04843, over 1426075.16 frames.], batch size: 24, lr: 6.37e-04
2022-04-29 02:23:28,146 INFO [train.py:763] (5/8) Epoch 11, batch 2400, loss[loss=0.1946, simple_loss=0.28, pruned_loss=0.05463, over 7114.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2849, pruned_loss=0.04839, over 1428363.91 frames.], batch size: 21, lr: 6.37e-04
2022-04-29 02:24:33,625 INFO [train.py:763] (5/8) Epoch 11, batch 2450, loss[loss=0.1968, simple_loss=0.2968, pruned_loss=0.04839, over 7241.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2853, pruned_loss=0.04829, over 1426870.19 frames.], batch size: 20, lr: 6.37e-04
2022-04-29 02:25:39,230 INFO [train.py:763] (5/8) Epoch 11, batch 2500, loss[loss=0.1906, simple_loss=0.2683, pruned_loss=0.05641, over 7068.00 frames.], tot_loss[loss=0.1914, simple_loss=0.285, pruned_loss=0.04894, over 1426531.57 frames.], batch size: 18, lr: 6.36e-04
2022-04-29 02:26:45,649 INFO [train.py:763] (5/8) Epoch 11, batch 2550, loss[loss=0.1727, simple_loss=0.2587, pruned_loss=0.04341, over 7267.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2854, pruned_loss=0.04916, over 1428526.33 frames.], batch size: 17, lr: 6.36e-04
2022-04-29 02:27:50,870 INFO [train.py:763] (5/8) Epoch 11, batch 2600, loss[loss=0.2338, simple_loss=0.332, pruned_loss=0.06776, over 7271.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2858, pruned_loss=0.0496, over 1423189.40 frames.], batch size: 24, lr: 6.36e-04
2022-04-29 02:28:56,398 INFO [train.py:763] (5/8) Epoch 11, batch 2650, loss[loss=0.1679, simple_loss=0.2692, pruned_loss=0.03331, over 7261.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2853, pruned_loss=0.04891, over 1420003.94 frames.], batch size: 19, lr: 6.36e-04
2022-04-29 02:30:03,352 INFO [train.py:763] (5/8) Epoch 11, batch 2700, loss[loss=0.2079, simple_loss=0.2953, pruned_loss=0.06023, over 7300.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2845, pruned_loss=0.04856, over 1423269.62 frames.], batch size: 25, lr: 6.35e-04
2022-04-29 02:31:08,829 INFO [train.py:763] (5/8) Epoch 11, batch 2750, loss[loss=0.1777, simple_loss=0.2742, pruned_loss=0.04057, over 7431.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2833, pruned_loss=0.04783, over 1425939.39 frames.], batch size: 20, lr: 6.35e-04
2022-04-29 02:32:14,651 INFO [train.py:763] (5/8) Epoch 11, batch 2800, loss[loss=0.2089, simple_loss=0.3025, pruned_loss=0.05758, over 7119.00 frames.], tot_loss[loss=0.1891, simple_loss=0.283, pruned_loss=0.0476, over 1427158.74 frames.], batch size: 21, lr: 6.35e-04
2022-04-29 02:33:21,119 INFO [train.py:763] (5/8) Epoch 11, batch 2850, loss[loss=0.1915, simple_loss=0.2911, pruned_loss=0.04599, over 7323.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2818, pruned_loss=0.04704, over 1429226.71 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:34:28,406 INFO [train.py:763] (5/8) Epoch 11, batch 2900, loss[loss=0.2023, simple_loss=0.29, pruned_loss=0.0573, over 7302.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2838, pruned_loss=0.04789, over 1424752.02 frames.], batch size: 24, lr: 6.34e-04
2022-04-29 02:35:35,078 INFO [train.py:763] (5/8) Epoch 11, batch 2950, loss[loss=0.1654, simple_loss=0.2612, pruned_loss=0.0348, over 7219.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2845, pruned_loss=0.04832, over 1421074.07 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:36:40,647 INFO [train.py:763] (5/8) Epoch 11, batch 3000, loss[loss=0.1899, simple_loss=0.2818, pruned_loss=0.049, over 7325.00 frames.], tot_loss[loss=0.1901, simple_loss=0.284, pruned_loss=0.0481, over 1422639.33 frames.], batch size: 25, lr: 6.33e-04
2022-04-29 02:36:40,648 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 02:36:55,964 INFO [train.py:792] (5/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
2022-04-29 02:38:01,328 INFO [train.py:763] (5/8) Epoch 11, batch 3050, loss[loss=0.2018, simple_loss=0.3094, pruned_loss=0.0471, over 7367.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2856, pruned_loss=0.04866, over 1420874.40 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:39:07,001 INFO [train.py:763] (5/8) Epoch 11, batch 3100, loss[loss=0.1948, simple_loss=0.2839, pruned_loss=0.05289, over 7330.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2846, pruned_loss=0.04804, over 1422921.99 frames.], batch size: 20, lr: 6.33e-04
2022-04-29 02:40:14,528 INFO [train.py:763] (5/8) Epoch 11, batch 3150, loss[loss=0.1918, simple_loss=0.277, pruned_loss=0.05336, over 7369.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2839, pruned_loss=0.04769, over 1424728.89 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:41:19,860 INFO [train.py:763] (5/8) Epoch 11, batch 3200, loss[loss=0.1642, simple_loss=0.262, pruned_loss=0.03315, over 7102.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2832, pruned_loss=0.04767, over 1424764.50 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:42:26,245 INFO [train.py:763] (5/8) Epoch 11, batch 3250, loss[loss=0.1743, simple_loss=0.2795, pruned_loss=0.0345, over 7415.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2839, pruned_loss=0.04793, over 1425786.83 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:43:31,321 INFO [train.py:763] (5/8) Epoch 11, batch 3300, loss[loss=0.1609, simple_loss=0.253, pruned_loss=0.03437, over 6994.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2849, pruned_loss=0.04844, over 1426059.92 frames.], batch size: 16, lr: 6.32e-04
2022-04-29 02:44:36,752 INFO [train.py:763] (5/8) Epoch 11, batch 3350, loss[loss=0.203, simple_loss=0.2855, pruned_loss=0.06026, over 7283.00 frames.], tot_loss[loss=0.191, simple_loss=0.2852, pruned_loss=0.04833, over 1426315.63 frames.], batch size: 18, lr: 6.31e-04
2022-04-29 02:45:42,400 INFO [train.py:763] (5/8) Epoch 11, batch 3400, loss[loss=0.1893, simple_loss=0.2862, pruned_loss=0.04616, over 6449.00 frames.], tot_loss[loss=0.1908, simple_loss=0.285, pruned_loss=0.04827, over 1420994.05 frames.], batch size: 37, lr: 6.31e-04
2022-04-29 02:46:49,531 INFO [train.py:763] (5/8) Epoch 11, batch 3450, loss[loss=0.1741, simple_loss=0.2689, pruned_loss=0.03964, over 7119.00 frames.], tot_loss[loss=0.1899, simple_loss=0.284, pruned_loss=0.0479, over 1418523.54 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:47:56,127 INFO [train.py:763] (5/8) Epoch 11, batch 3500, loss[loss=0.1916, simple_loss=0.2882, pruned_loss=0.04755, over 7318.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2847, pruned_loss=0.04818, over 1424412.85 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:49:02,215 INFO [train.py:763] (5/8) Epoch 11, batch 3550, loss[loss=0.1789, simple_loss=0.265, pruned_loss=0.04637, over 7005.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2848, pruned_loss=0.04845, over 1423556.99 frames.], batch size: 16, lr: 6.30e-04
2022-04-29 02:50:08,016 INFO [train.py:763] (5/8) Epoch 11, batch 3600, loss[loss=0.1715, simple_loss=0.2645, pruned_loss=0.03926, over 7233.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2856, pruned_loss=0.04889, over 1425495.35 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:51:13,363 INFO [train.py:763] (5/8) Epoch 11, batch 3650, loss[loss=0.1781, simple_loss=0.2831, pruned_loss=0.03657, over 7436.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2851, pruned_loss=0.04853, over 1424499.95 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:52:20,069 INFO [train.py:763] (5/8) Epoch 11, batch 3700, loss[loss=0.2008, simple_loss=0.297, pruned_loss=0.05233, over 6868.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2836, pruned_loss=0.048, over 1421481.39 frames.], batch size: 31, lr: 6.29e-04
2022-04-29 02:53:25,483 INFO [train.py:763] (5/8) Epoch 11, batch 3750, loss[loss=0.194, simple_loss=0.2853, pruned_loss=0.05132, over 7393.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2828, pruned_loss=0.04744, over 1425804.73 frames.], batch size: 23, lr: 6.29e-04
2022-04-29 02:54:30,954 INFO [train.py:763] (5/8) Epoch 11, batch 3800, loss[loss=0.2118, simple_loss=0.3184, pruned_loss=0.05262, over 7194.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2831, pruned_loss=0.04731, over 1428427.35 frames.], batch size: 26, lr: 6.29e-04
2022-04-29 02:55:36,110 INFO [train.py:763] (5/8) Epoch 11, batch 3850, loss[loss=0.1695, simple_loss=0.2718, pruned_loss=0.03354, over 7111.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2839, pruned_loss=0.04773, over 1428675.91 frames.], batch size: 21, lr: 6.29e-04
2022-04-29 02:56:41,387 INFO [train.py:763] (5/8) Epoch 11, batch 3900, loss[loss=0.1849, simple_loss=0.2823, pruned_loss=0.04375, over 7434.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2839, pruned_loss=0.04739, over 1429428.52 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:57:46,962 INFO [train.py:763] (5/8) Epoch 11, batch 3950, loss[loss=0.2245, simple_loss=0.3146, pruned_loss=0.06715, over 7227.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2842, pruned_loss=0.04816, over 1431216.83 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:58:52,094 INFO [train.py:763] (5/8) Epoch 11, batch 4000, loss[loss=0.2004, simple_loss=0.3039, pruned_loss=0.04845, over 7408.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2844, pruned_loss=0.04831, over 1426312.30 frames.], batch size: 21, lr: 6.28e-04
2022-04-29 02:59:57,360 INFO [train.py:763] (5/8) Epoch 11, batch 4050, loss[loss=0.1865, simple_loss=0.2875, pruned_loss=0.04271, over 7442.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2845, pruned_loss=0.0483, over 1424409.55 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:01:03,194 INFO [train.py:763] (5/8) Epoch 11, batch 4100, loss[loss=0.1865, simple_loss=0.2864, pruned_loss=0.04333, over 7318.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2842, pruned_loss=0.04839, over 1420655.71 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:02:08,247 INFO [train.py:763] (5/8) Epoch 11, batch 4150, loss[loss=0.2043, simple_loss=0.2915, pruned_loss=0.05853, over 7230.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2839, pruned_loss=0.04814, over 1421449.15 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:03:14,699 INFO [train.py:763] (5/8) Epoch 11, batch 4200, loss[loss=0.1943, simple_loss=0.2967, pruned_loss=0.04592, over 7339.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2841, pruned_loss=0.04831, over 1420615.19 frames.], batch size: 22, lr: 6.27e-04
2022-04-29 03:04:21,495 INFO [train.py:763] (5/8) Epoch 11, batch 4250, loss[loss=0.1538, simple_loss=0.2515, pruned_loss=0.02804, over 7420.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2838, pruned_loss=0.04797, over 1424041.87 frames.], batch size: 18, lr: 6.26e-04
2022-04-29 03:05:27,596 INFO [train.py:763] (5/8) Epoch 11, batch 4300, loss[loss=0.1965, simple_loss=0.2875, pruned_loss=0.05281, over 7226.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2832, pruned_loss=0.04796, over 1417495.90 frames.], batch size: 20, lr: 6.26e-04
2022-04-29 03:06:35,257 INFO [train.py:763] (5/8) Epoch 11, batch 4350, loss[loss=0.1962, simple_loss=0.2803, pruned_loss=0.05598, over 7201.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2814, pruned_loss=0.04742, over 1419620.59 frames.], batch size: 22, lr: 6.26e-04
2022-04-29 03:07:41,468 INFO [train.py:763] (5/8) Epoch 11, batch 4400, loss[loss=0.2075, simple_loss=0.2978, pruned_loss=0.05865, over 7318.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2818, pruned_loss=0.04795, over 1418175.25 frames.], batch size: 21, lr: 6.25e-04
2022-04-29 03:08:47,767 INFO [train.py:763] (5/8) Epoch 11, batch 4450, loss[loss=0.2215, simple_loss=0.3171, pruned_loss=0.0629, over 6527.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2814, pruned_loss=0.04842, over 1406381.03 frames.], batch size: 37, lr: 6.25e-04
2022-04-29 03:09:54,262 INFO [train.py:763] (5/8) Epoch 11, batch 4500, loss[loss=0.2003, simple_loss=0.2989, pruned_loss=0.05078, over 6431.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2809, pruned_loss=0.0489, over 1390259.12 frames.], batch size: 38, lr: 6.25e-04
2022-04-29 03:10:59,845 INFO [train.py:763] (5/8) Epoch 11, batch 4550, loss[loss=0.2031, simple_loss=0.2932, pruned_loss=0.05656, over 5108.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2837, pruned_loss=0.05075, over 1351239.20 frames.], batch size: 52, lr: 6.25e-04
2022-04-29 03:12:38,232 INFO [train.py:763] (5/8) Epoch 12, batch 0, loss[loss=0.1963, simple_loss=0.2963, pruned_loss=0.04817, over 7144.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2963, pruned_loss=0.04817, over 7144.00 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:13:44,621 INFO [train.py:763] (5/8) Epoch 12, batch 50, loss[loss=0.1699, simple_loss=0.2736, pruned_loss=0.03307, over 7235.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2836, pruned_loss=0.04628, over 318515.53 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:14:50,365 INFO [train.py:763] (5/8) Epoch 12, batch 100, loss[loss=0.251, simple_loss=0.3362, pruned_loss=0.08292, over 7178.00 frames.], tot_loss[loss=0.1908, simple_loss=0.286, pruned_loss=0.04781, over 564575.58 frames.], batch size: 23, lr: 6.03e-04
2022-04-29 03:15:56,444 INFO [train.py:763] (5/8) Epoch 12, batch 150, loss[loss=0.206, simple_loss=0.3033, pruned_loss=0.05435, over 7146.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2859, pruned_loss=0.04683, over 753649.32 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:17:02,805 INFO [train.py:763] (5/8) Epoch 12, batch 200, loss[loss=0.178, simple_loss=0.2853, pruned_loss=0.03529, over 7155.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2835, pruned_loss=0.04632, over 900958.48 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:18:09,064 INFO [train.py:763] (5/8) Epoch 12, batch 250, loss[loss=0.1894, simple_loss=0.271, pruned_loss=0.05386, over 6789.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2833, pruned_loss=0.04649, over 1013902.42 frames.], batch size: 15, lr: 6.02e-04
2022-04-29 03:19:15,284 INFO [train.py:763] (5/8) Epoch 12, batch 300, loss[loss=0.2003, simple_loss=0.2916, pruned_loss=0.05448, over 7145.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2823, pruned_loss=0.04653, over 1103407.41 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:20:20,574 INFO [train.py:763] (5/8) Epoch 12, batch 350, loss[loss=0.2035, simple_loss=0.2989, pruned_loss=0.05407, over 7008.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2823, pruned_loss=0.04579, over 1175895.03 frames.], batch size: 28, lr: 6.01e-04
2022-04-29 03:21:26,180 INFO [train.py:763] (5/8) Epoch 12, batch 400, loss[loss=0.1734, simple_loss=0.2699, pruned_loss=0.03851, over 7357.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2828, pruned_loss=0.04615, over 1233299.90 frames.], batch size: 19, lr: 6.01e-04
2022-04-29 03:22:31,840 INFO [train.py:763] (5/8) Epoch 12, batch 450, loss[loss=0.1913, simple_loss=0.299, pruned_loss=0.04183, over 7315.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2821, pruned_loss=0.04607, over 1276945.01 frames.], batch size: 21, lr: 6.01e-04
2022-04-29 03:23:38,039 INFO [train.py:763] (5/8) Epoch 12, batch 500, loss[loss=0.1863, simple_loss=0.2846, pruned_loss=0.04393, over 6636.00 frames.], tot_loss[loss=0.186, simple_loss=0.2807, pruned_loss=0.04563, over 1310416.82 frames.], batch size: 38, lr: 6.01e-04
2022-04-29 03:24:43,955 INFO [train.py:763] (5/8) Epoch 12, batch 550, loss[loss=0.1871, simple_loss=0.2792, pruned_loss=0.04751, over 7392.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2811, pruned_loss=0.0457, over 1332894.18 frames.], batch size: 23, lr: 6.00e-04
2022-04-29 03:25:49,969 INFO [train.py:763] (5/8) Epoch 12, batch 600, loss[loss=0.1527, simple_loss=0.2426, pruned_loss=0.03141, over 7212.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2801, pruned_loss=0.04587, over 1347466.69 frames.], batch size: 16, lr: 6.00e-04
2022-04-29 03:26:55,896 INFO [train.py:763] (5/8) Epoch 12, batch 650, loss[loss=0.1756, simple_loss=0.2635, pruned_loss=0.04379, over 7296.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2811, pruned_loss=0.04589, over 1366758.93 frames.], batch size: 18, lr: 6.00e-04
2022-04-29 03:28:02,301 INFO [train.py:763] (5/8) Epoch 12, batch 700, loss[loss=0.194, simple_loss=0.2786, pruned_loss=0.05472, over 6816.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2825, pruned_loss=0.04597, over 1384045.16 frames.], batch size: 15, lr: 6.00e-04
2022-04-29 03:29:07,997 INFO [train.py:763] (5/8) Epoch 12, batch 750, loss[loss=0.2173, simple_loss=0.3121, pruned_loss=0.06122, over 7204.00 frames.], tot_loss[loss=0.188, simple_loss=0.2832, pruned_loss=0.04644, over 1396329.94 frames.], batch size: 23, lr: 5.99e-04
2022-04-29 03:30:14,231 INFO [train.py:763] (5/8) Epoch 12, batch 800, loss[loss=0.1956, simple_loss=0.2931, pruned_loss=0.04905, over 7205.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2828, pruned_loss=0.04613, over 1405032.29 frames.], batch size: 22, lr: 5.99e-04
2022-04-29 03:31:20,656 INFO [train.py:763] (5/8) Epoch 12, batch 850, loss[loss=0.1768, simple_loss=0.2619, pruned_loss=0.04579, over 7158.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2827, pruned_loss=0.04635, over 1410935.81 frames.], batch size: 17, lr: 5.99e-04
2022-04-29 03:32:27,886 INFO [train.py:763] (5/8) Epoch 12, batch 900, loss[loss=0.1857, simple_loss=0.2794, pruned_loss=0.04603, over 7336.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2815, pruned_loss=0.04642, over 1413901.88 frames.], batch size: 20, lr: 5.99e-04
2022-04-29 03:33:44,139 INFO [train.py:763] (5/8) Epoch 12, batch 950, loss[loss=0.1827, simple_loss=0.2837, pruned_loss=0.04083, over 7166.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2811, pruned_loss=0.04611, over 1414766.87 frames.], batch size: 26, lr: 5.98e-04
2022-04-29 03:34:49,746 INFO [train.py:763] (5/8) Epoch 12, batch 1000, loss[loss=0.2071, simple_loss=0.3027, pruned_loss=0.05578, over 6603.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2819, pruned_loss=0.04653, over 1415167.55 frames.], batch size: 38, lr: 5.98e-04
2022-04-29 03:35:56,217 INFO [train.py:763] (5/8) Epoch 12, batch 1050, loss[loss=0.1818, simple_loss=0.2692, pruned_loss=0.04717, over 7249.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2809, pruned_loss=0.04635, over 1416342.25 frames.], batch size: 19, lr: 5.98e-04
2022-04-29 03:37:02,301 INFO [train.py:763] (5/8) Epoch 12, batch 1100, loss[loss=0.1884, simple_loss=0.2853, pruned_loss=0.0457, over 7385.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2813, pruned_loss=0.04611, over 1422472.14 frames.], batch size: 23, lr: 5.97e-04
2022-04-29 03:38:08,897 INFO [train.py:763] (5/8) Epoch 12, batch 1150, loss[loss=0.1822, simple_loss=0.2761, pruned_loss=0.04416, over 7318.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2811, pruned_loss=0.04664, over 1425324.13 frames.], batch size: 20, lr: 5.97e-04
2022-04-29 03:39:15,123 INFO [train.py:763] (5/8) Epoch 12, batch 1200, loss[loss=0.2225, simple_loss=0.301, pruned_loss=0.07203, over 5108.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2812, pruned_loss=0.04698, over 1421971.86 frames.], batch size: 53, lr: 5.97e-04
2022-04-29 03:40:21,635 INFO [train.py:763] (5/8) Epoch 12, batch 1250, loss[loss=0.174, simple_loss=0.2704, pruned_loss=0.03881, over 7152.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2816, pruned_loss=0.04689, over 1419435.27 frames.], batch size: 19, lr: 5.97e-04
2022-04-29 03:41:28,269 INFO [train.py:763] (5/8) Epoch 12, batch 1300, loss[loss=0.1647, simple_loss=0.265, pruned_loss=0.03218, over 7068.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2812, pruned_loss=0.04632, over 1419525.16 frames.], batch size: 18, lr: 5.96e-04
2022-04-29 03:42:33,930 INFO [train.py:763] (5/8) Epoch 12, batch 1350, loss[loss=0.2428, simple_loss=0.3178, pruned_loss=0.08393, over 5079.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2831, pruned_loss=0.04729, over 1416425.86 frames.], batch size: 53, lr: 5.96e-04
2022-04-29 03:43:39,831 INFO [train.py:763] (5/8) Epoch 12, batch 1400, loss[loss=0.1858, simple_loss=0.279, pruned_loss=0.04631, over 7327.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2831, pruned_loss=0.04723, over 1415780.50 frames.], batch size: 25, lr: 5.96e-04
2022-04-29 03:44:45,264 INFO [train.py:763] (5/8) Epoch 12, batch 1450, loss[loss=0.2013, simple_loss=0.2952, pruned_loss=0.05373, over 7329.00 frames.], tot_loss[loss=0.1886, simple_loss=0.283, pruned_loss=0.04705, over 1414511.72 frames.], batch size: 21, lr: 5.96e-04
2022-04-29 03:45:51,851 INFO [train.py:763] (5/8) Epoch 12, batch 1500, loss[loss=0.1878, simple_loss=0.2909, pruned_loss=0.04237, over 7190.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2822, pruned_loss=0.04669, over 1418138.12 frames.], batch size: 23, lr: 5.95e-04
2022-04-29 03:46:59,223 INFO [train.py:763] (5/8) Epoch 12, batch 1550, loss[loss=0.2238, simple_loss=0.3248, pruned_loss=0.0614, over 6989.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.04659, over 1419593.77 frames.], batch size: 28, lr: 5.95e-04
2022-04-29 03:48:05,687 INFO [train.py:763] (5/8) Epoch 12, batch 1600, loss[loss=0.1909, simple_loss=0.2888, pruned_loss=0.04646, over 7302.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2828, pruned_loss=0.04708, over 1419078.31 frames.], batch size: 25, lr: 5.95e-04
2022-04-29 03:49:11,832 INFO [train.py:763] (5/8) Epoch 12, batch 1650, loss[loss=0.2063, simple_loss=0.2975, pruned_loss=0.05751, over 7301.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2818, pruned_loss=0.04669, over 1422413.06 frames.], batch size: 24, lr: 5.95e-04
2022-04-29 03:50:17,597 INFO [train.py:763] (5/8) Epoch 12, batch 1700, loss[loss=0.1915, simple_loss=0.2727, pruned_loss=0.05515, over 7128.00 frames.], tot_loss[loss=0.187, simple_loss=0.2812, pruned_loss=0.04638, over 1418990.18 frames.], batch size: 17, lr: 5.94e-04
2022-04-29 03:51:23,279 INFO [train.py:763] (5/8) Epoch 12, batch 1750, loss[loss=0.1779, simple_loss=0.2829, pruned_loss=0.03643, over 7158.00 frames.], tot_loss[loss=0.1859, simple_loss=0.28, pruned_loss=0.04586, over 1422356.87 frames.], batch size: 26, lr: 5.94e-04
2022-04-29 03:52:29,192 INFO [train.py:763] (5/8) Epoch 12, batch 1800, loss[loss=0.1417, simple_loss=0.2315, pruned_loss=0.02595, over 7010.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2799, pruned_loss=0.04616, over 1427623.46 frames.], batch size: 16, lr: 5.94e-04
2022-04-29 03:53:35,428 INFO [train.py:763] (5/8) Epoch 12, batch 1850, loss[loss=0.1789, simple_loss=0.2854, pruned_loss=0.0362, over 7333.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2808, pruned_loss=0.04645, over 1428351.43 frames.], batch size: 22, lr: 5.94e-04
2022-04-29 03:54:41,520 INFO [train.py:763] (5/8) Epoch 12, batch 1900, loss[loss=0.1825, simple_loss=0.2873, pruned_loss=0.03889, over 7234.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2803, pruned_loss=0.0461, over 1428715.13 frames.], batch size: 20, lr: 5.93e-04
2022-04-29 03:55:47,388 INFO [train.py:763] (5/8) Epoch 12, batch 1950, loss[loss=0.1674, simple_loss=0.2602, pruned_loss=0.0373, over 7283.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2807, pruned_loss=0.04633, over 1428868.34 frames.], batch size: 17, lr: 5.93e-04
2022-04-29 03:56:53,851 INFO [train.py:763] (5/8) Epoch 12, batch 2000, loss[loss=0.1595, simple_loss=0.2467, pruned_loss=0.03613, over 7005.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2793, pruned_loss=0.04592, over 1428231.60 frames.], batch size: 16, lr: 5.93e-04
2022-04-29 03:57:59,761 INFO [train.py:763] (5/8) Epoch 12, batch 2050, loss[loss=0.2049, simple_loss=0.3002, pruned_loss=0.05475, over 7153.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2796, pruned_loss=0.04639, over 1421286.55 frames.], batch size: 19, lr: 5.93e-04
2022-04-29 03:59:05,466 INFO [train.py:763] (5/8) Epoch 12, batch 2100, loss[loss=0.1609, simple_loss=0.2555, pruned_loss=0.03314, over 7155.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2803, pruned_loss=0.04693, over 1421316.16 frames.], batch size: 19, lr: 5.92e-04
2022-04-29 04:00:11,339 INFO [train.py:763] (5/8) Epoch 12, batch 2150, loss[loss=0.1946, simple_loss=0.2886, pruned_loss=0.05031, over 7272.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2811, pruned_loss=0.04671, over 1421498.84 frames.], batch size: 18, lr: 5.92e-04
2022-04-29 04:01:17,164 INFO [train.py:763] (5/8) Epoch 12, batch 2200, loss[loss=0.1809, simple_loss=0.2794, pruned_loss=0.04123, over 7318.00 frames.], tot_loss[loss=0.1863, simple_loss=0.28, pruned_loss=0.0463, over 1422455.99 frames.], batch size: 20, lr: 5.92e-04
2022-04-29 04:02:23,230 INFO [train.py:763] (5/8) Epoch 12, batch 2250, loss[loss=0.193, simple_loss=0.2962, pruned_loss=0.0449, over 7052.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2803, pruned_loss=0.04612, over 1421334.89 frames.], batch size: 28, lr: 5.91e-04
2022-04-29 04:03:29,740 INFO [train.py:763] (5/8) Epoch 12, batch 2300, loss[loss=0.1898, simple_loss=0.2868, pruned_loss=0.04639, over 7116.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2806, pruned_loss=0.04633, over 1424914.38 frames.], batch size: 21, lr: 5.91e-04
2022-04-29 04:04:36,294 INFO [train.py:763] (5/8) Epoch 12, batch 2350, loss[loss=0.1793, simple_loss=0.2794, pruned_loss=0.03958, over 7163.00 frames.], tot_loss[loss=0.187, simple_loss=0.2812, pruned_loss=0.04637, over 1426375.69 frames.], batch size: 19, lr: 5.91e-04
2022-04-29 04:05:42,057 INFO [train.py:763] (5/8) Epoch 12, batch 2400, loss[loss=0.1569, simple_loss=0.2477, pruned_loss=0.03306, over 7149.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2804, pruned_loss=0.04619, over 1427093.62 frames.], batch size: 17, lr: 5.91e-04
2022-04-29 04:06:47,903 INFO [train.py:763] (5/8) Epoch 12, batch 2450, loss[loss=0.1731, simple_loss=0.2789, pruned_loss=0.03363, over 7218.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2804, pruned_loss=0.04639, over 1426739.18 frames.], batch size: 21, lr: 5.90e-04
2022-04-29 04:07:54,995 INFO [train.py:763] (5/8) Epoch 12, batch 2500, loss[loss=0.1948, simple_loss=0.284, pruned_loss=0.05277, over 7293.00 frames.], tot_loss[loss=0.1881, simple_loss=0.282, pruned_loss=0.04704, over 1426957.30 frames.], batch size: 18, lr: 5.90e-04
2022-04-29 04:09:01,292 INFO [train.py:763] (5/8) Epoch 12, batch 2550, loss[loss=0.1677, simple_loss=0.2593, pruned_loss=0.03805, over 7242.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2828, pruned_loss=0.04751, over 1428425.31 frames.], batch size: 16, lr: 5.90e-04
2022-04-29 04:10:08,005 INFO [train.py:763] (5/8) Epoch 12, batch 2600, loss[loss=0.1707, simple_loss=0.2659, pruned_loss=0.03773, over 7244.00 frames.], tot_loss[loss=0.189, simple_loss=0.2828, pruned_loss=0.04766, over 1424762.82 frames.], batch size: 16, lr: 5.90e-04
2022-04-29 04:11:13,663 INFO [train.py:763] (5/8) Epoch 12, batch 2650, loss[loss=0.1652, simple_loss=0.2537, pruned_loss=0.03837, over 6976.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2825, pruned_loss=0.04718, over 1423140.38 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:12:19,561 INFO [train.py:763] (5/8) Epoch 12, batch 2700, loss[loss=0.1744, simple_loss=0.2571, pruned_loss=0.04582, over 6990.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.04664, over 1424368.31 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:13:25,173 INFO [train.py:763] (5/8) Epoch 12, batch 2750, loss[loss=0.2376, simple_loss=0.3288, pruned_loss=0.07321, over 7116.00 frames.], tot_loss[loss=0.188, simple_loss=0.2823, pruned_loss=0.04685, over 1421682.76 frames.], batch size: 21, lr: 5.89e-04
2022-04-29 04:14:30,849 INFO [train.py:763] (5/8) Epoch 12, batch 2800, loss[loss=0.151, simple_loss=0.2419, pruned_loss=0.03008, over 7121.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2822, pruned_loss=0.04662, over 1420891.06 frames.], batch size: 17, lr: 5.89e-04
2022-04-29 04:15:37,564 INFO [train.py:763] (5/8) Epoch 12, batch 2850, loss[loss=0.1844, simple_loss=0.2872, pruned_loss=0.04075, over 7394.00 frames.], tot_loss[loss=0.188, simple_loss=0.2828, pruned_loss=0.04653, over 1427052.47 frames.], batch size: 23, lr: 5.88e-04
2022-04-29 04:16:43,245 INFO [train.py:763] (5/8) Epoch 12, batch 2900, loss[loss=0.1499, simple_loss=0.2458, pruned_loss=0.027, over 7352.00 frames.], tot_loss[loss=0.1888, simple_loss=0.284, pruned_loss=0.04681, over 1424693.30 frames.], batch size: 19, lr: 5.88e-04
2022-04-29 04:17:49,205 INFO [train.py:763] (5/8) Epoch 12, batch 2950, loss[loss=0.1829, simple_loss=0.2893, pruned_loss=0.0383, over 7111.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2823, pruned_loss=0.04605, over 1426194.61 frames.], batch size: 21, lr: 5.88e-04
2022-04-29 04:18:54,870 INFO [train.py:763] (5/8) Epoch 12, batch 3000, loss[loss=0.1497, simple_loss=0.2431, pruned_loss=0.02819, over 7278.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2829, pruned_loss=0.04667, over 1426406.70 frames.], batch size: 17, lr: 5.88e-04
2022-04-29 04:18:54,871 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 04:19:10,345 INFO [train.py:792] (5/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
2022-04-29 04:20:16,212 INFO [train.py:763] (5/8) Epoch 12, batch 3050, loss[loss=0.1503, simple_loss=0.2313, pruned_loss=0.03459, over 7143.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2823, pruned_loss=0.04628, over 1427850.66 frames.], batch size: 17, lr: 5.87e-04
2022-04-29 04:21:32,117 INFO [train.py:763] (5/8) Epoch 12, batch 3100, loss[loss=0.1798, simple_loss=0.2746, pruned_loss=0.04252, over 7106.00 frames.], tot_loss[loss=0.187, simple_loss=0.2815, pruned_loss=0.04621, over 1427119.24 frames.], batch size: 21, lr: 5.87e-04
2022-04-29 04:22:37,476 INFO [train.py:763] (5/8) Epoch 12, batch 3150, loss[loss=0.2211, simple_loss=0.3173, pruned_loss=0.06243, over 7336.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2824, pruned_loss=0.04672, over 1424623.21 frames.], batch size: 25, lr: 5.87e-04
2022-04-29 04:23:52,374 INFO [train.py:763] (5/8) Epoch 12, batch 3200, loss[loss=0.2375, simple_loss=0.3174, pruned_loss=0.07878, over 5015.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2819, pruned_loss=0.04643, over 1425607.04 frames.], batch size: 52, lr: 5.87e-04
2022-04-29 04:25:17,149 INFO [train.py:763] (5/8) Epoch 12, batch 3250, loss[loss=0.15, simple_loss=0.2333, pruned_loss=0.03337, over 7279.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2811, pruned_loss=0.04621, over 1429210.90 frames.], batch size: 17, lr: 5.86e-04
2022-04-29 04:26:23,038 INFO [train.py:763] (5/8) Epoch 12, batch 3300, loss[loss=0.1923, simple_loss=0.2862, pruned_loss=0.04923, over 7321.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2815, pruned_loss=0.04638, over 1428500.48 frames.], batch size: 20, lr: 5.86e-04
2022-04-29 04:27:37,939 INFO [train.py:763] (5/8) Epoch 12, batch 3350, loss[loss=0.1685, simple_loss=0.2582, pruned_loss=0.0394, over 6996.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2816, pruned_loss=0.04667, over 1421023.31 frames.], batch size: 16, lr: 5.86e-04
2022-04-29 04:29:03,563 INFO [train.py:763] (5/8) Epoch 12, batch 3400, loss[loss=0.2057, simple_loss=0.2972, pruned_loss=0.05707, over 7363.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2821, pruned_loss=0.0469, over 1424688.42 frames.], batch size: 23, lr: 5.86e-04
2022-04-29 04:30:18,598 INFO [train.py:763] (5/8) Epoch 12, batch 3450, loss[loss=0.1611, simple_loss=0.2565, pruned_loss=0.03287, over 7406.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2825, pruned_loss=0.04701, over 1413864.20 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:31:24,838 INFO [train.py:763] (5/8) Epoch 12, batch 3500, loss[loss=0.1827, simple_loss=0.2861, pruned_loss=0.03966, over 6777.00 frames.], tot_loss[loss=0.188, simple_loss=0.2823, pruned_loss=0.04686, over 1415985.82 frames.], batch size: 31, lr: 5.85e-04
2022-04-29 04:32:31,892 INFO [train.py:763] (5/8) Epoch 12, batch 3550, loss[loss=0.1535, simple_loss=0.2384, pruned_loss=0.03429, over 7016.00 frames.], tot_loss[loss=0.1879, simple_loss=0.282, pruned_loss=0.04692, over 1422400.46 frames.], batch size: 16, lr: 5.85e-04
2022-04-29 04:33:38,545 INFO [train.py:763] (5/8) Epoch 12, batch 3600, loss[loss=0.191, simple_loss=0.2837, pruned_loss=0.04916, over 7291.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2823, pruned_loss=0.04695, over 1422534.39 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:34:44,023 INFO [train.py:763] (5/8) Epoch 12, batch 3650, loss[loss=0.2155, simple_loss=0.3105, pruned_loss=0.06021, over 7413.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.0466, over 1425410.93 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:35:49,782 INFO [train.py:763] (5/8) Epoch 12, batch 3700, loss[loss=0.179, simple_loss=0.2689, pruned_loss=0.04457, over 7252.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2812, pruned_loss=0.04626, over 1426419.17 frames.], batch size: 19, lr: 5.84e-04
2022-04-29 04:36:55,384 INFO [train.py:763] (5/8) Epoch 12, batch 3750, loss[loss=0.1758, simple_loss=0.2727, pruned_loss=0.03941, over 7412.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2813, pruned_loss=0.04621, over 1426890.60 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:38:01,439 INFO [train.py:763] (5/8) Epoch 12, batch 3800, loss[loss=0.1862, simple_loss=0.288, pruned_loss=0.04219, over 7015.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2815, pruned_loss=0.04617, over 1430279.23 frames.], batch size: 28, lr: 5.84e-04
2022-04-29 04:39:06,792 INFO [train.py:763] (5/8) Epoch 12, batch 3850, loss[loss=0.1876, simple_loss=0.2879, pruned_loss=0.04359, over 7207.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2821, pruned_loss=0.04622, over 1426780.14 frames.], batch size: 22, lr: 5.83e-04
2022-04-29 04:40:13,171 INFO [train.py:763] (5/8) Epoch 12, batch 3900, loss[loss=0.2025, simple_loss=0.2997, pruned_loss=0.05262, over 7307.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2818, pruned_loss=0.04633, over 1425379.62 frames.], batch size: 24, lr: 5.83e-04
2022-04-29 04:41:18,543 INFO [train.py:763] (5/8) Epoch 12, batch 3950, loss[loss=0.1744, simple_loss=0.2692, pruned_loss=0.03982, over 7197.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2823, pruned_loss=0.04672, over 1424836.19 frames.], batch size: 23, lr: 5.83e-04
2022-04-29 04:42:24,208 INFO [train.py:763] (5/8) Epoch 12, batch 4000, loss[loss=0.1746, simple_loss=0.2637, pruned_loss=0.04275, over 7133.00 frames.], tot_loss[loss=0.1876, simple_loss=0.282, pruned_loss=0.04656, over 1424084.18 frames.], batch size: 17, lr: 5.83e-04
2022-04-29 04:43:29,493 INFO [train.py:763] (5/8) Epoch 12, batch 4050, loss[loss=0.1966, simple_loss=0.2983, pruned_loss=0.04742, over 7238.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2812, pruned_loss=0.04594, over 1425656.86 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:44:35,692 INFO [train.py:763] (5/8) Epoch 12, batch 4100, loss[loss=0.2185, simple_loss=0.3086, pruned_loss=0.06424, over 7141.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2808, pruned_loss=0.04555, over 1425239.85 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:45:41,166 INFO [train.py:763] (5/8) Epoch 12, batch 4150, loss[loss=0.1688, simple_loss=0.2701, pruned_loss=0.0337, over 7427.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2823, pruned_loss=0.0458, over 1420381.51 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:46:48,359 INFO [train.py:763] (5/8) Epoch 12, batch 4200, loss[loss=0.1922, simple_loss=0.2921, pruned_loss=0.04618, over 7152.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2812, pruned_loss=0.04519, over 1422117.14 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:47:54,431 INFO [train.py:763] (5/8) Epoch 12, batch 4250, loss[loss=0.1857, simple_loss=0.2972, pruned_loss=0.03707, over 7121.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2805, pruned_loss=0.04493, over 1418632.34 frames.], batch size: 26, lr: 5.81e-04
2022-04-29 04:49:00,807 INFO [train.py:763] (5/8) Epoch 12, batch 4300, loss[loss=0.166, simple_loss=0.2631, pruned_loss=0.03442, over 7427.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2809, pruned_loss=0.04575, over 1415181.97 frames.], batch size: 20, lr: 5.81e-04
2022-04-29 04:50:06,813 INFO [train.py:763] (5/8) Epoch 12, batch 4350, loss[loss=0.173, simple_loss=0.2525, pruned_loss=0.0467, over 7018.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2809, pruned_loss=0.04602, over 1410502.69 frames.], batch size: 16, lr: 5.81e-04
2022-04-29 04:51:13,422 INFO [train.py:763] (5/8) Epoch 12, batch 4400, loss[loss=0.2166, simple_loss=0.2966, pruned_loss=0.06833, over 5132.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2792, pruned_loss=0.04549, over 1409251.83 frames.], batch size: 52, lr: 5.81e-04
2022-04-29 04:52:19,274 INFO [train.py:763] (5/8) Epoch 12, batch 4450, loss[loss=0.2163, simple_loss=0.3099, pruned_loss=0.06137, over 7295.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2782, pruned_loss=0.04508, over 1406720.50 frames.], batch size: 24, lr: 5.81e-04
2022-04-29 04:53:25,187 INFO [train.py:763] (5/8) Epoch 12, batch 4500, loss[loss=0.1949, simple_loss=0.2909, pruned_loss=0.04947, over 7415.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2804, pruned_loss=0.0463, over 1387959.65 frames.], batch size: 21, lr: 5.80e-04
2022-04-29 04:54:31,139 INFO [train.py:763] (5/8) Epoch 12, batch 4550, loss[loss=0.2179, simple_loss=0.299, pruned_loss=0.06845, over 5416.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2834, pruned_loss=0.04787, over 1354103.88 frames.], batch size: 52, lr: 5.80e-04
2022-04-29 04:56:09,897 INFO [train.py:763] (5/8) Epoch 13, batch 0, loss[loss=0.1966, simple_loss=0.2884, pruned_loss=0.05234, over 7375.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2884, pruned_loss=0.05234, over 7375.00 frames.], batch size: 23, lr: 5.61e-04
2022-04-29 04:57:15,975 INFO [train.py:763] (5/8) Epoch 13, batch 50, loss[loss=0.2128, simple_loss=0.3079, pruned_loss=0.05883, over 7125.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2757, pruned_loss=0.04422, over 322597.83 frames.], batch size: 21, lr: 5.61e-04
2022-04-29 04:58:22,266 INFO [train.py:763] (5/8) Epoch 13, batch 100, loss[loss=0.1945, simple_loss=0.2876, pruned_loss=0.05068, over 7154.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2781, pruned_loss=0.04429, over 572452.04 frames.], batch size: 20, lr: 5.61e-04
2022-04-29 04:59:28,183 INFO [train.py:763] (5/8) Epoch 13, batch 150, loss[loss=0.1759, simple_loss=0.258, pruned_loss=0.04687, over 7001.00 frames.], tot_loss[loss=0.1835, simple_loss=0.278, pruned_loss=0.04446, over 763100.54 frames.], batch size: 16, lr: 5.61e-04
2022-04-29 05:00:33,627 INFO [train.py:763] (5/8) Epoch 13, batch 200, loss[loss=0.1904, simple_loss=0.3021, pruned_loss=0.03938, over 7192.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2791, pruned_loss=0.04453, over 909723.24 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:01:39,405 INFO [train.py:763] (5/8) Epoch 13, batch 250, loss[loss=0.2144, simple_loss=0.3088, pruned_loss=0.05995, over 7214.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2793, pruned_loss=0.0446, over 1025788.65 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:02:44,826 INFO [train.py:763] (5/8) Epoch 13, batch 300, loss[loss=0.1776, simple_loss=0.2847, pruned_loss=0.03524, over 7412.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2814, pruned_loss=0.04562, over 1112702.12 frames.], batch size: 21, lr: 5.60e-04
2022-04-29 05:03:50,339 INFO [train.py:763] (5/8) Epoch 13, batch 350, loss[loss=0.1685, simple_loss=0.2638, pruned_loss=0.03662, over 7427.00 frames.], tot_loss[loss=0.1854, simple_loss=0.28, pruned_loss=0.04542, over 1181351.30 frames.], batch size: 20, lr: 5.60e-04
2022-04-29 05:04:55,872 INFO [train.py:763] (5/8) Epoch 13, batch 400, loss[loss=0.1979, simple_loss=0.2915, pruned_loss=0.05213, over 7049.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2798, pruned_loss=0.04506, over 1231219.16 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:06:01,972 INFO [train.py:763] (5/8) Epoch 13, batch 450, loss[loss=0.1772, simple_loss=0.2841, pruned_loss=0.03518, over 6537.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2801, pruned_loss=0.04533, over 1273026.25 frames.], batch size: 38, lr: 5.59e-04
2022-04-29 05:07:07,987 INFO [train.py:763] (5/8) Epoch 13, batch 500, loss[loss=0.1937, simple_loss=0.2867, pruned_loss=0.05037, over 7027.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2794, pruned_loss=0.04503, over 1300265.79 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:08:13,631 INFO [train.py:763] (5/8) Epoch 13, batch 550, loss[loss=0.1496, simple_loss=0.2637, pruned_loss=0.01772, over 6518.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2795, pruned_loss=0.04465, over 1325708.29 frames.], batch size: 38, lr: 5.59e-04
2022-04-29 05:09:19,625 INFO [train.py:763] (5/8) Epoch 13, batch 600, loss[loss=0.1963, simple_loss=0.2917, pruned_loss=0.05043, over 7323.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2789, pruned_loss=0.04433, over 1348035.62 frames.], batch size: 21, lr: 5.59e-04
2022-04-29 05:10:25,767 INFO [train.py:763] (5/8) Epoch 13, batch 650, loss[loss=0.2049, simple_loss=0.2966, pruned_loss=0.0566, over 7053.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2805, pruned_loss=0.04518, over 1360493.83 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:11:32,553 INFO [train.py:763] (5/8) Epoch 13, batch 700, loss[loss=0.1585, simple_loss=0.2609, pruned_loss=0.02807, over 7265.00 frames.], tot_loss[loss=0.1849, simple_loss=0.28, pruned_loss=0.0449, over 1376604.35 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:12:37,750 INFO [train.py:763] (5/8) Epoch 13, batch 750, loss[loss=0.2205, simple_loss=0.3061, pruned_loss=0.06751, over 7189.00 frames.], tot_loss[loss=0.185, simple_loss=0.2799, pruned_loss=0.04502, over 1383481.27 frames.], batch size: 23, lr: 5.58e-04
2022-04-29 05:13:44,383 INFO [train.py:763] (5/8) Epoch 13, batch 800, loss[loss=0.2362, simple_loss=0.3287, pruned_loss=0.07184, over 7278.00 frames.], tot_loss[loss=0.186, simple_loss=0.2812, pruned_loss=0.04542, over 1392481.91 frames.], batch size: 25, lr: 5.58e-04
2022-04-29 05:14:50,894 INFO [train.py:763] (5/8) Epoch 13, batch 850, loss[loss=0.1755, simple_loss=0.281, pruned_loss=0.03501, over 7219.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2804, pruned_loss=0.04514, over 1401026.23 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:15:57,552 INFO [train.py:763] (5/8) Epoch 13, batch 900, loss[loss=0.1641, simple_loss=0.2526, pruned_loss=0.0378, over 7163.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2803, pruned_loss=0.04517, over 1403634.00 frames.], batch size: 18, lr: 5.57e-04
2022-04-29 05:17:04,249 INFO [train.py:763] (5/8) Epoch 13, batch 950, loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03044, over 7227.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2808, pruned_loss=0.0451, over 1403780.18 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:18:11,100 INFO [train.py:763] (5/8) Epoch 13, batch 1000, loss[loss=0.1949, simple_loss=0.2949, pruned_loss=0.04751, over 7204.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2808, pruned_loss=0.04522, over 1410999.90 frames.], batch size: 22, lr: 5.57e-04
2022-04-29 05:19:17,018 INFO [train.py:763] (5/8) Epoch 13, batch 1050, loss[loss=0.1988, simple_loss=0.2962, pruned_loss=0.05069, over 7425.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2799, pruned_loss=0.0452, over 1410996.32 frames.], batch size: 21, lr: 5.56e-04
2022-04-29 05:20:22,749 INFO [train.py:763] (5/8) Epoch 13, batch 1100, loss[loss=0.224, simple_loss=0.3247, pruned_loss=0.06164, over 6774.00 frames.], tot_loss[loss=0.186, simple_loss=0.2806, pruned_loss=0.0457, over 1410299.57 frames.], batch size: 31, lr: 5.56e-04
2022-04-29 05:21:28,737 INFO [train.py:763] (5/8) Epoch 13, batch 1150, loss[loss=0.2176, simple_loss=0.3023, pruned_loss=0.06647, over 7329.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2814, pruned_loss=0.04607, over 1410557.84 frames.], batch size: 22, lr: 5.56e-04
2022-04-29 05:22:34,611 INFO [train.py:763] (5/8) Epoch 13, batch 1200, loss[loss=0.2113, simple_loss=0.2988, pruned_loss=0.06187, over 4819.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2813, pruned_loss=0.04613, over 1409524.97 frames.], batch size: 52, lr: 5.56e-04
2022-04-29 05:23:40,307 INFO [train.py:763] (5/8) Epoch 13, batch 1250, loss[loss=0.185, simple_loss=0.2679, pruned_loss=0.05109, over 7437.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2819, pruned_loss=0.04618, over 1413856.71 frames.], batch size: 20, lr: 5.56e-04
2022-04-29 05:24:45,586 INFO [train.py:763] (5/8) Epoch 13, batch 1300, loss[loss=0.1933, simple_loss=0.2976, pruned_loss=0.04454, over 7251.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2817, pruned_loss=0.04572, over 1417522.79 frames.], batch size: 19, lr: 5.55e-04
2022-04-29 05:25:51,467 INFO [train.py:763] (5/8) Epoch 13, batch 1350, loss[loss=0.1789, simple_loss=0.2788, pruned_loss=0.0395, over 7270.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2804, pruned_loss=0.04554, over 1421335.52 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:26:57,112 INFO [train.py:763] (5/8) Epoch 13, batch 1400, loss[loss=0.1597, simple_loss=0.255, pruned_loss=0.03217, over 7158.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2812, pruned_loss=0.04593, over 1417143.10 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:28:02,598 INFO [train.py:763] (5/8) Epoch 13, batch 1450, loss[loss=0.1759, simple_loss=0.2561, pruned_loss=0.04789, over 7275.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2818, pruned_loss=0.04576, over 1420868.77 frames.], batch size: 17, lr: 5.55e-04
2022-04-29 05:29:08,111 INFO [train.py:763] (5/8) Epoch 13, batch 1500, loss[loss=0.1667, simple_loss=0.2449, pruned_loss=0.04421, over 7289.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2802, pruned_loss=0.0451, over 1422348.58 frames.], batch size: 17, lr: 5.54e-04
2022-04-29 05:30:14,053 INFO [train.py:763] (5/8) Epoch 13, batch 1550, loss[loss=0.1872, simple_loss=0.2951, pruned_loss=0.03962, over 6268.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2796, pruned_loss=0.04445, over 1417941.79 frames.], batch size: 37, lr: 5.54e-04
2022-04-29 05:31:19,488 INFO [train.py:763] (5/8) Epoch 13, batch 1600, loss[loss=0.1626, simple_loss=0.2656, pruned_loss=0.02982, over 7421.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04434, over 1417625.05 frames.], batch size: 21, lr: 5.54e-04
2022-04-29 05:32:25,611 INFO [train.py:763] (5/8) Epoch 13, batch 1650, loss[loss=0.1673, simple_loss=0.2556, pruned_loss=0.03952, over 7247.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2808, pruned_loss=0.04477, over 1419337.26 frames.], batch size: 20, lr: 5.54e-04
2022-04-29 05:33:31,242 INFO [train.py:763] (5/8) Epoch 13, batch 1700, loss[loss=0.204, simple_loss=0.3016, pruned_loss=0.05324, over 6437.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2807, pruned_loss=0.04471, over 1418647.10 frames.], batch size: 37, lr: 5.54e-04
2022-04-29 05:34:36,774 INFO [train.py:763] (5/8) Epoch 13, batch 1750, loss[loss=0.1489, simple_loss=0.2448, pruned_loss=0.02653, over 7286.00 frames.], tot_loss[loss=0.1845, simple_loss=0.28, pruned_loss=0.04451, over 1420998.82 frames.], batch size: 17, lr: 5.53e-04
2022-04-29 05:35:42,706 INFO [train.py:763] (5/8) Epoch 13, batch 1800, loss[loss=0.2093, simple_loss=0.3066, pruned_loss=0.05605, over 7139.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2795, pruned_loss=0.0444, over 1425364.38 frames.], batch size: 20, lr: 5.53e-04
2022-04-29 05:36:48,189 INFO [train.py:763] (5/8) Epoch 13, batch 1850, loss[loss=0.2325, simple_loss=0.3154, pruned_loss=0.0748, over 7272.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04437, over 1425597.59 frames.], batch size: 25, lr: 5.53e-04
2022-04-29 05:37:54,126 INFO [train.py:763] (5/8) Epoch 13, batch 1900, loss[loss=0.1924, simple_loss=0.2854, pruned_loss=0.04969, over 6148.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04453, over 1420454.11 frames.], batch size: 37, lr: 5.53e-04
2022-04-29 05:39:00,693 INFO [train.py:763] (5/8) Epoch 13, batch 1950, loss[loss=0.1795, simple_loss=0.2774, pruned_loss=0.04081, over 7268.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2811, pruned_loss=0.04437, over 1421814.00 frames.], batch size: 19, lr: 5.52e-04
2022-04-29 05:40:07,435 INFO [train.py:763] (5/8) Epoch 13, batch 2000, loss[loss=0.1929, simple_loss=0.2913, pruned_loss=0.04726, over 7341.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2817, pruned_loss=0.04428, over 1423460.86 frames.], batch size: 22, lr: 5.52e-04
2022-04-29 05:41:13,033 INFO [train.py:763] (5/8) Epoch 13, batch 2050, loss[loss=0.202, simple_loss=0.3011, pruned_loss=0.05149, over 7374.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2812, pruned_loss=0.04426, over 1425785.47 frames.], batch size: 23, lr: 5.52e-04
2022-04-29 05:42:18,157 INFO [train.py:763] (5/8) Epoch 13, batch 2100, loss[loss=0.1761, simple_loss=0.2818, pruned_loss=0.03517, over 7230.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2822, pruned_loss=0.04439, over 1425619.99 frames.], batch size: 20, lr: 5.52e-04
2022-04-29 05:43:24,245 INFO [train.py:763] (5/8) Epoch 13, batch 2150, loss[loss=0.1745, simple_loss=0.2816, pruned_loss=0.03371, over 7178.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2811, pruned_loss=0.04417, over 1428101.10 frames.], batch size: 26, lr: 5.52e-04
2022-04-29 05:44:29,799 INFO [train.py:763] (5/8) Epoch 13, batch 2200, loss[loss=0.1838, simple_loss=0.2795, pruned_loss=0.04405, over 7433.00 frames.], tot_loss[loss=0.185, simple_loss=0.2808, pruned_loss=0.04458, over 1426733.76 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:45:35,415 INFO [train.py:763] (5/8) Epoch 13, batch 2250, loss[loss=0.1889, simple_loss=0.2791, pruned_loss=0.04931, over 7226.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2807, pruned_loss=0.04457, over 1427737.05 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:46:41,463 INFO [train.py:763] (5/8) Epoch 13, batch 2300, loss[loss=0.1939, simple_loss=0.287, pruned_loss=0.05042, over 7064.00 frames.], tot_loss[loss=0.183, simple_loss=0.2784, pruned_loss=0.04375, over 1428416.30 frames.], batch size: 28, lr: 5.51e-04
2022-04-29 05:47:46,900 INFO [train.py:763] (5/8) Epoch 13, batch 2350, loss[loss=0.2448, simple_loss=0.3248, pruned_loss=0.08235, over 5219.00 frames.], tot_loss[loss=0.1837, simple_loss=0.279, pruned_loss=0.04422, over 1427758.92 frames.], batch size: 52, lr: 5.51e-04
2022-04-29 05:48:52,811 INFO [train.py:763] (5/8) Epoch 13, batch 2400, loss[loss=0.1477, simple_loss=0.2318, pruned_loss=0.03181, over 7284.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2784, pruned_loss=0.04368, over 1428605.03 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:49:58,375 INFO [train.py:763] (5/8) Epoch 13, batch 2450, loss[loss=0.2022, simple_loss=0.3019, pruned_loss=0.05124, over 6774.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2786, pruned_loss=0.04394, over 1430555.12 frames.], batch size: 31, lr: 5.50e-04
2022-04-29 05:51:03,653 INFO [train.py:763] (5/8) Epoch 13, batch 2500, loss[loss=0.1443, simple_loss=0.2295, pruned_loss=0.02958, over 7288.00 frames.], tot_loss[loss=0.1837, simple_loss=0.279, pruned_loss=0.04419, over 1427579.61 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:52:08,936 INFO [train.py:763] (5/8) Epoch 13, batch 2550, loss[loss=0.1914, simple_loss=0.2874, pruned_loss=0.04774, over 7295.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2791, pruned_loss=0.04432, over 1424151.45 frames.], batch size: 25, lr: 5.50e-04
2022-04-29 05:53:14,612 INFO [train.py:763] (5/8) Epoch 13, batch 2600, loss[loss=0.1651, simple_loss=0.2677, pruned_loss=0.03127, over 7408.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2789, pruned_loss=0.04442, over 1420738.61 frames.], batch size: 21, lr: 5.50e-04
2022-04-29 05:54:20,024 INFO [train.py:763] (5/8) Epoch 13, batch 2650, loss[loss=0.1964, simple_loss=0.2934, pruned_loss=0.0497, over 7122.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2795, pruned_loss=0.04473, over 1418006.26 frames.], batch size: 21, lr: 5.49e-04
2022-04-29 05:55:25,832 INFO [train.py:763] (5/8) Epoch 13, batch 2700, loss[loss=0.1854, simple_loss=0.2646, pruned_loss=0.05314, over 7424.00 frames.], tot_loss[loss=0.1843, simple_loss=0.279, pruned_loss=0.04476, over 1423945.24 frames.], batch size: 17, lr: 5.49e-04
2022-04-29 05:56:31,329 INFO [train.py:763] (5/8) Epoch 13, batch 2750, loss[loss=0.1966, simple_loss=0.3, pruned_loss=0.04659, over 7280.00 frames.], tot_loss[loss=0.1842, simple_loss=0.279, pruned_loss=0.04474, over 1428284.75 frames.], batch size: 24, lr: 5.49e-04
2022-04-29 05:57:36,896 INFO [train.py:763] (5/8) Epoch 13, batch 2800, loss[loss=0.1528, simple_loss=0.2437, pruned_loss=0.03096, over 7118.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2789, pruned_loss=0.04469, over 1426647.69 frames.], batch size: 17, lr: 5.49e-04
2022-04-29 05:58:42,732 INFO [train.py:763] (5/8) Epoch 13, batch 2850, loss[loss=0.1888, simple_loss=0.2896, pruned_loss=0.04406, over 7411.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2783, pruned_loss=0.04458, over 1428019.67 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 05:59:48,440 INFO [train.py:763] (5/8) Epoch 13, batch 2900, loss[loss=0.163, simple_loss=0.2586, pruned_loss=0.03368, over 7109.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2786, pruned_loss=0.04446, over 1429100.43 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 06:00:53,883 INFO [train.py:763] (5/8) Epoch 13, batch 2950, loss[loss=0.2346, simple_loss=0.32, pruned_loss=0.07462, over 7210.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2799, pruned_loss=0.0446, over 1430369.15 frames.], batch size: 23, lr: 5.48e-04
2022-04-29 06:01:59,750 INFO [train.py:763] (5/8) Epoch 13, batch 3000, loss[loss=0.1892, simple_loss=0.2952, pruned_loss=0.04161, over 7291.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2785, pruned_loss=0.04433, over 1430096.63 frames.], batch size: 24, lr: 5.48e-04
2022-04-29 06:01:59,751 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 06:02:15,158 INFO [train.py:792] (5/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
2022-04-29 06:03:21,970 INFO [train.py:763] (5/8) Epoch 13, batch 3050, loss[loss=0.1872, simple_loss=0.2774, pruned_loss=0.04854, over 7271.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2794, pruned_loss=0.04498, over 1430131.21 frames.], batch size: 17, lr: 5.48e-04
2022-04-29 06:04:29,185 INFO [train.py:763] (5/8) Epoch 13, batch 3100, loss[loss=0.2389, simple_loss=0.3261, pruned_loss=0.07588, over 7183.00 frames.], tot_loss[loss=0.1852, simple_loss=0.28, pruned_loss=0.0452, over 1431374.29 frames.], batch size: 23, lr: 5.47e-04
2022-04-29 06:05:35,709 INFO [train.py:763] (5/8) Epoch 13, batch 3150, loss[loss=0.2003, simple_loss=0.2902, pruned_loss=0.05519, over 5272.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2785, pruned_loss=0.04419, over 1429729.83 frames.], batch size: 52, lr: 5.47e-04
2022-04-29 06:06:41,386 INFO [train.py:763] (5/8) Epoch 13, batch 3200, loss[loss=0.1904, simple_loss=0.2906, pruned_loss=0.0451, over 7335.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2777, pruned_loss=0.04352, over 1430186.81 frames.], batch size: 22, lr: 5.47e-04
2022-04-29 06:07:46,887 INFO [train.py:763] (5/8) Epoch 13, batch 3250, loss[loss=0.2087, simple_loss=0.3002, pruned_loss=0.05864, over 7124.00 frames.], tot_loss[loss=0.1827, simple_loss=0.278, pruned_loss=0.04365, over 1426971.96 frames.], batch size: 26, lr: 5.47e-04
2022-04-29 06:08:52,450 INFO [train.py:763] (5/8) Epoch 13, batch 3300, loss[loss=0.1435, simple_loss=0.2367, pruned_loss=0.0252, over 7173.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2781, pruned_loss=0.04401, over 1424618.58 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:09:57,830 INFO [train.py:763] (5/8) Epoch 13, batch 3350, loss[loss=0.1735, simple_loss=0.2604, pruned_loss=0.04328, over 7386.00 frames.], tot_loss[loss=0.184, simple_loss=0.279, pruned_loss=0.04455, over 1426181.41 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:11:03,352 INFO [train.py:763] (5/8) Epoch 13, batch 3400, loss[loss=0.1654, simple_loss=0.2605, pruned_loss=0.03514, over 7165.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2788, pruned_loss=0.04449, over 1427179.03 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:12:10,257 INFO [train.py:763] (5/8) Epoch 13, batch 3450, loss[loss=0.1793, simple_loss=0.2894, pruned_loss=0.03462, over 7116.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04438, over 1426505.19 frames.], batch size: 21, lr: 5.46e-04
2022-04-29 06:13:16,592 INFO [train.py:763] (5/8) Epoch 13, batch 3500, loss[loss=0.192, simple_loss=0.2917, pruned_loss=0.04614, over 7350.00 frames.], tot_loss[loss=0.1832, simple_loss=0.278, pruned_loss=0.04414, over 1427674.55 frames.], batch size: 22, lr: 5.46e-04
2022-04-29 06:14:22,087 INFO [train.py:763] (5/8) Epoch 13, batch 3550, loss[loss=0.2144, simple_loss=0.3119, pruned_loss=0.0584, over 7324.00 frames.], tot_loss[loss=0.184, simple_loss=0.279, pruned_loss=0.04455, over 1428043.69 frames.], batch size: 21, lr: 5.45e-04
2022-04-29 06:15:27,782 INFO [train.py:763] (5/8) Epoch 13, batch 3600, loss[loss=0.1715, simple_loss=0.2687, pruned_loss=0.03717, over 7360.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2776, pruned_loss=0.04405, over 1430585.18 frames.], batch size: 19, lr: 5.45e-04
2022-04-29 06:16:33,714 INFO [train.py:763] (5/8) Epoch 13, batch 3650, loss[loss=0.1944, simple_loss=0.2939, pruned_loss=0.04741, over 7234.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2773, pruned_loss=0.04398, over 1430804.26 frames.], batch size: 20, lr: 5.45e-04
2022-04-29 06:17:39,185 INFO [train.py:763] (5/8) Epoch 13, batch 3700, loss[loss=0.2038, simple_loss=0.2983, pruned_loss=0.05462, over 7251.00 frames.], tot_loss[loss=0.184, simple_loss=0.2785, pruned_loss=0.04474, over 1421682.63 frames.], batch size: 24, lr: 5.45e-04
2022-04-29 06:18:44,839 INFO [train.py:763] (5/8) Epoch 13, batch 3750, loss[loss=0.2218, simple_loss=0.299, pruned_loss=0.07232, over 5113.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2795, pruned_loss=0.04502, over 1421068.43 frames.], batch size: 53, lr: 5.45e-04
2022-04-29 06:19:51,474 INFO [train.py:763] (5/8) Epoch 13, batch 3800, loss[loss=0.1677, simple_loss=0.2588, pruned_loss=0.03833, over 6991.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2796, pruned_loss=0.04488, over 1420320.39 frames.], batch size: 16, lr: 5.44e-04
2022-04-29 06:20:57,113 INFO [train.py:763] (5/8) Epoch 13, batch 3850, loss[loss=0.2018, simple_loss=0.2987, pruned_loss=0.05249, over 7212.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2797, pruned_loss=0.04489, over 1420590.48 frames.], batch size: 22, lr: 5.44e-04
2022-04-29 06:22:02,341 INFO [train.py:763] (5/8) Epoch 13, batch 3900, loss[loss=0.1633, simple_loss=0.2612, pruned_loss=0.03266, over 7320.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2803, pruned_loss=0.04494, over 1422431.74 frames.], batch size: 21, lr: 5.44e-04
2022-04-29 06:23:08,134 INFO [train.py:763] (5/8) Epoch 13, batch 3950, loss[loss=0.2407, simple_loss=0.3089, pruned_loss=0.08626, over 4964.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2788, pruned_loss=0.04405, over 1421005.44 frames.], batch size: 52, lr: 5.44e-04
2022-04-29 06:24:13,274 INFO [train.py:763] (5/8) Epoch 13, batch 4000, loss[loss=0.2168, simple_loss=0.3205, pruned_loss=0.05659, over 7328.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2794, pruned_loss=0.04444, over 1422853.87 frames.], batch size: 22, lr: 5.43e-04
2022-04-29 06:25:19,015 INFO [train.py:763] (5/8) Epoch 13, batch 4050, loss[loss=0.1624, simple_loss=0.2481, pruned_loss=0.03839, over 6847.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2786, pruned_loss=0.04429, over 1424374.15 frames.], batch size: 15, lr: 5.43e-04
2022-04-29 06:26:24,357 INFO [train.py:763] (5/8) Epoch 13, batch 4100, loss[loss=0.1951, simple_loss=0.2943, pruned_loss=0.04792, over 6760.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2789, pruned_loss=0.04472, over 1422019.32 frames.], batch size: 31, lr: 5.43e-04
2022-04-29 06:27:29,974 INFO [train.py:763] (5/8) Epoch 13, batch 4150, loss[loss=0.149, simple_loss=0.2604, pruned_loss=0.01878, over 7210.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2783, pruned_loss=0.04425, over 1420992.20 frames.], batch size: 21, lr: 5.43e-04
2022-04-29 06:28:36,039 INFO [train.py:763] (5/8) Epoch 13, batch 4200, loss[loss=0.1742, simple_loss=0.2654, pruned_loss=0.04153, over 7289.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2769, pruned_loss=0.04389, over 1422522.46 frames.], batch size: 17, lr: 5.43e-04
2022-04-29 06:29:41,319 INFO [train.py:763] (5/8) Epoch 13, batch 4250, loss[loss=0.2, simple_loss=0.2982, pruned_loss=0.05096, over 6348.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2771, pruned_loss=0.04387, over 1416965.23 frames.], batch size: 37, lr: 5.42e-04
2022-04-29 06:30:47,748 INFO [train.py:763] (5/8) Epoch 13, batch 4300, loss[loss=0.1721, simple_loss=0.276, pruned_loss=0.03405, over 7227.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2787, pruned_loss=0.04444, over 1412186.35 frames.], batch size: 21, lr: 5.42e-04
2022-04-29 06:31:53,163 INFO [train.py:763] (5/8) Epoch 13, batch 4350, loss[loss=0.1475, simple_loss=0.2365, pruned_loss=0.02921, over 6820.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2783, pruned_loss=0.04421, over 1408011.17 frames.], batch size: 15, lr: 5.42e-04
2022-04-29 06:33:10,023 INFO [train.py:763] (5/8) Epoch 13, batch 4400, loss[loss=0.1747, simple_loss=0.2787, pruned_loss=0.03533, over 7151.00 frames.], tot_loss[loss=0.183, simple_loss=0.2778, pruned_loss=0.04412, over 1401799.94 frames.], batch size: 20, lr: 5.42e-04
2022-04-29 06:34:14,938 INFO [train.py:763] (5/8) Epoch 13, batch 4450, loss[loss=0.213, simple_loss=0.2928, pruned_loss=0.06663, over 5246.00 frames.], tot_loss[loss=0.1839, simple_loss=0.279, pruned_loss=0.04441, over 1392847.04 frames.], batch size: 52, lr: 5.42e-04
2022-04-29 06:35:30,497 INFO [train.py:763] (5/8) Epoch 13, batch 4500, loss[loss=0.2174, simple_loss=0.3079, pruned_loss=0.06346, over 5101.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2802, pruned_loss=0.04532, over 1377119.03 frames.], batch size: 53, lr: 5.41e-04
2022-04-29 06:36:35,411 INFO [train.py:763] (5/8) Epoch 13, batch 4550, loss[loss=0.2098, simple_loss=0.3067, pruned_loss=0.05639, over 6680.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2814, pruned_loss=0.04594, over 1367497.19 frames.], batch size: 31, lr: 5.41e-04
2022-04-29 06:38:13,967 INFO [train.py:763] (5/8) Epoch 14, batch 0, loss[loss=0.1873, simple_loss=0.2816, pruned_loss=0.04654, over 7076.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2816, pruned_loss=0.04654, over 7076.00 frames.], batch size: 28, lr: 5.25e-04
2022-04-29 06:39:20,738 INFO [train.py:763] (5/8) Epoch 14, batch 50, loss[loss=0.2127, simple_loss=0.302, pruned_loss=0.06163, over 5128.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2801, pruned_loss=0.04315, over 322684.78 frames.], batch size: 53, lr: 5.24e-04
2022-04-29 06:40:45,789 INFO [train.py:763] (5/8) Epoch 14, batch 100, loss[loss=0.1713, simple_loss=0.2575, pruned_loss=0.04254, over 7164.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2805, pruned_loss=0.04401, over 569635.90 frames.], batch size: 18, lr: 5.24e-04
2022-04-29 06:41:59,835 INFO [train.py:763] (5/8) Epoch 14, batch 150, loss[loss=0.1902, simple_loss=0.2884, pruned_loss=0.04603, over 7116.00 frames.], tot_loss[loss=0.1846, simple_loss=0.281, pruned_loss=0.04411, over 759194.12 frames.], batch size: 21, lr: 5.24e-04
2022-04-29 06:43:06,519 INFO [train.py:763] (5/8) Epoch 14, batch 200, loss[loss=0.2043, simple_loss=0.2966, pruned_loss=0.05607, over 7314.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2808, pruned_loss=0.04402, over 903349.67 frames.], batch size: 20, lr: 5.24e-04
2022-04-29 06:44:23,227 INFO [train.py:763] (5/8) Epoch 14, batch 250, loss[loss=0.1896, simple_loss=0.2895, pruned_loss=0.04486, over 6609.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2798, pruned_loss=0.04385, over 1020943.19 frames.], batch size: 38, lr: 5.24e-04
2022-04-29 06:45:48,396 INFO [train.py:763] (5/8) Epoch 14, batch 300, loss[loss=0.164, simple_loss=0.2551, pruned_loss=0.0364, over 7137.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2772, pruned_loss=0.04293, over 1110395.72 frames.], batch size: 17, lr: 5.23e-04
2022-04-29 06:46:55,905 INFO [train.py:763] (5/8) Epoch 14, batch 350, loss[loss=0.162, simple_loss=0.2447, pruned_loss=0.03965, over 6791.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2776, pruned_loss=0.04386, over 1172371.52 frames.], batch size: 15, lr: 5.23e-04
2022-04-29 06:48:03,005 INFO [train.py:763] (5/8) Epoch 14, batch 400, loss[loss=0.162, simple_loss=0.2701, pruned_loss=0.02694, over 7142.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2775, pruned_loss=0.04378, over 1226725.10 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:49:01,689 INFO [train.py:763] (5/8) Epoch 14, batch 450, loss[loss=0.177, simple_loss=0.2787, pruned_loss=0.0377, over 7159.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2764, pruned_loss=0.04305, over 1271048.51 frames.], batch size: 19, lr: 5.23e-04
2022-04-29 06:50:05,442 INFO [train.py:763] (5/8) Epoch 14, batch 500, loss[loss=0.1552, simple_loss=0.2508, pruned_loss=0.02983, over 7433.00 frames.], tot_loss[loss=0.181, simple_loss=0.2767, pruned_loss=0.04261, over 1303170.77 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:51:07,464 INFO [train.py:763] (5/8) Epoch 14, batch 550, loss[loss=0.1761, simple_loss=0.2638, pruned_loss=0.04418, over 7275.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.04234, over 1331962.05 frames.], batch size: 18, lr: 5.22e-04
2022-04-29 06:52:12,675 INFO [train.py:763] (5/8) Epoch 14, batch 600, loss[loss=0.1767, simple_loss=0.2717, pruned_loss=0.04082, over 7235.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.04224, over 1354962.17 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:53:18,176 INFO [train.py:763] (5/8) Epoch 14, batch 650, loss[loss=0.1821, simple_loss=0.2858, pruned_loss=0.03921, over 7332.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04193, over 1369173.84 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:54:23,436 INFO [train.py:763] (5/8) Epoch 14, batch 700, loss[loss=0.169, simple_loss=0.268, pruned_loss=0.03495, over 7343.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2765, pruned_loss=0.04192, over 1382549.95 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:55:28,869 INFO [train.py:763] (5/8) Epoch 14, batch 750, loss[loss=0.1538, simple_loss=0.2673, pruned_loss=0.02018, over 7336.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2765, pruned_loss=0.04194, over 1391468.30 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:56:34,181 INFO [train.py:763] (5/8) Epoch 14, batch 800, loss[loss=0.1689, simple_loss=0.2694, pruned_loss=0.03423, over 7342.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2774, pruned_loss=0.04243, over 1398893.82 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 06:57:40,710 INFO [train.py:763] (5/8) Epoch 14, batch 850, loss[loss=0.1555, simple_loss=0.2421, pruned_loss=0.03446, over 7139.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04293, over 1402287.50 frames.], batch size: 17, lr: 5.21e-04
2022-04-29 06:58:46,057 INFO [train.py:763] (5/8) Epoch 14, batch 900, loss[loss=0.1735, simple_loss=0.2772, pruned_loss=0.03493, over 7253.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2784, pruned_loss=0.04296, over 1398352.73 frames.], batch size: 19, lr: 5.21e-04
2022-04-29 06:59:51,296 INFO [train.py:763] (5/8) Epoch 14, batch 950, loss[loss=0.1993, simple_loss=0.2968, pruned_loss=0.05088, over 7340.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2788, pruned_loss=0.04309, over 1406770.99 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 07:00:56,957 INFO [train.py:763] (5/8) Epoch 14, batch 1000, loss[loss=0.1961, simple_loss=0.2953, pruned_loss=0.04841, over 7060.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2787, pruned_loss=0.04306, over 1408201.76 frames.], batch size: 28, lr: 5.21e-04
2022-04-29 07:02:02,199 INFO [train.py:763] (5/8) Epoch 14, batch 1050, loss[loss=0.173, simple_loss=0.2676, pruned_loss=0.03923, over 7286.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2783, pruned_loss=0.04263, over 1413467.45 frames.], batch size: 18, lr: 5.20e-04
2022-04-29 07:03:07,572 INFO [train.py:763] (5/8) Epoch 14, batch 1100, loss[loss=0.1725, simple_loss=0.2617, pruned_loss=0.04166, over 7294.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2784, pruned_loss=0.04298, over 1417501.67 frames.], batch size: 17, lr: 5.20e-04
2022-04-29 07:04:13,191 INFO [train.py:763] (5/8) Epoch 14, batch 1150, loss[loss=0.1876, simple_loss=0.2876, pruned_loss=0.04377, over 7413.00 frames.], tot_loss[loss=0.182, simple_loss=0.2778, pruned_loss=0.04308, over 1421702.07 frames.], batch size: 21, lr: 5.20e-04
2022-04-29 07:05:18,951 INFO [train.py:763] (5/8) Epoch 14, batch 1200, loss[loss=0.162, simple_loss=0.2648, pruned_loss=0.02965, over 7435.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2766, pruned_loss=0.04229, over 1423238.72 frames.], batch size: 20, lr: 5.20e-04
2022-04-29 07:06:24,249 INFO [train.py:763] (5/8) Epoch 14, batch 1250, loss[loss=0.1713, simple_loss=0.2593, pruned_loss=0.04164, over 7355.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2768, pruned_loss=0.04233, over 1425826.19 frames.], batch size: 19, lr: 5.20e-04
2022-04-29 07:07:29,937 INFO [train.py:763] (5/8) Epoch 14, batch 1300, loss[loss=0.1667, simple_loss=0.2616, pruned_loss=0.03589, over 6313.00 frames.], tot_loss[loss=0.1814, simple_loss=0.277, pruned_loss=0.04286, over 1419730.79 frames.], batch size: 38, lr: 5.19e-04
2022-04-29 07:08:35,857 INFO [train.py:763] (5/8) Epoch 14, batch 1350, loss[loss=0.1615, simple_loss=0.2495, pruned_loss=0.03674, over 6985.00 frames.], tot_loss[loss=0.182, simple_loss=0.2779, pruned_loss=0.04306, over 1421107.69 frames.], batch size: 16, lr: 5.19e-04
2022-04-29 07:09:40,890 INFO [train.py:763] (5/8) Epoch 14, batch 1400, loss[loss=0.212, simple_loss=0.3062, pruned_loss=0.05892, over 7282.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2782, pruned_loss=0.04351, over 1421005.89 frames.], batch size: 24, lr: 5.19e-04
2022-04-29 07:10:46,117 INFO [train.py:763] (5/8) Epoch 14, batch 1450, loss[loss=0.2146, simple_loss=0.3141, pruned_loss=0.05753, over 7374.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2781, pruned_loss=0.04311, over 1417887.53 frames.], batch size: 23, lr: 5.19e-04
2022-04-29 07:11:52,498 INFO [train.py:763] (5/8) Epoch 14, batch 1500, loss[loss=0.1719, simple_loss=0.2694, pruned_loss=0.0372, over 7142.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2784, pruned_loss=0.04318, over 1411643.65 frames.], batch size: 20, lr: 5.19e-04
2022-04-29 07:12:59,718 INFO [train.py:763] (5/8) Epoch 14, batch 1550, loss[loss=0.1536, simple_loss=0.2595, pruned_loss=0.02382, over 7115.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2774, pruned_loss=0.04272, over 1416305.60 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:14:06,978 INFO [train.py:763] (5/8) Epoch 14, batch 1600, loss[loss=0.2093, simple_loss=0.3052, pruned_loss=0.05673, over 7401.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04277, over 1418380.25 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:15:13,442 INFO [train.py:763] (5/8) Epoch 14, batch 1650, loss[loss=0.2017, simple_loss=0.3066, pruned_loss=0.04837, over 7208.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2771, pruned_loss=0.04207, over 1423482.94 frames.], batch size: 23, lr: 5.18e-04
2022-04-29 07:16:19,630 INFO [train.py:763] (5/8) Epoch 14, batch 1700, loss[loss=0.1883, simple_loss=0.2809, pruned_loss=0.04783, over 7298.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2757, pruned_loss=0.04156, over 1427239.47 frames.], batch size: 25, lr: 5.18e-04
2022-04-29 07:17:25,764 INFO [train.py:763] (5/8) Epoch 14, batch 1750, loss[loss=0.1808, simple_loss=0.2841, pruned_loss=0.03879, over 7076.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2759, pruned_loss=0.04169, over 1430996.81 frames.], batch size: 28, lr: 5.18e-04
2022-04-29 07:18:31,000 INFO [train.py:763] (5/8) Epoch 14, batch 1800, loss[loss=0.1443, simple_loss=0.2409, pruned_loss=0.02384, over 7269.00 frames.], tot_loss[loss=0.181, simple_loss=0.2769, pruned_loss=0.04257, over 1427616.66 frames.], batch size: 17, lr: 5.17e-04
2022-04-29 07:19:36,655 INFO [train.py:763] (5/8) Epoch 14, batch 1850, loss[loss=0.1699, simple_loss=0.2703, pruned_loss=0.03478, over 7163.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2774, pruned_loss=0.04284, over 1431335.82 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:20:42,279 INFO [train.py:763] (5/8) Epoch 14, batch 1900, loss[loss=0.1657, simple_loss=0.2717, pruned_loss=0.02991, over 7116.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2764, pruned_loss=0.0423, over 1431288.40 frames.], batch size: 21, lr: 5.17e-04
2022-04-29 07:21:47,866 INFO [train.py:763] (5/8) Epoch 14, batch 1950, loss[loss=0.1601, simple_loss=0.261, pruned_loss=0.02964, over 7276.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2756, pruned_loss=0.04182, over 1431112.27 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:22:53,278 INFO [train.py:763] (5/8) Epoch 14, batch 2000, loss[loss=0.22, simple_loss=0.3107, pruned_loss=0.06466, over 6351.00 frames.], tot_loss[loss=0.1805, simple_loss=0.276, pruned_loss=0.04252, over 1427258.46 frames.], batch size: 37, lr: 5.17e-04
2022-04-29 07:23:58,404 INFO [train.py:763] (5/8) Epoch 14, batch 2050, loss[loss=0.1817, simple_loss=0.2779, pruned_loss=0.04277, over 7289.00 frames.], tot_loss[loss=0.1811, simple_loss=0.277, pruned_loss=0.04261, over 1428086.13 frames.], batch size: 25, lr: 5.16e-04
2022-04-29 07:25:03,744 INFO [train.py:763] (5/8) Epoch 14, batch 2100, loss[loss=0.153, simple_loss=0.2449, pruned_loss=0.03059, over 7423.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2765, pruned_loss=0.04285, over 1421523.49 frames.], batch size: 18, lr: 5.16e-04
2022-04-29 07:26:09,022 INFO [train.py:763] (5/8) Epoch 14, batch 2150, loss[loss=0.2204, simple_loss=0.3196, pruned_loss=0.06059, over 7207.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2771, pruned_loss=0.04293, over 1419846.46 frames.], batch size: 22, lr: 5.16e-04
2022-04-29 07:27:14,558 INFO [train.py:763] (5/8) Epoch 14, batch 2200, loss[loss=0.1744, simple_loss=0.2714, pruned_loss=0.03869, over 7435.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2782, pruned_loss=0.04345, over 1419492.78 frames.], batch size: 20, lr: 5.16e-04
2022-04-29 07:28:19,754 INFO [train.py:763] (5/8) Epoch 14, batch 2250, loss[loss=0.2096, simple_loss=0.3045, pruned_loss=0.05739, over 7056.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2789, pruned_loss=0.04369, over 1421550.84 frames.], batch size: 28, lr: 5.16e-04
2022-04-29 07:29:24,988 INFO [train.py:763] (5/8) Epoch 14, batch 2300, loss[loss=0.218, simple_loss=0.2804, pruned_loss=0.07778, over 6825.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2783, pruned_loss=0.0432, over 1420886.93 frames.], batch size: 15, lr: 5.15e-04
2022-04-29 07:30:30,170 INFO [train.py:763] (5/8) Epoch 14, batch 2350, loss[loss=0.1924, simple_loss=0.2785, pruned_loss=0.0531, over 7407.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2775, pruned_loss=0.04261, over 1423895.52 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:31:35,495 INFO [train.py:763] (5/8) Epoch 14, batch 2400, loss[loss=0.1704, simple_loss=0.2565, pruned_loss=0.04211, over 7426.00 frames.], tot_loss[loss=0.183, simple_loss=0.2787, pruned_loss=0.04367, over 1421444.82 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:32:40,933 INFO [train.py:763] (5/8) Epoch 14, batch 2450, loss[loss=0.204, simple_loss=0.3006, pruned_loss=0.05372, over 7417.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2791, pruned_loss=0.0436, over 1422935.03 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:33:46,240 INFO [train.py:763] (5/8) Epoch 14, batch 2500, loss[loss=0.1679, simple_loss=0.2712, pruned_loss=0.0323, over 7322.00 frames.], tot_loss[loss=0.1833, simple_loss=0.279, pruned_loss=0.04379, over 1424112.67 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:34:51,434 INFO [train.py:763] (5/8) Epoch 14, batch 2550, loss[loss=0.192, simple_loss=0.2713, pruned_loss=0.05635, over 7161.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2795, pruned_loss=0.04404, over 1426819.27 frames.], batch size: 18, lr: 5.14e-04
2022-04-29 07:35:56,550 INFO [train.py:763] (5/8) Epoch 14, batch 2600, loss[loss=0.1898, simple_loss=0.2897, pruned_loss=0.0449, over 7228.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2793, pruned_loss=0.04375, over 1421913.92 frames.], batch size: 23, lr: 5.14e-04
2022-04-29 07:37:01,623 INFO [train.py:763] (5/8) Epoch 14, batch 2650, loss[loss=0.2092, simple_loss=0.3047, pruned_loss=0.05686, over 7312.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2788, pruned_loss=0.0435, over 1423135.50 frames.], batch size: 25, lr: 5.14e-04
2022-04-29 07:38:06,939 INFO [train.py:763] (5/8) Epoch 14, batch 2700, loss[loss=0.215, simple_loss=0.3121, pruned_loss=0.05896, over 7317.00 frames.], tot_loss[loss=0.183, simple_loss=0.2789, pruned_loss=0.04355, over 1425133.26 frames.], batch size: 21, lr: 5.14e-04
2022-04-29 07:39:12,136 INFO [train.py:763] (5/8) Epoch 14, batch 2750, loss[loss=0.1888, simple_loss=0.2932, pruned_loss=0.04217, over 7291.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2785, pruned_loss=0.0431, over 1425277.61 frames.], batch size: 24, lr: 5.14e-04
2022-04-29 07:40:17,446 INFO [train.py:763] (5/8) Epoch 14, batch 2800, loss[loss=0.1942, simple_loss=0.2941, pruned_loss=0.04713, over 7142.00 frames.], tot_loss[loss=0.181, simple_loss=0.2773, pruned_loss=0.04236, over 1428454.46 frames.], batch size: 20, lr: 5.14e-04
2022-04-29 07:41:22,763 INFO [train.py:763] (5/8) Epoch 14, batch 2850, loss[loss=0.2011, simple_loss=0.2717, pruned_loss=0.06522, over 7204.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2784, pruned_loss=0.04269, over 1429414.06 frames.], batch size: 16, lr: 5.13e-04
2022-04-29 07:42:28,528 INFO [train.py:763] (5/8) Epoch 14, batch 2900, loss[loss=0.1721, simple_loss=0.2723, pruned_loss=0.03598, over 7391.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2787, pruned_loss=0.04299, over 1424333.32 frames.], batch size: 23, lr: 5.13e-04
2022-04-29 07:43:34,058 INFO [train.py:763] (5/8) Epoch 14, batch 2950, loss[loss=0.1771, simple_loss=0.276, pruned_loss=0.0391, over 7412.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2785, pruned_loss=0.04285, over 1425197.18 frames.], batch size: 20, lr: 5.13e-04
2022-04-29 07:44:39,584 INFO [train.py:763] (5/8) Epoch 14, batch 3000, loss[loss=0.238, simple_loss=0.3139, pruned_loss=0.08107, over 7162.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2779, pruned_loss=0.04314, over 1422561.39 frames.], batch size: 19, lr: 5.13e-04
2022-04-29 07:44:39,585 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 07:44:54,980 INFO [train.py:792] (5/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
2022-04-29 07:46:00,334 INFO [train.py:763] (5/8) Epoch 14, batch 3050, loss[loss=0.1735, simple_loss=0.2602, pruned_loss=0.04342, over 6782.00 frames.], tot_loss[loss=0.182, simple_loss=0.2778, pruned_loss=0.04314, over 1425014.04 frames.], batch size: 15, lr: 5.13e-04
2022-04-29 07:47:05,878 INFO [train.py:763] (5/8) Epoch 14, batch 3100, loss[loss=0.1773, simple_loss=0.2662, pruned_loss=0.04419, over 7329.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2784, pruned_loss=0.04337, over 1421871.98 frames.], batch size: 20, lr: 5.12e-04
2022-04-29 07:48:12,255 INFO [train.py:763] (5/8) Epoch 14, batch 3150, loss[loss=0.1796, simple_loss=0.2647, pruned_loss=0.04723, over 7275.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2768, pruned_loss=0.04238, over 1426409.26 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:49:18,813 INFO [train.py:763] (5/8) Epoch 14, batch 3200, loss[loss=0.1864, simple_loss=0.285, pruned_loss=0.04389, over 7068.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2757, pruned_loss=0.04199, over 1427869.34 frames.], batch size: 28, lr: 5.12e-04
2022-04-29 07:50:24,264 INFO [train.py:763] (5/8) Epoch 14, batch 3250, loss[loss=0.1602, simple_loss=0.2537, pruned_loss=0.03336, over 7063.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2757, pruned_loss=0.04239, over 1428308.38 frames.], batch size: 18, lr: 5.12e-04
2022-04-29 07:51:29,742 INFO [train.py:763] (5/8) Epoch 14, batch 3300, loss[loss=0.172, simple_loss=0.2499, pruned_loss=0.04706, over 7267.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2751, pruned_loss=0.04207, over 1426958.96 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:52:35,061 INFO [train.py:763] (5/8) Epoch 14, batch 3350, loss[loss=0.2029, simple_loss=0.2957, pruned_loss=0.05504, over 7194.00 frames.], tot_loss[loss=0.181, simple_loss=0.2769, pruned_loss=0.04248, over 1426333.70 frames.], batch size: 23, lr: 5.11e-04
2022-04-29 07:53:40,782 INFO [train.py:763] (5/8) Epoch 14, batch 3400, loss[loss=0.1426, simple_loss=0.2387, pruned_loss=0.02328, over 7213.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2774, pruned_loss=0.04253, over 1422874.92 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:54:45,995 INFO [train.py:763] (5/8) Epoch 14, batch 3450, loss[loss=0.1876, simple_loss=0.285, pruned_loss=0.04513, over 7046.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2782, pruned_loss=0.04318, over 1420300.91 frames.], batch size: 28, lr: 5.11e-04
2022-04-29 07:55:51,605 INFO [train.py:763] (5/8) Epoch 14, batch 3500, loss[loss=0.2168, simple_loss=0.3, pruned_loss=0.06686, over 7180.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2775, pruned_loss=0.04283, over 1425838.12 frames.], batch size: 26, lr: 5.11e-04
2022-04-29 07:56:57,025 INFO [train.py:763] (5/8) Epoch 14, batch 3550, loss[loss=0.1512, simple_loss=0.247, pruned_loss=0.02771, over 7228.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2787, pruned_loss=0.04348, over 1427325.36 frames.], batch size: 20, lr: 5.11e-04
2022-04-29 07:58:03,511 INFO [train.py:763] (5/8) Epoch 14, batch 3600, loss[loss=0.1772, simple_loss=0.2774, pruned_loss=0.03853, over 7321.00 frames.], tot_loss[loss=0.183, simple_loss=0.2786, pruned_loss=0.04366, over 1423855.21 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:59:08,920 INFO [train.py:763] (5/8) Epoch 14, batch 3650, loss[loss=0.1512, simple_loss=0.2559, pruned_loss=0.02321, over 7249.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2785, pruned_loss=0.04349, over 1424899.32 frames.], batch size: 19, lr: 5.10e-04
2022-04-29 08:00:14,238 INFO [train.py:763] (5/8) Epoch 14, batch 3700, loss[loss=0.1794, simple_loss=0.2696, pruned_loss=0.04465, over 7429.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2785, pruned_loss=0.04326, over 1421981.51 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:01:20,037 INFO [train.py:763] (5/8) Epoch 14, batch 3750, loss[loss=0.2282, simple_loss=0.3224, pruned_loss=0.06701, over 4764.00 frames.], tot_loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.04323, over 1423578.14 frames.], batch size: 53, lr: 5.10e-04
2022-04-29 08:02:27,027 INFO [train.py:763] (5/8) Epoch 14, batch 3800, loss[loss=0.1757, simple_loss=0.2608, pruned_loss=0.04529, over 7070.00 frames.], tot_loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.04314, over 1425403.19 frames.], batch size: 18, lr: 5.10e-04
2022-04-29 08:03:33,825 INFO [train.py:763] (5/8) Epoch 14, batch 3850, loss[loss=0.2106, simple_loss=0.3039, pruned_loss=0.05869, over 7229.00 frames.], tot_loss[loss=0.1827, simple_loss=0.279, pruned_loss=0.04321, over 1428489.94 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:04:40,270 INFO [train.py:763] (5/8) Epoch 14, batch 3900, loss[loss=0.1432, simple_loss=0.2436, pruned_loss=0.02139, over 7250.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.04282, over 1425538.66 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:05:46,501 INFO [train.py:763] (5/8) Epoch 14, batch 3950, loss[loss=0.1755, simple_loss=0.2733, pruned_loss=0.03886, over 7351.00 frames.], tot_loss[loss=0.182, simple_loss=0.2776, pruned_loss=0.04317, over 1421096.82 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:06:52,814 INFO [train.py:763] (5/8) Epoch 14, batch 4000, loss[loss=0.1921, simple_loss=0.2924, pruned_loss=0.04586, over 7214.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2775, pruned_loss=0.04318, over 1422013.74 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:07:57,996 INFO [train.py:763] (5/8) Epoch 14, batch 4050, loss[loss=0.1909, simple_loss=0.2887, pruned_loss=0.04657, over 7218.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2775, pruned_loss=0.04281, over 1427206.34 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:09:03,255 INFO [train.py:763] (5/8) Epoch 14, batch 4100, loss[loss=0.2065, simple_loss=0.2993, pruned_loss=0.05682, over 7204.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04277, over 1418367.05 frames.], batch size: 23, lr: 5.09e-04
2022-04-29 08:10:08,501 INFO [train.py:763] (5/8) Epoch 14, batch 4150, loss[loss=0.2381, simple_loss=0.3193, pruned_loss=0.07846, over 5122.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2778, pruned_loss=0.043, over 1412526.18 frames.], batch size: 52, lr: 5.08e-04
2022-04-29 08:11:13,735 INFO [train.py:763] (5/8) Epoch 14, batch 4200, loss[loss=0.1577, simple_loss=0.2514, pruned_loss=0.03197, over 7239.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2765, pruned_loss=0.04288, over 1409843.47 frames.], batch size: 20, lr: 5.08e-04
2022-04-29 08:12:19,836 INFO [train.py:763] (5/8) Epoch 14, batch 4250, loss[loss=0.1742, simple_loss=0.2607, pruned_loss=0.04379, over 7065.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2768, pruned_loss=0.04312, over 1408400.22 frames.], batch size: 18, lr: 5.08e-04
2022-04-29 08:13:25,931 INFO [train.py:763] (5/8) Epoch 14, batch 4300, loss[loss=0.1736, simple_loss=0.2603, pruned_loss=0.04348, over 6779.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2769, pruned_loss=0.04276, over 1404414.68 frames.], batch size: 15, lr: 5.08e-04
2022-04-29 08:14:30,949 INFO [train.py:763] (5/8) Epoch 14, batch 4350, loss[loss=0.1817, simple_loss=0.2734, pruned_loss=0.04502, over 7324.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2774, pruned_loss=0.04293, over 1408724.50 frames.], batch size: 21, lr: 5.08e-04
2022-04-29 08:15:37,012 INFO [train.py:763] (5/8) Epoch 14, batch 4400, loss[loss=0.1645, simple_loss=0.2643, pruned_loss=0.03234, over 7167.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04232, over 1410438.50 frames.], batch size: 19, lr: 5.08e-04
2022-04-29 08:16:42,690 INFO [train.py:763] (5/8) Epoch 14, batch 4450, loss[loss=0.1766, simple_loss=0.2601, pruned_loss=0.04659, over 7152.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2749, pruned_loss=0.04167, over 1403186.57 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:17:47,614 INFO [train.py:763] (5/8) Epoch 14, batch 4500, loss[loss=0.1857, simple_loss=0.2755, pruned_loss=0.04792, over 7061.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2752, pruned_loss=0.04185, over 1394969.88 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:18:51,986 INFO [train.py:763] (5/8) Epoch 14, batch 4550, loss[loss=0.2469, simple_loss=0.3139, pruned_loss=0.08998, over 5429.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2779, pruned_loss=0.04378, over 1366900.80 frames.], batch size: 52, lr: 5.07e-04
2022-04-29 08:20:20,836 INFO [train.py:763] (5/8) Epoch 15, batch 0, loss[loss=0.1967, simple_loss=0.3028, pruned_loss=0.04532, over 7302.00 frames.], tot_loss[loss=0.1967, simple_loss=0.3028, pruned_loss=0.04532, over 7302.00 frames.], batch size: 24, lr: 4.92e-04
2022-04-29 08:21:27,549 INFO [train.py:763] (5/8) Epoch 15, batch 50, loss[loss=0.1586, simple_loss=0.2576, pruned_loss=0.02977, over 7406.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2767, pruned_loss=0.04136, over 322327.26 frames.], batch size: 18, lr: 4.92e-04
2022-04-29 08:22:33,679 INFO [train.py:763] (5/8) Epoch 15, batch 100, loss[loss=0.1851, simple_loss=0.2832, pruned_loss=0.04349, over 7337.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2753, pruned_loss=0.04004, over 565802.32 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:23:40,364 INFO [train.py:763] (5/8) Epoch 15, batch 150, loss[loss=0.1666, simple_loss=0.2708, pruned_loss=0.03124, over 7141.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2746, pruned_loss=0.04027, over 755767.41 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:24:46,771 INFO [train.py:763] (5/8) Epoch 15, batch 200, loss[loss=0.1861, simple_loss=0.2817, pruned_loss=0.04523, over 7117.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2738, pruned_loss=0.0407, over 898824.96 frames.], batch size: 21, lr: 4.91e-04
2022-04-29 08:25:52,230 INFO [train.py:763] (5/8) Epoch 15, batch 250, loss[loss=0.1877, simple_loss=0.2941, pruned_loss=0.04067, over 7158.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2746, pruned_loss=0.04111, over 1014970.40 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:26:57,842 INFO [train.py:763] (5/8) Epoch 15, batch 300, loss[loss=0.1555, simple_loss=0.2598, pruned_loss=0.02562, over 7154.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2737, pruned_loss=0.04072, over 1109522.50 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:28:03,221 INFO [train.py:763] (5/8) Epoch 15, batch 350, loss[loss=0.1541, simple_loss=0.2496, pruned_loss=0.02927, over 7289.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2735, pruned_loss=0.04039, over 1180542.60 frames.], batch size: 18, lr: 4.91e-04
2022-04-29 08:29:08,693 INFO [train.py:763] (5/8) Epoch 15, batch 400, loss[loss=0.1721, simple_loss=0.2748, pruned_loss=0.03467, over 7258.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2753, pruned_loss=0.04126, over 1234213.30 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:30:14,243 INFO [train.py:763] (5/8) Epoch 15, batch 450, loss[loss=0.1515, simple_loss=0.2505, pruned_loss=0.02621, over 7438.00 frames.], tot_loss[loss=0.1796, simple_loss=0.276, pruned_loss=0.0416, over 1281022.66 frames.], batch size: 20, lr: 4.91e-04
2022-04-29 08:31:19,785 INFO [train.py:763] (5/8) Epoch 15, batch 500, loss[loss=0.2289, simple_loss=0.323, pruned_loss=0.06743, over 7207.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2775, pruned_loss=0.04215, over 1317712.08 frames.], batch size: 23, lr: 4.90e-04
2022-04-29 08:32:25,953 INFO [train.py:763] (5/8) Epoch 15, batch 550, loss[loss=0.1558, simple_loss=0.2462, pruned_loss=0.03274, over 7276.00 frames.], tot_loss[loss=0.1793, simple_loss=0.276, pruned_loss=0.04126, over 1345020.48 frames.], batch size: 18, lr: 4.90e-04
2022-04-29 08:33:31,112 INFO [train.py:763] (5/8) Epoch 15, batch 600, loss[loss=0.167, simple_loss=0.2579, pruned_loss=0.03809, over 7162.00 frames.], tot_loss[loss=0.1784, simple_loss=0.275, pruned_loss=0.04091, over 1361040.25 frames.], batch size: 19, lr: 4.90e-04
2022-04-29 08:34:36,402 INFO [train.py:763] (5/8) Epoch 15, batch 650, loss[loss=0.1835, simple_loss=0.2853, pruned_loss=0.04087, over 6471.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2755, pruned_loss=0.041, over 1374048.05 frames.], batch size: 38, lr: 4.90e-04
2022-04-29 08:35:42,062 INFO [train.py:763] (5/8) Epoch 15, batch 700, loss[loss=0.1856, simple_loss=0.2889, pruned_loss=0.04115, over 7026.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2752, pruned_loss=0.04129, over 1385581.25 frames.], batch size: 28, lr: 4.90e-04
2022-04-29 08:36:47,196 INFO [train.py:763] (5/8) Epoch 15, batch 750, loss[loss=0.1634, simple_loss=0.2555, pruned_loss=0.03562, over 7153.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2752, pruned_loss=0.04108, over 1394939.92 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:37:53,217 INFO [train.py:763] (5/8) Epoch 15, batch 800, loss[loss=0.19, simple_loss=0.2834, pruned_loss=0.04831, over 7252.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2753, pruned_loss=0.04115, over 1402008.94 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:39:00,107 INFO [train.py:763] (5/8) Epoch 15, batch 850, loss[loss=0.1766, simple_loss=0.2658, pruned_loss=0.04368, over 7144.00 frames.], tot_loss[loss=0.1785, simple_loss=0.275, pruned_loss=0.04103, over 1404105.68 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:40:05,811 INFO [train.py:763] (5/8) Epoch 15, batch 900, loss[loss=0.1923, simple_loss=0.2825, pruned_loss=0.051, over 7368.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2744, pruned_loss=0.04138, over 1402424.27 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:41:11,041 INFO [train.py:763] (5/8) Epoch 15, batch 950, loss[loss=0.1653, simple_loss=0.2741, pruned_loss=0.02828, over 7439.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2739, pruned_loss=0.04118, over 1405885.02 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:42:16,446 INFO [train.py:763] (5/8) Epoch 15, batch 1000, loss[loss=0.1917, simple_loss=0.2977, pruned_loss=0.04278, over 7297.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2741, pruned_loss=0.04121, over 1412454.77 frames.], batch size: 25, lr: 4.89e-04
2022-04-29 08:43:21,716 INFO [train.py:763] (5/8) Epoch 15, batch 1050, loss[loss=0.1764, simple_loss=0.2677, pruned_loss=0.04257, over 7328.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2745, pruned_loss=0.04126, over 1418162.86 frames.], batch size: 20, lr: 4.88e-04
2022-04-29 08:44:28,855 INFO [train.py:763] (5/8) Epoch 15, batch 1100, loss[loss=0.1729, simple_loss=0.2675, pruned_loss=0.03918, over 7353.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.04086, over 1421244.97 frames.], batch size: 19, lr: 4.88e-04
2022-04-29 08:45:35,103 INFO [train.py:763] (5/8) Epoch 15, batch 1150, loss[loss=0.2011, simple_loss=0.2886, pruned_loss=0.0568, over 4907.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.04082, over 1421581.88 frames.], batch size: 53, lr: 4.88e-04
2022-04-29 08:46:40,375 INFO [train.py:763] (5/8) Epoch 15, batch 1200, loss[loss=0.194, simple_loss=0.2775, pruned_loss=0.05522, over 7094.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2748, pruned_loss=0.04133, over 1419322.43 frames.], batch size: 21, lr: 4.88e-04
2022-04-29 08:47:45,864 INFO [train.py:763] (5/8) Epoch 15, batch 1250, loss[loss=0.1539, simple_loss=0.2514, pruned_loss=0.02814, over 6766.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2745, pruned_loss=0.04149, over 1418520.64 frames.], batch size: 15, lr: 4.88e-04
2022-04-29 08:48:51,152 INFO [train.py:763] (5/8) Epoch 15, batch 1300, loss[loss=0.1797, simple_loss=0.284, pruned_loss=0.03776, over 7196.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2756, pruned_loss=0.04183, over 1424648.26 frames.], batch size: 22, lr: 4.88e-04
2022-04-29 08:49:56,774 INFO [train.py:763] (5/8) Epoch 15, batch 1350, loss[loss=0.1597, simple_loss=0.2534, pruned_loss=0.03297, over 7161.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2757, pruned_loss=0.04198, over 1417316.74 frames.], batch size: 19, lr: 4.87e-04
2022-04-29 08:51:13,204 INFO [train.py:763] (5/8) Epoch 15, batch 1400, loss[loss=0.1894, simple_loss=0.2941, pruned_loss=0.04239, over 7343.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2768, pruned_loss=0.04265, over 1416319.72 frames.], batch size: 22, lr: 4.87e-04
2022-04-29 08:52:20,212 INFO [train.py:763] (5/8) Epoch 15, batch 1450, loss[loss=0.2051, simple_loss=0.3144, pruned_loss=0.04787, over 7407.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2771, pruned_loss=0.0425, over 1421862.21 frames.], batch size: 21, lr: 4.87e-04
2022-04-29 08:53:25,689 INFO [train.py:763] (5/8) Epoch 15, batch 1500, loss[loss=0.188, simple_loss=0.288, pruned_loss=0.044, over 7228.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04298, over 1421871.67 frames.], batch size: 23, lr: 4.87e-04
2022-04-29 08:54:40,093 INFO [train.py:763] (5/8) Epoch 15, batch 1550, loss[loss=0.1338, simple_loss=0.2165, pruned_loss=0.02557, over 7226.00 frames.], tot_loss[loss=0.1816, simple_loss=0.277, pruned_loss=0.04303, over 1420564.25 frames.], batch size: 16, lr: 4.87e-04
2022-04-29 08:56:04,037 INFO [train.py:763] (5/8) Epoch 15, batch 1600, loss[loss=0.1808, simple_loss=0.2684, pruned_loss=0.04661, over 6805.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04306, over 1422667.18 frames.], batch size: 15, lr: 4.87e-04
2022-04-29 08:57:19,997 INFO [train.py:763] (5/8) Epoch 15, batch 1650, loss[loss=0.1738, simple_loss=0.283, pruned_loss=0.0323, over 7147.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2771, pruned_loss=0.04279, over 1424554.77 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 08:58:25,684 INFO [train.py:763] (5/8) Epoch 15, batch 1700, loss[loss=0.1591, simple_loss=0.2482, pruned_loss=0.03504, over 7418.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2755, pruned_loss=0.04216, over 1424939.97 frames.], batch size: 18, lr: 4.86e-04
2022-04-29 08:59:40,157 INFO [train.py:763] (5/8) Epoch 15, batch 1750, loss[loss=0.1847, simple_loss=0.2892, pruned_loss=0.04013, over 7381.00 frames.], tot_loss[loss=0.18, simple_loss=0.2756, pruned_loss=0.04218, over 1424734.62 frames.], batch size: 23, lr: 4.86e-04
2022-04-29 09:00:47,137 INFO [train.py:763] (5/8) Epoch 15, batch 1800, loss[loss=0.1494, simple_loss=0.2349, pruned_loss=0.03196, over 7353.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2752, pruned_loss=0.04184, over 1423328.42 frames.], batch size: 19, lr: 4.86e-04
2022-04-29 09:02:11,307 INFO [train.py:763] (5/8) Epoch 15, batch 1850, loss[loss=0.1836, simple_loss=0.2898, pruned_loss=0.0387, over 7148.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2743, pruned_loss=0.0416, over 1425379.25 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 09:03:16,755 INFO [train.py:763] (5/8) Epoch 15, batch 1900, loss[loss=0.2057, simple_loss=0.3069, pruned_loss=0.05228, over 7316.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2751, pruned_loss=0.0419, over 1429304.19 frames.], batch size: 25, lr: 4.86e-04
2022-04-29 09:04:23,835 INFO [train.py:763] (5/8) Epoch 15, batch 1950, loss[loss=0.2093, simple_loss=0.3204, pruned_loss=0.04905, over 7186.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2764, pruned_loss=0.0424, over 1430108.44 frames.], batch size: 23, lr: 4.85e-04
2022-04-29 09:05:29,705 INFO [train.py:763] (5/8) Epoch 15, batch 2000, loss[loss=0.2078, simple_loss=0.2848, pruned_loss=0.0654, over 5089.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2771, pruned_loss=0.04266, over 1424120.82 frames.], batch size: 52, lr: 4.85e-04
2022-04-29 09:06:36,287 INFO [train.py:763] (5/8) Epoch 15, batch 2050, loss[loss=0.1803, simple_loss=0.2784, pruned_loss=0.04114, over 6098.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04281, over 1423044.35 frames.], batch size: 37, lr: 4.85e-04
2022-04-29 09:07:41,968 INFO [train.py:763] (5/8) Epoch 15, batch 2100, loss[loss=0.1772, simple_loss=0.2846, pruned_loss=0.03493, over 7122.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2773, pruned_loss=0.0426, over 1423861.73 frames.], batch size: 21, lr: 4.85e-04
2022-04-29 09:08:48,748 INFO [train.py:763] (5/8) Epoch 15, batch 2150, loss[loss=0.1765, simple_loss=0.2631, pruned_loss=0.04495, over 7257.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2774, pruned_loss=0.04263, over 1419066.18 frames.], batch size: 19, lr: 4.85e-04
2022-04-29 09:09:53,842 INFO [train.py:763] (5/8) Epoch 15, batch 2200, loss[loss=0.2042, simple_loss=0.3078, pruned_loss=0.05027, over 7206.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2768, pruned_loss=0.04218, over 1415986.39 frames.], batch size: 22, lr: 4.84e-04
2022-04-29 09:10:59,460 INFO [train.py:763] (5/8) Epoch 15, batch 2250, loss[loss=0.1806, simple_loss=0.2869, pruned_loss=0.03719, over 7416.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2761, pruned_loss=0.04206, over 1417657.69 frames.], batch size: 21, lr: 4.84e-04
2022-04-29 09:12:05,744 INFO [train.py:763] (5/8) Epoch 15, batch 2300, loss[loss=0.1836, simple_loss=0.2862, pruned_loss=0.04047, over 7200.00 frames.], tot_loss[loss=0.18, simple_loss=0.2765, pruned_loss=0.04174, over 1419902.27 frames.], batch size: 23, lr: 4.84e-04
2022-04-29 09:13:13,279 INFO [train.py:763] (5/8) Epoch 15, batch 2350, loss[loss=0.1994, simple_loss=0.2989, pruned_loss=0.04993, over 7283.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2761, pruned_loss=0.04188, over 1422347.70 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:14:19,343 INFO [train.py:763] (5/8) Epoch 15, batch 2400, loss[loss=0.2115, simple_loss=0.3058, pruned_loss=0.05862, over 7275.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2755, pruned_loss=0.04161, over 1425059.15 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:15:24,441 INFO [train.py:763] (5/8) Epoch 15, batch 2450, loss[loss=0.207, simple_loss=0.3098, pruned_loss=0.05213, over 6734.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2761, pruned_loss=0.04149, over 1424638.37 frames.], batch size: 31, lr: 4.84e-04
2022-04-29 09:16:31,167 INFO [train.py:763] (5/8) Epoch 15, batch 2500, loss[loss=0.1762, simple_loss=0.2807, pruned_loss=0.03583, over 7218.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2756, pruned_loss=0.04149, over 1426827.53 frames.], batch size: 21, lr: 4.83e-04
2022-04-29 09:17:37,367 INFO [train.py:763] (5/8) Epoch 15, batch 2550, loss[loss=0.1811, simple_loss=0.2854, pruned_loss=0.03845, over 7140.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2743, pruned_loss=0.04077, over 1423095.02 frames.], batch size: 20, lr: 4.83e-04
2022-04-29 09:18:44,504 INFO [train.py:763] (5/8) Epoch 15, batch 2600, loss[loss=0.1457, simple_loss=0.239, pruned_loss=0.02623, over 7362.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2748, pruned_loss=0.04079, over 1421609.76 frames.], batch size: 19, lr: 4.83e-04
2022-04-29 09:19:51,213 INFO [train.py:763] (5/8) Epoch 15, batch 2650, loss[loss=0.1739, simple_loss=0.2798, pruned_loss=0.03397, over 7386.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2748, pruned_loss=0.04113, over 1422494.68 frames.], batch size: 23, lr: 4.83e-04
2022-04-29 09:20:56,497 INFO [train.py:763] (5/8) Epoch 15, batch 2700, loss[loss=0.1751, simple_loss=0.2789, pruned_loss=0.03558, over 7106.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2757, pruned_loss=0.04192, over 1420168.93 frames.], batch size: 26, lr: 4.83e-04
2022-04-29 09:22:02,820 INFO [train.py:763] (5/8) Epoch 15, batch 2750, loss[loss=0.1692, simple_loss=0.2532, pruned_loss=0.04259, over 7271.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2761, pruned_loss=0.04207, over 1424174.90 frames.], batch size: 18, lr: 4.83e-04
2022-04-29 09:23:10,089 INFO [train.py:763] (5/8) Epoch 15, batch 2800, loss[loss=0.2106, simple_loss=0.2952, pruned_loss=0.063, over 7225.00 frames.], tot_loss[loss=0.18, simple_loss=0.276, pruned_loss=0.04204, over 1426056.64 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:24:17,269 INFO [train.py:763] (5/8) Epoch 15, batch 2850, loss[loss=0.1651, simple_loss=0.2578, pruned_loss=0.03616, over 7163.00 frames.], tot_loss[loss=0.1799, simple_loss=0.276, pruned_loss=0.0419, over 1424972.35 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:25:24,203 INFO [train.py:763] (5/8) Epoch 15, batch 2900, loss[loss=0.1781, simple_loss=0.2747, pruned_loss=0.04075, over 7170.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2761, pruned_loss=0.04168, over 1428041.12 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:26:29,785 INFO [train.py:763] (5/8) Epoch 15, batch 2950, loss[loss=0.1695, simple_loss=0.271, pruned_loss=0.03402, over 7343.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2761, pruned_loss=0.04153, over 1424381.04 frames.], batch size: 22, lr: 4.82e-04
2022-04-29 09:27:35,047 INFO [train.py:763] (5/8) Epoch 15, batch 3000, loss[loss=0.173, simple_loss=0.2714, pruned_loss=0.03731, over 7416.00 frames.], tot_loss[loss=0.18, simple_loss=0.2764, pruned_loss=0.04182, over 1428405.88 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:27:35,048 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 09:27:50,494 INFO [train.py:792] (5/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
2022-04-29 09:28:57,624 INFO [train.py:763] (5/8) Epoch 15, batch 3050, loss[loss=0.1362, simple_loss=0.2264, pruned_loss=0.02302, over 7420.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2756, pruned_loss=0.04163, over 1426675.21 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:30:04,543 INFO [train.py:763] (5/8) Epoch 15, batch 3100, loss[loss=0.1888, simple_loss=0.2988, pruned_loss=0.03941, over 7186.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2756, pruned_loss=0.04173, over 1426485.66 frames.], batch size: 23, lr: 4.81e-04
2022-04-29 09:31:11,569 INFO [train.py:763] (5/8) Epoch 15, batch 3150, loss[loss=0.1547, simple_loss=0.2466, pruned_loss=0.0314, over 7164.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2751, pruned_loss=0.04118, over 1423665.40 frames.], batch size: 18, lr: 4.81e-04
2022-04-29 09:32:29,193 INFO [train.py:763] (5/8) Epoch 15, batch 3200, loss[loss=0.1956, simple_loss=0.2928, pruned_loss=0.04922, over 7292.00 frames.], tot_loss[loss=0.179, simple_loss=0.2759, pruned_loss=0.04101, over 1423871.79 frames.], batch size: 24, lr: 4.81e-04
2022-04-29 09:33:36,700 INFO [train.py:763] (5/8) Epoch 15, batch 3250, loss[loss=0.193, simple_loss=0.2946, pruned_loss=0.04573, over 7315.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2745, pruned_loss=0.04091, over 1426010.88 frames.], batch size: 21, lr: 4.81e-04
2022-04-29 09:34:43,463 INFO [train.py:763] (5/8) Epoch 15, batch 3300, loss[loss=0.1908, simple_loss=0.2818, pruned_loss=0.04985, over 7319.00 frames.], tot_loss[loss=0.179, simple_loss=0.2758, pruned_loss=0.04113, over 1429780.42 frames.], batch size: 25, lr: 4.81e-04
2022-04-29 09:35:50,328 INFO [train.py:763] (5/8) Epoch 15, batch 3350, loss[loss=0.1836, simple_loss=0.2813, pruned_loss=0.04292, over 7244.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04128, over 1432113.10 frames.], batch size: 20, lr: 4.81e-04
2022-04-29 09:36:57,534 INFO [train.py:763] (5/8) Epoch 15, batch 3400, loss[loss=0.1762, simple_loss=0.2715, pruned_loss=0.04038, over 7139.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2764, pruned_loss=0.04195, over 1430244.78 frames.], batch size: 28, lr: 4.80e-04
2022-04-29 09:38:05,027 INFO [train.py:763] (5/8) Epoch 15, batch 3450, loss[loss=0.1587, simple_loss=0.2536, pruned_loss=0.03186, over 7352.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04173, over 1430646.54 frames.], batch size: 19, lr: 4.80e-04
2022-04-29 09:39:11,461 INFO [train.py:763] (5/8) Epoch 15, batch 3500, loss[loss=0.1832, simple_loss=0.294, pruned_loss=0.03618, over 7306.00 frames.], tot_loss[loss=0.18, simple_loss=0.2766, pruned_loss=0.04172, over 1429293.65 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:40:16,438 INFO [train.py:763] (5/8) Epoch 15, batch 3550, loss[loss=0.2128, simple_loss=0.3021, pruned_loss=0.06182, over 7172.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2771, pruned_loss=0.04193, over 1424591.54 frames.], batch size: 26, lr: 4.80e-04
2022-04-29 09:41:21,623 INFO [train.py:763] (5/8) Epoch 15, batch 3600, loss[loss=0.1807, simple_loss=0.2849, pruned_loss=0.0382, over 7330.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2762, pruned_loss=0.04118, over 1426900.73 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:42:26,936 INFO [train.py:763] (5/8) Epoch 15, batch 3650, loss[loss=0.1842, simple_loss=0.2592, pruned_loss=0.05457, over 7283.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2759, pruned_loss=0.04129, over 1426875.01 frames.], batch size: 18, lr: 4.80e-04
2022-04-29 09:43:33,159 INFO [train.py:763] (5/8) Epoch 15, batch 3700, loss[loss=0.1731, simple_loss=0.2537, pruned_loss=0.04625, over 6876.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2756, pruned_loss=0.04152, over 1424196.32 frames.], batch size: 15, lr: 4.79e-04
2022-04-29 09:44:39,884 INFO [train.py:763] (5/8) Epoch 15, batch 3750, loss[loss=0.2087, simple_loss=0.3136, pruned_loss=0.05187, over 7258.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2761, pruned_loss=0.04171, over 1421758.68 frames.], batch size: 25, lr: 4.79e-04
2022-04-29 09:45:46,842 INFO [train.py:763] (5/8) Epoch 15, batch 3800, loss[loss=0.1559, simple_loss=0.2533, pruned_loss=0.02924, over 7137.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04156, over 1425894.81 frames.], batch size: 17, lr: 4.79e-04
2022-04-29 09:46:53,825 INFO [train.py:763] (5/8) Epoch 15, batch 3850, loss[loss=0.1549, simple_loss=0.2592, pruned_loss=0.0253, over 7279.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2763, pruned_loss=0.04175, over 1422115.80 frames.], batch size: 18, lr: 4.79e-04
2022-04-29 09:48:00,489 INFO [train.py:763] (5/8) Epoch 15, batch 3900, loss[loss=0.1763, simple_loss=0.2772, pruned_loss=0.03771, over 7230.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2758, pruned_loss=0.04143, over 1423881.63 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:49:06,582 INFO [train.py:763] (5/8) Epoch 15, batch 3950, loss[loss=0.1848, simple_loss=0.2812, pruned_loss=0.04421, over 7232.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04159, over 1422303.94 frames.], batch size: 20, lr: 4.79e-04
2022-04-29 09:50:13,633 INFO [train.py:763] (5/8) Epoch 15, batch 4000, loss[loss=0.1869, simple_loss=0.2939, pruned_loss=0.0399, over 7317.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2758, pruned_loss=0.04137, over 1419438.94 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:51:19,319 INFO [train.py:763] (5/8) Epoch 15, batch 4050, loss[loss=0.1465, simple_loss=0.2484, pruned_loss=0.02232, over 7165.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2763, pruned_loss=0.04147, over 1418094.74 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:52:24,925 INFO [train.py:763] (5/8) Epoch 15, batch 4100, loss[loss=0.1676, simple_loss=0.2636, pruned_loss=0.03581, over 7164.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2755, pruned_loss=0.04106, over 1423864.24 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:53:30,120 INFO [train.py:763] (5/8) Epoch 15, batch 4150, loss[loss=0.2034, simple_loss=0.2972, pruned_loss=0.05474, over 7042.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2755, pruned_loss=0.04143, over 1418086.60 frames.], batch size: 28, lr: 4.78e-04
2022-04-29 09:54:36,334 INFO [train.py:763] (5/8) Epoch 15, batch 4200, loss[loss=0.177, simple_loss=0.2567, pruned_loss=0.04862, over 7001.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2745, pruned_loss=0.04117, over 1418310.94 frames.], batch size: 16, lr: 4.78e-04
2022-04-29 09:55:43,469 INFO [train.py:763] (5/8) Epoch 15, batch 4250, loss[loss=0.1752, simple_loss=0.2576, pruned_loss=0.04635, over 7170.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2738, pruned_loss=0.04106, over 1417844.11 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:56:48,663 INFO [train.py:763] (5/8) Epoch 15, batch 4300, loss[loss=0.1653, simple_loss=0.2569, pruned_loss=0.0369, over 6768.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2734, pruned_loss=0.04082, over 1413421.26 frames.], batch size: 31, lr: 4.78e-04
2022-04-29 09:57:53,923 INFO [train.py:763] (5/8) Epoch 15, batch 4350, loss[loss=0.1828, simple_loss=0.264, pruned_loss=0.0508, over 7171.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2735, pruned_loss=0.04054, over 1416466.72 frames.], batch size: 18, lr: 4.77e-04
2022-04-29 09:59:00,573 INFO [train.py:763] (5/8) Epoch 15, batch 4400, loss[loss=0.1827, simple_loss=0.287, pruned_loss=0.03916, over 7116.00 frames.], tot_loss[loss=0.177, simple_loss=0.2732, pruned_loss=0.04038, over 1416068.76 frames.], batch size: 21, lr: 4.77e-04
2022-04-29 10:00:06,761 INFO [train.py:763] (5/8) Epoch 15, batch 4450, loss[loss=0.2124, simple_loss=0.3215, pruned_loss=0.05166, over 7203.00 frames.], tot_loss[loss=0.177, simple_loss=0.2732, pruned_loss=0.0404, over 1410668.14 frames.], batch size: 22, lr: 4.77e-04
2022-04-29 10:01:11,555 INFO [train.py:763] (5/8) Epoch 15, batch 4500, loss[loss=0.1595, simple_loss=0.2481, pruned_loss=0.03545, over 7131.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2728, pruned_loss=0.04047, over 1399857.92 frames.], batch size: 17, lr: 4.77e-04
2022-04-29 10:02:15,686 INFO [train.py:763] (5/8) Epoch 15, batch 4550, loss[loss=0.2085, simple_loss=0.2902, pruned_loss=0.06339, over 5218.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2758, pruned_loss=0.04267, over 1349676.01 frames.], batch size: 52, lr: 4.77e-04
2022-04-29 10:03:53,501 INFO [train.py:763] (5/8) Epoch 16, batch 0, loss[loss=0.1842, simple_loss=0.275, pruned_loss=0.04671, over 7113.00 frames.], tot_loss[loss=0.1842, simple_loss=0.275, pruned_loss=0.04671, over 7113.00 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:04:59,096 INFO [train.py:763] (5/8) Epoch 16, batch 50, loss[loss=0.2098, simple_loss=0.3079, pruned_loss=0.05585, over 7313.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2811, pruned_loss=0.04553, over 316874.88 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:06:04,345 INFO [train.py:763] (5/8) Epoch 16, batch 100, loss[loss=0.139, simple_loss=0.2398, pruned_loss=0.01912, over 7144.00 frames.], tot_loss[loss=0.181, simple_loss=0.2773, pruned_loss=0.04236, over 558285.75 frames.], batch size: 20, lr: 4.63e-04
2022-04-29 10:07:09,685 INFO [train.py:763] (5/8) Epoch 16, batch 150, loss[loss=0.1573, simple_loss=0.2423, pruned_loss=0.03616, over 6998.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2739, pruned_loss=0.04086, over 746869.25 frames.], batch size: 16, lr: 4.63e-04
2022-04-29 10:08:15,066 INFO [train.py:763] (5/8) Epoch 16, batch 200, loss[loss=0.1371, simple_loss=0.2308, pruned_loss=0.0217, over 7140.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2758, pruned_loss=0.04127, over 895508.77 frames.], batch size: 17, lr: 4.63e-04
2022-04-29 10:09:20,558 INFO [train.py:763] (5/8) Epoch 16, batch 250, loss[loss=0.1732, simple_loss=0.266, pruned_loss=0.04027, over 7251.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2752, pruned_loss=0.04096, over 1015197.57 frames.], batch size: 19, lr: 4.63e-04
2022-04-29 10:10:25,851 INFO [train.py:763] (5/8) Epoch 16, batch 300, loss[loss=0.1563, simple_loss=0.2503, pruned_loss=0.03117, over 7064.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2755, pruned_loss=0.04085, over 1101379.05 frames.], batch size: 18, lr: 4.62e-04
2022-04-29 10:11:32,024 INFO [train.py:763] (5/8) Epoch 16, batch 350, loss[loss=0.1582, simple_loss=0.2516, pruned_loss=0.03246, over 6811.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2746, pruned_loss=0.04055, over 1171921.88 frames.], batch size: 15, lr: 4.62e-04
2022-04-29 10:12:37,990 INFO [train.py:763] (5/8) Epoch 16, batch 400, loss[loss=0.2278, simple_loss=0.3088, pruned_loss=0.0734, over 4991.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2754, pruned_loss=0.04057, over 1227567.47 frames.], batch size: 52, lr: 4.62e-04
2022-04-29 10:13:43,452 INFO [train.py:763] (5/8) Epoch 16, batch 450, loss[loss=0.1727, simple_loss=0.2599, pruned_loss=0.04275, over 7355.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2758, pruned_loss=0.04066, over 1267744.17 frames.], batch size: 19, lr: 4.62e-04
2022-04-29 10:14:49,058 INFO [train.py:763] (5/8) Epoch 16, batch 500, loss[loss=0.1686, simple_loss=0.2603, pruned_loss=0.03846, over 7159.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2753, pruned_loss=0.04044, over 1301651.73 frames.], batch size: 18, lr: 4.62e-04
2022-04-29 10:15:54,723 INFO [train.py:763] (5/8) Epoch 16, batch 550, loss[loss=0.148, simple_loss=0.2401, pruned_loss=0.02798, over 7132.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2746, pruned_loss=0.0403, over 1327296.38 frames.], batch size: 17, lr: 4.62e-04
2022-04-29 10:17:00,207 INFO [train.py:763] (5/8) Epoch 16, batch 600, loss[loss=0.1866, simple_loss=0.2936, pruned_loss=0.03978, over 7002.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2754, pruned_loss=0.04087, over 1342121.39 frames.], batch size: 28, lr: 4.62e-04
2022-04-29 10:18:05,534 INFO [train.py:763] (5/8) Epoch 16, batch 650, loss[loss=0.1576, simple_loss=0.2592, pruned_loss=0.02801, over 7321.00 frames.], tot_loss[loss=0.1791, simple_loss=0.276, pruned_loss=0.04108, over 1361234.78 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:19:10,733 INFO [train.py:763] (5/8) Epoch 16, batch 700, loss[loss=0.16, simple_loss=0.2504, pruned_loss=0.03478, over 7262.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2764, pruned_loss=0.04112, over 1368042.29 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:20:16,743 INFO [train.py:763] (5/8) Epoch 16, batch 750, loss[loss=0.1843, simple_loss=0.2874, pruned_loss=0.0406, over 7151.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2764, pruned_loss=0.04106, over 1377003.84 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:21:21,861 INFO [train.py:763] (5/8) Epoch 16, batch 800, loss[loss=0.1564, simple_loss=0.2451, pruned_loss=0.03384, over 7153.00 frames.], tot_loss[loss=0.179, simple_loss=0.2762, pruned_loss=0.04094, over 1387628.20 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:22:27,311 INFO [train.py:763] (5/8) Epoch 16, batch 850, loss[loss=0.1934, simple_loss=0.2813, pruned_loss=0.05273, over 6419.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2752, pruned_loss=0.0409, over 1396461.66 frames.], batch size: 38, lr: 4.61e-04
2022-04-29 10:23:32,968 INFO [train.py:763] (5/8) Epoch 16, batch 900, loss[loss=0.1537, simple_loss=0.2594, pruned_loss=0.02403, over 7334.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2747, pruned_loss=0.04046, over 1408659.23 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:24:38,450 INFO [train.py:763] (5/8) Epoch 16, batch 950, loss[loss=0.1671, simple_loss=0.2516, pruned_loss=0.04132, over 7147.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2753, pruned_loss=0.0408, over 1413655.76 frames.], batch size: 17, lr: 4.60e-04
2022-04-29 10:25:44,702 INFO [train.py:763] (5/8) Epoch 16, batch 1000, loss[loss=0.1865, simple_loss=0.2873, pruned_loss=0.04282, over 7119.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2755, pruned_loss=0.04081, over 1417612.79 frames.], batch size: 21, lr: 4.60e-04
2022-04-29 10:26:51,179 INFO [train.py:763] (5/8) Epoch 16, batch 1050, loss[loss=0.1765, simple_loss=0.2818, pruned_loss=0.03558, over 7322.00 frames.], tot_loss[loss=0.1783, simple_loss=0.275, pruned_loss=0.04083, over 1420960.85 frames.], batch size: 22, lr: 4.60e-04
2022-04-29 10:27:57,457 INFO [train.py:763] (5/8) Epoch 16, batch 1100, loss[loss=0.196, simple_loss=0.2885, pruned_loss=0.05174, over 7310.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2741, pruned_loss=0.04043, over 1422042.73 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:29:02,476 INFO [train.py:763] (5/8) Epoch 16, batch 1150, loss[loss=0.1897, simple_loss=0.284, pruned_loss=0.04772, over 7299.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2752, pruned_loss=0.04072, over 1422647.19 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:30:08,054 INFO [train.py:763] (5/8) Epoch 16, batch 1200, loss[loss=0.2186, simple_loss=0.3227, pruned_loss=0.05726, over 7319.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2749, pruned_loss=0.04117, over 1419650.45 frames.], batch size: 25, lr: 4.60e-04
2022-04-29 10:31:13,269 INFO [train.py:763] (5/8) Epoch 16, batch 1250, loss[loss=0.1717, simple_loss=0.2662, pruned_loss=0.0386, over 7270.00 frames.], tot_loss[loss=0.179, simple_loss=0.2752, pruned_loss=0.04141, over 1415488.26 frames.], batch size: 18, lr: 4.60e-04
2022-04-29 10:32:19,090 INFO [train.py:763] (5/8) Epoch 16, batch 1300, loss[loss=0.198, simple_loss=0.2947, pruned_loss=0.05071, over 7328.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2749, pruned_loss=0.04137, over 1412733.13 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:33:25,812 INFO [train.py:763] (5/8) Epoch 16, batch 1350, loss[loss=0.191, simple_loss=0.2711, pruned_loss=0.05542, over 6985.00 frames.], tot_loss[loss=0.179, simple_loss=0.2751, pruned_loss=0.04146, over 1418288.95 frames.], batch size: 16, lr: 4.59e-04
2022-04-29 10:34:32,931 INFO [train.py:763] (5/8) Epoch 16, batch 1400, loss[loss=0.1665, simple_loss=0.261, pruned_loss=0.03601, over 7148.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2735, pruned_loss=0.04061, over 1419860.74 frames.], batch size: 20, lr: 4.59e-04
2022-04-29 10:35:38,355 INFO [train.py:763] (5/8) Epoch 16, batch 1450, loss[loss=0.1912, simple_loss=0.2987, pruned_loss=0.04187, over 7333.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2743, pruned_loss=0.04048, over 1418856.30 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:36:44,001 INFO [train.py:763] (5/8) Epoch 16, batch 1500, loss[loss=0.1654, simple_loss=0.2625, pruned_loss=0.03415, over 7254.00 frames.], tot_loss[loss=0.176, simple_loss=0.2725, pruned_loss=0.03979, over 1425369.54 frames.], batch size: 19, lr: 4.59e-04
2022-04-29 10:37:49,281 INFO [train.py:763] (5/8) Epoch 16, batch 1550, loss[loss=0.1839, simple_loss=0.2806, pruned_loss=0.04355, over 7219.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2733, pruned_loss=0.04007, over 1422944.14 frames.], batch size: 21, lr: 4.59e-04
2022-04-29 10:38:55,276 INFO [train.py:763] (5/8) Epoch 16, batch 1600, loss[loss=0.1554, simple_loss=0.2541, pruned_loss=0.02838, over 7438.00 frames.], tot_loss[loss=0.176, simple_loss=0.273, pruned_loss=0.03954, over 1427657.80 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:40:00,457 INFO [train.py:763] (5/8) Epoch 16, batch 1650, loss[loss=0.177, simple_loss=0.2794, pruned_loss=0.03736, over 7410.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2738, pruned_loss=0.03962, over 1429820.11 frames.], batch size: 21, lr: 4.58e-04
2022-04-29 10:41:05,546 INFO [train.py:763] (5/8) Epoch 16, batch 1700, loss[loss=0.2185, simple_loss=0.3012, pruned_loss=0.06788, over 5478.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2741, pruned_loss=0.04016, over 1423794.04 frames.], batch size: 56, lr: 4.58e-04
2022-04-29 10:42:10,604 INFO [train.py:763] (5/8) Epoch 16, batch 1750, loss[loss=0.2018, simple_loss=0.2922, pruned_loss=0.05572, over 7371.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2753, pruned_loss=0.04078, over 1415371.51 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:43:15,528 INFO [train.py:763] (5/8) Epoch 16, batch 1800, loss[loss=0.1915, simple_loss=0.2833, pruned_loss=0.04983, over 7193.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2754, pruned_loss=0.04051, over 1416468.74 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:44:20,688 INFO [train.py:763] (5/8) Epoch 16, batch 1850, loss[loss=0.174, simple_loss=0.269, pruned_loss=0.03952, over 6539.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2759, pruned_loss=0.04093, over 1417696.74 frames.], batch size: 38, lr: 4.58e-04
2022-04-29 10:45:26,191 INFO [train.py:763] (5/8) Epoch 16, batch 1900, loss[loss=0.1822, simple_loss=0.2705, pruned_loss=0.04694, over 7426.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2753, pruned_loss=0.04042, over 1422014.00 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:46:31,351 INFO [train.py:763] (5/8) Epoch 16, batch 1950, loss[loss=0.1554, simple_loss=0.26, pruned_loss=0.02538, over 7323.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2749, pruned_loss=0.04041, over 1424312.94 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:47:36,629 INFO [train.py:763] (5/8) Epoch 16, batch 2000, loss[loss=0.1665, simple_loss=0.2592, pruned_loss=0.0369, over 7259.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2746, pruned_loss=0.04025, over 1426052.85 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:48:44,199 INFO [train.py:763] (5/8) Epoch 16, batch 2050, loss[loss=0.1426, simple_loss=0.2318, pruned_loss=0.02666, over 7409.00 frames.], tot_loss[loss=0.1764, simple_loss=0.273, pruned_loss=0.03987, over 1429274.08 frames.], batch size: 18, lr: 4.57e-04
2022-04-29 10:49:51,161 INFO [train.py:763] (5/8) Epoch 16, batch 2100, loss[loss=0.1856, simple_loss=0.2854, pruned_loss=0.04296, over 7405.00 frames.], tot_loss[loss=0.1761, simple_loss=0.273, pruned_loss=0.03953, over 1429538.46 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:50:58,036 INFO [train.py:763] (5/8) Epoch 16, batch 2150, loss[loss=0.1691, simple_loss=0.2726, pruned_loss=0.03283, over 7366.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2737, pruned_loss=0.03983, over 1425340.01 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:52:04,711 INFO [train.py:763] (5/8) Epoch 16, batch 2200, loss[loss=0.1838, simple_loss=0.2928, pruned_loss=0.03742, over 7325.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03943, over 1422234.06 frames.], batch size: 22, lr: 4.57e-04
2022-04-29 10:53:10,678 INFO [train.py:763] (5/8) Epoch 16, batch 2250, loss[loss=0.1731, simple_loss=0.2724, pruned_loss=0.0369, over 7425.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2739, pruned_loss=0.03969, over 1423613.03 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:54:16,237 INFO [train.py:763] (5/8) Epoch 16, batch 2300, loss[loss=0.1883, simple_loss=0.2939, pruned_loss=0.04131, over 7290.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2735, pruned_loss=0.03958, over 1422314.59 frames.], batch size: 24, lr: 4.56e-04
2022-04-29 10:55:22,552 INFO [train.py:763] (5/8) Epoch 16, batch 2350, loss[loss=0.1766, simple_loss=0.2767, pruned_loss=0.03828, over 7395.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2732, pruned_loss=0.03966, over 1425675.71 frames.], batch size: 23, lr: 4.56e-04
2022-04-29 10:56:28,590 INFO [train.py:763] (5/8) Epoch 16, batch 2400, loss[loss=0.1328, simple_loss=0.2267, pruned_loss=0.0194, over 7013.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2725, pruned_loss=0.03907, over 1424005.97 frames.], batch size: 16, lr: 4.56e-04
2022-04-29 10:57:34,911 INFO [train.py:763] (5/8) Epoch 16, batch 2450, loss[loss=0.1768, simple_loss=0.2792, pruned_loss=0.03713, over 7329.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2731, pruned_loss=0.03967, over 1423952.29 frames.], batch size: 22, lr: 4.56e-04
2022-04-29 10:58:41,499 INFO [train.py:763] (5/8) Epoch 16, batch 2500, loss[loss=0.2022, simple_loss=0.3034, pruned_loss=0.05046, over 7222.00 frames.], tot_loss[loss=0.1756, simple_loss=0.272, pruned_loss=0.03957, over 1423616.96 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:59:48,425 INFO [train.py:763] (5/8) Epoch 16, batch 2550, loss[loss=0.1647, simple_loss=0.2668, pruned_loss=0.03127, over 7208.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2723, pruned_loss=0.03994, over 1420242.76 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 11:00:54,062 INFO [train.py:763] (5/8) Epoch 16, batch 2600, loss[loss=0.1999, simple_loss=0.2911, pruned_loss=0.05438, over 7105.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2739, pruned_loss=0.04048, over 1422334.53 frames.], batch size: 28, lr: 4.55e-04
2022-04-29 11:01:59,327 INFO [train.py:763] (5/8) Epoch 16, batch 2650, loss[loss=0.1599, simple_loss=0.2641, pruned_loss=0.02791, over 7367.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2739, pruned_loss=0.04042, over 1420500.40 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:03:04,685 INFO [train.py:763] (5/8) Epoch 16, batch 2700, loss[loss=0.1976, simple_loss=0.2964, pruned_loss=0.04936, over 7337.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2723, pruned_loss=0.0399, over 1424008.51 frames.], batch size: 22, lr: 4.55e-04
2022-04-29 11:04:10,093 INFO [train.py:763] (5/8) Epoch 16, batch 2750, loss[loss=0.1491, simple_loss=0.2469, pruned_loss=0.02565, over 7150.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2726, pruned_loss=0.03989, over 1422838.76 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:05:15,591 INFO [train.py:763] (5/8) Epoch 16, batch 2800, loss[loss=0.2292, simple_loss=0.3173, pruned_loss=0.07053, over 5004.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2725, pruned_loss=0.04014, over 1422141.55 frames.], batch size: 52, lr: 4.55e-04
2022-04-29 11:06:20,608 INFO [train.py:763] (5/8) Epoch 16, batch 2850, loss[loss=0.1994, simple_loss=0.2958, pruned_loss=0.05149, over 7316.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2739, pruned_loss=0.04036, over 1422405.99 frames.], batch size: 21, lr: 4.55e-04
2022-04-29 11:07:35,854 INFO [train.py:763] (5/8) Epoch 16, batch 2900, loss[loss=0.1594, simple_loss=0.2607, pruned_loss=0.02906, over 7228.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2741, pruned_loss=0.04062, over 1418325.49 frames.], batch size: 20, lr: 4.55e-04
2022-04-29 11:08:42,373 INFO [train.py:763] (5/8) Epoch 16, batch 2950, loss[loss=0.1732, simple_loss=0.2599, pruned_loss=0.04324, over 7257.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.04087, over 1418814.93 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:09:49,129 INFO [train.py:763] (5/8) Epoch 16, batch 3000, loss[loss=0.2027, simple_loss=0.3112, pruned_loss=0.04711, over 7139.00 frames.], tot_loss[loss=0.178, simple_loss=0.2751, pruned_loss=0.04044, over 1423943.00 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:09:49,130 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 11:10:05,042 INFO [train.py:792] (5/8) Epoch 16, validation: loss=0.1677, simple_loss=0.2693, pruned_loss=0.03309, over 698248.00 frames.
2022-04-29 11:11:10,312 INFO [train.py:763] (5/8) Epoch 16, batch 3050, loss[loss=0.1991, simple_loss=0.2893, pruned_loss=0.05445, over 6160.00 frames.], tot_loss[loss=0.1777, simple_loss=0.275, pruned_loss=0.04014, over 1423143.35 frames.], batch size: 37, lr: 4.54e-04
2022-04-29 11:12:42,605 INFO [train.py:763] (5/8) Epoch 16, batch 3100, loss[loss=0.1661, simple_loss=0.2739, pruned_loss=0.02918, over 7309.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2751, pruned_loss=0.04038, over 1419463.50 frames.], batch size: 25, lr: 4.54e-04
2022-04-29 11:13:48,024 INFO [train.py:763] (5/8) Epoch 16, batch 3150, loss[loss=0.1786, simple_loss=0.2731, pruned_loss=0.04202, over 7334.00 frames.], tot_loss[loss=0.178, simple_loss=0.2749, pruned_loss=0.0405, over 1418679.56 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:15:03,462 INFO [train.py:763] (5/8) Epoch 16, batch 3200, loss[loss=0.1698, simple_loss=0.2721, pruned_loss=0.03374, over 7353.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2752, pruned_loss=0.04104, over 1419001.62 frames.], batch size: 19, lr: 4.54e-04
2022-04-29 11:16:27,100 INFO [train.py:763] (5/8) Epoch 16, batch 3250, loss[loss=0.1472, simple_loss=0.2411, pruned_loss=0.02671, over 7070.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2749, pruned_loss=0.04086, over 1424250.21 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:17:32,425 INFO [train.py:763] (5/8) Epoch 16, batch 3300, loss[loss=0.1836, simple_loss=0.2814, pruned_loss=0.04293, over 7155.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2754, pruned_loss=0.04079, over 1425355.22 frames.], batch size: 19, lr: 4.53e-04
2022-04-29 11:18:47,396 INFO [train.py:763] (5/8) Epoch 16, batch 3350, loss[loss=0.1886, simple_loss=0.291, pruned_loss=0.04311, over 7331.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2752, pruned_loss=0.04065, over 1426852.92 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:19:54,042 INFO [train.py:763] (5/8) Epoch 16, batch 3400, loss[loss=0.1438, simple_loss=0.2463, pruned_loss=0.02063, over 7150.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2749, pruned_loss=0.04069, over 1423826.47 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:21:00,500 INFO [train.py:763] (5/8) Epoch 16, batch 3450, loss[loss=0.1935, simple_loss=0.2855, pruned_loss=0.05082, over 7333.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2735, pruned_loss=0.04061, over 1424267.70 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:22:05,839 INFO [train.py:763] (5/8) Epoch 16, batch 3500, loss[loss=0.2033, simple_loss=0.2919, pruned_loss=0.05732, over 7206.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2728, pruned_loss=0.04021, over 1423589.31 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:23:11,002 INFO [train.py:763] (5/8) Epoch 16, batch 3550, loss[loss=0.1729, simple_loss=0.284, pruned_loss=0.03087, over 7117.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2728, pruned_loss=0.03992, over 1425652.14 frames.], batch size: 21, lr: 4.53e-04
2022-04-29 11:24:16,268 INFO [train.py:763] (5/8) Epoch 16, batch 3600, loss[loss=0.1629, simple_loss=0.2453, pruned_loss=0.04019, over 7263.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2737, pruned_loss=0.03997, over 1426947.67 frames.], batch size: 18, lr: 4.52e-04
2022-04-29 11:25:21,856 INFO [train.py:763] (5/8) Epoch 16, batch 3650, loss[loss=0.1664, simple_loss=0.2594, pruned_loss=0.03671, over 7317.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2733, pruned_loss=0.04027, over 1430117.72 frames.], batch size: 21, lr: 4.52e-04
2022-04-29 11:26:27,138 INFO [train.py:763] (5/8) Epoch 16, batch 3700, loss[loss=0.1722, simple_loss=0.2743, pruned_loss=0.03503, over 7152.00 frames.], tot_loss[loss=0.177, simple_loss=0.2733, pruned_loss=0.04028, over 1429447.12 frames.], batch size: 20, lr: 4.52e-04
2022-04-29 11:27:34,290 INFO [train.py:763] (5/8) Epoch 16, batch 3750, loss[loss=0.1892, simple_loss=0.2928, pruned_loss=0.04281, over 6190.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2741, pruned_loss=0.0404, over 1427113.54 frames.], batch size: 37, lr: 4.52e-04
2022-04-29 11:28:40,556 INFO [train.py:763] (5/8) Epoch 16, batch 3800, loss[loss=0.171, simple_loss=0.2663, pruned_loss=0.03786, over 6433.00 frames.], tot_loss[loss=0.1782, simple_loss=0.275, pruned_loss=0.04067, over 1426347.67 frames.], batch size: 38, lr: 4.52e-04
2022-04-29 11:29:46,874 INFO [train.py:763] (5/8) Epoch 16, batch 3850, loss[loss=0.1364, simple_loss=0.2348, pruned_loss=0.01906, over 6991.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2749, pruned_loss=0.04036, over 1425919.55 frames.], batch size: 16, lr: 4.52e-04
2022-04-29 11:30:53,559 INFO [train.py:763] (5/8) Epoch 16, batch 3900, loss[loss=0.1744, simple_loss=0.281, pruned_loss=0.03394, over 7208.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2739, pruned_loss=0.03985, over 1427992.67 frames.], batch size: 22, lr: 4.52e-04
2022-04-29 11:32:00,331 INFO [train.py:763] (5/8) Epoch 16, batch 3950, loss[loss=0.2, simple_loss=0.3015, pruned_loss=0.04922, over 7199.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2747, pruned_loss=0.03994, over 1427838.05 frames.], batch size: 23, lr: 4.51e-04
2022-04-29 11:33:05,772 INFO [train.py:763] (5/8) Epoch 16, batch 4000, loss[loss=0.1386, simple_loss=0.2396, pruned_loss=0.01878, over 7283.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2742, pruned_loss=0.03999, over 1429161.27 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:34:12,302 INFO [train.py:763] (5/8) Epoch 16, batch 4050, loss[loss=0.1942, simple_loss=0.2957, pruned_loss=0.04638, over 6753.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2737, pruned_loss=0.03975, over 1424979.70 frames.], batch size: 31, lr: 4.51e-04
2022-04-29 11:35:18,256 INFO [train.py:763] (5/8) Epoch 16, batch 4100, loss[loss=0.2078, simple_loss=0.3099, pruned_loss=0.05288, over 6522.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2755, pruned_loss=0.04055, over 1424785.98 frames.], batch size: 37, lr: 4.51e-04
2022-04-29 11:36:24,678 INFO [train.py:763] (5/8) Epoch 16, batch 4150, loss[loss=0.1485, simple_loss=0.2429, pruned_loss=0.027, over 7136.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2739, pruned_loss=0.04021, over 1423581.32 frames.], batch size: 17, lr: 4.51e-04
2022-04-29 11:37:30,203 INFO [train.py:763] (5/8) Epoch 16, batch 4200, loss[loss=0.1895, simple_loss=0.2893, pruned_loss=0.04481, over 7168.00 frames.], tot_loss[loss=0.178, simple_loss=0.2746, pruned_loss=0.04074, over 1423740.07 frames.], batch size: 26, lr: 4.51e-04
2022-04-29 11:38:36,632 INFO [train.py:763] (5/8) Epoch 16, batch 4250, loss[loss=0.172, simple_loss=0.2633, pruned_loss=0.04038, over 7276.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2753, pruned_loss=0.04089, over 1424276.31 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:39:43,774 INFO [train.py:763] (5/8) Epoch 16, batch 4300, loss[loss=0.1374, simple_loss=0.2402, pruned_loss=0.01733, over 7074.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2742, pruned_loss=0.0407, over 1423220.89 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:40:49,815 INFO [train.py:763] (5/8) Epoch 16, batch 4350, loss[loss=0.1652, simple_loss=0.2579, pruned_loss=0.03619, over 7172.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2737, pruned_loss=0.04053, over 1422416.62 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:41:55,142 INFO [train.py:763] (5/8) Epoch 16, batch 4400, loss[loss=0.1747, simple_loss=0.2764, pruned_loss=0.03649, over 7219.00 frames.], tot_loss[loss=0.1776, simple_loss=0.274, pruned_loss=0.04063, over 1420868.74 frames.], batch size: 21, lr: 4.50e-04
2022-04-29 11:43:00,293 INFO [train.py:763] (5/8) Epoch 16, batch 4450, loss[loss=0.1555, simple_loss=0.2453, pruned_loss=0.03287, over 7115.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2755, pruned_loss=0.04116, over 1416813.29 frames.], batch size: 17, lr: 4.50e-04
2022-04-29 11:44:06,067 INFO [train.py:763] (5/8) Epoch 16, batch 4500, loss[loss=0.1684, simple_loss=0.2736, pruned_loss=0.03155, over 7237.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2746, pruned_loss=0.04082, over 1415913.45 frames.], batch size: 20, lr: 4.50e-04
2022-04-29 11:45:13,650 INFO [train.py:763] (5/8) Epoch 16, batch 4550, loss[loss=0.2367, simple_loss=0.3188, pruned_loss=0.0773, over 4507.00 frames.], tot_loss[loss=0.179, simple_loss=0.2742, pruned_loss=0.04193, over 1381413.81 frames.], batch size: 53, lr: 4.50e-04
2022-04-29 11:46:42,230 INFO [train.py:763] (5/8) Epoch 17, batch 0, loss[loss=0.1906, simple_loss=0.2881, pruned_loss=0.04655, over 7235.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2881, pruned_loss=0.04655, over 7235.00 frames.], batch size: 20, lr: 4.38e-04
2022-04-29 11:47:48,729 INFO [train.py:763] (5/8) Epoch 17, batch 50, loss[loss=0.1537, simple_loss=0.2373, pruned_loss=0.03504, over 6979.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2717, pruned_loss=0.03947, over 323304.74 frames.], batch size: 16, lr: 4.38e-04
2022-04-29 11:48:54,538 INFO [train.py:763] (5/8) Epoch 17, batch 100, loss[loss=0.1357, simple_loss=0.2357, pruned_loss=0.01785, over 7143.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.03834, over 565521.03 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:50:00,288 INFO [train.py:763] (5/8) Epoch 17, batch 150, loss[loss=0.174, simple_loss=0.2702, pruned_loss=0.03897, over 7141.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2738, pruned_loss=0.03902, over 753070.49 frames.], batch size: 20, lr: 4.37e-04
2022-04-29 11:51:07,239 INFO [train.py:763] (5/8) Epoch 17, batch 200, loss[loss=0.1705, simple_loss=0.2703, pruned_loss=0.03537, over 7169.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2742, pruned_loss=0.03938, over 904455.88 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:52:14,166 INFO [train.py:763] (5/8) Epoch 17, batch 250, loss[loss=0.1625, simple_loss=0.2625, pruned_loss=0.03122, over 6725.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2745, pruned_loss=0.03942, over 1021677.30 frames.], batch size: 31, lr: 4.37e-04
2022-04-29 11:53:19,803 INFO [train.py:763] (5/8) Epoch 17, batch 300, loss[loss=0.1827, simple_loss=0.2765, pruned_loss=0.04447, over 7037.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2748, pruned_loss=0.03931, over 1104951.66 frames.], batch size: 28, lr: 4.37e-04
2022-04-29 11:54:25,516 INFO [train.py:763] (5/8) Epoch 17, batch 350, loss[loss=0.1676, simple_loss=0.2688, pruned_loss=0.03316, over 7325.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2732, pruned_loss=0.03923, over 1172914.16 frames.], batch size: 22, lr: 4.37e-04
2022-04-29 11:55:31,576 INFO [train.py:763] (5/8) Epoch 17, batch 400, loss[loss=0.1794, simple_loss=0.2664, pruned_loss=0.0462, over 6832.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2744, pruned_loss=0.03938, over 1232706.01 frames.], batch size: 15, lr: 4.37e-04
2022-04-29 11:56:37,258 INFO [train.py:763] (5/8) Epoch 17, batch 450, loss[loss=0.213, simple_loss=0.3168, pruned_loss=0.05461, over 7222.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2752, pruned_loss=0.03926, over 1275845.18 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:57:42,951 INFO [train.py:763] (5/8) Epoch 17, batch 500, loss[loss=0.2272, simple_loss=0.3085, pruned_loss=0.07301, over 7336.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2743, pruned_loss=0.03944, over 1313313.75 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:58:48,664 INFO [train.py:763] (5/8) Epoch 17, batch 550, loss[loss=0.1557, simple_loss=0.2514, pruned_loss=0.02999, over 7134.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2735, pruned_loss=0.03879, over 1340413.68 frames.], batch size: 17, lr: 4.36e-04
2022-04-29 11:59:54,500 INFO [train.py:763] (5/8) Epoch 17, batch 600, loss[loss=0.1566, simple_loss=0.2632, pruned_loss=0.02499, over 6597.00 frames.], tot_loss[loss=0.177, simple_loss=0.2749, pruned_loss=0.0395, over 1358173.32 frames.], batch size: 38, lr: 4.36e-04
2022-04-29 12:01:00,144 INFO [train.py:763] (5/8) Epoch 17, batch 650, loss[loss=0.2115, simple_loss=0.2965, pruned_loss=0.06328, over 5066.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2748, pruned_loss=0.03913, over 1370348.55 frames.], batch size: 54, lr: 4.36e-04
2022-04-29 12:02:07,663 INFO [train.py:763] (5/8) Epoch 17, batch 700, loss[loss=0.1488, simple_loss=0.2552, pruned_loss=0.02116, over 7323.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2748, pruned_loss=0.03921, over 1381889.58 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:03:15,585 INFO [train.py:763] (5/8) Epoch 17, batch 750, loss[loss=0.1498, simple_loss=0.2392, pruned_loss=0.03014, over 7418.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2735, pruned_loss=0.03905, over 1391963.32 frames.], batch size: 18, lr: 4.36e-04
2022-04-29 12:04:22,601 INFO [train.py:763] (5/8) Epoch 17, batch 800, loss[loss=0.1862, simple_loss=0.2816, pruned_loss=0.0454, over 7308.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2731, pruned_loss=0.03894, over 1403675.74 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:05:28,623 INFO [train.py:763] (5/8) Epoch 17, batch 850, loss[loss=0.1708, simple_loss=0.2731, pruned_loss=0.03422, over 7418.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2725, pruned_loss=0.03902, over 1406533.28 frames.], batch size: 21, lr: 4.35e-04
2022-04-29 12:06:34,122 INFO [train.py:763] (5/8) Epoch 17, batch 900, loss[loss=0.211, simple_loss=0.3031, pruned_loss=0.05942, over 7210.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03981, over 1406491.65 frames.], batch size: 22, lr: 4.35e-04
2022-04-29 12:07:40,037 INFO [train.py:763] (5/8) Epoch 17, batch 950, loss[loss=0.1827, simple_loss=0.2719, pruned_loss=0.04674, over 7272.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2746, pruned_loss=0.04013, over 1409012.41 frames.], batch size: 19, lr: 4.35e-04
2022-04-29 12:08:46,277 INFO [train.py:763] (5/8) Epoch 17, batch 1000, loss[loss=0.1698, simple_loss=0.2744, pruned_loss=0.03258, over 7298.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2738, pruned_loss=0.03964, over 1413899.28 frames.], batch size: 24, lr: 4.35e-04
2022-04-29 12:09:52,071 INFO [train.py:763] (5/8) Epoch 17, batch 1050, loss[loss=0.1661, simple_loss=0.2575, pruned_loss=0.03731, over 7261.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2729, pruned_loss=0.03905, over 1416102.07 frames.], batch size: 17, lr: 4.35e-04
2022-04-29 12:10:58,011 INFO [train.py:763] (5/8) Epoch 17, batch 1100, loss[loss=0.2016, simple_loss=0.3, pruned_loss=0.05161, over 7297.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2733, pruned_loss=0.03943, over 1419841.85 frames.], batch size: 25, lr: 4.35e-04
2022-04-29 12:12:04,986 INFO [train.py:763] (5/8) Epoch 17, batch 1150, loss[loss=0.1787, simple_loss=0.2768, pruned_loss=0.04026, over 7381.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03939, over 1418367.81 frames.], batch size: 23, lr: 4.35e-04
2022-04-29 12:13:12,262 INFO [train.py:763] (5/8) Epoch 17, batch 1200, loss[loss=0.1761, simple_loss=0.2713, pruned_loss=0.04044, over 7281.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2735, pruned_loss=0.03964, over 1416350.10 frames.], batch size: 18, lr: 4.34e-04
2022-04-29 12:14:19,386 INFO [train.py:763] (5/8) Epoch 17, batch 1250, loss[loss=0.1733, simple_loss=0.2787, pruned_loss=0.03402, over 7416.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2736, pruned_loss=0.03981, over 1418453.48 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:15:25,177 INFO [train.py:763] (5/8) Epoch 17, batch 1300, loss[loss=0.1826, simple_loss=0.2771, pruned_loss=0.04406, over 7156.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2735, pruned_loss=0.03993, over 1419674.97 frames.], batch size: 26, lr: 4.34e-04
2022-04-29 12:16:30,503 INFO [train.py:763] (5/8) Epoch 17, batch 1350, loss[loss=0.1505, simple_loss=0.2419, pruned_loss=0.02953, over 6985.00 frames.], tot_loss[loss=0.1767, simple_loss=0.274, pruned_loss=0.03971, over 1423101.88 frames.], batch size: 16, lr: 4.34e-04
2022-04-29 12:17:36,055 INFO [train.py:763] (5/8) Epoch 17, batch 1400, loss[loss=0.1709, simple_loss=0.2807, pruned_loss=0.03057, over 7110.00 frames.], tot_loss[loss=0.177, simple_loss=0.2746, pruned_loss=0.03966, over 1424262.88 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:18:41,491 INFO [train.py:763] (5/8) Epoch 17, batch 1450, loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03485, over 7152.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2745, pruned_loss=0.04001, over 1421948.09 frames.], batch size: 20, lr: 4.34e-04
2022-04-29 12:19:47,542 INFO [train.py:763] (5/8) Epoch 17, batch 1500, loss[loss=0.1735, simple_loss=0.2749, pruned_loss=0.03606, over 7302.00 frames.], tot_loss[loss=0.178, simple_loss=0.2755, pruned_loss=0.04027, over 1413874.46 frames.], batch size: 25, lr: 4.34e-04
2022-04-29 12:20:53,500 INFO [train.py:763] (5/8) Epoch 17, batch 1550, loss[loss=0.1914, simple_loss=0.2892, pruned_loss=0.04677, over 7159.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2747, pruned_loss=0.04019, over 1420773.87 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:21:59,200 INFO [train.py:763] (5/8) Epoch 17, batch 1600, loss[loss=0.1933, simple_loss=0.2892, pruned_loss=0.04868, over 7430.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2748, pruned_loss=0.04031, over 1422711.90 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:23:04,507 INFO [train.py:763] (5/8) Epoch 17, batch 1650, loss[loss=0.1479, simple_loss=0.2376, pruned_loss=0.02906, over 7277.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2747, pruned_loss=0.03997, over 1421433.60 frames.], batch size: 17, lr: 4.33e-04
2022-04-29 12:24:09,902 INFO [train.py:763] (5/8) Epoch 17, batch 1700, loss[loss=0.151, simple_loss=0.249, pruned_loss=0.02644, over 7359.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03961, over 1424348.12 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:25:15,257 INFO [train.py:763] (5/8) Epoch 17, batch 1750, loss[loss=0.2036, simple_loss=0.2979, pruned_loss=0.05465, over 7321.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2736, pruned_loss=0.03959, over 1424430.38 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:26:20,539 INFO [train.py:763] (5/8) Epoch 17, batch 1800, loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03354, over 7229.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2737, pruned_loss=0.03977, over 1428427.33 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:27:26,288 INFO [train.py:763] (5/8) Epoch 17, batch 1850, loss[loss=0.2344, simple_loss=0.315, pruned_loss=0.07683, over 5059.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2728, pruned_loss=0.03977, over 1426275.75 frames.], batch size: 52, lr: 4.33e-04
2022-04-29 12:28:31,343 INFO [train.py:763] (5/8) Epoch 17, batch 1900, loss[loss=0.1925, simple_loss=0.2955, pruned_loss=0.04479, over 7321.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03955, over 1426574.96 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:29:36,732 INFO [train.py:763] (5/8) Epoch 17, batch 1950, loss[loss=0.17, simple_loss=0.27, pruned_loss=0.03503, over 7312.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2749, pruned_loss=0.04026, over 1422621.71 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:30:42,619 INFO [train.py:763] (5/8) Epoch 17, batch 2000, loss[loss=0.18, simple_loss=0.2814, pruned_loss=0.0393, over 5207.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2739, pruned_loss=0.03994, over 1424016.39 frames.], batch size: 52, lr: 4.32e-04
2022-04-29 12:31:59,165 INFO [train.py:763] (5/8) Epoch 17, batch 2050, loss[loss=0.1952, simple_loss=0.293, pruned_loss=0.04867, over 7103.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2735, pruned_loss=0.03996, over 1419618.14 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:33:04,646 INFO [train.py:763] (5/8) Epoch 17, batch 2100, loss[loss=0.2181, simple_loss=0.3107, pruned_loss=0.06275, over 6841.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2734, pruned_loss=0.03995, over 1415817.53 frames.], batch size: 31, lr: 4.32e-04
2022-04-29 12:34:11,530 INFO [train.py:763] (5/8) Epoch 17, batch 2150, loss[loss=0.1869, simple_loss=0.2975, pruned_loss=0.03818, over 7216.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2728, pruned_loss=0.03925, over 1417578.46 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:35:18,273 INFO [train.py:763] (5/8) Epoch 17, batch 2200, loss[loss=0.1796, simple_loss=0.2585, pruned_loss=0.05039, over 6800.00 frames.], tot_loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.0389, over 1420302.10 frames.], batch size: 15, lr: 4.32e-04
2022-04-29 12:36:23,944 INFO [train.py:763] (5/8) Epoch 17, batch 2250, loss[loss=0.1417, simple_loss=0.2285, pruned_loss=0.02748, over 6974.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2711, pruned_loss=0.03826, over 1423542.71 frames.], batch size: 16, lr: 4.32e-04
2022-04-29 12:37:31,447 INFO [train.py:763] (5/8) Epoch 17, batch 2300, loss[loss=0.1567, simple_loss=0.248, pruned_loss=0.03269, over 7150.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2717, pruned_loss=0.03852, over 1426206.39 frames.], batch size: 20, lr: 4.31e-04
2022-04-29 12:38:38,665 INFO [train.py:763] (5/8) Epoch 17, batch 2350, loss[loss=0.1893, simple_loss=0.2891, pruned_loss=0.04477, over 7185.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2718, pruned_loss=0.03877, over 1426154.12 frames.], batch size: 26, lr: 4.31e-04
2022-04-29 12:39:44,067 INFO [train.py:763] (5/8) Epoch 17, batch 2400, loss[loss=0.1801, simple_loss=0.2869, pruned_loss=0.03662, over 6570.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2725, pruned_loss=0.03862, over 1424444.29 frames.], batch size: 38, lr: 4.31e-04
2022-04-29 12:40:49,293 INFO [train.py:763] (5/8) Epoch 17, batch 2450, loss[loss=0.1619, simple_loss=0.2597, pruned_loss=0.03203, over 7158.00 frames.], tot_loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03886, over 1425722.13 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:41:54,336 INFO [train.py:763] (5/8) Epoch 17, batch 2500, loss[loss=0.1774, simple_loss=0.2803, pruned_loss=0.03721, over 7116.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2743, pruned_loss=0.04031, over 1419012.53 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:42:59,727 INFO [train.py:763] (5/8) Epoch 17, batch 2550, loss[loss=0.1785, simple_loss=0.2797, pruned_loss=0.03869, over 7329.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.0399, over 1420240.57 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:44:04,854 INFO [train.py:763] (5/8) Epoch 17, batch 2600, loss[loss=0.1626, simple_loss=0.2417, pruned_loss=0.0417, over 7200.00 frames.], tot_loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.04005, over 1419647.11 frames.], batch size: 16, lr: 4.31e-04
2022-04-29 12:45:10,700 INFO [train.py:763] (5/8) Epoch 17, batch 2650, loss[loss=0.1739, simple_loss=0.2625, pruned_loss=0.04266, over 7356.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2737, pruned_loss=0.03968, over 1419614.87 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:46:17,011 INFO [train.py:763] (5/8) Epoch 17, batch 2700, loss[loss=0.1516, simple_loss=0.2477, pruned_loss=0.0278, over 7262.00 frames.], tot_loss[loss=0.1761, simple_loss=0.273, pruned_loss=0.03958, over 1419644.58 frames.], batch size: 18, lr: 4.30e-04
2022-04-29 12:47:22,082 INFO [train.py:763] (5/8) Epoch 17, batch 2750, loss[loss=0.2011, simple_loss=0.3027, pruned_loss=0.04978, over 7148.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2731, pruned_loss=0.03981, over 1417316.19 frames.], batch size: 20, lr: 4.30e-04
2022-04-29 12:48:28,862 INFO [train.py:763] (5/8) Epoch 17, batch 2800, loss[loss=0.154, simple_loss=0.2618, pruned_loss=0.02311, over 7319.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2722, pruned_loss=0.03913, over 1417023.84 frames.], batch size: 21, lr: 4.30e-04
2022-04-29 12:49:34,427 INFO [train.py:763] (5/8) Epoch 17, batch 2850, loss[loss=0.193, simple_loss=0.2952, pruned_loss=0.04537, over 7282.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2723, pruned_loss=0.03896, over 1419799.14 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:50:39,891 INFO [train.py:763] (5/8) Epoch 17, batch 2900, loss[loss=0.1782, simple_loss=0.2837, pruned_loss=0.03634, over 7200.00 frames.], tot_loss[loss=0.1758, simple_loss=0.273, pruned_loss=0.03927, over 1422991.55 frames.], batch size: 22, lr: 4.30e-04
2022-04-29 12:51:46,366 INFO [train.py:763] (5/8) Epoch 17, batch 2950, loss[loss=0.1836, simple_loss=0.29, pruned_loss=0.03862, over 6413.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2735, pruned_loss=0.03971, over 1419451.76 frames.], batch size: 38, lr: 4.30e-04
2022-04-29 12:52:52,640 INFO [train.py:763] (5/8) Epoch 17, batch 3000, loss[loss=0.1867, simple_loss=0.2875, pruned_loss=0.04296, over 7300.00 frames.], tot_loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.04014, over 1418648.30 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:52:52,641 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 12:53:07,981 INFO [train.py:792] (5/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
2022-04-29 12:54:13,319 INFO [train.py:763] (5/8) Epoch 17, batch 3050, loss[loss=0.2045, simple_loss=0.2969, pruned_loss=0.05609, over 7111.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2737, pruned_loss=0.04004, over 1417591.90 frames.], batch size: 21, lr: 4.29e-04
2022-04-29 12:55:18,438 INFO [train.py:763] (5/8) Epoch 17, batch 3100, loss[loss=0.1681, simple_loss=0.2718, pruned_loss=0.03216, over 7228.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2743, pruned_loss=0.04036, over 1419100.99 frames.], batch size: 20, lr: 4.29e-04
2022-04-29 12:56:23,984 INFO [train.py:763] (5/8) Epoch 17, batch 3150, loss[loss=0.1674, simple_loss=0.2638, pruned_loss=0.03545, over 7256.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2743, pruned_loss=0.04008, over 1421485.23 frames.], batch size: 19, lr: 4.29e-04
2022-04-29 12:57:29,301 INFO [train.py:763] (5/8) Epoch 17, batch 3200, loss[loss=0.1921, simple_loss=0.2909, pruned_loss=0.04666, over 6802.00 frames.], tot_loss[loss=0.1771, simple_loss=0.274, pruned_loss=0.04007, over 1419924.37 frames.], batch size: 31, lr: 4.29e-04
2022-04-29 12:58:34,635 INFO [train.py:763] (5/8) Epoch 17, batch 3250, loss[loss=0.2146, simple_loss=0.3059, pruned_loss=0.0616, over 7388.00 frames.], tot_loss[loss=0.176, simple_loss=0.2726, pruned_loss=0.03967, over 1422444.68 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 12:59:42,209 INFO [train.py:763] (5/8) Epoch 17, batch 3300, loss[loss=0.1466, simple_loss=0.2324, pruned_loss=0.03041, over 7162.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2712, pruned_loss=0.03907, over 1427139.92 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:00:47,857 INFO [train.py:763] (5/8) Epoch 17, batch 3350, loss[loss=0.1826, simple_loss=0.2773, pruned_loss=0.04401, over 7406.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2727, pruned_loss=0.03949, over 1426693.59 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:01:54,348 INFO [train.py:763] (5/8) Epoch 17, batch 3400, loss[loss=0.1953, simple_loss=0.2932, pruned_loss=0.04874, over 7389.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2735, pruned_loss=0.03951, over 1430405.11 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 13:02:59,887 INFO [train.py:763] (5/8) Epoch 17, batch 3450, loss[loss=0.1751, simple_loss=0.2601, pruned_loss=0.04499, over 7410.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2733, pruned_loss=0.0393, over 1430963.96 frames.], batch size: 18, lr: 4.28e-04
2022-04-29 13:04:05,576 INFO [train.py:763] (5/8) Epoch 17, batch 3500, loss[loss=0.1804, simple_loss=0.2762, pruned_loss=0.0423, over 6298.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2728, pruned_loss=0.03919, over 1433565.43 frames.], batch size: 37, lr: 4.28e-04
2022-04-29 13:05:11,606 INFO [train.py:763] (5/8) Epoch 17, batch 3550, loss[loss=0.1939, simple_loss=0.294, pruned_loss=0.04695, over 7228.00 frames.], tot_loss[loss=0.176, simple_loss=0.2733, pruned_loss=0.03937, over 1431444.94 frames.], batch size: 23, lr: 4.28e-04
2022-04-29 13:06:17,360 INFO [train.py:763] (5/8) Epoch 17, batch 3600, loss[loss=0.21, simple_loss=0.3082, pruned_loss=0.05592, over 7226.00 frames.], tot_loss[loss=0.1757, simple_loss=0.273, pruned_loss=0.0392, over 1432515.45 frames.], batch size: 21, lr: 4.28e-04
2022-04-29 13:07:22,980 INFO [train.py:763] (5/8) Epoch 17, batch 3650, loss[loss=0.1822, simple_loss=0.2813, pruned_loss=0.04159, over 7327.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2733, pruned_loss=0.03941, over 1423964.82 frames.], batch size: 22, lr: 4.28e-04
2022-04-29 13:08:28,137 INFO [train.py:763] (5/8) Epoch 17, batch 3700, loss[loss=0.1683, simple_loss=0.2663, pruned_loss=0.03514, over 6997.00 frames.], tot_loss[loss=0.176, simple_loss=0.2737, pruned_loss=0.03914, over 1424907.99 frames.], batch size: 16, lr: 4.28e-04
2022-04-29 13:09:33,329 INFO [train.py:763] (5/8) Epoch 17, batch 3750, loss[loss=0.1855, simple_loss=0.2837, pruned_loss=0.04363, over 7299.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2742, pruned_loss=0.03944, over 1426671.66 frames.], batch size: 25, lr: 4.28e-04
2022-04-29 13:10:39,697 INFO [train.py:763] (5/8) Epoch 17, batch 3800, loss[loss=0.1718, simple_loss=0.2713, pruned_loss=0.03618, over 7353.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2733, pruned_loss=0.03955, over 1426325.93 frames.], batch size: 19, lr: 4.28e-04
2022-04-29 13:11:45,021 INFO [train.py:763] (5/8) Epoch 17, batch 3850, loss[loss=0.1581, simple_loss=0.2542, pruned_loss=0.03096, over 7423.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2732, pruned_loss=0.03958, over 1424531.85 frames.], batch size: 18, lr: 4.27e-04
2022-04-29 13:12:50,428 INFO [train.py:763] (5/8) Epoch 17, batch 3900, loss[loss=0.154, simple_loss=0.249, pruned_loss=0.02948, over 7111.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03931, over 1420910.50 frames.], batch size: 21, lr: 4.27e-04
2022-04-29 13:13:55,782 INFO [train.py:763] (5/8) Epoch 17, batch 3950, loss[loss=0.1934, simple_loss=0.2852, pruned_loss=0.05083, over 7079.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2725, pruned_loss=0.03936, over 1422569.15 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:15:01,128 INFO [train.py:763] (5/8) Epoch 17, batch 4000, loss[loss=0.1613, simple_loss=0.2467, pruned_loss=0.03801, over 6788.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2718, pruned_loss=0.03919, over 1423296.11 frames.], batch size: 15, lr: 4.27e-04
2022-04-29 13:16:06,985 INFO [train.py:763] (5/8) Epoch 17, batch 4050, loss[loss=0.1886, simple_loss=0.2881, pruned_loss=0.04452, over 7075.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2725, pruned_loss=0.03952, over 1426781.98 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:17:12,353 INFO [train.py:763] (5/8) Epoch 17, batch 4100, loss[loss=0.1754, simple_loss=0.2759, pruned_loss=0.03742, over 7150.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2719, pruned_loss=0.03894, over 1423118.04 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:18:18,026 INFO [train.py:763] (5/8) Epoch 17, batch 4150, loss[loss=0.1888, simple_loss=0.2924, pruned_loss=0.04255, over 7338.00 frames.], tot_loss[loss=0.175, simple_loss=0.2722, pruned_loss=0.03893, over 1421801.98 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:19:24,105 INFO [train.py:763] (5/8) Epoch 17, batch 4200, loss[loss=0.1751, simple_loss=0.2591, pruned_loss=0.04553, over 7007.00 frames.], tot_loss[loss=0.174, simple_loss=0.2712, pruned_loss=0.03843, over 1422149.57 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:20:29,206 INFO [train.py:763] (5/8) Epoch 17, batch 4250, loss[loss=0.2084, simple_loss=0.305, pruned_loss=0.0559, over 7020.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2712, pruned_loss=0.03873, over 1417366.24 frames.], batch size: 32, lr: 4.26e-04
2022-04-29 13:21:35,164 INFO [train.py:763] (5/8) Epoch 17, batch 4300, loss[loss=0.1402, simple_loss=0.2321, pruned_loss=0.02412, over 7005.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2706, pruned_loss=0.03826, over 1418232.71 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:22:49,727 INFO [train.py:763] (5/8) Epoch 17, batch 4350, loss[loss=0.1738, simple_loss=0.2738, pruned_loss=0.03687, over 7221.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2712, pruned_loss=0.03868, over 1405219.09 frames.], batch size: 21, lr: 4.26e-04
2022-04-29 13:23:54,554 INFO [train.py:763] (5/8) Epoch 17, batch 4400, loss[loss=0.1337, simple_loss=0.2286, pruned_loss=0.0194, over 7061.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2724, pruned_loss=0.03918, over 1398939.36 frames.], batch size: 18, lr: 4.26e-04
2022-04-29 13:24:59,620 INFO [train.py:763] (5/8) Epoch 17, batch 4450, loss[loss=0.1852, simple_loss=0.2729, pruned_loss=0.04877, over 6286.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2731, pruned_loss=0.03919, over 1391704.55 frames.], batch size: 37, lr: 4.26e-04
2022-04-29 13:26:04,077 INFO [train.py:763] (5/8) Epoch 17, batch 4500, loss[loss=0.1541, simple_loss=0.2542, pruned_loss=0.02696, over 7014.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2742, pruned_loss=0.03978, over 1380115.76 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:27:09,438 INFO [train.py:763] (5/8) Epoch 17, batch 4550, loss[loss=0.1631, simple_loss=0.2653, pruned_loss=0.03041, over 7156.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2735, pruned_loss=0.03966, over 1369490.68 frames.], batch size: 19, lr: 4.26e-04
2022-04-29 13:29:06,514 INFO [train.py:763] (5/8) Epoch 18, batch 0, loss[loss=0.1762, simple_loss=0.2751, pruned_loss=0.03871, over 7267.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2751, pruned_loss=0.03871, over 7267.00 frames.], batch size: 25, lr: 4.15e-04
2022-04-29 13:30:22,090 INFO [train.py:763] (5/8) Epoch 18, batch 50, loss[loss=0.1902, simple_loss=0.2846, pruned_loss=0.04795, over 7341.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2731, pruned_loss=0.03852, over 325650.61 frames.], batch size: 22, lr: 4.15e-04
2022-04-29 13:31:37,252 INFO [train.py:763] (5/8) Epoch 18, batch 100, loss[loss=0.1759, simple_loss=0.2794, pruned_loss=0.03618, over 7342.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2695, pruned_loss=0.03664, over 575347.68 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:32:51,556 INFO [train.py:763] (5/8) Epoch 18, batch 150, loss[loss=0.1741, simple_loss=0.2786, pruned_loss=0.03481, over 7221.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2693, pruned_loss=0.03678, over 764437.60 frames.], batch size: 21, lr: 4.14e-04
2022-04-29 13:33:57,486 INFO [train.py:763] (5/8) Epoch 18, batch 200, loss[loss=0.1813, simple_loss=0.2604, pruned_loss=0.05107, over 7281.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2695, pruned_loss=0.03775, over 909630.04 frames.], batch size: 17, lr: 4.14e-04
2022-04-29 13:35:11,772 INFO [train.py:763] (5/8) Epoch 18, batch 250, loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03162, over 6736.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2701, pruned_loss=0.03873, over 1025581.79 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:36:17,275 INFO [train.py:763] (5/8) Epoch 18, batch 300, loss[loss=0.157, simple_loss=0.2493, pruned_loss=0.03233, over 7240.00 frames.], tot_loss[loss=0.1733, simple_loss=0.27, pruned_loss=0.03829, over 1115688.13 frames.], batch size: 20, lr: 4.14e-04
2022-04-29 13:37:24,214 INFO [train.py:763] (5/8) Epoch 18, batch 350, loss[loss=0.1972, simple_loss=0.2886, pruned_loss=0.05291, over 6775.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2698, pruned_loss=0.03802, over 1183087.02 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:38:31,278 INFO [train.py:763] (5/8) Epoch 18, batch 400, loss[loss=0.1964, simple_loss=0.2721, pruned_loss=0.06033, over 7061.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2716, pruned_loss=0.03858, over 1235219.53 frames.], batch size: 18, lr: 4.14e-04
2022-04-29 13:39:38,760 INFO [train.py:763] (5/8) Epoch 18, batch 450, loss[loss=0.1875, simple_loss=0.2968, pruned_loss=0.03912, over 7343.00 frames.], tot_loss[loss=0.1749, simple_loss=0.272, pruned_loss=0.03885, over 1276948.38 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:40:45,508 INFO [train.py:763] (5/8) Epoch 18, batch 500, loss[loss=0.1447, simple_loss=0.2281, pruned_loss=0.03068, over 7128.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2723, pruned_loss=0.03901, over 1307575.72 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:41:52,282 INFO [train.py:763] (5/8) Epoch 18, batch 550, loss[loss=0.1532, simple_loss=0.2412, pruned_loss=0.03265, over 7285.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2717, pruned_loss=0.0384, over 1336827.86 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:42:57,725 INFO [train.py:763] (5/8) Epoch 18, batch 600, loss[loss=0.1479, simple_loss=0.2439, pruned_loss=0.02599, over 7276.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2721, pruned_loss=0.03861, over 1357026.60 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:44:04,381 INFO [train.py:763] (5/8) Epoch 18, batch 650, loss[loss=0.166, simple_loss=0.273, pruned_loss=0.02949, over 7119.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2718, pruned_loss=0.03879, over 1375536.61 frames.], batch size: 21, lr: 4.13e-04
2022-04-29 13:45:09,479 INFO [train.py:763] (5/8) Epoch 18, batch 700, loss[loss=0.1861, simple_loss=0.2769, pruned_loss=0.0477, over 4862.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2724, pruned_loss=0.0392, over 1385391.79 frames.], batch size: 53, lr: 4.13e-04
2022-04-29 13:46:15,218 INFO [train.py:763] (5/8) Epoch 18, batch 750, loss[loss=0.1539, simple_loss=0.2535, pruned_loss=0.02713, over 7167.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2719, pruned_loss=0.03884, over 1394071.74 frames.], batch size: 19, lr: 4.13e-04
2022-04-29 13:47:20,152 INFO [train.py:763] (5/8) Epoch 18, batch 800, loss[loss=0.1923, simple_loss=0.2945, pruned_loss=0.04503, over 6755.00 frames.], tot_loss[loss=0.1748, simple_loss=0.272, pruned_loss=0.03875, over 1396165.13 frames.], batch size: 31, lr: 4.13e-04
2022-04-29 13:48:26,406 INFO [train.py:763] (5/8) Epoch 18, batch 850, loss[loss=0.1467, simple_loss=0.2519, pruned_loss=0.02074, over 7070.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03847, over 1403507.28 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:49:33,110 INFO [train.py:763] (5/8) Epoch 18, batch 900, loss[loss=0.1757, simple_loss=0.2563, pruned_loss=0.04759, over 6846.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2734, pruned_loss=0.03882, over 1408818.69 frames.], batch size: 15, lr: 4.12e-04
2022-04-29 13:50:38,408 INFO [train.py:763] (5/8) Epoch 18, batch 950, loss[loss=0.1949, simple_loss=0.2943, pruned_loss=0.0477, over 7374.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2718, pruned_loss=0.0383, over 1412316.33 frames.], batch size: 23, lr: 4.12e-04
2022-04-29 13:51:45,517 INFO [train.py:763] (5/8) Epoch 18, batch 1000, loss[loss=0.1691, simple_loss=0.2728, pruned_loss=0.03266, over 7140.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2717, pruned_loss=0.03795, over 1419182.35 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:52:52,993 INFO [train.py:763] (5/8) Epoch 18, batch 1050, loss[loss=0.1836, simple_loss=0.2936, pruned_loss=0.03681, over 7297.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03821, over 1417465.38 frames.], batch size: 25, lr: 4.12e-04
2022-04-29 13:53:58,533 INFO [train.py:763] (5/8) Epoch 18, batch 1100, loss[loss=0.1851, simple_loss=0.2833, pruned_loss=0.0435, over 7321.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2715, pruned_loss=0.03812, over 1417697.36 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:55:03,940 INFO [train.py:763] (5/8) Epoch 18, batch 1150, loss[loss=0.2031, simple_loss=0.2956, pruned_loss=0.05525, over 7283.00 frames.], tot_loss[loss=0.1745, simple_loss=0.272, pruned_loss=0.03847, over 1418486.03 frames.], batch size: 24, lr: 4.12e-04
2022-04-29 13:56:09,836 INFO [train.py:763] (5/8) Epoch 18, batch 1200, loss[loss=0.2282, simple_loss=0.3137, pruned_loss=0.07137, over 4989.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03856, over 1412922.65 frames.], batch size: 52, lr: 4.12e-04
2022-04-29 13:57:15,054 INFO [train.py:763] (5/8) Epoch 18, batch 1250, loss[loss=0.1762, simple_loss=0.2859, pruned_loss=0.0333, over 7110.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.038, over 1413290.20 frames.], batch size: 21, lr: 4.12e-04
2022-04-29 13:58:20,087 INFO [train.py:763] (5/8) Epoch 18, batch 1300, loss[loss=0.1574, simple_loss=0.2537, pruned_loss=0.03053, over 7157.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2722, pruned_loss=0.03862, over 1414569.70 frames.], batch size: 19, lr: 4.12e-04
2022-04-29 13:59:25,402 INFO [train.py:763] (5/8) Epoch 18, batch 1350, loss[loss=0.2116, simple_loss=0.2982, pruned_loss=0.0625, over 6961.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2733, pruned_loss=0.03945, over 1411838.90 frames.], batch size: 28, lr: 4.11e-04
2022-04-29 14:00:32,489 INFO [train.py:763] (5/8) Epoch 18, batch 1400, loss[loss=0.1556, simple_loss=0.2484, pruned_loss=0.03138, over 7051.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2721, pruned_loss=0.03886, over 1409802.95 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:01:39,736 INFO [train.py:763] (5/8) Epoch 18, batch 1450, loss[loss=0.177, simple_loss=0.2789, pruned_loss=0.03759, over 7317.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03839, over 1416838.47 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:02:46,025 INFO [train.py:763] (5/8) Epoch 18, batch 1500, loss[loss=0.1451, simple_loss=0.2377, pruned_loss=0.02621, over 7262.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03833, over 1420695.16 frames.], batch size: 19, lr: 4.11e-04
2022-04-29 14:03:53,122 INFO [train.py:763] (5/8) Epoch 18, batch 1550, loss[loss=0.1865, simple_loss=0.2935, pruned_loss=0.03974, over 7413.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2714, pruned_loss=0.03798, over 1424314.82 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:04:58,310 INFO [train.py:763] (5/8) Epoch 18, batch 1600, loss[loss=0.1892, simple_loss=0.2837, pruned_loss=0.04736, over 7209.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2716, pruned_loss=0.03813, over 1423491.03 frames.], batch size: 22, lr: 4.11e-04
2022-04-29 14:06:03,951 INFO [train.py:763] (5/8) Epoch 18, batch 1650, loss[loss=0.1767, simple_loss=0.2636, pruned_loss=0.04487, over 7165.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2714, pruned_loss=0.03816, over 1422735.65 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:07:10,558 INFO [train.py:763] (5/8) Epoch 18, batch 1700, loss[loss=0.1838, simple_loss=0.2753, pruned_loss=0.04617, over 7152.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2721, pruned_loss=0.03819, over 1423407.34 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:08:17,586 INFO [train.py:763] (5/8) Epoch 18, batch 1750, loss[loss=0.1742, simple_loss=0.2702, pruned_loss=0.03905, over 7146.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2728, pruned_loss=0.03867, over 1416290.30 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:09:24,698 INFO [train.py:763] (5/8) Epoch 18, batch 1800, loss[loss=0.1748, simple_loss=0.2718, pruned_loss=0.03888, over 7266.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2733, pruned_loss=0.03859, over 1417321.44 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:10:32,230 INFO [train.py:763] (5/8) Epoch 18, batch 1850, loss[loss=0.1862, simple_loss=0.2993, pruned_loss=0.03657, over 7315.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2733, pruned_loss=0.03852, over 1422753.38 frames.], batch size: 24, lr: 4.10e-04
2022-04-29 14:11:39,565 INFO [train.py:763] (5/8) Epoch 18, batch 1900, loss[loss=0.1637, simple_loss=0.2708, pruned_loss=0.02831, over 7151.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2733, pruned_loss=0.03848, over 1419871.55 frames.], batch size: 28, lr: 4.10e-04
2022-04-29 14:12:46,676 INFO [train.py:763] (5/8) Epoch 18, batch 1950, loss[loss=0.1517, simple_loss=0.2472, pruned_loss=0.02813, over 7006.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2738, pruned_loss=0.03881, over 1420833.12 frames.], batch size: 16, lr: 4.10e-04
2022-04-29 14:13:51,993 INFO [train.py:763] (5/8) Epoch 18, batch 2000, loss[loss=0.1723, simple_loss=0.2842, pruned_loss=0.03018, over 7141.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2732, pruned_loss=0.03878, over 1424284.80 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:14:57,427 INFO [train.py:763] (5/8) Epoch 18, batch 2050, loss[loss=0.1767, simple_loss=0.2735, pruned_loss=0.04001, over 7329.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2721, pruned_loss=0.03849, over 1424938.32 frames.], batch size: 25, lr: 4.10e-04
2022-04-29 14:16:02,573 INFO [train.py:763] (5/8) Epoch 18, batch 2100, loss[loss=0.1603, simple_loss=0.264, pruned_loss=0.0283, over 7162.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2725, pruned_loss=0.03833, over 1425292.70 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:17:08,137 INFO [train.py:763] (5/8) Epoch 18, batch 2150, loss[loss=0.1811, simple_loss=0.2852, pruned_loss=0.03852, over 7224.00 frames.], tot_loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.03867, over 1422223.22 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:18:13,401 INFO [train.py:763] (5/8) Epoch 18, batch 2200, loss[loss=0.1921, simple_loss=0.2948, pruned_loss=0.04474, over 7113.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2721, pruned_loss=0.03823, over 1425919.45 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:19:18,573 INFO [train.py:763] (5/8) Epoch 18, batch 2250, loss[loss=0.167, simple_loss=0.2718, pruned_loss=0.03106, over 6271.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2725, pruned_loss=0.03827, over 1425134.15 frames.], batch size: 37, lr: 4.09e-04
2022-04-29 14:20:23,891 INFO [train.py:763] (5/8) Epoch 18, batch 2300, loss[loss=0.1818, simple_loss=0.2801, pruned_loss=0.04173, over 7380.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2725, pruned_loss=0.03848, over 1426154.28 frames.], batch size: 23, lr: 4.09e-04
2022-04-29 14:21:28,915 INFO [train.py:763] (5/8) Epoch 18, batch 2350, loss[loss=0.1409, simple_loss=0.233, pruned_loss=0.02444, over 7277.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2718, pruned_loss=0.03794, over 1424074.00 frames.], batch size: 17, lr: 4.09e-04
2022-04-29 14:22:34,039 INFO [train.py:763] (5/8) Epoch 18, batch 2400, loss[loss=0.1737, simple_loss=0.269, pruned_loss=0.03913, over 7145.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2721, pruned_loss=0.03842, over 1420824.67 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:23:41,120 INFO [train.py:763] (5/8) Epoch 18, batch 2450, loss[loss=0.1938, simple_loss=0.3008, pruned_loss=0.04341, over 7141.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2717, pruned_loss=0.03802, over 1423146.29 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:24:46,859 INFO [train.py:763] (5/8) Epoch 18, batch 2500, loss[loss=0.1881, simple_loss=0.2903, pruned_loss=0.04295, over 7125.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2717, pruned_loss=0.03839, over 1421643.66 frames.], batch size: 26, lr: 4.09e-04
2022-04-29 14:25:51,855 INFO [train.py:763] (5/8) Epoch 18, batch 2550, loss[loss=0.1956, simple_loss=0.2987, pruned_loss=0.04627, over 7287.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2716, pruned_loss=0.0389, over 1421871.33 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:26:57,015 INFO [train.py:763] (5/8) Epoch 18, batch 2600, loss[loss=0.1318, simple_loss=0.2273, pruned_loss=0.01816, over 6997.00 frames.], tot_loss[loss=0.1756, simple_loss=0.273, pruned_loss=0.03909, over 1425767.65 frames.], batch size: 16, lr: 4.08e-04
2022-04-29 14:28:02,334 INFO [train.py:763] (5/8) Epoch 18, batch 2650, loss[loss=0.2209, simple_loss=0.3132, pruned_loss=0.06431, over 7289.00 frames.], tot_loss[loss=0.176, simple_loss=0.2733, pruned_loss=0.03937, over 1427724.14 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:29:08,099 INFO [train.py:763] (5/8) Epoch 18, batch 2700, loss[loss=0.1925, simple_loss=0.2849, pruned_loss=0.05007, over 7314.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2721, pruned_loss=0.03865, over 1431632.81 frames.], batch size: 25, lr: 4.08e-04
2022-04-29 14:30:14,906 INFO [train.py:763] (5/8) Epoch 18, batch 2750, loss[loss=0.18, simple_loss=0.286, pruned_loss=0.03699, over 7409.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2731, pruned_loss=0.03905, over 1430529.70 frames.], batch size: 21, lr: 4.08e-04
2022-04-29 14:31:21,341 INFO [train.py:763] (5/8) Epoch 18, batch 2800, loss[loss=0.2012, simple_loss=0.304, pruned_loss=0.04925, over 7075.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2729, pruned_loss=0.03892, over 1431042.22 frames.], batch size: 18, lr: 4.08e-04
2022-04-29 14:32:26,510 INFO [train.py:763] (5/8) Epoch 18, batch 2850, loss[loss=0.1898, simple_loss=0.2821, pruned_loss=0.04877, over 7166.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03849, over 1427604.33 frames.], batch size: 19, lr: 4.08e-04
2022-04-29 14:33:31,784 INFO [train.py:763] (5/8) Epoch 18, batch 2900, loss[loss=0.1953, simple_loss=0.2941, pruned_loss=0.04824, over 7144.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2722, pruned_loss=0.03834, over 1424993.49 frames.], batch size: 26, lr: 4.08e-04
2022-04-29 14:34:37,295 INFO [train.py:763] (5/8) Epoch 18, batch 2950, loss[loss=0.1465, simple_loss=0.2387, pruned_loss=0.02715, over 7271.00 frames.], tot_loss[loss=0.1744, simple_loss=0.272, pruned_loss=0.0384, over 1430175.52 frames.], batch size: 17, lr: 4.08e-04
2022-04-29 14:35:43,267 INFO [train.py:763] (5/8) Epoch 18, batch 3000, loss[loss=0.2179, simple_loss=0.3013, pruned_loss=0.06721, over 4807.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2715, pruned_loss=0.03834, over 1429350.63 frames.], batch size: 52, lr: 4.07e-04
2022-04-29 14:35:43,268 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 14:35:58,559 INFO [train.py:792] (5/8) Epoch 18, validation: loss=0.1668, simple_loss=0.2671, pruned_loss=0.03324, over 698248.00 frames.
2022-04-29 14:37:05,490 INFO [train.py:763] (5/8) Epoch 18, batch 3050, loss[loss=0.2028, simple_loss=0.2995, pruned_loss=0.05303, over 7184.00 frames.], tot_loss[loss=0.174, simple_loss=0.2713, pruned_loss=0.0383, over 1431007.58 frames.], batch size: 23, lr: 4.07e-04
2022-04-29 14:38:12,687 INFO [train.py:763] (5/8) Epoch 18, batch 3100, loss[loss=0.1699, simple_loss=0.2727, pruned_loss=0.03357, over 6437.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2711, pruned_loss=0.03828, over 1432241.68 frames.], batch size: 38, lr: 4.07e-04
2022-04-29 14:39:19,434 INFO [train.py:763] (5/8) Epoch 18, batch 3150, loss[loss=0.1597, simple_loss=0.2575, pruned_loss=0.03099, over 7273.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2712, pruned_loss=0.03825, over 1429899.33 frames.], batch size: 18, lr: 4.07e-04
2022-04-29 14:40:26,420 INFO [train.py:763] (5/8) Epoch 18, batch 3200, loss[loss=0.1832, simple_loss=0.2778, pruned_loss=0.04433, over 7172.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2708, pruned_loss=0.03801, over 1428768.32 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:41:32,523 INFO [train.py:763] (5/8) Epoch 18, batch 3250, loss[loss=0.1549, simple_loss=0.2459, pruned_loss=0.03201, over 7359.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2719, pruned_loss=0.03818, over 1425659.00 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:42:37,744 INFO [train.py:763] (5/8) Epoch 18, batch 3300, loss[loss=0.164, simple_loss=0.2725, pruned_loss=0.02775, over 6334.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2725, pruned_loss=0.03851, over 1425486.73 frames.], batch size: 38, lr: 4.07e-04
2022-04-29 14:43:43,240 INFO [train.py:763] (5/8) Epoch 18, batch 3350, loss[loss=0.1887, simple_loss=0.2915, pruned_loss=0.04297, over 7119.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2722, pruned_loss=0.03837, over 1424690.06 frames.], batch size: 21, lr: 4.07e-04
2022-04-29 14:44:48,486 INFO [train.py:763] (5/8) Epoch 18, batch 3400, loss[loss=0.1759, simple_loss=0.2662, pruned_loss=0.04279, over 7271.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2723, pruned_loss=0.03831, over 1424932.01 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:45:53,985 INFO [train.py:763] (5/8) Epoch 18, batch 3450, loss[loss=0.1432, simple_loss=0.2445, pruned_loss=0.02095, over 7359.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2699, pruned_loss=0.0375, over 1420893.88 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:46:59,200 INFO [train.py:763] (5/8) Epoch 18, batch 3500, loss[loss=0.1805, simple_loss=0.2703, pruned_loss=0.04532, over 7274.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2699, pruned_loss=0.03729, over 1423105.18 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:48:04,604 INFO [train.py:763] (5/8) Epoch 18, batch 3550, loss[loss=0.1555, simple_loss=0.244, pruned_loss=0.03353, over 7120.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2698, pruned_loss=0.03748, over 1423906.50 frames.], batch size: 17, lr: 4.06e-04
2022-04-29 14:49:09,820 INFO [train.py:763] (5/8) Epoch 18, batch 3600, loss[loss=0.1828, simple_loss=0.2801, pruned_loss=0.04275, over 7189.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2705, pruned_loss=0.03788, over 1420374.36 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:50:14,983 INFO [train.py:763] (5/8) Epoch 18, batch 3650, loss[loss=0.1848, simple_loss=0.2891, pruned_loss=0.0402, over 7319.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2714, pruned_loss=0.03835, over 1414667.39 frames.], batch size: 20, lr: 4.06e-04
2022-04-29 14:51:20,204 INFO [train.py:763] (5/8) Epoch 18, batch 3700, loss[loss=0.1822, simple_loss=0.2864, pruned_loss=0.039, over 7410.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2739, pruned_loss=0.03955, over 1417231.12 frames.], batch size: 21, lr: 4.06e-04
2022-04-29 14:52:25,586 INFO [train.py:763] (5/8) Epoch 18, batch 3750, loss[loss=0.2094, simple_loss=0.2988, pruned_loss=0.05999, over 7385.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03985, over 1413559.60 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:53:30,897 INFO [train.py:763] (5/8) Epoch 18, batch 3800, loss[loss=0.1765, simple_loss=0.2733, pruned_loss=0.03984, over 7354.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2743, pruned_loss=0.03974, over 1418745.06 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:54:36,411 INFO [train.py:763] (5/8) Epoch 18, batch 3850, loss[loss=0.1597, simple_loss=0.2489, pruned_loss=0.03523, over 7176.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2733, pruned_loss=0.03947, over 1417202.68 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:55:41,218 INFO [train.py:763] (5/8) Epoch 18, batch 3900, loss[loss=0.1602, simple_loss=0.2618, pruned_loss=0.02931, over 7112.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2739, pruned_loss=0.03951, over 1414587.03 frames.], batch size: 21, lr: 4.05e-04
2022-04-29 14:56:46,303 INFO [train.py:763] (5/8) Epoch 18, batch 3950, loss[loss=0.1927, simple_loss=0.2959, pruned_loss=0.04474, over 7155.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03964, over 1416356.91 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:57:51,530 INFO [train.py:763] (5/8) Epoch 18, batch 4000, loss[loss=0.1928, simple_loss=0.2892, pruned_loss=0.04821, over 5116.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03927, over 1418460.54 frames.], batch size: 52, lr: 4.05e-04
2022-04-29 14:58:57,196 INFO [train.py:763] (5/8) Epoch 18, batch 4050, loss[loss=0.1523, simple_loss=0.2378, pruned_loss=0.03343, over 6808.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2716, pruned_loss=0.03887, over 1416059.74 frames.], batch size: 15, lr: 4.05e-04
2022-04-29 15:00:03,392 INFO [train.py:763] (5/8) Epoch 18, batch 4100, loss[loss=0.1994, simple_loss=0.2894, pruned_loss=0.05466, over 4753.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2721, pruned_loss=0.03901, over 1415796.44 frames.], batch size: 52, lr: 4.05e-04
2022-04-29 15:01:09,080 INFO [train.py:763] (5/8) Epoch 18, batch 4150, loss[loss=0.1694, simple_loss=0.2797, pruned_loss=0.02952, over 7389.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2713, pruned_loss=0.03864, over 1421394.46 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:02:16,183 INFO [train.py:763] (5/8) Epoch 18, batch 4200, loss[loss=0.1755, simple_loss=0.2702, pruned_loss=0.04041, over 7208.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2716, pruned_loss=0.03863, over 1419615.35 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:03:23,613 INFO [train.py:763] (5/8) Epoch 18, batch 4250, loss[loss=0.1485, simple_loss=0.2411, pruned_loss=0.02798, over 6826.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2717, pruned_loss=0.03865, over 1419689.11 frames.], batch size: 15, lr: 4.04e-04
2022-04-29 15:04:28,934 INFO [train.py:763] (5/8) Epoch 18, batch 4300, loss[loss=0.2047, simple_loss=0.3001, pruned_loss=0.05461, over 7149.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2711, pruned_loss=0.03827, over 1418905.67 frames.], batch size: 26, lr: 4.04e-04
2022-04-29 15:05:35,082 INFO [train.py:763] (5/8) Epoch 18, batch 4350, loss[loss=0.1723, simple_loss=0.2728, pruned_loss=0.03589, over 7165.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2703, pruned_loss=0.038, over 1416390.13 frames.], batch size: 18, lr: 4.04e-04
2022-04-29 15:06:42,528 INFO [train.py:763] (5/8) Epoch 18, batch 4400, loss[loss=0.1827, simple_loss=0.2833, pruned_loss=0.04106, over 6436.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2703, pruned_loss=0.03819, over 1411857.71 frames.], batch size: 38, lr: 4.04e-04
2022-04-29 15:07:48,914 INFO [train.py:763] (5/8) Epoch 18, batch 4450, loss[loss=0.146, simple_loss=0.235, pruned_loss=0.02855, over 6780.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2693, pruned_loss=0.03821, over 1406797.83 frames.], batch size: 15, lr: 4.04e-04
2022-04-29 15:08:55,428 INFO [train.py:763] (5/8) Epoch 18, batch 4500, loss[loss=0.1639, simple_loss=0.2625, pruned_loss=0.03262, over 7150.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2706, pruned_loss=0.03866, over 1394291.49 frames.], batch size: 20, lr: 4.04e-04
2022-04-29 15:10:01,685 INFO [train.py:763] (5/8) Epoch 18, batch 4550, loss[loss=0.182, simple_loss=0.2812, pruned_loss=0.04142, over 6434.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2699, pruned_loss=0.03887, over 1368466.23 frames.], batch size: 38, lr: 4.04e-04
2022-04-29 15:11:30,601 INFO [train.py:763] (5/8) Epoch 19, batch 0, loss[loss=0.1546, simple_loss=0.2499, pruned_loss=0.02965, over 7356.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2499, pruned_loss=0.02965, over 7356.00 frames.], batch size: 19, lr: 3.94e-04
2022-04-29 15:12:36,743 INFO [train.py:763] (5/8) Epoch 19, batch 50, loss[loss=0.1561, simple_loss=0.2432, pruned_loss=0.03443, over 7285.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2697, pruned_loss=0.0375, over 320836.83 frames.], batch size: 18, lr: 3.94e-04
2022-04-29 15:13:42,682 INFO [train.py:763] (5/8) Epoch 19, batch 100, loss[loss=0.2182, simple_loss=0.307, pruned_loss=0.06467, over 5212.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2698, pruned_loss=0.03756, over 566036.96 frames.], batch size: 53, lr: 3.94e-04
2022-04-29 15:14:48,879 INFO [train.py:763] (5/8) Epoch 19, batch 150, loss[loss=0.1714, simple_loss=0.2769, pruned_loss=0.03295, over 7318.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2726, pruned_loss=0.03714, over 756368.93 frames.], batch size: 21, lr: 3.94e-04
2022-04-29 15:15:54,344 INFO [train.py:763] (5/8) Epoch 19, batch 200, loss[loss=0.1668, simple_loss=0.2741, pruned_loss=0.02978, over 7321.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2728, pruned_loss=0.03751, over 904007.07 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:17:00,302 INFO [train.py:763] (5/8) Epoch 19, batch 250, loss[loss=0.1701, simple_loss=0.2764, pruned_loss=0.03187, over 7329.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2708, pruned_loss=0.03677, over 1022811.94 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:18:06,691 INFO [train.py:763] (5/8) Epoch 19, batch 300, loss[loss=0.2005, simple_loss=0.305, pruned_loss=0.04799, over 7198.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2722, pruned_loss=0.03663, over 1112221.42 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:19:12,756 INFO [train.py:763] (5/8) Epoch 19, batch 350, loss[loss=0.1758, simple_loss=0.2783, pruned_loss=0.0367, over 7149.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2723, pruned_loss=0.0368, over 1184928.82 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:20:18,125 INFO [train.py:763] (5/8) Epoch 19, batch 400, loss[loss=0.1652, simple_loss=0.2704, pruned_loss=0.03001, over 7143.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2726, pruned_loss=0.03715, over 1237415.35 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:21:23,460 INFO [train.py:763] (5/8) Epoch 19, batch 450, loss[loss=0.1827, simple_loss=0.2818, pruned_loss=0.04177, over 7374.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2735, pruned_loss=0.03774, over 1274816.80 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:22:28,668 INFO [train.py:763] (5/8) Epoch 19, batch 500, loss[loss=0.1586, simple_loss=0.2705, pruned_loss=0.02334, over 7228.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2728, pruned_loss=0.03743, over 1306332.45 frames.], batch size: 21, lr: 3.93e-04
2022-04-29 15:23:34,245 INFO [train.py:763] (5/8) Epoch 19, batch 550, loss[loss=0.1741, simple_loss=0.2766, pruned_loss=0.03582, over 6872.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2724, pruned_loss=0.03734, over 1332869.13 frames.], batch size: 31, lr: 3.93e-04
2022-04-29 15:24:40,474 INFO [train.py:763] (5/8) Epoch 19, batch 600, loss[loss=0.149, simple_loss=0.2426, pruned_loss=0.02776, over 7162.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2702, pruned_loss=0.0366, over 1354924.67 frames.], batch size: 18, lr: 3.93e-04
2022-04-29 15:25:45,945 INFO [train.py:763] (5/8) Epoch 19, batch 650, loss[loss=0.1727, simple_loss=0.2653, pruned_loss=0.04004, over 7172.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2706, pruned_loss=0.03677, over 1369270.96 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:26:51,173 INFO [train.py:763] (5/8) Epoch 19, batch 700, loss[loss=0.1906, simple_loss=0.289, pruned_loss=0.04611, over 7232.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2717, pruned_loss=0.03746, over 1383081.54 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:27:56,786 INFO [train.py:763] (5/8) Epoch 19, batch 750, loss[loss=0.2028, simple_loss=0.3041, pruned_loss=0.05075, over 7294.00 frames.], tot_loss[loss=0.1728, simple_loss=0.271, pruned_loss=0.03726, over 1393384.73 frames.], batch size: 25, lr: 3.92e-04
2022-04-29 15:29:03,460 INFO [train.py:763] (5/8) Epoch 19, batch 800, loss[loss=0.1473, simple_loss=0.2412, pruned_loss=0.02671, over 7419.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2708, pruned_loss=0.03692, over 1402292.00 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:30:19,520 INFO [train.py:763] (5/8) Epoch 19, batch 850, loss[loss=0.2093, simple_loss=0.297, pruned_loss=0.06082, over 7089.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2717, pruned_loss=0.0373, over 1410189.01 frames.], batch size: 28, lr: 3.92e-04
2022-04-29 15:31:25,293 INFO [train.py:763] (5/8) Epoch 19, batch 900, loss[loss=0.1803, simple_loss=0.2834, pruned_loss=0.03862, over 7356.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2708, pruned_loss=0.03741, over 1415452.97 frames.], batch size: 19, lr: 3.92e-04
2022-04-29 15:32:30,749 INFO [train.py:763] (5/8) Epoch 19, batch 950, loss[loss=0.1726, simple_loss=0.2741, pruned_loss=0.03558, over 7238.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2714, pruned_loss=0.03768, over 1419245.46 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:33:36,036 INFO [train.py:763] (5/8) Epoch 19, batch 1000, loss[loss=0.1955, simple_loss=0.3022, pruned_loss=0.04441, over 7267.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.03771, over 1419917.10 frames.], batch size: 24, lr: 3.92e-04
2022-04-29 15:34:41,372 INFO [train.py:763] (5/8) Epoch 19, batch 1050, loss[loss=0.1759, simple_loss=0.268, pruned_loss=0.04188, over 7201.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2716, pruned_loss=0.03775, over 1419722.53 frames.], batch size: 22, lr: 3.92e-04
2022-04-29 15:35:47,015 INFO [train.py:763] (5/8) Epoch 19, batch 1100, loss[loss=0.1947, simple_loss=0.2962, pruned_loss=0.04663, over 7203.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2719, pruned_loss=0.03822, over 1417465.42 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:36:52,334 INFO [train.py:763] (5/8) Epoch 19, batch 1150, loss[loss=0.192, simple_loss=0.294, pruned_loss=0.04504, over 7257.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2729, pruned_loss=0.03833, over 1421160.70 frames.], batch size: 24, lr: 3.91e-04
2022-04-29 15:38:08,758 INFO [train.py:763] (5/8) Epoch 19, batch 1200, loss[loss=0.19, simple_loss=0.2831, pruned_loss=0.04839, over 7345.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.03768, over 1426500.82 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:39:14,193 INFO [train.py:763] (5/8) Epoch 19, batch 1250, loss[loss=0.1568, simple_loss=0.2481, pruned_loss=0.03275, over 7129.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2708, pruned_loss=0.03779, over 1426824.62 frames.], batch size: 17, lr: 3.91e-04
2022-04-29 15:40:19,879 INFO [train.py:763] (5/8) Epoch 19, batch 1300, loss[loss=0.1957, simple_loss=0.2993, pruned_loss=0.04607, over 7113.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2707, pruned_loss=0.03789, over 1428450.36 frames.], batch size: 21, lr: 3.91e-04
2022-04-29 15:41:25,082 INFO [train.py:763] (5/8) Epoch 19, batch 1350, loss[loss=0.2011, simple_loss=0.3089, pruned_loss=0.04663, over 7209.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.03785, over 1431141.07 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:42:30,866 INFO [train.py:763] (5/8) Epoch 19, batch 1400, loss[loss=0.1758, simple_loss=0.2731, pruned_loss=0.03923, over 7199.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2714, pruned_loss=0.03775, over 1432571.84 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:43:46,248 INFO [train.py:763] (5/8) Epoch 19, batch 1450, loss[loss=0.1857, simple_loss=0.2899, pruned_loss=0.04077, over 7205.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2725, pruned_loss=0.03829, over 1430358.77 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:45:09,723 INFO [train.py:763] (5/8) Epoch 19, batch 1500, loss[loss=0.1599, simple_loss=0.2688, pruned_loss=0.0255, over 7372.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2732, pruned_loss=0.03847, over 1427966.63 frames.], batch size: 23, lr: 3.91e-04
2022-04-29 15:46:15,430 INFO [train.py:763] (5/8) Epoch 19, batch 1550, loss[loss=0.1496, simple_loss=0.2507, pruned_loss=0.02424, over 7433.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2727, pruned_loss=0.03819, over 1430467.68 frames.], batch size: 20, lr: 3.91e-04
2022-04-29 15:47:30,079 INFO [train.py:763] (5/8) Epoch 19, batch 1600, loss[loss=0.1755, simple_loss=0.2818, pruned_loss=0.03463, over 7346.00 frames.], tot_loss[loss=0.1745, simple_loss=0.273, pruned_loss=0.03804, over 1425458.52 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:48:53,977 INFO [train.py:763] (5/8) Epoch 19, batch 1650, loss[loss=0.169, simple_loss=0.2736, pruned_loss=0.0322, over 7197.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2725, pruned_loss=0.03789, over 1421665.75 frames.], batch size: 23, lr: 3.90e-04
2022-04-29 15:50:08,831 INFO [train.py:763] (5/8) Epoch 19, batch 1700, loss[loss=0.1667, simple_loss=0.2579, pruned_loss=0.03773, over 7160.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2717, pruned_loss=0.03753, over 1421118.67 frames.], batch size: 19, lr: 3.90e-04
2022-04-29 15:51:14,407 INFO [train.py:763] (5/8) Epoch 19, batch 1750, loss[loss=0.1788, simple_loss=0.2897, pruned_loss=0.03397, over 7336.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2717, pruned_loss=0.03752, over 1426280.29 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:52:20,002 INFO [train.py:763] (5/8) Epoch 19, batch 1800, loss[loss=0.1701, simple_loss=0.2813, pruned_loss=0.02942, over 7291.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2715, pruned_loss=0.03736, over 1425561.59 frames.], batch size: 25, lr: 3.90e-04
2022-04-29 15:53:25,560 INFO [train.py:763] (5/8) Epoch 19, batch 1850, loss[loss=0.1701, simple_loss=0.26, pruned_loss=0.0401, over 7060.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2715, pruned_loss=0.03756, over 1428746.21 frames.], batch size: 18, lr: 3.90e-04
2022-04-29 15:54:30,873 INFO [train.py:763] (5/8) Epoch 19, batch 1900, loss[loss=0.1636, simple_loss=0.2666, pruned_loss=0.03026, over 7227.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2716, pruned_loss=0.03731, over 1429793.28 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:55:38,287 INFO [train.py:763] (5/8) Epoch 19, batch 1950, loss[loss=0.1556, simple_loss=0.2632, pruned_loss=0.024, over 6348.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2705, pruned_loss=0.0369, over 1429717.97 frames.], batch size: 38, lr: 3.90e-04
2022-04-29 15:56:45,600 INFO [train.py:763] (5/8) Epoch 19, batch 2000, loss[loss=0.179, simple_loss=0.2812, pruned_loss=0.0384, over 7233.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2698, pruned_loss=0.0369, over 1430592.42 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:57:52,879 INFO [train.py:763] (5/8) Epoch 19, batch 2050, loss[loss=0.1665, simple_loss=0.2718, pruned_loss=0.03063, over 7218.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2686, pruned_loss=0.03657, over 1429676.43 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 15:58:58,695 INFO [train.py:763] (5/8) Epoch 19, batch 2100, loss[loss=0.1677, simple_loss=0.2743, pruned_loss=0.03049, over 7437.00 frames.], tot_loss[loss=0.1709, simple_loss=0.269, pruned_loss=0.03647, over 1432253.44 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:00:05,508 INFO [train.py:763] (5/8) Epoch 19, batch 2150, loss[loss=0.1818, simple_loss=0.2801, pruned_loss=0.04176, over 7198.00 frames.], tot_loss[loss=0.1713, simple_loss=0.269, pruned_loss=0.03674, over 1426741.30 frames.], batch size: 22, lr: 3.89e-04
2022-04-29 16:01:11,310 INFO [train.py:763] (5/8) Epoch 19, batch 2200, loss[loss=0.1448, simple_loss=0.2371, pruned_loss=0.02619, over 6805.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2692, pruned_loss=0.03683, over 1421729.30 frames.], batch size: 15, lr: 3.89e-04
2022-04-29 16:02:17,300 INFO [train.py:763] (5/8) Epoch 19, batch 2250, loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.0325, over 7140.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03691, over 1422774.94 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:03:23,078 INFO [train.py:763] (5/8) Epoch 19, batch 2300, loss[loss=0.1968, simple_loss=0.2958, pruned_loss=0.04894, over 7374.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03635, over 1423007.85 frames.], batch size: 23, lr: 3.89e-04
2022-04-29 16:04:28,771 INFO [train.py:763] (5/8) Epoch 19, batch 2350, loss[loss=0.1594, simple_loss=0.2754, pruned_loss=0.02172, over 7319.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03689, over 1422206.91 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 16:05:34,127 INFO [train.py:763] (5/8) Epoch 19, batch 2400, loss[loss=0.1543, simple_loss=0.2462, pruned_loss=0.03119, over 7440.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03683, over 1423757.06 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:06:39,697 INFO [train.py:763] (5/8) Epoch 19, batch 2450, loss[loss=0.1981, simple_loss=0.2935, pruned_loss=0.05137, over 7006.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2702, pruned_loss=0.0372, over 1426746.54 frames.], batch size: 28, lr: 3.89e-04
2022-04-29 16:07:45,465 INFO [train.py:763] (5/8) Epoch 19, batch 2500, loss[loss=0.1948, simple_loss=0.2999, pruned_loss=0.0449, over 7178.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2699, pruned_loss=0.03739, over 1426520.18 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:08:50,999 INFO [train.py:763] (5/8) Epoch 19, batch 2550, loss[loss=0.1789, simple_loss=0.2737, pruned_loss=0.04205, over 7329.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2701, pruned_loss=0.03756, over 1425574.73 frames.], batch size: 20, lr: 3.88e-04
2022-04-29 16:09:56,850 INFO [train.py:763] (5/8) Epoch 19, batch 2600, loss[loss=0.1737, simple_loss=0.2817, pruned_loss=0.03282, over 6909.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2709, pruned_loss=0.0378, over 1426092.15 frames.], batch size: 31, lr: 3.88e-04
2022-04-29 16:11:03,368 INFO [train.py:763] (5/8) Epoch 19, batch 2650, loss[loss=0.1379, simple_loss=0.2263, pruned_loss=0.02479, over 7010.00 frames.], tot_loss[loss=0.172, simple_loss=0.2697, pruned_loss=0.03718, over 1427625.02 frames.], batch size: 16, lr: 3.88e-04
2022-04-29 16:12:10,014 INFO [train.py:763] (5/8) Epoch 19, batch 2700, loss[loss=0.1975, simple_loss=0.2879, pruned_loss=0.05351, over 7374.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2691, pruned_loss=0.03704, over 1428456.97 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:13:17,141 INFO [train.py:763] (5/8) Epoch 19, batch 2750, loss[loss=0.1637, simple_loss=0.2665, pruned_loss=0.03045, over 7206.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2692, pruned_loss=0.03689, over 1427158.43 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:14:22,710 INFO [train.py:763] (5/8) Epoch 19, batch 2800, loss[loss=0.1557, simple_loss=0.2465, pruned_loss=0.03247, over 7159.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2692, pruned_loss=0.03658, over 1431321.28 frames.], batch size: 18, lr: 3.88e-04
2022-04-29 16:15:28,765 INFO [train.py:763] (5/8) Epoch 19, batch 2850, loss[loss=0.1726, simple_loss=0.2814, pruned_loss=0.0319, over 7410.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2693, pruned_loss=0.03683, over 1433280.12 frames.], batch size: 21, lr: 3.88e-04
2022-04-29 16:16:34,850 INFO [train.py:763] (5/8) Epoch 19, batch 2900, loss[loss=0.1774, simple_loss=0.2776, pruned_loss=0.03856, over 7171.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2685, pruned_loss=0.03639, over 1428422.51 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:17:40,408 INFO [train.py:763] (5/8) Epoch 19, batch 2950, loss[loss=0.1746, simple_loss=0.2845, pruned_loss=0.03231, over 7223.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03693, over 1433270.49 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:18:45,959 INFO [train.py:763] (5/8) Epoch 19, batch 3000, loss[loss=0.2072, simple_loss=0.3093, pruned_loss=0.05253, over 7388.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2717, pruned_loss=0.03746, over 1431923.18 frames.], batch size: 23, lr: 3.87e-04
2022-04-29 16:18:45,960 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 16:19:01,554 INFO [train.py:792] (5/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
2022-04-29 16:20:06,923 INFO [train.py:763] (5/8) Epoch 19, batch 3050, loss[loss=0.1496, simple_loss=0.2505, pruned_loss=0.0243, over 7164.00 frames.], tot_loss[loss=0.173, simple_loss=0.2713, pruned_loss=0.03739, over 1433412.39 frames.], batch size: 19, lr: 3.87e-04
2022-04-29 16:21:12,184 INFO [train.py:763] (5/8) Epoch 19, batch 3100, loss[loss=0.1542, simple_loss=0.263, pruned_loss=0.02266, over 7114.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2717, pruned_loss=0.03779, over 1432695.73 frames.], batch size: 21, lr: 3.87e-04
2022-04-29 16:22:17,535 INFO [train.py:763] (5/8) Epoch 19, batch 3150, loss[loss=0.1639, simple_loss=0.2561, pruned_loss=0.03586, over 7273.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2708, pruned_loss=0.03747, over 1432871.44 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:23:23,029 INFO [train.py:763] (5/8) Epoch 19, batch 3200, loss[loss=0.1656, simple_loss=0.2733, pruned_loss=0.0289, over 6782.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2697, pruned_loss=0.03701, over 1433852.48 frames.], batch size: 31, lr: 3.87e-04
2022-04-29 16:24:28,069 INFO [train.py:763] (5/8) Epoch 19, batch 3250, loss[loss=0.1507, simple_loss=0.2385, pruned_loss=0.03147, over 7075.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03663, over 1429939.10 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:25:34,761 INFO [train.py:763] (5/8) Epoch 19, batch 3300, loss[loss=0.1674, simple_loss=0.2491, pruned_loss=0.04288, over 7135.00 frames.], tot_loss[loss=0.1709, simple_loss=0.269, pruned_loss=0.03637, over 1428946.50 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:26:41,786 INFO [train.py:763] (5/8) Epoch 19, batch 3350, loss[loss=0.1675, simple_loss=0.2697, pruned_loss=0.03265, over 7154.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2689, pruned_loss=0.03612, over 1428620.95 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:27:47,545 INFO [train.py:763] (5/8) Epoch 19, batch 3400, loss[loss=0.1295, simple_loss=0.2243, pruned_loss=0.01733, over 7292.00 frames.], tot_loss[loss=0.171, simple_loss=0.2695, pruned_loss=0.03622, over 1427659.00 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:28:53,018 INFO [train.py:763] (5/8) Epoch 19, batch 3450, loss[loss=0.1899, simple_loss=0.2927, pruned_loss=0.04351, over 7225.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2701, pruned_loss=0.03625, over 1426187.09 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:29:58,530 INFO [train.py:763] (5/8) Epoch 19, batch 3500, loss[loss=0.1642, simple_loss=0.2664, pruned_loss=0.03102, over 7270.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2696, pruned_loss=0.03638, over 1423592.88 frames.], batch size: 19, lr: 3.86e-04
2022-04-29 16:31:03,663 INFO [train.py:763] (5/8) Epoch 19, batch 3550, loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02961, over 7112.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2705, pruned_loss=0.03708, over 1425916.53 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:32:09,196 INFO [train.py:763] (5/8) Epoch 19, batch 3600, loss[loss=0.2098, simple_loss=0.3098, pruned_loss=0.0549, over 7182.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2702, pruned_loss=0.03731, over 1428766.03 frames.], batch size: 23, lr: 3.86e-04
2022-04-29 16:33:15,441 INFO [train.py:763] (5/8) Epoch 19, batch 3650, loss[loss=0.1764, simple_loss=0.2849, pruned_loss=0.03395, over 7318.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2699, pruned_loss=0.03741, over 1429992.11 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:34:21,095 INFO [train.py:763] (5/8) Epoch 19, batch 3700, loss[loss=0.1489, simple_loss=0.2496, pruned_loss=0.02408, over 7175.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2703, pruned_loss=0.03742, over 1431672.66 frames.], batch size: 18, lr: 3.86e-04
2022-04-29 16:35:26,774 INFO [train.py:763] (5/8) Epoch 19, batch 3750, loss[loss=0.2141, simple_loss=0.3104, pruned_loss=0.05893, over 7022.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2701, pruned_loss=0.03768, over 1425935.40 frames.], batch size: 28, lr: 3.86e-04
2022-04-29 16:36:32,310 INFO [train.py:763] (5/8) Epoch 19, batch 3800, loss[loss=0.1583, simple_loss=0.2543, pruned_loss=0.03117, over 7336.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2696, pruned_loss=0.03738, over 1421293.86 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:37:37,909 INFO [train.py:763] (5/8) Epoch 19, batch 3850, loss[loss=0.1508, simple_loss=0.2493, pruned_loss=0.02621, over 7272.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2692, pruned_loss=0.03705, over 1419500.09 frames.], batch size: 17, lr: 3.86e-04
2022-04-29 16:38:44,168 INFO [train.py:763] (5/8) Epoch 19, batch 3900, loss[loss=0.1951, simple_loss=0.2947, pruned_loss=0.04776, over 7105.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2701, pruned_loss=0.03719, over 1417019.40 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:39:50,752 INFO [train.py:763] (5/8) Epoch 19, batch 3950, loss[loss=0.1707, simple_loss=0.2672, pruned_loss=0.03712, over 7328.00 frames.], tot_loss[loss=0.1725, simple_loss=0.27, pruned_loss=0.03756, over 1410842.89 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:40:57,116 INFO [train.py:763] (5/8) Epoch 19, batch 4000, loss[loss=0.1516, simple_loss=0.2512, pruned_loss=0.026, over 7161.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2695, pruned_loss=0.03739, over 1409068.16 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:42:03,329 INFO [train.py:763] (5/8) Epoch 19, batch 4050, loss[loss=0.1662, simple_loss=0.2682, pruned_loss=0.03209, over 7327.00 frames.], tot_loss[loss=0.1719, simple_loss=0.269, pruned_loss=0.03741, over 1406538.55 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:43:09,197 INFO [train.py:763] (5/8) Epoch 19, batch 4100, loss[loss=0.1494, simple_loss=0.2455, pruned_loss=0.02669, over 7278.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2676, pruned_loss=0.03693, over 1407005.66 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:44:14,864 INFO [train.py:763] (5/8) Epoch 19, batch 4150, loss[loss=0.1614, simple_loss=0.2521, pruned_loss=0.03536, over 7063.00 frames.], tot_loss[loss=0.1698, simple_loss=0.267, pruned_loss=0.03636, over 1410701.00 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:45:20,207 INFO [train.py:763] (5/8) Epoch 19, batch 4200, loss[loss=0.148, simple_loss=0.24, pruned_loss=0.02801, over 7298.00 frames.], tot_loss[loss=0.171, simple_loss=0.2684, pruned_loss=0.0368, over 1405622.52 frames.], batch size: 16, lr: 3.85e-04
2022-04-29 16:46:26,006 INFO [train.py:763] (5/8) Epoch 19, batch 4250, loss[loss=0.1848, simple_loss=0.2865, pruned_loss=0.04156, over 7194.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2681, pruned_loss=0.0369, over 1403391.48 frames.], batch size: 23, lr: 3.85e-04
2022-04-29 16:47:31,498 INFO [train.py:763] (5/8) Epoch 19, batch 4300, loss[loss=0.156, simple_loss=0.26, pruned_loss=0.026, over 7213.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2678, pruned_loss=0.03674, over 1401324.70 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:48:37,211 INFO [train.py:763] (5/8) Epoch 19, batch 4350, loss[loss=0.2109, simple_loss=0.2968, pruned_loss=0.06247, over 5057.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2669, pruned_loss=0.03644, over 1403475.12 frames.], batch size: 52, lr: 3.84e-04
2022-04-29 16:49:42,596 INFO [train.py:763] (5/8) Epoch 19, batch 4400, loss[loss=0.1596, simple_loss=0.2525, pruned_loss=0.0333, over 7153.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2661, pruned_loss=0.03616, over 1398217.33 frames.], batch size: 19, lr: 3.84e-04
2022-04-29 16:50:47,791 INFO [train.py:763] (5/8) Epoch 19, batch 4450, loss[loss=0.1497, simple_loss=0.2406, pruned_loss=0.02939, over 7196.00 frames.], tot_loss[loss=0.17, simple_loss=0.2667, pruned_loss=0.03671, over 1390701.97 frames.], batch size: 16, lr: 3.84e-04
2022-04-29 16:51:52,277 INFO [train.py:763] (5/8) Epoch 19, batch 4500, loss[loss=0.1797, simple_loss=0.2899, pruned_loss=0.03477, over 7202.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2688, pruned_loss=0.03729, over 1384156.93 frames.], batch size: 23, lr: 3.84e-04
2022-04-29 16:52:57,058 INFO [train.py:763] (5/8) Epoch 19, batch 4550, loss[loss=0.1796, simple_loss=0.2749, pruned_loss=0.0422, over 6454.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2715, pruned_loss=0.03884, over 1336703.80 frames.], batch size: 38, lr: 3.84e-04
2022-04-29 16:54:25,843 INFO [train.py:763] (5/8) Epoch 20, batch 0, loss[loss=0.1791, simple_loss=0.2581, pruned_loss=0.05002, over 6999.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2581, pruned_loss=0.05002, over 6999.00 frames.], batch size: 16, lr: 3.75e-04
2022-04-29 16:55:32,597 INFO [train.py:763] (5/8) Epoch 20, batch 50, loss[loss=0.1897, simple_loss=0.2902, pruned_loss=0.04461, over 6379.00 frames.], tot_loss[loss=0.1711, simple_loss=0.269, pruned_loss=0.03667, over 322740.23 frames.], batch size: 38, lr: 3.75e-04
2022-04-29 16:56:38,011 INFO [train.py:763] (5/8) Epoch 20, batch 100, loss[loss=0.1648, simple_loss=0.2551, pruned_loss=0.03721, over 6819.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03682, over 565923.90 frames.], batch size: 15, lr: 3.75e-04
2022-04-29 16:57:44,566 INFO [train.py:763] (5/8) Epoch 20, batch 150, loss[loss=0.1545, simple_loss=0.2548, pruned_loss=0.02711, over 7159.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2698, pruned_loss=0.03691, over 755881.57 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 16:58:49,756 INFO [train.py:763] (5/8) Epoch 20, batch 200, loss[loss=0.173, simple_loss=0.2741, pruned_loss=0.03596, over 6755.00 frames.], tot_loss[loss=0.173, simple_loss=0.2709, pruned_loss=0.03756, over 900475.17 frames.], batch size: 31, lr: 3.75e-04
2022-04-29 16:59:55,582 INFO [train.py:763] (5/8) Epoch 20, batch 250, loss[loss=0.1603, simple_loss=0.263, pruned_loss=0.02876, over 7160.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03689, over 1012663.28 frames.], batch size: 19, lr: 3.75e-04
2022-04-29 17:01:00,766 INFO [train.py:763] (5/8) Epoch 20, batch 300, loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03105, over 7278.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2694, pruned_loss=0.03679, over 1101276.77 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 17:02:05,610 INFO [train.py:763] (5/8) Epoch 20, batch 350, loss[loss=0.1507, simple_loss=0.2576, pruned_loss=0.02188, over 7258.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2701, pruned_loss=0.03653, over 1168801.32 frames.], batch size: 19, lr: 3.74e-04
2022-04-29 17:03:10,961 INFO [train.py:763] (5/8) Epoch 20, batch 400, loss[loss=0.1746, simple_loss=0.2694, pruned_loss=0.0399, over 7071.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2689, pruned_loss=0.03628, over 1228146.76 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:04:16,938 INFO [train.py:763] (5/8) Epoch 20, batch 450, loss[loss=0.1959, simple_loss=0.2778, pruned_loss=0.05704, over 7062.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2689, pruned_loss=0.03601, over 1271605.75 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:05:22,378 INFO [train.py:763] (5/8) Epoch 20, batch 500, loss[loss=0.2082, simple_loss=0.3066, pruned_loss=0.05493, over 7038.00 frames.], tot_loss[loss=0.171, simple_loss=0.2693, pruned_loss=0.03631, over 1309913.09 frames.], batch size: 28, lr: 3.74e-04
2022-04-29 17:06:27,719 INFO [train.py:763] (5/8) Epoch 20, batch 550, loss[loss=0.1671, simple_loss=0.2536, pruned_loss=0.0403, over 7231.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2689, pruned_loss=0.03624, over 1336388.54 frames.], batch size: 16, lr: 3.74e-04
2022-04-29 17:07:34,459 INFO [train.py:763] (5/8) Epoch 20, batch 600, loss[loss=0.1756, simple_loss=0.2709, pruned_loss=0.04015, over 7207.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2694, pruned_loss=0.03648, over 1354721.35 frames.], batch size: 22, lr: 3.74e-04
2022-04-29 17:08:41,622 INFO [train.py:763] (5/8) Epoch 20, batch 650, loss[loss=0.1311, simple_loss=0.2211, pruned_loss=0.02058, over 7142.00 frames.], tot_loss[loss=0.17, simple_loss=0.2677, pruned_loss=0.03612, over 1368785.37 frames.], batch size: 17, lr: 3.74e-04
2022-04-29 17:09:47,496 INFO [train.py:763] (5/8) Epoch 20, batch 700, loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03072, over 7231.00 frames.], tot_loss[loss=0.1707, simple_loss=0.269, pruned_loss=0.03615, over 1378632.72 frames.], batch size: 20, lr: 3.74e-04
2022-04-29 17:10:53,620 INFO [train.py:763] (5/8) Epoch 20, batch 750, loss[loss=0.1396, simple_loss=0.235, pruned_loss=0.02209, over 7400.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2695, pruned_loss=0.03641, over 1384482.26 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:11:58,921 INFO [train.py:763] (5/8) Epoch 20, batch 800, loss[loss=0.1675, simple_loss=0.2728, pruned_loss=0.03104, over 7227.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2691, pruned_loss=0.03661, over 1383609.75 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:13:05,460 INFO [train.py:763] (5/8) Epoch 20, batch 850, loss[loss=0.2045, simple_loss=0.2989, pruned_loss=0.05505, over 7289.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2683, pruned_loss=0.03639, over 1390928.16 frames.], batch size: 25, lr: 3.73e-04
2022-04-29 17:14:10,909 INFO [train.py:763] (5/8) Epoch 20, batch 900, loss[loss=0.1923, simple_loss=0.2908, pruned_loss=0.04692, over 7227.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2675, pruned_loss=0.03597, over 1399939.42 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:15:15,951 INFO [train.py:763] (5/8) Epoch 20, batch 950, loss[loss=0.1704, simple_loss=0.2694, pruned_loss=0.03567, over 7328.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2684, pruned_loss=0.0367, over 1406113.22 frames.], batch size: 22, lr: 3.73e-04
2022-04-29 17:16:21,954 INFO [train.py:763] (5/8) Epoch 20, batch 1000, loss[loss=0.2036, simple_loss=0.2982, pruned_loss=0.0545, over 7186.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2701, pruned_loss=0.0374, over 1405166.78 frames.], batch size: 23, lr: 3.73e-04
2022-04-29 17:17:26,879 INFO [train.py:763] (5/8) Epoch 20, batch 1050, loss[loss=0.1615, simple_loss=0.2737, pruned_loss=0.02469, over 7409.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2712, pruned_loss=0.03723, over 1406368.93 frames.], batch size: 21, lr: 3.73e-04
2022-04-29 17:18:32,323 INFO [train.py:763] (5/8) Epoch 20, batch 1100, loss[loss=0.1535, simple_loss=0.2397, pruned_loss=0.03362, over 6790.00 frames.], tot_loss[loss=0.1719, simple_loss=0.27, pruned_loss=0.03686, over 1407231.77 frames.], batch size: 15, lr: 3.73e-04
2022-04-29 17:19:37,617 INFO [train.py:763] (5/8) Epoch 20, batch 1150, loss[loss=0.1635, simple_loss=0.2619, pruned_loss=0.03257, over 7309.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2699, pruned_loss=0.03657, over 1412632.48 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:20:42,601 INFO [train.py:763] (5/8) Epoch 20, batch 1200, loss[loss=0.1467, simple_loss=0.2393, pruned_loss=0.02703, over 7286.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2708, pruned_loss=0.03705, over 1415329.93 frames.], batch size: 18, lr: 3.73e-04
2022-04-29 17:21:47,935 INFO [train.py:763] (5/8) Epoch 20, batch 1250, loss[loss=0.1839, simple_loss=0.2798, pruned_loss=0.04397, over 7304.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2697, pruned_loss=0.03672, over 1416937.92 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:22:53,228 INFO [train.py:763] (5/8) Epoch 20, batch 1300, loss[loss=0.1619, simple_loss=0.2583, pruned_loss=0.03273, over 7075.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2691, pruned_loss=0.03639, over 1416299.40 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:23:59,022 INFO [train.py:763] (5/8) Epoch 20, batch 1350, loss[loss=0.1806, simple_loss=0.2832, pruned_loss=0.03903, over 7331.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2687, pruned_loss=0.03639, over 1423397.28 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:25:04,576 INFO [train.py:763] (5/8) Epoch 20, batch 1400, loss[loss=0.1839, simple_loss=0.2839, pruned_loss=0.04193, over 7389.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2691, pruned_loss=0.03663, over 1425967.49 frames.], batch size: 23, lr: 3.72e-04
2022-04-29 17:26:11,079 INFO [train.py:763] (5/8) Epoch 20, batch 1450, loss[loss=0.2267, simple_loss=0.3138, pruned_loss=0.06985, over 4817.00 frames.], tot_loss[loss=0.171, simple_loss=0.2687, pruned_loss=0.03659, over 1419981.60 frames.], batch size: 52, lr: 3.72e-04
2022-04-29 17:27:17,686 INFO [train.py:763] (5/8) Epoch 20, batch 1500, loss[loss=0.1557, simple_loss=0.2524, pruned_loss=0.02952, over 7326.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03689, over 1418395.38 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:28:24,679 INFO [train.py:763] (5/8) Epoch 20, batch 1550, loss[loss=0.1882, simple_loss=0.2961, pruned_loss=0.04019, over 6743.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2704, pruned_loss=0.03714, over 1420576.25 frames.], batch size: 31, lr: 3.72e-04
2022-04-29 17:29:31,795 INFO [train.py:763] (5/8) Epoch 20, batch 1600, loss[loss=0.1778, simple_loss=0.2826, pruned_loss=0.03648, over 7331.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2707, pruned_loss=0.03694, over 1421729.69 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:30:38,865 INFO [train.py:763] (5/8) Epoch 20, batch 1650, loss[loss=0.1627, simple_loss=0.269, pruned_loss=0.02821, over 7337.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2708, pruned_loss=0.03676, over 1422566.33 frames.], batch size: 20, lr: 3.72e-04
2022-04-29 17:31:46,144 INFO [train.py:763] (5/8) Epoch 20, batch 1700, loss[loss=0.1787, simple_loss=0.2832, pruned_loss=0.03707, over 7329.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2703, pruned_loss=0.0367, over 1422417.93 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:32:52,772 INFO [train.py:763] (5/8) Epoch 20, batch 1750, loss[loss=0.1671, simple_loss=0.2491, pruned_loss=0.04256, over 7406.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2701, pruned_loss=0.03649, over 1423553.01 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:33:59,699 INFO [train.py:763] (5/8) Epoch 20, batch 1800, loss[loss=0.1768, simple_loss=0.2768, pruned_loss=0.03835, over 7176.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2696, pruned_loss=0.03647, over 1423906.36 frames.], batch size: 23, lr: 3.71e-04
2022-04-29 17:35:06,986 INFO [train.py:763] (5/8) Epoch 20, batch 1850, loss[loss=0.1545, simple_loss=0.2513, pruned_loss=0.02886, over 7414.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03672, over 1423143.60 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:36:12,562 INFO [train.py:763] (5/8) Epoch 20, batch 1900, loss[loss=0.1725, simple_loss=0.287, pruned_loss=0.029, over 7157.00 frames.], tot_loss[loss=0.172, simple_loss=0.27, pruned_loss=0.03697, over 1424631.43 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:37:18,021 INFO [train.py:763] (5/8) Epoch 20, batch 1950, loss[loss=0.1542, simple_loss=0.2487, pruned_loss=0.02985, over 7256.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2694, pruned_loss=0.03683, over 1428147.52 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:38:24,305 INFO [train.py:763] (5/8) Epoch 20, batch 2000, loss[loss=0.1686, simple_loss=0.2748, pruned_loss=0.03125, over 6842.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2681, pruned_loss=0.03615, over 1424849.57 frames.], batch size: 31, lr: 3.71e-04
2022-04-29 17:39:29,417 INFO [train.py:763] (5/8) Epoch 20, batch 2050, loss[loss=0.1859, simple_loss=0.2913, pruned_loss=0.04022, over 7225.00 frames.], tot_loss[loss=0.171, simple_loss=0.2685, pruned_loss=0.03675, over 1424623.64 frames.], batch size: 21, lr: 3.71e-04
2022-04-29 17:40:35,610 INFO [train.py:763] (5/8) Epoch 20, batch 2100, loss[loss=0.1715, simple_loss=0.269, pruned_loss=0.03696, over 7062.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2693, pruned_loss=0.03679, over 1423547.42 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:41:42,820 INFO [train.py:763] (5/8) Epoch 20, batch 2150, loss[loss=0.144, simple_loss=0.2343, pruned_loss=0.0268, over 7202.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2703, pruned_loss=0.03731, over 1422496.27 frames.], batch size: 16, lr: 3.71e-04
2022-04-29 17:42:48,996 INFO [train.py:763] (5/8) Epoch 20, batch 2200, loss[loss=0.1993, simple_loss=0.3146, pruned_loss=0.04194, over 7209.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2684, pruned_loss=0.0366, over 1423765.19 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:43:54,403 INFO [train.py:763] (5/8) Epoch 20, batch 2250, loss[loss=0.2022, simple_loss=0.296, pruned_loss=0.05421, over 7213.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2691, pruned_loss=0.03694, over 1424853.14 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:45:01,648 INFO [train.py:763] (5/8) Epoch 20, batch 2300, loss[loss=0.2037, simple_loss=0.2975, pruned_loss=0.0549, over 5206.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2687, pruned_loss=0.03687, over 1422025.38 frames.], batch size: 52, lr: 3.71e-04
2022-04-29 17:46:08,310 INFO [train.py:763] (5/8) Epoch 20, batch 2350, loss[loss=0.1984, simple_loss=0.2944, pruned_loss=0.05115, over 7269.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2705, pruned_loss=0.03744, over 1417106.26 frames.], batch size: 24, lr: 3.70e-04
2022-04-29 17:47:15,579 INFO [train.py:763] (5/8) Epoch 20, batch 2400, loss[loss=0.1892, simple_loss=0.2822, pruned_loss=0.04807, over 7199.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2698, pruned_loss=0.03706, over 1420539.57 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:48:22,383 INFO [train.py:763] (5/8) Epoch 20, batch 2450, loss[loss=0.1798, simple_loss=0.2697, pruned_loss=0.04496, over 7162.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2688, pruned_loss=0.03643, over 1421113.47 frames.], batch size: 19, lr: 3.70e-04
2022-04-29 17:49:29,427 INFO [train.py:763] (5/8) Epoch 20, batch 2500, loss[loss=0.1816, simple_loss=0.2863, pruned_loss=0.03839, over 7413.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2696, pruned_loss=0.03706, over 1422590.85 frames.], batch size: 21, lr: 3.70e-04
2022-04-29 17:50:36,103 INFO [train.py:763] (5/8) Epoch 20, batch 2550, loss[loss=0.1896, simple_loss=0.2841, pruned_loss=0.04758, over 5244.00 frames.], tot_loss[loss=0.1719, simple_loss=0.27, pruned_loss=0.03689, over 1421130.51 frames.], batch size: 52, lr: 3.70e-04
2022-04-29 17:51:41,447 INFO [train.py:763] (5/8) Epoch 20, batch 2600, loss[loss=0.1645, simple_loss=0.2515, pruned_loss=0.03875, over 7070.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03711, over 1422298.56 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:52:58,243 INFO [train.py:763] (5/8) Epoch 20, batch 2650, loss[loss=0.1495, simple_loss=0.2495, pruned_loss=0.02482, over 7330.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2706, pruned_loss=0.03751, over 1418349.82 frames.], batch size: 20, lr: 3.70e-04
2022-04-29 17:54:04,065 INFO [train.py:763] (5/8) Epoch 20, batch 2700, loss[loss=0.1491, simple_loss=0.2434, pruned_loss=0.0274, over 7410.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2705, pruned_loss=0.03738, over 1421163.54 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:55:10,586 INFO [train.py:763] (5/8) Epoch 20, batch 2750, loss[loss=0.1425, simple_loss=0.2445, pruned_loss=0.02025, over 7145.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03715, over 1422333.74 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:56:15,905 INFO [train.py:763] (5/8) Epoch 20, batch 2800, loss[loss=0.1925, simple_loss=0.2884, pruned_loss=0.0483, over 7373.00 frames.], tot_loss[loss=0.1719, simple_loss=0.27, pruned_loss=0.03692, over 1425736.44 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:57:21,240 INFO [train.py:763] (5/8) Epoch 20, batch 2850, loss[loss=0.2235, simple_loss=0.3289, pruned_loss=0.05906, over 7213.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2698, pruned_loss=0.03695, over 1421398.87 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 17:58:26,462 INFO [train.py:763] (5/8) Epoch 20, batch 2900, loss[loss=0.1945, simple_loss=0.2913, pruned_loss=0.04884, over 7130.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2697, pruned_loss=0.03671, over 1415873.35 frames.], batch size: 28, lr: 3.69e-04
2022-04-29 17:59:31,732 INFO [train.py:763] (5/8) Epoch 20, batch 2950, loss[loss=0.1496, simple_loss=0.251, pruned_loss=0.02407, over 7364.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2697, pruned_loss=0.03668, over 1414546.41 frames.], batch size: 19, lr: 3.69e-04
2022-04-29 18:01:03,488 INFO [train.py:763] (5/8) Epoch 20, batch 3000, loss[loss=0.1568, simple_loss=0.2638, pruned_loss=0.0249, over 6754.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2695, pruned_loss=0.03666, over 1413541.74 frames.], batch size: 31, lr: 3.69e-04
2022-04-29 18:01:03,489 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 18:01:18,757 INFO [train.py:792] (5/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
2022-04-29 18:02:33,648 INFO [train.py:763] (5/8) Epoch 20, batch 3050, loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03013, over 7291.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03675, over 1414696.82 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:03:49,738 INFO [train.py:763] (5/8) Epoch 20, batch 3100, loss[loss=0.2012, simple_loss=0.2973, pruned_loss=0.05259, over 7369.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2703, pruned_loss=0.03708, over 1413808.37 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 18:05:13,904 INFO [train.py:763] (5/8) Epoch 20, batch 3150, loss[loss=0.1789, simple_loss=0.2728, pruned_loss=0.0425, over 7308.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2702, pruned_loss=0.03733, over 1419036.17 frames.], batch size: 24, lr: 3.69e-04
2022-04-29 18:06:18,926 INFO [train.py:763] (5/8) Epoch 20, batch 3200, loss[loss=0.1646, simple_loss=0.2644, pruned_loss=0.03241, over 7319.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03768, over 1423297.06 frames.], batch size: 21, lr: 3.69e-04
2022-04-29 18:07:24,053 INFO [train.py:763] (5/8) Epoch 20, batch 3250, loss[loss=0.1495, simple_loss=0.2611, pruned_loss=0.01894, over 7061.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2711, pruned_loss=0.03755, over 1421765.77 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:08:29,715 INFO [train.py:763] (5/8) Epoch 20, batch 3300, loss[loss=0.1511, simple_loss=0.2356, pruned_loss=0.03328, over 7149.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2706, pruned_loss=0.03744, over 1422754.53 frames.], batch size: 17, lr: 3.69e-04
2022-04-29 18:09:36,015 INFO [train.py:763] (5/8) Epoch 20, batch 3350, loss[loss=0.1694, simple_loss=0.2716, pruned_loss=0.03358, over 7238.00 frames.], tot_loss[loss=0.172, simple_loss=0.2701, pruned_loss=0.03693, over 1418702.89 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:10:42,852 INFO [train.py:763] (5/8) Epoch 20, batch 3400, loss[loss=0.1905, simple_loss=0.2953, pruned_loss=0.04283, over 6437.00 frames.], tot_loss[loss=0.173, simple_loss=0.2711, pruned_loss=0.03751, over 1415876.82 frames.], batch size: 38, lr: 3.68e-04
2022-04-29 18:11:49,530 INFO [train.py:763] (5/8) Epoch 20, batch 3450, loss[loss=0.159, simple_loss=0.2516, pruned_loss=0.03322, over 7318.00 frames.], tot_loss[loss=0.173, simple_loss=0.271, pruned_loss=0.03751, over 1414417.13 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:12:54,745 INFO [train.py:763] (5/8) Epoch 20, batch 3500, loss[loss=0.1857, simple_loss=0.2871, pruned_loss=0.0422, over 7085.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2712, pruned_loss=0.03759, over 1409897.34 frames.], batch size: 28, lr: 3.68e-04
2022-04-29 18:14:00,246 INFO [train.py:763] (5/8) Epoch 20, batch 3550, loss[loss=0.1837, simple_loss=0.2703, pruned_loss=0.04853, over 7254.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2704, pruned_loss=0.03716, over 1414449.29 frames.], batch size: 17, lr: 3.68e-04
2022-04-29 18:15:05,504 INFO [train.py:763] (5/8) Epoch 20, batch 3600, loss[loss=0.1802, simple_loss=0.2771, pruned_loss=0.0416, over 7368.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2711, pruned_loss=0.03728, over 1411457.27 frames.], batch size: 23, lr: 3.68e-04
2022-04-29 18:16:10,763 INFO [train.py:763] (5/8) Epoch 20, batch 3650, loss[loss=0.1625, simple_loss=0.263, pruned_loss=0.03102, over 7178.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03711, over 1413375.90 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:17:15,971 INFO [train.py:763] (5/8) Epoch 20, batch 3700, loss[loss=0.1575, simple_loss=0.2649, pruned_loss=0.02506, over 7312.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2706, pruned_loss=0.03686, over 1414237.19 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:18:22,133 INFO [train.py:763] (5/8) Epoch 20, batch 3750, loss[loss=0.1693, simple_loss=0.2613, pruned_loss=0.03861, over 7294.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2695, pruned_loss=0.03682, over 1418397.83 frames.], batch size: 25, lr: 3.68e-04
2022-04-29 18:19:27,285 INFO [train.py:763] (5/8) Epoch 20, batch 3800, loss[loss=0.1761, simple_loss=0.274, pruned_loss=0.03908, over 7132.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2692, pruned_loss=0.03686, over 1418974.53 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:20:33,283 INFO [train.py:763] (5/8) Epoch 20, batch 3850, loss[loss=0.1709, simple_loss=0.2743, pruned_loss=0.03374, over 7328.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2703, pruned_loss=0.03733, over 1419247.52 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:21:38,670 INFO [train.py:763] (5/8) Epoch 20, batch 3900, loss[loss=0.163, simple_loss=0.2611, pruned_loss=0.03244, over 7258.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2702, pruned_loss=0.03702, over 1423209.97 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:22:44,453 INFO [train.py:763] (5/8) Epoch 20, batch 3950, loss[loss=0.1737, simple_loss=0.2554, pruned_loss=0.04604, over 7421.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2716, pruned_loss=0.03761, over 1418653.72 frames.], batch size: 18, lr: 3.67e-04
2022-04-29 18:23:51,319 INFO [train.py:763] (5/8) Epoch 20, batch 4000, loss[loss=0.1764, simple_loss=0.2677, pruned_loss=0.0426, over 7361.00 frames.], tot_loss[loss=0.173, simple_loss=0.2713, pruned_loss=0.0373, over 1422460.68 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:24:58,656 INFO [train.py:763] (5/8) Epoch 20, batch 4050, loss[loss=0.2146, simple_loss=0.3069, pruned_loss=0.06111, over 5199.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03725, over 1419529.57 frames.], batch size: 52, lr: 3.67e-04
2022-04-29 18:26:05,464 INFO [train.py:763] (5/8) Epoch 20, batch 4100, loss[loss=0.1519, simple_loss=0.252, pruned_loss=0.02591, over 7220.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2708, pruned_loss=0.03737, over 1411153.56 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:27:10,995 INFO [train.py:763] (5/8) Epoch 20, batch 4150, loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02974, over 7448.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2712, pruned_loss=0.03712, over 1413078.07 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:28:16,328 INFO [train.py:763] (5/8) Epoch 20, batch 4200, loss[loss=0.1907, simple_loss=0.2872, pruned_loss=0.04709, over 6795.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2718, pruned_loss=0.03717, over 1412800.05 frames.], batch size: 31, lr: 3.67e-04
2022-04-29 18:29:32,309 INFO [train.py:763] (5/8) Epoch 20, batch 4250, loss[loss=0.1651, simple_loss=0.2717, pruned_loss=0.02921, over 7212.00 frames.], tot_loss[loss=0.172, simple_loss=0.2706, pruned_loss=0.03672, over 1416909.94 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:30:38,992 INFO [train.py:763] (5/8) Epoch 20, batch 4300, loss[loss=0.2094, simple_loss=0.3036, pruned_loss=0.05766, over 7294.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2705, pruned_loss=0.0365, over 1418383.33 frames.], batch size: 24, lr: 3.67e-04
2022-04-29 18:31:45,011 INFO [train.py:763] (5/8) Epoch 20, batch 4350, loss[loss=0.199, simple_loss=0.3058, pruned_loss=0.0461, over 7203.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2698, pruned_loss=0.03623, over 1417741.02 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:32:52,217 INFO [train.py:763] (5/8) Epoch 20, batch 4400, loss[loss=0.1589, simple_loss=0.246, pruned_loss=0.03587, over 7174.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2694, pruned_loss=0.03592, over 1416646.29 frames.], batch size: 18, lr: 3.66e-04
2022-04-29 18:33:58,457 INFO [train.py:763] (5/8) Epoch 20, batch 4450, loss[loss=0.1436, simple_loss=0.2426, pruned_loss=0.02229, over 7003.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03598, over 1409212.89 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:35:05,726 INFO [train.py:763] (5/8) Epoch 20, batch 4500, loss[loss=0.1519, simple_loss=0.2317, pruned_loss=0.03606, over 7013.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2694, pruned_loss=0.03621, over 1411142.16 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:36:13,273 INFO [train.py:763] (5/8) Epoch 20, batch 4550, loss[loss=0.1889, simple_loss=0.2837, pruned_loss=0.04706, over 4926.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2686, pruned_loss=0.03639, over 1395056.89 frames.], batch size: 52, lr: 3.66e-04
2022-04-29 18:37:42,391 INFO [train.py:763] (5/8) Epoch 21, batch 0, loss[loss=0.1884, simple_loss=0.2899, pruned_loss=0.04338, over 7272.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2899, pruned_loss=0.04338, over 7272.00 frames.], batch size: 25, lr: 3.58e-04
2022-04-29 18:38:48,210 INFO [train.py:763] (5/8) Epoch 21, batch 50, loss[loss=0.1627, simple_loss=0.2539, pruned_loss=0.03573, over 7174.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2721, pruned_loss=0.03949, over 318286.49 frames.], batch size: 18, lr: 3.58e-04
2022-04-29 18:39:53,575 INFO [train.py:763] (5/8) Epoch 21, batch 100, loss[loss=0.1606, simple_loss=0.262, pruned_loss=0.02955, over 7117.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2689, pruned_loss=0.03708, over 565112.02 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:41:00,345 INFO [train.py:763] (5/8) Epoch 21, batch 150, loss[loss=0.1698, simple_loss=0.2793, pruned_loss=0.03017, over 7325.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03555, over 755160.37 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:42:07,760 INFO [train.py:763] (5/8) Epoch 21, batch 200, loss[loss=0.1765, simple_loss=0.2896, pruned_loss=0.03172, over 7338.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2681, pruned_loss=0.03546, over 902788.53 frames.], batch size: 22, lr: 3.58e-04
2022-04-29 18:43:14,301 INFO [train.py:763] (5/8) Epoch 21, batch 250, loss[loss=0.1543, simple_loss=0.2554, pruned_loss=0.02663, over 7238.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03562, over 1016676.46 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:44:19,575 INFO [train.py:763] (5/8) Epoch 21, batch 300, loss[loss=0.173, simple_loss=0.2754, pruned_loss=0.03524, over 7241.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03589, over 1109172.37 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:45:25,085 INFO [train.py:763] (5/8) Epoch 21, batch 350, loss[loss=0.1415, simple_loss=0.2354, pruned_loss=0.02381, over 7171.00 frames.], tot_loss[loss=0.1686, simple_loss=0.267, pruned_loss=0.03511, over 1179787.76 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:46:30,622 INFO [train.py:763] (5/8) Epoch 21, batch 400, loss[loss=0.1819, simple_loss=0.2928, pruned_loss=0.03554, over 7223.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.0351, over 1232297.92 frames.], batch size: 21, lr: 3.57e-04
2022-04-29 18:47:36,050 INFO [train.py:763] (5/8) Epoch 21, batch 450, loss[loss=0.2101, simple_loss=0.2918, pruned_loss=0.06419, over 5198.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.03517, over 1274915.69 frames.], batch size: 52, lr: 3.57e-04
2022-04-29 18:48:41,852 INFO [train.py:763] (5/8) Epoch 21, batch 500, loss[loss=0.182, simple_loss=0.2673, pruned_loss=0.0484, over 7262.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03515, over 1309899.38 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:49:47,439 INFO [train.py:763] (5/8) Epoch 21, batch 550, loss[loss=0.1699, simple_loss=0.2705, pruned_loss=0.0346, over 7434.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2684, pruned_loss=0.0355, over 1333462.83 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:50:53,644 INFO [train.py:763] (5/8) Epoch 21, batch 600, loss[loss=0.1603, simple_loss=0.2618, pruned_loss=0.02937, over 7357.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2674, pruned_loss=0.03558, over 1355118.95 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:51:58,881 INFO [train.py:763] (5/8) Epoch 21, batch 650, loss[loss=0.156, simple_loss=0.2592, pruned_loss=0.02637, over 7331.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 1370089.93 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:53:04,515 INFO [train.py:763] (5/8) Epoch 21, batch 700, loss[loss=0.1928, simple_loss=0.2995, pruned_loss=0.04304, over 7320.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2687, pruned_loss=0.03584, over 1377909.11 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:54:10,411 INFO [train.py:763] (5/8) Epoch 21, batch 750, loss[loss=0.1679, simple_loss=0.2593, pruned_loss=0.0382, over 7154.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03568, over 1386862.56 frames.], batch size: 18, lr: 3.57e-04
2022-04-29 18:55:16,600 INFO [train.py:763] (5/8) Epoch 21, batch 800, loss[loss=0.1702, simple_loss=0.2745, pruned_loss=0.03298, over 7275.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2689, pruned_loss=0.03607, over 1399547.40 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 18:56:22,307 INFO [train.py:763] (5/8) Epoch 21, batch 850, loss[loss=0.1442, simple_loss=0.2402, pruned_loss=0.02411, over 7400.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03585, over 1405507.05 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:57:27,454 INFO [train.py:763] (5/8) Epoch 21, batch 900, loss[loss=0.1588, simple_loss=0.264, pruned_loss=0.0268, over 6509.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2678, pruned_loss=0.03559, over 1409526.33 frames.], batch size: 38, lr: 3.56e-04
2022-04-29 18:58:32,839 INFO [train.py:763] (5/8) Epoch 21, batch 950, loss[loss=0.1378, simple_loss=0.237, pruned_loss=0.01935, over 7299.00 frames.], tot_loss[loss=0.169, simple_loss=0.2672, pruned_loss=0.03536, over 1411503.21 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:59:38,152 INFO [train.py:763] (5/8) Epoch 21, batch 1000, loss[loss=0.1661, simple_loss=0.2632, pruned_loss=0.03452, over 7160.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03555, over 1412002.68 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:00:44,775 INFO [train.py:763] (5/8) Epoch 21, batch 1050, loss[loss=0.1614, simple_loss=0.2661, pruned_loss=0.02831, over 7340.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2673, pruned_loss=0.03553, over 1415788.99 frames.], batch size: 22, lr: 3.56e-04
2022-04-29 19:01:50,757 INFO [train.py:763] (5/8) Epoch 21, batch 1100, loss[loss=0.1658, simple_loss=0.2606, pruned_loss=0.03551, over 6566.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03536, over 1419322.53 frames.], batch size: 37, lr: 3.56e-04
2022-04-29 19:02:56,404 INFO [train.py:763] (5/8) Epoch 21, batch 1150, loss[loss=0.1616, simple_loss=0.259, pruned_loss=0.03212, over 7252.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03552, over 1420428.81 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:04:02,101 INFO [train.py:763] (5/8) Epoch 21, batch 1200, loss[loss=0.1906, simple_loss=0.279, pruned_loss=0.05107, over 7304.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2673, pruned_loss=0.03585, over 1421254.38 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 19:05:07,723 INFO [train.py:763] (5/8) Epoch 21, batch 1250, loss[loss=0.1441, simple_loss=0.2312, pruned_loss=0.02847, over 6989.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2675, pruned_loss=0.03602, over 1420223.52 frames.], batch size: 16, lr: 3.56e-04
2022-04-29 19:06:13,274 INFO [train.py:763] (5/8) Epoch 21, batch 1300, loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03771, over 7154.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2675, pruned_loss=0.03611, over 1419430.77 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:07:19,452 INFO [train.py:763] (5/8) Epoch 21, batch 1350, loss[loss=0.1885, simple_loss=0.2897, pruned_loss=0.04365, over 7409.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2671, pruned_loss=0.03577, over 1423721.90 frames.], batch size: 21, lr: 3.55e-04
2022-04-29 19:08:24,897 INFO [train.py:763] (5/8) Epoch 21, batch 1400, loss[loss=0.2164, simple_loss=0.3138, pruned_loss=0.05946, over 7202.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2665, pruned_loss=0.03588, over 1420116.34 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:09:30,411 INFO [train.py:763] (5/8) Epoch 21, batch 1450, loss[loss=0.1695, simple_loss=0.2775, pruned_loss=0.03071, over 7410.00 frames.], tot_loss[loss=0.17, simple_loss=0.268, pruned_loss=0.03594, over 1424311.30 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:10:36,222 INFO [train.py:763] (5/8) Epoch 21, batch 1500, loss[loss=0.1752, simple_loss=0.2768, pruned_loss=0.03682, over 7237.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2678, pruned_loss=0.03565, over 1425879.23 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:11:42,025 INFO [train.py:763] (5/8) Epoch 21, batch 1550, loss[loss=0.2039, simple_loss=0.3066, pruned_loss=0.05059, over 7237.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2679, pruned_loss=0.03595, over 1428412.22 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:12:47,951 INFO [train.py:763] (5/8) Epoch 21, batch 1600, loss[loss=0.1447, simple_loss=0.2381, pruned_loss=0.02569, over 6824.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2678, pruned_loss=0.03556, over 1428834.06 frames.], batch size: 15, lr: 3.55e-04
2022-04-29 19:13:54,886 INFO [train.py:763] (5/8) Epoch 21, batch 1650, loss[loss=0.1794, simple_loss=0.2791, pruned_loss=0.0398, over 6771.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03561, over 1430802.76 frames.], batch size: 31, lr: 3.55e-04
2022-04-29 19:15:01,801 INFO [train.py:763] (5/8) Epoch 21, batch 1700, loss[loss=0.1778, simple_loss=0.2843, pruned_loss=0.03565, over 7325.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03501, over 1432703.08 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:16:08,180 INFO [train.py:763] (5/8) Epoch 21, batch 1750, loss[loss=0.1686, simple_loss=0.2711, pruned_loss=0.03299, over 7240.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2689, pruned_loss=0.03571, over 1431679.32 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:17:14,200 INFO [train.py:763] (5/8) Epoch 21, batch 1800, loss[loss=0.1443, simple_loss=0.2349, pruned_loss=0.02683, over 7318.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03538, over 1430155.05 frames.], batch size: 17, lr: 3.55e-04
2022-04-29 19:18:19,481 INFO [train.py:763] (5/8) Epoch 21, batch 1850, loss[loss=0.1686, simple_loss=0.2739, pruned_loss=0.03165, over 6487.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03518, over 1426609.07 frames.], batch size: 38, lr: 3.55e-04
2022-04-29 19:19:25,207 INFO [train.py:763] (5/8) Epoch 21, batch 1900, loss[loss=0.1895, simple_loss=0.2863, pruned_loss=0.04637, over 5137.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03549, over 1424521.26 frames.], batch size: 52, lr: 3.54e-04
2022-04-29 19:20:31,909 INFO [train.py:763] (5/8) Epoch 21, batch 1950, loss[loss=0.1643, simple_loss=0.2497, pruned_loss=0.03949, over 7281.00 frames.], tot_loss[loss=0.17, simple_loss=0.2684, pruned_loss=0.03576, over 1425989.50 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:21:37,663 INFO [train.py:763] (5/8) Epoch 21, batch 2000, loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02868, over 7321.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2678, pruned_loss=0.03537, over 1427978.58 frames.], batch size: 20, lr: 3.54e-04
2022-04-29 19:22:44,045 INFO [train.py:763] (5/8) Epoch 21, batch 2050, loss[loss=0.1572, simple_loss=0.2438, pruned_loss=0.03531, over 7271.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03565, over 1428576.52 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:23:50,506 INFO [train.py:763] (5/8) Epoch 21, batch 2100, loss[loss=0.1599, simple_loss=0.2485, pruned_loss=0.03566, over 7428.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03563, over 1427639.67 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:24:56,275 INFO [train.py:763] (5/8) Epoch 21, batch 2150, loss[loss=0.1556, simple_loss=0.246, pruned_loss=0.03265, over 7156.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03523, over 1423115.89 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:26:02,252 INFO [train.py:763] (5/8) Epoch 21, batch 2200, loss[loss=0.1738, simple_loss=0.2776, pruned_loss=0.03505, over 7121.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2681, pruned_loss=0.03527, over 1425866.36 frames.], batch size: 21, lr: 3.54e-04
2022-04-29 19:27:08,594 INFO [train.py:763] (5/8) Epoch 21, batch 2250, loss[loss=0.1425, simple_loss=0.2381, pruned_loss=0.02349, over 7206.00 frames.], tot_loss[loss=0.17, simple_loss=0.2688, pruned_loss=0.03563, over 1424000.24 frames.], batch size: 16, lr: 3.54e-04
2022-04-29 19:28:14,985 INFO [train.py:763] (5/8) Epoch 21, batch 2300, loss[loss=0.245, simple_loss=0.3275, pruned_loss=0.08121, over 5229.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2692, pruned_loss=0.03587, over 1425642.64 frames.], batch size: 53, lr: 3.54e-04
2022-04-29 19:29:21,495 INFO [train.py:763] (5/8) Epoch 21, batch 2350, loss[loss=0.1809, simple_loss=0.2911, pruned_loss=0.03532, over 6345.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03554, over 1427369.81 frames.], batch size: 38, lr: 3.54e-04
2022-04-29 19:30:28,303 INFO [train.py:763] (5/8) Epoch 21, batch 2400, loss[loss=0.1493, simple_loss=0.2422, pruned_loss=0.0282, over 7144.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2675, pruned_loss=0.03539, over 1426147.83 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:31:33,885 INFO [train.py:763] (5/8) Epoch 21, batch 2450, loss[loss=0.1514, simple_loss=0.2385, pruned_loss=0.03219, over 7268.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2674, pruned_loss=0.03534, over 1424886.04 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:32:39,560 INFO [train.py:763] (5/8) Epoch 21, batch 2500, loss[loss=0.1711, simple_loss=0.2785, pruned_loss=0.03187, over 7410.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2674, pruned_loss=0.03569, over 1422885.63 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:33:46,129 INFO [train.py:763] (5/8) Epoch 21, batch 2550, loss[loss=0.1776, simple_loss=0.2738, pruned_loss=0.04067, over 7065.00 frames.], tot_loss[loss=0.17, simple_loss=0.2682, pruned_loss=0.03594, over 1422587.53 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:34:52,134 INFO [train.py:763] (5/8) Epoch 21, batch 2600, loss[loss=0.1626, simple_loss=0.2564, pruned_loss=0.03435, over 7155.00 frames.], tot_loss[loss=0.171, simple_loss=0.2693, pruned_loss=0.03637, over 1418204.70 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:35:58,119 INFO [train.py:763] (5/8) Epoch 21, batch 2650, loss[loss=0.1582, simple_loss=0.2543, pruned_loss=0.03108, over 7257.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2685, pruned_loss=0.03614, over 1421726.76 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:37:03,420 INFO [train.py:763] (5/8) Epoch 21, batch 2700, loss[loss=0.1674, simple_loss=0.2621, pruned_loss=0.03634, over 7165.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2673, pruned_loss=0.03602, over 1419582.88 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:38:08,441 INFO [train.py:763] (5/8) Epoch 21, batch 2750, loss[loss=0.1873, simple_loss=0.2792, pruned_loss=0.04769, over 7065.00 frames.], tot_loss[loss=0.17, simple_loss=0.2679, pruned_loss=0.036, over 1419576.98 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:39:13,888 INFO [train.py:763] (5/8) Epoch 21, batch 2800, loss[loss=0.1463, simple_loss=0.2431, pruned_loss=0.02477, over 7273.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2677, pruned_loss=0.03554, over 1420293.23 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:40:19,370 INFO [train.py:763] (5/8) Epoch 21, batch 2850, loss[loss=0.1588, simple_loss=0.2523, pruned_loss=0.03262, over 7157.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2676, pruned_loss=0.03554, over 1418857.96 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:41:24,557 INFO [train.py:763] (5/8) Epoch 21, batch 2900, loss[loss=0.1573, simple_loss=0.2566, pruned_loss=0.02906, over 7158.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2677, pruned_loss=0.03537, over 1420750.92 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:42:30,258 INFO [train.py:763] (5/8) Epoch 21, batch 2950, loss[loss=0.1888, simple_loss=0.288, pruned_loss=0.04473, over 7413.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2675, pruned_loss=0.03565, over 1421543.91 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:43:36,687 INFO [train.py:763] (5/8) Epoch 21, batch 3000, loss[loss=0.1613, simple_loss=0.253, pruned_loss=0.03483, over 7171.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2667, pruned_loss=0.03504, over 1426041.07 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:43:36,688 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 19:43:52,055 INFO [train.py:792] (5/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
2022-04-29 19:44:57,941 INFO [train.py:763] (5/8) Epoch 21, batch 3050, loss[loss=0.1832, simple_loss=0.2811, pruned_loss=0.04267, over 7081.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.03552, over 1427568.93 frames.], batch size: 28, lr: 3.52e-04
2022-04-29 19:46:03,957 INFO [train.py:763] (5/8) Epoch 21, batch 3100, loss[loss=0.1975, simple_loss=0.2852, pruned_loss=0.05489, over 4970.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03558, over 1428033.25 frames.], batch size: 52, lr: 3.52e-04
2022-04-29 19:47:10,170 INFO [train.py:763] (5/8) Epoch 21, batch 3150, loss[loss=0.1702, simple_loss=0.2801, pruned_loss=0.03015, over 7417.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2672, pruned_loss=0.03579, over 1425464.15 frames.], batch size: 21, lr: 3.52e-04
2022-04-29 19:48:15,888 INFO [train.py:763] (5/8) Epoch 21, batch 3200, loss[loss=0.1644, simple_loss=0.2626, pruned_loss=0.03316, over 7053.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.03501, over 1426699.12 frames.], batch size: 18, lr: 3.52e-04
2022-04-29 19:49:21,830 INFO [train.py:763] (5/8) Epoch 21, batch 3250, loss[loss=0.1562, simple_loss=0.2406, pruned_loss=0.03589, over 6988.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2682, pruned_loss=0.036, over 1428181.77 frames.], batch size: 16, lr: 3.52e-04
2022-04-29 19:50:27,766 INFO [train.py:763] (5/8) Epoch 21, batch 3300, loss[loss=0.1451, simple_loss=0.2461, pruned_loss=0.02206, over 7447.00 frames.], tot_loss[loss=0.1706, simple_loss=0.269, pruned_loss=0.03608, over 1430559.86 frames.], batch size: 20, lr: 3.52e-04
2022-04-29 19:51:34,065 INFO [train.py:763] (5/8) Epoch 21, batch 3350, loss[loss=0.1575, simple_loss=0.2602, pruned_loss=0.02739, over 7351.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2694, pruned_loss=0.03612, over 1429494.79 frames.], batch size: 19, lr: 3.52e-04
2022-04-29 19:52:40,203 INFO [train.py:763] (5/8) Epoch 21, batch 3400, loss[loss=0.1525, simple_loss=0.2484, pruned_loss=0.02826, over 7137.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2694, pruned_loss=0.03609, over 1425265.76 frames.], batch size: 17, lr: 3.52e-04
2022-04-29 19:53:45,695 INFO [train.py:763] (5/8) Epoch 21, batch 3450, loss[loss=0.2066, simple_loss=0.2996, pruned_loss=0.05681, over 7337.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2703, pruned_loss=0.03643, over 1426633.14 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:54:51,963 INFO [train.py:763] (5/8) Epoch 21, batch 3500, loss[loss=0.1633, simple_loss=0.2693, pruned_loss=0.02863, over 7327.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2696, pruned_loss=0.03611, over 1429076.66 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:55:58,080 INFO [train.py:763] (5/8) Epoch 21, batch 3550, loss[loss=0.1681, simple_loss=0.2702, pruned_loss=0.033, over 6655.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2704, pruned_loss=0.03623, over 1427530.97 frames.], batch size: 31, lr: 3.52e-04
2022-04-29 19:57:04,817 INFO [train.py:763] (5/8) Epoch 21, batch 3600, loss[loss=0.1418, simple_loss=0.2375, pruned_loss=0.02305, over 7253.00 frames.], tot_loss[loss=0.1714, simple_loss=0.27, pruned_loss=0.03637, over 1422569.64 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 19:58:10,365 INFO [train.py:763] (5/8) Epoch 21, batch 3650, loss[loss=0.1871, simple_loss=0.2784, pruned_loss=0.04786, over 7378.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2703, pruned_loss=0.03628, over 1424143.41 frames.], batch size: 23, lr: 3.51e-04
2022-04-29 19:59:15,686 INFO [train.py:763] (5/8) Epoch 21, batch 3700, loss[loss=0.1678, simple_loss=0.2726, pruned_loss=0.03149, over 7218.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2688, pruned_loss=0.03601, over 1426412.78 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:00:21,234 INFO [train.py:763] (5/8) Epoch 21, batch 3750, loss[loss=0.1638, simple_loss=0.2435, pruned_loss=0.04205, over 6984.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2687, pruned_loss=0.03633, over 1430861.32 frames.], batch size: 16, lr: 3.51e-04
2022-04-29 20:01:26,924 INFO [train.py:763] (5/8) Epoch 21, batch 3800, loss[loss=0.1603, simple_loss=0.2556, pruned_loss=0.03251, over 4836.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2675, pruned_loss=0.0359, over 1424823.92 frames.], batch size: 52, lr: 3.51e-04
2022-04-29 20:02:32,214 INFO [train.py:763] (5/8) Epoch 21, batch 3850, loss[loss=0.2207, simple_loss=0.3154, pruned_loss=0.06305, over 7237.00 frames.], tot_loss[loss=0.17, simple_loss=0.2681, pruned_loss=0.03597, over 1427112.27 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:03:37,827 INFO [train.py:763] (5/8) Epoch 21, batch 3900, loss[loss=0.1686, simple_loss=0.2789, pruned_loss=0.02915, over 6523.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03591, over 1427466.26 frames.], batch size: 38, lr: 3.51e-04
2022-04-29 20:04:43,334 INFO [train.py:763] (5/8) Epoch 21, batch 3950, loss[loss=0.1447, simple_loss=0.2311, pruned_loss=0.02917, over 7294.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2677, pruned_loss=0.03565, over 1425818.85 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 20:05:50,736 INFO [train.py:763] (5/8) Epoch 21, batch 4000, loss[loss=0.1595, simple_loss=0.2718, pruned_loss=0.02353, over 7318.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03582, over 1425492.49 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:06:57,089 INFO [train.py:763] (5/8) Epoch 21, batch 4050, loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03837, over 7375.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03561, over 1423693.90 frames.], batch size: 19, lr: 3.51e-04
2022-04-29 20:08:02,550 INFO [train.py:763] (5/8) Epoch 21, batch 4100, loss[loss=0.1789, simple_loss=0.2877, pruned_loss=0.03507, over 7327.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2682, pruned_loss=0.03561, over 1424278.81 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:09:08,417 INFO [train.py:763] (5/8) Epoch 21, batch 4150, loss[loss=0.1873, simple_loss=0.272, pruned_loss=0.05131, over 7068.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03552, over 1420072.38 frames.], batch size: 18, lr: 3.51e-04
2022-04-29 20:10:23,433 INFO [train.py:763] (5/8) Epoch 21, batch 4200, loss[loss=0.1852, simple_loss=0.2851, pruned_loss=0.04266, over 7136.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03573, over 1415432.29 frames.], batch size: 20, lr: 3.50e-04
2022-04-29 20:11:28,559 INFO [train.py:763] (5/8) Epoch 21, batch 4250, loss[loss=0.1621, simple_loss=0.2538, pruned_loss=0.03522, over 6747.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2679, pruned_loss=0.03565, over 1409384.01 frames.], batch size: 31, lr: 3.50e-04
2022-04-29 20:12:34,521 INFO [train.py:763] (5/8) Epoch 21, batch 4300, loss[loss=0.1759, simple_loss=0.28, pruned_loss=0.03592, over 7303.00 frames.], tot_loss[loss=0.169, simple_loss=0.2674, pruned_loss=0.03529, over 1411729.71 frames.], batch size: 24, lr: 3.50e-04
2022-04-29 20:13:40,102 INFO [train.py:763] (5/8) Epoch 21, batch 4350, loss[loss=0.157, simple_loss=0.2683, pruned_loss=0.02283, over 7349.00 frames.], tot_loss[loss=0.17, simple_loss=0.2689, pruned_loss=0.03556, over 1408261.90 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:14:45,320 INFO [train.py:763] (5/8) Epoch 21, batch 4400, loss[loss=0.1627, simple_loss=0.266, pruned_loss=0.02974, over 7110.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2702, pruned_loss=0.03637, over 1403319.24 frames.], batch size: 21, lr: 3.50e-04
2022-04-29 20:15:50,791 INFO [train.py:763] (5/8) Epoch 21, batch 4450, loss[loss=0.1776, simple_loss=0.2762, pruned_loss=0.03948, over 7343.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2715, pruned_loss=0.03691, over 1399812.24 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:17:22,900 INFO [train.py:763] (5/8) Epoch 21, batch 4500, loss[loss=0.2037, simple_loss=0.2972, pruned_loss=0.05512, over 7042.00 frames.], tot_loss[loss=0.1741, simple_loss=0.273, pruned_loss=0.03764, over 1388274.84 frames.], batch size: 28, lr: 3.50e-04
2022-04-29 20:18:27,316 INFO [train.py:763] (5/8) Epoch 21, batch 4550, loss[loss=0.2156, simple_loss=0.3021, pruned_loss=0.06456, over 4988.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2751, pruned_loss=0.03911, over 1347375.77 frames.], batch size: 53, lr: 3.50e-04
2022-04-29 20:20:15,481 INFO [train.py:763] (5/8) Epoch 22, batch 0, loss[loss=0.1596, simple_loss=0.251, pruned_loss=0.03406, over 6815.00 frames.], tot_loss[loss=0.1596, simple_loss=0.251, pruned_loss=0.03406, over 6815.00 frames.], batch size: 15, lr: 3.42e-04
2022-04-29 20:21:30,528 INFO [train.py:763] (5/8) Epoch 22, batch 50, loss[loss=0.1562, simple_loss=0.2668, pruned_loss=0.02277, over 7162.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2666, pruned_loss=0.03593, over 319926.30 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:22:35,953 INFO [train.py:763] (5/8) Epoch 22, batch 100, loss[loss=0.1328, simple_loss=0.2353, pruned_loss=0.01518, over 7284.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03537, over 566744.76 frames.], batch size: 18, lr: 3.42e-04
2022-04-29 20:23:41,424 INFO [train.py:763] (5/8) Epoch 22, batch 150, loss[loss=0.1719, simple_loss=0.2845, pruned_loss=0.02962, over 7308.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2693, pruned_loss=0.03555, over 754100.89 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:24:46,889 INFO [train.py:763] (5/8) Epoch 22, batch 200, loss[loss=0.1664, simple_loss=0.2718, pruned_loss=0.03044, over 6483.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2679, pruned_loss=0.03477, over 902033.55 frames.], batch size: 38, lr: 3.42e-04
2022-04-29 20:25:52,445 INFO [train.py:763] (5/8) Epoch 22, batch 250, loss[loss=0.1826, simple_loss=0.2795, pruned_loss=0.04281, over 7190.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2687, pruned_loss=0.03494, over 1017321.36 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:26:58,036 INFO [train.py:763] (5/8) Epoch 22, batch 300, loss[loss=0.1728, simple_loss=0.271, pruned_loss=0.03733, over 7159.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2687, pruned_loss=0.03523, over 1103363.16 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:28:05,356 INFO [train.py:763] (5/8) Epoch 22, batch 350, loss[loss=0.1614, simple_loss=0.267, pruned_loss=0.02789, over 7326.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2678, pruned_loss=0.03501, over 1177181.41 frames.], batch size: 22, lr: 3.42e-04
2022-04-29 20:29:12,808 INFO [train.py:763] (5/8) Epoch 22, batch 400, loss[loss=0.1858, simple_loss=0.2985, pruned_loss=0.03662, over 7182.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03533, over 1229799.38 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:30:18,166 INFO [train.py:763] (5/8) Epoch 22, batch 450, loss[loss=0.1815, simple_loss=0.2903, pruned_loss=0.03629, over 7292.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2687, pruned_loss=0.03587, over 1271364.89 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:31:24,306 INFO [train.py:763] (5/8) Epoch 22, batch 500, loss[loss=0.1489, simple_loss=0.2369, pruned_loss=0.03048, over 6776.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2693, pruned_loss=0.03573, over 1305959.78 frames.], batch size: 15, lr: 3.41e-04
2022-04-29 20:32:31,788 INFO [train.py:763] (5/8) Epoch 22, batch 550, loss[loss=0.1634, simple_loss=0.2719, pruned_loss=0.0274, over 7303.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2694, pruned_loss=0.03599, over 1335637.11 frames.], batch size: 24, lr: 3.41e-04
2022-04-29 20:33:39,042 INFO [train.py:763] (5/8) Epoch 22, batch 600, loss[loss=0.1718, simple_loss=0.2814, pruned_loss=0.03112, over 7118.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2697, pruned_loss=0.03591, over 1357883.09 frames.], batch size: 21, lr: 3.41e-04
2022-04-29 20:34:44,746 INFO [train.py:763] (5/8) Epoch 22, batch 650, loss[loss=0.165, simple_loss=0.2686, pruned_loss=0.03065, over 6711.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2696, pruned_loss=0.03567, over 1373076.66 frames.], batch size: 31, lr: 3.41e-04
2022-04-29 20:35:51,891 INFO [train.py:763] (5/8) Epoch 22, batch 700, loss[loss=0.2095, simple_loss=0.3006, pruned_loss=0.05922, over 4801.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2693, pruned_loss=0.03562, over 1379460.99 frames.], batch size: 52, lr: 3.41e-04
2022-04-29 20:36:59,164 INFO [train.py:763] (5/8) Epoch 22, batch 750, loss[loss=0.2022, simple_loss=0.304, pruned_loss=0.05019, over 7192.00 frames.], tot_loss[loss=0.171, simple_loss=0.2702, pruned_loss=0.03592, over 1391310.47 frames.], batch size: 23, lr: 3.41e-04
2022-04-29 20:38:05,936 INFO [train.py:763] (5/8) Epoch 22, batch 800, loss[loss=0.149, simple_loss=0.2452, pruned_loss=0.0264, over 7361.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2696, pruned_loss=0.03575, over 1396139.26 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:39:11,699 INFO [train.py:763] (5/8) Epoch 22, batch 850, loss[loss=0.1494, simple_loss=0.243, pruned_loss=0.02794, over 7423.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2683, pruned_loss=0.03535, over 1404384.57 frames.], batch size: 20, lr: 3.41e-04
2022-04-29 20:40:16,912 INFO [train.py:763] (5/8) Epoch 22, batch 900, loss[loss=0.1549, simple_loss=0.2483, pruned_loss=0.03072, over 7153.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2686, pruned_loss=0.03575, over 1408589.46 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:41:22,124 INFO [train.py:763] (5/8) Epoch 22, batch 950, loss[loss=0.1886, simple_loss=0.2936, pruned_loss=0.04181, over 7055.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2686, pruned_loss=0.0355, over 1410716.42 frames.], batch size: 28, lr: 3.41e-04
2022-04-29 20:42:27,348 INFO [train.py:763] (5/8) Epoch 22, batch 1000, loss[loss=0.2039, simple_loss=0.2892, pruned_loss=0.05923, over 7356.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2687, pruned_loss=0.03554, over 1417854.55 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:43:32,808 INFO [train.py:763] (5/8) Epoch 22, batch 1050, loss[loss=0.1825, simple_loss=0.273, pruned_loss=0.046, over 5081.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2684, pruned_loss=0.03545, over 1418515.93 frames.], batch size: 52, lr: 3.41e-04
2022-04-29 20:44:37,791 INFO [train.py:763] (5/8) Epoch 22, batch 1100, loss[loss=0.143, simple_loss=0.2316, pruned_loss=0.02718, over 7279.00 frames.], tot_loss[loss=0.1699, simple_loss=0.269, pruned_loss=0.03542, over 1418407.64 frames.], batch size: 17, lr: 3.40e-04
2022-04-29 20:45:43,161 INFO [train.py:763] (5/8) Epoch 22, batch 1150, loss[loss=0.1342, simple_loss=0.2399, pruned_loss=0.01428, over 7423.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2692, pruned_loss=0.03537, over 1421901.81 frames.], batch size: 20, lr: 3.40e-04
2022-04-29 20:46:49,152 INFO [train.py:763] (5/8) Epoch 22, batch 1200, loss[loss=0.161, simple_loss=0.2533, pruned_loss=0.03438, over 7271.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2682, pruned_loss=0.03507, over 1420537.13 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:47:55,638 INFO [train.py:763] (5/8) Epoch 22, batch 1250, loss[loss=0.1517, simple_loss=0.2409, pruned_loss=0.03125, over 6781.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03457, over 1423863.23 frames.], batch size: 15, lr: 3.40e-04
2022-04-29 20:49:00,852 INFO [train.py:763] (5/8) Epoch 22, batch 1300, loss[loss=0.1784, simple_loss=0.2844, pruned_loss=0.03616, over 7216.00 frames.], tot_loss[loss=0.1692, simple_loss=0.268, pruned_loss=0.03522, over 1426469.60 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:50:07,456 INFO [train.py:763] (5/8) Epoch 22, batch 1350, loss[loss=0.1474, simple_loss=0.2375, pruned_loss=0.02869, over 7279.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03523, over 1427794.30 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:51:13,808 INFO [train.py:763] (5/8) Epoch 22, batch 1400, loss[loss=0.1531, simple_loss=0.262, pruned_loss=0.02211, over 7450.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2673, pruned_loss=0.03497, over 1427678.21 frames.], batch size: 22, lr: 3.40e-04
2022-04-29 20:52:19,588 INFO [train.py:763] (5/8) Epoch 22, batch 1450, loss[loss=0.1594, simple_loss=0.2547, pruned_loss=0.03204, over 7419.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03508, over 1421964.87 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:53:25,454 INFO [train.py:763] (5/8) Epoch 22, batch 1500, loss[loss=0.1674, simple_loss=0.2699, pruned_loss=0.03242, over 7007.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2653, pruned_loss=0.03466, over 1423049.98 frames.], batch size: 28, lr: 3.40e-04
2022-04-29 20:54:31,382 INFO [train.py:763] (5/8) Epoch 22, batch 1550, loss[loss=0.1449, simple_loss=0.2438, pruned_loss=0.02299, over 7351.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2657, pruned_loss=0.03482, over 1414716.37 frames.], batch size: 19, lr: 3.40e-04
2022-04-29 20:55:37,834 INFO [train.py:763] (5/8) Epoch 22, batch 1600, loss[loss=0.1838, simple_loss=0.2872, pruned_loss=0.04026, over 7208.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2666, pruned_loss=0.03519, over 1412700.73 frames.], batch size: 21, lr: 3.40e-04
2022-04-29 20:56:43,437 INFO [train.py:763] (5/8) Epoch 22, batch 1650, loss[loss=0.1612, simple_loss=0.2644, pruned_loss=0.02896, over 7373.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2664, pruned_loss=0.03524, over 1415317.07 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:57:48,938 INFO [train.py:763] (5/8) Epoch 22, batch 1700, loss[loss=0.1511, simple_loss=0.2438, pruned_loss=0.0292, over 7406.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2668, pruned_loss=0.03521, over 1416370.33 frames.], batch size: 18, lr: 3.39e-04
2022-04-29 20:58:54,074 INFO [train.py:763] (5/8) Epoch 22, batch 1750, loss[loss=0.2338, simple_loss=0.3187, pruned_loss=0.07442, over 7145.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2677, pruned_loss=0.03535, over 1414942.14 frames.], batch size: 26, lr: 3.39e-04
2022-04-29 20:59:59,912 INFO [train.py:763] (5/8) Epoch 22, batch 1800, loss[loss=0.2213, simple_loss=0.3222, pruned_loss=0.06015, over 5036.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2675, pruned_loss=0.03534, over 1411821.48 frames.], batch size: 52, lr: 3.39e-04
2022-04-29 21:01:05,544 INFO [train.py:763] (5/8) Epoch 22, batch 1850, loss[loss=0.1764, simple_loss=0.2739, pruned_loss=0.03945, over 7433.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03542, over 1416745.34 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:02:10,918 INFO [train.py:763] (5/8) Epoch 22, batch 1900, loss[loss=0.2019, simple_loss=0.3094, pruned_loss=0.04724, over 7139.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03516, over 1420937.73 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:03:17,156 INFO [train.py:763] (5/8) Epoch 22, batch 1950, loss[loss=0.1863, simple_loss=0.2859, pruned_loss=0.04334, over 7153.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.03552, over 1418141.29 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:04:22,501 INFO [train.py:763] (5/8) Epoch 22, batch 2000, loss[loss=0.1857, simple_loss=0.2773, pruned_loss=0.04706, over 7251.00 frames.], tot_loss[loss=0.1704, simple_loss=0.269, pruned_loss=0.0359, over 1421596.66 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:05:28,502 INFO [train.py:763] (5/8) Epoch 22, batch 2050, loss[loss=0.1958, simple_loss=0.3009, pruned_loss=0.04533, over 7229.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.03585, over 1425702.21 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:06:35,603 INFO [train.py:763] (5/8) Epoch 22, batch 2100, loss[loss=0.1646, simple_loss=0.2661, pruned_loss=0.03152, over 7207.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03535, over 1420461.03 frames.], batch size: 23, lr: 3.39e-04
2022-04-29 21:07:42,151 INFO [train.py:763] (5/8) Epoch 22, batch 2150, loss[loss=0.164, simple_loss=0.2581, pruned_loss=0.03494, over 7156.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2684, pruned_loss=0.03558, over 1421171.77 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:08:47,300 INFO [train.py:763] (5/8) Epoch 22, batch 2200, loss[loss=0.1649, simple_loss=0.274, pruned_loss=0.02791, over 7150.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03599, over 1416298.09 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:09:53,563 INFO [train.py:763] (5/8) Epoch 22, batch 2250, loss[loss=0.1664, simple_loss=0.262, pruned_loss=0.03541, over 7150.00 frames.], tot_loss[loss=0.1705, simple_loss=0.269, pruned_loss=0.036, over 1411997.07 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:11:00,717 INFO [train.py:763] (5/8) Epoch 22, batch 2300, loss[loss=0.1637, simple_loss=0.2657, pruned_loss=0.03088, over 7308.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2679, pruned_loss=0.03589, over 1414091.72 frames.], batch size: 21, lr: 3.38e-04
2022-04-29 21:12:07,641 INFO [train.py:763] (5/8) Epoch 22, batch 2350, loss[loss=0.1754, simple_loss=0.2881, pruned_loss=0.03137, over 7334.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03546, over 1415913.34 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:13:14,360 INFO [train.py:763] (5/8) Epoch 22, batch 2400, loss[loss=0.1916, simple_loss=0.2812, pruned_loss=0.051, over 7287.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03569, over 1418502.25 frames.], batch size: 24, lr: 3.38e-04
2022-04-29 21:14:19,606 INFO [train.py:763] (5/8) Epoch 22, batch 2450, loss[loss=0.1851, simple_loss=0.2856, pruned_loss=0.04235, over 7208.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2692, pruned_loss=0.03571, over 1422610.91 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:15:24,882 INFO [train.py:763] (5/8) Epoch 22, batch 2500, loss[loss=0.1831, simple_loss=0.2879, pruned_loss=0.03918, over 6483.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03569, over 1421173.01 frames.], batch size: 37, lr: 3.38e-04
2022-04-29 21:16:30,048 INFO [train.py:763] (5/8) Epoch 22, batch 2550, loss[loss=0.1911, simple_loss=0.2959, pruned_loss=0.04311, over 7376.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2692, pruned_loss=0.03619, over 1422075.50 frames.], batch size: 23, lr: 3.38e-04
2022-04-29 21:17:35,658 INFO [train.py:763] (5/8) Epoch 22, batch 2600, loss[loss=0.1622, simple_loss=0.2689, pruned_loss=0.02773, over 7328.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2689, pruned_loss=0.03576, over 1426049.86 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:18:41,159 INFO [train.py:763] (5/8) Epoch 22, batch 2650, loss[loss=0.1844, simple_loss=0.285, pruned_loss=0.04191, over 7291.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.03532, over 1423355.77 frames.], batch size: 25, lr: 3.38e-04
2022-04-29 21:19:46,645 INFO [train.py:763] (5/8) Epoch 22, batch 2700, loss[loss=0.1366, simple_loss=0.2393, pruned_loss=0.01696, over 7156.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03527, over 1422950.79 frames.], batch size: 19, lr: 3.38e-04
2022-04-29 21:20:54,010 INFO [train.py:763] (5/8) Epoch 22, batch 2750, loss[loss=0.1682, simple_loss=0.2635, pruned_loss=0.03643, over 7163.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2675, pruned_loss=0.03597, over 1421682.99 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:22:00,027 INFO [train.py:763] (5/8) Epoch 22, batch 2800, loss[loss=0.1506, simple_loss=0.2404, pruned_loss=0.03042, over 7178.00 frames.], tot_loss[loss=0.17, simple_loss=0.2679, pruned_loss=0.03605, over 1420137.36 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:23:05,440 INFO [train.py:763] (5/8) Epoch 22, batch 2850, loss[loss=0.1719, simple_loss=0.277, pruned_loss=0.0334, over 7049.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2674, pruned_loss=0.0356, over 1421609.03 frames.], batch size: 28, lr: 3.38e-04
2022-04-29 21:24:10,667 INFO [train.py:763] (5/8) Epoch 22, batch 2900, loss[loss=0.1761, simple_loss=0.2775, pruned_loss=0.03734, over 7288.00 frames.], tot_loss[loss=0.1689, simple_loss=0.267, pruned_loss=0.03539, over 1423955.92 frames.], batch size: 25, lr: 3.37e-04
2022-04-29 21:25:15,980 INFO [train.py:763] (5/8) Epoch 22, batch 2950, loss[loss=0.1885, simple_loss=0.2854, pruned_loss=0.04577, over 7202.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.03535, over 1424513.82 frames.], batch size: 22, lr: 3.37e-04
2022-04-29 21:26:20,977 INFO [train.py:763] (5/8) Epoch 22, batch 3000, loss[loss=0.1343, simple_loss=0.228, pruned_loss=0.02031, over 6991.00 frames.], tot_loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03497, over 1423412.56 frames.], batch size: 16, lr: 3.37e-04
2022-04-29 21:26:20,978 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 21:26:36,379 INFO [train.py:792] (5/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
2022-04-29 21:27:41,670 INFO [train.py:763] (5/8) Epoch 22, batch 3050, loss[loss=0.1531, simple_loss=0.2511, pruned_loss=0.02761, over 7152.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03504, over 1425879.80 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:28:58,464 INFO [train.py:763] (5/8) Epoch 22, batch 3100, loss[loss=0.1655, simple_loss=0.2743, pruned_loss=0.02828, over 7234.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2663, pruned_loss=0.03497, over 1424962.57 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:30:03,944 INFO [train.py:763] (5/8) Epoch 22, batch 3150, loss[loss=0.1737, simple_loss=0.2819, pruned_loss=0.0327, over 7329.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2662, pruned_loss=0.035, over 1426190.37 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:31:09,279 INFO [train.py:763] (5/8) Epoch 22, batch 3200, loss[loss=0.1451, simple_loss=0.2493, pruned_loss=0.02048, over 7108.00 frames.], tot_loss[loss=0.168, simple_loss=0.2663, pruned_loss=0.03487, over 1428398.18 frames.], batch size: 21, lr: 3.37e-04
2022-04-29 21:32:14,552 INFO [train.py:763] (5/8) Epoch 22, batch 3250, loss[loss=0.1611, simple_loss=0.2643, pruned_loss=0.02892, over 6306.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03543, over 1422578.21 frames.], batch size: 37, lr: 3.37e-04
2022-04-29 21:33:19,831 INFO [train.py:763] (5/8) Epoch 22, batch 3300, loss[loss=0.1835, simple_loss=0.2799, pruned_loss=0.04348, over 7293.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2673, pruned_loss=0.03486, over 1422807.68 frames.], batch size: 24, lr: 3.37e-04
2022-04-29 21:34:25,359 INFO [train.py:763] (5/8) Epoch 22, batch 3350, loss[loss=0.1812, simple_loss=0.2866, pruned_loss=0.03787, over 7160.00 frames.], tot_loss[loss=0.1675, simple_loss=0.266, pruned_loss=0.03451, over 1428004.91 frames.], batch size: 26, lr: 3.37e-04
2022-04-29 21:35:30,553 INFO [train.py:763] (5/8) Epoch 22, batch 3400, loss[loss=0.1563, simple_loss=0.2574, pruned_loss=0.02759, over 7158.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2663, pruned_loss=0.0346, over 1429084.05 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:36:36,032 INFO [train.py:763] (5/8) Epoch 22, batch 3450, loss[loss=0.1589, simple_loss=0.2479, pruned_loss=0.03491, over 6752.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2656, pruned_loss=0.03466, over 1429947.12 frames.], batch size: 15, lr: 3.37e-04
2022-04-29 21:37:41,470 INFO [train.py:763] (5/8) Epoch 22, batch 3500, loss[loss=0.1596, simple_loss=0.2479, pruned_loss=0.03565, over 6769.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2658, pruned_loss=0.03478, over 1430603.65 frames.], batch size: 15, lr: 3.37e-04
2022-04-29 21:38:46,765 INFO [train.py:763] (5/8) Epoch 22, batch 3550, loss[loss=0.1699, simple_loss=0.2593, pruned_loss=0.04027, over 7427.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2663, pruned_loss=0.03522, over 1430293.90 frames.], batch size: 18, lr: 3.36e-04
2022-04-29 21:39:52,009 INFO [train.py:763] (5/8) Epoch 22, batch 3600, loss[loss=0.1397, simple_loss=0.2326, pruned_loss=0.02341, over 7289.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03515, over 1431459.37 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:40:57,420 INFO [train.py:763] (5/8) Epoch 22, batch 3650, loss[loss=0.1873, simple_loss=0.292, pruned_loss=0.04126, over 6455.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03509, over 1431072.75 frames.], batch size: 37, lr: 3.36e-04
2022-04-29 21:42:03,754 INFO [train.py:763] (5/8) Epoch 22, batch 3700, loss[loss=0.1592, simple_loss=0.248, pruned_loss=0.03515, over 7158.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2673, pruned_loss=0.03491, over 1429617.13 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:43:09,194 INFO [train.py:763] (5/8) Epoch 22, batch 3750, loss[loss=0.1568, simple_loss=0.2499, pruned_loss=0.03183, over 7297.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03494, over 1427619.61 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:44:14,442 INFO [train.py:763] (5/8) Epoch 22, batch 3800, loss[loss=0.172, simple_loss=0.2664, pruned_loss=0.03878, over 7383.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03439, over 1429904.89 frames.], batch size: 23, lr: 3.36e-04
2022-04-29 21:45:19,895 INFO [train.py:763] (5/8) Epoch 22, batch 3850, loss[loss=0.1869, simple_loss=0.2902, pruned_loss=0.04174, over 7120.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.0343, over 1431221.36 frames.], batch size: 28, lr: 3.36e-04
2022-04-29 21:46:26,375 INFO [train.py:763] (5/8) Epoch 22, batch 3900, loss[loss=0.1723, simple_loss=0.2819, pruned_loss=0.03133, over 7117.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2667, pruned_loss=0.03485, over 1430611.33 frames.], batch size: 21, lr: 3.36e-04
2022-04-29 21:47:31,500 INFO [train.py:763] (5/8) Epoch 22, batch 3950, loss[loss=0.1604, simple_loss=0.2719, pruned_loss=0.02442, over 7164.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2674, pruned_loss=0.03498, over 1430484.47 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:48:36,602 INFO [train.py:763] (5/8) Epoch 22, batch 4000, loss[loss=0.1346, simple_loss=0.2257, pruned_loss=0.02173, over 7282.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2666, pruned_loss=0.03476, over 1426797.46 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:49:42,517 INFO [train.py:763] (5/8) Epoch 22, batch 4050, loss[loss=0.1461, simple_loss=0.2298, pruned_loss=0.03116, over 6777.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2677, pruned_loss=0.03502, over 1421984.36 frames.], batch size: 15, lr: 3.36e-04
2022-04-29 21:50:49,121 INFO [train.py:763] (5/8) Epoch 22, batch 4100, loss[loss=0.1501, simple_loss=0.2379, pruned_loss=0.03115, over 6833.00 frames.], tot_loss[loss=0.169, simple_loss=0.2675, pruned_loss=0.03523, over 1418852.25 frames.], batch size: 15, lr: 3.36e-04
2022-04-29 21:51:54,121 INFO [train.py:763] (5/8) Epoch 22, batch 4150, loss[loss=0.1804, simple_loss=0.2882, pruned_loss=0.03625, over 7319.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2686, pruned_loss=0.03558, over 1417722.29 frames.], batch size: 21, lr: 3.35e-04
2022-04-29 21:52:59,304 INFO [train.py:763] (5/8) Epoch 22, batch 4200, loss[loss=0.1587, simple_loss=0.2428, pruned_loss=0.03732, over 6988.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2686, pruned_loss=0.03519, over 1422185.35 frames.], batch size: 16, lr: 3.35e-04
2022-04-29 21:54:05,537 INFO [train.py:763] (5/8) Epoch 22, batch 4250, loss[loss=0.1677, simple_loss=0.2673, pruned_loss=0.03409, over 7237.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2691, pruned_loss=0.03522, over 1423669.64 frames.], batch size: 20, lr: 3.35e-04
2022-04-29 21:55:12,529 INFO [train.py:763] (5/8) Epoch 22, batch 4300, loss[loss=0.1454, simple_loss=0.2345, pruned_loss=0.02821, over 7167.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2674, pruned_loss=0.03466, over 1421117.63 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:56:19,780 INFO [train.py:763] (5/8) Epoch 22, batch 4350, loss[loss=0.1585, simple_loss=0.2472, pruned_loss=0.03489, over 6800.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2669, pruned_loss=0.03471, over 1422498.08 frames.], batch size: 15, lr: 3.35e-04
2022-04-29 21:57:26,793 INFO [train.py:763] (5/8) Epoch 22, batch 4400, loss[loss=0.1554, simple_loss=0.2518, pruned_loss=0.0295, over 7074.00 frames.], tot_loss[loss=0.1676, simple_loss=0.266, pruned_loss=0.03458, over 1419880.79 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:58:31,948 INFO [train.py:763] (5/8) Epoch 22, batch 4450, loss[loss=0.193, simple_loss=0.2802, pruned_loss=0.05291, over 4922.00 frames.], tot_loss[loss=0.1674, simple_loss=0.266, pruned_loss=0.03444, over 1414478.50 frames.], batch size: 52, lr: 3.35e-04
2022-04-29 21:59:36,926 INFO [train.py:763] (5/8) Epoch 22, batch 4500, loss[loss=0.1576, simple_loss=0.2523, pruned_loss=0.0314, over 7073.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03491, over 1413014.01 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 22:00:41,215 INFO [train.py:763] (5/8) Epoch 22, batch 4550, loss[loss=0.214, simple_loss=0.3081, pruned_loss=0.06001, over 4920.00 frames.], tot_loss[loss=0.172, simple_loss=0.27, pruned_loss=0.03696, over 1357224.36 frames.], batch size: 53, lr: 3.35e-04
2022-04-29 22:02:00,641 INFO [train.py:763] (5/8) Epoch 23, batch 0, loss[loss=0.1734, simple_loss=0.2619, pruned_loss=0.04243, over 6814.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2619, pruned_loss=0.04243, over 6814.00 frames.], batch size: 15, lr: 3.28e-04
2022-04-29 22:03:02,945 INFO [train.py:763] (5/8) Epoch 23, batch 50, loss[loss=0.1386, simple_loss=0.2293, pruned_loss=0.024, over 7294.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03498, over 317399.33 frames.], batch size: 17, lr: 3.28e-04
2022-04-29 22:04:05,012 INFO [train.py:763] (5/8) Epoch 23, batch 100, loss[loss=0.172, simple_loss=0.2783, pruned_loss=0.03285, over 7335.00 frames.], tot_loss[loss=0.168, simple_loss=0.2678, pruned_loss=0.03408, over 567492.02 frames.], batch size: 20, lr: 3.28e-04
2022-04-29 22:05:10,558 INFO [train.py:763] (5/8) Epoch 23, batch 150, loss[loss=0.1792, simple_loss=0.2857, pruned_loss=0.03635, over 7389.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2684, pruned_loss=0.03494, over 753080.38 frames.], batch size: 23, lr: 3.28e-04
2022-04-29 22:06:15,914 INFO [train.py:763] (5/8) Epoch 23, batch 200, loss[loss=0.1784, simple_loss=0.2821, pruned_loss=0.03733, over 7217.00 frames.], tot_loss[loss=0.17, simple_loss=0.2687, pruned_loss=0.03563, over 904568.95 frames.], batch size: 22, lr: 3.28e-04
2022-04-29 22:07:21,267 INFO [train.py:763] (5/8) Epoch 23, batch 250, loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03103, over 7415.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03563, over 1016795.92 frames.], batch size: 21, lr: 3.28e-04
2022-04-29 22:08:27,060 INFO [train.py:763] (5/8) Epoch 23, batch 300, loss[loss=0.1542, simple_loss=0.2578, pruned_loss=0.02525, over 7140.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03558, over 1107583.06 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:09:32,884 INFO [train.py:763] (5/8) Epoch 23, batch 350, loss[loss=0.1517, simple_loss=0.2605, pruned_loss=0.02146, over 7290.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2676, pruned_loss=0.03503, over 1178780.60 frames.], batch size: 25, lr: 3.27e-04
2022-04-29 22:10:38,049 INFO [train.py:763] (5/8) Epoch 23, batch 400, loss[loss=0.1756, simple_loss=0.2758, pruned_loss=0.03773, over 7269.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2666, pruned_loss=0.03483, over 1229380.80 frames.], batch size: 24, lr: 3.27e-04
2022-04-29 22:11:43,834 INFO [train.py:763] (5/8) Epoch 23, batch 450, loss[loss=0.1532, simple_loss=0.2569, pruned_loss=0.02475, over 7139.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03452, over 1275526.87 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:12:49,138 INFO [train.py:763] (5/8) Epoch 23, batch 500, loss[loss=0.1624, simple_loss=0.2535, pruned_loss=0.0357, over 7352.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2664, pruned_loss=0.03434, over 1307527.45 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:13:54,755 INFO [train.py:763] (5/8) Epoch 23, batch 550, loss[loss=0.1959, simple_loss=0.2942, pruned_loss=0.04878, over 7208.00 frames.], tot_loss[loss=0.1675, simple_loss=0.266, pruned_loss=0.03447, over 1335776.81 frames.], batch size: 22, lr: 3.27e-04
2022-04-29 22:15:00,604 INFO [train.py:763] (5/8) Epoch 23, batch 600, loss[loss=0.1482, simple_loss=0.2434, pruned_loss=0.02644, over 7361.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2657, pruned_loss=0.03432, over 1353062.07 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:16:06,058 INFO [train.py:763] (5/8) Epoch 23, batch 650, loss[loss=0.1526, simple_loss=0.2571, pruned_loss=0.02404, over 7362.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2657, pruned_loss=0.03426, over 1362513.83 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:17:12,052 INFO [train.py:763] (5/8) Epoch 23, batch 700, loss[loss=0.1715, simple_loss=0.2754, pruned_loss=0.03376, over 7109.00 frames.], tot_loss[loss=0.166, simple_loss=0.2643, pruned_loss=0.03386, over 1380268.52 frames.], batch size: 26, lr: 3.27e-04
2022-04-29 22:18:17,844 INFO [train.py:763] (5/8) Epoch 23, batch 750, loss[loss=0.155, simple_loss=0.2438, pruned_loss=0.03309, over 6996.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2651, pruned_loss=0.03375, over 1391543.36 frames.], batch size: 16, lr: 3.27e-04
2022-04-29 22:19:23,435 INFO [train.py:763] (5/8) Epoch 23, batch 800, loss[loss=0.1707, simple_loss=0.2704, pruned_loss=0.0355, over 7250.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2647, pruned_loss=0.03378, over 1398473.98 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:20:28,947 INFO [train.py:763] (5/8) Epoch 23, batch 850, loss[loss=0.1679, simple_loss=0.2656, pruned_loss=0.03511, over 6692.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.03355, over 1404925.07 frames.], batch size: 31, lr: 3.27e-04
2022-04-29 22:21:34,334 INFO [train.py:763] (5/8) Epoch 23, batch 900, loss[loss=0.1762, simple_loss=0.2747, pruned_loss=0.03886, over 7427.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2649, pruned_loss=0.0339, over 1411123.10 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:22:49,573 INFO [train.py:763] (5/8) Epoch 23, batch 950, loss[loss=0.1596, simple_loss=0.263, pruned_loss=0.02811, over 6463.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2641, pruned_loss=0.03361, over 1416237.26 frames.], batch size: 38, lr: 3.26e-04
2022-04-29 22:23:55,242 INFO [train.py:763] (5/8) Epoch 23, batch 1000, loss[loss=0.1755, simple_loss=0.2736, pruned_loss=0.03871, over 7310.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2635, pruned_loss=0.0341, over 1418364.36 frames.], batch size: 21, lr: 3.26e-04
2022-04-29 22:25:00,706 INFO [train.py:763] (5/8) Epoch 23, batch 1050, loss[loss=0.1687, simple_loss=0.265, pruned_loss=0.03618, over 7229.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2648, pruned_loss=0.03455, over 1411927.05 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:26:07,031 INFO [train.py:763] (5/8) Epoch 23, batch 1100, loss[loss=0.1542, simple_loss=0.2728, pruned_loss=0.0178, over 7148.00 frames.], tot_loss[loss=0.1671, simple_loss=0.265, pruned_loss=0.03461, over 1412014.93 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:27:12,602 INFO [train.py:763] (5/8) Epoch 23, batch 1150, loss[loss=0.1649, simple_loss=0.2729, pruned_loss=0.02848, over 6626.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2643, pruned_loss=0.03417, over 1415190.20 frames.], batch size: 38, lr: 3.26e-04
2022-04-29 22:28:17,837 INFO [train.py:763] (5/8) Epoch 23, batch 1200, loss[loss=0.1589, simple_loss=0.2656, pruned_loss=0.02606, over 7166.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2654, pruned_loss=0.03422, over 1417747.34 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:29:23,312 INFO [train.py:763] (5/8) Epoch 23, batch 1250, loss[loss=0.1697, simple_loss=0.2668, pruned_loss=0.03634, over 7338.00 frames.], tot_loss[loss=0.167, simple_loss=0.2655, pruned_loss=0.03426, over 1418488.91 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:30:28,896 INFO [train.py:763] (5/8) Epoch 23, batch 1300, loss[loss=0.1762, simple_loss=0.2854, pruned_loss=0.03349, over 6648.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2656, pruned_loss=0.03435, over 1419687.52 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:31:51,697 INFO [train.py:763] (5/8) Epoch 23, batch 1350, loss[loss=0.1577, simple_loss=0.2465, pruned_loss=0.03447, over 7414.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03461, over 1425211.54 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:32:57,247 INFO [train.py:763] (5/8) Epoch 23, batch 1400, loss[loss=0.181, simple_loss=0.2924, pruned_loss=0.03474, over 7190.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03461, over 1423724.08 frames.], batch size: 26, lr: 3.26e-04
2022-04-29 22:34:20,494 INFO [train.py:763] (5/8) Epoch 23, batch 1450, loss[loss=0.1827, simple_loss=0.2874, pruned_loss=0.03906, over 7148.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03456, over 1421692.72 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:35:53,266 INFO [train.py:763] (5/8) Epoch 23, batch 1500, loss[loss=0.1691, simple_loss=0.2772, pruned_loss=0.0305, over 7144.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2668, pruned_loss=0.03466, over 1420352.76 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:36:59,423 INFO [train.py:763] (5/8) Epoch 23, batch 1550, loss[loss=0.1563, simple_loss=0.272, pruned_loss=0.02029, over 6785.00 frames.], tot_loss[loss=0.167, simple_loss=0.266, pruned_loss=0.03406, over 1421269.63 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:38:04,562 INFO [train.py:763] (5/8) Epoch 23, batch 1600, loss[loss=0.1601, simple_loss=0.2624, pruned_loss=0.0289, over 7311.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2665, pruned_loss=0.03383, over 1422627.89 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:39:10,556 INFO [train.py:763] (5/8) Epoch 23, batch 1650, loss[loss=0.1299, simple_loss=0.2167, pruned_loss=0.02157, over 6762.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2665, pruned_loss=0.03385, over 1413666.82 frames.], batch size: 15, lr: 3.25e-04
2022-04-29 22:40:17,830 INFO [train.py:763] (5/8) Epoch 23, batch 1700, loss[loss=0.1751, simple_loss=0.2791, pruned_loss=0.03552, over 7311.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03363, over 1417769.34 frames.], batch size: 21, lr: 3.25e-04
2022-04-29 22:41:24,857 INFO [train.py:763] (5/8) Epoch 23, batch 1750, loss[loss=0.1795, simple_loss=0.271, pruned_loss=0.04404, over 7063.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.0341, over 1418729.61 frames.], batch size: 18, lr: 3.25e-04
2022-04-29 22:42:30,374 INFO [train.py:763] (5/8) Epoch 23, batch 1800, loss[loss=0.1803, simple_loss=0.2785, pruned_loss=0.04102, over 7338.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2667, pruned_loss=0.03429, over 1419126.53 frames.], batch size: 22, lr: 3.25e-04
2022-04-29 22:43:35,685 INFO [train.py:763] (5/8) Epoch 23, batch 1850, loss[loss=0.1738, simple_loss=0.275, pruned_loss=0.03632, over 7300.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03409, over 1423681.43 frames.], batch size: 24, lr: 3.25e-04
2022-04-29 22:44:41,107 INFO [train.py:763] (5/8) Epoch 23, batch 1900, loss[loss=0.1823, simple_loss=0.2714, pruned_loss=0.04655, over 7026.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03438, over 1422252.37 frames.], batch size: 28, lr: 3.25e-04
2022-04-29 22:45:46,549 INFO [train.py:763] (5/8) Epoch 23, batch 1950, loss[loss=0.1562, simple_loss=0.2692, pruned_loss=0.0216, over 7110.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2678, pruned_loss=0.03482, over 1422660.34 frames.], batch size: 21, lr: 3.25e-04
2022-04-29 22:46:52,060 INFO [train.py:763] (5/8) Epoch 23, batch 2000, loss[loss=0.208, simple_loss=0.2904, pruned_loss=0.06285, over 4962.00 frames.], tot_loss[loss=0.1692, simple_loss=0.268, pruned_loss=0.0352, over 1420839.13 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:47:58,956 INFO [train.py:763] (5/8) Epoch 23, batch 2050, loss[loss=0.1361, simple_loss=0.2371, pruned_loss=0.01757, over 7436.00 frames.], tot_loss[loss=0.1689, simple_loss=0.268, pruned_loss=0.03491, over 1421369.32 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:49:05,152 INFO [train.py:763] (5/8) Epoch 23, batch 2100, loss[loss=0.1776, simple_loss=0.2651, pruned_loss=0.04505, over 7002.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03474, over 1422751.66 frames.], batch size: 16, lr: 3.25e-04
2022-04-29 22:50:10,657 INFO [train.py:763] (5/8) Epoch 23, batch 2150, loss[loss=0.2293, simple_loss=0.3118, pruned_loss=0.07343, over 4955.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2667, pruned_loss=0.03448, over 1420033.12 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:51:16,167 INFO [train.py:763] (5/8) Epoch 23, batch 2200, loss[loss=0.1764, simple_loss=0.2695, pruned_loss=0.04168, over 7138.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.0343, over 1418833.87 frames.], batch size: 17, lr: 3.25e-04
2022-04-29 22:52:21,336 INFO [train.py:763] (5/8) Epoch 23, batch 2250, loss[loss=0.1734, simple_loss=0.2752, pruned_loss=0.03581, over 7309.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03468, over 1408074.36 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 22:53:28,274 INFO [train.py:763] (5/8) Epoch 23, batch 2300, loss[loss=0.1554, simple_loss=0.2476, pruned_loss=0.0316, over 7279.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2665, pruned_loss=0.03451, over 1415599.57 frames.], batch size: 17, lr: 3.24e-04
2022-04-29 22:54:34,468 INFO [train.py:763] (5/8) Epoch 23, batch 2350, loss[loss=0.1606, simple_loss=0.268, pruned_loss=0.02658, over 7333.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.0352, over 1417079.14 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 22:55:39,715 INFO [train.py:763] (5/8) Epoch 23, batch 2400, loss[loss=0.1524, simple_loss=0.2392, pruned_loss=0.03283, over 6766.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03511, over 1419600.91 frames.], batch size: 15, lr: 3.24e-04
2022-04-29 22:56:45,976 INFO [train.py:763] (5/8) Epoch 23, batch 2450, loss[loss=0.162, simple_loss=0.2527, pruned_loss=0.03561, over 7238.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2673, pruned_loss=0.03507, over 1416499.21 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 22:57:51,402 INFO [train.py:763] (5/8) Epoch 23, batch 2500, loss[loss=0.1978, simple_loss=0.3097, pruned_loss=0.04294, over 7329.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2664, pruned_loss=0.0347, over 1417311.81 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 22:58:56,889 INFO [train.py:763] (5/8) Epoch 23, batch 2550, loss[loss=0.2129, simple_loss=0.3022, pruned_loss=0.06182, over 5330.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2655, pruned_loss=0.03438, over 1413803.93 frames.], batch size: 52, lr: 3.24e-04
2022-04-29 23:00:02,923 INFO [train.py:763] (5/8) Epoch 23, batch 2600, loss[loss=0.1467, simple_loss=0.2509, pruned_loss=0.02124, over 7283.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03449, over 1417106.02 frames.], batch size: 18, lr: 3.24e-04
2022-04-29 23:01:08,571 INFO [train.py:763] (5/8) Epoch 23, batch 2650, loss[loss=0.1683, simple_loss=0.2742, pruned_loss=0.03114, over 7326.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03476, over 1416005.02 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:02:14,031 INFO [train.py:763] (5/8) Epoch 23, batch 2700, loss[loss=0.1707, simple_loss=0.2704, pruned_loss=0.03554, over 7328.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03484, over 1421305.40 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 23:03:19,902 INFO [train.py:763] (5/8) Epoch 23, batch 2750, loss[loss=0.165, simple_loss=0.2654, pruned_loss=0.03235, over 7422.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03451, over 1425548.89 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:04:25,099 INFO [train.py:763] (5/8) Epoch 23, batch 2800, loss[loss=0.2279, simple_loss=0.3206, pruned_loss=0.06759, over 7234.00 frames.], tot_loss[loss=0.169, simple_loss=0.268, pruned_loss=0.03503, over 1421908.76 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 23:05:30,277 INFO [train.py:763] (5/8) Epoch 23, batch 2850, loss[loss=0.1709, simple_loss=0.2716, pruned_loss=0.03511, over 7360.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2688, pruned_loss=0.03544, over 1422582.92 frames.], batch size: 19, lr: 3.24e-04
2022-04-29 23:06:35,476 INFO [train.py:763] (5/8) Epoch 23, batch 2900, loss[loss=0.1693, simple_loss=0.2774, pruned_loss=0.03065, over 7316.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2689, pruned_loss=0.03489, over 1422298.37 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 23:07:40,687 INFO [train.py:763] (5/8) Epoch 23, batch 2950, loss[loss=0.1597, simple_loss=0.2483, pruned_loss=0.03557, over 7278.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2681, pruned_loss=0.03452, over 1426425.30 frames.], batch size: 17, lr: 3.23e-04
2022-04-29 23:08:45,895 INFO [train.py:763] (5/8) Epoch 23, batch 3000, loss[loss=0.1837, simple_loss=0.279, pruned_loss=0.0442, over 7115.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03453, over 1421770.52 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:08:45,896 INFO [train.py:783] (5/8) Computing validation loss
2022-04-29 23:09:01,229 INFO [train.py:792] (5/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
2022-04-29 23:10:07,041 INFO [train.py:763] (5/8) Epoch 23, batch 3050, loss[loss=0.1644, simple_loss=0.2568, pruned_loss=0.03598, over 7276.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2666, pruned_loss=0.03454, over 1416255.95 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:11:12,532 INFO [train.py:763] (5/8) Epoch 23, batch 3100, loss[loss=0.1815, simple_loss=0.2811, pruned_loss=0.04096, over 6837.00 frames.], tot_loss[loss=0.1675, simple_loss=0.266, pruned_loss=0.0345, over 1419893.94 frames.], batch size: 31, lr: 3.23e-04
2022-04-29 23:12:19,062 INFO [train.py:763] (5/8) Epoch 23, batch 3150, loss[loss=0.1507, simple_loss=0.2431, pruned_loss=0.0292, over 7016.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2663, pruned_loss=0.03432, over 1421909.38 frames.], batch size: 16, lr: 3.23e-04
2022-04-29 23:13:26,795 INFO [train.py:763] (5/8) Epoch 23, batch 3200, loss[loss=0.1588, simple_loss=0.2573, pruned_loss=0.0301, over 7321.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.03418, over 1426080.41 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:14:33,557 INFO [train.py:763] (5/8) Epoch 23, batch 3250, loss[loss=0.1497, simple_loss=0.2472, pruned_loss=0.02614, over 7165.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03404, over 1427715.99 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:15:38,821 INFO [train.py:763] (5/8) Epoch 23, batch 3300, loss[loss=0.1889, simple_loss=0.2972, pruned_loss=0.04031, over 7309.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03345, over 1427635.27 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:16:45,590 INFO [train.py:763] (5/8) Epoch 23, batch 3350, loss[loss=0.1652, simple_loss=0.273, pruned_loss=0.02867, over 7272.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03391, over 1424226.31 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:17:51,528 INFO [train.py:763] (5/8) Epoch 23, batch 3400, loss[loss=0.1752, simple_loss=0.2709, pruned_loss=0.03979, over 7369.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2656, pruned_loss=0.03401, over 1428132.53 frames.], batch size: 19, lr: 3.23e-04
2022-04-29 23:18:56,734 INFO [train.py:763] (5/8) Epoch 23, batch 3450, loss[loss=0.1709, simple_loss=0.2783, pruned_loss=0.0317, over 7335.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2667, pruned_loss=0.03427, over 1423464.02 frames.], batch size: 22, lr: 3.23e-04
2022-04-29 23:20:02,261 INFO [train.py:763] (5/8) Epoch 23, batch 3500, loss[loss=0.1614, simple_loss=0.2483, pruned_loss=0.03725, over 7179.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2659, pruned_loss=0.03419, over 1421817.11 frames.], batch size: 16, lr: 3.23e-04
2022-04-29 23:21:08,256 INFO [train.py:763] (5/8) Epoch 23, batch 3550, loss[loss=0.1773, simple_loss=0.2833, pruned_loss=0.03564, over 7110.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2659, pruned_loss=0.0341, over 1423212.65 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:22:13,616 INFO [train.py:763] (5/8) Epoch 23, batch 3600, loss[loss=0.1426, simple_loss=0.2386, pruned_loss=0.02332, over 7063.00 frames.], tot_loss[loss=0.167, simple_loss=0.2662, pruned_loss=0.03391, over 1423320.52 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:23:18,845 INFO [train.py:763] (5/8) Epoch 23, batch 3650, loss[loss=0.177, simple_loss=0.2761, pruned_loss=0.03897, over 7356.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2667, pruned_loss=0.03418, over 1423276.62 frames.], batch size: 19, lr: 3.22e-04
2022-04-29 23:24:24,046 INFO [train.py:763] (5/8) Epoch 23, batch 3700, loss[loss=0.1767, simple_loss=0.2775, pruned_loss=0.03798, over 6421.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.03408, over 1420665.65 frames.], batch size: 38, lr: 3.22e-04
2022-04-29 23:25:30,846 INFO [train.py:763] (5/8) Epoch 23, batch 3750, loss[loss=0.1658, simple_loss=0.251, pruned_loss=0.04026, over 7274.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03464, over 1422022.03 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:26:37,721 INFO [train.py:763] (5/8) Epoch 23, batch 3800, loss[loss=0.1547, simple_loss=0.2587, pruned_loss=0.0253, over 7427.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.03413, over 1423937.55 frames.], batch size: 20, lr: 3.22e-04
2022-04-29 23:27:43,268 INFO [train.py:763] (5/8) Epoch 23, batch 3850, loss[loss=0.1879, simple_loss=0.2857, pruned_loss=0.04505, over 5011.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2665, pruned_loss=0.03439, over 1420736.82 frames.], batch size: 53, lr: 3.22e-04
2022-04-29 23:28:48,643 INFO [train.py:763] (5/8) Epoch 23, batch 3900, loss[loss=0.1761, simple_loss=0.2745, pruned_loss=0.03885, over 6779.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2661, pruned_loss=0.03456, over 1417820.09 frames.], batch size: 31, lr: 3.22e-04
2022-04-29 23:29:53,693 INFO [train.py:763] (5/8) Epoch 23, batch 3950, loss[loss=0.1382, simple_loss=0.2291, pruned_loss=0.02361, over 7126.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03472, over 1417012.74 frames.], batch size: 17, lr: 3.22e-04
2022-04-29 23:30:59,590 INFO [train.py:763] (5/8) Epoch 23, batch 4000, loss[loss=0.1831, simple_loss=0.2841, pruned_loss=0.04104, over 7201.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03502, over 1415760.78 frames.], batch size: 22, lr: 3.22e-04
2022-04-29 23:32:05,451 INFO [train.py:763] (5/8) Epoch 23, batch 4050, loss[loss=0.2289, simple_loss=0.3146, pruned_loss=0.07163, over 4938.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2675, pruned_loss=0.03499, over 1417138.62 frames.], batch size: 52, lr: 3.22e-04
2022-04-29 23:33:10,721 INFO [train.py:763] (5/8) Epoch 23, batch 4100, loss[loss=0.159, simple_loss=0.2517, pruned_loss=0.03318, over 7273.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2674, pruned_loss=0.03494, over 1417152.42 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:34:16,157 INFO [train.py:763] (5/8) Epoch 23, batch 4150, loss[loss=0.1275, simple_loss=0.2216, pruned_loss=0.0167, over 6994.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2672, pruned_loss=0.03475, over 1418386.58 frames.], batch size: 16, lr: 3.22e-04
2022-04-29 23:35:21,255 INFO [train.py:763] (5/8) Epoch 23, batch 4200, loss[loss=0.1676, simple_loss=0.2675, pruned_loss=0.03383, over 7284.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2683, pruned_loss=0.03492, over 1418653.83 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:36:26,919 INFO [train.py:763] (5/8) Epoch 23, batch 4250, loss[loss=0.1909, simple_loss=0.2941, pruned_loss=0.04391, over 7383.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2671, pruned_loss=0.03428, over 1416373.17 frames.], batch size: 23, lr: 3.22e-04
2022-04-29 23:37:32,237 INFO [train.py:763] (5/8) Epoch 23, batch 4300, loss[loss=0.1534, simple_loss=0.233, pruned_loss=0.0369, over 6769.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03428, over 1415474.09 frames.], batch size: 15, lr: 3.21e-04
2022-04-29 23:38:37,672 INFO [train.py:763] (5/8) Epoch 23, batch 4350, loss[loss=0.1924, simple_loss=0.2933, pruned_loss=0.04578, over 6741.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.0345, over 1413404.53 frames.], batch size: 31, lr: 3.21e-04
2022-04-29 23:39:43,234 INFO [train.py:763] (5/8) Epoch 23, batch 4400, loss[loss=0.1599, simple_loss=0.2682, pruned_loss=0.02578, over 6339.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2668, pruned_loss=0.03441, over 1407761.68 frames.], batch size: 38, lr: 3.21e-04
2022-04-29 23:40:48,378 INFO [train.py:763] (5/8) Epoch 23, batch 4450, loss[loss=0.1738, simple_loss=0.2824, pruned_loss=0.03263, over 6400.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03379, over 1410087.65 frames.], batch size: 38, lr: 3.21e-04
2022-04-29 23:41:53,051 INFO [train.py:763] (5/8) Epoch 23, batch 4500, loss[loss=0.1674, simple_loss=0.2682, pruned_loss=0.03326, over 6403.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2662, pruned_loss=0.03464, over 1397344.48 frames.], batch size: 37, lr: 3.21e-04
2022-04-29 23:42:58,314 INFO [train.py:763] (5/8) Epoch 23, batch 4550, loss[loss=0.1579, simple_loss=0.2665, pruned_loss=0.0246, over 7292.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2662, pruned_loss=0.03484, over 1386154.38 frames.], batch size: 24, lr: 3.21e-04
2022-04-29 23:44:17,938 INFO [train.py:763] (5/8) Epoch 24, batch 0, loss[loss=0.1847, simple_loss=0.284, pruned_loss=0.04271, over 7065.00 frames.], tot_loss[loss=0.1847, simple_loss=0.284, pruned_loss=0.04271, over 7065.00 frames.], batch size: 18, lr: 3.15e-04
2022-04-29 23:45:23,862 INFO [train.py:763] (5/8) Epoch 24, batch 50, loss[loss=0.1836, simple_loss=0.2836, pruned_loss=0.04182, over 7259.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2666, pruned_loss=0.03401, over 321851.17 frames.], batch size: 19, lr: 3.15e-04
2022-04-29 23:46:30,367 INFO [train.py:763] (5/8) Epoch 24, batch 100, loss[loss=0.179, simple_loss=0.2863, pruned_loss=0.03589, over 7325.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2674, pruned_loss=0.03446, over 570288.27 frames.], batch size: 20, lr: 3.15e-04
2022-04-29 23:47:35,978 INFO [train.py:763] (5/8) Epoch 24, batch 150, loss[loss=0.1673, simple_loss=0.278, pruned_loss=0.02829, over 7326.00 frames.], tot_loss[loss=0.1671, simple_loss=0.266, pruned_loss=0.03409, over 761620.73 frames.], batch size: 21, lr: 3.14e-04
2022-04-29 23:48:41,597 INFO [train.py:763] (5/8) Epoch 24, batch 200, loss[loss=0.1559, simple_loss=0.2477, pruned_loss=0.03209, over 6753.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.03376, over 906216.35 frames.], batch size: 15, lr: 3.14e-04
2022-04-29 23:49:46,886 INFO [train.py:763] (5/8) Epoch 24, batch 250, loss[loss=0.1702, simple_loss=0.2705, pruned_loss=0.035, over 7235.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03337, over 1018538.54 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:50:52,238 INFO [train.py:763] (5/8) Epoch 24, batch 300, loss[loss=0.152, simple_loss=0.2527, pruned_loss=0.02566, over 7166.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2645, pruned_loss=0.03364, over 1112118.04 frames.], batch size: 19, lr: 3.14e-04
2022-04-29 23:51:57,524 INFO [train.py:763] (5/8) Epoch 24, batch 350, loss[loss=0.1895, simple_loss=0.2905, pruned_loss=0.04422, over 7225.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03377, over 1181180.60 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:53:03,345 INFO [train.py:763] (5/8) Epoch 24, batch 400, loss[loss=0.1488, simple_loss=0.2498, pruned_loss=0.02386, over 7240.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.03352, over 1236285.70 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:54:08,676 INFO [train.py:763] (5/8) Epoch 24, batch 450, loss[loss=0.1897, simple_loss=0.2938, pruned_loss=0.04278, over 7028.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03288, over 1277245.55 frames.], batch size: 28, lr: 3.14e-04
2022-04-29 23:55:14,216 INFO [train.py:763] (5/8) Epoch 24, batch 500, loss[loss=0.1584, simple_loss=0.2554, pruned_loss=0.03073, over 7163.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.03282, over 1312200.04 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:56:20,469 INFO [train.py:763] (5/8) Epoch 24, batch 550, loss[loss=0.1498, simple_loss=0.2506, pruned_loss=0.02451, over 7162.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03309, over 1339537.30 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:57:26,723 INFO [train.py:763] (5/8) Epoch 24, batch 600, loss[loss=0.1864, simple_loss=0.2763, pruned_loss=0.04827, over 7216.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2653, pruned_loss=0.03314, over 1358060.06 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:58:32,099 INFO [train.py:763] (5/8) Epoch 24, batch 650, loss[loss=0.1533, simple_loss=0.2377, pruned_loss=0.03447, over 7302.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2646, pruned_loss=0.03308, over 1371095.15 frames.], batch size: 17, lr: 3.14e-04
2022-04-29 23:59:38,746 INFO [train.py:763] (5/8) Epoch 24, batch 700, loss[loss=0.1575, simple_loss=0.2524, pruned_loss=0.03135, over 7204.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2644, pruned_loss=0.033, over 1387786.19 frames.], batch size: 16, lr: 3.14e-04
2022-04-30 00:00:44,930 INFO [train.py:763] (5/8) Epoch 24, batch 750, loss[loss=0.1492, simple_loss=0.2507, pruned_loss=0.02383, over 7241.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03309, over 1398955.14 frames.], batch size: 20, lr: 3.14e-04
2022-04-30 00:01:50,612 INFO [train.py:763] (5/8) Epoch 24, batch 800, loss[loss=0.2016, simple_loss=0.2959, pruned_loss=0.05364, over 7416.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2655, pruned_loss=0.03312, over 1406358.59 frames.], batch size: 21, lr: 3.14e-04
2022-04-30 00:02:56,133 INFO [train.py:763] (5/8) Epoch 24, batch 850, loss[loss=0.1596, simple_loss=0.2635, pruned_loss=0.02781, over 7324.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2649, pruned_loss=0.03288, over 1407981.26 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:04:01,373 INFO [train.py:763] (5/8) Epoch 24, batch 900, loss[loss=0.1811, simple_loss=0.28, pruned_loss=0.04106, over 7278.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2661, pruned_loss=0.03347, over 1410512.64 frames.], batch size: 25, lr: 3.13e-04
2022-04-30 00:05:07,036 INFO [train.py:763] (5/8) Epoch 24, batch 950, loss[loss=0.1677, simple_loss=0.2631, pruned_loss=0.03612, over 4831.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2648, pruned_loss=0.03312, over 1405036.29 frames.], batch size: 52, lr: 3.13e-04
2022-04-30 00:06:12,847 INFO [train.py:763] (5/8) Epoch 24, batch 1000, loss[loss=0.202, simple_loss=0.3045, pruned_loss=0.0498, over 7416.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03307, over 1411793.66 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:07:18,490 INFO [train.py:763] (5/8) Epoch 24, batch 1050, loss[loss=0.1585, simple_loss=0.264, pruned_loss=0.02647, over 7333.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2662, pruned_loss=0.03335, over 1418545.48 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:08:23,989 INFO [train.py:763] (5/8) Epoch 24, batch 1100, loss[loss=0.1807, simple_loss=0.2868, pruned_loss=0.03735, over 7321.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2656, pruned_loss=0.03311, over 1421286.79 frames.], batch size: 22, lr: 3.13e-04
2022-04-30 00:09:29,780 INFO [train.py:763] (5/8) Epoch 24, batch 1150, loss[loss=0.1617, simple_loss=0.281, pruned_loss=0.02125, over 7207.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2651, pruned_loss=0.03291, over 1424164.77 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:10:35,404 INFO [train.py:763] (5/8) Epoch 24, batch 1200, loss[loss=0.1763, simple_loss=0.2788, pruned_loss=0.03684, over 7386.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03308, over 1423490.61 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:11:41,676 INFO [train.py:763] (5/8) Epoch 24, batch 1250, loss[loss=0.174, simple_loss=0.2781, pruned_loss=0.03489, over 7148.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03365, over 1421112.85 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:12:47,628 INFO [train.py:763] (5/8) Epoch 24, batch 1300, loss[loss=0.1514, simple_loss=0.2424, pruned_loss=0.03019, over 6797.00 frames.], tot_loss[loss=0.166, simple_loss=0.265, pruned_loss=0.03351, over 1420538.16 frames.], batch size: 15, lr: 3.13e-04
2022-04-30 00:13:53,408 INFO [train.py:763] (5/8) Epoch 24, batch 1350, loss[loss=0.1559, simple_loss=0.2637, pruned_loss=0.02402, over 6467.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2659, pruned_loss=0.0337, over 1420792.68 frames.], batch size: 38, lr: 3.13e-04
2022-04-30 00:14:58,838 INFO [train.py:763] (5/8) Epoch 24, batch 1400, loss[loss=0.1484, simple_loss=0.2366, pruned_loss=0.03011, over 7295.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2666, pruned_loss=0.03385, over 1425931.06 frames.], batch size: 17, lr: 3.13e-04
2022-04-30 00:16:04,331 INFO [train.py:763] (5/8) Epoch 24, batch 1450, loss[loss=0.1717, simple_loss=0.2814, pruned_loss=0.03099, over 7148.00 frames.], tot_loss[loss=0.167, simple_loss=0.2662, pruned_loss=0.0339, over 1422425.16 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:17:11,267 INFO [train.py:763] (5/8) Epoch 24, batch 1500, loss[loss=0.1729, simple_loss=0.2742, pruned_loss=0.03575, over 6719.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03354, over 1421525.55 frames.], batch size: 31, lr: 3.13e-04
2022-04-30 00:18:17,540 INFO [train.py:763] (5/8) Epoch 24, batch 1550, loss[loss=0.1604, simple_loss=0.2565, pruned_loss=0.03213, over 7281.00 frames.], tot_loss[loss=0.167, simple_loss=0.2665, pruned_loss=0.03376, over 1422026.30 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:19:23,715 INFO [train.py:763] (5/8) Epoch 24, batch 1600, loss[loss=0.1282, simple_loss=0.2252, pruned_loss=0.01561, over 6852.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2659, pruned_loss=0.03351, over 1421748.14 frames.], batch size: 15, lr: 3.12e-04
2022-04-30 00:20:29,917 INFO [train.py:763] (5/8) Epoch 24, batch 1650, loss[loss=0.1762, simple_loss=0.2852, pruned_loss=0.03358, over 7217.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03366, over 1422830.36 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:21:35,725 INFO [train.py:763] (5/8) Epoch 24, batch 1700, loss[loss=0.1959, simple_loss=0.2961, pruned_loss=0.04784, over 7388.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2659, pruned_loss=0.03399, over 1421015.39 frames.], batch size: 23, lr: 3.12e-04
2022-04-30 00:22:40,924 INFO [train.py:763] (5/8) Epoch 24, batch 1750, loss[loss=0.1642, simple_loss=0.2529, pruned_loss=0.03778, over 7122.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.03415, over 1423398.71 frames.], batch size: 17, lr: 3.12e-04
2022-04-30 00:23:47,089 INFO [train.py:763] (5/8) Epoch 24, batch 1800, loss[loss=0.1475, simple_loss=0.2427, pruned_loss=0.02613, over 6983.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03404, over 1422941.20 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:24:52,832 INFO [train.py:763] (5/8) Epoch 24, batch 1850, loss[loss=0.1181, simple_loss=0.2159, pruned_loss=0.01018, over 6799.00 frames.], tot_loss[loss=0.166, simple_loss=0.2648, pruned_loss=0.03362, over 1419590.74 frames.], batch size: 15, lr: 3.12e-04
2022-04-30 00:26:09,448 INFO [train.py:763] (5/8) Epoch 24, batch 1900, loss[loss=0.1713, simple_loss=0.2675, pruned_loss=0.03755, over 7294.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03363, over 1421493.21 frames.], batch size: 25, lr: 3.12e-04
2022-04-30 00:27:15,226 INFO [train.py:763] (5/8) Epoch 24, batch 1950, loss[loss=0.1513, simple_loss=0.2507, pruned_loss=0.02596, over 7257.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2656, pruned_loss=0.0337, over 1422971.30 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:28:21,031 INFO [train.py:763] (5/8) Epoch 24, batch 2000, loss[loss=0.1484, simple_loss=0.2442, pruned_loss=0.02632, over 7158.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03358, over 1423574.19 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:29:27,107 INFO [train.py:763] (5/8) Epoch 24, batch 2050, loss[loss=0.1809, simple_loss=0.2862, pruned_loss=0.03773, over 7319.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2643, pruned_loss=0.03315, over 1426540.49 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:30:32,486 INFO [train.py:763] (5/8) Epoch 24, batch 2100, loss[loss=0.1634, simple_loss=0.2606, pruned_loss=0.03311, over 7261.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2646, pruned_loss=0.03297, over 1423532.32 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:31:37,976 INFO [train.py:763] (5/8) Epoch 24, batch 2150, loss[loss=0.1562, simple_loss=0.2505, pruned_loss=0.03092, over 7419.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03353, over 1421399.98 frames.], batch size: 20, lr: 3.12e-04
2022-04-30 00:32:43,336 INFO [train.py:763] (5/8) Epoch 24, batch 2200, loss[loss=0.1539, simple_loss=0.2411, pruned_loss=0.0334, over 6777.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2645, pruned_loss=0.0332, over 1420615.51 frames.], batch size: 15, lr: 3.12e-04
2022-04-30 00:33:49,451 INFO [train.py:763] (5/8) Epoch 24, batch 2250, loss[loss=0.183, simple_loss=0.2734, pruned_loss=0.04627, over 7061.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2646, pruned_loss=0.03303, over 1417675.19 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:34:55,315 INFO [train.py:763] (5/8) Epoch 24, batch 2300, loss[loss=0.1613, simple_loss=0.2445, pruned_loss=0.03909, over 7219.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.03333, over 1419165.40 frames.], batch size: 16, lr: 3.11e-04
2022-04-30 00:36:01,138 INFO [train.py:763] (5/8) Epoch 24, batch 2350, loss[loss=0.1563, simple_loss=0.2607, pruned_loss=0.02592, over 7308.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2638, pruned_loss=0.03316, over 1419257.51 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:37:06,716 INFO [train.py:763] (5/8) Epoch 24, batch 2400, loss[loss=0.161, simple_loss=0.2556, pruned_loss=0.03319, over 7340.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2653, pruned_loss=0.03313, over 1423555.58 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:38:21,821 INFO [train.py:763] (5/8) Epoch 24, batch 2450, loss[loss=0.1742, simple_loss=0.2571, pruned_loss=0.04572, over 7131.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.03336, over 1422926.96 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:39:27,189 INFO [train.py:763] (5/8) Epoch 24, batch 2500, loss[loss=0.188, simple_loss=0.3009, pruned_loss=0.0375, over 7412.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2663, pruned_loss=0.03378, over 1422702.92 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:40:32,706 INFO [train.py:763] (5/8) Epoch 24, batch 2550, loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02861, over 7423.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2662, pruned_loss=0.03367, over 1423847.46 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:41:38,104 INFO [train.py:763] (5/8) Epoch 24, batch 2600, loss[loss=0.1437, simple_loss=0.235, pruned_loss=0.02618, over 7150.00 frames.], tot_loss[loss=0.167, simple_loss=0.2663, pruned_loss=0.03384, over 1420604.45 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:42:43,682 INFO [train.py:763] (5/8) Epoch 24, batch 2650, loss[loss=0.1641, simple_loss=0.2671, pruned_loss=0.0305, over 7195.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2665, pruned_loss=0.03354, over 1422524.82 frames.], batch size: 22, lr: 3.11e-04
2022-04-30 00:43:49,275 INFO [train.py:763] (5/8) Epoch 24, batch 2700, loss[loss=0.1607, simple_loss=0.259, pruned_loss=0.03122, over 7068.00 frames.], tot_loss[loss=0.1666, simple_loss=0.266, pruned_loss=0.03361, over 1424489.00 frames.], batch size: 18, lr: 3.11e-04
2022-04-30 00:44:54,693 INFO [train.py:763] (5/8) Epoch 24, batch 2750, loss[loss=0.1584, simple_loss=0.2754, pruned_loss=0.02069, over 7139.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2651, pruned_loss=0.03329, over 1419024.87 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:46:00,212 INFO [train.py:763] (5/8) Epoch 24, batch 2800, loss[loss=0.1694, simple_loss=0.2638, pruned_loss=0.03748, over 7261.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2653, pruned_loss=0.03319, over 1420239.25 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:47:22,979 INFO [train.py:763] (5/8) Epoch 24, batch 2850, loss[loss=0.1543, simple_loss=0.2545, pruned_loss=0.027, over 7439.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.033, over 1419291.56 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:48:28,457 INFO [train.py:763] (5/8) Epoch 24, batch 2900, loss[loss=0.1573, simple_loss=0.2588, pruned_loss=0.02789, over 7192.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2664, pruned_loss=0.0332, over 1419772.03 frames.], batch size: 23, lr: 3.11e-04
2022-04-30 00:49:52,266 INFO [train.py:763] (5/8) Epoch 24, batch 2950, loss[loss=0.1712, simple_loss=0.2687, pruned_loss=0.03682, over 7105.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2664, pruned_loss=0.03317, over 1424971.97 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:51:06,867 INFO [train.py:763] (5/8) Epoch 24, batch 3000, loss[loss=0.1542, simple_loss=0.2564, pruned_loss=0.02596, over 6703.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.03283, over 1427992.74 frames.], batch size: 31, lr: 3.10e-04
2022-04-30 00:51:06,868 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 00:51:22,143 INFO [train.py:792] (5/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
2022-04-30 00:52:37,065 INFO [train.py:763] (5/8) Epoch 24, batch 3050, loss[loss=0.1621, simple_loss=0.2609, pruned_loss=0.03168, over 7120.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03273, over 1427677.20 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 00:53:42,766 INFO [train.py:763] (5/8) Epoch 24, batch 3100, loss[loss=0.1375, simple_loss=0.2319, pruned_loss=0.02153, over 7223.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03268, over 1429406.17 frames.], batch size: 16, lr: 3.10e-04
2022-04-30 00:54:48,073 INFO [train.py:763] (5/8) Epoch 24, batch 3150, loss[loss=0.1486, simple_loss=0.2494, pruned_loss=0.02389, over 7258.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03291, over 1430613.91 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:55:53,502 INFO [train.py:763] (5/8) Epoch 24, batch 3200, loss[loss=0.2201, simple_loss=0.301, pruned_loss=0.06959, over 5026.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2637, pruned_loss=0.03308, over 1429303.90 frames.], batch size: 52, lr: 3.10e-04
2022-04-30 00:56:59,207 INFO [train.py:763] (5/8) Epoch 24, batch 3250, loss[loss=0.1944, simple_loss=0.2811, pruned_loss=0.05391, over 7233.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.0336, over 1427153.03 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 00:58:05,424 INFO [train.py:763] (5/8) Epoch 24, batch 3300, loss[loss=0.1519, simple_loss=0.2525, pruned_loss=0.02565, over 7160.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2645, pruned_loss=0.03325, over 1426169.19 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:59:11,087 INFO [train.py:763] (5/8) Epoch 24, batch 3350, loss[loss=0.1496, simple_loss=0.2543, pruned_loss=0.02242, over 7255.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03348, over 1423215.54 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 01:00:16,804 INFO [train.py:763] (5/8) Epoch 24, batch 3400, loss[loss=0.1411, simple_loss=0.232, pruned_loss=0.02513, over 7271.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2643, pruned_loss=0.03366, over 1424954.20 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:01:22,331 INFO [train.py:763] (5/8) Epoch 24, batch 3450, loss[loss=0.1677, simple_loss=0.2715, pruned_loss=0.03189, over 7216.00 frames.], tot_loss[loss=0.166, simple_loss=0.2645, pruned_loss=0.0337, over 1420437.44 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 01:02:27,614 INFO [train.py:763] (5/8) Epoch 24, batch 3500, loss[loss=0.1361, simple_loss=0.226, pruned_loss=0.02313, over 7141.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03401, over 1422393.25 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:03:33,200 INFO [train.py:763] (5/8) Epoch 24, batch 3550, loss[loss=0.1553, simple_loss=0.2583, pruned_loss=0.02611, over 7330.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.03383, over 1423484.77 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:04:38,399 INFO [train.py:763] (5/8) Epoch 24, batch 3600, loss[loss=0.1793, simple_loss=0.2815, pruned_loss=0.03857, over 7206.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2661, pruned_loss=0.03374, over 1422149.23 frames.], batch size: 23, lr: 3.10e-04
2022-04-30 01:05:45,319 INFO [train.py:763] (5/8) Epoch 24, batch 3650, loss[loss=0.1866, simple_loss=0.2889, pruned_loss=0.04213, over 6299.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03375, over 1418364.36 frames.], batch size: 38, lr: 3.10e-04
2022-04-30 01:06:51,864 INFO [train.py:763] (5/8) Epoch 24, batch 3700, loss[loss=0.1402, simple_loss=0.2432, pruned_loss=0.01863, over 7435.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03329, over 1421558.84 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:07:57,546 INFO [train.py:763] (5/8) Epoch 24, batch 3750, loss[loss=0.1852, simple_loss=0.2844, pruned_loss=0.04298, over 7387.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03358, over 1424209.82 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:09:02,955 INFO [train.py:763] (5/8) Epoch 24, batch 3800, loss[loss=0.2289, simple_loss=0.3124, pruned_loss=0.07269, over 4868.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.03364, over 1422862.21 frames.], batch size: 52, lr: 3.09e-04
2022-04-30 01:10:08,031 INFO [train.py:763] (5/8) Epoch 24, batch 3850, loss[loss=0.1659, simple_loss=0.2622, pruned_loss=0.03477, over 7276.00 frames.], tot_loss[loss=0.1664, simple_loss=0.265, pruned_loss=0.03388, over 1422174.79 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:11:13,751 INFO [train.py:763] (5/8) Epoch 24, batch 3900, loss[loss=0.1703, simple_loss=0.2551, pruned_loss=0.04272, over 7254.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2656, pruned_loss=0.03406, over 1421488.27 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:12:19,231 INFO [train.py:763] (5/8) Epoch 24, batch 3950, loss[loss=0.1463, simple_loss=0.2434, pruned_loss=0.0246, over 7428.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03395, over 1423538.53 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:13:24,353 INFO [train.py:763] (5/8) Epoch 24, batch 4000, loss[loss=0.1576, simple_loss=0.2594, pruned_loss=0.02789, over 7315.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03367, over 1422798.01 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:14:29,919 INFO [train.py:763] (5/8) Epoch 24, batch 4050, loss[loss=0.173, simple_loss=0.2744, pruned_loss=0.03576, over 7428.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2656, pruned_loss=0.03391, over 1421905.25 frames.], batch size: 20, lr: 3.09e-04
2022-04-30 01:15:36,784 INFO [train.py:763] (5/8) Epoch 24, batch 4100, loss[loss=0.1817, simple_loss=0.2882, pruned_loss=0.03763, over 6212.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03401, over 1421993.79 frames.], batch size: 37, lr: 3.09e-04
2022-04-30 01:16:43,486 INFO [train.py:763] (5/8) Epoch 24, batch 4150, loss[loss=0.174, simple_loss=0.2817, pruned_loss=0.03315, over 7223.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03416, over 1418320.57 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:17:50,171 INFO [train.py:763] (5/8) Epoch 24, batch 4200, loss[loss=0.1737, simple_loss=0.2759, pruned_loss=0.03569, over 7195.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2675, pruned_loss=0.0343, over 1419943.88 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:18:56,572 INFO [train.py:763] (5/8) Epoch 24, batch 4250, loss[loss=0.1515, simple_loss=0.2579, pruned_loss=0.02251, over 6558.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.03414, over 1414500.89 frames.], batch size: 38, lr: 3.09e-04
2022-04-30 01:20:02,374 INFO [train.py:763] (5/8) Epoch 24, batch 4300, loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03084, over 7160.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2658, pruned_loss=0.0342, over 1414417.30 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:21:09,414 INFO [train.py:763] (5/8) Epoch 24, batch 4350, loss[loss=0.1658, simple_loss=0.2645, pruned_loss=0.03353, over 7325.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2644, pruned_loss=0.03387, over 1415511.02 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:22:16,106 INFO [train.py:763] (5/8) Epoch 24, batch 4400, loss[loss=0.1924, simple_loss=0.3002, pruned_loss=0.04231, over 7327.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03352, over 1414393.31 frames.], batch size: 24, lr: 3.09e-04
2022-04-30 01:23:21,726 INFO [train.py:763] (5/8) Epoch 24, batch 4450, loss[loss=0.1711, simple_loss=0.2858, pruned_loss=0.02824, over 7294.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2664, pruned_loss=0.03372, over 1404960.37 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:24:28,209 INFO [train.py:763] (5/8) Epoch 24, batch 4500, loss[loss=0.1923, simple_loss=0.2879, pruned_loss=0.04832, over 5162.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2678, pruned_loss=0.03425, over 1387718.05 frames.], batch size: 53, lr: 3.08e-04
2022-04-30 01:25:32,953 INFO [train.py:763] (5/8) Epoch 24, batch 4550, loss[loss=0.1875, simple_loss=0.2853, pruned_loss=0.04484, over 5265.00 frames.], tot_loss[loss=0.17, simple_loss=0.2699, pruned_loss=0.03505, over 1351106.01 frames.], batch size: 54, lr: 3.08e-04
2022-04-30 01:26:52,292 INFO [train.py:763] (5/8) Epoch 25, batch 0, loss[loss=0.1879, simple_loss=0.2958, pruned_loss=0.04002, over 7226.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2958, pruned_loss=0.04002, over 7226.00 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:27:58,479 INFO [train.py:763] (5/8) Epoch 25, batch 50, loss[loss=0.175, simple_loss=0.28, pruned_loss=0.03498, over 7317.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03293, over 322726.17 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:29:03,633 INFO [train.py:763] (5/8) Epoch 25, batch 100, loss[loss=0.176, simple_loss=0.271, pruned_loss=0.04049, over 5211.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2672, pruned_loss=0.03355, over 567029.23 frames.], batch size: 52, lr: 3.02e-04
2022-04-30 01:30:08,886 INFO [train.py:763] (5/8) Epoch 25, batch 150, loss[loss=0.1502, simple_loss=0.2412, pruned_loss=0.02956, over 7282.00 frames.], tot_loss[loss=0.167, simple_loss=0.2669, pruned_loss=0.03357, over 760865.24 frames.], batch size: 17, lr: 3.02e-04
2022-04-30 01:31:14,498 INFO [train.py:763] (5/8) Epoch 25, batch 200, loss[loss=0.1902, simple_loss=0.2933, pruned_loss=0.04353, over 7374.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03372, over 907524.56 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:32:20,364 INFO [train.py:763] (5/8) Epoch 25, batch 250, loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.03768, over 7204.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2658, pruned_loss=0.03379, over 1020139.41 frames.], batch size: 22, lr: 3.02e-04
2022-04-30 01:33:26,241 INFO [train.py:763] (5/8) Epoch 25, batch 300, loss[loss=0.1619, simple_loss=0.266, pruned_loss=0.02893, over 7324.00 frames.], tot_loss[loss=0.166, simple_loss=0.2654, pruned_loss=0.03336, over 1106106.93 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:34:31,519 INFO [train.py:763] (5/8) Epoch 25, batch 350, loss[loss=0.159, simple_loss=0.2567, pruned_loss=0.03066, over 7165.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03273, over 1176073.86 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:35:36,793 INFO [train.py:763] (5/8) Epoch 25, batch 400, loss[loss=0.1619, simple_loss=0.2584, pruned_loss=0.03266, over 7415.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2654, pruned_loss=0.03319, over 1233990.88 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:36:42,363 INFO [train.py:763] (5/8) Epoch 25, batch 450, loss[loss=0.1779, simple_loss=0.2787, pruned_loss=0.03853, over 7420.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2649, pruned_loss=0.03275, over 1274269.29 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:37:47,504 INFO [train.py:763] (5/8) Epoch 25, batch 500, loss[loss=0.1979, simple_loss=0.3049, pruned_loss=0.04544, over 7385.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2655, pruned_loss=0.03297, over 1301358.61 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:38:52,812 INFO [train.py:763] (5/8) Epoch 25, batch 550, loss[loss=0.1775, simple_loss=0.278, pruned_loss=0.03847, over 7239.00 frames.], tot_loss[loss=0.165, simple_loss=0.2649, pruned_loss=0.03253, over 1327775.66 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:39:58,989 INFO [train.py:763] (5/8) Epoch 25, batch 600, loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03046, over 7032.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.03291, over 1346460.63 frames.], batch size: 28, lr: 3.02e-04
2022-04-30 01:41:04,683 INFO [train.py:763] (5/8) Epoch 25, batch 650, loss[loss=0.1638, simple_loss=0.2649, pruned_loss=0.03134, over 7337.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2641, pruned_loss=0.03327, over 1360668.07 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:42:10,718 INFO [train.py:763] (5/8) Epoch 25, batch 700, loss[loss=0.1754, simple_loss=0.278, pruned_loss=0.03646, over 7143.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03326, over 1374536.80 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:43:16,100 INFO [train.py:763] (5/8) Epoch 25, batch 750, loss[loss=0.1519, simple_loss=0.2571, pruned_loss=0.02329, over 7433.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2649, pruned_loss=0.03347, over 1389858.39 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:44:20,968 INFO [train.py:763] (5/8) Epoch 25, batch 800, loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.03028, over 6751.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2649, pruned_loss=0.03321, over 1395703.84 frames.], batch size: 31, lr: 3.01e-04
2022-04-30 01:45:26,327 INFO [train.py:763] (5/8) Epoch 25, batch 850, loss[loss=0.1549, simple_loss=0.266, pruned_loss=0.02189, over 7111.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2655, pruned_loss=0.0331, over 1406289.18 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:46:33,141 INFO [train.py:763] (5/8) Epoch 25, batch 900, loss[loss=0.153, simple_loss=0.2344, pruned_loss=0.03584, over 6805.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.03288, over 1406170.08 frames.], batch size: 15, lr: 3.01e-04
2022-04-30 01:47:40,195 INFO [train.py:763] (5/8) Epoch 25, batch 950, loss[loss=0.1436, simple_loss=0.2351, pruned_loss=0.02606, over 7255.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03274, over 1412496.71 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:48:46,811 INFO [train.py:763] (5/8) Epoch 25, batch 1000, loss[loss=0.1777, simple_loss=0.2827, pruned_loss=0.03636, over 7106.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03309, over 1411885.57 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:49:52,655 INFO [train.py:763] (5/8) Epoch 25, batch 1050, loss[loss=0.1959, simple_loss=0.297, pruned_loss=0.04745, over 5268.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2653, pruned_loss=0.03292, over 1412743.85 frames.], batch size: 52, lr: 3.01e-04
2022-04-30 01:50:59,152 INFO [train.py:763] (5/8) Epoch 25, batch 1100, loss[loss=0.1789, simple_loss=0.2793, pruned_loss=0.03927, over 7109.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03287, over 1414544.12 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:52:04,516 INFO [train.py:763] (5/8) Epoch 25, batch 1150, loss[loss=0.1639, simple_loss=0.2681, pruned_loss=0.02986, over 7373.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03291, over 1418652.73 frames.], batch size: 23, lr: 3.01e-04
2022-04-30 01:53:10,911 INFO [train.py:763] (5/8) Epoch 25, batch 1200, loss[loss=0.1502, simple_loss=0.2473, pruned_loss=0.02653, over 7123.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2652, pruned_loss=0.03323, over 1422330.86 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:54:16,909 INFO [train.py:763] (5/8) Epoch 25, batch 1250, loss[loss=0.1472, simple_loss=0.2588, pruned_loss=0.01779, over 7327.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2661, pruned_loss=0.03345, over 1424669.99 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:55:23,802 INFO [train.py:763] (5/8) Epoch 25, batch 1300, loss[loss=0.1498, simple_loss=0.2558, pruned_loss=0.02194, over 7431.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2664, pruned_loss=0.03351, over 1427853.89 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:56:30,378 INFO [train.py:763] (5/8) Epoch 25, batch 1350, loss[loss=0.1552, simple_loss=0.2629, pruned_loss=0.02371, over 7330.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2672, pruned_loss=0.03383, over 1428023.59 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:57:36,867 INFO [train.py:763] (5/8) Epoch 25, batch 1400, loss[loss=0.1745, simple_loss=0.2757, pruned_loss=0.03664, over 7335.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2677, pruned_loss=0.03433, over 1428204.70 frames.], batch size: 22, lr: 3.01e-04
2022-04-30 01:58:42,273 INFO [train.py:763] (5/8) Epoch 25, batch 1450, loss[loss=0.1441, simple_loss=0.2419, pruned_loss=0.02313, over 7011.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2673, pruned_loss=0.03408, over 1429762.90 frames.], batch size: 16, lr: 3.01e-04
2022-04-30 01:59:49,364 INFO [train.py:763] (5/8) Epoch 25, batch 1500, loss[loss=0.1837, simple_loss=0.282, pruned_loss=0.04271, over 7224.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2666, pruned_loss=0.034, over 1428554.32 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:00:55,049 INFO [train.py:763] (5/8) Epoch 25, batch 1550, loss[loss=0.1434, simple_loss=0.2433, pruned_loss=0.0218, over 7132.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03384, over 1427369.76 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:02:00,075 INFO [train.py:763] (5/8) Epoch 25, batch 1600, loss[loss=0.1722, simple_loss=0.2887, pruned_loss=0.02782, over 7148.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2674, pruned_loss=0.03412, over 1424000.15 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:03:05,636 INFO [train.py:763] (5/8) Epoch 25, batch 1650, loss[loss=0.1626, simple_loss=0.281, pruned_loss=0.02207, over 7085.00 frames.], tot_loss[loss=0.167, simple_loss=0.2662, pruned_loss=0.03383, over 1425220.44 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:04:10,613 INFO [train.py:763] (5/8) Epoch 25, batch 1700, loss[loss=0.1602, simple_loss=0.2534, pruned_loss=0.03349, over 7319.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03338, over 1425328.93 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:05:15,844 INFO [train.py:763] (5/8) Epoch 25, batch 1750, loss[loss=0.1481, simple_loss=0.2422, pruned_loss=0.02697, over 7154.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2651, pruned_loss=0.03307, over 1424466.84 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:06:21,044 INFO [train.py:763] (5/8) Epoch 25, batch 1800, loss[loss=0.1937, simple_loss=0.3003, pruned_loss=0.04353, over 7139.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2653, pruned_loss=0.03351, over 1419947.59 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:07:26,300 INFO [train.py:763] (5/8) Epoch 25, batch 1850, loss[loss=0.178, simple_loss=0.2756, pruned_loss=0.04024, over 7421.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03325, over 1420942.87 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:08:31,449 INFO [train.py:763] (5/8) Epoch 25, batch 1900, loss[loss=0.1275, simple_loss=0.2187, pruned_loss=0.01814, over 7140.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.0329, over 1422347.30 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:09:36,781 INFO [train.py:763] (5/8) Epoch 25, batch 1950, loss[loss=0.2183, simple_loss=0.3112, pruned_loss=0.06273, over 4860.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03289, over 1420862.40 frames.], batch size: 52, lr: 3.00e-04
2022-04-30 02:10:42,031 INFO [train.py:763] (5/8) Epoch 25, batch 2000, loss[loss=0.1726, simple_loss=0.2711, pruned_loss=0.03711, over 7162.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2645, pruned_loss=0.03316, over 1416686.62 frames.], batch size: 19, lr: 3.00e-04
2022-04-30 02:11:47,912 INFO [train.py:763] (5/8) Epoch 25, batch 2050, loss[loss=0.1733, simple_loss=0.2705, pruned_loss=0.03809, over 7333.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03308, over 1418520.66 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:12:54,275 INFO [train.py:763] (5/8) Epoch 25, batch 2100, loss[loss=0.1873, simple_loss=0.2902, pruned_loss=0.04223, over 7205.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2658, pruned_loss=0.03335, over 1417263.37 frames.], batch size: 22, lr: 3.00e-04
2022-04-30 02:13:59,526 INFO [train.py:763] (5/8) Epoch 25, batch 2150, loss[loss=0.1514, simple_loss=0.2462, pruned_loss=0.02826, over 7173.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2663, pruned_loss=0.03316, over 1419742.29 frames.], batch size: 18, lr: 3.00e-04
2022-04-30 02:15:05,487 INFO [train.py:763] (5/8) Epoch 25, batch 2200, loss[loss=0.1752, simple_loss=0.2757, pruned_loss=0.03734, over 7058.00 frames.], tot_loss[loss=0.166, simple_loss=0.2661, pruned_loss=0.03292, over 1422783.77 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:16:11,388 INFO [train.py:763] (5/8) Epoch 25, batch 2250, loss[loss=0.1682, simple_loss=0.268, pruned_loss=0.03417, over 7362.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2653, pruned_loss=0.03297, over 1424965.62 frames.], batch size: 23, lr: 3.00e-04
2022-04-30 02:17:16,597 INFO [train.py:763] (5/8) Epoch 25, batch 2300, loss[loss=0.1719, simple_loss=0.2704, pruned_loss=0.03671, over 7069.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2664, pruned_loss=0.03348, over 1424882.96 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:18:23,385 INFO [train.py:763] (5/8) Epoch 25, batch 2350, loss[loss=0.1502, simple_loss=0.2479, pruned_loss=0.02627, over 7259.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03332, over 1425700.29 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:19:30,582 INFO [train.py:763] (5/8) Epoch 25, batch 2400, loss[loss=0.1924, simple_loss=0.2991, pruned_loss=0.04291, over 7381.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2649, pruned_loss=0.03335, over 1422755.22 frames.], batch size: 23, lr: 2.99e-04
2022-04-30 02:20:36,000 INFO [train.py:763] (5/8) Epoch 25, batch 2450, loss[loss=0.1848, simple_loss=0.2905, pruned_loss=0.0396, over 6728.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03353, over 1421491.33 frames.], batch size: 31, lr: 2.99e-04
2022-04-30 02:21:42,826 INFO [train.py:763] (5/8) Epoch 25, batch 2500, loss[loss=0.1671, simple_loss=0.2528, pruned_loss=0.04068, over 7347.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03311, over 1423303.40 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:22:48,790 INFO [train.py:763] (5/8) Epoch 25, batch 2550, loss[loss=0.1781, simple_loss=0.2653, pruned_loss=0.04552, over 7401.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03352, over 1425974.36 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:23:56,380 INFO [train.py:763] (5/8) Epoch 25, batch 2600, loss[loss=0.1616, simple_loss=0.2668, pruned_loss=0.02817, over 7158.00 frames.], tot_loss[loss=0.1662, simple_loss=0.265, pruned_loss=0.03369, over 1424761.22 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:25:02,543 INFO [train.py:763] (5/8) Epoch 25, batch 2650, loss[loss=0.1778, simple_loss=0.2691, pruned_loss=0.04326, over 7071.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2658, pruned_loss=0.03376, over 1420986.53 frames.], batch size: 28, lr: 2.99e-04
2022-04-30 02:26:07,760 INFO [train.py:763] (5/8) Epoch 25, batch 2700, loss[loss=0.1579, simple_loss=0.2663, pruned_loss=0.02472, over 7266.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2663, pruned_loss=0.03393, over 1422157.12 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:27:12,943 INFO [train.py:763] (5/8) Epoch 25, batch 2750, loss[loss=0.2028, simple_loss=0.3085, pruned_loss=0.04849, over 7276.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.0345, over 1415514.29 frames.], batch size: 25, lr: 2.99e-04
2022-04-30 02:28:19,412 INFO [train.py:763] (5/8) Epoch 25, batch 2800, loss[loss=0.1568, simple_loss=0.2538, pruned_loss=0.02992, over 7258.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03407, over 1417323.79 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:29:24,937 INFO [train.py:763] (5/8) Epoch 25, batch 2850, loss[loss=0.1861, simple_loss=0.2856, pruned_loss=0.04326, over 7402.00 frames.], tot_loss[loss=0.1662, simple_loss=0.265, pruned_loss=0.03364, over 1412458.98 frames.], batch size: 21, lr: 2.99e-04
2022-04-30 02:30:30,623 INFO [train.py:763] (5/8) Epoch 25, batch 2900, loss[loss=0.1587, simple_loss=0.2645, pruned_loss=0.02645, over 7143.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.0333, over 1417906.70 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:31:35,887 INFO [train.py:763] (5/8) Epoch 25, batch 2950, loss[loss=0.149, simple_loss=0.2528, pruned_loss=0.02259, over 7330.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03358, over 1417680.79 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:32:41,165 INFO [train.py:763] (5/8) Epoch 25, batch 3000, loss[loss=0.1441, simple_loss=0.2483, pruned_loss=0.01999, over 6337.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2662, pruned_loss=0.03332, over 1422056.54 frames.], batch size: 37, lr: 2.99e-04
2022-04-30 02:32:41,166 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 02:32:56,273 INFO [train.py:792] (5/8) Epoch 25, validation: loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 698248.00 frames.
2022-04-30 02:34:02,119 INFO [train.py:763] (5/8) Epoch 25, batch 3050, loss[loss=0.1588, simple_loss=0.2721, pruned_loss=0.02276, over 7338.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2672, pruned_loss=0.03362, over 1421333.73 frames.], batch size: 22, lr: 2.99e-04
2022-04-30 02:35:09,313 INFO [train.py:763] (5/8) Epoch 25, batch 3100, loss[loss=0.1641, simple_loss=0.2518, pruned_loss=0.03817, over 7262.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2667, pruned_loss=0.03357, over 1418865.00 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:36:16,403 INFO [train.py:763] (5/8) Epoch 25, batch 3150, loss[loss=0.1411, simple_loss=0.241, pruned_loss=0.02061, over 7131.00 frames.], tot_loss[loss=0.166, simple_loss=0.2657, pruned_loss=0.0331, over 1417488.95 frames.], batch size: 17, lr: 2.98e-04
2022-04-30 02:37:22,261 INFO [train.py:763] (5/8) Epoch 25, batch 3200, loss[loss=0.1605, simple_loss=0.2514, pruned_loss=0.03481, over 7157.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2657, pruned_loss=0.03324, over 1420997.19 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:38:29,215 INFO [train.py:763] (5/8) Epoch 25, batch 3250, loss[loss=0.1572, simple_loss=0.25, pruned_loss=0.03224, over 7277.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03306, over 1424009.31 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:39:35,760 INFO [train.py:763] (5/8) Epoch 25, batch 3300, loss[loss=0.154, simple_loss=0.2589, pruned_loss=0.02454, over 7168.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2646, pruned_loss=0.03311, over 1417018.34 frames.], batch size: 26, lr: 2.98e-04
2022-04-30 02:40:42,710 INFO [train.py:763] (5/8) Epoch 25, batch 3350, loss[loss=0.184, simple_loss=0.2887, pruned_loss=0.03963, over 7312.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.03283, over 1413959.59 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:41:49,874 INFO [train.py:763] (5/8) Epoch 25, batch 3400, loss[loss=0.1493, simple_loss=0.2542, pruned_loss=0.02221, over 6379.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2636, pruned_loss=0.03292, over 1418772.68 frames.], batch size: 38, lr: 2.98e-04
2022-04-30 02:42:55,396 INFO [train.py:763] (5/8) Epoch 25, batch 3450, loss[loss=0.1597, simple_loss=0.2551, pruned_loss=0.03211, over 7159.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2641, pruned_loss=0.03315, over 1418977.27 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:44:00,606 INFO [train.py:763] (5/8) Epoch 25, batch 3500, loss[loss=0.1903, simple_loss=0.2858, pruned_loss=0.04741, over 7386.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.03308, over 1418433.46 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:45:06,563 INFO [train.py:763] (5/8) Epoch 25, batch 3550, loss[loss=0.1681, simple_loss=0.2758, pruned_loss=0.03026, over 7413.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03276, over 1421058.75 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:46:12,320 INFO [train.py:763] (5/8) Epoch 25, batch 3600, loss[loss=0.1723, simple_loss=0.2714, pruned_loss=0.03662, over 7183.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2635, pruned_loss=0.03306, over 1425988.51 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:47:18,091 INFO [train.py:763] (5/8) Epoch 25, batch 3650, loss[loss=0.1253, simple_loss=0.2218, pruned_loss=0.01439, over 7258.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2634, pruned_loss=0.03296, over 1427560.36 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:48:25,758 INFO [train.py:763] (5/8) Epoch 25, batch 3700, loss[loss=0.1567, simple_loss=0.2467, pruned_loss=0.03337, over 7056.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2633, pruned_loss=0.03301, over 1424190.18 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:49:32,861 INFO [train.py:763] (5/8) Epoch 25, batch 3750, loss[loss=0.1632, simple_loss=0.2614, pruned_loss=0.03244, over 7158.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2639, pruned_loss=0.03346, over 1422485.93 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:50:38,249 INFO [train.py:763] (5/8) Epoch 25, batch 3800, loss[loss=0.1744, simple_loss=0.2774, pruned_loss=0.03569, over 6321.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03332, over 1421145.34 frames.], batch size: 38, lr: 2.98e-04
2022-04-30 02:51:43,566 INFO [train.py:763] (5/8) Epoch 25, batch 3850, loss[loss=0.1787, simple_loss=0.2748, pruned_loss=0.04134, over 7144.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2647, pruned_loss=0.03348, over 1418429.83 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:52:57,814 INFO [train.py:763] (5/8) Epoch 25, batch 3900, loss[loss=0.1322, simple_loss=0.2297, pruned_loss=0.01737, over 7412.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2648, pruned_loss=0.03309, over 1420640.09 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 02:54:03,678 INFO [train.py:763] (5/8) Epoch 25, batch 3950, loss[loss=0.172, simple_loss=0.2855, pruned_loss=0.02924, over 7228.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03349, over 1425135.32 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:55:09,641 INFO [train.py:763] (5/8) Epoch 25, batch 4000, loss[loss=0.1518, simple_loss=0.2529, pruned_loss=0.02538, over 7442.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2642, pruned_loss=0.03324, over 1418292.44 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:56:14,890 INFO [train.py:763] (5/8) Epoch 25, batch 4050, loss[loss=0.1759, simple_loss=0.2784, pruned_loss=0.0367, over 7419.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2649, pruned_loss=0.03342, over 1419172.06 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:57:21,071 INFO [train.py:763] (5/8) Epoch 25, batch 4100, loss[loss=0.153, simple_loss=0.2504, pruned_loss=0.02778, over 7407.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03363, over 1417746.87 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:58:26,419 INFO [train.py:763] (5/8) Epoch 25, batch 4150, loss[loss=0.1514, simple_loss=0.2516, pruned_loss=0.02561, over 7258.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03356, over 1422732.19 frames.], batch size: 19, lr: 2.97e-04
2022-04-30 02:59:32,222 INFO [train.py:763] (5/8) Epoch 25, batch 4200, loss[loss=0.1686, simple_loss=0.2715, pruned_loss=0.03285, over 7004.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03399, over 1419593.16 frames.], batch size: 28, lr: 2.97e-04
2022-04-30 03:00:37,743 INFO [train.py:763] (5/8) Epoch 25, batch 4250, loss[loss=0.1384, simple_loss=0.2317, pruned_loss=0.02258, over 7161.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03398, over 1419213.51 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:01:43,172 INFO [train.py:763] (5/8) Epoch 25, batch 4300, loss[loss=0.175, simple_loss=0.2713, pruned_loss=0.03936, over 7140.00 frames.], tot_loss[loss=0.1671, simple_loss=0.266, pruned_loss=0.03408, over 1422392.30 frames.], batch size: 26, lr: 2.97e-04
2022-04-30 03:03:06,202 INFO [train.py:763] (5/8) Epoch 25, batch 4350, loss[loss=0.1878, simple_loss=0.2813, pruned_loss=0.04716, over 7217.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03416, over 1415664.57 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:04:20,104 INFO [train.py:763] (5/8) Epoch 25, batch 4400, loss[loss=0.1526, simple_loss=0.2448, pruned_loss=0.03017, over 7065.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2663, pruned_loss=0.03373, over 1415161.70 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:05:34,213 INFO [train.py:763] (5/8) Epoch 25, batch 4450, loss[loss=0.183, simple_loss=0.289, pruned_loss=0.0385, over 7278.00 frames.], tot_loss[loss=0.1665, simple_loss=0.266, pruned_loss=0.0335, over 1414698.20 frames.], batch size: 24, lr: 2.97e-04
2022-04-30 03:06:39,195 INFO [train.py:763] (5/8) Epoch 25, batch 4500, loss[loss=0.1553, simple_loss=0.2588, pruned_loss=0.02591, over 7328.00 frames.], tot_loss[loss=0.167, simple_loss=0.2662, pruned_loss=0.0339, over 1398748.29 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:08:11,353 INFO [train.py:763] (5/8) Epoch 25, batch 4550, loss[loss=0.192, simple_loss=0.2917, pruned_loss=0.04615, over 5162.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2662, pruned_loss=0.03416, over 1390142.69 frames.], batch size: 52, lr: 2.97e-04
2022-04-30 03:09:39,582 INFO [train.py:763] (5/8) Epoch 26, batch 0, loss[loss=0.1813, simple_loss=0.2798, pruned_loss=0.04137, over 7171.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2798, pruned_loss=0.04137, over 7171.00 frames.], batch size: 18, lr: 2.91e-04
2022-04-30 03:10:45,456 INFO [train.py:763] (5/8) Epoch 26, batch 50, loss[loss=0.1598, simple_loss=0.2502, pruned_loss=0.03477, over 7285.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2635, pruned_loss=0.03334, over 319059.38 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:11:50,718 INFO [train.py:763] (5/8) Epoch 26, batch 100, loss[loss=0.1445, simple_loss=0.2386, pruned_loss=0.02521, over 7292.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2613, pruned_loss=0.03226, over 563358.21 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:12:56,056 INFO [train.py:763] (5/8) Epoch 26, batch 150, loss[loss=0.1835, simple_loss=0.276, pruned_loss=0.0455, over 6434.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.0326, over 751269.41 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:14:01,294 INFO [train.py:763] (5/8) Epoch 26, batch 200, loss[loss=0.1887, simple_loss=0.2872, pruned_loss=0.0451, over 7174.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03284, over 894352.90 frames.], batch size: 26, lr: 2.91e-04
2022-04-30 03:15:07,049 INFO [train.py:763] (5/8) Epoch 26, batch 250, loss[loss=0.1652, simple_loss=0.2593, pruned_loss=0.0356, over 6414.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03333, over 1006147.86 frames.], batch size: 38, lr: 2.91e-04
2022-04-30 03:16:13,124 INFO [train.py:763] (5/8) Epoch 26, batch 300, loss[loss=0.1609, simple_loss=0.2681, pruned_loss=0.0268, over 6166.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03332, over 1099954.58 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:17:18,449 INFO [train.py:763] (5/8) Epoch 26, batch 350, loss[loss=0.165, simple_loss=0.2774, pruned_loss=0.0263, over 6788.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2645, pruned_loss=0.03306, over 1167820.43 frames.], batch size: 31, lr: 2.91e-04
2022-04-30 03:18:23,751 INFO [train.py:763] (5/8) Epoch 26, batch 400, loss[loss=0.1683, simple_loss=0.2804, pruned_loss=0.02812, over 7150.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03275, over 1227807.65 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:19:29,479 INFO [train.py:763] (5/8) Epoch 26, batch 450, loss[loss=0.149, simple_loss=0.2417, pruned_loss=0.0282, over 7233.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03257, over 1275353.57 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:20:34,848 INFO [train.py:763] (5/8) Epoch 26, batch 500, loss[loss=0.2271, simple_loss=0.2975, pruned_loss=0.0784, over 5080.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03229, over 1306869.44 frames.], batch size: 52, lr: 2.91e-04
2022-04-30 03:21:40,171 INFO [train.py:763] (5/8) Epoch 26, batch 550, loss[loss=0.1795, simple_loss=0.2833, pruned_loss=0.03788, over 7214.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03261, over 1332467.34 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:22:45,582 INFO [train.py:763] (5/8) Epoch 26, batch 600, loss[loss=0.1441, simple_loss=0.2468, pruned_loss=0.02073, over 7264.00 frames.], tot_loss[loss=0.1647, simple_loss=0.264, pruned_loss=0.03273, over 1355101.62 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:23:51,111 INFO [train.py:763] (5/8) Epoch 26, batch 650, loss[loss=0.162, simple_loss=0.2539, pruned_loss=0.03504, over 7290.00 frames.], tot_loss[loss=0.1639, simple_loss=0.263, pruned_loss=0.03241, over 1371869.04 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:24:56,239 INFO [train.py:763] (5/8) Epoch 26, batch 700, loss[loss=0.1673, simple_loss=0.2773, pruned_loss=0.02863, over 7442.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03245, over 1381352.59 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:26:12,132 INFO [train.py:763] (5/8) Epoch 26, batch 750, loss[loss=0.1717, simple_loss=0.2714, pruned_loss=0.03602, over 7145.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2642, pruned_loss=0.03221, over 1389851.17 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:27:17,955 INFO [train.py:763] (5/8) Epoch 26, batch 800, loss[loss=0.1493, simple_loss=0.2533, pruned_loss=0.02266, over 7223.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2648, pruned_loss=0.0325, over 1395654.93 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:28:23,827 INFO [train.py:763] (5/8) Epoch 26, batch 850, loss[loss=0.172, simple_loss=0.2706, pruned_loss=0.03673, over 4726.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2644, pruned_loss=0.03251, over 1397565.99 frames.], batch size: 52, lr: 2.90e-04
2022-04-30 03:29:29,382 INFO [train.py:763] (5/8) Epoch 26, batch 900, loss[loss=0.1358, simple_loss=0.2322, pruned_loss=0.0197, over 7400.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03227, over 1406540.94 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:30:35,258 INFO [train.py:763] (5/8) Epoch 26, batch 950, loss[loss=0.153, simple_loss=0.2388, pruned_loss=0.03357, over 7236.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.03263, over 1408806.12 frames.], batch size: 16, lr: 2.90e-04
2022-04-30 03:31:40,722 INFO [train.py:763] (5/8) Epoch 26, batch 1000, loss[loss=0.1667, simple_loss=0.2717, pruned_loss=0.0308, over 7302.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03303, over 1411823.59 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:32:46,142 INFO [train.py:763] (5/8) Epoch 26, batch 1050, loss[loss=0.1846, simple_loss=0.2883, pruned_loss=0.04048, over 7201.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03287, over 1418255.26 frames.], batch size: 23, lr: 2.90e-04
2022-04-30 03:33:51,502 INFO [train.py:763] (5/8) Epoch 26, batch 1100, loss[loss=0.2099, simple_loss=0.3079, pruned_loss=0.05601, over 7210.00 frames.], tot_loss[loss=0.165, simple_loss=0.2645, pruned_loss=0.03278, over 1421875.25 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:34:56,897 INFO [train.py:763] (5/8) Epoch 26, batch 1150, loss[loss=0.1448, simple_loss=0.239, pruned_loss=0.02534, over 7153.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.0326, over 1422855.52 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:36:02,475 INFO [train.py:763] (5/8) Epoch 26, batch 1200, loss[loss=0.1648, simple_loss=0.2662, pruned_loss=0.03168, over 7271.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03244, over 1426639.81 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:37:08,331 INFO [train.py:763] (5/8) Epoch 26, batch 1250, loss[loss=0.1842, simple_loss=0.2865, pruned_loss=0.04097, over 6428.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03238, over 1427103.95 frames.], batch size: 38, lr: 2.90e-04
2022-04-30 03:38:14,033 INFO [train.py:763] (5/8) Epoch 26, batch 1300, loss[loss=0.166, simple_loss=0.2634, pruned_loss=0.03433, over 7282.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03273, over 1423787.72 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:39:20,375 INFO [train.py:763] (5/8) Epoch 26, batch 1350, loss[loss=0.1572, simple_loss=0.2534, pruned_loss=0.03052, over 7426.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2625, pruned_loss=0.03256, over 1427157.15 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:40:25,493 INFO [train.py:763] (5/8) Epoch 26, batch 1400, loss[loss=0.1653, simple_loss=0.2685, pruned_loss=0.03101, over 7199.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2627, pruned_loss=0.03259, over 1420435.29 frames.], batch size: 23, lr: 2.89e-04
2022-04-30 03:41:30,978 INFO [train.py:763] (5/8) Epoch 26, batch 1450, loss[loss=0.1484, simple_loss=0.244, pruned_loss=0.02646, over 7282.00 frames.], tot_loss[loss=0.1643, simple_loss=0.263, pruned_loss=0.03284, over 1422537.63 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:42:36,431 INFO [train.py:763] (5/8) Epoch 26, batch 1500, loss[loss=0.1952, simple_loss=0.2957, pruned_loss=0.04734, over 4966.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2631, pruned_loss=0.03282, over 1418545.12 frames.], batch size: 52, lr: 2.89e-04
2022-04-30 03:43:42,575 INFO [train.py:763] (5/8) Epoch 26, batch 1550, loss[loss=0.1723, simple_loss=0.277, pruned_loss=0.03377, over 7105.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03268, over 1421751.12 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:44:49,282 INFO [train.py:763] (5/8) Epoch 26, batch 1600, loss[loss=0.1437, simple_loss=0.2485, pruned_loss=0.01946, over 7262.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2632, pruned_loss=0.03286, over 1425582.93 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:45:54,879 INFO [train.py:763] (5/8) Epoch 26, batch 1650, loss[loss=0.1676, simple_loss=0.282, pruned_loss=0.02664, over 7123.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2629, pruned_loss=0.03246, over 1429175.71 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:47:00,384 INFO [train.py:763] (5/8) Epoch 26, batch 1700, loss[loss=0.1771, simple_loss=0.2766, pruned_loss=0.03883, over 7347.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2625, pruned_loss=0.03221, over 1430458.22 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:48:06,021 INFO [train.py:763] (5/8) Epoch 26, batch 1750, loss[loss=0.189, simple_loss=0.2825, pruned_loss=0.0478, over 7203.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.0325, over 1431132.48 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:49:13,276 INFO [train.py:763] (5/8) Epoch 26, batch 1800, loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.02998, over 7108.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2627, pruned_loss=0.03225, over 1428784.94 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:50:19,938 INFO [train.py:763] (5/8) Epoch 26, batch 1850, loss[loss=0.1918, simple_loss=0.2866, pruned_loss=0.0485, over 4710.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.03246, over 1428580.74 frames.], batch size: 53, lr: 2.89e-04
2022-04-30 03:51:25,631 INFO [train.py:763] (5/8) Epoch 26, batch 1900, loss[loss=0.1547, simple_loss=0.2576, pruned_loss=0.02587, over 7349.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2626, pruned_loss=0.03227, over 1427701.30 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:52:30,903 INFO [train.py:763] (5/8) Epoch 26, batch 1950, loss[loss=0.1954, simple_loss=0.3014, pruned_loss=0.04468, over 6459.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2634, pruned_loss=0.03291, over 1424655.61 frames.], batch size: 37, lr: 2.89e-04
2022-04-30 03:53:36,223 INFO [train.py:763] (5/8) Epoch 26, batch 2000, loss[loss=0.1627, simple_loss=0.2689, pruned_loss=0.02819, over 6737.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2631, pruned_loss=0.0328, over 1422731.02 frames.], batch size: 31, lr: 2.89e-04
2022-04-30 03:54:41,495 INFO [train.py:763] (5/8) Epoch 26, batch 2050, loss[loss=0.1681, simple_loss=0.2785, pruned_loss=0.02888, over 7225.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2642, pruned_loss=0.03296, over 1426332.09 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:55:48,146 INFO [train.py:763] (5/8) Epoch 26, batch 2100, loss[loss=0.1655, simple_loss=0.2713, pruned_loss=0.02991, over 7212.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2644, pruned_loss=0.03336, over 1424545.38 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:56:54,357 INFO [train.py:763] (5/8) Epoch 26, batch 2150, loss[loss=0.1711, simple_loss=0.268, pruned_loss=0.03709, over 7322.00 frames.], tot_loss[loss=0.166, simple_loss=0.2653, pruned_loss=0.03337, over 1428173.68 frames.], batch size: 25, lr: 2.89e-04
2022-04-30 03:57:59,849 INFO [train.py:763] (5/8) Epoch 26, batch 2200, loss[loss=0.1565, simple_loss=0.2553, pruned_loss=0.02888, over 7244.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03327, over 1426722.84 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 03:59:06,005 INFO [train.py:763] (5/8) Epoch 26, batch 2250, loss[loss=0.1537, simple_loss=0.2371, pruned_loss=0.03508, over 7011.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.0329, over 1431648.25 frames.], batch size: 16, lr: 2.88e-04
2022-04-30 04:00:11,175 INFO [train.py:763] (5/8) Epoch 26, batch 2300, loss[loss=0.1504, simple_loss=0.2398, pruned_loss=0.03047, over 7143.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2648, pruned_loss=0.03308, over 1433038.12 frames.], batch size: 17, lr: 2.88e-04
2022-04-30 04:01:17,209 INFO [train.py:763] (5/8) Epoch 26, batch 2350, loss[loss=0.1777, simple_loss=0.2805, pruned_loss=0.03749, over 7143.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2656, pruned_loss=0.03315, over 1431605.12 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:02:24,610 INFO [train.py:763] (5/8) Epoch 26, batch 2400, loss[loss=0.173, simple_loss=0.2823, pruned_loss=0.03189, over 7291.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2657, pruned_loss=0.03269, over 1432820.45 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:03:31,277 INFO [train.py:763] (5/8) Epoch 26, batch 2450, loss[loss=0.1598, simple_loss=0.2589, pruned_loss=0.0304, over 7237.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2651, pruned_loss=0.03225, over 1435450.91 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:04:36,625 INFO [train.py:763] (5/8) Epoch 26, batch 2500, loss[loss=0.1615, simple_loss=0.2719, pruned_loss=0.02551, over 7210.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2644, pruned_loss=0.03228, over 1436770.56 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:05:41,770 INFO [train.py:763] (5/8) Epoch 26, batch 2550, loss[loss=0.1798, simple_loss=0.274, pruned_loss=0.04286, over 6791.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2637, pruned_loss=0.03181, over 1433956.69 frames.], batch size: 31, lr: 2.88e-04
2022-04-30 04:06:47,203 INFO [train.py:763] (5/8) Epoch 26, batch 2600, loss[loss=0.1416, simple_loss=0.2304, pruned_loss=0.0264, over 6808.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.03223, over 1433968.84 frames.], batch size: 15, lr: 2.88e-04
2022-04-30 04:07:52,619 INFO [train.py:763] (5/8) Epoch 26, batch 2650, loss[loss=0.1846, simple_loss=0.2896, pruned_loss=0.03979, over 7300.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2648, pruned_loss=0.0327, over 1430415.66 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:08:58,044 INFO [train.py:763] (5/8) Epoch 26, batch 2700, loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03123, over 7335.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03279, over 1428248.77 frames.], batch size: 22, lr: 2.88e-04
2022-04-30 04:10:03,927 INFO [train.py:763] (5/8) Epoch 26, batch 2750, loss[loss=0.1565, simple_loss=0.2516, pruned_loss=0.03072, over 7168.00 frames.], tot_loss[loss=0.164, simple_loss=0.2639, pruned_loss=0.03206, over 1427272.61 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:11:09,748 INFO [train.py:763] (5/8) Epoch 26, batch 2800, loss[loss=0.1745, simple_loss=0.2682, pruned_loss=0.04038, over 7300.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.0321, over 1426752.38 frames.], batch size: 25, lr: 2.88e-04
2022-04-30 04:12:16,528 INFO [train.py:763] (5/8) Epoch 26, batch 2850, loss[loss=0.1369, simple_loss=0.2406, pruned_loss=0.01665, over 7255.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03229, over 1426272.47 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:13:21,810 INFO [train.py:763] (5/8) Epoch 26, batch 2900, loss[loss=0.1691, simple_loss=0.2654, pruned_loss=0.03638, over 7165.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.03232, over 1425485.14 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:14:26,961 INFO [train.py:763] (5/8) Epoch 26, batch 2950, loss[loss=0.1666, simple_loss=0.273, pruned_loss=0.03016, over 7126.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2654, pruned_loss=0.03301, over 1419571.41 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,486 INFO [train.py:763] (5/8) Epoch 26, batch 3000, loss[loss=0.1667, simple_loss=0.279, pruned_loss=0.02718, over 7421.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2655, pruned_loss=0.03307, over 1418968.48 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,487 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 04:15:47,843 INFO [train.py:792] (5/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
2022-04-30 04:16:54,031 INFO [train.py:763] (5/8) Epoch 26, batch 3050, loss[loss=0.167, simple_loss=0.2745, pruned_loss=0.02976, over 7129.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2643, pruned_loss=0.03325, over 1410535.78 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:17:59,874 INFO [train.py:763] (5/8) Epoch 26, batch 3100, loss[loss=0.1734, simple_loss=0.2799, pruned_loss=0.0334, over 7317.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03369, over 1417229.25 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:19:05,975 INFO [train.py:763] (5/8) Epoch 26, batch 3150, loss[loss=0.1843, simple_loss=0.2853, pruned_loss=0.04167, over 7206.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2651, pruned_loss=0.03341, over 1417499.64 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:20:11,642 INFO [train.py:763] (5/8) Epoch 26, batch 3200, loss[loss=0.2014, simple_loss=0.2977, pruned_loss=0.05249, over 7197.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03354, over 1419422.33 frames.], batch size: 23, lr: 2.87e-04
2022-04-30 04:21:17,164 INFO [train.py:763] (5/8) Epoch 26, batch 3250, loss[loss=0.1637, simple_loss=0.2622, pruned_loss=0.0326, over 6223.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2643, pruned_loss=0.03377, over 1419626.14 frames.], batch size: 37, lr: 2.87e-04
2022-04-30 04:22:22,729 INFO [train.py:763] (5/8) Epoch 26, batch 3300, loss[loss=0.1769, simple_loss=0.2911, pruned_loss=0.03134, over 6849.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2653, pruned_loss=0.03382, over 1419183.39 frames.], batch size: 31, lr: 2.87e-04
2022-04-30 04:23:27,762 INFO [train.py:763] (5/8) Epoch 26, batch 3350, loss[loss=0.1712, simple_loss=0.2748, pruned_loss=0.03378, over 7316.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03404, over 1420000.16 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:24:33,269 INFO [train.py:763] (5/8) Epoch 26, batch 3400, loss[loss=0.1573, simple_loss=0.2611, pruned_loss=0.02678, over 7147.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2665, pruned_loss=0.03383, over 1417697.90 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:25:38,630 INFO [train.py:763] (5/8) Epoch 26, batch 3450, loss[loss=0.1563, simple_loss=0.2654, pruned_loss=0.02355, over 7341.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2663, pruned_loss=0.03356, over 1421028.02 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:26:44,103 INFO [train.py:763] (5/8) Epoch 26, batch 3500, loss[loss=0.1456, simple_loss=0.2312, pruned_loss=0.03003, over 6775.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.03341, over 1423205.06 frames.], batch size: 15, lr: 2.87e-04
2022-04-30 04:27:49,687 INFO [train.py:763] (5/8) Epoch 26, batch 3550, loss[loss=0.1819, simple_loss=0.2735, pruned_loss=0.04515, over 5013.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03356, over 1415781.30 frames.], batch size: 52, lr: 2.87e-04
2022-04-30 04:28:54,787 INFO [train.py:763] (5/8) Epoch 26, batch 3600, loss[loss=0.1659, simple_loss=0.273, pruned_loss=0.02945, over 7149.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03364, over 1413578.64 frames.], batch size: 19, lr: 2.87e-04
2022-04-30 04:30:00,889 INFO [train.py:763] (5/8) Epoch 26, batch 3650, loss[loss=0.1624, simple_loss=0.2518, pruned_loss=0.03656, over 7068.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03401, over 1412791.62 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:31:07,248 INFO [train.py:763] (5/8) Epoch 26, batch 3700, loss[loss=0.1234, simple_loss=0.2139, pruned_loss=0.01639, over 7275.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2645, pruned_loss=0.03362, over 1412451.41 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:32:12,930 INFO [train.py:763] (5/8) Epoch 26, batch 3750, loss[loss=0.1571, simple_loss=0.2622, pruned_loss=0.02602, over 7220.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2632, pruned_loss=0.03298, over 1415984.79 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:33:20,042 INFO [train.py:763] (5/8) Epoch 26, batch 3800, loss[loss=0.1735, simple_loss=0.27, pruned_loss=0.03853, over 7325.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2631, pruned_loss=0.03298, over 1420314.36 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:34:26,375 INFO [train.py:763] (5/8) Epoch 26, batch 3850, loss[loss=0.143, simple_loss=0.242, pruned_loss=0.02197, over 7399.00 frames.], tot_loss[loss=0.1654, simple_loss=0.264, pruned_loss=0.03343, over 1413968.48 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:35:31,746 INFO [train.py:763] (5/8) Epoch 26, batch 3900, loss[loss=0.1639, simple_loss=0.2764, pruned_loss=0.02572, over 7113.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2635, pruned_loss=0.03307, over 1414904.74 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:36:37,013 INFO [train.py:763] (5/8) Epoch 26, batch 3950, loss[loss=0.1625, simple_loss=0.2592, pruned_loss=0.0329, over 7367.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03304, over 1419475.86 frames.], batch size: 19, lr: 2.86e-04
2022-04-30 04:37:42,776 INFO [train.py:763] (5/8) Epoch 26, batch 4000, loss[loss=0.1552, simple_loss=0.2626, pruned_loss=0.0239, over 7054.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2637, pruned_loss=0.03291, over 1424635.96 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:38:48,122 INFO [train.py:763] (5/8) Epoch 26, batch 4050, loss[loss=0.1705, simple_loss=0.2777, pruned_loss=0.03165, over 7326.00 frames.], tot_loss[loss=0.1655, simple_loss=0.265, pruned_loss=0.03303, over 1425938.71 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:39:53,371 INFO [train.py:763] (5/8) Epoch 26, batch 4100, loss[loss=0.1625, simple_loss=0.2616, pruned_loss=0.0317, over 7330.00 frames.], tot_loss[loss=0.165, simple_loss=0.2645, pruned_loss=0.03274, over 1424671.74 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:40:58,514 INFO [train.py:763] (5/8) Epoch 26, batch 4150, loss[loss=0.1778, simple_loss=0.2844, pruned_loss=0.03558, over 7118.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2651, pruned_loss=0.03297, over 1422082.54 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:42:03,903 INFO [train.py:763] (5/8) Epoch 26, batch 4200, loss[loss=0.1639, simple_loss=0.2769, pruned_loss=0.02543, over 7344.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2649, pruned_loss=0.03298, over 1423721.67 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:43:08,786 INFO [train.py:763] (5/8) Epoch 26, batch 4250, loss[loss=0.1736, simple_loss=0.2731, pruned_loss=0.037, over 7409.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2664, pruned_loss=0.03319, over 1416402.78 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:44:14,521 INFO [train.py:763] (5/8) Epoch 26, batch 4300, loss[loss=0.1662, simple_loss=0.2815, pruned_loss=0.02545, over 6737.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2663, pruned_loss=0.03314, over 1414155.09 frames.], batch size: 31, lr: 2.86e-04
2022-04-30 04:45:19,678 INFO [train.py:763] (5/8) Epoch 26, batch 4350, loss[loss=0.1603, simple_loss=0.2556, pruned_loss=0.03252, over 7007.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2663, pruned_loss=0.03314, over 1414189.68 frames.], batch size: 16, lr: 2.86e-04
2022-04-30 04:46:24,707 INFO [train.py:763] (5/8) Epoch 26, batch 4400, loss[loss=0.182, simple_loss=0.2878, pruned_loss=0.03809, over 6525.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2666, pruned_loss=0.03347, over 1402098.73 frames.], batch size: 38, lr: 2.86e-04
2022-04-30 04:47:29,337 INFO [train.py:763] (5/8) Epoch 26, batch 4450, loss[loss=0.1642, simple_loss=0.2678, pruned_loss=0.03027, over 7341.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2661, pruned_loss=0.03368, over 1397840.94 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:48:34,532 INFO [train.py:763] (5/8) Epoch 26, batch 4500, loss[loss=0.1589, simple_loss=0.2557, pruned_loss=0.03101, over 7170.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2666, pruned_loss=0.03429, over 1387654.25 frames.], batch size: 18, lr: 2.86e-04
2022-04-30 04:49:39,410 INFO [train.py:763] (5/8) Epoch 26, batch 4550, loss[loss=0.2036, simple_loss=0.2861, pruned_loss=0.06058, over 5102.00 frames.], tot_loss[loss=0.167, simple_loss=0.2652, pruned_loss=0.03435, over 1370169.31 frames.], batch size: 52, lr: 2.86e-04
2022-04-30 04:51:07,360 INFO [train.py:763] (5/8) Epoch 27, batch 0, loss[loss=0.1319, simple_loss=0.2201, pruned_loss=0.0219, over 7256.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2201, pruned_loss=0.0219, over 7256.00 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:52:13,086 INFO [train.py:763] (5/8) Epoch 27, batch 50, loss[loss=0.1702, simple_loss=0.2651, pruned_loss=0.03768, over 7256.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03344, over 321113.90 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:53:19,211 INFO [train.py:763] (5/8) Epoch 27, batch 100, loss[loss=0.1713, simple_loss=0.2789, pruned_loss=0.0319, over 7148.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2639, pruned_loss=0.03316, over 564337.81 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 04:54:25,261 INFO [train.py:763] (5/8) Epoch 27, batch 150, loss[loss=0.1621, simple_loss=0.2737, pruned_loss=0.02529, over 6414.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2651, pruned_loss=0.03279, over 752912.57 frames.], batch size: 37, lr: 2.80e-04
2022-04-30 04:55:31,378 INFO [train.py:763] (5/8) Epoch 27, batch 200, loss[loss=0.1613, simple_loss=0.2567, pruned_loss=0.03299, over 7205.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03264, over 898764.84 frames.], batch size: 23, lr: 2.80e-04
2022-04-30 04:56:38,005 INFO [train.py:763] (5/8) Epoch 27, batch 250, loss[loss=0.1654, simple_loss=0.2705, pruned_loss=0.03015, over 7299.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2646, pruned_loss=0.03229, over 1015030.35 frames.], batch size: 24, lr: 2.80e-04
2022-04-30 04:57:44,222 INFO [train.py:763] (5/8) Epoch 27, batch 300, loss[loss=0.1573, simple_loss=0.2664, pruned_loss=0.02408, over 6822.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03208, over 1105266.80 frames.], batch size: 31, lr: 2.80e-04
2022-04-30 04:58:50,133 INFO [train.py:763] (5/8) Epoch 27, batch 350, loss[loss=0.1423, simple_loss=0.239, pruned_loss=0.02281, over 7160.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2639, pruned_loss=0.03196, over 1178049.54 frames.], batch size: 19, lr: 2.80e-04
2022-04-30 04:59:56,372 INFO [train.py:763] (5/8) Epoch 27, batch 400, loss[loss=0.1477, simple_loss=0.2479, pruned_loss=0.0237, over 7135.00 frames.], tot_loss[loss=0.165, simple_loss=0.2649, pruned_loss=0.03255, over 1234037.19 frames.], batch size: 17, lr: 2.80e-04
2022-04-30 05:01:02,258 INFO [train.py:763] (5/8) Epoch 27, batch 450, loss[loss=0.1747, simple_loss=0.2754, pruned_loss=0.03695, over 7310.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03251, over 1270923.18 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:02:08,173 INFO [train.py:763] (5/8) Epoch 27, batch 500, loss[loss=0.1814, simple_loss=0.2919, pruned_loss=0.03542, over 7325.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2646, pruned_loss=0.03243, over 1308058.25 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:03:14,026 INFO [train.py:763] (5/8) Epoch 27, batch 550, loss[loss=0.2056, simple_loss=0.3008, pruned_loss=0.05518, over 7065.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2648, pruned_loss=0.03309, over 1329906.99 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:04:19,660 INFO [train.py:763] (5/8) Epoch 27, batch 600, loss[loss=0.138, simple_loss=0.2375, pruned_loss=0.0192, over 7326.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03287, over 1347882.89 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 05:05:24,803 INFO [train.py:763] (5/8) Epoch 27, batch 650, loss[loss=0.2004, simple_loss=0.3111, pruned_loss=0.04483, over 7112.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03306, over 1365478.58 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:06:40,263 INFO [train.py:763] (5/8) Epoch 27, batch 700, loss[loss=0.1498, simple_loss=0.2469, pruned_loss=0.02639, over 7062.00 frames.], tot_loss[loss=0.1648, simple_loss=0.264, pruned_loss=0.03282, over 1379349.77 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:07:46,097 INFO [train.py:763] (5/8) Epoch 27, batch 750, loss[loss=0.1692, simple_loss=0.2781, pruned_loss=0.03013, over 7224.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2632, pruned_loss=0.03252, over 1390680.92 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:08:51,498 INFO [train.py:763] (5/8) Epoch 27, batch 800, loss[loss=0.1568, simple_loss=0.2628, pruned_loss=0.02543, over 7038.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03275, over 1398511.46 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:09:56,927 INFO [train.py:763] (5/8) Epoch 27, batch 850, loss[loss=0.1769, simple_loss=0.2739, pruned_loss=0.03988, over 7295.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.0325, over 1405666.07 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:11:02,109 INFO [train.py:763] (5/8) Epoch 27, batch 900, loss[loss=0.1346, simple_loss=0.2265, pruned_loss=0.02134, over 6986.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03285, over 1408069.60 frames.], batch size: 16, lr: 2.80e-04
2022-04-30 05:12:07,295 INFO [train.py:763] (5/8) Epoch 27, batch 950, loss[loss=0.1571, simple_loss=0.2561, pruned_loss=0.029, over 7174.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2643, pruned_loss=0.03321, over 1411143.89 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:13:12,793 INFO [train.py:763] (5/8) Epoch 27, batch 1000, loss[loss=0.1786, simple_loss=0.2752, pruned_loss=0.04105, over 7431.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03332, over 1416818.89 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:14:18,819 INFO [train.py:763] (5/8) Epoch 27, batch 1050, loss[loss=0.1455, simple_loss=0.2533, pruned_loss=0.01887, over 7413.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03329, over 1416699.12 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:15:25,044 INFO [train.py:763] (5/8) Epoch 27, batch 1100, loss[loss=0.1623, simple_loss=0.2529, pruned_loss=0.0359, over 7064.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.03343, over 1415676.90 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:16:31,250 INFO [train.py:763] (5/8) Epoch 27, batch 1150, loss[loss=0.203, simple_loss=0.2904, pruned_loss=0.05776, over 7189.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.03334, over 1421010.01 frames.], batch size: 23, lr: 2.79e-04
2022-04-30 05:17:47,513 INFO [train.py:763] (5/8) Epoch 27, batch 1200, loss[loss=0.1646, simple_loss=0.2621, pruned_loss=0.03359, over 7142.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2639, pruned_loss=0.0329, over 1425760.85 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:19:01,927 INFO [train.py:763] (5/8) Epoch 27, batch 1250, loss[loss=0.1288, simple_loss=0.2214, pruned_loss=0.01817, over 7120.00 frames.], tot_loss[loss=0.165, simple_loss=0.2643, pruned_loss=0.03289, over 1423860.93 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:20:26,024 INFO [train.py:763] (5/8) Epoch 27, batch 1300, loss[loss=0.1538, simple_loss=0.2405, pruned_loss=0.0336, over 7271.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03287, over 1420035.08 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:21:31,877 INFO [train.py:763] (5/8) Epoch 27, batch 1350, loss[loss=0.1624, simple_loss=0.2513, pruned_loss=0.03673, over 7358.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03345, over 1419435.42 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:22:37,305 INFO [train.py:763] (5/8) Epoch 27, batch 1400, loss[loss=0.1497, simple_loss=0.2489, pruned_loss=0.02527, over 7065.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2633, pruned_loss=0.03281, over 1419537.20 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:24:10,284 INFO [train.py:763] (5/8) Epoch 27, batch 1450, loss[loss=0.1586, simple_loss=0.2531, pruned_loss=0.03203, over 7331.00 frames.], tot_loss[loss=0.1637, simple_loss=0.262, pruned_loss=0.03272, over 1421280.30 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:25:16,098 INFO [train.py:763] (5/8) Epoch 27, batch 1500, loss[loss=0.1833, simple_loss=0.2825, pruned_loss=0.04207, over 7121.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.03257, over 1423247.00 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:26:22,006 INFO [train.py:763] (5/8) Epoch 27, batch 1550, loss[loss=0.1566, simple_loss=0.2502, pruned_loss=0.03151, over 7257.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2627, pruned_loss=0.03289, over 1421530.37 frames.], batch size: 16, lr: 2.79e-04
2022-04-30 05:27:29,076 INFO [train.py:763] (5/8) Epoch 27, batch 1600, loss[loss=0.1684, simple_loss=0.2662, pruned_loss=0.03533, over 7413.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2632, pruned_loss=0.03314, over 1425137.73 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:28:35,024 INFO [train.py:763] (5/8) Epoch 27, batch 1650, loss[loss=0.1416, simple_loss=0.2407, pruned_loss=0.02121, over 7073.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2632, pruned_loss=0.03308, over 1426097.07 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:29:41,345 INFO [train.py:763] (5/8) Epoch 27, batch 1700, loss[loss=0.1606, simple_loss=0.2632, pruned_loss=0.02897, over 7346.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03266, over 1427641.09 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:30:48,493 INFO [train.py:763] (5/8) Epoch 27, batch 1750, loss[loss=0.1671, simple_loss=0.2716, pruned_loss=0.03124, over 6719.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03242, over 1429239.83 frames.], batch size: 31, lr: 2.79e-04
2022-04-30 05:31:54,574 INFO [train.py:763] (5/8) Epoch 27, batch 1800, loss[loss=0.1515, simple_loss=0.2535, pruned_loss=0.02472, over 7233.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03262, over 1427881.53 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:33:00,691 INFO [train.py:763] (5/8) Epoch 27, batch 1850, loss[loss=0.15, simple_loss=0.2413, pruned_loss=0.02931, over 7155.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.0327, over 1430502.14 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:34:06,844 INFO [train.py:763] (5/8) Epoch 27, batch 1900, loss[loss=0.1694, simple_loss=0.2553, pruned_loss=0.04169, over 7294.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2642, pruned_loss=0.03275, over 1430459.20 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:35:13,652 INFO [train.py:763] (5/8) Epoch 27, batch 1950, loss[loss=0.1729, simple_loss=0.27, pruned_loss=0.03788, over 6565.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2634, pruned_loss=0.03249, over 1426299.05 frames.], batch size: 38, lr: 2.78e-04
2022-04-30 05:36:20,339 INFO [train.py:763] (5/8) Epoch 27, batch 2000, loss[loss=0.1605, simple_loss=0.2639, pruned_loss=0.02857, over 7224.00 frames.], tot_loss[loss=0.1639, simple_loss=0.263, pruned_loss=0.03235, over 1426083.81 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:37:26,513 INFO [train.py:763] (5/8) Epoch 27, batch 2050, loss[loss=0.1888, simple_loss=0.2844, pruned_loss=0.04662, over 7223.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03246, over 1424553.78 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:38:32,987 INFO [train.py:763] (5/8) Epoch 27, batch 2100, loss[loss=0.1884, simple_loss=0.293, pruned_loss=0.04188, over 7332.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03255, over 1424823.51 frames.], batch size: 25, lr: 2.78e-04
2022-04-30 05:39:38,772 INFO [train.py:763] (5/8) Epoch 27, batch 2150, loss[loss=0.1518, simple_loss=0.2392, pruned_loss=0.03224, over 7154.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.03245, over 1423723.60 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:40:44,420 INFO [train.py:763] (5/8) Epoch 27, batch 2200, loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03056, over 7291.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2628, pruned_loss=0.03233, over 1422330.07 frames.], batch size: 24, lr: 2.78e-04
2022-04-30 05:41:50,161 INFO [train.py:763] (5/8) Epoch 27, batch 2250, loss[loss=0.17, simple_loss=0.262, pruned_loss=0.03904, over 7329.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2622, pruned_loss=0.03211, over 1424571.81 frames.], batch size: 22, lr: 2.78e-04
2022-04-30 05:42:56,036 INFO [train.py:763] (5/8) Epoch 27, batch 2300, loss[loss=0.1593, simple_loss=0.2625, pruned_loss=0.02803, over 7147.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03212, over 1421693.56 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:44:01,774 INFO [train.py:763] (5/8) Epoch 27, batch 2350, loss[loss=0.1598, simple_loss=0.2629, pruned_loss=0.02835, over 7164.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03229, over 1419384.37 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:45:08,047 INFO [train.py:763] (5/8) Epoch 27, batch 2400, loss[loss=0.1971, simple_loss=0.2867, pruned_loss=0.05372, over 7174.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03263, over 1422228.27 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:46:14,173 INFO [train.py:763] (5/8) Epoch 27, batch 2450, loss[loss=0.172, simple_loss=0.2718, pruned_loss=0.03613, over 6409.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03245, over 1423052.00 frames.], batch size: 37, lr: 2.78e-04
2022-04-30 05:47:19,806 INFO [train.py:763] (5/8) Epoch 27, batch 2500, loss[loss=0.1657, simple_loss=0.2532, pruned_loss=0.03912, over 6789.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2639, pruned_loss=0.03266, over 1420753.52 frames.], batch size: 15, lr: 2.78e-04
2022-04-30 05:48:25,890 INFO [train.py:763] (5/8) Epoch 27, batch 2550, loss[loss=0.1807, simple_loss=0.2813, pruned_loss=0.04001, over 7260.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03296, over 1420930.46 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:49:31,733 INFO [train.py:763] (5/8) Epoch 27, batch 2600, loss[loss=0.1674, simple_loss=0.272, pruned_loss=0.03143, over 7240.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03289, over 1420820.24 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:50:37,444 INFO [train.py:763] (5/8) Epoch 27, batch 2650, loss[loss=0.1522, simple_loss=0.2531, pruned_loss=0.02566, over 7004.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03274, over 1419852.43 frames.], batch size: 16, lr: 2.78e-04
2022-04-30 05:51:42,957 INFO [train.py:763] (5/8) Epoch 27, batch 2700, loss[loss=0.1465, simple_loss=0.2541, pruned_loss=0.01948, over 7323.00 frames.], tot_loss[loss=0.165, simple_loss=0.2649, pruned_loss=0.03259, over 1421463.88 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:52:49,079 INFO [train.py:763] (5/8) Epoch 27, batch 2750, loss[loss=0.1843, simple_loss=0.2822, pruned_loss=0.04315, over 7263.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2645, pruned_loss=0.0325, over 1419334.20 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:53:54,763 INFO [train.py:763] (5/8) Epoch 27, batch 2800, loss[loss=0.1849, simple_loss=0.2895, pruned_loss=0.04018, over 7234.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2644, pruned_loss=0.03249, over 1415143.55 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 05:55:00,526 INFO [train.py:763] (5/8) Epoch 27, batch 2850, loss[loss=0.1391, simple_loss=0.2291, pruned_loss=0.0246, over 7128.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2646, pruned_loss=0.0326, over 1420444.53 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 05:56:06,163 INFO [train.py:763] (5/8) Epoch 27, batch 2900, loss[loss=0.1996, simple_loss=0.2983, pruned_loss=0.05046, over 7267.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2648, pruned_loss=0.03237, over 1418952.91 frames.], batch size: 25, lr: 2.77e-04
2022-04-30 05:57:11,713 INFO [train.py:763] (5/8) Epoch 27, batch 2950, loss[loss=0.1817, simple_loss=0.2863, pruned_loss=0.03856, over 7196.00 frames.], tot_loss[loss=0.165, simple_loss=0.2652, pruned_loss=0.03244, over 1422338.70 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 05:58:18,063 INFO [train.py:763] (5/8) Epoch 27, batch 3000, loss[loss=0.162, simple_loss=0.2703, pruned_loss=0.02691, over 7114.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2651, pruned_loss=0.03218, over 1424474.34 frames.], batch size: 28, lr: 2.77e-04
2022-04-30 05:58:18,064 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 05:58:33,165 INFO [train.py:792] (5/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
2022-04-30 05:59:40,077 INFO [train.py:763] (5/8) Epoch 27, batch 3050, loss[loss=0.1512, simple_loss=0.2468, pruned_loss=0.02781, over 7137.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2649, pruned_loss=0.0319, over 1426189.18 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 06:00:45,837 INFO [train.py:763] (5/8) Epoch 27, batch 3100, loss[loss=0.171, simple_loss=0.2818, pruned_loss=0.03015, over 7388.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03223, over 1425230.32 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:01:51,944 INFO [train.py:763] (5/8) Epoch 27, batch 3150, loss[loss=0.1348, simple_loss=0.2212, pruned_loss=0.02419, over 7403.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03233, over 1423606.27 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:02:58,135 INFO [train.py:763] (5/8) Epoch 27, batch 3200, loss[loss=0.1428, simple_loss=0.2479, pruned_loss=0.01887, over 7312.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03257, over 1424614.41 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:04:04,079 INFO [train.py:763] (5/8) Epoch 27, batch 3250, loss[loss=0.1409, simple_loss=0.2403, pruned_loss=0.02077, over 7162.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2632, pruned_loss=0.03252, over 1424276.46 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:05:10,050 INFO [train.py:763] (5/8) Epoch 27, batch 3300, loss[loss=0.1295, simple_loss=0.2261, pruned_loss=0.01652, over 6990.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03238, over 1422808.75 frames.], batch size: 16, lr: 2.77e-04
2022-04-30 06:06:16,455 INFO [train.py:763] (5/8) Epoch 27, batch 3350, loss[loss=0.1786, simple_loss=0.2826, pruned_loss=0.0373, over 7362.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03224, over 1419711.05 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:07:23,120 INFO [train.py:763] (5/8) Epoch 27, batch 3400, loss[loss=0.1692, simple_loss=0.2702, pruned_loss=0.0341, over 7330.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.0324, over 1421722.29 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:08:29,077 INFO [train.py:763] (5/8) Epoch 27, batch 3450, loss[loss=0.1636, simple_loss=0.2684, pruned_loss=0.02942, over 7205.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03233, over 1423057.59 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:09:35,004 INFO [train.py:763] (5/8) Epoch 27, batch 3500, loss[loss=0.146, simple_loss=0.2401, pruned_loss=0.02595, over 7453.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03213, over 1423043.18 frames.], batch size: 19, lr: 2.77e-04
2022-04-30 06:10:40,869 INFO [train.py:763] (5/8) Epoch 27, batch 3550, loss[loss=0.1532, simple_loss=0.2584, pruned_loss=0.02394, over 7328.00 frames.], tot_loss[loss=0.1642, simple_loss=0.264, pruned_loss=0.03219, over 1423550.19 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:11:46,449 INFO [train.py:763] (5/8) Epoch 27, batch 3600, loss[loss=0.1719, simple_loss=0.2676, pruned_loss=0.03805, over 7058.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03288, over 1422639.39 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:12:52,029 INFO [train.py:763] (5/8) Epoch 27, batch 3650, loss[loss=0.1827, simple_loss=0.2869, pruned_loss=0.03923, over 7403.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2644, pruned_loss=0.03283, over 1423080.23 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:13:58,384 INFO [train.py:763] (5/8) Epoch 27, batch 3700, loss[loss=0.1572, simple_loss=0.2603, pruned_loss=0.02709, over 7432.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03262, over 1423341.52 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:15:04,105 INFO [train.py:763] (5/8) Epoch 27, batch 3750, loss[loss=0.1876, simple_loss=0.2856, pruned_loss=0.04476, over 5049.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03194, over 1419113.30 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:16:10,311 INFO [train.py:763] (5/8) Epoch 27, batch 3800, loss[loss=0.1493, simple_loss=0.2389, pruned_loss=0.02987, over 7258.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03185, over 1421442.48 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:17:16,533 INFO [train.py:763] (5/8) Epoch 27, batch 3850, loss[loss=0.157, simple_loss=0.2602, pruned_loss=0.02691, over 7156.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2633, pruned_loss=0.03165, over 1425969.90 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:18:22,912 INFO [train.py:763] (5/8) Epoch 27, batch 3900, loss[loss=0.1753, simple_loss=0.2744, pruned_loss=0.03805, over 7211.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03178, over 1424830.33 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:19:28,550 INFO [train.py:763] (5/8) Epoch 27, batch 3950, loss[loss=0.1794, simple_loss=0.2816, pruned_loss=0.03865, over 7201.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03201, over 1426167.25 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:20:34,839 INFO [train.py:763] (5/8) Epoch 27, batch 4000, loss[loss=0.2005, simple_loss=0.3097, pruned_loss=0.04568, over 6870.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03184, over 1422788.10 frames.], batch size: 31, lr: 2.76e-04
2022-04-30 06:21:40,924 INFO [train.py:763] (5/8) Epoch 27, batch 4050, loss[loss=0.2041, simple_loss=0.2963, pruned_loss=0.05593, over 5483.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2637, pruned_loss=0.03228, over 1416957.92 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:22:47,111 INFO [train.py:763] (5/8) Epoch 27, batch 4100, loss[loss=0.1315, simple_loss=0.2265, pruned_loss=0.01821, over 7150.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03203, over 1419254.50 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:24:03,987 INFO [train.py:763] (5/8) Epoch 27, batch 4150, loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03082, over 7150.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03244, over 1424358.59 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:25:09,379 INFO [train.py:763] (5/8) Epoch 27, batch 4200, loss[loss=0.1793, simple_loss=0.2783, pruned_loss=0.04016, over 4858.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03268, over 1417974.06 frames.], batch size: 53, lr: 2.76e-04
2022-04-30 06:26:15,110 INFO [train.py:763] (5/8) Epoch 27, batch 4250, loss[loss=0.1572, simple_loss=0.2553, pruned_loss=0.02955, over 7058.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.0323, over 1415523.21 frames.], batch size: 18, lr: 2.76e-04
2022-04-30 06:27:21,143 INFO [train.py:763] (5/8) Epoch 27, batch 4300, loss[loss=0.1393, simple_loss=0.2311, pruned_loss=0.02377, over 7133.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03188, over 1416469.30 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:28:27,406 INFO [train.py:763] (5/8) Epoch 27, batch 4350, loss[loss=0.1885, simple_loss=0.2966, pruned_loss=0.04026, over 7214.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03199, over 1416271.61 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:29:33,359 INFO [train.py:763] (5/8) Epoch 27, batch 4400, loss[loss=0.1575, simple_loss=0.2606, pruned_loss=0.02719, over 6305.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2638, pruned_loss=0.03267, over 1409030.91 frames.], batch size: 37, lr: 2.76e-04
2022-04-30 06:30:39,410 INFO [train.py:763] (5/8) Epoch 27, batch 4450, loss[loss=0.1433, simple_loss=0.2283, pruned_loss=0.02914, over 7221.00 frames.], tot_loss[loss=0.165, simple_loss=0.264, pruned_loss=0.03298, over 1403907.43 frames.], batch size: 16, lr: 2.76e-04
2022-04-30 06:31:44,900 INFO [train.py:763] (5/8) Epoch 27, batch 4500, loss[loss=0.1598, simple_loss=0.265, pruned_loss=0.02728, over 7226.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03326, over 1392079.09 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:32:50,038 INFO [train.py:763] (5/8) Epoch 27, batch 4550, loss[loss=0.1619, simple_loss=0.2768, pruned_loss=0.02353, over 6586.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2659, pruned_loss=0.034, over 1361151.82 frames.], batch size: 38, lr: 2.76e-04
2022-04-30 06:34:19,195 INFO [train.py:763] (5/8) Epoch 28, batch 0, loss[loss=0.1597, simple_loss=0.2697, pruned_loss=0.02488, over 7004.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2697, pruned_loss=0.02488, over 7004.00 frames.], batch size: 28, lr: 2.71e-04
2022-04-30 06:35:24,837 INFO [train.py:763] (5/8) Epoch 28, batch 50, loss[loss=0.1757, simple_loss=0.2758, pruned_loss=0.03786, over 7291.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2659, pruned_loss=0.03145, over 324659.01 frames.], batch size: 24, lr: 2.71e-04
2022-04-30 06:36:31,685 INFO [train.py:763] (5/8) Epoch 28, batch 100, loss[loss=0.1786, simple_loss=0.2731, pruned_loss=0.04203, over 7328.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2658, pruned_loss=0.03229, over 570349.69 frames.], batch size: 21, lr: 2.71e-04
2022-04-30 06:37:37,375 INFO [train.py:763] (5/8) Epoch 28, batch 150, loss[loss=0.1612, simple_loss=0.2734, pruned_loss=0.02452, over 7228.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2653, pruned_loss=0.03212, over 760609.94 frames.], batch size: 20, lr: 2.71e-04
2022-04-30 06:38:43,643 INFO [train.py:763] (5/8) Epoch 28, batch 200, loss[loss=0.1397, simple_loss=0.2375, pruned_loss=0.02093, over 7067.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2636, pruned_loss=0.03153, over 909983.34 frames.], batch size: 18, lr: 2.71e-04
2022-04-30 06:39:49,243 INFO [train.py:763] (5/8) Epoch 28, batch 250, loss[loss=0.1996, simple_loss=0.2929, pruned_loss=0.05309, over 5267.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2647, pruned_loss=0.03205, over 1020487.28 frames.], batch size: 52, lr: 2.71e-04
2022-04-30 06:40:54,490 INFO [train.py:763] (5/8) Epoch 28, batch 300, loss[loss=0.1707, simple_loss=0.2575, pruned_loss=0.0419, over 7172.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2649, pruned_loss=0.0322, over 1110360.04 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:41:59,627 INFO [train.py:763] (5/8) Epoch 28, batch 350, loss[loss=0.1536, simple_loss=0.2501, pruned_loss=0.02855, over 7067.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2653, pruned_loss=0.03218, over 1181530.99 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:43:05,889 INFO [train.py:763] (5/8) Epoch 28, batch 400, loss[loss=0.1502, simple_loss=0.2509, pruned_loss=0.0247, over 7147.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2646, pruned_loss=0.0319, over 1237656.18 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:44:12,424 INFO [train.py:763] (5/8) Epoch 28, batch 450, loss[loss=0.1715, simple_loss=0.2795, pruned_loss=0.03173, over 7128.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2646, pruned_loss=0.03229, over 1283304.76 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:45:17,947 INFO [train.py:763] (5/8) Epoch 28, batch 500, loss[loss=0.2146, simple_loss=0.3084, pruned_loss=0.06045, over 5105.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2642, pruned_loss=0.03254, over 1310786.62 frames.], batch size: 52, lr: 2.70e-04
2022-04-30 06:46:23,651 INFO [train.py:763] (5/8) Epoch 28, batch 550, loss[loss=0.1648, simple_loss=0.2632, pruned_loss=0.03318, over 7230.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2644, pruned_loss=0.03261, over 1332765.98 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:47:29,782 INFO [train.py:763] (5/8) Epoch 28, batch 600, loss[loss=0.1548, simple_loss=0.2451, pruned_loss=0.03229, over 7261.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2636, pruned_loss=0.03261, over 1349451.10 frames.], batch size: 19, lr: 2.70e-04
2022-04-30 06:48:35,502 INFO [train.py:763] (5/8) Epoch 28, batch 650, loss[loss=0.1535, simple_loss=0.2512, pruned_loss=0.02783, over 7076.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.03188, over 1367916.05 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:49:42,692 INFO [train.py:763] (5/8) Epoch 28, batch 700, loss[loss=0.1834, simple_loss=0.284, pruned_loss=0.04141, over 4940.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2632, pruned_loss=0.03256, over 1376045.98 frames.], batch size: 54, lr: 2.70e-04
2022-04-30 06:50:48,232 INFO [train.py:763] (5/8) Epoch 28, batch 750, loss[loss=0.1425, simple_loss=0.2532, pruned_loss=0.01594, over 7431.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2629, pruned_loss=0.03223, over 1382207.95 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:51:53,708 INFO [train.py:763] (5/8) Epoch 28, batch 800, loss[loss=0.1693, simple_loss=0.2723, pruned_loss=0.03316, over 7120.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03207, over 1388180.58 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:52:59,924 INFO [train.py:763] (5/8) Epoch 28, batch 850, loss[loss=0.181, simple_loss=0.2748, pruned_loss=0.04356, over 6535.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.03224, over 1392540.44 frames.], batch size: 38, lr: 2.70e-04
2022-04-30 06:54:06,454 INFO [train.py:763] (5/8) Epoch 28, batch 900, loss[loss=0.1905, simple_loss=0.2897, pruned_loss=0.04566, over 6787.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03212, over 1400067.88 frames.], batch size: 31, lr: 2.70e-04
2022-04-30 06:55:12,071 INFO [train.py:763] (5/8) Epoch 28, batch 950, loss[loss=0.1517, simple_loss=0.255, pruned_loss=0.02426, over 7194.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03239, over 1409820.38 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 06:56:17,981 INFO [train.py:763] (5/8) Epoch 28, batch 1000, loss[loss=0.1444, simple_loss=0.243, pruned_loss=0.0229, over 6830.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03233, over 1415178.70 frames.], batch size: 15, lr: 2.70e-04
2022-04-30 06:57:23,500 INFO [train.py:763] (5/8) Epoch 28, batch 1050, loss[loss=0.1455, simple_loss=0.2542, pruned_loss=0.01839, over 7419.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03189, over 1420353.13 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:58:29,254 INFO [train.py:763] (5/8) Epoch 28, batch 1100, loss[loss=0.1343, simple_loss=0.2285, pruned_loss=0.02004, over 7282.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03246, over 1422434.44 frames.], batch size: 17, lr: 2.70e-04
2022-04-30 06:59:35,706 INFO [train.py:763] (5/8) Epoch 28, batch 1150, loss[loss=0.1864, simple_loss=0.2786, pruned_loss=0.04714, over 7060.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03281, over 1421213.19 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:00:40,819 INFO [train.py:763] (5/8) Epoch 28, batch 1200, loss[loss=0.1519, simple_loss=0.2581, pruned_loss=0.02283, over 7053.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2653, pruned_loss=0.03267, over 1423564.86 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:01:47,026 INFO [train.py:763] (5/8) Epoch 28, batch 1250, loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03449, over 7225.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2646, pruned_loss=0.03252, over 1417512.91 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 07:02:52,932 INFO [train.py:763] (5/8) Epoch 28, batch 1300, loss[loss=0.1684, simple_loss=0.2761, pruned_loss=0.0304, over 7153.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03254, over 1420478.88 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:03:58,478 INFO [train.py:763] (5/8) Epoch 28, batch 1350, loss[loss=0.1694, simple_loss=0.289, pruned_loss=0.0249, over 7105.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03256, over 1425653.28 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:05:04,530 INFO [train.py:763] (5/8) Epoch 28, batch 1400, loss[loss=0.1624, simple_loss=0.251, pruned_loss=0.03687, over 7282.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2636, pruned_loss=0.03254, over 1427958.33 frames.], batch size: 17, lr: 2.69e-04
2022-04-30 07:06:10,016 INFO [train.py:763] (5/8) Epoch 28, batch 1450, loss[loss=0.1649, simple_loss=0.2677, pruned_loss=0.03105, over 7284.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03292, over 1431571.46 frames.], batch size: 24, lr: 2.69e-04
2022-04-30 07:07:16,033 INFO [train.py:763] (5/8) Epoch 28, batch 1500, loss[loss=0.1413, simple_loss=0.2453, pruned_loss=0.01868, over 7327.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2643, pruned_loss=0.03237, over 1428514.17 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:08:21,698 INFO [train.py:763] (5/8) Epoch 28, batch 1550, loss[loss=0.1689, simple_loss=0.2706, pruned_loss=0.03364, over 7224.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03224, over 1429899.60 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:09:26,979 INFO [train.py:763] (5/8) Epoch 28, batch 1600, loss[loss=0.1478, simple_loss=0.24, pruned_loss=0.02776, over 6822.00 frames.], tot_loss[loss=0.164, simple_loss=0.2641, pruned_loss=0.03193, over 1426500.58 frames.], batch size: 15, lr: 2.69e-04
2022-04-30 07:10:32,959 INFO [train.py:763] (5/8) Epoch 28, batch 1650, loss[loss=0.1506, simple_loss=0.2315, pruned_loss=0.03489, over 6736.00 frames.], tot_loss[loss=0.1631, simple_loss=0.263, pruned_loss=0.03157, over 1428174.65 frames.], batch size: 15, lr: 2.69e-04
2022-04-30 07:11:39,864 INFO [train.py:763] (5/8) Epoch 28, batch 1700, loss[loss=0.1468, simple_loss=0.243, pruned_loss=0.02529, over 7269.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03161, over 1431023.58 frames.], batch size: 19, lr: 2.69e-04
2022-04-30 07:12:45,215 INFO [train.py:763] (5/8) Epoch 28, batch 1750, loss[loss=0.1573, simple_loss=0.2675, pruned_loss=0.02353, over 7109.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03107, over 1433292.00 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:13:50,841 INFO [train.py:763] (5/8) Epoch 28, batch 1800, loss[loss=0.1429, simple_loss=0.2392, pruned_loss=0.02326, over 7003.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03086, over 1423216.27 frames.], batch size: 16, lr: 2.69e-04
2022-04-30 07:14:56,960 INFO [train.py:763] (5/8) Epoch 28, batch 1850, loss[loss=0.1676, simple_loss=0.2616, pruned_loss=0.03686, over 7419.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03111, over 1425482.36 frames.], batch size: 18, lr: 2.69e-04
2022-04-30 07:16:02,993 INFO [train.py:763] (5/8) Epoch 28, batch 1900, loss[loss=0.178, simple_loss=0.2774, pruned_loss=0.03927, over 7190.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2622, pruned_loss=0.03125, over 1425992.47 frames.], batch size: 26, lr: 2.69e-04
2022-04-30 07:17:09,681 INFO [train.py:763] (5/8) Epoch 28, batch 1950, loss[loss=0.1676, simple_loss=0.2767, pruned_loss=0.02928, over 7271.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03141, over 1428528.59 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:18:15,514 INFO [train.py:763] (5/8) Epoch 28, batch 2000, loss[loss=0.161, simple_loss=0.264, pruned_loss=0.02899, over 7196.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03105, over 1431806.92 frames.], batch size: 23, lr: 2.69e-04
2022-04-30 07:19:21,146 INFO [train.py:763] (5/8) Epoch 28, batch 2050, loss[loss=0.1496, simple_loss=0.255, pruned_loss=0.02213, over 7317.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03174, over 1424932.16 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:20:26,751 INFO [train.py:763] (5/8) Epoch 28, batch 2100, loss[loss=0.1687, simple_loss=0.2718, pruned_loss=0.03286, over 7288.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2611, pruned_loss=0.03131, over 1426046.03 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:21:33,846 INFO [train.py:763] (5/8) Epoch 28, batch 2150, loss[loss=0.1766, simple_loss=0.2819, pruned_loss=0.03567, over 7229.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03116, over 1427077.07 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:22:48,766 INFO [train.py:763] (5/8) Epoch 28, batch 2200, loss[loss=0.1825, simple_loss=0.2861, pruned_loss=0.03951, over 7283.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.03142, over 1421535.32 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:23:56,117 INFO [train.py:763] (5/8) Epoch 28, batch 2250, loss[loss=0.1829, simple_loss=0.2904, pruned_loss=0.03775, over 7115.00 frames.], tot_loss[loss=0.1634, simple_loss=0.263, pruned_loss=0.03186, over 1425635.36 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:25:01,837 INFO [train.py:763] (5/8) Epoch 28, batch 2300, loss[loss=0.1762, simple_loss=0.2831, pruned_loss=0.03469, over 7287.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03199, over 1427743.55 frames.], batch size: 24, lr: 2.68e-04
2022-04-30 07:26:07,552 INFO [train.py:763] (5/8) Epoch 28, batch 2350, loss[loss=0.1393, simple_loss=0.2468, pruned_loss=0.01593, over 7070.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03195, over 1425164.58 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:27:14,918 INFO [train.py:763] (5/8) Epoch 28, batch 2400, loss[loss=0.1501, simple_loss=0.2507, pruned_loss=0.02476, over 7357.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2618, pruned_loss=0.03185, over 1426665.18 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:28:20,446 INFO [train.py:763] (5/8) Epoch 28, batch 2450, loss[loss=0.1584, simple_loss=0.2659, pruned_loss=0.02547, over 7115.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2629, pruned_loss=0.03234, over 1417437.17 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:29:26,092 INFO [train.py:763] (5/8) Epoch 28, batch 2500, loss[loss=0.1368, simple_loss=0.2349, pruned_loss=0.01934, over 7411.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2621, pruned_loss=0.03225, over 1420780.35 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:30:32,244 INFO [train.py:763] (5/8) Epoch 28, batch 2550, loss[loss=0.1467, simple_loss=0.2375, pruned_loss=0.02795, over 7170.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2618, pruned_loss=0.03229, over 1418546.66 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:31:37,902 INFO [train.py:763] (5/8) Epoch 28, batch 2600, loss[loss=0.1715, simple_loss=0.2799, pruned_loss=0.0316, over 7201.00 frames.], tot_loss[loss=0.1631, simple_loss=0.262, pruned_loss=0.03207, over 1415793.05 frames.], batch size: 23, lr: 2.68e-04
2022-04-30 07:32:43,459 INFO [train.py:763] (5/8) Epoch 28, batch 2650, loss[loss=0.1515, simple_loss=0.2457, pruned_loss=0.02863, over 7420.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2616, pruned_loss=0.03206, over 1418741.05 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:33:59,647 INFO [train.py:763] (5/8) Epoch 28, batch 2700, loss[loss=0.1792, simple_loss=0.2742, pruned_loss=0.04207, over 4714.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2613, pruned_loss=0.03198, over 1418025.52 frames.], batch size: 52, lr: 2.68e-04
2022-04-30 07:35:13,952 INFO [train.py:763] (5/8) Epoch 28, batch 2750, loss[loss=0.155, simple_loss=0.2597, pruned_loss=0.02512, over 7315.00 frames.], tot_loss[loss=0.163, simple_loss=0.2617, pruned_loss=0.03213, over 1414554.22 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:36:28,360 INFO [train.py:763] (5/8) Epoch 28, batch 2800, loss[loss=0.1731, simple_loss=0.2653, pruned_loss=0.04051, over 7323.00 frames.], tot_loss[loss=0.163, simple_loss=0.262, pruned_loss=0.03206, over 1417503.98 frames.], batch size: 22, lr: 2.68e-04
2022-04-30 07:37:44,246 INFO [train.py:763] (5/8) Epoch 28, batch 2850, loss[loss=0.159, simple_loss=0.2636, pruned_loss=0.02721, over 7251.00 frames.], tot_loss[loss=0.163, simple_loss=0.2616, pruned_loss=0.0322, over 1418029.57 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:38:58,508 INFO [train.py:763] (5/8) Epoch 28, batch 2900, loss[loss=0.1369, simple_loss=0.2333, pruned_loss=0.02027, over 7281.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2616, pruned_loss=0.03208, over 1416782.53 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:40:13,610 INFO [train.py:763] (5/8) Epoch 28, batch 2950, loss[loss=0.1519, simple_loss=0.2375, pruned_loss=0.03318, over 7131.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2608, pruned_loss=0.03207, over 1417147.58 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:41:27,531 INFO [train.py:763] (5/8) Epoch 28, batch 3000, loss[loss=0.148, simple_loss=0.2571, pruned_loss=0.01944, over 7236.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2618, pruned_loss=0.03189, over 1418073.94 frames.], batch size: 20, lr: 2.68e-04
2022-04-30 07:41:27,532 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 07:41:44,121 INFO [train.py:792] (5/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
2022-04-30 07:42:49,826 INFO [train.py:763] (5/8) Epoch 28, batch 3050, loss[loss=0.1578, simple_loss=0.2569, pruned_loss=0.02932, over 7159.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2618, pruned_loss=0.03194, over 1421113.92 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:43:55,535 INFO [train.py:763] (5/8) Epoch 28, batch 3100, loss[loss=0.1383, simple_loss=0.2321, pruned_loss=0.02228, over 7270.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2613, pruned_loss=0.0319, over 1417682.71 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:45:01,669 INFO [train.py:763] (5/8) Epoch 28, batch 3150, loss[loss=0.1721, simple_loss=0.2786, pruned_loss=0.03282, over 7222.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.03158, over 1422005.10 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:46:07,730 INFO [train.py:763] (5/8) Epoch 28, batch 3200, loss[loss=0.1546, simple_loss=0.2571, pruned_loss=0.02605, over 7116.00 frames.], tot_loss[loss=0.163, simple_loss=0.2626, pruned_loss=0.03171, over 1421571.13 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:47:14,371 INFO [train.py:763] (5/8) Epoch 28, batch 3250, loss[loss=0.1523, simple_loss=0.2464, pruned_loss=0.02912, over 6829.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.03189, over 1421294.74 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:48:20,869 INFO [train.py:763] (5/8) Epoch 28, batch 3300, loss[loss=0.1648, simple_loss=0.2715, pruned_loss=0.02898, over 7219.00 frames.], tot_loss[loss=0.165, simple_loss=0.2647, pruned_loss=0.03258, over 1421117.14 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 07:49:26,971 INFO [train.py:763] (5/8) Epoch 28, batch 3350, loss[loss=0.1561, simple_loss=0.2609, pruned_loss=0.02563, over 7049.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03245, over 1419053.87 frames.], batch size: 28, lr: 2.67e-04
2022-04-30 07:50:33,797 INFO [train.py:763] (5/8) Epoch 28, batch 3400, loss[loss=0.1504, simple_loss=0.2399, pruned_loss=0.03049, over 7065.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.03245, over 1417584.69 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:51:39,852 INFO [train.py:763] (5/8) Epoch 28, batch 3450, loss[loss=0.1538, simple_loss=0.2407, pruned_loss=0.03348, over 7282.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03241, over 1420696.51 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 07:52:45,410 INFO [train.py:763] (5/8) Epoch 28, batch 3500, loss[loss=0.168, simple_loss=0.2733, pruned_loss=0.03133, over 6861.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.0321, over 1420206.90 frames.], batch size: 31, lr: 2.67e-04
2022-04-30 07:53:50,885 INFO [train.py:763] (5/8) Epoch 28, batch 3550, loss[loss=0.1388, simple_loss=0.2335, pruned_loss=0.022, over 7284.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03144, over 1423080.73 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:54:56,705 INFO [train.py:763] (5/8) Epoch 28, batch 3600, loss[loss=0.1614, simple_loss=0.2448, pruned_loss=0.03897, over 6770.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2622, pruned_loss=0.03185, over 1422990.34 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:56:02,363 INFO [train.py:763] (5/8) Epoch 28, batch 3650, loss[loss=0.1418, simple_loss=0.246, pruned_loss=0.01883, over 7338.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03159, over 1426548.76 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 07:57:08,121 INFO [train.py:763] (5/8) Epoch 28, batch 3700, loss[loss=0.1907, simple_loss=0.2845, pruned_loss=0.04847, over 7186.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03187, over 1426678.13 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 07:58:13,564 INFO [train.py:763] (5/8) Epoch 28, batch 3750, loss[loss=0.1951, simple_loss=0.288, pruned_loss=0.05104, over 4847.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03206, over 1426638.20 frames.], batch size: 52, lr: 2.67e-04
2022-04-30 07:59:19,104 INFO [train.py:763] (5/8) Epoch 28, batch 3800, loss[loss=0.1622, simple_loss=0.2577, pruned_loss=0.03331, over 7422.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03198, over 1427003.05 frames.], batch size: 20, lr: 2.67e-04
2022-04-30 08:00:24,616 INFO [train.py:763] (5/8) Epoch 28, batch 3850, loss[loss=0.1608, simple_loss=0.2638, pruned_loss=0.02887, over 7360.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2636, pruned_loss=0.03188, over 1427841.70 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 08:01:31,050 INFO [train.py:763] (5/8) Epoch 28, batch 3900, loss[loss=0.1708, simple_loss=0.271, pruned_loss=0.03532, over 7270.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03191, over 1430519.18 frames.], batch size: 24, lr: 2.67e-04
2022-04-30 08:02:37,689 INFO [train.py:763] (5/8) Epoch 28, batch 3950, loss[loss=0.1464, simple_loss=0.2324, pruned_loss=0.03018, over 7435.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2648, pruned_loss=0.03227, over 1431388.53 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 08:03:44,105 INFO [train.py:763] (5/8) Epoch 28, batch 4000, loss[loss=0.1592, simple_loss=0.2536, pruned_loss=0.03237, over 7352.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2646, pruned_loss=0.03223, over 1430592.61 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:04:50,787 INFO [train.py:763] (5/8) Epoch 28, batch 4050, loss[loss=0.157, simple_loss=0.2518, pruned_loss=0.03105, over 7281.00 frames.], tot_loss[loss=0.1648, simple_loss=0.265, pruned_loss=0.03236, over 1429709.93 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 08:05:55,982 INFO [train.py:763] (5/8) Epoch 28, batch 4100, loss[loss=0.1808, simple_loss=0.2788, pruned_loss=0.04139, over 7326.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2651, pruned_loss=0.0324, over 1430432.07 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:07:02,635 INFO [train.py:763] (5/8) Epoch 28, batch 4150, loss[loss=0.1505, simple_loss=0.2619, pruned_loss=0.01955, over 7325.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2641, pruned_loss=0.03181, over 1423972.87 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 08:08:09,149 INFO [train.py:763] (5/8) Epoch 28, batch 4200, loss[loss=0.125, simple_loss=0.224, pruned_loss=0.01294, over 7273.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2648, pruned_loss=0.03214, over 1421401.62 frames.], batch size: 19, lr: 2.66e-04
2022-04-30 08:09:14,670 INFO [train.py:763] (5/8) Epoch 28, batch 4250, loss[loss=0.1631, simple_loss=0.2716, pruned_loss=0.02727, over 6813.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03168, over 1422292.71 frames.], batch size: 31, lr: 2.66e-04
2022-04-30 08:10:19,667 INFO [train.py:763] (5/8) Epoch 28, batch 4300, loss[loss=0.1274, simple_loss=0.2244, pruned_loss=0.01519, over 7159.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2631, pruned_loss=0.03164, over 1417964.60 frames.], batch size: 18, lr: 2.66e-04
2022-04-30 08:11:24,970 INFO [train.py:763] (5/8) Epoch 28, batch 4350, loss[loss=0.1693, simple_loss=0.2739, pruned_loss=0.03234, over 7320.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03156, over 1419462.04 frames.], batch size: 21, lr: 2.66e-04
2022-04-30 08:12:30,146 INFO [train.py:763] (5/8) Epoch 28, batch 4400, loss[loss=0.2198, simple_loss=0.305, pruned_loss=0.06732, over 7280.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03195, over 1411470.53 frames.], batch size: 24, lr: 2.66e-04
2022-04-30 08:13:35,276 INFO [train.py:763] (5/8) Epoch 28, batch 4450, loss[loss=0.1663, simple_loss=0.2728, pruned_loss=0.02992, over 6503.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2633, pruned_loss=0.03209, over 1402852.70 frames.], batch size: 38, lr: 2.66e-04
2022-04-30 08:14:40,132 INFO [train.py:763] (5/8) Epoch 28, batch 4500, loss[loss=0.1934, simple_loss=0.2949, pruned_loss=0.04599, over 7226.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2647, pruned_loss=0.03272, over 1379566.88 frames.], batch size: 22, lr: 2.66e-04
2022-04-30 08:15:45,403 INFO [train.py:763] (5/8) Epoch 28, batch 4550, loss[loss=0.2176, simple_loss=0.3099, pruned_loss=0.06268, over 4989.00 frames.], tot_loss[loss=0.1671, simple_loss=0.267, pruned_loss=0.03361, over 1361986.30 frames.], batch size: 52, lr: 2.66e-04
2022-04-30 08:17:05,892 INFO [train.py:763] (5/8) Epoch 29, batch 0, loss[loss=0.1568, simple_loss=0.2615, pruned_loss=0.02604, over 7337.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2615, pruned_loss=0.02604, over 7337.00 frames.], batch size: 20, lr: 2.62e-04
2022-04-30 08:18:11,692 INFO [train.py:763] (5/8) Epoch 29, batch 50, loss[loss=0.1714, simple_loss=0.2644, pruned_loss=0.03917, over 7292.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2646, pruned_loss=0.03205, over 323660.90 frames.], batch size: 18, lr: 2.62e-04
2022-04-30 08:19:17,263 INFO [train.py:763] (5/8) Epoch 29, batch 100, loss[loss=0.1567, simple_loss=0.255, pruned_loss=0.02919, over 7287.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03102, over 571661.28 frames.], batch size: 17, lr: 2.62e-04
2022-04-30 08:20:22,570 INFO [train.py:763] (5/8) Epoch 29, batch 150, loss[loss=0.1944, simple_loss=0.2854, pruned_loss=0.05169, over 7283.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.0313, over 749404.22 frames.], batch size: 24, lr: 2.62e-04
2022-04-30 08:21:28,012 INFO [train.py:763] (5/8) Epoch 29, batch 200, loss[loss=0.1594, simple_loss=0.2522, pruned_loss=0.0333, over 7357.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2625, pruned_loss=0.03127, over 899969.57 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:22:33,079 INFO [train.py:763] (5/8) Epoch 29, batch 250, loss[loss=0.1427, simple_loss=0.2353, pruned_loss=0.02507, over 6818.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2631, pruned_loss=0.03132, over 1015752.63 frames.], batch size: 15, lr: 2.61e-04
2022-04-30 08:23:39,498 INFO [train.py:763] (5/8) Epoch 29, batch 300, loss[loss=0.1678, simple_loss=0.2635, pruned_loss=0.03609, over 7264.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03218, over 1107162.50 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:24:46,643 INFO [train.py:763] (5/8) Epoch 29, batch 350, loss[loss=0.1597, simple_loss=0.266, pruned_loss=0.02672, over 7331.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03163, over 1180521.54 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:25:52,379 INFO [train.py:763] (5/8) Epoch 29, batch 400, loss[loss=0.1656, simple_loss=0.2726, pruned_loss=0.0293, over 7300.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03188, over 1236573.97 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:26:57,832 INFO [train.py:763] (5/8) Epoch 29, batch 450, loss[loss=0.1813, simple_loss=0.2861, pruned_loss=0.0382, over 7404.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2619, pruned_loss=0.03176, over 1279296.51 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:28:03,217 INFO [train.py:763] (5/8) Epoch 29, batch 500, loss[loss=0.1577, simple_loss=0.2534, pruned_loss=0.03102, over 7314.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03161, over 1307687.12 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:29:08,676 INFO [train.py:763] (5/8) Epoch 29, batch 550, loss[loss=0.1613, simple_loss=0.2664, pruned_loss=0.02811, over 7289.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2624, pruned_loss=0.03151, over 1335826.89 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:30:14,689 INFO [train.py:763] (5/8) Epoch 29, batch 600, loss[loss=0.1616, simple_loss=0.2647, pruned_loss=0.02929, over 7201.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03144, over 1352012.52 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:31:20,880 INFO [train.py:763] (5/8) Epoch 29, batch 650, loss[loss=0.1563, simple_loss=0.255, pruned_loss=0.02881, over 7058.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03136, over 1366955.25 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:32:27,048 INFO [train.py:763] (5/8) Epoch 29, batch 700, loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03443, over 7320.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2627, pruned_loss=0.0315, over 1375809.55 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:33:32,286 INFO [train.py:763] (5/8) Epoch 29, batch 750, loss[loss=0.165, simple_loss=0.2738, pruned_loss=0.02817, over 7238.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03188, over 1382713.49 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:34:37,543 INFO [train.py:763] (5/8) Epoch 29, batch 800, loss[loss=0.1497, simple_loss=0.2468, pruned_loss=0.02626, over 7332.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.03152, over 1388650.88 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:35:43,025 INFO [train.py:763] (5/8) Epoch 29, batch 850, loss[loss=0.1559, simple_loss=0.2504, pruned_loss=0.03069, over 7062.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03123, over 1397806.94 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:36:48,532 INFO [train.py:763] (5/8) Epoch 29, batch 900, loss[loss=0.1632, simple_loss=0.272, pruned_loss=0.02724, over 7220.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2616, pruned_loss=0.03147, over 1401643.82 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:37:53,951 INFO [train.py:763] (5/8) Epoch 29, batch 950, loss[loss=0.1722, simple_loss=0.2731, pruned_loss=0.03566, over 7107.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03165, over 1407461.76 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:38:59,978 INFO [train.py:763] (5/8) Epoch 29, batch 1000, loss[loss=0.1538, simple_loss=0.2612, pruned_loss=0.0232, over 7149.00 frames.], tot_loss[loss=0.164, simple_loss=0.2639, pruned_loss=0.03204, over 1411344.24 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:40:06,275 INFO [train.py:763] (5/8) Epoch 29, batch 1050, loss[loss=0.1197, simple_loss=0.2205, pruned_loss=0.009428, over 7289.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03201, over 1407759.69 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:41:11,509 INFO [train.py:763] (5/8) Epoch 29, batch 1100, loss[loss=0.1683, simple_loss=0.2785, pruned_loss=0.02907, over 7335.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2652, pruned_loss=0.03251, over 1416903.76 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:42:16,631 INFO [train.py:763] (5/8) Epoch 29, batch 1150, loss[loss=0.1502, simple_loss=0.2381, pruned_loss=0.03122, over 6999.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2653, pruned_loss=0.03256, over 1417393.38 frames.], batch size: 16, lr: 2.61e-04
2022-04-30 08:43:21,918 INFO [train.py:763] (5/8) Epoch 29, batch 1200, loss[loss=0.1487, simple_loss=0.244, pruned_loss=0.02674, over 7164.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2647, pruned_loss=0.03228, over 1422479.47 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:44:27,480 INFO [train.py:763] (5/8) Epoch 29, batch 1250, loss[loss=0.2034, simple_loss=0.3016, pruned_loss=0.05256, over 5097.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2647, pruned_loss=0.03246, over 1417635.21 frames.], batch size: 52, lr: 2.60e-04
2022-04-30 08:45:34,627 INFO [train.py:763] (5/8) Epoch 29, batch 1300, loss[loss=0.1458, simple_loss=0.2525, pruned_loss=0.01959, over 7335.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2638, pruned_loss=0.03178, over 1418658.47 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 08:46:42,256 INFO [train.py:763] (5/8) Epoch 29, batch 1350, loss[loss=0.1738, simple_loss=0.2809, pruned_loss=0.03332, over 6278.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2634, pruned_loss=0.03153, over 1419102.14 frames.], batch size: 37, lr: 2.60e-04
2022-04-30 08:47:48,990 INFO [train.py:763] (5/8) Epoch 29, batch 1400, loss[loss=0.155, simple_loss=0.2394, pruned_loss=0.03535, over 6764.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03146, over 1419573.60 frames.], batch size: 15, lr: 2.60e-04
2022-04-30 08:48:56,322 INFO [train.py:763] (5/8) Epoch 29, batch 1450, loss[loss=0.1482, simple_loss=0.251, pruned_loss=0.02271, over 7453.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.0315, over 1419152.60 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 08:50:03,418 INFO [train.py:763] (5/8) Epoch 29, batch 1500, loss[loss=0.1722, simple_loss=0.277, pruned_loss=0.03372, over 7256.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03174, over 1417641.94 frames.], batch size: 19, lr: 2.60e-04
2022-04-30 08:51:10,023 INFO [train.py:763] (5/8) Epoch 29, batch 1550, loss[loss=0.1882, simple_loss=0.2838, pruned_loss=0.04631, over 7214.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03173, over 1418378.41 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 08:52:17,012 INFO [train.py:763] (5/8) Epoch 29, batch 1600, loss[loss=0.1667, simple_loss=0.273, pruned_loss=0.03019, over 7326.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2636, pruned_loss=0.03183, over 1419643.22 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:53:22,977 INFO [train.py:763] (5/8) Epoch 29, batch 1650, loss[loss=0.1932, simple_loss=0.2904, pruned_loss=0.04804, over 7166.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03185, over 1423517.47 frames.], batch size: 26, lr: 2.60e-04
2022-04-30 08:54:28,295 INFO [train.py:763] (5/8) Epoch 29, batch 1700, loss[loss=0.1607, simple_loss=0.2574, pruned_loss=0.03202, over 7147.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03208, over 1426523.39 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 08:55:35,298 INFO [train.py:763] (5/8) Epoch 29, batch 1750, loss[loss=0.1741, simple_loss=0.2743, pruned_loss=0.03696, over 7147.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2639, pruned_loss=0.03217, over 1423688.57 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 08:56:42,237 INFO [train.py:763] (5/8) Epoch 29, batch 1800, loss[loss=0.2018, simple_loss=0.2972, pruned_loss=0.05314, over 5172.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03195, over 1421262.69 frames.], batch size: 53, lr: 2.60e-04
2022-04-30 08:57:49,304 INFO [train.py:763] (5/8) Epoch 29, batch 1850, loss[loss=0.2058, simple_loss=0.2979, pruned_loss=0.05684, over 7116.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.0318, over 1425025.96 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:58:55,870 INFO [train.py:763] (5/8) Epoch 29, batch 1900, loss[loss=0.1395, simple_loss=0.2378, pruned_loss=0.02058, over 7250.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2629, pruned_loss=0.03178, over 1427599.46 frames.], batch size: 16, lr: 2.60e-04
2022-04-30 09:00:01,480 INFO [train.py:763] (5/8) Epoch 29, batch 1950, loss[loss=0.143, simple_loss=0.2397, pruned_loss=0.02317, over 7256.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03172, over 1428905.50 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:01:06,705 INFO [train.py:763] (5/8) Epoch 29, batch 2000, loss[loss=0.1489, simple_loss=0.2363, pruned_loss=0.03074, over 7332.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2626, pruned_loss=0.03182, over 1430104.46 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 09:02:12,110 INFO [train.py:763] (5/8) Epoch 29, batch 2050, loss[loss=0.1943, simple_loss=0.2863, pruned_loss=0.05113, over 7204.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03196, over 1430383.05 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 09:03:17,250 INFO [train.py:763] (5/8) Epoch 29, batch 2100, loss[loss=0.1513, simple_loss=0.2512, pruned_loss=0.02569, over 7145.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03173, over 1429155.41 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 09:04:22,319 INFO [train.py:763] (5/8) Epoch 29, batch 2150, loss[loss=0.1606, simple_loss=0.2551, pruned_loss=0.03303, over 7122.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.0316, over 1428162.38 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:05:27,764 INFO [train.py:763] (5/8) Epoch 29, batch 2200, loss[loss=0.1557, simple_loss=0.2738, pruned_loss=0.01881, over 7279.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03169, over 1423780.69 frames.], batch size: 24, lr: 2.60e-04
2022-04-30 09:06:32,915 INFO [train.py:763] (5/8) Epoch 29, batch 2250, loss[loss=0.2009, simple_loss=0.307, pruned_loss=0.04744, over 7161.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03175, over 1422259.44 frames.], batch size: 26, lr: 2.59e-04
2022-04-30 09:07:38,521 INFO [train.py:763] (5/8) Epoch 29, batch 2300, loss[loss=0.1525, simple_loss=0.2534, pruned_loss=0.02574, over 7318.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2635, pruned_loss=0.03152, over 1418819.14 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:08:43,835 INFO [train.py:763] (5/8) Epoch 29, batch 2350, loss[loss=0.1731, simple_loss=0.2859, pruned_loss=0.03018, over 7337.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03128, over 1420371.24 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:09:49,533 INFO [train.py:763] (5/8) Epoch 29, batch 2400, loss[loss=0.2045, simple_loss=0.3028, pruned_loss=0.05312, over 7278.00 frames.], tot_loss[loss=0.163, simple_loss=0.2634, pruned_loss=0.03129, over 1422368.84 frames.], batch size: 25, lr: 2.59e-04
2022-04-30 09:10:55,178 INFO [train.py:763] (5/8) Epoch 29, batch 2450, loss[loss=0.1679, simple_loss=0.2815, pruned_loss=0.02717, over 7150.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.03087, over 1426338.99 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:12:00,716 INFO [train.py:763] (5/8) Epoch 29, batch 2500, loss[loss=0.1474, simple_loss=0.2373, pruned_loss=0.02873, over 7244.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03109, over 1429869.24 frames.], batch size: 16, lr: 2.59e-04
2022-04-30 09:13:06,083 INFO [train.py:763] (5/8) Epoch 29, batch 2550, loss[loss=0.1611, simple_loss=0.2518, pruned_loss=0.03519, over 7425.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03123, over 1427273.20 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:14:11,177 INFO [train.py:763] (5/8) Epoch 29, batch 2600, loss[loss=0.1743, simple_loss=0.2799, pruned_loss=0.03433, over 7123.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03122, over 1426819.15 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:15:16,457 INFO [train.py:763] (5/8) Epoch 29, batch 2650, loss[loss=0.1343, simple_loss=0.2266, pruned_loss=0.02103, over 7135.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03075, over 1428895.45 frames.], batch size: 17, lr: 2.59e-04
2022-04-30 09:16:21,504 INFO [train.py:763] (5/8) Epoch 29, batch 2700, loss[loss=0.1623, simple_loss=0.2722, pruned_loss=0.02622, over 7118.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2626, pruned_loss=0.0311, over 1428919.43 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:17:27,807 INFO [train.py:763] (5/8) Epoch 29, batch 2750, loss[loss=0.1525, simple_loss=0.256, pruned_loss=0.0245, over 7234.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03164, over 1424477.95 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:18:33,551 INFO [train.py:763] (5/8) Epoch 29, batch 2800, loss[loss=0.1849, simple_loss=0.2776, pruned_loss=0.04615, over 7332.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2632, pruned_loss=0.03156, over 1423644.33 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:19:39,986 INFO [train.py:763] (5/8) Epoch 29, batch 2850, loss[loss=0.1558, simple_loss=0.2565, pruned_loss=0.02761, over 7231.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03121, over 1418106.37 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:20:45,398 INFO [train.py:763] (5/8) Epoch 29, batch 2900, loss[loss=0.149, simple_loss=0.2414, pruned_loss=0.02831, over 7014.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03108, over 1420467.28 frames.], batch size: 16, lr: 2.59e-04
2022-04-30 09:22:01,687 INFO [train.py:763] (5/8) Epoch 29, batch 2950, loss[loss=0.1768, simple_loss=0.2735, pruned_loss=0.04008, over 6478.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03051, over 1421982.26 frames.], batch size: 37, lr: 2.59e-04
2022-04-30 09:23:07,153 INFO [train.py:763] (5/8) Epoch 29, batch 3000, loss[loss=0.1843, simple_loss=0.2822, pruned_loss=0.0432, over 7121.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03066, over 1424754.20 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:23:07,154 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 09:23:22,371 INFO [train.py:792] (5/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
2022-04-30 09:24:27,452 INFO [train.py:763] (5/8) Epoch 29, batch 3050, loss[loss=0.1688, simple_loss=0.2792, pruned_loss=0.02917, over 7118.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03056, over 1426235.22 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:25:32,597 INFO [train.py:763] (5/8) Epoch 29, batch 3100, loss[loss=0.1618, simple_loss=0.2675, pruned_loss=0.02805, over 7411.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2624, pruned_loss=0.03063, over 1426653.21 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:26:38,425 INFO [train.py:763] (5/8) Epoch 29, batch 3150, loss[loss=0.1448, simple_loss=0.2335, pruned_loss=0.02805, over 7164.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.0307, over 1422601.62 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:27:44,835 INFO [train.py:763] (5/8) Epoch 29, batch 3200, loss[loss=0.1537, simple_loss=0.2533, pruned_loss=0.02707, over 7256.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03041, over 1425293.28 frames.], batch size: 19, lr: 2.59e-04
2022-04-30 09:28:51,983 INFO [train.py:763] (5/8) Epoch 29, batch 3250, loss[loss=0.1472, simple_loss=0.2581, pruned_loss=0.0182, over 7049.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.03089, over 1420280.31 frames.], batch size: 28, lr: 2.59e-04
2022-04-30 09:29:57,734 INFO [train.py:763] (5/8) Epoch 29, batch 3300, loss[loss=0.1573, simple_loss=0.2692, pruned_loss=0.02275, over 7328.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03073, over 1423359.66 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:31:03,719 INFO [train.py:763] (5/8) Epoch 29, batch 3350, loss[loss=0.1354, simple_loss=0.2302, pruned_loss=0.02026, over 7302.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2605, pruned_loss=0.03101, over 1427808.21 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:32:09,343 INFO [train.py:763] (5/8) Epoch 29, batch 3400, loss[loss=0.1652, simple_loss=0.2688, pruned_loss=0.03075, over 5065.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2608, pruned_loss=0.03116, over 1423829.20 frames.], batch size: 52, lr: 2.58e-04
2022-04-30 09:33:15,082 INFO [train.py:763] (5/8) Epoch 29, batch 3450, loss[loss=0.171, simple_loss=0.2738, pruned_loss=0.03411, over 7318.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2603, pruned_loss=0.03095, over 1420752.46 frames.], batch size: 24, lr: 2.58e-04
2022-04-30 09:34:21,151 INFO [train.py:763] (5/8) Epoch 29, batch 3500, loss[loss=0.1911, simple_loss=0.2962, pruned_loss=0.04303, over 7170.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03096, over 1423237.23 frames.], batch size: 26, lr: 2.58e-04
2022-04-30 09:35:26,539 INFO [train.py:763] (5/8) Epoch 29, batch 3550, loss[loss=0.1575, simple_loss=0.2484, pruned_loss=0.03331, over 7164.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03096, over 1422267.76 frames.], batch size: 18, lr: 2.58e-04
2022-04-30 09:36:32,242 INFO [train.py:763] (5/8) Epoch 29, batch 3600, loss[loss=0.1266, simple_loss=0.2259, pruned_loss=0.01365, over 7265.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03105, over 1426924.42 frames.], batch size: 19, lr: 2.58e-04
2022-04-30 09:37:46,880 INFO [train.py:763] (5/8) Epoch 29, batch 3650, loss[loss=0.1709, simple_loss=0.2831, pruned_loss=0.02931, over 6902.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.031, over 1428807.97 frames.], batch size: 31, lr: 2.58e-04
2022-04-30 09:38:52,220 INFO [train.py:763] (5/8) Epoch 29, batch 3700, loss[loss=0.1366, simple_loss=0.2203, pruned_loss=0.02643, over 7284.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03092, over 1429819.41 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:39:59,161 INFO [train.py:763] (5/8) Epoch 29, batch 3750, loss[loss=0.1632, simple_loss=0.2638, pruned_loss=0.03127, over 7086.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03113, over 1432188.61 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:41:05,875 INFO [train.py:763] (5/8) Epoch 29, batch 3800, loss[loss=0.164, simple_loss=0.2711, pruned_loss=0.02852, over 7204.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03119, over 1425052.86 frames.], batch size: 22, lr: 2.58e-04
2022-04-30 09:42:11,186 INFO [train.py:763] (5/8) Epoch 29, batch 3850, loss[loss=0.1231, simple_loss=0.21, pruned_loss=0.0181, over 7166.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03113, over 1426136.39 frames.], batch size: 16, lr: 2.58e-04
2022-04-30 09:43:16,818 INFO [train.py:763] (5/8) Epoch 29, batch 3900, loss[loss=0.1455, simple_loss=0.2347, pruned_loss=0.02814, over 7142.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03166, over 1426301.58 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:44:22,590 INFO [train.py:763] (5/8) Epoch 29, batch 3950, loss[loss=0.163, simple_loss=0.2658, pruned_loss=0.03013, over 7389.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03171, over 1420414.49 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:45:27,975 INFO [train.py:763] (5/8) Epoch 29, batch 4000, loss[loss=0.1554, simple_loss=0.2528, pruned_loss=0.02902, over 7294.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2645, pruned_loss=0.03226, over 1418693.36 frames.], batch size: 25, lr: 2.58e-04
2022-04-30 09:46:33,252 INFO [train.py:763] (5/8) Epoch 29, batch 4050, loss[loss=0.1746, simple_loss=0.2778, pruned_loss=0.03567, over 7095.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03228, over 1418536.82 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:47:39,305 INFO [train.py:763] (5/8) Epoch 29, batch 4100, loss[loss=0.1716, simple_loss=0.2788, pruned_loss=0.0322, over 7318.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.032, over 1420873.36 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:48:45,605 INFO [train.py:763] (5/8) Epoch 29, batch 4150, loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03324, over 7219.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2617, pruned_loss=0.03163, over 1422121.54 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:50:00,125 INFO [train.py:763] (5/8) Epoch 29, batch 4200, loss[loss=0.1543, simple_loss=0.2495, pruned_loss=0.02953, over 7446.00 frames.], tot_loss[loss=0.1629, simple_loss=0.262, pruned_loss=0.03191, over 1422992.67 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:51:13,967 INFO [train.py:763] (5/8) Epoch 29, batch 4250, loss[loss=0.1668, simple_loss=0.2669, pruned_loss=0.0334, over 7382.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03236, over 1417970.40 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:52:28,886 INFO [train.py:763] (5/8) Epoch 29, batch 4300, loss[loss=0.1583, simple_loss=0.2509, pruned_loss=0.0329, over 7266.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03189, over 1421220.91 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:53:43,997 INFO [train.py:763] (5/8) Epoch 29, batch 4350, loss[loss=0.1708, simple_loss=0.279, pruned_loss=0.03128, over 7230.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2625, pruned_loss=0.03204, over 1423386.35 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:54:58,500 INFO [train.py:763] (5/8) Epoch 29, batch 4400, loss[loss=0.1727, simple_loss=0.2655, pruned_loss=0.03989, over 7232.00 frames.], tot_loss[loss=0.163, simple_loss=0.2621, pruned_loss=0.03191, over 1419089.66 frames.], batch size: 20, lr: 2.57e-04
2022-04-30 09:56:12,790 INFO [train.py:763] (5/8) Epoch 29, batch 4450, loss[loss=0.1882, simple_loss=0.2906, pruned_loss=0.04287, over 6444.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.0314, over 1413068.17 frames.], batch size: 37, lr: 2.57e-04
2022-04-30 09:57:17,985 INFO [train.py:763] (5/8) Epoch 29, batch 4500, loss[loss=0.2118, simple_loss=0.3033, pruned_loss=0.06019, over 4984.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03177, over 1397904.05 frames.], batch size: 52, lr: 2.57e-04
2022-04-30 09:58:32,307 INFO [train.py:763] (5/8) Epoch 29, batch 4550, loss[loss=0.2035, simple_loss=0.2858, pruned_loss=0.06058, over 5006.00 frames.], tot_loss[loss=0.166, simple_loss=0.2656, pruned_loss=0.03317, over 1357000.74 frames.], batch size: 52, lr: 2.57e-04
2022-04-30 10:00:01,322 INFO [train.py:763] (5/8) Epoch 30, batch 0, loss[loss=0.1515, simple_loss=0.2412, pruned_loss=0.03089, over 7333.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2412, pruned_loss=0.03089, over 7333.00 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:01:06,995 INFO [train.py:763] (5/8) Epoch 30, batch 50, loss[loss=0.1719, simple_loss=0.2783, pruned_loss=0.0328, over 7258.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2625, pruned_loss=0.03359, over 317315.77 frames.], batch size: 19, lr: 2.53e-04
2022-04-30 10:02:12,188 INFO [train.py:763] (5/8) Epoch 30, batch 100, loss[loss=0.1696, simple_loss=0.2759, pruned_loss=0.03164, over 7374.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2638, pruned_loss=0.0317, over 561114.77 frames.], batch size: 23, lr: 2.53e-04
2022-04-30 10:03:17,813 INFO [train.py:763] (5/8) Epoch 30, batch 150, loss[loss=0.176, simple_loss=0.2686, pruned_loss=0.04167, over 7194.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03082, over 756395.99 frames.], batch size: 22, lr: 2.53e-04
2022-04-30 10:04:23,878 INFO [train.py:763] (5/8) Epoch 30, batch 200, loss[loss=0.1887, simple_loss=0.2772, pruned_loss=0.0501, over 4915.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.03049, over 900855.89 frames.], batch size: 54, lr: 2.53e-04
2022-04-30 10:05:30,041 INFO [train.py:763] (5/8) Epoch 30, batch 250, loss[loss=0.1609, simple_loss=0.2635, pruned_loss=0.02911, over 7261.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2639, pruned_loss=0.03129, over 1015583.93 frames.], batch size: 25, lr: 2.53e-04
2022-04-30 10:06:35,958 INFO [train.py:763] (5/8) Epoch 30, batch 300, loss[loss=0.1652, simple_loss=0.268, pruned_loss=0.03121, over 7327.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2637, pruned_loss=0.03137, over 1106796.08 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:07:41,458 INFO [train.py:763] (5/8) Epoch 30, batch 350, loss[loss=0.1307, simple_loss=0.2266, pruned_loss=0.0174, over 7161.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2632, pruned_loss=0.03097, over 1173815.12 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:08:46,858 INFO [train.py:763] (5/8) Epoch 30, batch 400, loss[loss=0.1577, simple_loss=0.2614, pruned_loss=0.02703, over 7220.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2626, pruned_loss=0.03089, over 1224881.96 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:09:52,327 INFO [train.py:763] (5/8) Epoch 30, batch 450, loss[loss=0.2165, simple_loss=0.3153, pruned_loss=0.05879, over 7156.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2632, pruned_loss=0.03119, over 1266203.99 frames.], batch size: 26, lr: 2.53e-04
2022-04-30 10:10:57,866 INFO [train.py:763] (5/8) Epoch 30, batch 500, loss[loss=0.1278, simple_loss=0.2171, pruned_loss=0.01928, over 7265.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03121, over 1301214.02 frames.], batch size: 17, lr: 2.53e-04
2022-04-30 10:12:03,594 INFO [train.py:763] (5/8) Epoch 30, batch 550, loss[loss=0.1986, simple_loss=0.3037, pruned_loss=0.04676, over 7414.00 frames.], tot_loss[loss=0.1629, simple_loss=0.263, pruned_loss=0.0314, over 1328654.13 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:13:09,443 INFO [train.py:763] (5/8) Epoch 30, batch 600, loss[loss=0.153, simple_loss=0.2434, pruned_loss=0.03131, over 7067.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2633, pruned_loss=0.03144, over 1348602.96 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:14:15,866 INFO [train.py:763] (5/8) Epoch 30, batch 650, loss[loss=0.1738, simple_loss=0.2812, pruned_loss=0.03325, over 7145.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03139, over 1370052.40 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:15:21,901 INFO [train.py:763] (5/8) Epoch 30, batch 700, loss[loss=0.1233, simple_loss=0.2183, pruned_loss=0.0142, over 7204.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03132, over 1379967.24 frames.], batch size: 16, lr: 2.52e-04
2022-04-30 10:16:28,673 INFO [train.py:763] (5/8) Epoch 30, batch 750, loss[loss=0.1604, simple_loss=0.2706, pruned_loss=0.02517, over 7234.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03107, over 1388245.11 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:17:34,229 INFO [train.py:763] (5/8) Epoch 30, batch 800, loss[loss=0.1528, simple_loss=0.2566, pruned_loss=0.0245, over 7316.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03154, over 1396010.62 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:18:39,967 INFO [train.py:763] (5/8) Epoch 30, batch 850, loss[loss=0.1483, simple_loss=0.2466, pruned_loss=0.02494, over 7440.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03134, over 1399183.88 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:19:45,743 INFO [train.py:763] (5/8) Epoch 30, batch 900, loss[loss=0.1587, simple_loss=0.247, pruned_loss=0.03519, over 6840.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03125, over 1403767.49 frames.], batch size: 15, lr: 2.52e-04
2022-04-30 10:20:52,504 INFO [train.py:763] (5/8) Epoch 30, batch 950, loss[loss=0.1908, simple_loss=0.2997, pruned_loss=0.04098, over 7061.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03123, over 1405447.90 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:21:58,503 INFO [train.py:763] (5/8) Epoch 30, batch 1000, loss[loss=0.1749, simple_loss=0.2823, pruned_loss=0.03376, over 7340.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03134, over 1407604.68 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:23:03,974 INFO [train.py:763] (5/8) Epoch 30, batch 1050, loss[loss=0.1824, simple_loss=0.2814, pruned_loss=0.04167, over 7043.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03117, over 1410858.19 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:24:09,740 INFO [train.py:763] (5/8) Epoch 30, batch 1100, loss[loss=0.1552, simple_loss=0.2591, pruned_loss=0.02562, over 7061.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03075, over 1415003.92 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:25:15,769 INFO [train.py:763] (5/8) Epoch 30, batch 1150, loss[loss=0.1459, simple_loss=0.2404, pruned_loss=0.02572, over 7457.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03115, over 1417315.40 frames.], batch size: 19, lr: 2.52e-04
2022-04-30 10:26:21,666 INFO [train.py:763] (5/8) Epoch 30, batch 1200, loss[loss=0.171, simple_loss=0.27, pruned_loss=0.03595, over 7196.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03139, over 1419218.87 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:27:27,468 INFO [train.py:763] (5/8) Epoch 30, batch 1250, loss[loss=0.1569, simple_loss=0.253, pruned_loss=0.0304, over 7404.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2632, pruned_loss=0.03171, over 1418608.42 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:28:33,939 INFO [train.py:763] (5/8) Epoch 30, batch 1300, loss[loss=0.1842, simple_loss=0.2898, pruned_loss=0.03925, over 7203.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2633, pruned_loss=0.03175, over 1418174.89 frames.], batch size: 26, lr: 2.52e-04
2022-04-30 10:29:40,257 INFO [train.py:763] (5/8) Epoch 30, batch 1350, loss[loss=0.1338, simple_loss=0.2222, pruned_loss=0.02272, over 7133.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2644, pruned_loss=0.03204, over 1415153.26 frames.], batch size: 17, lr: 2.52e-04
2022-04-30 10:30:45,705 INFO [train.py:763] (5/8) Epoch 30, batch 1400, loss[loss=0.1598, simple_loss=0.2647, pruned_loss=0.02749, over 7348.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2642, pruned_loss=0.03197, over 1418926.83 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:31:51,071 INFO [train.py:763] (5/8) Epoch 30, batch 1450, loss[loss=0.1598, simple_loss=0.2628, pruned_loss=0.02835, over 7138.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2636, pruned_loss=0.03152, over 1419736.51 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:32:56,520 INFO [train.py:763] (5/8) Epoch 30, batch 1500, loss[loss=0.1708, simple_loss=0.281, pruned_loss=0.03033, over 7304.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2642, pruned_loss=0.03156, over 1425535.53 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:34:02,187 INFO [train.py:763] (5/8) Epoch 30, batch 1550, loss[loss=0.1615, simple_loss=0.2586, pruned_loss=0.03216, over 7277.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2629, pruned_loss=0.03138, over 1427171.71 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:35:07,685 INFO [train.py:763] (5/8) Epoch 30, batch 1600, loss[loss=0.1707, simple_loss=0.2712, pruned_loss=0.03512, over 7265.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2623, pruned_loss=0.03103, over 1428283.72 frames.], batch size: 19, lr: 2.52e-04
2022-04-30 10:36:13,954 INFO [train.py:763] (5/8) Epoch 30, batch 1650, loss[loss=0.1535, simple_loss=0.2588, pruned_loss=0.02412, over 7113.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2629, pruned_loss=0.03071, over 1428306.53 frames.], batch size: 21, lr: 2.52e-04
2022-04-30 10:37:20,419 INFO [train.py:763] (5/8) Epoch 30, batch 1700, loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.03564, over 7292.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03093, over 1425172.13 frames.], batch size: 24, lr: 2.52e-04
2022-04-30 10:38:27,159 INFO [train.py:763] (5/8) Epoch 30, batch 1750, loss[loss=0.1774, simple_loss=0.2731, pruned_loss=0.04084, over 7392.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2622, pruned_loss=0.031, over 1427411.59 frames.], batch size: 23, lr: 2.52e-04
2022-04-30 10:39:33,079 INFO [train.py:763] (5/8) Epoch 30, batch 1800, loss[loss=0.1653, simple_loss=0.2609, pruned_loss=0.03479, over 7430.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.03076, over 1422986.38 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:40:39,000 INFO [train.py:763] (5/8) Epoch 30, batch 1850, loss[loss=0.1235, simple_loss=0.2179, pruned_loss=0.01452, over 7144.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.03102, over 1421183.57 frames.], batch size: 17, lr: 2.51e-04
2022-04-30 10:41:45,833 INFO [train.py:763] (5/8) Epoch 30, batch 1900, loss[loss=0.1642, simple_loss=0.2719, pruned_loss=0.02822, over 7326.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.0308, over 1425036.44 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:42:51,813 INFO [train.py:763] (5/8) Epoch 30, batch 1950, loss[loss=0.163, simple_loss=0.2713, pruned_loss=0.02738, over 7384.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03094, over 1425380.03 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:43:59,480 INFO [train.py:763] (5/8) Epoch 30, batch 2000, loss[loss=0.1911, simple_loss=0.2841, pruned_loss=0.04907, over 7165.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03038, over 1427444.02 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:45:05,778 INFO [train.py:763] (5/8) Epoch 30, batch 2050, loss[loss=0.1996, simple_loss=0.2975, pruned_loss=0.05085, over 7200.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03024, over 1424672.72 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:46:11,295 INFO [train.py:763] (5/8) Epoch 30, batch 2100, loss[loss=0.1804, simple_loss=0.2766, pruned_loss=0.04212, over 7152.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03034, over 1423022.18 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:47:17,306 INFO [train.py:763] (5/8) Epoch 30, batch 2150, loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.02895, over 7166.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02994, over 1427134.13 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:48:22,851 INFO [train.py:763] (5/8) Epoch 30, batch 2200, loss[loss=0.1457, simple_loss=0.243, pruned_loss=0.0242, over 7070.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03026, over 1428600.17 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:49:28,458 INFO [train.py:763] (5/8) Epoch 30, batch 2250, loss[loss=0.1975, simple_loss=0.2898, pruned_loss=0.0526, over 7195.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2623, pruned_loss=0.03075, over 1428336.38 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:50:34,518 INFO [train.py:763] (5/8) Epoch 30, batch 2300, loss[loss=0.1704, simple_loss=0.2667, pruned_loss=0.03704, over 7250.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2627, pruned_loss=0.03106, over 1430368.74 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:51:40,506 INFO [train.py:763] (5/8) Epoch 30, batch 2350, loss[loss=0.1491, simple_loss=0.2469, pruned_loss=0.02562, over 7073.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2624, pruned_loss=0.03108, over 1429928.37 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:52:46,211 INFO [train.py:763] (5/8) Epoch 30, batch 2400, loss[loss=0.1472, simple_loss=0.2426, pruned_loss=0.02585, over 7215.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03138, over 1428086.23 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:53:51,760 INFO [train.py:763] (5/8) Epoch 30, batch 2450, loss[loss=0.1496, simple_loss=0.2589, pruned_loss=0.02014, over 7221.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03122, over 1423764.32 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:54:57,040 INFO [train.py:763] (5/8) Epoch 30, batch 2500, loss[loss=0.1573, simple_loss=0.2663, pruned_loss=0.0242, over 7340.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.03123, over 1426610.80 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:56:03,561 INFO [train.py:763] (5/8) Epoch 30, batch 2550, loss[loss=0.2048, simple_loss=0.3088, pruned_loss=0.05035, over 7219.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03099, over 1428257.95 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:57:09,410 INFO [train.py:763] (5/8) Epoch 30, batch 2600, loss[loss=0.1498, simple_loss=0.2416, pruned_loss=0.02899, over 7409.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03121, over 1427321.86 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:58:15,107 INFO [train.py:763] (5/8) Epoch 30, batch 2650, loss[loss=0.1776, simple_loss=0.278, pruned_loss=0.03856, over 7414.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.03129, over 1424598.03 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:59:20,475 INFO [train.py:763] (5/8) Epoch 30, batch 2700, loss[loss=0.1639, simple_loss=0.2728, pruned_loss=0.02743, over 7267.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.03104, over 1418215.97 frames.], batch size: 25, lr: 2.51e-04
2022-04-30 11:00:26,179 INFO [train.py:763] (5/8) Epoch 30, batch 2750, loss[loss=0.1495, simple_loss=0.2506, pruned_loss=0.02422, over 7152.00 frames.], tot_loss[loss=0.162, simple_loss=0.262, pruned_loss=0.03097, over 1418848.15 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 11:01:31,738 INFO [train.py:763] (5/8) Epoch 30, batch 2800, loss[loss=0.1483, simple_loss=0.2427, pruned_loss=0.02697, over 7159.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03141, over 1421225.88 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 11:02:36,841 INFO [train.py:763] (5/8) Epoch 30, batch 2850, loss[loss=0.1804, simple_loss=0.2838, pruned_loss=0.03847, over 7196.00 frames.], tot_loss[loss=0.1631, simple_loss=0.263, pruned_loss=0.0316, over 1419179.11 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 11:03:42,118 INFO [train.py:763] (5/8) Epoch 30, batch 2900, loss[loss=0.1798, simple_loss=0.2819, pruned_loss=0.0389, over 7112.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2626, pruned_loss=0.03132, over 1423510.01 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 11:04:47,462 INFO [train.py:763] (5/8) Epoch 30, batch 2950, loss[loss=0.1541, simple_loss=0.2525, pruned_loss=0.02783, over 7247.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03103, over 1422458.75 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:05:53,069 INFO [train.py:763] (5/8) Epoch 30, batch 3000, loss[loss=0.1648, simple_loss=0.2681, pruned_loss=0.03069, over 7330.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03092, over 1421760.09 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:05:53,070 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 11:06:08,154 INFO [train.py:792] (5/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
2022-04-30 11:07:13,676 INFO [train.py:763] (5/8) Epoch 30, batch 3050, loss[loss=0.1326, simple_loss=0.2216, pruned_loss=0.02175, over 6999.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2627, pruned_loss=0.03148, over 1421537.91 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:08:19,236 INFO [train.py:763] (5/8) Epoch 30, batch 3100, loss[loss=0.1628, simple_loss=0.2747, pruned_loss=0.02542, over 7300.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03086, over 1425294.10 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:09:24,929 INFO [train.py:763] (5/8) Epoch 30, batch 3150, loss[loss=0.1603, simple_loss=0.2486, pruned_loss=0.03601, over 7001.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03102, over 1424588.08 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:10:31,197 INFO [train.py:763] (5/8) Epoch 30, batch 3200, loss[loss=0.1698, simple_loss=0.283, pruned_loss=0.02825, over 7203.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03088, over 1416862.53 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:11:37,945 INFO [train.py:763] (5/8) Epoch 30, batch 3250, loss[loss=0.1661, simple_loss=0.2765, pruned_loss=0.0279, over 7154.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.03131, over 1416306.72 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:12:45,390 INFO [train.py:763] (5/8) Epoch 30, batch 3300, loss[loss=0.1455, simple_loss=0.2312, pruned_loss=0.02993, over 7289.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2612, pruned_loss=0.0311, over 1422454.55 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:13:51,988 INFO [train.py:763] (5/8) Epoch 30, batch 3350, loss[loss=0.164, simple_loss=0.2649, pruned_loss=0.03155, over 7213.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.0312, over 1421969.02 frames.], batch size: 21, lr: 2.50e-04
2022-04-30 11:14:57,145 INFO [train.py:763] (5/8) Epoch 30, batch 3400, loss[loss=0.1719, simple_loss=0.2866, pruned_loss=0.02864, over 7320.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03056, over 1421056.22 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:16:02,387 INFO [train.py:763] (5/8) Epoch 30, batch 3450, loss[loss=0.1694, simple_loss=0.2707, pruned_loss=0.03405, over 6476.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03087, over 1425120.63 frames.], batch size: 38, lr: 2.50e-04
2022-04-30 11:17:08,609 INFO [train.py:763] (5/8) Epoch 30, batch 3500, loss[loss=0.1725, simple_loss=0.2773, pruned_loss=0.03391, over 7371.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.03082, over 1427113.99 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:18:14,703 INFO [train.py:763] (5/8) Epoch 30, batch 3550, loss[loss=0.1543, simple_loss=0.2464, pruned_loss=0.03115, over 7437.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03082, over 1428213.41 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:19:20,440 INFO [train.py:763] (5/8) Epoch 30, batch 3600, loss[loss=0.172, simple_loss=0.2665, pruned_loss=0.03876, over 7288.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2625, pruned_loss=0.03111, over 1422865.61 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:20:25,929 INFO [train.py:763] (5/8) Epoch 30, batch 3650, loss[loss=0.1435, simple_loss=0.2384, pruned_loss=0.02437, over 7127.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03082, over 1422516.53 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:21:32,104 INFO [train.py:763] (5/8) Epoch 30, batch 3700, loss[loss=0.1346, simple_loss=0.2307, pruned_loss=0.01924, over 7273.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03067, over 1425038.49 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:22:38,029 INFO [train.py:763] (5/8) Epoch 30, batch 3750, loss[loss=0.1552, simple_loss=0.2513, pruned_loss=0.02949, over 7260.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2605, pruned_loss=0.03067, over 1423298.85 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:23:45,287 INFO [train.py:763] (5/8) Epoch 30, batch 3800, loss[loss=0.1658, simple_loss=0.2496, pruned_loss=0.04099, over 7282.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2598, pruned_loss=0.03051, over 1424989.65 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:24:50,563 INFO [train.py:763] (5/8) Epoch 30, batch 3850, loss[loss=0.1513, simple_loss=0.2561, pruned_loss=0.02324, over 7062.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.0309, over 1424640.87 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:25:56,098 INFO [train.py:763] (5/8) Epoch 30, batch 3900, loss[loss=0.1663, simple_loss=0.27, pruned_loss=0.03129, over 7283.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.03088, over 1428488.99 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:27:01,588 INFO [train.py:763] (5/8) Epoch 30, batch 3950, loss[loss=0.1484, simple_loss=0.2385, pruned_loss=0.0291, over 7348.00 frames.], tot_loss[loss=0.161, simple_loss=0.2603, pruned_loss=0.03087, over 1428808.48 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:28:06,974 INFO [train.py:763] (5/8) Epoch 30, batch 4000, loss[loss=0.1356, simple_loss=0.2362, pruned_loss=0.0175, over 7161.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03118, over 1425999.23 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:29:11,961 INFO [train.py:763] (5/8) Epoch 30, batch 4050, loss[loss=0.1805, simple_loss=0.2746, pruned_loss=0.04317, over 7269.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03108, over 1425111.67 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:30:18,209 INFO [train.py:763] (5/8) Epoch 30, batch 4100, loss[loss=0.1827, simple_loss=0.2752, pruned_loss=0.04508, over 7152.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2617, pruned_loss=0.03095, over 1427085.00 frames.], batch size: 19, lr: 2.49e-04
2022-04-30 11:31:24,162 INFO [train.py:763] (5/8) Epoch 30, batch 4150, loss[loss=0.175, simple_loss=0.2784, pruned_loss=0.03577, over 7125.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03017, over 1428916.25 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:32:29,733 INFO [train.py:763] (5/8) Epoch 30, batch 4200, loss[loss=0.1298, simple_loss=0.2115, pruned_loss=0.02401, over 7266.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03006, over 1431404.21 frames.], batch size: 16, lr: 2.49e-04
2022-04-30 11:33:35,013 INFO [train.py:763] (5/8) Epoch 30, batch 4250, loss[loss=0.1496, simple_loss=0.2502, pruned_loss=0.02451, over 7195.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03029, over 1427657.99 frames.], batch size: 26, lr: 2.49e-04
2022-04-30 11:34:41,237 INFO [train.py:763] (5/8) Epoch 30, batch 4300, loss[loss=0.1741, simple_loss=0.287, pruned_loss=0.03061, over 7291.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03012, over 1430548.62 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:35:46,144 INFO [train.py:763] (5/8) Epoch 30, batch 4350, loss[loss=0.1402, simple_loss=0.2484, pruned_loss=0.01603, over 7108.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.0305, over 1421240.47 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:36:51,033 INFO [train.py:763] (5/8) Epoch 30, batch 4400, loss[loss=0.1616, simple_loss=0.2705, pruned_loss=0.02638, over 7115.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03044, over 1410362.22 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:37:56,310 INFO [train.py:763] (5/8) Epoch 30, batch 4450, loss[loss=0.1648, simple_loss=0.2647, pruned_loss=0.03241, over 6411.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03044, over 1409928.57 frames.], batch size: 37, lr: 2.49e-04
2022-04-30 11:39:02,211 INFO [train.py:763] (5/8) Epoch 30, batch 4500, loss[loss=0.1598, simple_loss=0.2637, pruned_loss=0.0279, over 6597.00 frames.], tot_loss[loss=0.162, simple_loss=0.262, pruned_loss=0.031, over 1385497.49 frames.], batch size: 38, lr: 2.49e-04
2022-04-30 11:40:07,230 INFO [train.py:763] (5/8) Epoch 30, batch 4550, loss[loss=0.1869, simple_loss=0.2855, pruned_loss=0.04412, over 4869.00 frames.], tot_loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03206, over 1355904.56 frames.], batch size: 52, lr: 2.49e-04
2022-04-30 11:41:35,695 INFO [train.py:763] (5/8) Epoch 31, batch 0, loss[loss=0.1724, simple_loss=0.2628, pruned_loss=0.04099, over 5241.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2628, pruned_loss=0.04099, over 5241.00 frames.], batch size: 52, lr: 2.45e-04
2022-04-30 11:42:41,160 INFO [train.py:763] (5/8) Epoch 31, batch 50, loss[loss=0.1722, simple_loss=0.2815, pruned_loss=0.03142, over 6457.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2664, pruned_loss=0.03154, over 320267.00 frames.], batch size: 38, lr: 2.45e-04
2022-04-30 11:43:46,473 INFO [train.py:763] (5/8) Epoch 31, batch 100, loss[loss=0.1648, simple_loss=0.2739, pruned_loss=0.02784, over 7318.00 frames.], tot_loss[loss=0.164, simple_loss=0.2642, pruned_loss=0.03188, over 567413.84 frames.], batch size: 25, lr: 2.45e-04
2022-04-30 11:44:52,573 INFO [train.py:763] (5/8) Epoch 31, batch 150, loss[loss=0.1947, simple_loss=0.2953, pruned_loss=0.04702, over 7139.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2617, pruned_loss=0.03055, over 758517.68 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:45:58,819 INFO [train.py:763] (5/8) Epoch 31, batch 200, loss[loss=0.1315, simple_loss=0.2311, pruned_loss=0.01595, over 6988.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.0302, over 902747.34 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:47:04,085 INFO [train.py:763] (5/8) Epoch 31, batch 250, loss[loss=0.1663, simple_loss=0.2679, pruned_loss=0.03239, over 7280.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03038, over 1022393.92 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:48:09,438 INFO [train.py:763] (5/8) Epoch 31, batch 300, loss[loss=0.1778, simple_loss=0.2771, pruned_loss=0.03921, over 7318.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03115, over 1113150.31 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:49:14,698 INFO [train.py:763] (5/8) Epoch 31, batch 350, loss[loss=0.1787, simple_loss=0.277, pruned_loss=0.04016, over 7059.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03122, over 1180952.66 frames.], batch size: 28, lr: 2.45e-04
2022-04-30 11:50:20,239 INFO [train.py:763] (5/8) Epoch 31, batch 400, loss[loss=0.1741, simple_loss=0.2774, pruned_loss=0.03539, over 7101.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.0311, over 1236521.11 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:51:25,629 INFO [train.py:763] (5/8) Epoch 31, batch 450, loss[loss=0.1654, simple_loss=0.2701, pruned_loss=0.03039, over 7325.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03039, over 1277304.03 frames.], batch size: 21, lr: 2.45e-04
2022-04-30 11:52:41,065 INFO [train.py:763] (5/8) Epoch 31, batch 500, loss[loss=0.164, simple_loss=0.2686, pruned_loss=0.0297, over 7336.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.03053, over 1313913.09 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:53:47,765 INFO [train.py:763] (5/8) Epoch 31, batch 550, loss[loss=0.1431, simple_loss=0.2525, pruned_loss=0.01688, over 7339.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03045, over 1342212.93 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:54:53,979 INFO [train.py:763] (5/8) Epoch 31, batch 600, loss[loss=0.1274, simple_loss=0.2261, pruned_loss=0.0144, over 7140.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03033, over 1364494.13 frames.], batch size: 17, lr: 2.45e-04
2022-04-30 11:55:59,912 INFO [train.py:763] (5/8) Epoch 31, batch 650, loss[loss=0.184, simple_loss=0.2696, pruned_loss=0.04919, over 6975.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2603, pruned_loss=0.03047, over 1379297.14 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:57:06,464 INFO [train.py:763] (5/8) Epoch 31, batch 700, loss[loss=0.1793, simple_loss=0.2856, pruned_loss=0.03646, over 7189.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03046, over 1387037.88 frames.], batch size: 23, lr: 2.45e-04
2022-04-30 11:58:13,272 INFO [train.py:763] (5/8) Epoch 31, batch 750, loss[loss=0.1638, simple_loss=0.2669, pruned_loss=0.03031, over 7113.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 1395081.63 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 11:59:18,739 INFO [train.py:763] (5/8) Epoch 31, batch 800, loss[loss=0.1381, simple_loss=0.231, pruned_loss=0.02264, over 7277.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2618, pruned_loss=0.03056, over 1399451.57 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:00:24,039 INFO [train.py:763] (5/8) Epoch 31, batch 850, loss[loss=0.1636, simple_loss=0.2639, pruned_loss=0.03168, over 7308.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2621, pruned_loss=0.03047, over 1407162.12 frames.], batch size: 25, lr: 2.44e-04
2022-04-30 12:01:28,733 INFO [train.py:763] (5/8) Epoch 31, batch 900, loss[loss=0.1614, simple_loss=0.2642, pruned_loss=0.02934, over 7332.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2633, pruned_loss=0.03106, over 1410360.46 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:02:34,062 INFO [train.py:763] (5/8) Epoch 31, batch 950, loss[loss=0.1485, simple_loss=0.2367, pruned_loss=0.0302, over 6828.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03103, over 1412126.82 frames.], batch size: 15, lr: 2.44e-04
2022-04-30 12:03:39,308 INFO [train.py:763] (5/8) Epoch 31, batch 1000, loss[loss=0.1412, simple_loss=0.2449, pruned_loss=0.01877, over 7421.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03083, over 1416210.29 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:04:53,742 INFO [train.py:763] (5/8) Epoch 31, batch 1050, loss[loss=0.1532, simple_loss=0.2531, pruned_loss=0.02661, over 7230.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.03098, over 1420029.23 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:05:59,158 INFO [train.py:763] (5/8) Epoch 31, batch 1100, loss[loss=0.1595, simple_loss=0.2635, pruned_loss=0.02781, over 7208.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03093, over 1417988.90 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:07:23,564 INFO [train.py:763] (5/8) Epoch 31, batch 1150, loss[loss=0.147, simple_loss=0.2365, pruned_loss=0.02873, over 7139.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03111, over 1421692.98 frames.], batch size: 17, lr: 2.44e-04
2022-04-30 12:08:30,105 INFO [train.py:763] (5/8) Epoch 31, batch 1200, loss[loss=0.1446, simple_loss=0.2495, pruned_loss=0.01986, over 7404.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2603, pruned_loss=0.03063, over 1424139.05 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:09:54,557 INFO [train.py:763] (5/8) Epoch 31, batch 1250, loss[loss=0.1948, simple_loss=0.3032, pruned_loss=0.04322, over 7201.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2605, pruned_loss=0.03086, over 1416958.57 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:11:00,229 INFO [train.py:763] (5/8) Epoch 31, batch 1300, loss[loss=0.1826, simple_loss=0.294, pruned_loss=0.03557, over 7150.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2605, pruned_loss=0.03084, over 1422231.01 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:12:14,870 INFO [train.py:763] (5/8) Epoch 31, batch 1350, loss[loss=0.1577, simple_loss=0.2496, pruned_loss=0.03287, over 7335.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2605, pruned_loss=0.03092, over 1420327.76 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:13:22,480 INFO [train.py:763] (5/8) Epoch 31, batch 1400, loss[loss=0.1518, simple_loss=0.2545, pruned_loss=0.02456, over 7231.00 frames.], tot_loss[loss=0.1606, simple_loss=0.26, pruned_loss=0.03065, over 1420546.55 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:14:38,784 INFO [train.py:763] (5/8) Epoch 31, batch 1450, loss[loss=0.1405, simple_loss=0.2371, pruned_loss=0.02189, over 7336.00 frames.], tot_loss[loss=0.1614, simple_loss=0.261, pruned_loss=0.03097, over 1422447.81 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:15:46,115 INFO [train.py:763] (5/8) Epoch 31, batch 1500, loss[loss=0.1972, simple_loss=0.2888, pruned_loss=0.05282, over 4880.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2612, pruned_loss=0.03079, over 1421108.36 frames.], batch size: 53, lr: 2.44e-04
2022-04-30 12:16:51,631 INFO [train.py:763] (5/8) Epoch 31, batch 1550, loss[loss=0.1444, simple_loss=0.2364, pruned_loss=0.02619, over 7401.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03033, over 1420411.27 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:17:56,941 INFO [train.py:763] (5/8) Epoch 31, batch 1600, loss[loss=0.1783, simple_loss=0.2855, pruned_loss=0.03553, over 7205.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.03032, over 1416653.55 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:19:02,306 INFO [train.py:763] (5/8) Epoch 31, batch 1650, loss[loss=0.1549, simple_loss=0.2574, pruned_loss=0.02621, over 7412.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03042, over 1417018.93 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:20:07,953 INFO [train.py:763] (5/8) Epoch 31, batch 1700, loss[loss=0.1878, simple_loss=0.2902, pruned_loss=0.04273, over 7114.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03103, over 1412354.88 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:21:14,794 INFO [train.py:763] (5/8) Epoch 31, batch 1750, loss[loss=0.1803, simple_loss=0.269, pruned_loss=0.04575, over 5341.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03074, over 1410137.28 frames.], batch size: 53, lr: 2.44e-04
2022-04-30 12:22:33,302 INFO [train.py:763] (5/8) Epoch 31, batch 1800, loss[loss=0.1507, simple_loss=0.2513, pruned_loss=0.02506, over 7231.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03093, over 1411165.10 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:23:40,197 INFO [train.py:763] (5/8) Epoch 31, batch 1850, loss[loss=0.1354, simple_loss=0.2251, pruned_loss=0.02281, over 7002.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03116, over 1405609.12 frames.], batch size: 16, lr: 2.44e-04
2022-04-30 12:24:46,006 INFO [train.py:763] (5/8) Epoch 31, batch 1900, loss[loss=0.1419, simple_loss=0.2349, pruned_loss=0.02447, over 7347.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03075, over 1411485.79 frames.], batch size: 19, lr: 2.44e-04
2022-04-30 12:25:51,352 INFO [train.py:763] (5/8) Epoch 31, batch 1950, loss[loss=0.1675, simple_loss=0.2676, pruned_loss=0.0337, over 7355.00 frames.], tot_loss[loss=0.1614, simple_loss=0.261, pruned_loss=0.0309, over 1417346.37 frames.], batch size: 19, lr: 2.43e-04
2022-04-30 12:26:56,760 INFO [train.py:763] (5/8) Epoch 31, batch 2000, loss[loss=0.1785, simple_loss=0.2613, pruned_loss=0.04785, over 7273.00 frames.], tot_loss[loss=0.1616, simple_loss=0.261, pruned_loss=0.03109, over 1418971.18 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:28:01,922 INFO [train.py:763] (5/8) Epoch 31, batch 2050, loss[loss=0.1621, simple_loss=0.2717, pruned_loss=0.02622, over 7147.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2607, pruned_loss=0.03103, over 1416710.30 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:29:07,877 INFO [train.py:763] (5/8) Epoch 31, batch 2100, loss[loss=0.1605, simple_loss=0.2614, pruned_loss=0.02974, over 6777.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03108, over 1415933.67 frames.], batch size: 15, lr: 2.43e-04
2022-04-30 12:30:13,155 INFO [train.py:763] (5/8) Epoch 31, batch 2150, loss[loss=0.1562, simple_loss=0.2544, pruned_loss=0.02901, over 7223.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03095, over 1419394.32 frames.], batch size: 21, lr: 2.43e-04
2022-04-30 12:31:18,650 INFO [train.py:763] (5/8) Epoch 31, batch 2200, loss[loss=0.1442, simple_loss=0.2507, pruned_loss=0.01883, over 7180.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.0306, over 1422343.75 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:32:23,987 INFO [train.py:763] (5/8) Epoch 31, batch 2250, loss[loss=0.1442, simple_loss=0.2422, pruned_loss=0.02311, over 7057.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03057, over 1423855.95 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:33:30,746 INFO [train.py:763] (5/8) Epoch 31, batch 2300, loss[loss=0.146, simple_loss=0.2586, pruned_loss=0.0167, over 7327.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03079, over 1420008.91 frames.], batch size: 22, lr: 2.43e-04
2022-04-30 12:34:36,639 INFO [train.py:763] (5/8) Epoch 31, batch 2350, loss[loss=0.1354, simple_loss=0.2228, pruned_loss=0.02397, over 7273.00 frames.], tot_loss[loss=0.163, simple_loss=0.2632, pruned_loss=0.0314, over 1424203.80 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:35:41,759 INFO [train.py:763] (5/8) Epoch 31, batch 2400, loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03561, over 7321.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03126, over 1419929.21 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:36:47,288 INFO [train.py:763] (5/8) Epoch 31, batch 2450, loss[loss=0.1825, simple_loss=0.284, pruned_loss=0.04055, over 7135.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.0313, over 1421431.13 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:37:52,783 INFO [train.py:763] (5/8) Epoch 31, batch 2500, loss[loss=0.1298, simple_loss=0.2171, pruned_loss=0.02129, over 7266.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 1424223.03 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:38:58,020 INFO [train.py:763] (5/8) Epoch 31, batch 2550, loss[loss=0.1652, simple_loss=0.2716, pruned_loss=0.02943, over 7323.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03169, over 1423757.47 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:40:03,281 INFO [train.py:763] (5/8) Epoch 31, batch 2600, loss[loss=0.1449, simple_loss=0.2404, pruned_loss=0.02473, over 7139.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03153, over 1422317.93 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:41:08,495 INFO [train.py:763] (5/8) Epoch 31, batch 2650, loss[loss=0.1904, simple_loss=0.2966, pruned_loss=0.04214, over 7129.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03127, over 1424793.70 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:42:15,354 INFO [train.py:763] (5/8) Epoch 31, batch 2700, loss[loss=0.1728, simple_loss=0.2758, pruned_loss=0.03487, over 7327.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03097, over 1423735.00 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:43:20,592 INFO [train.py:763] (5/8) Epoch 31, batch 2750, loss[loss=0.1717, simple_loss=0.2723, pruned_loss=0.0356, over 7104.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03127, over 1425096.85 frames.], batch size: 28, lr: 2.43e-04
2022-04-30 12:44:27,123 INFO [train.py:763] (5/8) Epoch 31, batch 2800, loss[loss=0.1504, simple_loss=0.2456, pruned_loss=0.02758, over 7400.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03099, over 1424380.01 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:45:34,097 INFO [train.py:763] (5/8) Epoch 31, batch 2850, loss[loss=0.1785, simple_loss=0.2773, pruned_loss=0.03985, over 6184.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03067, over 1420527.45 frames.], batch size: 37, lr: 2.43e-04
2022-04-30 12:46:39,731 INFO [train.py:763] (5/8) Epoch 31, batch 2900, loss[loss=0.142, simple_loss=0.2419, pruned_loss=0.0211, over 7237.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03047, over 1425036.32 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:47:44,749 INFO [train.py:763] (5/8) Epoch 31, batch 2950, loss[loss=0.1544, simple_loss=0.2594, pruned_loss=0.02466, over 7200.00 frames.], tot_loss[loss=0.161, simple_loss=0.2614, pruned_loss=0.03027, over 1417919.37 frames.], batch size: 23, lr: 2.43e-04
2022-04-30 12:48:50,669 INFO [train.py:763] (5/8) Epoch 31, batch 3000, loss[loss=0.1747, simple_loss=0.2779, pruned_loss=0.03576, over 7438.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2619, pruned_loss=0.03051, over 1419326.44 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:48:50,670 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 12:49:05,873 INFO [train.py:792] (5/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
2022-04-30 12:50:12,214 INFO [train.py:763] (5/8) Epoch 31, batch 3050, loss[loss=0.1396, simple_loss=0.2424, pruned_loss=0.01839, over 7302.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2614, pruned_loss=0.03037, over 1423050.02 frames.], batch size: 25, lr: 2.43e-04
2022-04-30 12:51:18,208 INFO [train.py:763] (5/8) Epoch 31, batch 3100, loss[loss=0.1535, simple_loss=0.2566, pruned_loss=0.0252, over 7148.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03042, over 1426752.50 frames.], batch size: 28, lr: 2.42e-04
2022-04-30 12:52:23,642 INFO [train.py:763] (5/8) Epoch 31, batch 3150, loss[loss=0.1445, simple_loss=0.2345, pruned_loss=0.02726, over 7283.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03059, over 1424286.20 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 12:53:29,088 INFO [train.py:763] (5/8) Epoch 31, batch 3200, loss[loss=0.1684, simple_loss=0.2741, pruned_loss=0.03135, over 7114.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2617, pruned_loss=0.03053, over 1426772.75 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:54:36,156 INFO [train.py:763] (5/8) Epoch 31, batch 3250, loss[loss=0.1703, simple_loss=0.2734, pruned_loss=0.03361, over 7341.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2624, pruned_loss=0.03061, over 1427297.34 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 12:55:42,940 INFO [train.py:763] (5/8) Epoch 31, batch 3300, loss[loss=0.1531, simple_loss=0.2576, pruned_loss=0.02428, over 7440.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03035, over 1422943.69 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:56:50,185 INFO [train.py:763] (5/8) Epoch 31, batch 3350, loss[loss=0.1714, simple_loss=0.2795, pruned_loss=0.03167, over 7312.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03018, over 1424930.37 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:57:56,835 INFO [train.py:763] (5/8) Epoch 31, batch 3400, loss[loss=0.1714, simple_loss=0.2647, pruned_loss=0.03907, over 7326.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.03053, over 1422168.54 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:59:03,248 INFO [train.py:763] (5/8) Epoch 31, batch 3450, loss[loss=0.1669, simple_loss=0.2662, pruned_loss=0.03378, over 7195.00 frames.], tot_loss[loss=0.1617, simple_loss=0.262, pruned_loss=0.03068, over 1425097.96 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:00:08,925 INFO [train.py:763] (5/8) Epoch 31, batch 3500, loss[loss=0.1821, simple_loss=0.284, pruned_loss=0.04011, over 7281.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2622, pruned_loss=0.0306, over 1427749.63 frames.], batch size: 24, lr: 2.42e-04
2022-04-30 13:01:14,845 INFO [train.py:763] (5/8) Epoch 31, batch 3550, loss[loss=0.1939, simple_loss=0.2896, pruned_loss=0.04912, over 7370.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03093, over 1430728.82 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:02:21,339 INFO [train.py:763] (5/8) Epoch 31, batch 3600, loss[loss=0.1604, simple_loss=0.2702, pruned_loss=0.02526, over 6332.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03111, over 1427895.56 frames.], batch size: 37, lr: 2.42e-04
2022-04-30 13:03:26,540 INFO [train.py:763] (5/8) Epoch 31, batch 3650, loss[loss=0.159, simple_loss=0.2651, pruned_loss=0.02649, over 7229.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03095, over 1427794.11 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:04:32,086 INFO [train.py:763] (5/8) Epoch 31, batch 3700, loss[loss=0.145, simple_loss=0.2393, pruned_loss=0.02534, over 7129.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.0305, over 1429985.13 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 13:05:36,818 INFO [train.py:763] (5/8) Epoch 31, batch 3750, loss[loss=0.1809, simple_loss=0.2814, pruned_loss=0.04023, over 7205.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03053, over 1424129.32 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:06:42,589 INFO [train.py:763] (5/8) Epoch 31, batch 3800, loss[loss=0.1641, simple_loss=0.2597, pruned_loss=0.03431, over 7379.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2615, pruned_loss=0.03065, over 1426075.71 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:07:47,980 INFO [train.py:763] (5/8) Epoch 31, batch 3850, loss[loss=0.1401, simple_loss=0.2414, pruned_loss=0.01937, over 7439.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03053, over 1427847.55 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:08:53,260 INFO [train.py:763] (5/8) Epoch 31, batch 3900, loss[loss=0.1626, simple_loss=0.2554, pruned_loss=0.0349, over 7162.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03072, over 1428605.31 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:09:58,653 INFO [train.py:763] (5/8) Epoch 31, batch 3950, loss[loss=0.1906, simple_loss=0.2992, pruned_loss=0.04105, over 7220.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03117, over 1423659.56 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:11:04,250 INFO [train.py:763] (5/8) Epoch 31, batch 4000, loss[loss=0.1425, simple_loss=0.2308, pruned_loss=0.02709, over 7405.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2603, pruned_loss=0.03106, over 1420368.02 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:12:09,634 INFO [train.py:763] (5/8) Epoch 31, batch 4050, loss[loss=0.1985, simple_loss=0.3031, pruned_loss=0.04692, over 7385.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2608, pruned_loss=0.03121, over 1418635.24 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:13:15,764 INFO [train.py:763] (5/8) Epoch 31, batch 4100, loss[loss=0.1481, simple_loss=0.2549, pruned_loss=0.0206, over 7212.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2609, pruned_loss=0.03095, over 1417715.51 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:14:21,778 INFO [train.py:763] (5/8) Epoch 31, batch 4150, loss[loss=0.1608, simple_loss=0.2679, pruned_loss=0.02686, over 7218.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03068, over 1421951.75 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:15:28,690 INFO [train.py:763] (5/8) Epoch 31, batch 4200, loss[loss=0.1477, simple_loss=0.2504, pruned_loss=0.02252, over 7326.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2604, pruned_loss=0.03067, over 1421921.46 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:16:35,617 INFO [train.py:763] (5/8) Epoch 31, batch 4250, loss[loss=0.1465, simple_loss=0.2424, pruned_loss=0.02535, over 7263.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2614, pruned_loss=0.03105, over 1420673.79 frames.], batch size: 19, lr: 2.42e-04
2022-04-30 13:17:40,855 INFO [train.py:763] (5/8) Epoch 31, batch 4300, loss[loss=0.1361, simple_loss=0.2259, pruned_loss=0.02314, over 7405.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2602, pruned_loss=0.03071, over 1421061.73 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:18:46,145 INFO [train.py:763] (5/8) Epoch 31, batch 4350, loss[loss=0.1604, simple_loss=0.2483, pruned_loss=0.0363, over 7174.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03107, over 1421425.35 frames.], batch size: 18, lr: 2.41e-04
2022-04-30 13:19:51,345 INFO [train.py:763] (5/8) Epoch 31, batch 4400, loss[loss=0.1702, simple_loss=0.2702, pruned_loss=0.03511, over 7308.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.03136, over 1407454.26 frames.], batch size: 25, lr: 2.41e-04
2022-04-30 13:20:56,969 INFO [train.py:763] (5/8) Epoch 31, batch 4450, loss[loss=0.1389, simple_loss=0.2342, pruned_loss=0.02181, over 6797.00 frames.], tot_loss[loss=0.1631, simple_loss=0.263, pruned_loss=0.03158, over 1404175.79 frames.], batch size: 15, lr: 2.41e-04
2022-04-30 13:22:02,217 INFO [train.py:763] (5/8) Epoch 31, batch 4500, loss[loss=0.1537, simple_loss=0.2695, pruned_loss=0.01893, over 6680.00 frames.], tot_loss[loss=0.164, simple_loss=0.2642, pruned_loss=0.03186, over 1396339.50 frames.], batch size: 31, lr: 2.41e-04
2022-04-30 13:23:07,080 INFO [train.py:763] (5/8) Epoch 31, batch 4550, loss[loss=0.1871, simple_loss=0.2912, pruned_loss=0.04153, over 5016.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03259, over 1357929.29 frames.], batch size: 53, lr: 2.41e-04
2022-04-30 13:24:35,151 INFO [train.py:763] (5/8) Epoch 32, batch 0, loss[loss=0.1594, simple_loss=0.2554, pruned_loss=0.03175, over 6753.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2554, pruned_loss=0.03175, over 6753.00 frames.], batch size: 31, lr: 2.38e-04
2022-04-30 13:25:38,921 INFO [train.py:763] (5/8) Epoch 32, batch 50, loss[loss=0.208, simple_loss=0.2962, pruned_loss=0.05986, over 5158.00 frames.], tot_loss[loss=0.1623, simple_loss=0.263, pruned_loss=0.03078, over 313853.92 frames.], batch size: 52, lr: 2.38e-04
2022-04-30 13:26:41,322 INFO [train.py:763] (5/8) Epoch 32, batch 100, loss[loss=0.1663, simple_loss=0.2673, pruned_loss=0.03264, over 6258.00 frames.], tot_loss[loss=0.1618, simple_loss=0.263, pruned_loss=0.0303, over 558781.67 frames.], batch size: 37, lr: 2.38e-04
2022-04-30 13:27:47,094 INFO [train.py:763] (5/8) Epoch 32, batch 150, loss[loss=0.1634, simple_loss=0.2649, pruned_loss=0.03098, over 7198.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2638, pruned_loss=0.03069, over 751765.47 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:28:52,462 INFO [train.py:763] (5/8) Epoch 32, batch 200, loss[loss=0.1303, simple_loss=0.2253, pruned_loss=0.01761, over 6991.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2615, pruned_loss=0.03, over 894740.21 frames.], batch size: 16, lr: 2.37e-04
2022-04-30 13:29:57,596 INFO [train.py:763] (5/8) Epoch 32, batch 250, loss[loss=0.1496, simple_loss=0.2505, pruned_loss=0.02438, over 7224.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2625, pruned_loss=0.03048, over 1009667.74 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:31:03,128 INFO [train.py:763] (5/8) Epoch 32, batch 300, loss[loss=0.1687, simple_loss=0.28, pruned_loss=0.02867, over 6727.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2631, pruned_loss=0.03077, over 1092768.98 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:32:10,148 INFO [train.py:763] (5/8) Epoch 32, batch 350, loss[loss=0.1522, simple_loss=0.2382, pruned_loss=0.03313, over 7403.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2627, pruned_loss=0.03083, over 1163556.05 frames.], batch size: 18, lr: 2.37e-04
2022-04-30 13:33:15,987 INFO [train.py:763] (5/8) Epoch 32, batch 400, loss[loss=0.1686, simple_loss=0.271, pruned_loss=0.03311, over 7430.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03066, over 1220023.62 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:34:21,567 INFO [train.py:763] (5/8) Epoch 32, batch 450, loss[loss=0.1861, simple_loss=0.2839, pruned_loss=0.04414, over 6758.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03082, over 1262640.46 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:35:26,876 INFO [train.py:763] (5/8) Epoch 32, batch 500, loss[loss=0.1896, simple_loss=0.2828, pruned_loss=0.04817, over 7187.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.0308, over 1300189.50 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:36:32,829 INFO [train.py:763] (5/8) Epoch 32, batch 550, loss[loss=0.1723, simple_loss=0.2741, pruned_loss=0.0352, over 7313.00 frames.], tot_loss[loss=0.162, simple_loss=0.2626, pruned_loss=0.03072, over 1329030.84 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:37:38,147 INFO [train.py:763] (5/8) Epoch 32, batch 600, loss[loss=0.172, simple_loss=0.2745, pruned_loss=0.03476, over 7287.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2627, pruned_loss=0.03078, over 1347254.72 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:38:43,404 INFO [train.py:763] (5/8) Epoch 32, batch 650, loss[loss=0.1599, simple_loss=0.2662, pruned_loss=0.02675, over 7160.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2627, pruned_loss=0.03058, over 1363664.51 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:39:48,623 INFO [train.py:763] (5/8) Epoch 32, batch 700, loss[loss=0.1606, simple_loss=0.2544, pruned_loss=0.03341, over 7133.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2627, pruned_loss=0.03081, over 1374011.78 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:40:55,077 INFO [train.py:763] (5/8) Epoch 32, batch 750, loss[loss=0.167, simple_loss=0.2666, pruned_loss=0.03364, over 7216.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2625, pruned_loss=0.03078, over 1379961.40 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:42:02,253 INFO [train.py:763] (5/8) Epoch 32, batch 800, loss[loss=0.1467, simple_loss=0.2493, pruned_loss=0.02206, over 7433.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03099, over 1390916.50 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:43:08,541 INFO [train.py:763] (5/8) Epoch 32, batch 850, loss[loss=0.1802, simple_loss=0.2884, pruned_loss=0.03603, over 7376.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03067, over 1398595.37 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:44:14,307 INFO [train.py:763] (5/8) Epoch 32, batch 900, loss[loss=0.1661, simple_loss=0.2607, pruned_loss=0.03575, over 7219.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03025, over 1407852.63 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:45:21,098 INFO [train.py:763] (5/8) Epoch 32, batch 950, loss[loss=0.1448, simple_loss=0.2471, pruned_loss=0.02122, over 7437.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03025, over 1412630.26 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:46:27,367 INFO [train.py:763] (5/8) Epoch 32, batch 1000, loss[loss=0.202, simple_loss=0.303, pruned_loss=0.05047, over 7205.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03036, over 1412917.41 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:47:33,316 INFO [train.py:763] (5/8) Epoch 32, batch 1050, loss[loss=0.1761, simple_loss=0.2789, pruned_loss=0.03667, over 7115.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03016, over 1412408.27 frames.], batch size: 28, lr: 2.37e-04
2022-04-30 13:48:38,621 INFO [train.py:763] (5/8) Epoch 32, batch 1100, loss[loss=0.168, simple_loss=0.2793, pruned_loss=0.02832, over 7295.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.0303, over 1417243.20 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:49:45,245 INFO [train.py:763] (5/8) Epoch 32, batch 1150, loss[loss=0.1636, simple_loss=0.2702, pruned_loss=0.02845, over 7179.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.0304, over 1418777.21 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:50:50,723 INFO [train.py:763] (5/8) Epoch 32, batch 1200, loss[loss=0.1966, simple_loss=0.2949, pruned_loss=0.0492, over 7160.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03065, over 1421360.67 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:51:56,752 INFO [train.py:763] (5/8) Epoch 32, batch 1250, loss[loss=0.1674, simple_loss=0.2762, pruned_loss=0.02928, over 6362.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2625, pruned_loss=0.0312, over 1419797.76 frames.], batch size: 38, lr: 2.37e-04
2022-04-30 13:53:02,504 INFO [train.py:763] (5/8) Epoch 32, batch 1300, loss[loss=0.1825, simple_loss=0.2863, pruned_loss=0.03936, over 7222.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.0309, over 1420196.24 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:54:10,203 INFO [train.py:763] (5/8) Epoch 32, batch 1350, loss[loss=0.1545, simple_loss=0.2423, pruned_loss=0.03334, over 7277.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03109, over 1419430.20 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:55:17,153 INFO [train.py:763] (5/8) Epoch 32, batch 1400, loss[loss=0.1736, simple_loss=0.2846, pruned_loss=0.03133, over 7144.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2616, pruned_loss=0.03136, over 1421798.93 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 13:56:22,423 INFO [train.py:763] (5/8) Epoch 32, batch 1450, loss[loss=0.1883, simple_loss=0.2915, pruned_loss=0.04254, over 6671.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03119, over 1424756.09 frames.], batch size: 31, lr: 2.36e-04
2022-04-30 13:57:27,829 INFO [train.py:763] (5/8) Epoch 32, batch 1500, loss[loss=0.1849, simple_loss=0.2886, pruned_loss=0.04056, over 4956.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03113, over 1422056.94 frames.], batch size: 52, lr: 2.36e-04
2022-04-30 13:58:33,081 INFO [train.py:763] (5/8) Epoch 32, batch 1550, loss[loss=0.1656, simple_loss=0.2692, pruned_loss=0.03099, over 7231.00 frames.], tot_loss[loss=0.1625, simple_loss=0.262, pruned_loss=0.0315, over 1418496.88 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 13:59:38,330 INFO [train.py:763] (5/8) Epoch 32, batch 1600, loss[loss=0.1737, simple_loss=0.288, pruned_loss=0.02971, over 7424.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03122, over 1419640.28 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:00:43,689 INFO [train.py:763] (5/8) Epoch 32, batch 1650, loss[loss=0.1499, simple_loss=0.2542, pruned_loss=0.02283, over 7212.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03069, over 1420702.75 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:01:48,791 INFO [train.py:763] (5/8) Epoch 32, batch 1700, loss[loss=0.1804, simple_loss=0.2891, pruned_loss=0.03583, over 7307.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03026, over 1423664.02 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:02:54,188 INFO [train.py:763] (5/8) Epoch 32, batch 1750, loss[loss=0.1818, simple_loss=0.2815, pruned_loss=0.04108, over 7027.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.0309, over 1416788.26 frames.], batch size: 28, lr: 2.36e-04
2022-04-30 14:03:59,648 INFO [train.py:763] (5/8) Epoch 32, batch 1800, loss[loss=0.1588, simple_loss=0.2503, pruned_loss=0.03364, over 7253.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03068, over 1421012.16 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:05:06,118 INFO [train.py:763] (5/8) Epoch 32, batch 1850, loss[loss=0.1434, simple_loss=0.2442, pruned_loss=0.02126, over 7312.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03079, over 1423185.96 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:06:21,245 INFO [train.py:763] (5/8) Epoch 32, batch 1900, loss[loss=0.1854, simple_loss=0.2904, pruned_loss=0.04023, over 7383.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.03054, over 1425335.01 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:07:26,674 INFO [train.py:763] (5/8) Epoch 32, batch 1950, loss[loss=0.1838, simple_loss=0.2773, pruned_loss=0.04517, over 7267.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.0305, over 1423904.80 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:08:33,682 INFO [train.py:763] (5/8) Epoch 32, batch 2000, loss[loss=0.1624, simple_loss=0.2631, pruned_loss=0.03082, over 6434.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2613, pruned_loss=0.03027, over 1425530.87 frames.], batch size: 38, lr: 2.36e-04
2022-04-30 14:09:39,831 INFO [train.py:763] (5/8) Epoch 32, batch 2050, loss[loss=0.1392, simple_loss=0.2335, pruned_loss=0.0225, over 7163.00 frames.], tot_loss[loss=0.1605, simple_loss=0.261, pruned_loss=0.03, over 1426589.99 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:10:45,533 INFO [train.py:763] (5/8) Epoch 32, batch 2100, loss[loss=0.1568, simple_loss=0.2532, pruned_loss=0.03021, over 7152.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02989, over 1427743.91 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:11:52,558 INFO [train.py:763] (5/8) Epoch 32, batch 2150, loss[loss=0.1539, simple_loss=0.2458, pruned_loss=0.03101, over 7405.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.02998, over 1428843.20 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:12:58,738 INFO [train.py:763] (5/8) Epoch 32, batch 2200, loss[loss=0.1899, simple_loss=0.2953, pruned_loss=0.04221, over 5040.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.0301, over 1423622.08 frames.], batch size: 52, lr: 2.36e-04
2022-04-30 14:14:05,704 INFO [train.py:763] (5/8) Epoch 32, batch 2250, loss[loss=0.1905, simple_loss=0.29, pruned_loss=0.04546, over 7183.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03024, over 1421011.17 frames.], batch size: 26, lr: 2.36e-04
2022-04-30 14:15:12,727 INFO [train.py:763] (5/8) Epoch 32, batch 2300, loss[loss=0.1824, simple_loss=0.2787, pruned_loss=0.04309, over 7213.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2597, pruned_loss=0.03056, over 1419998.04 frames.], batch size: 22, lr: 2.36e-04
2022-04-30 14:16:18,550 INFO [train.py:763] (5/8) Epoch 32, batch 2350, loss[loss=0.1707, simple_loss=0.2627, pruned_loss=0.03938, over 6810.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2595, pruned_loss=0.03051, over 1422268.93 frames.], batch size: 15, lr: 2.36e-04
2022-04-30 14:17:26,001 INFO [train.py:763] (5/8) Epoch 32, batch 2400, loss[loss=0.1462, simple_loss=0.2505, pruned_loss=0.02098, over 7423.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2589, pruned_loss=0.0301, over 1423450.31 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 14:18:32,881 INFO [train.py:763] (5/8) Epoch 32, batch 2450, loss[loss=0.1659, simple_loss=0.2613, pruned_loss=0.03521, over 7270.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2586, pruned_loss=0.03018, over 1425977.04 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:19:38,457 INFO [train.py:763] (5/8) Epoch 32, batch 2500, loss[loss=0.1895, simple_loss=0.2927, pruned_loss=0.04313, over 7315.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2591, pruned_loss=0.03029, over 1428191.55 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:20:45,072 INFO [train.py:763] (5/8) Epoch 32, batch 2550, loss[loss=0.1859, simple_loss=0.2831, pruned_loss=0.04437, over 7375.00 frames.], tot_loss[loss=0.16, simple_loss=0.2592, pruned_loss=0.03043, over 1427895.60 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:21:59,926 INFO [train.py:763] (5/8) Epoch 32, batch 2600, loss[loss=0.1501, simple_loss=0.2561, pruned_loss=0.02202, over 7205.00 frames.], tot_loss[loss=0.1597, simple_loss=0.259, pruned_loss=0.03024, over 1428948.09 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:23:23,013 INFO [train.py:763] (5/8) Epoch 32, batch 2650, loss[loss=0.1304, simple_loss=0.2162, pruned_loss=0.02234, over 6756.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2595, pruned_loss=0.03033, over 1424340.45 frames.], batch size: 15, lr: 2.35e-04
2022-04-30 14:24:36,943 INFO [train.py:763] (5/8) Epoch 32, batch 2700, loss[loss=0.1504, simple_loss=0.2483, pruned_loss=0.02625, over 7421.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03004, over 1425302.50 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:25:51,356 INFO [train.py:763] (5/8) Epoch 32, batch 2750, loss[loss=0.164, simple_loss=0.2566, pruned_loss=0.03575, over 7274.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.03023, over 1426201.25 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:26:57,664 INFO [train.py:763] (5/8) Epoch 32, batch 2800, loss[loss=0.1906, simple_loss=0.2952, pruned_loss=0.04303, over 7184.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03024, over 1425363.96 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:28:12,046 INFO [train.py:763] (5/8) Epoch 32, batch 2850, loss[loss=0.1548, simple_loss=0.2538, pruned_loss=0.02791, over 7331.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03013, over 1427051.18 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:29:27,125 INFO [train.py:763] (5/8) Epoch 32, batch 2900, loss[loss=0.1646, simple_loss=0.269, pruned_loss=0.03013, over 7299.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03062, over 1425839.15 frames.], batch size: 25, lr: 2.35e-04
2022-04-30 14:30:34,016 INFO [train.py:763] (5/8) Epoch 32, batch 2950, loss[loss=0.1681, simple_loss=0.2659, pruned_loss=0.03518, over 7427.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03038, over 1427820.31 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:31:40,123 INFO [train.py:763] (5/8) Epoch 32, batch 3000, loss[loss=0.1344, simple_loss=0.2293, pruned_loss=0.01969, over 7067.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2595, pruned_loss=0.03006, over 1427187.25 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:31:40,125 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 14:31:55,319 INFO [train.py:792] (5/8) Epoch 32, validation: loss=0.1696, simple_loss=0.2645, pruned_loss=0.0374, over 698248.00 frames.
2022-04-30 14:33:01,768 INFO [train.py:763] (5/8) Epoch 32, batch 3050, loss[loss=0.1681, simple_loss=0.2795, pruned_loss=0.02832, over 6368.00 frames.], tot_loss[loss=0.1595, simple_loss=0.259, pruned_loss=0.02997, over 1423043.61 frames.], batch size: 38, lr: 2.35e-04
2022-04-30 14:34:07,509 INFO [train.py:763] (5/8) Epoch 32, batch 3100, loss[loss=0.1694, simple_loss=0.278, pruned_loss=0.03041, over 7376.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.02968, over 1423016.45 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:35:13,888 INFO [train.py:763] (5/8) Epoch 32, batch 3150, loss[loss=0.1432, simple_loss=0.2395, pruned_loss=0.02348, over 7063.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.02999, over 1420438.39 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:36:20,358 INFO [train.py:763] (5/8) Epoch 32, batch 3200, loss[loss=0.1425, simple_loss=0.2372, pruned_loss=0.02396, over 7204.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02994, over 1421541.91 frames.], batch size: 16, lr: 2.35e-04
2022-04-30 14:37:25,788 INFO [train.py:763] (5/8) Epoch 32, batch 3250, loss[loss=0.1265, simple_loss=0.2257, pruned_loss=0.0136, over 7258.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03041, over 1418304.67 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:38:31,359 INFO [train.py:763] (5/8) Epoch 32, batch 3300, loss[loss=0.1796, simple_loss=0.2841, pruned_loss=0.0376, over 7232.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.02996, over 1423759.01 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:39:37,087 INFO [train.py:763] (5/8) Epoch 32, batch 3350, loss[loss=0.1713, simple_loss=0.2705, pruned_loss=0.03605, over 7316.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03005, over 1427387.66 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:40:43,415 INFO [train.py:763] (5/8) Epoch 32, batch 3400, loss[loss=0.1643, simple_loss=0.2613, pruned_loss=0.03364, over 7277.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03008, over 1427667.53 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:41:50,120 INFO [train.py:763] (5/8) Epoch 32, batch 3450, loss[loss=0.1498, simple_loss=0.2528, pruned_loss=0.0234, over 7337.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02998, over 1431553.52 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:42:56,326 INFO [train.py:763] (5/8) Epoch 32, batch 3500, loss[loss=0.1856, simple_loss=0.2855, pruned_loss=0.04279, over 7385.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03052, over 1427723.37 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:44:01,649 INFO [train.py:763] (5/8) Epoch 32, batch 3550, loss[loss=0.1553, simple_loss=0.2447, pruned_loss=0.03295, over 7404.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03053, over 1427269.50 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:45:06,997 INFO [train.py:763] (5/8) Epoch 32, batch 3600, loss[loss=0.1404, simple_loss=0.2389, pruned_loss=0.02097, over 7334.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03035, over 1423309.89 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:46:12,679 INFO [train.py:763] (5/8) Epoch 32, batch 3650, loss[loss=0.1558, simple_loss=0.2551, pruned_loss=0.02823, over 7330.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03002, over 1422784.71 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:47:18,410 INFO [train.py:763] (5/8) Epoch 32, batch 3700, loss[loss=0.1449, simple_loss=0.2413, pruned_loss=0.02427, over 7291.00 frames.], tot_loss[loss=0.1608, simple_loss=0.261, pruned_loss=0.03033, over 1426452.05 frames.], batch size: 17, lr: 2.35e-04
2022-04-30 14:48:25,081 INFO [train.py:763] (5/8) Epoch 32, batch 3750, loss[loss=0.1667, simple_loss=0.2791, pruned_loss=0.02712, over 7226.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03053, over 1426895.41 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:49:30,594 INFO [train.py:763] (5/8) Epoch 32, batch 3800, loss[loss=0.1878, simple_loss=0.2904, pruned_loss=0.04262, over 7211.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.0303, over 1427179.26 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:50:35,844 INFO [train.py:763] (5/8) Epoch 32, batch 3850, loss[loss=0.1439, simple_loss=0.2538, pruned_loss=0.01706, over 7311.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03039, over 1428549.23 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:51:41,194 INFO [train.py:763] (5/8) Epoch 32, batch 3900, loss[loss=0.1551, simple_loss=0.2469, pruned_loss=0.03163, over 6789.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03055, over 1428459.63 frames.], batch size: 15, lr: 2.35e-04
2022-04-30 14:52:46,610 INFO [train.py:763] (5/8) Epoch 32, batch 3950, loss[loss=0.1476, simple_loss=0.2397, pruned_loss=0.02771, over 7420.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03096, over 1430754.05 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:53:52,269 INFO [train.py:763] (5/8) Epoch 32, batch 4000, loss[loss=0.1694, simple_loss=0.2776, pruned_loss=0.03056, over 6404.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03053, over 1431113.73 frames.], batch size: 38, lr: 2.34e-04
2022-04-30 14:54:57,661 INFO [train.py:763] (5/8) Epoch 32, batch 4050, loss[loss=0.1438, simple_loss=0.2398, pruned_loss=0.02387, over 7267.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.0303, over 1426944.49 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:56:02,796 INFO [train.py:763] (5/8) Epoch 32, batch 4100, loss[loss=0.1771, simple_loss=0.2766, pruned_loss=0.03885, over 7158.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03025, over 1421147.91 frames.], batch size: 26, lr: 2.34e-04
2022-04-30 14:57:08,463 INFO [train.py:763] (5/8) Epoch 32, batch 4150, loss[loss=0.1639, simple_loss=0.2513, pruned_loss=0.03821, over 6804.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03012, over 1421236.31 frames.], batch size: 15, lr: 2.34e-04
2022-04-30 14:58:14,268 INFO [train.py:763] (5/8) Epoch 32, batch 4200, loss[loss=0.15, simple_loss=0.2482, pruned_loss=0.02584, over 7267.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.03037, over 1419384.59 frames.], batch size: 19, lr: 2.34e-04
2022-04-30 14:59:19,687 INFO [train.py:763] (5/8) Epoch 32, batch 4250, loss[loss=0.148, simple_loss=0.2378, pruned_loss=0.02904, over 7430.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.0301, over 1420749.76 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:00:26,394 INFO [train.py:763] (5/8) Epoch 32, batch 4300, loss[loss=0.1567, simple_loss=0.254, pruned_loss=0.0297, over 6667.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.03, over 1419887.34 frames.], batch size: 31, lr: 2.34e-04
2022-04-30 15:01:32,997 INFO [train.py:763] (5/8) Epoch 32, batch 4350, loss[loss=0.1524, simple_loss=0.2584, pruned_loss=0.02316, over 7221.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03014, over 1415905.02 frames.], batch size: 21, lr: 2.34e-04
2022-04-30 15:02:38,280 INFO [train.py:763] (5/8) Epoch 32, batch 4400, loss[loss=0.1425, simple_loss=0.2456, pruned_loss=0.01972, over 7155.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2595, pruned_loss=0.02983, over 1414948.41 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:03:43,367 INFO [train.py:763] (5/8) Epoch 32, batch 4450, loss[loss=0.1756, simple_loss=0.2816, pruned_loss=0.03479, over 7335.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02996, over 1407492.10 frames.], batch size: 22, lr: 2.34e-04
2022-04-30 15:04:48,250 INFO [train.py:763] (5/8) Epoch 32, batch 4500, loss[loss=0.15, simple_loss=0.2523, pruned_loss=0.02383, over 7139.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02983, over 1397940.62 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:05:53,076 INFO [train.py:763] (5/8) Epoch 32, batch 4550, loss[loss=0.1533, simple_loss=0.2545, pruned_loss=0.02604, over 5186.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.0306, over 1375383.58 frames.], batch size: 54, lr: 2.34e-04
2022-04-30 15:07:21,088 INFO [train.py:763] (5/8) Epoch 33, batch 0, loss[loss=0.1454, simple_loss=0.2413, pruned_loss=0.02474, over 7424.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2413, pruned_loss=0.02474, over 7424.00 frames.], batch size: 20, lr: 2.31e-04
2022-04-30 15:08:26,676 INFO [train.py:763] (5/8) Epoch 33, batch 50, loss[loss=0.1829, simple_loss=0.2697, pruned_loss=0.04804, over 7119.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2569, pruned_loss=0.03007, over 324830.75 frames.], batch size: 28, lr: 2.30e-04
2022-04-30 15:09:31,885 INFO [train.py:763] (5/8) Epoch 33, batch 100, loss[loss=0.1703, simple_loss=0.2815, pruned_loss=0.02952, over 7115.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03036, over 565641.47 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:10:37,379 INFO [train.py:763] (5/8) Epoch 33, batch 150, loss[loss=0.1539, simple_loss=0.2516, pruned_loss=0.02814, over 7068.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02986, over 755189.77 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:11:42,900 INFO [train.py:763] (5/8) Epoch 33, batch 200, loss[loss=0.1309, simple_loss=0.2259, pruned_loss=0.01793, over 7276.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2581, pruned_loss=0.02964, over 904967.05 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:12:48,577 INFO [train.py:763] (5/8) Epoch 33, batch 250, loss[loss=0.1895, simple_loss=0.2858, pruned_loss=0.04662, over 5241.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2581, pruned_loss=0.02953, over 1011995.82 frames.], batch size: 52, lr: 2.30e-04
2022-04-30 15:13:55,822 INFO [train.py:763] (5/8) Epoch 33, batch 300, loss[loss=0.178, simple_loss=0.2977, pruned_loss=0.02914, over 7367.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02977, over 1102438.89 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:15:01,951 INFO [train.py:763] (5/8) Epoch 33, batch 350, loss[loss=0.1431, simple_loss=0.2409, pruned_loss=0.02266, over 7132.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02995, over 1167343.53 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:16:08,897 INFO [train.py:763] (5/8) Epoch 33, batch 400, loss[loss=0.2023, simple_loss=0.3048, pruned_loss=0.04985, over 7413.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03045, over 1228044.52 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:17:14,703 INFO [train.py:763] (5/8) Epoch 33, batch 450, loss[loss=0.1238, simple_loss=0.2119, pruned_loss=0.01787, over 7412.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.03, over 1273318.51 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:18:21,055 INFO [train.py:763] (5/8) Epoch 33, batch 500, loss[loss=0.1703, simple_loss=0.2629, pruned_loss=0.03882, over 7289.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03059, over 1306338.97 frames.], batch size: 24, lr: 2.30e-04
2022-04-30 15:19:26,291 INFO [train.py:763] (5/8) Epoch 33, batch 550, loss[loss=0.1628, simple_loss=0.2693, pruned_loss=0.02819, over 6427.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.0306, over 1329970.51 frames.], batch size: 37, lr: 2.30e-04
2022-04-30 15:20:43,088 INFO [train.py:763] (5/8) Epoch 33, batch 600, loss[loss=0.1604, simple_loss=0.2678, pruned_loss=0.02655, over 7322.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03075, over 1352119.45 frames.], batch size: 25, lr: 2.30e-04
2022-04-30 15:21:48,334 INFO [train.py:763] (5/8) Epoch 33, batch 650, loss[loss=0.1458, simple_loss=0.2535, pruned_loss=0.01904, over 7166.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03032, over 1370491.59 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:22:53,616 INFO [train.py:763] (5/8) Epoch 33, batch 700, loss[loss=0.1363, simple_loss=0.2277, pruned_loss=0.02245, over 7126.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03026, over 1377324.81 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:23:58,788 INFO [train.py:763] (5/8) Epoch 33, batch 750, loss[loss=0.1649, simple_loss=0.2666, pruned_loss=0.03159, over 7211.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03077, over 1389598.67 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:25:05,625 INFO [train.py:763] (5/8) Epoch 33, batch 800, loss[loss=0.1554, simple_loss=0.2488, pruned_loss=0.03105, over 7269.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03052, over 1395145.86 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:26:11,927 INFO [train.py:763] (5/8) Epoch 33, batch 850, loss[loss=0.1644, simple_loss=0.2631, pruned_loss=0.03286, over 6428.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03025, over 1404926.39 frames.], batch size: 37, lr: 2.30e-04
2022-04-30 15:27:17,424 INFO [train.py:763] (5/8) Epoch 33, batch 900, loss[loss=0.1987, simple_loss=0.2869, pruned_loss=0.05529, over 4913.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.03032, over 1409698.48 frames.], batch size: 52, lr: 2.30e-04
2022-04-30 15:28:22,826 INFO [train.py:763] (5/8) Epoch 33, batch 950, loss[loss=0.1466, simple_loss=0.2394, pruned_loss=0.02692, over 7285.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2598, pruned_loss=0.03104, over 1407877.23 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:29:28,257 INFO [train.py:763] (5/8) Epoch 33, batch 1000, loss[loss=0.142, simple_loss=0.2476, pruned_loss=0.0182, over 7434.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2595, pruned_loss=0.03071, over 1409301.72 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:30:33,712 INFO [train.py:763] (5/8) Epoch 33, batch 1050, loss[loss=0.1354, simple_loss=0.2336, pruned_loss=0.01859, over 7156.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2592, pruned_loss=0.0302, over 1415047.26 frames.], batch size: 19, lr: 2.30e-04
2022-04-30 15:31:40,472 INFO [train.py:763] (5/8) Epoch 33, batch 1100, loss[loss=0.1733, simple_loss=0.2691, pruned_loss=0.03878, over 6513.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03027, over 1413148.90 frames.], batch size: 38, lr: 2.30e-04
2022-04-30 15:32:45,931 INFO [train.py:763] (5/8) Epoch 33, batch 1150, loss[loss=0.1605, simple_loss=0.2643, pruned_loss=0.02839, over 7440.00 frames.], tot_loss[loss=0.16, simple_loss=0.2594, pruned_loss=0.03033, over 1416254.14 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:33:51,385 INFO [train.py:763] (5/8) Epoch 33, batch 1200, loss[loss=0.1738, simple_loss=0.2724, pruned_loss=0.03765, over 7221.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2588, pruned_loss=0.03006, over 1420813.28 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:34:56,636 INFO [train.py:763] (5/8) Epoch 33, batch 1250, loss[loss=0.182, simple_loss=0.2815, pruned_loss=0.04126, over 7334.00 frames.], tot_loss[loss=0.1594, simple_loss=0.259, pruned_loss=0.02995, over 1417362.09 frames.], batch size: 22, lr: 2.30e-04
2022-04-30 15:36:02,620 INFO [train.py:763] (5/8) Epoch 33, batch 1300, loss[loss=0.1528, simple_loss=0.2642, pruned_loss=0.02073, over 7104.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2581, pruned_loss=0.02974, over 1417588.81 frames.], batch size: 26, lr: 2.30e-04
2022-04-30 15:37:09,767 INFO [train.py:763] (5/8) Epoch 33, batch 1350, loss[loss=0.1662, simple_loss=0.2679, pruned_loss=0.03222, over 7221.00 frames.], tot_loss[loss=0.1591, simple_loss=0.258, pruned_loss=0.03006, over 1419619.34 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:38:16,830 INFO [train.py:763] (5/8) Epoch 33, batch 1400, loss[loss=0.1523, simple_loss=0.2512, pruned_loss=0.02673, over 7263.00 frames.], tot_loss[loss=0.1589, simple_loss=0.258, pruned_loss=0.02992, over 1422664.55 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:39:22,846 INFO [train.py:763] (5/8) Epoch 33, batch 1450, loss[loss=0.1562, simple_loss=0.2734, pruned_loss=0.01946, over 7420.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2579, pruned_loss=0.02958, over 1425807.99 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:40:28,343 INFO [train.py:763] (5/8) Epoch 33, batch 1500, loss[loss=0.1843, simple_loss=0.2791, pruned_loss=0.04478, over 7390.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2585, pruned_loss=0.02997, over 1424082.80 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:41:33,829 INFO [train.py:763] (5/8) Epoch 33, batch 1550, loss[loss=0.1861, simple_loss=0.2905, pruned_loss=0.04091, over 7273.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2602, pruned_loss=0.03059, over 1421459.75 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:42:39,069 INFO [train.py:763] (5/8) Epoch 33, batch 1600, loss[loss=0.1663, simple_loss=0.2754, pruned_loss=0.0286, over 7332.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2598, pruned_loss=0.03041, over 1422845.96 frames.], batch size: 20, lr: 2.29e-04
2022-04-30 15:43:46,173 INFO [train.py:763] (5/8) Epoch 33, batch 1650, loss[loss=0.1671, simple_loss=0.2672, pruned_loss=0.03349, over 7195.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.03044, over 1422393.43 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 15:44:53,522 INFO [train.py:763] (5/8) Epoch 33, batch 1700, loss[loss=0.1926, simple_loss=0.2848, pruned_loss=0.05023, over 7376.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03012, over 1426690.15 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:46:00,135 INFO [train.py:763] (5/8) Epoch 33, batch 1750, loss[loss=0.1511, simple_loss=0.2503, pruned_loss=0.02593, over 7134.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02996, over 1421746.60 frames.], batch size: 28, lr: 2.29e-04
2022-04-30 15:47:05,297 INFO [train.py:763] (5/8) Epoch 33, batch 1800, loss[loss=0.1459, simple_loss=0.2318, pruned_loss=0.02998, over 7281.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03011, over 1423554.37 frames.], batch size: 17, lr: 2.29e-04
2022-04-30 15:48:11,900 INFO [train.py:763] (5/8) Epoch 33, batch 1850, loss[loss=0.1522, simple_loss=0.2487, pruned_loss=0.02784, over 7321.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.03042, over 1416031.21 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:49:17,345 INFO [train.py:763] (5/8) Epoch 33, batch 1900, loss[loss=0.1597, simple_loss=0.272, pruned_loss=0.02373, over 6735.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.03044, over 1411082.44 frames.], batch size: 31, lr: 2.29e-04
2022-04-30 15:50:23,830 INFO [train.py:763] (5/8) Epoch 33, batch 1950, loss[loss=0.1575, simple_loss=0.2555, pruned_loss=0.02972, over 6983.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03056, over 1416933.93 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 15:51:31,077 INFO [train.py:763] (5/8) Epoch 33, batch 2000, loss[loss=0.1281, simple_loss=0.221, pruned_loss=0.01756, over 7427.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03026, over 1422363.99 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:52:37,445 INFO [train.py:763] (5/8) Epoch 33, batch 2050, loss[loss=0.1555, simple_loss=0.2614, pruned_loss=0.02477, over 7198.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.02975, over 1422233.79 frames.], batch size: 26, lr: 2.29e-04
2022-04-30 15:53:42,712 INFO [train.py:763] (5/8) Epoch 33, batch 2100, loss[loss=0.1697, simple_loss=0.2801, pruned_loss=0.02967, over 7193.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2603, pruned_loss=0.02952, over 1424858.25 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:54:47,945 INFO [train.py:763] (5/8) Epoch 33, batch 2150, loss[loss=0.1585, simple_loss=0.2579, pruned_loss=0.02952, over 7291.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02933, over 1424177.05 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:55:53,183 INFO [train.py:763] (5/8) Epoch 33, batch 2200, loss[loss=0.1615, simple_loss=0.2662, pruned_loss=0.02834, over 7309.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2604, pruned_loss=0.02921, over 1427033.32 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:56:58,877 INFO [train.py:763] (5/8) Epoch 33, batch 2250, loss[loss=0.1558, simple_loss=0.2405, pruned_loss=0.0356, over 7271.00 frames.], tot_loss[loss=0.16, simple_loss=0.2607, pruned_loss=0.02967, over 1423379.70 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:58:05,274 INFO [train.py:763] (5/8) Epoch 33, batch 2300, loss[loss=0.162, simple_loss=0.2579, pruned_loss=0.03305, over 7153.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2615, pruned_loss=0.03016, over 1423970.53 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:59:10,710 INFO [train.py:763] (5/8) Epoch 33, batch 2350, loss[loss=0.1655, simple_loss=0.2629, pruned_loss=0.03409, over 7155.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02975, over 1424741.46 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 16:00:16,791 INFO [train.py:763] (5/8) Epoch 33, batch 2400, loss[loss=0.1897, simple_loss=0.2971, pruned_loss=0.04121, over 7353.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.03009, over 1425161.29 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 16:01:22,894 INFO [train.py:763] (5/8) Epoch 33, batch 2450, loss[loss=0.1877, simple_loss=0.2961, pruned_loss=0.03969, over 7221.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03056, over 1419545.12 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 16:02:28,049 INFO [train.py:763] (5/8) Epoch 33, batch 2500, loss[loss=0.1309, simple_loss=0.2245, pruned_loss=0.01859, over 7005.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2611, pruned_loss=0.03055, over 1418331.09 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 16:03:33,226 INFO [train.py:763] (5/8) Epoch 33, batch 2550, loss[loss=0.172, simple_loss=0.271, pruned_loss=0.03647, over 7323.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03062, over 1419983.44 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:04:38,859 INFO [train.py:763] (5/8) Epoch 33, batch 2600, loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03032, over 7045.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03048, over 1419582.16 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 16:05:45,692 INFO [train.py:763] (5/8) Epoch 33, batch 2650, loss[loss=0.152, simple_loss=0.2662, pruned_loss=0.01889, over 7339.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03015, over 1420797.26 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:06:52,576 INFO [train.py:763] (5/8) Epoch 33, batch 2700, loss[loss=0.1434, simple_loss=0.2348, pruned_loss=0.02597, over 7267.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02985, over 1425449.32 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:07:59,715 INFO [train.py:763] (5/8) Epoch 33, batch 2750, loss[loss=0.1477, simple_loss=0.245, pruned_loss=0.02519, over 7320.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.0294, over 1424031.95 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:09:06,795 INFO [train.py:763] (5/8) Epoch 33, batch 2800, loss[loss=0.1337, simple_loss=0.2343, pruned_loss=0.01661, over 7400.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2602, pruned_loss=0.02939, over 1429227.86 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:10:13,299 INFO [train.py:763] (5/8) Epoch 33, batch 2850, loss[loss=0.1438, simple_loss=0.2467, pruned_loss=0.02047, over 7188.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2605, pruned_loss=0.02949, over 1431111.80 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:11:18,332 INFO [train.py:763] (5/8) Epoch 33, batch 2900, loss[loss=0.1495, simple_loss=0.2564, pruned_loss=0.0213, over 7146.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2606, pruned_loss=0.02935, over 1427914.69 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:12:24,343 INFO [train.py:763] (5/8) Epoch 33, batch 2950, loss[loss=0.1343, simple_loss=0.2363, pruned_loss=0.01616, over 7151.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02901, over 1428076.88 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:13:31,374 INFO [train.py:763] (5/8) Epoch 33, batch 3000, loss[loss=0.1488, simple_loss=0.2521, pruned_loss=0.02275, over 7353.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02903, over 1427750.87 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:13:31,375 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 16:13:46,765 INFO [train.py:792] (5/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
2022-04-30 16:14:51,750 INFO [train.py:763] (5/8) Epoch 33, batch 3050, loss[loss=0.147, simple_loss=0.2523, pruned_loss=0.02087, over 7358.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2604, pruned_loss=0.02922, over 1428224.82 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:15:58,067 INFO [train.py:763] (5/8) Epoch 33, batch 3100, loss[loss=0.1292, simple_loss=0.2237, pruned_loss=0.01734, over 6785.00 frames.], tot_loss[loss=0.161, simple_loss=0.2615, pruned_loss=0.03019, over 1429089.58 frames.], batch size: 15, lr: 2.28e-04
2022-04-30 16:17:04,955 INFO [train.py:763] (5/8) Epoch 33, batch 3150, loss[loss=0.1492, simple_loss=0.2398, pruned_loss=0.02929, over 7276.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02988, over 1429372.81 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:18:11,847 INFO [train.py:763] (5/8) Epoch 33, batch 3200, loss[loss=0.1831, simple_loss=0.2842, pruned_loss=0.04095, over 5047.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03009, over 1425292.88 frames.], batch size: 53, lr: 2.28e-04
2022-04-30 16:19:17,476 INFO [train.py:763] (5/8) Epoch 33, batch 3250, loss[loss=0.1529, simple_loss=0.2463, pruned_loss=0.02977, over 7135.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03063, over 1423076.15 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:20:22,902 INFO [train.py:763] (5/8) Epoch 33, batch 3300, loss[loss=0.1773, simple_loss=0.2835, pruned_loss=0.03555, over 7054.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03105, over 1419763.90 frames.], batch size: 28, lr: 2.28e-04
2022-04-30 16:21:28,694 INFO [train.py:763] (5/8) Epoch 33, batch 3350, loss[loss=0.1578, simple_loss=0.2643, pruned_loss=0.02568, over 7140.00 frames.], tot_loss[loss=0.161, simple_loss=0.2604, pruned_loss=0.03079, over 1422299.66 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:22:44,385 INFO [train.py:763] (5/8) Epoch 33, batch 3400, loss[loss=0.1767, simple_loss=0.2714, pruned_loss=0.04097, over 7199.00 frames.], tot_loss[loss=0.1616, simple_loss=0.261, pruned_loss=0.03108, over 1422403.76 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:23:50,293 INFO [train.py:763] (5/8) Epoch 33, batch 3450, loss[loss=0.1575, simple_loss=0.2508, pruned_loss=0.03214, over 7013.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03105, over 1428017.15 frames.], batch size: 16, lr: 2.28e-04
2022-04-30 16:24:55,496 INFO [train.py:763] (5/8) Epoch 33, batch 3500, loss[loss=0.1909, simple_loss=0.2864, pruned_loss=0.04769, over 7187.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03084, over 1429609.90 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:26:01,147 INFO [train.py:763] (5/8) Epoch 33, batch 3550, loss[loss=0.132, simple_loss=0.2224, pruned_loss=0.02083, over 7290.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03054, over 1431388.33 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:27:06,629 INFO [train.py:763] (5/8) Epoch 33, batch 3600, loss[loss=0.1487, simple_loss=0.258, pruned_loss=0.01971, over 7322.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03059, over 1432792.41 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:28:13,479 INFO [train.py:763] (5/8) Epoch 33, batch 3650, loss[loss=0.1507, simple_loss=0.253, pruned_loss=0.02421, over 6639.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03042, over 1428012.53 frames.], batch size: 38, lr: 2.28e-04
2022-04-30 16:29:20,527 INFO [train.py:763] (5/8) Epoch 33, batch 3700, loss[loss=0.1565, simple_loss=0.2532, pruned_loss=0.02992, over 7244.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2599, pruned_loss=0.03044, over 1423430.85 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:30:26,042 INFO [train.py:763] (5/8) Epoch 33, batch 3750, loss[loss=0.1568, simple_loss=0.2619, pruned_loss=0.02581, over 7293.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03022, over 1421062.96 frames.], batch size: 24, lr: 2.28e-04
2022-04-30 16:31:31,742 INFO [train.py:763] (5/8) Epoch 33, batch 3800, loss[loss=0.1642, simple_loss=0.2727, pruned_loss=0.0279, over 7147.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03034, over 1424945.94 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:32:38,626 INFO [train.py:763] (5/8) Epoch 33, batch 3850, loss[loss=0.1777, simple_loss=0.2807, pruned_loss=0.0374, over 7186.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03075, over 1427145.79 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:33:45,502 INFO [train.py:763] (5/8) Epoch 33, batch 3900, loss[loss=0.1733, simple_loss=0.2763, pruned_loss=0.03515, over 7223.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03022, over 1426116.11 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:34:52,463 INFO [train.py:763] (5/8) Epoch 33, batch 3950, loss[loss=0.1574, simple_loss=0.2639, pruned_loss=0.02541, over 7331.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03026, over 1423237.32 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:35:59,194 INFO [train.py:763] (5/8) Epoch 33, batch 4000, loss[loss=0.1617, simple_loss=0.2584, pruned_loss=0.03252, over 7059.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.02999, over 1423189.21 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:37:13,145 INFO [train.py:763] (5/8) Epoch 33, batch 4050, loss[loss=0.1717, simple_loss=0.2717, pruned_loss=0.03586, over 7159.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03041, over 1418058.41 frames.], batch size: 26, lr: 2.27e-04
2022-04-30 16:38:27,104 INFO [train.py:763] (5/8) Epoch 33, batch 4100, loss[loss=0.1623, simple_loss=0.2676, pruned_loss=0.02851, over 6501.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03074, over 1418941.59 frames.], batch size: 38, lr: 2.27e-04
2022-04-30 16:39:41,396 INFO [train.py:763] (5/8) Epoch 33, batch 4150, loss[loss=0.1425, simple_loss=0.2313, pruned_loss=0.02687, over 7413.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03059, over 1418185.07 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:40:55,333 INFO [train.py:763] (5/8) Epoch 33, batch 4200, loss[loss=0.188, simple_loss=0.2923, pruned_loss=0.04189, over 7242.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03051, over 1420168.98 frames.], batch size: 20, lr: 2.27e-04
2022-04-30 16:42:02,052 INFO [train.py:763] (5/8) Epoch 33, batch 4250, loss[loss=0.1407, simple_loss=0.2307, pruned_loss=0.02532, over 7141.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2616, pruned_loss=0.03075, over 1420289.14 frames.], batch size: 17, lr: 2.27e-04
2022-04-30 16:43:17,921 INFO [train.py:763] (5/8) Epoch 33, batch 4300, loss[loss=0.1392, simple_loss=0.2329, pruned_loss=0.02275, over 6993.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03058, over 1420847.82 frames.], batch size: 16, lr: 2.27e-04
2022-04-30 16:44:24,674 INFO [train.py:763] (5/8) Epoch 33, batch 4350, loss[loss=0.1356, simple_loss=0.2244, pruned_loss=0.02335, over 6735.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03096, over 1415527.11 frames.], batch size: 15, lr: 2.27e-04
2022-04-30 16:45:48,496 INFO [train.py:763] (5/8) Epoch 33, batch 4400, loss[loss=0.1636, simple_loss=0.259, pruned_loss=0.0341, over 7161.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.0306, over 1416260.39 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:46:53,556 INFO [train.py:763] (5/8) Epoch 33, batch 4450, loss[loss=0.1755, simple_loss=0.27, pruned_loss=0.0405, over 7190.00 frames.], tot_loss[loss=0.1618, simple_loss=0.262, pruned_loss=0.03079, over 1400886.15 frames.], batch size: 23, lr: 2.27e-04
2022-04-30 16:48:00,244 INFO [train.py:763] (5/8) Epoch 33, batch 4500, loss[loss=0.1788, simple_loss=0.2851, pruned_loss=0.03627, over 4947.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03125, over 1391693.78 frames.], batch size: 52, lr: 2.27e-04
2022-04-30 16:49:05,872 INFO [train.py:763] (5/8) Epoch 33, batch 4550, loss[loss=0.2014, simple_loss=0.2886, pruned_loss=0.05707, over 5229.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2644, pruned_loss=0.03196, over 1351848.91 frames.], batch size: 52, lr: 2.27e-04
2022-04-30 16:50:25,381 INFO [train.py:763] (5/8) Epoch 34, batch 0, loss[loss=0.1568, simple_loss=0.2597, pruned_loss=0.02692, over 7238.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2597, pruned_loss=0.02692, over 7238.00 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:51:31,607 INFO [train.py:763] (5/8) Epoch 34, batch 50, loss[loss=0.1665, simple_loss=0.2764, pruned_loss=0.02829, over 7270.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03094, over 318314.87 frames.], batch size: 24, lr: 2.24e-04
2022-04-30 16:52:37,606 INFO [train.py:763] (5/8) Epoch 34, batch 100, loss[loss=0.1599, simple_loss=0.267, pruned_loss=0.02634, over 7185.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02924, over 567692.98 frames.], batch size: 26, lr: 2.24e-04
2022-04-30 16:53:43,314 INFO [train.py:763] (5/8) Epoch 34, batch 150, loss[loss=0.1888, simple_loss=0.2837, pruned_loss=0.0469, over 7379.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02932, over 760247.62 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:54:49,445 INFO [train.py:763] (5/8) Epoch 34, batch 200, loss[loss=0.1489, simple_loss=0.2461, pruned_loss=0.02581, over 7064.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02936, over 909943.73 frames.], batch size: 18, lr: 2.24e-04
2022-04-30 16:55:56,556 INFO [train.py:763] (5/8) Epoch 34, batch 250, loss[loss=0.1599, simple_loss=0.2627, pruned_loss=0.02854, over 7232.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2583, pruned_loss=0.02928, over 1027202.16 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:57:03,057 INFO [train.py:763] (5/8) Epoch 34, batch 300, loss[loss=0.1449, simple_loss=0.238, pruned_loss=0.02594, over 7159.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02947, over 1113925.51 frames.], batch size: 19, lr: 2.24e-04
2022-04-30 16:58:08,941 INFO [train.py:763] (5/8) Epoch 34, batch 350, loss[loss=0.1764, simple_loss=0.2787, pruned_loss=0.03708, over 7186.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02975, over 1185860.37 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:59:14,462 INFO [train.py:763] (5/8) Epoch 34, batch 400, loss[loss=0.153, simple_loss=0.2492, pruned_loss=0.0284, over 7330.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02988, over 1240266.69 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 17:00:20,021 INFO [train.py:763] (5/8) Epoch 34, batch 450, loss[loss=0.1878, simple_loss=0.2942, pruned_loss=0.04072, over 6772.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.0298, over 1284744.82 frames.], batch size: 31, lr: 2.24e-04
2022-04-30 17:01:26,964 INFO [train.py:763] (5/8) Epoch 34, batch 500, loss[loss=0.19, simple_loss=0.2899, pruned_loss=0.045, over 7331.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02945, over 1313953.06 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:02:32,708 INFO [train.py:763] (5/8) Epoch 34, batch 550, loss[loss=0.1358, simple_loss=0.2362, pruned_loss=0.01771, over 7065.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2581, pruned_loss=0.02905, over 1335020.89 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:03:38,765 INFO [train.py:763] (5/8) Epoch 34, batch 600, loss[loss=0.1548, simple_loss=0.2582, pruned_loss=0.02575, over 7319.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2598, pruned_loss=0.02948, over 1353910.53 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:04:44,668 INFO [train.py:763] (5/8) Epoch 34, batch 650, loss[loss=0.1309, simple_loss=0.2354, pruned_loss=0.01317, over 7176.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2604, pruned_loss=0.02952, over 1372852.52 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:05:50,790 INFO [train.py:763] (5/8) Epoch 34, batch 700, loss[loss=0.1581, simple_loss=0.2491, pruned_loss=0.03358, over 7266.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02947, over 1387406.92 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:06:58,025 INFO [train.py:763] (5/8) Epoch 34, batch 750, loss[loss=0.136, simple_loss=0.2417, pruned_loss=0.01509, over 7254.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02939, over 1393723.92 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:08:04,372 INFO [train.py:763] (5/8) Epoch 34, batch 800, loss[loss=0.1627, simple_loss=0.2795, pruned_loss=0.02296, over 7224.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02927, over 1402583.80 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:09:09,698 INFO [train.py:763] (5/8) Epoch 34, batch 850, loss[loss=0.1846, simple_loss=0.2869, pruned_loss=0.04115, over 7287.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2604, pruned_loss=0.02921, over 1402573.98 frames.], batch size: 24, lr: 2.23e-04
2022-04-30 17:10:15,226 INFO [train.py:763] (5/8) Epoch 34, batch 900, loss[loss=0.2056, simple_loss=0.2862, pruned_loss=0.06251, over 5331.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.02949, over 1406237.96 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:11:21,168 INFO [train.py:763] (5/8) Epoch 34, batch 950, loss[loss=0.1585, simple_loss=0.2517, pruned_loss=0.03269, over 7251.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02946, over 1409400.00 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:12:27,415 INFO [train.py:763] (5/8) Epoch 34, batch 1000, loss[loss=0.1699, simple_loss=0.2672, pruned_loss=0.03635, over 6708.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2603, pruned_loss=0.02955, over 1410533.78 frames.], batch size: 31, lr: 2.23e-04
2022-04-30 17:13:34,603 INFO [train.py:763] (5/8) Epoch 34, batch 1050, loss[loss=0.1637, simple_loss=0.2627, pruned_loss=0.03236, over 7412.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02919, over 1415230.18 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:14:40,038 INFO [train.py:763] (5/8) Epoch 34, batch 1100, loss[loss=0.1457, simple_loss=0.2482, pruned_loss=0.02155, over 7366.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02943, over 1419853.79 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:15:45,153 INFO [train.py:763] (5/8) Epoch 34, batch 1150, loss[loss=0.1844, simple_loss=0.2802, pruned_loss=0.04428, over 7186.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02941, over 1421333.59 frames.], batch size: 23, lr: 2.23e-04
2022-04-30 17:16:50,475 INFO [train.py:763] (5/8) Epoch 34, batch 1200, loss[loss=0.1616, simple_loss=0.2532, pruned_loss=0.03499, over 7267.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.0293, over 1424747.65 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:17:56,084 INFO [train.py:763] (5/8) Epoch 34, batch 1250, loss[loss=0.1653, simple_loss=0.2707, pruned_loss=0.02999, over 7336.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02979, over 1423709.63 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:19:02,076 INFO [train.py:763] (5/8) Epoch 34, batch 1300, loss[loss=0.1684, simple_loss=0.2701, pruned_loss=0.03332, over 7082.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03014, over 1420443.37 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:20:07,323 INFO [train.py:763] (5/8) Epoch 34, batch 1350, loss[loss=0.1733, simple_loss=0.2777, pruned_loss=0.03446, over 7092.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03031, over 1423135.88 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:21:12,466 INFO [train.py:763] (5/8) Epoch 34, batch 1400, loss[loss=0.15, simple_loss=0.2516, pruned_loss=0.02423, over 7332.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03044, over 1421708.17 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:22:17,959 INFO [train.py:763] (5/8) Epoch 34, batch 1450, loss[loss=0.1559, simple_loss=0.2524, pruned_loss=0.02972, over 7265.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03053, over 1420190.46 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:23:24,439 INFO [train.py:763] (5/8) Epoch 34, batch 1500, loss[loss=0.1321, simple_loss=0.2295, pruned_loss=0.01732, over 7127.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03022, over 1420708.28 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:24:29,702 INFO [train.py:763] (5/8) Epoch 34, batch 1550, loss[loss=0.1735, simple_loss=0.2794, pruned_loss=0.03379, over 7230.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02989, over 1420336.96 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:25:36,478 INFO [train.py:763] (5/8) Epoch 34, batch 1600, loss[loss=0.1625, simple_loss=0.2643, pruned_loss=0.03032, over 7031.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02994, over 1421799.75 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:26:43,363 INFO [train.py:763] (5/8) Epoch 34, batch 1650, loss[loss=0.1484, simple_loss=0.2512, pruned_loss=0.02281, over 7413.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.0292, over 1426838.66 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:27:48,838 INFO [train.py:763] (5/8) Epoch 34, batch 1700, loss[loss=0.1757, simple_loss=0.266, pruned_loss=0.04265, over 5176.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02951, over 1425654.28 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:28:54,325 INFO [train.py:763] (5/8) Epoch 34, batch 1750, loss[loss=0.1524, simple_loss=0.2534, pruned_loss=0.02567, over 7176.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2586, pruned_loss=0.02925, over 1425247.60 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:29:59,726 INFO [train.py:763] (5/8) Epoch 34, batch 1800, loss[loss=0.175, simple_loss=0.284, pruned_loss=0.03298, over 7359.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2581, pruned_loss=0.02913, over 1428942.83 frames.], batch size: 25, lr: 2.23e-04
2022-04-30 17:31:04,985 INFO [train.py:763] (5/8) Epoch 34, batch 1850, loss[loss=0.1488, simple_loss=0.2506, pruned_loss=0.02352, over 7061.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02905, over 1426641.72 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:32:10,321 INFO [train.py:763] (5/8) Epoch 34, batch 1900, loss[loss=0.1978, simple_loss=0.2814, pruned_loss=0.05709, over 7374.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2581, pruned_loss=0.0294, over 1426341.19 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:33:15,844 INFO [train.py:763] (5/8) Epoch 34, batch 1950, loss[loss=0.1485, simple_loss=0.2434, pruned_loss=0.02675, over 7146.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2586, pruned_loss=0.02965, over 1424661.48 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:34:22,083 INFO [train.py:763] (5/8) Epoch 34, batch 2000, loss[loss=0.1641, simple_loss=0.2713, pruned_loss=0.02847, over 6544.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2586, pruned_loss=0.02992, over 1419740.09 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:35:27,878 INFO [train.py:763] (5/8) Epoch 34, batch 2050, loss[loss=0.1703, simple_loss=0.275, pruned_loss=0.03278, over 7111.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2598, pruned_loss=0.03018, over 1421237.18 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:36:33,097 INFO [train.py:763] (5/8) Epoch 34, batch 2100, loss[loss=0.166, simple_loss=0.2705, pruned_loss=0.03076, over 7409.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.0304, over 1424101.13 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:37:40,128 INFO [train.py:763] (5/8) Epoch 34, batch 2150, loss[loss=0.142, simple_loss=0.2501, pruned_loss=0.01691, over 6469.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.02995, over 1427333.79 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:38:46,199 INFO [train.py:763] (5/8) Epoch 34, batch 2200, loss[loss=0.1439, simple_loss=0.2469, pruned_loss=0.02044, over 7426.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03034, over 1423836.83 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:39:51,388 INFO [train.py:763] (5/8) Epoch 34, batch 2250, loss[loss=0.1401, simple_loss=0.2376, pruned_loss=0.02131, over 7283.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.0302, over 1421503.90 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:40:56,561 INFO [train.py:763] (5/8) Epoch 34, batch 2300, loss[loss=0.1773, simple_loss=0.2727, pruned_loss=0.04089, over 7206.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03019, over 1418293.98 frames.], batch size: 26, lr: 2.22e-04
2022-04-30 17:42:01,782 INFO [train.py:763] (5/8) Epoch 34, batch 2350, loss[loss=0.1484, simple_loss=0.2508, pruned_loss=0.02306, over 7129.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02978, over 1416395.83 frames.], batch size: 28, lr: 2.22e-04
2022-04-30 17:43:08,017 INFO [train.py:763] (5/8) Epoch 34, batch 2400, loss[loss=0.1232, simple_loss=0.2137, pruned_loss=0.01632, over 6982.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.0294, over 1422274.43 frames.], batch size: 16, lr: 2.22e-04
2022-04-30 17:44:15,067 INFO [train.py:763] (5/8) Epoch 34, batch 2450, loss[loss=0.1528, simple_loss=0.253, pruned_loss=0.0263, over 7434.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02916, over 1422417.90 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:45:22,384 INFO [train.py:763] (5/8) Epoch 34, batch 2500, loss[loss=0.1739, simple_loss=0.2813, pruned_loss=0.03324, over 6543.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02927, over 1423947.59 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:46:28,719 INFO [train.py:763] (5/8) Epoch 34, batch 2550, loss[loss=0.1673, simple_loss=0.266, pruned_loss=0.03435, over 7117.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02935, over 1423677.82 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:47:35,761 INFO [train.py:763] (5/8) Epoch 34, batch 2600, loss[loss=0.1844, simple_loss=0.2888, pruned_loss=0.03995, over 7199.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02943, over 1423860.64 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 17:48:40,942 INFO [train.py:763] (5/8) Epoch 34, batch 2650, loss[loss=0.1724, simple_loss=0.2778, pruned_loss=0.03352, over 7205.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.0294, over 1423320.80 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:49:46,282 INFO [train.py:763] (5/8) Epoch 34, batch 2700, loss[loss=0.1777, simple_loss=0.2861, pruned_loss=0.03467, over 7133.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.02995, over 1424847.99 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:50:51,546 INFO [train.py:763] (5/8) Epoch 34, batch 2750, loss[loss=0.178, simple_loss=0.2801, pruned_loss=0.03793, over 7327.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03002, over 1424393.19 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:51:57,732 INFO [train.py:763] (5/8) Epoch 34, batch 2800, loss[loss=0.146, simple_loss=0.2471, pruned_loss=0.02246, over 7331.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02994, over 1426047.26 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:53:04,501 INFO [train.py:763] (5/8) Epoch 34, batch 2850, loss[loss=0.1509, simple_loss=0.257, pruned_loss=0.02238, over 7154.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02999, over 1423818.45 frames.], batch size: 19, lr: 2.22e-04
2022-04-30 17:54:11,627 INFO [train.py:763] (5/8) Epoch 34, batch 2900, loss[loss=0.1917, simple_loss=0.3029, pruned_loss=0.04026, over 6326.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03009, over 1422825.44 frames.], batch size: 37, lr: 2.22e-04
2022-04-30 17:55:17,496 INFO [train.py:763] (5/8) Epoch 34, batch 2950, loss[loss=0.1405, simple_loss=0.2289, pruned_loss=0.02601, over 7199.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.0302, over 1416487.50 frames.], batch size: 16, lr: 2.22e-04
2022-04-30 17:56:22,959 INFO [train.py:763] (5/8) Epoch 34, batch 3000, loss[loss=0.1767, simple_loss=0.2793, pruned_loss=0.03709, over 7387.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.03002, over 1420557.20 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:56:22,961 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 17:56:38,270 INFO [train.py:792] (5/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
2022-04-30 17:57:44,335 INFO [train.py:763] (5/8) Epoch 34, batch 3050, loss[loss=0.1864, simple_loss=0.2881, pruned_loss=0.04231, over 7234.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.03001, over 1423533.88 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:58:51,173 INFO [train.py:763] (5/8) Epoch 34, batch 3100, loss[loss=0.1773, simple_loss=0.2749, pruned_loss=0.03982, over 7376.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.03, over 1420236.33 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:59:56,672 INFO [train.py:763] (5/8) Epoch 34, batch 3150, loss[loss=0.1881, simple_loss=0.2931, pruned_loss=0.0415, over 7192.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.02974, over 1422800.89 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:01:02,263 INFO [train.py:763] (5/8) Epoch 34, batch 3200, loss[loss=0.167, simple_loss=0.2741, pruned_loss=0.02998, over 7205.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2606, pruned_loss=0.02978, over 1427332.91 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:02:09,381 INFO [train.py:763] (5/8) Epoch 34, batch 3250, loss[loss=0.1603, simple_loss=0.2546, pruned_loss=0.03296, over 7433.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02961, over 1425649.21 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:03:15,763 INFO [train.py:763] (5/8) Epoch 34, batch 3300, loss[loss=0.1358, simple_loss=0.2283, pruned_loss=0.02168, over 7429.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02938, over 1426216.78 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:04:21,129 INFO [train.py:763] (5/8) Epoch 34, batch 3350, loss[loss=0.1459, simple_loss=0.2501, pruned_loss=0.02081, over 7428.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02913, over 1429738.09 frames.], batch size: 20, lr: 2.21e-04
2022-04-30 18:05:26,510 INFO [train.py:763] (5/8) Epoch 34, batch 3400, loss[loss=0.1449, simple_loss=0.234, pruned_loss=0.02786, over 7279.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.02946, over 1426075.67 frames.], batch size: 18, lr: 2.21e-04
2022-04-30 18:06:31,942 INFO [train.py:763] (5/8) Epoch 34, batch 3450, loss[loss=0.1337, simple_loss=0.2207, pruned_loss=0.02337, over 6997.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02992, over 1429071.10 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:07:37,458 INFO [train.py:763] (5/8) Epoch 34, batch 3500, loss[loss=0.1452, simple_loss=0.2503, pruned_loss=0.01999, over 7320.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02946, over 1427984.18 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:08:42,513 INFO [train.py:763] (5/8) Epoch 34, batch 3550, loss[loss=0.1596, simple_loss=0.2645, pruned_loss=0.02732, over 6715.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02983, over 1420785.15 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:09:48,194 INFO [train.py:763] (5/8) Epoch 34, batch 3600, loss[loss=0.1788, simple_loss=0.2738, pruned_loss=0.04195, over 7197.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03021, over 1419226.22 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:10:55,330 INFO [train.py:763] (5/8) Epoch 34, batch 3650, loss[loss=0.1575, simple_loss=0.2672, pruned_loss=0.02387, over 7294.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03047, over 1420584.07 frames.], batch size: 25, lr: 2.21e-04
2022-04-30 18:12:01,496 INFO [train.py:763] (5/8) Epoch 34, batch 3700, loss[loss=0.1488, simple_loss=0.2614, pruned_loss=0.01816, over 6473.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2609, pruned_loss=0.03005, over 1420117.20 frames.], batch size: 38, lr: 2.21e-04
2022-04-30 18:13:06,706 INFO [train.py:763] (5/8) Epoch 34, batch 3750, loss[loss=0.1732, simple_loss=0.2705, pruned_loss=0.03788, over 5316.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.02996, over 1417315.14 frames.], batch size: 52, lr: 2.21e-04
2022-04-30 18:14:11,988 INFO [train.py:763] (5/8) Epoch 34, batch 3800, loss[loss=0.1758, simple_loss=0.279, pruned_loss=0.03633, over 6742.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02988, over 1418170.99 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:15:17,338 INFO [train.py:763] (5/8) Epoch 34, batch 3850, loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.03095, over 7280.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2612, pruned_loss=0.03019, over 1421347.34 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:16:23,813 INFO [train.py:763] (5/8) Epoch 34, batch 3900, loss[loss=0.1338, simple_loss=0.2227, pruned_loss=0.02242, over 6763.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03015, over 1418360.16 frames.], batch size: 15, lr: 2.21e-04
2022-04-30 18:17:30,971 INFO [train.py:763] (5/8) Epoch 34, batch 3950, loss[loss=0.139, simple_loss=0.2371, pruned_loss=0.02042, over 7144.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02953, over 1418804.24 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:18:37,956 INFO [train.py:763] (5/8) Epoch 34, batch 4000, loss[loss=0.157, simple_loss=0.253, pruned_loss=0.03048, over 7017.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02971, over 1417924.46 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:19:54,755 INFO [train.py:763] (5/8) Epoch 34, batch 4050, loss[loss=0.1618, simple_loss=0.2667, pruned_loss=0.02849, over 6342.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.0297, over 1420836.27 frames.], batch size: 37, lr: 2.21e-04
2022-04-30 18:21:01,776 INFO [train.py:763] (5/8) Epoch 34, batch 4100, loss[loss=0.1631, simple_loss=0.2691, pruned_loss=0.02852, over 7224.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02937, over 1425905.20 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:22:08,653 INFO [train.py:763] (5/8) Epoch 34, batch 4150, loss[loss=0.1687, simple_loss=0.2811, pruned_loss=0.0281, over 7324.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02969, over 1424479.27 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:23:15,044 INFO [train.py:763] (5/8) Epoch 34, batch 4200, loss[loss=0.1702, simple_loss=0.2793, pruned_loss=0.03054, over 7310.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02962, over 1422117.98 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:24:20,541 INFO [train.py:763] (5/8) Epoch 34, batch 4250, loss[loss=0.1372, simple_loss=0.2312, pruned_loss=0.02155, over 7287.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.0294, over 1427077.81 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:25:25,966 INFO [train.py:763] (5/8) Epoch 34, batch 4300, loss[loss=0.1574, simple_loss=0.2555, pruned_loss=0.02963, over 7158.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02928, over 1419108.88 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:26:32,713 INFO [train.py:763] (5/8) Epoch 34, batch 4350, loss[loss=0.1818, simple_loss=0.2756, pruned_loss=0.04403, over 7285.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02993, over 1415151.44 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:27:38,208 INFO [train.py:763] (5/8) Epoch 34, batch 4400, loss[loss=0.1578, simple_loss=0.2592, pruned_loss=0.0282, over 7163.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03025, over 1410817.26 frames.], batch size: 19, lr: 2.21e-04
2022-04-30 18:28:42,660 INFO [train.py:763] (5/8) Epoch 34, batch 4450, loss[loss=0.1656, simple_loss=0.2617, pruned_loss=0.0347, over 6710.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03064, over 1394914.29 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:29:47,247 INFO [train.py:763] (5/8) Epoch 34, batch 4500, loss[loss=0.1616, simple_loss=0.2689, pruned_loss=0.02718, over 7163.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03121, over 1380510.70 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:30:51,777 INFO [train.py:763] (5/8) Epoch 34, batch 4550, loss[loss=0.1897, simple_loss=0.2905, pruned_loss=0.04445, over 5467.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2635, pruned_loss=0.03195, over 1354792.11 frames.], batch size: 53, lr: 2.21e-04
2022-04-30 18:32:11,389 INFO [train.py:763] (5/8) Epoch 35, batch 0, loss[loss=0.1434, simple_loss=0.2464, pruned_loss=0.02023, over 7333.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2464, pruned_loss=0.02023, over 7333.00 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:33:17,377 INFO [train.py:763] (5/8) Epoch 35, batch 50, loss[loss=0.1669, simple_loss=0.268, pruned_loss=0.03289, over 7424.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2614, pruned_loss=0.03055, over 315939.48 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:34:22,747 INFO [train.py:763] (5/8) Epoch 35, batch 100, loss[loss=0.185, simple_loss=0.2816, pruned_loss=0.04422, over 4741.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02988, over 561176.66 frames.], batch size: 52, lr: 2.17e-04
2022-04-30 18:35:28,405 INFO [train.py:763] (5/8) Epoch 35, batch 150, loss[loss=0.1822, simple_loss=0.2774, pruned_loss=0.04351, over 7227.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2581, pruned_loss=0.02958, over 750495.04 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:36:34,088 INFO [train.py:763] (5/8) Epoch 35, batch 200, loss[loss=0.1507, simple_loss=0.2589, pruned_loss=0.02121, over 7317.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.02995, over 901035.98 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:37:50,845 INFO [train.py:763] (5/8) Epoch 35, batch 250, loss[loss=0.1403, simple_loss=0.2398, pruned_loss=0.02046, over 7158.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02951, over 1020609.24 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:38:58,244 INFO [train.py:763] (5/8) Epoch 35, batch 300, loss[loss=0.1907, simple_loss=0.2849, pruned_loss=0.04828, over 7139.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.0299, over 1105924.12 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:40:05,547 INFO [train.py:763] (5/8) Epoch 35, batch 350, loss[loss=0.1978, simple_loss=0.3011, pruned_loss=0.04719, over 6835.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2616, pruned_loss=0.02985, over 1174962.49 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:41:12,764 INFO [train.py:763] (5/8) Epoch 35, batch 400, loss[loss=0.1902, simple_loss=0.2882, pruned_loss=0.04616, over 7213.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2625, pruned_loss=0.03016, over 1230988.29 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:42:19,853 INFO [train.py:763] (5/8) Epoch 35, batch 450, loss[loss=0.1632, simple_loss=0.2639, pruned_loss=0.03129, over 7201.00 frames.], tot_loss[loss=0.1612, simple_loss=0.262, pruned_loss=0.03018, over 1278935.93 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:43:25,157 INFO [train.py:763] (5/8) Epoch 35, batch 500, loss[loss=0.1693, simple_loss=0.2736, pruned_loss=0.03246, over 7206.00 frames.], tot_loss[loss=0.1613, simple_loss=0.262, pruned_loss=0.03035, over 1310569.42 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:44:30,970 INFO [train.py:763] (5/8) Epoch 35, batch 550, loss[loss=0.1529, simple_loss=0.2529, pruned_loss=0.02643, over 7433.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2623, pruned_loss=0.03004, over 1336911.45 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:45:37,231 INFO [train.py:763] (5/8) Epoch 35, batch 600, loss[loss=0.1676, simple_loss=0.266, pruned_loss=0.03461, over 7190.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.02962, over 1359299.60 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:46:44,902 INFO [train.py:763] (5/8) Epoch 35, batch 650, loss[loss=0.1586, simple_loss=0.2546, pruned_loss=0.03125, over 7157.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02918, over 1374809.30 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:47:52,737 INFO [train.py:763] (5/8) Epoch 35, batch 700, loss[loss=0.1477, simple_loss=0.2422, pruned_loss=0.02653, over 7269.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03004, over 1386471.35 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:48:58,275 INFO [train.py:763] (5/8) Epoch 35, batch 750, loss[loss=0.1447, simple_loss=0.242, pruned_loss=0.02369, over 7329.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02992, over 1385611.56 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:50:03,737 INFO [train.py:763] (5/8) Epoch 35, batch 800, loss[loss=0.1812, simple_loss=0.284, pruned_loss=0.03926, over 7402.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.0302, over 1394090.93 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:51:09,204 INFO [train.py:763] (5/8) Epoch 35, batch 850, loss[loss=0.1411, simple_loss=0.2438, pruned_loss=0.01917, over 7226.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.03019, over 1395373.10 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:52:23,433 INFO [train.py:763] (5/8) Epoch 35, batch 900, loss[loss=0.1579, simple_loss=0.2654, pruned_loss=0.02524, over 6700.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03029, over 1401794.02 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:53:37,770 INFO [train.py:763] (5/8) Epoch 35, batch 950, loss[loss=0.1396, simple_loss=0.2262, pruned_loss=0.02652, over 7004.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2614, pruned_loss=0.0304, over 1405655.41 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 18:54:42,879 INFO [train.py:763] (5/8) Epoch 35, batch 1000, loss[loss=0.1359, simple_loss=0.2339, pruned_loss=0.01892, over 7281.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2604, pruned_loss=0.02971, over 1407233.29 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 18:55:57,243 INFO [train.py:763] (5/8) Epoch 35, batch 1050, loss[loss=0.1475, simple_loss=0.2444, pruned_loss=0.02531, over 7351.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02972, over 1408369.79 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:57:20,302 INFO [train.py:763] (5/8) Epoch 35, batch 1100, loss[loss=0.1802, simple_loss=0.2629, pruned_loss=0.04874, over 7207.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02959, over 1409025.81 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:58:25,989 INFO [train.py:763] (5/8) Epoch 35, batch 1150, loss[loss=0.1699, simple_loss=0.2606, pruned_loss=0.0396, over 7291.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02902, over 1414401.98 frames.], batch size: 24, lr: 2.17e-04
2022-04-30 18:59:32,117 INFO [train.py:763] (5/8) Epoch 35, batch 1200, loss[loss=0.1273, simple_loss=0.2231, pruned_loss=0.01573, over 7259.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2605, pruned_loss=0.02961, over 1409657.08 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:00:55,258 INFO [train.py:763] (5/8) Epoch 35, batch 1250, loss[loss=0.1291, simple_loss=0.2186, pruned_loss=0.01979, over 7028.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.0293, over 1411701.72 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:02:00,728 INFO [train.py:763] (5/8) Epoch 35, batch 1300, loss[loss=0.1505, simple_loss=0.2395, pruned_loss=0.03078, over 7133.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02947, over 1415461.50 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:03:07,770 INFO [train.py:763] (5/8) Epoch 35, batch 1350, loss[loss=0.1601, simple_loss=0.2632, pruned_loss=0.02851, over 7257.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02967, over 1419904.27 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 19:04:12,917 INFO [train.py:763] (5/8) Epoch 35, batch 1400, loss[loss=0.1388, simple_loss=0.2266, pruned_loss=0.0255, over 7005.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.03002, over 1418255.92 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:05:18,838 INFO [train.py:763] (5/8) Epoch 35, batch 1450, loss[loss=0.1209, simple_loss=0.2104, pruned_loss=0.0157, over 6832.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02975, over 1414712.60 frames.], batch size: 15, lr: 2.17e-04
2022-04-30 19:06:24,730 INFO [train.py:763] (5/8) Epoch 35, batch 1500, loss[loss=0.1475, simple_loss=0.2466, pruned_loss=0.02416, over 7320.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02952, over 1418972.43 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 19:07:30,582 INFO [train.py:763] (5/8) Epoch 35, batch 1550, loss[loss=0.1492, simple_loss=0.2613, pruned_loss=0.01856, over 7242.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2597, pruned_loss=0.02904, over 1420265.14 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 19:08:36,020 INFO [train.py:763] (5/8) Epoch 35, batch 1600, loss[loss=0.1788, simple_loss=0.273, pruned_loss=0.0423, over 7363.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02911, over 1419918.34 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:09:42,628 INFO [train.py:763] (5/8) Epoch 35, batch 1650, loss[loss=0.1535, simple_loss=0.2599, pruned_loss=0.02356, over 7163.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02915, over 1420938.22 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:10:49,568 INFO [train.py:763] (5/8) Epoch 35, batch 1700, loss[loss=0.1539, simple_loss=0.2416, pruned_loss=0.03316, over 7296.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.02898, over 1423401.27 frames.], batch size: 25, lr: 2.16e-04
2022-04-30 19:11:56,507 INFO [train.py:763] (5/8) Epoch 35, batch 1750, loss[loss=0.1408, simple_loss=0.2387, pruned_loss=0.02141, over 7280.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.0292, over 1419128.49 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:13:03,552 INFO [train.py:763] (5/8) Epoch 35, batch 1800, loss[loss=0.1688, simple_loss=0.2703, pruned_loss=0.03366, over 7220.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02917, over 1421349.82 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:14:09,383 INFO [train.py:763] (5/8) Epoch 35, batch 1850, loss[loss=0.172, simple_loss=0.2798, pruned_loss=0.03205, over 7116.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02914, over 1424111.30 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:15:15,155 INFO [train.py:763] (5/8) Epoch 35, batch 1900, loss[loss=0.1621, simple_loss=0.2687, pruned_loss=0.02774, over 6806.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2597, pruned_loss=0.02907, over 1425680.64 frames.], batch size: 31, lr: 2.16e-04
2022-04-30 19:16:21,443 INFO [train.py:763] (5/8) Epoch 35, batch 1950, loss[loss=0.1652, simple_loss=0.266, pruned_loss=0.03223, over 7234.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02936, over 1422245.60 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:17:27,464 INFO [train.py:763] (5/8) Epoch 35, batch 2000, loss[loss=0.139, simple_loss=0.2272, pruned_loss=0.02535, over 7012.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02984, over 1419653.16 frames.], batch size: 16, lr: 2.16e-04
2022-04-30 19:18:34,501 INFO [train.py:763] (5/8) Epoch 35, batch 2050, loss[loss=0.2093, simple_loss=0.3215, pruned_loss=0.04853, over 7309.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2606, pruned_loss=0.02949, over 1423962.84 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:19:40,394 INFO [train.py:763] (5/8) Epoch 35, batch 2100, loss[loss=0.1541, simple_loss=0.2666, pruned_loss=0.02082, over 7405.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2601, pruned_loss=0.02957, over 1422716.33 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:20:47,329 INFO [train.py:763] (5/8) Epoch 35, batch 2150, loss[loss=0.1451, simple_loss=0.2359, pruned_loss=0.02709, over 7254.00 frames.], tot_loss[loss=0.159, simple_loss=0.2588, pruned_loss=0.02964, over 1425151.47 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:21:54,061 INFO [train.py:763] (5/8) Epoch 35, batch 2200, loss[loss=0.1306, simple_loss=0.2215, pruned_loss=0.01981, over 7421.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2582, pruned_loss=0.02925, over 1424414.93 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:23:01,264 INFO [train.py:763] (5/8) Epoch 35, batch 2250, loss[loss=0.1625, simple_loss=0.2716, pruned_loss=0.02666, over 7328.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02935, over 1421862.84 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:24:07,989 INFO [train.py:763] (5/8) Epoch 35, batch 2300, loss[loss=0.1139, simple_loss=0.2017, pruned_loss=0.01307, over 7128.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2581, pruned_loss=0.02932, over 1425307.84 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:25:12,953 INFO [train.py:763] (5/8) Epoch 35, batch 2350, loss[loss=0.1699, simple_loss=0.2696, pruned_loss=0.03512, over 5335.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02953, over 1423984.15 frames.], batch size: 52, lr: 2.16e-04
2022-04-30 19:26:18,892 INFO [train.py:763] (5/8) Epoch 35, batch 2400, loss[loss=0.1516, simple_loss=0.248, pruned_loss=0.0276, over 7421.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02956, over 1427435.84 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:27:24,050 INFO [train.py:763] (5/8) Epoch 35, batch 2450, loss[loss=0.1372, simple_loss=0.2398, pruned_loss=0.01734, over 7154.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02932, over 1423366.45 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:28:30,241 INFO [train.py:763] (5/8) Epoch 35, batch 2500, loss[loss=0.138, simple_loss=0.2463, pruned_loss=0.01486, over 7148.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.0292, over 1426478.41 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:29:36,786 INFO [train.py:763] (5/8) Epoch 35, batch 2550, loss[loss=0.1457, simple_loss=0.2466, pruned_loss=0.02235, over 7352.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2592, pruned_loss=0.02965, over 1423495.63 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:30:41,925 INFO [train.py:763] (5/8) Epoch 35, batch 2600, loss[loss=0.1482, simple_loss=0.253, pruned_loss=0.02167, over 7160.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02974, over 1424702.51 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:31:47,698 INFO [train.py:763] (5/8) Epoch 35, batch 2650, loss[loss=0.1996, simple_loss=0.2938, pruned_loss=0.05271, over 5304.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.0296, over 1424153.44 frames.], batch size: 52, lr: 2.16e-04
2022-04-30 19:32:53,216 INFO [train.py:763] (5/8) Epoch 35, batch 2700, loss[loss=0.1572, simple_loss=0.2592, pruned_loss=0.02759, over 7316.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2596, pruned_loss=0.0297, over 1424461.27 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:33:59,271 INFO [train.py:763] (5/8) Epoch 35, batch 2750, loss[loss=0.1772, simple_loss=0.281, pruned_loss=0.03669, over 7116.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.0298, over 1426333.51 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:35:05,459 INFO [train.py:763] (5/8) Epoch 35, batch 2800, loss[loss=0.1761, simple_loss=0.2832, pruned_loss=0.03445, over 7204.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02974, over 1427269.61 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:36:12,144 INFO [train.py:763] (5/8) Epoch 35, batch 2850, loss[loss=0.1381, simple_loss=0.2276, pruned_loss=0.02427, over 7288.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2582, pruned_loss=0.0292, over 1428405.42 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:37:18,079 INFO [train.py:763] (5/8) Epoch 35, batch 2900, loss[loss=0.1544, simple_loss=0.2482, pruned_loss=0.03025, over 7251.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2582, pruned_loss=0.02925, over 1427112.14 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:38:23,363 INFO [train.py:763] (5/8) Epoch 35, batch 2950, loss[loss=0.1419, simple_loss=0.2381, pruned_loss=0.02291, over 7168.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02978, over 1425401.54 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:39:28,874 INFO [train.py:763] (5/8) Epoch 35, batch 3000, loss[loss=0.1508, simple_loss=0.2516, pruned_loss=0.02505, over 7176.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.0304, over 1422119.48 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:39:28,875 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 19:39:43,929 INFO [train.py:792] (5/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
2022-04-30 19:40:49,420 INFO [train.py:763] (5/8) Epoch 35, batch 3050, loss[loss=0.152, simple_loss=0.2515, pruned_loss=0.02627, over 7280.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03014, over 1424057.18 frames.], batch size: 24, lr: 2.16e-04
2022-04-30 19:41:55,477 INFO [train.py:763] (5/8) Epoch 35, batch 3100, loss[loss=0.1588, simple_loss=0.2629, pruned_loss=0.02738, over 7280.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2613, pruned_loss=0.02984, over 1428475.54 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:43:02,580 INFO [train.py:763] (5/8) Epoch 35, batch 3150, loss[loss=0.1711, simple_loss=0.2705, pruned_loss=0.03582, over 7377.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.02968, over 1426782.73 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:44:09,430 INFO [train.py:763] (5/8) Epoch 35, batch 3200, loss[loss=0.1317, simple_loss=0.2255, pruned_loss=0.01893, over 7134.00 frames.], tot_loss[loss=0.16, simple_loss=0.2609, pruned_loss=0.0296, over 1420410.01 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:45:15,570 INFO [train.py:763] (5/8) Epoch 35, batch 3250, loss[loss=0.1608, simple_loss=0.2688, pruned_loss=0.02641, over 5079.00 frames.], tot_loss[loss=0.16, simple_loss=0.2607, pruned_loss=0.02963, over 1417920.70 frames.], batch size: 53, lr: 2.15e-04
2022-04-30 19:46:21,016 INFO [train.py:763] (5/8) Epoch 35, batch 3300, loss[loss=0.1906, simple_loss=0.2871, pruned_loss=0.04705, over 7208.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2615, pruned_loss=0.02997, over 1421478.88 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:47:26,303 INFO [train.py:763] (5/8) Epoch 35, batch 3350, loss[loss=0.1681, simple_loss=0.2718, pruned_loss=0.03216, over 7193.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2616, pruned_loss=0.02992, over 1425595.94 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:48:32,225 INFO [train.py:763] (5/8) Epoch 35, batch 3400, loss[loss=0.1472, simple_loss=0.2585, pruned_loss=0.01794, over 7267.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02937, over 1424596.29 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:49:37,620 INFO [train.py:763] (5/8) Epoch 35, batch 3450, loss[loss=0.1421, simple_loss=0.2327, pruned_loss=0.02579, over 7279.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.02943, over 1422474.72 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:50:43,220 INFO [train.py:763] (5/8) Epoch 35, batch 3500, loss[loss=0.161, simple_loss=0.2548, pruned_loss=0.03362, over 7405.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02967, over 1419529.21 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:51:48,959 INFO [train.py:763] (5/8) Epoch 35, batch 3550, loss[loss=0.1645, simple_loss=0.2676, pruned_loss=0.0307, over 7102.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2605, pruned_loss=0.02962, over 1423079.58 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 19:52:54,522 INFO [train.py:763] (5/8) Epoch 35, batch 3600, loss[loss=0.1639, simple_loss=0.2744, pruned_loss=0.02667, over 7265.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2611, pruned_loss=0.02998, over 1421897.21 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:54:00,486 INFO [train.py:763] (5/8) Epoch 35, batch 3650, loss[loss=0.1627, simple_loss=0.2696, pruned_loss=0.02792, over 7288.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03013, over 1423292.50 frames.], batch size: 24, lr: 2.15e-04
2022-04-30 19:55:05,857 INFO [train.py:763] (5/8) Epoch 35, batch 3700, loss[loss=0.1766, simple_loss=0.2863, pruned_loss=0.03349, over 7103.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.03012, over 1426267.99 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:56:11,431 INFO [train.py:763] (5/8) Epoch 35, batch 3750, loss[loss=0.1697, simple_loss=0.273, pruned_loss=0.03325, over 7329.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2611, pruned_loss=0.03026, over 1425606.06 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 19:57:16,648 INFO [train.py:763] (5/8) Epoch 35, batch 3800, loss[loss=0.1528, simple_loss=0.2448, pruned_loss=0.03043, over 7348.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2615, pruned_loss=0.03017, over 1427885.63 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:58:21,849 INFO [train.py:763] (5/8) Epoch 35, batch 3850, loss[loss=0.1182, simple_loss=0.217, pruned_loss=0.009707, over 6993.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2617, pruned_loss=0.02993, over 1424525.20 frames.], batch size: 16, lr: 2.15e-04
2022-04-30 19:59:27,370 INFO [train.py:763] (5/8) Epoch 35, batch 3900, loss[loss=0.1564, simple_loss=0.2631, pruned_loss=0.02489, over 7179.00 frames.], tot_loss[loss=0.1604, simple_loss=0.261, pruned_loss=0.02994, over 1426521.37 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:00:33,653 INFO [train.py:763] (5/8) Epoch 35, batch 3950, loss[loss=0.1513, simple_loss=0.2612, pruned_loss=0.02076, over 6820.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2608, pruned_loss=0.0294, over 1424236.38 frames.], batch size: 31, lr: 2.15e-04
2022-04-30 20:01:41,084 INFO [train.py:763] (5/8) Epoch 35, batch 4000, loss[loss=0.1915, simple_loss=0.2889, pruned_loss=0.04702, over 7135.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2613, pruned_loss=0.02966, over 1423394.61 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 20:02:46,174 INFO [train.py:763] (5/8) Epoch 35, batch 4050, loss[loss=0.1494, simple_loss=0.2605, pruned_loss=0.01911, over 7217.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2607, pruned_loss=0.02901, over 1425812.46 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:03:51,649 INFO [train.py:763] (5/8) Epoch 35, batch 4100, loss[loss=0.1293, simple_loss=0.2186, pruned_loss=0.02003, over 7149.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2601, pruned_loss=0.02888, over 1426110.03 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 20:04:57,467 INFO [train.py:763] (5/8) Epoch 35, batch 4150, loss[loss=0.1578, simple_loss=0.2623, pruned_loss=0.02666, over 7196.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02906, over 1418597.72 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:06:03,192 INFO [train.py:763] (5/8) Epoch 35, batch 4200, loss[loss=0.1619, simple_loss=0.2701, pruned_loss=0.02681, over 7231.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02959, over 1416140.18 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:07:09,103 INFO [train.py:763] (5/8) Epoch 35, batch 4250, loss[loss=0.1541, simple_loss=0.2627, pruned_loss=0.02277, over 7217.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02936, over 1415849.46 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:08:14,300 INFO [train.py:763] (5/8) Epoch 35, batch 4300, loss[loss=0.1525, simple_loss=0.251, pruned_loss=0.02699, over 7190.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2583, pruned_loss=0.02936, over 1412487.29 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:09:20,409 INFO [train.py:763] (5/8) Epoch 35, batch 4350, loss[loss=0.1441, simple_loss=0.2491, pruned_loss=0.01951, over 7422.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2574, pruned_loss=0.02901, over 1410413.80 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:10:26,460 INFO [train.py:763] (5/8) Epoch 35, batch 4400, loss[loss=0.1409, simple_loss=0.2454, pruned_loss=0.01825, over 7348.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2573, pruned_loss=0.02902, over 1415289.35 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:11:33,068 INFO [train.py:763] (5/8) Epoch 35, batch 4450, loss[loss=0.1618, simple_loss=0.2517, pruned_loss=0.03599, over 7211.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2565, pruned_loss=0.02883, over 1405889.21 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:12:39,700 INFO [train.py:763] (5/8) Epoch 35, batch 4500, loss[loss=0.1804, simple_loss=0.2879, pruned_loss=0.03644, over 7227.00 frames.], tot_loss[loss=0.1579, simple_loss=0.257, pruned_loss=0.02934, over 1393554.74 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:13:46,217 INFO [train.py:763] (5/8) Epoch 35, batch 4550, loss[loss=0.1495, simple_loss=0.2583, pruned_loss=0.02035, over 7255.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2586, pruned_loss=0.03042, over 1353666.43 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:15:13,849 INFO [train.py:763] (5/8) Epoch 36, batch 0, loss[loss=0.1604, simple_loss=0.2671, pruned_loss=0.02684, over 7326.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2671, pruned_loss=0.02684, over 7326.00 frames.], batch size: 22, lr: 2.12e-04
2022-04-30 20:16:19,182 INFO [train.py:763] (5/8) Epoch 36, batch 50, loss[loss=0.1381, simple_loss=0.2281, pruned_loss=0.02408, over 7064.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.0304, over 320494.87 frames.], batch size: 18, lr: 2.12e-04
2022-04-30 20:17:24,383 INFO [train.py:763] (5/8) Epoch 36, batch 100, loss[loss=0.1532, simple_loss=0.267, pruned_loss=0.01971, over 7337.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2596, pruned_loss=0.02926, over 566561.18 frames.], batch size: 20, lr: 2.12e-04
2022-04-30 20:18:29,500 INFO [train.py:763] (5/8) Epoch 36, batch 150, loss[loss=0.1641, simple_loss=0.2722, pruned_loss=0.02799, over 7097.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02961, over 753770.75 frames.], batch size: 28, lr: 2.11e-04
2022-04-30 20:19:34,478 INFO [train.py:763] (5/8) Epoch 36, batch 200, loss[loss=0.163, simple_loss=0.2787, pruned_loss=0.02364, over 7323.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2623, pruned_loss=0.02957, over 905759.55 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:20:39,733 INFO [train.py:763] (5/8) Epoch 36, batch 250, loss[loss=0.1486, simple_loss=0.2481, pruned_loss=0.02457, over 7263.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2613, pruned_loss=0.02894, over 1018530.21 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:21:45,228 INFO [train.py:763] (5/8) Epoch 36, batch 300, loss[loss=0.1619, simple_loss=0.2719, pruned_loss=0.02599, over 7340.00 frames.], tot_loss[loss=0.1589, simple_loss=0.26, pruned_loss=0.02889, over 1105677.91 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:22:50,520 INFO [train.py:763] (5/8) Epoch 36, batch 350, loss[loss=0.1419, simple_loss=0.2352, pruned_loss=0.02424, over 7168.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02883, over 1174133.88 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:23:55,936 INFO [train.py:763] (5/8) Epoch 36, batch 400, loss[loss=0.1407, simple_loss=0.2462, pruned_loss=0.01756, over 7231.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02881, over 1233146.04 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:25:01,051 INFO [train.py:763] (5/8) Epoch 36, batch 450, loss[loss=0.1596, simple_loss=0.2736, pruned_loss=0.02276, over 7145.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2597, pruned_loss=0.0288, over 1277607.60 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:26:07,080 INFO [train.py:763] (5/8) Epoch 36, batch 500, loss[loss=0.1504, simple_loss=0.2533, pruned_loss=0.0237, over 7236.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02912, over 1306405.97 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:27:14,411 INFO [train.py:763] (5/8) Epoch 36, batch 550, loss[loss=0.1511, simple_loss=0.2495, pruned_loss=0.02635, over 7066.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02933, over 1322916.30 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:28:22,081 INFO [train.py:763] (5/8) Epoch 36, batch 600, loss[loss=0.1399, simple_loss=0.235, pruned_loss=0.0224, over 7436.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.02874, over 1347805.30 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:29:29,901 INFO [train.py:763] (5/8) Epoch 36, batch 650, loss[loss=0.1399, simple_loss=0.2297, pruned_loss=0.02511, over 7144.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2568, pruned_loss=0.0285, over 1367169.72 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:30:35,973 INFO [train.py:763] (5/8) Epoch 36, batch 700, loss[loss=0.1858, simple_loss=0.2817, pruned_loss=0.04491, over 7224.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2575, pruned_loss=0.02899, over 1380590.43 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:31:41,366 INFO [train.py:763] (5/8) Epoch 36, batch 750, loss[loss=0.1517, simple_loss=0.2468, pruned_loss=0.02828, over 7162.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2568, pruned_loss=0.02867, over 1388663.77 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:32:47,561 INFO [train.py:763] (5/8) Epoch 36, batch 800, loss[loss=0.1526, simple_loss=0.2485, pruned_loss=0.02837, over 7423.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2562, pruned_loss=0.02859, over 1398660.69 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:33:53,520 INFO [train.py:763] (5/8) Epoch 36, batch 850, loss[loss=0.1432, simple_loss=0.2409, pruned_loss=0.0228, over 7256.00 frames.], tot_loss[loss=0.1573, simple_loss=0.257, pruned_loss=0.02877, over 1397538.81 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:34:59,129 INFO [train.py:763] (5/8) Epoch 36, batch 900, loss[loss=0.1629, simple_loss=0.2691, pruned_loss=0.02837, over 7064.00 frames.], tot_loss[loss=0.157, simple_loss=0.2569, pruned_loss=0.02851, over 1406194.02 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:36:04,440 INFO [train.py:763] (5/8) Epoch 36, batch 950, loss[loss=0.1334, simple_loss=0.2234, pruned_loss=0.02175, over 7269.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02856, over 1409757.84 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:37:09,733 INFO [train.py:763] (5/8) Epoch 36, batch 1000, loss[loss=0.1583, simple_loss=0.2606, pruned_loss=0.02795, over 6776.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2571, pruned_loss=0.02832, over 1412937.60 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:38:15,275 INFO [train.py:763] (5/8) Epoch 36, batch 1050, loss[loss=0.1752, simple_loss=0.2763, pruned_loss=0.03702, over 7403.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02864, over 1417918.08 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:39:20,508 INFO [train.py:763] (5/8) Epoch 36, batch 1100, loss[loss=0.1768, simple_loss=0.2936, pruned_loss=0.03002, over 7238.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2573, pruned_loss=0.02888, over 1418275.33 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:40:26,426 INFO [train.py:763] (5/8) Epoch 36, batch 1150, loss[loss=0.1745, simple_loss=0.2775, pruned_loss=0.03577, over 5189.00 frames.], tot_loss[loss=0.1579, simple_loss=0.258, pruned_loss=0.02895, over 1417333.32 frames.], batch size: 52, lr: 2.11e-04
2022-04-30 20:41:32,766 INFO [train.py:763] (5/8) Epoch 36, batch 1200, loss[loss=0.1771, simple_loss=0.2748, pruned_loss=0.03969, over 7144.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02887, over 1419810.69 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:42:37,811 INFO [train.py:763] (5/8) Epoch 36, batch 1250, loss[loss=0.1839, simple_loss=0.2879, pruned_loss=0.03992, over 7216.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02886, over 1420038.44 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:43:42,986 INFO [train.py:763] (5/8) Epoch 36, batch 1300, loss[loss=0.1405, simple_loss=0.2279, pruned_loss=0.02651, over 7147.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2596, pruned_loss=0.02879, over 1422250.63 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:44:48,213 INFO [train.py:763] (5/8) Epoch 36, batch 1350, loss[loss=0.1509, simple_loss=0.2502, pruned_loss=0.0258, over 7068.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02885, over 1418510.50 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:45:54,984 INFO [train.py:763] (5/8) Epoch 36, batch 1400, loss[loss=0.1173, simple_loss=0.2084, pruned_loss=0.01313, over 7008.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02918, over 1417903.67 frames.], batch size: 16, lr: 2.11e-04
2022-04-30 20:47:00,120 INFO [train.py:763] (5/8) Epoch 36, batch 1450, loss[loss=0.1768, simple_loss=0.2773, pruned_loss=0.03816, over 7267.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.0294, over 1418699.77 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:48:05,227 INFO [train.py:763] (5/8) Epoch 36, batch 1500, loss[loss=0.1868, simple_loss=0.2924, pruned_loss=0.04056, over 7289.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02965, over 1415324.37 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:49:10,954 INFO [train.py:763] (5/8) Epoch 36, batch 1550, loss[loss=0.1511, simple_loss=0.2561, pruned_loss=0.02302, over 6799.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03016, over 1410349.87 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:50:16,889 INFO [train.py:763] (5/8) Epoch 36, batch 1600, loss[loss=0.1779, simple_loss=0.2717, pruned_loss=0.042, over 7376.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.0297, over 1410774.13 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:51:24,054 INFO [train.py:763] (5/8) Epoch 36, batch 1650, loss[loss=0.172, simple_loss=0.2784, pruned_loss=0.03273, over 7191.00 frames.], tot_loss[loss=0.1588, simple_loss=0.259, pruned_loss=0.02931, over 1414124.33 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:52:38,234 INFO [train.py:763] (5/8) Epoch 36, batch 1700, loss[loss=0.1384, simple_loss=0.2448, pruned_loss=0.016, over 7167.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02944, over 1413325.25 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:53:43,586 INFO [train.py:763] (5/8) Epoch 36, batch 1750, loss[loss=0.1597, simple_loss=0.2645, pruned_loss=0.02747, over 7356.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02959, over 1407824.13 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:54:48,734 INFO [train.py:763] (5/8) Epoch 36, batch 1800, loss[loss=0.166, simple_loss=0.2751, pruned_loss=0.02844, over 7314.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02973, over 1409746.40 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 20:55:54,038 INFO [train.py:763] (5/8) Epoch 36, batch 1850, loss[loss=0.1567, simple_loss=0.2568, pruned_loss=0.02824, over 7252.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.0296, over 1410254.62 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:56:59,662 INFO [train.py:763] (5/8) Epoch 36, batch 1900, loss[loss=0.1857, simple_loss=0.2777, pruned_loss=0.04689, over 6847.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02959, over 1416407.23 frames.], batch size: 31, lr: 2.10e-04
2022-04-30 20:58:07,236 INFO [train.py:763] (5/8) Epoch 36, batch 1950, loss[loss=0.1566, simple_loss=0.2613, pruned_loss=0.02599, over 7221.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2597, pruned_loss=0.02964, over 1420007.74 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 20:59:14,634 INFO [train.py:763] (5/8) Epoch 36, batch 2000, loss[loss=0.1575, simple_loss=0.2684, pruned_loss=0.0233, over 7419.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02939, over 1417545.99 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:00:22,196 INFO [train.py:763] (5/8) Epoch 36, batch 2050, loss[loss=0.1529, simple_loss=0.2481, pruned_loss=0.0289, over 7237.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02899, over 1420006.25 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:01:28,534 INFO [train.py:763] (5/8) Epoch 36, batch 2100, loss[loss=0.1361, simple_loss=0.241, pruned_loss=0.01563, over 7145.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02897, over 1420733.94 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:02:35,131 INFO [train.py:763] (5/8) Epoch 36, batch 2150, loss[loss=0.1583, simple_loss=0.2599, pruned_loss=0.02836, over 7410.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02928, over 1418247.40 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:03:42,425 INFO [train.py:763] (5/8) Epoch 36, batch 2200, loss[loss=0.1463, simple_loss=0.2457, pruned_loss=0.02346, over 7257.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02924, over 1419740.65 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:04:49,056 INFO [train.py:763] (5/8) Epoch 36, batch 2250, loss[loss=0.1639, simple_loss=0.27, pruned_loss=0.02894, over 7144.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02962, over 1420469.95 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:05:54,016 INFO [train.py:763] (5/8) Epoch 36, batch 2300, loss[loss=0.1944, simple_loss=0.2941, pruned_loss=0.04733, over 7210.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02926, over 1420157.68 frames.], batch size: 23, lr: 2.10e-04
2022-04-30 21:06:59,116 INFO [train.py:763] (5/8) Epoch 36, batch 2350, loss[loss=0.1404, simple_loss=0.2288, pruned_loss=0.02599, over 7288.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.0296, over 1413773.40 frames.], batch size: 17, lr: 2.10e-04
2022-04-30 21:08:06,484 INFO [train.py:763] (5/8) Epoch 36, batch 2400, loss[loss=0.1676, simple_loss=0.2732, pruned_loss=0.03099, over 7306.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02946, over 1419506.81 frames.], batch size: 25, lr: 2.10e-04
2022-04-30 21:09:12,594 INFO [train.py:763] (5/8) Epoch 36, batch 2450, loss[loss=0.1734, simple_loss=0.2702, pruned_loss=0.03835, over 7182.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02959, over 1424838.33 frames.], batch size: 26, lr: 2.10e-04
2022-04-30 21:10:36,033 INFO [train.py:763] (5/8) Epoch 36, batch 2500, loss[loss=0.1408, simple_loss=0.2454, pruned_loss=0.01814, over 7154.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2584, pruned_loss=0.02939, over 1427579.73 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:11:41,255 INFO [train.py:763] (5/8) Epoch 36, batch 2550, loss[loss=0.1928, simple_loss=0.282, pruned_loss=0.05182, over 7289.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2586, pruned_loss=0.02934, over 1428704.25 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 21:12:55,226 INFO [train.py:763] (5/8) Epoch 36, batch 2600, loss[loss=0.1713, simple_loss=0.2573, pruned_loss=0.04267, over 6826.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02947, over 1424804.53 frames.], batch size: 15, lr: 2.10e-04
2022-04-30 21:14:18,385 INFO [train.py:763] (5/8) Epoch 36, batch 2650, loss[loss=0.1733, simple_loss=0.2762, pruned_loss=0.03519, over 7214.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02985, over 1427452.24 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:15:32,425 INFO [train.py:763] (5/8) Epoch 36, batch 2700, loss[loss=0.1402, simple_loss=0.2413, pruned_loss=0.01953, over 6407.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02979, over 1424268.16 frames.], batch size: 38, lr: 2.10e-04
2022-04-30 21:16:46,242 INFO [train.py:763] (5/8) Epoch 36, batch 2750, loss[loss=0.2207, simple_loss=0.309, pruned_loss=0.06614, over 4679.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.0295, over 1424329.30 frames.], batch size: 53, lr: 2.10e-04
2022-04-30 21:17:52,038 INFO [train.py:763] (5/8) Epoch 36, batch 2800, loss[loss=0.1486, simple_loss=0.2484, pruned_loss=0.02439, over 7276.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02954, over 1428750.11 frames.], batch size: 18, lr: 2.10e-04
2022-04-30 21:19:07,519 INFO [train.py:763] (5/8) Epoch 36, batch 2850, loss[loss=0.1829, simple_loss=0.2876, pruned_loss=0.03914, over 6471.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02948, over 1427540.18 frames.], batch size: 38, lr: 2.10e-04
2022-04-30 21:20:12,996 INFO [train.py:763] (5/8) Epoch 36, batch 2900, loss[loss=0.1344, simple_loss=0.2263, pruned_loss=0.02125, over 7012.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2596, pruned_loss=0.02952, over 1427987.33 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:21:20,755 INFO [train.py:763] (5/8) Epoch 36, batch 2950, loss[loss=0.1599, simple_loss=0.2588, pruned_loss=0.03049, over 7425.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02956, over 1423574.66 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:22:27,905 INFO [train.py:763] (5/8) Epoch 36, batch 3000, loss[loss=0.1725, simple_loss=0.2829, pruned_loss=0.03107, over 7217.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02953, over 1420451.28 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:22:27,906 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 21:22:43,065 INFO [train.py:792] (5/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
2022-04-30 21:23:48,282 INFO [train.py:763] (5/8) Epoch 36, batch 3050, loss[loss=0.1525, simple_loss=0.2362, pruned_loss=0.03438, over 6823.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.03, over 1419798.69 frames.], batch size: 15, lr: 2.10e-04
2022-04-30 21:24:54,085 INFO [train.py:763] (5/8) Epoch 36, batch 3100, loss[loss=0.1467, simple_loss=0.2385, pruned_loss=0.02739, over 7449.00 frames.], tot_loss[loss=0.1591, simple_loss=0.259, pruned_loss=0.02957, over 1419114.56 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:26:01,310 INFO [train.py:763] (5/8) Epoch 36, batch 3150, loss[loss=0.1264, simple_loss=0.2241, pruned_loss=0.01434, over 7003.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02929, over 1418507.87 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:27:07,790 INFO [train.py:763] (5/8) Epoch 36, batch 3200, loss[loss=0.1705, simple_loss=0.2754, pruned_loss=0.03278, over 5084.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02921, over 1418690.76 frames.], batch size: 53, lr: 2.10e-04
2022-04-30 21:28:14,751 INFO [train.py:763] (5/8) Epoch 36, batch 3250, loss[loss=0.1843, simple_loss=0.2819, pruned_loss=0.04332, over 7204.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.0292, over 1418167.45 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:29:20,187 INFO [train.py:763] (5/8) Epoch 36, batch 3300, loss[loss=0.1631, simple_loss=0.2669, pruned_loss=0.02961, over 7411.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02911, over 1415644.53 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:30:25,147 INFO [train.py:763] (5/8) Epoch 36, batch 3350, loss[loss=0.1683, simple_loss=0.2763, pruned_loss=0.03013, over 7373.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02927, over 1411286.28 frames.], batch size: 23, lr: 2.09e-04
2022-04-30 21:31:31,788 INFO [train.py:763] (5/8) Epoch 36, batch 3400, loss[loss=0.1501, simple_loss=0.2437, pruned_loss=0.02823, over 7130.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02948, over 1415896.69 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:32:37,222 INFO [train.py:763] (5/8) Epoch 36, batch 3450, loss[loss=0.159, simple_loss=0.2499, pruned_loss=0.03403, over 7272.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2582, pruned_loss=0.02908, over 1418680.53 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:33:42,452 INFO [train.py:763] (5/8) Epoch 36, batch 3500, loss[loss=0.1586, simple_loss=0.2519, pruned_loss=0.03269, over 7355.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2584, pruned_loss=0.02906, over 1416336.15 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:34:47,632 INFO [train.py:763] (5/8) Epoch 36, batch 3550, loss[loss=0.1157, simple_loss=0.2047, pruned_loss=0.01335, over 6795.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02897, over 1413280.68 frames.], batch size: 15, lr: 2.09e-04
2022-04-30 21:35:54,860 INFO [train.py:763] (5/8) Epoch 36, batch 3600, loss[loss=0.1402, simple_loss=0.2334, pruned_loss=0.02348, over 6998.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2575, pruned_loss=0.02898, over 1419756.52 frames.], batch size: 16, lr: 2.09e-04
2022-04-30 21:37:01,815 INFO [train.py:763] (5/8) Epoch 36, batch 3650, loss[loss=0.158, simple_loss=0.2606, pruned_loss=0.02765, over 7158.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2574, pruned_loss=0.02884, over 1422368.55 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:38:09,026 INFO [train.py:763] (5/8) Epoch 36, batch 3700, loss[loss=0.1437, simple_loss=0.2548, pruned_loss=0.01627, over 7228.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02881, over 1426169.63 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:39:14,214 INFO [train.py:763] (5/8) Epoch 36, batch 3750, loss[loss=0.185, simple_loss=0.2872, pruned_loss=0.04133, over 7289.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2584, pruned_loss=0.02904, over 1422413.73 frames.], batch size: 24, lr: 2.09e-04
2022-04-30 21:40:19,615 INFO [train.py:763] (5/8) Epoch 36, batch 3800, loss[loss=0.1363, simple_loss=0.231, pruned_loss=0.0208, over 7286.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02853, over 1424402.30 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:41:25,007 INFO [train.py:763] (5/8) Epoch 36, batch 3850, loss[loss=0.1819, simple_loss=0.275, pruned_loss=0.04443, over 5063.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02897, over 1423495.93 frames.], batch size: 52, lr: 2.09e-04
2022-04-30 21:42:30,260 INFO [train.py:763] (5/8) Epoch 36, batch 3900, loss[loss=0.1461, simple_loss=0.2488, pruned_loss=0.02174, over 7333.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2575, pruned_loss=0.02873, over 1425269.88 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:43:35,823 INFO [train.py:763] (5/8) Epoch 36, batch 3950, loss[loss=0.1515, simple_loss=0.2424, pruned_loss=0.03029, over 7278.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02904, over 1426526.87 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:44:41,521 INFO [train.py:763] (5/8) Epoch 36, batch 4000, loss[loss=0.1551, simple_loss=0.2542, pruned_loss=0.02794, over 7146.00 frames.], tot_loss[loss=0.1582, simple_loss=0.258, pruned_loss=0.02916, over 1427132.51 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:45:48,403 INFO [train.py:763] (5/8) Epoch 36, batch 4050, loss[loss=0.1829, simple_loss=0.2909, pruned_loss=0.03748, over 7143.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02911, over 1426451.01 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:46:54,633 INFO [train.py:763] (5/8) Epoch 36, batch 4100, loss[loss=0.1673, simple_loss=0.2691, pruned_loss=0.0328, over 7321.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02888, over 1424875.15 frames.], batch size: 25, lr: 2.09e-04
2022-04-30 21:48:00,284 INFO [train.py:763] (5/8) Epoch 36, batch 4150, loss[loss=0.1613, simple_loss=0.2655, pruned_loss=0.02855, over 7230.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02874, over 1426843.29 frames.], batch size: 21, lr: 2.09e-04
2022-04-30 21:49:06,768 INFO [train.py:763] (5/8) Epoch 36, batch 4200, loss[loss=0.1655, simple_loss=0.27, pruned_loss=0.03047, over 7335.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02836, over 1428839.85 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:50:13,182 INFO [train.py:763] (5/8) Epoch 36, batch 4250, loss[loss=0.1541, simple_loss=0.2584, pruned_loss=0.02488, over 7205.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02887, over 1431835.35 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:51:18,751 INFO [train.py:763] (5/8) Epoch 36, batch 4300, loss[loss=0.1566, simple_loss=0.2567, pruned_loss=0.02826, over 7321.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02866, over 1426277.41 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:52:24,308 INFO [train.py:763] (5/8) Epoch 36, batch 4350, loss[loss=0.1725, simple_loss=0.2883, pruned_loss=0.0283, over 7328.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02847, over 1430513.63 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:53:30,951 INFO [train.py:763] (5/8) Epoch 36, batch 4400, loss[loss=0.1617, simple_loss=0.2632, pruned_loss=0.03015, over 7333.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02846, over 1423276.78 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:54:38,271 INFO [train.py:763] (5/8) Epoch 36, batch 4450, loss[loss=0.1647, simple_loss=0.2434, pruned_loss=0.04294, over 7419.00 frames.], tot_loss[loss=0.1581, simple_loss=0.259, pruned_loss=0.02856, over 1421936.94 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:55:43,449 INFO [train.py:763] (5/8) Epoch 36, batch 4500, loss[loss=0.14, simple_loss=0.235, pruned_loss=0.02244, over 7270.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.02866, over 1416045.75 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:56:47,992 INFO [train.py:763] (5/8) Epoch 36, batch 4550, loss[loss=0.1594, simple_loss=0.2601, pruned_loss=0.02932, over 6601.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2598, pruned_loss=0.02877, over 1391560.24 frames.], batch size: 38, lr: 2.09e-04
2022-04-30 21:58:07,236 INFO [train.py:763] (5/8) Epoch 37, batch 0, loss[loss=0.1467, simple_loss=0.2565, pruned_loss=0.01845, over 7368.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2565, pruned_loss=0.01845, over 7368.00 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 21:59:13,883 INFO [train.py:763] (5/8) Epoch 37, batch 50, loss[loss=0.1809, simple_loss=0.2839, pruned_loss=0.03898, over 6421.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2526, pruned_loss=0.02529, over 322412.92 frames.], batch size: 38, lr: 2.06e-04
2022-04-30 22:00:20,507 INFO [train.py:763] (5/8) Epoch 37, batch 100, loss[loss=0.1629, simple_loss=0.2617, pruned_loss=0.03208, over 7252.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2565, pruned_loss=0.02784, over 559546.20 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:01:27,283 INFO [train.py:763] (5/8) Epoch 37, batch 150, loss[loss=0.1892, simple_loss=0.2905, pruned_loss=0.04395, over 7376.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02841, over 747657.97 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:02:34,177 INFO [train.py:763] (5/8) Epoch 37, batch 200, loss[loss=0.1675, simple_loss=0.2727, pruned_loss=0.03115, over 7419.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2577, pruned_loss=0.0281, over 896069.54 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:03:39,634 INFO [train.py:763] (5/8) Epoch 37, batch 250, loss[loss=0.144, simple_loss=0.2433, pruned_loss=0.02232, over 7359.00 frames.], tot_loss[loss=0.1565, simple_loss=0.257, pruned_loss=0.02802, over 1014187.96 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:04:45,210 INFO [train.py:763] (5/8) Epoch 37, batch 300, loss[loss=0.1927, simple_loss=0.2878, pruned_loss=0.04879, over 7237.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02864, over 1104953.71 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:05:51,698 INFO [train.py:763] (5/8) Epoch 37, batch 350, loss[loss=0.1303, simple_loss=0.2307, pruned_loss=0.01496, over 7264.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02865, over 1173054.04 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:06:57,564 INFO [train.py:763] (5/8) Epoch 37, batch 400, loss[loss=0.1488, simple_loss=0.2387, pruned_loss=0.02952, over 7275.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02879, over 1232699.62 frames.], batch size: 17, lr: 2.06e-04
2022-04-30 22:08:03,019 INFO [train.py:763] (5/8) Epoch 37, batch 450, loss[loss=0.1725, simple_loss=0.2782, pruned_loss=0.03339, over 7104.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02869, over 1275969.21 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:09:09,223 INFO [train.py:763] (5/8) Epoch 37, batch 500, loss[loss=0.1292, simple_loss=0.225, pruned_loss=0.01669, over 7288.00 frames.], tot_loss[loss=0.1567, simple_loss=0.257, pruned_loss=0.02822, over 1311651.23 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:10:16,147 INFO [train.py:763] (5/8) Epoch 37, batch 550, loss[loss=0.163, simple_loss=0.2606, pruned_loss=0.03269, over 7322.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02833, over 1336757.43 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:11:22,964 INFO [train.py:763] (5/8) Epoch 37, batch 600, loss[loss=0.1798, simple_loss=0.2827, pruned_loss=0.03841, over 7368.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02838, over 1357757.81 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:12:30,635 INFO [train.py:763] (5/8) Epoch 37, batch 650, loss[loss=0.1568, simple_loss=0.2668, pruned_loss=0.02342, over 7338.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02884, over 1373582.35 frames.], batch size: 22, lr: 2.06e-04
2022-04-30 22:13:38,157 INFO [train.py:763] (5/8) Epoch 37, batch 700, loss[loss=0.168, simple_loss=0.2558, pruned_loss=0.04011, over 7165.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02884, over 1386470.75 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:14:45,731 INFO [train.py:763] (5/8) Epoch 37, batch 750, loss[loss=0.1509, simple_loss=0.2602, pruned_loss=0.02084, over 7368.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2594, pruned_loss=0.02901, over 1400868.81 frames.], batch size: 23, lr: 2.05e-04
2022-04-30 22:15:51,457 INFO [train.py:763] (5/8) Epoch 37, batch 800, loss[loss=0.1429, simple_loss=0.2388, pruned_loss=0.02351, over 7414.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02896, over 1408783.79 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:16:56,741 INFO [train.py:763] (5/8) Epoch 37, batch 850, loss[loss=0.1359, simple_loss=0.232, pruned_loss=0.01991, over 7355.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02887, over 1410621.80 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:18:02,422 INFO [train.py:763] (5/8) Epoch 37, batch 900, loss[loss=0.1743, simple_loss=0.2629, pruned_loss=0.04286, over 7286.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02879, over 1412358.96 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:19:07,698 INFO [train.py:763] (5/8) Epoch 37, batch 950, loss[loss=0.1514, simple_loss=0.251, pruned_loss=0.02585, over 7254.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02909, over 1418068.27 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:20:12,878 INFO [train.py:763] (5/8) Epoch 37, batch 1000, loss[loss=0.1635, simple_loss=0.265, pruned_loss=0.03106, over 7220.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.0293, over 1420825.44 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:21:18,161 INFO [train.py:763] (5/8) Epoch 37, batch 1050, loss[loss=0.1456, simple_loss=0.2508, pruned_loss=0.02019, over 7333.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02944, over 1420595.43 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:22:25,737 INFO [train.py:763] (5/8) Epoch 37, batch 1100, loss[loss=0.144, simple_loss=0.2357, pruned_loss=0.02617, over 6784.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.0293, over 1423482.22 frames.], batch size: 15, lr: 2.05e-04
2022-04-30 22:23:31,646 INFO [train.py:763] (5/8) Epoch 37, batch 1150, loss[loss=0.1416, simple_loss=0.2313, pruned_loss=0.02599, over 7273.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02935, over 1420698.53 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:24:36,970 INFO [train.py:763] (5/8) Epoch 37, batch 1200, loss[loss=0.172, simple_loss=0.2698, pruned_loss=0.03716, over 7162.00 frames.], tot_loss[loss=0.159, simple_loss=0.2598, pruned_loss=0.02911, over 1422938.52 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:25:43,869 INFO [train.py:763] (5/8) Epoch 37, batch 1250, loss[loss=0.1688, simple_loss=0.268, pruned_loss=0.0348, over 6283.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.0288, over 1426242.23 frames.], batch size: 37, lr: 2.05e-04
2022-04-30 22:26:50,675 INFO [train.py:763] (5/8) Epoch 37, batch 1300, loss[loss=0.1379, simple_loss=0.2237, pruned_loss=0.02605, over 7264.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02918, over 1425843.57 frames.], batch size: 17, lr: 2.05e-04
2022-04-30 22:27:56,063 INFO [train.py:763] (5/8) Epoch 37, batch 1350, loss[loss=0.1757, simple_loss=0.2838, pruned_loss=0.03379, over 7130.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.0293, over 1419009.03 frames.], batch size: 21, lr: 2.05e-04
2022-04-30 22:29:02,061 INFO [train.py:763] (5/8) Epoch 37, batch 1400, loss[loss=0.1703, simple_loss=0.2818, pruned_loss=0.02938, over 7274.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02931, over 1419521.09 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:30:07,331 INFO [train.py:763] (5/8) Epoch 37, batch 1450, loss[loss=0.1708, simple_loss=0.2739, pruned_loss=0.03384, over 7195.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02959, over 1424083.23 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:31:13,185 INFO [train.py:763] (5/8) Epoch 37, batch 1500, loss[loss=0.1688, simple_loss=0.2717, pruned_loss=0.03294, over 7320.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2602, pruned_loss=0.02941, over 1424472.67 frames.], batch size: 25, lr: 2.05e-04
2022-04-30 22:32:18,524 INFO [train.py:763] (5/8) Epoch 37, batch 1550, loss[loss=0.1383, simple_loss=0.2428, pruned_loss=0.01689, over 7244.00 frames.], tot_loss[loss=0.159, simple_loss=0.2596, pruned_loss=0.0292, over 1421472.41 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:33:23,886 INFO [train.py:763] (5/8) Epoch 37, batch 1600, loss[loss=0.1584, simple_loss=0.2574, pruned_loss=0.02973, over 7250.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2602, pruned_loss=0.02966, over 1424178.04 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:34:29,223 INFO [train.py:763] (5/8) Epoch 37, batch 1650, loss[loss=0.1792, simple_loss=0.2873, pruned_loss=0.03553, over 7001.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02949, over 1423767.43 frames.], batch size: 28, lr: 2.05e-04
2022-04-30 22:35:34,595 INFO [train.py:763] (5/8) Epoch 37, batch 1700, loss[loss=0.1559, simple_loss=0.2436, pruned_loss=0.0341, over 7163.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02927, over 1422198.27 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:36:40,248 INFO [train.py:763] (5/8) Epoch 37, batch 1750, loss[loss=0.1634, simple_loss=0.2644, pruned_loss=0.03121, over 4526.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02943, over 1420785.59 frames.], batch size: 52, lr: 2.05e-04
2022-04-30 22:37:45,572 INFO [train.py:763] (5/8) Epoch 37, batch 1800, loss[loss=0.1405, simple_loss=0.2404, pruned_loss=0.02029, over 7332.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.029, over 1419214.67 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:38:50,832 INFO [train.py:763] (5/8) Epoch 37, batch 1850, loss[loss=0.1386, simple_loss=0.2364, pruned_loss=0.02044, over 7286.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02913, over 1421058.43 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:39:57,182 INFO [train.py:763] (5/8) Epoch 37, batch 1900, loss[loss=0.1484, simple_loss=0.231, pruned_loss=0.03287, over 7207.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02935, over 1424332.23 frames.], batch size: 16, lr: 2.05e-04
2022-04-30 22:41:04,601 INFO [train.py:763] (5/8) Epoch 37, batch 1950, loss[loss=0.1518, simple_loss=0.2534, pruned_loss=0.0251, over 7255.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02948, over 1426864.87 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:42:12,277 INFO [train.py:763] (5/8) Epoch 37, batch 2000, loss[loss=0.1321, simple_loss=0.2222, pruned_loss=0.02098, over 7395.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02941, over 1425377.02 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:43:17,405 INFO [train.py:763] (5/8) Epoch 37, batch 2050, loss[loss=0.1475, simple_loss=0.2512, pruned_loss=0.02192, over 7263.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02984, over 1422980.91 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:44:22,377 INFO [train.py:763] (5/8) Epoch 37, batch 2100, loss[loss=0.17, simple_loss=0.2782, pruned_loss=0.03087, over 7157.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03007, over 1417162.52 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:45:27,590 INFO [train.py:763] (5/8) Epoch 37, batch 2150, loss[loss=0.1351, simple_loss=0.2367, pruned_loss=0.01681, over 7068.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02982, over 1417411.70 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:46:32,468 INFO [train.py:763] (5/8) Epoch 37, batch 2200, loss[loss=0.1512, simple_loss=0.243, pruned_loss=0.02963, over 7067.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2609, pruned_loss=0.02966, over 1418772.86 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:47:37,566 INFO [train.py:763] (5/8) Epoch 37, batch 2250, loss[loss=0.1509, simple_loss=0.2567, pruned_loss=0.02255, over 6595.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2613, pruned_loss=0.02989, over 1417954.84 frames.], batch size: 38, lr: 2.05e-04
2022-04-30 22:48:44,667 INFO [train.py:763] (5/8) Epoch 37, batch 2300, loss[loss=0.148, simple_loss=0.2524, pruned_loss=0.02184, over 7059.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2607, pruned_loss=0.02977, over 1421508.85 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:49:50,012 INFO [train.py:763] (5/8) Epoch 37, batch 2350, loss[loss=0.1729, simple_loss=0.2648, pruned_loss=0.04049, over 7317.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2609, pruned_loss=0.02991, over 1419881.33 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:50:55,504 INFO [train.py:763] (5/8) Epoch 37, batch 2400, loss[loss=0.1422, simple_loss=0.2297, pruned_loss=0.02735, over 7403.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2594, pruned_loss=0.029, over 1425391.84 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:52:02,208 INFO [train.py:763] (5/8) Epoch 37, batch 2450, loss[loss=0.1649, simple_loss=0.2657, pruned_loss=0.03203, over 7336.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02918, over 1427401.91 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:53:07,503 INFO [train.py:763] (5/8) Epoch 37, batch 2500, loss[loss=0.1465, simple_loss=0.2422, pruned_loss=0.02541, over 7163.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02924, over 1426852.65 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:54:13,280 INFO [train.py:763] (5/8) Epoch 37, batch 2550, loss[loss=0.1443, simple_loss=0.2359, pruned_loss=0.02634, over 7155.00 frames.], tot_loss[loss=0.159, simple_loss=0.2597, pruned_loss=0.02912, over 1424080.23 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:55:19,551 INFO [train.py:763] (5/8) Epoch 37, batch 2600, loss[loss=0.1476, simple_loss=0.2499, pruned_loss=0.02266, over 7433.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2598, pruned_loss=0.02889, over 1423485.44 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:56:24,708 INFO [train.py:763] (5/8) Epoch 37, batch 2650, loss[loss=0.1827, simple_loss=0.2877, pruned_loss=0.03886, over 7216.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02898, over 1424708.72 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 22:57:30,431 INFO [train.py:763] (5/8) Epoch 37, batch 2700, loss[loss=0.1926, simple_loss=0.2897, pruned_loss=0.04778, over 7228.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2595, pruned_loss=0.02893, over 1423356.27 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:58:35,696 INFO [train.py:763] (5/8) Epoch 37, batch 2750, loss[loss=0.1559, simple_loss=0.2551, pruned_loss=0.02838, over 7356.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2596, pruned_loss=0.02898, over 1425340.38 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 22:59:42,100 INFO [train.py:763] (5/8) Epoch 37, batch 2800, loss[loss=0.1587, simple_loss=0.2603, pruned_loss=0.02853, over 7270.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02888, over 1423849.83 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:00:49,180 INFO [train.py:763] (5/8) Epoch 37, batch 2850, loss[loss=0.1594, simple_loss=0.2576, pruned_loss=0.03059, over 7408.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02896, over 1423456.75 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:01:56,179 INFO [train.py:763] (5/8) Epoch 37, batch 2900, loss[loss=0.1436, simple_loss=0.2354, pruned_loss=0.02585, over 7117.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02879, over 1424097.65 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:03:03,301 INFO [train.py:763] (5/8) Epoch 37, batch 2950, loss[loss=0.1316, simple_loss=0.2208, pruned_loss=0.02122, over 7413.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.0292, over 1428535.85 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:04:10,181 INFO [train.py:763] (5/8) Epoch 37, batch 3000, loss[loss=0.1883, simple_loss=0.2896, pruned_loss=0.04349, over 7198.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02939, over 1428427.25 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:04:10,182 INFO [train.py:783] (5/8) Computing validation loss
2022-04-30 23:04:25,434 INFO [train.py:792] (5/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
2022-04-30 23:05:32,558 INFO [train.py:763] (5/8) Epoch 37, batch 3050, loss[loss=0.1374, simple_loss=0.2288, pruned_loss=0.02298, over 7157.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02933, over 1429162.68 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:06:38,297 INFO [train.py:763] (5/8) Epoch 37, batch 3100, loss[loss=0.1719, simple_loss=0.2696, pruned_loss=0.03714, over 7207.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02941, over 1422224.78 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:07:53,031 INFO [train.py:763] (5/8) Epoch 37, batch 3150, loss[loss=0.1655, simple_loss=0.2643, pruned_loss=0.03329, over 7384.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02933, over 1420743.07 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:08:58,937 INFO [train.py:763] (5/8) Epoch 37, batch 3200, loss[loss=0.1694, simple_loss=0.2775, pruned_loss=0.03066, over 7110.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02959, over 1425588.07 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:10:06,291 INFO [train.py:763] (5/8) Epoch 37, batch 3250, loss[loss=0.1458, simple_loss=0.2359, pruned_loss=0.0279, over 7261.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.0291, over 1427335.73 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:11:13,126 INFO [train.py:763] (5/8) Epoch 37, batch 3300, loss[loss=0.1565, simple_loss=0.2613, pruned_loss=0.02591, over 7237.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02873, over 1426684.14 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:12:18,277 INFO [train.py:763] (5/8) Epoch 37, batch 3350, loss[loss=0.1766, simple_loss=0.2852, pruned_loss=0.03404, over 7198.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2598, pruned_loss=0.02899, over 1427490.45 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:13:23,569 INFO [train.py:763] (5/8) Epoch 37, batch 3400, loss[loss=0.1811, simple_loss=0.276, pruned_loss=0.04312, over 6720.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2598, pruned_loss=0.02895, over 1431031.25 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:14:28,973 INFO [train.py:763] (5/8) Epoch 37, batch 3450, loss[loss=0.146, simple_loss=0.2462, pruned_loss=0.02283, over 7426.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2605, pruned_loss=0.02912, over 1432130.61 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:15:34,300 INFO [train.py:763] (5/8) Epoch 37, batch 3500, loss[loss=0.1426, simple_loss=0.2503, pruned_loss=0.01745, over 7246.00 frames.], tot_loss[loss=0.1591, simple_loss=0.26, pruned_loss=0.02911, over 1430173.89 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:16:39,550 INFO [train.py:763] (5/8) Epoch 37, batch 3550, loss[loss=0.1487, simple_loss=0.2562, pruned_loss=0.02061, over 7155.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2606, pruned_loss=0.02921, over 1430383.64 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:17:44,643 INFO [train.py:763] (5/8) Epoch 37, batch 3600, loss[loss=0.1646, simple_loss=0.2617, pruned_loss=0.03379, over 6746.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2605, pruned_loss=0.02925, over 1427755.52 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:18:50,221 INFO [train.py:763] (5/8) Epoch 37, batch 3650, loss[loss=0.1653, simple_loss=0.2674, pruned_loss=0.0316, over 7082.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02878, over 1430489.64 frames.], batch size: 28, lr: 2.04e-04
2022-04-30 23:19:55,915 INFO [train.py:763] (5/8) Epoch 37, batch 3700, loss[loss=0.1755, simple_loss=0.287, pruned_loss=0.03201, over 7264.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.0292, over 1421822.28 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:21:00,950 INFO [train.py:763] (5/8) Epoch 37, batch 3750, loss[loss=0.1396, simple_loss=0.2445, pruned_loss=0.01737, over 7155.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02926, over 1417161.30 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:22:07,065 INFO [train.py:763] (5/8) Epoch 37, batch 3800, loss[loss=0.1687, simple_loss=0.2686, pruned_loss=0.03435, over 7384.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02922, over 1417103.49 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:23:12,321 INFO [train.py:763] (5/8) Epoch 37, batch 3850, loss[loss=0.151, simple_loss=0.2584, pruned_loss=0.02184, over 7117.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02898, over 1420187.39 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:24:18,024 INFO [train.py:763] (5/8) Epoch 37, batch 3900, loss[loss=0.1569, simple_loss=0.2614, pruned_loss=0.02619, over 7325.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02887, over 1422007.73 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:25:32,665 INFO [train.py:763] (5/8) Epoch 37, batch 3950, loss[loss=0.1748, simple_loss=0.2823, pruned_loss=0.03364, over 7211.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.0289, over 1416864.05 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:26:37,880 INFO [train.py:763] (5/8) Epoch 37, batch 4000, loss[loss=0.1448, simple_loss=0.2435, pruned_loss=0.02304, over 7156.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02878, over 1417971.47 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:28:01,973 INFO [train.py:763] (5/8) Epoch 37, batch 4050, loss[loss=0.142, simple_loss=0.2299, pruned_loss=0.0271, over 7281.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02877, over 1410575.92 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:29:07,118 INFO [train.py:763] (5/8) Epoch 37, batch 4100, loss[loss=0.1615, simple_loss=0.2655, pruned_loss=0.02877, over 7215.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02904, over 1412175.85 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:30:21,710 INFO [train.py:763] (5/8) Epoch 37, batch 4150, loss[loss=0.1493, simple_loss=0.2463, pruned_loss=0.02613, over 7250.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02873, over 1411258.53 frames.], batch size: 19, lr: 2.03e-04
2022-04-30 23:31:36,376 INFO [train.py:763] (5/8) Epoch 37, batch 4200, loss[loss=0.1416, simple_loss=0.2487, pruned_loss=0.01725, over 7288.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02826, over 1411879.26 frames.], batch size: 24, lr: 2.03e-04
2022-04-30 23:32:51,955 INFO [train.py:763] (5/8) Epoch 37, batch 4250, loss[loss=0.1473, simple_loss=0.2489, pruned_loss=0.02285, over 7229.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2574, pruned_loss=0.02821, over 1413067.90 frames.], batch size: 20, lr: 2.03e-04
2022-04-30 23:33:58,668 INFO [train.py:763] (5/8) Epoch 37, batch 4300, loss[loss=0.1731, simple_loss=0.2667, pruned_loss=0.03971, over 5065.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2557, pruned_loss=0.02782, over 1410244.49 frames.], batch size: 53, lr: 2.03e-04
2022-04-30 23:35:04,838 INFO [train.py:763] (5/8) Epoch 37, batch 4350, loss[loss=0.1411, simple_loss=0.2286, pruned_loss=0.02682, over 6989.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2542, pruned_loss=0.0275, over 1413558.76 frames.], batch size: 16, lr: 2.03e-04
2022-04-30 23:36:10,340 INFO [train.py:763] (5/8) Epoch 37, batch 4400, loss[loss=0.1392, simple_loss=0.2353, pruned_loss=0.02156, over 7191.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2541, pruned_loss=0.02729, over 1414414.83 frames.], batch size: 16, lr: 2.03e-04
2022-04-30 23:37:17,180 INFO [train.py:763] (5/8) Epoch 37, batch 4450, loss[loss=0.1458, simple_loss=0.239, pruned_loss=0.02628, over 7259.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2537, pruned_loss=0.02743, over 1407224.66 frames.], batch size: 16, lr: 2.03e-04
2022-04-30 23:38:22,789 INFO [train.py:763] (5/8) Epoch 37, batch 4500, loss[loss=0.1516, simple_loss=0.2574, pruned_loss=0.02289, over 6310.00 frames.], tot_loss[loss=0.155, simple_loss=0.2542, pruned_loss=0.0279, over 1383022.36 frames.], batch size: 38, lr: 2.03e-04
2022-04-30 23:39:28,660 INFO [train.py:763] (5/8) Epoch 37, batch 4550, loss[loss=0.1729, simple_loss=0.2696, pruned_loss=0.03806, over 4979.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2543, pruned_loss=0.02844, over 1355267.99 frames.], batch size: 52, lr: 2.03e-04
2022-04-30 23:40:56,601 INFO [train.py:763] (5/8) Epoch 38, batch 0, loss[loss=0.1553, simple_loss=0.2565, pruned_loss=0.02699, over 7261.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2565, pruned_loss=0.02699, over 7261.00 frames.], batch size: 19, lr: 2.01e-04
2022-04-30 23:42:03,246 INFO [train.py:763] (5/8) Epoch 38, batch 50, loss[loss=0.1544, simple_loss=0.26, pruned_loss=0.02441, over 7150.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03007, over 319783.62 frames.], batch size: 20, lr: 2.01e-04
2022-04-30 23:43:10,092 INFO [train.py:763] (5/8) Epoch 38, batch 100, loss[loss=0.1504, simple_loss=0.2653, pruned_loss=0.01775, over 6784.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02962, over 565702.61 frames.], batch size: 31, lr: 2.01e-04
2022-04-30 23:44:16,794 INFO [train.py:763] (5/8) Epoch 38, batch 150, loss[loss=0.1671, simple_loss=0.2596, pruned_loss=0.03725, over 7166.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2583, pruned_loss=0.02974, over 755877.05 frames.], batch size: 18, lr: 2.01e-04
2022-04-30 23:45:22,777 INFO [train.py:763] (5/8) Epoch 38, batch 200, loss[loss=0.1611, simple_loss=0.2594, pruned_loss=0.03136, over 7420.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02963, over 902153.24 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:46:29,138 INFO [train.py:763] (5/8) Epoch 38, batch 250, loss[loss=0.1505, simple_loss=0.2598, pruned_loss=0.02059, over 6569.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02944, over 1018674.99 frames.], batch size: 38, lr: 2.00e-04
2022-04-30 23:47:35,368 INFO [train.py:763] (5/8) Epoch 38, batch 300, loss[loss=0.1679, simple_loss=0.2744, pruned_loss=0.03066, over 7430.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02938, over 1113268.74 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:48:41,449 INFO [train.py:763] (5/8) Epoch 38, batch 350, loss[loss=0.154, simple_loss=0.2543, pruned_loss=0.02687, over 7312.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02903, over 1179853.47 frames.], batch size: 24, lr: 2.00e-04
2022-04-30 23:49:47,448 INFO [train.py:763] (5/8) Epoch 38, batch 400, loss[loss=0.1502, simple_loss=0.2627, pruned_loss=0.01882, over 7233.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02896, over 1229262.83 frames.], batch size: 21, lr: 2.00e-04
2022-04-30 23:50:53,874 INFO [train.py:763] (5/8) Epoch 38, batch 450, loss[loss=0.1887, simple_loss=0.2834, pruned_loss=0.04701, over 7198.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02935, over 1274849.42 frames.], batch size: 23, lr: 2.00e-04
2022-04-30 23:52:00,166 INFO [train.py:763] (5/8) Epoch 38, batch 500, loss[loss=0.1631, simple_loss=0.2752, pruned_loss=0.02545, over 7147.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02931, over 1301567.09 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:53:06,416 INFO [train.py:763] (5/8) Epoch 38, batch 550, loss[loss=0.1714, simple_loss=0.2767, pruned_loss=0.03304, over 7417.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02903, over 1327091.87 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:54:12,149 INFO [train.py:763] (5/8) Epoch 38, batch 600, loss[loss=0.1302, simple_loss=0.2242, pruned_loss=0.01811, over 7176.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02899, over 1345679.62 frames.], batch size: 18, lr: 2.00e-04
2022-04-30 23:55:17,891 INFO [train.py:763] (5/8) Epoch 38, batch 650, loss[loss=0.1452, simple_loss=0.2307, pruned_loss=0.02991, over 7285.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.02906, over 1364745.43 frames.], batch size: 17, lr: 2.00e-04
2022-04-30 23:56:23,415 INFO [train.py:763] (5/8) Epoch 38, batch 700, loss[loss=0.1395, simple_loss=0.2279, pruned_loss=0.02548, over 6816.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02897, over 1377882.90 frames.], batch size: 15, lr: 2.00e-04
2022-04-30 23:57:28,964 INFO [train.py:763] (5/8) Epoch 38, batch 750, loss[loss=0.1587, simple_loss=0.2613, pruned_loss=0.02804, over 6365.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2567, pruned_loss=0.02855, over 1386571.00 frames.], batch size: 38, lr: 2.00e-04
2022-04-30 23:58:35,121 INFO [train.py:763] (5/8) Epoch 38, batch 800, loss[loss=0.1431, simple_loss=0.2482, pruned_loss=0.01902, over 7246.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2566, pruned_loss=0.02811, over 1399296.83 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:59:41,185 INFO [train.py:763] (5/8) Epoch 38, batch 850, loss[loss=0.1685, simple_loss=0.2722, pruned_loss=0.03235, over 7052.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2564, pruned_loss=0.02812, over 1405131.99 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:00:47,052 INFO [train.py:763] (5/8) Epoch 38, batch 900, loss[loss=0.1694, simple_loss=0.2733, pruned_loss=0.03274, over 7416.00 frames.], tot_loss[loss=0.1571, simple_loss=0.257, pruned_loss=0.0286, over 1404474.66 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:01:52,978 INFO [train.py:763] (5/8) Epoch 38, batch 950, loss[loss=0.1258, simple_loss=0.2152, pruned_loss=0.01823, over 7146.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02894, over 1405156.08 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:02:58,572 INFO [train.py:763] (5/8) Epoch 38, batch 1000, loss[loss=0.1345, simple_loss=0.2312, pruned_loss=0.01892, over 7348.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02882, over 1408089.46 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:04:03,999 INFO [train.py:763] (5/8) Epoch 38, batch 1050, loss[loss=0.1637, simple_loss=0.2771, pruned_loss=0.02508, over 6919.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.029, over 1410787.99 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:05:09,986 INFO [train.py:763] (5/8) Epoch 38, batch 1100, loss[loss=0.1684, simple_loss=0.2695, pruned_loss=0.03368, over 7376.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02864, over 1415247.35 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:06:15,681 INFO [train.py:763] (5/8) Epoch 38, batch 1150, loss[loss=0.1409, simple_loss=0.2357, pruned_loss=0.02299, over 7273.00 frames.], tot_loss[loss=0.1568, simple_loss=0.257, pruned_loss=0.02828, over 1419403.56 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:07:21,228 INFO [train.py:763] (5/8) Epoch 38, batch 1200, loss[loss=0.1751, simple_loss=0.2758, pruned_loss=0.03725, over 6809.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2565, pruned_loss=0.02811, over 1420400.36 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:08:27,095 INFO [train.py:763] (5/8) Epoch 38, batch 1250, loss[loss=0.153, simple_loss=0.2551, pruned_loss=0.02539, over 7434.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2565, pruned_loss=0.02818, over 1421597.20 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:09:34,188 INFO [train.py:763] (5/8) Epoch 38, batch 1300, loss[loss=0.1343, simple_loss=0.2178, pruned_loss=0.02542, over 7282.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2558, pruned_loss=0.0282, over 1425245.80 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:10:39,855 INFO [train.py:763] (5/8) Epoch 38, batch 1350, loss[loss=0.1443, simple_loss=0.2487, pruned_loss=0.01999, over 7323.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2562, pruned_loss=0.02817, over 1425880.32 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:11:45,179 INFO [train.py:763] (5/8) Epoch 38, batch 1400, loss[loss=0.1371, simple_loss=0.243, pruned_loss=0.0156, over 7151.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2557, pruned_loss=0.02783, over 1424734.46 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:12:50,405 INFO [train.py:763] (5/8) Epoch 38, batch 1450, loss[loss=0.1705, simple_loss=0.2628, pruned_loss=0.0391, over 7296.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2567, pruned_loss=0.02801, over 1425158.96 frames.], batch size: 25, lr: 2.00e-04
2022-05-01 00:13:55,959 INFO [train.py:763] (5/8) Epoch 38, batch 1500, loss[loss=0.1937, simple_loss=0.3031, pruned_loss=0.04216, over 7099.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02863, over 1423634.72 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:15:03,019 INFO [train.py:763] (5/8) Epoch 38, batch 1550, loss[loss=0.1642, simple_loss=0.2587, pruned_loss=0.03489, over 7211.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2566, pruned_loss=0.02832, over 1423800.29 frames.], batch size: 22, lr: 2.00e-04
2022-05-01 00:16:09,262 INFO [train.py:763] (5/8) Epoch 38, batch 1600, loss[loss=0.1886, simple_loss=0.2924, pruned_loss=0.04242, over 6703.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2562, pruned_loss=0.02816, over 1426009.78 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:17:15,074 INFO [train.py:763] (5/8) Epoch 38, batch 1650, loss[loss=0.1574, simple_loss=0.2598, pruned_loss=0.02755, over 7213.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2567, pruned_loss=0.02846, over 1425309.76 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:18:31,387 INFO [train.py:763] (5/8) Epoch 38, batch 1700, loss[loss=0.1366, simple_loss=0.2406, pruned_loss=0.0163, over 7106.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02848, over 1427129.57 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:19:36,543 INFO [train.py:763] (5/8) Epoch 38, batch 1750, loss[loss=0.1511, simple_loss=0.2517, pruned_loss=0.02519, over 7426.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2585, pruned_loss=0.02849, over 1426128.35 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:20:42,266 INFO [train.py:763] (5/8) Epoch 38, batch 1800, loss[loss=0.1624, simple_loss=0.266, pruned_loss=0.02943, over 7205.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2589, pruned_loss=0.02875, over 1423220.84 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:21:47,723 INFO [train.py:763] (5/8) Epoch 38, batch 1850, loss[loss=0.1516, simple_loss=0.2548, pruned_loss=0.02424, over 7159.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02899, over 1420683.56 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:22:54,649 INFO [train.py:763] (5/8) Epoch 38, batch 1900, loss[loss=0.1374, simple_loss=0.2409, pruned_loss=0.01694, over 7270.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02866, over 1424182.44 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:24:00,343 INFO [train.py:763] (5/8) Epoch 38, batch 1950, loss[loss=0.1392, simple_loss=0.2463, pruned_loss=0.01604, over 7318.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02915, over 1424045.53 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:25:06,442 INFO [train.py:763] (5/8) Epoch 38, batch 2000, loss[loss=0.1436, simple_loss=0.2437, pruned_loss=0.02179, over 7261.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2583, pruned_loss=0.0292, over 1423462.11 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:26:13,057 INFO [train.py:763] (5/8) Epoch 38, batch 2050, loss[loss=0.1577, simple_loss=0.254, pruned_loss=0.03073, over 7331.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02947, over 1422096.75 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:27:18,301 INFO [train.py:763] (5/8) Epoch 38, batch 2100, loss[loss=0.1543, simple_loss=0.2454, pruned_loss=0.03156, over 7218.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02918, over 1423744.22 frames.], batch size: 16, lr: 1.99e-04
2022-05-01 00:28:25,405 INFO [train.py:763] (5/8) Epoch 38, batch 2150, loss[loss=0.1623, simple_loss=0.258, pruned_loss=0.03335, over 7263.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02914, over 1421395.33 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:29:31,362 INFO [train.py:763] (5/8) Epoch 38, batch 2200, loss[loss=0.1706, simple_loss=0.2675, pruned_loss=0.0368, over 7207.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02936, over 1421512.96 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:30:38,814 INFO [train.py:763] (5/8) Epoch 38, batch 2250, loss[loss=0.1595, simple_loss=0.2649, pruned_loss=0.02702, over 7145.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02881, over 1424641.12 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:31:44,026 INFO [train.py:763] (5/8) Epoch 38, batch 2300, loss[loss=0.155, simple_loss=0.2491, pruned_loss=0.03042, over 7150.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02869, over 1424179.76 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:32:50,161 INFO [train.py:763] (5/8) Epoch 38, batch 2350, loss[loss=0.1407, simple_loss=0.2443, pruned_loss=0.01853, over 7230.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02835, over 1425327.84 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:33:55,527 INFO [train.py:763] (5/8) Epoch 38, batch 2400, loss[loss=0.1637, simple_loss=0.2684, pruned_loss=0.02949, over 7147.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02831, over 1427732.75 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:35:01,022 INFO [train.py:763] (5/8) Epoch 38, batch 2450, loss[loss=0.1256, simple_loss=0.2212, pruned_loss=0.01502, over 7414.00 frames.], tot_loss[loss=0.1567, simple_loss=0.257, pruned_loss=0.02816, over 1428904.37 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:36:06,997 INFO [train.py:763] (5/8) Epoch 38, batch 2500, loss[loss=0.1605, simple_loss=0.2643, pruned_loss=0.02836, over 7418.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2562, pruned_loss=0.02799, over 1426875.56 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:37:12,688 INFO [train.py:763] (5/8) Epoch 38, batch 2550, loss[loss=0.1522, simple_loss=0.2527, pruned_loss=0.02585, over 7432.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2559, pruned_loss=0.02775, over 1431362.61 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:38:18,039 INFO [train.py:763] (5/8) Epoch 38, batch 2600, loss[loss=0.1823, simple_loss=0.2779, pruned_loss=0.04338, over 7201.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2568, pruned_loss=0.02831, over 1429039.11 frames.], batch size: 26, lr: 1.99e-04
2022-05-01 00:39:23,365 INFO [train.py:763] (5/8) Epoch 38, batch 2650, loss[loss=0.1818, simple_loss=0.2914, pruned_loss=0.03613, over 7073.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2575, pruned_loss=0.02845, over 1429346.24 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 00:40:27,514 INFO [train.py:763] (5/8) Epoch 38, batch 2700, loss[loss=0.1867, simple_loss=0.2967, pruned_loss=0.03831, over 7294.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.02861, over 1427041.28 frames.], batch size: 25, lr: 1.99e-04
2022-05-01 00:41:33,244 INFO [train.py:763] (5/8) Epoch 38, batch 2750, loss[loss=0.1299, simple_loss=0.2313, pruned_loss=0.01422, over 7157.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02867, over 1427307.78 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:42:38,769 INFO [train.py:763] (5/8) Epoch 38, batch 2800, loss[loss=0.1687, simple_loss=0.2732, pruned_loss=0.03211, over 7344.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2576, pruned_loss=0.02838, over 1424499.56 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:43:44,130 INFO [train.py:763] (5/8) Epoch 38, batch 2850, loss[loss=0.1671, simple_loss=0.2753, pruned_loss=0.02941, over 6389.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02875, over 1425442.63 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:44:49,676 INFO [train.py:763] (5/8) Epoch 38, batch 2900, loss[loss=0.1647, simple_loss=0.2714, pruned_loss=0.02893, over 7322.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2581, pruned_loss=0.02826, over 1424514.34 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:45:55,143 INFO [train.py:763] (5/8) Epoch 38, batch 2950, loss[loss=0.177, simple_loss=0.2723, pruned_loss=0.04085, over 7340.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2575, pruned_loss=0.0284, over 1428196.94 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:47:00,418 INFO [train.py:763] (5/8) Epoch 38, batch 3000, loss[loss=0.1694, simple_loss=0.2664, pruned_loss=0.03614, over 7232.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.0286, over 1429536.21 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:47:00,419 INFO [train.py:783] (5/8) Computing validation loss
2022-05-01 00:47:15,873 INFO [train.py:792] (5/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
2022-05-01 00:48:21,033 INFO [train.py:763] (5/8) Epoch 38, batch 3050, loss[loss=0.1539, simple_loss=0.2435, pruned_loss=0.03216, over 7141.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2576, pruned_loss=0.02871, over 1426025.49 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:49:26,206 INFO [train.py:763] (5/8) Epoch 38, batch 3100, loss[loss=0.1573, simple_loss=0.2648, pruned_loss=0.02487, over 6204.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2579, pruned_loss=0.02887, over 1418129.54 frames.], batch size: 37, lr: 1.99e-04
2022-05-01 00:50:31,509 INFO [train.py:763] (5/8) Epoch 38, batch 3150, loss[loss=0.1496, simple_loss=0.2466, pruned_loss=0.02627, over 7412.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02898, over 1423277.59 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:51:36,877 INFO [train.py:763] (5/8) Epoch 38, batch 3200, loss[loss=0.1701, simple_loss=0.2699, pruned_loss=0.03518, over 6368.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02887, over 1423851.72 frames.], batch size: 37, lr: 1.99e-04
2022-05-01 00:52:42,223 INFO [train.py:763] (5/8) Epoch 38, batch 3250, loss[loss=0.1681, simple_loss=0.2646, pruned_loss=0.03581, over 6591.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02851, over 1424253.43 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:53:47,533 INFO [train.py:763] (5/8) Epoch 38, batch 3300, loss[loss=0.1512, simple_loss=0.2467, pruned_loss=0.02782, over 7160.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2581, pruned_loss=0.02821, over 1424585.33 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:54:52,922 INFO [train.py:763] (5/8) Epoch 38, batch 3350, loss[loss=0.1663, simple_loss=0.2509, pruned_loss=0.04084, over 7141.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02814, over 1425683.15 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:55:59,023 INFO [train.py:763] (5/8) Epoch 38, batch 3400, loss[loss=0.1618, simple_loss=0.2584, pruned_loss=0.03262, over 7368.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2576, pruned_loss=0.02838, over 1426144.53 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:57:06,509 INFO [train.py:763] (5/8) Epoch 38, batch 3450, loss[loss=0.1628, simple_loss=0.2705, pruned_loss=0.02756, over 7206.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.0287, over 1418279.54 frames.], batch size: 23, lr: 1.99e-04
2022-05-01 00:58:13,610 INFO [train.py:763] (5/8) Epoch 38, batch 3500, loss[loss=0.1353, simple_loss=0.2389, pruned_loss=0.01581, over 7154.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02838, over 1419996.06 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:59:19,216 INFO [train.py:763] (5/8) Epoch 38, batch 3550, loss[loss=0.16, simple_loss=0.2661, pruned_loss=0.0269, over 7333.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02862, over 1421889.60 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 01:00:25,366 INFO [train.py:763] (5/8) Epoch 38, batch 3600, loss[loss=0.1269, simple_loss=0.2255, pruned_loss=0.0142, over 7296.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02889, over 1422694.74 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 01:01:30,575 INFO [train.py:763] (5/8) Epoch 38, batch 3650, loss[loss=0.1581, simple_loss=0.2739, pruned_loss=0.02109, over 7160.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02888, over 1424622.93 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 01:02:35,706 INFO [train.py:763] (5/8) Epoch 38, batch 3700, loss[loss=0.1543, simple_loss=0.2617, pruned_loss=0.02346, over 6416.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02842, over 1421460.56 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 01:03:41,350 INFO [train.py:763] (5/8) Epoch 38, batch 3750, loss[loss=0.1787, simple_loss=0.2743, pruned_loss=0.04158, over 7207.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2574, pruned_loss=0.02894, over 1414450.25 frames.], batch size: 23, lr: 1.98e-04
2022-05-01 01:04:46,831 INFO [train.py:763] (5/8) Epoch 38, batch 3800, loss[loss=0.1482, simple_loss=0.2529, pruned_loss=0.02174, over 7360.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2572, pruned_loss=0.02868, over 1422000.18 frames.], batch size: 19, lr: 1.98e-04
2022-05-01 01:05:52,032 INFO [train.py:763] (5/8) Epoch 38, batch 3850, loss[loss=0.2455, simple_loss=0.3175, pruned_loss=0.08673, over 5121.00 frames.], tot_loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02902, over 1418841.07 frames.], batch size: 53, lr: 1.98e-04
2022-05-01 01:06:57,236 INFO [train.py:763] (5/8) Epoch 38, batch 3900, loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03847, over 7073.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02872, over 1420786.80 frames.], batch size: 28, lr: 1.98e-04
2022-05-01 01:08:02,835 INFO [train.py:763] (5/8) Epoch 38, batch 3950, loss[loss=0.1775, simple_loss=0.2809, pruned_loss=0.03705, over 7296.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2576, pruned_loss=0.02824, over 1422868.81 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:09:08,088 INFO [train.py:763] (5/8) Epoch 38, batch 4000, loss[loss=0.1506, simple_loss=0.2543, pruned_loss=0.02346, over 6866.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02821, over 1425575.56 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:10:13,455 INFO [train.py:763] (5/8) Epoch 38, batch 4050, loss[loss=0.1645, simple_loss=0.2692, pruned_loss=0.02991, over 6818.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02867, over 1424517.95 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:11:18,890 INFO [train.py:763] (5/8) Epoch 38, batch 4100, loss[loss=0.1553, simple_loss=0.2626, pruned_loss=0.02403, over 7211.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02877, over 1422555.33 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:12:24,232 INFO [train.py:763] (5/8) Epoch 38, batch 4150, loss[loss=0.1686, simple_loss=0.2817, pruned_loss=0.02774, over 7218.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.0289, over 1420253.44 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:13:30,538 INFO [train.py:763] (5/8) Epoch 38, batch 4200, loss[loss=0.1723, simple_loss=0.2753, pruned_loss=0.03463, over 6779.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02899, over 1420144.27 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:14:35,837 INFO [train.py:763] (5/8) Epoch 38, batch 4250, loss[loss=0.1438, simple_loss=0.2327, pruned_loss=0.02741, over 7144.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02878, over 1417690.39 frames.], batch size: 17, lr: 1.98e-04
2022-05-01 01:15:41,256 INFO [train.py:763] (5/8) Epoch 38, batch 4300, loss[loss=0.1655, simple_loss=0.2693, pruned_loss=0.03084, over 7283.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.02851, over 1418209.73 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:16:46,658 INFO [train.py:763] (5/8) Epoch 38, batch 4350, loss[loss=0.1394, simple_loss=0.2428, pruned_loss=0.01802, over 7443.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2598, pruned_loss=0.02884, over 1413972.92 frames.], batch size: 20, lr: 1.98e-04
2022-05-01 01:17:51,731 INFO [train.py:763] (5/8) Epoch 38, batch 4400, loss[loss=0.1479, simple_loss=0.2578, pruned_loss=0.01901, over 7335.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2609, pruned_loss=0.0291, over 1410908.40 frames.], batch size: 22, lr: 1.98e-04
2022-05-01 01:18:57,808 INFO [train.py:763] (5/8) Epoch 38, batch 4450, loss[loss=0.1331, simple_loss=0.2263, pruned_loss=0.01997, over 7010.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2619, pruned_loss=0.02956, over 1399230.92 frames.], batch size: 16, lr: 1.98e-04
2022-05-01 01:20:03,891 INFO [train.py:763] (5/8) Epoch 38, batch 4500, loss[loss=0.1181, simple_loss=0.2161, pruned_loss=0.0101, over 7162.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2618, pruned_loss=0.02957, over 1388317.92 frames.], batch size: 18, lr: 1.98e-04
2022-05-01 01:21:09,325 INFO [train.py:763] (5/8) Epoch 38, batch 4550, loss[loss=0.195, simple_loss=0.2863, pruned_loss=0.05183, over 4949.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2643, pruned_loss=0.03124, over 1349082.18 frames.], batch size: 53, lr: 1.98e-04
2022-05-01 01:22:39,309 INFO [train.py:763] (5/8) Epoch 39, batch 0, loss[loss=0.1818, simple_loss=0.285, pruned_loss=0.03931, over 7290.00 frames.], tot_loss[loss=0.1818, simple_loss=0.285, pruned_loss=0.03931, over 7290.00 frames.], batch size: 24, lr: 1.96e-04
2022-05-01 01:23:45,004 INFO [train.py:763] (5/8) Epoch 39, batch 50, loss[loss=0.1305, simple_loss=0.2286, pruned_loss=0.01624, over 7289.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2624, pruned_loss=0.03063, over 316829.92 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:24:50,357 INFO [train.py:763] (5/8) Epoch 39, batch 100, loss[loss=0.1784, simple_loss=0.2778, pruned_loss=0.03948, over 7360.00 frames.], tot_loss[loss=0.1581, simple_loss=0.259, pruned_loss=0.02862, over 561548.00 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:25:56,220 INFO [train.py:763] (5/8) Epoch 39, batch 150, loss[loss=0.1479, simple_loss=0.2496, pruned_loss=0.02313, over 7233.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2557, pruned_loss=0.02772, over 753925.72 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:27:01,298 INFO [train.py:763] (5/8) Epoch 39, batch 200, loss[loss=0.1528, simple_loss=0.2425, pruned_loss=0.03155, over 7393.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2582, pruned_loss=0.02795, over 902181.20 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:28:06,663 INFO [train.py:763] (5/8) Epoch 39, batch 250, loss[loss=0.1638, simple_loss=0.2665, pruned_loss=0.03056, over 7111.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2576, pruned_loss=0.02775, over 1014886.03 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:29:11,531 INFO [train.py:763] (5/8) Epoch 39, batch 300, loss[loss=0.1993, simple_loss=0.2959, pruned_loss=0.05138, over 7285.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2584, pruned_loss=0.02787, over 1105345.84 frames.], batch size: 24, lr: 1.95e-04
2022-05-01 01:30:16,878 INFO [train.py:763] (5/8) Epoch 39, batch 350, loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03091, over 7152.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2579, pruned_loss=0.02825, over 1171150.07 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:31:22,223 INFO [train.py:763] (5/8) Epoch 39, batch 400, loss[loss=0.1525, simple_loss=0.2574, pruned_loss=0.02378, over 7207.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2579, pruned_loss=0.02812, over 1228259.63 frames.], batch size: 26, lr: 1.95e-04
2022-05-01 01:32:27,456 INFO [train.py:763] (5/8) Epoch 39, batch 450, loss[loss=0.193, simple_loss=0.3012, pruned_loss=0.04235, over 7280.00 frames.], tot_loss[loss=0.156, simple_loss=0.2568, pruned_loss=0.0276, over 1272549.28 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:33:32,870 INFO [train.py:763] (5/8) Epoch 39, batch 500, loss[loss=0.1586, simple_loss=0.2708, pruned_loss=0.02324, over 7317.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2563, pruned_loss=0.02758, over 1305016.27 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:34:38,283 INFO [train.py:763] (5/8) Epoch 39, batch 550, loss[loss=0.1632, simple_loss=0.2596, pruned_loss=0.03342, over 7231.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02862, over 1326454.86 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:35:43,501 INFO [train.py:763] (5/8) Epoch 39, batch 600, loss[loss=0.1467, simple_loss=0.2385, pruned_loss=0.02744, over 7259.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2564, pruned_loss=0.02801, over 1348307.32 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:36:48,740 INFO [train.py:763] (5/8) Epoch 39, batch 650, loss[loss=0.1614, simple_loss=0.2641, pruned_loss=0.02936, over 7233.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2563, pruned_loss=0.02804, over 1368003.01 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:37:53,925 INFO [train.py:763] (5/8) Epoch 39, batch 700, loss[loss=0.1193, simple_loss=0.2167, pruned_loss=0.01096, over 7276.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2572, pruned_loss=0.02813, over 1380720.89 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:38:59,267 INFO [train.py:763] (5/8) Epoch 39, batch 750, loss[loss=0.1537, simple_loss=0.2489, pruned_loss=0.02927, over 7356.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02831, over 1386714.13 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:40:04,496 INFO [train.py:763] (5/8) Epoch 39, batch 800, loss[loss=0.1642, simple_loss=0.2728, pruned_loss=0.02785, over 7110.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2569, pruned_loss=0.02788, over 1395900.36 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:41:18,505 INFO [train.py:763] (5/8) Epoch 39, batch 850, loss[loss=0.1672, simple_loss=0.2623, pruned_loss=0.03605, over 7136.00 frames.], tot_loss[loss=0.1563, simple_loss=0.257, pruned_loss=0.02778, over 1402678.56 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:42:32,267 INFO [train.py:763] (5/8) Epoch 39, batch 900, loss[loss=0.1683, simple_loss=0.2635, pruned_loss=0.03658, over 7187.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2578, pruned_loss=0.02786, over 1408324.72 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:43:55,214 INFO [train.py:763] (5/8) Epoch 39, batch 950, loss[loss=0.1688, simple_loss=0.2667, pruned_loss=0.03541, over 5043.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2577, pruned_loss=0.02789, over 1411782.12 frames.], batch size: 53, lr: 1.95e-04
2022-05-01 01:45:01,225 INFO [train.py:763] (5/8) Epoch 39, batch 1000, loss[loss=0.1612, simple_loss=0.2668, pruned_loss=0.02784, over 7104.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2582, pruned_loss=0.02818, over 1410683.96 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:46:06,274 INFO [train.py:763] (5/8) Epoch 39, batch 1050, loss[loss=0.145, simple_loss=0.2459, pruned_loss=0.02204, over 7218.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2581, pruned_loss=0.02809, over 1409781.18 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:47:29,495 INFO [train.py:763] (5/8) Epoch 39, batch 1100, loss[loss=0.1562, simple_loss=0.257, pruned_loss=0.02768, over 7158.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2575, pruned_loss=0.02808, over 1407969.32 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:48:43,945 INFO [train.py:763] (5/8) Epoch 39, batch 1150, loss[loss=0.1864, simple_loss=0.2874, pruned_loss=0.0427, over 6767.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2575, pruned_loss=0.02792, over 1415368.90 frames.], batch size: 31, lr: 1.95e-04
2022-05-01 01:49:48,906 INFO [train.py:763] (5/8) Epoch 39, batch 1200, loss[loss=0.1533, simple_loss=0.2566, pruned_loss=0.02503, over 6567.00 frames.], tot_loss[loss=0.158, simple_loss=0.2589, pruned_loss=0.02854, over 1418192.73 frames.], batch size: 38, lr: 1.95e-04
2022-05-01 01:50:54,372 INFO [train.py:763] (5/8) Epoch 39, batch 1250, loss[loss=0.1635, simple_loss=0.2684, pruned_loss=0.02925, over 7279.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02859, over 1422432.34 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:51:59,445 INFO [train.py:763] (5/8) Epoch 39, batch 1300, loss[loss=0.161, simple_loss=0.2672, pruned_loss=0.02742, over 7424.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02861, over 1422653.20 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:53:04,819 INFO [train.py:763] (5/8) Epoch 39, batch 1350, loss[loss=0.1594, simple_loss=0.2645, pruned_loss=0.02718, over 6164.00 frames.], tot_loss[loss=0.158, simple_loss=0.2582, pruned_loss=0.02888, over 1422034.82 frames.], batch size: 37, lr: 1.95e-04
2022-05-01 01:54:11,092 INFO [train.py:763] (5/8) Epoch 39, batch 1400, loss[loss=0.1536, simple_loss=0.243, pruned_loss=0.03212, over 6511.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02891, over 1423812.16 frames.], batch size: 38, lr: 1.95e-04
2022-05-01 01:55:16,355 INFO [train.py:763] (5/8) Epoch 39, batch 1450, loss[loss=0.1907, simple_loss=0.2906, pruned_loss=0.0454, over 7199.00 frames.], tot_loss[loss=0.158, simple_loss=0.2582, pruned_loss=0.02885, over 1424718.51 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:56:21,447 INFO [train.py:763] (5/8) Epoch 39, batch 1500, loss[loss=0.1475, simple_loss=0.2365, pruned_loss=0.02927, over 7140.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02875, over 1425732.81 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:57:28,670 INFO [train.py:763] (5/8) Epoch 39, batch 1550, loss[loss=0.1684, simple_loss=0.2658, pruned_loss=0.03548, over 7184.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02879, over 1423855.62 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:58:35,232 INFO [train.py:763] (5/8) Epoch 39, batch 1600, loss[loss=0.1728, simple_loss=0.2763, pruned_loss=0.03467, over 7105.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02863, over 1426680.76 frames.], batch size: 28, lr: 1.95e-04
2022-05-01 01:59:41,358 INFO [train.py:763] (5/8) Epoch 39, batch 1650, loss[loss=0.1743, simple_loss=0.2713, pruned_loss=0.03867, over 4937.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02871, over 1419255.67 frames.], batch size: 53, lr: 1.95e-04
2022-05-01 02:00:47,169 INFO [train.py:763] (5/8) Epoch 39, batch 1700, loss[loss=0.1342, simple_loss=0.2258, pruned_loss=0.02128, over 6996.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2589, pruned_loss=0.02876, over 1411993.07 frames.], batch size: 16, lr: 1.95e-04
2022-05-01 02:01:53,362 INFO [train.py:763] (5/8) Epoch 39, batch 1750, loss[loss=0.1638, simple_loss=0.2741, pruned_loss=0.02669, over 7326.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02831, over 1413111.22 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 02:02:58,283 INFO [train.py:763] (5/8) Epoch 39, batch 1800, loss[loss=0.1616, simple_loss=0.2683, pruned_loss=0.02745, over 7337.00 frames.], tot_loss[loss=0.1579, simple_loss=0.259, pruned_loss=0.02847, over 1415560.48 frames.], batch size: 22, lr: 1.95e-04
2022-05-01 02:04:03,604 INFO [train.py:763] (5/8) Epoch 39, batch 1850, loss[loss=0.129, simple_loss=0.226, pruned_loss=0.01597, over 7063.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2588, pruned_loss=0.02833, over 1418560.14 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 02:05:08,887 INFO [train.py:763] (5/8) Epoch 39, batch 1900, loss[loss=0.1389, simple_loss=0.2426, pruned_loss=0.01762, over 7159.00 frames.], tot_loss[loss=0.1575, simple_loss=0.259, pruned_loss=0.02804, over 1422968.11 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:06:14,313 INFO [train.py:763] (5/8) Epoch 39, batch 1950, loss[loss=0.1547, simple_loss=0.2557, pruned_loss=0.02687, over 5065.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2587, pruned_loss=0.02828, over 1417046.53 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:07:19,654 INFO [train.py:763] (5/8) Epoch 39, batch 2000, loss[loss=0.1441, simple_loss=0.2408, pruned_loss=0.02368, over 7069.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2575, pruned_loss=0.02789, over 1420980.52 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:08:24,812 INFO [train.py:763] (5/8) Epoch 39, batch 2050, loss[loss=0.153, simple_loss=0.2529, pruned_loss=0.02653, over 7432.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2574, pruned_loss=0.02779, over 1425196.28 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:09:30,532 INFO [train.py:763] (5/8) Epoch 39, batch 2100, loss[loss=0.1703, simple_loss=0.2646, pruned_loss=0.038, over 7415.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2573, pruned_loss=0.02804, over 1424080.05 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:10:35,932 INFO [train.py:763] (5/8) Epoch 39, batch 2150, loss[loss=0.1577, simple_loss=0.27, pruned_loss=0.02275, over 7152.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2576, pruned_loss=0.02834, over 1428851.35 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:11:43,132 INFO [train.py:763] (5/8) Epoch 39, batch 2200, loss[loss=0.1526, simple_loss=0.2597, pruned_loss=0.02276, over 7224.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02823, over 1431277.78 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:12:48,273 INFO [train.py:763] (5/8) Epoch 39, batch 2250, loss[loss=0.1773, simple_loss=0.2694, pruned_loss=0.04259, over 7208.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02876, over 1429040.73 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:13:53,531 INFO [train.py:763] (5/8) Epoch 39, batch 2300, loss[loss=0.1501, simple_loss=0.2565, pruned_loss=0.0218, over 7428.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2578, pruned_loss=0.02887, over 1426292.93 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:15:00,688 INFO [train.py:763] (5/8) Epoch 39, batch 2350, loss[loss=0.1618, simple_loss=0.2704, pruned_loss=0.02655, over 7331.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2573, pruned_loss=0.02904, over 1426089.59 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:16:07,737 INFO [train.py:763] (5/8) Epoch 39, batch 2400, loss[loss=0.1671, simple_loss=0.2745, pruned_loss=0.02986, over 7202.00 frames.], tot_loss[loss=0.1573, simple_loss=0.257, pruned_loss=0.02877, over 1426872.47 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:17:13,331 INFO [train.py:763] (5/8) Epoch 39, batch 2450, loss[loss=0.1553, simple_loss=0.2657, pruned_loss=0.02249, over 7092.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2575, pruned_loss=0.02873, over 1422843.41 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:18:19,523 INFO [train.py:763] (5/8) Epoch 39, batch 2500, loss[loss=0.1628, simple_loss=0.2602, pruned_loss=0.03271, over 7409.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2575, pruned_loss=0.02885, over 1419554.69 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:19:24,724 INFO [train.py:763] (5/8) Epoch 39, batch 2550, loss[loss=0.1854, simple_loss=0.2876, pruned_loss=0.04163, over 7069.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02878, over 1419513.84 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:20:31,566 INFO [train.py:763] (5/8) Epoch 39, batch 2600, loss[loss=0.1627, simple_loss=0.2652, pruned_loss=0.03008, over 7333.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02839, over 1419025.40 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:21:37,536 INFO [train.py:763] (5/8) Epoch 39, batch 2650, loss[loss=0.1494, simple_loss=0.2481, pruned_loss=0.02536, over 7147.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02859, over 1421761.28 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:22:43,389 INFO [train.py:763] (5/8) Epoch 39, batch 2700, loss[loss=0.1659, simple_loss=0.2669, pruned_loss=0.03247, over 7164.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02857, over 1422786.30 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:23:48,614 INFO [train.py:763] (5/8) Epoch 39, batch 2750, loss[loss=0.1605, simple_loss=0.2675, pruned_loss=0.02676, over 7294.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02825, over 1425891.30 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:24:53,692 INFO [train.py:763] (5/8) Epoch 39, batch 2800, loss[loss=0.1474, simple_loss=0.2446, pruned_loss=0.02509, over 7060.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2584, pruned_loss=0.02846, over 1422061.20 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:25:58,657 INFO [train.py:763] (5/8) Epoch 39, batch 2850, loss[loss=0.1517, simple_loss=0.2511, pruned_loss=0.02618, over 6510.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2585, pruned_loss=0.02851, over 1418765.95 frames.], batch size: 38, lr: 1.94e-04
2022-05-01 02:27:03,584 INFO [train.py:763] (5/8) Epoch 39, batch 2900, loss[loss=0.1468, simple_loss=0.2423, pruned_loss=0.02562, over 7059.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02838, over 1419296.55 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:28:08,503 INFO [train.py:763] (5/8) Epoch 39, batch 2950, loss[loss=0.1541, simple_loss=0.2599, pruned_loss=0.02415, over 7308.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2596, pruned_loss=0.02884, over 1418752.69 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:29:13,392 INFO [train.py:763] (5/8) Epoch 39, batch 3000, loss[loss=0.1805, simple_loss=0.2821, pruned_loss=0.03942, over 7330.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.02896, over 1412907.24 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:29:13,393 INFO [train.py:783] (5/8) Computing validation loss
2022-05-01 02:29:28,415 INFO [train.py:792] (5/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
2022-05-01 02:30:33,960 INFO [train.py:763] (5/8) Epoch 39, batch 3050, loss[loss=0.1467, simple_loss=0.2469, pruned_loss=0.02326, over 7363.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.029, over 1414320.80 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:31:41,157 INFO [train.py:763] (5/8) Epoch 39, batch 3100, loss[loss=0.1728, simple_loss=0.2754, pruned_loss=0.03507, over 7131.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02885, over 1416298.63 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:32:47,805 INFO [train.py:763] (5/8) Epoch 39, batch 3150, loss[loss=0.1693, simple_loss=0.2838, pruned_loss=0.02743, over 7139.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2595, pruned_loss=0.0287, over 1420185.33 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:33:53,389 INFO [train.py:763] (5/8) Epoch 39, batch 3200, loss[loss=0.2107, simple_loss=0.302, pruned_loss=0.05972, over 4646.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2596, pruned_loss=0.02861, over 1420304.85 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:34:58,491 INFO [train.py:763] (5/8) Epoch 39, batch 3250, loss[loss=0.1551, simple_loss=0.2596, pruned_loss=0.02533, over 7374.00 frames.], tot_loss[loss=0.1588, simple_loss=0.26, pruned_loss=0.02877, over 1418789.10 frames.], batch size: 23, lr: 1.94e-04
2022-05-01 02:36:03,622 INFO [train.py:763] (5/8) Epoch 39, batch 3300, loss[loss=0.1494, simple_loss=0.2511, pruned_loss=0.02387, over 7124.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02853, over 1418181.85 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:37:08,802 INFO [train.py:763] (5/8) Epoch 39, batch 3350, loss[loss=0.1646, simple_loss=0.2749, pruned_loss=0.02715, over 7106.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02864, over 1415730.72 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:38:14,801 INFO [train.py:763] (5/8) Epoch 39, batch 3400, loss[loss=0.1529, simple_loss=0.2454, pruned_loss=0.03022, over 7158.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2569, pruned_loss=0.02818, over 1416938.53 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:39:20,473 INFO [train.py:763] (5/8) Epoch 39, batch 3450, loss[loss=0.1289, simple_loss=0.2212, pruned_loss=0.01828, over 7290.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02874, over 1416410.43 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:40:25,693 INFO [train.py:763] (5/8) Epoch 39, batch 3500, loss[loss=0.1694, simple_loss=0.2811, pruned_loss=0.02879, over 7318.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02903, over 1418146.73 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:41:31,491 INFO [train.py:763] (5/8) Epoch 39, batch 3550, loss[loss=0.1504, simple_loss=0.24, pruned_loss=0.03046, over 7066.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02896, over 1419931.21 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:42:37,770 INFO [train.py:763] (5/8) Epoch 39, batch 3600, loss[loss=0.1714, simple_loss=0.2715, pruned_loss=0.0356, over 5041.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02896, over 1417095.41 frames.], batch size: 53, lr: 1.94e-04
2022-05-01 02:43:44,826 INFO [train.py:763] (5/8) Epoch 39, batch 3650, loss[loss=0.1776, simple_loss=0.2747, pruned_loss=0.0402, over 6449.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02865, over 1418631.10 frames.], batch size: 37, lr: 1.94e-04
2022-05-01 02:44:50,057 INFO [train.py:763] (5/8) Epoch 39, batch 3700, loss[loss=0.1458, simple_loss=0.2455, pruned_loss=0.02304, over 7131.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02875, over 1422342.82 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:45:55,098 INFO [train.py:763] (5/8) Epoch 39, batch 3750, loss[loss=0.1583, simple_loss=0.2536, pruned_loss=0.03156, over 7348.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02865, over 1419573.41 frames.], batch size: 19, lr: 1.93e-04
2022-05-01 02:47:00,708 INFO [train.py:763] (5/8) Epoch 39, batch 3800, loss[loss=0.1263, simple_loss=0.2224, pruned_loss=0.01511, over 7013.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2592, pruned_loss=0.02863, over 1423544.66 frames.], batch size: 16, lr: 1.93e-04
2022-05-01 02:48:07,771 INFO [train.py:763] (5/8) Epoch 39, batch 3850, loss[loss=0.1691, simple_loss=0.2825, pruned_loss=0.02784, over 7403.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2583, pruned_loss=0.02817, over 1419698.78 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:49:13,677 INFO [train.py:763] (5/8) Epoch 39, batch 3900, loss[loss=0.1623, simple_loss=0.2683, pruned_loss=0.02818, over 7197.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2584, pruned_loss=0.02815, over 1420920.94 frames.], batch size: 23, lr: 1.93e-04
2022-05-01 02:50:20,010 INFO [train.py:763] (5/8) Epoch 39, batch 3950, loss[loss=0.1458, simple_loss=0.2484, pruned_loss=0.02161, over 7071.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02848, over 1415226.81 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:51:25,349 INFO [train.py:763] (5/8) Epoch 39, batch 4000, loss[loss=0.1477, simple_loss=0.2429, pruned_loss=0.02624, over 7140.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.0289, over 1415001.66 frames.], batch size: 17, lr: 1.93e-04
2022-05-01 02:52:30,797 INFO [train.py:763] (5/8) Epoch 39, batch 4050, loss[loss=0.1587, simple_loss=0.2692, pruned_loss=0.02413, over 7193.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02915, over 1420577.80 frames.], batch size: 22, lr: 1.93e-04
2022-05-01 02:53:35,948 INFO [train.py:763] (5/8) Epoch 39, batch 4100, loss[loss=0.1578, simple_loss=0.2608, pruned_loss=0.02743, over 7240.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02891, over 1420381.36 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 02:54:41,373 INFO [train.py:763] (5/8) Epoch 39, batch 4150, loss[loss=0.1663, simple_loss=0.2473, pruned_loss=0.04271, over 7272.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02888, over 1422375.11 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:55:46,812 INFO [train.py:763] (5/8) Epoch 39, batch 4200, loss[loss=0.1599, simple_loss=0.2584, pruned_loss=0.0307, over 7154.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02872, over 1423831.73 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:56:52,119 INFO [train.py:763] (5/8) Epoch 39, batch 4250, loss[loss=0.1517, simple_loss=0.2589, pruned_loss=0.02222, over 7306.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02897, over 1418745.09 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:57:57,426 INFO [train.py:763] (5/8) Epoch 39, batch 4300, loss[loss=0.1309, simple_loss=0.2232, pruned_loss=0.01932, over 7167.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02911, over 1418956.71 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:59:02,815 INFO [train.py:763] (5/8) Epoch 39, batch 4350, loss[loss=0.1608, simple_loss=0.2686, pruned_loss=0.02655, over 7337.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02905, over 1420336.20 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 03:00:09,031 INFO [train.py:763] (5/8) Epoch 39, batch 4400, loss[loss=0.1799, simple_loss=0.2849, pruned_loss=0.03741, over 6874.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02889, over 1421200.77 frames.], batch size: 31, lr: 1.93e-04
2022-05-01 03:01:14,008 INFO [train.py:763] (5/8) Epoch 39, batch 4450, loss[loss=0.141, simple_loss=0.2347, pruned_loss=0.02371, over 7175.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02898, over 1408466.45 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 03:02:19,224 INFO [train.py:763] (5/8) Epoch 39, batch 4500, loss[loss=0.1393, simple_loss=0.2459, pruned_loss=0.01642, over 7226.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02916, over 1400583.68 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 03:03:25,872 INFO [train.py:763] (5/8) Epoch 39, batch 4550, loss[loss=0.1609, simple_loss=0.2455, pruned_loss=0.03811, over 7208.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2563, pruned_loss=0.02891, over 1391183.23 frames.], batch size: 16, lr: 1.93e-04
2022-05-01 03:04:15,399 INFO [train.py:971] (5/8) Done!