2022-05-03 11:40:27,489 INFO [train.py:775] (5/8) Training started
2022-05-03 11:40:27,489 INFO [train.py:785] (5/8) Device: cuda:5
2022-05-03 11:40:27,491 INFO [train.py:794] (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, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Debug', 'k2-with-cuda': True, 'k2-git-sha1': '1b29f0a946f50186aaa82df46a59f492ade9692b', 'k2-git-date': 'Tue Apr 12 20:46:49 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.1+cu111', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.8', 'icefall-git-branch': 'spgi', 'icefall-git-sha1': 'e2e5c77-dirty', 'icefall-git-date': 'Mon May 2 14:38:25 2022', 'icefall-path': '/exp/draj/mini_scale_2022/icefall', 'k2-path': '/exp/draj/mini_scale_2022/k2/k2/python/k2/__init__.py', 'lhotse-path': '/exp/draj/mini_scale_2022/lhotse/lhotse/__init__.py', 'hostname': 'r8n04', 'IP address': '10.1.8.4'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 20, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp/v2'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 4, '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': 10, 'use_fp16': True, 'manifest_dir': PosixPath('data/manifests'), 'enable_musan': True, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'max_duration': 200, 'num_buckets': 30, 'on_the_fly_feats': False, 'shuffle': True, 'num_workers': 8, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'blank_id': 0, 'vocab_size': 500}
2022-05-03 11:40:27,492 INFO [train.py:796] (5/8) About to create model
2022-05-03 11:40:27,843 INFO [train.py:800] (5/8) Number of model parameters: 78648040
2022-05-03 11:40:33,537 INFO [train.py:806] (5/8) Using DDP
2022-05-03 11:40:34,140 INFO [asr_datamodule.py:321] (5/8) About to get SPGISpeech train cuts
2022-05-03 11:40:34,143 INFO [asr_datamodule.py:179] (5/8) About to get Musan cuts
2022-05-03 11:40:36,099 INFO [asr_datamodule.py:184] (5/8) Enable MUSAN
2022-05-03 11:40:36,099 INFO [asr_datamodule.py:207] (5/8) Enable SpecAugment
2022-05-03 11:40:36,099 INFO [asr_datamodule.py:208] (5/8) Time warp factor: 80
2022-05-03 11:40:36,099 INFO [asr_datamodule.py:221] (5/8) About to create train dataset
2022-05-03 11:40:36,100 INFO [asr_datamodule.py:234] (5/8) Using DynamicBucketingSampler.
2022-05-03 11:40:36,494 INFO [asr_datamodule.py:242] (5/8) About to create train dataloader
2022-05-03 11:40:36,495 INFO [asr_datamodule.py:326] (5/8) About to get SPGISpeech dev cuts
2022-05-03 11:40:36,496 INFO [asr_datamodule.py:274] (5/8) About to create dev dataset
2022-05-03 11:40:36,643 INFO [asr_datamodule.py:289] (5/8) About to create dev dataloader
2022-05-03 11:41:08,013 INFO [train.py:715] (5/8) Epoch 0, batch 0, loss[loss=3.467, simple_loss=6.935, pruned_loss=5.919, over 4955.00 frames.], tot_loss[loss=3.467, simple_loss=6.935, pruned_loss=5.919, over 4955.00 frames.], batch size: 35, lr: 3.00e-03
2022-05-03 11:41:08,560 INFO [distributed.py:874] (5/8) Reducer buckets have been rebuilt in this iteration.
2022-05-03 11:41:46,315 INFO [train.py:715] (5/8) Epoch 0, batch 50, loss[loss=0.4226, simple_loss=0.8452, pruned_loss=6.694, over 4947.00 frames.], tot_loss[loss=1.327, simple_loss=2.654, pruned_loss=6.453, over 219518.87 frames.], batch size: 15, lr: 3.00e-03
2022-05-03 11:42:25,579 INFO [train.py:715] (5/8) Epoch 0, batch 100, loss[loss=0.383, simple_loss=0.766, pruned_loss=6.64, over 4816.00 frames.], tot_loss[loss=0.8197, simple_loss=1.639, pruned_loss=6.572, over 387432.24 frames.], batch size: 21, lr: 3.00e-03
2022-05-03 11:43:04,757 INFO [train.py:715] (5/8) Epoch 0, batch 150, loss[loss=0.3556, simple_loss=0.7112, pruned_loss=6.657, over 4896.00 frames.], tot_loss[loss=0.6327, simple_loss=1.265, pruned_loss=6.591, over 517004.28 frames.], batch size: 17, lr: 3.00e-03
2022-05-03 11:43:43,122 INFO [train.py:715] (5/8) Epoch 0, batch 200, loss[loss=0.3518, simple_loss=0.7037, pruned_loss=6.737, over 4758.00 frames.], tot_loss[loss=0.5331, simple_loss=1.066, pruned_loss=6.581, over 617402.75 frames.], batch size: 19, lr: 3.00e-03
2022-05-03 11:44:22,066 INFO [train.py:715] (5/8) Epoch 0, batch 250, loss[loss=0.3214, simple_loss=0.6429, pruned_loss=6.494, over 4990.00 frames.], tot_loss[loss=0.4742, simple_loss=0.9484, pruned_loss=6.591, over 696372.56 frames.], batch size: 25, lr: 3.00e-03
2022-05-03 11:45:01,537 INFO [train.py:715] (5/8) Epoch 0, batch 300, loss[loss=0.3174, simple_loss=0.6347, pruned_loss=6.667, over 4793.00 frames.], tot_loss[loss=0.4341, simple_loss=0.8683, pruned_loss=6.603, over 757586.21 frames.], batch size: 17, lr: 3.00e-03
2022-05-03 11:45:41,191 INFO [train.py:715] (5/8) Epoch 0, batch 350, loss[loss=0.3249, simple_loss=0.6499, pruned_loss=6.653, over 4988.00 frames.], tot_loss[loss=0.4066, simple_loss=0.8132, pruned_loss=6.618, over 805325.11 frames.], batch size: 16, lr: 3.00e-03
2022-05-03 11:46:19,551 INFO [train.py:715] (5/8) Epoch 0, batch 400, loss[loss=0.3169, simple_loss=0.6337, pruned_loss=6.554, over 4860.00 frames.], tot_loss[loss=0.3856, simple_loss=0.7713, pruned_loss=6.633, over 842759.16 frames.], batch size: 32, lr: 3.00e-03
2022-05-03 11:46:58,908 INFO [train.py:715] (5/8) Epoch 0, batch 450, loss[loss=0.2969, simple_loss=0.5938, pruned_loss=6.605, over 4767.00 frames.], tot_loss[loss=0.3693, simple_loss=0.7386, pruned_loss=6.643, over 871240.56 frames.], batch size: 14, lr: 2.99e-03
2022-05-03 11:47:38,001 INFO [train.py:715] (5/8) Epoch 0, batch 500, loss[loss=0.3548, simple_loss=0.7097, pruned_loss=6.724, over 4892.00 frames.], tot_loss[loss=0.3577, simple_loss=0.7154, pruned_loss=6.647, over 893458.63 frames.], batch size: 19, lr: 2.99e-03
2022-05-03 11:48:17,106 INFO [train.py:715] (5/8) Epoch 0, batch 550, loss[loss=0.2731, simple_loss=0.5462, pruned_loss=6.68, over 4860.00 frames.], tot_loss[loss=0.3464, simple_loss=0.6928, pruned_loss=6.646, over 910360.01 frames.], batch size: 15, lr: 2.99e-03
2022-05-03 11:48:55,927 INFO [train.py:715] (5/8) Epoch 0, batch 600, loss[loss=0.3202, simple_loss=0.6405, pruned_loss=6.771, over 4909.00 frames.], tot_loss[loss=0.3367, simple_loss=0.6735, pruned_loss=6.661, over 924373.66 frames.], batch size: 39, lr: 2.99e-03
2022-05-03 11:49:35,147 INFO [train.py:715] (5/8) Epoch 0, batch 650, loss[loss=0.2637, simple_loss=0.5274, pruned_loss=6.745, over 4992.00 frames.], tot_loss[loss=0.3258, simple_loss=0.6516, pruned_loss=6.681, over 935726.75 frames.], batch size: 14, lr: 2.99e-03
2022-05-03 11:50:14,495 INFO [train.py:715] (5/8) Epoch 0, batch 700, loss[loss=0.2706, simple_loss=0.5411, pruned_loss=6.798, over 4702.00 frames.], tot_loss[loss=0.3146, simple_loss=0.6292, pruned_loss=6.7, over 944480.91 frames.], batch size: 15, lr: 2.99e-03
2022-05-03 11:50:52,999 INFO [train.py:715] (5/8) Epoch 0, batch 750, loss[loss=0.2317, simple_loss=0.4634, pruned_loss=6.648, over 4938.00 frames.], tot_loss[loss=0.3016, simple_loss=0.6033, pruned_loss=6.713, over 950118.50 frames.], batch size: 21, lr: 2.98e-03
2022-05-03 11:51:32,779 INFO [train.py:715] (5/8) Epoch 0, batch 800, loss[loss=0.2369, simple_loss=0.4737, pruned_loss=6.615, over 4990.00 frames.], tot_loss[loss=0.2902, simple_loss=0.5804, pruned_loss=6.717, over 955322.30 frames.], batch size: 16, lr: 2.98e-03
2022-05-03 11:52:12,743 INFO [train.py:715] (5/8) Epoch 0, batch 850, loss[loss=0.2205, simple_loss=0.441, pruned_loss=6.624, over 4976.00 frames.], tot_loss[loss=0.2795, simple_loss=0.5591, pruned_loss=6.72, over 959951.22 frames.], batch size: 35, lr: 2.98e-03
2022-05-03 11:52:51,639 INFO [train.py:715] (5/8) Epoch 0, batch 900, loss[loss=0.2287, simple_loss=0.4574, pruned_loss=6.752, over 4927.00 frames.], tot_loss[loss=0.269, simple_loss=0.5379, pruned_loss=6.717, over 963034.12 frames.], batch size: 29, lr: 2.98e-03
2022-05-03 11:53:30,229 INFO [train.py:715] (5/8) Epoch 0, batch 950, loss[loss=0.2421, simple_loss=0.4842, pruned_loss=6.821, over 4824.00 frames.], tot_loss[loss=0.2604, simple_loss=0.5208, pruned_loss=6.717, over 965510.39 frames.], batch size: 25, lr: 2.97e-03
2022-05-03 11:54:09,541 INFO [train.py:715] (5/8) Epoch 0, batch 1000, loss[loss=0.2314, simple_loss=0.4628, pruned_loss=6.658, over 4982.00 frames.], tot_loss[loss=0.2515, simple_loss=0.503, pruned_loss=6.713, over 967284.40 frames.], batch size: 25, lr: 2.97e-03
2022-05-03 11:54:48,898 INFO [train.py:715] (5/8) Epoch 0, batch 1050, loss[loss=0.2078, simple_loss=0.4156, pruned_loss=6.668, over 4963.00 frames.], tot_loss[loss=0.2445, simple_loss=0.4891, pruned_loss=6.715, over 968780.08 frames.], batch size: 15, lr: 2.97e-03
2022-05-03 11:55:27,472 INFO [train.py:715] (5/8) Epoch 0, batch 1100, loss[loss=0.2207, simple_loss=0.4415, pruned_loss=6.774, over 4758.00 frames.], tot_loss[loss=0.2376, simple_loss=0.4753, pruned_loss=6.714, over 969432.93 frames.], batch size: 16, lr: 2.96e-03
2022-05-03 11:56:07,478 INFO [train.py:715] (5/8) Epoch 0, batch 1150, loss[loss=0.1751, simple_loss=0.3502, pruned_loss=6.738, over 4751.00 frames.], tot_loss[loss=0.2327, simple_loss=0.4654, pruned_loss=6.721, over 969457.01 frames.], batch size: 19, lr: 2.96e-03
2022-05-03 11:56:47,814 INFO [train.py:715] (5/8) Epoch 0, batch 1200, loss[loss=0.2238, simple_loss=0.4475, pruned_loss=6.743, over 4875.00 frames.], tot_loss[loss=0.2265, simple_loss=0.453, pruned_loss=6.72, over 970119.64 frames.], batch size: 16, lr: 2.96e-03
2022-05-03 11:57:28,445 INFO [train.py:715] (5/8) Epoch 0, batch 1250, loss[loss=0.1955, simple_loss=0.391, pruned_loss=6.751, over 4780.00 frames.], tot_loss[loss=0.2222, simple_loss=0.4444, pruned_loss=6.718, over 970497.83 frames.], batch size: 18, lr: 2.95e-03
2022-05-03 11:58:07,342 INFO [train.py:715] (5/8) Epoch 0, batch 1300, loss[loss=0.2336, simple_loss=0.4671, pruned_loss=6.799, over 4939.00 frames.], tot_loss[loss=0.2186, simple_loss=0.4372, pruned_loss=6.719, over 971252.11 frames.], batch size: 23, lr: 2.95e-03
2022-05-03 11:58:47,750 INFO [train.py:715] (5/8) Epoch 0, batch 1350, loss[loss=0.2059, simple_loss=0.4117, pruned_loss=6.632, over 4911.00 frames.], tot_loss[loss=0.2153, simple_loss=0.4307, pruned_loss=6.718, over 971732.62 frames.], batch size: 18, lr: 2.95e-03
2022-05-03 11:59:28,712 INFO [train.py:715] (5/8) Epoch 0, batch 1400, loss[loss=0.1952, simple_loss=0.3903, pruned_loss=6.609, over 4805.00 frames.], tot_loss[loss=0.2114, simple_loss=0.4228, pruned_loss=6.714, over 972436.64 frames.], batch size: 25, lr: 2.94e-03
2022-05-03 12:00:09,336 INFO [train.py:715] (5/8) Epoch 0, batch 1450, loss[loss=0.1926, simple_loss=0.3852, pruned_loss=6.724, over 4968.00 frames.], tot_loss[loss=0.2074, simple_loss=0.4148, pruned_loss=6.709, over 972863.21 frames.], batch size: 15, lr: 2.94e-03
2022-05-03 12:00:48,851 INFO [train.py:715] (5/8) Epoch 0, batch 1500, loss[loss=0.1946, simple_loss=0.3891, pruned_loss=6.723, over 4981.00 frames.], tot_loss[loss=0.2046, simple_loss=0.4092, pruned_loss=6.707, over 972996.01 frames.], batch size: 35, lr: 2.94e-03
2022-05-03 12:01:29,923 INFO [train.py:715] (5/8) Epoch 0, batch 1550, loss[loss=0.1998, simple_loss=0.3996, pruned_loss=6.624, over 4985.00 frames.], tot_loss[loss=0.2023, simple_loss=0.4046, pruned_loss=6.707, over 972637.06 frames.], batch size: 28, lr: 2.93e-03
2022-05-03 12:02:11,270 INFO [train.py:715] (5/8) Epoch 0, batch 1600, loss[loss=0.1716, simple_loss=0.3431, pruned_loss=6.581, over 4838.00 frames.], tot_loss[loss=0.1988, simple_loss=0.3975, pruned_loss=6.699, over 972208.52 frames.], batch size: 12, lr: 2.93e-03
2022-05-03 12:02:51,044 INFO [train.py:715] (5/8) Epoch 0, batch 1650, loss[loss=0.1864, simple_loss=0.3728, pruned_loss=6.693, over 4855.00 frames.], tot_loss[loss=0.1965, simple_loss=0.3929, pruned_loss=6.694, over 972118.74 frames.], batch size: 20, lr: 2.92e-03
2022-05-03 12:03:32,813 INFO [train.py:715] (5/8) Epoch 0, batch 1700, loss[loss=0.1745, simple_loss=0.3489, pruned_loss=6.667, over 4880.00 frames.], tot_loss[loss=0.1934, simple_loss=0.3868, pruned_loss=6.687, over 972437.07 frames.], batch size: 16, lr: 2.92e-03
2022-05-03 12:04:14,555 INFO [train.py:715] (5/8) Epoch 0, batch 1750, loss[loss=0.1969, simple_loss=0.3939, pruned_loss=6.727, over 4802.00 frames.], tot_loss[loss=0.1925, simple_loss=0.3851, pruned_loss=6.686, over 972330.85 frames.], batch size: 24, lr: 2.91e-03
2022-05-03 12:04:56,012 INFO [train.py:715] (5/8) Epoch 0, batch 1800, loss[loss=0.1719, simple_loss=0.3438, pruned_loss=6.584, over 4848.00 frames.], tot_loss[loss=0.1911, simple_loss=0.3821, pruned_loss=6.68, over 972052.74 frames.], batch size: 30, lr: 2.91e-03
2022-05-03 12:05:36,582 INFO [train.py:715] (5/8) Epoch 0, batch 1850, loss[loss=0.1942, simple_loss=0.3884, pruned_loss=6.785, over 4818.00 frames.], tot_loss[loss=0.1887, simple_loss=0.3775, pruned_loss=6.672, over 970809.98 frames.], batch size: 25, lr: 2.91e-03
2022-05-03 12:06:18,617 INFO [train.py:715] (5/8) Epoch 0, batch 1900, loss[loss=0.2104, simple_loss=0.4209, pruned_loss=6.566, over 4800.00 frames.], tot_loss[loss=0.1871, simple_loss=0.3742, pruned_loss=6.671, over 970707.37 frames.], batch size: 14, lr: 2.90e-03
2022-05-03 12:07:00,155 INFO [train.py:715] (5/8) Epoch 0, batch 1950, loss[loss=0.2058, simple_loss=0.4115, pruned_loss=6.651, over 4857.00 frames.], tot_loss[loss=0.1861, simple_loss=0.3722, pruned_loss=6.67, over 972070.28 frames.], batch size: 30, lr: 2.90e-03
2022-05-03 12:07:38,878 INFO [train.py:715] (5/8) Epoch 0, batch 2000, loss[loss=0.1858, simple_loss=0.3716, pruned_loss=6.585, over 4980.00 frames.], tot_loss[loss=0.184, simple_loss=0.368, pruned_loss=6.661, over 972341.98 frames.], batch size: 28, lr: 2.89e-03
2022-05-03 12:08:20,001 INFO [train.py:715] (5/8) Epoch 0, batch 2050, loss[loss=0.1846, simple_loss=0.3692, pruned_loss=6.772, over 4846.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3674, pruned_loss=6.661, over 972195.39 frames.], batch size: 15, lr: 2.89e-03
2022-05-03 12:09:00,598 INFO [train.py:715] (5/8) Epoch 0, batch 2100, loss[loss=0.1732, simple_loss=0.3464, pruned_loss=6.608, over 4920.00 frames.], tot_loss[loss=0.1827, simple_loss=0.3654, pruned_loss=6.662, over 972263.78 frames.], batch size: 29, lr: 2.88e-03
2022-05-03 12:09:41,214 INFO [train.py:715] (5/8) Epoch 0, batch 2150, loss[loss=0.1784, simple_loss=0.3569, pruned_loss=6.689, over 4879.00 frames.], tot_loss[loss=0.1815, simple_loss=0.3631, pruned_loss=6.662, over 971888.36 frames.], batch size: 19, lr: 2.88e-03
2022-05-03 12:10:20,510 INFO [train.py:715] (5/8) Epoch 0, batch 2200, loss[loss=0.1688, simple_loss=0.3376, pruned_loss=6.578, over 4883.00 frames.], tot_loss[loss=0.1804, simple_loss=0.3608, pruned_loss=6.665, over 972292.46 frames.], batch size: 32, lr: 2.87e-03
2022-05-03 12:11:01,496 INFO [train.py:715] (5/8) Epoch 0, batch 2250, loss[loss=0.1609, simple_loss=0.3219, pruned_loss=6.658, over 4810.00 frames.], tot_loss[loss=0.1798, simple_loss=0.3595, pruned_loss=6.665, over 972039.90 frames.], batch size: 27, lr: 2.86e-03
2022-05-03 12:11:42,778 INFO [train.py:715] (5/8) Epoch 0, batch 2300, loss[loss=0.1733, simple_loss=0.3466, pruned_loss=6.738, over 4823.00 frames.], tot_loss[loss=0.1786, simple_loss=0.3573, pruned_loss=6.664, over 971541.65 frames.], batch size: 15, lr: 2.86e-03
2022-05-03 12:12:22,382 INFO [train.py:715] (5/8) Epoch 0, batch 2350, loss[loss=0.1945, simple_loss=0.3891, pruned_loss=6.744, over 4916.00 frames.], tot_loss[loss=0.1787, simple_loss=0.3574, pruned_loss=6.668, over 971958.82 frames.], batch size: 23, lr: 2.85e-03
2022-05-03 12:13:03,133 INFO [train.py:715] (5/8) Epoch 0, batch 2400, loss[loss=0.1831, simple_loss=0.3662, pruned_loss=6.784, over 4743.00 frames.], tot_loss[loss=0.1771, simple_loss=0.3542, pruned_loss=6.667, over 972500.27 frames.], batch size: 16, lr: 2.85e-03
2022-05-03 12:13:43,820 INFO [train.py:715] (5/8) Epoch 0, batch 2450, loss[loss=0.1598, simple_loss=0.3195, pruned_loss=6.665, over 4924.00 frames.], tot_loss[loss=0.1762, simple_loss=0.3524, pruned_loss=6.666, over 971617.13 frames.], batch size: 29, lr: 2.84e-03
2022-05-03 12:14:24,683 INFO [train.py:715] (5/8) Epoch 0, batch 2500, loss[loss=0.1488, simple_loss=0.2975, pruned_loss=6.565, over 4971.00 frames.], tot_loss[loss=0.1759, simple_loss=0.3519, pruned_loss=6.668, over 972476.77 frames.], batch size: 24, lr: 2.84e-03
2022-05-03 12:15:03,914 INFO [train.py:715] (5/8) Epoch 0, batch 2550, loss[loss=0.1905, simple_loss=0.3809, pruned_loss=6.576, over 4850.00 frames.], tot_loss[loss=0.1752, simple_loss=0.3505, pruned_loss=6.664, over 972038.52 frames.], batch size: 20, lr: 2.83e-03
2022-05-03 12:15:44,626 INFO [train.py:715] (5/8) Epoch 0, batch 2600, loss[loss=0.1743, simple_loss=0.3487, pruned_loss=6.733, over 4707.00 frames.], tot_loss[loss=0.1743, simple_loss=0.3486, pruned_loss=6.657, over 971571.00 frames.], batch size: 15, lr: 2.83e-03
2022-05-03 12:16:25,711 INFO [train.py:715] (5/8) Epoch 0, batch 2650, loss[loss=0.1729, simple_loss=0.3458, pruned_loss=6.583, over 4810.00 frames.], tot_loss[loss=0.1731, simple_loss=0.3462, pruned_loss=6.652, over 971887.84 frames.], batch size: 13, lr: 2.82e-03
2022-05-03 12:17:08,087 INFO [train.py:715] (5/8) Epoch 0, batch 2700, loss[loss=0.1612, simple_loss=0.3225, pruned_loss=6.552, over 4991.00 frames.], tot_loss[loss=0.1728, simple_loss=0.3456, pruned_loss=6.648, over 972410.93 frames.], batch size: 14, lr: 2.81e-03
2022-05-03 12:17:48,878 INFO [train.py:715] (5/8) Epoch 0, batch 2750, loss[loss=0.1679, simple_loss=0.3358, pruned_loss=6.579, over 4927.00 frames.], tot_loss[loss=0.1722, simple_loss=0.3444, pruned_loss=6.647, over 972317.58 frames.], batch size: 39, lr: 2.81e-03
2022-05-03 12:18:29,713 INFO [train.py:715] (5/8) Epoch 0, batch 2800, loss[loss=0.1859, simple_loss=0.3718, pruned_loss=6.682, over 4951.00 frames.], tot_loss[loss=0.1712, simple_loss=0.3425, pruned_loss=6.645, over 971260.95 frames.], batch size: 21, lr: 2.80e-03
2022-05-03 12:19:10,266 INFO [train.py:715] (5/8) Epoch 0, batch 2850, loss[loss=0.1795, simple_loss=0.359, pruned_loss=6.694, over 4758.00 frames.], tot_loss[loss=0.1712, simple_loss=0.3425, pruned_loss=6.646, over 971575.66 frames.], batch size: 19, lr: 2.80e-03
2022-05-03 12:19:49,122 INFO [train.py:715] (5/8) Epoch 0, batch 2900, loss[loss=0.1788, simple_loss=0.3576, pruned_loss=6.709, over 4749.00 frames.], tot_loss[loss=0.1707, simple_loss=0.3413, pruned_loss=6.642, over 971274.62 frames.], batch size: 16, lr: 2.79e-03
2022-05-03 12:20:29,371 INFO [train.py:715] (5/8) Epoch 0, batch 2950, loss[loss=0.1616, simple_loss=0.3232, pruned_loss=6.715, over 4985.00 frames.], tot_loss[loss=0.171, simple_loss=0.3419, pruned_loss=6.645, over 971115.11 frames.], batch size: 28, lr: 2.78e-03
2022-05-03 12:21:11,360 INFO [train.py:715] (5/8) Epoch 0, batch 3000, loss[loss=0.8461, simple_loss=0.3666, pruned_loss=6.629, over 4777.00 frames.], tot_loss[loss=0.2063, simple_loss=0.3411, pruned_loss=6.647, over 971047.87 frames.], batch size: 17, lr: 2.78e-03
2022-05-03 12:21:11,361 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 12:21:21,130 INFO [train.py:742] (5/8) Epoch 0, validation: loss=2.223, simple_loss=0.2788, pruned_loss=2.083, over 914524.00 frames.
2022-05-03 12:22:02,161 INFO [train.py:715] (5/8) Epoch 0, batch 3050, loss[loss=0.204, simple_loss=0.2806, pruned_loss=0.637, over 4917.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3416, pruned_loss=5.403, over 971916.86 frames.], batch size: 19, lr: 2.77e-03
2022-05-03 12:22:41,570 INFO [train.py:715] (5/8) Epoch 0, batch 3100, loss[loss=0.1626, simple_loss=0.2724, pruned_loss=0.2641, over 4818.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3405, pruned_loss=4.317, over 971488.57 frames.], batch size: 13, lr: 2.77e-03
2022-05-03 12:23:22,424 INFO [train.py:715] (5/8) Epoch 0, batch 3150, loss[loss=0.2168, simple_loss=0.3711, pruned_loss=0.3121, over 4968.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3415, pruned_loss=3.43, over 971419.12 frames.], batch size: 35, lr: 2.76e-03
2022-05-03 12:24:03,662 INFO [train.py:715] (5/8) Epoch 0, batch 3200, loss[loss=0.1936, simple_loss=0.3393, pruned_loss=0.239, over 4919.00 frames.], tot_loss[loss=0.2125, simple_loss=0.341, pruned_loss=2.728, over 971206.82 frames.], batch size: 18, lr: 2.75e-03
2022-05-03 12:24:44,883 INFO [train.py:715] (5/8) Epoch 0, batch 3250, loss[loss=0.1866, simple_loss=0.334, pruned_loss=0.196, over 4875.00 frames.], tot_loss[loss=0.2079, simple_loss=0.3403, pruned_loss=2.172, over 971898.01 frames.], batch size: 16, lr: 2.75e-03
2022-05-03 12:25:24,112 INFO [train.py:715] (5/8) Epoch 0, batch 3300, loss[loss=0.1987, simple_loss=0.3503, pruned_loss=0.2354, over 4688.00 frames.], tot_loss[loss=0.2029, simple_loss=0.3377, pruned_loss=1.737, over 971650.36 frames.], batch size: 15, lr: 2.74e-03
2022-05-03 12:26:05,355 INFO [train.py:715] (5/8) Epoch 0, batch 3350, loss[loss=0.1472, simple_loss=0.2683, pruned_loss=0.1303, over 4927.00 frames.], tot_loss[loss=0.1991, simple_loss=0.3363, pruned_loss=1.397, over 971606.49 frames.], batch size: 23, lr: 2.73e-03
2022-05-03 12:26:46,192 INFO [train.py:715] (5/8) Epoch 0, batch 3400, loss[loss=0.1935, simple_loss=0.3453, pruned_loss=0.2079, over 4841.00 frames.], tot_loss[loss=0.1955, simple_loss=0.3344, pruned_loss=1.129, over 972044.86 frames.], batch size: 15, lr: 2.73e-03
2022-05-03 12:27:25,312 INFO [train.py:715] (5/8) Epoch 0, batch 3450, loss[loss=0.1983, simple_loss=0.3569, pruned_loss=0.198, over 4894.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3333, pruned_loss=0.9203, over 973116.58 frames.], batch size: 22, lr: 2.72e-03
2022-05-03 12:28:06,922 INFO [train.py:715] (5/8) Epoch 0, batch 3500, loss[loss=0.201, simple_loss=0.3556, pruned_loss=0.2319, over 4687.00 frames.], tot_loss[loss=0.1912, simple_loss=0.333, pruned_loss=0.7591, over 971724.63 frames.], batch size: 15, lr: 2.72e-03
2022-05-03 12:28:48,558 INFO [train.py:715] (5/8) Epoch 0, batch 3550, loss[loss=0.1753, simple_loss=0.3194, pruned_loss=0.1564, over 4700.00 frames.], tot_loss[loss=0.1895, simple_loss=0.3324, pruned_loss=0.632, over 971882.20 frames.], batch size: 15, lr: 2.71e-03
2022-05-03 12:29:29,802 INFO [train.py:715] (5/8) Epoch 0, batch 3600, loss[loss=0.1894, simple_loss=0.3428, pruned_loss=0.1799, over 4980.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3322, pruned_loss=0.5325, over 971994.19 frames.], batch size: 28, lr: 2.70e-03
2022-05-03 12:30:09,006 INFO [train.py:715] (5/8) Epoch 0, batch 3650, loss[loss=0.1782, simple_loss=0.322, pruned_loss=0.172, over 4937.00 frames.], tot_loss[loss=0.1865, simple_loss=0.3307, pruned_loss=0.4529, over 973142.86 frames.], batch size: 21, lr: 2.70e-03
2022-05-03 12:30:50,514 INFO [train.py:715] (5/8) Epoch 0, batch 3700, loss[loss=0.1586, simple_loss=0.2885, pruned_loss=0.1432, over 4913.00 frames.], tot_loss[loss=0.1853, simple_loss=0.3299, pruned_loss=0.3915, over 972964.64 frames.], batch size: 18, lr: 2.69e-03
2022-05-03 12:31:32,106 INFO [train.py:715] (5/8) Epoch 0, batch 3750, loss[loss=0.1786, simple_loss=0.3251, pruned_loss=0.1604, over 4966.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3283, pruned_loss=0.3423, over 972078.02 frames.], batch size: 24, lr: 2.68e-03
2022-05-03 12:32:11,315 INFO [train.py:715] (5/8) Epoch 0, batch 3800, loss[loss=0.1861, simple_loss=0.336, pruned_loss=0.1813, over 4973.00 frames.], tot_loss[loss=0.1825, simple_loss=0.327, pruned_loss=0.3039, over 972133.59 frames.], batch size: 14, lr: 2.68e-03
2022-05-03 12:33:05,632 INFO [train.py:715] (5/8) Epoch 0, batch 3850, loss[loss=0.1842, simple_loss=0.3321, pruned_loss=0.1816, over 4914.00 frames.], tot_loss[loss=0.1818, simple_loss=0.3266, pruned_loss=0.2737, over 972672.91 frames.], batch size: 19, lr: 2.67e-03
2022-05-03 12:33:46,700 INFO [train.py:715] (5/8) Epoch 0, batch 3900, loss[loss=0.1645, simple_loss=0.3011, pruned_loss=0.1401, over 4860.00 frames.], tot_loss[loss=0.181, simple_loss=0.3259, pruned_loss=0.2499, over 972452.30 frames.], batch size: 20, lr: 2.66e-03
2022-05-03 12:34:26,863 INFO [train.py:715] (5/8) Epoch 0, batch 3950, loss[loss=0.1962, simple_loss=0.3552, pruned_loss=0.1859, over 4775.00 frames.], tot_loss[loss=0.1807, simple_loss=0.3258, pruned_loss=0.232, over 971604.17 frames.], batch size: 18, lr: 2.66e-03
2022-05-03 12:35:06,668 INFO [train.py:715] (5/8) Epoch 0, batch 4000, loss[loss=0.173, simple_loss=0.3149, pruned_loss=0.1552, over 4884.00 frames.], tot_loss[loss=0.1797, simple_loss=0.3245, pruned_loss=0.216, over 972824.53 frames.], batch size: 22, lr: 2.65e-03
2022-05-03 12:35:47,600 INFO [train.py:715] (5/8) Epoch 0, batch 4050, loss[loss=0.1711, simple_loss=0.3132, pruned_loss=0.1451, over 4832.00 frames.], tot_loss[loss=0.179, simple_loss=0.3237, pruned_loss=0.2043, over 972870.01 frames.], batch size: 30, lr: 2.64e-03
2022-05-03 12:36:28,812 INFO [train.py:715] (5/8) Epoch 0, batch 4100, loss[loss=0.165, simple_loss=0.3008, pruned_loss=0.1456, over 4774.00 frames.], tot_loss[loss=0.1787, simple_loss=0.3235, pruned_loss=0.1953, over 972547.19 frames.], batch size: 12, lr: 2.64e-03
2022-05-03 12:37:07,958 INFO [train.py:715] (5/8) Epoch 0, batch 4150, loss[loss=0.1525, simple_loss=0.28, pruned_loss=0.1256, over 4984.00 frames.], tot_loss[loss=0.1777, simple_loss=0.3219, pruned_loss=0.1868, over 972365.90 frames.], batch size: 25, lr: 2.63e-03
2022-05-03 12:37:49,192 INFO [train.py:715] (5/8) Epoch 0, batch 4200, loss[loss=0.1948, simple_loss=0.3502, pruned_loss=0.1965, over 4978.00 frames.], tot_loss[loss=0.1778, simple_loss=0.3223, pruned_loss=0.1816, over 973056.20 frames.], batch size: 35, lr: 2.63e-03
2022-05-03 12:38:30,920 INFO [train.py:715] (5/8) Epoch 0, batch 4250, loss[loss=0.1864, simple_loss=0.337, pruned_loss=0.1791, over 4794.00 frames.], tot_loss[loss=0.1766, simple_loss=0.3206, pruned_loss=0.1753, over 973077.26 frames.], batch size: 14, lr: 2.62e-03
2022-05-03 12:39:11,499 INFO [train.py:715] (5/8) Epoch 0, batch 4300, loss[loss=0.148, simple_loss=0.276, pruned_loss=0.09995, over 4924.00 frames.], tot_loss[loss=0.1768, simple_loss=0.3211, pruned_loss=0.1717, over 973711.85 frames.], batch size: 17, lr: 2.61e-03
2022-05-03 12:39:51,576 INFO [train.py:715] (5/8) Epoch 0, batch 4350, loss[loss=0.1834, simple_loss=0.3326, pruned_loss=0.1707, over 4913.00 frames.], tot_loss[loss=0.1772, simple_loss=0.322, pruned_loss=0.1694, over 974144.23 frames.], batch size: 17, lr: 2.61e-03
2022-05-03 12:40:33,096 INFO [train.py:715] (5/8) Epoch 0, batch 4400, loss[loss=0.1668, simple_loss=0.3067, pruned_loss=0.1348, over 4976.00 frames.], tot_loss[loss=0.1759, simple_loss=0.32, pruned_loss=0.1652, over 973436.18 frames.], batch size: 14, lr: 2.60e-03
2022-05-03 12:41:14,315 INFO [train.py:715] (5/8) Epoch 0, batch 4450, loss[loss=0.1565, simple_loss=0.2878, pruned_loss=0.1257, over 4736.00 frames.], tot_loss[loss=0.1752, simple_loss=0.3189, pruned_loss=0.1617, over 972157.18 frames.], batch size: 12, lr: 2.59e-03
2022-05-03 12:41:53,450 INFO [train.py:715] (5/8) Epoch 0, batch 4500, loss[loss=0.1647, simple_loss=0.305, pruned_loss=0.1222, over 4913.00 frames.], tot_loss[loss=0.1748, simple_loss=0.3184, pruned_loss=0.1597, over 972184.44 frames.], batch size: 18, lr: 2.59e-03
2022-05-03 12:42:34,821 INFO [train.py:715] (5/8) Epoch 0, batch 4550, loss[loss=0.193, simple_loss=0.3462, pruned_loss=0.199, over 4978.00 frames.], tot_loss[loss=0.174, simple_loss=0.317, pruned_loss=0.1577, over 971942.74 frames.], batch size: 40, lr: 2.58e-03
2022-05-03 12:43:16,371 INFO [train.py:715] (5/8) Epoch 0, batch 4600, loss[loss=0.2066, simple_loss=0.373, pruned_loss=0.2009, over 4929.00 frames.], tot_loss[loss=0.1741, simple_loss=0.3173, pruned_loss=0.1563, over 972981.61 frames.], batch size: 39, lr: 2.57e-03
2022-05-03 12:43:56,540 INFO [train.py:715] (5/8) Epoch 0, batch 4650, loss[loss=0.188, simple_loss=0.3401, pruned_loss=0.1798, over 4925.00 frames.], tot_loss[loss=0.1728, simple_loss=0.3153, pruned_loss=0.1534, over 972644.01 frames.], batch size: 18, lr: 2.57e-03
2022-05-03 12:44:36,477 INFO [train.py:715] (5/8) Epoch 0, batch 4700, loss[loss=0.146, simple_loss=0.2689, pruned_loss=0.1156, over 4800.00 frames.], tot_loss[loss=0.1724, simple_loss=0.3147, pruned_loss=0.1517, over 972069.33 frames.], batch size: 12, lr: 2.56e-03
2022-05-03 12:45:17,611 INFO [train.py:715] (5/8) Epoch 0, batch 4750, loss[loss=0.1567, simple_loss=0.2869, pruned_loss=0.1325, over 4947.00 frames.], tot_loss[loss=0.1723, simple_loss=0.3146, pruned_loss=0.1509, over 972097.50 frames.], batch size: 29, lr: 2.55e-03
2022-05-03 12:45:58,876 INFO [train.py:715] (5/8) Epoch 0, batch 4800, loss[loss=0.1895, simple_loss=0.3411, pruned_loss=0.1899, over 4789.00 frames.], tot_loss[loss=0.1722, simple_loss=0.3145, pruned_loss=0.1506, over 972475.47 frames.], batch size: 17, lr: 2.55e-03
2022-05-03 12:46:38,838 INFO [train.py:715] (5/8) Epoch 0, batch 4850, loss[loss=0.1738, simple_loss=0.3164, pruned_loss=0.1559, over 4927.00 frames.], tot_loss[loss=0.1707, simple_loss=0.312, pruned_loss=0.1474, over 972635.63 frames.], batch size: 18, lr: 2.54e-03
2022-05-03 12:47:19,643 INFO [train.py:715] (5/8) Epoch 0, batch 4900, loss[loss=0.168, simple_loss=0.3093, pruned_loss=0.1333, over 4983.00 frames.], tot_loss[loss=0.171, simple_loss=0.3126, pruned_loss=0.1472, over 973033.50 frames.], batch size: 28, lr: 2.54e-03
2022-05-03 12:48:01,144 INFO [train.py:715] (5/8) Epoch 0, batch 4950, loss[loss=0.1721, simple_loss=0.3155, pruned_loss=0.1436, over 4831.00 frames.], tot_loss[loss=0.1715, simple_loss=0.3134, pruned_loss=0.1477, over 973242.45 frames.], batch size: 26, lr: 2.53e-03
2022-05-03 12:48:41,425 INFO [train.py:715] (5/8) Epoch 0, batch 5000, loss[loss=0.1697, simple_loss=0.3114, pruned_loss=0.1398, over 4874.00 frames.], tot_loss[loss=0.171, simple_loss=0.313, pruned_loss=0.146, over 972703.64 frames.], batch size: 38, lr: 2.52e-03
2022-05-03 12:49:22,158 INFO [train.py:715] (5/8) Epoch 0, batch 5050, loss[loss=0.1685, simple_loss=0.3092, pruned_loss=0.1391, over 4791.00 frames.], tot_loss[loss=0.1709, simple_loss=0.3127, pruned_loss=0.1455, over 973269.64 frames.], batch size: 18, lr: 2.52e-03
2022-05-03 12:50:05,004 INFO [train.py:715] (5/8) Epoch 0, batch 5100, loss[loss=0.1759, simple_loss=0.3215, pruned_loss=0.1517, over 4863.00 frames.], tot_loss[loss=0.1704, simple_loss=0.3119, pruned_loss=0.1449, over 972943.20 frames.], batch size: 32, lr: 2.51e-03
2022-05-03 12:50:48,213 INFO [train.py:715] (5/8) Epoch 0, batch 5150, loss[loss=0.1861, simple_loss=0.339, pruned_loss=0.1662, over 4738.00 frames.], tot_loss[loss=0.1705, simple_loss=0.312, pruned_loss=0.145, over 972416.79 frames.], batch size: 16, lr: 2.50e-03
2022-05-03 12:51:28,078 INFO [train.py:715] (5/8) Epoch 0, batch 5200, loss[loss=0.1991, simple_loss=0.3644, pruned_loss=0.1693, over 4880.00 frames.], tot_loss[loss=0.1703, simple_loss=0.3118, pruned_loss=0.1442, over 972224.64 frames.], batch size: 20, lr: 2.50e-03
2022-05-03 12:52:08,700 INFO [train.py:715] (5/8) Epoch 0, batch 5250, loss[loss=0.1696, simple_loss=0.3087, pruned_loss=0.1528, over 4782.00 frames.], tot_loss[loss=0.1692, simple_loss=0.3101, pruned_loss=0.1419, over 972267.68 frames.], batch size: 14, lr: 2.49e-03
2022-05-03 12:52:49,813 INFO [train.py:715] (5/8) Epoch 0, batch 5300, loss[loss=0.1597, simple_loss=0.2948, pruned_loss=0.1226, over 4833.00 frames.], tot_loss[loss=0.169, simple_loss=0.3097, pruned_loss=0.1415, over 972921.47 frames.], batch size: 15, lr: 2.49e-03
2022-05-03 12:53:30,342 INFO [train.py:715] (5/8) Epoch 0, batch 5350, loss[loss=0.1709, simple_loss=0.3158, pruned_loss=0.1304, over 4921.00 frames.], tot_loss[loss=0.1689, simple_loss=0.3095, pruned_loss=0.141, over 972708.40 frames.], batch size: 23, lr: 2.48e-03
2022-05-03 12:54:10,019 INFO [train.py:715] (5/8) Epoch 0, batch 5400, loss[loss=0.1651, simple_loss=0.3043, pruned_loss=0.1301, over 4926.00 frames.], tot_loss[loss=0.1685, simple_loss=0.309, pruned_loss=0.1399, over 973690.97 frames.], batch size: 23, lr: 2.47e-03
2022-05-03 12:54:50,454 INFO [train.py:715] (5/8) Epoch 0, batch 5450, loss[loss=0.1771, simple_loss=0.3253, pruned_loss=0.1441, over 4916.00 frames.], tot_loss[loss=0.1681, simple_loss=0.3084, pruned_loss=0.1395, over 973550.35 frames.], batch size: 17, lr: 2.47e-03
2022-05-03 12:55:31,409 INFO [train.py:715] (5/8) Epoch 0, batch 5500, loss[loss=0.1884, simple_loss=0.3418, pruned_loss=0.1749, over 4918.00 frames.], tot_loss[loss=0.1676, simple_loss=0.3076, pruned_loss=0.138, over 973598.30 frames.], batch size: 17, lr: 2.46e-03
2022-05-03 12:56:11,128 INFO [train.py:715] (5/8) Epoch 0, batch 5550, loss[loss=0.1782, simple_loss=0.3261, pruned_loss=0.1518, over 4931.00 frames.], tot_loss[loss=0.1681, simple_loss=0.3084, pruned_loss=0.1385, over 973624.66 frames.], batch size: 18, lr: 2.45e-03
2022-05-03 12:56:51,161 INFO [train.py:715] (5/8) Epoch 0, batch 5600, loss[loss=0.1769, simple_loss=0.323, pruned_loss=0.1544, over 4764.00 frames.], tot_loss[loss=0.1678, simple_loss=0.3082, pruned_loss=0.1376, over 973934.78 frames.], batch size: 17, lr: 2.45e-03
2022-05-03 12:57:32,363 INFO [train.py:715] (5/8) Epoch 0, batch 5650, loss[loss=0.1847, simple_loss=0.3354, pruned_loss=0.1702, over 4793.00 frames.], tot_loss[loss=0.1676, simple_loss=0.3078, pruned_loss=0.1369, over 974095.50 frames.], batch size: 21, lr: 2.44e-03
2022-05-03 12:58:12,922 INFO [train.py:715] (5/8) Epoch 0, batch 5700, loss[loss=0.1715, simple_loss=0.3153, pruned_loss=0.1386, over 4950.00 frames.], tot_loss[loss=0.1663, simple_loss=0.3055, pruned_loss=0.1351, over 974164.95 frames.], batch size: 21, lr: 2.44e-03
2022-05-03 12:58:52,125 INFO [train.py:715] (5/8) Epoch 0, batch 5750, loss[loss=0.1532, simple_loss=0.2822, pruned_loss=0.1207, over 4876.00 frames.], tot_loss[loss=0.1667, simple_loss=0.3063, pruned_loss=0.1358, over 973851.70 frames.], batch size: 16, lr: 2.43e-03
2022-05-03 12:59:33,130 INFO [train.py:715] (5/8) Epoch 0, batch 5800, loss[loss=0.1561, simple_loss=0.2866, pruned_loss=0.128, over 4856.00 frames.], tot_loss[loss=0.1658, simple_loss=0.3047, pruned_loss=0.1343, over 972961.67 frames.], batch size: 20, lr: 2.42e-03
2022-05-03 13:00:14,322 INFO [train.py:715] (5/8) Epoch 0, batch 5850, loss[loss=0.1566, simple_loss=0.2896, pruned_loss=0.1185, over 4943.00 frames.], tot_loss[loss=0.1668, simple_loss=0.3064, pruned_loss=0.1358, over 972532.92 frames.], batch size: 35, lr: 2.42e-03
2022-05-03 13:00:54,233 INFO [train.py:715] (5/8) Epoch 0, batch 5900, loss[loss=0.1894, simple_loss=0.3481, pruned_loss=0.1531, over 4934.00 frames.], tot_loss[loss=0.1666, simple_loss=0.3061, pruned_loss=0.135, over 972813.74 frames.], batch size: 21, lr: 2.41e-03
2022-05-03 13:01:33,982 INFO [train.py:715] (5/8) Epoch 0, batch 5950, loss[loss=0.1555, simple_loss=0.2868, pruned_loss=0.1211, over 4771.00 frames.], tot_loss[loss=0.1669, simple_loss=0.3066, pruned_loss=0.1363, over 971925.54 frames.], batch size: 14, lr: 2.41e-03
2022-05-03 13:02:14,778 INFO [train.py:715] (5/8) Epoch 0, batch 6000, loss[loss=0.3025, simple_loss=0.315, pruned_loss=0.145, over 4882.00 frames.], tot_loss[loss=0.1675, simple_loss=0.3055, pruned_loss=0.1344, over 972755.58 frames.], batch size: 22, lr: 2.40e-03
2022-05-03 13:02:14,779 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 13:02:25,809 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1779, simple_loss=0.2457, pruned_loss=0.05502, over 914524.00 frames.
2022-05-03 13:03:07,311 INFO [train.py:715] (5/8) Epoch 0, batch 6050, loss[loss=0.3147, simple_loss=0.321, pruned_loss=0.1542, over 4771.00 frames.], tot_loss[loss=0.1988, simple_loss=0.308, pruned_loss=0.1382, over 970706.56 frames.], batch size: 17, lr: 2.39e-03
2022-05-03 13:03:47,840 INFO [train.py:715] (5/8) Epoch 0, batch 6100, loss[loss=0.276, simple_loss=0.2982, pruned_loss=0.1269, over 4742.00 frames.], tot_loss[loss=0.2183, simple_loss=0.3074, pruned_loss=0.1372, over 971125.73 frames.], batch size: 16, lr: 2.39e-03
2022-05-03 13:04:27,377 INFO [train.py:715] (5/8) Epoch 0, batch 6150, loss[loss=0.2786, simple_loss=0.2949, pruned_loss=0.1311, over 4979.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3084, pruned_loss=0.1368, over 971542.86 frames.], batch size: 25, lr: 2.38e-03
2022-05-03 13:05:08,108 INFO [train.py:715] (5/8) Epoch 0, batch 6200, loss[loss=0.232, simple_loss=0.2698, pruned_loss=0.09711, over 4795.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3089, pruned_loss=0.1356, over 971148.77 frames.], batch size: 17, lr: 2.38e-03
2022-05-03 13:05:48,913 INFO [train.py:715] (5/8) Epoch 0, batch 6250, loss[loss=0.2479, simple_loss=0.2818, pruned_loss=0.107, over 4788.00 frames.], tot_loss[loss=0.2537, simple_loss=0.3082, pruned_loss=0.1338, over 972043.61 frames.], batch size: 14, lr: 2.37e-03
2022-05-03 13:06:29,112 INFO [train.py:715] (5/8) Epoch 0, batch 6300, loss[loss=0.3157, simple_loss=0.3302, pruned_loss=0.1506, over 4818.00 frames.], tot_loss[loss=0.2592, simple_loss=0.3073, pruned_loss=0.1322, over 972362.08 frames.], batch size: 15, lr: 2.37e-03
2022-05-03 13:07:09,796 INFO [train.py:715] (5/8) Epoch 0, batch 6350, loss[loss=0.2606, simple_loss=0.2961, pruned_loss=0.1126, over 4777.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3087, pruned_loss=0.1328, over 972021.47 frames.], batch size: 14, lr: 2.36e-03
2022-05-03 13:07:50,719 INFO [train.py:715] (5/8) Epoch 0, batch 6400, loss[loss=0.2642, simple_loss=0.3091, pruned_loss=0.1097, over 4976.00 frames.], tot_loss[loss=0.269, simple_loss=0.3078, pruned_loss=0.1312, over 971580.13 frames.], batch size: 24, lr: 2.35e-03
2022-05-03 13:08:30,733 INFO [train.py:715] (5/8) Epoch 0, batch 6450, loss[loss=0.1974, simple_loss=0.2505, pruned_loss=0.07214, over 4964.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3067, pruned_loss=0.1295, over 971680.88 frames.], batch size: 24, lr: 2.35e-03
2022-05-03 13:09:10,065 INFO [train.py:715] (5/8) Epoch 0, batch 6500, loss[loss=0.3468, simple_loss=0.3493, pruned_loss=0.1722, over 4981.00 frames.], tot_loss[loss=0.2744, simple_loss=0.3082, pruned_loss=0.1301, over 971805.71 frames.], batch size: 35, lr: 2.34e-03
2022-05-03 13:09:50,936 INFO [train.py:715] (5/8) Epoch 0, batch 6550, loss[loss=0.2776, simple_loss=0.305, pruned_loss=0.1251, over 4836.00 frames.], tot_loss[loss=0.2771, simple_loss=0.3088, pruned_loss=0.1303, over 971538.43 frames.], batch size: 15, lr: 2.34e-03
2022-05-03 13:10:31,735 INFO [train.py:715] (5/8) Epoch 0, batch 6600, loss[loss=0.3048, simple_loss=0.33, pruned_loss=0.1398, over 4815.00 frames.], tot_loss[loss=0.2774, simple_loss=0.3081, pruned_loss=0.1293, over 971844.03 frames.], batch size: 27, lr: 2.33e-03
2022-05-03 13:11:11,211 INFO [train.py:715] (5/8) Epoch 0, batch 6650, loss[loss=0.2139, simple_loss=0.2661, pruned_loss=0.08082, over 4970.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3083, pruned_loss=0.1286, over 971912.69 frames.], batch size: 24, lr: 2.33e-03
2022-05-03 13:11:51,652 INFO [train.py:715] (5/8) Epoch 0, batch 6700, loss[loss=0.2309, simple_loss=0.2647, pruned_loss=0.09853, over 4758.00 frames.], tot_loss[loss=0.2789, simple_loss=0.3082, pruned_loss=0.1284, over 972343.01 frames.], batch size: 12, lr: 2.32e-03
2022-05-03 13:12:32,421 INFO [train.py:715] (5/8) Epoch 0, batch 6750, loss[loss=0.2947, simple_loss=0.3272, pruned_loss=0.1311, over 4839.00 frames.], tot_loss[loss=0.2789, simple_loss=0.3083, pruned_loss=0.1276, over 972705.91 frames.], batch size: 15, lr: 2.31e-03
2022-05-03 13:13:12,498 INFO [train.py:715] (5/8) Epoch 0, batch 6800, loss[loss=0.2359, simple_loss=0.2718, pruned_loss=0.1001, over 4887.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3072, pruned_loss=0.1263, over 972959.76 frames.], batch size: 16, lr: 2.31e-03
2022-05-03 13:13:52,213 INFO [train.py:715] (5/8) Epoch 0, batch 6850, loss[loss=0.2368, simple_loss=0.2814, pruned_loss=0.0961, over 4831.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3069, pruned_loss=0.1258, over 973052.15 frames.], batch size: 13, lr: 2.30e-03
2022-05-03 13:14:32,490 INFO [train.py:715] (5/8) Epoch 0, batch 6900, loss[loss=0.345, simple_loss=0.3555, pruned_loss=0.1673, over 4928.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3069, pruned_loss=0.126, over 972402.36 frames.], batch size: 39, lr: 2.30e-03
2022-05-03 13:15:12,914 INFO [train.py:715] (5/8) Epoch 0, batch 6950, loss[loss=0.2173, simple_loss=0.261, pruned_loss=0.0868, over 4827.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3068, pruned_loss=0.1254, over 971134.36 frames.], batch size: 13, lr: 2.29e-03
2022-05-03 13:15:53,033 INFO [train.py:715] (5/8) Epoch 0, batch 7000, loss[loss=0.2717, simple_loss=0.303, pruned_loss=0.1202, over 4848.00 frames.], tot_loss[loss=0.2776, simple_loss=0.307, pruned_loss=0.1249, over 971455.59 frames.], batch size: 32, lr: 2.29e-03
2022-05-03 13:16:33,739 INFO [train.py:715] (5/8) Epoch 0, batch 7050, loss[loss=0.27, simple_loss=0.3031, pruned_loss=0.1185, over 4751.00 frames.], tot_loss[loss=0.2767, simple_loss=0.3064, pruned_loss=0.1241, over 970322.68 frames.], batch size: 19, lr: 2.28e-03
2022-05-03 13:17:14,924 INFO [train.py:715] (5/8) Epoch 0, batch 7100, loss[loss=0.2809, simple_loss=0.3164, pruned_loss=0.1227, over 4984.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3074, pruned_loss=0.1249, over 971186.62 frames.], batch size: 25, lr: 2.28e-03
2022-05-03 13:17:55,872 INFO [train.py:715] (5/8) Epoch 0, batch 7150, loss[loss=0.2473, simple_loss=0.2779, pruned_loss=0.1083, over 4758.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3061, pruned_loss=0.1231, over 970843.02 frames.], batch size: 14, lr: 2.27e-03
2022-05-03 13:18:35,508 INFO [train.py:715] (5/8) Epoch 0, batch 7200, loss[loss=0.3186, simple_loss=0.3354, pruned_loss=0.1509, over 4985.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3062, pruned_loss=0.1227, over 970856.79 frames.], batch size: 39, lr: 2.27e-03
2022-05-03 13:19:16,091 INFO [train.py:715] (5/8) Epoch 0, batch 7250, loss[loss=0.2771, simple_loss=0.3106, pruned_loss=0.1218, over 4965.00 frames.], tot_loss[loss=0.2743, simple_loss=0.3053, pruned_loss=0.1219, over 971574.92 frames.], batch size: 24, lr: 2.26e-03
2022-05-03 13:19:55,969 INFO [train.py:715] (5/8) Epoch 0, batch 7300, loss[loss=0.2823, simple_loss=0.3046, pruned_loss=0.13, over 4816.00 frames.], tot_loss[loss=0.2736, simple_loss=0.305, pruned_loss=0.1213, over 972631.82 frames.], batch size: 13, lr: 2.26e-03
2022-05-03 13:20:36,062 INFO [train.py:715] (5/8) Epoch 0, batch 7350, loss[loss=0.2636, simple_loss=0.3072, pruned_loss=0.1101, over 4977.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3037, pruned_loss=0.1198, over 972367.18 frames.], batch size: 15, lr: 2.25e-03
2022-05-03 13:21:16,439 INFO [train.py:715] (5/8) Epoch 0, batch 7400, loss[loss=0.3088, simple_loss=0.3242, pruned_loss=0.1467, over 4952.00 frames.], tot_loss[loss=0.2732, simple_loss=0.3048, pruned_loss=0.1208, over 972033.85 frames.], batch size: 21, lr: 2.24e-03
2022-05-03 13:21:57,043 INFO [train.py:715] (5/8) Epoch 0, batch 7450, loss[loss=0.2746, simple_loss=0.3084, pruned_loss=0.1204, over 4979.00 frames.], tot_loss[loss=0.274, simple_loss=0.3057, pruned_loss=0.1212, over 972215.21 frames.], batch size: 28, lr: 2.24e-03
2022-05-03 13:22:36,843 INFO [train.py:715] (5/8) Epoch 0, batch 7500, loss[loss=0.2662, simple_loss=0.2911, pruned_loss=0.1207, over 4873.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3046, pruned_loss=0.1198, over 972515.41 frames.], batch size: 32, lr: 2.23e-03
2022-05-03 13:23:16,572 INFO [train.py:715] (5/8) Epoch 0, batch 7550, loss[loss=0.2758, simple_loss=0.3132, pruned_loss=0.1192, over 4699.00 frames.], tot_loss[loss=0.2734, simple_loss=0.3058, pruned_loss=0.1205, over 972447.91 frames.], batch size: 15, lr: 2.23e-03
2022-05-03 13:23:57,046 INFO [train.py:715] (5/8) Epoch 0, batch 7600, loss[loss=0.2672, simple_loss=0.3089, pruned_loss=0.1128, over 4960.00 frames.], tot_loss[loss=0.271, simple_loss=0.3041, pruned_loss=0.119, over 972186.72 frames.], batch size: 15, lr: 2.22e-03
2022-05-03 13:24:37,500 INFO [train.py:715] (5/8) Epoch 0, batch 7650, loss[loss=0.2186, simple_loss=0.2617, pruned_loss=0.08772, over 4978.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3036, pruned_loss=0.1184, over 972121.49 frames.], batch size: 28, lr: 2.22e-03
2022-05-03 13:25:16,994 INFO [train.py:715] (5/8) Epoch 0, batch 7700, loss[loss=0.2413, simple_loss=0.2836, pruned_loss=0.09953, over 4821.00 frames.], tot_loss[loss=0.2709, simple_loss=0.3042, pruned_loss=0.1188, over 972265.85 frames.], batch size: 27, lr: 2.21e-03
2022-05-03 13:25:57,323 INFO [train.py:715] (5/8) Epoch 0, batch 7750, loss[loss=0.2829, simple_loss=0.3177, pruned_loss=0.124, over 4855.00 frames.], tot_loss[loss=0.2684, simple_loss=0.3022, pruned_loss=0.1173, over 972355.49 frames.], batch size: 30, lr: 2.21e-03
2022-05-03 13:26:38,374 INFO [train.py:715] (5/8) Epoch 0, batch 7800, loss[loss=0.2329, simple_loss=0.2887, pruned_loss=0.08852, over 4970.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3024, pruned_loss=0.1169, over 973399.50 frames.], batch size: 28, lr: 2.20e-03
2022-05-03 13:27:18,718 INFO [train.py:715] (5/8) Epoch 0, batch 7850, loss[loss=0.2514, simple_loss=0.2826, pruned_loss=0.1101, over 4795.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3027, pruned_loss=0.1168, over 973873.62 frames.], batch size: 12, lr: 2.20e-03
2022-05-03 13:27:58,879 INFO [train.py:715] (5/8) Epoch 0, batch 7900, loss[loss=0.2196, simple_loss=0.2579, pruned_loss=0.09069, over 4978.00 frames.], tot_loss[loss=0.2692, simple_loss=0.3037, pruned_loss=0.1173, over 973358.08 frames.], batch size: 14, lr: 2.19e-03
2022-05-03 13:28:39,526 INFO [train.py:715] (5/8) Epoch 0, batch 7950, loss[loss=0.2849, simple_loss=0.3159, pruned_loss=0.1269, over 4815.00 frames.], tot_loss[loss=0.2686, simple_loss=0.303, pruned_loss=0.1171, over 973468.51 frames.], batch size: 13, lr: 2.19e-03
2022-05-03 13:29:22,243 INFO [train.py:715] (5/8) Epoch 0, batch 8000, loss[loss=0.2241, simple_loss=0.2771, pruned_loss=0.08553, over 4938.00 frames.], tot_loss[loss=0.2681, simple_loss=0.3028, pruned_loss=0.1167, over 973147.24 frames.], batch size: 29, lr: 2.18e-03
2022-05-03 13:30:02,106 INFO [train.py:715] (5/8) Epoch 0, batch 8050, loss[loss=0.3434, simple_loss=0.3597, pruned_loss=0.1635, over 4938.00 frames.], tot_loss[loss=0.2687, simple_loss=0.3037, pruned_loss=0.1168, over 973798.21 frames.], batch size: 29, lr: 2.18e-03
2022-05-03 13:30:41,975 INFO [train.py:715] (5/8) Epoch 0, batch 8100, loss[loss=0.3096, simple_loss=0.3214, pruned_loss=0.149, over 4646.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3045, pruned_loss=0.1173, over 973819.93 frames.], batch size: 13, lr: 2.17e-03
2022-05-03 13:31:22,996 INFO [train.py:715] (5/8) Epoch 0, batch 8150, loss[loss=0.2347, simple_loss=0.2776, pruned_loss=0.09595, over 4840.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3033, pruned_loss=0.116, over 973790.69 frames.], batch size: 13, lr: 2.17e-03
2022-05-03 13:32:02,629 INFO [train.py:715] (5/8) Epoch 0, batch 8200, loss[loss=0.2306, simple_loss=0.2795, pruned_loss=0.09082, over 4844.00 frames.], tot_loss[loss=0.2683, simple_loss=0.304, pruned_loss=0.1163, over 973757.80 frames.], batch size: 20, lr: 2.16e-03
2022-05-03 13:32:42,151 INFO [train.py:715] (5/8) Epoch 0, batch 8250, loss[loss=0.2994, simple_loss=0.3268, pruned_loss=0.136, over 4805.00 frames.], tot_loss[loss=0.2673, simple_loss=0.303, pruned_loss=0.1158, over 973224.43 frames.], batch size: 21, lr: 2.16e-03
2022-05-03 13:33:23,000 INFO [train.py:715] (5/8) Epoch 0, batch 8300, loss[loss=0.2276, simple_loss=0.2839, pruned_loss=0.08566, over 4839.00 frames.], tot_loss[loss=0.266, simple_loss=0.3023, pruned_loss=0.1149, over 973063.48 frames.], batch size: 20, lr: 2.15e-03
2022-05-03 13:34:03,431 INFO [train.py:715] (5/8) Epoch 0, batch 8350, loss[loss=0.2436, simple_loss=0.2979, pruned_loss=0.09462, over 4899.00 frames.], tot_loss[loss=0.266, simple_loss=0.3025, pruned_loss=0.1147, over 973516.78 frames.], batch size: 19, lr: 2.15e-03
2022-05-03 13:34:43,094 INFO [train.py:715] (5/8) Epoch 0, batch 8400, loss[loss=0.2187, simple_loss=0.2707, pruned_loss=0.08333, over 4645.00 frames.], tot_loss[loss=0.2645, simple_loss=0.302, pruned_loss=0.1136, over 973655.13 frames.], batch size: 13, lr: 2.15e-03
2022-05-03 13:35:23,382 INFO [train.py:715] (5/8) Epoch 0, batch 8450, loss[loss=0.2294, simple_loss=0.273, pruned_loss=0.09294, over 4972.00 frames.], tot_loss[loss=0.2638, simple_loss=0.3011, pruned_loss=0.1133, over 973794.10 frames.], batch size: 14, lr: 2.14e-03
2022-05-03 13:36:04,642 INFO [train.py:715] (5/8) Epoch 0, batch 8500, loss[loss=0.2333, simple_loss=0.2746, pruned_loss=0.09597, over 4829.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3001, pruned_loss=0.1124, over 973602.90 frames.], batch size: 15, lr: 2.14e-03
2022-05-03 13:36:45,703 INFO [train.py:715] (5/8) Epoch 0, batch 8550, loss[loss=0.2666, simple_loss=0.2992, pruned_loss=0.117, over 4928.00 frames.], tot_loss[loss=0.264, simple_loss=0.3011, pruned_loss=0.1134, over 973864.21 frames.], batch size: 23, lr: 2.13e-03
2022-05-03 13:37:25,356 INFO [train.py:715] (5/8) Epoch 0, batch 8600, loss[loss=0.2319, simple_loss=0.2773, pruned_loss=0.09322, over 4982.00 frames.], tot_loss[loss=0.262, simple_loss=0.2998, pruned_loss=0.1122, over 974462.66 frames.], batch size: 28, lr: 2.13e-03
2022-05-03 13:38:06,736 INFO [train.py:715] (5/8) Epoch 0, batch 8650, loss[loss=0.2406, simple_loss=0.2852, pruned_loss=0.09796, over 4877.00 frames.], tot_loss[loss=0.2606, simple_loss=0.2987, pruned_loss=0.1112, over 973569.48 frames.], batch size: 20, lr: 2.12e-03
2022-05-03 13:38:47,678 INFO [train.py:715] (5/8) Epoch 0, batch 8700, loss[loss=0.2282, simple_loss=0.2751, pruned_loss=0.09069, over 4810.00 frames.], tot_loss[loss=0.2619, simple_loss=0.2996, pruned_loss=0.1121, over 973056.23 frames.], batch size: 21, lr: 2.12e-03
2022-05-03 13:39:27,762 INFO [train.py:715] (5/8) Epoch 0, batch 8750, loss[loss=0.2395, simple_loss=0.2806, pruned_loss=0.09917, over 4798.00 frames.], tot_loss[loss=0.2619, simple_loss=0.2996, pruned_loss=0.1121, over 972185.11 frames.], batch size: 24, lr: 2.11e-03
2022-05-03 13:40:08,239 INFO [train.py:715] (5/8) Epoch 0, batch 8800, loss[loss=0.2683, simple_loss=0.2921, pruned_loss=0.1222, over 4851.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3002, pruned_loss=0.1123, over 971749.26 frames.], batch size: 32, lr: 2.11e-03
2022-05-03 13:40:48,808 INFO [train.py:715] (5/8) Epoch 0, batch 8850, loss[loss=0.3505, simple_loss=0.3809, pruned_loss=0.16, over 4806.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3007, pruned_loss=0.1125, over 971759.05 frames.], batch size: 24, lr: 2.10e-03
2022-05-03 13:41:29,539 INFO [train.py:715] (5/8) Epoch 0, batch 8900, loss[loss=0.2488, simple_loss=0.2984, pruned_loss=0.09959, over 4865.00 frames.], tot_loss[loss=0.2606, simple_loss=0.299, pruned_loss=0.1111, over 971992.75 frames.], batch size: 16, lr: 2.10e-03
2022-05-03 13:42:09,375 INFO [train.py:715] (5/8) Epoch 0, batch 8950, loss[loss=0.2288, simple_loss=0.2691, pruned_loss=0.09426, over 4956.00 frames.], tot_loss[loss=0.2594, simple_loss=0.2979, pruned_loss=0.1104, over 971690.00 frames.], batch size: 21, lr: 2.10e-03
2022-05-03 13:42:49,917 INFO [train.py:715] (5/8) Epoch 0, batch 9000, loss[loss=0.2419, simple_loss=0.2881, pruned_loss=0.09786, over 4815.00 frames.], tot_loss[loss=0.2593, simple_loss=0.2981, pruned_loss=0.1103, over 971941.47 frames.], batch size: 15, lr: 2.09e-03
2022-05-03 13:42:49,918 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 13:43:03,385 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1592, simple_loss=0.2426, pruned_loss=0.03794, over 914524.00 frames.
2022-05-03 13:43:44,295 INFO [train.py:715] (5/8) Epoch 0, batch 9050, loss[loss=0.2192, simple_loss=0.2618, pruned_loss=0.08831, over 4968.00 frames.], tot_loss[loss=0.2591, simple_loss=0.2978, pruned_loss=0.1102, over 971845.50 frames.], batch size: 24, lr: 2.09e-03
2022-05-03 13:44:24,662 INFO [train.py:715] (5/8) Epoch 0, batch 9100, loss[loss=0.2869, simple_loss=0.3081, pruned_loss=0.1328, over 4787.00 frames.], tot_loss[loss=0.2585, simple_loss=0.2976, pruned_loss=0.1097, over 971602.66 frames.], batch size: 17, lr: 2.08e-03
2022-05-03 13:45:04,786 INFO [train.py:715] (5/8) Epoch 0, batch 9150, loss[loss=0.2701, simple_loss=0.3129, pruned_loss=0.1136, over 4949.00 frames.], tot_loss[loss=0.2575, simple_loss=0.2973, pruned_loss=0.1089, over 972091.43 frames.], batch size: 39, lr: 2.08e-03
2022-05-03 13:45:44,986 INFO [train.py:715] (5/8) Epoch 0, batch 9200, loss[loss=0.2555, simple_loss=0.2977, pruned_loss=0.1067, over 4831.00 frames.], tot_loss[loss=0.2574, simple_loss=0.2972, pruned_loss=0.1088, over 971137.40 frames.], batch size: 15, lr: 2.07e-03
2022-05-03 13:46:26,073 INFO [train.py:715] (5/8) Epoch 0, batch 9250, loss[loss=0.239, simple_loss=0.2756, pruned_loss=0.1013, over 4985.00 frames.], tot_loss[loss=0.257, simple_loss=0.2968, pruned_loss=0.1087, over 971502.79 frames.], batch size: 27, lr: 2.07e-03
2022-05-03 13:47:06,384 INFO [train.py:715] (5/8) Epoch 0, batch 9300, loss[loss=0.2359, simple_loss=0.2937, pruned_loss=0.08909, over 4810.00 frames.], tot_loss[loss=0.258, simple_loss=0.2978, pruned_loss=0.1092, over 971080.95 frames.], batch size: 25, lr: 2.06e-03
2022-05-03 13:47:45,667 INFO [train.py:715] (5/8) Epoch 0, batch 9350, loss[loss=0.2772, simple_loss=0.3102, pruned_loss=0.1221, over 4827.00 frames.], tot_loss[loss=0.2575, simple_loss=0.2974, pruned_loss=0.1088, over 971259.61 frames.], batch size: 15, lr: 2.06e-03
2022-05-03 13:48:27,107 INFO [train.py:715] (5/8) Epoch 0, batch 9400, loss[loss=0.2736, simple_loss=0.3093, pruned_loss=0.119, over 4913.00 frames.], tot_loss[loss=0.2579, simple_loss=0.2975, pruned_loss=0.1091, over 971542.97 frames.], batch size: 17, lr: 2.06e-03
2022-05-03 13:49:07,597 INFO [train.py:715] (5/8) Epoch 0, batch 9450, loss[loss=0.2117, simple_loss=0.2709, pruned_loss=0.07628, over 4768.00 frames.], tot_loss[loss=0.2558, simple_loss=0.2963, pruned_loss=0.1077, over 970401.74 frames.], batch size: 18, lr: 2.05e-03
2022-05-03 13:49:47,926 INFO [train.py:715] (5/8) Epoch 0, batch 9500, loss[loss=0.2282, simple_loss=0.282, pruned_loss=0.08713, over 4829.00 frames.], tot_loss[loss=0.2548, simple_loss=0.2956, pruned_loss=0.107, over 970992.73 frames.], batch size: 26, lr: 2.05e-03
2022-05-03 13:50:28,015 INFO [train.py:715] (5/8) Epoch 0, batch 9550, loss[loss=0.2675, simple_loss=0.3043, pruned_loss=0.1153, over 4860.00 frames.], tot_loss[loss=0.2543, simple_loss=0.2953, pruned_loss=0.1066, over 972069.16 frames.], batch size: 32, lr: 2.04e-03
2022-05-03 13:51:08,461 INFO [train.py:715] (5/8) Epoch 0, batch 9600, loss[loss=0.2908, simple_loss=0.3336, pruned_loss=0.124, over 4939.00 frames.], tot_loss[loss=0.2546, simple_loss=0.2956, pruned_loss=0.1068, over 972770.55 frames.], batch size: 21, lr: 2.04e-03
2022-05-03 13:51:48,910 INFO [train.py:715] (5/8) Epoch 0, batch 9650, loss[loss=0.249, simple_loss=0.2883, pruned_loss=0.1049, over 4923.00 frames.], tot_loss[loss=0.254, simple_loss=0.2952, pruned_loss=0.1064, over 972402.00 frames.], batch size: 23, lr: 2.03e-03
2022-05-03 13:52:27,667 INFO [train.py:715] (5/8) Epoch 0, batch 9700, loss[loss=0.3107, simple_loss=0.3309, pruned_loss=0.1453, over 4938.00 frames.], tot_loss[loss=0.2553, simple_loss=0.2962, pruned_loss=0.1072, over 971900.36 frames.], batch size: 29, lr: 2.03e-03
2022-05-03 13:53:08,243 INFO [train.py:715] (5/8) Epoch 0, batch 9750, loss[loss=0.2845, simple_loss=0.3181, pruned_loss=0.1254, over 4879.00 frames.], tot_loss[loss=0.2549, simple_loss=0.2963, pruned_loss=0.1068, over 971441.99 frames.], batch size: 20, lr: 2.03e-03
2022-05-03 13:53:47,972 INFO [train.py:715] (5/8) Epoch 0, batch 9800, loss[loss=0.2434, simple_loss=0.2921, pruned_loss=0.09737, over 4810.00 frames.], tot_loss[loss=0.2552, simple_loss=0.2964, pruned_loss=0.107, over 970649.95 frames.], batch size: 21, lr: 2.02e-03
2022-05-03 13:54:27,875 INFO [train.py:715] (5/8) Epoch 0, batch 9850, loss[loss=0.29, simple_loss=0.3148, pruned_loss=0.1326, over 4967.00 frames.], tot_loss[loss=0.256, simple_loss=0.297, pruned_loss=0.1076, over 971728.00 frames.], batch size: 28, lr: 2.02e-03
2022-05-03 13:55:07,637 INFO [train.py:715] (5/8) Epoch 0, batch 9900, loss[loss=0.2079, simple_loss=0.2667, pruned_loss=0.07458, over 4873.00 frames.], tot_loss[loss=0.2551, simple_loss=0.2964, pruned_loss=0.1068, over 971912.25 frames.], batch size: 20, lr: 2.01e-03
2022-05-03 13:55:47,708 INFO [train.py:715] (5/8) Epoch 0, batch 9950, loss[loss=0.2252, simple_loss=0.2739, pruned_loss=0.08828, over 4830.00 frames.], tot_loss[loss=0.2517, simple_loss=0.2942, pruned_loss=0.1046, over 970989.97 frames.], batch size: 30, lr: 2.01e-03
2022-05-03 13:56:27,935 INFO [train.py:715] (5/8) Epoch 0, batch 10000, loss[loss=0.2015, simple_loss=0.2639, pruned_loss=0.06955, over 4828.00 frames.], tot_loss[loss=0.2528, simple_loss=0.2952, pruned_loss=0.1052, over 971624.30 frames.], batch size: 13, lr: 2.01e-03
2022-05-03 13:57:07,309 INFO [train.py:715] (5/8) Epoch 0, batch 10050, loss[loss=0.2581, simple_loss=0.3101, pruned_loss=0.1031, over 4921.00 frames.], tot_loss[loss=0.2524, simple_loss=0.2949, pruned_loss=0.105, over 971419.45 frames.], batch size: 23, lr: 2.00e-03
2022-05-03 13:57:47,861 INFO [train.py:715] (5/8) Epoch 0, batch 10100, loss[loss=0.1911, simple_loss=0.2561, pruned_loss=0.06306, over 4827.00 frames.], tot_loss[loss=0.2516, simple_loss=0.2941, pruned_loss=0.1045, over 971991.31 frames.], batch size: 13, lr: 2.00e-03
2022-05-03 13:58:27,709 INFO [train.py:715] (5/8) Epoch 0, batch 10150, loss[loss=0.2425, simple_loss=0.2927, pruned_loss=0.09619, over 4692.00 frames.], tot_loss[loss=0.2495, simple_loss=0.2927, pruned_loss=0.1031, over 972271.73 frames.], batch size: 15, lr: 1.99e-03
2022-05-03 13:59:07,280 INFO [train.py:715] (5/8) Epoch 0, batch 10200, loss[loss=0.1999, simple_loss=0.2563, pruned_loss=0.07177, over 4825.00 frames.], tot_loss[loss=0.249, simple_loss=0.2925, pruned_loss=0.1027, over 972265.87 frames.], batch size: 26, lr: 1.99e-03
2022-05-03 13:59:47,208 INFO [train.py:715] (5/8) Epoch 0, batch 10250, loss[loss=0.1804, simple_loss=0.2394, pruned_loss=0.06076, over 4918.00 frames.], tot_loss[loss=0.2502, simple_loss=0.2931, pruned_loss=0.1037, over 972212.14 frames.], batch size: 29, lr: 1.99e-03
2022-05-03 14:00:28,081 INFO [train.py:715] (5/8) Epoch 0, batch 10300, loss[loss=0.2665, simple_loss=0.3048, pruned_loss=0.1141, over 4921.00 frames.], tot_loss[loss=0.2485, simple_loss=0.2925, pruned_loss=0.1022, over 972256.24 frames.], batch size: 18, lr: 1.98e-03
2022-05-03 14:01:08,330 INFO [train.py:715] (5/8) Epoch 0, batch 10350, loss[loss=0.2881, simple_loss=0.3127, pruned_loss=0.1317, over 4814.00 frames.], tot_loss[loss=0.2493, simple_loss=0.2929, pruned_loss=0.1029, over 972513.66 frames.], batch size: 26, lr: 1.98e-03
2022-05-03 14:01:47,787 INFO [train.py:715] (5/8) Epoch 0, batch 10400, loss[loss=0.2688, simple_loss=0.3113, pruned_loss=0.1132, over 4840.00 frames.], tot_loss[loss=0.2513, simple_loss=0.2939, pruned_loss=0.1043, over 972156.67 frames.], batch size: 26, lr: 1.97e-03
2022-05-03 14:02:28,425 INFO [train.py:715] (5/8) Epoch 0, batch 10450, loss[loss=0.2572, simple_loss=0.2975, pruned_loss=0.1084, over 4789.00 frames.], tot_loss[loss=0.25, simple_loss=0.2929, pruned_loss=0.1036, over 971475.31 frames.], batch size: 21, lr: 1.97e-03
2022-05-03 14:03:09,166 INFO [train.py:715] (5/8) Epoch 0, batch 10500, loss[loss=0.2582, simple_loss=0.2873, pruned_loss=0.1146, over 4753.00 frames.], tot_loss[loss=0.251, simple_loss=0.2935, pruned_loss=0.1043, over 971416.25 frames.], batch size: 19, lr: 1.97e-03
2022-05-03 14:03:48,866 INFO [train.py:715] (5/8) Epoch 0, batch 10550, loss[loss=0.2145, simple_loss=0.2671, pruned_loss=0.08096, over 4976.00 frames.], tot_loss[loss=0.2506, simple_loss=0.2936, pruned_loss=0.1038, over 971519.32 frames.], batch size: 15, lr: 1.96e-03
2022-05-03 14:04:28,877 INFO [train.py:715] (5/8) Epoch 0, batch 10600, loss[loss=0.213, simple_loss=0.2576, pruned_loss=0.08425, over 4846.00 frames.], tot_loss[loss=0.2482, simple_loss=0.2917, pruned_loss=0.1023, over 972398.20 frames.], batch size: 15, lr: 1.96e-03
2022-05-03 14:05:09,748 INFO [train.py:715] (5/8) Epoch 0, batch 10650, loss[loss=0.3238, simple_loss=0.3529, pruned_loss=0.1473, over 4862.00 frames.], tot_loss[loss=0.2491, simple_loss=0.2928, pruned_loss=0.1027, over 972245.50 frames.], batch size: 38, lr: 1.96e-03
2022-05-03 14:05:49,653 INFO [train.py:715] (5/8) Epoch 0, batch 10700, loss[loss=0.2024, simple_loss=0.2508, pruned_loss=0.07702, over 4961.00 frames.], tot_loss[loss=0.2494, simple_loss=0.2929, pruned_loss=0.1029, over 972986.52 frames.], batch size: 15, lr: 1.95e-03
2022-05-03 14:06:29,545 INFO [train.py:715] (5/8) Epoch 0, batch 10750, loss[loss=0.2832, simple_loss=0.3076, pruned_loss=0.1294, over 4923.00 frames.], tot_loss[loss=0.2479, simple_loss=0.2915, pruned_loss=0.1021, over 972518.95 frames.], batch size: 18, lr: 1.95e-03
2022-05-03 14:07:09,720 INFO [train.py:715] (5/8) Epoch 0, batch 10800, loss[loss=0.2792, simple_loss=0.313, pruned_loss=0.1227, over 4960.00 frames.], tot_loss[loss=0.2471, simple_loss=0.2908, pruned_loss=0.1017, over 972405.13 frames.], batch size: 35, lr: 1.94e-03
2022-05-03 14:07:50,565 INFO [train.py:715] (5/8) Epoch 0, batch 10850, loss[loss=0.2017, simple_loss=0.2548, pruned_loss=0.07428, over 4699.00 frames.], tot_loss[loss=0.2476, simple_loss=0.2914, pruned_loss=0.1018, over 971885.22 frames.], batch size: 15, lr: 1.94e-03
2022-05-03 14:08:30,100 INFO [train.py:715] (5/8) Epoch 0, batch 10900, loss[loss=0.2102, simple_loss=0.2702, pruned_loss=0.07513, over 4958.00 frames.], tot_loss[loss=0.2469, simple_loss=0.2909, pruned_loss=0.1015, over 971571.95 frames.], batch size: 24, lr: 1.94e-03
2022-05-03 14:09:10,039 INFO [train.py:715] (5/8) Epoch 0, batch 10950, loss[loss=0.2399, simple_loss=0.2886, pruned_loss=0.09555, over 4926.00 frames.], tot_loss[loss=0.2464, simple_loss=0.2905, pruned_loss=0.1011, over 971996.04 frames.], batch size: 29, lr: 1.93e-03
2022-05-03 14:09:50,817 INFO [train.py:715] (5/8) Epoch 0, batch 11000, loss[loss=0.263, simple_loss=0.3183, pruned_loss=0.1038, over 4702.00 frames.], tot_loss[loss=0.2453, simple_loss=0.2903, pruned_loss=0.1002, over 971789.65 frames.], batch size: 15, lr: 1.93e-03
2022-05-03 14:10:31,097 INFO [train.py:715] (5/8) Epoch 0, batch 11050, loss[loss=0.2487, simple_loss=0.2846, pruned_loss=0.1064, over 4888.00 frames.], tot_loss[loss=0.2467, simple_loss=0.2913, pruned_loss=0.1011, over 972032.14 frames.], batch size: 32, lr: 1.93e-03
2022-05-03 14:11:11,143 INFO [train.py:715] (5/8) Epoch 0, batch 11100, loss[loss=0.1845, simple_loss=0.2502, pruned_loss=0.05942, over 4798.00 frames.], tot_loss[loss=0.2466, simple_loss=0.2907, pruned_loss=0.1012, over 971479.05 frames.], batch size: 21, lr: 1.92e-03
2022-05-03 14:11:51,018 INFO [train.py:715] (5/8) Epoch 0, batch 11150, loss[loss=0.3194, simple_loss=0.345, pruned_loss=0.1468, over 4906.00 frames.], tot_loss[loss=0.2472, simple_loss=0.2915, pruned_loss=0.1015, over 971912.28 frames.], batch size: 17, lr: 1.92e-03
2022-05-03 14:12:31,467 INFO [train.py:715] (5/8) Epoch 0, batch 11200, loss[loss=0.294, simple_loss=0.326, pruned_loss=0.131, over 4788.00 frames.], tot_loss[loss=0.2478, simple_loss=0.2918, pruned_loss=0.1019, over 972252.27 frames.], batch size: 14, lr: 1.92e-03
2022-05-03 14:13:10,947 INFO [train.py:715] (5/8) Epoch 0, batch 11250, loss[loss=0.2867, simple_loss=0.3217, pruned_loss=0.1258, over 4917.00 frames.], tot_loss[loss=0.2486, simple_loss=0.2924, pruned_loss=0.1024, over 972557.51 frames.], batch size: 39, lr: 1.91e-03
2022-05-03 14:13:51,037 INFO [train.py:715] (5/8) Epoch 0, batch 11300, loss[loss=0.2852, simple_loss=0.3163, pruned_loss=0.1271, over 4917.00 frames.], tot_loss[loss=0.2482, simple_loss=0.2923, pruned_loss=0.1021, over 973286.42 frames.], batch size: 17, lr: 1.91e-03
2022-05-03 14:14:31,682 INFO [train.py:715] (5/8) Epoch 0, batch 11350, loss[loss=0.2184, simple_loss=0.2775, pruned_loss=0.07963, over 4836.00 frames.], tot_loss[loss=0.2488, simple_loss=0.2929, pruned_loss=0.1024, over 973259.20 frames.], batch size: 30, lr: 1.90e-03
2022-05-03 14:15:12,112 INFO [train.py:715] (5/8) Epoch 0, batch 11400, loss[loss=0.2267, simple_loss=0.2712, pruned_loss=0.09112, over 4795.00 frames.], tot_loss[loss=0.2478, simple_loss=0.292, pruned_loss=0.1018, over 972870.66 frames.], batch size: 13, lr: 1.90e-03
2022-05-03 14:15:51,354 INFO [train.py:715] (5/8) Epoch 0, batch 11450, loss[loss=0.2477, simple_loss=0.2977, pruned_loss=0.09885, over 4781.00 frames.], tot_loss[loss=0.2468, simple_loss=0.2911, pruned_loss=0.1013, over 973007.04 frames.], batch size: 17, lr: 1.90e-03
2022-05-03 14:16:32,019 INFO [train.py:715] (5/8) Epoch 0, batch 11500, loss[loss=0.2398, simple_loss=0.2892, pruned_loss=0.09522, over 4969.00 frames.], tot_loss[loss=0.2459, simple_loss=0.2905, pruned_loss=0.1006, over 972663.01 frames.], batch size: 24, lr: 1.89e-03
2022-05-03 14:17:12,405 INFO [train.py:715] (5/8) Epoch 0, batch 11550, loss[loss=0.2196, simple_loss=0.2708, pruned_loss=0.08416, over 4790.00 frames.], tot_loss[loss=0.2451, simple_loss=0.2898, pruned_loss=0.1002, over 972557.66 frames.], batch size: 14, lr: 1.89e-03
2022-05-03 14:17:52,481 INFO [train.py:715] (5/8) Epoch 0, batch 11600, loss[loss=0.2028, simple_loss=0.2611, pruned_loss=0.07226, over 4766.00 frames.], tot_loss[loss=0.2436, simple_loss=0.2884, pruned_loss=0.09937, over 972463.01 frames.], batch size: 18, lr: 1.89e-03
2022-05-03 14:18:32,574 INFO [train.py:715] (5/8) Epoch 0, batch 11650, loss[loss=0.2314, simple_loss=0.2879, pruned_loss=0.08746, over 4928.00 frames.], tot_loss[loss=0.2451, simple_loss=0.2899, pruned_loss=0.1001, over 972320.60 frames.], batch size: 21, lr: 1.88e-03
2022-05-03 14:19:13,494 INFO [train.py:715] (5/8) Epoch 0, batch 11700, loss[loss=0.1984, simple_loss=0.2621, pruned_loss=0.06741, over 4889.00 frames.], tot_loss[loss=0.2448, simple_loss=0.2897, pruned_loss=0.09993, over 972280.89 frames.], batch size: 19, lr: 1.88e-03
2022-05-03 14:19:53,840 INFO [train.py:715] (5/8) Epoch 0, batch 11750, loss[loss=0.2545, simple_loss=0.2841, pruned_loss=0.1124, over 4908.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2896, pruned_loss=0.09933, over 972226.44 frames.], batch size: 22, lr: 1.88e-03
2022-05-03 14:20:34,216 INFO [train.py:715] (5/8) Epoch 0, batch 11800, loss[loss=0.2389, simple_loss=0.2802, pruned_loss=0.09876, over 4878.00 frames.], tot_loss[loss=0.2451, simple_loss=0.2901, pruned_loss=0.1001, over 971890.95 frames.], batch size: 22, lr: 1.87e-03
2022-05-03 14:21:14,572 INFO [train.py:715] (5/8) Epoch 0, batch 11850, loss[loss=0.2607, simple_loss=0.304, pruned_loss=0.1087, over 4982.00 frames.], tot_loss[loss=0.2445, simple_loss=0.2903, pruned_loss=0.09938, over 972298.20 frames.], batch size: 39, lr: 1.87e-03
2022-05-03 14:21:55,675 INFO [train.py:715] (5/8) Epoch 0, batch 11900, loss[loss=0.2376, simple_loss=0.2828, pruned_loss=0.09625, over 4924.00 frames.], tot_loss[loss=0.2439, simple_loss=0.2897, pruned_loss=0.09908, over 972594.31 frames.], batch size: 18, lr: 1.87e-03
2022-05-03 14:22:35,858 INFO [train.py:715] (5/8) Epoch 0, batch 11950, loss[loss=0.2905, simple_loss=0.3254, pruned_loss=0.1278, over 4864.00 frames.], tot_loss[loss=0.2428, simple_loss=0.289, pruned_loss=0.09831, over 973296.12 frames.], batch size: 20, lr: 1.86e-03
2022-05-03 14:23:15,972 INFO [train.py:715] (5/8) Epoch 0, batch 12000, loss[loss=0.2073, simple_loss=0.2694, pruned_loss=0.0726, over 4755.00 frames.], tot_loss[loss=0.2414, simple_loss=0.2879, pruned_loss=0.09746, over 972139.18 frames.], batch size: 14, lr: 1.86e-03
2022-05-03 14:23:15,973 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 14:23:31,274 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1516, simple_loss=0.2368, pruned_loss=0.03315, over 914524.00 frames.
2022-05-03 14:24:11,265 INFO [train.py:715] (5/8) Epoch 0, batch 12050, loss[loss=0.2412, simple_loss=0.2923, pruned_loss=0.09505, over 4925.00 frames.], tot_loss[loss=0.2409, simple_loss=0.2879, pruned_loss=0.09694, over 972046.31 frames.], batch size: 29, lr: 1.86e-03
2022-05-03 14:24:51,292 INFO [train.py:715] (5/8) Epoch 0, batch 12100, loss[loss=0.2496, simple_loss=0.2876, pruned_loss=0.1058, over 4823.00 frames.], tot_loss[loss=0.241, simple_loss=0.2881, pruned_loss=0.09692, over 972506.72 frames.], batch size: 15, lr: 1.85e-03
2022-05-03 14:25:31,591 INFO [train.py:715] (5/8) Epoch 0, batch 12150, loss[loss=0.222, simple_loss=0.2709, pruned_loss=0.08657, over 4876.00 frames.], tot_loss[loss=0.243, simple_loss=0.2892, pruned_loss=0.0984, over 972548.93 frames.], batch size: 38, lr: 1.85e-03
2022-05-03 14:26:11,158 INFO [train.py:715] (5/8) Epoch 0, batch 12200, loss[loss=0.2497, simple_loss=0.2992, pruned_loss=0.1001, over 4876.00 frames.], tot_loss[loss=0.2437, simple_loss=0.2898, pruned_loss=0.09879, over 972703.34 frames.], batch size: 30, lr: 1.85e-03
2022-05-03 14:26:51,060 INFO [train.py:715] (5/8) Epoch 0, batch 12250, loss[loss=0.2804, simple_loss=0.3225, pruned_loss=0.1192, over 4708.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2902, pruned_loss=0.09903, over 972384.68 frames.], batch size: 15, lr: 1.84e-03
2022-05-03 14:27:31,547 INFO [train.py:715] (5/8) Epoch 0, batch 12300, loss[loss=0.25, simple_loss=0.3073, pruned_loss=0.09635, over 4906.00 frames.], tot_loss[loss=0.2448, simple_loss=0.2906, pruned_loss=0.09949, over 972091.88 frames.], batch size: 17, lr: 1.84e-03
2022-05-03 14:28:10,859 INFO [train.py:715] (5/8) Epoch 0, batch 12350, loss[loss=0.2418, simple_loss=0.2897, pruned_loss=0.09699, over 4837.00 frames.], tot_loss[loss=0.2428, simple_loss=0.2892, pruned_loss=0.09819, over 972529.23 frames.], batch size: 32, lr: 1.84e-03
2022-05-03 14:28:50,839 INFO [train.py:715] (5/8) Epoch 0, batch 12400, loss[loss=0.2805, simple_loss=0.311, pruned_loss=0.125, over 4791.00 frames.], tot_loss[loss=0.2418, simple_loss=0.2887, pruned_loss=0.09751, over 972210.90 frames.], batch size: 14, lr: 1.83e-03
2022-05-03 14:29:31,168 INFO [train.py:715] (5/8) Epoch 0, batch 12450, loss[loss=0.2692, simple_loss=0.2979, pruned_loss=0.1202, over 4882.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2884, pruned_loss=0.09786, over 972041.13 frames.], batch size: 16, lr: 1.83e-03
2022-05-03 14:30:11,384 INFO [train.py:715] (5/8) Epoch 0, batch 12500, loss[loss=0.2317, simple_loss=0.2705, pruned_loss=0.09645, over 4760.00 frames.], tot_loss[loss=0.2433, simple_loss=0.289, pruned_loss=0.09877, over 972204.37 frames.], batch size: 19, lr: 1.83e-03
2022-05-03 14:30:50,305 INFO [train.py:715] (5/8) Epoch 0, batch 12550, loss[loss=0.2566, simple_loss=0.3017, pruned_loss=0.1057, over 4796.00 frames.], tot_loss[loss=0.2419, simple_loss=0.2879, pruned_loss=0.09796, over 972605.73 frames.], batch size: 12, lr: 1.83e-03
2022-05-03 14:31:30,333 INFO [train.py:715] (5/8) Epoch 0, batch 12600, loss[loss=0.2049, simple_loss=0.2634, pruned_loss=0.07324, over 4917.00 frames.], tot_loss[loss=0.2412, simple_loss=0.2878, pruned_loss=0.0973, over 972357.73 frames.], batch size: 18, lr: 1.82e-03
2022-05-03 14:32:11,361 INFO [train.py:715] (5/8) Epoch 0, batch 12650, loss[loss=0.2639, simple_loss=0.3002, pruned_loss=0.1138, over 4914.00 frames.], tot_loss[loss=0.2417, simple_loss=0.2884, pruned_loss=0.0975, over 972281.84 frames.], batch size: 39, lr: 1.82e-03
2022-05-03 14:32:51,083 INFO [train.py:715] (5/8) Epoch 0, batch 12700, loss[loss=0.2465, simple_loss=0.2903, pruned_loss=0.1014, over 4878.00 frames.], tot_loss[loss=0.2424, simple_loss=0.2887, pruned_loss=0.098, over 973027.04 frames.], batch size: 19, lr: 1.82e-03
2022-05-03 14:33:30,729 INFO [train.py:715] (5/8) Epoch 0, batch 12750, loss[loss=0.2352, simple_loss=0.2969, pruned_loss=0.08672, over 4872.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2883, pruned_loss=0.09791, over 973053.91 frames.], batch size: 16, lr: 1.81e-03
2022-05-03 14:34:11,170 INFO [train.py:715] (5/8) Epoch 0, batch 12800, loss[loss=0.2348, simple_loss=0.2767, pruned_loss=0.09642, over 4814.00 frames.], tot_loss[loss=0.2404, simple_loss=0.2873, pruned_loss=0.09672, over 973322.29 frames.], batch size: 13, lr: 1.81e-03
2022-05-03 14:34:51,660 INFO [train.py:715] (5/8) Epoch 0, batch 12850, loss[loss=0.2134, simple_loss=0.266, pruned_loss=0.08043, over 4900.00 frames.], tot_loss[loss=0.2404, simple_loss=0.2872, pruned_loss=0.09674, over 972993.53 frames.], batch size: 17, lr: 1.81e-03
2022-05-03 14:35:31,481 INFO [train.py:715] (5/8) Epoch 0, batch 12900, loss[loss=0.2235, simple_loss=0.2883, pruned_loss=0.07931, over 4845.00 frames.], tot_loss[loss=0.2401, simple_loss=0.2872, pruned_loss=0.09651, over 972897.05 frames.], batch size: 26, lr: 1.80e-03
2022-05-03 14:36:11,738 INFO [train.py:715] (5/8) Epoch 0, batch 12950, loss[loss=0.2567, simple_loss=0.3022, pruned_loss=0.1056, over 4959.00 frames.], tot_loss[loss=0.2395, simple_loss=0.2867, pruned_loss=0.09616, over 972584.75 frames.], batch size: 15, lr: 1.80e-03
2022-05-03 14:36:52,264 INFO [train.py:715] (5/8) Epoch 0, batch 13000, loss[loss=0.2482, simple_loss=0.2863, pruned_loss=0.105, over 4861.00 frames.], tot_loss[loss=0.2401, simple_loss=0.2867, pruned_loss=0.09677, over 972251.62 frames.], batch size: 34, lr: 1.80e-03
2022-05-03 14:37:32,733 INFO [train.py:715] (5/8) Epoch 0, batch 13050, loss[loss=0.2245, simple_loss=0.2787, pruned_loss=0.08515, over 4901.00 frames.], tot_loss[loss=0.2385, simple_loss=0.2854, pruned_loss=0.09581, over 972105.33 frames.], batch size: 19, lr: 1.79e-03
2022-05-03 14:38:12,065 INFO [train.py:715] (5/8) Epoch 0, batch 13100, loss[loss=0.2524, simple_loss=0.2912, pruned_loss=0.1068, over 4868.00 frames.], tot_loss[loss=0.239, simple_loss=0.2859, pruned_loss=0.09609, over 972590.74 frames.], batch size: 32, lr: 1.79e-03
2022-05-03 14:38:52,503 INFO [train.py:715] (5/8) Epoch 0, batch 13150, loss[loss=0.2006, simple_loss=0.2541, pruned_loss=0.07356, over 4966.00 frames.], tot_loss[loss=0.2394, simple_loss=0.2865, pruned_loss=0.09617, over 972153.59 frames.], batch size: 28, lr: 1.79e-03
2022-05-03 14:39:32,996 INFO [train.py:715] (5/8) Epoch 0, batch 13200, loss[loss=0.28, simple_loss=0.3066, pruned_loss=0.1267, over 4901.00 frames.], tot_loss[loss=0.2407, simple_loss=0.2871, pruned_loss=0.09716, over 971827.42 frames.], batch size: 19, lr: 1.79e-03
2022-05-03 14:40:12,562 INFO [train.py:715] (5/8) Epoch 0, batch 13250, loss[loss=0.241, simple_loss=0.2942, pruned_loss=0.09388, over 4817.00 frames.], tot_loss[loss=0.2401, simple_loss=0.2869, pruned_loss=0.09672, over 972257.96 frames.], batch size: 25, lr: 1.78e-03
2022-05-03 14:40:52,439 INFO [train.py:715] (5/8) Epoch 0, batch 13300, loss[loss=0.2154, simple_loss=0.2653, pruned_loss=0.08274, over 4986.00 frames.], tot_loss[loss=0.2393, simple_loss=0.2863, pruned_loss=0.09615, over 972618.78 frames.], batch size: 25, lr: 1.78e-03
2022-05-03 14:41:32,817 INFO [train.py:715] (5/8) Epoch 0, batch 13350, loss[loss=0.2406, simple_loss=0.2819, pruned_loss=0.09964, over 4885.00 frames.], tot_loss[loss=0.2378, simple_loss=0.2858, pruned_loss=0.09495, over 973307.77 frames.], batch size: 19, lr: 1.78e-03
2022-05-03 14:42:13,149 INFO [train.py:715] (5/8) Epoch 0, batch 13400, loss[loss=0.2548, simple_loss=0.3017, pruned_loss=0.104, over 4839.00 frames.], tot_loss[loss=0.2379, simple_loss=0.2858, pruned_loss=0.09506, over 973100.51 frames.], batch size: 30, lr: 1.77e-03
2022-05-03 14:42:52,943 INFO [train.py:715] (5/8) Epoch 0, batch 13450, loss[loss=0.2405, simple_loss=0.2898, pruned_loss=0.09556, over 4827.00 frames.], tot_loss[loss=0.2379, simple_loss=0.2854, pruned_loss=0.09526, over 972605.51 frames.], batch size: 15, lr: 1.77e-03
2022-05-03 14:43:33,176 INFO [train.py:715] (5/8) Epoch 0, batch 13500, loss[loss=0.2075, simple_loss=0.2628, pruned_loss=0.0761, over 4893.00 frames.], tot_loss[loss=0.238, simple_loss=0.2857, pruned_loss=0.09519, over 972427.03 frames.], batch size: 19, lr: 1.77e-03
2022-05-03 14:44:13,366 INFO [train.py:715] (5/8) Epoch 0, batch 13550, loss[loss=0.2561, simple_loss=0.3093, pruned_loss=0.1015, over 4856.00 frames.], tot_loss[loss=0.2388, simple_loss=0.2865, pruned_loss=0.09562, over 972129.44 frames.], batch size: 32, lr: 1.77e-03
2022-05-03 14:44:52,806 INFO [train.py:715] (5/8) Epoch 0, batch 13600, loss[loss=0.2264, simple_loss=0.2748, pruned_loss=0.08905, over 4935.00 frames.], tot_loss[loss=0.2386, simple_loss=0.2861, pruned_loss=0.09553, over 972126.13 frames.], batch size: 21, lr: 1.76e-03
2022-05-03 14:45:32,768 INFO [train.py:715] (5/8) Epoch 0, batch 13650, loss[loss=0.2441, simple_loss=0.2929, pruned_loss=0.09761, over 4697.00 frames.], tot_loss[loss=0.239, simple_loss=0.2861, pruned_loss=0.09597, over 972522.71 frames.], batch size: 15, lr: 1.76e-03
2022-05-03 14:46:12,700 INFO [train.py:715] (5/8) Epoch 0, batch 13700, loss[loss=0.3067, simple_loss=0.3267, pruned_loss=0.1433, over 4920.00 frames.], tot_loss[loss=0.2386, simple_loss=0.2857, pruned_loss=0.09578, over 972429.97 frames.], batch size: 18, lr: 1.76e-03
2022-05-03 14:46:52,709 INFO [train.py:715] (5/8) Epoch 0, batch 13750, loss[loss=0.2439, simple_loss=0.2998, pruned_loss=0.09405, over 4968.00 frames.], tot_loss[loss=0.2366, simple_loss=0.2846, pruned_loss=0.09433, over 971529.73 frames.], batch size: 39, lr: 1.75e-03
2022-05-03 14:47:32,542 INFO [train.py:715] (5/8) Epoch 0, batch 13800, loss[loss=0.2311, simple_loss=0.2748, pruned_loss=0.09367, over 4954.00 frames.], tot_loss[loss=0.2366, simple_loss=0.2845, pruned_loss=0.09434, over 971783.69 frames.], batch size: 35, lr: 1.75e-03
2022-05-03 14:48:12,871 INFO [train.py:715] (5/8) Epoch 0, batch 13850, loss[loss=0.259, simple_loss=0.2949, pruned_loss=0.1116, over 4917.00 frames.], tot_loss[loss=0.236, simple_loss=0.2842, pruned_loss=0.09395, over 972647.97 frames.], batch size: 17, lr: 1.75e-03
2022-05-03 14:48:53,731 INFO [train.py:715] (5/8) Epoch 0, batch 13900, loss[loss=0.1911, simple_loss=0.2467, pruned_loss=0.0678, over 4828.00 frames.], tot_loss[loss=0.2341, simple_loss=0.2829, pruned_loss=0.09267, over 971937.25 frames.], batch size: 26, lr: 1.75e-03
2022-05-03 14:49:33,780 INFO [train.py:715] (5/8) Epoch 0, batch 13950, loss[loss=0.2284, simple_loss=0.2662, pruned_loss=0.09527, over 4752.00 frames.], tot_loss[loss=0.2331, simple_loss=0.2823, pruned_loss=0.09199, over 971568.80 frames.], batch size: 16, lr: 1.74e-03
2022-05-03 14:50:14,378 INFO [train.py:715] (5/8) Epoch 0, batch 14000, loss[loss=0.2738, simple_loss=0.3085, pruned_loss=0.1195, over 4841.00 frames.], tot_loss[loss=0.2328, simple_loss=0.282, pruned_loss=0.0918, over 971999.62 frames.], batch size: 15, lr: 1.74e-03
2022-05-03 14:50:55,237 INFO [train.py:715] (5/8) Epoch 0, batch 14050, loss[loss=0.2261, simple_loss=0.2799, pruned_loss=0.0862, over 4940.00 frames.], tot_loss[loss=0.2337, simple_loss=0.2825, pruned_loss=0.09247, over 971446.38 frames.], batch size: 21, lr: 1.74e-03
2022-05-03 14:51:35,695 INFO [train.py:715] (5/8) Epoch 0, batch 14100, loss[loss=0.3009, simple_loss=0.3285, pruned_loss=0.1366, over 4883.00 frames.], tot_loss[loss=0.2348, simple_loss=0.2831, pruned_loss=0.0933, over 971585.32 frames.], batch size: 22, lr: 1.73e-03
2022-05-03 14:52:16,206 INFO [train.py:715] (5/8) Epoch 0, batch 14150, loss[loss=0.2441, simple_loss=0.2969, pruned_loss=0.0956, over 4960.00 frames.], tot_loss[loss=0.2359, simple_loss=0.2838, pruned_loss=0.09395, over 972430.92 frames.], batch size: 15, lr: 1.73e-03
2022-05-03 14:52:56,858 INFO [train.py:715] (5/8) Epoch 0, batch 14200, loss[loss=0.2186, simple_loss=0.28, pruned_loss=0.07864, over 4752.00 frames.], tot_loss[loss=0.2357, simple_loss=0.2839, pruned_loss=0.0938, over 971663.81 frames.], batch size: 19, lr: 1.73e-03
2022-05-03 14:53:37,709 INFO [train.py:715] (5/8) Epoch 0, batch 14250, loss[loss=0.2697, simple_loss=0.305, pruned_loss=0.1172, over 4847.00 frames.], tot_loss[loss=0.2347, simple_loss=0.2828, pruned_loss=0.09332, over 972027.26 frames.], batch size: 30, lr: 1.73e-03
2022-05-03 14:54:18,427 INFO [train.py:715] (5/8) Epoch 0, batch 14300, loss[loss=0.2471, simple_loss=0.2875, pruned_loss=0.1033, over 4697.00 frames.], tot_loss[loss=0.2332, simple_loss=0.282, pruned_loss=0.09222, over 972429.18 frames.], batch size: 15, lr: 1.72e-03
2022-05-03 14:54:59,480 INFO [train.py:715] (5/8) Epoch 0, batch 14350, loss[loss=0.2174, simple_loss=0.2739, pruned_loss=0.0805, over 4762.00 frames.], tot_loss[loss=0.2344, simple_loss=0.2828, pruned_loss=0.09297, over 971836.67 frames.], batch size: 17, lr: 1.72e-03
2022-05-03 14:55:40,712 INFO [train.py:715] (5/8) Epoch 0, batch 14400, loss[loss=0.1865, simple_loss=0.2501, pruned_loss=0.06141, over 4863.00 frames.], tot_loss[loss=0.2325, simple_loss=0.2817, pruned_loss=0.09167, over 971303.86 frames.], batch size: 16, lr: 1.72e-03
2022-05-03 14:56:21,182 INFO [train.py:715] (5/8) Epoch 0, batch 14450, loss[loss=0.2151, simple_loss=0.2669, pruned_loss=0.08163, over 4981.00 frames.], tot_loss[loss=0.232, simple_loss=0.2812, pruned_loss=0.09147, over 972496.75 frames.], batch size: 27, lr: 1.72e-03
2022-05-03 14:57:01,536 INFO [train.py:715] (5/8) Epoch 0, batch 14500, loss[loss=0.1866, simple_loss=0.2465, pruned_loss=0.06335, over 4900.00 frames.], tot_loss[loss=0.2316, simple_loss=0.2809, pruned_loss=0.09112, over 972373.16 frames.], batch size: 19, lr: 1.71e-03
2022-05-03 14:57:42,204 INFO [train.py:715] (5/8) Epoch 0, batch 14550, loss[loss=0.2028, simple_loss=0.2554, pruned_loss=0.07512, over 4780.00 frames.], tot_loss[loss=0.2331, simple_loss=0.2822, pruned_loss=0.09205, over 971551.81 frames.], batch size: 17, lr: 1.71e-03
2022-05-03 14:58:22,171 INFO [train.py:715] (5/8) Epoch 0, batch 14600, loss[loss=0.2366, simple_loss=0.2886, pruned_loss=0.09232, over 4947.00 frames.], tot_loss[loss=0.2345, simple_loss=0.2833, pruned_loss=0.09283, over 972153.07 frames.], batch size: 21, lr: 1.71e-03
2022-05-03 14:59:01,454 INFO [train.py:715] (5/8) Epoch 0, batch 14650, loss[loss=0.2046, simple_loss=0.2604, pruned_loss=0.07441, over 4820.00 frames.], tot_loss[loss=0.2338, simple_loss=0.2827, pruned_loss=0.0924, over 972460.26 frames.], batch size: 27, lr: 1.70e-03
2022-05-03 14:59:41,812 INFO [train.py:715] (5/8) Epoch 0, batch 14700, loss[loss=0.246, simple_loss=0.2835, pruned_loss=0.1043, over 4786.00 frames.], tot_loss[loss=0.2329, simple_loss=0.282, pruned_loss=0.09195, over 972036.53 frames.], batch size: 18, lr: 1.70e-03
2022-05-03 15:00:22,079 INFO [train.py:715] (5/8) Epoch 0, batch 14750, loss[loss=0.2481, simple_loss=0.2941, pruned_loss=0.101, over 4759.00 frames.], tot_loss[loss=0.2327, simple_loss=0.2819, pruned_loss=0.0917, over 972322.26 frames.], batch size: 16, lr: 1.70e-03
2022-05-03 15:01:02,116 INFO [train.py:715] (5/8) Epoch 0, batch 14800, loss[loss=0.1958, simple_loss=0.2501, pruned_loss=0.07074, over 4872.00 frames.], tot_loss[loss=0.2325, simple_loss=0.2815, pruned_loss=0.09179, over 972576.13 frames.], batch size: 32, lr: 1.70e-03
2022-05-03 15:01:41,994 INFO [train.py:715] (5/8) Epoch 0, batch 14850, loss[loss=0.1876, simple_loss=0.2538, pruned_loss=0.06072, over 4823.00 frames.], tot_loss[loss=0.2347, simple_loss=0.2834, pruned_loss=0.09298, over 972132.72 frames.], batch size: 25, lr: 1.69e-03
2022-05-03 15:02:22,718 INFO [train.py:715] (5/8) Epoch 0, batch 14900, loss[loss=0.2518, simple_loss=0.2982, pruned_loss=0.1027, over 4837.00 frames.], tot_loss[loss=0.2341, simple_loss=0.2829, pruned_loss=0.09268, over 972651.01 frames.], batch size: 15, lr: 1.69e-03
2022-05-03 15:03:02,603 INFO [train.py:715] (5/8) Epoch 0, batch 14950, loss[loss=0.2039, simple_loss=0.2649, pruned_loss=0.0714, over 4958.00 frames.], tot_loss[loss=0.2329, simple_loss=0.2818, pruned_loss=0.09197, over 973316.99 frames.], batch size: 35, lr: 1.69e-03
2022-05-03 15:03:42,035 INFO [train.py:715] (5/8) Epoch 0, batch 15000, loss[loss=0.2365, simple_loss=0.2874, pruned_loss=0.09284, over 4921.00 frames.], tot_loss[loss=0.2334, simple_loss=0.2822, pruned_loss=0.09231, over 971676.31 frames.], batch size: 23, lr: 1.69e-03
2022-05-03 15:03:42,035 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 15:03:53,632 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1454, simple_loss=0.2314, pruned_loss=0.02968, over 914524.00 frames.
2022-05-03 15:04:32,990 INFO [train.py:715] (5/8) Epoch 0, batch 15050, loss[loss=0.2392, simple_loss=0.2905, pruned_loss=0.09396, over 4806.00 frames.], tot_loss[loss=0.2324, simple_loss=0.2816, pruned_loss=0.0916, over 972240.58 frames.], batch size: 21, lr: 1.68e-03
2022-05-03 15:05:13,562 INFO [train.py:715] (5/8) Epoch 0, batch 15100, loss[loss=0.2178, simple_loss=0.2545, pruned_loss=0.09056, over 4759.00 frames.], tot_loss[loss=0.2316, simple_loss=0.2812, pruned_loss=0.09095, over 971153.17 frames.], batch size: 12, lr: 1.68e-03
2022-05-03 15:05:53,895 INFO [train.py:715] (5/8) Epoch 0, batch 15150, loss[loss=0.2469, simple_loss=0.2918, pruned_loss=0.101, over 4957.00 frames.], tot_loss[loss=0.2308, simple_loss=0.2808, pruned_loss=0.09037, over 971643.51 frames.], batch size: 29, lr: 1.68e-03
2022-05-03 15:06:33,820 INFO [train.py:715] (5/8) Epoch 0, batch 15200, loss[loss=0.2908, simple_loss=0.3194, pruned_loss=0.1311, over 4696.00 frames.], tot_loss[loss=0.2308, simple_loss=0.2805, pruned_loss=0.09056, over 971482.66 frames.], batch size: 15, lr: 1.68e-03
2022-05-03 15:07:13,391 INFO [train.py:715] (5/8) Epoch 0, batch 15250, loss[loss=0.2431, simple_loss=0.2793, pruned_loss=0.1035, over 4775.00 frames.], tot_loss[loss=0.2305, simple_loss=0.2804, pruned_loss=0.09027, over 972710.38 frames.], batch size: 14, lr: 1.67e-03
2022-05-03 15:07:53,252 INFO [train.py:715] (5/8) Epoch 0, batch 15300, loss[loss=0.2192, simple_loss=0.267, pruned_loss=0.08571, over 4969.00 frames.], tot_loss[loss=0.231, simple_loss=0.2809, pruned_loss=0.09049, over 973120.32 frames.], batch size: 39, lr: 1.67e-03
2022-05-03 15:08:33,608 INFO [train.py:715] (5/8) Epoch 0, batch 15350, loss[loss=0.2084, simple_loss=0.259, pruned_loss=0.07888, over 4986.00 frames.], tot_loss[loss=0.231, simple_loss=0.2809, pruned_loss=0.09056, over 972672.70 frames.], batch size: 25, lr: 1.67e-03
2022-05-03 15:09:13,456 INFO [train.py:715] (5/8) Epoch 0, batch 15400, loss[loss=0.251, simple_loss=0.3074, pruned_loss=0.09731, over 4960.00 frames.], tot_loss[loss=0.2309, simple_loss=0.2811, pruned_loss=0.09031, over 974195.73 frames.], batch size: 24, lr: 1.67e-03
2022-05-03 15:09:53,909 INFO [train.py:715] (5/8) Epoch 0, batch 15450, loss[loss=0.2356, simple_loss=0.3029, pruned_loss=0.08414, over 4635.00 frames.], tot_loss[loss=0.2299, simple_loss=0.2804, pruned_loss=0.08969, over 973525.86 frames.], batch size: 13, lr: 1.66e-03
2022-05-03 15:10:33,370 INFO [train.py:715] (5/8) Epoch 0, batch 15500, loss[loss=0.2287, simple_loss=0.2891, pruned_loss=0.08417, over 4895.00 frames.], tot_loss[loss=0.2296, simple_loss=0.2804, pruned_loss=0.08943, over 973277.82 frames.], batch size: 19, lr: 1.66e-03
2022-05-03 15:11:12,567 INFO [train.py:715] (5/8) Epoch 0, batch 15550, loss[loss=0.2995, simple_loss=0.3169, pruned_loss=0.1411, over 4695.00 frames.], tot_loss[loss=0.2289, simple_loss=0.2798, pruned_loss=0.08897, over 972519.53 frames.], batch size: 15, lr: 1.66e-03
2022-05-03 15:11:52,063 INFO [train.py:715] (5/8) Epoch 0, batch 15600, loss[loss=0.2188, simple_loss=0.282, pruned_loss=0.07786, over 4786.00 frames.], tot_loss[loss=0.2276, simple_loss=0.279, pruned_loss=0.08815, over 971981.38 frames.], batch size: 17, lr: 1.66e-03
2022-05-03 15:12:31,510 INFO [train.py:715] (5/8) Epoch 0, batch 15650, loss[loss=0.2032, simple_loss=0.2559, pruned_loss=0.07529, over 4970.00 frames.], tot_loss[loss=0.2275, simple_loss=0.2786, pruned_loss=0.0882, over 972309.51 frames.], batch size: 14, lr: 1.65e-03
2022-05-03 15:13:11,298 INFO [train.py:715] (5/8) Epoch 0, batch 15700, loss[loss=0.1976, simple_loss=0.2474, pruned_loss=0.07393, over 4795.00 frames.], tot_loss[loss=0.2274, simple_loss=0.2784, pruned_loss=0.08823, over 972406.37 frames.], batch size: 13, lr: 1.65e-03
2022-05-03 15:13:50,901 INFO [train.py:715] (5/8) Epoch 0, batch 15750, loss[loss=0.2745, simple_loss=0.3112, pruned_loss=0.1189, over 4984.00 frames.], tot_loss[loss=0.2279, simple_loss=0.2789, pruned_loss=0.08845, over 972529.90 frames.], batch size: 25, lr: 1.65e-03
2022-05-03 15:14:30,844 INFO [train.py:715] (5/8) Epoch 0, batch 15800, loss[loss=0.2043, simple_loss=0.2605, pruned_loss=0.07405, over 4890.00 frames.], tot_loss[loss=0.2261, simple_loss=0.2775, pruned_loss=0.08738, over 973099.90 frames.], batch size: 22, lr: 1.65e-03
2022-05-03 15:15:10,664 INFO [train.py:715] (5/8) Epoch 0, batch 15850, loss[loss=0.1956, simple_loss=0.2597, pruned_loss=0.06569, over 4781.00 frames.], tot_loss[loss=0.2268, simple_loss=0.278, pruned_loss=0.08785, over 972365.14 frames.], batch size: 14, lr: 1.65e-03
2022-05-03 15:15:50,240 INFO [train.py:715] (5/8) Epoch 0, batch 15900, loss[loss=0.1944, simple_loss=0.2451, pruned_loss=0.0718, over 4748.00 frames.], tot_loss[loss=0.228, simple_loss=0.2787, pruned_loss=0.08869, over 972733.54 frames.], batch size: 12, lr: 1.64e-03
2022-05-03 15:16:30,475 INFO [train.py:715] (5/8) Epoch 0, batch 15950, loss[loss=0.1789, simple_loss=0.2381, pruned_loss=0.05983, over 4756.00 frames.], tot_loss[loss=0.2278, simple_loss=0.278, pruned_loss=0.0888, over 972178.73 frames.], batch size: 12, lr: 1.64e-03
2022-05-03 15:17:12,823 INFO [train.py:715] (5/8) Epoch 0, batch 16000, loss[loss=0.2429, simple_loss=0.295, pruned_loss=0.09544, over 4882.00 frames.], tot_loss[loss=0.2285, simple_loss=0.279, pruned_loss=0.08898, over 972934.82 frames.], batch size: 19, lr: 1.64e-03
2022-05-03 15:17:52,704 INFO [train.py:715] (5/8) Epoch 0, batch 16050, loss[loss=0.2592, simple_loss=0.3151, pruned_loss=0.1017, over 4779.00 frames.], tot_loss[loss=0.2288, simple_loss=0.2799, pruned_loss=0.08882, over 972657.29 frames.], batch size: 17, lr: 1.64e-03
2022-05-03 15:18:33,254 INFO [train.py:715] (5/8) Epoch 0, batch 16100, loss[loss=0.2508, simple_loss=0.3016, pruned_loss=0.1, over 4800.00 frames.], tot_loss[loss=0.2288, simple_loss=0.2799, pruned_loss=0.08884, over 972243.51 frames.], batch size: 25, lr: 1.63e-03
2022-05-03 15:19:13,428 INFO [train.py:715] (5/8) Epoch 0, batch 16150, loss[loss=0.3008, simple_loss=0.3257, pruned_loss=0.1379, over 4938.00 frames.], tot_loss[loss=0.2291, simple_loss=0.28, pruned_loss=0.08906, over 971267.63 frames.], batch size: 35, lr: 1.63e-03
2022-05-03 15:19:52,896 INFO [train.py:715] (5/8) Epoch 0, batch 16200, loss[loss=0.1883, simple_loss=0.2471, pruned_loss=0.0647, over 4967.00 frames.], tot_loss[loss=0.2288, simple_loss=0.2797, pruned_loss=0.08894, over 972499.94 frames.], batch size: 35, lr: 1.63e-03
2022-05-03 15:20:32,318 INFO [train.py:715] (5/8) Epoch 0, batch 16250, loss[loss=0.27, simple_loss=0.3078, pruned_loss=0.1161, over 4879.00 frames.], tot_loss[loss=0.2269, simple_loss=0.2782, pruned_loss=0.0878, over 972404.22 frames.], batch size: 16, lr: 1.63e-03
2022-05-03 15:21:12,243 INFO [train.py:715] (5/8) Epoch 0, batch 16300, loss[loss=0.2224, simple_loss=0.2777, pruned_loss=0.08352, over 4689.00 frames.], tot_loss[loss=0.2262, simple_loss=0.2778, pruned_loss=0.08731, over 972637.68 frames.], batch size: 15, lr: 1.62e-03
2022-05-03 15:21:51,669 INFO [train.py:715] (5/8) Epoch 0, batch 16350, loss[loss=0.2821, simple_loss=0.3225, pruned_loss=0.1208, over 4879.00 frames.], tot_loss[loss=0.2283, simple_loss=0.2793, pruned_loss=0.08864, over 972428.81 frames.], batch size: 32, lr: 1.62e-03
2022-05-03 15:22:31,098 INFO [train.py:715] (5/8) Epoch 0, batch 16400, loss[loss=0.1876, simple_loss=0.2573, pruned_loss=0.05902, over 4943.00 frames.], tot_loss[loss=0.2269, simple_loss=0.2783, pruned_loss=0.08772, over 973220.98 frames.], batch size: 21, lr: 1.62e-03
2022-05-03 15:23:11,044 INFO [train.py:715] (5/8) Epoch 0, batch 16450, loss[loss=0.214, simple_loss=0.2732, pruned_loss=0.07745, over 4795.00 frames.], tot_loss[loss=0.2275, simple_loss=0.2787, pruned_loss=0.08815, over 972908.27 frames.], batch size: 21, lr: 1.62e-03
2022-05-03 15:23:51,581 INFO [train.py:715] (5/8) Epoch 0, batch 16500, loss[loss=0.2413, simple_loss=0.2908, pruned_loss=0.09593, over 4892.00 frames.], tot_loss[loss=0.2292, simple_loss=0.2801, pruned_loss=0.08917, over 972767.91 frames.], batch size: 22, lr: 1.62e-03
2022-05-03 15:24:31,535 INFO [train.py:715] (5/8) Epoch 0, batch 16550, loss[loss=0.1973, simple_loss=0.2583, pruned_loss=0.06815, over 4983.00 frames.], tot_loss[loss=0.2283, simple_loss=0.2792, pruned_loss=0.0887, over 973239.75 frames.], batch size: 25, lr: 1.61e-03
2022-05-03 15:25:11,223 INFO [train.py:715] (5/8) Epoch 0, batch 16600, loss[loss=0.2443, simple_loss=0.2967, pruned_loss=0.09593, over 4862.00 frames.], tot_loss[loss=0.2281, simple_loss=0.2788, pruned_loss=0.08864, over 972942.69 frames.], batch size: 20, lr: 1.61e-03
2022-05-03 15:25:50,675 INFO [train.py:715] (5/8) Epoch 0, batch 16650, loss[loss=0.2221, simple_loss=0.2706, pruned_loss=0.08674, over 4858.00 frames.], tot_loss[loss=0.2269, simple_loss=0.278, pruned_loss=0.08791, over 972666.41 frames.], batch size: 30, lr: 1.61e-03
2022-05-03 15:26:30,539 INFO [train.py:715] (5/8) Epoch 0, batch 16700, loss[loss=0.253, simple_loss=0.2913, pruned_loss=0.1074, over 4777.00 frames.], tot_loss[loss=0.2267, simple_loss=0.2779, pruned_loss=0.08776, over 972561.24 frames.], batch size: 17, lr: 1.61e-03
2022-05-03 15:27:09,632 INFO [train.py:715] (5/8) Epoch 0, batch 16750, loss[loss=0.2381, simple_loss=0.2684, pruned_loss=0.1039, over 4777.00 frames.], tot_loss[loss=0.2283, simple_loss=0.2788, pruned_loss=0.08892, over 972470.82 frames.], batch size: 17, lr: 1.60e-03
2022-05-03 15:27:48,778 INFO [train.py:715] (5/8) Epoch 0, batch 16800, loss[loss=0.215, simple_loss=0.2687, pruned_loss=0.08063, over 4763.00 frames.], tot_loss[loss=0.2262, simple_loss=0.2771, pruned_loss=0.08764, over 971798.16 frames.], batch size: 12, lr: 1.60e-03
2022-05-03 15:28:28,414 INFO [train.py:715] (5/8) Epoch 0, batch 16850, loss[loss=0.2112, simple_loss=0.2636, pruned_loss=0.07941, over 4772.00 frames.], tot_loss[loss=0.2263, simple_loss=0.2776, pruned_loss=0.08751, over 971018.94 frames.], batch size: 14, lr: 1.60e-03
2022-05-03 15:29:08,023 INFO [train.py:715] (5/8) Epoch 0, batch 16900, loss[loss=0.2664, simple_loss=0.3187, pruned_loss=0.1071, over 4927.00 frames.], tot_loss[loss=0.2273, simple_loss=0.2787, pruned_loss=0.08799, over 971547.14 frames.], batch size: 18, lr: 1.60e-03
2022-05-03 15:29:47,263 INFO [train.py:715] (5/8) Epoch 0, batch 16950, loss[loss=0.1807, simple_loss=0.2297, pruned_loss=0.06584, over 4711.00 frames.], tot_loss[loss=0.2271, simple_loss=0.2788, pruned_loss=0.08772, over 971453.95 frames.], batch size: 12, lr: 1.60e-03
2022-05-03 15:30:27,231 INFO [train.py:715] (5/8) Epoch 0, batch 17000, loss[loss=0.1995, simple_loss=0.2524, pruned_loss=0.07334, over 4795.00 frames.], tot_loss[loss=0.2263, simple_loss=0.2781, pruned_loss=0.08726, over 971823.33 frames.], batch size: 12, lr: 1.59e-03
2022-05-03 15:31:07,728 INFO [train.py:715] (5/8) Epoch 0, batch 17050, loss[loss=0.2393, simple_loss=0.2806, pruned_loss=0.09899, over 4816.00 frames.], tot_loss[loss=0.227, simple_loss=0.2786, pruned_loss=0.08771, over 972081.13 frames.], batch size: 21, lr: 1.59e-03
2022-05-03 15:31:47,483 INFO [train.py:715] (5/8) Epoch 0, batch 17100, loss[loss=0.25, simple_loss=0.3002, pruned_loss=0.09989, over 4783.00 frames.], tot_loss[loss=0.2272, simple_loss=0.2789, pruned_loss=0.08777, over 972092.19 frames.], batch size: 14, lr: 1.59e-03
2022-05-03 15:32:26,650 INFO [train.py:715] (5/8) Epoch 0, batch 17150, loss[loss=0.2068, simple_loss=0.2636, pruned_loss=0.07497, over 4822.00 frames.], tot_loss[loss=0.2271, simple_loss=0.279, pruned_loss=0.08763, over 972212.01 frames.], batch size: 26, lr: 1.59e-03
2022-05-03 15:33:06,904 INFO [train.py:715] (5/8) Epoch 0, batch 17200, loss[loss=0.2525, simple_loss=0.2973, pruned_loss=0.1039, over 4901.00 frames.], tot_loss[loss=0.2268, simple_loss=0.2785, pruned_loss=0.08757, over 971511.95 frames.], batch size: 17, lr: 1.58e-03
2022-05-03 15:33:46,678 INFO [train.py:715] (5/8) Epoch 0, batch 17250, loss[loss=0.2392, simple_loss=0.2745, pruned_loss=0.102, over 4975.00 frames.], tot_loss[loss=0.2272, simple_loss=0.2783, pruned_loss=0.08803, over 971370.02 frames.], batch size: 14, lr: 1.58e-03
2022-05-03 15:34:26,234 INFO [train.py:715] (5/8) Epoch 0, batch 17300, loss[loss=0.1993, simple_loss=0.261, pruned_loss=0.06882, over 4924.00 frames.], tot_loss[loss=0.2262, simple_loss=0.2772, pruned_loss=0.08763, over 971346.61 frames.], batch size: 23, lr: 1.58e-03
2022-05-03 15:35:06,290 INFO [train.py:715] (5/8) Epoch 0, batch 17350, loss[loss=0.2139, simple_loss=0.2646, pruned_loss=0.08163, over 4924.00 frames.], tot_loss[loss=0.2256, simple_loss=0.2765, pruned_loss=0.08731, over 971308.31 frames.], batch size: 29, lr: 1.58e-03
2022-05-03 15:35:46,526 INFO [train.py:715] (5/8) Epoch 0, batch 17400, loss[loss=0.1801, simple_loss=0.2385, pruned_loss=0.06091, over 4822.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2765, pruned_loss=0.08685, over 971342.31 frames.], batch size: 13, lr: 1.58e-03
2022-05-03 15:36:26,419 INFO [train.py:715] (5/8) Epoch 0, batch 17450, loss[loss=0.203, simple_loss=0.2588, pruned_loss=0.07361, over 4987.00 frames.], tot_loss[loss=0.2257, simple_loss=0.277, pruned_loss=0.08718, over 971052.88 frames.], batch size: 31, lr: 1.57e-03
2022-05-03 15:37:07,031 INFO [train.py:715] (5/8) Epoch 0, batch 17500, loss[loss=0.2396, simple_loss=0.2856, pruned_loss=0.09676, over 4909.00 frames.], tot_loss[loss=0.226, simple_loss=0.2775, pruned_loss=0.0873, over 971682.42 frames.], batch size: 17, lr: 1.57e-03
2022-05-03 15:37:47,460 INFO [train.py:715] (5/8) Epoch 0, batch 17550, loss[loss=0.177, simple_loss=0.2368, pruned_loss=0.05864, over 4965.00 frames.], tot_loss[loss=0.2251, simple_loss=0.2765, pruned_loss=0.08683, over 971303.51 frames.], batch size: 35, lr: 1.57e-03
2022-05-03 15:38:27,018 INFO [train.py:715] (5/8) Epoch 0, batch 17600, loss[loss=0.1978, simple_loss=0.2588, pruned_loss=0.06843, over 4888.00 frames.], tot_loss[loss=0.2238, simple_loss=0.2753, pruned_loss=0.08619, over 972302.29 frames.], batch size: 22, lr: 1.57e-03
2022-05-03 15:39:06,941 INFO [train.py:715] (5/8) Epoch 0, batch 17650, loss[loss=0.2257, simple_loss=0.2691, pruned_loss=0.09112, over 4983.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2753, pruned_loss=0.08579, over 972631.36 frames.], batch size: 24, lr: 1.57e-03
2022-05-03 15:39:47,479 INFO [train.py:715] (5/8) Epoch 0, batch 17700, loss[loss=0.2145, simple_loss=0.2766, pruned_loss=0.07617, over 4963.00 frames.], tot_loss[loss=0.2229, simple_loss=0.2751, pruned_loss=0.08539, over 972685.34 frames.], batch size: 15, lr: 1.56e-03
2022-05-03 15:40:27,378 INFO [train.py:715] (5/8) Epoch 0, batch 17750, loss[loss=0.2568, simple_loss=0.3029, pruned_loss=0.1053, over 4881.00 frames.], tot_loss[loss=0.2234, simple_loss=0.2753, pruned_loss=0.08569, over 972217.61 frames.], batch size: 39, lr: 1.56e-03
2022-05-03 15:41:07,053 INFO [train.py:715] (5/8) Epoch 0, batch 17800, loss[loss=0.2265, simple_loss=0.2762, pruned_loss=0.08841, over 4807.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2763, pruned_loss=0.08594, over 973839.26 frames.], batch size: 25, lr: 1.56e-03
2022-05-03 15:41:47,858 INFO [train.py:715] (5/8) Epoch 0, batch 17850, loss[loss=0.1957, simple_loss=0.2566, pruned_loss=0.06746, over 4855.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2758, pruned_loss=0.08561, over 972842.91 frames.], batch size: 16, lr: 1.56e-03
2022-05-03 15:42:28,481 INFO [train.py:715] (5/8) Epoch 0, batch 17900, loss[loss=0.2961, simple_loss=0.3103, pruned_loss=0.1409, over 4851.00 frames.], tot_loss[loss=0.2238, simple_loss=0.2758, pruned_loss=0.08584, over 972375.89 frames.], batch size: 13, lr: 1.56e-03
2022-05-03 15:43:07,987 INFO [train.py:715] (5/8) Epoch 0, batch 17950, loss[loss=0.1867, simple_loss=0.234, pruned_loss=0.06965, over 4846.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2755, pruned_loss=0.08576, over 972273.44 frames.], batch size: 13, lr: 1.55e-03
2022-05-03 15:43:48,222 INFO [train.py:715] (5/8) Epoch 0, batch 18000, loss[loss=0.1772, simple_loss=0.2342, pruned_loss=0.0601, over 4786.00 frames.], tot_loss[loss=0.224, simple_loss=0.276, pruned_loss=0.08602, over 973163.80 frames.], batch size: 12, lr: 1.55e-03
2022-05-03 15:43:48,222 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 15:43:57,826 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.141, simple_loss=0.228, pruned_loss=0.02706, over 914524.00 frames.
2022-05-03 15:44:38,089 INFO [train.py:715] (5/8) Epoch 0, batch 18050, loss[loss=0.2011, simple_loss=0.2703, pruned_loss=0.06591, over 4684.00 frames.], tot_loss[loss=0.2248, simple_loss=0.2765, pruned_loss=0.08656, over 972193.59 frames.], batch size: 15, lr: 1.55e-03
2022-05-03 15:45:18,345 INFO [train.py:715] (5/8) Epoch 0, batch 18100, loss[loss=0.2383, simple_loss=0.2895, pruned_loss=0.09357, over 4774.00 frames.], tot_loss[loss=0.2253, simple_loss=0.277, pruned_loss=0.08678, over 972958.55 frames.], batch size: 18, lr: 1.55e-03
2022-05-03 15:45:58,159 INFO [train.py:715] (5/8) Epoch 0, batch 18150, loss[loss=0.2698, simple_loss=0.3238, pruned_loss=0.1079, over 4896.00 frames.], tot_loss[loss=0.2255, simple_loss=0.2775, pruned_loss=0.08672, over 973228.63 frames.], batch size: 19, lr: 1.55e-03
2022-05-03 15:46:37,570 INFO [train.py:715] (5/8) Epoch 0, batch 18200, loss[loss=0.2067, simple_loss=0.2693, pruned_loss=0.07207, over 4748.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2768, pruned_loss=0.08575, over 972900.70 frames.], batch size: 12, lr: 1.54e-03
2022-05-03 15:47:17,742 INFO [train.py:715] (5/8) Epoch 0, batch 18250, loss[loss=0.2665, simple_loss=0.3083, pruned_loss=0.1124, over 4820.00 frames.], tot_loss[loss=0.2245, simple_loss=0.2767, pruned_loss=0.08609, over 973124.98 frames.], batch size: 13, lr: 1.54e-03
2022-05-03 15:47:59,028 INFO [train.py:715] (5/8) Epoch 0, batch 18300, loss[loss=0.2342, simple_loss=0.2739, pruned_loss=0.09729, over 4805.00 frames.], tot_loss[loss=0.2236, simple_loss=0.2759, pruned_loss=0.08567, over 971856.92 frames.], batch size: 13, lr: 1.54e-03
2022-05-03 15:48:38,800 INFO [train.py:715] (5/8) Epoch 0, batch 18350, loss[loss=0.2053, simple_loss=0.2696, pruned_loss=0.0705, over 4820.00 frames.], tot_loss[loss=0.2234, simple_loss=0.2754, pruned_loss=0.08572, over 970622.34 frames.], batch size: 26, lr: 1.54e-03
2022-05-03 15:49:19,076 INFO [train.py:715] (5/8) Epoch 0, batch 18400, loss[loss=0.1895, simple_loss=0.2539, pruned_loss=0.06257, over 4803.00 frames.], tot_loss[loss=0.2254, simple_loss=0.2774, pruned_loss=0.08666, over 970465.70 frames.], batch size: 24, lr: 1.54e-03
2022-05-03 15:49:59,576 INFO [train.py:715] (5/8) Epoch 0, batch 18450, loss[loss=0.1736, simple_loss=0.2527, pruned_loss=0.04721, over 4881.00 frames.], tot_loss[loss=0.2247, simple_loss=0.2771, pruned_loss=0.08614, over 971041.47 frames.], batch size: 19, lr: 1.53e-03
2022-05-03 15:50:39,243 INFO [train.py:715] (5/8) Epoch 0, batch 18500, loss[loss=0.2323, simple_loss=0.2883, pruned_loss=0.08813, over 4766.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2763, pruned_loss=0.08519, over 971022.86 frames.], batch size: 14, lr: 1.53e-03
2022-05-03 15:51:19,773 INFO [train.py:715] (5/8) Epoch 0, batch 18550, loss[loss=0.2228, simple_loss=0.28, pruned_loss=0.08276, over 4968.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2748, pruned_loss=0.0848, over 970818.15 frames.], batch size: 35, lr: 1.53e-03
2022-05-03 15:52:00,081 INFO [train.py:715] (5/8) Epoch 0, batch 18600, loss[loss=0.2665, simple_loss=0.3021, pruned_loss=0.1155, over 4893.00 frames.], tot_loss[loss=0.2221, simple_loss=0.2748, pruned_loss=0.08473, over 971187.05 frames.], batch size: 22, lr: 1.53e-03
2022-05-03 15:52:40,196 INFO [train.py:715] (5/8) Epoch 0, batch 18650, loss[loss=0.1639, simple_loss=0.2253, pruned_loss=0.05127, over 4948.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2748, pruned_loss=0.08393, over 971337.73 frames.], batch size: 18, lr: 1.53e-03
2022-05-03 15:53:19,596 INFO [train.py:715] (5/8) Epoch 0, batch 18700, loss[loss=0.236, simple_loss=0.2883, pruned_loss=0.0919, over 4856.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2756, pruned_loss=0.08395, over 971764.58 frames.], batch size: 30, lr: 1.52e-03
2022-05-03 15:53:59,904 INFO [train.py:715] (5/8) Epoch 0, batch 18750, loss[loss=0.1924, simple_loss=0.2414, pruned_loss=0.07174, over 4700.00 frames.], tot_loss[loss=0.221, simple_loss=0.2748, pruned_loss=0.08359, over 971179.03 frames.], batch size: 15, lr: 1.52e-03
2022-05-03 15:54:41,175 INFO [train.py:715] (5/8) Epoch 0, batch 18800, loss[loss=0.2309, simple_loss=0.2784, pruned_loss=0.09166, over 4985.00 frames.], tot_loss[loss=0.2208, simple_loss=0.2745, pruned_loss=0.08353, over 971747.62 frames.], batch size: 28, lr: 1.52e-03
2022-05-03 15:55:20,399 INFO [train.py:715] (5/8) Epoch 0, batch 18850, loss[loss=0.2097, simple_loss=0.2711, pruned_loss=0.07418, over 4701.00 frames.], tot_loss[loss=0.221, simple_loss=0.2747, pruned_loss=0.0837, over 971408.71 frames.], batch size: 15, lr: 1.52e-03
2022-05-03 15:56:01,304 INFO [train.py:715] (5/8) Epoch 0, batch 18900, loss[loss=0.1905, simple_loss=0.2511, pruned_loss=0.06493, over 4926.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2741, pruned_loss=0.0834, over 971298.88 frames.], batch size: 18, lr: 1.52e-03
2022-05-03 15:56:41,738 INFO [train.py:715] (5/8) Epoch 0, batch 18950, loss[loss=0.2176, simple_loss=0.2553, pruned_loss=0.08989, over 4748.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2731, pruned_loss=0.08261, over 971497.04 frames.], batch size: 12, lr: 1.52e-03
2022-05-03 15:57:21,399 INFO [train.py:715] (5/8) Epoch 0, batch 19000, loss[loss=0.218, simple_loss=0.2687, pruned_loss=0.08366, over 4976.00 frames.], tot_loss[loss=0.22, simple_loss=0.2739, pruned_loss=0.08302, over 970998.25 frames.], batch size: 15, lr: 1.51e-03
2022-05-03 15:58:01,846 INFO [train.py:715] (5/8) Epoch 0, batch 19050, loss[loss=0.2171, simple_loss=0.2789, pruned_loss=0.07764, over 4830.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2742, pruned_loss=0.08307, over 971810.79 frames.], batch size: 30, lr: 1.51e-03
2022-05-03 15:58:42,180 INFO [train.py:715] (5/8) Epoch 0, batch 19100, loss[loss=0.2264, simple_loss=0.2729, pruned_loss=0.08995, over 4759.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2744, pruned_loss=0.08331, over 971893.80 frames.], batch size: 16, lr: 1.51e-03
2022-05-03 15:59:22,500 INFO [train.py:715] (5/8) Epoch 0, batch 19150, loss[loss=0.2166, simple_loss=0.2787, pruned_loss=0.07725, over 4811.00 frames.], tot_loss[loss=0.2209, simple_loss=0.2746, pruned_loss=0.08363, over 972675.32 frames.], batch size: 25, lr: 1.51e-03
2022-05-03 16:00:01,716 INFO [train.py:715] (5/8) Epoch 0, batch 19200, loss[loss=0.1807, simple_loss=0.2517, pruned_loss=0.05489, over 4933.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2742, pruned_loss=0.08296, over 972615.19 frames.], batch size: 23, lr: 1.51e-03
2022-05-03 16:00:42,579 INFO [train.py:715] (5/8) Epoch 0, batch 19250, loss[loss=0.2292, simple_loss=0.2899, pruned_loss=0.08429, over 4913.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2743, pruned_loss=0.08353, over 973397.71 frames.], batch size: 18, lr: 1.50e-03
2022-05-03 16:01:23,361 INFO [train.py:715] (5/8) Epoch 0, batch 19300, loss[loss=0.2186, simple_loss=0.2862, pruned_loss=0.07548, over 4940.00 frames.], tot_loss[loss=0.2216, simple_loss=0.2752, pruned_loss=0.08395, over 973782.08 frames.], batch size: 21, lr: 1.50e-03
2022-05-03 16:02:03,052 INFO [train.py:715] (5/8) Epoch 0, batch 19350, loss[loss=0.2136, simple_loss=0.2718, pruned_loss=0.07768, over 4974.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2749, pruned_loss=0.08398, over 973960.83 frames.], batch size: 14, lr: 1.50e-03
2022-05-03 16:02:43,218 INFO [train.py:715] (5/8) Epoch 0, batch 19400, loss[loss=0.1602, simple_loss=0.2244, pruned_loss=0.048, over 4941.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2741, pruned_loss=0.08327, over 973424.83 frames.], batch size: 21, lr: 1.50e-03
2022-05-03 16:03:24,062 INFO [train.py:715] (5/8) Epoch 0, batch 19450, loss[loss=0.1866, simple_loss=0.2491, pruned_loss=0.06205, over 4840.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2731, pruned_loss=0.08318, over 973074.55 frames.], batch size: 15, lr: 1.50e-03
2022-05-03 16:04:03,574 INFO [train.py:715] (5/8) Epoch 0, batch 19500, loss[loss=0.198, simple_loss=0.264, pruned_loss=0.06597, over 4782.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2743, pruned_loss=0.08392, over 972420.33 frames.], batch size: 18, lr: 1.50e-03
2022-05-03 16:04:42,925 INFO [train.py:715] (5/8) Epoch 0, batch 19550, loss[loss=0.2233, simple_loss=0.2784, pruned_loss=0.08408, over 4972.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2737, pruned_loss=0.0833, over 972032.33 frames.], batch size: 21, lr: 1.49e-03
2022-05-03 16:05:23,274 INFO [train.py:715] (5/8) Epoch 0, batch 19600, loss[loss=0.2432, simple_loss=0.2871, pruned_loss=0.09964, over 4856.00 frames.], tot_loss[loss=0.2206, simple_loss=0.274, pruned_loss=0.08355, over 971631.63 frames.], batch size: 32, lr: 1.49e-03
2022-05-03 16:06:03,059 INFO [train.py:715] (5/8) Epoch 0, batch 19650, loss[loss=0.2427, simple_loss=0.3018, pruned_loss=0.09182, over 4951.00 frames.], tot_loss[loss=0.2208, simple_loss=0.274, pruned_loss=0.0838, over 971751.76 frames.], batch size: 40, lr: 1.49e-03
2022-05-03 16:06:42,546 INFO [train.py:715] (5/8) Epoch 0, batch 19700, loss[loss=0.2533, simple_loss=0.2955, pruned_loss=0.1056, over 4772.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2743, pruned_loss=0.08389, over 972113.99 frames.], batch size: 17, lr: 1.49e-03
2022-05-03 16:07:22,615 INFO [train.py:715] (5/8) Epoch 0, batch 19750, loss[loss=0.3282, simple_loss=0.3512, pruned_loss=0.1526, over 4895.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2734, pruned_loss=0.0835, over 972132.86 frames.], batch size: 17, lr: 1.49e-03
2022-05-03 16:08:02,296 INFO [train.py:715] (5/8) Epoch 0, batch 19800, loss[loss=0.2177, simple_loss=0.2685, pruned_loss=0.08347, over 4817.00 frames.], tot_loss[loss=0.2217, simple_loss=0.2743, pruned_loss=0.08455, over 971726.93 frames.], batch size: 25, lr: 1.48e-03
2022-05-03 16:08:42,107 INFO [train.py:715] (5/8) Epoch 0, batch 19850, loss[loss=0.1619, simple_loss=0.2285, pruned_loss=0.04768, over 4831.00 frames.], tot_loss[loss=0.2213, simple_loss=0.274, pruned_loss=0.08429, over 971577.65 frames.], batch size: 26, lr: 1.48e-03
2022-05-03 16:09:21,341 INFO [train.py:715] (5/8) Epoch 0, batch 19900, loss[loss=0.2291, simple_loss=0.2811, pruned_loss=0.08852, over 4915.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2737, pruned_loss=0.08373, over 971088.15 frames.], batch size: 23, lr: 1.48e-03
2022-05-03 16:10:02,117 INFO [train.py:715] (5/8) Epoch 0, batch 19950, loss[loss=0.1751, simple_loss=0.2361, pruned_loss=0.05712, over 4805.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2737, pruned_loss=0.08348, over 971921.88 frames.], batch size: 21, lr: 1.48e-03
2022-05-03 16:10:42,167 INFO [train.py:715] (5/8) Epoch 0, batch 20000, loss[loss=0.2638, simple_loss=0.3039, pruned_loss=0.1118, over 4911.00 frames.], tot_loss[loss=0.2196, simple_loss=0.2733, pruned_loss=0.08296, over 971972.36 frames.], batch size: 17, lr: 1.48e-03
2022-05-03 16:11:21,520 INFO [train.py:715] (5/8) Epoch 0, batch 20050, loss[loss=0.1955, simple_loss=0.2636, pruned_loss=0.06371, over 4871.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2715, pruned_loss=0.08142, over 972574.67 frames.], batch size: 22, lr: 1.48e-03
2022-05-03 16:12:01,700 INFO [train.py:715] (5/8) Epoch 0, batch 20100, loss[loss=0.2242, simple_loss=0.2761, pruned_loss=0.08616, over 4839.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2728, pruned_loss=0.08215, over 973141.37 frames.], batch size: 13, lr: 1.47e-03
2022-05-03 16:12:41,690 INFO [train.py:715] (5/8) Epoch 0, batch 20150, loss[loss=0.2315, simple_loss=0.2866, pruned_loss=0.08824, over 4994.00 frames.], tot_loss[loss=0.2179, simple_loss=0.2719, pruned_loss=0.082, over 973628.63 frames.], batch size: 14, lr: 1.47e-03
2022-05-03 16:13:21,724 INFO [train.py:715] (5/8) Epoch 0, batch 20200, loss[loss=0.198, simple_loss=0.2595, pruned_loss=0.06822, over 4960.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2713, pruned_loss=0.08163, over 974791.49 frames.], batch size: 24, lr: 1.47e-03
2022-05-03 16:14:01,254 INFO [train.py:715] (5/8) Epoch 0, batch 20250, loss[loss=0.2108, simple_loss=0.2643, pruned_loss=0.0787, over 4823.00 frames.], tot_loss[loss=0.2186, simple_loss=0.2726, pruned_loss=0.08229, over 974967.97 frames.], batch size: 26, lr: 1.47e-03
2022-05-03 16:14:42,004 INFO [train.py:715] (5/8) Epoch 0, batch 20300, loss[loss=0.1961, simple_loss=0.2536, pruned_loss=0.06927, over 4957.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2731, pruned_loss=0.08216, over 973939.94 frames.], batch size: 21, lr: 1.47e-03
2022-05-03 16:15:21,889 INFO [train.py:715] (5/8) Epoch 0, batch 20350, loss[loss=0.2531, simple_loss=0.3102, pruned_loss=0.09804, over 4888.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2716, pruned_loss=0.08107, over 973688.97 frames.], batch size: 22, lr: 1.47e-03
2022-05-03 16:16:00,951 INFO [train.py:715] (5/8) Epoch 0, batch 20400, loss[loss=0.2544, simple_loss=0.3059, pruned_loss=0.1015, over 4886.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2715, pruned_loss=0.08112, over 973428.08 frames.], batch size: 16, lr: 1.46e-03
2022-05-03 16:16:40,897 INFO [train.py:715] (5/8) Epoch 0, batch 20450, loss[loss=0.1953, simple_loss=0.2431, pruned_loss=0.0737, over 4780.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2728, pruned_loss=0.08193, over 973902.01 frames.], batch size: 14, lr: 1.46e-03
2022-05-03 16:17:20,435 INFO [train.py:715] (5/8) Epoch 0, batch 20500, loss[loss=0.2073, simple_loss=0.267, pruned_loss=0.07386, over 4911.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2734, pruned_loss=0.08245, over 973822.51 frames.], batch size: 18, lr: 1.46e-03
2022-05-03 16:18:00,498 INFO [train.py:715] (5/8) Epoch 0, batch 20550, loss[loss=0.2301, simple_loss=0.2811, pruned_loss=0.08953, over 4804.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2745, pruned_loss=0.08319, over 973062.94 frames.], batch size: 13, lr: 1.46e-03
2022-05-03 16:18:39,954 INFO [train.py:715] (5/8) Epoch 0, batch 20600, loss[loss=0.2171, simple_loss=0.282, pruned_loss=0.07612, over 4887.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2739, pruned_loss=0.08234, over 972807.33 frames.], batch size: 16, lr: 1.46e-03
2022-05-03 16:19:19,648 INFO [train.py:715] (5/8) Epoch 0, batch 20650, loss[loss=0.223, simple_loss=0.2769, pruned_loss=0.08454, over 4918.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2744, pruned_loss=0.08268, over 973255.87 frames.], batch size: 18, lr: 1.46e-03
2022-05-03 16:20:00,378 INFO [train.py:715] (5/8) Epoch 0, batch 20700, loss[loss=0.2534, simple_loss=0.3003, pruned_loss=0.1033, over 4965.00 frames.], tot_loss[loss=0.2194, simple_loss=0.2736, pruned_loss=0.08266, over 972491.31 frames.], batch size: 24, lr: 1.45e-03
2022-05-03 16:20:39,701 INFO [train.py:715] (5/8) Epoch 0, batch 20750, loss[loss=0.1855, simple_loss=0.2551, pruned_loss=0.05796, over 4773.00 frames.], tot_loss[loss=0.2192, simple_loss=0.2733, pruned_loss=0.08256, over 972008.20 frames.], batch size: 18, lr: 1.45e-03
2022-05-03 16:21:19,880 INFO [train.py:715] (5/8) Epoch 0, batch 20800, loss[loss=0.2054, simple_loss=0.2616, pruned_loss=0.07456, over 4970.00 frames.], tot_loss[loss=0.219, simple_loss=0.2734, pruned_loss=0.08227, over 971503.77 frames.], batch size: 24, lr: 1.45e-03
2022-05-03 16:21:59,638 INFO [train.py:715] (5/8) Epoch 0, batch 20850, loss[loss=0.2466, simple_loss=0.3108, pruned_loss=0.09113, over 4902.00 frames.], tot_loss[loss=0.218, simple_loss=0.2724, pruned_loss=0.08178, over 971788.30 frames.], batch size: 19, lr: 1.45e-03
2022-05-03 16:22:39,125 INFO [train.py:715] (5/8) Epoch 0, batch 20900, loss[loss=0.1807, simple_loss=0.247, pruned_loss=0.05717, over 4966.00 frames.], tot_loss[loss=0.218, simple_loss=0.2724, pruned_loss=0.08179, over 971328.35 frames.], batch size: 28, lr: 1.45e-03
2022-05-03 16:23:19,651 INFO [train.py:715] (5/8) Epoch 0, batch 20950, loss[loss=0.233, simple_loss=0.2869, pruned_loss=0.08957, over 4919.00 frames.], tot_loss[loss=0.2188, simple_loss=0.2733, pruned_loss=0.08214, over 971891.21 frames.], batch size: 17, lr: 1.45e-03
2022-05-03 16:24:00,682 INFO [train.py:715] (5/8) Epoch 0, batch 21000, loss[loss=0.2464, simple_loss=0.2933, pruned_loss=0.09974, over 4852.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2746, pruned_loss=0.08327, over 971638.49 frames.], batch size: 30, lr: 1.44e-03
2022-05-03 16:24:00,683 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 16:24:16,219 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1386, simple_loss=0.2255, pruned_loss=0.02581, over 914524.00 frames.
2022-05-03 16:24:57,015 INFO [train.py:715] (5/8) Epoch 0, batch 21050, loss[loss=0.1695, simple_loss=0.2393, pruned_loss=0.04982, over 4973.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2749, pruned_loss=0.08386, over 972385.06 frames.], batch size: 24, lr: 1.44e-03
2022-05-03 16:25:36,594 INFO [train.py:715] (5/8) Epoch 0, batch 21100, loss[loss=0.16, simple_loss=0.2303, pruned_loss=0.04491, over 4787.00 frames.], tot_loss[loss=0.2197, simple_loss=0.2737, pruned_loss=0.08292, over 971860.77 frames.], batch size: 12, lr: 1.44e-03
2022-05-03 16:26:16,948 INFO [train.py:715] (5/8) Epoch 0, batch 21150, loss[loss=0.226, simple_loss=0.2872, pruned_loss=0.08245, over 4869.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2742, pruned_loss=0.083, over 972452.94 frames.], batch size: 16, lr: 1.44e-03
2022-05-03 16:26:56,812 INFO [train.py:715] (5/8) Epoch 0, batch 21200, loss[loss=0.2492, simple_loss=0.2966, pruned_loss=0.1009, over 4970.00 frames.], tot_loss[loss=0.2203, simple_loss=0.2747, pruned_loss=0.08294, over 972387.10 frames.], batch size: 15, lr: 1.44e-03
2022-05-03 16:27:37,351 INFO [train.py:715] (5/8) Epoch 0, batch 21250, loss[loss=0.2618, simple_loss=0.3049, pruned_loss=0.1094, over 4936.00 frames.], tot_loss[loss=0.2191, simple_loss=0.2737, pruned_loss=0.08229, over 972384.95 frames.], batch size: 18, lr: 1.44e-03
2022-05-03 16:28:17,123 INFO [train.py:715] (5/8) Epoch 0, batch 21300, loss[loss=0.2477, simple_loss=0.3044, pruned_loss=0.09551, over 4915.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2728, pruned_loss=0.08199, over 971382.22 frames.], batch size: 23, lr: 1.43e-03
2022-05-03 16:28:57,542 INFO [train.py:715] (5/8) Epoch 0, batch 21350, loss[loss=0.2454, simple_loss=0.2986, pruned_loss=0.0961, over 4964.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2727, pruned_loss=0.08199, over 971361.86 frames.], batch size: 15, lr: 1.43e-03
2022-05-03 16:29:38,279 INFO [train.py:715] (5/8) Epoch 0, batch 21400, loss[loss=0.1688, simple_loss=0.233, pruned_loss=0.05229, over 4764.00 frames.], tot_loss[loss=0.216, simple_loss=0.271, pruned_loss=0.08054, over 971199.89 frames.], batch size: 18, lr: 1.43e-03
2022-05-03 16:30:17,947 INFO [train.py:715] (5/8) Epoch 0, batch 21450, loss[loss=0.1833, simple_loss=0.247, pruned_loss=0.05976, over 4803.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2709, pruned_loss=0.08045, over 971271.69 frames.], batch size: 18, lr: 1.43e-03
2022-05-03 16:30:57,791 INFO [train.py:715] (5/8) Epoch 0, batch 21500, loss[loss=0.2318, simple_loss=0.2749, pruned_loss=0.09434, over 4850.00 frames.], tot_loss[loss=0.2154, simple_loss=0.2707, pruned_loss=0.08008, over 971216.42 frames.], batch size: 32, lr: 1.43e-03
2022-05-03 16:31:38,007 INFO [train.py:715] (5/8) Epoch 0, batch 21550, loss[loss=0.2234, simple_loss=0.2786, pruned_loss=0.08407, over 4909.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2716, pruned_loss=0.08076, over 972297.21 frames.], batch size: 17, lr: 1.43e-03
2022-05-03 16:32:18,472 INFO [train.py:715] (5/8) Epoch 0, batch 21600, loss[loss=0.2387, simple_loss=0.2799, pruned_loss=0.0987, over 4795.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2717, pruned_loss=0.08099, over 971075.49 frames.], batch size: 18, lr: 1.42e-03
2022-05-03 16:32:58,234 INFO [train.py:715] (5/8) Epoch 0, batch 21650, loss[loss=0.2175, simple_loss=0.2789, pruned_loss=0.07806, over 4969.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2731, pruned_loss=0.082, over 971600.81 frames.], batch size: 24, lr: 1.42e-03
2022-05-03 16:33:39,048 INFO [train.py:715] (5/8) Epoch 0, batch 21700, loss[loss=0.2485, simple_loss=0.3054, pruned_loss=0.09584, over 4959.00 frames.], tot_loss[loss=0.2183, simple_loss=0.2726, pruned_loss=0.08199, over 971438.15 frames.], batch size: 24, lr: 1.42e-03
2022-05-03 16:34:19,205 INFO [train.py:715] (5/8) Epoch 0, batch 21750, loss[loss=0.2326, simple_loss=0.2848, pruned_loss=0.09024, over 4643.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2722, pruned_loss=0.08165, over 971253.52 frames.], batch size: 13, lr: 1.42e-03
2022-05-03 16:34:58,788 INFO [train.py:715] (5/8) Epoch 0, batch 21800, loss[loss=0.2393, simple_loss=0.2863, pruned_loss=0.09611, over 4858.00 frames.], tot_loss[loss=0.218, simple_loss=0.2723, pruned_loss=0.08181, over 971499.88 frames.], batch size: 20, lr: 1.42e-03
2022-05-03 16:35:38,619 INFO [train.py:715] (5/8) Epoch 0, batch 21850, loss[loss=0.2552, simple_loss=0.3023, pruned_loss=0.104, over 4770.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2726, pruned_loss=0.0818, over 971518.01 frames.], batch size: 18, lr: 1.42e-03
2022-05-03 16:36:19,092 INFO [train.py:715] (5/8) Epoch 0, batch 21900, loss[loss=0.1903, simple_loss=0.2544, pruned_loss=0.06311, over 4856.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2728, pruned_loss=0.08197, over 972024.93 frames.], batch size: 20, lr: 1.42e-03
2022-05-03 16:36:59,000 INFO [train.py:715] (5/8) Epoch 0, batch 21950, loss[loss=0.1764, simple_loss=0.2336, pruned_loss=0.05961, over 4829.00 frames.], tot_loss[loss=0.2187, simple_loss=0.2728, pruned_loss=0.08228, over 971914.05 frames.], batch size: 13, lr: 1.41e-03
2022-05-03 16:37:38,285 INFO [train.py:715] (5/8) Epoch 0, batch 22000, loss[loss=0.2527, simple_loss=0.2929, pruned_loss=0.1062, over 4878.00 frames.], tot_loss[loss=0.218, simple_loss=0.2722, pruned_loss=0.08192, over 972535.89 frames.], batch size: 16, lr: 1.41e-03
2022-05-03 16:38:18,445 INFO [train.py:715] (5/8) Epoch 0, batch 22050, loss[loss=0.2206, simple_loss=0.2743, pruned_loss=0.0834, over 4897.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2711, pruned_loss=0.08091, over 973252.38 frames.], batch size: 22, lr: 1.41e-03
2022-05-03 16:38:58,602 INFO [train.py:715] (5/8) Epoch 0, batch 22100, loss[loss=0.2228, simple_loss=0.2895, pruned_loss=0.07805, over 4788.00 frames.], tot_loss[loss=0.215, simple_loss=0.2704, pruned_loss=0.07982, over 973462.10 frames.], batch size: 17, lr: 1.41e-03
2022-05-03 16:39:38,117 INFO [train.py:715] (5/8) Epoch 0, batch 22150, loss[loss=0.2296, simple_loss=0.2841, pruned_loss=0.08755, over 4958.00 frames.], tot_loss[loss=0.2165, simple_loss=0.2715, pruned_loss=0.08075, over 972343.38 frames.], batch size: 35, lr: 1.41e-03
2022-05-03 16:40:17,923 INFO [train.py:715] (5/8) Epoch 0, batch 22200, loss[loss=0.1706, simple_loss=0.2175, pruned_loss=0.06185, over 4821.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2716, pruned_loss=0.08132, over 972568.25 frames.], batch size: 12, lr: 1.41e-03
2022-05-03 16:40:58,312 INFO [train.py:715] (5/8) Epoch 0, batch 22250, loss[loss=0.2066, simple_loss=0.2492, pruned_loss=0.08204, over 4908.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2722, pruned_loss=0.08171, over 972734.97 frames.], batch size: 17, lr: 1.40e-03
2022-05-03 16:41:38,376 INFO [train.py:715] (5/8) Epoch 0, batch 22300, loss[loss=0.2384, simple_loss=0.2948, pruned_loss=0.09102, over 4957.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2717, pruned_loss=0.08119, over 972859.66 frames.], batch size: 21, lr: 1.40e-03
2022-05-03 16:42:18,084 INFO [train.py:715] (5/8) Epoch 0, batch 22350, loss[loss=0.2851, simple_loss=0.3394, pruned_loss=0.1154, over 4776.00 frames.], tot_loss[loss=0.2168, simple_loss=0.2717, pruned_loss=0.08091, over 973484.84 frames.], batch size: 14, lr: 1.40e-03
2022-05-03 16:42:58,247 INFO [train.py:715] (5/8) Epoch 0, batch 22400, loss[loss=0.2278, simple_loss=0.2824, pruned_loss=0.08661, over 4857.00 frames.], tot_loss[loss=0.2156, simple_loss=0.2711, pruned_loss=0.08003, over 973187.59 frames.], batch size: 32, lr: 1.40e-03
2022-05-03 16:43:38,082 INFO [train.py:715] (5/8) Epoch 0, batch 22450, loss[loss=0.1514, simple_loss=0.2091, pruned_loss=0.04685, over 4730.00 frames.], tot_loss[loss=0.217, simple_loss=0.2722, pruned_loss=0.08093, over 972837.85 frames.], batch size: 12, lr: 1.40e-03
2022-05-03 16:44:17,445 INFO [train.py:715] (5/8) Epoch 0, batch 22500, loss[loss=0.1766, simple_loss=0.2381, pruned_loss=0.0575, over 4744.00 frames.], tot_loss[loss=0.2162, simple_loss=0.2714, pruned_loss=0.08055, over 971879.81 frames.], batch size: 12, lr: 1.40e-03
2022-05-03 16:44:57,228 INFO [train.py:715] (5/8) Epoch 0, batch 22550, loss[loss=0.1821, simple_loss=0.2437, pruned_loss=0.06028, over 4853.00 frames.], tot_loss[loss=0.2166, simple_loss=0.2714, pruned_loss=0.08086, over 971836.64 frames.], batch size: 20, lr: 1.40e-03
2022-05-03 16:45:37,436 INFO [train.py:715] (5/8) Epoch 0, batch 22600, loss[loss=0.2165, simple_loss=0.2729, pruned_loss=0.08004, over 4864.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2708, pruned_loss=0.08037, over 971838.43 frames.], batch size: 16, lr: 1.39e-03
2022-05-03 16:46:18,081 INFO [train.py:715] (5/8) Epoch 0, batch 22650, loss[loss=0.2044, simple_loss=0.2597, pruned_loss=0.0746, over 4968.00 frames.], tot_loss[loss=0.2158, simple_loss=0.2706, pruned_loss=0.08044, over 971563.05 frames.], batch size: 14, lr: 1.39e-03
2022-05-03 16:46:57,298 INFO [train.py:715] (5/8) Epoch 0, batch 22700, loss[loss=0.2122, simple_loss=0.2639, pruned_loss=0.08026, over 4973.00 frames.], tot_loss[loss=0.2145, simple_loss=0.27, pruned_loss=0.07946, over 971905.57 frames.], batch size: 15, lr: 1.39e-03
2022-05-03 16:47:37,373 INFO [train.py:715] (5/8) Epoch 0, batch 22750, loss[loss=0.2315, simple_loss=0.2851, pruned_loss=0.08899, over 4781.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2704, pruned_loss=0.07959, over 971786.68 frames.], batch size: 18, lr: 1.39e-03
2022-05-03 16:48:17,856 INFO [train.py:715] (5/8) Epoch 0, batch 22800, loss[loss=0.2181, simple_loss=0.2683, pruned_loss=0.08394, over 4987.00 frames.], tot_loss[loss=0.216, simple_loss=0.271, pruned_loss=0.08046, over 972947.01 frames.], batch size: 25, lr: 1.39e-03
2022-05-03 16:48:57,453 INFO [train.py:715] (5/8) Epoch 0, batch 22850, loss[loss=0.1714, simple_loss=0.2357, pruned_loss=0.05356, over 4855.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2701, pruned_loss=0.07919, over 972851.01 frames.], batch size: 32, lr: 1.39e-03
2022-05-03 16:49:37,562 INFO [train.py:715] (5/8) Epoch 0, batch 22900, loss[loss=0.2221, simple_loss=0.2872, pruned_loss=0.07846, over 4875.00 frames.], tot_loss[loss=0.214, simple_loss=0.2692, pruned_loss=0.07936, over 972853.82 frames.], batch size: 22, lr: 1.39e-03
2022-05-03 16:50:17,830 INFO [train.py:715] (5/8) Epoch 0, batch 22950, loss[loss=0.2647, simple_loss=0.316, pruned_loss=0.1068, over 4909.00 frames.], tot_loss[loss=0.2133, simple_loss=0.2688, pruned_loss=0.07894, over 972603.91 frames.], batch size: 18, lr: 1.38e-03
2022-05-03 16:50:58,463 INFO [train.py:715] (5/8) Epoch 0, batch 23000, loss[loss=0.2474, simple_loss=0.2971, pruned_loss=0.09883, over 4893.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2687, pruned_loss=0.0792, over 971977.11 frames.], batch size: 22, lr: 1.38e-03
2022-05-03 16:51:37,479 INFO [train.py:715] (5/8) Epoch 0, batch 23050, loss[loss=0.1855, simple_loss=0.2548, pruned_loss=0.05806, over 4860.00 frames.], tot_loss[loss=0.2142, simple_loss=0.2693, pruned_loss=0.07958, over 972470.44 frames.], batch size: 20, lr: 1.38e-03
2022-05-03 16:52:18,416 INFO [train.py:715] (5/8) Epoch 0, batch 23100, loss[loss=0.2572, simple_loss=0.2977, pruned_loss=0.1083, over 4964.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2695, pruned_loss=0.07982, over 972171.36 frames.], batch size: 15, lr: 1.38e-03
2022-05-03 16:52:59,441 INFO [train.py:715] (5/8) Epoch 0, batch 23150, loss[loss=0.2005, simple_loss=0.2648, pruned_loss=0.06805, over 4916.00 frames.], tot_loss[loss=0.212, simple_loss=0.2676, pruned_loss=0.07817, over 971554.01 frames.], batch size: 17, lr: 1.38e-03
2022-05-03 16:53:39,182 INFO [train.py:715] (5/8) Epoch 0, batch 23200, loss[loss=0.2116, simple_loss=0.2766, pruned_loss=0.07332, over 4965.00 frames.], tot_loss[loss=0.2122, simple_loss=0.268, pruned_loss=0.07823, over 971739.34 frames.], batch size: 24, lr: 1.38e-03
2022-05-03 16:54:19,750 INFO [train.py:715] (5/8) Epoch 0, batch 23250, loss[loss=0.2055, simple_loss=0.2678, pruned_loss=0.07154, over 4907.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2695, pruned_loss=0.07915, over 971449.32 frames.], batch size: 18, lr: 1.38e-03
2022-05-03 16:55:00,174 INFO [train.py:715] (5/8) Epoch 0, batch 23300, loss[loss=0.2347, simple_loss=0.292, pruned_loss=0.08868, over 4933.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2697, pruned_loss=0.07909, over 971450.30 frames.], batch size: 21, lr: 1.37e-03
2022-05-03 16:55:40,655 INFO [train.py:715] (5/8) Epoch 0, batch 23350, loss[loss=0.2096, simple_loss=0.2702, pruned_loss=0.07448, over 4787.00 frames.], tot_loss[loss=0.215, simple_loss=0.2705, pruned_loss=0.07974, over 971953.08 frames.], batch size: 17, lr: 1.37e-03
2022-05-03 16:56:21,254 INFO [train.py:715] (5/8) Epoch 0, batch 23400, loss[loss=0.194, simple_loss=0.2665, pruned_loss=0.06078, over 4929.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2706, pruned_loss=0.07952, over 972765.66 frames.], batch size: 18, lr: 1.37e-03
2022-05-03 16:57:02,269 INFO [train.py:715] (5/8) Epoch 0, batch 23450, loss[loss=0.2759, simple_loss=0.3234, pruned_loss=0.1142, over 4868.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2705, pruned_loss=0.07966, over 972217.75 frames.], batch size: 32, lr: 1.37e-03
2022-05-03 16:57:43,369 INFO [train.py:715] (5/8) Epoch 0, batch 23500, loss[loss=0.2615, simple_loss=0.3182, pruned_loss=0.1024, over 4795.00 frames.], tot_loss[loss=0.2153, simple_loss=0.271, pruned_loss=0.07981, over 972158.27 frames.], batch size: 14, lr: 1.37e-03
2022-05-03 16:58:23,221 INFO [train.py:715] (5/8) Epoch 0, batch 23550, loss[loss=0.1962, simple_loss=0.2651, pruned_loss=0.06362, over 4925.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2712, pruned_loss=0.08046, over 971408.60 frames.], batch size: 23, lr: 1.37e-03
2022-05-03 16:59:04,085 INFO [train.py:715] (5/8) Epoch 0, batch 23600, loss[loss=0.2035, simple_loss=0.2621, pruned_loss=0.0724, over 4875.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2708, pruned_loss=0.07971, over 970700.75 frames.], batch size: 32, lr: 1.37e-03
2022-05-03 16:59:44,346 INFO [train.py:715] (5/8) Epoch 0, batch 23650, loss[loss=0.2144, simple_loss=0.2874, pruned_loss=0.07066, over 4983.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2714, pruned_loss=0.08001, over 971749.81 frames.], batch size: 28, lr: 1.36e-03
2022-05-03 17:00:24,466 INFO [train.py:715] (5/8) Epoch 0, batch 23700, loss[loss=0.2134, simple_loss=0.2641, pruned_loss=0.08142, over 4978.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2708, pruned_loss=0.07986, over 972187.57 frames.], batch size: 14, lr: 1.36e-03
2022-05-03 17:01:03,660 INFO [train.py:715] (5/8) Epoch 0, batch 23750, loss[loss=0.2334, simple_loss=0.2714, pruned_loss=0.09771, over 4907.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2713, pruned_loss=0.08023, over 972811.42 frames.], batch size: 17, lr: 1.36e-03
2022-05-03 17:01:43,659 INFO [train.py:715] (5/8) Epoch 0, batch 23800, loss[loss=0.2123, simple_loss=0.2636, pruned_loss=0.08054, over 4926.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2705, pruned_loss=0.07987, over 972611.40 frames.], batch size: 29, lr: 1.36e-03
2022-05-03 17:02:24,148 INFO [train.py:715] (5/8) Epoch 0, batch 23850, loss[loss=0.1965, simple_loss=0.2463, pruned_loss=0.07333, over 4749.00 frames.], tot_loss[loss=0.215, simple_loss=0.2704, pruned_loss=0.07983, over 971547.27 frames.], batch size: 16, lr: 1.36e-03
2022-05-03 17:03:03,306 INFO [train.py:715] (5/8) Epoch 0, batch 23900, loss[loss=0.1475, simple_loss=0.2207, pruned_loss=0.03716, over 4761.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2681, pruned_loss=0.07826, over 970694.52 frames.], batch size: 19, lr: 1.36e-03
2022-05-03 17:03:43,451 INFO [train.py:715] (5/8) Epoch 0, batch 23950, loss[loss=0.203, simple_loss=0.2644, pruned_loss=0.07081, over 4927.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2678, pruned_loss=0.07751, over 970491.53 frames.], batch size: 18, lr: 1.36e-03
2022-05-03 17:04:26,564 INFO [train.py:715] (5/8) Epoch 0, batch 24000, loss[loss=0.2519, simple_loss=0.305, pruned_loss=0.09938, over 4968.00 frames.], tot_loss[loss=0.2143, simple_loss=0.27, pruned_loss=0.07932, over 971431.48 frames.], batch size: 15, lr: 1.35e-03
2022-05-03 17:04:26,565 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 17:04:40,850 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1357, simple_loss=0.2226, pruned_loss=0.02435, over 914524.00 frames.
2022-05-03 17:05:21,167 INFO [train.py:715] (5/8) Epoch 0, batch 24050, loss[loss=0.2023, simple_loss=0.2703, pruned_loss=0.0671, over 4711.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2696, pruned_loss=0.07901, over 971528.40 frames.], batch size: 15, lr: 1.35e-03
2022-05-03 17:06:00,594 INFO [train.py:715] (5/8) Epoch 0, batch 24100, loss[loss=0.242, simple_loss=0.2848, pruned_loss=0.09959, over 4840.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2696, pruned_loss=0.07875, over 972204.52 frames.], batch size: 32, lr: 1.35e-03
2022-05-03 17:06:40,579 INFO [train.py:715] (5/8) Epoch 0, batch 24150, loss[loss=0.2525, simple_loss=0.3085, pruned_loss=0.09827, over 4779.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2697, pruned_loss=0.07864, over 971460.30 frames.], batch size: 18, lr: 1.35e-03
2022-05-03 17:07:20,606 INFO [train.py:715] (5/8) Epoch 0, batch 24200, loss[loss=0.2665, simple_loss=0.3052, pruned_loss=0.1139, over 4848.00 frames.], tot_loss[loss=0.2139, simple_loss=0.2697, pruned_loss=0.07898, over 971481.20 frames.], batch size: 32, lr: 1.35e-03
2022-05-03 17:08:01,226 INFO [train.py:715] (5/8) Epoch 0, batch 24250, loss[loss=0.1844, simple_loss=0.241, pruned_loss=0.06387, over 4672.00 frames.], tot_loss[loss=0.2127, simple_loss=0.2687, pruned_loss=0.07832, over 971116.38 frames.], batch size: 13, lr: 1.35e-03
2022-05-03 17:08:40,830 INFO [train.py:715] (5/8) Epoch 0, batch 24300, loss[loss=0.2702, simple_loss=0.334, pruned_loss=0.1031, over 4930.00 frames.], tot_loss[loss=0.2132, simple_loss=0.2689, pruned_loss=0.07869, over 969974.94 frames.], batch size: 18, lr: 1.35e-03
2022-05-03 17:09:21,009 INFO [train.py:715] (5/8) Epoch 0, batch 24350, loss[loss=0.1883, simple_loss=0.2465, pruned_loss=0.06502, over 4818.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2703, pruned_loss=0.07929, over 971336.62 frames.], batch size: 25, lr: 1.35e-03
2022-05-03 17:10:01,415 INFO [train.py:715] (5/8) Epoch 0, batch 24400, loss[loss=0.1798, simple_loss=0.236, pruned_loss=0.06182, over 4860.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2698, pruned_loss=0.07875, over 970873.70 frames.], batch size: 32, lr: 1.34e-03
2022-05-03 17:10:40,936 INFO [train.py:715] (5/8) Epoch 0, batch 24450, loss[loss=0.2103, simple_loss=0.273, pruned_loss=0.07383, over 4713.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2694, pruned_loss=0.07911, over 971107.79 frames.], batch size: 15, lr: 1.34e-03
2022-05-03 17:11:21,047 INFO [train.py:715] (5/8) Epoch 0, batch 24500, loss[loss=0.1764, simple_loss=0.2447, pruned_loss=0.054, over 4691.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2686, pruned_loss=0.07877, over 972040.34 frames.], batch size: 15, lr: 1.34e-03
2022-05-03 17:12:01,316 INFO [train.py:715] (5/8) Epoch 0, batch 24550, loss[loss=0.2357, simple_loss=0.2815, pruned_loss=0.09499, over 4900.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2677, pruned_loss=0.07847, over 971626.55 frames.], batch size: 19, lr: 1.34e-03
2022-05-03 17:12:41,513 INFO [train.py:715] (5/8) Epoch 0, batch 24600, loss[loss=0.3044, simple_loss=0.3364, pruned_loss=0.1362, over 4761.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2694, pruned_loss=0.07907, over 971763.47 frames.], batch size: 16, lr: 1.34e-03
2022-05-03 17:13:20,990 INFO [train.py:715] (5/8) Epoch 0, batch 24650, loss[loss=0.2388, simple_loss=0.2973, pruned_loss=0.09017, over 4879.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2682, pruned_loss=0.07829, over 971199.26 frames.], batch size: 22, lr: 1.34e-03
2022-05-03 17:14:01,416 INFO [train.py:715] (5/8) Epoch 0, batch 24700, loss[loss=0.2251, simple_loss=0.284, pruned_loss=0.08313, over 4972.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2684, pruned_loss=0.07812, over 971394.26 frames.], batch size: 25, lr: 1.34e-03
2022-05-03 17:14:42,118 INFO [train.py:715] (5/8) Epoch 0, batch 24750, loss[loss=0.2172, simple_loss=0.2795, pruned_loss=0.07747, over 4860.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2675, pruned_loss=0.07757, over 971413.37 frames.], batch size: 30, lr: 1.33e-03
2022-05-03 17:15:21,174 INFO [train.py:715] (5/8) Epoch 0, batch 24800, loss[loss=0.2065, simple_loss=0.2632, pruned_loss=0.07495, over 4854.00 frames.], tot_loss[loss=0.211, simple_loss=0.2671, pruned_loss=0.07745, over 971744.67 frames.], batch size: 32, lr: 1.33e-03
2022-05-03 17:16:01,310 INFO [train.py:715] (5/8) Epoch 0, batch 24850, loss[loss=0.1962, simple_loss=0.2621, pruned_loss=0.06517, over 4767.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2669, pruned_loss=0.07727, over 971133.81 frames.], batch size: 19, lr: 1.33e-03
2022-05-03 17:16:41,586 INFO [train.py:715] (5/8) Epoch 0, batch 24900, loss[loss=0.1915, simple_loss=0.2524, pruned_loss=0.06529, over 4917.00 frames.], tot_loss[loss=0.2111, simple_loss=0.267, pruned_loss=0.07767, over 970947.60 frames.], batch size: 18, lr: 1.33e-03
2022-05-03 17:17:21,627 INFO [train.py:715] (5/8) Epoch 0, batch 24950, loss[loss=0.2196, simple_loss=0.2752, pruned_loss=0.08202, over 4980.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2656, pruned_loss=0.07695, over 971606.23 frames.], batch size: 39, lr: 1.33e-03
2022-05-03 17:18:01,149 INFO [train.py:715] (5/8) Epoch 0, batch 25000, loss[loss=0.206, simple_loss=0.2694, pruned_loss=0.07133, over 4988.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2656, pruned_loss=0.07641, over 972701.71 frames.], batch size: 15, lr: 1.33e-03
2022-05-03 17:18:41,404 INFO [train.py:715] (5/8) Epoch 0, batch 25050, loss[loss=0.226, simple_loss=0.284, pruned_loss=0.08402, over 4649.00 frames.], tot_loss[loss=0.209, simple_loss=0.2657, pruned_loss=0.07619, over 972657.30 frames.], batch size: 13, lr: 1.33e-03
2022-05-03 17:19:21,100 INFO [train.py:715] (5/8) Epoch 0, batch 25100, loss[loss=0.2316, simple_loss=0.2937, pruned_loss=0.08472, over 4893.00 frames.], tot_loss[loss=0.2103, simple_loss=0.267, pruned_loss=0.07679, over 972723.50 frames.], batch size: 22, lr: 1.33e-03
2022-05-03 17:20:00,596 INFO [train.py:715] (5/8) Epoch 0, batch 25150, loss[loss=0.2338, simple_loss=0.2888, pruned_loss=0.08935, over 4939.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2665, pruned_loss=0.07643, over 972727.56 frames.], batch size: 39, lr: 1.32e-03
2022-05-03 17:20:41,131 INFO [train.py:715] (5/8) Epoch 0, batch 25200, loss[loss=0.2552, simple_loss=0.3109, pruned_loss=0.09969, over 4955.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2657, pruned_loss=0.07623, over 972321.33 frames.], batch size: 24, lr: 1.32e-03
2022-05-03 17:21:21,698 INFO [train.py:715] (5/8) Epoch 0, batch 25250, loss[loss=0.1943, simple_loss=0.2464, pruned_loss=0.07109, over 4827.00 frames.], tot_loss[loss=0.2082, simple_loss=0.265, pruned_loss=0.07573, over 971745.32 frames.], batch size: 12, lr: 1.32e-03
2022-05-03 17:22:02,260 INFO [train.py:715] (5/8) Epoch 0, batch 25300, loss[loss=0.2244, simple_loss=0.2697, pruned_loss=0.08958, over 4896.00 frames.], tot_loss[loss=0.2083, simple_loss=0.265, pruned_loss=0.07583, over 972055.11 frames.], batch size: 19, lr: 1.32e-03
2022-05-03 17:22:42,092 INFO [train.py:715] (5/8) Epoch 0, batch 25350, loss[loss=0.156, simple_loss=0.2183, pruned_loss=0.0468, over 4773.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2661, pruned_loss=0.0761, over 971620.73 frames.], batch size: 12, lr: 1.32e-03
2022-05-03 17:23:22,551 INFO [train.py:715] (5/8) Epoch 0, batch 25400, loss[loss=0.2054, simple_loss=0.252, pruned_loss=0.07945, over 4982.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2653, pruned_loss=0.07578, over 971965.43 frames.], batch size: 25, lr: 1.32e-03
2022-05-03 17:24:02,722 INFO [train.py:715] (5/8) Epoch 0, batch 25450, loss[loss=0.1577, simple_loss=0.2175, pruned_loss=0.04895, over 4825.00 frames.], tot_loss[loss=0.2081, simple_loss=0.265, pruned_loss=0.0756, over 971886.27 frames.], batch size: 13, lr: 1.32e-03
2022-05-03 17:24:41,710 INFO [train.py:715] (5/8) Epoch 0, batch 25500, loss[loss=0.1609, simple_loss=0.2318, pruned_loss=0.04497, over 4920.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2647, pruned_loss=0.07494, over 972240.14 frames.], batch size: 23, lr: 1.32e-03
2022-05-03 17:25:22,420 INFO [train.py:715] (5/8) Epoch 0, batch 25550, loss[loss=0.1656, simple_loss=0.238, pruned_loss=0.04659, over 4902.00 frames.], tot_loss[loss=0.2073, simple_loss=0.265, pruned_loss=0.0748, over 972612.57 frames.], batch size: 19, lr: 1.31e-03
2022-05-03 17:26:02,028 INFO [train.py:715] (5/8) Epoch 0, batch 25600, loss[loss=0.1959, simple_loss=0.2532, pruned_loss=0.06934, over 4895.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2644, pruned_loss=0.07439, over 972487.83 frames.], batch size: 19, lr: 1.31e-03
2022-05-03 17:26:41,735 INFO [train.py:715] (5/8) Epoch 0, batch 25650, loss[loss=0.1714, simple_loss=0.2414, pruned_loss=0.05076, over 4931.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2639, pruned_loss=0.07391, over 972471.18 frames.], batch size: 29, lr: 1.31e-03
2022-05-03 17:27:21,451 INFO [train.py:715] (5/8) Epoch 0, batch 25700, loss[loss=0.1936, simple_loss=0.2619, pruned_loss=0.0626, over 4856.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2636, pruned_loss=0.07351, over 972244.84 frames.], batch size: 20, lr: 1.31e-03
2022-05-03 17:28:01,731 INFO [train.py:715] (5/8) Epoch 0, batch 25750, loss[loss=0.1988, simple_loss=0.2628, pruned_loss=0.0674, over 4857.00 frames.], tot_loss[loss=0.206, simple_loss=0.2642, pruned_loss=0.07393, over 972337.13 frames.], batch size: 15, lr: 1.31e-03
2022-05-03 17:28:41,510 INFO [train.py:715] (5/8) Epoch 0, batch 25800, loss[loss=0.2002, simple_loss=0.2627, pruned_loss=0.06889, over 4776.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2653, pruned_loss=0.0747, over 972282.50 frames.], batch size: 18, lr: 1.31e-03
2022-05-03 17:29:20,753 INFO [train.py:715] (5/8) Epoch 0, batch 25850, loss[loss=0.2187, simple_loss=0.2794, pruned_loss=0.07902, over 4802.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2659, pruned_loss=0.07578, over 973201.19 frames.], batch size: 21, lr: 1.31e-03
2022-05-03 17:30:01,471 INFO [train.py:715] (5/8) Epoch 0, batch 25900, loss[loss=0.2243, simple_loss=0.2795, pruned_loss=0.08453, over 4832.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2657, pruned_loss=0.07594, over 972742.15 frames.], batch size: 13, lr: 1.31e-03
2022-05-03 17:30:41,214 INFO [train.py:715] (5/8) Epoch 0, batch 25950, loss[loss=0.1917, simple_loss=0.2567, pruned_loss=0.06336, over 4940.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2661, pruned_loss=0.07608, over 972144.17 frames.], batch size: 21, lr: 1.30e-03
2022-05-03 17:31:21,224 INFO [train.py:715] (5/8) Epoch 0, batch 26000, loss[loss=0.2126, simple_loss=0.2665, pruned_loss=0.07933, over 4866.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2662, pruned_loss=0.07611, over 972760.60 frames.], batch size: 16, lr: 1.30e-03
2022-05-03 17:32:01,169 INFO [train.py:715] (5/8) Epoch 0, batch 26050, loss[loss=0.192, simple_loss=0.2492, pruned_loss=0.06739, over 4971.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2658, pruned_loss=0.07558, over 972714.82 frames.], batch size: 35, lr: 1.30e-03
2022-05-03 17:32:41,633 INFO [train.py:715] (5/8) Epoch 0, batch 26100, loss[loss=0.2323, simple_loss=0.2905, pruned_loss=0.08703, over 4945.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2658, pruned_loss=0.07527, over 972230.10 frames.], batch size: 35, lr: 1.30e-03
2022-05-03 17:33:21,953 INFO [train.py:715] (5/8) Epoch 0, batch 26150, loss[loss=0.2465, simple_loss=0.2861, pruned_loss=0.1034, over 4962.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2667, pruned_loss=0.07611, over 972335.16 frames.], batch size: 24, lr: 1.30e-03
2022-05-03 17:34:00,855 INFO [train.py:715] (5/8) Epoch 0, batch 26200, loss[loss=0.1632, simple_loss=0.2314, pruned_loss=0.0475, over 4916.00 frames.], tot_loss[loss=0.207, simple_loss=0.2649, pruned_loss=0.07459, over 970896.70 frames.], batch size: 18, lr: 1.30e-03
2022-05-03 17:34:41,485 INFO [train.py:715] (5/8) Epoch 0, batch 26250, loss[loss=0.2053, simple_loss=0.2612, pruned_loss=0.0747, over 4835.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2649, pruned_loss=0.07474, over 970111.44 frames.], batch size: 15, lr: 1.30e-03
2022-05-03 17:35:21,435 INFO [train.py:715] (5/8) Epoch 0, batch 26300, loss[loss=0.1875, simple_loss=0.2594, pruned_loss=0.05783, over 4935.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2649, pruned_loss=0.07509, over 970477.30 frames.], batch size: 21, lr: 1.30e-03
2022-05-03 17:36:01,276 INFO [train.py:715] (5/8) Epoch 0, batch 26350, loss[loss=0.2093, simple_loss=0.2702, pruned_loss=0.07418, over 4978.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2654, pruned_loss=0.07514, over 971490.83 frames.], batch size: 14, lr: 1.30e-03
2022-05-03 17:36:41,216 INFO [train.py:715] (5/8) Epoch 0, batch 26400, loss[loss=0.2351, simple_loss=0.2797, pruned_loss=0.09522, over 4789.00 frames.], tot_loss[loss=0.208, simple_loss=0.2653, pruned_loss=0.07535, over 971958.73 frames.], batch size: 17, lr: 1.29e-03
2022-05-03 17:37:21,339 INFO [train.py:715] (5/8) Epoch 0, batch 26450, loss[loss=0.1693, simple_loss=0.2398, pruned_loss=0.04939, over 4841.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2651, pruned_loss=0.07479, over 971759.19 frames.], batch size: 30, lr: 1.29e-03
2022-05-03 17:38:02,048 INFO [train.py:715] (5/8) Epoch 0, batch 26500, loss[loss=0.1756, simple_loss=0.24, pruned_loss=0.05561, over 4877.00 frames.], tot_loss[loss=0.2079, simple_loss=0.2654, pruned_loss=0.07519, over 972537.62 frames.], batch size: 32, lr: 1.29e-03
2022-05-03 17:38:41,411 INFO [train.py:715] (5/8) Epoch 0, batch 26550, loss[loss=0.153, simple_loss=0.2226, pruned_loss=0.04173, over 4797.00 frames.], tot_loss[loss=0.207, simple_loss=0.2649, pruned_loss=0.07451, over 971863.35 frames.], batch size: 21, lr: 1.29e-03
2022-05-03 17:39:21,082 INFO [train.py:715] (5/8) Epoch 0, batch 26600, loss[loss=0.2518, simple_loss=0.3008, pruned_loss=0.1013, over 4928.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2661, pruned_loss=0.07569, over 972807.06 frames.], batch size: 29, lr: 1.29e-03
2022-05-03 17:40:01,331 INFO [train.py:715] (5/8) Epoch 0, batch 26650, loss[loss=0.1926, simple_loss=0.253, pruned_loss=0.06606, over 4813.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2658, pruned_loss=0.07571, over 973280.60 frames.], batch size: 25, lr: 1.29e-03
2022-05-03 17:40:40,794 INFO [train.py:715] (5/8) Epoch 0, batch 26700, loss[loss=0.2737, simple_loss=0.3204, pruned_loss=0.1135, over 4920.00 frames.], tot_loss[loss=0.209, simple_loss=0.2663, pruned_loss=0.07585, over 973149.31 frames.], batch size: 23, lr: 1.29e-03
2022-05-03 17:41:20,819 INFO [train.py:715] (5/8) Epoch 0, batch 26750, loss[loss=0.1923, simple_loss=0.2415, pruned_loss=0.07159, over 4858.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2654, pruned_loss=0.07505, over 973516.45 frames.], batch size: 13, lr: 1.29e-03
2022-05-03 17:42:01,246 INFO [train.py:715] (5/8) Epoch 0, batch 26800, loss[loss=0.2095, simple_loss=0.2701, pruned_loss=0.07445, over 4864.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2642, pruned_loss=0.07428, over 973182.29 frames.], batch size: 16, lr: 1.28e-03
2022-05-03 17:42:41,669 INFO [train.py:715] (5/8) Epoch 0, batch 26850, loss[loss=0.2102, simple_loss=0.2703, pruned_loss=0.0751, over 4968.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2639, pruned_loss=0.07389, over 972672.21 frames.], batch size: 21, lr: 1.28e-03
2022-05-03 17:43:21,530 INFO [train.py:715] (5/8) Epoch 0, batch 26900, loss[loss=0.167, simple_loss=0.2339, pruned_loss=0.0501, over 4868.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2639, pruned_loss=0.07411, over 972581.22 frames.], batch size: 20, lr: 1.28e-03
2022-05-03 17:44:02,262 INFO [train.py:715] (5/8) Epoch 0, batch 26950, loss[loss=0.3036, simple_loss=0.3241, pruned_loss=0.1416, over 4914.00 frames.], tot_loss[loss=0.2074, simple_loss=0.265, pruned_loss=0.07491, over 973049.65 frames.], batch size: 18, lr: 1.28e-03
2022-05-03 17:44:42,416 INFO [train.py:715] (5/8) Epoch 0, batch 27000, loss[loss=0.1958, simple_loss=0.2544, pruned_loss=0.06859, over 4901.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2645, pruned_loss=0.07433, over 972203.43 frames.], batch size: 19, lr: 1.28e-03
2022-05-03 17:44:42,417 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 17:44:51,200 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1338, simple_loss=0.2208, pruned_loss=0.02337, over 914524.00 frames.
2022-05-03 17:45:31,269 INFO [train.py:715] (5/8) Epoch 0, batch 27050, loss[loss=0.1881, simple_loss=0.2559, pruned_loss=0.06011, over 4770.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2638, pruned_loss=0.07387, over 972711.94 frames.], batch size: 14, lr: 1.28e-03
2022-05-03 17:46:10,742 INFO [train.py:715] (5/8) Epoch 0, batch 27100, loss[loss=0.2538, simple_loss=0.3023, pruned_loss=0.1027, over 4944.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2651, pruned_loss=0.07552, over 972433.36 frames.], batch size: 21, lr: 1.28e-03
2022-05-03 17:46:51,329 INFO [train.py:715] (5/8) Epoch 0, batch 27150, loss[loss=0.2041, simple_loss=0.2721, pruned_loss=0.06805, over 4916.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2653, pruned_loss=0.07557, over 972201.73 frames.], batch size: 23, lr: 1.28e-03
2022-05-03 17:47:31,712 INFO [train.py:715] (5/8) Epoch 0, batch 27200, loss[loss=0.2254, simple_loss=0.2722, pruned_loss=0.08933, over 4731.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2648, pruned_loss=0.07513, over 972368.56 frames.], batch size: 16, lr: 1.28e-03
2022-05-03 17:48:11,810 INFO [train.py:715] (5/8) Epoch 0, batch 27250, loss[loss=0.1955, simple_loss=0.258, pruned_loss=0.06646, over 4870.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2648, pruned_loss=0.07571, over 971254.65 frames.], batch size: 16, lr: 1.27e-03
2022-05-03 17:48:51,959 INFO [train.py:715] (5/8) Epoch 0, batch 27300, loss[loss=0.2157, simple_loss=0.283, pruned_loss=0.07416, over 4805.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2641, pruned_loss=0.07507, over 971404.38 frames.], batch size: 24, lr: 1.27e-03
2022-05-03 17:49:31,862 INFO [train.py:715] (5/8) Epoch 0, batch 27350, loss[loss=0.2348, simple_loss=0.2943, pruned_loss=0.0877, over 4967.00 frames.], tot_loss[loss=0.2068, simple_loss=0.264, pruned_loss=0.07482, over 971818.36 frames.], batch size: 28, lr: 1.27e-03
2022-05-03 17:50:11,824 INFO [train.py:715] (5/8) Epoch 0, batch 27400, loss[loss=0.2121, simple_loss=0.2629, pruned_loss=0.08064, over 4850.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2638, pruned_loss=0.0744, over 971325.98 frames.], batch size: 32, lr: 1.27e-03
2022-05-03 17:50:51,093 INFO [train.py:715] (5/8) Epoch 0, batch 27450, loss[loss=0.1787, simple_loss=0.2309, pruned_loss=0.06329, over 4828.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2634, pruned_loss=0.07383, over 970659.85 frames.], batch size: 13, lr: 1.27e-03
2022-05-03 17:51:31,236 INFO [train.py:715] (5/8) Epoch 0, batch 27500, loss[loss=0.2049, simple_loss=0.2549, pruned_loss=0.07751, over 4785.00 frames.], tot_loss[loss=0.2048, simple_loss=0.263, pruned_loss=0.07329, over 970571.61 frames.], batch size: 18, lr: 1.27e-03
2022-05-03 17:52:11,049 INFO [train.py:715] (5/8) Epoch 0, batch 27550, loss[loss=0.188, simple_loss=0.2638, pruned_loss=0.05611, over 4807.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2631, pruned_loss=0.07294, over 971159.05 frames.], batch size: 25, lr: 1.27e-03
2022-05-03 17:52:50,538 INFO [train.py:715] (5/8) Epoch 0, batch 27600, loss[loss=0.2016, simple_loss=0.2746, pruned_loss=0.06433, over 4771.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2632, pruned_loss=0.07299, over 970819.58 frames.], batch size: 12, lr: 1.27e-03
2022-05-03 17:53:29,968 INFO [train.py:715] (5/8) Epoch 0, batch 27650, loss[loss=0.2012, simple_loss=0.2722, pruned_loss=0.06507, over 4923.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2633, pruned_loss=0.07319, over 971127.10 frames.], batch size: 23, lr: 1.27e-03
2022-05-03 17:54:09,971 INFO [train.py:715] (5/8) Epoch 0, batch 27700, loss[loss=0.2169, simple_loss=0.2715, pruned_loss=0.08112, over 4948.00 frames.], tot_loss[loss=0.2048, simple_loss=0.2631, pruned_loss=0.07324, over 971308.62 frames.], batch size: 21, lr: 1.26e-03
2022-05-03 17:54:50,341 INFO [train.py:715] (5/8) Epoch 0, batch 27750, loss[loss=0.2373, simple_loss=0.2878, pruned_loss=0.09345, over 4962.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2644, pruned_loss=0.07441, over 971886.45 frames.], batch size: 35, lr: 1.26e-03
2022-05-03 17:55:30,111 INFO [train.py:715] (5/8) Epoch 0, batch 27800, loss[loss=0.188, simple_loss=0.2521, pruned_loss=0.06192, over 4805.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2645, pruned_loss=0.07402, over 972319.40 frames.], batch size: 24, lr: 1.26e-03
2022-05-03 17:56:10,357 INFO [train.py:715] (5/8) Epoch 0, batch 27850, loss[loss=0.2138, simple_loss=0.2836, pruned_loss=0.07196, over 4955.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2641, pruned_loss=0.07387, over 972132.31 frames.], batch size: 24, lr: 1.26e-03
2022-05-03 17:56:49,941 INFO [train.py:715] (5/8) Epoch 0, batch 27900, loss[loss=0.2551, simple_loss=0.2972, pruned_loss=0.1065, over 4780.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2644, pruned_loss=0.07406, over 972225.95 frames.], batch size: 18, lr: 1.26e-03
2022-05-03 17:57:29,408 INFO [train.py:715] (5/8) Epoch 0, batch 27950, loss[loss=0.2304, simple_loss=0.2632, pruned_loss=0.09876, over 4903.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2637, pruned_loss=0.07432, over 972558.08 frames.], batch size: 19, lr: 1.26e-03
2022-05-03 17:58:09,430 INFO [train.py:715] (5/8) Epoch 0, batch 28000, loss[loss=0.1609, simple_loss=0.2222, pruned_loss=0.04982, over 4897.00 frames.], tot_loss[loss=0.2063, simple_loss=0.264, pruned_loss=0.07432, over 972915.17 frames.], batch size: 17, lr: 1.26e-03
2022-05-03 17:58:49,657 INFO [train.py:715] (5/8) Epoch 0, batch 28050, loss[loss=0.2498, simple_loss=0.2906, pruned_loss=0.1045, over 4940.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2641, pruned_loss=0.07428, over 973434.88 frames.], batch size: 23, lr: 1.26e-03
2022-05-03 17:59:29,707 INFO [train.py:715] (5/8) Epoch 0, batch 28100, loss[loss=0.2286, simple_loss=0.2886, pruned_loss=0.08425, over 4755.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2646, pruned_loss=0.07427, over 973624.56 frames.], batch size: 16, lr: 1.26e-03
2022-05-03 18:00:08,962 INFO [train.py:715] (5/8) Epoch 0, batch 28150, loss[loss=0.2057, simple_loss=0.2673, pruned_loss=0.07203, over 4753.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2646, pruned_loss=0.07458, over 973015.50 frames.], batch size: 19, lr: 1.25e-03
2022-05-03 18:00:49,201 INFO [train.py:715] (5/8) Epoch 0, batch 28200, loss[loss=0.2275, simple_loss=0.2801, pruned_loss=0.0875, over 4855.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2649, pruned_loss=0.07483, over 973218.59 frames.], batch size: 30, lr: 1.25e-03
2022-05-03 18:01:28,907 INFO [train.py:715] (5/8) Epoch 0, batch 28250, loss[loss=0.1941, simple_loss=0.2551, pruned_loss=0.0665, over 4767.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2649, pruned_loss=0.07487, over 973187.26 frames.], batch size: 16, lr: 1.25e-03
2022-05-03 18:02:07,674 INFO [train.py:715] (5/8) Epoch 0, batch 28300, loss[loss=0.2166, simple_loss=0.2697, pruned_loss=0.0818, over 4887.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2651, pruned_loss=0.07519, over 973117.82 frames.], batch size: 22, lr: 1.25e-03
2022-05-03 18:02:48,208 INFO [train.py:715] (5/8) Epoch 0, batch 28350, loss[loss=0.2067, simple_loss=0.2837, pruned_loss=0.06481, over 4771.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2647, pruned_loss=0.07433, over 972958.58 frames.], batch size: 18, lr: 1.25e-03
2022-05-03 18:03:27,712 INFO [train.py:715] (5/8) Epoch 0, batch 28400, loss[loss=0.2347, simple_loss=0.2928, pruned_loss=0.0883, over 4915.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2642, pruned_loss=0.07411, over 971994.66 frames.], batch size: 39, lr: 1.25e-03
2022-05-03 18:04:07,959 INFO [train.py:715] (5/8) Epoch 0, batch 28450, loss[loss=0.2631, simple_loss=0.3053, pruned_loss=0.1104, over 4912.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2637, pruned_loss=0.07423, over 972069.32 frames.], batch size: 39, lr: 1.25e-03
2022-05-03 18:04:47,631 INFO [train.py:715] (5/8) Epoch 0, batch 28500, loss[loss=0.2273, simple_loss=0.269, pruned_loss=0.09286, over 4792.00 frames.], tot_loss[loss=0.205, simple_loss=0.2628, pruned_loss=0.07365, over 971578.15 frames.], batch size: 14, lr: 1.25e-03
2022-05-03 18:05:28,103 INFO [train.py:715] (5/8) Epoch 0, batch 28550, loss[loss=0.1727, simple_loss=0.2417, pruned_loss=0.05182, over 4763.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2632, pruned_loss=0.07367, over 972237.21 frames.], batch size: 18, lr: 1.25e-03
2022-05-03 18:06:07,734 INFO [train.py:715] (5/8) Epoch 0, batch 28600, loss[loss=0.2054, simple_loss=0.2598, pruned_loss=0.07553, over 4883.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2639, pruned_loss=0.07376, over 972419.22 frames.], batch size: 16, lr: 1.24e-03
2022-05-03 18:06:46,961 INFO [train.py:715] (5/8) Epoch 0, batch 28650, loss[loss=0.2196, simple_loss=0.2845, pruned_loss=0.07737, over 4960.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2645, pruned_loss=0.07408, over 972648.53 frames.], batch size: 21, lr: 1.24e-03
2022-05-03 18:07:26,842 INFO [train.py:715] (5/8) Epoch 0, batch 28700, loss[loss=0.2116, simple_loss=0.2724, pruned_loss=0.0754, over 4978.00 frames.], tot_loss[loss=0.2056, simple_loss=0.2641, pruned_loss=0.07356, over 971657.13 frames.], batch size: 15, lr: 1.24e-03
2022-05-03 18:08:06,484 INFO [train.py:715] (5/8) Epoch 0, batch 28750, loss[loss=0.1923, simple_loss=0.2423, pruned_loss=0.07112, over 4961.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2652, pruned_loss=0.07467, over 972660.69 frames.], batch size: 15, lr: 1.24e-03
2022-05-03 18:08:46,806 INFO [train.py:715] (5/8) Epoch 0, batch 28800, loss[loss=0.212, simple_loss=0.2692, pruned_loss=0.07736, over 4995.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2645, pruned_loss=0.07393, over 972792.76 frames.], batch size: 14, lr: 1.24e-03
2022-05-03 18:09:25,924 INFO [train.py:715] (5/8) Epoch 0, batch 28850, loss[loss=0.2578, simple_loss=0.2878, pruned_loss=0.1139, over 4833.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2641, pruned_loss=0.07417, over 973003.94 frames.], batch size: 30, lr: 1.24e-03
2022-05-03 18:10:05,950 INFO [train.py:715] (5/8) Epoch 0, batch 28900, loss[loss=0.1623, simple_loss=0.2289, pruned_loss=0.0479, over 4813.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2639, pruned_loss=0.07429, over 973163.97 frames.], batch size: 25, lr: 1.24e-03
2022-05-03 18:10:45,832 INFO [train.py:715] (5/8) Epoch 0, batch 28950, loss[loss=0.1721, simple_loss=0.2327, pruned_loss=0.0558, over 4776.00 frames.], tot_loss[loss=0.2065, simple_loss=0.264, pruned_loss=0.0745, over 972852.17 frames.], batch size: 14, lr: 1.24e-03
2022-05-03 18:11:24,706 INFO [train.py:715] (5/8) Epoch 0, batch 29000, loss[loss=0.19, simple_loss=0.2461, pruned_loss=0.06697, over 4696.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2643, pruned_loss=0.07416, over 973866.94 frames.], batch size: 15, lr: 1.24e-03
2022-05-03 18:12:05,309 INFO [train.py:715] (5/8) Epoch 0, batch 29050, loss[loss=0.2059, simple_loss=0.2625, pruned_loss=0.07465, over 4933.00 frames.], tot_loss[loss=0.2054, simple_loss=0.264, pruned_loss=0.07337, over 974240.39 frames.], batch size: 23, lr: 1.24e-03
2022-05-03 18:12:45,442 INFO [train.py:715] (5/8) Epoch 0, batch 29100, loss[loss=0.2279, simple_loss=0.2718, pruned_loss=0.09199, over 4810.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2643, pruned_loss=0.07391, over 973329.32 frames.], batch size: 13, lr: 1.23e-03
2022-05-03 18:13:25,065 INFO [train.py:715] (5/8) Epoch 0, batch 29150, loss[loss=0.1879, simple_loss=0.2476, pruned_loss=0.06409, over 4944.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2636, pruned_loss=0.07345, over 973142.16 frames.], batch size: 21, lr: 1.23e-03
2022-05-03 18:14:04,265 INFO [train.py:715] (5/8) Epoch 0, batch 29200, loss[loss=0.1832, simple_loss=0.2513, pruned_loss=0.05759, over 4896.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2626, pruned_loss=0.0728, over 973516.65 frames.], batch size: 19, lr: 1.23e-03
2022-05-03 18:14:44,209 INFO [train.py:715] (5/8) Epoch 0, batch 29250, loss[loss=0.1646, simple_loss=0.2311, pruned_loss=0.04903, over 4908.00 frames.], tot_loss[loss=0.2035, simple_loss=0.262, pruned_loss=0.07251, over 973037.74 frames.], batch size: 19, lr: 1.23e-03
2022-05-03 18:15:24,227 INFO [train.py:715] (5/8) Epoch 0, batch 29300, loss[loss=0.1865, simple_loss=0.2427, pruned_loss=0.06511, over 4872.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2622, pruned_loss=0.07296, over 972909.89 frames.], batch size: 22, lr: 1.23e-03
2022-05-03 18:16:04,639 INFO [train.py:715] (5/8) Epoch 0, batch 29350, loss[loss=0.1917, simple_loss=0.2537, pruned_loss=0.06486, over 4873.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2626, pruned_loss=0.07342, over 973275.58 frames.], batch size: 32, lr: 1.23e-03
2022-05-03 18:16:44,081 INFO [train.py:715] (5/8) Epoch 0, batch 29400, loss[loss=0.2455, simple_loss=0.3062, pruned_loss=0.09241, over 4962.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2629, pruned_loss=0.07391, over 972611.87 frames.], batch size: 15, lr: 1.23e-03
2022-05-03 18:17:23,552 INFO [train.py:715] (5/8) Epoch 0, batch 29450, loss[loss=0.17, simple_loss=0.2314, pruned_loss=0.05428, over 4805.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2623, pruned_loss=0.07336, over 972473.54 frames.], batch size: 25, lr: 1.23e-03
2022-05-03 18:18:03,747 INFO [train.py:715] (5/8) Epoch 0, batch 29500, loss[loss=0.1485, simple_loss=0.2107, pruned_loss=0.0432, over 4860.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2613, pruned_loss=0.07222, over 972652.39 frames.], batch size: 20, lr: 1.23e-03
2022-05-03 18:18:42,857 INFO [train.py:715] (5/8) Epoch 0, batch 29550, loss[loss=0.206, simple_loss=0.2692, pruned_loss=0.0714, over 4748.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2621, pruned_loss=0.07251, over 972961.60 frames.], batch size: 16, lr: 1.23e-03
2022-05-03 18:19:23,017 INFO [train.py:715] (5/8) Epoch 0, batch 29600, loss[loss=0.2385, simple_loss=0.2817, pruned_loss=0.09768, over 4796.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2622, pruned_loss=0.07281, over 973603.28 frames.], batch size: 12, lr: 1.22e-03
2022-05-03 18:20:02,961 INFO [train.py:715] (5/8) Epoch 0, batch 29650, loss[loss=0.2157, simple_loss=0.2748, pruned_loss=0.07827, over 4953.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2622, pruned_loss=0.07262, over 973428.81 frames.], batch size: 29, lr: 1.22e-03
2022-05-03 18:20:42,828 INFO [train.py:715] (5/8) Epoch 0, batch 29700, loss[loss=0.1995, simple_loss=0.2541, pruned_loss=0.07245, over 4976.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2627, pruned_loss=0.07246, over 973752.81 frames.], batch size: 14, lr: 1.22e-03
2022-05-03 18:21:23,324 INFO [train.py:715] (5/8) Epoch 0, batch 29750, loss[loss=0.2672, simple_loss=0.3062, pruned_loss=0.1141, over 4698.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2629, pruned_loss=0.07303, over 973810.28 frames.], batch size: 15, lr: 1.22e-03
2022-05-03 18:22:03,150 INFO [train.py:715] (5/8) Epoch 0, batch 29800, loss[loss=0.2273, simple_loss=0.2767, pruned_loss=0.08893, over 4636.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2629, pruned_loss=0.07303, over 973685.46 frames.], batch size: 13, lr: 1.22e-03
2022-05-03 18:22:44,057 INFO [train.py:715] (5/8) Epoch 0, batch 29850, loss[loss=0.2013, simple_loss=0.2519, pruned_loss=0.07542, over 4689.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2623, pruned_loss=0.07258, over 973101.72 frames.], batch size: 15, lr: 1.22e-03
2022-05-03 18:23:23,987 INFO [train.py:715] (5/8) Epoch 0, batch 29900, loss[loss=0.1553, simple_loss=0.2193, pruned_loss=0.04565, over 4763.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2622, pruned_loss=0.07268, over 972327.84 frames.], batch size: 12, lr: 1.22e-03
2022-05-03 18:24:03,885 INFO [train.py:715] (5/8) Epoch 0, batch 29950, loss[loss=0.1818, simple_loss=0.2438, pruned_loss=0.05985, over 4988.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2622, pruned_loss=0.07258, over 972770.28 frames.], batch size: 28, lr: 1.22e-03
2022-05-03 18:24:43,766 INFO [train.py:715] (5/8) Epoch 0, batch 30000, loss[loss=0.1995, simple_loss=0.2702, pruned_loss=0.06439, over 4913.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2616, pruned_loss=0.07206, over 972142.37 frames.], batch size: 17, lr: 1.22e-03
2022-05-03 18:24:43,766 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 18:25:00,379 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1316, simple_loss=0.2189, pruned_loss=0.02213, over 914524.00 frames.
2022-05-03 18:25:40,681 INFO [train.py:715] (5/8) Epoch 0, batch 30050, loss[loss=0.1522, simple_loss=0.2143, pruned_loss=0.04501, over 4870.00 frames.], tot_loss[loss=0.2019, simple_loss=0.261, pruned_loss=0.07145, over 972259.12 frames.], batch size: 20, lr: 1.22e-03
2022-05-03 18:26:21,234 INFO [train.py:715] (5/8) Epoch 0, batch 30100, loss[loss=0.1633, simple_loss=0.2405, pruned_loss=0.04309, over 4966.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2611, pruned_loss=0.07135, over 973183.78 frames.], batch size: 21, lr: 1.21e-03
2022-05-03 18:27:01,913 INFO [train.py:715] (5/8) Epoch 0, batch 30150, loss[loss=0.1468, simple_loss=0.2189, pruned_loss=0.03736, over 4757.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2605, pruned_loss=0.07102, over 972705.44 frames.], batch size: 14, lr: 1.21e-03
2022-05-03 18:27:42,050 INFO [train.py:715] (5/8) Epoch 0, batch 30200, loss[loss=0.2092, simple_loss=0.2562, pruned_loss=0.08109, over 4808.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2605, pruned_loss=0.07121, over 973231.48 frames.], batch size: 12, lr: 1.21e-03
2022-05-03 18:28:22,543 INFO [train.py:715] (5/8) Epoch 0, batch 30250, loss[loss=0.1734, simple_loss=0.2371, pruned_loss=0.05482, over 4821.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2608, pruned_loss=0.07148, over 972621.41 frames.], batch size: 27, lr: 1.21e-03
2022-05-03 18:29:02,642 INFO [train.py:715] (5/8) Epoch 0, batch 30300, loss[loss=0.2025, simple_loss=0.2653, pruned_loss=0.06983, over 4911.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2603, pruned_loss=0.07106, over 972866.35 frames.], batch size: 19, lr: 1.21e-03
2022-05-03 18:29:43,073 INFO [train.py:715] (5/8) Epoch 0, batch 30350, loss[loss=0.2412, simple_loss=0.2894, pruned_loss=0.09646, over 4947.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2605, pruned_loss=0.07139, over 972059.09 frames.], batch size: 21, lr: 1.21e-03
2022-05-03 18:30:23,199 INFO [train.py:715] (5/8) Epoch 0, batch 30400, loss[loss=0.2068, simple_loss=0.2566, pruned_loss=0.07851, over 4837.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2611, pruned_loss=0.07212, over 972174.41 frames.], batch size: 13, lr: 1.21e-03
2022-05-03 18:31:02,970 INFO [train.py:715] (5/8) Epoch 0, batch 30450, loss[loss=0.2168, simple_loss=0.2805, pruned_loss=0.07655, over 4765.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2621, pruned_loss=0.07247, over 971915.44 frames.], batch size: 19, lr: 1.21e-03
2022-05-03 18:31:42,723 INFO [train.py:715] (5/8) Epoch 0, batch 30500, loss[loss=0.2296, simple_loss=0.274, pruned_loss=0.09259, over 4929.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2633, pruned_loss=0.07306, over 971894.42 frames.], batch size: 18, lr: 1.21e-03
2022-05-03 18:32:22,642 INFO [train.py:715] (5/8) Epoch 0, batch 30550, loss[loss=0.2293, simple_loss=0.2956, pruned_loss=0.08148, over 4784.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2632, pruned_loss=0.07291, over 971536.27 frames.], batch size: 18, lr: 1.21e-03
2022-05-03 18:33:01,763 INFO [train.py:715] (5/8) Epoch 0, batch 30600, loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03531, over 4804.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2618, pruned_loss=0.07248, over 971230.57 frames.], batch size: 14, lr: 1.20e-03
2022-05-03 18:33:41,703 INFO [train.py:715] (5/8) Epoch 0, batch 30650, loss[loss=0.2033, simple_loss=0.2674, pruned_loss=0.06958, over 4835.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2627, pruned_loss=0.07271, over 970544.16 frames.], batch size: 15, lr: 1.20e-03
2022-05-03 18:34:21,523 INFO [train.py:715] (5/8) Epoch 0, batch 30700, loss[loss=0.1824, simple_loss=0.2418, pruned_loss=0.06152, over 4771.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2638, pruned_loss=0.0734, over 971704.49 frames.], batch size: 12, lr: 1.20e-03
2022-05-03 18:35:01,619 INFO [train.py:715] (5/8) Epoch 0, batch 30750, loss[loss=0.1635, simple_loss=0.2332, pruned_loss=0.04689, over 4802.00 frames.], tot_loss[loss=0.2056, simple_loss=0.264, pruned_loss=0.07363, over 972014.63 frames.], batch size: 13, lr: 1.20e-03
2022-05-03 18:35:40,969 INFO [train.py:715] (5/8) Epoch 0, batch 30800, loss[loss=0.1741, simple_loss=0.2446, pruned_loss=0.05177, over 4987.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2634, pruned_loss=0.07303, over 971897.99 frames.], batch size: 28, lr: 1.20e-03
2022-05-03 18:36:21,306 INFO [train.py:715] (5/8) Epoch 0, batch 30850, loss[loss=0.1819, simple_loss=0.2288, pruned_loss=0.06748, over 4783.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2632, pruned_loss=0.07331, over 972387.23 frames.], batch size: 14, lr: 1.20e-03
2022-05-03 18:37:01,151 INFO [train.py:715] (5/8) Epoch 0, batch 30900, loss[loss=0.1664, simple_loss=0.238, pruned_loss=0.04735, over 4994.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2623, pruned_loss=0.07241, over 973249.30 frames.], batch size: 14, lr: 1.20e-03
2022-05-03 18:37:40,867 INFO [train.py:715] (5/8) Epoch 0, batch 30950, loss[loss=0.2201, simple_loss=0.2859, pruned_loss=0.07718, over 4989.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2628, pruned_loss=0.07299, over 973462.24 frames.], batch size: 28, lr: 1.20e-03
2022-05-03 18:38:20,953 INFO [train.py:715] (5/8) Epoch 0, batch 31000, loss[loss=0.1726, simple_loss=0.2359, pruned_loss=0.0546, over 4949.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2628, pruned_loss=0.07284, over 973327.50 frames.], batch size: 35, lr: 1.20e-03
2022-05-03 18:39:00,966 INFO [train.py:715] (5/8) Epoch 0, batch 31050, loss[loss=0.1597, simple_loss=0.2279, pruned_loss=0.04573, over 4821.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2618, pruned_loss=0.07184, over 972330.28 frames.], batch size: 15, lr: 1.20e-03
2022-05-03 18:39:40,373 INFO [train.py:715] (5/8) Epoch 0, batch 31100, loss[loss=0.171, simple_loss=0.2476, pruned_loss=0.04721, over 4850.00 frames.], tot_loss[loss=0.201, simple_loss=0.2605, pruned_loss=0.07078, over 972181.13 frames.], batch size: 20, lr: 1.20e-03
2022-05-03 18:40:19,539 INFO [train.py:715] (5/8) Epoch 0, batch 31150, loss[loss=0.1781, simple_loss=0.2436, pruned_loss=0.05637, over 4766.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2606, pruned_loss=0.07041, over 973194.85 frames.], batch size: 18, lr: 1.19e-03
2022-05-03 18:40:59,613 INFO [train.py:715] (5/8) Epoch 0, batch 31200, loss[loss=0.2094, simple_loss=0.2761, pruned_loss=0.07139, over 4885.00 frames.], tot_loss[loss=0.2028, simple_loss=0.262, pruned_loss=0.07178, over 973363.37 frames.], batch size: 22, lr: 1.19e-03
2022-05-03 18:41:39,407 INFO [train.py:715] (5/8) Epoch 0, batch 31250, loss[loss=0.218, simple_loss=0.2755, pruned_loss=0.08028, over 4694.00 frames.], tot_loss[loss=0.203, simple_loss=0.2623, pruned_loss=0.07181, over 973043.48 frames.], batch size: 15, lr: 1.19e-03
2022-05-03 18:42:18,883 INFO [train.py:715] (5/8) Epoch 0, batch 31300, loss[loss=0.1957, simple_loss=0.2482, pruned_loss=0.07157, over 4975.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2626, pruned_loss=0.07211, over 973772.95 frames.], batch size: 14, lr: 1.19e-03
2022-05-03 18:42:59,219 INFO [train.py:715] (5/8) Epoch 0, batch 31350, loss[loss=0.1997, simple_loss=0.2616, pruned_loss=0.06891, over 4985.00 frames.], tot_loss[loss=0.2029, simple_loss=0.262, pruned_loss=0.07192, over 972758.64 frames.], batch size: 14, lr: 1.19e-03
2022-05-03 18:43:38,895 INFO [train.py:715] (5/8) Epoch 0, batch 31400, loss[loss=0.2058, simple_loss=0.2588, pruned_loss=0.07646, over 4873.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2625, pruned_loss=0.07196, over 972620.67 frames.], batch size: 32, lr: 1.19e-03
2022-05-03 18:44:18,171 INFO [train.py:715] (5/8) Epoch 0, batch 31450, loss[loss=0.1553, simple_loss=0.2228, pruned_loss=0.04393, over 4979.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2621, pruned_loss=0.07187, over 973456.15 frames.], batch size: 28, lr: 1.19e-03
2022-05-03 18:44:57,274 INFO [train.py:715] (5/8) Epoch 0, batch 31500, loss[loss=0.1921, simple_loss=0.2511, pruned_loss=0.06656, over 4893.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2624, pruned_loss=0.07216, over 973645.71 frames.], batch size: 22, lr: 1.19e-03
2022-05-03 18:45:37,321 INFO [train.py:715] (5/8) Epoch 0, batch 31550, loss[loss=0.2394, simple_loss=0.2876, pruned_loss=0.09556, over 4926.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2615, pruned_loss=0.07177, over 973281.42 frames.], batch size: 39, lr: 1.19e-03
2022-05-03 18:46:17,102 INFO [train.py:715] (5/8) Epoch 0, batch 31600, loss[loss=0.1719, simple_loss=0.2401, pruned_loss=0.0519, over 4959.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2622, pruned_loss=0.07221, over 972496.38 frames.], batch size: 15, lr: 1.19e-03
2022-05-03 18:46:56,333 INFO [train.py:715] (5/8) Epoch 0, batch 31650, loss[loss=0.1866, simple_loss=0.2481, pruned_loss=0.0626, over 4977.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2626, pruned_loss=0.07257, over 972398.20 frames.], batch size: 24, lr: 1.19e-03
2022-05-03 18:47:36,246 INFO [train.py:715] (5/8) Epoch 0, batch 31700, loss[loss=0.2053, simple_loss=0.264, pruned_loss=0.07325, over 4954.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2619, pruned_loss=0.07248, over 972972.40 frames.], batch size: 35, lr: 1.18e-03
2022-05-03 18:48:16,471 INFO [train.py:715] (5/8) Epoch 0, batch 31750, loss[loss=0.2097, simple_loss=0.2736, pruned_loss=0.07286, over 4984.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2625, pruned_loss=0.07288, over 973502.71 frames.], batch size: 35, lr: 1.18e-03
2022-05-03 18:48:56,201 INFO [train.py:715] (5/8) Epoch 0, batch 31800, loss[loss=0.2294, simple_loss=0.2737, pruned_loss=0.09251, over 4964.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2617, pruned_loss=0.07209, over 972584.91 frames.], batch size: 24, lr: 1.18e-03
2022-05-03 18:49:35,467 INFO [train.py:715] (5/8) Epoch 0, batch 31850, loss[loss=0.1839, simple_loss=0.2462, pruned_loss=0.06078, over 4976.00 frames.], tot_loss[loss=0.2021, simple_loss=0.261, pruned_loss=0.07164, over 972933.17 frames.], batch size: 24, lr: 1.18e-03
2022-05-03 18:50:15,965 INFO [train.py:715] (5/8) Epoch 0, batch 31900, loss[loss=0.2919, simple_loss=0.3073, pruned_loss=0.1382, over 4711.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2595, pruned_loss=0.07171, over 973120.85 frames.], batch size: 15, lr: 1.18e-03
2022-05-03 18:50:55,672 INFO [train.py:715] (5/8) Epoch 0, batch 31950, loss[loss=0.2283, simple_loss=0.2911, pruned_loss=0.08272, over 4906.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2603, pruned_loss=0.07172, over 973215.39 frames.], batch size: 17, lr: 1.18e-03
2022-05-03 18:51:37,233 INFO [train.py:715] (5/8) Epoch 0, batch 32000, loss[loss=0.1757, simple_loss=0.2384, pruned_loss=0.05652, over 4927.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2617, pruned_loss=0.07226, over 973930.86 frames.], batch size: 29, lr: 1.18e-03
2022-05-03 18:52:17,384 INFO [train.py:715] (5/8) Epoch 0, batch 32050, loss[loss=0.2015, simple_loss=0.2639, pruned_loss=0.06954, over 4736.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2616, pruned_loss=0.07191, over 973475.81 frames.], batch size: 16, lr: 1.18e-03
2022-05-03 18:52:57,283 INFO [train.py:715] (5/8) Epoch 0, batch 32100, loss[loss=0.1709, simple_loss=0.2383, pruned_loss=0.05174, over 4825.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2614, pruned_loss=0.07186, over 973894.51 frames.], batch size: 15, lr: 1.18e-03
2022-05-03 18:53:36,625 INFO [train.py:715] (5/8) Epoch 0, batch 32150, loss[loss=0.2537, simple_loss=0.2822, pruned_loss=0.1126, over 4839.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2611, pruned_loss=0.07197, over 973098.01 frames.], batch size: 32, lr: 1.18e-03
2022-05-03 18:54:15,806 INFO [train.py:715] (5/8) Epoch 0, batch 32200, loss[loss=0.1643, simple_loss=0.2252, pruned_loss=0.0517, over 4802.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2614, pruned_loss=0.07184, over 972382.94 frames.], batch size: 24, lr: 1.18e-03
2022-05-03 18:54:55,961 INFO [train.py:715] (5/8) Epoch 0, batch 32250, loss[loss=0.1932, simple_loss=0.2469, pruned_loss=0.06976, over 4654.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2628, pruned_loss=0.07303, over 971958.96 frames.], batch size: 13, lr: 1.17e-03
2022-05-03 18:55:35,806 INFO [train.py:715] (5/8) Epoch 0, batch 32300, loss[loss=0.1748, simple_loss=0.2483, pruned_loss=0.0507, over 4746.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2614, pruned_loss=0.07201, over 971555.01 frames.], batch size: 16, lr: 1.17e-03
2022-05-03 18:56:15,320 INFO [train.py:715] (5/8) Epoch 0, batch 32350, loss[loss=0.2541, simple_loss=0.2925, pruned_loss=0.1079, over 4846.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2615, pruned_loss=0.07219, over 971299.11 frames.], batch size: 30, lr: 1.17e-03
2022-05-03 18:56:55,311 INFO [train.py:715] (5/8) Epoch 0, batch 32400, loss[loss=0.2216, simple_loss=0.2742, pruned_loss=0.08449, over 4752.00 frames.], tot_loss[loss=0.202, simple_loss=0.261, pruned_loss=0.07153, over 971181.36 frames.], batch size: 19, lr: 1.17e-03
2022-05-03 18:57:35,386 INFO [train.py:715] (5/8) Epoch 0, batch 32450, loss[loss=0.2353, simple_loss=0.2952, pruned_loss=0.0877, over 4877.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2603, pruned_loss=0.07134, over 972223.89 frames.], batch size: 16, lr: 1.17e-03
2022-05-03 18:58:15,182 INFO [train.py:715] (5/8) Epoch 0, batch 32500, loss[loss=0.2038, simple_loss=0.2572, pruned_loss=0.0752, over 4909.00 frames.], tot_loss[loss=0.2009, simple_loss=0.26, pruned_loss=0.07094, over 971909.82 frames.], batch size: 29, lr: 1.17e-03
2022-05-03 18:58:54,507 INFO [train.py:715] (5/8) Epoch 0, batch 32550, loss[loss=0.2125, simple_loss=0.2793, pruned_loss=0.07286, over 4808.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2584, pruned_loss=0.07016, over 972283.61 frames.], batch size: 21, lr: 1.17e-03
2022-05-03 18:59:34,022 INFO [train.py:715] (5/8) Epoch 0, batch 32600, loss[loss=0.2342, simple_loss=0.2885, pruned_loss=0.08998, over 4751.00 frames.], tot_loss[loss=0.1987, simple_loss=0.258, pruned_loss=0.0697, over 971420.12 frames.], batch size: 16, lr: 1.17e-03
2022-05-03 19:00:13,280 INFO [train.py:715] (5/8) Epoch 0, batch 32650, loss[loss=0.1922, simple_loss=0.254, pruned_loss=0.06526, over 4660.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2582, pruned_loss=0.06968, over 971325.25 frames.], batch size: 13, lr: 1.17e-03
2022-05-03 19:00:52,618 INFO [train.py:715] (5/8) Epoch 0, batch 32700, loss[loss=0.1851, simple_loss=0.2522, pruned_loss=0.05897, over 4869.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2585, pruned_loss=0.06967, over 971981.77 frames.], batch size: 16, lr: 1.17e-03
2022-05-03 19:01:32,097 INFO [train.py:715] (5/8) Epoch 0, batch 32750, loss[loss=0.2057, simple_loss=0.2671, pruned_loss=0.07216, over 4954.00 frames.], tot_loss[loss=0.199, simple_loss=0.2589, pruned_loss=0.06959, over 972138.91 frames.], batch size: 39, lr: 1.17e-03
2022-05-03 19:02:12,126 INFO [train.py:715] (5/8) Epoch 0, batch 32800, loss[loss=0.2217, simple_loss=0.2887, pruned_loss=0.07739, over 4771.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2583, pruned_loss=0.06956, over 972012.84 frames.], batch size: 18, lr: 1.16e-03
2022-05-03 19:02:51,635 INFO [train.py:715] (5/8) Epoch 0, batch 32850, loss[loss=0.2484, simple_loss=0.302, pruned_loss=0.09735, over 4690.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2594, pruned_loss=0.07005, over 972829.92 frames.], batch size: 15, lr: 1.16e-03
2022-05-03 19:03:31,120 INFO [train.py:715] (5/8) Epoch 0, batch 32900, loss[loss=0.224, simple_loss=0.2758, pruned_loss=0.08611, over 4857.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2584, pruned_loss=0.06957, over 971707.54 frames.], batch size: 20, lr: 1.16e-03
2022-05-03 19:04:11,180 INFO [train.py:715] (5/8) Epoch 0, batch 32950, loss[loss=0.177, simple_loss=0.2348, pruned_loss=0.05966, over 4801.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2586, pruned_loss=0.07013, over 971295.57 frames.], batch size: 12, lr: 1.16e-03
2022-05-03 19:04:50,684 INFO [train.py:715] (5/8) Epoch 0, batch 33000, loss[loss=0.1614, simple_loss=0.2338, pruned_loss=0.04452, over 4792.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2593, pruned_loss=0.07018, over 970538.90 frames.], batch size: 21, lr: 1.16e-03
2022-05-03 19:04:50,685 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 19:05:00,796 INFO [train.py:742] (5/8) Epoch 0, validation: loss=0.1303, simple_loss=0.2174, pruned_loss=0.02158, over 914524.00 frames.
2022-05-03 19:05:40,740 INFO [train.py:715] (5/8) Epoch 0, batch 33050, loss[loss=0.1892, simple_loss=0.2503, pruned_loss=0.06403, over 4780.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2605, pruned_loss=0.07107, over 971048.21 frames.], batch size: 17, lr: 1.16e-03
2022-05-03 19:06:20,345 INFO [train.py:715] (5/8) Epoch 0, batch 33100, loss[loss=0.2153, simple_loss=0.2689, pruned_loss=0.08081, over 4980.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2609, pruned_loss=0.07143, over 972293.83 frames.], batch size: 14, lr: 1.16e-03
2022-05-03 19:07:01,018 INFO [train.py:715] (5/8) Epoch 0, batch 33150, loss[loss=0.2582, simple_loss=0.2929, pruned_loss=0.1118, over 4929.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2612, pruned_loss=0.07173, over 972558.82 frames.], batch size: 39, lr: 1.16e-03
2022-05-03 19:07:41,360 INFO [train.py:715] (5/8) Epoch 0, batch 33200, loss[loss=0.1854, simple_loss=0.256, pruned_loss=0.05737, over 4976.00 frames.], tot_loss[loss=0.202, simple_loss=0.2608, pruned_loss=0.07155, over 971351.10 frames.], batch size: 24, lr: 1.16e-03
2022-05-03 19:08:21,595 INFO [train.py:715] (5/8) Epoch 0, batch 33250, loss[loss=0.2598, simple_loss=0.2948, pruned_loss=0.1124, over 4836.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2609, pruned_loss=0.07196, over 971452.85 frames.], batch size: 15, lr: 1.16e-03
2022-05-03 19:09:01,806 INFO [train.py:715] (5/8) Epoch 0, batch 33300, loss[loss=0.2244, simple_loss=0.2825, pruned_loss=0.08311, over 4885.00 frames.], tot_loss[loss=0.2022, simple_loss=0.261, pruned_loss=0.07173, over 972344.94 frames.], batch size: 20, lr: 1.16e-03
2022-05-03 19:09:42,525 INFO [train.py:715] (5/8) Epoch 0, batch 33350, loss[loss=0.19, simple_loss=0.2482, pruned_loss=0.06588, over 4947.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2621, pruned_loss=0.07215, over 971552.26 frames.], batch size: 39, lr: 1.16e-03
2022-05-03 19:10:22,675 INFO [train.py:715] (5/8) Epoch 0, batch 33400, loss[loss=0.2179, simple_loss=0.2721, pruned_loss=0.08185, over 4911.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2607, pruned_loss=0.07121, over 970555.10 frames.], batch size: 19, lr: 1.15e-03
2022-05-03 19:11:02,699 INFO [train.py:715] (5/8) Epoch 0, batch 33450, loss[loss=0.1981, simple_loss=0.2579, pruned_loss=0.06913, over 4947.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2599, pruned_loss=0.07034, over 970740.12 frames.], batch size: 21, lr: 1.15e-03
2022-05-03 19:11:43,358 INFO [train.py:715] (5/8) Epoch 0, batch 33500, loss[loss=0.2187, simple_loss=0.2705, pruned_loss=0.08345, over 4904.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2598, pruned_loss=0.07094, over 970663.91 frames.], batch size: 17, lr: 1.15e-03
2022-05-03 19:12:23,712 INFO [train.py:715] (5/8) Epoch 0, batch 33550, loss[loss=0.1765, simple_loss=0.2436, pruned_loss=0.05472, over 4900.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2584, pruned_loss=0.07038, over 970447.26 frames.], batch size: 19, lr: 1.15e-03
2022-05-03 19:13:02,895 INFO [train.py:715] (5/8) Epoch 0, batch 33600, loss[loss=0.1778, simple_loss=0.2339, pruned_loss=0.06082, over 4644.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2585, pruned_loss=0.07003, over 971079.11 frames.], batch size: 13, lr: 1.15e-03
2022-05-03 19:13:43,472 INFO [train.py:715] (5/8) Epoch 0, batch 33650, loss[loss=0.1904, simple_loss=0.2508, pruned_loss=0.06498, over 4844.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2599, pruned_loss=0.07035, over 971975.68 frames.], batch size: 32, lr: 1.15e-03
2022-05-03 19:14:23,805 INFO [train.py:715] (5/8) Epoch 0, batch 33700, loss[loss=0.2453, simple_loss=0.2895, pruned_loss=0.1005, over 4864.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2594, pruned_loss=0.06978, over 971692.98 frames.], batch size: 32, lr: 1.15e-03
2022-05-03 19:15:03,030 INFO [train.py:715] (5/8) Epoch 0, batch 33750, loss[loss=0.1865, simple_loss=0.257, pruned_loss=0.05803, over 4769.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2598, pruned_loss=0.06985, over 971057.33 frames.], batch size: 12, lr: 1.15e-03
2022-05-03 19:15:42,515 INFO [train.py:715] (5/8) Epoch 0, batch 33800, loss[loss=0.1804, simple_loss=0.2402, pruned_loss=0.06034, over 4828.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2598, pruned_loss=0.07003, over 971017.97 frames.], batch size: 26, lr: 1.15e-03
2022-05-03 19:16:22,771 INFO [train.py:715] (5/8) Epoch 0, batch 33850, loss[loss=0.2069, simple_loss=0.2608, pruned_loss=0.07647, over 4990.00 frames.], tot_loss[loss=0.2004, simple_loss=0.26, pruned_loss=0.07035, over 971555.26 frames.], batch size: 25, lr: 1.15e-03
2022-05-03 19:17:02,057 INFO [train.py:715] (5/8) Epoch 0, batch 33900, loss[loss=0.1971, simple_loss=0.2594, pruned_loss=0.06741, over 4956.00 frames.], tot_loss[loss=0.201, simple_loss=0.2603, pruned_loss=0.07079, over 972406.06 frames.], batch size: 29, lr: 1.15e-03
2022-05-03 19:17:41,115 INFO [train.py:715] (5/8) Epoch 0, batch 33950, loss[loss=0.2047, simple_loss=0.2652, pruned_loss=0.07207, over 4853.00 frames.], tot_loss[loss=0.2019, simple_loss=0.261, pruned_loss=0.07141, over 972821.64 frames.], batch size: 20, lr: 1.15e-03
2022-05-03 19:18:21,087 INFO [train.py:715] (5/8) Epoch 0, batch 34000, loss[loss=0.2293, simple_loss=0.2653, pruned_loss=0.0966, over 4843.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2608, pruned_loss=0.07141, over 972851.68 frames.], batch size: 30, lr: 1.14e-03
2022-05-03 19:19:00,963 INFO [train.py:715] (5/8) Epoch 0, batch 34050, loss[loss=0.1993, simple_loss=0.2673, pruned_loss=0.06565, over 4741.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2607, pruned_loss=0.07086, over 972243.11 frames.], batch size: 16, lr: 1.14e-03
2022-05-03 19:19:40,629 INFO [train.py:715] (5/8) Epoch 0, batch 34100, loss[loss=0.2216, simple_loss=0.2817, pruned_loss=0.08076, over 4784.00 frames.], tot_loss[loss=0.2014, simple_loss=0.261, pruned_loss=0.07087, over 972413.23 frames.], batch size: 14, lr: 1.14e-03
2022-05-03 19:20:19,825 INFO [train.py:715] (5/8) Epoch 0, batch 34150, loss[loss=0.2351, simple_loss=0.3028, pruned_loss=0.08364, over 4930.00 frames.], tot_loss[loss=0.2017, simple_loss=0.261, pruned_loss=0.07123, over 972834.59 frames.], batch size: 18, lr: 1.14e-03
2022-05-03 19:20:59,752 INFO [train.py:715] (5/8) Epoch 0, batch 34200, loss[loss=0.2156, simple_loss=0.2876, pruned_loss=0.07185, over 4805.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2603, pruned_loss=0.07068, over 972918.37 frames.], batch size: 21, lr: 1.14e-03
2022-05-03 19:21:39,295 INFO [train.py:715] (5/8) Epoch 0, batch 34250, loss[loss=0.2228, simple_loss=0.2732, pruned_loss=0.08621, over 4769.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2606, pruned_loss=0.07088, over 972596.25 frames.], batch size: 14, lr: 1.14e-03
2022-05-03 19:22:18,602 INFO [train.py:715] (5/8) Epoch 0, batch 34300, loss[loss=0.21, simple_loss=0.2751, pruned_loss=0.07245, over 4968.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2612, pruned_loss=0.07112, over 972842.15 frames.], batch size: 35, lr: 1.14e-03
2022-05-03 19:22:58,855 INFO [train.py:715] (5/8) Epoch 0, batch 34350, loss[loss=0.1737, simple_loss=0.2515, pruned_loss=0.04792, over 4957.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2594, pruned_loss=0.06966, over 972109.29 frames.], batch size: 24, lr: 1.14e-03
2022-05-03 19:23:39,057 INFO [train.py:715] (5/8) Epoch 0, batch 34400, loss[loss=0.1718, simple_loss=0.2391, pruned_loss=0.05219, over 4903.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2597, pruned_loss=0.06967, over 972112.96 frames.], batch size: 19, lr: 1.14e-03
2022-05-03 19:24:18,629 INFO [train.py:715] (5/8) Epoch 0, batch 34450, loss[loss=0.1657, simple_loss=0.2333, pruned_loss=0.04907, over 4796.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2607, pruned_loss=0.07052, over 971899.73 frames.], batch size: 21, lr: 1.14e-03
2022-05-03 19:24:57,901 INFO [train.py:715] (5/8) Epoch 0, batch 34500, loss[loss=0.1728, simple_loss=0.2368, pruned_loss=0.05443, over 4918.00 frames.], tot_loss[loss=0.2003, simple_loss=0.26, pruned_loss=0.07028, over 972733.33 frames.], batch size: 29, lr: 1.14e-03
2022-05-03 19:25:38,245 INFO [train.py:715] (5/8) Epoch 0, batch 34550, loss[loss=0.2074, simple_loss=0.2698, pruned_loss=0.07255, over 4835.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2585, pruned_loss=0.06894, over 972316.93 frames.], batch size: 30, lr: 1.14e-03
2022-05-03 19:26:17,979 INFO [train.py:715] (5/8) Epoch 0, batch 34600, loss[loss=0.1856, simple_loss=0.2499, pruned_loss=0.06066, over 4887.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2588, pruned_loss=0.06891, over 972822.86 frames.], batch size: 22, lr: 1.13e-03
2022-05-03 19:26:57,210 INFO [train.py:715] (5/8) Epoch 0, batch 34650, loss[loss=0.1875, simple_loss=0.2478, pruned_loss=0.06359, over 4673.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2588, pruned_loss=0.06944, over 972992.56 frames.], batch size: 14, lr: 1.13e-03
2022-05-03 19:27:37,739 INFO [train.py:715] (5/8) Epoch 0, batch 34700, loss[loss=0.2312, simple_loss=0.2761, pruned_loss=0.09319, over 4910.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2585, pruned_loss=0.0697, over 973366.86 frames.], batch size: 19, lr: 1.13e-03
2022-05-03 19:28:15,920 INFO [train.py:715] (5/8) Epoch 0, batch 34750, loss[loss=0.1639, simple_loss=0.2332, pruned_loss=0.0473, over 4931.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2582, pruned_loss=0.06951, over 973634.63 frames.], batch size: 18, lr: 1.13e-03
2022-05-03 19:28:53,212 INFO [train.py:715] (5/8) Epoch 0, batch 34800, loss[loss=0.1588, simple_loss=0.2292, pruned_loss=0.04424, over 4802.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2574, pruned_loss=0.06914, over 973165.35 frames.], batch size: 12, lr: 1.13e-03
2022-05-03 19:29:42,568 INFO [train.py:715] (5/8) Epoch 1, batch 0, loss[loss=0.2052, simple_loss=0.2519, pruned_loss=0.07922, over 4884.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2519, pruned_loss=0.07922, over 4884.00 frames.], batch size: 32, lr: 1.11e-03
2022-05-03 19:30:21,869 INFO [train.py:715] (5/8) Epoch 1, batch 50, loss[loss=0.2099, simple_loss=0.2618, pruned_loss=0.07906, over 4696.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2593, pruned_loss=0.0718, over 219656.04 frames.], batch size: 15, lr: 1.11e-03
2022-05-03 19:31:01,845 INFO [train.py:715] (5/8) Epoch 1, batch 100, loss[loss=0.2076, simple_loss=0.2591, pruned_loss=0.07799, over 4976.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2573, pruned_loss=0.07004, over 387515.08 frames.], batch size: 14, lr: 1.11e-03
2022-05-03 19:31:41,279 INFO [train.py:715] (5/8) Epoch 1, batch 150, loss[loss=0.1812, simple_loss=0.2361, pruned_loss=0.06319, over 4977.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2574, pruned_loss=0.06999, over 517329.53 frames.], batch size: 26, lr: 1.11e-03
2022-05-03 19:32:20,516 INFO [train.py:715] (5/8) Epoch 1, batch 200, loss[loss=0.2006, simple_loss=0.2646, pruned_loss=0.06829, over 4793.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2572, pruned_loss=0.07025, over 618039.20 frames.], batch size: 17, lr: 1.11e-03
2022-05-03 19:33:00,052 INFO [train.py:715] (5/8) Epoch 1, batch 250, loss[loss=0.1583, simple_loss=0.2231, pruned_loss=0.04679, over 4685.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2592, pruned_loss=0.07068, over 696514.51 frames.], batch size: 13, lr: 1.11e-03
2022-05-03 19:33:40,739 INFO [train.py:715] (5/8) Epoch 1, batch 300, loss[loss=0.1749, simple_loss=0.2403, pruned_loss=0.05472, over 4970.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2584, pruned_loss=0.06954, over 759039.95 frames.], batch size: 24, lr: 1.11e-03
2022-05-03 19:34:21,106 INFO [train.py:715] (5/8) Epoch 1, batch 350, loss[loss=0.2166, simple_loss=0.2753, pruned_loss=0.07895, over 4930.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2589, pruned_loss=0.07044, over 806378.38 frames.], batch size: 18, lr: 1.11e-03
2022-05-03 19:35:01,377 INFO [train.py:715] (5/8) Epoch 1, batch 400, loss[loss=0.1665, simple_loss=0.2284, pruned_loss=0.05224, over 4809.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2588, pruned_loss=0.06997, over 843173.89 frames.], batch size: 14, lr: 1.11e-03
2022-05-03 19:35:42,057 INFO [train.py:715] (5/8) Epoch 1, batch 450, loss[loss=0.197, simple_loss=0.2543, pruned_loss=0.06986, over 4904.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2581, pruned_loss=0.06942, over 872727.46 frames.], batch size: 18, lr: 1.11e-03
2022-05-03 19:36:22,763 INFO [train.py:715] (5/8) Epoch 1, batch 500, loss[loss=0.1795, simple_loss=0.2381, pruned_loss=0.06042, over 4954.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2576, pruned_loss=0.06875, over 895583.20 frames.], batch size: 15, lr: 1.11e-03
2022-05-03 19:37:03,287 INFO [train.py:715] (5/8) Epoch 1, batch 550, loss[loss=0.2414, simple_loss=0.2834, pruned_loss=0.09969, over 4810.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2588, pruned_loss=0.06942, over 912681.18 frames.], batch size: 21, lr: 1.11e-03
2022-05-03 19:37:43,264 INFO [train.py:715] (5/8) Epoch 1, batch 600, loss[loss=0.2062, simple_loss=0.263, pruned_loss=0.07473, over 4816.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2595, pruned_loss=0.07037, over 926546.65 frames.], batch size: 27, lr: 1.10e-03
2022-05-03 19:38:23,975 INFO [train.py:715] (5/8) Epoch 1, batch 650, loss[loss=0.154, simple_loss=0.2342, pruned_loss=0.03695, over 4826.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2586, pruned_loss=0.0694, over 936339.77 frames.], batch size: 26, lr: 1.10e-03
2022-05-03 19:39:04,139 INFO [train.py:715] (5/8) Epoch 1, batch 700, loss[loss=0.2096, simple_loss=0.2712, pruned_loss=0.07398, over 4882.00 frames.], tot_loss[loss=0.1978, simple_loss=0.258, pruned_loss=0.06881, over 945090.51 frames.], batch size: 22, lr: 1.10e-03
2022-05-03 19:39:44,118 INFO [train.py:715] (5/8) Epoch 1, batch 750, loss[loss=0.2044, simple_loss=0.2551, pruned_loss=0.0768, over 4973.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2578, pruned_loss=0.06862, over 951799.15 frames.], batch size: 15, lr: 1.10e-03
2022-05-03 19:40:24,214 INFO [train.py:715] (5/8) Epoch 1, batch 800, loss[loss=0.1973, simple_loss=0.259, pruned_loss=0.06777, over 4932.00 frames.], tot_loss[loss=0.199, simple_loss=0.2587, pruned_loss=0.06959, over 956682.44 frames.], batch size: 23, lr: 1.10e-03
2022-05-03 19:41:04,456 INFO [train.py:715] (5/8) Epoch 1, batch 850, loss[loss=0.1667, simple_loss=0.2304, pruned_loss=0.05144, over 4823.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2581, pruned_loss=0.06913, over 959239.27 frames.], batch size: 27, lr: 1.10e-03
2022-05-03 19:41:43,687 INFO [train.py:715] (5/8) Epoch 1, batch 900, loss[loss=0.1625, simple_loss=0.2273, pruned_loss=0.04888, over 4762.00 frames.], tot_loss[loss=0.197, simple_loss=0.2571, pruned_loss=0.06847, over 961836.24 frames.], batch size: 19, lr: 1.10e-03
2022-05-03 19:42:22,967 INFO [train.py:715] (5/8) Epoch 1, batch 950, loss[loss=0.2107, simple_loss=0.2608, pruned_loss=0.0803, over 4957.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2573, pruned_loss=0.06852, over 964153.45 frames.], batch size: 35, lr: 1.10e-03
2022-05-03 19:43:02,561 INFO [train.py:715] (5/8) Epoch 1, batch 1000, loss[loss=0.152, simple_loss=0.2283, pruned_loss=0.03783, over 4819.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2572, pruned_loss=0.06828, over 965269.20 frames.], batch size: 12, lr: 1.10e-03
2022-05-03 19:43:41,898 INFO [train.py:715] (5/8) Epoch 1, batch 1050, loss[loss=0.1978, simple_loss=0.2548, pruned_loss=0.07036, over 4774.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2576, pruned_loss=0.06859, over 966949.63 frames.], batch size: 19, lr: 1.10e-03
2022-05-03 19:44:20,960 INFO [train.py:715] (5/8) Epoch 1, batch 1100, loss[loss=0.1701, simple_loss=0.2271, pruned_loss=0.05659, over 4757.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2575, pruned_loss=0.0685, over 968678.52 frames.], batch size: 19, lr: 1.10e-03
2022-05-03 19:45:00,272 INFO [train.py:715] (5/8) Epoch 1, batch 1150, loss[loss=0.1573, simple_loss=0.2323, pruned_loss=0.04116, over 4904.00 frames.], tot_loss[loss=0.197, simple_loss=0.2576, pruned_loss=0.06816, over 969226.24 frames.], batch size: 18, lr: 1.10e-03
2022-05-03 19:45:40,268 INFO [train.py:715] (5/8) Epoch 1, batch 1200, loss[loss=0.1831, simple_loss=0.233, pruned_loss=0.06657, over 4776.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2578, pruned_loss=0.06887, over 969258.50 frames.], batch size: 14, lr: 1.10e-03
2022-05-03 19:46:19,423 INFO [train.py:715] (5/8) Epoch 1, batch 1250, loss[loss=0.1801, simple_loss=0.2443, pruned_loss=0.05793, over 4829.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2568, pruned_loss=0.06827, over 969610.89 frames.], batch size: 26, lr: 1.10e-03
2022-05-03 19:46:58,953 INFO [train.py:715] (5/8) Epoch 1, batch 1300, loss[loss=0.1852, simple_loss=0.2447, pruned_loss=0.06288, over 4968.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2558, pruned_loss=0.06765, over 970601.13 frames.], batch size: 24, lr: 1.09e-03
2022-05-03 19:47:39,266 INFO [train.py:715] (5/8) Epoch 1, batch 1350, loss[loss=0.2062, simple_loss=0.2673, pruned_loss=0.07249, over 4949.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2565, pruned_loss=0.06815, over 970994.41 frames.], batch size: 24, lr: 1.09e-03
2022-05-03 19:48:18,890 INFO [train.py:715] (5/8) Epoch 1, batch 1400, loss[loss=0.1648, simple_loss=0.2279, pruned_loss=0.05084, over 4938.00 frames.], tot_loss[loss=0.1976, simple_loss=0.257, pruned_loss=0.06906, over 971423.99 frames.], batch size: 35, lr: 1.09e-03
2022-05-03 19:48:58,740 INFO [train.py:715] (5/8) Epoch 1, batch 1450, loss[loss=0.1701, simple_loss=0.2462, pruned_loss=0.04701, over 4853.00 frames.], tot_loss[loss=0.1969, simple_loss=0.257, pruned_loss=0.06841, over 971790.37 frames.], batch size: 30, lr: 1.09e-03
2022-05-03 19:49:38,349 INFO [train.py:715] (5/8) Epoch 1, batch 1500, loss[loss=0.211, simple_loss=0.2702, pruned_loss=0.07586, over 4977.00 frames.], tot_loss[loss=0.1978, simple_loss=0.258, pruned_loss=0.06876, over 971873.65 frames.], batch size: 28, lr: 1.09e-03
2022-05-03 19:50:17,872 INFO [train.py:715] (5/8) Epoch 1, batch 1550, loss[loss=0.2434, simple_loss=0.2841, pruned_loss=0.1014, over 4890.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2585, pruned_loss=0.0691, over 971591.52 frames.], batch size: 16, lr: 1.09e-03
2022-05-03 19:50:57,100 INFO [train.py:715] (5/8) Epoch 1, batch 1600, loss[loss=0.1759, simple_loss=0.2375, pruned_loss=0.05711, over 4640.00 frames.], tot_loss[loss=0.1979, simple_loss=0.258, pruned_loss=0.06888, over 971807.87 frames.], batch size: 13, lr: 1.09e-03
2022-05-03 19:51:36,397 INFO [train.py:715] (5/8) Epoch 1, batch 1650, loss[loss=0.1913, simple_loss=0.2541, pruned_loss=0.06425, over 4791.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2576, pruned_loss=0.0685, over 971294.85 frames.], batch size: 21, lr: 1.09e-03
2022-05-03 19:52:16,979 INFO [train.py:715] (5/8) Epoch 1, batch 1700, loss[loss=0.2124, simple_loss=0.2777, pruned_loss=0.0735, over 4981.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2563, pruned_loss=0.06766, over 971962.73 frames.], batch size: 14, lr: 1.09e-03
2022-05-03 19:52:56,157 INFO [train.py:715] (5/8) Epoch 1, batch 1750, loss[loss=0.183, simple_loss=0.2443, pruned_loss=0.06086, over 4697.00 frames.], tot_loss[loss=0.1956, simple_loss=0.256, pruned_loss=0.06758, over 971743.29 frames.], batch size: 15, lr: 1.09e-03
2022-05-03 19:53:35,894 INFO [train.py:715] (5/8) Epoch 1, batch 1800, loss[loss=0.1448, simple_loss=0.2173, pruned_loss=0.03618, over 4794.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2549, pruned_loss=0.06685, over 971903.20 frames.], batch size: 18, lr: 1.09e-03
2022-05-03 19:54:15,255 INFO [train.py:715] (5/8) Epoch 1, batch 1850, loss[loss=0.2219, simple_loss=0.283, pruned_loss=0.08044, over 4692.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2555, pruned_loss=0.06746, over 972425.22 frames.], batch size: 15, lr: 1.09e-03
2022-05-03 19:54:54,775 INFO [train.py:715] (5/8) Epoch 1, batch 1900, loss[loss=0.1976, simple_loss=0.2575, pruned_loss=0.06885, over 4888.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2557, pruned_loss=0.06761, over 972290.15 frames.], batch size: 19, lr: 1.09e-03
2022-05-03 19:55:34,083 INFO [train.py:715] (5/8) Epoch 1, batch 1950, loss[loss=0.208, simple_loss=0.2619, pruned_loss=0.07698, over 4788.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2565, pruned_loss=0.06812, over 971885.43 frames.], batch size: 21, lr: 1.08e-03
2022-05-03 19:56:14,074 INFO [train.py:715] (5/8) Epoch 1, batch 2000, loss[loss=0.1832, simple_loss=0.2453, pruned_loss=0.06058, over 4761.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2557, pruned_loss=0.06752, over 971943.61 frames.], batch size: 16, lr: 1.08e-03
2022-05-03 19:56:53,564 INFO [train.py:715] (5/8) Epoch 1, batch 2050, loss[loss=0.1831, simple_loss=0.2437, pruned_loss=0.06125, over 4959.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2552, pruned_loss=0.06675, over 972223.95 frames.], batch size: 24, lr: 1.08e-03
2022-05-03 19:57:33,038 INFO [train.py:715] (5/8) Epoch 1, batch 2100, loss[loss=0.2031, simple_loss=0.2563, pruned_loss=0.07498, over 4802.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2557, pruned_loss=0.06756, over 972418.42 frames.], batch size: 25, lr: 1.08e-03
2022-05-03 19:58:12,721 INFO [train.py:715] (5/8) Epoch 1, batch 2150, loss[loss=0.1443, simple_loss=0.2131, pruned_loss=0.03771, over 4962.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2574, pruned_loss=0.06876, over 972712.29 frames.], batch size: 24, lr: 1.08e-03
2022-05-03 19:58:52,400 INFO [train.py:715] (5/8) Epoch 1, batch 2200, loss[loss=0.1814, simple_loss=0.2453, pruned_loss=0.05875, over 4776.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2567, pruned_loss=0.06798, over 972348.19 frames.], batch size: 17, lr: 1.08e-03
2022-05-03 19:59:32,131 INFO [train.py:715] (5/8) Epoch 1, batch 2250, loss[loss=0.2164, simple_loss=0.2693, pruned_loss=0.08179, over 4911.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2569, pruned_loss=0.0681, over 972016.17 frames.], batch size: 17, lr: 1.08e-03
2022-05-03 20:00:11,170 INFO [train.py:715] (5/8) Epoch 1, batch 2300, loss[loss=0.2248, simple_loss=0.2777, pruned_loss=0.08593, over 4932.00 frames.], tot_loss[loss=0.1967, simple_loss=0.257, pruned_loss=0.06817, over 972161.37 frames.], batch size: 39, lr: 1.08e-03
2022-05-03 20:00:51,306 INFO [train.py:715] (5/8) Epoch 1, batch 2350, loss[loss=0.1818, simple_loss=0.2454, pruned_loss=0.05914, over 4827.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2568, pruned_loss=0.06809, over 972743.38 frames.], batch size: 15, lr: 1.08e-03
2022-05-03 20:01:30,583 INFO [train.py:715] (5/8) Epoch 1, batch 2400, loss[loss=0.1939, simple_loss=0.2557, pruned_loss=0.0661, over 4961.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2562, pruned_loss=0.06759, over 972942.44 frames.], batch size: 14, lr: 1.08e-03
2022-05-03 20:02:09,728 INFO [train.py:715] (5/8) Epoch 1, batch 2450, loss[loss=0.1814, simple_loss=0.2462, pruned_loss=0.05826, over 4770.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2565, pruned_loss=0.0674, over 972379.13 frames.], batch size: 18, lr: 1.08e-03
2022-05-03 20:02:48,980 INFO [train.py:715] (5/8) Epoch 1, batch 2500, loss[loss=0.2038, simple_loss=0.2615, pruned_loss=0.07301, over 4859.00 frames.], tot_loss[loss=0.1959, simple_loss=0.257, pruned_loss=0.0674, over 971648.19 frames.], batch size: 20, lr: 1.08e-03
2022-05-03 20:03:28,530 INFO [train.py:715] (5/8) Epoch 1, batch 2550, loss[loss=0.133, simple_loss=0.1962, pruned_loss=0.03491, over 4972.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2559, pruned_loss=0.06713, over 971262.63 frames.], batch size: 14, lr: 1.08e-03
2022-05-03 20:04:08,261 INFO [train.py:715] (5/8) Epoch 1, batch 2600, loss[loss=0.177, simple_loss=0.2401, pruned_loss=0.05694, over 4938.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2558, pruned_loss=0.06628, over 972006.87 frames.], batch size: 23, lr: 1.08e-03
2022-05-03 20:04:47,470 INFO [train.py:715] (5/8) Epoch 1, batch 2650, loss[loss=0.1857, simple_loss=0.2396, pruned_loss=0.06588, over 4891.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2557, pruned_loss=0.06637, over 971745.22 frames.], batch size: 19, lr: 1.07e-03
2022-05-03 20:05:27,538 INFO [train.py:715] (5/8) Epoch 1, batch 2700, loss[loss=0.2022, simple_loss=0.2573, pruned_loss=0.0735, over 4962.00 frames.], tot_loss[loss=0.194, simple_loss=0.2555, pruned_loss=0.06623, over 972400.88 frames.], batch size: 15, lr: 1.07e-03
2022-05-03 20:06:06,952 INFO [train.py:715] (5/8) Epoch 1, batch 2750, loss[loss=0.1816, simple_loss=0.23, pruned_loss=0.06657, over 4820.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2559, pruned_loss=0.06651, over 972135.91 frames.], batch size: 13, lr: 1.07e-03
2022-05-03 20:06:45,686 INFO [train.py:715] (5/8) Epoch 1, batch 2800, loss[loss=0.2001, simple_loss=0.2552, pruned_loss=0.07247, over 4819.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2561, pruned_loss=0.06719, over 973267.16 frames.], batch size: 15, lr: 1.07e-03
2022-05-03 20:07:25,349 INFO [train.py:715] (5/8) Epoch 1, batch 2850, loss[loss=0.1866, simple_loss=0.2479, pruned_loss=0.06263, over 4825.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2557, pruned_loss=0.0671, over 972903.99 frames.], batch size: 25, lr: 1.07e-03
2022-05-03 20:08:05,007 INFO [train.py:715] (5/8) Epoch 1, batch 2900, loss[loss=0.1576, simple_loss=0.2259, pruned_loss=0.0446, over 4939.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2544, pruned_loss=0.06635, over 972151.89 frames.], batch size: 35, lr: 1.07e-03
2022-05-03 20:08:44,122 INFO [train.py:715] (5/8) Epoch 1, batch 2950, loss[loss=0.2612, simple_loss=0.2878, pruned_loss=0.1173, over 4691.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2544, pruned_loss=0.06671, over 972189.97 frames.], batch size: 15, lr: 1.07e-03
2022-05-03 20:09:22,832 INFO [train.py:715] (5/8) Epoch 1, batch 3000, loss[loss=0.2072, simple_loss=0.2672, pruned_loss=0.0736, over 4945.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2549, pruned_loss=0.06648, over 973231.18 frames.], batch size: 21, lr: 1.07e-03
2022-05-03 20:09:22,832 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 20:09:34,564 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1276, simple_loss=0.2149, pruned_loss=0.0201, over 914524.00 frames.
2022-05-03 20:10:13,438 INFO [train.py:715] (5/8) Epoch 1, batch 3050, loss[loss=0.2435, simple_loss=0.2916, pruned_loss=0.09776, over 4774.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2547, pruned_loss=0.06632, over 973084.19 frames.], batch size: 18, lr: 1.07e-03
2022-05-03 20:10:53,452 INFO [train.py:715] (5/8) Epoch 1, batch 3100, loss[loss=0.2088, simple_loss=0.2694, pruned_loss=0.07411, over 4758.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2559, pruned_loss=0.06738, over 972640.14 frames.], batch size: 16, lr: 1.07e-03
2022-05-03 20:11:32,597 INFO [train.py:715] (5/8) Epoch 1, batch 3150, loss[loss=0.1905, simple_loss=0.2677, pruned_loss=0.05666, over 4944.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2563, pruned_loss=0.06777, over 973413.49 frames.], batch size: 23, lr: 1.07e-03
2022-05-03 20:12:11,816 INFO [train.py:715] (5/8) Epoch 1, batch 3200, loss[loss=0.2684, simple_loss=0.3196, pruned_loss=0.1086, over 4748.00 frames.], tot_loss[loss=0.197, simple_loss=0.2571, pruned_loss=0.06845, over 972700.82 frames.], batch size: 19, lr: 1.07e-03
2022-05-03 20:12:51,454 INFO [train.py:715] (5/8) Epoch 1, batch 3250, loss[loss=0.2154, simple_loss=0.2746, pruned_loss=0.07814, over 4875.00 frames.], tot_loss[loss=0.1952, simple_loss=0.256, pruned_loss=0.06721, over 972513.01 frames.], batch size: 16, lr: 1.07e-03
2022-05-03 20:13:31,209 INFO [train.py:715] (5/8) Epoch 1, batch 3300, loss[loss=0.1827, simple_loss=0.2536, pruned_loss=0.05585, over 4986.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2556, pruned_loss=0.06711, over 972052.56 frames.], batch size: 20, lr: 1.07e-03
2022-05-03 20:14:10,766 INFO [train.py:715] (5/8) Epoch 1, batch 3350, loss[loss=0.1942, simple_loss=0.2616, pruned_loss=0.06333, over 4945.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2568, pruned_loss=0.06752, over 972926.14 frames.], batch size: 29, lr: 1.07e-03
2022-05-03 20:14:50,046 INFO [train.py:715] (5/8) Epoch 1, batch 3400, loss[loss=0.2162, simple_loss=0.2745, pruned_loss=0.07893, over 4982.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2576, pruned_loss=0.06869, over 973493.44 frames.], batch size: 31, lr: 1.06e-03
2022-05-03 20:15:30,665 INFO [train.py:715] (5/8) Epoch 1, batch 3450, loss[loss=0.1801, simple_loss=0.2455, pruned_loss=0.05729, over 4977.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2567, pruned_loss=0.06827, over 972974.88 frames.], batch size: 15, lr: 1.06e-03
2022-05-03 20:16:09,590 INFO [train.py:715] (5/8) Epoch 1, batch 3500, loss[loss=0.2176, simple_loss=0.2719, pruned_loss=0.08167, over 4747.00 frames.], tot_loss[loss=0.197, simple_loss=0.2564, pruned_loss=0.06877, over 972129.98 frames.], batch size: 16, lr: 1.06e-03
2022-05-03 20:16:48,613 INFO [train.py:715] (5/8) Epoch 1, batch 3550, loss[loss=0.1789, simple_loss=0.2487, pruned_loss=0.05454, over 4780.00 frames.], tot_loss[loss=0.196, simple_loss=0.2558, pruned_loss=0.06807, over 972007.93 frames.], batch size: 18, lr: 1.06e-03
2022-05-03 20:17:28,372 INFO [train.py:715] (5/8) Epoch 1, batch 3600, loss[loss=0.2041, simple_loss=0.2568, pruned_loss=0.07571, over 4843.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2551, pruned_loss=0.06716, over 972366.30 frames.], batch size: 30, lr: 1.06e-03
2022-05-03 20:18:08,019 INFO [train.py:715] (5/8) Epoch 1, batch 3650, loss[loss=0.2236, simple_loss=0.2719, pruned_loss=0.08769, over 4972.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2548, pruned_loss=0.06697, over 972101.53 frames.], batch size: 14, lr: 1.06e-03
2022-05-03 20:18:46,982 INFO [train.py:715] (5/8) Epoch 1, batch 3700, loss[loss=0.1448, simple_loss=0.2204, pruned_loss=0.03455, over 4975.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2546, pruned_loss=0.06629, over 972365.52 frames.], batch size: 28, lr: 1.06e-03
2022-05-03 20:19:25,657 INFO [train.py:715] (5/8) Epoch 1, batch 3750, loss[loss=0.1903, simple_loss=0.2568, pruned_loss=0.06192, over 4911.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2542, pruned_loss=0.06599, over 972006.00 frames.], batch size: 17, lr: 1.06e-03
2022-05-03 20:20:05,930 INFO [train.py:715] (5/8) Epoch 1, batch 3800, loss[loss=0.1803, simple_loss=0.246, pruned_loss=0.05727, over 4858.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2535, pruned_loss=0.06569, over 971741.61 frames.], batch size: 12, lr: 1.06e-03
2022-05-03 20:20:44,900 INFO [train.py:715] (5/8) Epoch 1, batch 3850, loss[loss=0.1957, simple_loss=0.258, pruned_loss=0.06668, over 4887.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2545, pruned_loss=0.06619, over 972582.32 frames.], batch size: 16, lr: 1.06e-03
2022-05-03 20:21:23,754 INFO [train.py:715] (5/8) Epoch 1, batch 3900, loss[loss=0.1941, simple_loss=0.2599, pruned_loss=0.06418, over 4970.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2548, pruned_loss=0.0661, over 972529.43 frames.], batch size: 15, lr: 1.06e-03
2022-05-03 20:22:03,281 INFO [train.py:715] (5/8) Epoch 1, batch 3950, loss[loss=0.1557, simple_loss=0.2181, pruned_loss=0.04662, over 4924.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2541, pruned_loss=0.06648, over 972040.33 frames.], batch size: 18, lr: 1.06e-03
2022-05-03 20:22:42,792 INFO [train.py:715] (5/8) Epoch 1, batch 4000, loss[loss=0.2048, simple_loss=0.2459, pruned_loss=0.08187, over 4858.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2547, pruned_loss=0.06682, over 971407.41 frames.], batch size: 32, lr: 1.06e-03
2022-05-03 20:23:21,454 INFO [train.py:715] (5/8) Epoch 1, batch 4050, loss[loss=0.3409, simple_loss=0.3766, pruned_loss=0.1526, over 4862.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2554, pruned_loss=0.0672, over 972421.95 frames.], batch size: 20, lr: 1.06e-03
2022-05-03 20:24:00,886 INFO [train.py:715] (5/8) Epoch 1, batch 4100, loss[loss=0.1803, simple_loss=0.2422, pruned_loss=0.05925, over 4977.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2558, pruned_loss=0.06749, over 972748.64 frames.], batch size: 25, lr: 1.05e-03
2022-05-03 20:24:40,538 INFO [train.py:715] (5/8) Epoch 1, batch 4150, loss[loss=0.1881, simple_loss=0.2496, pruned_loss=0.06328, over 4930.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2558, pruned_loss=0.06764, over 972458.99 frames.], batch size: 29, lr: 1.05e-03
2022-05-03 20:25:19,582 INFO [train.py:715] (5/8) Epoch 1, batch 4200, loss[loss=0.2366, simple_loss=0.284, pruned_loss=0.0946, over 4842.00 frames.], tot_loss[loss=0.1953, simple_loss=0.2556, pruned_loss=0.06747, over 972401.44 frames.], batch size: 15, lr: 1.05e-03
2022-05-03 20:25:58,621 INFO [train.py:715] (5/8) Epoch 1, batch 4250, loss[loss=0.1422, simple_loss=0.217, pruned_loss=0.03367, over 4811.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2553, pruned_loss=0.0674, over 972994.37 frames.], batch size: 12, lr: 1.05e-03
2022-05-03 20:26:38,138 INFO [train.py:715] (5/8) Epoch 1, batch 4300, loss[loss=0.2165, simple_loss=0.2795, pruned_loss=0.07676, over 4770.00 frames.], tot_loss[loss=0.1946, simple_loss=0.255, pruned_loss=0.06705, over 972134.21 frames.], batch size: 14, lr: 1.05e-03
2022-05-03 20:27:17,802 INFO [train.py:715] (5/8) Epoch 1, batch 4350, loss[loss=0.2152, simple_loss=0.2837, pruned_loss=0.07334, over 4749.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2557, pruned_loss=0.06724, over 972564.27 frames.], batch size: 19, lr: 1.05e-03
2022-05-03 20:27:56,249 INFO [train.py:715] (5/8) Epoch 1, batch 4400, loss[loss=0.2456, simple_loss=0.3124, pruned_loss=0.08938, over 4806.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2558, pruned_loss=0.0675, over 973021.25 frames.], batch size: 21, lr: 1.05e-03
2022-05-03 20:28:35,844 INFO [train.py:715] (5/8) Epoch 1, batch 4450, loss[loss=0.1997, simple_loss=0.2645, pruned_loss=0.06742, over 4942.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2557, pruned_loss=0.06681, over 973251.85 frames.], batch size: 24, lr: 1.05e-03
2022-05-03 20:29:15,592 INFO [train.py:715] (5/8) Epoch 1, batch 4500, loss[loss=0.2036, simple_loss=0.2657, pruned_loss=0.07071, over 4811.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2556, pruned_loss=0.0669, over 972550.85 frames.], batch size: 25, lr: 1.05e-03
2022-05-03 20:29:54,815 INFO [train.py:715] (5/8) Epoch 1, batch 4550, loss[loss=0.1979, simple_loss=0.2555, pruned_loss=0.07013, over 4866.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2546, pruned_loss=0.06661, over 973863.87 frames.], batch size: 20, lr: 1.05e-03
2022-05-03 20:30:33,518 INFO [train.py:715] (5/8) Epoch 1, batch 4600, loss[loss=0.2026, simple_loss=0.2555, pruned_loss=0.07478, over 4979.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2553, pruned_loss=0.06695, over 974391.71 frames.], batch size: 15, lr: 1.05e-03
2022-05-03 20:31:13,057 INFO [train.py:715] (5/8) Epoch 1, batch 4650, loss[loss=0.1498, simple_loss=0.2217, pruned_loss=0.03897, over 4789.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2547, pruned_loss=0.06636, over 974278.05 frames.], batch size: 17, lr: 1.05e-03
2022-05-03 20:31:52,502 INFO [train.py:715] (5/8) Epoch 1, batch 4700, loss[loss=0.1907, simple_loss=0.2598, pruned_loss=0.06085, over 4880.00 frames.], tot_loss[loss=0.192, simple_loss=0.2533, pruned_loss=0.06534, over 973922.56 frames.], batch size: 19, lr: 1.05e-03
2022-05-03 20:32:31,320 INFO [train.py:715] (5/8) Epoch 1, batch 4750, loss[loss=0.2306, simple_loss=0.284, pruned_loss=0.08863, over 4944.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2535, pruned_loss=0.06545, over 974023.06 frames.], batch size: 21, lr: 1.05e-03
2022-05-03 20:33:11,341 INFO [train.py:715] (5/8) Epoch 1, batch 4800, loss[loss=0.2006, simple_loss=0.2676, pruned_loss=0.0668, over 4978.00 frames.], tot_loss[loss=0.193, simple_loss=0.2542, pruned_loss=0.06592, over 974282.51 frames.], batch size: 24, lr: 1.05e-03
2022-05-03 20:33:51,177 INFO [train.py:715] (5/8) Epoch 1, batch 4850, loss[loss=0.1777, simple_loss=0.2379, pruned_loss=0.05875, over 4898.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2533, pruned_loss=0.06512, over 974780.74 frames.], batch size: 22, lr: 1.05e-03
2022-05-03 20:34:30,464 INFO [train.py:715] (5/8) Epoch 1, batch 4900, loss[loss=0.1914, simple_loss=0.2525, pruned_loss=0.06512, over 4785.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2536, pruned_loss=0.06569, over 974645.08 frames.], batch size: 18, lr: 1.04e-03
2022-05-03 20:35:09,823 INFO [train.py:715] (5/8) Epoch 1, batch 4950, loss[loss=0.1816, simple_loss=0.2474, pruned_loss=0.05787, over 4770.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2553, pruned_loss=0.06697, over 974556.53 frames.], batch size: 18, lr: 1.04e-03
2022-05-03 20:35:50,158 INFO [train.py:715] (5/8) Epoch 1, batch 5000, loss[loss=0.2583, simple_loss=0.3057, pruned_loss=0.1055, over 4864.00 frames.], tot_loss[loss=0.1941, simple_loss=0.255, pruned_loss=0.06654, over 974907.42 frames.], batch size: 38, lr: 1.04e-03
2022-05-03 20:36:29,716 INFO [train.py:715] (5/8) Epoch 1, batch 5050, loss[loss=0.1955, simple_loss=0.2534, pruned_loss=0.06881, over 4831.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2545, pruned_loss=0.06629, over 974407.68 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:37:08,715 INFO [train.py:715] (5/8) Epoch 1, batch 5100, loss[loss=0.1914, simple_loss=0.2601, pruned_loss=0.06131, over 4971.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2541, pruned_loss=0.06568, over 974088.41 frames.], batch size: 25, lr: 1.04e-03
2022-05-03 20:37:48,747 INFO [train.py:715] (5/8) Epoch 1, batch 5150, loss[loss=0.1875, simple_loss=0.2662, pruned_loss=0.05435, over 4828.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2543, pruned_loss=0.06532, over 973302.95 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:38:30,127 INFO [train.py:715] (5/8) Epoch 1, batch 5200, loss[loss=0.1962, simple_loss=0.2678, pruned_loss=0.06225, over 4915.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2531, pruned_loss=0.06478, over 972836.64 frames.], batch size: 29, lr: 1.04e-03
2022-05-03 20:39:09,103 INFO [train.py:715] (5/8) Epoch 1, batch 5250, loss[loss=0.2092, simple_loss=0.2688, pruned_loss=0.07479, over 4964.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2527, pruned_loss=0.06443, over 973252.32 frames.], batch size: 35, lr: 1.04e-03
2022-05-03 20:39:48,466 INFO [train.py:715] (5/8) Epoch 1, batch 5300, loss[loss=0.1771, simple_loss=0.2425, pruned_loss=0.05583, over 4803.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2527, pruned_loss=0.06453, over 973834.62 frames.], batch size: 14, lr: 1.04e-03
2022-05-03 20:40:28,101 INFO [train.py:715] (5/8) Epoch 1, batch 5350, loss[loss=0.1992, simple_loss=0.2614, pruned_loss=0.06851, over 4925.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2524, pruned_loss=0.06421, over 973434.42 frames.], batch size: 18, lr: 1.04e-03
2022-05-03 20:41:07,642 INFO [train.py:715] (5/8) Epoch 1, batch 5400, loss[loss=0.1837, simple_loss=0.2372, pruned_loss=0.06505, over 4876.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2515, pruned_loss=0.06376, over 972951.26 frames.], batch size: 22, lr: 1.04e-03
2022-05-03 20:41:46,693 INFO [train.py:715] (5/8) Epoch 1, batch 5450, loss[loss=0.1765, simple_loss=0.2465, pruned_loss=0.05324, over 4792.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2523, pruned_loss=0.06408, over 972776.31 frames.], batch size: 24, lr: 1.04e-03
2022-05-03 20:42:26,574 INFO [train.py:715] (5/8) Epoch 1, batch 5500, loss[loss=0.1796, simple_loss=0.2306, pruned_loss=0.06426, over 4954.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2531, pruned_loss=0.06451, over 973438.74 frames.], batch size: 21, lr: 1.04e-03
2022-05-03 20:43:06,477 INFO [train.py:715] (5/8) Epoch 1, batch 5550, loss[loss=0.1768, simple_loss=0.2336, pruned_loss=0.05998, over 4862.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2524, pruned_loss=0.06449, over 973747.41 frames.], batch size: 34, lr: 1.04e-03
2022-05-03 20:43:45,489 INFO [train.py:715] (5/8) Epoch 1, batch 5600, loss[loss=0.1963, simple_loss=0.2647, pruned_loss=0.06391, over 4925.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2528, pruned_loss=0.06454, over 974023.75 frames.], batch size: 23, lr: 1.04e-03
2022-05-03 20:44:24,782 INFO [train.py:715] (5/8) Epoch 1, batch 5650, loss[loss=0.2043, simple_loss=0.2658, pruned_loss=0.0714, over 4855.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2526, pruned_loss=0.06492, over 973793.19 frames.], batch size: 34, lr: 1.03e-03
2022-05-03 20:45:04,548 INFO [train.py:715] (5/8) Epoch 1, batch 5700, loss[loss=0.1579, simple_loss=0.2323, pruned_loss=0.04173, over 4988.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2529, pruned_loss=0.06529, over 974383.89 frames.], batch size: 28, lr: 1.03e-03
2022-05-03 20:45:44,079 INFO [train.py:715] (5/8) Epoch 1, batch 5750, loss[loss=0.1793, simple_loss=0.236, pruned_loss=0.06129, over 4968.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2527, pruned_loss=0.06502, over 974068.18 frames.], batch size: 35, lr: 1.03e-03
2022-05-03 20:46:23,088 INFO [train.py:715] (5/8) Epoch 1, batch 5800, loss[loss=0.2096, simple_loss=0.2777, pruned_loss=0.07077, over 4775.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2534, pruned_loss=0.06545, over 973137.25 frames.], batch size: 18, lr: 1.03e-03
2022-05-03 20:47:03,040 INFO [train.py:715] (5/8) Epoch 1, batch 5850, loss[loss=0.2039, simple_loss=0.2586, pruned_loss=0.0746, over 4880.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2542, pruned_loss=0.06602, over 973990.67 frames.], batch size: 16, lr: 1.03e-03
2022-05-03 20:47:42,849 INFO [train.py:715] (5/8) Epoch 1, batch 5900, loss[loss=0.1824, simple_loss=0.255, pruned_loss=0.05489, over 4850.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2536, pruned_loss=0.0656, over 972701.56 frames.], batch size: 15, lr: 1.03e-03
2022-05-03 20:48:21,955 INFO [train.py:715] (5/8) Epoch 1, batch 5950, loss[loss=0.1778, simple_loss=0.2486, pruned_loss=0.05353, over 4878.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2546, pruned_loss=0.0662, over 973005.57 frames.], batch size: 19, lr: 1.03e-03
2022-05-03 20:49:01,786 INFO [train.py:715] (5/8) Epoch 1, batch 6000, loss[loss=0.1617, simple_loss=0.2267, pruned_loss=0.04837, over 4836.00 frames.], tot_loss[loss=0.1926, simple_loss=0.254, pruned_loss=0.06559, over 972738.12 frames.], batch size: 13, lr: 1.03e-03
2022-05-03 20:49:01,786 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 20:49:14,258 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1267, simple_loss=0.2135, pruned_loss=0.01993, over 914524.00 frames.
2022-05-03 20:49:53,682 INFO [train.py:715] (5/8) Epoch 1, batch 6050, loss[loss=0.196, simple_loss=0.2484, pruned_loss=0.07179, over 4839.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2541, pruned_loss=0.06529, over 973141.55 frames.], batch size: 30, lr: 1.03e-03
2022-05-03 20:50:33,747 INFO [train.py:715] (5/8) Epoch 1, batch 6100, loss[loss=0.184, simple_loss=0.242, pruned_loss=0.06305, over 4849.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2547, pruned_loss=0.06556, over 974168.98 frames.], batch size: 20, lr: 1.03e-03
2022-05-03 20:51:13,277 INFO [train.py:715] (5/8) Epoch 1, batch 6150, loss[loss=0.1988, simple_loss=0.2592, pruned_loss=0.06917, over 4926.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2536, pruned_loss=0.06508, over 973531.49 frames.], batch size: 23, lr: 1.03e-03
2022-05-03 20:51:51,973 INFO [train.py:715] (5/8) Epoch 1, batch 6200, loss[loss=0.1809, simple_loss=0.2334, pruned_loss=0.06418, over 4737.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2532, pruned_loss=0.06521, over 972987.59 frames.], batch size: 16, lr: 1.03e-03
2022-05-03 20:52:32,163 INFO [train.py:715] (5/8) Epoch 1, batch 6250, loss[loss=0.2085, simple_loss=0.2763, pruned_loss=0.07031, over 4905.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2538, pruned_loss=0.06514, over 973240.03 frames.], batch size: 18, lr: 1.03e-03
2022-05-03 20:53:11,875 INFO [train.py:715] (5/8) Epoch 1, batch 6300, loss[loss=0.1723, simple_loss=0.233, pruned_loss=0.05579, over 4777.00 frames.], tot_loss[loss=0.1923, simple_loss=0.254, pruned_loss=0.06535, over 972889.86 frames.], batch size: 18, lr: 1.03e-03
2022-05-03 20:53:51,073 INFO [train.py:715] (5/8) Epoch 1, batch 6350, loss[loss=0.212, simple_loss=0.2601, pruned_loss=0.08195, over 4982.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2541, pruned_loss=0.06548, over 972490.28 frames.], batch size: 31, lr: 1.03e-03
2022-05-03 20:54:30,386 INFO [train.py:715] (5/8) Epoch 1, batch 6400, loss[loss=0.2178, simple_loss=0.2883, pruned_loss=0.07367, over 4753.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2548, pruned_loss=0.06619, over 972414.28 frames.], batch size: 19, lr: 1.03e-03
2022-05-03 20:55:09,939 INFO [train.py:715] (5/8) Epoch 1, batch 6450, loss[loss=0.1755, simple_loss=0.2402, pruned_loss=0.05543, over 4838.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2537, pruned_loss=0.06609, over 972787.71 frames.], batch size: 30, lr: 1.02e-03
2022-05-03 20:55:49,579 INFO [train.py:715] (5/8) Epoch 1, batch 6500, loss[loss=0.1867, simple_loss=0.2535, pruned_loss=0.05996, over 4944.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2537, pruned_loss=0.06551, over 973141.99 frames.], batch size: 24, lr: 1.02e-03
2022-05-03 20:56:28,198 INFO [train.py:715] (5/8) Epoch 1, batch 6550, loss[loss=0.1633, simple_loss=0.2227, pruned_loss=0.05195, over 4782.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2525, pruned_loss=0.06497, over 972314.21 frames.], batch size: 18, lr: 1.02e-03
2022-05-03 20:57:08,074 INFO [train.py:715] (5/8) Epoch 1, batch 6600, loss[loss=0.1758, simple_loss=0.2345, pruned_loss=0.0586, over 4959.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2524, pruned_loss=0.06564, over 972062.31 frames.], batch size: 35, lr: 1.02e-03
2022-05-03 20:57:48,547 INFO [train.py:715] (5/8) Epoch 1, batch 6650, loss[loss=0.1721, simple_loss=0.246, pruned_loss=0.04907, over 4803.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2532, pruned_loss=0.06568, over 972942.48 frames.], batch size: 25, lr: 1.02e-03
2022-05-03 20:58:28,004 INFO [train.py:715] (5/8) Epoch 1, batch 6700, loss[loss=0.2104, simple_loss=0.2592, pruned_loss=0.0808, over 4793.00 frames.], tot_loss[loss=0.194, simple_loss=0.2546, pruned_loss=0.0667, over 971528.73 frames.], batch size: 14, lr: 1.02e-03
2022-05-03 20:59:07,323 INFO [train.py:715] (5/8) Epoch 1, batch 6750, loss[loss=0.186, simple_loss=0.2329, pruned_loss=0.06954, over 4692.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2551, pruned_loss=0.06695, over 971734.19 frames.], batch size: 15, lr: 1.02e-03
2022-05-03 20:59:47,254 INFO [train.py:715] (5/8) Epoch 1, batch 6800, loss[loss=0.1942, simple_loss=0.2547, pruned_loss=0.06684, over 4879.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2547, pruned_loss=0.06653, over 972571.87 frames.], batch size: 22, lr: 1.02e-03
2022-05-03 21:00:26,797 INFO [train.py:715] (5/8) Epoch 1, batch 6850, loss[loss=0.2291, simple_loss=0.2818, pruned_loss=0.0882, over 4859.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2553, pruned_loss=0.06646, over 973093.09 frames.], batch size: 30, lr: 1.02e-03
2022-05-03 21:01:05,421 INFO [train.py:715] (5/8) Epoch 1, batch 6900, loss[loss=0.2088, simple_loss=0.2787, pruned_loss=0.06945, over 4902.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2552, pruned_loss=0.06591, over 973762.89 frames.], batch size: 19, lr: 1.02e-03
2022-05-03 21:01:44,713 INFO [train.py:715] (5/8) Epoch 1, batch 6950, loss[loss=0.1695, simple_loss=0.2348, pruned_loss=0.05211, over 4852.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2543, pruned_loss=0.0653, over 973964.39 frames.], batch size: 20, lr: 1.02e-03
2022-05-03 21:02:24,792 INFO [train.py:715] (5/8) Epoch 1, batch 7000, loss[loss=0.2342, simple_loss=0.2776, pruned_loss=0.0954, over 4779.00 frames.], tot_loss[loss=0.192, simple_loss=0.2533, pruned_loss=0.06535, over 972343.44 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 21:03:03,639 INFO [train.py:715] (5/8) Epoch 1, batch 7050, loss[loss=0.2334, simple_loss=0.2856, pruned_loss=0.09057, over 4920.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2525, pruned_loss=0.06491, over 972104.88 frames.], batch size: 18, lr: 1.02e-03
2022-05-03 21:03:42,605 INFO [train.py:715] (5/8) Epoch 1, batch 7100, loss[loss=0.1597, simple_loss=0.2275, pruned_loss=0.04594, over 4774.00 frames.], tot_loss[loss=0.1901, simple_loss=0.252, pruned_loss=0.06416, over 972074.37 frames.], batch size: 18, lr: 1.02e-03
2022-05-03 21:04:22,593 INFO [train.py:715] (5/8) Epoch 1, batch 7150, loss[loss=0.1998, simple_loss=0.2501, pruned_loss=0.07475, over 4842.00 frames.], tot_loss[loss=0.1904, simple_loss=0.252, pruned_loss=0.06442, over 971614.66 frames.], batch size: 30, lr: 1.02e-03
2022-05-03 21:05:02,515 INFO [train.py:715] (5/8) Epoch 1, batch 7200, loss[loss=0.2292, simple_loss=0.2834, pruned_loss=0.08751, over 4829.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2539, pruned_loss=0.06531, over 972114.43 frames.], batch size: 30, lr: 1.02e-03
2022-05-03 21:05:41,154 INFO [train.py:715] (5/8) Epoch 1, batch 7250, loss[loss=0.2019, simple_loss=0.2657, pruned_loss=0.069, over 4889.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2533, pruned_loss=0.06491, over 971273.82 frames.], batch size: 19, lr: 1.02e-03
2022-05-03 21:06:21,085 INFO [train.py:715] (5/8) Epoch 1, batch 7300, loss[loss=0.1626, simple_loss=0.24, pruned_loss=0.04256, over 4751.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2532, pruned_loss=0.06509, over 971908.18 frames.], batch size: 19, lr: 1.01e-03
2022-05-03 21:07:00,826 INFO [train.py:715] (5/8) Epoch 1, batch 7350, loss[loss=0.1992, simple_loss=0.2565, pruned_loss=0.071, over 4813.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2532, pruned_loss=0.06461, over 972706.09 frames.], batch size: 25, lr: 1.01e-03
2022-05-03 21:07:39,613 INFO [train.py:715] (5/8) Epoch 1, batch 7400, loss[loss=0.1578, simple_loss=0.2159, pruned_loss=0.0499, over 4897.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2519, pruned_loss=0.06378, over 973213.87 frames.], batch size: 22, lr: 1.01e-03
2022-05-03 21:08:18,527 INFO [train.py:715] (5/8) Epoch 1, batch 7450, loss[loss=0.2374, simple_loss=0.283, pruned_loss=0.09586, over 4767.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2511, pruned_loss=0.06296, over 972557.20 frames.], batch size: 17, lr: 1.01e-03
2022-05-03 21:08:58,342 INFO [train.py:715] (5/8) Epoch 1, batch 7500, loss[loss=0.2215, simple_loss=0.2823, pruned_loss=0.0804, over 4923.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2515, pruned_loss=0.0634, over 972653.17 frames.], batch size: 29, lr: 1.01e-03
2022-05-03 21:09:38,021 INFO [train.py:715] (5/8) Epoch 1, batch 7550, loss[loss=0.2047, simple_loss=0.2739, pruned_loss=0.06777, over 4903.00 frames.], tot_loss[loss=0.1889, simple_loss=0.251, pruned_loss=0.06333, over 972700.69 frames.], batch size: 19, lr: 1.01e-03
2022-05-03 21:10:16,230 INFO [train.py:715] (5/8) Epoch 1, batch 7600, loss[loss=0.2011, simple_loss=0.2664, pruned_loss=0.06794, over 4935.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2523, pruned_loss=0.06406, over 973094.88 frames.], batch size: 23, lr: 1.01e-03
2022-05-03 21:10:55,969 INFO [train.py:715] (5/8) Epoch 1, batch 7650, loss[loss=0.2244, simple_loss=0.265, pruned_loss=0.09188, over 4832.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2514, pruned_loss=0.06419, over 972415.02 frames.], batch size: 30, lr: 1.01e-03
2022-05-03 21:11:35,788 INFO [train.py:715] (5/8) Epoch 1, batch 7700, loss[loss=0.1836, simple_loss=0.2487, pruned_loss=0.05925, over 4835.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2511, pruned_loss=0.06391, over 972425.12 frames.], batch size: 26, lr: 1.01e-03
2022-05-03 21:12:14,131 INFO [train.py:715] (5/8) Epoch 1, batch 7750, loss[loss=0.1929, simple_loss=0.2494, pruned_loss=0.06819, over 4737.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2508, pruned_loss=0.06391, over 972224.51 frames.], batch size: 16, lr: 1.01e-03
2022-05-03 21:12:53,243 INFO [train.py:715] (5/8) Epoch 1, batch 7800, loss[loss=0.1716, simple_loss=0.2377, pruned_loss=0.0528, over 4825.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2514, pruned_loss=0.06401, over 971409.09 frames.], batch size: 25, lr: 1.01e-03
2022-05-03 21:13:33,310 INFO [train.py:715] (5/8) Epoch 1, batch 7850, loss[loss=0.1945, simple_loss=0.27, pruned_loss=0.05952, over 4981.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2523, pruned_loss=0.06462, over 971934.71 frames.], batch size: 25, lr: 1.01e-03
2022-05-03 21:14:12,714 INFO [train.py:715] (5/8) Epoch 1, batch 7900, loss[loss=0.1853, simple_loss=0.2447, pruned_loss=0.0629, over 4747.00 frames.], tot_loss[loss=0.1917, simple_loss=0.253, pruned_loss=0.0652, over 971794.34 frames.], batch size: 16, lr: 1.01e-03
2022-05-03 21:14:51,152 INFO [train.py:715] (5/8) Epoch 1, batch 7950, loss[loss=0.1541, simple_loss=0.2319, pruned_loss=0.03816, over 4990.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2523, pruned_loss=0.06468, over 972281.19 frames.], batch size: 24, lr: 1.01e-03
2022-05-03 21:15:31,258 INFO [train.py:715] (5/8) Epoch 1, batch 8000, loss[loss=0.2106, simple_loss=0.2638, pruned_loss=0.07865, over 4876.00 frames.], tot_loss[loss=0.1906, simple_loss=0.252, pruned_loss=0.06467, over 971286.40 frames.], batch size: 32, lr: 1.01e-03
2022-05-03 21:16:11,048 INFO [train.py:715] (5/8) Epoch 1, batch 8050, loss[loss=0.1878, simple_loss=0.2585, pruned_loss=0.05853, over 4989.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2518, pruned_loss=0.06469, over 972450.00 frames.], batch size: 25, lr: 1.01e-03
2022-05-03 21:16:50,421 INFO [train.py:715] (5/8) Epoch 1, batch 8100, loss[loss=0.1536, simple_loss=0.2359, pruned_loss=0.03567, over 4815.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2526, pruned_loss=0.0652, over 972351.50 frames.], batch size: 25, lr: 1.01e-03
2022-05-03 21:17:28,623 INFO [train.py:715] (5/8) Epoch 1, batch 8150, loss[loss=0.1945, simple_loss=0.2676, pruned_loss=0.06074, over 4913.00 frames.], tot_loss[loss=0.192, simple_loss=0.253, pruned_loss=0.06546, over 971938.59 frames.], batch size: 18, lr: 1.00e-03
2022-05-03 21:18:08,543 INFO [train.py:715] (5/8) Epoch 1, batch 8200, loss[loss=0.1591, simple_loss=0.23, pruned_loss=0.04414, over 4757.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2525, pruned_loss=0.06502, over 971865.96 frames.], batch size: 19, lr: 1.00e-03
2022-05-03 21:18:48,018 INFO [train.py:715] (5/8) Epoch 1, batch 8250, loss[loss=0.1835, simple_loss=0.2487, pruned_loss=0.05914, over 4946.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2532, pruned_loss=0.06549, over 972261.16 frames.], batch size: 29, lr: 1.00e-03
2022-05-03 21:19:26,203 INFO [train.py:715] (5/8) Epoch 1, batch 8300, loss[loss=0.1794, simple_loss=0.2483, pruned_loss=0.0553, over 4757.00 frames.], tot_loss[loss=0.193, simple_loss=0.2538, pruned_loss=0.06606, over 972585.39 frames.], batch size: 16, lr: 1.00e-03
2022-05-03 21:20:06,142 INFO [train.py:715] (5/8) Epoch 1, batch 8350, loss[loss=0.1523, simple_loss=0.2265, pruned_loss=0.03899, over 4766.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2536, pruned_loss=0.06548, over 972420.68 frames.], batch size: 18, lr: 1.00e-03
2022-05-03 21:20:45,726 INFO [train.py:715] (5/8) Epoch 1, batch 8400, loss[loss=0.1787, simple_loss=0.2517, pruned_loss=0.05287, over 4778.00 frames.], tot_loss[loss=0.191, simple_loss=0.2531, pruned_loss=0.06451, over 972858.41 frames.], batch size: 18, lr: 1.00e-03
2022-05-03 21:21:25,100 INFO [train.py:715] (5/8) Epoch 1, batch 8450, loss[loss=0.1695, simple_loss=0.2355, pruned_loss=0.05181, over 4945.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2531, pruned_loss=0.06433, over 972497.88 frames.], batch size: 35, lr: 1.00e-03
2022-05-03 21:22:03,495 INFO [train.py:715] (5/8) Epoch 1, batch 8500, loss[loss=0.1881, simple_loss=0.2518, pruned_loss=0.06223, over 4747.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2539, pruned_loss=0.06487, over 973233.91 frames.], batch size: 19, lr: 1.00e-03
2022-05-03 21:22:43,391 INFO [train.py:715] (5/8) Epoch 1, batch 8550, loss[loss=0.18, simple_loss=0.2375, pruned_loss=0.06121, over 4835.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2541, pruned_loss=0.06479, over 972625.60 frames.], batch size: 30, lr: 1.00e-03
2022-05-03 21:23:22,900 INFO [train.py:715] (5/8) Epoch 1, batch 8600, loss[loss=0.2205, simple_loss=0.2866, pruned_loss=0.07721, over 4874.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2534, pruned_loss=0.06466, over 972933.55 frames.], batch size: 30, lr: 1.00e-03
2022-05-03 21:24:00,902 INFO [train.py:715] (5/8) Epoch 1, batch 8650, loss[loss=0.1607, simple_loss=0.2278, pruned_loss=0.0468, over 4818.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2533, pruned_loss=0.0646, over 974323.93 frames.], batch size: 27, lr: 9.99e-04
2022-05-03 21:24:41,121 INFO [train.py:715] (5/8) Epoch 1, batch 8700, loss[loss=0.1855, simple_loss=0.2534, pruned_loss=0.05875, over 4916.00 frames.], tot_loss[loss=0.191, simple_loss=0.2533, pruned_loss=0.06438, over 974438.00 frames.], batch size: 23, lr: 9.98e-04
2022-05-03 21:25:21,115 INFO [train.py:715] (5/8) Epoch 1, batch 8750, loss[loss=0.1539, simple_loss=0.223, pruned_loss=0.04243, over 4878.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2532, pruned_loss=0.06454, over 974451.57 frames.], batch size: 16, lr: 9.98e-04
2022-05-03 21:26:00,205 INFO [train.py:715] (5/8) Epoch 1, batch 8800, loss[loss=0.2225, simple_loss=0.2795, pruned_loss=0.08272, over 4859.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2542, pruned_loss=0.06501, over 973975.59 frames.], batch size: 20, lr: 9.97e-04
2022-05-03 21:26:39,531 INFO [train.py:715] (5/8) Epoch 1, batch 8850, loss[loss=0.2436, simple_loss=0.2856, pruned_loss=0.1008, over 4690.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2548, pruned_loss=0.0657, over 973262.31 frames.], batch size: 15, lr: 9.97e-04
2022-05-03 21:27:19,648 INFO [train.py:715] (5/8) Epoch 1, batch 8900, loss[loss=0.1516, simple_loss=0.221, pruned_loss=0.04112, over 4917.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2551, pruned_loss=0.06601, over 972483.73 frames.], batch size: 18, lr: 9.96e-04
2022-05-03 21:27:59,348 INFO [train.py:715] (5/8) Epoch 1, batch 8950, loss[loss=0.2039, simple_loss=0.2678, pruned_loss=0.06996, over 4792.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2547, pruned_loss=0.06587, over 971439.34 frames.], batch size: 14, lr: 9.96e-04
2022-05-03 21:28:37,780 INFO [train.py:715] (5/8) Epoch 1, batch 9000, loss[loss=0.1872, simple_loss=0.2402, pruned_loss=0.06707, over 4774.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2551, pruned_loss=0.06594, over 972010.28 frames.], batch size: 14, lr: 9.95e-04
2022-05-03 21:28:37,780 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 21:28:47,501 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1253, simple_loss=0.2125, pruned_loss=0.01906, over 914524.00 frames.
2022-05-03 21:29:25,992 INFO [train.py:715] (5/8) Epoch 1, batch 9050, loss[loss=0.2006, simple_loss=0.2583, pruned_loss=0.0714, over 4650.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2533, pruned_loss=0.06499, over 971998.05 frames.], batch size: 13, lr: 9.94e-04
2022-05-03 21:30:06,204 INFO [train.py:715] (5/8) Epoch 1, batch 9100, loss[loss=0.1757, simple_loss=0.2431, pruned_loss=0.05418, over 4954.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2534, pruned_loss=0.06479, over 972204.46 frames.], batch size: 21, lr: 9.94e-04
2022-05-03 21:30:45,841 INFO [train.py:715] (5/8) Epoch 1, batch 9150, loss[loss=0.171, simple_loss=0.2247, pruned_loss=0.05862, over 4780.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2525, pruned_loss=0.06415, over 971662.55 frames.], batch size: 18, lr: 9.93e-04
2022-05-03 21:31:24,121 INFO [train.py:715] (5/8) Epoch 1, batch 9200, loss[loss=0.1858, simple_loss=0.2618, pruned_loss=0.0549, over 4803.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2518, pruned_loss=0.06402, over 972016.59 frames.], batch size: 21, lr: 9.93e-04
2022-05-03 21:32:03,941 INFO [train.py:715] (5/8) Epoch 1, batch 9250, loss[loss=0.2031, simple_loss=0.2604, pruned_loss=0.07293, over 4940.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2517, pruned_loss=0.06389, over 972002.51 frames.], batch size: 29, lr: 9.92e-04
2022-05-03 21:32:43,821 INFO [train.py:715] (5/8) Epoch 1, batch 9300, loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04416, over 4929.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2524, pruned_loss=0.06412, over 972133.08 frames.], batch size: 21, lr: 9.92e-04
2022-05-03 21:33:22,871 INFO [train.py:715] (5/8) Epoch 1, batch 9350, loss[loss=0.1483, simple_loss=0.2146, pruned_loss=0.04107, over 4817.00 frames.], tot_loss[loss=0.1899, simple_loss=0.252, pruned_loss=0.06391, over 972169.83 frames.], batch size: 21, lr: 9.91e-04
2022-05-03 21:34:02,359 INFO [train.py:715] (5/8) Epoch 1, batch 9400, loss[loss=0.1916, simple_loss=0.2491, pruned_loss=0.06709, over 4761.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2518, pruned_loss=0.06425, over 971483.32 frames.], batch size: 14, lr: 9.91e-04
2022-05-03 21:34:42,532 INFO [train.py:715] (5/8) Epoch 1, batch 9450, loss[loss=0.1678, simple_loss=0.2391, pruned_loss=0.04823, over 4912.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2518, pruned_loss=0.06397, over 971417.95 frames.], batch size: 17, lr: 9.90e-04
2022-05-03 21:35:22,125 INFO [train.py:715] (5/8) Epoch 1, batch 9500, loss[loss=0.167, simple_loss=0.2292, pruned_loss=0.05237, over 4794.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2516, pruned_loss=0.06364, over 971679.55 frames.], batch size: 14, lr: 9.89e-04
2022-05-03 21:36:00,395 INFO [train.py:715] (5/8) Epoch 1, batch 9550, loss[loss=0.2461, simple_loss=0.2814, pruned_loss=0.1054, over 4817.00 frames.], tot_loss[loss=0.19, simple_loss=0.2518, pruned_loss=0.06405, over 973045.69 frames.], batch size: 27, lr: 9.89e-04
2022-05-03 21:36:40,619 INFO [train.py:715] (5/8) Epoch 1, batch 9600, loss[loss=0.1833, simple_loss=0.2497, pruned_loss=0.05846, over 4799.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2516, pruned_loss=0.0644, over 972775.50 frames.], batch size: 24, lr: 9.88e-04
2022-05-03 21:37:20,354 INFO [train.py:715] (5/8) Epoch 1, batch 9650, loss[loss=0.2272, simple_loss=0.2924, pruned_loss=0.081, over 4963.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2525, pruned_loss=0.06433, over 972465.40 frames.], batch size: 24, lr: 9.88e-04
2022-05-03 21:37:58,743 INFO [train.py:715] (5/8) Epoch 1, batch 9700, loss[loss=0.1979, simple_loss=0.2518, pruned_loss=0.072, over 4791.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2522, pruned_loss=0.06421, over 973103.92 frames.], batch size: 18, lr: 9.87e-04
2022-05-03 21:38:38,640 INFO [train.py:715] (5/8) Epoch 1, batch 9750, loss[loss=0.2, simple_loss=0.2649, pruned_loss=0.06754, over 4777.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2534, pruned_loss=0.06463, over 973083.48 frames.], batch size: 17, lr: 9.87e-04
2022-05-03 21:39:19,057 INFO [train.py:715] (5/8) Epoch 1, batch 9800, loss[loss=0.256, simple_loss=0.3092, pruned_loss=0.1014, over 4958.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2526, pruned_loss=0.06451, over 973041.28 frames.], batch size: 35, lr: 9.86e-04
2022-05-03 21:39:58,295 INFO [train.py:715] (5/8) Epoch 1, batch 9850, loss[loss=0.1674, simple_loss=0.2435, pruned_loss=0.04566, over 4694.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2522, pruned_loss=0.06436, over 972344.90 frames.], batch size: 15, lr: 9.86e-04
2022-05-03 21:40:37,079 INFO [train.py:715] (5/8) Epoch 1, batch 9900, loss[loss=0.1968, simple_loss=0.2658, pruned_loss=0.0639, over 4920.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2531, pruned_loss=0.06508, over 972117.80 frames.], batch size: 18, lr: 9.85e-04
2022-05-03 21:41:17,360 INFO [train.py:715] (5/8) Epoch 1, batch 9950, loss[loss=0.201, simple_loss=0.2535, pruned_loss=0.07421, over 4872.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2519, pruned_loss=0.06432, over 972532.86 frames.], batch size: 16, lr: 9.85e-04
2022-05-03 21:41:57,263 INFO [train.py:715] (5/8) Epoch 1, batch 10000, loss[loss=0.2009, simple_loss=0.2641, pruned_loss=0.06882, over 4937.00 frames.], tot_loss[loss=0.1897, simple_loss=0.252, pruned_loss=0.0637, over 973214.37 frames.], batch size: 39, lr: 9.84e-04
2022-05-03 21:42:36,321 INFO [train.py:715] (5/8) Epoch 1, batch 10050, loss[loss=0.1814, simple_loss=0.2482, pruned_loss=0.0573, over 4806.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2507, pruned_loss=0.0632, over 972555.64 frames.], batch size: 26, lr: 9.83e-04
2022-05-03 21:43:15,951 INFO [train.py:715] (5/8) Epoch 1, batch 10100, loss[loss=0.1615, simple_loss=0.2289, pruned_loss=0.04702, over 4776.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2514, pruned_loss=0.06391, over 972586.57 frames.], batch size: 18, lr: 9.83e-04
2022-05-03 21:43:55,967 INFO [train.py:715] (5/8) Epoch 1, batch 10150, loss[loss=0.2773, simple_loss=0.3376, pruned_loss=0.1085, over 4889.00 frames.], tot_loss[loss=0.19, simple_loss=0.2519, pruned_loss=0.06405, over 972525.07 frames.], batch size: 22, lr: 9.82e-04
2022-05-03 21:44:35,078 INFO [train.py:715] (5/8) Epoch 1, batch 10200, loss[loss=0.1942, simple_loss=0.2579, pruned_loss=0.06526, over 4911.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2522, pruned_loss=0.0638, over 973346.40 frames.], batch size: 17, lr: 9.82e-04
2022-05-03 21:45:14,036 INFO [train.py:715] (5/8) Epoch 1, batch 10250, loss[loss=0.1656, simple_loss=0.2465, pruned_loss=0.04231, over 4895.00 frames.], tot_loss[loss=0.1884, simple_loss=0.251, pruned_loss=0.06292, over 972577.44 frames.], batch size: 22, lr: 9.81e-04
2022-05-03 21:45:54,202 INFO [train.py:715] (5/8) Epoch 1, batch 10300, loss[loss=0.1659, simple_loss=0.2345, pruned_loss=0.04863, over 4818.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2516, pruned_loss=0.06357, over 971603.56 frames.], batch size: 26, lr: 9.81e-04
2022-05-03 21:46:34,446 INFO [train.py:715] (5/8) Epoch 1, batch 10350, loss[loss=0.2212, simple_loss=0.2775, pruned_loss=0.08245, over 4826.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2516, pruned_loss=0.06327, over 971092.27 frames.], batch size: 27, lr: 9.80e-04
2022-05-03 21:47:13,905 INFO [train.py:715] (5/8) Epoch 1, batch 10400, loss[loss=0.2039, simple_loss=0.2661, pruned_loss=0.0709, over 4776.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2524, pruned_loss=0.06402, over 971142.25 frames.], batch size: 14, lr: 9.80e-04
2022-05-03 21:47:53,942 INFO [train.py:715] (5/8) Epoch 1, batch 10450, loss[loss=0.1558, simple_loss=0.2279, pruned_loss=0.04185, over 4910.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2525, pruned_loss=0.06403, over 972164.67 frames.], batch size: 17, lr: 9.79e-04
2022-05-03 21:48:34,474 INFO [train.py:715] (5/8) Epoch 1, batch 10500, loss[loss=0.2133, simple_loss=0.2771, pruned_loss=0.0748, over 4910.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2516, pruned_loss=0.06335, over 972145.49 frames.], batch size: 18, lr: 9.79e-04
2022-05-03 21:49:13,758 INFO [train.py:715] (5/8) Epoch 1, batch 10550, loss[loss=0.1809, simple_loss=0.2477, pruned_loss=0.05708, over 4760.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2521, pruned_loss=0.06334, over 973033.59 frames.], batch size: 19, lr: 9.78e-04
2022-05-03 21:49:52,639 INFO [train.py:715] (5/8) Epoch 1, batch 10600, loss[loss=0.1723, simple_loss=0.2438, pruned_loss=0.05038, over 4777.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2517, pruned_loss=0.06291, over 972703.39 frames.], batch size: 18, lr: 9.78e-04
2022-05-03 21:50:33,173 INFO [train.py:715] (5/8) Epoch 1, batch 10650, loss[loss=0.2381, simple_loss=0.2856, pruned_loss=0.09529, over 4852.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2515, pruned_loss=0.06319, over 971927.61 frames.], batch size: 30, lr: 9.77e-04
2022-05-03 21:51:13,723 INFO [train.py:715] (5/8) Epoch 1, batch 10700, loss[loss=0.1898, simple_loss=0.2542, pruned_loss=0.06272, over 4839.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2522, pruned_loss=0.06347, over 972301.95 frames.], batch size: 15, lr: 9.76e-04
2022-05-03 21:51:52,989 INFO [train.py:715] (5/8) Epoch 1, batch 10750, loss[loss=0.2087, simple_loss=0.2693, pruned_loss=0.07411, over 4856.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2531, pruned_loss=0.06425, over 972498.69 frames.], batch size: 30, lr: 9.76e-04
2022-05-03 21:52:32,270 INFO [train.py:715] (5/8) Epoch 1, batch 10800, loss[loss=0.1912, simple_loss=0.2523, pruned_loss=0.06507, over 4971.00 frames.], tot_loss[loss=0.191, simple_loss=0.2534, pruned_loss=0.06429, over 972965.52 frames.], batch size: 14, lr: 9.75e-04
2022-05-03 21:53:12,731 INFO [train.py:715] (5/8) Epoch 1, batch 10850, loss[loss=0.2118, simple_loss=0.2674, pruned_loss=0.07815, over 4910.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2527, pruned_loss=0.064, over 972955.79 frames.], batch size: 35, lr: 9.75e-04
2022-05-03 21:53:52,217 INFO [train.py:715] (5/8) Epoch 1, batch 10900, loss[loss=0.1915, simple_loss=0.2558, pruned_loss=0.06359, over 4976.00 frames.], tot_loss[loss=0.1905, simple_loss=0.253, pruned_loss=0.06399, over 973346.15 frames.], batch size: 28, lr: 9.74e-04
2022-05-03 21:54:30,705 INFO [train.py:715] (5/8) Epoch 1, batch 10950, loss[loss=0.2287, simple_loss=0.2862, pruned_loss=0.08564, over 4831.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2532, pruned_loss=0.06424, over 973778.09 frames.], batch size: 25, lr: 9.74e-04
2022-05-03 21:55:10,751 INFO [train.py:715] (5/8) Epoch 1, batch 11000, loss[loss=0.1816, simple_loss=0.2487, pruned_loss=0.05721, over 4990.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2523, pruned_loss=0.06327, over 973746.54 frames.], batch size: 28, lr: 9.73e-04
2022-05-03 21:55:50,515 INFO [train.py:715] (5/8) Epoch 1, batch 11050, loss[loss=0.1745, simple_loss=0.2307, pruned_loss=0.05912, over 4742.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2519, pruned_loss=0.06317, over 972831.35 frames.], batch size: 16, lr: 9.73e-04
2022-05-03 21:56:29,266 INFO [train.py:715] (5/8) Epoch 1, batch 11100, loss[loss=0.1951, simple_loss=0.2535, pruned_loss=0.0684, over 4812.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2511, pruned_loss=0.06274, over 972965.02 frames.], batch size: 21, lr: 9.72e-04
2022-05-03 21:57:08,674 INFO [train.py:715] (5/8) Epoch 1, batch 11150, loss[loss=0.1879, simple_loss=0.2504, pruned_loss=0.0627, over 4835.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2513, pruned_loss=0.06282, over 972231.53 frames.], batch size: 30, lr: 9.72e-04
2022-05-03 21:57:48,803 INFO [train.py:715] (5/8) Epoch 1, batch 11200, loss[loss=0.168, simple_loss=0.2417, pruned_loss=0.0471, over 4909.00 frames.], tot_loss[loss=0.1879, simple_loss=0.251, pruned_loss=0.06239, over 971923.17 frames.], batch size: 19, lr: 9.71e-04
2022-05-03 21:58:28,395 INFO [train.py:715] (5/8) Epoch 1, batch 11250, loss[loss=0.1711, simple_loss=0.2409, pruned_loss=0.05067, over 4795.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2504, pruned_loss=0.06193, over 972055.75 frames.], batch size: 24, lr: 9.71e-04
2022-05-03 21:59:06,581 INFO [train.py:715] (5/8) Epoch 1, batch 11300, loss[loss=0.1823, simple_loss=0.2432, pruned_loss=0.06068, over 4808.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2503, pruned_loss=0.06199, over 972012.13 frames.], batch size: 25, lr: 9.70e-04
2022-05-03 21:59:46,984 INFO [train.py:715] (5/8) Epoch 1, batch 11350, loss[loss=0.1992, simple_loss=0.2627, pruned_loss=0.06783, over 4824.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2504, pruned_loss=0.06184, over 972903.83 frames.], batch size: 15, lr: 9.70e-04
2022-05-03 22:00:26,695 INFO [train.py:715] (5/8) Epoch 1, batch 11400, loss[loss=0.1638, simple_loss=0.2219, pruned_loss=0.05282, over 4967.00 frames.], tot_loss[loss=0.1872, simple_loss=0.25, pruned_loss=0.06217, over 972239.46 frames.], batch size: 14, lr: 9.69e-04
2022-05-03 22:01:04,857 INFO [train.py:715] (5/8) Epoch 1, batch 11450, loss[loss=0.1701, simple_loss=0.2421, pruned_loss=0.0491, over 4957.00 frames.], tot_loss[loss=0.1876, simple_loss=0.25, pruned_loss=0.06258, over 972578.11 frames.], batch size: 23, lr: 9.69e-04
2022-05-03 22:01:44,067 INFO [train.py:715] (5/8) Epoch 1, batch 11500, loss[loss=0.2154, simple_loss=0.274, pruned_loss=0.0784, over 4876.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2512, pruned_loss=0.06327, over 973096.75 frames.], batch size: 16, lr: 9.68e-04
2022-05-03 22:02:23,956 INFO [train.py:715] (5/8) Epoch 1, batch 11550, loss[loss=0.2037, simple_loss=0.2568, pruned_loss=0.07532, over 4834.00 frames.], tot_loss[loss=0.189, simple_loss=0.2515, pruned_loss=0.06321, over 972294.07 frames.], batch size: 30, lr: 9.68e-04
2022-05-03 22:03:03,166 INFO [train.py:715] (5/8) Epoch 1, batch 11600, loss[loss=0.1692, simple_loss=0.233, pruned_loss=0.0527, over 4982.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2518, pruned_loss=0.06341, over 972416.32 frames.], batch size: 25, lr: 9.67e-04
2022-05-03 22:03:41,492 INFO [train.py:715] (5/8) Epoch 1, batch 11650, loss[loss=0.1759, simple_loss=0.2424, pruned_loss=0.05466, over 4957.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2517, pruned_loss=0.06339, over 972410.27 frames.], batch size: 35, lr: 9.67e-04
2022-05-03 22:04:21,431 INFO [train.py:715] (5/8) Epoch 1, batch 11700, loss[loss=0.1593, simple_loss=0.2325, pruned_loss=0.04303, over 4834.00 frames.], tot_loss[loss=0.1882, simple_loss=0.251, pruned_loss=0.06269, over 971956.24 frames.], batch size: 25, lr: 9.66e-04
2022-05-03 22:05:01,248 INFO [train.py:715] (5/8) Epoch 1, batch 11750, loss[loss=0.2117, simple_loss=0.2698, pruned_loss=0.07677, over 4928.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2515, pruned_loss=0.06291, over 971666.59 frames.], batch size: 35, lr: 9.66e-04
2022-05-03 22:05:40,550 INFO [train.py:715] (5/8) Epoch 1, batch 11800, loss[loss=0.1935, simple_loss=0.2411, pruned_loss=0.07291, over 4867.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2518, pruned_loss=0.06328, over 971688.81 frames.], batch size: 32, lr: 9.65e-04
2022-05-03 22:06:19,253 INFO [train.py:715] (5/8) Epoch 1, batch 11850, loss[loss=0.1963, simple_loss=0.2576, pruned_loss=0.06753, over 4940.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2509, pruned_loss=0.06283, over 971969.75 frames.], batch size: 21, lr: 9.65e-04
2022-05-03 22:06:59,286 INFO [train.py:715] (5/8) Epoch 1, batch 11900, loss[loss=0.1884, simple_loss=0.2432, pruned_loss=0.06681, over 4839.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2501, pruned_loss=0.06232, over 971789.40 frames.], batch size: 30, lr: 9.64e-04
2022-05-03 22:07:38,634 INFO [train.py:715] (5/8) Epoch 1, batch 11950, loss[loss=0.1682, simple_loss=0.2463, pruned_loss=0.04504, over 4821.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2494, pruned_loss=0.06186, over 972197.88 frames.], batch size: 27, lr: 9.63e-04
2022-05-03 22:08:17,118 INFO [train.py:715] (5/8) Epoch 1, batch 12000, loss[loss=0.175, simple_loss=0.2477, pruned_loss=0.05115, over 4926.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2495, pruned_loss=0.06167, over 972580.33 frames.], batch size: 23, lr: 9.63e-04
2022-05-03 22:08:17,118 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 22:08:27,630 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1244, simple_loss=0.2116, pruned_loss=0.01858, over 914524.00 frames.
2022-05-03 22:09:06,366 INFO [train.py:715] (5/8) Epoch 1, batch 12050, loss[loss=0.2207, simple_loss=0.2813, pruned_loss=0.0801, over 4958.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2511, pruned_loss=0.06222, over 973261.17 frames.], batch size: 35, lr: 9.62e-04
2022-05-03 22:09:46,990 INFO [train.py:715] (5/8) Epoch 1, batch 12100, loss[loss=0.2143, simple_loss=0.2636, pruned_loss=0.08254, over 4932.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2512, pruned_loss=0.06249, over 972473.86 frames.], batch size: 23, lr: 9.62e-04
2022-05-03 22:10:27,668 INFO [train.py:715] (5/8) Epoch 1, batch 12150, loss[loss=0.1861, simple_loss=0.2507, pruned_loss=0.06074, over 4857.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2515, pruned_loss=0.06284, over 972393.67 frames.], batch size: 39, lr: 9.61e-04
2022-05-03 22:11:06,640 INFO [train.py:715] (5/8) Epoch 1, batch 12200, loss[loss=0.2014, simple_loss=0.2467, pruned_loss=0.07801, over 4905.00 frames.], tot_loss[loss=0.1881, simple_loss=0.251, pruned_loss=0.06258, over 972168.90 frames.], batch size: 17, lr: 9.61e-04
2022-05-03 22:11:46,543 INFO [train.py:715] (5/8) Epoch 1, batch 12250, loss[loss=0.1938, simple_loss=0.2523, pruned_loss=0.0677, over 4969.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2509, pruned_loss=0.06193, over 971235.85 frames.], batch size: 14, lr: 9.60e-04
2022-05-03 22:12:27,155 INFO [train.py:715] (5/8) Epoch 1, batch 12300, loss[loss=0.2168, simple_loss=0.2921, pruned_loss=0.07072, over 4946.00 frames.], tot_loss[loss=0.188, simple_loss=0.2509, pruned_loss=0.06254, over 971925.32 frames.], batch size: 21, lr: 9.60e-04
2022-05-03 22:13:06,770 INFO [train.py:715] (5/8) Epoch 1, batch 12350, loss[loss=0.2229, simple_loss=0.2944, pruned_loss=0.07573, over 4833.00 frames.], tot_loss[loss=0.1882, simple_loss=0.251, pruned_loss=0.06267, over 972835.51 frames.], batch size: 15, lr: 9.59e-04
2022-05-03 22:13:45,540 INFO [train.py:715] (5/8) Epoch 1, batch 12400, loss[loss=0.1856, simple_loss=0.2598, pruned_loss=0.05574, over 4828.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2506, pruned_loss=0.06275, over 972821.39 frames.], batch size: 26, lr: 9.59e-04
2022-05-03 22:14:25,685 INFO [train.py:715] (5/8) Epoch 1, batch 12450, loss[loss=0.1673, simple_loss=0.2401, pruned_loss=0.04723, over 4830.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2514, pruned_loss=0.06296, over 973368.50 frames.], batch size: 15, lr: 9.58e-04
2022-05-03 22:15:05,667 INFO [train.py:715] (5/8) Epoch 1, batch 12500, loss[loss=0.1661, simple_loss=0.234, pruned_loss=0.04907, over 4764.00 frames.], tot_loss[loss=0.189, simple_loss=0.2515, pruned_loss=0.06321, over 972948.00 frames.], batch size: 19, lr: 9.58e-04
2022-05-03 22:15:44,875 INFO [train.py:715] (5/8) Epoch 1, batch 12550, loss[loss=0.1781, simple_loss=0.2545, pruned_loss=0.05082, over 4990.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2519, pruned_loss=0.06337, over 972983.46 frames.], batch size: 20, lr: 9.57e-04
2022-05-03 22:16:24,271 INFO [train.py:715] (5/8) Epoch 1, batch 12600, loss[loss=0.1847, simple_loss=0.2502, pruned_loss=0.0596, over 4752.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2515, pruned_loss=0.06314, over 972792.51 frames.], batch size: 16, lr: 9.57e-04
2022-05-03 22:17:04,547 INFO [train.py:715] (5/8) Epoch 1, batch 12650, loss[loss=0.1624, simple_loss=0.2239, pruned_loss=0.05045, over 4938.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2509, pruned_loss=0.06311, over 973021.85 frames.], batch size: 29, lr: 9.56e-04
2022-05-03 22:17:43,552 INFO [train.py:715] (5/8) Epoch 1, batch 12700, loss[loss=0.2036, simple_loss=0.2694, pruned_loss=0.06892, over 4953.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2506, pruned_loss=0.06289, over 973179.08 frames.], batch size: 21, lr: 9.56e-04
2022-05-03 22:18:22,947 INFO [train.py:715] (5/8) Epoch 1, batch 12750, loss[loss=0.2243, simple_loss=0.2709, pruned_loss=0.08884, over 4755.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2508, pruned_loss=0.06303, over 972957.69 frames.], batch size: 16, lr: 9.55e-04
2022-05-03 22:19:03,051 INFO [train.py:715] (5/8) Epoch 1, batch 12800, loss[loss=0.1645, simple_loss=0.2379, pruned_loss=0.04551, over 4945.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2511, pruned_loss=0.06324, over 972264.76 frames.], batch size: 39, lr: 9.55e-04
2022-05-03 22:19:42,870 INFO [train.py:715] (5/8) Epoch 1, batch 12850, loss[loss=0.1496, simple_loss=0.2146, pruned_loss=0.04237, over 4781.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2508, pruned_loss=0.06303, over 972489.48 frames.], batch size: 17, lr: 9.54e-04
2022-05-03 22:20:21,819 INFO [train.py:715] (5/8) Epoch 1, batch 12900, loss[loss=0.1709, simple_loss=0.236, pruned_loss=0.05295, over 4957.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2513, pruned_loss=0.06347, over 973280.84 frames.], batch size: 24, lr: 9.54e-04
2022-05-03 22:21:01,111 INFO [train.py:715] (5/8) Epoch 1, batch 12950, loss[loss=0.1774, simple_loss=0.2466, pruned_loss=0.05409, over 4957.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2516, pruned_loss=0.06335, over 973064.04 frames.], batch size: 21, lr: 9.53e-04
2022-05-03 22:21:41,526 INFO [train.py:715] (5/8) Epoch 1, batch 13000, loss[loss=0.1877, simple_loss=0.2597, pruned_loss=0.05783, over 4910.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2517, pruned_loss=0.06362, over 972725.11 frames.], batch size: 18, lr: 9.53e-04
2022-05-03 22:22:21,098 INFO [train.py:715] (5/8) Epoch 1, batch 13050, loss[loss=0.2137, simple_loss=0.2725, pruned_loss=0.07747, over 4933.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2515, pruned_loss=0.06354, over 972380.49 frames.], batch size: 35, lr: 9.52e-04
2022-05-03 22:23:01,176 INFO [train.py:715] (5/8) Epoch 1, batch 13100, loss[loss=0.1949, simple_loss=0.2603, pruned_loss=0.06476, over 4953.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2524, pruned_loss=0.064, over 972217.49 frames.], batch size: 35, lr: 9.52e-04
2022-05-03 22:23:41,360 INFO [train.py:715] (5/8) Epoch 1, batch 13150, loss[loss=0.1863, simple_loss=0.2481, pruned_loss=0.06223, over 4800.00 frames.], tot_loss[loss=0.189, simple_loss=0.2515, pruned_loss=0.06325, over 972300.19 frames.], batch size: 14, lr: 9.51e-04
2022-05-03 22:24:23,878 INFO [train.py:715] (5/8) Epoch 1, batch 13200, loss[loss=0.1941, simple_loss=0.2577, pruned_loss=0.06525, over 4975.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2509, pruned_loss=0.06318, over 971484.72 frames.], batch size: 15, lr: 9.51e-04
2022-05-03 22:25:03,006 INFO [train.py:715] (5/8) Epoch 1, batch 13250, loss[loss=0.1788, simple_loss=0.2487, pruned_loss=0.0545, over 4849.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2509, pruned_loss=0.06349, over 971589.36 frames.], batch size: 20, lr: 9.51e-04
2022-05-03 22:25:41,751 INFO [train.py:715] (5/8) Epoch 1, batch 13300, loss[loss=0.1923, simple_loss=0.2492, pruned_loss=0.06771, over 4910.00 frames.], tot_loss[loss=0.1879, simple_loss=0.25, pruned_loss=0.06293, over 971988.47 frames.], batch size: 17, lr: 9.50e-04
2022-05-03 22:26:21,980 INFO [train.py:715] (5/8) Epoch 1, batch 13350, loss[loss=0.1587, simple_loss=0.224, pruned_loss=0.04674, over 4683.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2488, pruned_loss=0.06214, over 971686.43 frames.], batch size: 15, lr: 9.50e-04
2022-05-03 22:27:01,385 INFO [train.py:715] (5/8) Epoch 1, batch 13400, loss[loss=0.1616, simple_loss=0.2302, pruned_loss=0.04652, over 4800.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2492, pruned_loss=0.06191, over 971576.64 frames.], batch size: 17, lr: 9.49e-04
2022-05-03 22:27:41,356 INFO [train.py:715] (5/8) Epoch 1, batch 13450, loss[loss=0.1759, simple_loss=0.2439, pruned_loss=0.05397, over 4808.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2501, pruned_loss=0.0628, over 971202.07 frames.], batch size: 21, lr: 9.49e-04
2022-05-03 22:28:21,068 INFO [train.py:715] (5/8) Epoch 1, batch 13500, loss[loss=0.1633, simple_loss=0.2322, pruned_loss=0.0472, over 4926.00 frames.], tot_loss[loss=0.1876, simple_loss=0.25, pruned_loss=0.06261, over 971530.89 frames.], batch size: 18, lr: 9.48e-04
2022-05-03 22:29:01,036 INFO [train.py:715] (5/8) Epoch 1, batch 13550, loss[loss=0.1829, simple_loss=0.2451, pruned_loss=0.06034, over 4905.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2508, pruned_loss=0.06299, over 971908.89 frames.], batch size: 19, lr: 9.48e-04
2022-05-03 22:29:39,299 INFO [train.py:715] (5/8) Epoch 1, batch 13600, loss[loss=0.1643, simple_loss=0.2304, pruned_loss=0.0491, over 4813.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2511, pruned_loss=0.06331, over 972845.57 frames.], batch size: 13, lr: 9.47e-04
2022-05-03 22:30:18,506 INFO [train.py:715] (5/8) Epoch 1, batch 13650, loss[loss=0.202, simple_loss=0.2699, pruned_loss=0.06703, over 4841.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2505, pruned_loss=0.06319, over 972407.89 frames.], batch size: 26, lr: 9.47e-04
2022-05-03 22:30:58,734 INFO [train.py:715] (5/8) Epoch 1, batch 13700, loss[loss=0.2247, simple_loss=0.2852, pruned_loss=0.08209, over 4935.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2503, pruned_loss=0.06272, over 972732.31 frames.], batch size: 39, lr: 9.46e-04
2022-05-03 22:31:38,132 INFO [train.py:715] (5/8) Epoch 1, batch 13750, loss[loss=0.1749, simple_loss=0.2374, pruned_loss=0.05621, over 4806.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2494, pruned_loss=0.06194, over 972488.26 frames.], batch size: 21, lr: 9.46e-04
2022-05-03 22:32:17,280 INFO [train.py:715] (5/8) Epoch 1, batch 13800, loss[loss=0.18, simple_loss=0.2455, pruned_loss=0.05728, over 4818.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2494, pruned_loss=0.06185, over 973050.07 frames.], batch size: 27, lr: 9.45e-04
2022-05-03 22:32:56,966 INFO [train.py:715] (5/8) Epoch 1, batch 13850, loss[loss=0.1908, simple_loss=0.2505, pruned_loss=0.0655, over 4756.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2501, pruned_loss=0.06213, over 973195.57 frames.], batch size: 16, lr: 9.45e-04
2022-05-03 22:33:36,808 INFO [train.py:715] (5/8) Epoch 1, batch 13900, loss[loss=0.1864, simple_loss=0.249, pruned_loss=0.06195, over 4828.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2504, pruned_loss=0.0622, over 973332.07 frames.], batch size: 26, lr: 9.44e-04
2022-05-03 22:34:15,306 INFO [train.py:715] (5/8) Epoch 1, batch 13950, loss[loss=0.2166, simple_loss=0.2765, pruned_loss=0.07837, over 4914.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2506, pruned_loss=0.06225, over 972218.83 frames.], batch size: 19, lr: 9.44e-04
2022-05-03 22:34:54,565 INFO [train.py:715] (5/8) Epoch 1, batch 14000, loss[loss=0.204, simple_loss=0.2613, pruned_loss=0.07337, over 4837.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2507, pruned_loss=0.06237, over 971422.12 frames.], batch size: 30, lr: 9.43e-04
2022-05-03 22:35:34,712 INFO [train.py:715] (5/8) Epoch 1, batch 14050, loss[loss=0.2158, simple_loss=0.2706, pruned_loss=0.08049, over 4982.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2507, pruned_loss=0.06251, over 972240.63 frames.], batch size: 14, lr: 9.43e-04
2022-05-03 22:36:13,513 INFO [train.py:715] (5/8) Epoch 1, batch 14100, loss[loss=0.214, simple_loss=0.2718, pruned_loss=0.07811, over 4821.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2508, pruned_loss=0.06225, over 971913.00 frames.], batch size: 13, lr: 9.42e-04
2022-05-03 22:36:52,747 INFO [train.py:715] (5/8) Epoch 1, batch 14150, loss[loss=0.1485, simple_loss=0.2128, pruned_loss=0.04208, over 4762.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2506, pruned_loss=0.06192, over 971635.89 frames.], batch size: 12, lr: 9.42e-04
2022-05-03 22:37:31,979 INFO [train.py:715] (5/8) Epoch 1, batch 14200, loss[loss=0.2042, simple_loss=0.2672, pruned_loss=0.07063, over 4916.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2509, pruned_loss=0.0627, over 972527.68 frames.], batch size: 39, lr: 9.41e-04
2022-05-03 22:38:12,093 INFO [train.py:715] (5/8) Epoch 1, batch 14250, loss[loss=0.1966, simple_loss=0.2602, pruned_loss=0.06651, over 4979.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2509, pruned_loss=0.06309, over 972767.30 frames.], batch size: 15, lr: 9.41e-04
2022-05-03 22:38:50,569 INFO [train.py:715] (5/8) Epoch 1, batch 14300, loss[loss=0.1984, simple_loss=0.2548, pruned_loss=0.07095, over 4929.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2505, pruned_loss=0.06244, over 974015.84 frames.], batch size: 21, lr: 9.40e-04
2022-05-03 22:39:29,557 INFO [train.py:715] (5/8) Epoch 1, batch 14350, loss[loss=0.1962, simple_loss=0.2549, pruned_loss=0.06881, over 4858.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2512, pruned_loss=0.06271, over 974208.92 frames.], batch size: 32, lr: 9.40e-04
2022-05-03 22:40:09,907 INFO [train.py:715] (5/8) Epoch 1, batch 14400, loss[loss=0.1842, simple_loss=0.2473, pruned_loss=0.06058, over 4811.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2513, pruned_loss=0.06291, over 973423.35 frames.], batch size: 13, lr: 9.39e-04
2022-05-03 22:40:48,727 INFO [train.py:715] (5/8) Epoch 1, batch 14450, loss[loss=0.1995, simple_loss=0.2605, pruned_loss=0.06926, over 4841.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2506, pruned_loss=0.06221, over 973863.54 frames.], batch size: 15, lr: 9.39e-04
2022-05-03 22:41:28,251 INFO [train.py:715] (5/8) Epoch 1, batch 14500, loss[loss=0.2046, simple_loss=0.2589, pruned_loss=0.07515, over 4987.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2501, pruned_loss=0.06231, over 973653.36 frames.], batch size: 14, lr: 9.39e-04
2022-05-03 22:42:08,353 INFO [train.py:715] (5/8) Epoch 1, batch 14550, loss[loss=0.1877, simple_loss=0.2514, pruned_loss=0.06205, over 4827.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2504, pruned_loss=0.06238, over 972945.60 frames.], batch size: 26, lr: 9.38e-04
2022-05-03 22:42:47,865 INFO [train.py:715] (5/8) Epoch 1, batch 14600, loss[loss=0.2175, simple_loss=0.2866, pruned_loss=0.07417, over 4786.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2511, pruned_loss=0.063, over 972761.65 frames.], batch size: 17, lr: 9.38e-04
2022-05-03 22:43:26,825 INFO [train.py:715] (5/8) Epoch 1, batch 14650, loss[loss=0.1525, simple_loss=0.2192, pruned_loss=0.04289, over 4886.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2502, pruned_loss=0.06175, over 972778.52 frames.], batch size: 16, lr: 9.37e-04
2022-05-03 22:44:05,662 INFO [train.py:715] (5/8) Epoch 1, batch 14700, loss[loss=0.1629, simple_loss=0.2263, pruned_loss=0.04977, over 4808.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2498, pruned_loss=0.06164, over 972884.85 frames.], batch size: 12, lr: 9.37e-04
2022-05-03 22:44:45,791 INFO [train.py:715] (5/8) Epoch 1, batch 14750, loss[loss=0.2021, simple_loss=0.2736, pruned_loss=0.06526, over 4753.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2505, pruned_loss=0.06184, over 972544.70 frames.], batch size: 16, lr: 9.36e-04
2022-05-03 22:45:24,936 INFO [train.py:715] (5/8) Epoch 1, batch 14800, loss[loss=0.1885, simple_loss=0.239, pruned_loss=0.06897, over 4979.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2499, pruned_loss=0.062, over 971876.27 frames.], batch size: 14, lr: 9.36e-04
2022-05-03 22:46:04,492 INFO [train.py:715] (5/8) Epoch 1, batch 14850, loss[loss=0.1985, simple_loss=0.2684, pruned_loss=0.06432, over 4787.00 frames.], tot_loss[loss=0.185, simple_loss=0.2481, pruned_loss=0.06093, over 972745.63 frames.], batch size: 21, lr: 9.35e-04
2022-05-03 22:46:43,812 INFO [train.py:715] (5/8) Epoch 1, batch 14900, loss[loss=0.1705, simple_loss=0.2407, pruned_loss=0.05015, over 4992.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2488, pruned_loss=0.06108, over 972097.88 frames.], batch size: 14, lr: 9.35e-04
2022-05-03 22:47:22,417 INFO [train.py:715] (5/8) Epoch 1, batch 14950, loss[loss=0.2049, simple_loss=0.2599, pruned_loss=0.0749, over 4908.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2493, pruned_loss=0.06149, over 972400.21 frames.], batch size: 19, lr: 9.34e-04
2022-05-03 22:48:02,034 INFO [train.py:715] (5/8) Epoch 1, batch 15000, loss[loss=0.159, simple_loss=0.2176, pruned_loss=0.05023, over 4781.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2495, pruned_loss=0.06195, over 972563.91 frames.], batch size: 14, lr: 9.34e-04
2022-05-03 22:48:02,035 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 22:48:17,508 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1242, simple_loss=0.2115, pruned_loss=0.01842, over 914524.00 frames.
2022-05-03 22:48:57,644 INFO [train.py:715] (5/8) Epoch 1, batch 15050, loss[loss=0.1662, simple_loss=0.2354, pruned_loss=0.04849, over 4893.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2506, pruned_loss=0.06311, over 971626.30 frames.], batch size: 38, lr: 9.33e-04
2022-05-03 22:49:37,559 INFO [train.py:715] (5/8) Epoch 1, batch 15100, loss[loss=0.169, simple_loss=0.2454, pruned_loss=0.04631, over 4979.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2497, pruned_loss=0.06242, over 972285.82 frames.], batch size: 25, lr: 9.33e-04
2022-05-03 22:50:18,097 INFO [train.py:715] (5/8) Epoch 1, batch 15150, loss[loss=0.1526, simple_loss=0.2241, pruned_loss=0.04054, over 4876.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2492, pruned_loss=0.06201, over 971985.93 frames.], batch size: 20, lr: 9.32e-04
2022-05-03 22:50:57,475 INFO [train.py:715] (5/8) Epoch 1, batch 15200, loss[loss=0.1927, simple_loss=0.2555, pruned_loss=0.06499, over 4880.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2494, pruned_loss=0.06197, over 972608.53 frames.], batch size: 22, lr: 9.32e-04
2022-05-03 22:51:37,953 INFO [train.py:715] (5/8) Epoch 1, batch 15250, loss[loss=0.1702, simple_loss=0.2281, pruned_loss=0.05609, over 4746.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2501, pruned_loss=0.06281, over 972515.78 frames.], batch size: 16, lr: 9.32e-04
2022-05-03 22:52:17,873 INFO [train.py:715] (5/8) Epoch 1, batch 15300, loss[loss=0.1668, simple_loss=0.2216, pruned_loss=0.05599, over 4900.00 frames.], tot_loss[loss=0.1874, simple_loss=0.25, pruned_loss=0.06244, over 972178.80 frames.], batch size: 29, lr: 9.31e-04
2022-05-03 22:52:57,760 INFO [train.py:715] (5/8) Epoch 1, batch 15350, loss[loss=0.1917, simple_loss=0.2663, pruned_loss=0.05853, over 4982.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2501, pruned_loss=0.06254, over 972748.00 frames.], batch size: 35, lr: 9.31e-04
2022-05-03 22:53:37,898 INFO [train.py:715] (5/8) Epoch 1, batch 15400, loss[loss=0.1852, simple_loss=0.2505, pruned_loss=0.05989, over 4792.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2507, pruned_loss=0.06227, over 971906.20 frames.], batch size: 17, lr: 9.30e-04
2022-05-03 22:54:18,168 INFO [train.py:715] (5/8) Epoch 1, batch 15450, loss[loss=0.1963, simple_loss=0.2601, pruned_loss=0.06627, over 4775.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2497, pruned_loss=0.06175, over 972623.90 frames.], batch size: 17, lr: 9.30e-04
2022-05-03 22:54:58,643 INFO [train.py:715] (5/8) Epoch 1, batch 15500, loss[loss=0.1825, simple_loss=0.2504, pruned_loss=0.0573, over 4930.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2497, pruned_loss=0.06132, over 973741.81 frames.], batch size: 18, lr: 9.29e-04
2022-05-03 22:55:37,735 INFO [train.py:715] (5/8) Epoch 1, batch 15550, loss[loss=0.1608, simple_loss=0.2296, pruned_loss=0.04605, over 4916.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2502, pruned_loss=0.06179, over 972890.24 frames.], batch size: 18, lr: 9.29e-04
2022-05-03 22:56:18,061 INFO [train.py:715] (5/8) Epoch 1, batch 15600, loss[loss=0.2056, simple_loss=0.2738, pruned_loss=0.06872, over 4916.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2499, pruned_loss=0.06177, over 972690.36 frames.], batch size: 18, lr: 9.28e-04
2022-05-03 22:56:58,352 INFO [train.py:715] (5/8) Epoch 1, batch 15650, loss[loss=0.1819, simple_loss=0.2346, pruned_loss=0.06459, over 4934.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2492, pruned_loss=0.06148, over 972959.83 frames.], batch size: 29, lr: 9.28e-04
2022-05-03 22:57:38,272 INFO [train.py:715] (5/8) Epoch 1, batch 15700, loss[loss=0.1597, simple_loss=0.2284, pruned_loss=0.04549, over 4821.00 frames.], tot_loss[loss=0.1864, simple_loss=0.249, pruned_loss=0.06195, over 973485.66 frames.], batch size: 26, lr: 9.27e-04
2022-05-03 22:58:17,913 INFO [train.py:715] (5/8) Epoch 1, batch 15750, loss[loss=0.174, simple_loss=0.2381, pruned_loss=0.05501, over 4834.00 frames.], tot_loss[loss=0.1865, simple_loss=0.249, pruned_loss=0.06201, over 973362.04 frames.], batch size: 15, lr: 9.27e-04
2022-05-03 22:58:58,193 INFO [train.py:715] (5/8) Epoch 1, batch 15800, loss[loss=0.1803, simple_loss=0.2449, pruned_loss=0.05784, over 4780.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2505, pruned_loss=0.0629, over 972548.19 frames.], batch size: 14, lr: 9.27e-04
2022-05-03 22:59:38,876 INFO [train.py:715] (5/8) Epoch 1, batch 15850, loss[loss=0.1366, simple_loss=0.2112, pruned_loss=0.03104, over 4981.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2497, pruned_loss=0.06193, over 973120.20 frames.], batch size: 25, lr: 9.26e-04
2022-05-03 23:00:18,431 INFO [train.py:715] (5/8) Epoch 1, batch 15900, loss[loss=0.1732, simple_loss=0.237, pruned_loss=0.05465, over 4906.00 frames.], tot_loss[loss=0.1857, simple_loss=0.249, pruned_loss=0.06123, over 972699.33 frames.], batch size: 18, lr: 9.26e-04
2022-05-03 23:00:58,069 INFO [train.py:715] (5/8) Epoch 1, batch 15950, loss[loss=0.1662, simple_loss=0.2364, pruned_loss=0.04804, over 4840.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2482, pruned_loss=0.06098, over 972090.50 frames.], batch size: 13, lr: 9.25e-04
2022-05-03 23:01:37,502 INFO [train.py:715] (5/8) Epoch 1, batch 16000, loss[loss=0.2289, simple_loss=0.2948, pruned_loss=0.08147, over 4946.00 frames.], tot_loss[loss=0.1841, simple_loss=0.248, pruned_loss=0.06015, over 971687.45 frames.], batch size: 21, lr: 9.25e-04
2022-05-03 23:02:16,259 INFO [train.py:715] (5/8) Epoch 1, batch 16050, loss[loss=0.1782, simple_loss=0.2504, pruned_loss=0.05295, over 4876.00 frames.], tot_loss[loss=0.184, simple_loss=0.2479, pruned_loss=0.06008, over 971570.61 frames.], batch size: 22, lr: 9.24e-04
2022-05-03 23:02:55,585 INFO [train.py:715] (5/8) Epoch 1, batch 16100, loss[loss=0.2057, simple_loss=0.2704, pruned_loss=0.07052, over 4814.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2484, pruned_loss=0.06065, over 970901.45 frames.], batch size: 15, lr: 9.24e-04
2022-05-03 23:03:35,231 INFO [train.py:715] (5/8) Epoch 1, batch 16150, loss[loss=0.1816, simple_loss=0.2419, pruned_loss=0.06068, over 4832.00 frames.], tot_loss[loss=0.185, simple_loss=0.2487, pruned_loss=0.06068, over 971068.93 frames.], batch size: 13, lr: 9.23e-04
2022-05-03 23:04:15,419 INFO [train.py:715] (5/8) Epoch 1, batch 16200, loss[loss=0.1811, simple_loss=0.2432, pruned_loss=0.05943, over 4942.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2484, pruned_loss=0.06028, over 971350.98 frames.], batch size: 21, lr: 9.23e-04
2022-05-03 23:04:53,725 INFO [train.py:715] (5/8) Epoch 1, batch 16250, loss[loss=0.2076, simple_loss=0.2786, pruned_loss=0.06832, over 4883.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2493, pruned_loss=0.06094, over 971277.68 frames.], batch size: 39, lr: 9.22e-04
2022-05-03 23:05:33,191 INFO [train.py:715] (5/8) Epoch 1, batch 16300, loss[loss=0.1864, simple_loss=0.2412, pruned_loss=0.06579, over 4756.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2488, pruned_loss=0.0608, over 970777.82 frames.], batch size: 16, lr: 9.22e-04
2022-05-03 23:06:12,740 INFO [train.py:715] (5/8) Epoch 1, batch 16350, loss[loss=0.1551, simple_loss=0.2322, pruned_loss=0.03901, over 4803.00 frames.], tot_loss[loss=0.1857, simple_loss=0.249, pruned_loss=0.06124, over 971602.86 frames.], batch size: 25, lr: 9.22e-04
2022-05-03 23:06:51,397 INFO [train.py:715] (5/8) Epoch 1, batch 16400, loss[loss=0.1911, simple_loss=0.2557, pruned_loss=0.06327, over 4782.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2488, pruned_loss=0.06113, over 971033.39 frames.], batch size: 14, lr: 9.21e-04
2022-05-03 23:07:30,894 INFO [train.py:715] (5/8) Epoch 1, batch 16450, loss[loss=0.1666, simple_loss=0.2351, pruned_loss=0.04899, over 4892.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2493, pruned_loss=0.06149, over 970651.39 frames.], batch size: 19, lr: 9.21e-04
2022-05-03 23:08:10,540 INFO [train.py:715] (5/8) Epoch 1, batch 16500, loss[loss=0.2163, simple_loss=0.2779, pruned_loss=0.07736, over 4775.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2488, pruned_loss=0.06131, over 971323.34 frames.], batch size: 16, lr: 9.20e-04
2022-05-03 23:08:50,452 INFO [train.py:715] (5/8) Epoch 1, batch 16550, loss[loss=0.1434, simple_loss=0.2075, pruned_loss=0.03964, over 4981.00 frames.], tot_loss[loss=0.1856, simple_loss=0.249, pruned_loss=0.06114, over 972108.23 frames.], batch size: 14, lr: 9.20e-04
2022-05-03 23:09:28,843 INFO [train.py:715] (5/8) Epoch 1, batch 16600, loss[loss=0.179, simple_loss=0.248, pruned_loss=0.05495, over 4687.00 frames.], tot_loss[loss=0.185, simple_loss=0.2485, pruned_loss=0.06074, over 971172.36 frames.], batch size: 15, lr: 9.19e-04
2022-05-03 23:10:09,002 INFO [train.py:715] (5/8) Epoch 1, batch 16650, loss[loss=0.2241, simple_loss=0.2661, pruned_loss=0.09111, over 4842.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2486, pruned_loss=0.06082, over 970962.08 frames.], batch size: 30, lr: 9.19e-04
2022-05-03 23:10:48,681 INFO [train.py:715] (5/8) Epoch 1, batch 16700, loss[loss=0.2106, simple_loss=0.2721, pruned_loss=0.07458, over 4767.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2505, pruned_loss=0.06208, over 971654.74 frames.], batch size: 18, lr: 9.18e-04
2022-05-03 23:11:28,440 INFO [train.py:715] (5/8) Epoch 1, batch 16750, loss[loss=0.1975, simple_loss=0.254, pruned_loss=0.07052, over 4968.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2502, pruned_loss=0.06214, over 970951.98 frames.], batch size: 35, lr: 9.18e-04
2022-05-03 23:12:08,278 INFO [train.py:715] (5/8) Epoch 1, batch 16800, loss[loss=0.165, simple_loss=0.2438, pruned_loss=0.04311, over 4948.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2502, pruned_loss=0.06233, over 971487.00 frames.], batch size: 21, lr: 9.18e-04
2022-05-03 23:12:47,924 INFO [train.py:715] (5/8) Epoch 1, batch 16850, loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05312, over 4824.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2497, pruned_loss=0.06191, over 971411.01 frames.], batch size: 15, lr: 9.17e-04
2022-05-03 23:13:27,907 INFO [train.py:715] (5/8) Epoch 1, batch 16900, loss[loss=0.191, simple_loss=0.2622, pruned_loss=0.05987, over 4831.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2494, pruned_loss=0.06164, over 971348.60 frames.], batch size: 26, lr: 9.17e-04
2022-05-03 23:14:06,929 INFO [train.py:715] (5/8) Epoch 1, batch 16950, loss[loss=0.1273, simple_loss=0.1971, pruned_loss=0.02878, over 4814.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2495, pruned_loss=0.0617, over 971902.57 frames.], batch size: 13, lr: 9.16e-04
2022-05-03 23:14:46,345 INFO [train.py:715] (5/8) Epoch 1, batch 17000, loss[loss=0.1553, simple_loss=0.2208, pruned_loss=0.04484, over 4963.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2486, pruned_loss=0.06101, over 971698.06 frames.], batch size: 39, lr: 9.16e-04
2022-05-03 23:15:26,356 INFO [train.py:715] (5/8) Epoch 1, batch 17050, loss[loss=0.1952, simple_loss=0.2653, pruned_loss=0.06253, over 4816.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2492, pruned_loss=0.06128, over 972172.89 frames.], batch size: 25, lr: 9.15e-04
2022-05-03 23:16:05,140 INFO [train.py:715] (5/8) Epoch 1, batch 17100, loss[loss=0.1885, simple_loss=0.2743, pruned_loss=0.05135, over 4969.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2502, pruned_loss=0.0618, over 972064.30 frames.], batch size: 15, lr: 9.15e-04
2022-05-03 23:16:44,847 INFO [train.py:715] (5/8) Epoch 1, batch 17150, loss[loss=0.1745, simple_loss=0.2491, pruned_loss=0.04995, over 4875.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2502, pruned_loss=0.06179, over 972044.17 frames.], batch size: 22, lr: 9.15e-04
2022-05-03 23:17:25,478 INFO [train.py:715] (5/8) Epoch 1, batch 17200, loss[loss=0.1565, simple_loss=0.215, pruned_loss=0.04902, over 4770.00 frames.], tot_loss[loss=0.185, simple_loss=0.2488, pruned_loss=0.06061, over 971379.53 frames.], batch size: 18, lr: 9.14e-04
2022-05-03 23:18:05,276 INFO [train.py:715] (5/8) Epoch 1, batch 17250, loss[loss=0.203, simple_loss=0.26, pruned_loss=0.07298, over 4769.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2485, pruned_loss=0.06064, over 971496.71 frames.], batch size: 14, lr: 9.14e-04
2022-05-03 23:18:43,786 INFO [train.py:715] (5/8) Epoch 1, batch 17300, loss[loss=0.2025, simple_loss=0.2638, pruned_loss=0.07065, over 4880.00 frames.], tot_loss[loss=0.1844, simple_loss=0.248, pruned_loss=0.0604, over 972251.63 frames.], batch size: 22, lr: 9.13e-04
2022-05-03 23:19:23,810 INFO [train.py:715] (5/8) Epoch 1, batch 17350, loss[loss=0.2109, simple_loss=0.2704, pruned_loss=0.0757, over 4778.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2488, pruned_loss=0.06044, over 972197.08 frames.], batch size: 17, lr: 9.13e-04
2022-05-03 23:20:03,642 INFO [train.py:715] (5/8) Epoch 1, batch 17400, loss[loss=0.1582, simple_loss=0.2443, pruned_loss=0.03605, over 4899.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2492, pruned_loss=0.06088, over 972136.65 frames.], batch size: 19, lr: 9.12e-04
2022-05-03 23:20:42,895 INFO [train.py:715] (5/8) Epoch 1, batch 17450, loss[loss=0.17, simple_loss=0.234, pruned_loss=0.05301, over 4973.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2483, pruned_loss=0.06058, over 971818.88 frames.], batch size: 15, lr: 9.12e-04
2022-05-03 23:21:23,295 INFO [train.py:715] (5/8) Epoch 1, batch 17500, loss[loss=0.2466, simple_loss=0.289, pruned_loss=0.1021, over 4812.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2477, pruned_loss=0.06053, over 972001.38 frames.], batch size: 26, lr: 9.11e-04
2022-05-03 23:22:03,722 INFO [train.py:715] (5/8) Epoch 1, batch 17550, loss[loss=0.227, simple_loss=0.276, pruned_loss=0.08898, over 4979.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2474, pruned_loss=0.06019, over 972406.98 frames.], batch size: 35, lr: 9.11e-04
2022-05-03 23:22:44,345 INFO [train.py:715] (5/8) Epoch 1, batch 17600, loss[loss=0.2241, simple_loss=0.2961, pruned_loss=0.07602, over 4863.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2489, pruned_loss=0.06143, over 973105.35 frames.], batch size: 20, lr: 9.11e-04
2022-05-03 23:23:24,041 INFO [train.py:715] (5/8) Epoch 1, batch 17650, loss[loss=0.1817, simple_loss=0.249, pruned_loss=0.05723, over 4866.00 frames.], tot_loss[loss=0.1851, simple_loss=0.248, pruned_loss=0.06108, over 972766.69 frames.], batch size: 30, lr: 9.10e-04
2022-05-03 23:24:04,738 INFO [train.py:715] (5/8) Epoch 1, batch 17700, loss[loss=0.2023, simple_loss=0.2641, pruned_loss=0.07027, over 4936.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2475, pruned_loss=0.06076, over 972610.64 frames.], batch size: 29, lr: 9.10e-04
2022-05-03 23:24:44,983 INFO [train.py:715] (5/8) Epoch 1, batch 17750, loss[loss=0.1799, simple_loss=0.2518, pruned_loss=0.05398, over 4895.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2469, pruned_loss=0.06022, over 971554.48 frames.], batch size: 16, lr: 9.09e-04
2022-05-03 23:25:24,520 INFO [train.py:715] (5/8) Epoch 1, batch 17800, loss[loss=0.1969, simple_loss=0.2507, pruned_loss=0.07155, over 4832.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2475, pruned_loss=0.0608, over 971252.32 frames.], batch size: 30, lr: 9.09e-04
2022-05-03 23:26:04,927 INFO [train.py:715] (5/8) Epoch 1, batch 17850, loss[loss=0.2233, simple_loss=0.2827, pruned_loss=0.08193, over 4917.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2485, pruned_loss=0.06142, over 971340.01 frames.], batch size: 17, lr: 9.08e-04
2022-05-03 23:26:44,323 INFO [train.py:715] (5/8) Epoch 1, batch 17900, loss[loss=0.1999, simple_loss=0.2582, pruned_loss=0.07077, over 4908.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2478, pruned_loss=0.06102, over 971828.66 frames.], batch size: 17, lr: 9.08e-04
2022-05-03 23:27:23,560 INFO [train.py:715] (5/8) Epoch 1, batch 17950, loss[loss=0.1655, simple_loss=0.2252, pruned_loss=0.05293, over 4878.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2481, pruned_loss=0.06124, over 970588.81 frames.], batch size: 16, lr: 9.08e-04
2022-05-03 23:28:02,857 INFO [train.py:715] (5/8) Epoch 1, batch 18000, loss[loss=0.1622, simple_loss=0.232, pruned_loss=0.04616, over 4779.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2476, pruned_loss=0.06105, over 970143.26 frames.], batch size: 14, lr: 9.07e-04
2022-05-03 23:28:02,857 INFO [train.py:733] (5/8) Computing validation loss
2022-05-03 23:28:17,471 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.123, simple_loss=0.21, pruned_loss=0.01804, over 914524.00 frames.
2022-05-03 23:28:56,681 INFO [train.py:715] (5/8) Epoch 1, batch 18050, loss[loss=0.18, simple_loss=0.25, pruned_loss=0.055, over 4900.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2475, pruned_loss=0.06065, over 970989.90 frames.], batch size: 17, lr: 9.07e-04
2022-05-03 23:29:37,117 INFO [train.py:715] (5/8) Epoch 1, batch 18100, loss[loss=0.1874, simple_loss=0.2552, pruned_loss=0.05976, over 4937.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2485, pruned_loss=0.06103, over 971399.13 frames.], batch size: 29, lr: 9.06e-04
2022-05-03 23:30:16,930 INFO [train.py:715] (5/8) Epoch 1, batch 18150, loss[loss=0.2136, simple_loss=0.2815, pruned_loss=0.07284, over 4818.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2481, pruned_loss=0.06063, over 970668.29 frames.], batch size: 26, lr: 9.06e-04
2022-05-03 23:30:55,300 INFO [train.py:715] (5/8) Epoch 1, batch 18200, loss[loss=0.1528, simple_loss=0.227, pruned_loss=0.03932, over 4876.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2466, pruned_loss=0.05995, over 971336.26 frames.], batch size: 22, lr: 9.05e-04
2022-05-03 23:31:34,989 INFO [train.py:715] (5/8) Epoch 1, batch 18250, loss[loss=0.1885, simple_loss=0.2475, pruned_loss=0.06479, over 4712.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2476, pruned_loss=0.06066, over 971958.47 frames.], batch size: 12, lr: 9.05e-04
2022-05-03 23:32:14,613 INFO [train.py:715] (5/8) Epoch 1, batch 18300, loss[loss=0.1828, simple_loss=0.2523, pruned_loss=0.05669, over 4988.00 frames.], tot_loss[loss=0.183, simple_loss=0.2463, pruned_loss=0.05984, over 972533.71 frames.], batch size: 28, lr: 9.05e-04
2022-05-03 23:32:53,398 INFO [train.py:715] (5/8) Epoch 1, batch 18350, loss[loss=0.2224, simple_loss=0.2857, pruned_loss=0.07958, over 4916.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2469, pruned_loss=0.06014, over 972155.01 frames.], batch size: 29, lr: 9.04e-04
2022-05-03 23:33:33,132 INFO [train.py:715] (5/8) Epoch 1, batch 18400, loss[loss=0.19, simple_loss=0.254, pruned_loss=0.06301, over 4862.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2474, pruned_loss=0.06025, over 972313.48 frames.], batch size: 22, lr: 9.04e-04
2022-05-03 23:34:13,408 INFO [train.py:715] (5/8) Epoch 1, batch 18450, loss[loss=0.2042, simple_loss=0.2716, pruned_loss=0.06845, over 4760.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2474, pruned_loss=0.0601, over 971627.38 frames.], batch size: 17, lr: 9.03e-04
2022-05-03 23:34:52,235 INFO [train.py:715] (5/8) Epoch 1, batch 18500, loss[loss=0.16, simple_loss=0.2347, pruned_loss=0.04266, over 4973.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2475, pruned_loss=0.05989, over 971496.99 frames.], batch size: 24, lr: 9.03e-04
2022-05-03 23:35:31,272 INFO [train.py:715] (5/8) Epoch 1, batch 18550, loss[loss=0.1831, simple_loss=0.2437, pruned_loss=0.0612, over 4836.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2481, pruned_loss=0.06019, over 970751.87 frames.], batch size: 30, lr: 9.03e-04
2022-05-03 23:36:11,452 INFO [train.py:715] (5/8) Epoch 1, batch 18600, loss[loss=0.2044, simple_loss=0.2592, pruned_loss=0.07485, over 4774.00 frames.], tot_loss[loss=0.1842, simple_loss=0.248, pruned_loss=0.06023, over 971109.96 frames.], batch size: 17, lr: 9.02e-04
2022-05-03 23:36:50,769 INFO [train.py:715] (5/8) Epoch 1, batch 18650, loss[loss=0.1717, simple_loss=0.241, pruned_loss=0.05118, over 4928.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2477, pruned_loss=0.06005, over 971322.82 frames.], batch size: 29, lr: 9.02e-04
2022-05-03 23:37:29,514 INFO [train.py:715] (5/8) Epoch 1, batch 18700, loss[loss=0.1725, simple_loss=0.2388, pruned_loss=0.05305, over 4882.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2481, pruned_loss=0.0605, over 972079.68 frames.], batch size: 22, lr: 9.01e-04
2022-05-03 23:38:08,761 INFO [train.py:715] (5/8) Epoch 1, batch 18750, loss[loss=0.2149, simple_loss=0.258, pruned_loss=0.08595, over 4846.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2477, pruned_loss=0.06053, over 971747.83 frames.], batch size: 32, lr: 9.01e-04
2022-05-03 23:38:48,687 INFO [train.py:715] (5/8) Epoch 1, batch 18800, loss[loss=0.1811, simple_loss=0.241, pruned_loss=0.06059, over 4986.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2469, pruned_loss=0.05991, over 971719.35 frames.], batch size: 28, lr: 9.00e-04
2022-05-03 23:39:27,388 INFO [train.py:715] (5/8) Epoch 1, batch 18850, loss[loss=0.2177, simple_loss=0.2749, pruned_loss=0.08023, over 4882.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2477, pruned_loss=0.06034, over 972034.34 frames.], batch size: 19, lr: 9.00e-04
2022-05-03 23:40:06,873 INFO [train.py:715] (5/8) Epoch 1, batch 18900, loss[loss=0.1787, simple_loss=0.2511, pruned_loss=0.05319, over 4896.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2466, pruned_loss=0.05947, over 971884.93 frames.], batch size: 19, lr: 9.00e-04
2022-05-03 23:40:46,607 INFO [train.py:715] (5/8) Epoch 1, batch 18950, loss[loss=0.1622, simple_loss=0.234, pruned_loss=0.04522, over 4880.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2478, pruned_loss=0.06023, over 971418.36 frames.], batch size: 22, lr: 8.99e-04
2022-05-03 23:41:25,993 INFO [train.py:715] (5/8) Epoch 1, batch 19000, loss[loss=0.1582, simple_loss=0.2285, pruned_loss=0.04397, over 4799.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2478, pruned_loss=0.05999, over 971556.11 frames.], batch size: 21, lr: 8.99e-04
2022-05-03 23:42:05,675 INFO [train.py:715] (5/8) Epoch 1, batch 19050, loss[loss=0.1733, simple_loss=0.2474, pruned_loss=0.04957, over 4799.00 frames.], tot_loss[loss=0.1833, simple_loss=0.247, pruned_loss=0.05981, over 971551.64 frames.], batch size: 25, lr: 8.98e-04
2022-05-03 23:42:44,847 INFO [train.py:715] (5/8) Epoch 1, batch 19100, loss[loss=0.1843, simple_loss=0.2494, pruned_loss=0.05958, over 4794.00 frames.], tot_loss[loss=0.1844, simple_loss=0.248, pruned_loss=0.06042, over 971164.18 frames.], batch size: 14, lr: 8.98e-04
2022-05-03 23:43:24,773 INFO [train.py:715] (5/8) Epoch 1, batch 19150, loss[loss=0.1893, simple_loss=0.2573, pruned_loss=0.06066, over 4763.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2481, pruned_loss=0.06067, over 970890.82 frames.], batch size: 19, lr: 8.98e-04
2022-05-03 23:44:03,412 INFO [train.py:715] (5/8) Epoch 1, batch 19200, loss[loss=0.1787, simple_loss=0.2437, pruned_loss=0.05679, over 4757.00 frames.], tot_loss[loss=0.1844, simple_loss=0.248, pruned_loss=0.06046, over 970738.15 frames.], batch size: 19, lr: 8.97e-04
2022-05-03 23:44:42,697 INFO [train.py:715] (5/8) Epoch 1, batch 19250, loss[loss=0.1446, simple_loss=0.2158, pruned_loss=0.03667, over 4980.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2475, pruned_loss=0.05992, over 970643.02 frames.], batch size: 35, lr: 8.97e-04
2022-05-03 23:45:23,324 INFO [train.py:715] (5/8) Epoch 1, batch 19300, loss[loss=0.1751, simple_loss=0.2393, pruned_loss=0.05547, over 4867.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2473, pruned_loss=0.06005, over 970388.95 frames.], batch size: 20, lr: 8.96e-04
2022-05-03 23:46:02,785 INFO [train.py:715] (5/8) Epoch 1, batch 19350, loss[loss=0.2115, simple_loss=0.2743, pruned_loss=0.0743, over 4978.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2465, pruned_loss=0.05942, over 971669.28 frames.], batch size: 40, lr: 8.96e-04
2022-05-03 23:46:41,169 INFO [train.py:715] (5/8) Epoch 1, batch 19400, loss[loss=0.191, simple_loss=0.2571, pruned_loss=0.0624, over 4830.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2472, pruned_loss=0.05951, over 971728.97 frames.], batch size: 26, lr: 8.95e-04
2022-05-03 23:47:20,593 INFO [train.py:715] (5/8) Epoch 1, batch 19450, loss[loss=0.1861, simple_loss=0.2532, pruned_loss=0.05952, over 4786.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2476, pruned_loss=0.05982, over 970774.02 frames.], batch size: 17, lr: 8.95e-04
2022-05-03 23:48:00,486 INFO [train.py:715] (5/8) Epoch 1, batch 19500, loss[loss=0.1751, simple_loss=0.2442, pruned_loss=0.05304, over 4799.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2477, pruned_loss=0.06038, over 971188.72 frames.], batch size: 24, lr: 8.95e-04
2022-05-03 23:48:39,200 INFO [train.py:715] (5/8) Epoch 1, batch 19550, loss[loss=0.1725, simple_loss=0.2298, pruned_loss=0.05763, over 4662.00 frames.], tot_loss[loss=0.185, simple_loss=0.2484, pruned_loss=0.06075, over 971567.46 frames.], batch size: 14, lr: 8.94e-04
2022-05-03 23:49:18,325 INFO [train.py:715] (5/8) Epoch 1, batch 19600, loss[loss=0.1997, simple_loss=0.265, pruned_loss=0.06715, over 4849.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2486, pruned_loss=0.06084, over 972089.39 frames.], batch size: 32, lr: 8.94e-04
2022-05-03 23:49:58,547 INFO [train.py:715] (5/8) Epoch 1, batch 19650, loss[loss=0.1677, simple_loss=0.237, pruned_loss=0.04914, over 4869.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2489, pruned_loss=0.06102, over 973225.34 frames.], batch size: 16, lr: 8.93e-04
2022-05-03 23:50:37,446 INFO [train.py:715] (5/8) Epoch 1, batch 19700, loss[loss=0.1713, simple_loss=0.2395, pruned_loss=0.05158, over 4849.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2484, pruned_loss=0.06094, over 973551.21 frames.], batch size: 13, lr: 8.93e-04
2022-05-03 23:51:16,596 INFO [train.py:715] (5/8) Epoch 1, batch 19750, loss[loss=0.2037, simple_loss=0.261, pruned_loss=0.07318, over 4858.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2484, pruned_loss=0.06083, over 973620.37 frames.], batch size: 32, lr: 8.93e-04
2022-05-03 23:51:56,237 INFO [train.py:715] (5/8) Epoch 1, batch 19800, loss[loss=0.246, simple_loss=0.2831, pruned_loss=0.1045, over 4975.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2494, pruned_loss=0.06165, over 972569.70 frames.], batch size: 15, lr: 8.92e-04
2022-05-03 23:52:36,505 INFO [train.py:715] (5/8) Epoch 1, batch 19850, loss[loss=0.2118, simple_loss=0.2644, pruned_loss=0.07962, over 4844.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2486, pruned_loss=0.06106, over 972003.12 frames.], batch size: 27, lr: 8.92e-04
2022-05-03 23:53:15,889 INFO [train.py:715] (5/8) Epoch 1, batch 19900, loss[loss=0.1911, simple_loss=0.253, pruned_loss=0.06463, over 4871.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2476, pruned_loss=0.0601, over 971683.66 frames.], batch size: 20, lr: 8.91e-04
2022-05-03 23:53:54,986 INFO [train.py:715] (5/8) Epoch 1, batch 19950, loss[loss=0.2046, simple_loss=0.2596, pruned_loss=0.07478, over 4953.00 frames.], tot_loss[loss=0.1846, simple_loss=0.248, pruned_loss=0.06065, over 972353.29 frames.], batch size: 14, lr: 8.91e-04
2022-05-03 23:54:35,247 INFO [train.py:715] (5/8) Epoch 1, batch 20000, loss[loss=0.1617, simple_loss=0.2349, pruned_loss=0.04429, over 4895.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2481, pruned_loss=0.06063, over 971643.51 frames.], batch size: 19, lr: 8.91e-04
2022-05-03 23:55:14,863 INFO [train.py:715] (5/8) Epoch 1, batch 20050, loss[loss=0.1771, simple_loss=0.2411, pruned_loss=0.05661, over 4799.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2473, pruned_loss=0.05982, over 972171.38 frames.], batch size: 14, lr: 8.90e-04
2022-05-03 23:55:54,264 INFO [train.py:715] (5/8) Epoch 1, batch 20100, loss[loss=0.171, simple_loss=0.2421, pruned_loss=0.04994, over 4827.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2475, pruned_loss=0.0598, over 972238.89 frames.], batch size: 27, lr: 8.90e-04
2022-05-03 23:56:34,282 INFO [train.py:715] (5/8) Epoch 1, batch 20150, loss[loss=0.2028, simple_loss=0.2594, pruned_loss=0.07315, over 4944.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2474, pruned_loss=0.05981, over 971465.58 frames.], batch size: 35, lr: 8.89e-04
2022-05-03 23:57:15,156 INFO [train.py:715] (5/8) Epoch 1, batch 20200, loss[loss=0.2005, simple_loss=0.2782, pruned_loss=0.06144, over 4977.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2479, pruned_loss=0.06036, over 972143.35 frames.], batch size: 28, lr: 8.89e-04
2022-05-03 23:57:53,970 INFO [train.py:715] (5/8) Epoch 1, batch 20250, loss[loss=0.195, simple_loss=0.2603, pruned_loss=0.06482, over 4811.00 frames.], tot_loss[loss=0.1842, simple_loss=0.248, pruned_loss=0.06019, over 972154.86 frames.], batch size: 25, lr: 8.89e-04
2022-05-03 23:58:33,270 INFO [train.py:715] (5/8) Epoch 1, batch 20300, loss[loss=0.1849, simple_loss=0.2551, pruned_loss=0.05729, over 4882.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2472, pruned_loss=0.05982, over 972519.89 frames.], batch size: 16, lr: 8.88e-04
2022-05-03 23:59:13,198 INFO [train.py:715] (5/8) Epoch 1, batch 20350, loss[loss=0.1374, simple_loss=0.1989, pruned_loss=0.03794, over 4790.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2479, pruned_loss=0.06053, over 973429.28 frames.], batch size: 12, lr: 8.88e-04
2022-05-03 23:59:51,741 INFO [train.py:715] (5/8) Epoch 1, batch 20400, loss[loss=0.1994, simple_loss=0.261, pruned_loss=0.06893, over 4966.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2475, pruned_loss=0.06017, over 973088.60 frames.], batch size: 31, lr: 8.87e-04
2022-05-04 00:00:31,297 INFO [train.py:715] (5/8) Epoch 1, batch 20450, loss[loss=0.1848, simple_loss=0.2435, pruned_loss=0.06298, over 4817.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2476, pruned_loss=0.06047, over 972844.95 frames.], batch size: 21, lr: 8.87e-04
2022-05-04 00:01:10,343 INFO [train.py:715] (5/8) Epoch 1, batch 20500, loss[loss=0.1706, simple_loss=0.2337, pruned_loss=0.05379, over 4792.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2471, pruned_loss=0.05989, over 972027.89 frames.], batch size: 14, lr: 8.87e-04
2022-05-04 00:01:50,040 INFO [train.py:715] (5/8) Epoch 1, batch 20550, loss[loss=0.1723, simple_loss=0.2303, pruned_loss=0.05717, over 4786.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2471, pruned_loss=0.05988, over 971924.90 frames.], batch size: 17, lr: 8.86e-04
2022-05-04 00:02:28,909 INFO [train.py:715] (5/8) Epoch 1, batch 20600, loss[loss=0.1873, simple_loss=0.2446, pruned_loss=0.06498, over 4982.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2482, pruned_loss=0.06035, over 971344.39 frames.], batch size: 28, lr: 8.86e-04
2022-05-04 00:03:08,452 INFO [train.py:715] (5/8) Epoch 1, batch 20650, loss[loss=0.1767, simple_loss=0.2423, pruned_loss=0.05553, over 4904.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2485, pruned_loss=0.06052, over 970790.10 frames.], batch size: 17, lr: 8.85e-04
2022-05-04 00:03:48,940 INFO [train.py:715] (5/8) Epoch 1, batch 20700, loss[loss=0.1811, simple_loss=0.2565, pruned_loss=0.05285, over 4784.00 frames.], tot_loss[loss=0.1841, simple_loss=0.248, pruned_loss=0.06017, over 971006.84 frames.], batch size: 18, lr: 8.85e-04
2022-05-04 00:04:28,575 INFO [train.py:715] (5/8) Epoch 1, batch 20750, loss[loss=0.1676, simple_loss=0.2328, pruned_loss=0.05121, over 4738.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2466, pruned_loss=0.05919, over 971416.09 frames.], batch size: 14, lr: 8.85e-04
2022-05-04 00:05:07,876 INFO [train.py:715] (5/8) Epoch 1, batch 20800, loss[loss=0.2278, simple_loss=0.2925, pruned_loss=0.08155, over 4854.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2464, pruned_loss=0.0592, over 971769.96 frames.], batch size: 20, lr: 8.84e-04
2022-05-04 00:05:47,728 INFO [train.py:715] (5/8) Epoch 1, batch 20850, loss[loss=0.1647, simple_loss=0.2299, pruned_loss=0.04979, over 4988.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05918, over 971865.28 frames.], batch size: 15, lr: 8.84e-04
2022-05-04 00:06:27,483 INFO [train.py:715] (5/8) Epoch 1, batch 20900, loss[loss=0.1794, simple_loss=0.2433, pruned_loss=0.05772, over 4863.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2456, pruned_loss=0.05871, over 972568.51 frames.], batch size: 20, lr: 8.83e-04
2022-05-04 00:07:06,277 INFO [train.py:715] (5/8) Epoch 1, batch 20950, loss[loss=0.1963, simple_loss=0.2782, pruned_loss=0.05718, over 4924.00 frames.], tot_loss[loss=0.1817, simple_loss=0.246, pruned_loss=0.05869, over 971605.18 frames.], batch size: 18, lr: 8.83e-04
2022-05-04 00:07:45,659 INFO [train.py:715] (5/8) Epoch 1, batch 21000, loss[loss=0.221, simple_loss=0.2782, pruned_loss=0.08191, over 4978.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2464, pruned_loss=0.05939, over 971505.87 frames.], batch size: 39, lr: 8.83e-04
2022-05-04 00:07:45,659 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 00:08:00,761 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1226, simple_loss=0.2094, pruned_loss=0.01784, over 914524.00 frames.
2022-05-04 00:08:40,111 INFO [train.py:715] (5/8) Epoch 1, batch 21050, loss[loss=0.2194, simple_loss=0.2806, pruned_loss=0.07909, over 4731.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2459, pruned_loss=0.05925, over 970734.56 frames.], batch size: 16, lr: 8.82e-04
2022-05-04 00:09:19,948 INFO [train.py:715] (5/8) Epoch 1, batch 21100, loss[loss=0.1544, simple_loss=0.2246, pruned_loss=0.04206, over 4991.00 frames.], tot_loss[loss=0.1818, simple_loss=0.246, pruned_loss=0.05882, over 970565.42 frames.], batch size: 14, lr: 8.82e-04
2022-05-04 00:09:58,320 INFO [train.py:715] (5/8) Epoch 1, batch 21150, loss[loss=0.2017, simple_loss=0.2682, pruned_loss=0.06763, over 4912.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2462, pruned_loss=0.05918, over 971881.13 frames.], batch size: 18, lr: 8.81e-04
2022-05-04 00:10:40,729 INFO [train.py:715] (5/8) Epoch 1, batch 21200, loss[loss=0.1496, simple_loss=0.2312, pruned_loss=0.03404, over 4929.00 frames.], tot_loss[loss=0.1816, simple_loss=0.246, pruned_loss=0.05859, over 971858.28 frames.], batch size: 23, lr: 8.81e-04
2022-05-04 00:11:20,088 INFO [train.py:715] (5/8) Epoch 1, batch 21250, loss[loss=0.1597, simple_loss=0.243, pruned_loss=0.03816, over 4903.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2463, pruned_loss=0.05837, over 971977.30 frames.], batch size: 19, lr: 8.81e-04
2022-05-04 00:11:59,258 INFO [train.py:715] (5/8) Epoch 1, batch 21300, loss[loss=0.1971, simple_loss=0.2552, pruned_loss=0.0695, over 4851.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2475, pruned_loss=0.05943, over 971825.22 frames.], batch size: 20, lr: 8.80e-04
2022-05-04 00:12:38,144 INFO [train.py:715] (5/8) Epoch 1, batch 21350, loss[loss=0.1611, simple_loss=0.2273, pruned_loss=0.04745, over 4786.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2467, pruned_loss=0.05938, over 971049.68 frames.], batch size: 14, lr: 8.80e-04
2022-05-04 00:13:17,800 INFO [train.py:715] (5/8) Epoch 1, batch 21400, loss[loss=0.1624, simple_loss=0.2278, pruned_loss=0.04846, over 4858.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2463, pruned_loss=0.05954, over 971723.03 frames.], batch size: 20, lr: 8.80e-04
2022-05-04 00:13:57,966 INFO [train.py:715] (5/8) Epoch 1, batch 21450, loss[loss=0.1499, simple_loss=0.2183, pruned_loss=0.04079, over 4774.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2481, pruned_loss=0.06049, over 973340.14 frames.], batch size: 19, lr: 8.79e-04
2022-05-04 00:14:36,215 INFO [train.py:715] (5/8) Epoch 1, batch 21500, loss[loss=0.2244, simple_loss=0.2776, pruned_loss=0.08558, over 4940.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2483, pruned_loss=0.06033, over 972233.18 frames.], batch size: 18, lr: 8.79e-04
2022-05-04 00:15:15,309 INFO [train.py:715] (5/8) Epoch 1, batch 21550, loss[loss=0.1365, simple_loss=0.1969, pruned_loss=0.03804, over 4834.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2489, pruned_loss=0.06095, over 972055.42 frames.], batch size: 13, lr: 8.78e-04
2022-05-04 00:15:54,610 INFO [train.py:715] (5/8) Epoch 1, batch 21600, loss[loss=0.1779, simple_loss=0.2427, pruned_loss=0.05656, over 4928.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2492, pruned_loss=0.06114, over 971851.88 frames.], batch size: 29, lr: 8.78e-04
2022-05-04 00:16:33,916 INFO [train.py:715] (5/8) Epoch 1, batch 21650, loss[loss=0.1397, simple_loss=0.2022, pruned_loss=0.0386, over 4989.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2495, pruned_loss=0.06172, over 971855.90 frames.], batch size: 14, lr: 8.78e-04
2022-05-04 00:17:12,479 INFO [train.py:715] (5/8) Epoch 1, batch 21700, loss[loss=0.1787, simple_loss=0.2443, pruned_loss=0.05658, over 4745.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2484, pruned_loss=0.06054, over 972056.94 frames.], batch size: 16, lr: 8.77e-04
2022-05-04 00:17:52,132 INFO [train.py:715] (5/8) Epoch 1, batch 21750, loss[loss=0.1676, simple_loss=0.223, pruned_loss=0.05612, over 4821.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2484, pruned_loss=0.06103, over 971822.69 frames.], batch size: 13, lr: 8.77e-04
2022-05-04 00:18:31,688 INFO [train.py:715] (5/8) Epoch 1, batch 21800, loss[loss=0.1672, simple_loss=0.2228, pruned_loss=0.05581, over 4871.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2483, pruned_loss=0.0607, over 971812.19 frames.], batch size: 30, lr: 8.76e-04
2022-05-04 00:19:10,441 INFO [train.py:715] (5/8) Epoch 1, batch 21850, loss[loss=0.1845, simple_loss=0.2414, pruned_loss=0.06375, over 4835.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2477, pruned_loss=0.06047, over 972219.37 frames.], batch size: 12, lr: 8.76e-04
2022-05-04 00:19:50,595 INFO [train.py:715] (5/8) Epoch 1, batch 21900, loss[loss=0.2066, simple_loss=0.2654, pruned_loss=0.07387, over 4833.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2479, pruned_loss=0.06071, over 972760.03 frames.], batch size: 26, lr: 8.76e-04
2022-05-04 00:20:30,151 INFO [train.py:715] (5/8) Epoch 1, batch 21950, loss[loss=0.1771, simple_loss=0.2436, pruned_loss=0.05527, over 4796.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2468, pruned_loss=0.05978, over 973187.93 frames.], batch size: 24, lr: 8.75e-04
2022-05-04 00:21:09,938 INFO [train.py:715] (5/8) Epoch 1, batch 22000, loss[loss=0.1691, simple_loss=0.2349, pruned_loss=0.05168, over 4742.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2465, pruned_loss=0.05942, over 972266.59 frames.], batch size: 12, lr: 8.75e-04
2022-05-04 00:21:48,903 INFO [train.py:715] (5/8) Epoch 1, batch 22050, loss[loss=0.1734, simple_loss=0.2391, pruned_loss=0.05381, over 4942.00 frames.], tot_loss[loss=0.1823, simple_loss=0.246, pruned_loss=0.05929, over 972349.06 frames.], batch size: 29, lr: 8.75e-04
2022-05-04 00:22:28,892 INFO [train.py:715] (5/8) Epoch 1, batch 22100, loss[loss=0.1898, simple_loss=0.2459, pruned_loss=0.06692, over 4763.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2472, pruned_loss=0.06031, over 972375.61 frames.], batch size: 17, lr: 8.74e-04
2022-05-04 00:23:08,222 INFO [train.py:715] (5/8) Epoch 1, batch 22150, loss[loss=0.1687, simple_loss=0.2423, pruned_loss=0.04751, over 4977.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2478, pruned_loss=0.06044, over 973555.04 frames.], batch size: 24, lr: 8.74e-04
2022-05-04 00:23:46,646 INFO [train.py:715] (5/8) Epoch 1, batch 22200, loss[loss=0.1524, simple_loss=0.2306, pruned_loss=0.03707, over 4940.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2487, pruned_loss=0.06112, over 973750.59 frames.], batch size: 29, lr: 8.73e-04
2022-05-04 00:24:25,883 INFO [train.py:715] (5/8) Epoch 1, batch 22250, loss[loss=0.2048, simple_loss=0.275, pruned_loss=0.06731, over 4854.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2499, pruned_loss=0.06134, over 973562.07 frames.], batch size: 20, lr: 8.73e-04
2022-05-04 00:25:05,560 INFO [train.py:715] (5/8) Epoch 1, batch 22300, loss[loss=0.1825, simple_loss=0.2478, pruned_loss=0.05863, over 4828.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2492, pruned_loss=0.06105, over 973613.94 frames.], batch size: 12, lr: 8.73e-04
2022-05-04 00:25:45,329 INFO [train.py:715] (5/8) Epoch 1, batch 22350, loss[loss=0.1745, simple_loss=0.2345, pruned_loss=0.05726, over 4863.00 frames.], tot_loss[loss=0.185, simple_loss=0.2481, pruned_loss=0.06096, over 972842.92 frames.], batch size: 22, lr: 8.72e-04
2022-05-04 00:26:24,287 INFO [train.py:715] (5/8) Epoch 1, batch 22400, loss[loss=0.1579, simple_loss=0.2282, pruned_loss=0.04378, over 4874.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2484, pruned_loss=0.06109, over 973736.93 frames.], batch size: 16, lr: 8.72e-04
2022-05-04 00:27:04,011 INFO [train.py:715] (5/8) Epoch 1, batch 22450, loss[loss=0.168, simple_loss=0.2232, pruned_loss=0.05644, over 4884.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2468, pruned_loss=0.05983, over 973489.24 frames.], batch size: 16, lr: 8.72e-04
2022-05-04 00:27:43,648 INFO [train.py:715] (5/8) Epoch 1, batch 22500, loss[loss=0.1695, simple_loss=0.2422, pruned_loss=0.04836, over 4933.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2475, pruned_loss=0.0607, over 973425.81 frames.], batch size: 23, lr: 8.71e-04
2022-05-04 00:28:22,145 INFO [train.py:715] (5/8) Epoch 1, batch 22550, loss[loss=0.2016, simple_loss=0.2572, pruned_loss=0.07295, over 4901.00 frames.], tot_loss[loss=0.184, simple_loss=0.2473, pruned_loss=0.06036, over 972921.10 frames.], batch size: 19, lr: 8.71e-04
2022-05-04 00:29:02,211 INFO [train.py:715] (5/8) Epoch 1, batch 22600, loss[loss=0.2201, simple_loss=0.2686, pruned_loss=0.08584, over 4836.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2479, pruned_loss=0.06038, over 972668.78 frames.], batch size: 30, lr: 8.70e-04
2022-05-04 00:29:42,689 INFO [train.py:715] (5/8) Epoch 1, batch 22650, loss[loss=0.1862, simple_loss=0.257, pruned_loss=0.05772, over 4971.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2472, pruned_loss=0.05951, over 973178.53 frames.], batch size: 25, lr: 8.70e-04
2022-05-04 00:30:22,584 INFO [train.py:715] (5/8) Epoch 1, batch 22700, loss[loss=0.1912, simple_loss=0.2481, pruned_loss=0.06717, over 4937.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2479, pruned_loss=0.06055, over 973549.07 frames.], batch size: 39, lr: 8.70e-04
2022-05-04 00:31:00,978 INFO [train.py:715] (5/8) Epoch 1, batch 22750, loss[loss=0.1781, simple_loss=0.2509, pruned_loss=0.05264, over 4987.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2471, pruned_loss=0.05983, over 973973.23 frames.], batch size: 26, lr: 8.69e-04
2022-05-04 00:31:41,162 INFO [train.py:715] (5/8) Epoch 1, batch 22800, loss[loss=0.1696, simple_loss=0.2428, pruned_loss=0.04815, over 4748.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2472, pruned_loss=0.05989, over 973502.11 frames.], batch size: 16, lr: 8.69e-04
2022-05-04 00:32:20,887 INFO [train.py:715] (5/8) Epoch 1, batch 22850, loss[loss=0.1473, simple_loss=0.2201, pruned_loss=0.03723, over 4843.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2483, pruned_loss=0.06042, over 972589.45 frames.], batch size: 13, lr: 8.68e-04
2022-05-04 00:32:59,721 INFO [train.py:715] (5/8) Epoch 1, batch 22900, loss[loss=0.2164, simple_loss=0.2792, pruned_loss=0.07677, over 4795.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2476, pruned_loss=0.05985, over 972019.13 frames.], batch size: 17, lr: 8.68e-04
2022-05-04 00:33:39,272 INFO [train.py:715] (5/8) Epoch 1, batch 22950, loss[loss=0.171, simple_loss=0.2267, pruned_loss=0.05765, over 4837.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2484, pruned_loss=0.06052, over 972972.68 frames.], batch size: 30, lr: 8.68e-04
2022-05-04 00:34:19,075 INFO [train.py:715] (5/8) Epoch 1, batch 23000, loss[loss=0.1665, simple_loss=0.2334, pruned_loss=0.04984, over 4872.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2476, pruned_loss=0.06009, over 972641.49 frames.], batch size: 20, lr: 8.67e-04
2022-05-04 00:34:57,980 INFO [train.py:715] (5/8) Epoch 1, batch 23050, loss[loss=0.2173, simple_loss=0.2742, pruned_loss=0.08021, over 4772.00 frames.], tot_loss[loss=0.183, simple_loss=0.2468, pruned_loss=0.05964, over 972852.34 frames.], batch size: 18, lr: 8.67e-04
2022-05-04 00:35:37,122 INFO [train.py:715] (5/8) Epoch 1, batch 23100, loss[loss=0.1909, simple_loss=0.2437, pruned_loss=0.06901, over 4798.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2465, pruned_loss=0.05963, over 972870.02 frames.], batch size: 24, lr: 8.67e-04
2022-05-04 00:36:16,855 INFO [train.py:715] (5/8) Epoch 1, batch 23150, loss[loss=0.1478, simple_loss=0.2123, pruned_loss=0.04167, over 4946.00 frames.], tot_loss[loss=0.1826, simple_loss=0.246, pruned_loss=0.05958, over 972595.76 frames.], batch size: 24, lr: 8.66e-04
2022-05-04 00:36:56,382 INFO [train.py:715] (5/8) Epoch 1, batch 23200, loss[loss=0.1908, simple_loss=0.2614, pruned_loss=0.06004, over 4954.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2462, pruned_loss=0.05933, over 972354.78 frames.], batch size: 21, lr: 8.66e-04
2022-05-04 00:37:34,616 INFO [train.py:715] (5/8) Epoch 1, batch 23250, loss[loss=0.1785, simple_loss=0.2411, pruned_loss=0.05796, over 4846.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2463, pruned_loss=0.0594, over 972020.94 frames.], batch size: 34, lr: 8.66e-04
2022-05-04 00:38:14,195 INFO [train.py:715] (5/8) Epoch 1, batch 23300, loss[loss=0.1612, simple_loss=0.2203, pruned_loss=0.05109, over 4839.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2457, pruned_loss=0.05867, over 971505.26 frames.], batch size: 15, lr: 8.65e-04
2022-05-04 00:38:53,771 INFO [train.py:715] (5/8) Epoch 1, batch 23350, loss[loss=0.1693, simple_loss=0.239, pruned_loss=0.04973, over 4750.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2456, pruned_loss=0.05832, over 972473.42 frames.], batch size: 16, lr: 8.65e-04
2022-05-04 00:39:32,067 INFO [train.py:715] (5/8) Epoch 1, batch 23400, loss[loss=0.1863, simple_loss=0.2577, pruned_loss=0.05748, over 4921.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2455, pruned_loss=0.05852, over 972339.98 frames.], batch size: 18, lr: 8.64e-04
2022-05-04 00:40:11,305 INFO [train.py:715] (5/8) Epoch 1, batch 23450, loss[loss=0.184, simple_loss=0.2523, pruned_loss=0.05788, over 4783.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2466, pruned_loss=0.05942, over 971939.51 frames.], batch size: 14, lr: 8.64e-04
2022-05-04 00:40:50,694 INFO [train.py:715] (5/8) Epoch 1, batch 23500, loss[loss=0.2089, simple_loss=0.2553, pruned_loss=0.08128, over 4966.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2463, pruned_loss=0.05963, over 971757.76 frames.], batch size: 39, lr: 8.64e-04
2022-05-04 00:41:29,529 INFO [train.py:715] (5/8) Epoch 1, batch 23550, loss[loss=0.1639, simple_loss=0.243, pruned_loss=0.04237, over 4802.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2466, pruned_loss=0.05948, over 971461.18 frames.], batch size: 21, lr: 8.63e-04
2022-05-04 00:42:07,727 INFO [train.py:715] (5/8) Epoch 1, batch 23600, loss[loss=0.2243, simple_loss=0.2828, pruned_loss=0.08291, over 4983.00 frames.], tot_loss[loss=0.1819, simple_loss=0.246, pruned_loss=0.05894, over 969901.92 frames.], batch size: 33, lr: 8.63e-04
2022-05-04 00:42:47,238 INFO [train.py:715] (5/8) Epoch 1, batch 23650, loss[loss=0.1568, simple_loss=0.2318, pruned_loss=0.0409, over 4689.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2455, pruned_loss=0.05863, over 969607.23 frames.], batch size: 15, lr: 8.63e-04
2022-05-04 00:43:26,749 INFO [train.py:715] (5/8) Epoch 1, batch 23700, loss[loss=0.1878, simple_loss=0.2597, pruned_loss=0.05795, over 4816.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2451, pruned_loss=0.05813, over 970219.44 frames.], batch size: 13, lr: 8.62e-04
2022-05-04 00:44:05,089 INFO [train.py:715] (5/8) Epoch 1, batch 23750, loss[loss=0.1352, simple_loss=0.2009, pruned_loss=0.03475, over 4808.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2452, pruned_loss=0.05835, over 970354.57 frames.], batch size: 12, lr: 8.62e-04
2022-05-04 00:44:44,142 INFO [train.py:715] (5/8) Epoch 1, batch 23800, loss[loss=0.2199, simple_loss=0.2801, pruned_loss=0.07982, over 4959.00 frames.], tot_loss[loss=0.1818, simple_loss=0.246, pruned_loss=0.0588, over 970790.41 frames.], batch size: 15, lr: 8.61e-04
2022-05-04 00:45:24,227 INFO [train.py:715] (5/8) Epoch 1, batch 23850, loss[loss=0.1935, simple_loss=0.259, pruned_loss=0.06398, over 4981.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2471, pruned_loss=0.05931, over 971242.15 frames.], batch size: 20, lr: 8.61e-04
2022-05-04 00:46:03,789 INFO [train.py:715] (5/8) Epoch 1, batch 23900, loss[loss=0.1787, simple_loss=0.2444, pruned_loss=0.05653, over 4980.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2453, pruned_loss=0.0584, over 971303.48 frames.], batch size: 15, lr: 8.61e-04
2022-05-04 00:46:42,592 INFO [train.py:715] (5/8) Epoch 1, batch 23950, loss[loss=0.1932, simple_loss=0.2461, pruned_loss=0.07018, over 4952.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2465, pruned_loss=0.05903, over 971781.23 frames.], batch size: 14, lr: 8.60e-04
2022-05-04 00:47:22,329 INFO [train.py:715] (5/8) Epoch 1, batch 24000, loss[loss=0.1494, simple_loss=0.2164, pruned_loss=0.04121, over 4869.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2455, pruned_loss=0.05832, over 971273.70 frames.], batch size: 22, lr: 8.60e-04
2022-05-04 00:47:22,330 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 00:47:34,529 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1217, simple_loss=0.2087, pruned_loss=0.01736, over 914524.00 frames.
2022-05-04 00:48:14,356 INFO [train.py:715] (5/8) Epoch 1, batch 24050, loss[loss=0.195, simple_loss=0.2483, pruned_loss=0.0708, over 4988.00 frames.], tot_loss[loss=0.1817, simple_loss=0.246, pruned_loss=0.05867, over 970852.08 frames.], batch size: 26, lr: 8.60e-04
2022-05-04 00:48:53,681 INFO [train.py:715] (5/8) Epoch 1, batch 24100, loss[loss=0.1633, simple_loss=0.234, pruned_loss=0.04631, over 4873.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05917, over 970922.29 frames.], batch size: 22, lr: 8.59e-04
2022-05-04 00:49:32,277 INFO [train.py:715] (5/8) Epoch 1, batch 24150, loss[loss=0.1522, simple_loss=0.2191, pruned_loss=0.04265, over 4706.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2466, pruned_loss=0.05926, over 971097.24 frames.], batch size: 15, lr: 8.59e-04
2022-05-04 00:50:11,571 INFO [train.py:715] (5/8) Epoch 1, batch 24200, loss[loss=0.1884, simple_loss=0.259, pruned_loss=0.0589, over 4857.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2461, pruned_loss=0.05902, over 971290.02 frames.], batch size: 22, lr: 8.59e-04
2022-05-04 00:50:52,251 INFO [train.py:715] (5/8) Epoch 1, batch 24250, loss[loss=0.1681, simple_loss=0.2341, pruned_loss=0.05102, over 4899.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2459, pruned_loss=0.05918, over 971795.20 frames.], batch size: 17, lr: 8.58e-04
2022-05-04 00:51:31,678 INFO [train.py:715] (5/8) Epoch 1, batch 24300, loss[loss=0.1635, simple_loss=0.2259, pruned_loss=0.05055, over 4904.00 frames.], tot_loss[loss=0.1824, simple_loss=0.246, pruned_loss=0.05937, over 971642.98 frames.], batch size: 19, lr: 8.58e-04
2022-05-04 00:52:11,124 INFO [train.py:715] (5/8) Epoch 1, batch 24350, loss[loss=0.222, simple_loss=0.2591, pruned_loss=0.0925, over 4984.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2453, pruned_loss=0.05916, over 971723.92 frames.], batch size: 14, lr: 8.57e-04
2022-05-04 00:52:51,498 INFO [train.py:715] (5/8) Epoch 1, batch 24400, loss[loss=0.1618, simple_loss=0.241, pruned_loss=0.04131, over 4819.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2463, pruned_loss=0.05907, over 972258.56 frames.], batch size: 21, lr: 8.57e-04
2022-05-04 00:53:30,579 INFO [train.py:715] (5/8) Epoch 1, batch 24450, loss[loss=0.1498, simple_loss=0.2257, pruned_loss=0.03692, over 4978.00 frames.], tot_loss[loss=0.1819, simple_loss=0.246, pruned_loss=0.05889, over 972170.14 frames.], batch size: 15, lr: 8.57e-04
2022-05-04 00:54:09,301 INFO [train.py:715] (5/8) Epoch 1, batch 24500, loss[loss=0.2479, simple_loss=0.2816, pruned_loss=0.1071, over 4695.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2457, pruned_loss=0.05921, over 971744.28 frames.], batch size: 15, lr: 8.56e-04
2022-05-04 00:54:48,963 INFO [train.py:715] (5/8) Epoch 1, batch 24550, loss[loss=0.189, simple_loss=0.2464, pruned_loss=0.06579, over 4960.00 frames.], tot_loss[loss=0.1834, simple_loss=0.247, pruned_loss=0.05994, over 971847.64 frames.], batch size: 15, lr: 8.56e-04
2022-05-04 00:55:29,265 INFO [train.py:715] (5/8) Epoch 1, batch 24600, loss[loss=0.1832, simple_loss=0.2478, pruned_loss=0.05935, over 4800.00 frames.], tot_loss[loss=0.1835, simple_loss=0.247, pruned_loss=0.06, over 971733.01 frames.], batch size: 25, lr: 8.56e-04
2022-05-04 00:56:08,133 INFO [train.py:715] (5/8) Epoch 1, batch 24650, loss[loss=0.1509, simple_loss=0.2133, pruned_loss=0.04422, over 4749.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2464, pruned_loss=0.05992, over 971706.18 frames.], batch size: 12, lr: 8.55e-04
2022-05-04 00:56:47,165 INFO [train.py:715] (5/8) Epoch 1, batch 24700, loss[loss=0.1592, simple_loss=0.2243, pruned_loss=0.0471, over 4949.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2464, pruned_loss=0.05964, over 971679.93 frames.], batch size: 21, lr: 8.55e-04
2022-05-04 00:57:27,340 INFO [train.py:715] (5/8) Epoch 1, batch 24750, loss[loss=0.1511, simple_loss=0.2235, pruned_loss=0.03933, over 4904.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2461, pruned_loss=0.05951, over 972045.85 frames.], batch size: 19, lr: 8.55e-04
2022-05-04 00:58:06,479 INFO [train.py:715] (5/8) Epoch 1, batch 24800, loss[loss=0.1987, simple_loss=0.2467, pruned_loss=0.07537, over 4742.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2463, pruned_loss=0.06046, over 971626.69 frames.], batch size: 16, lr: 8.54e-04
2022-05-04 00:58:45,104 INFO [train.py:715] (5/8) Epoch 1, batch 24850, loss[loss=0.1636, simple_loss=0.2356, pruned_loss=0.04583, over 4959.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2456, pruned_loss=0.05987, over 971670.08 frames.], batch size: 21, lr: 8.54e-04
2022-05-04 00:59:25,588 INFO [train.py:715] (5/8) Epoch 1, batch 24900, loss[loss=0.1943, simple_loss=0.2553, pruned_loss=0.06667, over 4951.00 frames.], tot_loss[loss=0.182, simple_loss=0.2455, pruned_loss=0.05922, over 972755.00 frames.], batch size: 21, lr: 8.54e-04
2022-05-04 01:00:05,519 INFO [train.py:715] (5/8) Epoch 1, batch 24950, loss[loss=0.1681, simple_loss=0.2345, pruned_loss=0.05083, over 4988.00 frames.], tot_loss[loss=0.182, simple_loss=0.2456, pruned_loss=0.05915, over 973444.36 frames.], batch size: 28, lr: 8.53e-04
2022-05-04 01:00:44,291 INFO [train.py:715] (5/8) Epoch 1, batch 25000, loss[loss=0.1893, simple_loss=0.2553, pruned_loss=0.06161, over 4963.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2456, pruned_loss=0.05884, over 972713.13 frames.], batch size: 24, lr: 8.53e-04
2022-05-04 01:01:22,934 INFO [train.py:715] (5/8) Epoch 1, batch 25050, loss[loss=0.1822, simple_loss=0.2558, pruned_loss=0.0543, over 4913.00 frames.], tot_loss[loss=0.1807, simple_loss=0.245, pruned_loss=0.05823, over 972229.91 frames.], batch size: 23, lr: 8.53e-04
2022-05-04 01:02:02,855 INFO [train.py:715] (5/8) Epoch 1, batch 25100, loss[loss=0.1772, simple_loss=0.2383, pruned_loss=0.05804, over 4844.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2445, pruned_loss=0.05808, over 972389.51 frames.], batch size: 32, lr: 8.52e-04
2022-05-04 01:02:42,032 INFO [train.py:715] (5/8) Epoch 1, batch 25150, loss[loss=0.1717, simple_loss=0.2299, pruned_loss=0.05672, over 4903.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2445, pruned_loss=0.05823, over 973288.02 frames.], batch size: 19, lr: 8.52e-04
2022-05-04 01:03:20,873 INFO [train.py:715] (5/8) Epoch 1, batch 25200, loss[loss=0.1728, simple_loss=0.2391, pruned_loss=0.05326, over 4755.00 frames.], tot_loss[loss=0.18, simple_loss=0.2441, pruned_loss=0.05797, over 972951.08 frames.], batch size: 19, lr: 8.51e-04
2022-05-04 01:04:00,097 INFO [train.py:715] (5/8) Epoch 1, batch 25250, loss[loss=0.2593, simple_loss=0.3159, pruned_loss=0.1013, over 4966.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2439, pruned_loss=0.05769, over 972183.04 frames.], batch size: 21, lr: 8.51e-04
2022-05-04 01:04:40,223 INFO [train.py:715] (5/8) Epoch 1, batch 25300, loss[loss=0.2098, simple_loss=0.2621, pruned_loss=0.07878, over 4835.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2441, pruned_loss=0.05767, over 971727.32 frames.], batch size: 30, lr: 8.51e-04
2022-05-04 01:05:18,875 INFO [train.py:715] (5/8) Epoch 1, batch 25350, loss[loss=0.1684, simple_loss=0.2238, pruned_loss=0.05649, over 4742.00 frames.], tot_loss[loss=0.179, simple_loss=0.2434, pruned_loss=0.05735, over 971496.37 frames.], batch size: 16, lr: 8.50e-04
2022-05-04 01:05:58,214 INFO [train.py:715] (5/8) Epoch 1, batch 25400, loss[loss=0.1567, simple_loss=0.2237, pruned_loss=0.04489, over 4777.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2425, pruned_loss=0.05658, over 971498.53 frames.], batch size: 18, lr: 8.50e-04
2022-05-04 01:06:38,478 INFO [train.py:715] (5/8) Epoch 1, batch 25450, loss[loss=0.1681, simple_loss=0.2343, pruned_loss=0.051, over 4857.00 frames.], tot_loss[loss=0.179, simple_loss=0.2436, pruned_loss=0.0572, over 971934.02 frames.], batch size: 13, lr: 8.50e-04
2022-05-04 01:07:18,419 INFO [train.py:715] (5/8) Epoch 1, batch 25500, loss[loss=0.2097, simple_loss=0.2717, pruned_loss=0.07387, over 4832.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2442, pruned_loss=0.05756, over 971998.25 frames.], batch size: 15, lr: 8.49e-04
2022-05-04 01:07:56,846 INFO [train.py:715] (5/8) Epoch 1, batch 25550, loss[loss=0.1518, simple_loss=0.2213, pruned_loss=0.04113, over 4887.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2446, pruned_loss=0.05809, over 972168.82 frames.], batch size: 17, lr: 8.49e-04
2022-05-04 01:08:36,978 INFO [train.py:715] (5/8) Epoch 1, batch 25600, loss[loss=0.1889, simple_loss=0.2522, pruned_loss=0.06279, over 4781.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2446, pruned_loss=0.05797, over 972730.87 frames.], batch size: 18, lr: 8.49e-04
2022-05-04 01:09:17,500 INFO [train.py:715] (5/8) Epoch 1, batch 25650, loss[loss=0.1994, simple_loss=0.2544, pruned_loss=0.07218, over 4974.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2449, pruned_loss=0.05835, over 971956.04 frames.], batch size: 24, lr: 8.48e-04
2022-05-04 01:09:56,988 INFO [train.py:715] (5/8) Epoch 1, batch 25700, loss[loss=0.1719, simple_loss=0.2477, pruned_loss=0.0481, over 4785.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2463, pruned_loss=0.05936, over 971466.32 frames.], batch size: 17, lr: 8.48e-04
2022-05-04 01:10:36,899 INFO [train.py:715] (5/8) Epoch 1, batch 25750, loss[loss=0.1666, simple_loss=0.2271, pruned_loss=0.0531, over 4808.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2454, pruned_loss=0.05868, over 971825.50 frames.], batch size: 12, lr: 8.48e-04
2022-05-04 01:11:17,394 INFO [train.py:715] (5/8) Epoch 1, batch 25800, loss[loss=0.1867, simple_loss=0.2491, pruned_loss=0.06211, over 4924.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2466, pruned_loss=0.0592, over 972552.43 frames.], batch size: 18, lr: 8.47e-04
2022-05-04 01:11:56,816 INFO [train.py:715] (5/8) Epoch 1, batch 25850, loss[loss=0.2019, simple_loss=0.2636, pruned_loss=0.07012, over 4758.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2462, pruned_loss=0.05896, over 971928.03 frames.], batch size: 16, lr: 8.47e-04
2022-05-04 01:12:35,646 INFO [train.py:715] (5/8) Epoch 1, batch 25900, loss[loss=0.1783, simple_loss=0.24, pruned_loss=0.05835, over 4814.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2454, pruned_loss=0.0586, over 972107.68 frames.], batch size: 27, lr: 8.47e-04
2022-05-04 01:13:15,322 INFO [train.py:715] (5/8) Epoch 1, batch 25950, loss[loss=0.1718, simple_loss=0.2389, pruned_loss=0.05234, over 4909.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2451, pruned_loss=0.05827, over 971651.71 frames.], batch size: 18, lr: 8.46e-04
2022-05-04 01:13:55,202 INFO [train.py:715] (5/8) Epoch 1, batch 26000, loss[loss=0.1633, simple_loss=0.2444, pruned_loss=0.04105, over 4804.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2449, pruned_loss=0.05805, over 971476.28 frames.], batch size: 21, lr: 8.46e-04
2022-05-04 01:14:34,090 INFO [train.py:715] (5/8) Epoch 1, batch 26050, loss[loss=0.2062, simple_loss=0.2617, pruned_loss=0.07533, over 4804.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2454, pruned_loss=0.05862, over 970993.63 frames.], batch size: 24, lr: 8.46e-04
2022-05-04 01:15:13,488 INFO [train.py:715] (5/8) Epoch 1, batch 26100, loss[loss=0.1625, simple_loss=0.2367, pruned_loss=0.04409, over 4852.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2457, pruned_loss=0.05876, over 970101.76 frames.], batch size: 20, lr: 8.45e-04
2022-05-04 01:15:53,621 INFO [train.py:715] (5/8) Epoch 1, batch 26150, loss[loss=0.1619, simple_loss=0.2335, pruned_loss=0.04516, over 4785.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2447, pruned_loss=0.05781, over 970360.95 frames.], batch size: 18, lr: 8.45e-04
2022-05-04 01:16:32,570 INFO [train.py:715] (5/8) Epoch 1, batch 26200, loss[loss=0.1519, simple_loss=0.2158, pruned_loss=0.04405, over 4828.00 frames.], tot_loss[loss=0.1805, simple_loss=0.245, pruned_loss=0.05796, over 970594.70 frames.], batch size: 12, lr: 8.44e-04
2022-05-04 01:17:11,433 INFO [train.py:715] (5/8) Epoch 1, batch 26250, loss[loss=0.199, simple_loss=0.2601, pruned_loss=0.06899, over 4803.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2451, pruned_loss=0.05823, over 970770.90 frames.], batch size: 21, lr: 8.44e-04
2022-05-04 01:17:51,342 INFO [train.py:715] (5/8) Epoch 1, batch 26300, loss[loss=0.2061, simple_loss=0.2677, pruned_loss=0.07222, over 4862.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2458, pruned_loss=0.05869, over 971304.52 frames.], batch size: 20, lr: 8.44e-04
2022-05-04 01:18:31,199 INFO [train.py:715] (5/8) Epoch 1, batch 26350, loss[loss=0.1481, simple_loss=0.2145, pruned_loss=0.04083, over 4770.00 frames.], tot_loss[loss=0.1816, simple_loss=0.246, pruned_loss=0.05866, over 971820.16 frames.], batch size: 12, lr: 8.43e-04
2022-05-04 01:19:09,968 INFO [train.py:715] (5/8) Epoch 1, batch 26400, loss[loss=0.2026, simple_loss=0.2607, pruned_loss=0.07229, over 4959.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05914, over 971734.11 frames.], batch size: 35, lr: 8.43e-04
2022-05-04 01:19:49,168 INFO [train.py:715] (5/8) Epoch 1, batch 26450, loss[loss=0.1816, simple_loss=0.2561, pruned_loss=0.05349, over 4751.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2462, pruned_loss=0.05862, over 971764.37 frames.], batch size: 14, lr: 8.43e-04
2022-05-04 01:20:28,904 INFO [train.py:715] (5/8) Epoch 1, batch 26500, loss[loss=0.2006, simple_loss=0.2605, pruned_loss=0.07036, over 4909.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2451, pruned_loss=0.05802, over 972226.27 frames.], batch size: 17, lr: 8.42e-04
2022-05-04 01:21:08,260 INFO [train.py:715] (5/8) Epoch 1, batch 26550, loss[loss=0.1846, simple_loss=0.2446, pruned_loss=0.0623, over 4920.00 frames.], tot_loss[loss=0.1793, simple_loss=0.244, pruned_loss=0.05729, over 971684.33 frames.], batch size: 18, lr: 8.42e-04
2022-05-04 01:21:47,615 INFO [train.py:715] (5/8) Epoch 1, batch 26600, loss[loss=0.1404, simple_loss=0.2164, pruned_loss=0.03216, over 4737.00 frames.], tot_loss[loss=0.179, simple_loss=0.2441, pruned_loss=0.05698, over 972530.88 frames.], batch size: 16, lr: 8.42e-04
2022-05-04 01:22:27,660 INFO [train.py:715] (5/8) Epoch 1, batch 26650, loss[loss=0.1919, simple_loss=0.2481, pruned_loss=0.0678, over 4898.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2444, pruned_loss=0.05715, over 972222.75 frames.], batch size: 39, lr: 8.41e-04
2022-05-04 01:23:07,610 INFO [train.py:715] (5/8) Epoch 1, batch 26700, loss[loss=0.235, simple_loss=0.2856, pruned_loss=0.09225, over 4846.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2443, pruned_loss=0.05748, over 971821.65 frames.], batch size: 30, lr: 8.41e-04
2022-05-04 01:23:46,583 INFO [train.py:715] (5/8) Epoch 1, batch 26750, loss[loss=0.1843, simple_loss=0.2418, pruned_loss=0.06343, over 4951.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2449, pruned_loss=0.05791, over 971617.94 frames.], batch size: 21, lr: 8.41e-04
2022-05-04 01:24:26,596 INFO [train.py:715] (5/8) Epoch 1, batch 26800, loss[loss=0.1964, simple_loss=0.2519, pruned_loss=0.07046, over 4865.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2457, pruned_loss=0.05878, over 971694.66 frames.], batch size: 20, lr: 8.40e-04
2022-05-04 01:25:06,137 INFO [train.py:715] (5/8) Epoch 1, batch 26850, loss[loss=0.2095, simple_loss=0.2673, pruned_loss=0.07588, over 4838.00 frames.], tot_loss[loss=0.1819, simple_loss=0.246, pruned_loss=0.05892, over 972250.78 frames.], batch size: 30, lr: 8.40e-04
2022-05-04 01:25:45,417 INFO [train.py:715] (5/8) Epoch 1, batch 26900, loss[loss=0.1983, simple_loss=0.2449, pruned_loss=0.07585, over 4784.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2457, pruned_loss=0.05866, over 971657.29 frames.], batch size: 14, lr: 8.40e-04
2022-05-04 01:26:24,109 INFO [train.py:715] (5/8) Epoch 1, batch 26950, loss[loss=0.1575, simple_loss=0.2366, pruned_loss=0.03915, over 4855.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2456, pruned_loss=0.05846, over 972694.26 frames.], batch size: 20, lr: 8.39e-04
2022-05-04 01:27:04,122 INFO [train.py:715] (5/8) Epoch 1, batch 27000, loss[loss=0.163, simple_loss=0.2334, pruned_loss=0.04634, over 4986.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2454, pruned_loss=0.058, over 972990.90 frames.], batch size: 25, lr: 8.39e-04
2022-05-04 01:27:04,123 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 01:27:12,718 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1212, simple_loss=0.2081, pruned_loss=0.01718, over 914524.00 frames.
2022-05-04 01:27:53,062 INFO [train.py:715] (5/8) Epoch 1, batch 27050, loss[loss=0.1732, simple_loss=0.2387, pruned_loss=0.05386, over 4815.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2444, pruned_loss=0.05698, over 973062.94 frames.], batch size: 21, lr: 8.39e-04
2022-05-04 01:28:33,371 INFO [train.py:715] (5/8) Epoch 1, batch 27100, loss[loss=0.2032, simple_loss=0.2783, pruned_loss=0.06408, over 4897.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2452, pruned_loss=0.05786, over 972352.98 frames.], batch size: 17, lr: 8.38e-04
2022-05-04 01:29:11,777 INFO [train.py:715] (5/8) Epoch 1, batch 27150, loss[loss=0.1923, simple_loss=0.2665, pruned_loss=0.05905, over 4931.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2458, pruned_loss=0.05798, over 972471.03 frames.], batch size: 29, lr: 8.38e-04
2022-05-04 01:29:51,719 INFO [train.py:715] (5/8) Epoch 1, batch 27200, loss[loss=0.1896, simple_loss=0.2646, pruned_loss=0.05725, over 4897.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2457, pruned_loss=0.05753, over 972165.80 frames.], batch size: 39, lr: 8.38e-04
2022-05-04 01:30:32,011 INFO [train.py:715] (5/8) Epoch 1, batch 27250, loss[loss=0.1426, simple_loss=0.2057, pruned_loss=0.03973, over 4828.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2447, pruned_loss=0.05732, over 971975.53 frames.], batch size: 13, lr: 8.37e-04
2022-05-04 01:31:11,132 INFO [train.py:715] (5/8) Epoch 1, batch 27300, loss[loss=0.1377, simple_loss=0.2144, pruned_loss=0.03049, over 4821.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2446, pruned_loss=0.05712, over 971369.99 frames.], batch size: 26, lr: 8.37e-04
2022-05-04 01:31:49,671 INFO [train.py:715] (5/8) Epoch 1, batch 27350, loss[loss=0.199, simple_loss=0.2599, pruned_loss=0.06899, over 4908.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2446, pruned_loss=0.05712, over 971137.25 frames.], batch size: 17, lr: 8.37e-04
2022-05-04 01:32:29,600 INFO [train.py:715] (5/8) Epoch 1, batch 27400, loss[loss=0.2147, simple_loss=0.2642, pruned_loss=0.08261, over 4967.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2447, pruned_loss=0.05731, over 972299.46 frames.], batch size: 28, lr: 8.36e-04
2022-05-04 01:33:09,595 INFO [train.py:715] (5/8) Epoch 1, batch 27450, loss[loss=0.1915, simple_loss=0.2613, pruned_loss=0.06084, over 4794.00 frames.], tot_loss[loss=0.18, simple_loss=0.2447, pruned_loss=0.05763, over 972116.19 frames.], batch size: 18, lr: 8.36e-04
2022-05-04 01:33:48,103 INFO [train.py:715] (5/8) Epoch 1, batch 27500, loss[loss=0.173, simple_loss=0.2369, pruned_loss=0.05454, over 4942.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2453, pruned_loss=0.05792, over 973245.50 frames.], batch size: 24, lr: 8.36e-04
2022-05-04 01:34:27,759 INFO [train.py:715] (5/8) Epoch 1, batch 27550, loss[loss=0.1667, simple_loss=0.229, pruned_loss=0.05219, over 4746.00 frames.], tot_loss[loss=0.179, simple_loss=0.244, pruned_loss=0.057, over 972889.36 frames.], batch size: 16, lr: 8.35e-04
2022-05-04 01:35:07,986 INFO [train.py:715] (5/8) Epoch 1, batch 27600, loss[loss=0.174, simple_loss=0.2285, pruned_loss=0.05972, over 4840.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2439, pruned_loss=0.05745, over 972812.26 frames.], batch size: 30, lr: 8.35e-04
2022-05-04 01:35:47,294 INFO [train.py:715] (5/8) Epoch 1, batch 27650, loss[loss=0.209, simple_loss=0.2784, pruned_loss=0.0698, over 4899.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2436, pruned_loss=0.05753, over 973017.99 frames.], batch size: 39, lr: 8.35e-04
2022-05-04 01:36:26,732 INFO [train.py:715] (5/8) Epoch 1, batch 27700, loss[loss=0.1504, simple_loss=0.2161, pruned_loss=0.04238, over 4813.00 frames.], tot_loss[loss=0.1798, simple_loss=0.244, pruned_loss=0.05778, over 972838.80 frames.], batch size: 12, lr: 8.34e-04
2022-05-04 01:37:07,283 INFO [train.py:715] (5/8) Epoch 1, batch 27750, loss[loss=0.1607, simple_loss=0.2421, pruned_loss=0.03962, over 4776.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2436, pruned_loss=0.0576, over 972706.75 frames.], batch size: 18, lr: 8.34e-04
2022-05-04 01:37:47,070 INFO [train.py:715] (5/8) Epoch 1, batch 27800, loss[loss=0.1588, simple_loss=0.2381, pruned_loss=0.03973, over 4897.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2438, pruned_loss=0.05778, over 972796.93 frames.], batch size: 19, lr: 8.34e-04
2022-05-04 01:38:26,356 INFO [train.py:715] (5/8) Epoch 1, batch 27850, loss[loss=0.1514, simple_loss=0.2234, pruned_loss=0.03965, over 4875.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2443, pruned_loss=0.05818, over 972267.34 frames.], batch size: 20, lr: 8.33e-04
2022-05-04 01:39:06,467 INFO [train.py:715] (5/8) Epoch 1, batch 27900, loss[loss=0.1926, simple_loss=0.2493, pruned_loss=0.068, over 4837.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2435, pruned_loss=0.05753, over 971629.38 frames.], batch size: 13, lr: 8.33e-04
2022-05-04 01:39:45,945 INFO [train.py:715] (5/8) Epoch 1, batch 27950, loss[loss=0.1662, simple_loss=0.2407, pruned_loss=0.04584, over 4953.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2445, pruned_loss=0.05788, over 972062.48 frames.], batch size: 24, lr: 8.33e-04
2022-05-04 01:40:25,328 INFO [train.py:715] (5/8) Epoch 1, batch 28000, loss[loss=0.1315, simple_loss=0.1997, pruned_loss=0.03163, over 4652.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2446, pruned_loss=0.05794, over 972661.01 frames.], batch size: 13, lr: 8.32e-04
2022-05-04 01:41:04,104 INFO [train.py:715] (5/8) Epoch 1, batch 28050, loss[loss=0.1909, simple_loss=0.2479, pruned_loss=0.06697, over 4800.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2442, pruned_loss=0.05804, over 972235.96 frames.], batch size: 14, lr: 8.32e-04
2022-05-04 01:41:44,524 INFO [train.py:715] (5/8) Epoch 1, batch 28100, loss[loss=0.1771, simple_loss=0.2404, pruned_loss=0.05687, over 4896.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2442, pruned_loss=0.0584, over 971895.56 frames.], batch size: 39, lr: 8.32e-04
2022-05-04 01:42:23,898 INFO [train.py:715] (5/8) Epoch 1, batch 28150, loss[loss=0.1749, simple_loss=0.2396, pruned_loss=0.05514, over 4795.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2456, pruned_loss=0.0595, over 972252.68 frames.], batch size: 18, lr: 8.31e-04
2022-05-04 01:43:03,287 INFO [train.py:715] (5/8) Epoch 1, batch 28200, loss[loss=0.185, simple_loss=0.2401, pruned_loss=0.0649, over 4907.00 frames.], tot_loss[loss=0.1815, simple_loss=0.245, pruned_loss=0.05907, over 972844.30 frames.], batch size: 17, lr: 8.31e-04
2022-05-04 01:43:43,971 INFO [train.py:715] (5/8) Epoch 1, batch 28250, loss[loss=0.1464, simple_loss=0.2218, pruned_loss=0.03547, over 4835.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2453, pruned_loss=0.05893, over 973091.10 frames.], batch size: 15, lr: 8.31e-04
2022-05-04 01:44:24,415 INFO [train.py:715] (5/8) Epoch 1, batch 28300, loss[loss=0.1413, simple_loss=0.2183, pruned_loss=0.03214, over 4917.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2444, pruned_loss=0.05826, over 972896.38 frames.], batch size: 29, lr: 8.30e-04
2022-05-04 01:45:03,748 INFO [train.py:715] (5/8) Epoch 1, batch 28350, loss[loss=0.1585, simple_loss=0.2394, pruned_loss=0.03878, over 4897.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2438, pruned_loss=0.05849, over 972096.86 frames.], batch size: 19, lr: 8.30e-04
2022-05-04 01:45:42,699 INFO [train.py:715] (5/8) Epoch 1, batch 28400, loss[loss=0.1359, simple_loss=0.2157, pruned_loss=0.02804, over 4928.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2437, pruned_loss=0.05838, over 972176.88 frames.], batch size: 23, lr: 8.30e-04
2022-05-04 01:46:23,128 INFO [train.py:715] (5/8) Epoch 1, batch 28450, loss[loss=0.1999, simple_loss=0.2681, pruned_loss=0.06581, over 4849.00 frames.], tot_loss[loss=0.18, simple_loss=0.2439, pruned_loss=0.05805, over 971887.70 frames.], batch size: 20, lr: 8.29e-04
2022-05-04 01:47:02,712 INFO [train.py:715] (5/8) Epoch 1, batch 28500, loss[loss=0.1762, simple_loss=0.2323, pruned_loss=0.06004, over 4768.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2442, pruned_loss=0.05819, over 971898.82 frames.], batch size: 19, lr: 8.29e-04
2022-05-04 01:47:41,715 INFO [train.py:715] (5/8) Epoch 1, batch 28550, loss[loss=0.2072, simple_loss=0.2687, pruned_loss=0.07288, over 4902.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2451, pruned_loss=0.05851, over 971568.44 frames.], batch size: 17, lr: 8.29e-04
2022-05-04 01:48:22,002 INFO [train.py:715] (5/8) Epoch 1, batch 28600, loss[loss=0.1617, simple_loss=0.2252, pruned_loss=0.0491, over 4971.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2463, pruned_loss=0.05958, over 971868.39 frames.], batch size: 14, lr: 8.28e-04
2022-05-04 01:49:01,947 INFO [train.py:715] (5/8) Epoch 1, batch 28650, loss[loss=0.2143, simple_loss=0.2742, pruned_loss=0.07719, over 4924.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2456, pruned_loss=0.05928, over 972029.94 frames.], batch size: 18, lr: 8.28e-04
2022-05-04 01:49:41,099 INFO [train.py:715] (5/8) Epoch 1, batch 28700, loss[loss=0.2361, simple_loss=0.2878, pruned_loss=0.09226, over 4815.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2456, pruned_loss=0.05931, over 972035.01 frames.], batch size: 13, lr: 8.28e-04
2022-05-04 01:50:20,240 INFO [train.py:715] (5/8) Epoch 1, batch 28750, loss[loss=0.1846, simple_loss=0.2385, pruned_loss=0.0653, over 4776.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2445, pruned_loss=0.05869, over 971592.38 frames.], batch size: 17, lr: 8.27e-04
2022-05-04 01:51:00,835 INFO [train.py:715] (5/8) Epoch 1, batch 28800, loss[loss=0.1943, simple_loss=0.2679, pruned_loss=0.06034, over 4939.00 frames.], tot_loss[loss=0.1809, simple_loss=0.245, pruned_loss=0.05837, over 971788.40 frames.], batch size: 21, lr: 8.27e-04
2022-05-04 01:51:40,143 INFO [train.py:715] (5/8) Epoch 1, batch 28850, loss[loss=0.2045, simple_loss=0.2663, pruned_loss=0.07134, over 4793.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2443, pruned_loss=0.05761, over 971537.76 frames.], batch size: 21, lr: 8.27e-04
2022-05-04 01:52:19,906 INFO [train.py:715] (5/8) Epoch 1, batch 28900, loss[loss=0.1688, simple_loss=0.2481, pruned_loss=0.04475, over 4879.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2441, pruned_loss=0.0572, over 971304.00 frames.], batch size: 22, lr: 8.27e-04
2022-05-04 01:53:00,602 INFO [train.py:715] (5/8) Epoch 1, batch 28950, loss[loss=0.2178, simple_loss=0.2746, pruned_loss=0.08053, over 4782.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2446, pruned_loss=0.05785, over 970830.36 frames.], batch size: 17, lr: 8.26e-04
2022-05-04 01:53:40,737 INFO [train.py:715] (5/8) Epoch 1, batch 29000, loss[loss=0.1757, simple_loss=0.2388, pruned_loss=0.05634, over 4771.00 frames.], tot_loss[loss=0.1809, simple_loss=0.245, pruned_loss=0.05844, over 970847.83 frames.], batch size: 17, lr: 8.26e-04
2022-05-04 01:54:19,715 INFO [train.py:715] (5/8) Epoch 1, batch 29050, loss[loss=0.1531, simple_loss=0.2222, pruned_loss=0.04203, over 4904.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2447, pruned_loss=0.05794, over 971039.27 frames.], batch size: 19, lr: 8.26e-04
2022-05-04 01:54:59,585 INFO [train.py:715] (5/8) Epoch 1, batch 29100, loss[loss=0.1589, simple_loss=0.2377, pruned_loss=0.04007, over 4963.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2442, pruned_loss=0.05724, over 972073.20 frames.], batch size: 24, lr: 8.25e-04
2022-05-04 01:55:40,265 INFO [train.py:715] (5/8) Epoch 1, batch 29150, loss[loss=0.1726, simple_loss=0.2294, pruned_loss=0.05796, over 4762.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2442, pruned_loss=0.058, over 971677.34 frames.], batch size: 16, lr: 8.25e-04
2022-05-04 01:56:22,368 INFO [train.py:715] (5/8) Epoch 1, batch 29200, loss[loss=0.1898, simple_loss=0.2509, pruned_loss=0.06435, over 4896.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2446, pruned_loss=0.05823, over 970278.84 frames.], batch size: 22, lr: 8.25e-04
2022-05-04 01:57:01,393 INFO [train.py:715] (5/8) Epoch 1, batch 29250, loss[loss=0.2, simple_loss=0.2718, pruned_loss=0.06412, over 4759.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2449, pruned_loss=0.05814, over 970913.51 frames.], batch size: 19, lr: 8.24e-04
2022-05-04 01:57:41,943 INFO [train.py:715] (5/8) Epoch 1, batch 29300, loss[loss=0.1585, simple_loss=0.2135, pruned_loss=0.05172, over 4751.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2452, pruned_loss=0.05865, over 972398.85 frames.], batch size: 12, lr: 8.24e-04
2022-05-04 01:58:22,151 INFO [train.py:715] (5/8) Epoch 1, batch 29350, loss[loss=0.1656, simple_loss=0.2253, pruned_loss=0.05289, over 4863.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2456, pruned_loss=0.05877, over 972878.89 frames.], batch size: 20, lr: 8.24e-04
2022-05-04 01:59:00,689 INFO [train.py:715] (5/8) Epoch 1, batch 29400, loss[loss=0.1791, simple_loss=0.244, pruned_loss=0.05712, over 4812.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2453, pruned_loss=0.05855, over 973157.72 frames.], batch size: 27, lr: 8.23e-04
2022-05-04 01:59:40,304 INFO [train.py:715] (5/8) Epoch 1, batch 29450, loss[loss=0.1729, simple_loss=0.2333, pruned_loss=0.05628, over 4853.00 frames.], tot_loss[loss=0.182, simple_loss=0.2458, pruned_loss=0.05909, over 972792.98 frames.], batch size: 30, lr: 8.23e-04
2022-05-04 02:00:20,002 INFO [train.py:715] (5/8) Epoch 1, batch 29500, loss[loss=0.1613, simple_loss=0.2195, pruned_loss=0.05161, over 4881.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2452, pruned_loss=0.05885, over 973513.04 frames.], batch size: 22, lr: 8.23e-04
2022-05-04 02:00:59,407 INFO [train.py:715] (5/8) Epoch 1, batch 29550, loss[loss=0.1527, simple_loss=0.2164, pruned_loss=0.04451, over 4989.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2445, pruned_loss=0.05836, over 973177.35 frames.], batch size: 25, lr: 8.22e-04
2022-05-04 02:01:37,991 INFO [train.py:715] (5/8) Epoch 1, batch 29600, loss[loss=0.1402, simple_loss=0.2116, pruned_loss=0.0344, over 4792.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2433, pruned_loss=0.05767, over 972794.83 frames.], batch size: 12, lr: 8.22e-04
2022-05-04 02:02:18,238 INFO [train.py:715] (5/8) Epoch 1, batch 29650, loss[loss=0.1779, simple_loss=0.2351, pruned_loss=0.0603, over 4864.00 frames.], tot_loss[loss=0.179, simple_loss=0.2431, pruned_loss=0.0574, over 973793.35 frames.], batch size: 32, lr: 8.22e-04
2022-05-04 02:02:58,331 INFO [train.py:715] (5/8) Epoch 1, batch 29700, loss[loss=0.1794, simple_loss=0.255, pruned_loss=0.05187, over 4930.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2431, pruned_loss=0.05724, over 973581.20 frames.], batch size: 21, lr: 8.21e-04
2022-05-04 02:03:36,328 INFO [train.py:715] (5/8) Epoch 1, batch 29750, loss[loss=0.171, simple_loss=0.2325, pruned_loss=0.05478, over 4753.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2442, pruned_loss=0.05816, over 973689.34 frames.], batch size: 19, lr: 8.21e-04
2022-05-04 02:04:15,639 INFO [train.py:715] (5/8) Epoch 1, batch 29800, loss[loss=0.1402, simple_loss=0.2179, pruned_loss=0.03129, over 4692.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2438, pruned_loss=0.05786, over 972861.01 frames.], batch size: 15, lr: 8.21e-04
2022-05-04 02:04:55,049 INFO [train.py:715] (5/8) Epoch 1, batch 29850, loss[loss=0.1663, simple_loss=0.2358, pruned_loss=0.04843, over 4824.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2439, pruned_loss=0.05784, over 972985.09 frames.], batch size: 26, lr: 8.20e-04
2022-05-04 02:05:34,426 INFO [train.py:715] (5/8) Epoch 1, batch 29900, loss[loss=0.2053, simple_loss=0.2761, pruned_loss=0.0672, over 4963.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2437, pruned_loss=0.05739, over 973157.24 frames.], batch size: 39, lr: 8.20e-04
2022-05-04 02:06:12,928 INFO [train.py:715] (5/8) Epoch 1, batch 29950, loss[loss=0.179, simple_loss=0.2487, pruned_loss=0.0547, over 4924.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2422, pruned_loss=0.05632, over 972466.54 frames.], batch size: 18, lr: 8.20e-04
2022-05-04 02:06:52,735 INFO [train.py:715] (5/8) Epoch 1, batch 30000, loss[loss=0.204, simple_loss=0.2681, pruned_loss=0.06991, over 4769.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2429, pruned_loss=0.05691, over 972750.92 frames.], batch size: 19, lr: 8.20e-04
2022-05-04 02:06:52,736 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 02:07:09,692 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1207, simple_loss=0.2076, pruned_loss=0.01687, over 914524.00 frames.
2022-05-04 02:07:50,180 INFO [train.py:715] (5/8) Epoch 1, batch 30050, loss[loss=0.1884, simple_loss=0.2414, pruned_loss=0.06764, over 4850.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2429, pruned_loss=0.05719, over 972035.83 frames.], batch size: 32, lr: 8.19e-04
2022-05-04 02:08:29,661 INFO [train.py:715] (5/8) Epoch 1, batch 30100, loss[loss=0.1729, simple_loss=0.24, pruned_loss=0.05289, over 4930.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2446, pruned_loss=0.05842, over 971370.26 frames.], batch size: 29, lr: 8.19e-04
2022-05-04 02:09:09,057 INFO [train.py:715] (5/8) Epoch 1, batch 30150, loss[loss=0.197, simple_loss=0.2482, pruned_loss=0.07289, over 4915.00 frames.], tot_loss[loss=0.18, simple_loss=0.2438, pruned_loss=0.05808, over 971031.68 frames.], batch size: 17, lr: 8.19e-04
2022-05-04 02:09:48,369 INFO [train.py:715] (5/8) Epoch 1, batch 30200, loss[loss=0.2278, simple_loss=0.2849, pruned_loss=0.08538, over 4822.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2445, pruned_loss=0.05846, over 971500.44 frames.], batch size: 13, lr: 8.18e-04
2022-05-04 02:10:28,818 INFO [train.py:715] (5/8) Epoch 1, batch 30250, loss[loss=0.162, simple_loss=0.2278, pruned_loss=0.04814, over 4886.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2447, pruned_loss=0.0584, over 971466.86 frames.], batch size: 16, lr: 8.18e-04
2022-05-04 02:11:08,797 INFO [train.py:715] (5/8) Epoch 1, batch 30300, loss[loss=0.1548, simple_loss=0.2258, pruned_loss=0.04191, over 4820.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2449, pruned_loss=0.05848, over 971794.79 frames.], batch size: 26, lr: 8.18e-04
2022-05-04 02:11:47,709 INFO [train.py:715] (5/8) Epoch 1, batch 30350, loss[loss=0.1742, simple_loss=0.2409, pruned_loss=0.05374, over 4838.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2448, pruned_loss=0.05831, over 971594.58 frames.], batch size: 32, lr: 8.17e-04
2022-05-04 02:12:27,777 INFO [train.py:715] (5/8) Epoch 1, batch 30400, loss[loss=0.1637, simple_loss=0.2325, pruned_loss=0.0474, over 4853.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2449, pruned_loss=0.05847, over 971518.10 frames.], batch size: 32, lr: 8.17e-04
2022-05-04 02:13:07,264 INFO [train.py:715] (5/8) Epoch 1, batch 30450, loss[loss=0.2144, simple_loss=0.2601, pruned_loss=0.08436, over 4855.00 frames.], tot_loss[loss=0.181, simple_loss=0.2451, pruned_loss=0.05848, over 971741.67 frames.], batch size: 30, lr: 8.17e-04
2022-05-04 02:13:46,439 INFO [train.py:715] (5/8) Epoch 1, batch 30500, loss[loss=0.1793, simple_loss=0.243, pruned_loss=0.05778, over 4835.00 frames.], tot_loss[loss=0.181, simple_loss=0.2457, pruned_loss=0.05816, over 972036.06 frames.], batch size: 26, lr: 8.16e-04
2022-05-04 02:14:25,539 INFO [train.py:715] (5/8) Epoch 1, batch 30550, loss[loss=0.1411, simple_loss=0.2102, pruned_loss=0.03606, over 4777.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2452, pruned_loss=0.05805, over 972094.89 frames.], batch size: 18, lr: 8.16e-04
2022-05-04 02:15:05,339 INFO [train.py:715] (5/8) Epoch 1, batch 30600, loss[loss=0.179, simple_loss=0.2355, pruned_loss=0.06125, over 4910.00 frames.], tot_loss[loss=0.18, simple_loss=0.2446, pruned_loss=0.05771, over 971602.77 frames.], batch size: 23, lr: 8.16e-04
2022-05-04 02:15:44,804 INFO [train.py:715] (5/8) Epoch 1, batch 30650, loss[loss=0.1809, simple_loss=0.2417, pruned_loss=0.06002, over 4854.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2454, pruned_loss=0.05815, over 971409.54 frames.], batch size: 32, lr: 8.15e-04
2022-05-04 02:16:23,385 INFO [train.py:715] (5/8) Epoch 1, batch 30700, loss[loss=0.1541, simple_loss=0.2274, pruned_loss=0.04035, over 4809.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2443, pruned_loss=0.05728, over 971944.55 frames.], batch size: 27, lr: 8.15e-04
2022-05-04 02:17:03,635 INFO [train.py:715] (5/8) Epoch 1, batch 30750, loss[loss=0.1982, simple_loss=0.2514, pruned_loss=0.07245, over 4802.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2444, pruned_loss=0.05757, over 972178.10 frames.], batch size: 21, lr: 8.15e-04
2022-05-04 02:17:43,205 INFO [train.py:715] (5/8) Epoch 1, batch 30800, loss[loss=0.2006, simple_loss=0.2697, pruned_loss=0.06575, over 4774.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2441, pruned_loss=0.05762, over 972638.74 frames.], batch size: 17, lr: 8.15e-04
2022-05-04 02:18:22,128 INFO [train.py:715] (5/8) Epoch 1, batch 30850, loss[loss=0.2143, simple_loss=0.2661, pruned_loss=0.08122, over 4855.00 frames.], tot_loss[loss=0.179, simple_loss=0.2437, pruned_loss=0.0571, over 972257.57 frames.], batch size: 30, lr: 8.14e-04
2022-05-04 02:19:01,713 INFO [train.py:715] (5/8) Epoch 1, batch 30900, loss[loss=0.165, simple_loss=0.2321, pruned_loss=0.04891, over 4904.00 frames.], tot_loss[loss=0.1791, simple_loss=0.244, pruned_loss=0.05714, over 972876.00 frames.], batch size: 17, lr: 8.14e-04
2022-05-04 02:19:41,341 INFO [train.py:715] (5/8) Epoch 1, batch 30950, loss[loss=0.1686, simple_loss=0.2473, pruned_loss=0.04489, over 4738.00 frames.], tot_loss[loss=0.179, simple_loss=0.2441, pruned_loss=0.05698, over 973369.19 frames.], batch size: 16, lr: 8.14e-04
2022-05-04 02:20:20,851 INFO [train.py:715] (5/8) Epoch 1, batch 31000, loss[loss=0.156, simple_loss=0.2355, pruned_loss=0.03829, over 4866.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2433, pruned_loss=0.05675, over 972770.36 frames.], batch size: 20, lr: 8.13e-04
2022-05-04 02:21:00,354 INFO [train.py:715] (5/8) Epoch 1, batch 31050, loss[loss=0.1565, simple_loss=0.2256, pruned_loss=0.04372, over 4762.00 frames.], tot_loss[loss=0.179, simple_loss=0.2434, pruned_loss=0.05727, over 972367.20 frames.], batch size: 19, lr: 8.13e-04
2022-05-04 02:21:40,836 INFO [train.py:715] (5/8) Epoch 1, batch 31100, loss[loss=0.1827, simple_loss=0.2323, pruned_loss=0.06656, over 4756.00 frames.], tot_loss[loss=0.179, simple_loss=0.2434, pruned_loss=0.05726, over 972636.12 frames.], batch size: 19, lr: 8.13e-04
2022-05-04 02:22:20,580 INFO [train.py:715] (5/8) Epoch 1, batch 31150, loss[loss=0.1599, simple_loss=0.2319, pruned_loss=0.04388, over 4939.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2453, pruned_loss=0.05789, over 972523.24 frames.], batch size: 21, lr: 8.12e-04
2022-05-04 02:22:59,625 INFO [train.py:715] (5/8) Epoch 1, batch 31200, loss[loss=0.1446, simple_loss=0.2211, pruned_loss=0.03409, over 4829.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2445, pruned_loss=0.05749, over 972587.56 frames.], batch size: 27, lr: 8.12e-04
2022-05-04 02:23:39,860 INFO [train.py:715] (5/8) Epoch 1, batch 31250, loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.04061, over 4777.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2446, pruned_loss=0.05741, over 971651.63 frames.], batch size: 12, lr: 8.12e-04
2022-05-04 02:24:19,619 INFO [train.py:715] (5/8) Epoch 1, batch 31300, loss[loss=0.2338, simple_loss=0.2832, pruned_loss=0.0922, over 4825.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2447, pruned_loss=0.05782, over 971854.01 frames.], batch size: 15, lr: 8.11e-04
2022-05-04 02:24:59,060 INFO [train.py:715] (5/8) Epoch 1, batch 31350, loss[loss=0.1625, simple_loss=0.2397, pruned_loss=0.04262, over 4936.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2449, pruned_loss=0.05782, over 972555.73 frames.], batch size: 21, lr: 8.11e-04
2022-05-04 02:25:38,857 INFO [train.py:715] (5/8) Epoch 1, batch 31400, loss[loss=0.1601, simple_loss=0.221, pruned_loss=0.04959, over 4802.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2455, pruned_loss=0.05813, over 972702.98 frames.], batch size: 13, lr: 8.11e-04
2022-05-04 02:26:18,863 INFO [train.py:715] (5/8) Epoch 1, batch 31450, loss[loss=0.19, simple_loss=0.2593, pruned_loss=0.06038, over 4856.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2451, pruned_loss=0.05813, over 972002.68 frames.], batch size: 20, lr: 8.11e-04
2022-05-04 02:26:58,727 INFO [train.py:715] (5/8) Epoch 1, batch 31500, loss[loss=0.1953, simple_loss=0.2574, pruned_loss=0.06662, over 4911.00 frames.], tot_loss[loss=0.18, simple_loss=0.2446, pruned_loss=0.05767, over 971828.25 frames.], batch size: 29, lr: 8.10e-04
2022-05-04 02:27:37,227 INFO [train.py:715] (5/8) Epoch 1, batch 31550, loss[loss=0.158, simple_loss=0.2274, pruned_loss=0.04428, over 4767.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2448, pruned_loss=0.05773, over 972132.30 frames.], batch size: 19, lr: 8.10e-04
2022-05-04 02:28:17,413 INFO [train.py:715] (5/8) Epoch 1, batch 31600, loss[loss=0.193, simple_loss=0.2516, pruned_loss=0.06717, over 4965.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2453, pruned_loss=0.05756, over 972560.44 frames.], batch size: 35, lr: 8.10e-04
2022-05-04 02:28:57,087 INFO [train.py:715] (5/8) Epoch 1, batch 31650, loss[loss=0.1855, simple_loss=0.241, pruned_loss=0.06497, over 4955.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2444, pruned_loss=0.05702, over 972974.21 frames.], batch size: 35, lr: 8.09e-04
2022-05-04 02:29:36,999 INFO [train.py:715] (5/8) Epoch 1, batch 31700, loss[loss=0.2253, simple_loss=0.2716, pruned_loss=0.08955, over 4793.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2443, pruned_loss=0.05765, over 973103.98 frames.], batch size: 24, lr: 8.09e-04
2022-05-04 02:30:16,361 INFO [train.py:715] (5/8) Epoch 1, batch 31750, loss[loss=0.1474, simple_loss=0.2175, pruned_loss=0.03866, over 4824.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2432, pruned_loss=0.05726, over 973350.38 frames.], batch size: 15, lr: 8.09e-04
2022-05-04 02:30:56,483 INFO [train.py:715] (5/8) Epoch 1, batch 31800, loss[loss=0.1549, simple_loss=0.228, pruned_loss=0.04086, over 4793.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2437, pruned_loss=0.058, over 973076.66 frames.], batch size: 21, lr: 8.08e-04
2022-05-04 02:31:36,272 INFO [train.py:715] (5/8) Epoch 1, batch 31850, loss[loss=0.1574, simple_loss=0.2215, pruned_loss=0.04661, over 4919.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2433, pruned_loss=0.05742, over 973832.94 frames.], batch size: 23, lr: 8.08e-04
2022-05-04 02:32:15,741 INFO [train.py:715] (5/8) Epoch 1, batch 31900, loss[loss=0.2133, simple_loss=0.2875, pruned_loss=0.06957, over 4760.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2443, pruned_loss=0.05767, over 973931.85 frames.], batch size: 19, lr: 8.08e-04
2022-05-04 02:32:55,105 INFO [train.py:715] (5/8) Epoch 1, batch 31950, loss[loss=0.1369, simple_loss=0.2058, pruned_loss=0.03404, over 4800.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2447, pruned_loss=0.05775, over 973610.24 frames.], batch size: 12, lr: 8.08e-04
2022-05-04 02:33:34,636 INFO [train.py:715] (5/8) Epoch 1, batch 32000, loss[loss=0.1732, simple_loss=0.2487, pruned_loss=0.0488, over 4964.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2454, pruned_loss=0.05786, over 973271.19 frames.], batch size: 24, lr: 8.07e-04
2022-05-04 02:34:14,067 INFO [train.py:715] (5/8) Epoch 1, batch 32050, loss[loss=0.1965, simple_loss=0.2622, pruned_loss=0.06539, over 4828.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2445, pruned_loss=0.0572, over 972379.81 frames.], batch size: 26, lr: 8.07e-04
2022-05-04 02:34:53,315 INFO [train.py:715] (5/8) Epoch 1, batch 32100, loss[loss=0.1862, simple_loss=0.2556, pruned_loss=0.05835, over 4905.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2456, pruned_loss=0.0583, over 972772.22 frames.], batch size: 22, lr: 8.07e-04
2022-05-04 02:35:32,937 INFO [train.py:715] (5/8) Epoch 1, batch 32150, loss[loss=0.1838, simple_loss=0.2503, pruned_loss=0.0586, over 4763.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2453, pruned_loss=0.05858, over 972078.97 frames.], batch size: 16, lr: 8.06e-04
2022-05-04 02:36:12,937 INFO [train.py:715] (5/8) Epoch 1, batch 32200, loss[loss=0.201, simple_loss=0.2679, pruned_loss=0.06704, over 4967.00 frames.], tot_loss[loss=0.181, simple_loss=0.2456, pruned_loss=0.05821, over 972515.35 frames.], batch size: 15, lr: 8.06e-04
2022-05-04 02:36:51,838 INFO [train.py:715] (5/8) Epoch 1, batch 32250, loss[loss=0.2041, simple_loss=0.2575, pruned_loss=0.07538, over 4952.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2451, pruned_loss=0.05796, over 971910.93 frames.], batch size: 35, lr: 8.06e-04
2022-05-04 02:37:31,251 INFO [train.py:715] (5/8) Epoch 1, batch 32300, loss[loss=0.1675, simple_loss=0.2265, pruned_loss=0.05427, over 4854.00 frames.], tot_loss[loss=0.181, simple_loss=0.2453, pruned_loss=0.05832, over 971196.86 frames.], batch size: 32, lr: 8.05e-04
2022-05-04 02:38:10,686 INFO [train.py:715] (5/8) Epoch 1, batch 32350, loss[loss=0.1678, simple_loss=0.2355, pruned_loss=0.05009, over 4950.00 frames.], tot_loss[loss=0.18, simple_loss=0.2446, pruned_loss=0.0577, over 971680.16 frames.], batch size: 23, lr: 8.05e-04
2022-05-04 02:38:50,282 INFO [train.py:715] (5/8) Epoch 1, batch 32400, loss[loss=0.1802, simple_loss=0.243, pruned_loss=0.05869, over 4786.00 frames.], tot_loss[loss=0.1781, simple_loss=0.243, pruned_loss=0.05661, over 971962.19 frames.], batch size: 14, lr: 8.05e-04
2022-05-04 02:39:29,215 INFO [train.py:715] (5/8) Epoch 1, batch 32450, loss[loss=0.1507, simple_loss=0.2187, pruned_loss=0.04139, over 4792.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2438, pruned_loss=0.05731, over 971448.68 frames.], batch size: 21, lr: 8.05e-04
2022-05-04 02:40:08,859 INFO [train.py:715] (5/8) Epoch 1, batch 32500, loss[loss=0.1844, simple_loss=0.245, pruned_loss=0.06191, over 4780.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2431, pruned_loss=0.05705, over 971393.74 frames.], batch size: 17, lr: 8.04e-04
2022-05-04 02:40:48,376 INFO [train.py:715] (5/8) Epoch 1, batch 32550, loss[loss=0.1674, simple_loss=0.2272, pruned_loss=0.05381, over 4980.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2432, pruned_loss=0.05674, over 971491.80 frames.], batch size: 35, lr: 8.04e-04
2022-05-04 02:41:27,296 INFO [train.py:715] (5/8) Epoch 1, batch 32600, loss[loss=0.1933, simple_loss=0.2643, pruned_loss=0.06112, over 4929.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2428, pruned_loss=0.05688, over 971069.03 frames.], batch size: 29, lr: 8.04e-04
2022-05-04 02:42:06,687 INFO [train.py:715] (5/8) Epoch 1, batch 32650, loss[loss=0.188, simple_loss=0.2563, pruned_loss=0.05981, over 4940.00 frames.], tot_loss[loss=0.1784, simple_loss=0.243, pruned_loss=0.05692, over 970832.68 frames.], batch size: 21, lr: 8.03e-04
2022-05-04 02:42:46,231 INFO [train.py:715] (5/8) Epoch 1, batch 32700, loss[loss=0.1519, simple_loss=0.2151, pruned_loss=0.04435, over 4853.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2423, pruned_loss=0.05645, over 971651.11 frames.], batch size: 13, lr: 8.03e-04
2022-05-04 02:43:25,960 INFO [train.py:715] (5/8) Epoch 1, batch 32750, loss[loss=0.2412, simple_loss=0.2953, pruned_loss=0.09359, over 4920.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2436, pruned_loss=0.05675, over 971872.35 frames.], batch size: 39, lr: 8.03e-04
2022-05-04 02:44:05,920 INFO [train.py:715] (5/8) Epoch 1, batch 32800, loss[loss=0.1594, simple_loss=0.2332, pruned_loss=0.04276, over 4957.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2437, pruned_loss=0.0571, over 972392.25 frames.], batch size: 24, lr: 8.02e-04
2022-05-04 02:44:45,555 INFO [train.py:715] (5/8) Epoch 1, batch 32850, loss[loss=0.1819, simple_loss=0.2534, pruned_loss=0.05521, over 4879.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2441, pruned_loss=0.05735, over 971817.00 frames.], batch size: 16, lr: 8.02e-04
2022-05-04 02:45:24,930 INFO [train.py:715] (5/8) Epoch 1, batch 32900, loss[loss=0.1767, simple_loss=0.2476, pruned_loss=0.05294, over 4929.00 frames.], tot_loss[loss=0.1793, simple_loss=0.244, pruned_loss=0.05733, over 972216.57 frames.], batch size: 29, lr: 8.02e-04
2022-05-04 02:46:04,177 INFO [train.py:715] (5/8) Epoch 1, batch 32950, loss[loss=0.1664, simple_loss=0.2356, pruned_loss=0.04854, over 4958.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2435, pruned_loss=0.05685, over 972621.82 frames.], batch size: 24, lr: 8.02e-04
2022-05-04 02:46:43,642 INFO [train.py:715] (5/8) Epoch 1, batch 33000, loss[loss=0.1788, simple_loss=0.2486, pruned_loss=0.05454, over 4796.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05696, over 971688.55 frames.], batch size: 21, lr: 8.01e-04
2022-05-04 02:46:43,643 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 02:46:52,424 INFO [train.py:742] (5/8) Epoch 1, validation: loss=0.1208, simple_loss=0.2074, pruned_loss=0.01714, over 914524.00 frames.
2022-05-04 02:47:32,102 INFO [train.py:715] (5/8) Epoch 1, batch 33050, loss[loss=0.167, simple_loss=0.2364, pruned_loss=0.04882, over 4974.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2428, pruned_loss=0.05674, over 971833.35 frames.], batch size: 14, lr: 8.01e-04
2022-05-04 02:48:12,133 INFO [train.py:715] (5/8) Epoch 1, batch 33100, loss[loss=0.1961, simple_loss=0.2674, pruned_loss=0.06239, over 4964.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2431, pruned_loss=0.05696, over 970850.03 frames.], batch size: 24, lr: 8.01e-04
2022-05-04 02:48:51,999 INFO [train.py:715] (5/8) Epoch 1, batch 33150, loss[loss=0.1601, simple_loss=0.2161, pruned_loss=0.0521, over 4912.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2444, pruned_loss=0.05763, over 971300.02 frames.], batch size: 18, lr: 8.00e-04
2022-05-04 02:49:31,135 INFO [train.py:715] (5/8) Epoch 1, batch 33200, loss[loss=0.2058, simple_loss=0.2552, pruned_loss=0.07824, over 4960.00 frames.], tot_loss[loss=0.1782, simple_loss=0.243, pruned_loss=0.05671, over 972677.84 frames.], batch size: 35, lr: 8.00e-04
2022-05-04 02:50:11,556 INFO [train.py:715] (5/8) Epoch 1, batch 33250, loss[loss=0.1873, simple_loss=0.2424, pruned_loss=0.06607, over 4717.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2431, pruned_loss=0.05697, over 972293.05 frames.], batch size: 15, lr: 8.00e-04
2022-05-04 02:50:51,588 INFO [train.py:715] (5/8) Epoch 1, batch 33300, loss[loss=0.195, simple_loss=0.2633, pruned_loss=0.06331, over 4989.00 frames.], tot_loss[loss=0.1785, simple_loss=0.243, pruned_loss=0.05695, over 972705.05 frames.], batch size: 25, lr: 8.00e-04
2022-05-04 02:51:31,061 INFO [train.py:715] (5/8) Epoch 1, batch 33350, loss[loss=0.197, simple_loss=0.2596, pruned_loss=0.06721, over 4872.00 frames.], tot_loss[loss=0.178, simple_loss=0.2426, pruned_loss=0.05668, over 972975.38 frames.], batch size: 16, lr: 7.99e-04
2022-05-04 02:52:11,435 INFO [train.py:715] (5/8) Epoch 1, batch 33400, loss[loss=0.1772, simple_loss=0.2379, pruned_loss=0.05822, over 4781.00 frames.], tot_loss[loss=0.1782, simple_loss=0.243, pruned_loss=0.05671, over 973472.43 frames.], batch size: 18, lr: 7.99e-04
2022-05-04 02:52:51,302 INFO [train.py:715] (5/8) Epoch 1, batch 33450, loss[loss=0.2071, simple_loss=0.2718, pruned_loss=0.07122, over 4912.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2436, pruned_loss=0.05764, over 973518.36 frames.], batch size: 39, lr: 7.99e-04
2022-05-04 02:53:30,409 INFO [train.py:715] (5/8) Epoch 1, batch 33500, loss[loss=0.1857, simple_loss=0.2415, pruned_loss=0.06492, over 4924.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2445, pruned_loss=0.05813, over 973340.06 frames.], batch size: 23, lr: 7.98e-04
2022-05-04 02:54:10,339 INFO [train.py:715] (5/8) Epoch 1, batch 33550, loss[loss=0.1515, simple_loss=0.2266, pruned_loss=0.03816, over 4800.00 frames.], tot_loss[loss=0.179, simple_loss=0.2437, pruned_loss=0.05719, over 972923.92 frames.], batch size: 25, lr: 7.98e-04
2022-05-04 02:54:50,183 INFO [train.py:715] (5/8) Epoch 1, batch 33600, loss[loss=0.1713, simple_loss=0.2438, pruned_loss=0.04946, over 4695.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2434, pruned_loss=0.05685, over 972107.97 frames.], batch size: 15, lr: 7.98e-04
2022-05-04 02:55:29,606 INFO [train.py:715] (5/8) Epoch 1, batch 33650, loss[loss=0.1787, simple_loss=0.2405, pruned_loss=0.05849, over 4835.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2435, pruned_loss=0.05694, over 971954.90 frames.], batch size: 15, lr: 7.97e-04
2022-05-04 02:56:08,649 INFO [train.py:715] (5/8) Epoch 1, batch 33700, loss[loss=0.174, simple_loss=0.2346, pruned_loss=0.0567, over 4904.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2436, pruned_loss=0.05681, over 971125.62 frames.], batch size: 19, lr: 7.97e-04
2022-05-04 02:56:47,805 INFO [train.py:715] (5/8) Epoch 1, batch 33750, loss[loss=0.1607, simple_loss=0.232, pruned_loss=0.04467, over 4923.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2424, pruned_loss=0.05592, over 970839.03 frames.], batch size: 29, lr: 7.97e-04
2022-05-04 02:57:27,454 INFO [train.py:715] (5/8) Epoch 1, batch 33800, loss[loss=0.2003, simple_loss=0.2653, pruned_loss=0.06764, over 4780.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2426, pruned_loss=0.0563, over 971788.37 frames.], batch size: 17, lr: 7.97e-04
2022-05-04 02:58:06,282 INFO [train.py:715] (5/8) Epoch 1, batch 33850, loss[loss=0.1872, simple_loss=0.2431, pruned_loss=0.06568, over 4731.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2426, pruned_loss=0.05619, over 971003.49 frames.], batch size: 16, lr: 7.96e-04
2022-05-04 02:58:45,801 INFO [train.py:715] (5/8) Epoch 1, batch 33900, loss[loss=0.1387, simple_loss=0.2139, pruned_loss=0.03179, over 4970.00 frames.], tot_loss[loss=0.178, simple_loss=0.2432, pruned_loss=0.05642, over 971229.52 frames.], batch size: 25, lr: 7.96e-04
2022-05-04 02:59:25,367 INFO [train.py:715] (5/8) Epoch 1, batch 33950, loss[loss=0.1497, simple_loss=0.226, pruned_loss=0.03674, over 4982.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2444, pruned_loss=0.0571, over 972470.99 frames.], batch size: 15, lr: 7.96e-04
2022-05-04 03:00:05,091 INFO [train.py:715] (5/8) Epoch 1, batch 34000, loss[loss=0.1603, simple_loss=0.2262, pruned_loss=0.04718, over 4930.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2439, pruned_loss=0.05659, over 972402.14 frames.], batch size: 23, lr: 7.95e-04
2022-05-04 03:00:44,411 INFO [train.py:715] (5/8) Epoch 1, batch 34050, loss[loss=0.2045, simple_loss=0.2641, pruned_loss=0.07243, over 4847.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2458, pruned_loss=0.05772, over 972299.73 frames.], batch size: 30, lr: 7.95e-04
2022-05-04 03:01:23,795 INFO [train.py:715] (5/8) Epoch 1, batch 34100, loss[loss=0.1639, simple_loss=0.2334, pruned_loss=0.04722, over 4688.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2457, pruned_loss=0.05774, over 972148.04 frames.], batch size: 15, lr: 7.95e-04
2022-05-04 03:02:03,179 INFO [train.py:715] (5/8) Epoch 1, batch 34150, loss[loss=0.1684, simple_loss=0.2286, pruned_loss=0.05413, over 4812.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2441, pruned_loss=0.05707, over 971663.87 frames.], batch size: 13, lr: 7.95e-04
2022-05-04 03:02:42,209 INFO [train.py:715] (5/8) Epoch 1, batch 34200, loss[loss=0.1548, simple_loss=0.2323, pruned_loss=0.03867, over 4974.00 frames.], tot_loss[loss=0.1775, simple_loss=0.243, pruned_loss=0.056, over 972176.94 frames.], batch size: 25, lr: 7.94e-04
2022-05-04 03:03:21,757 INFO [train.py:715] (5/8) Epoch 1, batch 34250, loss[loss=0.261, simple_loss=0.3099, pruned_loss=0.1061, over 4692.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2427, pruned_loss=0.05621, over 973021.16 frames.], batch size: 15, lr: 7.94e-04
2022-05-04 03:04:01,437 INFO [train.py:715] (5/8) Epoch 1, batch 34300, loss[loss=0.1896, simple_loss=0.2459, pruned_loss=0.06671, over 4920.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2429, pruned_loss=0.05643, over 972484.68 frames.], batch size: 29, lr: 7.94e-04
2022-05-04 03:04:40,846 INFO [train.py:715] (5/8) Epoch 1, batch 34350, loss[loss=0.1782, simple_loss=0.2466, pruned_loss=0.05491, over 4755.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2426, pruned_loss=0.05606, over 972402.49 frames.], batch size: 12, lr: 7.93e-04
2022-05-04 03:05:19,751 INFO [train.py:715] (5/8) Epoch 1, batch 34400, loss[loss=0.1404, simple_loss=0.2147, pruned_loss=0.03304, over 4849.00 frames.], tot_loss[loss=0.178, simple_loss=0.243, pruned_loss=0.05647, over 972703.15 frames.], batch size: 13, lr: 7.93e-04
2022-05-04 03:05:59,257 INFO [train.py:715] (5/8) Epoch 1, batch 34450, loss[loss=0.2137, simple_loss=0.2676, pruned_loss=0.07992, over 4750.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2438, pruned_loss=0.05701, over 971843.24 frames.], batch size: 16, lr: 7.93e-04
2022-05-04 03:06:38,477 INFO [train.py:715] (5/8) Epoch 1, batch 34500, loss[loss=0.1681, simple_loss=0.2403, pruned_loss=0.04795, over 4818.00 frames.], tot_loss[loss=0.1793, simple_loss=0.244, pruned_loss=0.05735, over 971575.89 frames.], batch size: 26, lr: 7.93e-04
2022-05-04 03:07:17,764 INFO [train.py:715] (5/8) Epoch 1, batch 34550, loss[loss=0.1854, simple_loss=0.252, pruned_loss=0.05937, over 4909.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2445, pruned_loss=0.05766, over 971982.61 frames.], batch size: 19, lr: 7.92e-04
2022-05-04 03:07:57,339 INFO [train.py:715] (5/8) Epoch 1, batch 34600, loss[loss=0.1788, simple_loss=0.254, pruned_loss=0.05178, over 4920.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2449, pruned_loss=0.05751, over 972631.28 frames.], batch size: 17, lr: 7.92e-04
2022-05-04 03:08:37,226 INFO [train.py:715] (5/8) Epoch 1, batch 34650, loss[loss=0.1991, simple_loss=0.2608, pruned_loss=0.06868, over 4937.00 frames.], tot_loss[loss=0.179, simple_loss=0.2443, pruned_loss=0.05682, over 972351.31 frames.], batch size: 23, lr: 7.92e-04
2022-05-04 03:09:17,429 INFO [train.py:715] (5/8) Epoch 1, batch 34700, loss[loss=0.1821, simple_loss=0.2601, pruned_loss=0.05208, over 4811.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2433, pruned_loss=0.05649, over 970799.06 frames.], batch size: 27, lr: 7.91e-04
2022-05-04 03:09:55,738 INFO [train.py:715] (5/8) Epoch 1, batch 34750, loss[loss=0.1587, simple_loss=0.2161, pruned_loss=0.05058, over 4794.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2438, pruned_loss=0.05688, over 970793.20 frames.], batch size: 18, lr: 7.91e-04
2022-05-04 03:10:32,244 INFO [train.py:715] (5/8) Epoch 1, batch 34800, loss[loss=0.1685, simple_loss=0.2362, pruned_loss=0.05038, over 4933.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2427, pruned_loss=0.05615, over 971197.79 frames.], batch size: 23, lr: 7.91e-04
2022-05-04 03:11:25,711 INFO [train.py:715] (5/8) Epoch 2, batch 0, loss[loss=0.1871, simple_loss=0.2506, pruned_loss=0.06187, over 4883.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2506, pruned_loss=0.06187, over 4883.00 frames.], batch size: 22, lr: 7.59e-04
2022-05-04 03:12:05,778 INFO [train.py:715] (5/8) Epoch 2, batch 50, loss[loss=0.215, simple_loss=0.2636, pruned_loss=0.08325, over 4961.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2404, pruned_loss=0.05549, over 219401.41 frames.], batch size: 39, lr: 7.59e-04
2022-05-04 03:12:46,584 INFO [train.py:715] (5/8) Epoch 2, batch 100, loss[loss=0.2022, simple_loss=0.2598, pruned_loss=0.07228, over 4799.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2418, pruned_loss=0.05723, over 386356.21 frames.], batch size: 21, lr: 7.59e-04
2022-05-04 03:13:27,201 INFO [train.py:715] (5/8) Epoch 2, batch 150, loss[loss=0.2184, simple_loss=0.2891, pruned_loss=0.07387, over 4759.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2406, pruned_loss=0.05645, over 515700.34 frames.], batch size: 19, lr: 7.59e-04
2022-05-04 03:14:07,251 INFO [train.py:715] (5/8) Epoch 2, batch 200, loss[loss=0.1951, simple_loss=0.2572, pruned_loss=0.06651, over 4789.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2423, pruned_loss=0.057, over 617121.03 frames.], batch size: 14, lr: 7.58e-04
2022-05-04 03:14:48,007 INFO [train.py:715] (5/8) Epoch 2, batch 250, loss[loss=0.1434, simple_loss=0.2295, pruned_loss=0.02865, over 4880.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2413, pruned_loss=0.05553, over 694862.33 frames.], batch size: 16, lr: 7.58e-04
2022-05-04 03:15:29,357 INFO [train.py:715] (5/8) Epoch 2, batch 300, loss[loss=0.1215, simple_loss=0.1967, pruned_loss=0.02315, over 4947.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2407, pruned_loss=0.05508, over 757156.87 frames.], batch size: 29, lr: 7.58e-04
2022-05-04 03:16:10,306 INFO [train.py:715] (5/8) Epoch 2, batch 350, loss[loss=0.2181, simple_loss=0.2692, pruned_loss=0.0835, over 4971.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2429, pruned_loss=0.05664, over 805449.22 frames.], batch size: 24, lr: 7.57e-04
2022-05-04 03:16:49,968 INFO [train.py:715] (5/8) Epoch 2, batch 400, loss[loss=0.1761, simple_loss=0.2374, pruned_loss=0.05735, over 4769.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2427, pruned_loss=0.05595, over 843176.76 frames.], batch size: 14, lr: 7.57e-04
2022-05-04 03:17:30,475 INFO [train.py:715] (5/8) Epoch 2, batch 450, loss[loss=0.222, simple_loss=0.2839, pruned_loss=0.08001, over 4780.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2444, pruned_loss=0.05723, over 871910.53 frames.], batch size: 14, lr: 7.57e-04
2022-05-04 03:18:11,617 INFO [train.py:715] (5/8) Epoch 2, batch 500, loss[loss=0.1588, simple_loss=0.2275, pruned_loss=0.04506, over 4846.00 frames.], tot_loss[loss=0.178, simple_loss=0.243, pruned_loss=0.05648, over 894210.28 frames.], batch size: 20, lr: 7.57e-04
2022-05-04 03:18:51,554 INFO [train.py:715] (5/8) Epoch 2, batch 550, loss[loss=0.1765, simple_loss=0.2365, pruned_loss=0.05828, over 4763.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2416, pruned_loss=0.0558, over 910740.76 frames.], batch size: 18, lr: 7.56e-04
2022-05-04 03:19:31,922 INFO [train.py:715] (5/8) Epoch 2, batch 600, loss[loss=0.1723, simple_loss=0.2439, pruned_loss=0.05037, over 4892.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2434, pruned_loss=0.05698, over 924588.15 frames.], batch size: 19, lr: 7.56e-04
2022-05-04 03:20:12,756 INFO [train.py:715] (5/8) Epoch 2, batch 650, loss[loss=0.1703, simple_loss=0.245, pruned_loss=0.0478, over 4859.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2425, pruned_loss=0.05652, over 934997.26 frames.], batch size: 20, lr: 7.56e-04
2022-05-04 03:20:53,354 INFO [train.py:715] (5/8) Epoch 2, batch 700, loss[loss=0.1591, simple_loss=0.2255, pruned_loss=0.04639, over 4943.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2418, pruned_loss=0.05565, over 943496.08 frames.], batch size: 35, lr: 7.56e-04
2022-05-04 03:21:32,906 INFO [train.py:715] (5/8) Epoch 2, batch 750, loss[loss=0.1678, simple_loss=0.2316, pruned_loss=0.05201, over 4773.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2407, pruned_loss=0.05503, over 948803.51 frames.], batch size: 14, lr: 7.55e-04
2022-05-04 03:22:13,350 INFO [train.py:715] (5/8) Epoch 2, batch 800, loss[loss=0.1748, simple_loss=0.237, pruned_loss=0.05629, over 4964.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2398, pruned_loss=0.05467, over 954125.44 frames.], batch size: 15, lr: 7.55e-04
2022-05-04 03:22:54,008 INFO [train.py:715] (5/8) Epoch 2, batch 850, loss[loss=0.1982, simple_loss=0.2688, pruned_loss=0.06379, over 4787.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2413, pruned_loss=0.05554, over 958746.00 frames.], batch size: 18, lr: 7.55e-04
2022-05-04 03:23:34,291 INFO [train.py:715] (5/8) Epoch 2, batch 900, loss[loss=0.1783, simple_loss=0.2511, pruned_loss=0.05277, over 4988.00 frames.], tot_loss[loss=0.1771, simple_loss=0.242, pruned_loss=0.05609, over 961760.15 frames.], batch size: 15, lr: 7.55e-04
2022-05-04 03:24:14,723 INFO [train.py:715] (5/8) Epoch 2, batch 950, loss[loss=0.1854, simple_loss=0.261, pruned_loss=0.05493, over 4776.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2414, pruned_loss=0.05589, over 964590.61 frames.], batch size: 17, lr: 7.54e-04
2022-05-04 03:24:55,405 INFO [train.py:715] (5/8) Epoch 2, batch 1000, loss[loss=0.172, simple_loss=0.2266, pruned_loss=0.05872, over 4977.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2417, pruned_loss=0.05631, over 966803.04 frames.], batch size: 14, lr: 7.54e-04
2022-05-04 03:25:36,199 INFO [train.py:715] (5/8) Epoch 2, batch 1050, loss[loss=0.1582, simple_loss=0.2329, pruned_loss=0.04173, over 4856.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2417, pruned_loss=0.05626, over 968938.49 frames.], batch size: 20, lr: 7.54e-04
2022-05-04 03:26:15,807 INFO [train.py:715] (5/8) Epoch 2, batch 1100, loss[loss=0.1855, simple_loss=0.2534, pruned_loss=0.0588, over 4971.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2425, pruned_loss=0.05621, over 969480.94 frames.], batch size: 24, lr: 7.53e-04
2022-05-04 03:26:56,307 INFO [train.py:715] (5/8) Epoch 2, batch 1150, loss[loss=0.1684, simple_loss=0.2268, pruned_loss=0.05497, over 4964.00 frames.], tot_loss[loss=0.1795, simple_loss=0.244, pruned_loss=0.05752, over 970312.32 frames.], batch size: 35, lr: 7.53e-04
2022-05-04 03:27:37,642 INFO [train.py:715] (5/8) Epoch 2, batch 1200, loss[loss=0.1443, simple_loss=0.2171, pruned_loss=0.03572, over 4946.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2429, pruned_loss=0.05696, over 971199.50 frames.], batch size: 14, lr: 7.53e-04
2022-05-04 03:28:18,254 INFO [train.py:715] (5/8) Epoch 2, batch 1250, loss[loss=0.181, simple_loss=0.2433, pruned_loss=0.0593, over 4829.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2434, pruned_loss=0.05674, over 971199.34 frames.], batch size: 26, lr: 7.53e-04
2022-05-04 03:28:57,938 INFO [train.py:715] (5/8) Epoch 2, batch 1300, loss[loss=0.168, simple_loss=0.2456, pruned_loss=0.04525, over 4811.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2428, pruned_loss=0.05616, over 971800.57 frames.], batch size: 26, lr: 7.52e-04
2022-05-04 03:29:38,477 INFO [train.py:715] (5/8) Epoch 2, batch 1350, loss[loss=0.1328, simple_loss=0.2172, pruned_loss=0.02419, over 4854.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2418, pruned_loss=0.05583, over 971366.46 frames.], batch size: 20, lr: 7.52e-04
2022-05-04 03:30:19,111 INFO [train.py:715] (5/8) Epoch 2, batch 1400, loss[loss=0.1697, simple_loss=0.2486, pruned_loss=0.04535, over 4884.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2416, pruned_loss=0.05549, over 970714.39 frames.], batch size: 22, lr: 7.52e-04
2022-05-04 03:30:59,080 INFO [train.py:715] (5/8) Epoch 2, batch 1450, loss[loss=0.1634, simple_loss=0.2305, pruned_loss=0.04822, over 4919.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2409, pruned_loss=0.05517, over 971395.67 frames.], batch size: 23, lr: 7.52e-04
2022-05-04 03:31:39,484 INFO [train.py:715] (5/8) Epoch 2, batch 1500, loss[loss=0.1881, simple_loss=0.2508, pruned_loss=0.06276, over 4780.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2401, pruned_loss=0.05477, over 972710.90 frames.], batch size: 17, lr: 7.51e-04
2022-05-04 03:32:20,466 INFO [train.py:715] (5/8) Epoch 2, batch 1550, loss[loss=0.1707, simple_loss=0.2373, pruned_loss=0.05204, over 4753.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2412, pruned_loss=0.05513, over 973551.12 frames.], batch size: 19, lr: 7.51e-04
2022-05-04 03:33:00,545 INFO [train.py:715] (5/8) Epoch 2, batch 1600, loss[loss=0.2021, simple_loss=0.269, pruned_loss=0.0676, over 4860.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2411, pruned_loss=0.05495, over 972939.70 frames.], batch size: 32, lr: 7.51e-04
2022-05-04 03:33:40,361 INFO [train.py:715] (5/8) Epoch 2, batch 1650, loss[loss=0.1843, simple_loss=0.2581, pruned_loss=0.05522, over 4783.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2403, pruned_loss=0.05407, over 973394.45 frames.], batch size: 18, lr: 7.51e-04
2022-05-04 03:34:21,231 INFO [train.py:715] (5/8) Epoch 2, batch 1700, loss[loss=0.225, simple_loss=0.2821, pruned_loss=0.08393, over 4689.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2408, pruned_loss=0.05429, over 973465.52 frames.], batch size: 15, lr: 7.50e-04
2022-05-04 03:35:02,279 INFO [train.py:715] (5/8) Epoch 2, batch 1750, loss[loss=0.1616, simple_loss=0.2274, pruned_loss=0.04791, over 4989.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2403, pruned_loss=0.05393, over 972971.60 frames.], batch size: 14, lr: 7.50e-04
2022-05-04 03:35:42,183 INFO [train.py:715] (5/8) Epoch 2, batch 1800, loss[loss=0.1727, simple_loss=0.2358, pruned_loss=0.05478, over 4823.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2404, pruned_loss=0.05442, over 972408.97 frames.], batch size: 25, lr: 7.50e-04
2022-05-04 03:36:22,546 INFO [train.py:715] (5/8) Epoch 2, batch 1850, loss[loss=0.1917, simple_loss=0.2429, pruned_loss=0.07021, over 4812.00 frames.], tot_loss[loss=0.1761, simple_loss=0.241, pruned_loss=0.0556, over 971164.36 frames.], batch size: 12, lr: 7.50e-04
2022-05-04 03:37:03,511 INFO [train.py:715] (5/8) Epoch 2, batch 1900, loss[loss=0.1926, simple_loss=0.2587, pruned_loss=0.0633, over 4880.00 frames.], tot_loss[loss=0.176, simple_loss=0.2411, pruned_loss=0.05548, over 971832.20 frames.], batch size: 22, lr: 7.49e-04
2022-05-04 03:37:44,309 INFO [train.py:715] (5/8) Epoch 2, batch 1950, loss[loss=0.1558, simple_loss=0.2223, pruned_loss=0.04466, over 4904.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2412, pruned_loss=0.05576, over 972894.56 frames.], batch size: 18, lr: 7.49e-04
2022-05-04 03:38:24,092 INFO [train.py:715] (5/8) Epoch 2, batch 2000, loss[loss=0.229, simple_loss=0.27, pruned_loss=0.09403, over 4854.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2404, pruned_loss=0.05492, over 972430.53 frames.], batch size: 38, lr: 7.49e-04
2022-05-04 03:39:04,263 INFO [train.py:715] (5/8) Epoch 2, batch 2050, loss[loss=0.1518, simple_loss=0.2198, pruned_loss=0.04195, over 4975.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2399, pruned_loss=0.05422, over 972799.68 frames.], batch size: 24, lr: 7.48e-04
2022-05-04 03:39:45,391 INFO [train.py:715] (5/8) Epoch 2, batch 2100, loss[loss=0.1694, simple_loss=0.2282, pruned_loss=0.05535, over 4954.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2402, pruned_loss=0.05455, over 972829.94 frames.], batch size: 35, lr: 7.48e-04
2022-05-04 03:40:25,368 INFO [train.py:715] (5/8) Epoch 2, batch 2150, loss[loss=0.1676, simple_loss=0.2323, pruned_loss=0.05146, over 4957.00 frames.], tot_loss[loss=0.1742, simple_loss=0.24, pruned_loss=0.05416, over 972260.50 frames.], batch size: 35, lr: 7.48e-04
2022-05-04 03:41:04,898 INFO [train.py:715] (5/8) Epoch 2, batch 2200, loss[loss=0.2112, simple_loss=0.2583, pruned_loss=0.08209, over 4844.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2399, pruned_loss=0.05452, over 972538.43 frames.], batch size: 20, lr: 7.48e-04
2022-05-04 03:41:45,616 INFO [train.py:715] (5/8) Epoch 2, batch 2250, loss[loss=0.1952, simple_loss=0.2471, pruned_loss=0.07166, over 4985.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2405, pruned_loss=0.0551, over 972836.08 frames.], batch size: 35, lr: 7.47e-04
2022-05-04 03:42:26,413 INFO [train.py:715] (5/8) Epoch 2, batch 2300, loss[loss=0.1654, simple_loss=0.2346, pruned_loss=0.04807, over 4928.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2412, pruned_loss=0.05533, over 972948.67 frames.], batch size: 21, lr: 7.47e-04
2022-05-04 03:43:05,626 INFO [train.py:715] (5/8) Epoch 2, batch 2350, loss[loss=0.1929, simple_loss=0.2533, pruned_loss=0.06627, over 4708.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2406, pruned_loss=0.05549, over 972637.78 frames.], batch size: 15, lr: 7.47e-04
2022-05-04 03:43:48,333 INFO [train.py:715] (5/8) Epoch 2, batch 2400, loss[loss=0.1628, simple_loss=0.2287, pruned_loss=0.04843, over 4822.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2401, pruned_loss=0.05512, over 972081.04 frames.], batch size: 26, lr: 7.47e-04
2022-05-04 03:44:29,321 INFO [train.py:715] (5/8) Epoch 2, batch 2450, loss[loss=0.1846, simple_loss=0.2566, pruned_loss=0.05628, over 4853.00 frames.], tot_loss[loss=0.175, simple_loss=0.2402, pruned_loss=0.05488, over 972342.39 frames.], batch size: 20, lr: 7.46e-04
2022-05-04 03:45:09,460 INFO [train.py:715] (5/8) Epoch 2, batch 2500, loss[loss=0.1943, simple_loss=0.2584, pruned_loss=0.06506, over 4904.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2404, pruned_loss=0.05502, over 972417.83 frames.], batch size: 17, lr: 7.46e-04
2022-05-04 03:45:49,052 INFO [train.py:715] (5/8) Epoch 2, batch 2550, loss[loss=0.1889, simple_loss=0.2596, pruned_loss=0.05912, over 4858.00 frames.], tot_loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.0546, over 972718.21 frames.], batch size: 20, lr: 7.46e-04
2022-05-04 03:46:29,879 INFO [train.py:715] (5/8) Epoch 2, batch 2600, loss[loss=0.1446, simple_loss=0.2109, pruned_loss=0.0391, over 4935.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2411, pruned_loss=0.05483, over 972479.36 frames.], batch size: 23, lr: 7.46e-04
2022-05-04 03:47:10,396 INFO [train.py:715] (5/8) Epoch 2, batch 2650, loss[loss=0.1554, simple_loss=0.2205, pruned_loss=0.04518, over 4925.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2414, pruned_loss=0.05524, over 973040.41 frames.], batch size: 29, lr: 7.45e-04
2022-05-04 03:47:49,289 INFO [train.py:715] (5/8) Epoch 2, batch 2700, loss[loss=0.1669, simple_loss=0.2343, pruned_loss=0.04973, over 4980.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2418, pruned_loss=0.05524, over 972749.54 frames.], batch size: 15, lr: 7.45e-04
2022-05-04 03:48:29,312 INFO [train.py:715] (5/8) Epoch 2, batch 2750, loss[loss=0.1507, simple_loss=0.2147, pruned_loss=0.0433, over 4841.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2422, pruned_loss=0.05593, over 972119.84 frames.], batch size: 13, lr: 7.45e-04
2022-05-04 03:49:10,354 INFO [train.py:715] (5/8) Epoch 2, batch 2800, loss[loss=0.188, simple_loss=0.26, pruned_loss=0.05802, over 4780.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2413, pruned_loss=0.05478, over 972189.30 frames.], batch size: 17, lr: 7.45e-04
2022-05-04 03:49:50,285 INFO [train.py:715] (5/8) Epoch 2, batch 2850, loss[loss=0.192, simple_loss=0.2479, pruned_loss=0.06808, over 4846.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2407, pruned_loss=0.05418, over 971997.98 frames.], batch size: 30, lr: 7.44e-04
2022-05-04 03:50:29,541 INFO [train.py:715] (5/8) Epoch 2, batch 2900, loss[loss=0.1722, simple_loss=0.2257, pruned_loss=0.05942, over 4868.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2417, pruned_loss=0.05506, over 971998.61 frames.], batch size: 32, lr: 7.44e-04
2022-05-04 03:51:09,906 INFO [train.py:715] (5/8) Epoch 2, batch 2950, loss[loss=0.1678, simple_loss=0.2268, pruned_loss=0.0544, over 4718.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2414, pruned_loss=0.05489, over 972483.28 frames.], batch size: 15, lr: 7.44e-04
2022-05-04 03:51:50,592 INFO [train.py:715] (5/8) Epoch 2, batch 3000, loss[loss=0.246, simple_loss=0.2855, pruned_loss=0.1033, over 4877.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2422, pruned_loss=0.05551, over 972562.54 frames.], batch size: 16, lr: 7.44e-04
2022-05-04 03:51:50,593 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 03:52:00,001 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1191, simple_loss=0.2058, pruned_loss=0.01615, over 914524.00 frames.
2022-05-04 03:52:40,631 INFO [train.py:715] (5/8) Epoch 2, batch 3050, loss[loss=0.1861, simple_loss=0.2575, pruned_loss=0.05735, over 4776.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2425, pruned_loss=0.05586, over 972641.87 frames.], batch size: 17, lr: 7.43e-04
2022-05-04 03:53:19,881 INFO [train.py:715] (5/8) Epoch 2, batch 3100, loss[loss=0.1774, simple_loss=0.2547, pruned_loss=0.05008, over 4829.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2424, pruned_loss=0.05553, over 972553.05 frames.], batch size: 26, lr: 7.43e-04
2022-05-04 03:53:59,889 INFO [train.py:715] (5/8) Epoch 2, batch 3150, loss[loss=0.1728, simple_loss=0.2386, pruned_loss=0.05356, over 4974.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2416, pruned_loss=0.05528, over 972364.15 frames.], batch size: 24, lr: 7.43e-04
2022-05-04 03:54:40,192 INFO [train.py:715] (5/8) Epoch 2, batch 3200, loss[loss=0.1471, simple_loss=0.2099, pruned_loss=0.04218, over 4748.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2416, pruned_loss=0.05568, over 972699.71 frames.], batch size: 12, lr: 7.43e-04
2022-05-04 03:55:19,795 INFO [train.py:715] (5/8) Epoch 2, batch 3250, loss[loss=0.1673, simple_loss=0.2408, pruned_loss=0.04686, over 4886.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2414, pruned_loss=0.05514, over 972392.19 frames.], batch size: 22, lr: 7.42e-04
2022-05-04 03:55:59,355 INFO [train.py:715] (5/8) Epoch 2, batch 3300, loss[loss=0.1449, simple_loss=0.2118, pruned_loss=0.03902, over 4976.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2411, pruned_loss=0.05488, over 971580.85 frames.], batch size: 14, lr: 7.42e-04
2022-05-04 03:56:39,599 INFO [train.py:715] (5/8) Epoch 2, batch 3350, loss[loss=0.1645, simple_loss=0.2291, pruned_loss=0.04994, over 4854.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2403, pruned_loss=0.05445, over 971154.26 frames.], batch size: 13, lr: 7.42e-04
2022-05-04 03:57:20,091 INFO [train.py:715] (5/8) Epoch 2, batch 3400, loss[loss=0.2003, simple_loss=0.2701, pruned_loss=0.06528, over 4968.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05472, over 971755.25 frames.], batch size: 24, lr: 7.42e-04
2022-05-04 03:57:58,920 INFO [train.py:715] (5/8) Epoch 2, batch 3450, loss[loss=0.1527, simple_loss=0.2235, pruned_loss=0.04097, over 4880.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2412, pruned_loss=0.05477, over 971842.74 frames.], batch size: 20, lr: 7.41e-04
2022-05-04 03:58:38,941 INFO [train.py:715] (5/8) Epoch 2, batch 3500, loss[loss=0.1332, simple_loss=0.2084, pruned_loss=0.02897, over 4802.00 frames.], tot_loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.0546, over 972030.20 frames.], batch size: 12, lr: 7.41e-04
2022-05-04 03:59:19,006 INFO [train.py:715] (5/8) Epoch 2, batch 3550, loss[loss=0.1578, simple_loss=0.226, pruned_loss=0.04482, over 4838.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2414, pruned_loss=0.05462, over 973285.93 frames.], batch size: 30, lr: 7.41e-04
2022-05-04 03:59:58,780 INFO [train.py:715] (5/8) Epoch 2, batch 3600, loss[loss=0.1931, simple_loss=0.2519, pruned_loss=0.06722, over 4859.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2416, pruned_loss=0.05493, over 973172.09 frames.], batch size: 20, lr: 7.41e-04
2022-05-04 04:00:37,770 INFO [train.py:715] (5/8) Epoch 2, batch 3650, loss[loss=0.1788, simple_loss=0.2351, pruned_loss=0.06122, over 4826.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2416, pruned_loss=0.05474, over 972699.44 frames.], batch size: 15, lr: 7.40e-04
2022-05-04 04:01:18,182 INFO [train.py:715] (5/8) Epoch 2, batch 3700, loss[loss=0.1929, simple_loss=0.2534, pruned_loss=0.06624, over 4756.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2414, pruned_loss=0.05484, over 972480.36 frames.], batch size: 16, lr: 7.40e-04
2022-05-04 04:01:58,355 INFO [train.py:715] (5/8) Epoch 2, batch 3750, loss[loss=0.1548, simple_loss=0.2235, pruned_loss=0.04305, over 4754.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2405, pruned_loss=0.05467, over 972482.18 frames.], batch size: 16, lr: 7.40e-04
2022-05-04 04:02:37,082 INFO [train.py:715] (5/8) Epoch 2, batch 3800, loss[loss=0.172, simple_loss=0.2294, pruned_loss=0.05724, over 4689.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2402, pruned_loss=0.05466, over 971791.12 frames.], batch size: 15, lr: 7.40e-04
2022-05-04 04:03:17,279 INFO [train.py:715] (5/8) Epoch 2, batch 3850, loss[loss=0.1741, simple_loss=0.2484, pruned_loss=0.0499, over 4927.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2406, pruned_loss=0.05453, over 971780.07 frames.], batch size: 29, lr: 7.39e-04
2022-05-04 04:03:57,612 INFO [train.py:715] (5/8) Epoch 2, batch 3900, loss[loss=0.2143, simple_loss=0.269, pruned_loss=0.07983, over 4864.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2403, pruned_loss=0.05465, over 972023.10 frames.], batch size: 20, lr: 7.39e-04
2022-05-04 04:04:36,856 INFO [train.py:715] (5/8) Epoch 2, batch 3950, loss[loss=0.1448, simple_loss=0.2156, pruned_loss=0.03705, over 4919.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2403, pruned_loss=0.05445, over 972123.59 frames.], batch size: 18, lr: 7.39e-04
2022-05-04 04:05:16,468 INFO [train.py:715] (5/8) Epoch 2, batch 4000, loss[loss=0.1626, simple_loss=0.2319, pruned_loss=0.04662, over 4916.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2401, pruned_loss=0.05401, over 971735.20 frames.], batch size: 22, lr: 7.39e-04
2022-05-04 04:05:57,029 INFO [train.py:715] (5/8) Epoch 2, batch 4050, loss[loss=0.1471, simple_loss=0.2166, pruned_loss=0.03877, over 4946.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2402, pruned_loss=0.05412, over 971600.84 frames.], batch size: 21, lr: 7.38e-04
2022-05-04 04:06:37,524 INFO [train.py:715] (5/8) Epoch 2, batch 4100, loss[loss=0.1539, simple_loss=0.2336, pruned_loss=0.03708, over 4890.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2413, pruned_loss=0.0545, over 971748.44 frames.], batch size: 22, lr: 7.38e-04
2022-05-04 04:07:16,033 INFO [train.py:715] (5/8) Epoch 2, batch 4150, loss[loss=0.1707, simple_loss=0.2469, pruned_loss=0.04724, over 4985.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2422, pruned_loss=0.05497, over 972135.51 frames.], batch size: 25, lr: 7.38e-04
2022-05-04 04:07:55,386 INFO [train.py:715] (5/8) Epoch 2, batch 4200, loss[loss=0.1342, simple_loss=0.2006, pruned_loss=0.03395, over 4860.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2411, pruned_loss=0.05472, over 972155.72 frames.], batch size: 12, lr: 7.38e-04
2022-05-04 04:08:35,832 INFO [train.py:715] (5/8) Epoch 2, batch 4250, loss[loss=0.1737, simple_loss=0.2441, pruned_loss=0.05163, over 4893.00 frames.], tot_loss[loss=0.176, simple_loss=0.2417, pruned_loss=0.05509, over 972097.79 frames.], batch size: 22, lr: 7.37e-04
2022-05-04 04:09:15,086 INFO [train.py:715] (5/8) Epoch 2, batch 4300, loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03912, over 4754.00 frames.], tot_loss[loss=0.177, simple_loss=0.2426, pruned_loss=0.05566, over 971558.60 frames.], batch size: 19, lr: 7.37e-04
2022-05-04 04:09:54,870 INFO [train.py:715] (5/8) Epoch 2, batch 4350, loss[loss=0.2036, simple_loss=0.2651, pruned_loss=0.07109, over 4902.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2411, pruned_loss=0.05452, over 972024.57 frames.], batch size: 19, lr: 7.37e-04
2022-05-04 04:10:34,725 INFO [train.py:715] (5/8) Epoch 2, batch 4400, loss[loss=0.1636, simple_loss=0.2378, pruned_loss=0.04472, over 4909.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2402, pruned_loss=0.05365, over 971980.85 frames.], batch size: 29, lr: 7.37e-04
2022-05-04 04:11:14,732 INFO [train.py:715] (5/8) Epoch 2, batch 4450, loss[loss=0.1759, simple_loss=0.2417, pruned_loss=0.05506, over 4781.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2401, pruned_loss=0.05372, over 972194.91 frames.], batch size: 17, lr: 7.36e-04
2022-05-04 04:11:53,881 INFO [train.py:715] (5/8) Epoch 2, batch 4500, loss[loss=0.1746, simple_loss=0.2421, pruned_loss=0.05357, over 4891.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2395, pruned_loss=0.05348, over 972407.90 frames.], batch size: 19, lr: 7.36e-04
2022-05-04 04:12:33,897 INFO [train.py:715] (5/8) Epoch 2, batch 4550, loss[loss=0.1675, simple_loss=0.2285, pruned_loss=0.05324, over 4810.00 frames.], tot_loss[loss=0.175, simple_loss=0.2405, pruned_loss=0.05474, over 972185.94 frames.], batch size: 13, lr: 7.36e-04
2022-05-04 04:13:14,648 INFO [train.py:715] (5/8) Epoch 2, batch 4600, loss[loss=0.1657, simple_loss=0.2235, pruned_loss=0.05392, over 4971.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2398, pruned_loss=0.05445, over 972119.61 frames.], batch size: 14, lr: 7.36e-04
2022-05-04 04:13:53,701 INFO [train.py:715] (5/8) Epoch 2, batch 4650, loss[loss=0.1695, simple_loss=0.2369, pruned_loss=0.05098, over 4843.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2407, pruned_loss=0.05499, over 971600.61 frames.], batch size: 15, lr: 7.35e-04
2022-05-04 04:14:33,012 INFO [train.py:715] (5/8) Epoch 2, batch 4700, loss[loss=0.1879, simple_loss=0.2703, pruned_loss=0.0528, over 4776.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2409, pruned_loss=0.05465, over 971918.79 frames.], batch size: 14, lr: 7.35e-04
2022-05-04 04:15:13,199 INFO [train.py:715] (5/8) Epoch 2, batch 4750, loss[loss=0.1748, simple_loss=0.2459, pruned_loss=0.0519, over 4827.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2412, pruned_loss=0.055, over 972703.86 frames.], batch size: 26, lr: 7.35e-04
2022-05-04 04:15:53,748 INFO [train.py:715] (5/8) Epoch 2, batch 4800, loss[loss=0.1423, simple_loss=0.2194, pruned_loss=0.03262, over 4813.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2422, pruned_loss=0.05533, over 972329.40 frames.], batch size: 21, lr: 7.35e-04
2022-05-04 04:16:33,019 INFO [train.py:715] (5/8) Epoch 2, batch 4850, loss[loss=0.1841, simple_loss=0.2454, pruned_loss=0.06145, over 4821.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2427, pruned_loss=0.05522, over 972507.26 frames.], batch size: 15, lr: 7.34e-04
2022-05-04 04:17:12,486 INFO [train.py:715] (5/8) Epoch 2, batch 4900, loss[loss=0.1845, simple_loss=0.2601, pruned_loss=0.05443, over 4767.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2409, pruned_loss=0.0544, over 972496.70 frames.], batch size: 14, lr: 7.34e-04
2022-05-04 04:17:52,932 INFO [train.py:715] (5/8) Epoch 2, batch 4950, loss[loss=0.1495, simple_loss=0.2238, pruned_loss=0.03762, over 4949.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2405, pruned_loss=0.05398, over 972087.01 frames.], batch size: 29, lr: 7.34e-04
2022-05-04 04:18:32,546 INFO [train.py:715] (5/8) Epoch 2, batch 5000, loss[loss=0.1791, simple_loss=0.2377, pruned_loss=0.06022, over 4957.00 frames.], tot_loss[loss=0.175, simple_loss=0.2408, pruned_loss=0.05461, over 972290.71 frames.], batch size: 35, lr: 7.34e-04
2022-05-04 04:19:12,100 INFO [train.py:715] (5/8) Epoch 2, batch 5050, loss[loss=0.194, simple_loss=0.2556, pruned_loss=0.06624, over 4911.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2418, pruned_loss=0.05518, over 973099.37 frames.], batch size: 17, lr: 7.33e-04
2022-05-04 04:19:53,173 INFO [train.py:715] (5/8) Epoch 2, batch 5100, loss[loss=0.1658, simple_loss=0.2404, pruned_loss=0.04555, over 4928.00 frames.], tot_loss[loss=0.176, simple_loss=0.2416, pruned_loss=0.05514, over 973255.18 frames.], batch size: 23, lr: 7.33e-04
2022-05-04 04:20:34,125 INFO [train.py:715] (5/8) Epoch 2, batch 5150, loss[loss=0.2074, simple_loss=0.259, pruned_loss=0.07791, over 4851.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2409, pruned_loss=0.05452, over 972740.41 frames.], batch size: 30, lr: 7.33e-04
2022-05-04 04:21:13,074 INFO [train.py:715] (5/8) Epoch 2, batch 5200, loss[loss=0.1611, simple_loss=0.2272, pruned_loss=0.04748, over 4832.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2409, pruned_loss=0.05464, over 972966.91 frames.], batch size: 15, lr: 7.33e-04
2022-05-04 04:21:52,857 INFO [train.py:715] (5/8) Epoch 2, batch 5250, loss[loss=0.1814, simple_loss=0.2424, pruned_loss=0.0602, over 4782.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2422, pruned_loss=0.05557, over 972746.35 frames.], batch size: 12, lr: 7.32e-04
2022-05-04 04:22:33,070 INFO [train.py:715] (5/8) Epoch 2, batch 5300, loss[loss=0.1896, simple_loss=0.2513, pruned_loss=0.06392, over 4963.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2422, pruned_loss=0.05547, over 972207.80 frames.], batch size: 21, lr: 7.32e-04
2022-05-04 04:23:12,249 INFO [train.py:715] (5/8) Epoch 2, batch 5350, loss[loss=0.1406, simple_loss=0.2053, pruned_loss=0.03793, over 4774.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2415, pruned_loss=0.05465, over 971847.63 frames.], batch size: 18, lr: 7.32e-04
2022-05-04 04:23:51,613 INFO [train.py:715] (5/8) Epoch 2, batch 5400, loss[loss=0.2317, simple_loss=0.2863, pruned_loss=0.08858, over 4962.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2404, pruned_loss=0.05441, over 971548.16 frames.], batch size: 39, lr: 7.32e-04
2022-05-04 04:24:32,289 INFO [train.py:715] (5/8) Epoch 2, batch 5450, loss[loss=0.1627, simple_loss=0.2435, pruned_loss=0.04095, over 4789.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2409, pruned_loss=0.05463, over 970140.76 frames.], batch size: 17, lr: 7.31e-04
2022-05-04 04:25:12,077 INFO [train.py:715] (5/8) Epoch 2, batch 5500, loss[loss=0.2105, simple_loss=0.2624, pruned_loss=0.07927, over 4828.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2406, pruned_loss=0.05446, over 971071.10 frames.], batch size: 26, lr: 7.31e-04
2022-05-04 04:25:51,713 INFO [train.py:715] (5/8) Epoch 2, batch 5550, loss[loss=0.1784, simple_loss=0.2503, pruned_loss=0.05327, over 4789.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2405, pruned_loss=0.05448, over 971715.49 frames.], batch size: 14, lr: 7.31e-04
2022-05-04 04:26:32,210 INFO [train.py:715] (5/8) Epoch 2, batch 5600, loss[loss=0.1928, simple_loss=0.2514, pruned_loss=0.06717, over 4845.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2395, pruned_loss=0.05398, over 971173.62 frames.], batch size: 32, lr: 7.31e-04
2022-05-04 04:27:13,267 INFO [train.py:715] (5/8) Epoch 2, batch 5650, loss[loss=0.1558, simple_loss=0.2159, pruned_loss=0.04782, over 4660.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2398, pruned_loss=0.05399, over 972074.98 frames.], batch size: 13, lr: 7.30e-04
2022-05-04 04:27:53,170 INFO [train.py:715] (5/8) Epoch 2, batch 5700, loss[loss=0.1332, simple_loss=0.203, pruned_loss=0.03171, over 4858.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2393, pruned_loss=0.05344, over 972449.16 frames.], batch size: 13, lr: 7.30e-04
2022-05-04 04:28:33,027 INFO [train.py:715] (5/8) Epoch 2, batch 5750, loss[loss=0.1789, simple_loss=0.2381, pruned_loss=0.05981, over 4840.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2406, pruned_loss=0.05438, over 973102.68 frames.], batch size: 32, lr: 7.30e-04
2022-05-04 04:29:13,951 INFO [train.py:715] (5/8) Epoch 2, batch 5800, loss[loss=0.1702, simple_loss=0.2451, pruned_loss=0.04767, over 4806.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2398, pruned_loss=0.05366, over 972009.94 frames.], batch size: 14, lr: 7.30e-04
2022-05-04 04:29:55,090 INFO [train.py:715] (5/8) Epoch 2, batch 5850, loss[loss=0.1703, simple_loss=0.2257, pruned_loss=0.05743, over 4955.00 frames.], tot_loss[loss=0.173, simple_loss=0.2394, pruned_loss=0.0533, over 972934.95 frames.], batch size: 35, lr: 7.29e-04
2022-05-04 04:30:34,560 INFO [train.py:715] (5/8) Epoch 2, batch 5900, loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03898, over 4936.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2405, pruned_loss=0.05394, over 972959.26 frames.], batch size: 23, lr: 7.29e-04
2022-05-04 04:31:15,152 INFO [train.py:715] (5/8) Epoch 2, batch 5950, loss[loss=0.1539, simple_loss=0.2173, pruned_loss=0.04524, over 4894.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2404, pruned_loss=0.05423, over 973175.61 frames.], batch size: 22, lr: 7.29e-04
2022-05-04 04:31:56,155 INFO [train.py:715] (5/8) Epoch 2, batch 6000, loss[loss=0.2151, simple_loss=0.27, pruned_loss=0.08008, over 4763.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2405, pruned_loss=0.05397, over 971730.20 frames.], batch size: 14, lr: 7.29e-04
2022-05-04 04:31:56,156 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 04:32:04,807 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1188, simple_loss=0.2054, pruned_loss=0.01614, over 914524.00 frames.
2022-05-04 04:32:46,137 INFO [train.py:715] (5/8) Epoch 2, batch 6050, loss[loss=0.1504, simple_loss=0.2241, pruned_loss=0.03833, over 4953.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2397, pruned_loss=0.05373, over 972003.44 frames.], batch size: 21, lr: 7.29e-04
2022-05-04 04:33:25,858 INFO [train.py:715] (5/8) Epoch 2, batch 6100, loss[loss=0.1347, simple_loss=0.1961, pruned_loss=0.03666, over 4774.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2404, pruned_loss=0.05418, over 971685.76 frames.], batch size: 12, lr: 7.28e-04
2022-05-04 04:34:05,821 INFO [train.py:715] (5/8) Epoch 2, batch 6150, loss[loss=0.1785, simple_loss=0.2388, pruned_loss=0.05911, over 4703.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2405, pruned_loss=0.05433, over 971654.47 frames.], batch size: 15, lr: 7.28e-04
2022-05-04 04:34:46,189 INFO [train.py:715] (5/8) Epoch 2, batch 6200, loss[loss=0.1395, simple_loss=0.2081, pruned_loss=0.03539, over 4754.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2399, pruned_loss=0.05415, over 971664.97 frames.], batch size: 16, lr: 7.28e-04
2022-05-04 04:35:26,608 INFO [train.py:715] (5/8) Epoch 2, batch 6250, loss[loss=0.1287, simple_loss=0.202, pruned_loss=0.02771, over 4696.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2394, pruned_loss=0.05406, over 971417.87 frames.], batch size: 15, lr: 7.28e-04
2022-05-04 04:36:05,786 INFO [train.py:715] (5/8) Epoch 2, batch 6300, loss[loss=0.1891, simple_loss=0.2427, pruned_loss=0.06775, over 4797.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2395, pruned_loss=0.054, over 971174.85 frames.], batch size: 17, lr: 7.27e-04
2022-05-04 04:36:46,022 INFO [train.py:715] (5/8) Epoch 2, batch 6350, loss[loss=0.2197, simple_loss=0.2756, pruned_loss=0.08192, over 4779.00 frames.], tot_loss[loss=0.174, simple_loss=0.2397, pruned_loss=0.05413, over 970883.25 frames.], batch size: 17, lr: 7.27e-04
2022-05-04 04:37:26,516 INFO [train.py:715] (5/8) Epoch 2, batch 6400, loss[loss=0.2076, simple_loss=0.262, pruned_loss=0.07667, over 4785.00 frames.], tot_loss[loss=0.175, simple_loss=0.2408, pruned_loss=0.05457, over 970527.17 frames.], batch size: 14, lr: 7.27e-04
2022-05-04 04:38:05,325 INFO [train.py:715] (5/8) Epoch 2, batch 6450, loss[loss=0.1945, simple_loss=0.2581, pruned_loss=0.06547, over 4978.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2413, pruned_loss=0.05486, over 971141.47 frames.], batch size: 35, lr: 7.27e-04
2022-05-04 04:38:44,600 INFO [train.py:715] (5/8) Epoch 2, batch 6500, loss[loss=0.2053, simple_loss=0.2726, pruned_loss=0.06895, over 4905.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2409, pruned_loss=0.05499, over 970913.59 frames.], batch size: 17, lr: 7.26e-04
2022-05-04 04:39:24,832 INFO [train.py:715] (5/8) Epoch 2, batch 6550, loss[loss=0.2788, simple_loss=0.3058, pruned_loss=0.126, over 4785.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2414, pruned_loss=0.05547, over 971575.07 frames.], batch size: 17, lr: 7.26e-04
2022-05-04 04:40:04,767 INFO [train.py:715] (5/8) Epoch 2, batch 6600, loss[loss=0.1895, simple_loss=0.2546, pruned_loss=0.06221, over 4779.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2414, pruned_loss=0.05513, over 971177.92 frames.], batch size: 17, lr: 7.26e-04
2022-05-04 04:40:43,857 INFO [train.py:715] (5/8) Epoch 2, batch 6650, loss[loss=0.1473, simple_loss=0.217, pruned_loss=0.03886, over 4813.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2405, pruned_loss=0.05421, over 971617.75 frames.], batch size: 25, lr: 7.26e-04
2022-05-04 04:41:23,368 INFO [train.py:715] (5/8) Epoch 2, batch 6700, loss[loss=0.1559, simple_loss=0.221, pruned_loss=0.0454, over 4831.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2405, pruned_loss=0.05412, over 971627.28 frames.], batch size: 15, lr: 7.25e-04
2022-05-04 04:42:03,551 INFO [train.py:715] (5/8) Epoch 2, batch 6750, loss[loss=0.1737, simple_loss=0.2352, pruned_loss=0.05609, over 4709.00 frames.], tot_loss[loss=0.1754, simple_loss=0.241, pruned_loss=0.05485, over 971911.43 frames.], batch size: 15, lr: 7.25e-04
2022-05-04 04:42:41,716 INFO [train.py:715] (5/8) Epoch 2, batch 6800, loss[loss=0.1936, simple_loss=0.2534, pruned_loss=0.06693, over 4893.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2401, pruned_loss=0.05409, over 972102.96 frames.], batch size: 19, lr: 7.25e-04
2022-05-04 04:43:20,938 INFO [train.py:715] (5/8) Epoch 2, batch 6850, loss[loss=0.1719, simple_loss=0.2355, pruned_loss=0.05421, over 4705.00 frames.], tot_loss[loss=0.175, simple_loss=0.2409, pruned_loss=0.05458, over 972633.25 frames.], batch size: 15, lr: 7.25e-04
2022-05-04 04:44:01,038 INFO [train.py:715] (5/8) Epoch 2, batch 6900, loss[loss=0.2238, simple_loss=0.2833, pruned_loss=0.08212, over 4932.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2411, pruned_loss=0.05498, over 971995.71 frames.], batch size: 18, lr: 7.24e-04
2022-05-04 04:44:41,210 INFO [train.py:715] (5/8) Epoch 2, batch 6950, loss[loss=0.1852, simple_loss=0.2362, pruned_loss=0.06709, over 4748.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2403, pruned_loss=0.05461, over 972047.09 frames.], batch size: 12, lr: 7.24e-04
2022-05-04 04:45:19,405 INFO [train.py:715] (5/8) Epoch 2, batch 7000, loss[loss=0.1856, simple_loss=0.2464, pruned_loss=0.06241, over 4770.00 frames.], tot_loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.05469, over 971338.21 frames.], batch size: 14, lr: 7.24e-04
2022-05-04 04:45:59,979 INFO [train.py:715] (5/8) Epoch 2, batch 7050, loss[loss=0.1662, simple_loss=0.2334, pruned_loss=0.04951, over 4691.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2398, pruned_loss=0.05398, over 971533.26 frames.], batch size: 15, lr: 7.24e-04
2022-05-04 04:46:40,403 INFO [train.py:715] (5/8) Epoch 2, batch 7100, loss[loss=0.1655, simple_loss=0.2376, pruned_loss=0.04665, over 4770.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2404, pruned_loss=0.05418, over 971396.36 frames.], batch size: 17, lr: 7.24e-04
2022-05-04 04:47:19,790 INFO [train.py:715] (5/8) Epoch 2, batch 7150, loss[loss=0.166, simple_loss=0.2378, pruned_loss=0.04713, over 4968.00 frames.], tot_loss[loss=0.174, simple_loss=0.2397, pruned_loss=0.05415, over 972173.28 frames.], batch size: 39, lr: 7.23e-04
2022-05-04 04:48:00,087 INFO [train.py:715] (5/8) Epoch 2, batch 7200, loss[loss=0.1758, simple_loss=0.25, pruned_loss=0.05079, over 4700.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.05372, over 972386.60 frames.], batch size: 15, lr: 7.23e-04
2022-05-04 04:48:41,278 INFO [train.py:715] (5/8) Epoch 2, batch 7250, loss[loss=0.1725, simple_loss=0.2466, pruned_loss=0.04924, over 4937.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2398, pruned_loss=0.05394, over 972880.09 frames.], batch size: 21, lr: 7.23e-04
2022-05-04 04:49:21,916 INFO [train.py:715] (5/8) Epoch 2, batch 7300, loss[loss=0.2233, simple_loss=0.2663, pruned_loss=0.09017, over 4970.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2404, pruned_loss=0.05454, over 973087.76 frames.], batch size: 24, lr: 7.23e-04
2022-05-04 04:50:01,601 INFO [train.py:715] (5/8) Epoch 2, batch 7350, loss[loss=0.1559, simple_loss=0.2395, pruned_loss=0.03618, over 4915.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2402, pruned_loss=0.0542, over 973168.66 frames.], batch size: 18, lr: 7.22e-04
2022-05-04 04:50:42,528 INFO [train.py:715] (5/8) Epoch 2, batch 7400, loss[loss=0.1829, simple_loss=0.2527, pruned_loss=0.05655, over 4793.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2407, pruned_loss=0.05437, over 972576.01 frames.], batch size: 14, lr: 7.22e-04
2022-05-04 04:51:24,320 INFO [train.py:715] (5/8) Epoch 2, batch 7450, loss[loss=0.1724, simple_loss=0.2412, pruned_loss=0.05186, over 4879.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2395, pruned_loss=0.05353, over 972812.18 frames.], batch size: 16, lr: 7.22e-04
2022-05-04 04:52:04,705 INFO [train.py:715] (5/8) Epoch 2, batch 7500, loss[loss=0.1656, simple_loss=0.2184, pruned_loss=0.05646, over 4843.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2408, pruned_loss=0.05421, over 972883.17 frames.], batch size: 13, lr: 7.22e-04
2022-05-04 04:52:45,159 INFO [train.py:715] (5/8) Epoch 2, batch 7550, loss[loss=0.1893, simple_loss=0.2434, pruned_loss=0.06761, over 4794.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2412, pruned_loss=0.05413, over 973434.14 frames.], batch size: 12, lr: 7.21e-04
2022-05-04 04:53:26,933 INFO [train.py:715] (5/8) Epoch 2, batch 7600, loss[loss=0.1634, simple_loss=0.2235, pruned_loss=0.05161, over 4910.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2407, pruned_loss=0.05355, over 973600.49 frames.], batch size: 19, lr: 7.21e-04
2022-05-04 04:54:08,312 INFO [train.py:715] (5/8) Epoch 2, batch 7650, loss[loss=0.1505, simple_loss=0.2236, pruned_loss=0.03869, over 4812.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2403, pruned_loss=0.0532, over 973356.28 frames.], batch size: 27, lr: 7.21e-04
2022-05-04 04:54:48,379 INFO [train.py:715] (5/8) Epoch 2, batch 7700, loss[loss=0.1494, simple_loss=0.2227, pruned_loss=0.03805, over 4863.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2405, pruned_loss=0.05328, over 972610.43 frames.], batch size: 22, lr: 7.21e-04
2022-05-04 04:55:29,830 INFO [train.py:715] (5/8) Epoch 2, batch 7750, loss[loss=0.168, simple_loss=0.2298, pruned_loss=0.05304, over 4818.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2402, pruned_loss=0.05345, over 972419.60 frames.], batch size: 26, lr: 7.21e-04
2022-05-04 04:56:11,499 INFO [train.py:715] (5/8) Epoch 2, batch 7800, loss[loss=0.1794, simple_loss=0.2428, pruned_loss=0.05802, over 4780.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2423, pruned_loss=0.05467, over 972558.19 frames.], batch size: 17, lr: 7.20e-04
2022-05-04 04:56:52,002 INFO [train.py:715] (5/8) Epoch 2, batch 7850, loss[loss=0.1659, simple_loss=0.234, pruned_loss=0.04887, over 4929.00 frames.], tot_loss[loss=0.176, simple_loss=0.2427, pruned_loss=0.0546, over 973183.00 frames.], batch size: 23, lr: 7.20e-04
2022-05-04 04:57:33,357 INFO [train.py:715] (5/8) Epoch 2, batch 7900, loss[loss=0.1765, simple_loss=0.2444, pruned_loss=0.05432, over 4899.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2421, pruned_loss=0.05454, over 972546.87 frames.], batch size: 18, lr: 7.20e-04
2022-05-04 04:58:15,548 INFO [train.py:715] (5/8) Epoch 2, batch 7950, loss[loss=0.1699, simple_loss=0.2207, pruned_loss=0.05956, over 4799.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2421, pruned_loss=0.05488, over 972888.04 frames.], batch size: 12, lr: 7.20e-04
2022-05-04 04:58:57,042 INFO [train.py:715] (5/8) Epoch 2, batch 8000, loss[loss=0.1542, simple_loss=0.2205, pruned_loss=0.044, over 4798.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2418, pruned_loss=0.05479, over 972182.44 frames.], batch size: 25, lr: 7.19e-04
2022-05-04 04:59:37,243 INFO [train.py:715] (5/8) Epoch 2, batch 8050, loss[loss=0.1903, simple_loss=0.2448, pruned_loss=0.06786, over 4706.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2418, pruned_loss=0.0548, over 972810.54 frames.], batch size: 15, lr: 7.19e-04
2022-05-04 05:00:18,968 INFO [train.py:715] (5/8) Epoch 2, batch 8100, loss[loss=0.2156, simple_loss=0.2614, pruned_loss=0.08492, over 4699.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2408, pruned_loss=0.05437, over 972427.57 frames.], batch size: 15, lr: 7.19e-04
2022-05-04 05:01:00,834 INFO [train.py:715] (5/8) Epoch 2, batch 8150, loss[loss=0.202, simple_loss=0.2672, pruned_loss=0.06841, over 4740.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2407, pruned_loss=0.05481, over 972398.81 frames.], batch size: 16, lr: 7.19e-04
2022-05-04 05:01:41,272 INFO [train.py:715] (5/8) Epoch 2, batch 8200, loss[loss=0.1761, simple_loss=0.2374, pruned_loss=0.05746, over 4765.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2415, pruned_loss=0.05515, over 972068.32 frames.], batch size: 19, lr: 7.18e-04
2022-05-04 05:02:22,251 INFO [train.py:715] (5/8) Epoch 2, batch 8250, loss[loss=0.2504, simple_loss=0.296, pruned_loss=0.1024, over 4871.00 frames.], tot_loss[loss=0.1763, simple_loss=0.242, pruned_loss=0.05531, over 972612.21 frames.], batch size: 39, lr: 7.18e-04
2022-05-04 05:03:04,361 INFO [train.py:715] (5/8) Epoch 2, batch 8300, loss[loss=0.1596, simple_loss=0.228, pruned_loss=0.04562, over 4821.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2415, pruned_loss=0.05492, over 972994.72 frames.], batch size: 27, lr: 7.18e-04
2022-05-04 05:03:46,078 INFO [train.py:715] (5/8) Epoch 2, batch 8350, loss[loss=0.1711, simple_loss=0.2413, pruned_loss=0.05045, over 4964.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2412, pruned_loss=0.05477, over 971970.14 frames.], batch size: 35, lr: 7.18e-04
2022-05-04 05:04:26,322 INFO [train.py:715] (5/8) Epoch 2, batch 8400, loss[loss=0.205, simple_loss=0.2697, pruned_loss=0.07015, over 4910.00 frames.], tot_loss[loss=0.1741, simple_loss=0.24, pruned_loss=0.05416, over 971748.40 frames.], batch size: 39, lr: 7.18e-04
2022-05-04 05:05:07,470 INFO [train.py:715] (5/8) Epoch 2, batch 8450, loss[loss=0.1484, simple_loss=0.2175, pruned_loss=0.03963, over 4850.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2391, pruned_loss=0.05368, over 972207.26 frames.], batch size: 32, lr: 7.17e-04
2022-05-04 05:05:49,562 INFO [train.py:715] (5/8) Epoch 2, batch 8500, loss[loss=0.1747, simple_loss=0.2457, pruned_loss=0.05182, over 4747.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2396, pruned_loss=0.05374, over 972007.67 frames.], batch size: 16, lr: 7.17e-04
2022-05-04 05:06:29,761 INFO [train.py:715] (5/8) Epoch 2, batch 8550, loss[loss=0.1694, simple_loss=0.2322, pruned_loss=0.0533, over 4789.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2401, pruned_loss=0.05417, over 972167.74 frames.], batch size: 21, lr: 7.17e-04
2022-05-04 05:07:10,972 INFO [train.py:715] (5/8) Epoch 2, batch 8600, loss[loss=0.1996, simple_loss=0.2621, pruned_loss=0.06853, over 4934.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2409, pruned_loss=0.0547, over 972130.05 frames.], batch size: 23, lr: 7.17e-04
2022-05-04 05:07:52,994 INFO [train.py:715] (5/8) Epoch 2, batch 8650, loss[loss=0.178, simple_loss=0.2417, pruned_loss=0.0572, over 4797.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2412, pruned_loss=0.05456, over 971976.71 frames.], batch size: 24, lr: 7.16e-04
2022-05-04 05:08:34,287 INFO [train.py:715] (5/8) Epoch 2, batch 8700, loss[loss=0.1677, simple_loss=0.2322, pruned_loss=0.05162, over 4775.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2413, pruned_loss=0.05496, over 971429.40 frames.], batch size: 18, lr: 7.16e-04
2022-05-04 05:09:14,826 INFO [train.py:715] (5/8) Epoch 2, batch 8750, loss[loss=0.1852, simple_loss=0.246, pruned_loss=0.06217, over 4848.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2404, pruned_loss=0.05521, over 971392.66 frames.], batch size: 32, lr: 7.16e-04
2022-05-04 05:09:56,626 INFO [train.py:715] (5/8) Epoch 2, batch 8800, loss[loss=0.1589, simple_loss=0.2205, pruned_loss=0.04862, over 4972.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2391, pruned_loss=0.05452, over 971276.02 frames.], batch size: 15, lr: 7.16e-04
2022-05-04 05:10:38,733 INFO [train.py:715] (5/8) Epoch 2, batch 8850, loss[loss=0.1571, simple_loss=0.2294, pruned_loss=0.0424, over 4858.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2385, pruned_loss=0.05387, over 971748.76 frames.], batch size: 13, lr: 7.15e-04
2022-05-04 05:11:18,695 INFO [train.py:715] (5/8) Epoch 2, batch 8900, loss[loss=0.164, simple_loss=0.2287, pruned_loss=0.04969, over 4782.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2375, pruned_loss=0.05332, over 972287.12 frames.], batch size: 17, lr: 7.15e-04
2022-05-04 05:12:00,190 INFO [train.py:715] (5/8) Epoch 2, batch 8950, loss[loss=0.1814, simple_loss=0.2502, pruned_loss=0.05631, over 4951.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2389, pruned_loss=0.05362, over 971899.26 frames.], batch size: 24, lr: 7.15e-04
2022-05-04 05:12:42,403 INFO [train.py:715] (5/8) Epoch 2, batch 9000, loss[loss=0.2282, simple_loss=0.2845, pruned_loss=0.08591, over 4785.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2403, pruned_loss=0.05442, over 972525.51 frames.], batch size: 14, lr: 7.15e-04
2022-05-04 05:12:42,404 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 05:12:58,992 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2047, pruned_loss=0.01572, over 914524.00 frames.
2022-05-04 05:13:41,063 INFO [train.py:715] (5/8) Epoch 2, batch 9050, loss[loss=0.1395, simple_loss=0.2168, pruned_loss=0.03106, over 4777.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2387, pruned_loss=0.05327, over 972839.35 frames.], batch size: 18, lr: 7.15e-04
2022-05-04 05:14:21,243 INFO [train.py:715] (5/8) Epoch 2, batch 9100, loss[loss=0.1758, simple_loss=0.2477, pruned_loss=0.05192, over 4932.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2397, pruned_loss=0.05456, over 972998.84 frames.], batch size: 23, lr: 7.14e-04
2022-05-04 05:15:02,338 INFO [train.py:715] (5/8) Epoch 2, batch 9150, loss[loss=0.1908, simple_loss=0.2575, pruned_loss=0.06207, over 4906.00 frames.], tot_loss[loss=0.174, simple_loss=0.2396, pruned_loss=0.0542, over 973825.96 frames.], batch size: 29, lr: 7.14e-04
2022-05-04 05:15:43,580 INFO [train.py:715] (5/8) Epoch 2, batch 9200, loss[loss=0.1939, simple_loss=0.2565, pruned_loss=0.06559, over 4973.00 frames.], tot_loss[loss=0.1733, simple_loss=0.239, pruned_loss=0.05374, over 974067.00 frames.], batch size: 39, lr: 7.14e-04
2022-05-04 05:16:25,102 INFO [train.py:715] (5/8) Epoch 2, batch 9250, loss[loss=0.1856, simple_loss=0.2528, pruned_loss=0.05918, over 4923.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2397, pruned_loss=0.05363, over 974344.46 frames.], batch size: 17, lr: 7.14e-04
2022-05-04 05:17:05,074 INFO [train.py:715] (5/8) Epoch 2, batch 9300, loss[loss=0.151, simple_loss=0.2159, pruned_loss=0.04306, over 4789.00 frames.], tot_loss[loss=0.1737, simple_loss=0.24, pruned_loss=0.05365, over 974338.00 frames.], batch size: 14, lr: 7.13e-04
2022-05-04 05:17:46,770 INFO [train.py:715] (5/8) Epoch 2, batch 9350, loss[loss=0.129, simple_loss=0.2038, pruned_loss=0.0271, over 4800.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2403, pruned_loss=0.05368, over 973395.56 frames.], batch size: 14, lr: 7.13e-04
2022-05-04 05:18:28,857 INFO [train.py:715] (5/8) Epoch 2, batch 9400, loss[loss=0.1604, simple_loss=0.2219, pruned_loss=0.04943, over 4731.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2394, pruned_loss=0.05354, over 973042.79 frames.], batch size: 12, lr: 7.13e-04
2022-05-04 05:19:08,508 INFO [train.py:715] (5/8) Epoch 2, batch 9450, loss[loss=0.1713, simple_loss=0.2483, pruned_loss=0.04719, over 4872.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2393, pruned_loss=0.0537, over 972551.71 frames.], batch size: 22, lr: 7.13e-04
2022-05-04 05:19:48,362 INFO [train.py:715] (5/8) Epoch 2, batch 9500, loss[loss=0.1869, simple_loss=0.2549, pruned_loss=0.05948, over 4924.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2383, pruned_loss=0.05313, over 972961.92 frames.], batch size: 23, lr: 7.13e-04
2022-05-04 05:20:28,634 INFO [train.py:715] (5/8) Epoch 2, batch 9550, loss[loss=0.1279, simple_loss=0.1989, pruned_loss=0.02848, over 4743.00 frames.], tot_loss[loss=0.1731, simple_loss=0.239, pruned_loss=0.0536, over 972138.20 frames.], batch size: 12, lr: 7.12e-04
2022-05-04 05:21:08,639 INFO [train.py:715] (5/8) Epoch 2, batch 9600, loss[loss=0.1763, simple_loss=0.2422, pruned_loss=0.05525, over 4967.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05317, over 972364.84 frames.], batch size: 39, lr: 7.12e-04
2022-05-04 05:21:47,536 INFO [train.py:715] (5/8) Epoch 2, batch 9650, loss[loss=0.1463, simple_loss=0.223, pruned_loss=0.03481, over 4818.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2372, pruned_loss=0.05267, over 973099.09 frames.], batch size: 26, lr: 7.12e-04
2022-05-04 05:22:27,780 INFO [train.py:715] (5/8) Epoch 2, batch 9700, loss[loss=0.1891, simple_loss=0.2552, pruned_loss=0.06149, over 4835.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2385, pruned_loss=0.05348, over 971572.03 frames.], batch size: 15, lr: 7.12e-04
2022-05-04 05:23:08,410 INFO [train.py:715] (5/8) Epoch 2, batch 9750, loss[loss=0.1915, simple_loss=0.2391, pruned_loss=0.07191, over 4772.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2387, pruned_loss=0.05381, over 971653.45 frames.], batch size: 14, lr: 7.11e-04
2022-05-04 05:23:47,699 INFO [train.py:715] (5/8) Epoch 2, batch 9800, loss[loss=0.1613, simple_loss=0.2348, pruned_loss=0.04394, over 4704.00 frames.], tot_loss[loss=0.173, simple_loss=0.2384, pruned_loss=0.05378, over 971810.01 frames.], batch size: 15, lr: 7.11e-04
2022-05-04 05:24:26,796 INFO [train.py:715] (5/8) Epoch 2, batch 9850, loss[loss=0.1832, simple_loss=0.2622, pruned_loss=0.05209, over 4889.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2396, pruned_loss=0.05414, over 971584.67 frames.], batch size: 19, lr: 7.11e-04
2022-05-04 05:25:06,817 INFO [train.py:715] (5/8) Epoch 2, batch 9900, loss[loss=0.1521, simple_loss=0.2175, pruned_loss=0.04339, over 4985.00 frames.], tot_loss[loss=0.1745, simple_loss=0.24, pruned_loss=0.05447, over 972066.22 frames.], batch size: 14, lr: 7.11e-04
2022-05-04 05:25:46,409 INFO [train.py:715] (5/8) Epoch 2, batch 9950, loss[loss=0.1719, simple_loss=0.2294, pruned_loss=0.05715, over 4903.00 frames.], tot_loss[loss=0.174, simple_loss=0.2401, pruned_loss=0.05393, over 972310.63 frames.], batch size: 17, lr: 7.11e-04
2022-05-04 05:26:25,429 INFO [train.py:715] (5/8) Epoch 2, batch 10000, loss[loss=0.164, simple_loss=0.2395, pruned_loss=0.04422, over 4938.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2395, pruned_loss=0.05359, over 972470.46 frames.], batch size: 23, lr: 7.10e-04
2022-05-04 05:27:06,107 INFO [train.py:715] (5/8) Epoch 2, batch 10050, loss[loss=0.133, simple_loss=0.2162, pruned_loss=0.02488, over 4823.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2398, pruned_loss=0.05366, over 972707.44 frames.], batch size: 13, lr: 7.10e-04
2022-05-04 05:27:45,913 INFO [train.py:715] (5/8) Epoch 2, batch 10100, loss[loss=0.1799, simple_loss=0.2495, pruned_loss=0.05516, over 4922.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2393, pruned_loss=0.0532, over 972533.82 frames.], batch size: 23, lr: 7.10e-04
2022-05-04 05:28:25,923 INFO [train.py:715] (5/8) Epoch 2, batch 10150, loss[loss=0.2209, simple_loss=0.28, pruned_loss=0.0809, over 4760.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2397, pruned_loss=0.05307, over 972588.34 frames.], batch size: 19, lr: 7.10e-04
2022-05-04 05:29:06,178 INFO [train.py:715] (5/8) Epoch 2, batch 10200, loss[loss=0.1686, simple_loss=0.2439, pruned_loss=0.04665, over 4875.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2397, pruned_loss=0.05285, over 972418.12 frames.], batch size: 16, lr: 7.09e-04
2022-05-04 05:29:47,604 INFO [train.py:715] (5/8) Epoch 2, batch 10250, loss[loss=0.1543, simple_loss=0.222, pruned_loss=0.04327, over 4754.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2395, pruned_loss=0.05287, over 972737.38 frames.], batch size: 19, lr: 7.09e-04
2022-05-04 05:30:27,422 INFO [train.py:715] (5/8) Epoch 2, batch 10300, loss[loss=0.19, simple_loss=0.266, pruned_loss=0.05694, over 4911.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2395, pruned_loss=0.05282, over 973135.24 frames.], batch size: 17, lr: 7.09e-04
2022-05-04 05:31:07,041 INFO [train.py:715] (5/8) Epoch 2, batch 10350, loss[loss=0.1596, simple_loss=0.225, pruned_loss=0.04712, over 4966.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2394, pruned_loss=0.05245, over 973649.85 frames.], batch size: 25, lr: 7.09e-04
2022-05-04 05:31:49,856 INFO [train.py:715] (5/8) Epoch 2, batch 10400, loss[loss=0.1648, simple_loss=0.2399, pruned_loss=0.04487, over 4814.00 frames.], tot_loss[loss=0.172, simple_loss=0.2395, pruned_loss=0.05231, over 973388.64 frames.], batch size: 26, lr: 7.09e-04
2022-05-04 05:32:31,027 INFO [train.py:715] (5/8) Epoch 2, batch 10450, loss[loss=0.16, simple_loss=0.2329, pruned_loss=0.04356, over 4987.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2406, pruned_loss=0.05313, over 973807.57 frames.], batch size: 25, lr: 7.08e-04
2022-05-04 05:33:11,291 INFO [train.py:715] (5/8) Epoch 2, batch 10500, loss[loss=0.1476, simple_loss=0.2179, pruned_loss=0.0387, over 4865.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2395, pruned_loss=0.05259, over 972881.38 frames.], batch size: 13, lr: 7.08e-04
2022-05-04 05:33:50,625 INFO [train.py:715] (5/8) Epoch 2, batch 10550, loss[loss=0.1821, simple_loss=0.2434, pruned_loss=0.06037, over 4951.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2396, pruned_loss=0.05274, over 973038.95 frames.], batch size: 14, lr: 7.08e-04
2022-05-04 05:34:31,848 INFO [train.py:715] (5/8) Epoch 2, batch 10600, loss[loss=0.1833, simple_loss=0.2447, pruned_loss=0.061, over 4977.00 frames.], tot_loss[loss=0.1719, simple_loss=0.239, pruned_loss=0.05238, over 972587.28 frames.], batch size: 24, lr: 7.08e-04
2022-05-04 05:35:12,039 INFO [train.py:715] (5/8) Epoch 2, batch 10650, loss[loss=0.2149, simple_loss=0.263, pruned_loss=0.08344, over 4895.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2404, pruned_loss=0.05331, over 972888.68 frames.], batch size: 19, lr: 7.07e-04
2022-05-04 05:35:51,942 INFO [train.py:715] (5/8) Epoch 2, batch 10700, loss[loss=0.2132, simple_loss=0.2823, pruned_loss=0.07203, over 4798.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2409, pruned_loss=0.05345, over 972790.39 frames.], batch size: 24, lr: 7.07e-04
2022-05-04 05:36:32,505 INFO [train.py:715] (5/8) Epoch 2, batch 10750, loss[loss=0.2047, simple_loss=0.2641, pruned_loss=0.07266, over 4912.00 frames.], tot_loss[loss=0.175, simple_loss=0.2416, pruned_loss=0.05423, over 972386.76 frames.], batch size: 19, lr: 7.07e-04
2022-05-04 05:37:13,647 INFO [train.py:715] (5/8) Epoch 2, batch 10800, loss[loss=0.1555, simple_loss=0.2286, pruned_loss=0.04116, over 4822.00 frames.], tot_loss[loss=0.1738, simple_loss=0.24, pruned_loss=0.05376, over 971959.06 frames.], batch size: 26, lr: 7.07e-04
2022-05-04 05:37:53,814 INFO [train.py:715] (5/8) Epoch 2, batch 10850, loss[loss=0.1951, simple_loss=0.2587, pruned_loss=0.06573, over 4746.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2407, pruned_loss=0.05432, over 972043.16 frames.], batch size: 19, lr: 7.07e-04
2022-05-04 05:38:33,331 INFO [train.py:715] (5/8) Epoch 2, batch 10900, loss[loss=0.1615, simple_loss=0.2329, pruned_loss=0.04504, over 4988.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2401, pruned_loss=0.05414, over 973341.44 frames.], batch size: 25, lr: 7.06e-04
2022-05-04 05:39:14,361 INFO [train.py:715] (5/8) Epoch 2, batch 10950, loss[loss=0.1525, simple_loss=0.2195, pruned_loss=0.04279, over 4773.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2406, pruned_loss=0.05414, over 973258.94 frames.], batch size: 19, lr: 7.06e-04
2022-05-04 05:39:54,190 INFO [train.py:715] (5/8) Epoch 2, batch 11000, loss[loss=0.1852, simple_loss=0.267, pruned_loss=0.05166, over 4886.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2401, pruned_loss=0.05336, over 972987.14 frames.], batch size: 22, lr: 7.06e-04
2022-05-04 05:40:33,762 INFO [train.py:715] (5/8) Epoch 2, batch 11050, loss[loss=0.2304, simple_loss=0.2841, pruned_loss=0.08833, over 4944.00 frames.], tot_loss[loss=0.173, simple_loss=0.2396, pruned_loss=0.05315, over 973454.22 frames.], batch size: 39, lr: 7.06e-04
2022-05-04 05:41:14,435 INFO [train.py:715] (5/8) Epoch 2, batch 11100, loss[loss=0.1999, simple_loss=0.2613, pruned_loss=0.0693, over 4762.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2381, pruned_loss=0.0526, over 973477.63 frames.], batch size: 18, lr: 7.05e-04
2022-05-04 05:41:54,868 INFO [train.py:715] (5/8) Epoch 2, batch 11150, loss[loss=0.152, simple_loss=0.2364, pruned_loss=0.03379, over 4906.00 frames.], tot_loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.0528, over 972975.65 frames.], batch size: 17, lr: 7.05e-04
2022-05-04 05:42:35,626 INFO [train.py:715] (5/8) Epoch 2, batch 11200, loss[loss=0.204, simple_loss=0.2655, pruned_loss=0.07125, over 4841.00 frames.], tot_loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.05278, over 972678.33 frames.], batch size: 30, lr: 7.05e-04
2022-05-04 05:43:15,656 INFO [train.py:715] (5/8) Epoch 2, batch 11250, loss[loss=0.1305, simple_loss=0.2114, pruned_loss=0.02479, over 4928.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2384, pruned_loss=0.05229, over 973149.62 frames.], batch size: 23, lr: 7.05e-04
2022-05-04 05:43:56,722 INFO [train.py:715] (5/8) Epoch 2, batch 11300, loss[loss=0.2107, simple_loss=0.2676, pruned_loss=0.07692, over 4893.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2373, pruned_loss=0.05189, over 973479.40 frames.], batch size: 22, lr: 7.05e-04
2022-05-04 05:44:37,061 INFO [train.py:715] (5/8) Epoch 2, batch 11350, loss[loss=0.1698, simple_loss=0.2462, pruned_loss=0.04669, over 4956.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2362, pruned_loss=0.05174, over 973715.25 frames.], batch size: 21, lr: 7.04e-04
2022-05-04 05:45:16,683 INFO [train.py:715] (5/8) Epoch 2, batch 11400, loss[loss=0.2408, simple_loss=0.2852, pruned_loss=0.09822, over 4813.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2366, pruned_loss=0.05211, over 972942.66 frames.], batch size: 15, lr: 7.04e-04
2022-05-04 05:45:56,740 INFO [train.py:715] (5/8) Epoch 2, batch 11450, loss[loss=0.1862, simple_loss=0.2539, pruned_loss=0.05924, over 4941.00 frames.], tot_loss[loss=0.1711, simple_loss=0.237, pruned_loss=0.05255, over 972365.22 frames.], batch size: 29, lr: 7.04e-04
2022-05-04 05:46:37,328 INFO [train.py:715] (5/8) Epoch 2, batch 11500, loss[loss=0.1773, simple_loss=0.2397, pruned_loss=0.0574, over 4788.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2377, pruned_loss=0.05351, over 971698.63 frames.], batch size: 18, lr: 7.04e-04
2022-05-04 05:47:18,057 INFO [train.py:715] (5/8) Epoch 2, batch 11550, loss[loss=0.1791, simple_loss=0.2438, pruned_loss=0.05724, over 4862.00 frames.], tot_loss[loss=0.1713, simple_loss=0.237, pruned_loss=0.05282, over 971620.96 frames.], batch size: 20, lr: 7.04e-04
2022-05-04 05:47:58,023 INFO [train.py:715] (5/8) Epoch 2, batch 11600, loss[loss=0.1454, simple_loss=0.2238, pruned_loss=0.03355, over 4979.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2364, pruned_loss=0.05255, over 971850.28 frames.], batch size: 25, lr: 7.03e-04
2022-05-04 05:48:39,181 INFO [train.py:715] (5/8) Epoch 2, batch 11650, loss[loss=0.1618, simple_loss=0.2338, pruned_loss=0.04487, over 4811.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2366, pruned_loss=0.05225, over 971833.62 frames.], batch size: 25, lr: 7.03e-04
2022-05-04 05:49:19,427 INFO [train.py:715] (5/8) Epoch 2, batch 11700, loss[loss=0.1704, simple_loss=0.2349, pruned_loss=0.05293, over 4986.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2365, pruned_loss=0.0523, over 972417.33 frames.], batch size: 28, lr: 7.03e-04
2022-05-04 05:49:59,624 INFO [train.py:715] (5/8) Epoch 2, batch 11750, loss[loss=0.1926, simple_loss=0.2586, pruned_loss=0.06329, over 4982.00 frames.], tot_loss[loss=0.17, simple_loss=0.2361, pruned_loss=0.05199, over 972123.01 frames.], batch size: 35, lr: 7.03e-04
2022-05-04 05:50:40,403 INFO [train.py:715] (5/8) Epoch 2, batch 11800, loss[loss=0.1728, simple_loss=0.231, pruned_loss=0.05724, over 4837.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2358, pruned_loss=0.05168, over 972330.79 frames.], batch size: 26, lr: 7.02e-04
2022-05-04 05:51:20,989 INFO [train.py:715] (5/8) Epoch 2, batch 11850, loss[loss=0.1759, simple_loss=0.2528, pruned_loss=0.0495, over 4971.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2368, pruned_loss=0.05199, over 972621.86 frames.], batch size: 24, lr: 7.02e-04
2022-05-04 05:52:00,404 INFO [train.py:715] (5/8) Epoch 2, batch 11900, loss[loss=0.1971, simple_loss=0.2564, pruned_loss=0.06886, over 4965.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2378, pruned_loss=0.05265, over 972647.18 frames.], batch size: 29, lr: 7.02e-04
2022-05-04 05:52:40,335 INFO [train.py:715] (5/8) Epoch 2, batch 11950, loss[loss=0.1435, simple_loss=0.2087, pruned_loss=0.03915, over 4875.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2378, pruned_loss=0.05257, over 971983.63 frames.], batch size: 16, lr: 7.02e-04
2022-05-04 05:53:21,659 INFO [train.py:715] (5/8) Epoch 2, batch 12000, loss[loss=0.1608, simple_loss=0.2267, pruned_loss=0.04748, over 4782.00 frames.], tot_loss[loss=0.1704, simple_loss=0.237, pruned_loss=0.05194, over 970883.80 frames.], batch size: 18, lr: 7.02e-04
2022-05-04 05:53:21,659 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 05:53:45,623 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2049, pruned_loss=0.01568, over 914524.00 frames.
2022-05-04 05:54:27,032 INFO [train.py:715] (5/8) Epoch 2, batch 12050, loss[loss=0.176, simple_loss=0.2421, pruned_loss=0.05491, over 4882.00 frames.], tot_loss[loss=0.1708, simple_loss=0.237, pruned_loss=0.05235, over 971864.28 frames.], batch size: 22, lr: 7.01e-04
2022-05-04 05:55:07,118 INFO [train.py:715] (5/8) Epoch 2, batch 12100, loss[loss=0.1737, simple_loss=0.2417, pruned_loss=0.05287, over 4863.00 frames.], tot_loss[loss=0.171, simple_loss=0.2373, pruned_loss=0.05229, over 971696.13 frames.], batch size: 20, lr: 7.01e-04
2022-05-04 05:55:47,110 INFO [train.py:715] (5/8) Epoch 2, batch 12150, loss[loss=0.1822, simple_loss=0.2516, pruned_loss=0.0564, over 4874.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2372, pruned_loss=0.05214, over 971665.12 frames.], batch size: 19, lr: 7.01e-04
2022-05-04 05:56:27,811 INFO [train.py:715] (5/8) Epoch 2, batch 12200, loss[loss=0.1605, simple_loss=0.2225, pruned_loss=0.04922, over 4958.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2377, pruned_loss=0.05266, over 972046.82 frames.], batch size: 35, lr: 7.01e-04
2022-05-04 05:57:07,987 INFO [train.py:715] (5/8) Epoch 2, batch 12250, loss[loss=0.1754, simple_loss=0.2495, pruned_loss=0.0506, over 4895.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2376, pruned_loss=0.05259, over 972843.76 frames.], batch size: 17, lr: 7.01e-04
2022-05-04 05:57:48,413 INFO [train.py:715] (5/8) Epoch 2, batch 12300, loss[loss=0.1631, simple_loss=0.2339, pruned_loss=0.04613, over 4754.00 frames.], tot_loss[loss=0.1718, simple_loss=0.238, pruned_loss=0.05282, over 972425.94 frames.], batch size: 19, lr: 7.00e-04
2022-05-04 05:58:28,545 INFO [train.py:715] (5/8) Epoch 2, batch 12350, loss[loss=0.1712, simple_loss=0.2341, pruned_loss=0.05414, over 4951.00 frames.], tot_loss[loss=0.1718, simple_loss=0.238, pruned_loss=0.05287, over 972962.62 frames.], batch size: 21, lr: 7.00e-04
2022-05-04 05:59:09,759 INFO [train.py:715] (5/8) Epoch 2, batch 12400, loss[loss=0.2157, simple_loss=0.264, pruned_loss=0.08366, over 4851.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2381, pruned_loss=0.05289, over 972549.62 frames.], batch size: 32, lr: 7.00e-04
2022-05-04 05:59:50,019 INFO [train.py:715] (5/8) Epoch 2, batch 12450, loss[loss=0.1876, simple_loss=0.251, pruned_loss=0.0621, over 4875.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2383, pruned_loss=0.05323, over 973265.78 frames.], batch size: 16, lr: 7.00e-04
2022-05-04 06:00:29,889 INFO [train.py:715] (5/8) Epoch 2, batch 12500, loss[loss=0.1603, simple_loss=0.239, pruned_loss=0.0408, over 4757.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2394, pruned_loss=0.0541, over 972779.03 frames.], batch size: 16, lr: 6.99e-04
2022-05-04 06:01:10,540 INFO [train.py:715] (5/8) Epoch 2, batch 12550, loss[loss=0.1707, simple_loss=0.2374, pruned_loss=0.05197, over 4945.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2392, pruned_loss=0.05377, over 972701.44 frames.], batch size: 39, lr: 6.99e-04
2022-05-04 06:01:50,876 INFO [train.py:715] (5/8) Epoch 2, batch 12600, loss[loss=0.1708, simple_loss=0.2324, pruned_loss=0.0546, over 4961.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.05365, over 972285.54 frames.], batch size: 24, lr: 6.99e-04
2022-05-04 06:02:30,897 INFO [train.py:715] (5/8) Epoch 2, batch 12650, loss[loss=0.1524, simple_loss=0.2161, pruned_loss=0.04434, over 4902.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2401, pruned_loss=0.05389, over 971960.68 frames.], batch size: 22, lr: 6.99e-04
2022-05-04 06:03:11,025 INFO [train.py:715] (5/8) Epoch 2, batch 12700, loss[loss=0.1847, simple_loss=0.2376, pruned_loss=0.06593, over 4883.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2393, pruned_loss=0.05362, over 971312.25 frames.], batch size: 19, lr: 6.99e-04
2022-05-04 06:03:51,757 INFO [train.py:715] (5/8) Epoch 2, batch 12750, loss[loss=0.1872, simple_loss=0.254, pruned_loss=0.06024, over 4799.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.0537, over 971801.70 frames.], batch size: 14, lr: 6.98e-04
2022-05-04 06:04:31,919 INFO [train.py:715] (5/8) Epoch 2, batch 12800, loss[loss=0.1694, simple_loss=0.2377, pruned_loss=0.05058, over 4837.00 frames.], tot_loss[loss=0.174, simple_loss=0.2396, pruned_loss=0.05416, over 971072.96 frames.], batch size: 27, lr: 6.98e-04
2022-05-04 06:05:11,621 INFO [train.py:715] (5/8) Epoch 2, batch 12850, loss[loss=0.1715, simple_loss=0.2245, pruned_loss=0.05925, over 4828.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2385, pruned_loss=0.05342, over 971284.48 frames.], batch size: 30, lr: 6.98e-04
2022-05-04 06:05:52,437 INFO [train.py:715] (5/8) Epoch 2, batch 12900, loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03288, over 4750.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2386, pruned_loss=0.05339, over 971690.08 frames.], batch size: 16, lr: 6.98e-04
2022-05-04 06:06:32,857 INFO [train.py:715] (5/8) Epoch 2, batch 12950, loss[loss=0.1558, simple_loss=0.2171, pruned_loss=0.04727, over 4824.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2396, pruned_loss=0.05373, over 971808.80 frames.], batch size: 12, lr: 6.98e-04
2022-05-04 06:07:12,810 INFO [train.py:715] (5/8) Epoch 2, batch 13000, loss[loss=0.1584, simple_loss=0.2292, pruned_loss=0.04383, over 4791.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2398, pruned_loss=0.0536, over 972005.00 frames.], batch size: 18, lr: 6.97e-04
2022-05-04 06:07:53,256 INFO [train.py:715] (5/8) Epoch 2, batch 13050, loss[loss=0.1473, simple_loss=0.2255, pruned_loss=0.03456, over 4795.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2392, pruned_loss=0.05303, over 972439.71 frames.], batch size: 24, lr: 6.97e-04
2022-05-04 06:08:34,489 INFO [train.py:715] (5/8) Epoch 2, batch 13100, loss[loss=0.1472, simple_loss=0.2115, pruned_loss=0.0415, over 4885.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2386, pruned_loss=0.05286, over 971987.59 frames.], batch size: 22, lr: 6.97e-04
2022-05-04 06:09:14,679 INFO [train.py:715] (5/8) Epoch 2, batch 13150, loss[loss=0.1857, simple_loss=0.2547, pruned_loss=0.05839, over 4887.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2384, pruned_loss=0.05269, over 971060.81 frames.], batch size: 19, lr: 6.97e-04
2022-05-04 06:09:54,440 INFO [train.py:715] (5/8) Epoch 2, batch 13200, loss[loss=0.1894, simple_loss=0.2584, pruned_loss=0.06017, over 4928.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2389, pruned_loss=0.05305, over 970844.83 frames.], batch size: 23, lr: 6.96e-04
2022-05-04 06:10:35,331 INFO [train.py:715] (5/8) Epoch 2, batch 13250, loss[loss=0.1684, simple_loss=0.2365, pruned_loss=0.0501, over 4882.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2393, pruned_loss=0.05331, over 971535.32 frames.], batch size: 22, lr: 6.96e-04
2022-05-04 06:11:15,867 INFO [train.py:715] (5/8) Epoch 2, batch 13300, loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03731, over 4938.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2386, pruned_loss=0.05345, over 972153.44 frames.], batch size: 21, lr: 6.96e-04
2022-05-04 06:11:55,897 INFO [train.py:715] (5/8) Epoch 2, batch 13350, loss[loss=0.1765, simple_loss=0.2573, pruned_loss=0.04783, over 4784.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2386, pruned_loss=0.05315, over 971569.72 frames.], batch size: 18, lr: 6.96e-04
2022-05-04 06:12:36,496 INFO [train.py:715] (5/8) Epoch 2, batch 13400, loss[loss=0.1389, simple_loss=0.2201, pruned_loss=0.02888, over 4912.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2385, pruned_loss=0.05286, over 971141.71 frames.], batch size: 19, lr: 6.96e-04
2022-05-04 06:13:17,583 INFO [train.py:715] (5/8) Epoch 2, batch 13450, loss[loss=0.1886, simple_loss=0.2551, pruned_loss=0.06108, over 4879.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2394, pruned_loss=0.0531, over 970883.37 frames.], batch size: 32, lr: 6.95e-04
2022-05-04 06:13:57,535 INFO [train.py:715] (5/8) Epoch 2, batch 13500, loss[loss=0.1779, simple_loss=0.2426, pruned_loss=0.05657, over 4984.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2388, pruned_loss=0.05291, over 972018.89 frames.], batch size: 15, lr: 6.95e-04
2022-05-04 06:14:37,540 INFO [train.py:715] (5/8) Epoch 2, batch 13550, loss[loss=0.1354, simple_loss=0.2171, pruned_loss=0.02684, over 4921.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2394, pruned_loss=0.05302, over 971875.76 frames.], batch size: 23, lr: 6.95e-04
2022-05-04 06:15:18,686 INFO [train.py:715] (5/8) Epoch 2, batch 13600, loss[loss=0.1922, simple_loss=0.2588, pruned_loss=0.06274, over 4978.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2399, pruned_loss=0.05348, over 971778.07 frames.], batch size: 25, lr: 6.95e-04
2022-05-04 06:15:59,130 INFO [train.py:715] (5/8) Epoch 2, batch 13650, loss[loss=0.1934, simple_loss=0.2524, pruned_loss=0.06717, over 4881.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2399, pruned_loss=0.05375, over 971545.10 frames.], batch size: 22, lr: 6.95e-04
2022-05-04 06:16:38,699 INFO [train.py:715] (5/8) Epoch 2, batch 13700, loss[loss=0.1667, simple_loss=0.2398, pruned_loss=0.04682, over 4924.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2396, pruned_loss=0.05331, over 971545.86 frames.], batch size: 18, lr: 6.94e-04
2022-05-04 06:17:19,976 INFO [train.py:715] (5/8) Epoch 2, batch 13750, loss[loss=0.1927, simple_loss=0.2557, pruned_loss=0.06483, over 4910.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.0527, over 971794.73 frames.], batch size: 17, lr: 6.94e-04
2022-05-04 06:18:00,041 INFO [train.py:715] (5/8) Epoch 2, batch 13800, loss[loss=0.1463, simple_loss=0.2218, pruned_loss=0.03541, over 4876.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05272, over 972053.24 frames.], batch size: 16, lr: 6.94e-04
2022-05-04 06:18:39,729 INFO [train.py:715] (5/8) Epoch 2, batch 13850, loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03361, over 4922.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2392, pruned_loss=0.05324, over 971969.84 frames.], batch size: 18, lr: 6.94e-04
2022-05-04 06:19:19,324 INFO [train.py:715] (5/8) Epoch 2, batch 13900, loss[loss=0.1974, simple_loss=0.2619, pruned_loss=0.06646, over 4961.00 frames.], tot_loss[loss=0.1729, simple_loss=0.239, pruned_loss=0.05342, over 972196.41 frames.], batch size: 14, lr: 6.94e-04
2022-05-04 06:20:00,086 INFO [train.py:715] (5/8) Epoch 2, batch 13950, loss[loss=0.1653, simple_loss=0.2318, pruned_loss=0.04938, over 4906.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2385, pruned_loss=0.05311, over 972147.42 frames.], batch size: 17, lr: 6.93e-04
2022-05-04 06:20:40,298 INFO [train.py:715] (5/8) Epoch 2, batch 14000, loss[loss=0.1875, simple_loss=0.251, pruned_loss=0.06198, over 4961.00 frames.], tot_loss[loss=0.173, simple_loss=0.2392, pruned_loss=0.05336, over 972240.97 frames.], batch size: 15, lr: 6.93e-04
2022-05-04 06:21:19,547 INFO [train.py:715] (5/8) Epoch 2, batch 14050, loss[loss=0.1723, simple_loss=0.2388, pruned_loss=0.05287, over 4937.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2389, pruned_loss=0.05315, over 973196.63 frames.], batch size: 29, lr: 6.93e-04
2022-05-04 06:22:01,051 INFO [train.py:715] (5/8) Epoch 2, batch 14100, loss[loss=0.1825, simple_loss=0.2498, pruned_loss=0.05763, over 4706.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2387, pruned_loss=0.05311, over 973408.11 frames.], batch size: 15, lr: 6.93e-04
2022-05-04 06:22:41,694 INFO [train.py:715] (5/8) Epoch 2, batch 14150, loss[loss=0.1819, simple_loss=0.2518, pruned_loss=0.05602, over 4846.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.05214, over 973603.60 frames.], batch size: 20, lr: 6.93e-04
2022-05-04 06:23:21,647 INFO [train.py:715] (5/8) Epoch 2, batch 14200, loss[loss=0.2057, simple_loss=0.2692, pruned_loss=0.07113, over 4811.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2386, pruned_loss=0.05298, over 974185.15 frames.], batch size: 21, lr: 6.92e-04
2022-05-04 06:24:01,485 INFO [train.py:715] (5/8) Epoch 2, batch 14250, loss[loss=0.1955, simple_loss=0.2594, pruned_loss=0.06578, over 4919.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2381, pruned_loss=0.05278, over 974643.41 frames.], batch size: 19, lr: 6.92e-04
2022-05-04 06:24:42,096 INFO [train.py:715] (5/8) Epoch 2, batch 14300, loss[loss=0.1851, simple_loss=0.2481, pruned_loss=0.06103, over 4881.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2375, pruned_loss=0.05213, over 973602.76 frames.], batch size: 22, lr: 6.92e-04
2022-05-04 06:25:21,662 INFO [train.py:715] (5/8) Epoch 2, batch 14350, loss[loss=0.1861, simple_loss=0.2488, pruned_loss=0.06168, over 4633.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05241, over 973609.82 frames.], batch size: 13, lr: 6.92e-04
2022-05-04 06:26:01,520 INFO [train.py:715] (5/8) Epoch 2, batch 14400, loss[loss=0.1969, simple_loss=0.2564, pruned_loss=0.06866, over 4848.00 frames.], tot_loss[loss=0.1706, simple_loss=0.237, pruned_loss=0.05205, over 973657.42 frames.], batch size: 32, lr: 6.92e-04
2022-05-04 06:26:41,864 INFO [train.py:715] (5/8) Epoch 2, batch 14450, loss[loss=0.1625, simple_loss=0.2324, pruned_loss=0.04635, over 4878.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2377, pruned_loss=0.05242, over 973273.47 frames.], batch size: 16, lr: 6.91e-04
2022-05-04 06:27:22,100 INFO [train.py:715] (5/8) Epoch 2, batch 14500, loss[loss=0.1731, simple_loss=0.2401, pruned_loss=0.05299, over 4938.00 frames.], tot_loss[loss=0.171, simple_loss=0.2379, pruned_loss=0.05206, over 973402.92 frames.], batch size: 35, lr: 6.91e-04
2022-05-04 06:28:01,695 INFO [train.py:715] (5/8) Epoch 2, batch 14550, loss[loss=0.1472, simple_loss=0.2146, pruned_loss=0.0399, over 4787.00 frames.], tot_loss[loss=0.171, simple_loss=0.2379, pruned_loss=0.05209, over 973343.38 frames.], batch size: 24, lr: 6.91e-04
2022-05-04 06:28:42,169 INFO [train.py:715] (5/8) Epoch 2, batch 14600, loss[loss=0.1327, simple_loss=0.2016, pruned_loss=0.03194, over 4878.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2375, pruned_loss=0.05237, over 972319.99 frames.], batch size: 16, lr: 6.91e-04
2022-05-04 06:29:22,668 INFO [train.py:715] (5/8) Epoch 2, batch 14650, loss[loss=0.1717, simple_loss=0.2336, pruned_loss=0.05485, over 4778.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2378, pruned_loss=0.0525, over 972158.13 frames.], batch size: 14, lr: 6.90e-04
2022-05-04 06:30:01,961 INFO [train.py:715] (5/8) Epoch 2, batch 14700, loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03369, over 4747.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2374, pruned_loss=0.05237, over 971997.30 frames.], batch size: 16, lr: 6.90e-04
2022-05-04 06:30:41,283 INFO [train.py:715] (5/8) Epoch 2, batch 14750, loss[loss=0.1513, simple_loss=0.2194, pruned_loss=0.04162, over 4863.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2372, pruned_loss=0.05222, over 971826.37 frames.], batch size: 20, lr: 6.90e-04
2022-05-04 06:31:21,775 INFO [train.py:715] (5/8) Epoch 2, batch 14800, loss[loss=0.1821, simple_loss=0.2311, pruned_loss=0.06654, over 4791.00 frames.], tot_loss[loss=0.1721, simple_loss=0.238, pruned_loss=0.05306, over 972092.49 frames.], batch size: 12, lr: 6.90e-04
2022-05-04 06:32:01,272 INFO [train.py:715] (5/8) Epoch 2, batch 14850, loss[loss=0.2138, simple_loss=0.2738, pruned_loss=0.07691, over 4848.00 frames.], tot_loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.0533, over 972320.22 frames.], batch size: 32, lr: 6.90e-04
2022-05-04 06:32:40,957 INFO [train.py:715] (5/8) Epoch 2, batch 14900, loss[loss=0.1386, simple_loss=0.218, pruned_loss=0.0296, over 4984.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2375, pruned_loss=0.05249, over 972336.57 frames.], batch size: 33, lr: 6.89e-04
2022-05-04 06:33:21,120 INFO [train.py:715] (5/8) Epoch 2, batch 14950, loss[loss=0.2418, simple_loss=0.3131, pruned_loss=0.08527, over 4760.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2378, pruned_loss=0.0526, over 973487.52 frames.], batch size: 17, lr: 6.89e-04
2022-05-04 06:34:01,759 INFO [train.py:715] (5/8) Epoch 2, batch 15000, loss[loss=0.1358, simple_loss=0.2011, pruned_loss=0.0353, over 4826.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2375, pruned_loss=0.05239, over 972996.13 frames.], batch size: 13, lr: 6.89e-04
2022-05-04 06:34:01,760 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 06:34:11,141 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1176, simple_loss=0.2043, pruned_loss=0.01548, over 914524.00 frames.
2022-05-04 06:34:52,069 INFO [train.py:715] (5/8) Epoch 2, batch 15050, loss[loss=0.1654, simple_loss=0.2296, pruned_loss=0.0506, over 4711.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2375, pruned_loss=0.05259, over 971615.42 frames.], batch size: 15, lr: 6.89e-04
2022-05-04 06:35:31,190 INFO [train.py:715] (5/8) Epoch 2, batch 15100, loss[loss=0.1916, simple_loss=0.2381, pruned_loss=0.0725, over 4853.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2376, pruned_loss=0.05255, over 971616.69 frames.], batch size: 32, lr: 6.89e-04
2022-05-04 06:36:11,675 INFO [train.py:715] (5/8) Epoch 2, batch 15150, loss[loss=0.2026, simple_loss=0.2778, pruned_loss=0.06372, over 4815.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2372, pruned_loss=0.05167, over 972399.19 frames.], batch size: 27, lr: 6.88e-04
2022-05-04 06:36:52,158 INFO [train.py:715] (5/8) Epoch 2, batch 15200, loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.03395, over 4842.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2378, pruned_loss=0.05196, over 972421.05 frames.], batch size: 13, lr: 6.88e-04
2022-05-04 06:37:31,886 INFO [train.py:715] (5/8) Epoch 2, batch 15250, loss[loss=0.1743, simple_loss=0.2365, pruned_loss=0.05602, over 4930.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2376, pruned_loss=0.0519, over 971785.40 frames.], batch size: 21, lr: 6.88e-04
2022-05-04 06:38:11,349 INFO [train.py:715] (5/8) Epoch 2, batch 15300, loss[loss=0.1688, simple_loss=0.2266, pruned_loss=0.05553, over 4925.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.05219, over 971718.51 frames.], batch size: 18, lr: 6.88e-04
2022-05-04 06:38:51,806 INFO [train.py:715] (5/8) Epoch 2, batch 15350, loss[loss=0.2067, simple_loss=0.2715, pruned_loss=0.07091, over 4926.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05239, over 971224.77 frames.], batch size: 23, lr: 6.88e-04
2022-05-04 06:39:32,695 INFO [train.py:715] (5/8) Epoch 2, batch 15400, loss[loss=0.1331, simple_loss=0.209, pruned_loss=0.02863, over 4906.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2384, pruned_loss=0.05298, over 971241.11 frames.], batch size: 19, lr: 6.87e-04
2022-05-04 06:40:11,869 INFO [train.py:715] (5/8) Epoch 2, batch 15450, loss[loss=0.1657, simple_loss=0.2334, pruned_loss=0.04902, over 4882.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2393, pruned_loss=0.05358, over 971658.36 frames.], batch size: 16, lr: 6.87e-04
2022-05-04 06:40:52,377 INFO [train.py:715] (5/8) Epoch 2, batch 15500, loss[loss=0.1546, simple_loss=0.2254, pruned_loss=0.04187, over 4883.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2388, pruned_loss=0.05282, over 971535.05 frames.], batch size: 22, lr: 6.87e-04
2022-05-04 06:41:32,624 INFO [train.py:715] (5/8) Epoch 2, batch 15550, loss[loss=0.1458, simple_loss=0.2171, pruned_loss=0.03725, over 4913.00 frames.], tot_loss[loss=0.173, simple_loss=0.2394, pruned_loss=0.05328, over 971937.70 frames.], batch size: 18, lr: 6.87e-04
2022-05-04 06:42:12,564 INFO [train.py:715] (5/8) Epoch 2, batch 15600, loss[loss=0.2078, simple_loss=0.269, pruned_loss=0.07327, over 4740.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2387, pruned_loss=0.05273, over 971901.96 frames.], batch size: 16, lr: 6.87e-04
2022-05-04 06:42:52,376 INFO [train.py:715] (5/8) Epoch 2, batch 15650, loss[loss=0.171, simple_loss=0.239, pruned_loss=0.05154, over 4833.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2384, pruned_loss=0.05259, over 972943.39 frames.], batch size: 15, lr: 6.86e-04
2022-05-04 06:43:33,100 INFO [train.py:715] (5/8) Epoch 2, batch 15700, loss[loss=0.193, simple_loss=0.273, pruned_loss=0.05648, over 4752.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2383, pruned_loss=0.0525, over 971919.94 frames.], batch size: 19, lr: 6.86e-04
2022-05-04 06:44:13,631 INFO [train.py:715] (5/8) Epoch 2, batch 15750, loss[loss=0.1852, simple_loss=0.2499, pruned_loss=0.06024, over 4926.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2386, pruned_loss=0.05239, over 971459.22 frames.], batch size: 23, lr: 6.86e-04
2022-05-04 06:44:52,975 INFO [train.py:715] (5/8) Epoch 2, batch 15800, loss[loss=0.1642, simple_loss=0.2358, pruned_loss=0.04628, over 4811.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2381, pruned_loss=0.0522, over 971920.97 frames.], batch size: 26, lr: 6.86e-04
2022-05-04 06:45:33,633 INFO [train.py:715] (5/8) Epoch 2, batch 15850, loss[loss=0.1735, simple_loss=0.233, pruned_loss=0.057, over 4940.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2386, pruned_loss=0.05281, over 972369.02 frames.], batch size: 23, lr: 6.86e-04
2022-05-04 06:46:14,114 INFO [train.py:715] (5/8) Epoch 2, batch 15900, loss[loss=0.1782, simple_loss=0.2424, pruned_loss=0.05698, over 4872.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2389, pruned_loss=0.05281, over 973000.78 frames.], batch size: 22, lr: 6.85e-04
2022-05-04 06:46:53,883 INFO [train.py:715] (5/8) Epoch 2, batch 15950, loss[loss=0.22, simple_loss=0.2746, pruned_loss=0.08271, over 4967.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05288, over 973010.49 frames.], batch size: 24, lr: 6.85e-04
2022-05-04 06:47:34,111 INFO [train.py:715] (5/8) Epoch 2, batch 16000, loss[loss=0.205, simple_loss=0.2696, pruned_loss=0.07023, over 4942.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2378, pruned_loss=0.05241, over 972496.96 frames.], batch size: 21, lr: 6.85e-04
2022-05-04 06:48:14,443 INFO [train.py:715] (5/8) Epoch 2, batch 16050, loss[loss=0.18, simple_loss=0.241, pruned_loss=0.05955, over 4950.00 frames.], tot_loss[loss=0.1716, simple_loss=0.238, pruned_loss=0.0526, over 972413.33 frames.], batch size: 21, lr: 6.85e-04
2022-05-04 06:48:54,892 INFO [train.py:715] (5/8) Epoch 2, batch 16100, loss[loss=0.1769, simple_loss=0.2403, pruned_loss=0.05682, over 4859.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2375, pruned_loss=0.05255, over 971918.79 frames.], batch size: 32, lr: 6.85e-04
2022-05-04 06:49:34,156 INFO [train.py:715] (5/8) Epoch 2, batch 16150, loss[loss=0.1572, simple_loss=0.2184, pruned_loss=0.04803, over 4904.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2374, pruned_loss=0.05279, over 972129.53 frames.], batch size: 18, lr: 6.84e-04
2022-05-04 06:50:14,547 INFO [train.py:715] (5/8) Epoch 2, batch 16200, loss[loss=0.1674, simple_loss=0.2389, pruned_loss=0.04794, over 4696.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2386, pruned_loss=0.05316, over 971515.41 frames.], batch size: 15, lr: 6.84e-04
2022-05-04 06:50:54,953 INFO [train.py:715] (5/8) Epoch 2, batch 16250, loss[loss=0.143, simple_loss=0.2055, pruned_loss=0.04022, over 4972.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2387, pruned_loss=0.05321, over 972102.89 frames.], batch size: 14, lr: 6.84e-04
2022-05-04 06:51:34,798 INFO [train.py:715] (5/8) Epoch 2, batch 16300, loss[loss=0.1368, simple_loss=0.2049, pruned_loss=0.03438, over 4754.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2385, pruned_loss=0.05341, over 971261.31 frames.], batch size: 16, lr: 6.84e-04
2022-05-04 06:52:14,670 INFO [train.py:715] (5/8) Epoch 2, batch 16350, loss[loss=0.1886, simple_loss=0.244, pruned_loss=0.06662, over 4946.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2387, pruned_loss=0.05324, over 971178.70 frames.], batch size: 29, lr: 6.84e-04
2022-05-04 06:52:55,176 INFO [train.py:715] (5/8) Epoch 2, batch 16400, loss[loss=0.1966, simple_loss=0.266, pruned_loss=0.06363, over 4803.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2386, pruned_loss=0.05343, over 971266.08 frames.], batch size: 21, lr: 6.83e-04
2022-05-04 06:53:35,569 INFO [train.py:715] (5/8) Epoch 2, batch 16450, loss[loss=0.1649, simple_loss=0.2313, pruned_loss=0.0492, over 4949.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2389, pruned_loss=0.05335, over 971424.18 frames.], batch size: 21, lr: 6.83e-04
2022-05-04 06:54:15,148 INFO [train.py:715] (5/8) Epoch 2, batch 16500, loss[loss=0.1837, simple_loss=0.2397, pruned_loss=0.06383, over 4791.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05292, over 971936.45 frames.], batch size: 14, lr: 6.83e-04
2022-05-04 06:54:56,130 INFO [train.py:715] (5/8) Epoch 2, batch 16550, loss[loss=0.169, simple_loss=0.2408, pruned_loss=0.04855, over 4866.00 frames.], tot_loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.05328, over 971878.39 frames.], batch size: 30, lr: 6.83e-04
2022-05-04 06:55:36,864 INFO [train.py:715] (5/8) Epoch 2, batch 16600, loss[loss=0.2032, simple_loss=0.2647, pruned_loss=0.07079, over 4815.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2391, pruned_loss=0.05358, over 972103.80 frames.], batch size: 25, lr: 6.83e-04
2022-05-04 06:56:16,717 INFO [train.py:715] (5/8) Epoch 2, batch 16650, loss[loss=0.2047, simple_loss=0.2602, pruned_loss=0.07461, over 4912.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2392, pruned_loss=0.05333, over 971262.17 frames.], batch size: 39, lr: 6.82e-04
2022-05-04 06:56:57,162 INFO [train.py:715] (5/8) Epoch 2, batch 16700, loss[loss=0.1969, simple_loss=0.2584, pruned_loss=0.06776, over 4889.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2389, pruned_loss=0.05306, over 971741.66 frames.], batch size: 16, lr: 6.82e-04
2022-05-04 06:57:37,918 INFO [train.py:715] (5/8) Epoch 2, batch 16750, loss[loss=0.1924, simple_loss=0.2531, pruned_loss=0.06581, over 4854.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2381, pruned_loss=0.05272, over 972282.10 frames.], batch size: 20, lr: 6.82e-04
2022-05-04 06:58:18,636 INFO [train.py:715] (5/8) Epoch 2, batch 16800, loss[loss=0.1643, simple_loss=0.2226, pruned_loss=0.05303, over 4903.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05167, over 972595.36 frames.], batch size: 19, lr: 6.82e-04
2022-05-04 06:58:58,051 INFO [train.py:715] (5/8) Epoch 2, batch 16850, loss[loss=0.1438, simple_loss=0.2187, pruned_loss=0.03448, over 4837.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05111, over 972680.63 frames.], batch size: 26, lr: 6.82e-04
2022-05-04 06:59:39,318 INFO [train.py:715] (5/8) Epoch 2, batch 16900, loss[loss=0.1842, simple_loss=0.2394, pruned_loss=0.0645, over 4920.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2374, pruned_loss=0.05198, over 972481.02 frames.], batch size: 18, lr: 6.81e-04
2022-05-04 07:00:20,139 INFO [train.py:715] (5/8) Epoch 2, batch 16950, loss[loss=0.1557, simple_loss=0.2187, pruned_loss=0.04635, over 4812.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2375, pruned_loss=0.05238, over 972980.66 frames.], batch size: 26, lr: 6.81e-04
2022-05-04 07:00:59,944 INFO [train.py:715] (5/8) Epoch 2, batch 17000, loss[loss=0.1491, simple_loss=0.2197, pruned_loss=0.03925, over 4926.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2382, pruned_loss=0.05307, over 972353.93 frames.], batch size: 21, lr: 6.81e-04
2022-05-04 07:01:40,376 INFO [train.py:715] (5/8) Epoch 2, batch 17050, loss[loss=0.1632, simple_loss=0.2214, pruned_loss=0.05251, over 4780.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2377, pruned_loss=0.05284, over 972013.80 frames.], batch size: 17, lr: 6.81e-04
2022-05-04 07:02:20,965 INFO [train.py:715] (5/8) Epoch 2, batch 17100, loss[loss=0.1293, simple_loss=0.2, pruned_loss=0.02926, over 4784.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2376, pruned_loss=0.05295, over 971820.72 frames.], batch size: 12, lr: 6.81e-04
2022-05-04 07:03:01,197 INFO [train.py:715] (5/8) Epoch 2, batch 17150, loss[loss=0.1936, simple_loss=0.2706, pruned_loss=0.05833, over 4748.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2381, pruned_loss=0.05337, over 971283.89 frames.], batch size: 16, lr: 6.81e-04
2022-05-04 07:03:40,485 INFO [train.py:715] (5/8) Epoch 2, batch 17200, loss[loss=0.1886, simple_loss=0.2416, pruned_loss=0.06781, over 4780.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2381, pruned_loss=0.05352, over 972223.71 frames.], batch size: 18, lr: 6.80e-04
2022-05-04 07:04:20,887 INFO [train.py:715] (5/8) Epoch 2, batch 17250, loss[loss=0.1866, simple_loss=0.2418, pruned_loss=0.06571, over 4811.00 frames.], tot_loss[loss=0.173, simple_loss=0.2385, pruned_loss=0.05376, over 971815.34 frames.], batch size: 27, lr: 6.80e-04
2022-05-04 07:05:01,349 INFO [train.py:715] (5/8) Epoch 2, batch 17300, loss[loss=0.2049, simple_loss=0.2727, pruned_loss=0.06848, over 4991.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2384, pruned_loss=0.05345, over 972253.18 frames.], batch size: 14, lr: 6.80e-04
2022-05-04 07:05:40,925 INFO [train.py:715] (5/8) Epoch 2, batch 17350, loss[loss=0.2046, simple_loss=0.2531, pruned_loss=0.07803, over 4994.00 frames.], tot_loss[loss=0.171, simple_loss=0.2372, pruned_loss=0.05235, over 971711.30 frames.], batch size: 14, lr: 6.80e-04
2022-05-04 07:06:20,384 INFO [train.py:715] (5/8) Epoch 2, batch 17400, loss[loss=0.2075, simple_loss=0.2694, pruned_loss=0.07281, over 4899.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05277, over 972529.17 frames.], batch size: 19, lr: 6.80e-04
2022-05-04 07:07:00,340 INFO [train.py:715] (5/8) Epoch 2, batch 17450, loss[loss=0.1655, simple_loss=0.2398, pruned_loss=0.04559, over 4817.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2389, pruned_loss=0.05303, over 972728.06 frames.], batch size: 26, lr: 6.79e-04
2022-05-04 07:07:40,090 INFO [train.py:715] (5/8) Epoch 2, batch 17500, loss[loss=0.1911, simple_loss=0.249, pruned_loss=0.06659, over 4838.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2387, pruned_loss=0.05315, over 972357.86 frames.], batch size: 30, lr: 6.79e-04
2022-05-04 07:08:18,849 INFO [train.py:715] (5/8) Epoch 2, batch 17550, loss[loss=0.177, simple_loss=0.2218, pruned_loss=0.06607, over 4841.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2383, pruned_loss=0.05265, over 971895.89 frames.], batch size: 13, lr: 6.79e-04
2022-05-04 07:08:58,970 INFO [train.py:715] (5/8) Epoch 2, batch 17600, loss[loss=0.1841, simple_loss=0.2551, pruned_loss=0.0565, over 4738.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2386, pruned_loss=0.05255, over 971563.03 frames.], batch size: 16, lr: 6.79e-04
2022-05-04 07:09:38,387 INFO [train.py:715] (5/8) Epoch 2, batch 17650, loss[loss=0.2179, simple_loss=0.2676, pruned_loss=0.08412, over 4870.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2372, pruned_loss=0.05175, over 971117.41 frames.], batch size: 32, lr: 6.79e-04
2022-05-04 07:10:17,891 INFO [train.py:715] (5/8) Epoch 2, batch 17700, loss[loss=0.1419, simple_loss=0.2078, pruned_loss=0.03798, over 4784.00 frames.], tot_loss[loss=0.17, simple_loss=0.2369, pruned_loss=0.0515, over 971624.63 frames.], batch size: 12, lr: 6.78e-04
2022-05-04 07:10:57,825 INFO [train.py:715] (5/8) Epoch 2, batch 17750, loss[loss=0.151, simple_loss=0.2091, pruned_loss=0.04648, over 4780.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2379, pruned_loss=0.05235, over 972135.32 frames.], batch size: 18, lr: 6.78e-04
2022-05-04 07:11:37,688 INFO [train.py:715] (5/8) Epoch 2, batch 17800, loss[loss=0.1821, simple_loss=0.2479, pruned_loss=0.05821, over 4774.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2371, pruned_loss=0.05169, over 972579.64 frames.], batch size: 18, lr: 6.78e-04
2022-05-04 07:12:17,974 INFO [train.py:715] (5/8) Epoch 2, batch 17850, loss[loss=0.2148, simple_loss=0.2679, pruned_loss=0.08088, over 4839.00 frames.], tot_loss[loss=0.17, simple_loss=0.2368, pruned_loss=0.05157, over 972748.50 frames.], batch size: 15, lr: 6.78e-04
2022-05-04 07:12:56,814 INFO [train.py:715] (5/8) Epoch 2, batch 17900, loss[loss=0.2178, simple_loss=0.2774, pruned_loss=0.07909, over 4858.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2364, pruned_loss=0.05113, over 971989.41 frames.], batch size: 32, lr: 6.78e-04
2022-05-04 07:13:36,739 INFO [train.py:715] (5/8) Epoch 2, batch 17950, loss[loss=0.1638, simple_loss=0.2232, pruned_loss=0.05217, over 4852.00 frames.], tot_loss[loss=0.1704, simple_loss=0.237, pruned_loss=0.05187, over 973294.64 frames.], batch size: 32, lr: 6.77e-04
2022-05-04 07:14:16,912 INFO [train.py:715] (5/8) Epoch 2, batch 18000, loss[loss=0.1743, simple_loss=0.2485, pruned_loss=0.05004, over 4913.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2383, pruned_loss=0.05252, over 972439.40 frames.], batch size: 19, lr: 6.77e-04
2022-05-04 07:14:16,913 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 07:14:26,628 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1173, simple_loss=0.2039, pruned_loss=0.01538, over 914524.00 frames.
2022-05-04 07:15:07,354 INFO [train.py:715] (5/8) Epoch 2, batch 18050, loss[loss=0.1687, simple_loss=0.2393, pruned_loss=0.04904, over 4906.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.05213, over 972624.68 frames.], batch size: 19, lr: 6.77e-04
2022-05-04 07:15:46,536 INFO [train.py:715] (5/8) Epoch 2, batch 18100, loss[loss=0.1627, simple_loss=0.2297, pruned_loss=0.04786, over 4887.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2386, pruned_loss=0.05308, over 972854.81 frames.], batch size: 22, lr: 6.77e-04
2022-05-04 07:16:27,420 INFO [train.py:715] (5/8) Epoch 2, batch 18150, loss[loss=0.1829, simple_loss=0.2456, pruned_loss=0.06014, over 4937.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2385, pruned_loss=0.05268, over 972944.92 frames.], batch size: 23, lr: 6.77e-04
2022-05-04 07:17:08,371 INFO [train.py:715] (5/8) Epoch 2, batch 18200, loss[loss=0.1449, simple_loss=0.2116, pruned_loss=0.03913, over 4852.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2375, pruned_loss=0.05172, over 974085.41 frames.], batch size: 20, lr: 6.76e-04
2022-05-04 07:17:49,831 INFO [train.py:715] (5/8) Epoch 2, batch 18250, loss[loss=0.182, simple_loss=0.2493, pruned_loss=0.05732, over 4940.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2385, pruned_loss=0.05236, over 973761.66 frames.], batch size: 29, lr: 6.76e-04
2022-05-04 07:18:30,275 INFO [train.py:715] (5/8) Epoch 2, batch 18300, loss[loss=0.1522, simple_loss=0.2132, pruned_loss=0.04559, over 4881.00 frames.], tot_loss[loss=0.171, simple_loss=0.238, pruned_loss=0.05196, over 973388.37 frames.], batch size: 22, lr: 6.76e-04
2022-05-04 07:19:12,137 INFO [train.py:715] (5/8) Epoch 2, batch 18350, loss[loss=0.2029, simple_loss=0.2514, pruned_loss=0.07718, over 4964.00 frames.], tot_loss[loss=0.1711, simple_loss=0.238, pruned_loss=0.05211, over 973873.32 frames.], batch size: 35, lr: 6.76e-04
2022-05-04 07:19:56,499 INFO [train.py:715] (5/8) Epoch 2, batch 18400, loss[loss=0.1787, simple_loss=0.2441, pruned_loss=0.05669, over 4910.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2385, pruned_loss=0.05261, over 974423.24 frames.], batch size: 18, lr: 6.76e-04
2022-05-04 07:20:36,594 INFO [train.py:715] (5/8) Epoch 2, batch 18450, loss[loss=0.1699, simple_loss=0.2448, pruned_loss=0.04748, over 4857.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2391, pruned_loss=0.05319, over 973550.26 frames.], batch size: 20, lr: 6.75e-04
2022-05-04 07:21:18,110 INFO [train.py:715] (5/8) Epoch 2, batch 18500, loss[loss=0.1926, simple_loss=0.2441, pruned_loss=0.07061, over 4904.00 frames.], tot_loss[loss=0.1723, simple_loss=0.239, pruned_loss=0.05279, over 973126.95 frames.], batch size: 19, lr: 6.75e-04
2022-05-04 07:21:59,810 INFO [train.py:715] (5/8) Epoch 2, batch 18550, loss[loss=0.1336, simple_loss=0.2102, pruned_loss=0.02848, over 4783.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2392, pruned_loss=0.0527, over 973059.36 frames.], batch size: 17, lr: 6.75e-04
2022-05-04 07:22:41,510 INFO [train.py:715] (5/8) Epoch 2, batch 18600, loss[loss=0.1879, simple_loss=0.2473, pruned_loss=0.06422, over 4988.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2385, pruned_loss=0.0526, over 972239.69 frames.], batch size: 31, lr: 6.75e-04
2022-05-04 07:23:21,829 INFO [train.py:715] (5/8) Epoch 2, batch 18650, loss[loss=0.1806, simple_loss=0.2391, pruned_loss=0.06101, over 4876.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2394, pruned_loss=0.05341, over 972769.51 frames.], batch size: 16, lr: 6.75e-04
2022-05-04 07:24:03,485 INFO [train.py:715] (5/8) Epoch 2, batch 18700, loss[loss=0.1657, simple_loss=0.2318, pruned_loss=0.04977, over 4794.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2397, pruned_loss=0.05373, over 972502.48 frames.], batch size: 24, lr: 6.75e-04
2022-05-04 07:24:45,167 INFO [train.py:715] (5/8) Epoch 2, batch 18750, loss[loss=0.1887, simple_loss=0.263, pruned_loss=0.05715, over 4769.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2398, pruned_loss=0.0536, over 971898.12 frames.], batch size: 19, lr: 6.74e-04
2022-05-04 07:25:25,717 INFO [train.py:715] (5/8) Epoch 2, batch 18800, loss[loss=0.1944, simple_loss=0.2565, pruned_loss=0.0661, over 4796.00 frames.], tot_loss[loss=0.1727, simple_loss=0.239, pruned_loss=0.05322, over 971669.63 frames.], batch size: 21, lr: 6.74e-04
2022-05-04 07:26:06,668 INFO [train.py:715] (5/8) Epoch 2, batch 18850, loss[loss=0.1493, simple_loss=0.2217, pruned_loss=0.03845, over 4795.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2385, pruned_loss=0.05262, over 971234.21 frames.], batch size: 17, lr: 6.74e-04
2022-05-04 07:26:48,079 INFO [train.py:715] (5/8) Epoch 2, batch 18900, loss[loss=0.1405, simple_loss=0.2065, pruned_loss=0.03726, over 4812.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2386, pruned_loss=0.05304, over 970999.42 frames.], batch size: 12, lr: 6.74e-04
2022-05-04 07:27:29,071 INFO [train.py:715] (5/8) Epoch 2, batch 18950, loss[loss=0.1979, simple_loss=0.2599, pruned_loss=0.06795, over 4836.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2381, pruned_loss=0.05228, over 971888.39 frames.], batch size: 26, lr: 6.74e-04
2022-05-04 07:28:09,465 INFO [train.py:715] (5/8) Epoch 2, batch 19000, loss[loss=0.1571, simple_loss=0.231, pruned_loss=0.04158, over 4835.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2387, pruned_loss=0.05221, over 972864.85 frames.], batch size: 26, lr: 6.73e-04
2022-05-04 07:28:50,995 INFO [train.py:715] (5/8) Epoch 2, batch 19050, loss[loss=0.1678, simple_loss=0.2284, pruned_loss=0.05365, over 4986.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2372, pruned_loss=0.05133, over 973158.69 frames.], batch size: 25, lr: 6.73e-04
2022-05-04 07:29:32,577 INFO [train.py:715] (5/8) Epoch 2, batch 19100, loss[loss=0.1567, simple_loss=0.2419, pruned_loss=0.03578, over 4964.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2373, pruned_loss=0.05197, over 973369.86 frames.], batch size: 24, lr: 6.73e-04
2022-05-04 07:30:13,195 INFO [train.py:715] (5/8) Epoch 2, batch 19150, loss[loss=0.2021, simple_loss=0.2629, pruned_loss=0.07068, over 4917.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2375, pruned_loss=0.05232, over 973209.87 frames.], batch size: 39, lr: 6.73e-04
2022-05-04 07:30:53,904 INFO [train.py:715] (5/8) Epoch 2, batch 19200, loss[loss=0.1825, simple_loss=0.2538, pruned_loss=0.05558, over 4944.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2378, pruned_loss=0.0522, over 973072.34 frames.], batch size: 21, lr: 6.73e-04
2022-05-04 07:31:35,009 INFO [train.py:715] (5/8) Epoch 2, batch 19250, loss[loss=0.1668, simple_loss=0.243, pruned_loss=0.04525, over 4963.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2367, pruned_loss=0.05144, over 972721.76 frames.], batch size: 24, lr: 6.72e-04
2022-05-04 07:32:15,454 INFO [train.py:715] (5/8) Epoch 2, batch 19300, loss[loss=0.1447, simple_loss=0.2136, pruned_loss=0.03785, over 4756.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2371, pruned_loss=0.05181, over 972539.72 frames.], batch size: 14, lr: 6.72e-04
2022-05-04 07:32:55,609 INFO [train.py:715] (5/8) Epoch 2, batch 19350, loss[loss=0.2138, simple_loss=0.2617, pruned_loss=0.08298, over 4976.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2368, pruned_loss=0.05208, over 972403.62 frames.], batch size: 33, lr: 6.72e-04
2022-05-04 07:33:36,557 INFO [train.py:715] (5/8) Epoch 2, batch 19400, loss[loss=0.1781, simple_loss=0.2397, pruned_loss=0.05823, over 4814.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2379, pruned_loss=0.05249, over 971546.22 frames.], batch size: 13, lr: 6.72e-04
2022-05-04 07:34:18,478 INFO [train.py:715] (5/8) Epoch 2, batch 19450, loss[loss=0.2192, simple_loss=0.2779, pruned_loss=0.08028, over 4759.00 frames.], tot_loss[loss=0.1716, simple_loss=0.238, pruned_loss=0.05265, over 971675.81 frames.], batch size: 17, lr: 6.72e-04
2022-05-04 07:34:58,696 INFO [train.py:715] (5/8) Epoch 2, batch 19500, loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04701, over 4741.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2376, pruned_loss=0.05239, over 972199.28 frames.], batch size: 12, lr: 6.72e-04
2022-05-04 07:35:38,980 INFO [train.py:715] (5/8) Epoch 2, batch 19550, loss[loss=0.1815, simple_loss=0.2474, pruned_loss=0.05779, over 4764.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2375, pruned_loss=0.05248, over 972190.70 frames.], batch size: 19, lr: 6.71e-04
2022-05-04 07:36:20,455 INFO [train.py:715] (5/8) Epoch 2, batch 19600, loss[loss=0.1464, simple_loss=0.2174, pruned_loss=0.03773, over 4978.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2369, pruned_loss=0.05238, over 972068.00 frames.], batch size: 15, lr: 6.71e-04
2022-05-04 07:37:01,109 INFO [train.py:715] (5/8) Epoch 2, batch 19650, loss[loss=0.1827, simple_loss=0.2367, pruned_loss=0.0643, over 4837.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2362, pruned_loss=0.05216, over 971811.25 frames.], batch size: 30, lr: 6.71e-04
2022-05-04 07:37:40,948 INFO [train.py:715] (5/8) Epoch 2, batch 19700, loss[loss=0.163, simple_loss=0.2375, pruned_loss=0.04421, over 4744.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2366, pruned_loss=0.05242, over 971141.29 frames.], batch size: 16, lr: 6.71e-04
2022-05-04 07:38:21,835 INFO [train.py:715] (5/8) Epoch 2, batch 19750, loss[loss=0.1844, simple_loss=0.2476, pruned_loss=0.06065, over 4978.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2369, pruned_loss=0.05228, over 971533.79 frames.], batch size: 25, lr: 6.71e-04
2022-05-04 07:39:02,976 INFO [train.py:715] (5/8) Epoch 2, batch 19800, loss[loss=0.151, simple_loss=0.2267, pruned_loss=0.03767, over 4870.00 frames.], tot_loss[loss=0.171, simple_loss=0.2378, pruned_loss=0.05208, over 971180.20 frames.], batch size: 22, lr: 6.70e-04
2022-05-04 07:39:42,766 INFO [train.py:715] (5/8) Epoch 2, batch 19850, loss[loss=0.1753, simple_loss=0.2492, pruned_loss=0.05067, over 4860.00 frames.], tot_loss[loss=0.171, simple_loss=0.2379, pruned_loss=0.05206, over 971909.92 frames.], batch size: 20, lr: 6.70e-04
2022-05-04 07:40:23,481 INFO [train.py:715] (5/8) Epoch 2, batch 19900, loss[loss=0.203, simple_loss=0.2627, pruned_loss=0.07166, over 4818.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2379, pruned_loss=0.05218, over 972349.41 frames.], batch size: 15, lr: 6.70e-04
2022-05-04 07:41:04,459 INFO [train.py:715] (5/8) Epoch 2, batch 19950, loss[loss=0.1251, simple_loss=0.196, pruned_loss=0.02712, over 4963.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2371, pruned_loss=0.05162, over 972398.59 frames.], batch size: 15, lr: 6.70e-04
2022-05-04 07:41:44,805 INFO [train.py:715] (5/8) Epoch 2, batch 20000, loss[loss=0.1497, simple_loss=0.2125, pruned_loss=0.04342, over 4967.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2374, pruned_loss=0.05174, over 972910.22 frames.], batch size: 15, lr: 6.70e-04
2022-05-04 07:42:25,548 INFO [train.py:715] (5/8) Epoch 2, batch 20050, loss[loss=0.1531, simple_loss=0.2149, pruned_loss=0.04559, over 4983.00 frames.], tot_loss[loss=0.17, simple_loss=0.2367, pruned_loss=0.05169, over 973746.05 frames.], batch size: 14, lr: 6.69e-04
2022-05-04 07:43:06,875 INFO [train.py:715] (5/8) Epoch 2, batch 20100, loss[loss=0.2138, simple_loss=0.2751, pruned_loss=0.07623, over 4989.00 frames.], tot_loss[loss=0.17, simple_loss=0.2373, pruned_loss=0.05135, over 973193.29 frames.], batch size: 31, lr: 6.69e-04
2022-05-04 07:43:48,579 INFO [train.py:715] (5/8) Epoch 2, batch 20150, loss[loss=0.1799, simple_loss=0.2414, pruned_loss=0.05916, over 4873.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2377, pruned_loss=0.05162, over 973729.37 frames.], batch size: 16, lr: 6.69e-04
2022-05-04 07:44:28,871 INFO [train.py:715] (5/8) Epoch 2, batch 20200, loss[loss=0.1369, simple_loss=0.207, pruned_loss=0.03342, over 4770.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2376, pruned_loss=0.05161, over 974168.70 frames.], batch size: 17, lr: 6.69e-04
2022-05-04 07:45:10,315 INFO [train.py:715] (5/8) Epoch 2, batch 20250, loss[loss=0.1643, simple_loss=0.2357, pruned_loss=0.04647, over 4735.00 frames.], tot_loss[loss=0.17, simple_loss=0.2374, pruned_loss=0.05133, over 974281.79 frames.], batch size: 16, lr: 6.69e-04
2022-05-04 07:45:52,272 INFO [train.py:715] (5/8) Epoch 2, batch 20300, loss[loss=0.1434, simple_loss=0.214, pruned_loss=0.03645, over 4830.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2371, pruned_loss=0.05115, over 974139.33 frames.], batch size: 13, lr: 6.69e-04
2022-05-04 07:46:33,088 INFO [train.py:715] (5/8) Epoch 2, batch 20350, loss[loss=0.2096, simple_loss=0.2677, pruned_loss=0.07578, over 4863.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2367, pruned_loss=0.0514, over 973823.03 frames.], batch size: 38, lr: 6.68e-04
2022-05-04 07:47:14,061 INFO [train.py:715] (5/8) Epoch 2, batch 20400, loss[loss=0.1431, simple_loss=0.2088, pruned_loss=0.03868, over 4829.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2373, pruned_loss=0.05184, over 973796.80 frames.], batch size: 13, lr: 6.68e-04
2022-05-04 07:47:56,148 INFO [train.py:715] (5/8) Epoch 2, batch 20450, loss[loss=0.1668, simple_loss=0.2354, pruned_loss=0.04904, over 4791.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05226, over 973466.58 frames.], batch size: 18, lr: 6.68e-04
2022-05-04 07:48:37,718 INFO [train.py:715] (5/8) Epoch 2, batch 20500, loss[loss=0.2056, simple_loss=0.2632, pruned_loss=0.07404, over 4931.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2383, pruned_loss=0.05239, over 973302.19 frames.], batch size: 18, lr: 6.68e-04
2022-05-04 07:49:18,511 INFO [train.py:715] (5/8) Epoch 2, batch 20550, loss[loss=0.1866, simple_loss=0.2537, pruned_loss=0.05969, over 4933.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2376, pruned_loss=0.05186, over 973298.32 frames.], batch size: 29, lr: 6.68e-04
2022-05-04 07:49:59,710 INFO [train.py:715] (5/8) Epoch 2, batch 20600, loss[loss=0.1834, simple_loss=0.246, pruned_loss=0.06045, over 4904.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2376, pruned_loss=0.05174, over 972925.33 frames.], batch size: 22, lr: 6.67e-04
2022-05-04 07:50:41,268 INFO [train.py:715] (5/8) Epoch 2, batch 20650, loss[loss=0.1915, simple_loss=0.2419, pruned_loss=0.07057, over 4982.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2375, pruned_loss=0.0519, over 973071.08 frames.], batch size: 31, lr: 6.67e-04
2022-05-04 07:51:22,505 INFO [train.py:715] (5/8) Epoch 2, batch 20700, loss[loss=0.1423, simple_loss=0.2227, pruned_loss=0.03097, over 4985.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05189, over 973075.11 frames.], batch size: 28, lr: 6.67e-04
2022-05-04 07:52:03,036 INFO [train.py:715] (5/8) Epoch 2, batch 20750, loss[loss=0.1469, simple_loss=0.2144, pruned_loss=0.0397, over 4833.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2376, pruned_loss=0.05175, over 972544.52 frames.], batch size: 32, lr: 6.67e-04
2022-05-04 07:52:44,281 INFO [train.py:715] (5/8) Epoch 2, batch 20800, loss[loss=0.2232, simple_loss=0.2848, pruned_loss=0.08084, over 4776.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2373, pruned_loss=0.05194, over 971743.66 frames.], batch size: 18, lr: 6.67e-04
2022-05-04 07:53:25,481 INFO [train.py:715] (5/8) Epoch 2, batch 20850, loss[loss=0.156, simple_loss=0.2175, pruned_loss=0.04723, over 4837.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2361, pruned_loss=0.05138, over 971131.17 frames.], batch size: 30, lr: 6.66e-04
2022-05-04 07:54:06,138 INFO [train.py:715] (5/8) Epoch 2, batch 20900, loss[loss=0.1759, simple_loss=0.2268, pruned_loss=0.06246, over 4863.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05168, over 971766.17 frames.], batch size: 16, lr: 6.66e-04
2022-05-04 07:54:47,191 INFO [train.py:715] (5/8) Epoch 2, batch 20950, loss[loss=0.1488, simple_loss=0.2075, pruned_loss=0.0451, over 4829.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05194, over 971080.23 frames.], batch size: 13, lr: 6.66e-04
2022-05-04 07:55:28,388 INFO [train.py:715] (5/8) Epoch 2, batch 21000, loss[loss=0.1436, simple_loss=0.2076, pruned_loss=0.03979, over 4805.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2364, pruned_loss=0.05155, over 970630.09 frames.], batch size: 14, lr: 6.66e-04
2022-05-04 07:55:28,388 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 07:55:39,044 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1174, simple_loss=0.2036, pruned_loss=0.01562, over 914524.00 frames.
2022-05-04 07:56:20,518 INFO [train.py:715] (5/8) Epoch 2, batch 21050, loss[loss=0.1679, simple_loss=0.2261, pruned_loss=0.05482, over 4867.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2356, pruned_loss=0.05098, over 970528.09 frames.], batch size: 32, lr: 6.66e-04
2022-05-04 07:57:00,990 INFO [train.py:715] (5/8) Epoch 2, batch 21100, loss[loss=0.1453, simple_loss=0.2102, pruned_loss=0.0402, over 4960.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2364, pruned_loss=0.05122, over 970700.82 frames.], batch size: 28, lr: 6.66e-04
2022-05-04 07:57:41,495 INFO [train.py:715] (5/8) Epoch 2, batch 21150, loss[loss=0.1793, simple_loss=0.2449, pruned_loss=0.05682, over 4798.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05174, over 970563.62 frames.], batch size: 21, lr: 6.65e-04
2022-05-04 07:58:22,039 INFO [train.py:715] (5/8) Epoch 2, batch 21200, loss[loss=0.1736, simple_loss=0.2381, pruned_loss=0.05458, over 4900.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2366, pruned_loss=0.05138, over 971359.28 frames.], batch size: 19, lr: 6.65e-04
2022-05-04 07:59:02,133 INFO [train.py:715] (5/8) Epoch 2, batch 21250, loss[loss=0.1668, simple_loss=0.2346, pruned_loss=0.04949, over 4814.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2366, pruned_loss=0.05078, over 970656.53 frames.], batch size: 21, lr: 6.65e-04
2022-05-04 07:59:42,845 INFO [train.py:715] (5/8) Epoch 2, batch 21300, loss[loss=0.1556, simple_loss=0.2296, pruned_loss=0.04079, over 4695.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2368, pruned_loss=0.05093, over 970913.05 frames.], batch size: 15, lr: 6.65e-04
2022-05-04 08:00:23,556 INFO [train.py:715] (5/8) Epoch 2, batch 21350, loss[loss=0.139, simple_loss=0.2175, pruned_loss=0.03021, over 4870.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2368, pruned_loss=0.05085, over 971467.60 frames.], batch size: 20, lr: 6.65e-04
2022-05-04 08:01:04,863 INFO [train.py:715] (5/8) Epoch 2, batch 21400, loss[loss=0.1682, simple_loss=0.2345, pruned_loss=0.05096, over 4853.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2363, pruned_loss=0.05071, over 971584.33 frames.], batch size: 30, lr: 6.64e-04
2022-05-04 08:01:45,133 INFO [train.py:715] (5/8) Epoch 2, batch 21450, loss[loss=0.1536, simple_loss=0.2226, pruned_loss=0.04225, over 4733.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2368, pruned_loss=0.05109, over 972475.98 frames.], batch size: 12, lr: 6.64e-04
2022-05-04 08:02:26,069 INFO [train.py:715] (5/8) Epoch 2, batch 21500, loss[loss=0.1696, simple_loss=0.2359, pruned_loss=0.05168, over 4649.00 frames.], tot_loss[loss=0.169, simple_loss=0.2364, pruned_loss=0.05079, over 971787.59 frames.], batch size: 13, lr: 6.64e-04
2022-05-04 08:03:07,354 INFO [train.py:715] (5/8) Epoch 2, batch 21550, loss[loss=0.1776, simple_loss=0.2542, pruned_loss=0.05047, over 4781.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05188, over 971398.21 frames.], batch size: 14, lr: 6.64e-04
2022-05-04 08:03:47,341 INFO [train.py:715] (5/8) Epoch 2, batch 21600, loss[loss=0.1947, simple_loss=0.2432, pruned_loss=0.07315, over 4752.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05175, over 971150.73 frames.], batch size: 16, lr: 6.64e-04
2022-05-04 08:04:28,567 INFO [train.py:715] (5/8) Epoch 2, batch 21650, loss[loss=0.1813, simple_loss=0.2528, pruned_loss=0.0549, over 4759.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05112, over 971210.38 frames.], batch size: 19, lr: 6.64e-04
2022-05-04 08:05:10,112 INFO [train.py:715] (5/8) Epoch 2, batch 21700, loss[loss=0.1636, simple_loss=0.2195, pruned_loss=0.05381, over 4821.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2364, pruned_loss=0.0511, over 970558.74 frames.], batch size: 13, lr: 6.63e-04
2022-05-04 08:05:50,686 INFO [train.py:715] (5/8) Epoch 2, batch 21750, loss[loss=0.1446, simple_loss=0.2147, pruned_loss=0.03725, over 4927.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05113, over 969869.13 frames.], batch size: 18, lr: 6.63e-04
2022-05-04 08:06:31,759 INFO [train.py:715] (5/8) Epoch 2, batch 21800, loss[loss=0.1769, simple_loss=0.2375, pruned_loss=0.05814, over 4771.00 frames.], tot_loss[loss=0.1693, simple_loss=0.236, pruned_loss=0.05132, over 970188.48 frames.], batch size: 14, lr: 6.63e-04
2022-05-04 08:07:12,175 INFO [train.py:715] (5/8) Epoch 2, batch 21850, loss[loss=0.1848, simple_loss=0.251, pruned_loss=0.05933, over 4788.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2365, pruned_loss=0.05217, over 971386.01 frames.], batch size: 17, lr: 6.63e-04
2022-05-04 08:07:53,264 INFO [train.py:715] (5/8) Epoch 2, batch 21900, loss[loss=0.1664, simple_loss=0.2387, pruned_loss=0.04706, over 4810.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2359, pruned_loss=0.05176, over 971034.14 frames.], batch size: 12, lr: 6.63e-04
2022-05-04 08:08:33,956 INFO [train.py:715] (5/8) Epoch 2, batch 21950, loss[loss=0.2093, simple_loss=0.2564, pruned_loss=0.08117, over 4969.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2372, pruned_loss=0.05248, over 971091.81 frames.], batch size: 15, lr: 6.62e-04
2022-05-04 08:09:15,713 INFO [train.py:715] (5/8) Epoch 2, batch 22000, loss[loss=0.1487, simple_loss=0.2189, pruned_loss=0.03926, over 4760.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2364, pruned_loss=0.05162, over 972158.77 frames.], batch size: 19, lr: 6.62e-04
2022-05-04 08:09:57,818 INFO [train.py:715] (5/8) Epoch 2, batch 22050, loss[loss=0.175, simple_loss=0.2429, pruned_loss=0.0535, over 4832.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2364, pruned_loss=0.05071, over 972760.73 frames.], batch size: 30, lr: 6.62e-04
2022-05-04 08:10:38,628 INFO [train.py:715] (5/8) Epoch 2, batch 22100, loss[loss=0.1885, simple_loss=0.2561, pruned_loss=0.06041, over 4953.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2378, pruned_loss=0.05171, over 972875.02 frames.], batch size: 35, lr: 6.62e-04
2022-05-04 08:11:20,106 INFO [train.py:715] (5/8) Epoch 2, batch 22150, loss[loss=0.1979, simple_loss=0.2628, pruned_loss=0.06656, over 4879.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2377, pruned_loss=0.05194, over 973210.46 frames.], batch size: 16, lr: 6.62e-04
2022-05-04 08:12:01,868 INFO [train.py:715] (5/8) Epoch 2, batch 22200, loss[loss=0.1296, simple_loss=0.1932, pruned_loss=0.03302, over 4786.00 frames.], tot_loss[loss=0.1698, simple_loss=0.237, pruned_loss=0.05127, over 973905.97 frames.], batch size: 12, lr: 6.62e-04
2022-05-04 08:12:43,329 INFO [train.py:715] (5/8) Epoch 2, batch 22250, loss[loss=0.2, simple_loss=0.2582, pruned_loss=0.07091, over 4896.00 frames.], tot_loss[loss=0.17, simple_loss=0.2375, pruned_loss=0.05123, over 973075.09 frames.], batch size: 17, lr: 6.61e-04
2022-05-04 08:13:24,125 INFO [train.py:715] (5/8) Epoch 2, batch 22300, loss[loss=0.193, simple_loss=0.2679, pruned_loss=0.05906, over 4980.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2383, pruned_loss=0.05173, over 972844.54 frames.], batch size: 39, lr: 6.61e-04
2022-05-04 08:14:05,209 INFO [train.py:715] (5/8) Epoch 2, batch 22350, loss[loss=0.1415, simple_loss=0.2186, pruned_loss=0.03214, over 4935.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2377, pruned_loss=0.05164, over 972867.38 frames.], batch size: 21, lr: 6.61e-04
2022-05-04 08:14:46,092 INFO [train.py:715] (5/8) Epoch 2, batch 22400, loss[loss=0.1536, simple_loss=0.2324, pruned_loss=0.03746, over 4748.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2369, pruned_loss=0.05168, over 972540.94 frames.], batch size: 16, lr: 6.61e-04
2022-05-04 08:15:26,445 INFO [train.py:715] (5/8) Epoch 2, batch 22450, loss[loss=0.1722, simple_loss=0.2413, pruned_loss=0.05154, over 4802.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2374, pruned_loss=0.05208, over 972523.81 frames.], batch size: 25, lr: 6.61e-04
2022-05-04 08:16:07,662 INFO [train.py:715] (5/8) Epoch 2, batch 22500, loss[loss=0.1876, simple_loss=0.2461, pruned_loss=0.06458, over 4702.00 frames.], tot_loss[loss=0.17, simple_loss=0.237, pruned_loss=0.05155, over 972929.46 frames.], batch size: 15, lr: 6.61e-04
2022-05-04 08:16:48,522 INFO [train.py:715] (5/8) Epoch 2, batch 22550, loss[loss=0.1752, simple_loss=0.2414, pruned_loss=0.05452, over 4881.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2366, pruned_loss=0.05148, over 972977.28 frames.], batch size: 16, lr: 6.60e-04
2022-05-04 08:17:29,224 INFO [train.py:715] (5/8) Epoch 2, batch 22600, loss[loss=0.1756, simple_loss=0.2443, pruned_loss=0.05342, over 4921.00 frames.], tot_loss[loss=0.171, simple_loss=0.2376, pruned_loss=0.05221, over 972542.16 frames.], batch size: 17, lr: 6.60e-04
2022-05-04 08:18:09,994 INFO [train.py:715] (5/8) Epoch 2, batch 22650, loss[loss=0.1961, simple_loss=0.2679, pruned_loss=0.06213, over 4693.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2381, pruned_loss=0.05244, over 972907.93 frames.], batch size: 15, lr: 6.60e-04
2022-05-04 08:18:50,670 INFO [train.py:715] (5/8) Epoch 2, batch 22700, loss[loss=0.172, simple_loss=0.245, pruned_loss=0.04949, over 4812.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2388, pruned_loss=0.0525, over 972546.66 frames.], batch size: 26, lr: 6.60e-04
2022-05-04 08:19:31,401 INFO [train.py:715] (5/8) Epoch 2, batch 22750, loss[loss=0.1744, simple_loss=0.2567, pruned_loss=0.04599, over 4836.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2387, pruned_loss=0.05251, over 973251.94 frames.], batch size: 26, lr: 6.60e-04
2022-05-04 08:20:12,248 INFO [train.py:715] (5/8) Epoch 2, batch 22800, loss[loss=0.1739, simple_loss=0.2375, pruned_loss=0.05514, over 4951.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2386, pruned_loss=0.05255, over 973135.62 frames.], batch size: 15, lr: 6.59e-04
2022-05-04 08:20:53,299 INFO [train.py:715] (5/8) Epoch 2, batch 22850, loss[loss=0.1456, simple_loss=0.206, pruned_loss=0.04255, over 4793.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2384, pruned_loss=0.05247, over 972364.48 frames.], batch size: 14, lr: 6.59e-04
2022-05-04 08:21:34,651 INFO [train.py:715] (5/8) Epoch 2, batch 22900, loss[loss=0.1947, simple_loss=0.2537, pruned_loss=0.06788, over 4988.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2382, pruned_loss=0.05219, over 972535.34 frames.], batch size: 25, lr: 6.59e-04
2022-05-04 08:22:15,452 INFO [train.py:715] (5/8) Epoch 2, batch 22950, loss[loss=0.1823, simple_loss=0.2426, pruned_loss=0.06101, over 4978.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.05217, over 972382.18 frames.], batch size: 24, lr: 6.59e-04
2022-05-04 08:22:56,050 INFO [train.py:715] (5/8) Epoch 2, batch 23000, loss[loss=0.1997, simple_loss=0.2592, pruned_loss=0.07013, over 4836.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2376, pruned_loss=0.05276, over 971925.37 frames.], batch size: 32, lr: 6.59e-04
2022-05-04 08:23:37,063 INFO [train.py:715] (5/8) Epoch 2, batch 23050, loss[loss=0.1547, simple_loss=0.2225, pruned_loss=0.04347, over 4964.00 frames.], tot_loss[loss=0.1707, simple_loss=0.237, pruned_loss=0.05222, over 972985.68 frames.], batch size: 24, lr: 6.59e-04
2022-05-04 08:24:17,898 INFO [train.py:715] (5/8) Epoch 2, batch 23100, loss[loss=0.1754, simple_loss=0.235, pruned_loss=0.05793, over 4870.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2363, pruned_loss=0.0517, over 972757.15 frames.], batch size: 32, lr: 6.58e-04
2022-05-04 08:24:58,403 INFO [train.py:715] (5/8) Epoch 2, batch 23150, loss[loss=0.1733, simple_loss=0.2554, pruned_loss=0.04559, over 4863.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2362, pruned_loss=0.05127, over 972441.62 frames.], batch size: 20, lr: 6.58e-04
2022-05-04 08:25:39,726 INFO [train.py:715] (5/8) Epoch 2, batch 23200, loss[loss=0.1449, simple_loss=0.2063, pruned_loss=0.04174, over 4993.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2349, pruned_loss=0.05066, over 972738.52 frames.], batch size: 16, lr: 6.58e-04
2022-05-04 08:26:20,397 INFO [train.py:715] (5/8) Epoch 2, batch 23250, loss[loss=0.1575, simple_loss=0.2388, pruned_loss=0.03804, over 4923.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2364, pruned_loss=0.05144, over 972808.95 frames.], batch size: 18, lr: 6.58e-04
2022-05-04 08:27:00,748 INFO [train.py:715] (5/8) Epoch 2, batch 23300, loss[loss=0.1685, simple_loss=0.2348, pruned_loss=0.05107, over 4942.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2364, pruned_loss=0.05151, over 972906.58 frames.], batch size: 35, lr: 6.58e-04
2022-05-04 08:27:41,447 INFO [train.py:715] (5/8) Epoch 2, batch 23350, loss[loss=0.1798, simple_loss=0.248, pruned_loss=0.05576, over 4855.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05111, over 972984.94 frames.], batch size: 32, lr: 6.57e-04
2022-05-04 08:28:22,396 INFO [train.py:715] (5/8) Epoch 2, batch 23400, loss[loss=0.2019, simple_loss=0.2544, pruned_loss=0.07475, over 4815.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2353, pruned_loss=0.05057, over 973253.59 frames.], batch size: 25, lr: 6.57e-04
2022-05-04 08:29:03,327 INFO [train.py:715] (5/8) Epoch 2, batch 23450, loss[loss=0.1507, simple_loss=0.2222, pruned_loss=0.03959, over 4991.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2349, pruned_loss=0.05016, over 972693.71 frames.], batch size: 20, lr: 6.57e-04
2022-05-04 08:29:43,621 INFO [train.py:715] (5/8) Epoch 2, batch 23500, loss[loss=0.1737, simple_loss=0.2413, pruned_loss=0.05303, over 4982.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2354, pruned_loss=0.05036, over 972483.66 frames.], batch size: 28, lr: 6.57e-04
2022-05-04 08:30:24,811 INFO [train.py:715] (5/8) Epoch 2, batch 23550, loss[loss=0.1646, simple_loss=0.2378, pruned_loss=0.04566, over 4919.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2358, pruned_loss=0.05052, over 972270.74 frames.], batch size: 23, lr: 6.57e-04
2022-05-04 08:31:05,708 INFO [train.py:715] (5/8) Epoch 2, batch 23600, loss[loss=0.2106, simple_loss=0.2803, pruned_loss=0.07038, over 4952.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2356, pruned_loss=0.04985, over 972232.25 frames.], batch size: 21, lr: 6.57e-04
2022-05-04 08:31:45,437 INFO [train.py:715] (5/8) Epoch 2, batch 23650, loss[loss=0.1903, simple_loss=0.2549, pruned_loss=0.06281, over 4750.00 frames.], tot_loss[loss=0.1685, simple_loss=0.236, pruned_loss=0.05046, over 972644.45 frames.], batch size: 16, lr: 6.56e-04
2022-05-04 08:32:27,507 INFO [train.py:715] (5/8) Epoch 2, batch 23700, loss[loss=0.1599, simple_loss=0.2171, pruned_loss=0.05137, over 4785.00 frames.], tot_loss[loss=0.1685, simple_loss=0.236, pruned_loss=0.05051, over 972479.28 frames.], batch size: 17, lr: 6.56e-04
2022-05-04 08:33:07,931 INFO [train.py:715] (5/8) Epoch 2, batch 23750, loss[loss=0.1987, simple_loss=0.2428, pruned_loss=0.07731, over 4779.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2365, pruned_loss=0.05123, over 972214.07 frames.], batch size: 17, lr: 6.56e-04
2022-05-04 08:33:48,797 INFO [train.py:715] (5/8) Epoch 2, batch 23800, loss[loss=0.1805, simple_loss=0.2601, pruned_loss=0.05048, over 4766.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2361, pruned_loss=0.05114, over 972240.34 frames.], batch size: 16, lr: 6.56e-04
2022-05-04 08:34:29,263 INFO [train.py:715] (5/8) Epoch 2, batch 23850, loss[loss=0.1644, simple_loss=0.2226, pruned_loss=0.05312, over 4894.00 frames.], tot_loss[loss=0.1687, simple_loss=0.236, pruned_loss=0.05076, over 971821.27 frames.], batch size: 22, lr: 6.56e-04
2022-05-04 08:35:10,697 INFO [train.py:715] (5/8) Epoch 2, batch 23900, loss[loss=0.1467, simple_loss=0.206, pruned_loss=0.04364, over 4788.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2357, pruned_loss=0.05056, over 971841.13 frames.], batch size: 14, lr: 6.56e-04
2022-05-04 08:35:51,717 INFO [train.py:715] (5/8) Epoch 2, batch 23950, loss[loss=0.1602, simple_loss=0.2321, pruned_loss=0.04413, over 4778.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2363, pruned_loss=0.05091, over 971552.59 frames.], batch size: 17, lr: 6.55e-04
2022-05-04 08:36:31,647 INFO [train.py:715] (5/8) Epoch 2, batch 24000, loss[loss=0.143, simple_loss=0.2266, pruned_loss=0.02976, over 4986.00 frames.], tot_loss[loss=0.17, simple_loss=0.2368, pruned_loss=0.05159, over 972090.58 frames.], batch size: 28, lr: 6.55e-04
2022-05-04 08:36:31,648 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 08:36:40,333 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1168, simple_loss=0.2032, pruned_loss=0.01518, over 914524.00 frames.
2022-05-04 08:37:20,459 INFO [train.py:715] (5/8) Epoch 2, batch 24050, loss[loss=0.1882, simple_loss=0.2549, pruned_loss=0.06069, over 4882.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2378, pruned_loss=0.05176, over 973337.15 frames.], batch size: 22, lr: 6.55e-04
2022-05-04 08:38:01,994 INFO [train.py:715] (5/8) Epoch 2, batch 24100, loss[loss=0.1734, simple_loss=0.2339, pruned_loss=0.05644, over 4791.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2379, pruned_loss=0.05152, over 972578.89 frames.], batch size: 14, lr: 6.55e-04
2022-05-04 08:38:42,994 INFO [train.py:715] (5/8) Epoch 2, batch 24150, loss[loss=0.1859, simple_loss=0.2532, pruned_loss=0.05931, over 4851.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2371, pruned_loss=0.05125, over 972413.73 frames.], batch size: 20, lr: 6.55e-04
2022-05-04 08:39:24,313 INFO [train.py:715] (5/8) Epoch 2, batch 24200, loss[loss=0.167, simple_loss=0.2296, pruned_loss=0.0522, over 4980.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2379, pruned_loss=0.05187, over 973239.68 frames.], batch size: 15, lr: 6.55e-04
2022-05-04 08:40:05,198 INFO [train.py:715] (5/8) Epoch 2, batch 24250, loss[loss=0.154, simple_loss=0.2225, pruned_loss=0.04279, over 4899.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2369, pruned_loss=0.05127, over 972822.80 frames.], batch size: 19, lr: 6.54e-04
2022-05-04 08:40:46,094 INFO [train.py:715] (5/8) Epoch 2, batch 24300, loss[loss=0.1386, simple_loss=0.2142, pruned_loss=0.0315, over 4985.00 frames.], tot_loss[loss=0.1692, simple_loss=0.236, pruned_loss=0.05122, over 973720.93 frames.], batch size: 20, lr: 6.54e-04
2022-05-04 08:41:26,676 INFO [train.py:715] (5/8) Epoch 2, batch 24350, loss[loss=0.1594, simple_loss=0.2247, pruned_loss=0.04702, over 4923.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2368, pruned_loss=0.05132, over 973262.16 frames.], batch size: 29, lr: 6.54e-04
2022-05-04 08:42:06,527 INFO [train.py:715] (5/8) Epoch 2, batch 24400, loss[loss=0.1474, simple_loss=0.2093, pruned_loss=0.04274, over 4905.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2354, pruned_loss=0.05049, over 972718.43 frames.], batch size: 17, lr: 6.54e-04
2022-05-04 08:42:47,544 INFO [train.py:715] (5/8) Epoch 2, batch 24450, loss[loss=0.2394, simple_loss=0.288, pruned_loss=0.09543, over 4879.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05117, over 972243.54 frames.], batch size: 16, lr: 6.54e-04
2022-05-04 08:43:27,488 INFO [train.py:715] (5/8) Epoch 2, batch 24500, loss[loss=0.1537, simple_loss=0.2194, pruned_loss=0.04397, over 4977.00 frames.], tot_loss[loss=0.1684, simple_loss=0.235, pruned_loss=0.05087, over 972546.31 frames.], batch size: 24, lr: 6.53e-04
2022-05-04 08:44:07,366 INFO [train.py:715] (5/8) Epoch 2, batch 24550, loss[loss=0.1621, simple_loss=0.2333, pruned_loss=0.04542, over 4808.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2344, pruned_loss=0.05016, over 972518.01 frames.], batch size: 24, lr: 6.53e-04
2022-05-04 08:44:46,871 INFO [train.py:715] (5/8) Epoch 2, batch 24600, loss[loss=0.1886, simple_loss=0.2458, pruned_loss=0.06567, over 4778.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2339, pruned_loss=0.04949, over 972619.48 frames.], batch size: 12, lr: 6.53e-04
2022-05-04 08:45:27,054 INFO [train.py:715] (5/8) Epoch 2, batch 24650, loss[loss=0.1757, simple_loss=0.2524, pruned_loss=0.04953, over 4916.00 frames.], tot_loss[loss=0.168, simple_loss=0.2355, pruned_loss=0.05028, over 972498.05 frames.], batch size: 23, lr: 6.53e-04
2022-05-04 08:46:06,406 INFO [train.py:715] (5/8) Epoch 2, batch 24700, loss[loss=0.1749, simple_loss=0.2476, pruned_loss=0.05107, over 4940.00 frames.], tot_loss[loss=0.1687, simple_loss=0.236, pruned_loss=0.05071, over 971810.22 frames.], batch size: 24, lr: 6.53e-04
2022-05-04 08:46:45,150 INFO [train.py:715] (5/8) Epoch 2, batch 24750, loss[loss=0.1735, simple_loss=0.2323, pruned_loss=0.0573, over 4992.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2362, pruned_loss=0.05076, over 972684.13 frames.], batch size: 14, lr: 6.53e-04
2022-05-04 08:47:24,974 INFO [train.py:715] (5/8) Epoch 2, batch 24800, loss[loss=0.1737, simple_loss=0.237, pruned_loss=0.0552, over 4862.00 frames.], tot_loss[loss=0.17, simple_loss=0.237, pruned_loss=0.0515, over 973069.03 frames.], batch size: 32, lr: 6.52e-04
2022-05-04 08:48:04,567 INFO [train.py:715] (5/8) Epoch 2, batch 24850, loss[loss=0.1518, simple_loss=0.2052, pruned_loss=0.04921, over 4765.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2362, pruned_loss=0.05099, over 971651.40 frames.], batch size: 17, lr: 6.52e-04
2022-05-04 08:48:43,454 INFO [train.py:715] (5/8) Epoch 2, batch 24900, loss[loss=0.1438, simple_loss=0.225, pruned_loss=0.0313, over 4912.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2359, pruned_loss=0.05094, over 972521.44 frames.], batch size: 18, lr: 6.52e-04
2022-05-04 08:49:22,924 INFO [train.py:715] (5/8) Epoch 2, batch 24950, loss[loss=0.1816, simple_loss=0.2467, pruned_loss=0.05825, over 4753.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2358, pruned_loss=0.0509, over 971936.40 frames.], batch size: 19, lr: 6.52e-04
2022-05-04 08:50:02,456 INFO [train.py:715] (5/8) Epoch 2, batch 25000, loss[loss=0.1793, simple_loss=0.2485, pruned_loss=0.05504, over 4801.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2359, pruned_loss=0.05064, over 972377.69 frames.], batch size: 21, lr: 6.52e-04
2022-05-04 08:50:41,254 INFO [train.py:715] (5/8) Epoch 2, batch 25050, loss[loss=0.1331, simple_loss=0.2177, pruned_loss=0.02423, over 4904.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2366, pruned_loss=0.05081, over 971846.69 frames.], batch size: 19, lr: 6.52e-04
2022-05-04 08:51:19,781 INFO [train.py:715] (5/8) Epoch 2, batch 25100, loss[loss=0.1726, simple_loss=0.2368, pruned_loss=0.05417, over 4862.00 frames.], tot_loss[loss=0.1707, simple_loss=0.238, pruned_loss=0.05164, over 972261.30 frames.], batch size: 32, lr: 6.51e-04
2022-05-04 08:51:59,031 INFO [train.py:715] (5/8) Epoch 2, batch 25150, loss[loss=0.1591, simple_loss=0.2379, pruned_loss=0.04016, over 4792.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2365, pruned_loss=0.05122, over 972677.51 frames.], batch size: 24, lr: 6.51e-04
2022-05-04 08:52:37,843 INFO [train.py:715] (5/8) Epoch 2, batch 25200, loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02923, over 4818.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2361, pruned_loss=0.05124, over 972428.63 frames.], batch size: 26, lr: 6.51e-04
2022-05-04 08:53:16,877 INFO [train.py:715] (5/8) Epoch 2, batch 25250, loss[loss=0.1698, simple_loss=0.2376, pruned_loss=0.05102, over 4804.00 frames.], tot_loss[loss=0.169, simple_loss=0.2359, pruned_loss=0.05108, over 972142.96 frames.], batch size: 13, lr: 6.51e-04
2022-05-04 08:53:55,851 INFO [train.py:715] (5/8) Epoch 2, batch 25300, loss[loss=0.1977, simple_loss=0.2619, pruned_loss=0.06676, over 4875.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2355, pruned_loss=0.05065, over 972291.68 frames.], batch size: 16, lr: 6.51e-04
2022-05-04 08:54:35,068 INFO [train.py:715] (5/8) Epoch 2, batch 25350, loss[loss=0.1872, simple_loss=0.2504, pruned_loss=0.062, over 4982.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2357, pruned_loss=0.05062, over 972864.84 frames.], batch size: 33, lr: 6.51e-04
2022-05-04 08:55:14,142 INFO [train.py:715] (5/8) Epoch 2, batch 25400, loss[loss=0.1381, simple_loss=0.2054, pruned_loss=0.03544, over 4768.00 frames.], tot_loss[loss=0.1677, simple_loss=0.235, pruned_loss=0.05017, over 972406.35 frames.], batch size: 18, lr: 6.50e-04
2022-05-04 08:55:52,989 INFO [train.py:715] (5/8) Epoch 2, batch 25450, loss[loss=0.1776, simple_loss=0.2461, pruned_loss=0.05455, over 4834.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2351, pruned_loss=0.05053, over 972873.16 frames.], batch size: 20, lr: 6.50e-04
2022-05-04 08:56:32,018 INFO [train.py:715] (5/8) Epoch 2, batch 25500, loss[loss=0.1865, simple_loss=0.2636, pruned_loss=0.05466, over 4770.00 frames.], tot_loss[loss=0.17, simple_loss=0.2365, pruned_loss=0.05174, over 972881.26 frames.], batch size: 17, lr: 6.50e-04
2022-05-04 08:57:11,299 INFO [train.py:715] (5/8) Epoch 2, batch 25550, loss[loss=0.1144, simple_loss=0.1761, pruned_loss=0.02631, over 4740.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2364, pruned_loss=0.05174, over 971849.34 frames.], batch size: 12, lr: 6.50e-04
2022-05-04 08:57:50,302 INFO [train.py:715] (5/8) Epoch 2, batch 25600, loss[loss=0.1367, simple_loss=0.2131, pruned_loss=0.0301, over 4962.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2356, pruned_loss=0.05094, over 972509.64 frames.], batch size: 14, lr: 6.50e-04
2022-05-04 08:58:29,641 INFO [train.py:715] (5/8) Epoch 2, batch 25650, loss[loss=0.1549, simple_loss=0.2137, pruned_loss=0.0481, over 4799.00 frames.], tot_loss[loss=0.1686, simple_loss=0.235, pruned_loss=0.0511, over 971393.39 frames.], batch size: 21, lr: 6.50e-04
2022-05-04 08:59:09,547 INFO [train.py:715] (5/8) Epoch 2, batch 25700, loss[loss=0.146, simple_loss=0.2186, pruned_loss=0.03672, over 4903.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2349, pruned_loss=0.05104, over 971994.27 frames.], batch size: 17, lr: 6.49e-04
2022-05-04 08:59:48,685 INFO [train.py:715] (5/8) Epoch 2, batch 25750, loss[loss=0.1326, simple_loss=0.2037, pruned_loss=0.03071, over 4796.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2359, pruned_loss=0.05135, over 971420.18 frames.], batch size: 18, lr: 6.49e-04
2022-05-04 09:00:27,436 INFO [train.py:715] (5/8) Epoch 2, batch 25800, loss[loss=0.1881, simple_loss=0.2535, pruned_loss=0.06138, over 4826.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2359, pruned_loss=0.05127, over 971622.86 frames.], batch size: 27, lr: 6.49e-04
2022-05-04 09:01:06,417 INFO [train.py:715] (5/8) Epoch 2, batch 25850, loss[loss=0.1692, simple_loss=0.2258, pruned_loss=0.05631, over 4864.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.0511, over 971799.08 frames.], batch size: 32, lr: 6.49e-04
2022-05-04 09:01:46,178 INFO [train.py:715] (5/8) Epoch 2, batch 25900, loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05237, over 4892.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2362, pruned_loss=0.0511, over 972522.46 frames.], batch size: 39, lr: 6.49e-04
2022-05-04 09:02:25,987 INFO [train.py:715] (5/8) Epoch 2, batch 25950, loss[loss=0.1395, simple_loss=0.2136, pruned_loss=0.03275, over 4855.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2345, pruned_loss=0.04998, over 972255.11 frames.], batch size: 20, lr: 6.49e-04
2022-05-04 09:03:05,063 INFO [train.py:715] (5/8) Epoch 2, batch 26000, loss[loss=0.1736, simple_loss=0.2365, pruned_loss=0.05536, over 4911.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2347, pruned_loss=0.05004, over 972281.63 frames.], batch size: 17, lr: 6.48e-04
2022-05-04 09:03:44,732 INFO [train.py:715] (5/8) Epoch 2, batch 26050, loss[loss=0.1726, simple_loss=0.2484, pruned_loss=0.04843, over 4941.00 frames.], tot_loss[loss=0.1668, simple_loss=0.234, pruned_loss=0.04975, over 972602.95 frames.], batch size: 23, lr: 6.48e-04
2022-05-04 09:04:24,303 INFO [train.py:715] (5/8) Epoch 2, batch 26100, loss[loss=0.1776, simple_loss=0.2454, pruned_loss=0.05486, over 4971.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2341, pruned_loss=0.04974, over 972568.18 frames.], batch size: 24, lr: 6.48e-04
2022-05-04 09:05:03,477 INFO [train.py:715] (5/8) Epoch 2, batch 26150, loss[loss=0.1535, simple_loss=0.2338, pruned_loss=0.03658, over 4833.00 frames.], tot_loss[loss=0.167, simple_loss=0.2343, pruned_loss=0.04984, over 971578.90 frames.], batch size: 26, lr: 6.48e-04
2022-05-04 09:05:42,983 INFO [train.py:715] (5/8) Epoch 2, batch 26200, loss[loss=0.1633, simple_loss=0.2355, pruned_loss=0.0456, over 4905.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2353, pruned_loss=0.0506, over 971711.60 frames.], batch size: 22, lr: 6.48e-04
2022-05-04 09:06:22,730 INFO [train.py:715] (5/8) Epoch 2, batch 26250, loss[loss=0.1592, simple_loss=0.2292, pruned_loss=0.04458, over 4754.00 frames.], tot_loss[loss=0.1681, simple_loss=0.235, pruned_loss=0.05055, over 971685.87 frames.], batch size: 19, lr: 6.48e-04
2022-05-04 09:07:02,318 INFO [train.py:715] (5/8) Epoch 2, batch 26300, loss[loss=0.2015, simple_loss=0.2636, pruned_loss=0.06974, over 4931.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.0507, over 972450.45 frames.], batch size: 39, lr: 6.47e-04
2022-05-04 09:07:40,823 INFO [train.py:715] (5/8) Epoch 2, batch 26350, loss[loss=0.1483, simple_loss=0.208, pruned_loss=0.04431, over 4946.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05126, over 973077.62 frames.], batch size: 21, lr: 6.47e-04
2022-05-04 09:08:23,926 INFO [train.py:715] (5/8) Epoch 2, batch 26400, loss[loss=0.1864, simple_loss=0.256, pruned_loss=0.05835, over 4759.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2368, pruned_loss=0.05092, over 972583.55 frames.], batch size: 16, lr: 6.47e-04
2022-05-04 09:09:03,680 INFO [train.py:715] (5/8) Epoch 2, batch 26450, loss[loss=0.1859, simple_loss=0.2616, pruned_loss=0.05507, over 4887.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2363, pruned_loss=0.05016, over 971833.37 frames.], batch size: 22, lr: 6.47e-04
2022-05-04 09:09:42,579 INFO [train.py:715] (5/8) Epoch 2, batch 26500, loss[loss=0.2068, simple_loss=0.2602, pruned_loss=0.07667, over 4835.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2362, pruned_loss=0.0505, over 971390.05 frames.], batch size: 30, lr: 6.47e-04
2022-05-04 09:10:22,389 INFO [train.py:715] (5/8) Epoch 2, batch 26550, loss[loss=0.141, simple_loss=0.2111, pruned_loss=0.03541, over 4837.00 frames.], tot_loss[loss=0.1689, simple_loss=0.236, pruned_loss=0.05087, over 970754.50 frames.], batch size: 13, lr: 6.46e-04
2022-05-04 09:11:02,374 INFO [train.py:715] (5/8) Epoch 2, batch 26600, loss[loss=0.1845, simple_loss=0.2362, pruned_loss=0.0664, over 4973.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2365, pruned_loss=0.05143, over 971184.98 frames.], batch size: 35, lr: 6.46e-04
2022-05-04 09:11:41,991 INFO [train.py:715] (5/8) Epoch 2, batch 26650, loss[loss=0.1818, simple_loss=0.2469, pruned_loss=0.05835, over 4837.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2356, pruned_loss=0.05096, over 970293.62 frames.], batch size: 30, lr: 6.46e-04
2022-05-04 09:12:21,003 INFO [train.py:715] (5/8) Epoch 2, batch 26700, loss[loss=0.1912, simple_loss=0.2456, pruned_loss=0.06837, over 4961.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2366, pruned_loss=0.05188, over 971241.05 frames.], batch size: 24, lr: 6.46e-04
2022-05-04 09:13:00,965 INFO [train.py:715] (5/8) Epoch 2, batch 26750, loss[loss=0.1726, simple_loss=0.2417, pruned_loss=0.05172, over 4801.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2375, pruned_loss=0.05169, over 971875.35 frames.], batch size: 25, lr: 6.46e-04
2022-05-04 09:13:40,190 INFO [train.py:715] (5/8) Epoch 2, batch 26800, loss[loss=0.1544, simple_loss=0.2254, pruned_loss=0.04171, over 4990.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2376, pruned_loss=0.05206, over 971525.61 frames.], batch size: 25, lr: 6.46e-04
2022-05-04 09:14:19,181 INFO [train.py:715] (5/8) Epoch 2, batch 26850, loss[loss=0.1892, simple_loss=0.249, pruned_loss=0.06471, over 4822.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2379, pruned_loss=0.05246, over 972023.72 frames.], batch size: 26, lr: 6.45e-04
2022-05-04 09:14:58,116 INFO [train.py:715] (5/8) Epoch 2, batch 26900, loss[loss=0.2442, simple_loss=0.3015, pruned_loss=0.09343, over 4767.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2372, pruned_loss=0.05221, over 971837.97 frames.], batch size: 17, lr: 6.45e-04
2022-05-04 09:15:37,579 INFO [train.py:715] (5/8) Epoch 2, batch 26950, loss[loss=0.1409, simple_loss=0.2101, pruned_loss=0.03582, over 4797.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2354, pruned_loss=0.05101, over 971308.29 frames.], batch size: 24, lr: 6.45e-04
2022-05-04 09:16:16,464 INFO [train.py:715] (5/8) Epoch 2, batch 27000, loss[loss=0.1466, simple_loss=0.2188, pruned_loss=0.03725, over 4941.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2364, pruned_loss=0.05171, over 970702.57 frames.], batch size: 29, lr: 6.45e-04
2022-05-04 09:16:16,464 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 09:16:25,253 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1164, simple_loss=0.2027, pruned_loss=0.01502, over 914524.00 frames.
2022-05-04 09:17:03,617 INFO [train.py:715] (5/8) Epoch 2, batch 27050, loss[loss=0.2096, simple_loss=0.2566, pruned_loss=0.08133, over 4889.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2355, pruned_loss=0.05148, over 971090.10 frames.], batch size: 22, lr: 6.45e-04
2022-05-04 09:17:42,881 INFO [train.py:715] (5/8) Epoch 2, batch 27100, loss[loss=0.189, simple_loss=0.2568, pruned_loss=0.06055, over 4924.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2368, pruned_loss=0.05199, over 971245.25 frames.], batch size: 19, lr: 6.45e-04
2022-05-04 09:18:22,883 INFO [train.py:715] (5/8) Epoch 2, batch 27150, loss[loss=0.19, simple_loss=0.2503, pruned_loss=0.06486, over 4936.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2371, pruned_loss=0.05225, over 971254.57 frames.], batch size: 21, lr: 6.44e-04
2022-05-04 09:19:02,264 INFO [train.py:715] (5/8) Epoch 2, batch 27200, loss[loss=0.1638, simple_loss=0.2393, pruned_loss=0.04415, over 4802.00 frames.], tot_loss[loss=0.169, simple_loss=0.2356, pruned_loss=0.05117, over 971822.98 frames.], batch size: 25, lr: 6.44e-04
2022-05-04 09:19:41,119 INFO [train.py:715] (5/8) Epoch 2, batch 27250, loss[loss=0.1663, simple_loss=0.2449, pruned_loss=0.04388, over 4904.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2353, pruned_loss=0.05073, over 971536.06 frames.], batch size: 39, lr: 6.44e-04
2022-05-04 09:20:20,688 INFO [train.py:715] (5/8) Epoch 2, batch 27300, loss[loss=0.1756, simple_loss=0.2453, pruned_loss=0.05295, over 4927.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2355, pruned_loss=0.05051, over 972228.87 frames.], batch size: 29, lr: 6.44e-04
2022-05-04 09:20:59,720 INFO [train.py:715] (5/8) Epoch 2, batch 27350, loss[loss=0.1893, simple_loss=0.2603, pruned_loss=0.05914, over 4796.00 frames.], tot_loss[loss=0.1675, simple_loss=0.235, pruned_loss=0.05003, over 972024.09 frames.], batch size: 21, lr: 6.44e-04
2022-05-04 09:21:38,801 INFO [train.py:715] (5/8) Epoch 2, batch 27400, loss[loss=0.1782, simple_loss=0.2405, pruned_loss=0.05791, over 4917.00 frames.], tot_loss[loss=0.168, simple_loss=0.2356, pruned_loss=0.05018, over 972755.16 frames.], batch size: 18, lr: 6.44e-04
2022-05-04 09:22:17,479 INFO [train.py:715] (5/8) Epoch 2, batch 27450, loss[loss=0.1929, simple_loss=0.2577, pruned_loss=0.06401, over 4870.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05073, over 971535.42 frames.], batch size: 22, lr: 6.44e-04
2022-05-04 09:22:57,211 INFO [train.py:715] (5/8) Epoch 2, batch 27500, loss[loss=0.1632, simple_loss=0.2304, pruned_loss=0.04803, over 4897.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2359, pruned_loss=0.05139, over 972905.89 frames.], batch size: 17, lr: 6.43e-04
2022-05-04 09:23:37,093 INFO [train.py:715] (5/8) Epoch 2, batch 27550, loss[loss=0.172, simple_loss=0.2412, pruned_loss=0.05143, over 4803.00 frames.], tot_loss[loss=0.168, simple_loss=0.235, pruned_loss=0.05043, over 972482.54 frames.], batch size: 21, lr: 6.43e-04
2022-05-04 09:24:16,422 INFO [train.py:715] (5/8) Epoch 2, batch 27600, loss[loss=0.1421, simple_loss=0.2178, pruned_loss=0.03321, over 4748.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2351, pruned_loss=0.0502, over 972075.95 frames.], batch size: 19, lr: 6.43e-04
2022-05-04 09:24:55,993 INFO [train.py:715] (5/8) Epoch 2, batch 27650, loss[loss=0.172, simple_loss=0.2473, pruned_loss=0.04839, over 4895.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2355, pruned_loss=0.05051, over 972666.75 frames.], batch size: 19, lr: 6.43e-04
2022-05-04 09:25:36,591 INFO [train.py:715] (5/8) Epoch 2, batch 27700, loss[loss=0.1671, simple_loss=0.2256, pruned_loss=0.0543, over 4794.00 frames.], tot_loss[loss=0.1677, simple_loss=0.235, pruned_loss=0.05024, over 972741.21 frames.], batch size: 21, lr: 6.43e-04
2022-05-04 09:26:16,918 INFO [train.py:715] (5/8) Epoch 2, batch 27750, loss[loss=0.177, simple_loss=0.2396, pruned_loss=0.05725, over 4906.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2354, pruned_loss=0.05057, over 971630.92 frames.], batch size: 17, lr: 6.43e-04
2022-05-04 09:26:56,302 INFO [train.py:715] (5/8) Epoch 2, batch 27800, loss[loss=0.1813, simple_loss=0.2429, pruned_loss=0.05991, over 4973.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2348, pruned_loss=0.05026, over 972834.09 frames.], batch size: 14, lr: 6.42e-04
2022-05-04 09:27:36,593 INFO [train.py:715] (5/8) Epoch 2, batch 27850, loss[loss=0.1499, simple_loss=0.219, pruned_loss=0.04035, over 4928.00 frames.], tot_loss[loss=0.1675, simple_loss=0.235, pruned_loss=0.04998, over 973261.99 frames.], batch size: 18, lr: 6.42e-04
2022-05-04 09:28:15,903 INFO [train.py:715] (5/8) Epoch 2, batch 27900, loss[loss=0.1362, simple_loss=0.1971, pruned_loss=0.03765, over 4752.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2344, pruned_loss=0.04968, over 972942.55 frames.], batch size: 12, lr: 6.42e-04
2022-05-04 09:28:55,086 INFO [train.py:715] (5/8) Epoch 2, batch 27950, loss[loss=0.174, simple_loss=0.2432, pruned_loss=0.0524, over 4934.00 frames.], tot_loss[loss=0.167, simple_loss=0.2346, pruned_loss=0.04972, over 973638.05 frames.], batch size: 21, lr: 6.42e-04
2022-05-04 09:29:34,666 INFO [train.py:715] (5/8) Epoch 2, batch 28000, loss[loss=0.1644, simple_loss=0.2408, pruned_loss=0.04402, over 4800.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2344, pruned_loss=0.04954, over 972991.58 frames.], batch size: 21, lr: 6.42e-04
2022-05-04 09:30:15,046 INFO [train.py:715] (5/8) Epoch 2, batch 28050, loss[loss=0.1466, simple_loss=0.2126, pruned_loss=0.04032, over 4895.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2339, pruned_loss=0.04939, over 972370.80 frames.], batch size: 17, lr: 6.42e-04
2022-05-04 09:30:54,018 INFO [train.py:715] (5/8) Epoch 2, batch 28100, loss[loss=0.1653, simple_loss=0.2315, pruned_loss=0.04951, over 4793.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2337, pruned_loss=0.04927, over 972670.19 frames.], batch size: 24, lr: 6.41e-04
2022-05-04 09:31:33,557 INFO [train.py:715] (5/8) Epoch 2, batch 28150, loss[loss=0.1871, simple_loss=0.2476, pruned_loss=0.06335, over 4866.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2335, pruned_loss=0.04946, over 972914.39 frames.], batch size: 20, lr: 6.41e-04
2022-05-04 09:32:13,295 INFO [train.py:715] (5/8) Epoch 2, batch 28200, loss[loss=0.1482, simple_loss=0.2249, pruned_loss=0.03573, over 4817.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2349, pruned_loss=0.05028, over 972855.69 frames.], batch size: 27, lr: 6.41e-04
2022-05-04 09:32:52,900 INFO [train.py:715] (5/8) Epoch 2, batch 28250, loss[loss=0.1288, simple_loss=0.2002, pruned_loss=0.02869, over 4744.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2355, pruned_loss=0.05046, over 972800.23 frames.], batch size: 19, lr: 6.41e-04
2022-05-04 09:33:31,976 INFO [train.py:715] (5/8) Epoch 2, batch 28300, loss[loss=0.1718, simple_loss=0.2439, pruned_loss=0.04987, over 4875.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2361, pruned_loss=0.05089, over 971935.83 frames.], batch size: 16, lr: 6.41e-04
2022-05-04 09:34:11,317 INFO [train.py:715] (5/8) Epoch 2, batch 28350, loss[loss=0.1808, simple_loss=0.252, pruned_loss=0.05482, over 4777.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2363, pruned_loss=0.05055, over 971634.27 frames.], batch size: 17, lr: 6.41e-04
2022-05-04 09:34:51,511 INFO [train.py:715] (5/8) Epoch 2, batch 28400, loss[loss=0.1523, simple_loss=0.2218, pruned_loss=0.04137, over 4851.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2375, pruned_loss=0.05152, over 971884.32 frames.], batch size: 13, lr: 6.40e-04
2022-05-04 09:35:30,758 INFO [train.py:715] (5/8) Epoch 2, batch 28450, loss[loss=0.1972, simple_loss=0.2491, pruned_loss=0.07264, over 4771.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2371, pruned_loss=0.05108, over 972441.14 frames.], batch size: 14, lr: 6.40e-04
2022-05-04 09:36:10,158 INFO [train.py:715] (5/8) Epoch 2, batch 28500, loss[loss=0.1778, simple_loss=0.2458, pruned_loss=0.05491, over 4816.00 frames.], tot_loss[loss=0.169, simple_loss=0.2363, pruned_loss=0.05087, over 972513.49 frames.], batch size: 26, lr: 6.40e-04
2022-05-04 09:36:50,108 INFO [train.py:715] (5/8) Epoch 2, batch 28550, loss[loss=0.1912, simple_loss=0.2749, pruned_loss=0.05377, over 4839.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2365, pruned_loss=0.05088, over 972162.83 frames.], batch size: 26, lr: 6.40e-04
2022-05-04 09:37:30,235 INFO [train.py:715] (5/8) Epoch 2, batch 28600, loss[loss=0.2088, simple_loss=0.2666, pruned_loss=0.07546, over 4724.00 frames.], tot_loss[loss=0.169, simple_loss=0.2363, pruned_loss=0.05087, over 971828.02 frames.], batch size: 15, lr: 6.40e-04
2022-05-04 09:38:09,269 INFO [train.py:715] (5/8) Epoch 2, batch 28650, loss[loss=0.1662, simple_loss=0.2383, pruned_loss=0.04702, over 4798.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2372, pruned_loss=0.05133, over 972450.46 frames.], batch size: 21, lr: 6.40e-04
2022-05-04 09:38:49,122 INFO [train.py:715] (5/8) Epoch 2, batch 28700, loss[loss=0.1591, simple_loss=0.2253, pruned_loss=0.0465, over 4810.00 frames.], tot_loss[loss=0.171, simple_loss=0.2375, pruned_loss=0.05219, over 971786.16 frames.], batch size: 26, lr: 6.39e-04
2022-05-04 09:39:29,582 INFO [train.py:715] (5/8) Epoch 2, batch 28750, loss[loss=0.1696, simple_loss=0.2263, pruned_loss=0.05644, over 4791.00 frames.], tot_loss[loss=0.1707, simple_loss=0.237, pruned_loss=0.05218, over 972438.58 frames.], batch size: 12, lr: 6.39e-04
2022-05-04 09:40:08,506 INFO [train.py:715] (5/8) Epoch 2, batch 28800, loss[loss=0.1761, simple_loss=0.248, pruned_loss=0.05207, over 4813.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05113, over 972014.43 frames.], batch size: 27, lr: 6.39e-04
2022-05-04 09:40:48,099 INFO [train.py:715] (5/8) Epoch 2, batch 28850, loss[loss=0.1554, simple_loss=0.2183, pruned_loss=0.04624, over 4779.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2357, pruned_loss=0.05077, over 972057.12 frames.], batch size: 18, lr: 6.39e-04
2022-05-04 09:41:28,105 INFO [train.py:715] (5/8) Epoch 2, batch 28900, loss[loss=0.1734, simple_loss=0.246, pruned_loss=0.05042, over 4872.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2357, pruned_loss=0.05086, over 971202.11 frames.], batch size: 16, lr: 6.39e-04
2022-05-04 09:42:07,483 INFO [train.py:715] (5/8) Epoch 2, batch 28950, loss[loss=0.1472, simple_loss=0.2203, pruned_loss=0.03709, over 4690.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2354, pruned_loss=0.05117, over 970922.34 frames.], batch size: 15, lr: 6.39e-04
2022-05-04 09:42:46,856 INFO [train.py:715] (5/8) Epoch 2, batch 29000, loss[loss=0.1596, simple_loss=0.2194, pruned_loss=0.04993, over 4696.00 frames.], tot_loss[loss=0.169, simple_loss=0.2354, pruned_loss=0.05129, over 971248.48 frames.], batch size: 15, lr: 6.38e-04
2022-05-04 09:43:26,611 INFO [train.py:715] (5/8) Epoch 2, batch 29050, loss[loss=0.1535, simple_loss=0.2158, pruned_loss=0.04563, over 4881.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2356, pruned_loss=0.05134, over 971371.49 frames.], batch size: 32, lr: 6.38e-04
2022-05-04 09:44:06,287 INFO [train.py:715] (5/8) Epoch 2, batch 29100, loss[loss=0.2017, simple_loss=0.2454, pruned_loss=0.07898, over 4851.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2354, pruned_loss=0.05108, over 970506.18 frames.], batch size: 34, lr: 6.38e-04
2022-05-04 09:44:45,459 INFO [train.py:715] (5/8) Epoch 2, batch 29150, loss[loss=0.1504, simple_loss=0.2124, pruned_loss=0.04417, over 4971.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2354, pruned_loss=0.05119, over 971955.40 frames.], batch size: 14, lr: 6.38e-04
2022-05-04 09:45:24,943 INFO [train.py:715] (5/8) Epoch 2, batch 29200, loss[loss=0.1839, simple_loss=0.2413, pruned_loss=0.06323, over 4902.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2345, pruned_loss=0.05055, over 972259.64 frames.], batch size: 18, lr: 6.38e-04
2022-05-04 09:46:05,373 INFO [train.py:715] (5/8) Epoch 2, batch 29250, loss[loss=0.1416, simple_loss=0.2119, pruned_loss=0.03564, over 4950.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2343, pruned_loss=0.05038, over 972167.85 frames.], batch size: 23, lr: 6.38e-04
2022-05-04 09:46:44,477 INFO [train.py:715] (5/8) Epoch 2, batch 29300, loss[loss=0.1931, simple_loss=0.2651, pruned_loss=0.06054, over 4766.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2351, pruned_loss=0.0507, over 971888.95 frames.], batch size: 14, lr: 6.37e-04
2022-05-04 09:47:23,245 INFO [train.py:715] (5/8) Epoch 2, batch 29350, loss[loss=0.1519, simple_loss=0.2166, pruned_loss=0.04359, over 4929.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2353, pruned_loss=0.05084, over 972372.16 frames.], batch size: 29, lr: 6.37e-04
2022-05-04 09:48:02,463 INFO [train.py:715] (5/8) Epoch 2, batch 29400, loss[loss=0.1556, simple_loss=0.2318, pruned_loss=0.03965, over 4908.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2349, pruned_loss=0.05035, over 972432.49 frames.], batch size: 19, lr: 6.37e-04
2022-05-04 09:48:41,884 INFO [train.py:715] (5/8) Epoch 2, batch 29450, loss[loss=0.1396, simple_loss=0.1983, pruned_loss=0.04046, over 4762.00 frames.], tot_loss[loss=0.1675, simple_loss=0.235, pruned_loss=0.04999, over 972092.75 frames.], batch size: 12, lr: 6.37e-04
2022-05-04 09:49:20,752 INFO [train.py:715] (5/8) Epoch 2, batch 29500, loss[loss=0.1784, simple_loss=0.255, pruned_loss=0.05083, over 4811.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2362, pruned_loss=0.05041, over 972099.94 frames.], batch size: 21, lr: 6.37e-04
2022-05-04 09:49:59,765 INFO [train.py:715] (5/8) Epoch 2, batch 29550, loss[loss=0.1793, simple_loss=0.238, pruned_loss=0.06034, over 4875.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2356, pruned_loss=0.0504, over 971674.38 frames.], batch size: 20, lr: 6.37e-04
2022-05-04 09:50:39,178 INFO [train.py:715] (5/8) Epoch 2, batch 29600, loss[loss=0.2388, simple_loss=0.2914, pruned_loss=0.0931, over 4882.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2358, pruned_loss=0.05061, over 971640.94 frames.], batch size: 16, lr: 6.37e-04
2022-05-04 09:51:18,363 INFO [train.py:715] (5/8) Epoch 2, batch 29650, loss[loss=0.1607, simple_loss=0.2282, pruned_loss=0.04659, over 4817.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2354, pruned_loss=0.05011, over 971725.21 frames.], batch size: 21, lr: 6.36e-04
2022-05-04 09:51:57,125 INFO [train.py:715] (5/8) Epoch 2, batch 29700, loss[loss=0.1353, simple_loss=0.2076, pruned_loss=0.03149, over 4980.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2352, pruned_loss=0.04947, over 971228.74 frames.], batch size: 15, lr: 6.36e-04
2022-05-04 09:52:36,249 INFO [train.py:715] (5/8) Epoch 2, batch 29750, loss[loss=0.1598, simple_loss=0.2364, pruned_loss=0.04163, over 4806.00 frames.], tot_loss[loss=0.167, simple_loss=0.2351, pruned_loss=0.04945, over 972166.05 frames.], batch size: 21, lr: 6.36e-04
2022-05-04 09:53:15,366 INFO [train.py:715] (5/8) Epoch 2, batch 29800, loss[loss=0.161, simple_loss=0.2303, pruned_loss=0.0459, over 4816.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2351, pruned_loss=0.04997, over 972077.01 frames.], batch size: 21, lr: 6.36e-04
2022-05-04 09:53:53,996 INFO [train.py:715] (5/8) Epoch 2, batch 29850, loss[loss=0.1943, simple_loss=0.2629, pruned_loss=0.06282, over 4923.00 frames.], tot_loss[loss=0.1676, simple_loss=0.235, pruned_loss=0.05014, over 971732.74 frames.], batch size: 18, lr: 6.36e-04
2022-05-04 09:54:33,006 INFO [train.py:715] (5/8) Epoch 2, batch 29900, loss[loss=0.1806, simple_loss=0.2544, pruned_loss=0.05339, over 4697.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2351, pruned_loss=0.05007, over 971591.24 frames.], batch size: 15, lr: 6.36e-04
2022-05-04 09:55:12,826 INFO [train.py:715] (5/8) Epoch 2, batch 29950, loss[loss=0.2077, simple_loss=0.2727, pruned_loss=0.0714, over 4899.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2346, pruned_loss=0.04959, over 972366.76 frames.], batch size: 22, lr: 6.35e-04
2022-05-04 09:55:51,633 INFO [train.py:715] (5/8) Epoch 2, batch 30000, loss[loss=0.1421, simple_loss=0.2158, pruned_loss=0.03419, over 4838.00 frames.], tot_loss[loss=0.1673, simple_loss=0.235, pruned_loss=0.04978, over 972181.79 frames.], batch size: 13, lr: 6.35e-04
2022-05-04 09:55:51,633 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 09:56:00,453 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1166, simple_loss=0.2028, pruned_loss=0.01515, over 914524.00 frames.
2022-05-04 09:56:39,115 INFO [train.py:715] (5/8) Epoch 2, batch 30050, loss[loss=0.1476, simple_loss=0.2209, pruned_loss=0.03719, over 4756.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2354, pruned_loss=0.04954, over 973208.40 frames.], batch size: 19, lr: 6.35e-04
2022-05-04 09:57:18,476 INFO [train.py:715] (5/8) Epoch 2, batch 30100, loss[loss=0.1336, simple_loss=0.2159, pruned_loss=0.02566, over 4807.00 frames.], tot_loss[loss=0.1676, simple_loss=0.236, pruned_loss=0.04961, over 972891.28 frames.], batch size: 25, lr: 6.35e-04
2022-05-04 09:57:57,547 INFO [train.py:715] (5/8) Epoch 2, batch 30150, loss[loss=0.1549, simple_loss=0.218, pruned_loss=0.04593, over 4898.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2372, pruned_loss=0.05015, over 972036.61 frames.], batch size: 17, lr: 6.35e-04
2022-05-04 09:58:37,028 INFO [train.py:715] (5/8) Epoch 2, batch 30200, loss[loss=0.2336, simple_loss=0.2845, pruned_loss=0.09136, over 4850.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2364, pruned_loss=0.0502, over 972297.25 frames.], batch size: 13, lr: 6.35e-04
2022-05-04 09:59:15,776 INFO [train.py:715] (5/8) Epoch 2, batch 30250, loss[loss=0.1735, simple_loss=0.2457, pruned_loss=0.05062, over 4775.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2365, pruned_loss=0.05015, over 971981.65 frames.], batch size: 18, lr: 6.34e-04
2022-05-04 09:59:55,024 INFO [train.py:715] (5/8) Epoch 2, batch 30300, loss[loss=0.1504, simple_loss=0.2228, pruned_loss=0.03896, over 4962.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2353, pruned_loss=0.04949, over 972020.42 frames.], batch size: 35, lr: 6.34e-04
2022-05-04 10:00:35,003 INFO [train.py:715] (5/8) Epoch 2, batch 30350, loss[loss=0.1482, simple_loss=0.2247, pruned_loss=0.03585, over 4808.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2353, pruned_loss=0.05005, over 972261.19 frames.], batch size: 25, lr: 6.34e-04
2022-05-04 10:01:14,087 INFO [train.py:715] (5/8) Epoch 2, batch 30400, loss[loss=0.1554, simple_loss=0.2363, pruned_loss=0.03729, over 4752.00 frames.], tot_loss[loss=0.168, simple_loss=0.2352, pruned_loss=0.05041, over 972077.30 frames.], batch size: 19, lr: 6.34e-04
2022-05-04 10:01:53,190 INFO [train.py:715] (5/8) Epoch 2, batch 30450, loss[loss=0.1671, simple_loss=0.2298, pruned_loss=0.05219, over 4637.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2342, pruned_loss=0.04966, over 971319.27 frames.], batch size: 13, lr: 6.34e-04
2022-05-04 10:02:32,960 INFO [train.py:715] (5/8) Epoch 2, batch 30500, loss[loss=0.1609, simple_loss=0.2419, pruned_loss=0.03995, over 4834.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2353, pruned_loss=0.05029, over 971458.23 frames.], batch size: 26, lr: 6.34e-04
2022-05-04 10:03:12,630 INFO [train.py:715] (5/8) Epoch 2, batch 30550, loss[loss=0.1411, simple_loss=0.2161, pruned_loss=0.03307, over 4884.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2362, pruned_loss=0.0506, over 972086.93 frames.], batch size: 19, lr: 6.33e-04
2022-05-04 10:03:51,362 INFO [train.py:715] (5/8) Epoch 2, batch 30600, loss[loss=0.2083, simple_loss=0.268, pruned_loss=0.07429, over 4989.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2362, pruned_loss=0.05029, over 972211.85 frames.], batch size: 16, lr: 6.33e-04
2022-05-04 10:04:31,216 INFO [train.py:715] (5/8) Epoch 2, batch 30650, loss[loss=0.1608, simple_loss=0.2279, pruned_loss=0.04683, over 4895.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2357, pruned_loss=0.05006, over 972868.85 frames.], batch size: 19, lr: 6.33e-04
2022-05-04 10:05:11,279 INFO [train.py:715] (5/8) Epoch 2, batch 30700, loss[loss=0.1918, simple_loss=0.2539, pruned_loss=0.06487, over 4827.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2361, pruned_loss=0.05059, over 973099.38 frames.], batch size: 15, lr: 6.33e-04
2022-05-04 10:05:51,101 INFO [train.py:715] (5/8) Epoch 2, batch 30750, loss[loss=0.1974, simple_loss=0.2737, pruned_loss=0.06052, over 4773.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2356, pruned_loss=0.05031, over 972726.38 frames.], batch size: 18, lr: 6.33e-04
2022-05-04 10:06:30,170 INFO [train.py:715] (5/8) Epoch 2, batch 30800, loss[loss=0.1566, simple_loss=0.225, pruned_loss=0.04415, over 4752.00 frames.], tot_loss[loss=0.168, simple_loss=0.2353, pruned_loss=0.05035, over 972153.26 frames.], batch size: 16, lr: 6.33e-04
2022-05-04 10:07:09,681 INFO [train.py:715] (5/8) Epoch 2, batch 30850, loss[loss=0.1703, simple_loss=0.2489, pruned_loss=0.04584, over 4893.00 frames.], tot_loss[loss=0.1686, simple_loss=0.236, pruned_loss=0.05061, over 972268.29 frames.], batch size: 17, lr: 6.33e-04
2022-05-04 10:07:49,326 INFO [train.py:715] (5/8) Epoch 2, batch 30900, loss[loss=0.187, simple_loss=0.2613, pruned_loss=0.0564, over 4976.00 frames.], tot_loss[loss=0.168, simple_loss=0.2354, pruned_loss=0.05033, over 971939.77 frames.], batch size: 15, lr: 6.32e-04
2022-05-04 10:08:27,844 INFO [train.py:715] (5/8) Epoch 2, batch 30950, loss[loss=0.1452, simple_loss=0.224, pruned_loss=0.03318, over 4834.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2357, pruned_loss=0.05043, over 971640.44 frames.], batch size: 30, lr: 6.32e-04
2022-05-04 10:09:07,791 INFO [train.py:715] (5/8) Epoch 2, batch 31000, loss[loss=0.1839, simple_loss=0.2585, pruned_loss=0.05468, over 4879.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2356, pruned_loss=0.0505, over 971771.41 frames.], batch size: 22, lr: 6.32e-04
2022-05-04 10:09:48,228 INFO [train.py:715] (5/8) Epoch 2, batch 31050, loss[loss=0.1951, simple_loss=0.2431, pruned_loss=0.07357, over 4890.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2354, pruned_loss=0.05044, over 971936.83 frames.], batch size: 32, lr: 6.32e-04
2022-05-04 10:10:27,709 INFO [train.py:715] (5/8) Epoch 2, batch 31100, loss[loss=0.1922, simple_loss=0.2296, pruned_loss=0.07744, over 4825.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2348, pruned_loss=0.05023, over 971993.02 frames.], batch size: 12, lr: 6.32e-04
2022-05-04 10:11:07,495 INFO [train.py:715] (5/8) Epoch 2, batch 31150, loss[loss=0.1514, simple_loss=0.2268, pruned_loss=0.03803, over 4814.00 frames.], tot_loss[loss=0.1673, simple_loss=0.235, pruned_loss=0.04981, over 972150.91 frames.], batch size: 25, lr: 6.32e-04
2022-05-04 10:11:47,660 INFO [train.py:715] (5/8) Epoch 2, batch 31200, loss[loss=0.155, simple_loss=0.224, pruned_loss=0.04297, over 4902.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2347, pruned_loss=0.05043, over 972338.05 frames.], batch size: 17, lr: 6.31e-04
2022-05-04 10:12:27,456 INFO [train.py:715] (5/8) Epoch 2, batch 31250, loss[loss=0.1665, simple_loss=0.2385, pruned_loss=0.0473, over 4981.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2358, pruned_loss=0.05116, over 972492.82 frames.], batch size: 14, lr: 6.31e-04
2022-05-04 10:13:06,650 INFO [train.py:715] (5/8) Epoch 2, batch 31300, loss[loss=0.1675, simple_loss=0.2329, pruned_loss=0.05103, over 4908.00 frames.], tot_loss[loss=0.1675, simple_loss=0.235, pruned_loss=0.05003, over 972312.91 frames.], batch size: 18, lr: 6.31e-04
2022-05-04 10:13:46,601 INFO [train.py:715] (5/8) Epoch 2, batch 31350, loss[loss=0.1994, simple_loss=0.263, pruned_loss=0.06791, over 4876.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05064, over 972494.69 frames.], batch size: 22, lr: 6.31e-04
2022-05-04 10:14:26,952 INFO [train.py:715] (5/8) Epoch 2, batch 31400, loss[loss=0.1382, simple_loss=0.2138, pruned_loss=0.03132, over 4790.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2349, pruned_loss=0.05066, over 972160.49 frames.], batch size: 24, lr: 6.31e-04
2022-05-04 10:15:06,594 INFO [train.py:715] (5/8) Epoch 2, batch 31450, loss[loss=0.1858, simple_loss=0.2491, pruned_loss=0.06128, over 4906.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2344, pruned_loss=0.05009, over 972742.62 frames.], batch size: 29, lr: 6.31e-04
2022-05-04 10:15:46,236 INFO [train.py:715] (5/8) Epoch 2, batch 31500, loss[loss=0.1673, simple_loss=0.2423, pruned_loss=0.04613, over 4696.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2351, pruned_loss=0.05024, over 972629.63 frames.], batch size: 15, lr: 6.31e-04
2022-05-04 10:16:26,029 INFO [train.py:715] (5/8) Epoch 2, batch 31550, loss[loss=0.1249, simple_loss=0.2029, pruned_loss=0.02342, over 4779.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2359, pruned_loss=0.05059, over 972853.97 frames.], batch size: 12, lr: 6.30e-04
2022-05-04 10:17:05,438 INFO [train.py:715] (5/8) Epoch 2, batch 31600, loss[loss=0.1658, simple_loss=0.2414, pruned_loss=0.04512, over 4853.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2359, pruned_loss=0.05036, over 972065.65 frames.], batch size: 20, lr: 6.30e-04
2022-05-04 10:17:44,220 INFO [train.py:715] (5/8) Epoch 2, batch 31650, loss[loss=0.1626, simple_loss=0.2409, pruned_loss=0.04211, over 4925.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2368, pruned_loss=0.05095, over 972712.21 frames.], batch size: 18, lr: 6.30e-04
2022-05-04 10:18:24,067 INFO [train.py:715] (5/8) Epoch 2, batch 31700, loss[loss=0.1677, simple_loss=0.2375, pruned_loss=0.04888, over 4806.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2375, pruned_loss=0.05128, over 972613.26 frames.], batch size: 21, lr: 6.30e-04
2022-05-04 10:19:04,302 INFO [train.py:715] (5/8) Epoch 2, batch 31750, loss[loss=0.1681, simple_loss=0.2401, pruned_loss=0.04803, over 4807.00 frames.], tot_loss[loss=0.17, simple_loss=0.2371, pruned_loss=0.05148, over 971595.52 frames.], batch size: 25, lr: 6.30e-04
2022-05-04 10:19:44,139 INFO [train.py:715] (5/8) Epoch 2, batch 31800, loss[loss=0.1872, simple_loss=0.254, pruned_loss=0.06024, over 4853.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2369, pruned_loss=0.05125, over 972180.84 frames.], batch size: 30, lr: 6.30e-04
2022-05-04 10:20:23,462 INFO [train.py:715] (5/8) Epoch 2, batch 31850, loss[loss=0.1821, simple_loss=0.2462, pruned_loss=0.05902, over 4831.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2377, pruned_loss=0.05169, over 971753.66 frames.], batch size: 30, lr: 6.29e-04
2022-05-04 10:21:02,953 INFO [train.py:715] (5/8) Epoch 2, batch 31900, loss[loss=0.1478, simple_loss=0.2204, pruned_loss=0.03761, over 4925.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2362, pruned_loss=0.0508, over 972732.59 frames.], batch size: 18, lr: 6.29e-04
2022-05-04 10:21:42,549 INFO [train.py:715] (5/8) Epoch 2, batch 31950, loss[loss=0.1618, simple_loss=0.2335, pruned_loss=0.04508, over 4782.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2359, pruned_loss=0.05026, over 973008.00 frames.], batch size: 17, lr: 6.29e-04
2022-05-04 10:22:21,472 INFO [train.py:715] (5/8) Epoch 2, batch 32000, loss[loss=0.1627, simple_loss=0.2259, pruned_loss=0.04973, over 4823.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2356, pruned_loss=0.05047, over 973632.24 frames.], batch size: 15, lr: 6.29e-04
2022-05-04 10:23:01,105 INFO [train.py:715] (5/8) Epoch 2, batch 32050, loss[loss=0.169, simple_loss=0.2365, pruned_loss=0.05074, over 4767.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2346, pruned_loss=0.0502, over 973198.04 frames.], batch size: 19, lr: 6.29e-04
2022-05-04 10:23:41,014 INFO [train.py:715] (5/8) Epoch 2, batch 32100, loss[loss=0.1682, simple_loss=0.2321, pruned_loss=0.05219, over 4891.00 frames.], tot_loss[loss=0.167, simple_loss=0.2341, pruned_loss=0.04993, over 973216.03 frames.], batch size: 16, lr: 6.29e-04
2022-05-04 10:24:20,300 INFO [train.py:715] (5/8) Epoch 2, batch 32150, loss[loss=0.187, simple_loss=0.2368, pruned_loss=0.06863, over 4829.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2334, pruned_loss=0.04904, over 972095.05 frames.], batch size: 15, lr: 6.29e-04
2022-05-04 10:24:59,275 INFO [train.py:715] (5/8) Epoch 2, batch 32200, loss[loss=0.1711, simple_loss=0.2329, pruned_loss=0.05461, over 4925.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2341, pruned_loss=0.04976, over 972936.80 frames.], batch size: 39, lr: 6.28e-04
2022-05-04 10:25:39,136 INFO [train.py:715] (5/8) Epoch 2, batch 32250, loss[loss=0.152, simple_loss=0.2284, pruned_loss=0.03778, over 4760.00 frames.], tot_loss[loss=0.167, simple_loss=0.2341, pruned_loss=0.04992, over 972822.46 frames.], batch size: 19, lr: 6.28e-04
2022-05-04 10:26:18,493 INFO [train.py:715] (5/8) Epoch 2, batch 32300, loss[loss=0.1551, simple_loss=0.2268, pruned_loss=0.04172, over 4978.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2341, pruned_loss=0.04983, over 972592.80 frames.], batch size: 14, lr: 6.28e-04
2022-05-04 10:26:57,487 INFO [train.py:715] (5/8) Epoch 2, batch 32350, loss[loss=0.1636, simple_loss=0.2336, pruned_loss=0.04676, over 4864.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2344, pruned_loss=0.0499, over 972950.92 frames.], batch size: 30, lr: 6.28e-04
2022-05-04 10:27:37,323 INFO [train.py:715] (5/8) Epoch 2, batch 32400, loss[loss=0.1527, simple_loss=0.2197, pruned_loss=0.04284, over 4764.00 frames.], tot_loss[loss=0.167, simple_loss=0.2341, pruned_loss=0.04997, over 972597.34 frames.], batch size: 14, lr: 6.28e-04
2022-05-04 10:28:17,091 INFO [train.py:715] (5/8) Epoch 2, batch 32450, loss[loss=0.1879, simple_loss=0.2472, pruned_loss=0.06433, over 4785.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2344, pruned_loss=0.05061, over 972100.10 frames.], batch size: 18, lr: 6.28e-04
2022-05-04 10:28:56,077 INFO [train.py:715] (5/8) Epoch 2, batch 32500, loss[loss=0.1658, simple_loss=0.2353, pruned_loss=0.04817, over 4926.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2344, pruned_loss=0.05044, over 972102.11 frames.], batch size: 18, lr: 6.27e-04
2022-05-04 10:29:35,591 INFO [train.py:715] (5/8) Epoch 2, batch 32550, loss[loss=0.1764, simple_loss=0.2402, pruned_loss=0.05637, over 4850.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2341, pruned_loss=0.05067, over 972291.95 frames.], batch size: 30, lr: 6.27e-04
2022-05-04 10:30:15,647 INFO [train.py:715] (5/8) Epoch 2, batch 32600, loss[loss=0.1413, simple_loss=0.2114, pruned_loss=0.03557, over 4872.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2347, pruned_loss=0.05081, over 971694.11 frames.], batch size: 22, lr: 6.27e-04
2022-05-04 10:30:54,903 INFO [train.py:715] (5/8) Epoch 2, batch 32650, loss[loss=0.1959, simple_loss=0.2433, pruned_loss=0.07427, over 4834.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2341, pruned_loss=0.05027, over 972044.15 frames.], batch size: 15, lr: 6.27e-04
2022-05-04 10:31:33,745 INFO [train.py:715] (5/8) Epoch 2, batch 32700, loss[loss=0.1406, simple_loss=0.2218, pruned_loss=0.02973, over 4934.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2336, pruned_loss=0.04988, over 971360.41 frames.], batch size: 29, lr: 6.27e-04
2022-05-04 10:32:13,538 INFO [train.py:715] (5/8) Epoch 2, batch 32750, loss[loss=0.2045, simple_loss=0.2646, pruned_loss=0.07225, over 4782.00 frames.], tot_loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04992, over 971347.99 frames.], batch size: 17, lr: 6.27e-04
2022-05-04 10:32:53,520 INFO [train.py:715] (5/8) Epoch 2, batch 32800, loss[loss=0.1662, simple_loss=0.2317, pruned_loss=0.05035, over 4811.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2355, pruned_loss=0.05066, over 971793.76 frames.], batch size: 26, lr: 6.27e-04
2022-05-04 10:33:32,249 INFO [train.py:715] (5/8) Epoch 2, batch 32850, loss[loss=0.1716, simple_loss=0.2466, pruned_loss=0.04832, over 4892.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2355, pruned_loss=0.05013, over 972613.90 frames.], batch size: 19, lr: 6.26e-04
2022-05-04 10:34:11,597 INFO [train.py:715] (5/8) Epoch 2, batch 32900, loss[loss=0.1851, simple_loss=0.2571, pruned_loss=0.05655, over 4763.00 frames.], tot_loss[loss=0.1684, simple_loss=0.236, pruned_loss=0.05042, over 973012.87 frames.], batch size: 19, lr: 6.26e-04
2022-05-04 10:34:51,513 INFO [train.py:715] (5/8) Epoch 2, batch 32950, loss[loss=0.1682, simple_loss=0.2299, pruned_loss=0.0532, over 4766.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2352, pruned_loss=0.05029, over 972491.65 frames.], batch size: 16, lr: 6.26e-04
2022-05-04 10:35:30,091 INFO [train.py:715] (5/8) Epoch 2, batch 33000, loss[loss=0.1486, simple_loss=0.2188, pruned_loss=0.03917, over 4913.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2347, pruned_loss=0.05001, over 971762.80 frames.], batch size: 29, lr: 6.26e-04
2022-05-04 10:35:30,091 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 10:35:38,852 INFO [train.py:742] (5/8) Epoch 2, validation: loss=0.1163, simple_loss=0.2025, pruned_loss=0.01504, over 914524.00 frames.
2022-05-04 10:36:17,839 INFO [train.py:715] (5/8) Epoch 2, batch 33050, loss[loss=0.1492, simple_loss=0.2208, pruned_loss=0.03883, over 4912.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2348, pruned_loss=0.04999, over 972004.04 frames.], batch size: 18, lr: 6.26e-04
2022-05-04 10:36:57,377 INFO [train.py:715] (5/8) Epoch 2, batch 33100, loss[loss=0.1518, simple_loss=0.2255, pruned_loss=0.03907, over 4820.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2354, pruned_loss=0.04967, over 972104.08 frames.], batch size: 13, lr: 6.26e-04
2022-05-04 10:37:37,175 INFO [train.py:715] (5/8) Epoch 2, batch 33150, loss[loss=0.198, simple_loss=0.2634, pruned_loss=0.06625, over 4694.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2351, pruned_loss=0.04977, over 971759.15 frames.], batch size: 15, lr: 6.25e-04
2022-05-04 10:38:16,780 INFO [train.py:715] (5/8) Epoch 2, batch 33200, loss[loss=0.1711, simple_loss=0.2294, pruned_loss=0.05645, over 4873.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2341, pruned_loss=0.04932, over 972275.20 frames.], batch size: 32, lr: 6.25e-04
2022-05-04 10:38:56,315 INFO [train.py:715] (5/8) Epoch 2, batch 33250, loss[loss=0.1616, simple_loss=0.2344, pruned_loss=0.04437, over 4839.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2346, pruned_loss=0.04945, over 973307.44 frames.], batch size: 15, lr: 6.25e-04
2022-05-04 10:39:35,520 INFO [train.py:715] (5/8) Epoch 2, batch 33300, loss[loss=0.1593, simple_loss=0.236, pruned_loss=0.04131, over 4834.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2341, pruned_loss=0.04917, over 973347.32 frames.], batch size: 15, lr: 6.25e-04
2022-05-04 10:40:14,693 INFO [train.py:715] (5/8) Epoch 2, batch 33350, loss[loss=0.1464, simple_loss=0.2227, pruned_loss=0.03502, over 4983.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.0495, over 973772.40 frames.], batch size: 39, lr: 6.25e-04
2022-05-04 10:40:53,958 INFO [train.py:715] (5/8) Epoch 2, batch 33400, loss[loss=0.2027, simple_loss=0.2655, pruned_loss=0.06996, over 4807.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2356, pruned_loss=0.04972, over 973662.82 frames.], batch size: 21, lr: 6.25e-04
2022-05-04 10:41:33,181 INFO [train.py:715] (5/8) Epoch 2, batch 33450, loss[loss=0.1424, simple_loss=0.2029, pruned_loss=0.04094, over 4830.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.04951, over 972415.56 frames.], batch size: 12, lr: 6.25e-04
2022-05-04 10:42:13,245 INFO [train.py:715] (5/8) Epoch 2, batch 33500, loss[loss=0.1385, simple_loss=0.2063, pruned_loss=0.03536, over 4791.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2345, pruned_loss=0.04955, over 972514.17 frames.], batch size: 14, lr: 6.24e-04
2022-05-04 10:42:52,005 INFO [train.py:715] (5/8) Epoch 2, batch 33550, loss[loss=0.1402, simple_loss=0.212, pruned_loss=0.03415, over 4906.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2339, pruned_loss=0.04946, over 973076.83 frames.], batch size: 22, lr: 6.24e-04
2022-05-04 10:43:31,502 INFO [train.py:715] (5/8) Epoch 2, batch 33600, loss[loss=0.18, simple_loss=0.2412, pruned_loss=0.05936, over 4967.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2342, pruned_loss=0.04973, over 972984.57 frames.], batch size: 14, lr: 6.24e-04
2022-05-04 10:44:11,049 INFO [train.py:715] (5/8) Epoch 2, batch 33650, loss[loss=0.1579, simple_loss=0.2337, pruned_loss=0.04106, over 4852.00 frames.], tot_loss[loss=0.168, simple_loss=0.2355, pruned_loss=0.05028, over 972096.27 frames.], batch size: 12, lr: 6.24e-04
2022-05-04 10:44:50,485 INFO [train.py:715] (5/8) Epoch 2, batch 33700, loss[loss=0.2006, simple_loss=0.2751, pruned_loss=0.06305, over 4712.00 frames.], tot_loss[loss=0.168, simple_loss=0.2354, pruned_loss=0.05034, over 971565.68 frames.], batch size: 15, lr: 6.24e-04
2022-05-04 10:45:29,904 INFO [train.py:715] (5/8) Epoch 2, batch 33750, loss[loss=0.1622, simple_loss=0.2342, pruned_loss=0.04508, over 4938.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2352, pruned_loss=0.05052, over 972657.89 frames.], batch size: 21, lr: 6.24e-04
2022-05-04 10:46:09,309 INFO [train.py:715] (5/8) Epoch 2, batch 33800, loss[loss=0.1777, simple_loss=0.2363, pruned_loss=0.05956, over 4974.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2342, pruned_loss=0.05002, over 972854.88 frames.], batch size: 14, lr: 6.23e-04
2022-05-04 10:46:49,487 INFO [train.py:715] (5/8) Epoch 2, batch 33850, loss[loss=0.162, simple_loss=0.224, pruned_loss=0.05004, over 4694.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2344, pruned_loss=0.05013, over 973408.60 frames.], batch size: 15, lr: 6.23e-04
2022-05-04 10:47:28,883 INFO [train.py:715] (5/8) Epoch 2, batch 33900, loss[loss=0.1785, simple_loss=0.2496, pruned_loss=0.05366, over 4983.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2348, pruned_loss=0.0508, over 973711.01 frames.], batch size: 25, lr: 6.23e-04
2022-05-04 10:48:08,026 INFO [train.py:715] (5/8) Epoch 2, batch 33950, loss[loss=0.1672, simple_loss=0.2369, pruned_loss=0.04877, over 4982.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2352, pruned_loss=0.05086, over 973538.09 frames.], batch size: 25, lr: 6.23e-04
2022-05-04 10:48:47,951 INFO [train.py:715] (5/8) Epoch 2, batch 34000, loss[loss=0.1437, simple_loss=0.2111, pruned_loss=0.03816, over 4927.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2355, pruned_loss=0.05108, over 973498.28 frames.], batch size: 18, lr: 6.23e-04
2022-05-04 10:49:27,580 INFO [train.py:715] (5/8) Epoch 2, batch 34050, loss[loss=0.1459, simple_loss=0.2251, pruned_loss=0.03336, over 4918.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2353, pruned_loss=0.05082, over 973366.91 frames.], batch size: 18, lr: 6.23e-04
2022-05-04 10:50:07,045 INFO [train.py:715] (5/8) Epoch 2, batch 34100, loss[loss=0.1944, simple_loss=0.2598, pruned_loss=0.06455, over 4960.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2353, pruned_loss=0.05087, over 973036.72 frames.], batch size: 35, lr: 6.23e-04
2022-05-04 10:50:46,459 INFO [train.py:715] (5/8) Epoch 2, batch 34150, loss[loss=0.1168, simple_loss=0.1932, pruned_loss=0.02025, over 4847.00 frames.], tot_loss[loss=0.168, simple_loss=0.2348, pruned_loss=0.05058, over 973334.05 frames.], batch size: 12, lr: 6.22e-04
2022-05-04 10:51:26,744 INFO [train.py:715] (5/8) Epoch 2, batch 34200, loss[loss=0.1592, simple_loss=0.2414, pruned_loss=0.03853, over 4860.00 frames.], tot_loss[loss=0.168, simple_loss=0.2352, pruned_loss=0.05046, over 973190.49 frames.], batch size: 20, lr: 6.22e-04
2022-05-04 10:52:06,315 INFO [train.py:715] (5/8) Epoch 2, batch 34250, loss[loss=0.2319, simple_loss=0.2959, pruned_loss=0.08393, over 4967.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2349, pruned_loss=0.04996, over 972292.59 frames.], batch size: 24, lr: 6.22e-04
2022-05-04 10:52:45,480 INFO [train.py:715] (5/8) Epoch 2, batch 34300, loss[loss=0.1752, simple_loss=0.2506, pruned_loss=0.04988, over 4929.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2331, pruned_loss=0.04888, over 971441.70 frames.], batch size: 21, lr: 6.22e-04
2022-05-04 10:53:25,366 INFO [train.py:715] (5/8) Epoch 2, batch 34350, loss[loss=0.1778, simple_loss=0.2531, pruned_loss=0.05124, over 4900.00 frames.], tot_loss[loss=0.166, simple_loss=0.2333, pruned_loss=0.04937, over 971053.94 frames.], batch size: 19, lr: 6.22e-04
2022-05-04 10:54:07,390 INFO [train.py:715] (5/8) Epoch 2, batch 34400, loss[loss=0.1683, simple_loss=0.2394, pruned_loss=0.04859, over 4755.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2338, pruned_loss=0.05005, over 970621.63 frames.], batch size: 16, lr: 6.22e-04
2022-05-04 10:54:46,513 INFO [train.py:715] (5/8) Epoch 2, batch 34450, loss[loss=0.16, simple_loss=0.2294, pruned_loss=0.04535, over 4897.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2341, pruned_loss=0.05029, over 971574.14 frames.], batch size: 39, lr: 6.22e-04
2022-05-04 10:55:25,437 INFO [train.py:715] (5/8) Epoch 2, batch 34500, loss[loss=0.1622, simple_loss=0.2347, pruned_loss=0.04488, over 4770.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2347, pruned_loss=0.05086, over 971980.65 frames.], batch size: 14, lr: 6.21e-04
2022-05-04 10:56:05,346 INFO [train.py:715] (5/8) Epoch 2, batch 34550, loss[loss=0.1558, simple_loss=0.2261, pruned_loss=0.04274, over 4846.00 frames.], tot_loss[loss=0.168, simple_loss=0.2345, pruned_loss=0.05071, over 972743.99 frames.], batch size: 32, lr: 6.21e-04
2022-05-04 10:56:44,132 INFO [train.py:715] (5/8) Epoch 2, batch 34600, loss[loss=0.1652, simple_loss=0.2315, pruned_loss=0.04944, over 4932.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2342, pruned_loss=0.05029, over 972843.50 frames.], batch size: 21, lr: 6.21e-04
2022-05-04 10:57:23,173 INFO [train.py:715] (5/8) Epoch 2, batch 34650, loss[loss=0.1788, simple_loss=0.241, pruned_loss=0.05831, over 4829.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2345, pruned_loss=0.05065, over 973026.43 frames.], batch size: 13, lr: 6.21e-04
2022-05-04 10:58:02,538 INFO [train.py:715] (5/8) Epoch 2, batch 34700, loss[loss=0.2144, simple_loss=0.2725, pruned_loss=0.07817, over 4780.00 frames.], tot_loss[loss=0.1685, simple_loss=0.235, pruned_loss=0.05099, over 973142.07 frames.], batch size: 17, lr: 6.21e-04
2022-05-04 10:58:40,563 INFO [train.py:715] (5/8) Epoch 2, batch 34750, loss[loss=0.1862, simple_loss=0.2511, pruned_loss=0.06067, over 4858.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2352, pruned_loss=0.05101, over 973448.18 frames.], batch size: 13, lr: 6.21e-04
2022-05-04 10:59:17,104 INFO [train.py:715] (5/8) Epoch 2, batch 34800, loss[loss=0.1425, simple_loss=0.213, pruned_loss=0.03596, over 4782.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.05109, over 972853.01 frames.], batch size: 12, lr: 6.20e-04
2022-05-04 11:00:07,063 INFO [train.py:715] (5/8) Epoch 3, batch 0, loss[loss=0.1307, simple_loss=0.1925, pruned_loss=0.03448, over 4801.00 frames.], tot_loss[loss=0.1307, simple_loss=0.1925, pruned_loss=0.03448, over 4801.00 frames.], batch size: 12, lr: 5.87e-04
2022-05-04 11:00:45,739 INFO [train.py:715] (5/8) Epoch 3, batch 50, loss[loss=0.1459, simple_loss=0.2124, pruned_loss=0.03976, over 4779.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2332, pruned_loss=0.05062, over 219005.82 frames.], batch size: 17, lr: 5.87e-04
2022-05-04 11:01:25,682 INFO [train.py:715] (5/8) Epoch 3, batch 100, loss[loss=0.165, simple_loss=0.2323, pruned_loss=0.04885, over 4945.00 frames.], tot_loss[loss=0.1699, simple_loss=0.236, pruned_loss=0.05187, over 386414.99 frames.], batch size: 29, lr: 5.87e-04
2022-05-04 11:02:05,237 INFO [train.py:715] (5/8) Epoch 3, batch 150, loss[loss=0.1766, simple_loss=0.2386, pruned_loss=0.05727, over 4851.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2345, pruned_loss=0.05087, over 516654.00 frames.], batch size: 30, lr: 5.86e-04
2022-05-04 11:02:44,383 INFO [train.py:715] (5/8) Epoch 3, batch 200, loss[loss=0.1257, simple_loss=0.2064, pruned_loss=0.02255, over 4818.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2337, pruned_loss=0.0499, over 618247.71 frames.], batch size: 25, lr: 5.86e-04
2022-05-04 11:03:23,624 INFO [train.py:715] (5/8) Epoch 3, batch 250, loss[loss=0.1791, simple_loss=0.2338, pruned_loss=0.06224, over 4826.00 frames.], tot_loss[loss=0.1667, simple_loss=0.234, pruned_loss=0.04973, over 697224.97 frames.], batch size: 13, lr: 5.86e-04
2022-05-04 11:04:03,632 INFO [train.py:715] (5/8) Epoch 3, batch 300, loss[loss=0.1619, simple_loss=0.2397, pruned_loss=0.04201, over 4847.00 frames.], tot_loss[loss=0.1648, simple_loss=0.233, pruned_loss=0.04829, over 757731.88 frames.], batch size: 26, lr: 5.86e-04
2022-05-04 11:04:42,643 INFO [train.py:715] (5/8) Epoch 3, batch 350, loss[loss=0.1812, simple_loss=0.2462, pruned_loss=0.0581, over 4756.00 frames.], tot_loss[loss=0.1668, simple_loss=0.235, pruned_loss=0.04934, over 805414.23 frames.], batch size: 16, lr: 5.86e-04
2022-05-04 11:05:21,843 INFO [train.py:715] (5/8) Epoch 3, batch 400, loss[loss=0.1318, simple_loss=0.2048, pruned_loss=0.02943, over 4989.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.04853, over 842317.75 frames.], batch size: 25, lr: 5.86e-04
2022-05-04 11:06:01,611 INFO [train.py:715] (5/8) Epoch 3, batch 450, loss[loss=0.1405, simple_loss=0.2238, pruned_loss=0.0286, over 4821.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2345, pruned_loss=0.04947, over 871047.57 frames.], batch size: 21, lr: 5.86e-04
2022-05-04 11:06:41,122 INFO [train.py:715] (5/8) Epoch 3, batch 500, loss[loss=0.1616, simple_loss=0.2355, pruned_loss=0.04384, over 4844.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2344, pruned_loss=0.04923, over 893022.16 frames.], batch size: 30, lr: 5.85e-04
2022-05-04 11:07:20,466 INFO [train.py:715] (5/8) Epoch 3, batch 550, loss[loss=0.1686, simple_loss=0.23, pruned_loss=0.05361, over 4852.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2339, pruned_loss=0.04879, over 911162.30 frames.], batch size: 15, lr: 5.85e-04
2022-05-04 11:07:59,337 INFO [train.py:715] (5/8) Epoch 3, batch 600, loss[loss=0.1486, simple_loss=0.2124, pruned_loss=0.04236, over 4812.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2322, pruned_loss=0.04803, over 924880.40 frames.], batch size: 13, lr: 5.85e-04
2022-05-04 11:08:39,294 INFO [train.py:715] (5/8) Epoch 3, batch 650, loss[loss=0.1972, simple_loss=0.253, pruned_loss=0.07066, over 4962.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2326, pruned_loss=0.04837, over 935642.27 frames.], batch size: 15, lr: 5.85e-04
2022-05-04 11:09:18,635 INFO [train.py:715] (5/8) Epoch 3, batch 700, loss[loss=0.1599, simple_loss=0.2368, pruned_loss=0.04147, over 4839.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2333, pruned_loss=0.04831, over 943490.24 frames.], batch size: 13, lr: 5.85e-04
2022-05-04 11:09:57,737 INFO [train.py:715] (5/8) Epoch 3, batch 750, loss[loss=0.1402, simple_loss=0.2209, pruned_loss=0.02976, over 4919.00 frames.], tot_loss[loss=0.165, simple_loss=0.2333, pruned_loss=0.04835, over 950282.74 frames.], batch size: 29, lr: 5.85e-04
2022-05-04 11:10:37,302 INFO [train.py:715] (5/8) Epoch 3, batch 800, loss[loss=0.1643, simple_loss=0.2263, pruned_loss=0.05112, over 4799.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2335, pruned_loss=0.04874, over 954998.61 frames.], batch size: 21, lr: 5.85e-04
2022-05-04 11:11:17,439 INFO [train.py:715] (5/8) Epoch 3, batch 850, loss[loss=0.1883, simple_loss=0.2526, pruned_loss=0.06194, over 4867.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2337, pruned_loss=0.04948, over 959124.86 frames.], batch size: 38, lr: 5.84e-04
2022-05-04 11:11:56,827 INFO [train.py:715] (5/8) Epoch 3, batch 900, loss[loss=0.1519, simple_loss=0.2167, pruned_loss=0.04356, over 4965.00 frames.], tot_loss[loss=0.166, simple_loss=0.2332, pruned_loss=0.04938, over 962753.58 frames.], batch size: 35, lr: 5.84e-04
2022-05-04 11:12:35,438 INFO [train.py:715] (5/8) Epoch 3, batch 950, loss[loss=0.1546, simple_loss=0.2316, pruned_loss=0.03882, over 4969.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2336, pruned_loss=0.04973, over 965396.35 frames.], batch size: 14, lr: 5.84e-04
2022-05-04 11:13:15,423 INFO [train.py:715] (5/8) Epoch 3, batch 1000, loss[loss=0.1736, simple_loss=0.2293, pruned_loss=0.05888, over 4702.00 frames.], tot_loss[loss=0.167, simple_loss=0.2337, pruned_loss=0.05016, over 966627.33 frames.], batch size: 15, lr: 5.84e-04
2022-05-04 11:13:55,091 INFO [train.py:715] (5/8) Epoch 3, batch 1050, loss[loss=0.1652, simple_loss=0.2299, pruned_loss=0.05032, over 4780.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2334, pruned_loss=0.04967, over 967104.16 frames.], batch size: 14, lr: 5.84e-04
2022-05-04 11:14:34,002 INFO [train.py:715] (5/8) Epoch 3, batch 1100, loss[loss=0.2053, simple_loss=0.2547, pruned_loss=0.07793, over 4848.00 frames.], tot_loss[loss=0.1656, simple_loss=0.233, pruned_loss=0.04911, over 968701.33 frames.], batch size: 34, lr: 5.84e-04
2022-05-04 11:15:12,875 INFO [train.py:715] (5/8) Epoch 3, batch 1150, loss[loss=0.1584, simple_loss=0.2336, pruned_loss=0.04166, over 4706.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2341, pruned_loss=0.04941, over 969646.96 frames.], batch size: 15, lr: 5.84e-04
2022-05-04 11:15:52,681 INFO [train.py:715] (5/8) Epoch 3, batch 1200, loss[loss=0.173, simple_loss=0.2459, pruned_loss=0.05003, over 4984.00 frames.], tot_loss[loss=0.165, simple_loss=0.2331, pruned_loss=0.04844, over 971095.03 frames.], batch size: 24, lr: 5.83e-04
2022-05-04 11:16:31,655 INFO [train.py:715] (5/8) Epoch 3, batch 1250, loss[loss=0.2134, simple_loss=0.2753, pruned_loss=0.07571, over 4701.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2338, pruned_loss=0.04946, over 970664.71 frames.], batch size: 15, lr: 5.83e-04
2022-05-04 11:17:10,162 INFO [train.py:715] (5/8) Epoch 3, batch 1300, loss[loss=0.1602, simple_loss=0.2318, pruned_loss=0.04432, over 4914.00 frames.], tot_loss[loss=0.166, simple_loss=0.2336, pruned_loss=0.04918, over 971688.33 frames.], batch size: 29, lr: 5.83e-04
2022-05-04 11:17:49,721 INFO [train.py:715] (5/8) Epoch 3, batch 1350, loss[loss=0.1522, simple_loss=0.2296, pruned_loss=0.03738, over 4922.00 frames.], tot_loss[loss=0.166, simple_loss=0.2338, pruned_loss=0.04905, over 971168.64 frames.], batch size: 29, lr: 5.83e-04
2022-05-04 11:18:28,998 INFO [train.py:715] (5/8) Epoch 3, batch 1400, loss[loss=0.1514, simple_loss=0.2127, pruned_loss=0.04505, over 4842.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2337, pruned_loss=0.04906, over 971339.39 frames.], batch size: 32, lr: 5.83e-04
2022-05-04 11:19:07,864 INFO [train.py:715] (5/8) Epoch 3, batch 1450, loss[loss=0.1828, simple_loss=0.2563, pruned_loss=0.05472, over 4790.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2335, pruned_loss=0.04909, over 971299.37 frames.], batch size: 17, lr: 5.83e-04
2022-05-04 11:19:46,420 INFO [train.py:715] (5/8) Epoch 3, batch 1500, loss[loss=0.145, simple_loss=0.2251, pruned_loss=0.0325, over 4814.00 frames.], tot_loss[loss=0.1649, simple_loss=0.233, pruned_loss=0.04842, over 971416.18 frames.], batch size: 21, lr: 5.83e-04
2022-05-04 11:20:26,147 INFO [train.py:715] (5/8) Epoch 3, batch 1550, loss[loss=0.1727, simple_loss=0.2448, pruned_loss=0.05036, over 4973.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2335, pruned_loss=0.04888, over 971904.12 frames.], batch size: 24, lr: 5.83e-04
2022-05-04 11:21:05,411 INFO [train.py:715] (5/8) Epoch 3, batch 1600, loss[loss=0.1347, simple_loss=0.2156, pruned_loss=0.02692, over 4989.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.0488, over 972799.32 frames.], batch size: 28, lr: 5.82e-04
2022-05-04 11:21:43,530 INFO [train.py:715] (5/8) Epoch 3, batch 1650, loss[loss=0.1497, simple_loss=0.2221, pruned_loss=0.03862, over 4949.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2327, pruned_loss=0.04833, over 973398.21 frames.], batch size: 35, lr: 5.82e-04
2022-05-04 11:22:22,779 INFO [train.py:715] (5/8) Epoch 3, batch 1700, loss[loss=0.1648, simple_loss=0.2424, pruned_loss=0.04361, over 4828.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04797, over 972939.93 frames.], batch size: 27, lr: 5.82e-04
2022-05-04 11:23:02,317 INFO [train.py:715] (5/8) Epoch 3, batch 1750, loss[loss=0.1686, simple_loss=0.2239, pruned_loss=0.05669, over 4759.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2329, pruned_loss=0.04836, over 972805.99 frames.], batch size: 19, lr: 5.82e-04
2022-05-04 11:23:41,619 INFO [train.py:715] (5/8) Epoch 3, batch 1800, loss[loss=0.182, simple_loss=0.2431, pruned_loss=0.06045, over 4857.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2329, pruned_loss=0.04823, over 973479.58 frames.], batch size: 20, lr: 5.82e-04
2022-05-04 11:24:20,318 INFO [train.py:715] (5/8) Epoch 3, batch 1850, loss[loss=0.1259, simple_loss=0.1967, pruned_loss=0.02757, over 4839.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2331, pruned_loss=0.04868, over 973779.71 frames.], batch size: 13, lr: 5.82e-04
2022-05-04 11:25:00,294 INFO [train.py:715] (5/8) Epoch 3, batch 1900, loss[loss=0.1778, simple_loss=0.2382, pruned_loss=0.05869, over 4976.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2321, pruned_loss=0.04827, over 974158.98 frames.], batch size: 35, lr: 5.82e-04
2022-05-04 11:25:39,886 INFO [train.py:715] (5/8) Epoch 3, batch 1950, loss[loss=0.1783, simple_loss=0.2452, pruned_loss=0.05572, over 4956.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2332, pruned_loss=0.04914, over 973424.49 frames.], batch size: 39, lr: 5.81e-04
2022-05-04 11:26:18,803 INFO [train.py:715] (5/8) Epoch 3, batch 2000, loss[loss=0.2259, simple_loss=0.2744, pruned_loss=0.08871, over 4779.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2335, pruned_loss=0.04914, over 972759.72 frames.], batch size: 18, lr: 5.81e-04
2022-05-04 11:26:58,010 INFO [train.py:715] (5/8) Epoch 3, batch 2050, loss[loss=0.1704, simple_loss=0.2403, pruned_loss=0.05028, over 4855.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2336, pruned_loss=0.04906, over 971665.86 frames.], batch size: 38, lr: 5.81e-04
2022-05-04 11:27:37,794 INFO [train.py:715] (5/8) Epoch 3, batch 2100, loss[loss=0.1555, simple_loss=0.2272, pruned_loss=0.04189, over 4736.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2338, pruned_loss=0.04918, over 971964.34 frames.], batch size: 16, lr: 5.81e-04
2022-05-04 11:28:17,048 INFO [train.py:715] (5/8) Epoch 3, batch 2150, loss[loss=0.1692, simple_loss=0.2267, pruned_loss=0.05588, over 4753.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2334, pruned_loss=0.04897, over 971288.13 frames.], batch size: 16, lr: 5.81e-04
2022-05-04 11:28:55,720 INFO [train.py:715] (5/8) Epoch 3, batch 2200, loss[loss=0.1247, simple_loss=0.1862, pruned_loss=0.03154, over 4818.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2339, pruned_loss=0.04927, over 972120.19 frames.], batch size: 13, lr: 5.81e-04
2022-05-04 11:29:35,101 INFO [train.py:715] (5/8) Epoch 3, batch 2250, loss[loss=0.1702, simple_loss=0.2358, pruned_loss=0.05233, over 4888.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2329, pruned_loss=0.04901, over 972469.19 frames.], batch size: 32, lr: 5.81e-04
2022-05-04 11:30:14,520 INFO [train.py:715] (5/8) Epoch 3, batch 2300, loss[loss=0.1659, simple_loss=0.2421, pruned_loss=0.04482, over 4858.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2332, pruned_loss=0.04927, over 971785.00 frames.], batch size: 20, lr: 5.80e-04
2022-05-04 11:30:53,578 INFO [train.py:715] (5/8) Epoch 3, batch 2350, loss[loss=0.1603, simple_loss=0.2287, pruned_loss=0.04598, over 4858.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2328, pruned_loss=0.04899, over 971441.75 frames.], batch size: 30, lr: 5.80e-04
2022-05-04 11:31:32,372 INFO [train.py:715] (5/8) Epoch 3, batch 2400, loss[loss=0.1374, simple_loss=0.2175, pruned_loss=0.02859, over 4817.00 frames.], tot_loss[loss=0.166, simple_loss=0.2334, pruned_loss=0.04929, over 971799.56 frames.], batch size: 27, lr: 5.80e-04
2022-05-04 11:32:12,610 INFO [train.py:715] (5/8) Epoch 3, batch 2450, loss[loss=0.1598, simple_loss=0.2271, pruned_loss=0.04625, over 4812.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2332, pruned_loss=0.04898, over 972087.58 frames.], batch size: 24, lr: 5.80e-04
2022-05-04 11:32:51,963 INFO [train.py:715] (5/8) Epoch 3, batch 2500, loss[loss=0.1739, simple_loss=0.2394, pruned_loss=0.05418, over 4977.00 frames.], tot_loss[loss=0.164, simple_loss=0.232, pruned_loss=0.04796, over 971768.68 frames.], batch size: 31, lr: 5.80e-04
2022-05-04 11:33:30,787 INFO [train.py:715] (5/8) Epoch 3, batch 2550, loss[loss=0.154, simple_loss=0.2222, pruned_loss=0.0429, over 4974.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2324, pruned_loss=0.04818, over 971593.62 frames.], batch size: 24, lr: 5.80e-04
2022-05-04 11:34:11,446 INFO [train.py:715] (5/8) Epoch 3, batch 2600, loss[loss=0.1738, simple_loss=0.2456, pruned_loss=0.05104, over 4962.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2329, pruned_loss=0.04859, over 971509.19 frames.], batch size: 24, lr: 5.80e-04
2022-05-04 11:34:51,560 INFO [train.py:715] (5/8) Epoch 3, batch 2650, loss[loss=0.1649, simple_loss=0.2303, pruned_loss=0.04975, over 4773.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2337, pruned_loss=0.04897, over 970597.15 frames.], batch size: 18, lr: 5.80e-04
2022-05-04 11:35:30,754 INFO [train.py:715] (5/8) Epoch 3, batch 2700, loss[loss=0.2024, simple_loss=0.2752, pruned_loss=0.06477, over 4893.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2343, pruned_loss=0.04895, over 971239.31 frames.], batch size: 19, lr: 5.79e-04
2022-05-04 11:36:10,257 INFO [train.py:715] (5/8) Epoch 3, batch 2750, loss[loss=0.1729, simple_loss=0.2334, pruned_loss=0.0562, over 4852.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2328, pruned_loss=0.04812, over 971044.76 frames.], batch size: 32, lr: 5.79e-04
2022-05-04 11:36:50,509 INFO [train.py:715] (5/8) Epoch 3, batch 2800, loss[loss=0.1641, simple_loss=0.2365, pruned_loss=0.04592, over 4917.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2319, pruned_loss=0.04745, over 971527.58 frames.], batch size: 17, lr: 5.79e-04
2022-05-04 11:37:29,792 INFO [train.py:715] (5/8) Epoch 3, batch 2850, loss[loss=0.1884, simple_loss=0.2513, pruned_loss=0.06272, over 4882.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04742, over 972517.75 frames.], batch size: 22, lr: 5.79e-04
2022-05-04 11:38:08,468 INFO [train.py:715] (5/8) Epoch 3, batch 2900, loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03941, over 4816.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2315, pruned_loss=0.04739, over 971326.35 frames.], batch size: 26, lr: 5.79e-04
2022-05-04 11:38:48,424 INFO [train.py:715] (5/8) Epoch 3, batch 2950, loss[loss=0.144, simple_loss=0.2045, pruned_loss=0.04177, over 4813.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04731, over 970691.71 frames.], batch size: 12, lr: 5.79e-04
2022-05-04 11:39:28,057 INFO [train.py:715] (5/8) Epoch 3, batch 3000, loss[loss=0.1638, simple_loss=0.229, pruned_loss=0.04932, over 4791.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2323, pruned_loss=0.04816, over 970990.31 frames.], batch size: 24, lr: 5.79e-04
2022-05-04 11:39:28,057 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 11:39:36,790 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1153, simple_loss=0.2015, pruned_loss=0.0146, over 914524.00 frames.
2022-05-04 11:40:16,885 INFO [train.py:715] (5/8) Epoch 3, batch 3050, loss[loss=0.1562, simple_loss=0.2239, pruned_loss=0.04427, over 4889.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2321, pruned_loss=0.04822, over 971469.86 frames.], batch size: 22, lr: 5.78e-04
2022-05-04 11:40:55,667 INFO [train.py:715] (5/8) Epoch 3, batch 3100, loss[loss=0.1496, simple_loss=0.2221, pruned_loss=0.03857, over 4741.00 frames.], tot_loss[loss=0.165, simple_loss=0.2328, pruned_loss=0.04863, over 970937.63 frames.], batch size: 12, lr: 5.78e-04
2022-05-04 11:41:35,054 INFO [train.py:715] (5/8) Epoch 3, batch 3150, loss[loss=0.2107, simple_loss=0.2626, pruned_loss=0.07942, over 4752.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04887, over 971170.99 frames.], batch size: 16, lr: 5.78e-04
2022-05-04 11:42:14,855 INFO [train.py:715] (5/8) Epoch 3, batch 3200, loss[loss=0.1747, simple_loss=0.2318, pruned_loss=0.05877, over 4826.00 frames.], tot_loss[loss=0.166, simple_loss=0.2339, pruned_loss=0.049, over 972215.06 frames.], batch size: 26, lr: 5.78e-04
2022-05-04 11:42:54,654 INFO [train.py:715] (5/8) Epoch 3, batch 3250, loss[loss=0.1659, simple_loss=0.2338, pruned_loss=0.04899, over 4921.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2332, pruned_loss=0.04868, over 971952.67 frames.], batch size: 17, lr: 5.78e-04
2022-05-04 11:43:33,194 INFO [train.py:715] (5/8) Epoch 3, batch 3300, loss[loss=0.1638, simple_loss=0.2372, pruned_loss=0.04521, over 4889.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2346, pruned_loss=0.0492, over 972925.91 frames.], batch size: 16, lr: 5.78e-04
2022-05-04 11:44:13,008 INFO [train.py:715] (5/8) Epoch 3, batch 3350, loss[loss=0.1484, simple_loss=0.2193, pruned_loss=0.03876, over 4931.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2339, pruned_loss=0.04865, over 973154.66 frames.], batch size: 29, lr: 5.78e-04
2022-05-04 11:44:52,484 INFO [train.py:715] (5/8) Epoch 3, batch 3400, loss[loss=0.1388, simple_loss=0.2069, pruned_loss=0.03541, over 4873.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2343, pruned_loss=0.04896, over 973702.62 frames.], batch size: 16, lr: 5.77e-04
2022-05-04 11:45:31,169 INFO [train.py:715] (5/8) Epoch 3, batch 3450, loss[loss=0.1533, simple_loss=0.2165, pruned_loss=0.04511, over 4811.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2347, pruned_loss=0.04905, over 974029.24 frames.], batch size: 13, lr: 5.77e-04
2022-05-04 11:46:10,503 INFO [train.py:715] (5/8) Epoch 3, batch 3500, loss[loss=0.1592, simple_loss=0.2292, pruned_loss=0.0446, over 4804.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2348, pruned_loss=0.04935, over 974087.06 frames.], batch size: 25, lr: 5.77e-04
2022-05-04 11:46:50,808 INFO [train.py:715] (5/8) Epoch 3, batch 3550, loss[loss=0.1433, simple_loss=0.2179, pruned_loss=0.03436, over 4842.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2334, pruned_loss=0.04899, over 973789.28 frames.], batch size: 13, lr: 5.77e-04
2022-05-04 11:47:30,665 INFO [train.py:715] (5/8) Epoch 3, batch 3600, loss[loss=0.1514, simple_loss=0.2268, pruned_loss=0.03797, over 4854.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2327, pruned_loss=0.04858, over 972677.44 frames.], batch size: 20, lr: 5.77e-04
2022-05-04 11:48:09,899 INFO [train.py:715] (5/8) Epoch 3, batch 3650, loss[loss=0.1655, simple_loss=0.2261, pruned_loss=0.05242, over 4808.00 frames.], tot_loss[loss=0.1653, simple_loss=0.233, pruned_loss=0.04876, over 972647.26 frames.], batch size: 25, lr: 5.77e-04
2022-05-04 11:48:49,626 INFO [train.py:715] (5/8) Epoch 3, batch 3700, loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03147, over 4767.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2347, pruned_loss=0.0498, over 972605.00 frames.], batch size: 17, lr: 5.77e-04
2022-05-04 11:49:29,642 INFO [train.py:715] (5/8) Epoch 3, batch 3750, loss[loss=0.2203, simple_loss=0.2743, pruned_loss=0.08314, over 4765.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2346, pruned_loss=0.04982, over 972517.29 frames.], batch size: 14, lr: 5.77e-04
2022-05-04 11:50:09,329 INFO [train.py:715] (5/8) Epoch 3, batch 3800, loss[loss=0.1452, simple_loss=0.2192, pruned_loss=0.03556, over 4891.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2334, pruned_loss=0.04901, over 973555.90 frames.], batch size: 22, lr: 5.76e-04
2022-05-04 11:50:48,714 INFO [train.py:715] (5/8) Epoch 3, batch 3850, loss[loss=0.1457, simple_loss=0.2203, pruned_loss=0.03549, over 4942.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2336, pruned_loss=0.04892, over 973324.40 frames.], batch size: 23, lr: 5.76e-04
2022-05-04 11:51:28,562 INFO [train.py:715] (5/8) Epoch 3, batch 3900, loss[loss=0.1653, simple_loss=0.2268, pruned_loss=0.0519, over 4840.00 frames.], tot_loss[loss=0.1661, simple_loss=0.234, pruned_loss=0.04904, over 972837.66 frames.], batch size: 13, lr: 5.76e-04
2022-05-04 11:52:08,060 INFO [train.py:715] (5/8) Epoch 3, batch 3950, loss[loss=0.2258, simple_loss=0.2579, pruned_loss=0.09686, over 4975.00 frames.], tot_loss[loss=0.167, simple_loss=0.2347, pruned_loss=0.04968, over 973158.37 frames.], batch size: 15, lr: 5.76e-04
2022-05-04 11:52:47,080 INFO [train.py:715] (5/8) Epoch 3, batch 4000, loss[loss=0.1815, simple_loss=0.2596, pruned_loss=0.05173, over 4976.00 frames.], tot_loss[loss=0.167, simple_loss=0.2346, pruned_loss=0.04972, over 973448.60 frames.], batch size: 28, lr: 5.76e-04
2022-05-04 11:53:26,527 INFO [train.py:715] (5/8) Epoch 3, batch 4050, loss[loss=0.1383, simple_loss=0.2123, pruned_loss=0.03211, over 4886.00 frames.], tot_loss[loss=0.166, simple_loss=0.2336, pruned_loss=0.04921, over 973742.44 frames.], batch size: 19, lr: 5.76e-04
2022-05-04 11:54:06,701 INFO [train.py:715] (5/8) Epoch 3, batch 4100, loss[loss=0.1833, simple_loss=0.2516, pruned_loss=0.05753, over 4839.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2334, pruned_loss=0.04914, over 972277.79 frames.], batch size: 15, lr: 5.76e-04
2022-05-04 11:54:45,655 INFO [train.py:715] (5/8) Epoch 3, batch 4150, loss[loss=0.1808, simple_loss=0.2502, pruned_loss=0.0557, over 4787.00 frames.], tot_loss[loss=0.1666, simple_loss=0.234, pruned_loss=0.04961, over 972045.60 frames.], batch size: 18, lr: 5.76e-04
2022-05-04 11:55:24,491 INFO [train.py:715] (5/8) Epoch 3, batch 4200, loss[loss=0.169, simple_loss=0.2398, pruned_loss=0.04909, over 4955.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2341, pruned_loss=0.04924, over 972019.64 frames.], batch size: 35, lr: 5.75e-04
2022-05-04 11:56:04,945 INFO [train.py:715] (5/8) Epoch 3, batch 4250, loss[loss=0.1476, simple_loss=0.2155, pruned_loss=0.0398, over 4949.00 frames.], tot_loss[loss=0.1668, simple_loss=0.234, pruned_loss=0.04978, over 971883.56 frames.], batch size: 24, lr: 5.75e-04
2022-05-04 11:56:44,320 INFO [train.py:715] (5/8) Epoch 3, batch 4300, loss[loss=0.1822, simple_loss=0.2599, pruned_loss=0.05219, over 4765.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2341, pruned_loss=0.04942, over 972070.48 frames.], batch size: 18, lr: 5.75e-04
2022-05-04 11:57:23,797 INFO [train.py:715] (5/8) Epoch 3, batch 4350, loss[loss=0.1505, simple_loss=0.2282, pruned_loss=0.03639, over 4935.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2344, pruned_loss=0.04959, over 972214.02 frames.], batch size: 23, lr: 5.75e-04
2022-05-04 11:58:03,478 INFO [train.py:715] (5/8) Epoch 3, batch 4400, loss[loss=0.2235, simple_loss=0.271, pruned_loss=0.08799, over 4825.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2348, pruned_loss=0.05, over 972217.75 frames.], batch size: 15, lr: 5.75e-04
2022-05-04 11:58:43,519 INFO [train.py:715] (5/8) Epoch 3, batch 4450, loss[loss=0.1628, simple_loss=0.228, pruned_loss=0.04882, over 4772.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2346, pruned_loss=0.04987, over 971461.89 frames.], batch size: 18, lr: 5.75e-04
2022-05-04 11:59:22,564 INFO [train.py:715] (5/8) Epoch 3, batch 4500, loss[loss=0.1305, simple_loss=0.2067, pruned_loss=0.02717, over 4856.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2338, pruned_loss=0.04945, over 971836.96 frames.], batch size: 20, lr: 5.75e-04
2022-05-04 12:00:01,991 INFO [train.py:715] (5/8) Epoch 3, batch 4550, loss[loss=0.1483, simple_loss=0.2258, pruned_loss=0.03543, over 4789.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04883, over 972741.91 frames.], batch size: 17, lr: 5.74e-04
2022-05-04 12:00:41,744 INFO [train.py:715] (5/8) Epoch 3, batch 4600, loss[loss=0.1524, simple_loss=0.2295, pruned_loss=0.0377, over 4974.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2327, pruned_loss=0.04845, over 972853.15 frames.], batch size: 25, lr: 5.74e-04
2022-05-04 12:01:21,000 INFO [train.py:715] (5/8) Epoch 3, batch 4650, loss[loss=0.1768, simple_loss=0.2375, pruned_loss=0.05804, over 4777.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2329, pruned_loss=0.04865, over 972662.77 frames.], batch size: 18, lr: 5.74e-04
2022-05-04 12:01:59,930 INFO [train.py:715] (5/8) Epoch 3, batch 4700, loss[loss=0.1698, simple_loss=0.2316, pruned_loss=0.05399, over 4877.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2324, pruned_loss=0.04847, over 973017.15 frames.], batch size: 16, lr: 5.74e-04
2022-05-04 12:02:39,133 INFO [train.py:715] (5/8) Epoch 3, batch 4750, loss[loss=0.2281, simple_loss=0.2717, pruned_loss=0.09228, over 4768.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2313, pruned_loss=0.04815, over 972583.38 frames.], batch size: 19, lr: 5.74e-04
2022-05-04 12:03:18,737 INFO [train.py:715] (5/8) Epoch 3, batch 4800, loss[loss=0.1658, simple_loss=0.2305, pruned_loss=0.05056, over 4708.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2308, pruned_loss=0.04798, over 972055.54 frames.], batch size: 15, lr: 5.74e-04
2022-05-04 12:03:58,122 INFO [train.py:715] (5/8) Epoch 3, batch 4850, loss[loss=0.1889, simple_loss=0.2428, pruned_loss=0.0675, over 4975.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2319, pruned_loss=0.04855, over 972493.43 frames.], batch size: 14, lr: 5.74e-04
2022-05-04 12:04:36,947 INFO [train.py:715] (5/8) Epoch 3, batch 4900, loss[loss=0.1543, simple_loss=0.2346, pruned_loss=0.03695, over 4981.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2302, pruned_loss=0.04732, over 971916.07 frames.], batch size: 25, lr: 5.74e-04
2022-05-04 12:05:16,865 INFO [train.py:715] (5/8) Epoch 3, batch 4950, loss[loss=0.1973, simple_loss=0.2556, pruned_loss=0.06955, over 4789.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2302, pruned_loss=0.04728, over 972232.00 frames.], batch size: 21, lr: 5.73e-04
2022-05-04 12:05:56,313 INFO [train.py:715] (5/8) Epoch 3, batch 5000, loss[loss=0.2008, simple_loss=0.2647, pruned_loss=0.06842, over 4959.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2302, pruned_loss=0.04713, over 972546.61 frames.], batch size: 24, lr: 5.73e-04
2022-05-04 12:06:35,118 INFO [train.py:715] (5/8) Epoch 3, batch 5050, loss[loss=0.1995, simple_loss=0.258, pruned_loss=0.07056, over 4789.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2309, pruned_loss=0.04731, over 972752.77 frames.], batch size: 17, lr: 5.73e-04
2022-05-04 12:07:14,484 INFO [train.py:715] (5/8) Epoch 3, batch 5100, loss[loss=0.1476, simple_loss=0.2117, pruned_loss=0.04178, over 4994.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2313, pruned_loss=0.04746, over 972733.57 frames.], batch size: 14, lr: 5.73e-04
2022-05-04 12:07:54,245 INFO [train.py:715] (5/8) Epoch 3, batch 5150, loss[loss=0.176, simple_loss=0.2414, pruned_loss=0.0553, over 4977.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04679, over 972294.51 frames.], batch size: 14, lr: 5.73e-04
2022-05-04 12:08:32,989 INFO [train.py:715] (5/8) Epoch 3, batch 5200, loss[loss=0.1939, simple_loss=0.2596, pruned_loss=0.06406, over 4806.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2308, pruned_loss=0.04711, over 972370.56 frames.], batch size: 26, lr: 5.73e-04
2022-05-04 12:09:12,105 INFO [train.py:715] (5/8) Epoch 3, batch 5250, loss[loss=0.1409, simple_loss=0.2224, pruned_loss=0.02968, over 4752.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2323, pruned_loss=0.04766, over 972734.79 frames.], batch size: 19, lr: 5.73e-04
2022-05-04 12:09:52,196 INFO [train.py:715] (5/8) Epoch 3, batch 5300, loss[loss=0.1927, simple_loss=0.2514, pruned_loss=0.06697, over 4916.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2331, pruned_loss=0.04831, over 972110.21 frames.], batch size: 18, lr: 5.72e-04
2022-05-04 12:10:31,370 INFO [train.py:715] (5/8) Epoch 3, batch 5350, loss[loss=0.1301, simple_loss=0.2022, pruned_loss=0.029, over 4744.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2327, pruned_loss=0.04822, over 972526.57 frames.], batch size: 16, lr: 5.72e-04
2022-05-04 12:11:10,302 INFO [train.py:715] (5/8) Epoch 3, batch 5400, loss[loss=0.1697, simple_loss=0.238, pruned_loss=0.05068, over 4815.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2336, pruned_loss=0.04869, over 972939.75 frames.], batch size: 21, lr: 5.72e-04
2022-05-04 12:11:49,949 INFO [train.py:715] (5/8) Epoch 3, batch 5450, loss[loss=0.1981, simple_loss=0.2508, pruned_loss=0.07267, over 4789.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2348, pruned_loss=0.04992, over 972387.42 frames.], batch size: 17, lr: 5.72e-04
2022-05-04 12:12:30,201 INFO [train.py:715] (5/8) Epoch 3, batch 5500, loss[loss=0.14, simple_loss=0.2057, pruned_loss=0.03717, over 4981.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2343, pruned_loss=0.04925, over 973544.18 frames.], batch size: 28, lr: 5.72e-04
2022-05-04 12:13:09,476 INFO [train.py:715] (5/8) Epoch 3, batch 5550, loss[loss=0.1683, simple_loss=0.2291, pruned_loss=0.05377, over 4867.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2333, pruned_loss=0.04913, over 973035.28 frames.], batch size: 16, lr: 5.72e-04
2022-05-04 12:13:49,876 INFO [train.py:715] (5/8) Epoch 3, batch 5600, loss[loss=0.1726, simple_loss=0.2424, pruned_loss=0.05137, over 4763.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2336, pruned_loss=0.04959, over 972440.70 frames.], batch size: 14, lr: 5.72e-04
2022-05-04 12:14:29,645 INFO [train.py:715] (5/8) Epoch 3, batch 5650, loss[loss=0.16, simple_loss=0.2303, pruned_loss=0.04482, over 4944.00 frames.], tot_loss[loss=0.166, simple_loss=0.2333, pruned_loss=0.04933, over 971757.84 frames.], batch size: 29, lr: 5.72e-04
2022-05-04 12:15:08,733 INFO [train.py:715] (5/8) Epoch 3, batch 5700, loss[loss=0.1406, simple_loss=0.2187, pruned_loss=0.03123, over 4827.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2331, pruned_loss=0.04968, over 972716.84 frames.], batch size: 15, lr: 5.71e-04
2022-05-04 12:15:48,069 INFO [train.py:715] (5/8) Epoch 3, batch 5750, loss[loss=0.1435, simple_loss=0.2149, pruned_loss=0.03601, over 4699.00 frames.], tot_loss[loss=0.1655, simple_loss=0.232, pruned_loss=0.04948, over 972903.47 frames.], batch size: 15, lr: 5.71e-04
2022-05-04 12:16:27,886 INFO [train.py:715] (5/8) Epoch 3, batch 5800, loss[loss=0.1478, simple_loss=0.2169, pruned_loss=0.03933, over 4758.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2318, pruned_loss=0.04892, over 972579.34 frames.], batch size: 19, lr: 5.71e-04
2022-05-04 12:17:07,624 INFO [train.py:715] (5/8) Epoch 3, batch 5850, loss[loss=0.2057, simple_loss=0.2729, pruned_loss=0.06924, over 4920.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2321, pruned_loss=0.04906, over 971700.10 frames.], batch size: 18, lr: 5.71e-04
2022-05-04 12:17:46,986 INFO [train.py:715] (5/8) Epoch 3, batch 5900, loss[loss=0.2, simple_loss=0.2561, pruned_loss=0.072, over 4750.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2317, pruned_loss=0.04849, over 971735.18 frames.], batch size: 16, lr: 5.71e-04
2022-05-04 12:18:26,962 INFO [train.py:715] (5/8) Epoch 3, batch 5950, loss[loss=0.1318, simple_loss=0.1946, pruned_loss=0.03455, over 4817.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2309, pruned_loss=0.0483, over 970982.20 frames.], batch size: 12, lr: 5.71e-04
2022-05-04 12:19:06,642 INFO [train.py:715] (5/8) Epoch 3, batch 6000, loss[loss=0.1676, simple_loss=0.2372, pruned_loss=0.04901, over 4926.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2319, pruned_loss=0.04881, over 971607.62 frames.], batch size: 23, lr: 5.71e-04
2022-05-04 12:19:06,643 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 12:19:15,396 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1149, simple_loss=0.2013, pruned_loss=0.01424, over 914524.00 frames.
2022-05-04 12:19:55,207 INFO [train.py:715] (5/8) Epoch 3, batch 6050, loss[loss=0.1945, simple_loss=0.2526, pruned_loss=0.06822, over 4844.00 frames.], tot_loss[loss=0.165, simple_loss=0.2325, pruned_loss=0.04875, over 972511.04 frames.], batch size: 34, lr: 5.71e-04
2022-05-04 12:20:34,636 INFO [train.py:715] (5/8) Epoch 3, batch 6100, loss[loss=0.1731, simple_loss=0.2429, pruned_loss=0.05158, over 4806.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2329, pruned_loss=0.04879, over 972316.77 frames.], batch size: 24, lr: 5.70e-04
2022-05-04 12:21:13,559 INFO [train.py:715] (5/8) Epoch 3, batch 6150, loss[loss=0.1565, simple_loss=0.2314, pruned_loss=0.0408, over 4801.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2321, pruned_loss=0.04827, over 972426.39 frames.], batch size: 17, lr: 5.70e-04
2022-05-04 12:21:53,158 INFO [train.py:715] (5/8) Epoch 3, batch 6200, loss[loss=0.1644, simple_loss=0.2286, pruned_loss=0.05009, over 4947.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2329, pruned_loss=0.04867, over 973240.49 frames.], batch size: 23, lr: 5.70e-04
2022-05-04 12:22:33,151 INFO [train.py:715] (5/8) Epoch 3, batch 6250, loss[loss=0.1518, simple_loss=0.2185, pruned_loss=0.04258, over 4810.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2317, pruned_loss=0.04797, over 971897.55 frames.], batch size: 25, lr: 5.70e-04
2022-05-04 12:23:12,503 INFO [train.py:715] (5/8) Epoch 3, batch 6300, loss[loss=0.1762, simple_loss=0.2386, pruned_loss=0.05688, over 4877.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04742, over 971511.97 frames.], batch size: 22, lr: 5.70e-04
2022-05-04 12:23:51,735 INFO [train.py:715] (5/8) Epoch 3, batch 6350, loss[loss=0.1883, simple_loss=0.248, pruned_loss=0.06434, over 4887.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04793, over 970904.47 frames.], batch size: 22, lr: 5.70e-04
2022-05-04 12:24:31,947 INFO [train.py:715] (5/8) Epoch 3, batch 6400, loss[loss=0.1294, simple_loss=0.2047, pruned_loss=0.0271, over 4938.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.04811, over 972291.93 frames.], batch size: 29, lr: 5.70e-04
2022-05-04 12:25:11,500 INFO [train.py:715] (5/8) Epoch 3, batch 6450, loss[loss=0.161, simple_loss=0.2315, pruned_loss=0.04522, over 4758.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2322, pruned_loss=0.04869, over 971993.19 frames.], batch size: 16, lr: 5.70e-04
2022-05-04 12:25:50,480 INFO [train.py:715] (5/8) Epoch 3, batch 6500, loss[loss=0.1531, simple_loss=0.2322, pruned_loss=0.03698, over 4958.00 frames.], tot_loss[loss=0.165, simple_loss=0.2326, pruned_loss=0.04867, over 971730.85 frames.], batch size: 21, lr: 5.69e-04
2022-05-04 12:26:30,133 INFO [train.py:715] (5/8) Epoch 3, batch 6550, loss[loss=0.1421, simple_loss=0.2165, pruned_loss=0.03388, over 4790.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2321, pruned_loss=0.04849, over 970895.00 frames.], batch size: 12, lr: 5.69e-04
2022-05-04 12:27:09,928 INFO [train.py:715] (5/8) Epoch 3, batch 6600, loss[loss=0.1482, simple_loss=0.2156, pruned_loss=0.04039, over 4963.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2332, pruned_loss=0.04925, over 970621.22 frames.], batch size: 39, lr: 5.69e-04
2022-05-04 12:27:49,184 INFO [train.py:715] (5/8) Epoch 3, batch 6650, loss[loss=0.1649, simple_loss=0.2434, pruned_loss=0.04325, over 4986.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2323, pruned_loss=0.04835, over 971073.14 frames.], batch size: 25, lr: 5.69e-04
2022-05-04 12:28:28,359 INFO [train.py:715] (5/8) Epoch 3, batch 6700, loss[loss=0.1592, simple_loss=0.2337, pruned_loss=0.04235, over 4791.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2321, pruned_loss=0.04786, over 971226.36 frames.], batch size: 24, lr: 5.69e-04
2022-05-04 12:29:08,702 INFO [train.py:715] (5/8) Epoch 3, batch 6750, loss[loss=0.1866, simple_loss=0.2463, pruned_loss=0.06346, over 4959.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2328, pruned_loss=0.04849, over 971091.27 frames.], batch size: 15, lr: 5.69e-04
2022-05-04 12:29:47,742 INFO [train.py:715] (5/8) Epoch 3, batch 6800, loss[loss=0.1487, simple_loss=0.2159, pruned_loss=0.04071, over 4950.00 frames.], tot_loss[loss=0.165, simple_loss=0.2327, pruned_loss=0.04866, over 971499.99 frames.], batch size: 24, lr: 5.69e-04
2022-05-04 12:30:27,116 INFO [train.py:715] (5/8) Epoch 3, batch 6850, loss[loss=0.1769, simple_loss=0.2381, pruned_loss=0.05784, over 4900.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04881, over 970918.03 frames.], batch size: 18, lr: 5.68e-04
2022-05-04 12:31:06,818 INFO [train.py:715] (5/8) Epoch 3, batch 6900, loss[loss=0.177, simple_loss=0.2503, pruned_loss=0.05187, over 4785.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2324, pruned_loss=0.04822, over 970193.75 frames.], batch size: 18, lr: 5.68e-04
2022-05-04 12:31:46,650 INFO [train.py:715] (5/8) Epoch 3, batch 6950, loss[loss=0.1455, simple_loss=0.22, pruned_loss=0.0355, over 4861.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04766, over 970956.09 frames.], batch size: 32, lr: 5.68e-04
2022-05-04 12:32:25,806 INFO [train.py:715] (5/8) Epoch 3, batch 7000, loss[loss=0.1655, simple_loss=0.2396, pruned_loss=0.04574, over 4920.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2318, pruned_loss=0.04748, over 970632.47 frames.], batch size: 23, lr: 5.68e-04
2022-05-04 12:33:05,829 INFO [train.py:715] (5/8) Epoch 3, batch 7050, loss[loss=0.1539, simple_loss=0.2207, pruned_loss=0.04354, over 4794.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2318, pruned_loss=0.04738, over 970661.34 frames.], batch size: 18, lr: 5.68e-04
2022-05-04 12:33:45,719 INFO [train.py:715] (5/8) Epoch 3, batch 7100, loss[loss=0.1479, simple_loss=0.2124, pruned_loss=0.04168, over 4757.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2323, pruned_loss=0.04759, over 971453.69 frames.], batch size: 19, lr: 5.68e-04
2022-05-04 12:34:24,805 INFO [train.py:715] (5/8) Epoch 3, batch 7150, loss[loss=0.1791, simple_loss=0.2478, pruned_loss=0.05522, over 4875.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2321, pruned_loss=0.04761, over 972016.61 frames.], batch size: 39, lr: 5.68e-04
2022-05-04 12:35:04,375 INFO [train.py:715] (5/8) Epoch 3, batch 7200, loss[loss=0.1563, simple_loss=0.2292, pruned_loss=0.04169, over 4775.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2327, pruned_loss=0.0482, over 973016.32 frames.], batch size: 18, lr: 5.68e-04
2022-05-04 12:35:44,147 INFO [train.py:715] (5/8) Epoch 3, batch 7250, loss[loss=0.1643, simple_loss=0.2254, pruned_loss=0.05162, over 4791.00 frames.], tot_loss[loss=0.1647, simple_loss=0.233, pruned_loss=0.04826, over 972724.62 frames.], batch size: 17, lr: 5.67e-04
2022-05-04 12:36:23,544 INFO [train.py:715] (5/8) Epoch 3, batch 7300, loss[loss=0.1778, simple_loss=0.2457, pruned_loss=0.05491, over 4982.00 frames.], tot_loss[loss=0.165, simple_loss=0.233, pruned_loss=0.04848, over 973230.59 frames.], batch size: 15, lr: 5.67e-04
2022-05-04 12:37:03,011 INFO [train.py:715] (5/8) Epoch 3, batch 7350, loss[loss=0.1583, simple_loss=0.2164, pruned_loss=0.05007, over 4891.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2326, pruned_loss=0.04847, over 973364.11 frames.], batch size: 17, lr: 5.67e-04
2022-05-04 12:37:42,374 INFO [train.py:715] (5/8) Epoch 3, batch 7400, loss[loss=0.1645, simple_loss=0.2411, pruned_loss=0.04399, over 4879.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2324, pruned_loss=0.04824, over 973126.08 frames.], batch size: 22, lr: 5.67e-04
2022-05-04 12:38:22,630 INFO [train.py:715] (5/8) Epoch 3, batch 7450, loss[loss=0.1616, simple_loss=0.235, pruned_loss=0.04407, over 4827.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04767, over 973526.40 frames.], batch size: 15, lr: 5.67e-04
2022-05-04 12:39:01,776 INFO [train.py:715] (5/8) Epoch 3, batch 7500, loss[loss=0.1828, simple_loss=0.2547, pruned_loss=0.05546, over 4947.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04772, over 973367.59 frames.], batch size: 39, lr: 5.67e-04
2022-05-04 12:39:41,042 INFO [train.py:715] (5/8) Epoch 3, batch 7550, loss[loss=0.1697, simple_loss=0.2357, pruned_loss=0.05186, over 4948.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2316, pruned_loss=0.04741, over 973487.71 frames.], batch size: 35, lr: 5.67e-04
2022-05-04 12:40:22,794 INFO [train.py:715] (5/8) Epoch 3, batch 7600, loss[loss=0.1899, simple_loss=0.2551, pruned_loss=0.06237, over 4952.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2328, pruned_loss=0.04818, over 973526.40 frames.], batch size: 35, lr: 5.67e-04
2022-05-04 12:41:02,165 INFO [train.py:715] (5/8) Epoch 3, batch 7650, loss[loss=0.1272, simple_loss=0.2009, pruned_loss=0.02681, over 4829.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2336, pruned_loss=0.04895, over 973419.78 frames.], batch size: 25, lr: 5.66e-04
2022-05-04 12:41:41,414 INFO [train.py:715] (5/8) Epoch 3, batch 7700, loss[loss=0.1541, simple_loss=0.2189, pruned_loss=0.04461, over 4934.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2336, pruned_loss=0.04884, over 972398.18 frames.], batch size: 23, lr: 5.66e-04
2022-05-04 12:42:20,880 INFO [train.py:715] (5/8) Epoch 3, batch 7750, loss[loss=0.1492, simple_loss=0.2173, pruned_loss=0.04058, over 4934.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04877, over 972900.25 frames.], batch size: 18, lr: 5.66e-04
2022-05-04 12:43:00,213 INFO [train.py:715] (5/8) Epoch 3, batch 7800, loss[loss=0.1691, simple_loss=0.2275, pruned_loss=0.0553, over 4714.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04791, over 971781.33 frames.], batch size: 15, lr: 5.66e-04
2022-05-04 12:43:38,786 INFO [train.py:715] (5/8) Epoch 3, batch 7850, loss[loss=0.1757, simple_loss=0.2356, pruned_loss=0.05789, over 4840.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2319, pruned_loss=0.04749, over 971953.31 frames.], batch size: 30, lr: 5.66e-04
2022-05-04 12:44:18,370 INFO [train.py:715] (5/8) Epoch 3, batch 7900, loss[loss=0.1986, simple_loss=0.2675, pruned_loss=0.06485, over 4847.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2319, pruned_loss=0.04748, over 972494.24 frames.], batch size: 15, lr: 5.66e-04
2022-05-04 12:44:58,145 INFO [train.py:715] (5/8) Epoch 3, batch 7950, loss[loss=0.1848, simple_loss=0.2499, pruned_loss=0.05986, over 4791.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04751, over 973262.64 frames.], batch size: 18, lr: 5.66e-04
2022-05-04 12:45:36,727 INFO [train.py:715] (5/8) Epoch 3, batch 8000, loss[loss=0.1898, simple_loss=0.2616, pruned_loss=0.05901, over 4914.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2331, pruned_loss=0.0483, over 973495.94 frames.], batch size: 19, lr: 5.66e-04
2022-05-04 12:46:14,904 INFO [train.py:715] (5/8) Epoch 3, batch 8050, loss[loss=0.1785, simple_loss=0.2366, pruned_loss=0.06022, over 4785.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2333, pruned_loss=0.04849, over 973494.04 frames.], batch size: 17, lr: 5.65e-04
2022-05-04 12:46:53,636 INFO [train.py:715] (5/8) Epoch 3, batch 8100, loss[loss=0.1861, simple_loss=0.2517, pruned_loss=0.06024, over 4983.00 frames.], tot_loss[loss=0.165, simple_loss=0.2329, pruned_loss=0.04856, over 973818.79 frames.], batch size: 15, lr: 5.65e-04
2022-05-04 12:47:31,942 INFO [train.py:715] (5/8) Epoch 3, batch 8150, loss[loss=0.1462, simple_loss=0.2294, pruned_loss=0.03154, over 4911.00 frames.], tot_loss[loss=0.164, simple_loss=0.2315, pruned_loss=0.04825, over 973595.75 frames.], batch size: 17, lr: 5.65e-04
2022-05-04 12:48:10,086 INFO [train.py:715] (5/8) Epoch 3, batch 8200, loss[loss=0.1481, simple_loss=0.2179, pruned_loss=0.0392, over 4838.00 frames.], tot_loss[loss=0.1643, simple_loss=0.232, pruned_loss=0.0483, over 972989.58 frames.], batch size: 30, lr: 5.65e-04
2022-05-04 12:48:49,891 INFO [train.py:715] (5/8) Epoch 3, batch 8250, loss[loss=0.174, simple_loss=0.2488, pruned_loss=0.04961, over 4957.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2323, pruned_loss=0.04833, over 973885.65 frames.], batch size: 24, lr: 5.65e-04
2022-05-04 12:49:30,623 INFO [train.py:715] (5/8) Epoch 3, batch 8300, loss[loss=0.1667, simple_loss=0.2292, pruned_loss=0.05215, over 4913.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04789, over 972712.18 frames.], batch size: 18, lr: 5.65e-04
2022-05-04 12:50:10,665 INFO [train.py:715] (5/8) Epoch 3, batch 8350, loss[loss=0.1508, simple_loss=0.2367, pruned_loss=0.03245, over 4801.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2312, pruned_loss=0.04802, over 972393.27 frames.], batch size: 21, lr: 5.65e-04
2022-05-04 12:50:50,665 INFO [train.py:715] (5/8) Epoch 3, batch 8400, loss[loss=0.1803, simple_loss=0.2502, pruned_loss=0.05518, over 4926.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04745, over 972014.69 frames.], batch size: 29, lr: 5.65e-04
2022-05-04 12:51:30,647 INFO [train.py:715] (5/8) Epoch 3, batch 8450, loss[loss=0.1292, simple_loss=0.204, pruned_loss=0.02723, over 4969.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.04683, over 971610.42 frames.], batch size: 24, lr: 5.64e-04
2022-05-04 12:52:10,868 INFO [train.py:715] (5/8) Epoch 3, batch 8500, loss[loss=0.1702, simple_loss=0.2302, pruned_loss=0.05512, over 4840.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2316, pruned_loss=0.04699, over 972263.76 frames.], batch size: 15, lr: 5.64e-04
2022-05-04 12:52:49,927 INFO [train.py:715] (5/8) Epoch 3, batch 8550, loss[loss=0.1836, simple_loss=0.2448, pruned_loss=0.06118, over 4895.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2324, pruned_loss=0.04727, over 972887.49 frames.], batch size: 22, lr: 5.64e-04
2022-05-04 12:53:31,548 INFO [train.py:715] (5/8) Epoch 3, batch 8600, loss[loss=0.1482, simple_loss=0.2095, pruned_loss=0.04347, over 4904.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2323, pruned_loss=0.04747, over 973960.26 frames.], batch size: 23, lr: 5.64e-04
2022-05-04 12:54:13,120 INFO [train.py:715] (5/8) Epoch 3, batch 8650, loss[loss=0.1555, simple_loss=0.2305, pruned_loss=0.04024, over 4932.00 frames.], tot_loss[loss=0.1632, simple_loss=0.232, pruned_loss=0.04718, over 974282.16 frames.], batch size: 29, lr: 5.64e-04
2022-05-04 12:54:53,243 INFO [train.py:715] (5/8) Epoch 3, batch 8700, loss[loss=0.1486, simple_loss=0.2144, pruned_loss=0.04139, over 4792.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.04718, over 973541.49 frames.], batch size: 24, lr: 5.64e-04
2022-05-04 12:55:34,485 INFO [train.py:715] (5/8) Epoch 3, batch 8750, loss[loss=0.1496, simple_loss=0.2101, pruned_loss=0.04459, over 4987.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04745, over 973040.45 frames.], batch size: 31, lr: 5.64e-04
2022-05-04 12:56:14,899 INFO [train.py:715] (5/8) Epoch 3, batch 8800, loss[loss=0.1985, simple_loss=0.2643, pruned_loss=0.06634, over 4782.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2312, pruned_loss=0.04771, over 972731.67 frames.], batch size: 17, lr: 5.64e-04
2022-05-04 12:56:55,632 INFO [train.py:715] (5/8) Epoch 3, batch 8850, loss[loss=0.1663, simple_loss=0.24, pruned_loss=0.04632, over 4924.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2313, pruned_loss=0.0477, over 972176.15 frames.], batch size: 18, lr: 5.63e-04
2022-05-04 12:57:35,612 INFO [train.py:715] (5/8) Epoch 3, batch 8900, loss[loss=0.202, simple_loss=0.2706, pruned_loss=0.06671, over 4749.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.0472, over 971415.95 frames.], batch size: 16, lr: 5.63e-04
2022-05-04 12:58:17,382 INFO [train.py:715] (5/8) Epoch 3, batch 8950, loss[loss=0.1915, simple_loss=0.2643, pruned_loss=0.05934, over 4982.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2317, pruned_loss=0.0473, over 971475.99 frames.], batch size: 24, lr: 5.63e-04
2022-05-04 12:58:59,336 INFO [train.py:715] (5/8) Epoch 3, batch 9000, loss[loss=0.1537, simple_loss=0.2246, pruned_loss=0.04137, over 4949.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2326, pruned_loss=0.0479, over 970552.76 frames.], batch size: 15, lr: 5.63e-04
2022-05-04 12:58:59,337 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 12:59:08,109 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1147, simple_loss=0.2006, pruned_loss=0.01442, over 914524.00 frames.
2022-05-04 12:59:49,673 INFO [train.py:715] (5/8) Epoch 3, batch 9050, loss[loss=0.1911, simple_loss=0.2586, pruned_loss=0.06176, over 4937.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2326, pruned_loss=0.04829, over 971042.73 frames.], batch size: 39, lr: 5.63e-04
2022-05-04 13:00:30,622 INFO [train.py:715] (5/8) Epoch 3, batch 9100, loss[loss=0.1774, simple_loss=0.2559, pruned_loss=0.04943, over 4846.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04805, over 971598.88 frames.], batch size: 30, lr: 5.63e-04
2022-05-04 13:01:11,922 INFO [train.py:715] (5/8) Epoch 3, batch 9150, loss[loss=0.1769, simple_loss=0.2492, pruned_loss=0.05228, over 4920.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2328, pruned_loss=0.04821, over 971982.04 frames.], batch size: 17, lr: 5.63e-04
2022-05-04 13:01:53,285 INFO [train.py:715] (5/8) Epoch 3, batch 9200, loss[loss=0.1857, simple_loss=0.2432, pruned_loss=0.06409, over 4988.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.04778, over 972066.94 frames.], batch size: 31, lr: 5.63e-04
2022-05-04 13:02:34,661 INFO [train.py:715] (5/8) Epoch 3, batch 9250, loss[loss=0.1546, simple_loss=0.2321, pruned_loss=0.0386, over 4887.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2333, pruned_loss=0.04815, over 972421.23 frames.], batch size: 22, lr: 5.62e-04
2022-05-04 13:03:15,390 INFO [train.py:715] (5/8) Epoch 3, batch 9300, loss[loss=0.1852, simple_loss=0.2511, pruned_loss=0.05959, over 4638.00 frames.], tot_loss[loss=0.165, simple_loss=0.2332, pruned_loss=0.04844, over 972562.68 frames.], batch size: 13, lr: 5.62e-04
2022-05-04 13:03:56,628 INFO [train.py:715] (5/8) Epoch 3, batch 9350, loss[loss=0.1555, simple_loss=0.2277, pruned_loss=0.04164, over 4846.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2338, pruned_loss=0.04873, over 973103.17 frames.], batch size: 34, lr: 5.62e-04
2022-05-04 13:04:38,910 INFO [train.py:715] (5/8) Epoch 3, batch 9400, loss[loss=0.1611, simple_loss=0.2379, pruned_loss=0.04214, over 4808.00 frames.], tot_loss[loss=0.166, simple_loss=0.234, pruned_loss=0.049, over 972880.28 frames.], batch size: 25, lr: 5.62e-04
2022-05-04 13:05:19,296 INFO [train.py:715] (5/8) Epoch 3, batch 9450, loss[loss=0.1695, simple_loss=0.2455, pruned_loss=0.04674, over 4927.00 frames.], tot_loss[loss=0.1662, simple_loss=0.234, pruned_loss=0.04923, over 972466.51 frames.], batch size: 29, lr: 5.62e-04
2022-05-04 13:06:00,819 INFO [train.py:715] (5/8) Epoch 3, batch 9500, loss[loss=0.1834, simple_loss=0.2462, pruned_loss=0.0603, over 4803.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.0488, over 971239.66 frames.], batch size: 21, lr: 5.62e-04
2022-05-04 13:06:42,687 INFO [train.py:715] (5/8) Epoch 3, batch 9550, loss[loss=0.1665, simple_loss=0.2372, pruned_loss=0.0479, over 4771.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2312, pruned_loss=0.04766, over 970629.53 frames.], batch size: 19, lr: 5.62e-04
2022-05-04 13:07:24,292 INFO [train.py:715] (5/8) Epoch 3, batch 9600, loss[loss=0.1445, simple_loss=0.2097, pruned_loss=0.03963, over 4963.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04742, over 971629.43 frames.], batch size: 28, lr: 5.62e-04
2022-05-04 13:08:05,434 INFO [train.py:715] (5/8) Epoch 3, batch 9650, loss[loss=0.1499, simple_loss=0.2151, pruned_loss=0.0424, over 4649.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2315, pruned_loss=0.0481, over 972053.73 frames.], batch size: 13, lr: 5.61e-04
2022-05-04 13:08:46,926 INFO [train.py:715] (5/8) Epoch 3, batch 9700, loss[loss=0.1766, simple_loss=0.2449, pruned_loss=0.05415, over 4924.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2328, pruned_loss=0.04871, over 971785.54 frames.], batch size: 23, lr: 5.61e-04
2022-05-04 13:09:27,938 INFO [train.py:715] (5/8) Epoch 3, batch 9750, loss[loss=0.1833, simple_loss=0.2455, pruned_loss=0.06054, over 4775.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2334, pruned_loss=0.04882, over 971836.30 frames.], batch size: 17, lr: 5.61e-04
2022-05-04 13:10:08,808 INFO [train.py:715] (5/8) Epoch 3, batch 9800, loss[loss=0.1598, simple_loss=0.2234, pruned_loss=0.04809, over 4889.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2336, pruned_loss=0.04894, over 972021.85 frames.], batch size: 17, lr: 5.61e-04
2022-05-04 13:10:50,543 INFO [train.py:715] (5/8) Epoch 3, batch 9850, loss[loss=0.1669, simple_loss=0.2475, pruned_loss=0.04316, over 4805.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2334, pruned_loss=0.04844, over 972436.61 frames.], batch size: 21, lr: 5.61e-04
2022-05-04 13:11:32,495 INFO [train.py:715] (5/8) Epoch 3, batch 9900, loss[loss=0.1998, simple_loss=0.268, pruned_loss=0.06585, over 4928.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2328, pruned_loss=0.04798, over 972622.63 frames.], batch size: 18, lr: 5.61e-04
2022-05-04 13:12:12,991 INFO [train.py:715] (5/8) Epoch 3, batch 9950, loss[loss=0.1873, simple_loss=0.2449, pruned_loss=0.06489, over 4835.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.04778, over 972271.70 frames.], batch size: 26, lr: 5.61e-04
2022-05-04 13:12:54,728 INFO [train.py:715] (5/8) Epoch 3, batch 10000, loss[loss=0.1466, simple_loss=0.2163, pruned_loss=0.03848, over 4783.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2321, pruned_loss=0.04806, over 972740.10 frames.], batch size: 18, lr: 5.61e-04
2022-05-04 13:13:36,180 INFO [train.py:715] (5/8) Epoch 3, batch 10050, loss[loss=0.171, simple_loss=0.2375, pruned_loss=0.05222, over 4936.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2318, pruned_loss=0.04775, over 973267.70 frames.], batch size: 29, lr: 5.61e-04
2022-05-04 13:14:17,625 INFO [train.py:715] (5/8) Epoch 3, batch 10100, loss[loss=0.1828, simple_loss=0.2431, pruned_loss=0.06127, over 4908.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2315, pruned_loss=0.0474, over 973295.70 frames.], batch size: 17, lr: 5.60e-04
2022-05-04 13:14:58,619 INFO [train.py:715] (5/8) Epoch 3, batch 10150, loss[loss=0.1273, simple_loss=0.1988, pruned_loss=0.02791, over 4906.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04726, over 973227.41 frames.], batch size: 17, lr: 5.60e-04
2022-05-04 13:15:40,199 INFO [train.py:715] (5/8) Epoch 3, batch 10200, loss[loss=0.1651, simple_loss=0.2353, pruned_loss=0.04743, over 4781.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2311, pruned_loss=0.0472, over 972591.89 frames.], batch size: 18, lr: 5.60e-04
2022-05-04 13:16:21,935 INFO [train.py:715] (5/8) Epoch 3, batch 10250, loss[loss=0.1391, simple_loss=0.2055, pruned_loss=0.03637, over 4973.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.04664, over 972047.64 frames.], batch size: 14, lr: 5.60e-04
2022-05-04 13:17:01,820 INFO [train.py:715] (5/8) Epoch 3, batch 10300, loss[loss=0.1362, simple_loss=0.2043, pruned_loss=0.03402, over 4940.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2301, pruned_loss=0.04701, over 973145.10 frames.], batch size: 21, lr: 5.60e-04
2022-05-04 13:17:42,060 INFO [train.py:715] (5/8) Epoch 3, batch 10350, loss[loss=0.1729, simple_loss=0.2374, pruned_loss=0.05416, over 4897.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04762, over 972392.86 frames.], batch size: 17, lr: 5.60e-04
2022-05-04 13:18:22,567 INFO [train.py:715] (5/8) Epoch 3, batch 10400, loss[loss=0.1322, simple_loss=0.1989, pruned_loss=0.03273, over 4914.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2318, pruned_loss=0.04828, over 972849.09 frames.], batch size: 23, lr: 5.60e-04
2022-05-04 13:19:03,208 INFO [train.py:715] (5/8) Epoch 3, batch 10450, loss[loss=0.1786, simple_loss=0.2484, pruned_loss=0.05442, over 4802.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2315, pruned_loss=0.04787, over 972780.83 frames.], batch size: 25, lr: 5.60e-04
2022-05-04 13:19:43,608 INFO [train.py:715] (5/8) Epoch 3, batch 10500, loss[loss=0.1479, simple_loss=0.2202, pruned_loss=0.03779, over 4826.00 frames.], tot_loss[loss=0.164, simple_loss=0.2322, pruned_loss=0.04795, over 972659.12 frames.], batch size: 26, lr: 5.59e-04
2022-05-04 13:20:24,625 INFO [train.py:715] (5/8) Epoch 3, batch 10550, loss[loss=0.2134, simple_loss=0.2727, pruned_loss=0.07703, over 4986.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04803, over 971859.54 frames.], batch size: 31, lr: 5.59e-04
2022-05-04 13:21:07,131 INFO [train.py:715] (5/8) Epoch 3, batch 10600, loss[loss=0.1615, simple_loss=0.2333, pruned_loss=0.04488, over 4928.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2325, pruned_loss=0.04789, over 971854.58 frames.], batch size: 29, lr: 5.59e-04
2022-05-04 13:21:48,621 INFO [train.py:715] (5/8) Epoch 3, batch 10650, loss[loss=0.1991, simple_loss=0.2651, pruned_loss=0.0666, over 4855.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2328, pruned_loss=0.04773, over 971976.92 frames.], batch size: 20, lr: 5.59e-04
2022-05-04 13:22:30,745 INFO [train.py:715] (5/8) Epoch 3, batch 10700, loss[loss=0.2036, simple_loss=0.2679, pruned_loss=0.06962, over 4771.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2333, pruned_loss=0.04802, over 972130.28 frames.], batch size: 17, lr: 5.59e-04
2022-05-04 13:23:13,529 INFO [train.py:715] (5/8) Epoch 3, batch 10750, loss[loss=0.1749, simple_loss=0.2363, pruned_loss=0.05673, over 4842.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2323, pruned_loss=0.04772, over 972503.73 frames.], batch size: 30, lr: 5.59e-04
2022-05-04 13:23:56,757 INFO [train.py:715] (5/8) Epoch 3, batch 10800, loss[loss=0.183, simple_loss=0.2413, pruned_loss=0.06233, over 4846.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2327, pruned_loss=0.04759, over 972036.05 frames.], batch size: 32, lr: 5.59e-04
2022-05-04 13:24:38,554 INFO [train.py:715] (5/8) Epoch 3, batch 10850, loss[loss=0.1704, simple_loss=0.2432, pruned_loss=0.04874, over 4847.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2334, pruned_loss=0.04794, over 972270.73 frames.], batch size: 32, lr: 5.59e-04
2022-05-04 13:25:21,317 INFO [train.py:715] (5/8) Epoch 3, batch 10900, loss[loss=0.125, simple_loss=0.196, pruned_loss=0.02696, over 4856.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2332, pruned_loss=0.04788, over 973021.46 frames.], batch size: 15, lr: 5.58e-04
2022-05-04 13:26:04,552 INFO [train.py:715] (5/8) Epoch 3, batch 10950, loss[loss=0.1259, simple_loss=0.1914, pruned_loss=0.03025, over 4982.00 frames.], tot_loss[loss=0.1655, simple_loss=0.234, pruned_loss=0.04852, over 972926.86 frames.], batch size: 14, lr: 5.58e-04
2022-05-04 13:26:46,515 INFO [train.py:715] (5/8) Epoch 3, batch 11000, loss[loss=0.1543, simple_loss=0.2265, pruned_loss=0.0411, over 4757.00 frames.], tot_loss[loss=0.165, simple_loss=0.2337, pruned_loss=0.04816, over 972969.26 frames.], batch size: 14, lr: 5.58e-04
2022-05-04 13:27:28,083 INFO [train.py:715] (5/8) Epoch 3, batch 11050, loss[loss=0.1593, simple_loss=0.2298, pruned_loss=0.04439, over 4927.00 frames.], tot_loss[loss=0.1644, simple_loss=0.233, pruned_loss=0.04789, over 973260.57 frames.], batch size: 23, lr: 5.58e-04
2022-05-04 13:28:11,600 INFO [train.py:715] (5/8) Epoch 3, batch 11100, loss[loss=0.1895, simple_loss=0.2648, pruned_loss=0.0571, over 4882.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2322, pruned_loss=0.04794, over 972920.06 frames.], batch size: 16, lr: 5.58e-04
2022-05-04 13:28:53,679 INFO [train.py:715] (5/8) Epoch 3, batch 11150, loss[loss=0.1438, simple_loss=0.2143, pruned_loss=0.03663, over 4933.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2322, pruned_loss=0.04756, over 973599.50 frames.], batch size: 21, lr: 5.58e-04
2022-05-04 13:29:35,735 INFO [train.py:715] (5/8) Epoch 3, batch 11200, loss[loss=0.1587, simple_loss=0.227, pruned_loss=0.04518, over 4960.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2327, pruned_loss=0.04836, over 973003.73 frames.], batch size: 24, lr: 5.58e-04
2022-05-04 13:30:18,279 INFO [train.py:715] (5/8) Epoch 3, batch 11250, loss[loss=0.1993, simple_loss=0.26, pruned_loss=0.06932, over 4836.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2319, pruned_loss=0.04787, over 972063.05 frames.], batch size: 15, lr: 5.58e-04
2022-05-04 13:31:01,499 INFO [train.py:715] (5/8) Epoch 3, batch 11300, loss[loss=0.1658, simple_loss=0.234, pruned_loss=0.04877, over 4880.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2316, pruned_loss=0.04799, over 972148.97 frames.], batch size: 32, lr: 5.57e-04
2022-05-04 13:31:42,776 INFO [train.py:715] (5/8) Epoch 3, batch 11350, loss[loss=0.1607, simple_loss=0.2259, pruned_loss=0.0477, over 4837.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2312, pruned_loss=0.04817, over 973024.01 frames.], batch size: 30, lr: 5.57e-04
2022-05-04 13:32:25,112 INFO [train.py:715] (5/8) Epoch 3, batch 11400, loss[loss=0.1626, simple_loss=0.2288, pruned_loss=0.0482, over 4793.00 frames.], tot_loss[loss=0.1625, simple_loss=0.23, pruned_loss=0.04748, over 972460.57 frames.], batch size: 18, lr: 5.57e-04
2022-05-04 13:33:08,053 INFO [train.py:715] (5/8) Epoch 3, batch 11450, loss[loss=0.1957, simple_loss=0.2516, pruned_loss=0.06995, over 4756.00 frames.], tot_loss[loss=0.1635, simple_loss=0.231, pruned_loss=0.04806, over 972750.97 frames.], batch size: 19, lr: 5.57e-04
2022-05-04 13:33:50,189 INFO [train.py:715] (5/8) Epoch 3, batch 11500, loss[loss=0.168, simple_loss=0.239, pruned_loss=0.04848, over 4877.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2314, pruned_loss=0.04801, over 973532.69 frames.], batch size: 22, lr: 5.57e-04
2022-05-04 13:34:32,232 INFO [train.py:715] (5/8) Epoch 3, batch 11550, loss[loss=0.1552, simple_loss=0.2296, pruned_loss=0.04043, over 4883.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2307, pruned_loss=0.04777, over 972866.91 frames.], batch size: 22, lr: 5.57e-04
2022-05-04 13:35:14,412 INFO [train.py:715] (5/8) Epoch 3, batch 11600, loss[loss=0.1621, simple_loss=0.226, pruned_loss=0.04913, over 4959.00 frames.], tot_loss[loss=0.163, simple_loss=0.2307, pruned_loss=0.04758, over 972660.33 frames.], batch size: 35, lr: 5.57e-04
2022-05-04 13:35:57,173 INFO [train.py:715] (5/8) Epoch 3, batch 11650, loss[loss=0.1362, simple_loss=0.2138, pruned_loss=0.02927, over 4890.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2299, pruned_loss=0.04676, over 973040.37 frames.], batch size: 16, lr: 5.57e-04
2022-05-04 13:36:39,264 INFO [train.py:715] (5/8) Epoch 3, batch 11700, loss[loss=0.1297, simple_loss=0.2134, pruned_loss=0.02301, over 4930.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04646, over 973683.29 frames.], batch size: 21, lr: 5.57e-04
2022-05-04 13:37:21,483 INFO [train.py:715] (5/8) Epoch 3, batch 11750, loss[loss=0.2016, simple_loss=0.261, pruned_loss=0.07106, over 4977.00 frames.], tot_loss[loss=0.162, simple_loss=0.2305, pruned_loss=0.04679, over 972686.33 frames.], batch size: 39, lr: 5.56e-04
2022-05-04 13:38:05,288 INFO [train.py:715] (5/8) Epoch 3, batch 11800, loss[loss=0.1719, simple_loss=0.2225, pruned_loss=0.06066, over 4792.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2315, pruned_loss=0.04765, over 971885.83 frames.], batch size: 17, lr: 5.56e-04
2022-05-04 13:38:47,459 INFO [train.py:715] (5/8) Epoch 3, batch 11850, loss[loss=0.1366, simple_loss=0.1992, pruned_loss=0.03702, over 4784.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2315, pruned_loss=0.04785, over 972703.21 frames.], batch size: 12, lr: 5.56e-04
2022-05-04 13:39:29,614 INFO [train.py:715] (5/8) Epoch 3, batch 11900, loss[loss=0.1542, simple_loss=0.2215, pruned_loss=0.04341, over 4832.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2321, pruned_loss=0.04831, over 972748.94 frames.], batch size: 13, lr: 5.56e-04
2022-05-04 13:40:11,705 INFO [train.py:715] (5/8) Epoch 3, batch 11950, loss[loss=0.1619, simple_loss=0.2306, pruned_loss=0.04656, over 4967.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2315, pruned_loss=0.04816, over 972412.77 frames.], batch size: 28, lr: 5.56e-04
2022-05-04 13:40:54,207 INFO [train.py:715] (5/8) Epoch 3, batch 12000, loss[loss=0.1697, simple_loss=0.24, pruned_loss=0.04968, over 4909.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2308, pruned_loss=0.04789, over 972934.98 frames.], batch size: 17, lr: 5.56e-04
2022-05-04 13:40:54,208 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 13:41:02,572 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01401, over 914524.00 frames.
2022-05-04 13:41:44,686 INFO [train.py:715] (5/8) Epoch 3, batch 12050, loss[loss=0.1551, simple_loss=0.2288, pruned_loss=0.0407, over 4928.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2308, pruned_loss=0.04772, over 973098.41 frames.], batch size: 39, lr: 5.56e-04
2022-05-04 13:42:26,374 INFO [train.py:715] (5/8) Epoch 3, batch 12100, loss[loss=0.203, simple_loss=0.2575, pruned_loss=0.07426, over 4760.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2306, pruned_loss=0.04741, over 972728.82 frames.], batch size: 17, lr: 5.56e-04
2022-05-04 13:43:08,777 INFO [train.py:715] (5/8) Epoch 3, batch 12150, loss[loss=0.1608, simple_loss=0.2229, pruned_loss=0.04934, over 4837.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2309, pruned_loss=0.04708, over 972723.30 frames.], batch size: 13, lr: 5.55e-04
2022-05-04 13:43:52,022 INFO [train.py:715] (5/8) Epoch 3, batch 12200, loss[loss=0.1623, simple_loss=0.2308, pruned_loss=0.04689, over 4689.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2305, pruned_loss=0.04725, over 971537.10 frames.], batch size: 15, lr: 5.55e-04
2022-05-04 13:44:33,692 INFO [train.py:715] (5/8) Epoch 3, batch 12250, loss[loss=0.16, simple_loss=0.2261, pruned_loss=0.04689, over 4734.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2316, pruned_loss=0.04749, over 971401.55 frames.], batch size: 16, lr: 5.55e-04
2022-05-04 13:45:15,596 INFO [train.py:715] (5/8) Epoch 3, batch 12300, loss[loss=0.1741, simple_loss=0.2428, pruned_loss=0.05269, over 4927.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04771, over 972138.18 frames.], batch size: 23, lr: 5.55e-04
2022-05-04 13:45:58,055 INFO [train.py:715] (5/8) Epoch 3, batch 12350, loss[loss=0.1646, simple_loss=0.2379, pruned_loss=0.04566, over 4851.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2321, pruned_loss=0.04756, over 971819.05 frames.], batch size: 20, lr: 5.55e-04
2022-05-04 13:46:41,410 INFO [train.py:715] (5/8) Epoch 3, batch 12400, loss[loss=0.1945, simple_loss=0.2608, pruned_loss=0.06416, over 4741.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2324, pruned_loss=0.04772, over 971350.13 frames.], batch size: 16, lr: 5.55e-04
2022-05-04 13:47:23,078 INFO [train.py:715] (5/8) Epoch 3, batch 12450, loss[loss=0.2464, simple_loss=0.306, pruned_loss=0.09343, over 4817.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2335, pruned_loss=0.04859, over 972149.46 frames.], batch size: 15, lr: 5.55e-04
2022-05-04 13:48:04,575 INFO [train.py:715] (5/8) Epoch 3, batch 12500, loss[loss=0.1579, simple_loss=0.232, pruned_loss=0.04194, over 4748.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2323, pruned_loss=0.0477, over 971901.76 frames.], batch size: 16, lr: 5.55e-04
2022-05-04 13:48:47,323 INFO [train.py:715] (5/8) Epoch 3, batch 12550, loss[loss=0.1711, simple_loss=0.2339, pruned_loss=0.05411, over 4772.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2329, pruned_loss=0.04827, over 971183.66 frames.], batch size: 18, lr: 5.54e-04
2022-05-04 13:49:29,601 INFO [train.py:715] (5/8) Epoch 3, batch 12600, loss[loss=0.1547, simple_loss=0.2355, pruned_loss=0.03696, over 4932.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2329, pruned_loss=0.04781, over 970563.61 frames.], batch size: 23, lr: 5.54e-04
2022-05-04 13:50:11,351 INFO [train.py:715] (5/8) Epoch 3, batch 12650, loss[loss=0.1652, simple_loss=0.242, pruned_loss=0.04417, over 4795.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.0475, over 969746.32 frames.], batch size: 21, lr: 5.54e-04
2022-05-04 13:50:53,070 INFO [train.py:715] (5/8) Epoch 3, batch 12700, loss[loss=0.1993, simple_loss=0.2623, pruned_loss=0.06816, over 4840.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04737, over 970735.02 frames.], batch size: 13, lr: 5.54e-04
2022-05-04 13:51:35,156 INFO [train.py:715] (5/8) Epoch 3, batch 12750, loss[loss=0.1307, simple_loss=0.2118, pruned_loss=0.02475, over 4887.00 frames.], tot_loss[loss=0.1637, simple_loss=0.232, pruned_loss=0.04763, over 970773.76 frames.], batch size: 22, lr: 5.54e-04
2022-05-04 13:52:17,430 INFO [train.py:715] (5/8) Epoch 3, batch 12800, loss[loss=0.1712, simple_loss=0.226, pruned_loss=0.05817, over 4667.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2314, pruned_loss=0.04778, over 971440.45 frames.], batch size: 13, lr: 5.54e-04
2022-05-04 13:52:58,271 INFO [train.py:715] (5/8) Epoch 3, batch 12850, loss[loss=0.1524, simple_loss=0.2211, pruned_loss=0.04187, over 4957.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2314, pruned_loss=0.04768, over 972166.14 frames.], batch size: 24, lr: 5.54e-04
2022-05-04 13:53:40,953 INFO [train.py:715] (5/8) Epoch 3, batch 12900, loss[loss=0.1475, simple_loss=0.2129, pruned_loss=0.04108, over 4861.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.04815, over 971660.54 frames.], batch size: 32, lr: 5.54e-04
2022-05-04 13:54:23,568 INFO [train.py:715] (5/8) Epoch 3, batch 12950, loss[loss=0.1945, simple_loss=0.2614, pruned_loss=0.06376, over 4815.00 frames.], tot_loss[loss=0.1652, simple_loss=0.233, pruned_loss=0.04868, over 972376.32 frames.], batch size: 25, lr: 5.54e-04
2022-05-04 13:55:04,928 INFO [train.py:715] (5/8) Epoch 3, batch 13000, loss[loss=0.1421, simple_loss=0.2159, pruned_loss=0.03417, over 4961.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2333, pruned_loss=0.04866, over 973154.94 frames.], batch size: 21, lr: 5.53e-04
2022-05-04 13:55:46,801 INFO [train.py:715] (5/8) Epoch 3, batch 13050, loss[loss=0.1851, simple_loss=0.2435, pruned_loss=0.06335, over 4980.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2332, pruned_loss=0.04886, over 972598.97 frames.], batch size: 33, lr: 5.53e-04
2022-05-04 13:56:28,797 INFO [train.py:715] (5/8) Epoch 3, batch 13100, loss[loss=0.1548, simple_loss=0.2263, pruned_loss=0.04165, over 4833.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2331, pruned_loss=0.04886, over 972697.04 frames.], batch size: 26, lr: 5.53e-04
2022-05-04 13:57:10,551 INFO [train.py:715] (5/8) Epoch 3, batch 13150, loss[loss=0.176, simple_loss=0.251, pruned_loss=0.05055, over 4833.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2334, pruned_loss=0.04894, over 971476.91 frames.], batch size: 27, lr: 5.53e-04
2022-05-04 13:57:52,130 INFO [train.py:715] (5/8) Epoch 3, batch 13200, loss[loss=0.1677, simple_loss=0.2359, pruned_loss=0.04977, over 4828.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2324, pruned_loss=0.0485, over 971554.92 frames.], batch size: 13, lr: 5.53e-04
2022-05-04 13:58:34,761 INFO [train.py:715] (5/8) Epoch 3, batch 13250, loss[loss=0.1636, simple_loss=0.2431, pruned_loss=0.04207, over 4961.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2318, pruned_loss=0.04816, over 971475.34 frames.], batch size: 24, lr: 5.53e-04
2022-05-04 13:59:17,143 INFO [train.py:715] (5/8) Epoch 3, batch 13300, loss[loss=0.1274, simple_loss=0.1922, pruned_loss=0.03132, over 4975.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2313, pruned_loss=0.04769, over 972678.81 frames.], batch size: 28, lr: 5.53e-04
2022-05-04 13:59:58,632 INFO [train.py:715] (5/8) Epoch 3, batch 13350, loss[loss=0.1861, simple_loss=0.2456, pruned_loss=0.06331, over 4691.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2308, pruned_loss=0.04775, over 972250.50 frames.], batch size: 15, lr: 5.53e-04
2022-05-04 14:00:40,471 INFO [train.py:715] (5/8) Epoch 3, batch 13400, loss[loss=0.1782, simple_loss=0.243, pruned_loss=0.05667, over 4814.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2302, pruned_loss=0.04735, over 971413.33 frames.], batch size: 15, lr: 5.52e-04
2022-05-04 14:01:23,064 INFO [train.py:715] (5/8) Epoch 3, batch 13450, loss[loss=0.1606, simple_loss=0.2493, pruned_loss=0.03594, over 4903.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2311, pruned_loss=0.04791, over 971685.40 frames.], batch size: 39, lr: 5.52e-04
2022-05-04 14:02:04,526 INFO [train.py:715] (5/8) Epoch 3, batch 13500, loss[loss=0.1945, simple_loss=0.2639, pruned_loss=0.06251, over 4912.00 frames.], tot_loss[loss=0.1642, simple_loss=0.232, pruned_loss=0.0482, over 972200.98 frames.], batch size: 39, lr: 5.52e-04
2022-05-04 14:02:46,052 INFO [train.py:715] (5/8) Epoch 3, batch 13550, loss[loss=0.15, simple_loss=0.2235, pruned_loss=0.03828, over 4799.00 frames.], tot_loss[loss=0.163, simple_loss=0.2315, pruned_loss=0.04728, over 972537.73 frames.], batch size: 24, lr: 5.52e-04
2022-05-04 14:03:28,390 INFO [train.py:715] (5/8) Epoch 3, batch 13600, loss[loss=0.1595, simple_loss=0.2312, pruned_loss=0.04384, over 4814.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04673, over 971945.20 frames.], batch size: 12, lr: 5.52e-04
2022-05-04 14:04:10,283 INFO [train.py:715] (5/8) Epoch 3, batch 13650, loss[loss=0.1632, simple_loss=0.2413, pruned_loss=0.04259, over 4942.00 frames.], tot_loss[loss=0.1617, simple_loss=0.231, pruned_loss=0.04624, over 971199.04 frames.], batch size: 21, lr: 5.52e-04
2022-05-04 14:04:51,707 INFO [train.py:715] (5/8) Epoch 3, batch 13700, loss[loss=0.2035, simple_loss=0.2637, pruned_loss=0.07162, over 4790.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2313, pruned_loss=0.04682, over 970129.74 frames.], batch size: 14, lr: 5.52e-04
2022-05-04 14:05:34,465 INFO [train.py:715] (5/8) Epoch 3, batch 13750, loss[loss=0.2177, simple_loss=0.2749, pruned_loss=0.08022, over 4751.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2318, pruned_loss=0.04751, over 970254.63 frames.], batch size: 16, lr: 5.52e-04
2022-05-04 14:06:16,544 INFO [train.py:715] (5/8) Epoch 3, batch 13800, loss[loss=0.1309, simple_loss=0.1939, pruned_loss=0.03397, over 4861.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04711, over 970804.58 frames.], batch size: 30, lr: 5.52e-04
2022-05-04 14:06:58,027 INFO [train.py:715] (5/8) Epoch 3, batch 13850, loss[loss=0.2056, simple_loss=0.2629, pruned_loss=0.07414, over 4903.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2306, pruned_loss=0.04696, over 971630.06 frames.], batch size: 19, lr: 5.51e-04
2022-05-04 14:07:39,254 INFO [train.py:715] (5/8) Epoch 3, batch 13900, loss[loss=0.1576, simple_loss=0.2263, pruned_loss=0.04447, over 4837.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2309, pruned_loss=0.04724, over 971229.37 frames.], batch size: 15, lr: 5.51e-04
2022-05-04 14:08:21,712 INFO [train.py:715] (5/8) Epoch 3, batch 13950, loss[loss=0.1913, simple_loss=0.2544, pruned_loss=0.06412, over 4859.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2308, pruned_loss=0.04747, over 971740.08 frames.], batch size: 32, lr: 5.51e-04
2022-05-04 14:09:04,160 INFO [train.py:715] (5/8) Epoch 3, batch 14000, loss[loss=0.2011, simple_loss=0.2644, pruned_loss=0.06887, over 4933.00 frames.], tot_loss[loss=0.1633, simple_loss=0.232, pruned_loss=0.04732, over 971848.63 frames.], batch size: 23, lr: 5.51e-04
2022-05-04 14:09:45,591 INFO [train.py:715] (5/8) Epoch 3, batch 14050, loss[loss=0.1696, simple_loss=0.2429, pruned_loss=0.04816, over 4921.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04747, over 972406.89 frames.], batch size: 18, lr: 5.51e-04
2022-05-04 14:10:28,387 INFO [train.py:715] (5/8) Epoch 3, batch 14100, loss[loss=0.1477, simple_loss=0.2199, pruned_loss=0.03772, over 4857.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.0478, over 972337.50 frames.], batch size: 20, lr: 5.51e-04
2022-05-04 14:11:10,226 INFO [train.py:715] (5/8) Epoch 3, batch 14150, loss[loss=0.176, simple_loss=0.2549, pruned_loss=0.04858, over 4809.00 frames.], tot_loss[loss=0.164, simple_loss=0.2325, pruned_loss=0.04773, over 971970.18 frames.], batch size: 25, lr: 5.51e-04
2022-05-04 14:11:51,374 INFO [train.py:715] (5/8) Epoch 3, batch 14200, loss[loss=0.1942, simple_loss=0.2512, pruned_loss=0.06862, over 4848.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2328, pruned_loss=0.04803, over 971907.66 frames.], batch size: 32, lr: 5.51e-04
2022-05-04 14:12:33,512 INFO [train.py:715] (5/8) Epoch 3, batch 14250, loss[loss=0.1862, simple_loss=0.2498, pruned_loss=0.06135, over 4839.00 frames.], tot_loss[loss=0.165, simple_loss=0.2333, pruned_loss=0.04831, over 972415.75 frames.], batch size: 15, lr: 5.51e-04
2022-05-04 14:13:15,874 INFO [train.py:715] (5/8) Epoch 3, batch 14300, loss[loss=0.1444, simple_loss=0.2081, pruned_loss=0.04032, over 4883.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2325, pruned_loss=0.04817, over 972010.25 frames.], batch size: 19, lr: 5.50e-04
2022-05-04 14:13:58,172 INFO [train.py:715] (5/8) Epoch 3, batch 14350, loss[loss=0.1578, simple_loss=0.2122, pruned_loss=0.05163, over 4965.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2314, pruned_loss=0.04767, over 973143.08 frames.], batch size: 15, lr: 5.50e-04
2022-05-04 14:14:38,943 INFO [train.py:715] (5/8) Epoch 3, batch 14400, loss[loss=0.172, simple_loss=0.2481, pruned_loss=0.04795, over 4865.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2324, pruned_loss=0.04813, over 971891.33 frames.], batch size: 20, lr: 5.50e-04
2022-05-04 14:15:21,404 INFO [train.py:715] (5/8) Epoch 3, batch 14450, loss[loss=0.1272, simple_loss=0.2006, pruned_loss=0.0269, over 4919.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04791, over 972280.11 frames.], batch size: 18, lr: 5.50e-04
2022-05-04 14:16:03,344 INFO [train.py:715] (5/8) Epoch 3, batch 14500, loss[loss=0.1626, simple_loss=0.2213, pruned_loss=0.05192, over 4987.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04764, over 972359.76 frames.], batch size: 28, lr: 5.50e-04
2022-05-04 14:16:44,532 INFO [train.py:715] (5/8) Epoch 3, batch 14550, loss[loss=0.1533, simple_loss=0.2286, pruned_loss=0.03902, over 4981.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04764, over 972921.77 frames.], batch size: 25, lr: 5.50e-04
2022-05-04 14:17:26,989 INFO [train.py:715] (5/8) Epoch 3, batch 14600, loss[loss=0.146, simple_loss=0.2192, pruned_loss=0.03642, over 4982.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2317, pruned_loss=0.04741, over 973239.13 frames.], batch size: 35, lr: 5.50e-04
2022-05-04 14:18:08,865 INFO [train.py:715] (5/8) Epoch 3, batch 14650, loss[loss=0.1862, simple_loss=0.2419, pruned_loss=0.06529, over 4984.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2311, pruned_loss=0.04733, over 973326.04 frames.], batch size: 39, lr: 5.50e-04
2022-05-04 14:18:50,910 INFO [train.py:715] (5/8) Epoch 3, batch 14700, loss[loss=0.1516, simple_loss=0.2262, pruned_loss=0.03849, over 4760.00 frames.], tot_loss[loss=0.163, simple_loss=0.2314, pruned_loss=0.04729, over 972977.30 frames.], batch size: 19, lr: 5.49e-04
2022-05-04 14:19:32,223 INFO [train.py:715] (5/8) Epoch 3, batch 14750, loss[loss=0.1946, simple_loss=0.2688, pruned_loss=0.06018, over 4973.00 frames.], tot_loss[loss=0.1632, simple_loss=0.232, pruned_loss=0.04721, over 972531.19 frames.], batch size: 24, lr: 5.49e-04
2022-05-04 14:20:14,636 INFO [train.py:715] (5/8) Epoch 3, batch 14800, loss[loss=0.1942, simple_loss=0.2534, pruned_loss=0.06754, over 4748.00 frames.], tot_loss[loss=0.1633, simple_loss=0.232, pruned_loss=0.04726, over 972034.18 frames.], batch size: 16, lr: 5.49e-04
2022-05-04 14:20:56,944 INFO [train.py:715] (5/8) Epoch 3, batch 14850, loss[loss=0.1407, simple_loss=0.2114, pruned_loss=0.03501, over 4821.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2322, pruned_loss=0.04799, over 972100.20 frames.], batch size: 26, lr: 5.49e-04
2022-05-04 14:21:37,867 INFO [train.py:715] (5/8) Epoch 3, batch 14900, loss[loss=0.16, simple_loss=0.2288, pruned_loss=0.04559, over 4802.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2329, pruned_loss=0.04874, over 972079.99 frames.], batch size: 21, lr: 5.49e-04
2022-05-04 14:22:20,819 INFO [train.py:715] (5/8) Epoch 3, batch 14950, loss[loss=0.1546, simple_loss=0.2181, pruned_loss=0.04553, over 4847.00 frames.], tot_loss[loss=0.1656, simple_loss=0.233, pruned_loss=0.04913, over 971710.11 frames.], batch size: 30, lr: 5.49e-04
2022-05-04 14:23:02,219 INFO [train.py:715] (5/8) Epoch 3, batch 15000, loss[loss=0.1613, simple_loss=0.2301, pruned_loss=0.04626, over 4921.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2322, pruned_loss=0.04837, over 971336.94 frames.], batch size: 17, lr: 5.49e-04
2022-05-04 14:23:02,221 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 14:23:10,877 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01402, over 914524.00 frames.
2022-05-04 14:23:52,705 INFO [train.py:715] (5/8) Epoch 3, batch 15050, loss[loss=0.1518, simple_loss=0.2185, pruned_loss=0.04259, over 4902.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.04812, over 972018.55 frames.], batch size: 19, lr: 5.49e-04
2022-05-04 14:24:34,037 INFO [train.py:715] (5/8) Epoch 3, batch 15100, loss[loss=0.1488, simple_loss=0.2188, pruned_loss=0.03939, over 4864.00 frames.], tot_loss[loss=0.164, simple_loss=0.2319, pruned_loss=0.04801, over 972173.49 frames.], batch size: 32, lr: 5.49e-04
2022-05-04 14:25:16,182 INFO [train.py:715] (5/8) Epoch 3, batch 15150, loss[loss=0.1699, simple_loss=0.252, pruned_loss=0.04389, over 4868.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04788, over 972830.35 frames.], batch size: 16, lr: 5.48e-04
2022-05-04 14:25:57,816 INFO [train.py:715] (5/8) Epoch 3, batch 15200, loss[loss=0.1792, simple_loss=0.2437, pruned_loss=0.05734, over 4846.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2304, pruned_loss=0.04745, over 971794.24 frames.], batch size: 32, lr: 5.48e-04
2022-05-04 14:26:39,371 INFO [train.py:715] (5/8) Epoch 3, batch 15250, loss[loss=0.1712, simple_loss=0.239, pruned_loss=0.05172, over 4886.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2301, pruned_loss=0.04733, over 972077.80 frames.], batch size: 19, lr: 5.48e-04
2022-05-04 14:27:20,698 INFO [train.py:715] (5/8) Epoch 3, batch 15300, loss[loss=0.1503, simple_loss=0.2175, pruned_loss=0.04162, over 4948.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2315, pruned_loss=0.04775, over 971757.99 frames.], batch size: 21, lr: 5.48e-04
2022-05-04 14:28:02,526 INFO [train.py:715] (5/8) Epoch 3, batch 15350, loss[loss=0.209, simple_loss=0.2575, pruned_loss=0.08019, over 4870.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2326, pruned_loss=0.04828, over 972431.12 frames.], batch size: 39, lr: 5.48e-04
2022-05-04 14:28:44,644 INFO [train.py:715] (5/8) Epoch 3, batch 15400, loss[loss=0.1701, simple_loss=0.2296, pruned_loss=0.05534, over 4705.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2321, pruned_loss=0.04817, over 971748.11 frames.], batch size: 15, lr: 5.48e-04
2022-05-04 14:29:25,740 INFO [train.py:715] (5/8) Epoch 3, batch 15450, loss[loss=0.1453, simple_loss=0.2099, pruned_loss=0.04039, over 4640.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2318, pruned_loss=0.04791, over 971922.08 frames.], batch size: 13, lr: 5.48e-04
2022-05-04 14:30:08,687 INFO [train.py:715] (5/8) Epoch 3, batch 15500, loss[loss=0.1453, simple_loss=0.2256, pruned_loss=0.03253, over 4935.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2317, pruned_loss=0.0475, over 972269.49 frames.], batch size: 21, lr: 5.48e-04
2022-05-04 14:30:50,520 INFO [train.py:715] (5/8) Epoch 3, batch 15550, loss[loss=0.182, simple_loss=0.2531, pruned_loss=0.05541, over 4810.00 frames.], tot_loss[loss=0.163, simple_loss=0.2318, pruned_loss=0.0471, over 971729.63 frames.], batch size: 21, lr: 5.48e-04
2022-05-04 14:31:35,085 INFO [train.py:715] (5/8) Epoch 3, batch 15600, loss[loss=0.1355, simple_loss=0.216, pruned_loss=0.02755, over 4861.00 frames.], tot_loss[loss=0.1624, simple_loss=0.231, pruned_loss=0.04695, over 971816.01 frames.], batch size: 38, lr: 5.47e-04
2022-05-04 14:32:16,102 INFO [train.py:715] (5/8) Epoch 3, batch 15650, loss[loss=0.1406, simple_loss=0.2192, pruned_loss=0.03097, over 4788.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04679, over 971156.61 frames.], batch size: 18, lr: 5.47e-04
2022-05-04 14:32:57,690 INFO [train.py:715] (5/8) Epoch 3, batch 15700, loss[loss=0.1764, simple_loss=0.2478, pruned_loss=0.05255, over 4986.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2316, pruned_loss=0.04715, over 971484.48 frames.], batch size: 27, lr: 5.47e-04
2022-05-04 14:33:40,536 INFO [train.py:715] (5/8) Epoch 3, batch 15750, loss[loss=0.1425, simple_loss=0.2164, pruned_loss=0.03431, over 4982.00 frames.], tot_loss[loss=0.1624, simple_loss=0.231, pruned_loss=0.04684, over 971266.49 frames.], batch size: 24, lr: 5.47e-04
2022-05-04 14:34:22,329 INFO [train.py:715] (5/8) Epoch 3, batch 15800, loss[loss=0.1607, simple_loss=0.2255, pruned_loss=0.04796, over 4893.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04754, over 972037.01 frames.], batch size: 19, lr: 5.47e-04
2022-05-04 14:35:03,584 INFO [train.py:715] (5/8) Epoch 3, batch 15850, loss[loss=0.1598, simple_loss=0.2326, pruned_loss=0.0435, over 4828.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.0475, over 972365.99 frames.], batch size: 26, lr: 5.47e-04
2022-05-04 14:35:45,948 INFO [train.py:715] (5/8) Epoch 3, batch 15900, loss[loss=0.1791, simple_loss=0.2409, pruned_loss=0.05871, over 4851.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2308, pruned_loss=0.04719, over 971630.58 frames.], batch size: 30, lr: 5.47e-04
2022-05-04 14:36:28,595 INFO [train.py:715] (5/8) Epoch 3, batch 15950, loss[loss=0.1527, simple_loss=0.2199, pruned_loss=0.04279, over 4776.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04734, over 971982.14 frames.], batch size: 14, lr: 5.47e-04
2022-05-04 14:37:09,186 INFO [train.py:715] (5/8) Epoch 3, batch 16000, loss[loss=0.1772, simple_loss=0.2403, pruned_loss=0.05705, over 4831.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2301, pruned_loss=0.04719, over 971312.52 frames.], batch size: 30, lr: 5.47e-04
2022-05-04 14:37:50,848 INFO [train.py:715] (5/8) Epoch 3, batch 16050, loss[loss=0.1616, simple_loss=0.2339, pruned_loss=0.04465, over 4851.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2306, pruned_loss=0.04716, over 971271.21 frames.], batch size: 30, lr: 5.46e-04
2022-05-04 14:38:33,473 INFO [train.py:715] (5/8) Epoch 3, batch 16100, loss[loss=0.1596, simple_loss=0.2335, pruned_loss=0.04288, over 4849.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2309, pruned_loss=0.04738, over 971904.02 frames.], batch size: 20, lr: 5.46e-04
2022-05-04 14:39:15,447 INFO [train.py:715] (5/8) Epoch 3, batch 16150, loss[loss=0.1372, simple_loss=0.2194, pruned_loss=0.02754, over 4977.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2305, pruned_loss=0.04729, over 972992.78 frames.], batch size: 24, lr: 5.46e-04
2022-05-04 14:39:56,198 INFO [train.py:715] (5/8) Epoch 3, batch 16200, loss[loss=0.1611, simple_loss=0.2295, pruned_loss=0.04639, over 4766.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2302, pruned_loss=0.04703, over 972908.14 frames.], batch size: 14, lr: 5.46e-04
2022-05-04 14:40:38,480 INFO [train.py:715] (5/8) Epoch 3, batch 16250, loss[loss=0.181, simple_loss=0.245, pruned_loss=0.05846, over 4938.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2289, pruned_loss=0.04624, over 971998.77 frames.], batch size: 23, lr: 5.46e-04
2022-05-04 14:41:20,557 INFO [train.py:715] (5/8) Epoch 3, batch 16300, loss[loss=0.1431, simple_loss=0.2187, pruned_loss=0.0337, over 4817.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2296, pruned_loss=0.04612, over 972158.01 frames.], batch size: 12, lr: 5.46e-04
2022-05-04 14:42:01,218 INFO [train.py:715] (5/8) Epoch 3, batch 16350, loss[loss=0.1574, simple_loss=0.2326, pruned_loss=0.0411, over 4989.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2302, pruned_loss=0.0465, over 972086.17 frames.], batch size: 20, lr: 5.46e-04
2022-05-04 14:42:43,181 INFO [train.py:715] (5/8) Epoch 3, batch 16400, loss[loss=0.1709, simple_loss=0.244, pruned_loss=0.04884, over 4808.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04616, over 971378.09 frames.], batch size: 25, lr: 5.46e-04
2022-05-04 14:43:25,720 INFO [train.py:715] (5/8) Epoch 3, batch 16450, loss[loss=0.1522, simple_loss=0.2201, pruned_loss=0.04214, over 4980.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2291, pruned_loss=0.04587, over 971679.31 frames.], batch size: 31, lr: 5.45e-04
2022-05-04 14:44:08,340 INFO [train.py:715] (5/8) Epoch 3, batch 16500, loss[loss=0.1634, simple_loss=0.231, pruned_loss=0.04794, over 4941.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2307, pruned_loss=0.04701, over 971589.90 frames.], batch size: 35, lr: 5.45e-04
2022-05-04 14:44:49,053 INFO [train.py:715] (5/8) Epoch 3, batch 16550, loss[loss=0.1924, simple_loss=0.264, pruned_loss=0.06039, over 4984.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2307, pruned_loss=0.04693, over 972161.17 frames.], batch size: 25, lr: 5.45e-04
2022-05-04 14:45:31,915 INFO [train.py:715] (5/8) Epoch 3, batch 16600, loss[loss=0.1949, simple_loss=0.2504, pruned_loss=0.06967, over 4874.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04706, over 971739.22 frames.], batch size: 16, lr: 5.45e-04
2022-05-04 14:46:14,681 INFO [train.py:715] (5/8) Epoch 3, batch 16650, loss[loss=0.1604, simple_loss=0.2182, pruned_loss=0.05129, over 4696.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2291, pruned_loss=0.0463, over 971295.02 frames.], batch size: 15, lr: 5.45e-04
2022-05-04 14:46:55,374 INFO [train.py:715] (5/8) Epoch 3, batch 16700, loss[loss=0.1509, simple_loss=0.2211, pruned_loss=0.04035, over 4785.00 frames.], tot_loss[loss=0.162, simple_loss=0.2296, pruned_loss=0.04716, over 972065.68 frames.], batch size: 17, lr: 5.45e-04
2022-05-04 14:47:37,402 INFO [train.py:715] (5/8) Epoch 3, batch 16750, loss[loss=0.1833, simple_loss=0.2504, pruned_loss=0.05807, over 4820.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2294, pruned_loss=0.04693, over 972494.52 frames.], batch size: 26, lr: 5.45e-04
2022-05-04 14:48:19,851 INFO [train.py:715] (5/8) Epoch 3, batch 16800, loss[loss=0.1387, simple_loss=0.222, pruned_loss=0.02774, over 4964.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2294, pruned_loss=0.04657, over 972376.35 frames.], batch size: 24, lr: 5.45e-04
2022-05-04 14:49:01,327 INFO [train.py:715] (5/8) Epoch 3, batch 16850, loss[loss=0.1893, simple_loss=0.2575, pruned_loss=0.06052, over 4913.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2293, pruned_loss=0.04661, over 971353.99 frames.], batch size: 17, lr: 5.45e-04
2022-05-04 14:49:42,735 INFO [train.py:715] (5/8) Epoch 3, batch 16900, loss[loss=0.1703, simple_loss=0.2368, pruned_loss=0.05192, over 4867.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04754, over 970728.54 frames.], batch size: 32, lr: 5.44e-04
2022-05-04 14:50:24,686 INFO [train.py:715] (5/8) Epoch 3, batch 16950, loss[loss=0.2058, simple_loss=0.2623, pruned_loss=0.07465, over 4693.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2316, pruned_loss=0.04797, over 970686.19 frames.], batch size: 15, lr: 5.44e-04
2022-05-04 14:51:07,227 INFO [train.py:715] (5/8) Epoch 3, batch 17000, loss[loss=0.122, simple_loss=0.1957, pruned_loss=0.02413, over 4838.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2316, pruned_loss=0.04767, over 970994.42 frames.], batch size: 15, lr: 5.44e-04
2022-05-04 14:51:47,561 INFO [train.py:715] (5/8) Epoch 3, batch 17050, loss[loss=0.1822, simple_loss=0.2398, pruned_loss=0.06233, over 4821.00 frames.], tot_loss[loss=0.1641, simple_loss=0.232, pruned_loss=0.04804, over 971305.74 frames.], batch size: 26, lr: 5.44e-04
2022-05-04 14:52:29,488 INFO [train.py:715] (5/8) Epoch 3, batch 17100, loss[loss=0.176, simple_loss=0.2402, pruned_loss=0.05588, over 4988.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2322, pruned_loss=0.04816, over 971851.93 frames.], batch size: 31, lr: 5.44e-04
2022-05-04 14:53:11,182 INFO [train.py:715] (5/8) Epoch 3, batch 17150, loss[loss=0.1634, simple_loss=0.239, pruned_loss=0.04386, over 4859.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04881, over 972706.63 frames.], batch size: 20, lr: 5.44e-04
2022-05-04 14:53:52,372 INFO [train.py:715] (5/8) Epoch 3, batch 17200, loss[loss=0.1931, simple_loss=0.2627, pruned_loss=0.06177, over 4868.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04769, over 973163.76 frames.], batch size: 16, lr: 5.44e-04
2022-05-04 14:54:33,050 INFO [train.py:715] (5/8) Epoch 3, batch 17250, loss[loss=0.1596, simple_loss=0.2275, pruned_loss=0.04588, over 4975.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2319, pruned_loss=0.04731, over 973313.40 frames.], batch size: 15, lr: 5.44e-04
2022-05-04 14:55:14,506 INFO [train.py:715] (5/8) Epoch 3, batch 17300, loss[loss=0.1597, simple_loss=0.2325, pruned_loss=0.04342, over 4794.00 frames.], tot_loss[loss=0.164, simple_loss=0.2328, pruned_loss=0.04763, over 972175.14 frames.], batch size: 18, lr: 5.44e-04
2022-05-04 14:55:56,122 INFO [train.py:715] (5/8) Epoch 3, batch 17350, loss[loss=0.1205, simple_loss=0.2026, pruned_loss=0.01924, over 4971.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2322, pruned_loss=0.04739, over 973090.20 frames.], batch size: 28, lr: 5.43e-04
2022-05-04 14:56:36,184 INFO [train.py:715] (5/8) Epoch 3, batch 17400, loss[loss=0.1415, simple_loss=0.2119, pruned_loss=0.03561, over 4757.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2314, pruned_loss=0.04735, over 972147.82 frames.], batch size: 19, lr: 5.43e-04
2022-05-04 14:57:18,249 INFO [train.py:715] (5/8) Epoch 3, batch 17450, loss[loss=0.2375, simple_loss=0.3004, pruned_loss=0.08735, over 4764.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2307, pruned_loss=0.04751, over 972527.35 frames.], batch size: 18, lr: 5.43e-04
2022-05-04 14:58:00,473 INFO [train.py:715] (5/8) Epoch 3, batch 17500, loss[loss=0.135, simple_loss=0.2098, pruned_loss=0.03013, over 4886.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2301, pruned_loss=0.0469, over 971541.08 frames.], batch size: 17, lr: 5.43e-04
2022-05-04 14:58:41,508 INFO [train.py:715] (5/8) Epoch 3, batch 17550, loss[loss=0.1743, simple_loss=0.2457, pruned_loss=0.05151, over 4803.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2296, pruned_loss=0.0464, over 971282.45 frames.], batch size: 24, lr: 5.43e-04
2022-05-04 14:59:22,855 INFO [train.py:715] (5/8) Epoch 3, batch 17600, loss[loss=0.1196, simple_loss=0.1828, pruned_loss=0.0282, over 4842.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2298, pruned_loss=0.04636, over 971650.49 frames.], batch size: 12, lr: 5.43e-04
2022-05-04 15:00:04,536 INFO [train.py:715] (5/8) Epoch 3, batch 17650, loss[loss=0.1526, simple_loss=0.2388, pruned_loss=0.03324, over 4913.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04641, over 972026.06 frames.], batch size: 18, lr: 5.43e-04
2022-05-04 15:00:46,082 INFO [train.py:715] (5/8) Epoch 3, batch 17700, loss[loss=0.1857, simple_loss=0.2663, pruned_loss=0.05258, over 4786.00 frames.], tot_loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04612, over 972030.89 frames.], batch size: 17, lr: 5.43e-04
2022-05-04 15:01:26,900 INFO [train.py:715] (5/8) Epoch 3, batch 17750, loss[loss=0.1997, simple_loss=0.2878, pruned_loss=0.05581, over 4892.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2308, pruned_loss=0.04616, over 971702.68 frames.], batch size: 19, lr: 5.43e-04
2022-05-04 15:02:08,925 INFO [train.py:715] (5/8) Epoch 3, batch 17800, loss[loss=0.142, simple_loss=0.2155, pruned_loss=0.0343, over 4921.00 frames.], tot_loss[loss=0.161, simple_loss=0.2301, pruned_loss=0.04599, over 971358.57 frames.], batch size: 18, lr: 5.42e-04
2022-05-04 15:02:50,345 INFO [train.py:715] (5/8) Epoch 3, batch 17850, loss[loss=0.1408, simple_loss=0.2105, pruned_loss=0.03559, over 4753.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2302, pruned_loss=0.04577, over 971671.49 frames.], batch size: 16, lr: 5.42e-04
2022-05-04 15:03:30,307 INFO [train.py:715] (5/8) Epoch 3, batch 17900, loss[loss=0.1816, simple_loss=0.2459, pruned_loss=0.05863, over 4785.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2306, pruned_loss=0.04605, over 971989.43 frames.], batch size: 17, lr: 5.42e-04
2022-05-04 15:04:12,141 INFO [train.py:715] (5/8) Epoch 3, batch 17950, loss[loss=0.1629, simple_loss=0.2409, pruned_loss=0.0425, over 4955.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2316, pruned_loss=0.04688, over 972284.47 frames.], batch size: 21, lr: 5.42e-04
2022-05-04 15:04:53,400 INFO [train.py:715] (5/8) Epoch 3, batch 18000, loss[loss=0.1801, simple_loss=0.2379, pruned_loss=0.06111, over 4846.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04746, over 972393.55 frames.], batch size: 15, lr: 5.42e-04
2022-05-04 15:04:53,401 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 15:05:02,070 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1143, simple_loss=0.2002, pruned_loss=0.01414, over 914524.00 frames.
2022-05-04 15:05:43,865 INFO [train.py:715] (5/8) Epoch 3, batch 18050, loss[loss=0.1758, simple_loss=0.2524, pruned_loss=0.04963, over 4788.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2324, pruned_loss=0.04794, over 972831.80 frames.], batch size: 17, lr: 5.42e-04
2022-05-04 15:06:25,504 INFO [train.py:715] (5/8) Epoch 3, batch 18100, loss[loss=0.1681, simple_loss=0.2341, pruned_loss=0.05098, over 4743.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2325, pruned_loss=0.04836, over 972660.73 frames.], batch size: 16, lr: 5.42e-04
2022-05-04 15:07:06,172 INFO [train.py:715] (5/8) Epoch 3, batch 18150, loss[loss=0.1875, simple_loss=0.2448, pruned_loss=0.06505, over 4885.00 frames.], tot_loss[loss=0.1642, simple_loss=0.232, pruned_loss=0.04818, over 971343.16 frames.], batch size: 22, lr: 5.42e-04
2022-05-04 15:07:47,678 INFO [train.py:715] (5/8) Epoch 3, batch 18200, loss[loss=0.1535, simple_loss=0.2149, pruned_loss=0.04609, over 4990.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04753, over 972977.17 frames.], batch size: 25, lr: 5.42e-04
2022-05-04 15:08:29,474 INFO [train.py:715] (5/8) Epoch 3, batch 18250, loss[loss=0.1678, simple_loss=0.2313, pruned_loss=0.05211, over 4870.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2309, pruned_loss=0.04762, over 972421.93 frames.], batch size: 20, lr: 5.41e-04
2022-05-04 15:09:10,291 INFO [train.py:715] (5/8) Epoch 3, batch 18300, loss[loss=0.1702, simple_loss=0.2317, pruned_loss=0.05434, over 4899.00 frames.], tot_loss[loss=0.162, simple_loss=0.2297, pruned_loss=0.04714, over 972845.35 frames.], batch size: 19, lr: 5.41e-04
2022-05-04 15:09:51,599 INFO [train.py:715] (5/8) Epoch 3, batch 18350, loss[loss=0.1401, simple_loss=0.2091, pruned_loss=0.03552, over 4859.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2302, pruned_loss=0.04727, over 972449.95 frames.], batch size: 30, lr: 5.41e-04
2022-05-04 15:10:33,028 INFO [train.py:715] (5/8) Epoch 3, batch 18400, loss[loss=0.1469, simple_loss=0.2234, pruned_loss=0.03518, over 4939.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2314, pruned_loss=0.04756, over 972592.25 frames.], batch size: 21, lr: 5.41e-04
2022-05-04 15:11:13,983 INFO [train.py:715] (5/8) Epoch 3, batch 18450, loss[loss=0.1356, simple_loss=0.1941, pruned_loss=0.0386, over 4894.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04763, over 973069.62 frames.], batch size: 19, lr: 5.41e-04
2022-05-04 15:11:55,019 INFO [train.py:715] (5/8) Epoch 3, batch 18500, loss[loss=0.1661, simple_loss=0.2273, pruned_loss=0.05249, over 4870.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04702, over 973163.99 frames.], batch size: 16, lr: 5.41e-04
2022-05-04 15:12:36,396 INFO [train.py:715] (5/8) Epoch 3, batch 18550, loss[loss=0.1497, simple_loss=0.2232, pruned_loss=0.03809, over 4862.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04711, over 973049.09 frames.], batch size: 16, lr: 5.41e-04
2022-05-04 15:13:18,631 INFO [train.py:715] (5/8) Epoch 3, batch 18600, loss[loss=0.1703, simple_loss=0.2474, pruned_loss=0.04658, over 4971.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04656, over 973029.11 frames.], batch size: 35, lr: 5.41e-04
2022-05-04 15:13:58,620 INFO [train.py:715] (5/8) Epoch 3, batch 18650, loss[loss=0.1569, simple_loss=0.2293, pruned_loss=0.0422, over 4799.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04637, over 972211.31 frames.], batch size: 21, lr: 5.41e-04
2022-05-04 15:14:39,320 INFO [train.py:715] (5/8) Epoch 3, batch 18700, loss[loss=0.1498, simple_loss=0.2187, pruned_loss=0.04045, over 4847.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2304, pruned_loss=0.04677, over 971663.39 frames.], batch size: 20, lr: 5.40e-04
2022-05-04 15:15:20,421 INFO [train.py:715] (5/8) Epoch 3, batch 18750, loss[loss=0.1669, simple_loss=0.2295, pruned_loss=0.05212, over 4928.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2296, pruned_loss=0.04643, over 970966.51 frames.], batch size: 18, lr: 5.40e-04
2022-05-04 15:16:00,280 INFO [train.py:715] (5/8) Epoch 3, batch 18800, loss[loss=0.1327, simple_loss=0.1966, pruned_loss=0.03435, over 4811.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2297, pruned_loss=0.04651, over 971457.16 frames.], batch size: 12, lr: 5.40e-04
2022-05-04 15:16:41,100 INFO [train.py:715] (5/8) Epoch 3, batch 18850, loss[loss=0.154, simple_loss=0.2325, pruned_loss=0.03781, over 4956.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2318, pruned_loss=0.04754, over 971276.17 frames.], batch size: 21, lr: 5.40e-04
2022-05-04 15:17:21,062 INFO [train.py:715] (5/8) Epoch 3, batch 18900, loss[loss=0.1502, simple_loss=0.2232, pruned_loss=0.03859, over 4941.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2319, pruned_loss=0.04764, over 972000.96 frames.], batch size: 23, lr: 5.40e-04
2022-05-04 15:18:01,542 INFO [train.py:715] (5/8) Epoch 3, batch 18950, loss[loss=0.1327, simple_loss=0.2054, pruned_loss=0.03004, over 4980.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2308, pruned_loss=0.04707, over 971956.83 frames.], batch size: 25, lr: 5.40e-04
2022-05-04 15:18:40,944 INFO [train.py:715] (5/8) Epoch 3, batch 19000, loss[loss=0.1857, simple_loss=0.2484, pruned_loss=0.06148, over 4812.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2299, pruned_loss=0.04675, over 972900.45 frames.], batch size: 25, lr: 5.40e-04
2022-05-04 15:19:20,770 INFO [train.py:715] (5/8) Epoch 3, batch 19050, loss[loss=0.153, simple_loss=0.2242, pruned_loss=0.04091, over 4780.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2304, pruned_loss=0.04695, over 972909.19 frames.], batch size: 18, lr: 5.40e-04
2022-05-04 15:20:01,073 INFO [train.py:715] (5/8) Epoch 3, batch 19100, loss[loss=0.1719, simple_loss=0.234, pruned_loss=0.05488, over 4793.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04666, over 972995.20 frames.], batch size: 24, lr: 5.40e-04
2022-05-04 15:20:40,502 INFO [train.py:715] (5/8) Epoch 3, batch 19150, loss[loss=0.1756, simple_loss=0.2418, pruned_loss=0.05472, over 4733.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2305, pruned_loss=0.04705, over 972347.55 frames.], batch size: 16, lr: 5.40e-04
2022-05-04 15:21:20,178 INFO [train.py:715] (5/8) Epoch 3, batch 19200, loss[loss=0.1516, simple_loss=0.2207, pruned_loss=0.04121, over 4874.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2304, pruned_loss=0.04706, over 972628.40 frames.], batch size: 20, lr: 5.39e-04
2022-05-04 15:21:59,823 INFO [train.py:715] (5/8) Epoch 3, batch 19250, loss[loss=0.1652, simple_loss=0.2342, pruned_loss=0.04808, over 4946.00 frames.], tot_loss[loss=0.163, simple_loss=0.2311, pruned_loss=0.04744, over 972712.69 frames.], batch size: 21, lr: 5.39e-04
2022-05-04 15:22:40,128 INFO [train.py:715] (5/8) Epoch 3, batch 19300, loss[loss=0.1359, simple_loss=0.2157, pruned_loss=0.02806, over 4803.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2301, pruned_loss=0.04669, over 972138.47 frames.], batch size: 24, lr: 5.39e-04
2022-05-04 15:23:19,476 INFO [train.py:715] (5/8) Epoch 3, batch 19350, loss[loss=0.2528, simple_loss=0.3132, pruned_loss=0.09617, over 4744.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2304, pruned_loss=0.0469, over 971174.58 frames.], batch size: 19, lr: 5.39e-04
2022-05-04 15:23:59,200 INFO [train.py:715] (5/8) Epoch 3, batch 19400, loss[loss=0.1805, simple_loss=0.2441, pruned_loss=0.05841, over 4923.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04666, over 971456.15 frames.], batch size: 18, lr: 5.39e-04
2022-05-04 15:24:39,294 INFO [train.py:715] (5/8) Epoch 3, batch 19450, loss[loss=0.1427, simple_loss=0.2063, pruned_loss=0.03956, over 4969.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2313, pruned_loss=0.04644, over 971202.91 frames.], batch size: 14, lr: 5.39e-04
2022-05-04 15:25:18,371 INFO [train.py:715] (5/8) Epoch 3, batch 19500, loss[loss=0.2515, simple_loss=0.2789, pruned_loss=0.1121, over 4705.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2305, pruned_loss=0.04653, over 971138.57 frames.], batch size: 15, lr: 5.39e-04
2022-05-04 15:25:58,124 INFO [train.py:715] (5/8) Epoch 3, batch 19550, loss[loss=0.1429, simple_loss=0.213, pruned_loss=0.03636, over 4987.00 frames.], tot_loss[loss=0.1611, simple_loss=0.23, pruned_loss=0.04606, over 971858.41 frames.], batch size: 28, lr: 5.39e-04
2022-05-04 15:26:37,673 INFO [train.py:715] (5/8) Epoch 3, batch 19600, loss[loss=0.1667, simple_loss=0.2423, pruned_loss=0.04561, over 4849.00 frames.], tot_loss[loss=0.1624, simple_loss=0.231, pruned_loss=0.04686, over 972855.96 frames.], batch size: 32, lr: 5.39e-04
2022-05-04 15:27:17,574 INFO [train.py:715] (5/8) Epoch 3, batch 19650, loss[loss=0.1672, simple_loss=0.2369, pruned_loss=0.04875, over 4802.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2303, pruned_loss=0.04613, over 972389.85 frames.], batch size: 14, lr: 5.38e-04
2022-05-04 15:27:56,474 INFO [train.py:715] (5/8) Epoch 3, batch 19700, loss[loss=0.169, simple_loss=0.2508, pruned_loss=0.04361, over 4820.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2301, pruned_loss=0.04639, over 972618.24 frames.], batch size: 25, lr: 5.38e-04
2022-05-04 15:28:36,072 INFO [train.py:715] (5/8) Epoch 3, batch 19750, loss[loss=0.1611, simple_loss=0.2328, pruned_loss=0.04471, over 4967.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2297, pruned_loss=0.04622, over 972275.73 frames.], batch size: 21, lr: 5.38e-04
2022-05-04 15:29:15,540 INFO [train.py:715] (5/8) Epoch 3, batch 19800, loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.0302, over 4693.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2291, pruned_loss=0.04579, over 973160.15 frames.], batch size: 15, lr: 5.38e-04
2022-05-04 15:29:55,119 INFO [train.py:715] (5/8) Epoch 3, batch 19850, loss[loss=0.1625, simple_loss=0.2159, pruned_loss=0.05455, over 4853.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2303, pruned_loss=0.04635, over 972423.65 frames.], batch size: 30, lr: 5.38e-04
2022-05-04 15:30:34,815 INFO [train.py:715] (5/8) Epoch 3, batch 19900, loss[loss=0.1656, simple_loss=0.2262, pruned_loss=0.05251, over 4708.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2299, pruned_loss=0.04587, over 972167.13 frames.], batch size: 15, lr: 5.38e-04
2022-05-04 15:31:15,111 INFO [train.py:715] (5/8) Epoch 3, batch 19950, loss[loss=0.1679, simple_loss=0.2397, pruned_loss=0.04805, over 4934.00 frames.], tot_loss[loss=0.161, simple_loss=0.2299, pruned_loss=0.04605, over 971564.68 frames.], batch size: 23, lr: 5.38e-04
2022-05-04 15:31:54,891 INFO [train.py:715] (5/8) Epoch 3, batch 20000, loss[loss=0.157, simple_loss=0.2239, pruned_loss=0.04498, over 4695.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04641, over 971728.83 frames.], batch size: 15, lr: 5.38e-04
2022-05-04 15:32:34,162 INFO [train.py:715] (5/8) Epoch 3, batch 20050, loss[loss=0.1659, simple_loss=0.2342, pruned_loss=0.0488, over 4935.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2303, pruned_loss=0.04595, over 972169.96 frames.], batch size: 29, lr: 5.38e-04
2022-05-04 15:33:14,402 INFO [train.py:715] (5/8) Epoch 3, batch 20100, loss[loss=0.1402, simple_loss=0.2016, pruned_loss=0.03937, over 4777.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2302, pruned_loss=0.04598, over 971717.97 frames.], batch size: 17, lr: 5.37e-04
2022-05-04 15:33:54,294 INFO [train.py:715] (5/8) Epoch 3, batch 20150, loss[loss=0.148, simple_loss=0.221, pruned_loss=0.03751, over 4926.00 frames.], tot_loss[loss=0.1598, simple_loss=0.229, pruned_loss=0.0453, over 972279.17 frames.], batch size: 23, lr: 5.37e-04
2022-05-04 15:34:33,627 INFO [train.py:715] (5/8) Epoch 3, batch 20200, loss[loss=0.2094, simple_loss=0.2477, pruned_loss=0.08554, over 4880.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2284, pruned_loss=0.04545, over 972345.75 frames.], batch size: 16, lr: 5.37e-04
2022-05-04 15:35:13,293 INFO [train.py:715] (5/8) Epoch 3, batch 20250, loss[loss=0.1301, simple_loss=0.2042, pruned_loss=0.02805, over 4919.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04521, over 973146.38 frames.], batch size: 23, lr: 5.37e-04
2022-05-04 15:35:53,127 INFO [train.py:715] (5/8) Epoch 3, batch 20300, loss[loss=0.1763, simple_loss=0.2374, pruned_loss=0.05761, over 4958.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2284, pruned_loss=0.04561, over 972278.86 frames.], batch size: 39, lr: 5.37e-04
2022-05-04 15:36:33,511 INFO [train.py:715] (5/8) Epoch 3, batch 20350, loss[loss=0.1603, simple_loss=0.2295, pruned_loss=0.04556, over 4754.00 frames.], tot_loss[loss=0.161, simple_loss=0.2294, pruned_loss=0.04633, over 972388.92 frames.], batch size: 19, lr: 5.37e-04
2022-05-04 15:37:12,087 INFO [train.py:715] (5/8) Epoch 3, batch 20400, loss[loss=0.1303, simple_loss=0.2067, pruned_loss=0.02697, over 4776.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2294, pruned_loss=0.0462, over 972632.13 frames.], batch size: 17, lr: 5.37e-04
2022-05-04 15:37:51,791 INFO [train.py:715] (5/8) Epoch 3, batch 20450, loss[loss=0.1537, simple_loss=0.2334, pruned_loss=0.03702, over 4824.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04684, over 972454.93 frames.], batch size: 15, lr: 5.37e-04
2022-05-04 15:38:31,860 INFO [train.py:715] (5/8) Epoch 3, batch 20500, loss[loss=0.162, simple_loss=0.2348, pruned_loss=0.04458, over 4945.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2293, pruned_loss=0.04678, over 971674.46 frames.], batch size: 29, lr: 5.37e-04
2022-05-04 15:39:10,979 INFO [train.py:715] (5/8) Epoch 3, batch 20550, loss[loss=0.143, simple_loss=0.2133, pruned_loss=0.03632, over 4909.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2295, pruned_loss=0.0467, over 972039.72 frames.], batch size: 19, lr: 5.36e-04
2022-05-04 15:39:50,434 INFO [train.py:715] (5/8) Epoch 3, batch 20600, loss[loss=0.2146, simple_loss=0.278, pruned_loss=0.07563, over 4968.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2308, pruned_loss=0.04772, over 971557.63 frames.], batch size: 39, lr: 5.36e-04
2022-05-04 15:40:30,881 INFO [train.py:715] (5/8) Epoch 3, batch 20650, loss[loss=0.1476, simple_loss=0.2117, pruned_loss=0.04181, over 4705.00 frames.], tot_loss[loss=0.163, simple_loss=0.2309, pruned_loss=0.04754, over 971317.18 frames.], batch size: 15, lr: 5.36e-04
2022-05-04 15:41:10,734 INFO [train.py:715] (5/8) Epoch 3, batch 20700, loss[loss=0.1561, simple_loss=0.2329, pruned_loss=0.03966, over 4884.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2305, pruned_loss=0.04742, over 971338.91 frames.], batch size: 22, lr: 5.36e-04
2022-05-04 15:41:50,203 INFO [train.py:715] (5/8) Epoch 3, batch 20750, loss[loss=0.1669, simple_loss=0.2278, pruned_loss=0.05302, over 4966.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2313, pruned_loss=0.04747, over 971497.49 frames.], batch size: 15, lr: 5.36e-04
2022-05-04 15:42:30,288 INFO [train.py:715] (5/8) Epoch 3, batch 20800, loss[loss=0.1266, simple_loss=0.2006, pruned_loss=0.02628, over 4981.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2301, pruned_loss=0.04689, over 971948.47 frames.], batch size: 15, lr: 5.36e-04
2022-05-04 15:43:11,031 INFO [train.py:715] (5/8) Epoch 3, batch 20850, loss[loss=0.1686, simple_loss=0.2396, pruned_loss=0.04881, over 4843.00 frames.], tot_loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.04674, over 972458.13 frames.], batch size: 15, lr: 5.36e-04
2022-05-04 15:43:50,800 INFO [train.py:715] (5/8) Epoch 3, batch 20900, loss[loss=0.1736, simple_loss=0.2515, pruned_loss=0.04779, over 4927.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.0468, over 972252.10 frames.], batch size: 29, lr: 5.36e-04
2022-05-04 15:44:31,209 INFO [train.py:715] (5/8) Epoch 3, batch 20950, loss[loss=0.1654, simple_loss=0.2471, pruned_loss=0.04181, over 4881.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2312, pruned_loss=0.04681, over 972525.85 frames.], batch size: 22, lr: 5.36e-04
2022-05-04 15:45:11,740 INFO [train.py:715] (5/8) Epoch 3, batch 21000, loss[loss=0.1398, simple_loss=0.2154, pruned_loss=0.03212, over 4901.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04703, over 971998.28 frames.], batch size: 17, lr: 5.36e-04
2022-05-04 15:45:11,740 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 15:45:24,192 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1137, simple_loss=0.1999, pruned_loss=0.01377, over 914524.00 frames.
2022-05-04 15:46:04,597 INFO [train.py:715] (5/8) Epoch 3, batch 21050, loss[loss=0.1939, simple_loss=0.2557, pruned_loss=0.06606, over 4892.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2317, pruned_loss=0.0474, over 972295.76 frames.], batch size: 19, lr: 5.35e-04
2022-05-04 15:46:45,382 INFO [train.py:715] (5/8) Epoch 3, batch 21100, loss[loss=0.1779, simple_loss=0.2443, pruned_loss=0.05577, over 4909.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.04717, over 972766.01 frames.], batch size: 17, lr: 5.35e-04
2022-05-04 15:47:25,780 INFO [train.py:715] (5/8) Epoch 3, batch 21150, loss[loss=0.1716, simple_loss=0.244, pruned_loss=0.04956, over 4907.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2317, pruned_loss=0.04767, over 972434.40 frames.], batch size: 23, lr: 5.35e-04
2022-05-04 15:48:08,588 INFO [train.py:715] (5/8) Epoch 3, batch 21200, loss[loss=0.1381, simple_loss=0.2137, pruned_loss=0.03128, over 4922.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04746, over 973145.96 frames.], batch size: 29, lr: 5.35e-04
2022-05-04 15:48:49,621 INFO [train.py:715] (5/8) Epoch 3, batch 21250, loss[loss=0.1569, simple_loss=0.2224, pruned_loss=0.04575, over 4858.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2313, pruned_loss=0.04739, over 974304.01 frames.], batch size: 20, lr: 5.35e-04
2022-05-04 15:49:28,344 INFO [train.py:715] (5/8) Epoch 3, batch 21300, loss[loss=0.1392, simple_loss=0.2083, pruned_loss=0.03507, over 4797.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04706, over 973694.07 frames.], batch size: 17, lr: 5.35e-04
2022-05-04 15:50:10,542 INFO [train.py:715] (5/8) Epoch 3, batch 21350, loss[loss=0.1583, simple_loss=0.2377, pruned_loss=0.03948, over 4990.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2316, pruned_loss=0.04739, over 973843.60 frames.], batch size: 26, lr: 5.35e-04
2022-05-04 15:50:51,358 INFO [train.py:715] (5/8) Epoch 3, batch 21400, loss[loss=0.2128, simple_loss=0.2669, pruned_loss=0.07932, over 4973.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2309, pruned_loss=0.04746, over 974166.38 frames.], batch size: 15, lr: 5.35e-04
2022-05-04 15:51:30,338 INFO [train.py:715] (5/8) Epoch 3, batch 21450, loss[loss=0.1762, simple_loss=0.2402, pruned_loss=0.05612, over 4788.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2307, pruned_loss=0.0472, over 973266.31 frames.], batch size: 14, lr: 5.35e-04
2022-05-04 15:52:08,620 INFO [train.py:715] (5/8) Epoch 3, batch 21500, loss[loss=0.1621, simple_loss=0.229, pruned_loss=0.04762, over 4884.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2307, pruned_loss=0.04709, over 972726.58 frames.], batch size: 22, lr: 5.34e-04
2022-05-04 15:52:47,668 INFO [train.py:715] (5/8) Epoch 3, batch 21550, loss[loss=0.1773, simple_loss=0.2479, pruned_loss=0.05335, over 4907.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04702, over 972248.72 frames.], batch size: 19, lr: 5.34e-04
2022-05-04 15:53:27,198 INFO [train.py:715] (5/8) Epoch 3, batch 21600, loss[loss=0.1539, simple_loss=0.2334, pruned_loss=0.03723, over 4923.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04678, over 972452.40 frames.], batch size: 18, lr: 5.34e-04
2022-05-04 15:54:06,106 INFO [train.py:715] (5/8) Epoch 3, batch 21650, loss[loss=0.12, simple_loss=0.1908, pruned_loss=0.02465, over 4726.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04664, over 971655.63 frames.], batch size: 12, lr: 5.34e-04
2022-05-04 15:54:46,391 INFO [train.py:715] (5/8) Epoch 3, batch 21700, loss[loss=0.1345, simple_loss=0.2031, pruned_loss=0.03292, over 4767.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04675, over 971515.12 frames.], batch size: 12, lr: 5.34e-04
2022-05-04 15:55:26,904 INFO [train.py:715] (5/8) Epoch 3, batch 21750, loss[loss=0.1547, simple_loss=0.2278, pruned_loss=0.04085, over 4973.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2305, pruned_loss=0.04694, over 971874.86 frames.], batch size: 14, lr: 5.34e-04
2022-05-04 15:56:06,025 INFO [train.py:715] (5/8) Epoch 3, batch 21800, loss[loss=0.161, simple_loss=0.2304, pruned_loss=0.04579, over 4779.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04745, over 971620.36 frames.], batch size: 17, lr: 5.34e-04
2022-05-04 15:56:44,181 INFO [train.py:715] (5/8) Epoch 3, batch 21850, loss[loss=0.1473, simple_loss=0.2137, pruned_loss=0.04048, over 4980.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2305, pruned_loss=0.0471, over 971970.34 frames.], batch size: 28, lr: 5.34e-04
2022-05-04 15:57:22,930 INFO [train.py:715] (5/8) Epoch 3, batch 21900, loss[loss=0.141, simple_loss=0.2192, pruned_loss=0.03145, over 4812.00 frames.], tot_loss[loss=0.162, simple_loss=0.2303, pruned_loss=0.04686, over 972382.79 frames.], batch size: 26, lr: 5.34e-04
2022-05-04 15:58:03,619 INFO [train.py:715] (5/8) Epoch 3, batch 21950, loss[loss=0.1469, simple_loss=0.2208, pruned_loss=0.03644, over 4968.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2307, pruned_loss=0.04674, over 972719.90 frames.], batch size: 24, lr: 5.34e-04
2022-05-04 15:58:43,249 INFO [train.py:715] (5/8) Epoch 3, batch 22000, loss[loss=0.1793, simple_loss=0.2452, pruned_loss=0.05668, over 4903.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2303, pruned_loss=0.04669, over 972450.59 frames.], batch size: 22, lr: 5.33e-04
2022-05-04 15:59:23,570 INFO [train.py:715] (5/8) Epoch 3, batch 22050, loss[loss=0.1769, simple_loss=0.2542, pruned_loss=0.04979, over 4749.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04682, over 972975.30 frames.], batch size: 16, lr: 5.33e-04
2022-05-04 16:00:04,303 INFO [train.py:715] (5/8) Epoch 3, batch 22100, loss[loss=0.1568, simple_loss=0.2219, pruned_loss=0.04586, over 4693.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2312, pruned_loss=0.04684, over 973204.05 frames.], batch size: 15, lr: 5.33e-04
2022-05-04 16:00:44,823 INFO [train.py:715] (5/8) Epoch 3, batch 22150, loss[loss=0.174, simple_loss=0.237, pruned_loss=0.05548, over 4974.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2311, pruned_loss=0.04707, over 973050.93 frames.], batch size: 15, lr: 5.33e-04
2022-05-04 16:01:24,043 INFO [train.py:715] (5/8) Epoch 3, batch 22200, loss[loss=0.1497, simple_loss=0.2165, pruned_loss=0.04145, over 4777.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04711, over 972336.11 frames.], batch size: 14, lr: 5.33e-04
2022-05-04 16:02:04,291 INFO [train.py:715] (5/8) Epoch 3, batch 22250, loss[loss=0.1295, simple_loss=0.1902, pruned_loss=0.03443, over 4807.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2305, pruned_loss=0.04693, over 971979.45 frames.], batch size: 12, lr: 5.33e-04
2022-05-04 16:02:45,551 INFO [train.py:715] (5/8) Epoch 3, batch 22300, loss[loss=0.1249, simple_loss=0.1938, pruned_loss=0.02801, over 4879.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04677, over 972284.98 frames.], batch size: 20, lr: 5.33e-04
2022-05-04 16:03:24,534 INFO [train.py:715] (5/8) Epoch 3, batch 22350, loss[loss=0.1542, simple_loss=0.2141, pruned_loss=0.04718, over 4787.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2306, pruned_loss=0.04688, over 971566.87 frames.], batch size: 14, lr: 5.33e-04
2022-05-04 16:04:04,612 INFO [train.py:715] (5/8) Epoch 3, batch 22400, loss[loss=0.1397, simple_loss=0.2029, pruned_loss=0.03821, over 4813.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04753, over 971498.10 frames.], batch size: 13, lr: 5.33e-04
2022-05-04 16:04:45,520 INFO [train.py:715] (5/8) Epoch 3, batch 22450, loss[loss=0.1684, simple_loss=0.2445, pruned_loss=0.04612, over 4952.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2316, pruned_loss=0.04707, over 971746.40 frames.], batch size: 24, lr: 5.32e-04
2022-05-04 16:05:25,968 INFO [train.py:715] (5/8) Epoch 3, batch 22500, loss[loss=0.188, simple_loss=0.2455, pruned_loss=0.0652, over 4925.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2318, pruned_loss=0.04734, over 972216.99 frames.], batch size: 29, lr: 5.32e-04
2022-05-04 16:06:05,380 INFO [train.py:715] (5/8) Epoch 3, batch 22550, loss[loss=0.1378, simple_loss=0.1975, pruned_loss=0.03899, over 4986.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2319, pruned_loss=0.04733, over 972240.40 frames.], batch size: 31, lr: 5.32e-04
2022-05-04 16:06:45,618 INFO [train.py:715] (5/8) Epoch 3, batch 22600, loss[loss=0.1514, simple_loss=0.227, pruned_loss=0.03795, over 4977.00 frames.], tot_loss[loss=0.163, simple_loss=0.2317, pruned_loss=0.04714, over 972509.04 frames.], batch size: 35, lr: 5.32e-04
2022-05-04 16:07:26,481 INFO [train.py:715] (5/8) Epoch 3, batch 22650, loss[loss=0.131, simple_loss=0.208, pruned_loss=0.02703, over 4693.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2313, pruned_loss=0.04711, over 973440.01 frames.], batch size: 15, lr: 5.32e-04
2022-05-04 16:08:06,299 INFO [train.py:715] (5/8) Epoch 3, batch 22700, loss[loss=0.1385, simple_loss=0.2085, pruned_loss=0.03425, over 4929.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2312, pruned_loss=0.04686, over 973730.80 frames.], batch size: 21, lr: 5.32e-04
2022-05-04 16:08:46,703 INFO [train.py:715] (5/8) Epoch 3, batch 22750, loss[loss=0.1747, simple_loss=0.2323, pruned_loss=0.05848, over 4875.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04737, over 973306.46 frames.], batch size: 13, lr: 5.32e-04
2022-05-04 16:09:27,106 INFO [train.py:715] (5/8) Epoch 3, batch 22800, loss[loss=0.1406, simple_loss=0.214, pruned_loss=0.03357, over 4954.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2322, pruned_loss=0.04732, over 972134.96 frames.], batch size: 15, lr: 5.32e-04
2022-05-04 16:10:07,179 INFO [train.py:715] (5/8) Epoch 3, batch 22850, loss[loss=0.1504, simple_loss=0.224, pruned_loss=0.03841, over 4823.00 frames.], tot_loss[loss=0.163, simple_loss=0.2317, pruned_loss=0.04717, over 971799.40 frames.], batch size: 26, lr: 5.32e-04
2022-05-04 16:10:46,897 INFO [train.py:715] (5/8) Epoch 3, batch 22900, loss[loss=0.1448, simple_loss=0.2214, pruned_loss=0.03411, over 4784.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2318, pruned_loss=0.0474, over 972624.85 frames.], batch size: 14, lr: 5.32e-04
2022-05-04 16:11:27,325 INFO [train.py:715] (5/8) Epoch 3, batch 22950, loss[loss=0.2307, simple_loss=0.2928, pruned_loss=0.08424, over 4947.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04756, over 972299.69 frames.], batch size: 21, lr: 5.31e-04
2022-05-04 16:12:08,437 INFO [train.py:715] (5/8) Epoch 3, batch 23000, loss[loss=0.16, simple_loss=0.2382, pruned_loss=0.04096, over 4987.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2322, pruned_loss=0.04755, over 971999.17 frames.], batch size: 25, lr: 5.31e-04
2022-05-04 16:12:48,297 INFO [train.py:715] (5/8) Epoch 3, batch 23050, loss[loss=0.1541, simple_loss=0.2277, pruned_loss=0.04025, over 4961.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2323, pruned_loss=0.04764, over 972045.41 frames.], batch size: 15, lr: 5.31e-04
2022-05-04 16:13:28,631 INFO [train.py:715] (5/8) Epoch 3, batch 23100, loss[loss=0.1266, simple_loss=0.2036, pruned_loss=0.02477, over 4990.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2321, pruned_loss=0.04727, over 972043.65 frames.], batch size: 16, lr: 5.31e-04
2022-05-04 16:14:09,396 INFO [train.py:715] (5/8) Epoch 3, batch 23150, loss[loss=0.1438, simple_loss=0.2072, pruned_loss=0.04018, over 4946.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2314, pruned_loss=0.04711, over 972513.94 frames.], batch size: 24, lr: 5.31e-04
2022-05-04 16:14:49,968 INFO [train.py:715] (5/8) Epoch 3, batch 23200, loss[loss=0.1416, simple_loss=0.2117, pruned_loss=0.03579, over 4811.00 frames.], tot_loss[loss=0.1624, simple_loss=0.231, pruned_loss=0.04692, over 971976.40 frames.], batch size: 25, lr: 5.31e-04
2022-05-04 16:15:29,489 INFO [train.py:715] (5/8) Epoch 3, batch 23250, loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03265, over 4872.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2318, pruned_loss=0.0472, over 972796.84 frames.], batch size: 16, lr: 5.31e-04
2022-05-04 16:16:10,262 INFO [train.py:715] (5/8) Epoch 3, batch 23300, loss[loss=0.2154, simple_loss=0.2835, pruned_loss=0.07368, over 4809.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2319, pruned_loss=0.04702, over 972913.99 frames.], batch size: 21, lr: 5.31e-04
2022-05-04 16:16:49,871 INFO [train.py:715] (5/8) Epoch 3, batch 23350, loss[loss=0.1511, simple_loss=0.2341, pruned_loss=0.03405, over 4770.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2307, pruned_loss=0.0463, over 972721.03 frames.], batch size: 18, lr: 5.31e-04
2022-05-04 16:17:27,676 INFO [train.py:715] (5/8) Epoch 3, batch 23400, loss[loss=0.138, simple_loss=0.2038, pruned_loss=0.03611, over 4785.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2296, pruned_loss=0.04566, over 972146.99 frames.], batch size: 18, lr: 5.30e-04
2022-05-04 16:18:06,222 INFO [train.py:715] (5/8) Epoch 3, batch 23450, loss[loss=0.1754, simple_loss=0.2362, pruned_loss=0.05731, over 4858.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2306, pruned_loss=0.04649, over 972774.33 frames.], batch size: 20, lr: 5.30e-04
2022-05-04 16:18:44,911 INFO [train.py:715] (5/8) Epoch 3, batch 23500, loss[loss=0.1557, simple_loss=0.215, pruned_loss=0.04824, over 4807.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04605, over 973099.17 frames.], batch size: 21, lr: 5.30e-04
2022-05-04 16:19:24,105 INFO [train.py:715] (5/8) Epoch 3, batch 23550, loss[loss=0.1563, simple_loss=0.2271, pruned_loss=0.04277, over 4971.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2296, pruned_loss=0.04599, over 972705.75 frames.], batch size: 25, lr: 5.30e-04
2022-05-04 16:20:05,337 INFO [train.py:715] (5/8) Epoch 3, batch 23600, loss[loss=0.1758, simple_loss=0.2524, pruned_loss=0.04956, over 4866.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2295, pruned_loss=0.04612, over 972203.71 frames.], batch size: 16, lr: 5.30e-04
2022-05-04 16:20:44,861 INFO [train.py:715] (5/8) Epoch 3, batch 23650, loss[loss=0.1776, simple_loss=0.2465, pruned_loss=0.0543, over 4767.00 frames.], tot_loss[loss=0.1607, simple_loss=0.229, pruned_loss=0.04621, over 972040.10 frames.], batch size: 14, lr: 5.30e-04
2022-05-04 16:21:24,818 INFO [train.py:715] (5/8) Epoch 3, batch 23700, loss[loss=0.1486, simple_loss=0.223, pruned_loss=0.03715, over 4875.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2294, pruned_loss=0.04615, over 971216.74 frames.], batch size: 20, lr: 5.30e-04
2022-05-04 16:22:03,569 INFO [train.py:715] (5/8) Epoch 3, batch 23750, loss[loss=0.1853, simple_loss=0.2438, pruned_loss=0.06338, over 4902.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2294, pruned_loss=0.04593, over 972430.72 frames.], batch size: 19, lr: 5.30e-04
2022-05-04 16:22:43,185 INFO [train.py:715] (5/8) Epoch 3, batch 23800, loss[loss=0.1785, simple_loss=0.2414, pruned_loss=0.0578, over 4766.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2299, pruned_loss=0.04628, over 971811.48 frames.], batch size: 18, lr: 5.30e-04
2022-05-04 16:23:22,783 INFO [train.py:715] (5/8) Epoch 3, batch 23850, loss[loss=0.1849, simple_loss=0.2412, pruned_loss=0.06426, over 4988.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2298, pruned_loss=0.04628, over 972575.52 frames.], batch size: 25, lr: 5.30e-04
2022-05-04 16:24:02,500 INFO [train.py:715] (5/8) Epoch 3, batch 23900, loss[loss=0.1719, simple_loss=0.2323, pruned_loss=0.05577, over 4967.00 frames.], tot_loss[loss=0.162, simple_loss=0.2306, pruned_loss=0.0467, over 972571.91 frames.], batch size: 35, lr: 5.29e-04
2022-05-04 16:24:41,551 INFO [train.py:715] (5/8) Epoch 3, batch 23950, loss[loss=0.1434, simple_loss=0.2146, pruned_loss=0.03607, over 4845.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04611, over 972313.98 frames.], batch size: 32, lr: 5.29e-04
2022-05-04 16:25:20,399 INFO [train.py:715] (5/8) Epoch 3, batch 24000, loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.0283, over 4919.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2294, pruned_loss=0.04576, over 972685.26 frames.], batch size: 29, lr: 5.29e-04
2022-05-04 16:25:20,400 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 16:25:32,864 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1132, simple_loss=0.1992, pruned_loss=0.0136, over 914524.00 frames.
2022-05-04 16:26:12,212 INFO [train.py:715] (5/8) Epoch 3, batch 24050, loss[loss=0.142, simple_loss=0.2132, pruned_loss=0.03535, over 4792.00 frames.], tot_loss[loss=0.161, simple_loss=0.2293, pruned_loss=0.04636, over 972571.08 frames.], batch size: 17, lr: 5.29e-04
2022-05-04 16:26:52,061 INFO [train.py:715] (5/8) Epoch 3, batch 24100, loss[loss=0.131, simple_loss=0.2093, pruned_loss=0.02637, over 4889.00 frames.], tot_loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04608, over 972288.12 frames.], batch size: 32, lr: 5.29e-04
2022-05-04 16:27:30,860 INFO [train.py:715] (5/8) Epoch 3, batch 24150, loss[loss=0.152, simple_loss=0.2205, pruned_loss=0.0418, over 4833.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2293, pruned_loss=0.04564, over 972212.19 frames.], batch size: 26, lr: 5.29e-04
2022-05-04 16:28:10,107 INFO [train.py:715] (5/8) Epoch 3, batch 24200, loss[loss=0.1423, simple_loss=0.2215, pruned_loss=0.03157, over 4988.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2289, pruned_loss=0.04537, over 971488.38 frames.], batch size: 25, lr: 5.29e-04
2022-05-04 16:28:50,507 INFO [train.py:715] (5/8) Epoch 3, batch 24250, loss[loss=0.1785, simple_loss=0.243, pruned_loss=0.05703, over 4957.00 frames.], tot_loss[loss=0.161, simple_loss=0.2297, pruned_loss=0.04618, over 972165.12 frames.], batch size: 39, lr: 5.29e-04
2022-05-04 16:29:30,767 INFO [train.py:715] (5/8) Epoch 3, batch 24300, loss[loss=0.1321, simple_loss=0.195, pruned_loss=0.03462, over 4891.00 frames.], tot_loss[loss=0.1612, simple_loss=0.23, pruned_loss=0.04619, over 972003.57 frames.], batch size: 22, lr: 5.29e-04
2022-05-04 16:30:10,087 INFO [train.py:715] (5/8) Epoch 3, batch 24350, loss[loss=0.1641, simple_loss=0.2265, pruned_loss=0.05089, over 4944.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04638, over 972178.38 frames.], batch size: 21, lr: 5.29e-04
2022-05-04 16:30:49,733 INFO [train.py:715] (5/8) Epoch 3, batch 24400, loss[loss=0.1892, simple_loss=0.2536, pruned_loss=0.06243, over 4872.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2308, pruned_loss=0.04684, over 971593.42 frames.], batch size: 32, lr: 5.28e-04
2022-05-04 16:31:29,800 INFO [train.py:715] (5/8) Epoch 3, batch 24450, loss[loss=0.1431, simple_loss=0.2095, pruned_loss=0.03837, over 4787.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2287, pruned_loss=0.04571, over 971765.00 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:32:09,115 INFO [train.py:715] (5/8) Epoch 3, batch 24500, loss[loss=0.1344, simple_loss=0.2051, pruned_loss=0.03187, over 4774.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2282, pruned_loss=0.04579, over 971402.61 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:32:48,514 INFO [train.py:715] (5/8) Epoch 3, batch 24550, loss[loss=0.1682, simple_loss=0.2196, pruned_loss=0.05839, over 4769.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2299, pruned_loss=0.04665, over 971545.97 frames.], batch size: 17, lr: 5.28e-04
2022-05-04 16:33:28,756 INFO [train.py:715] (5/8) Epoch 3, batch 24600, loss[loss=0.1617, simple_loss=0.2291, pruned_loss=0.04718, over 4892.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2309, pruned_loss=0.04694, over 971381.18 frames.], batch size: 19, lr: 5.28e-04
2022-05-04 16:34:08,286 INFO [train.py:715] (5/8) Epoch 3, batch 24650, loss[loss=0.1615, simple_loss=0.2323, pruned_loss=0.04532, over 4966.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2292, pruned_loss=0.04599, over 970976.27 frames.], batch size: 15, lr: 5.28e-04
2022-05-04 16:34:47,790 INFO [train.py:715] (5/8) Epoch 3, batch 24700, loss[loss=0.1679, simple_loss=0.2441, pruned_loss=0.04587, over 4786.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2303, pruned_loss=0.04622, over 971114.35 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:35:26,410 INFO [train.py:715] (5/8) Epoch 3, batch 24750, loss[loss=0.1382, simple_loss=0.2052, pruned_loss=0.03555, over 4793.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2287, pruned_loss=0.04532, over 971278.29 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:36:07,060 INFO [train.py:715] (5/8) Epoch 3, batch 24800, loss[loss=0.1582, simple_loss=0.2338, pruned_loss=0.04127, over 4930.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2293, pruned_loss=0.04593, over 971131.59 frames.], batch size: 29, lr: 5.28e-04
2022-05-04 16:36:46,783 INFO [train.py:715] (5/8) Epoch 3, batch 24850, loss[loss=0.1734, simple_loss=0.2371, pruned_loss=0.05483, over 4936.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2284, pruned_loss=0.04608, over 971562.19 frames.], batch size: 23, lr: 5.28e-04
2022-05-04 16:37:25,563 INFO [train.py:715] (5/8) Epoch 3, batch 24900, loss[loss=0.1795, simple_loss=0.2497, pruned_loss=0.0546, over 4829.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2289, pruned_loss=0.04603, over 971657.48 frames.], batch size: 15, lr: 5.27e-04
2022-05-04 16:38:05,477 INFO [train.py:715] (5/8) Epoch 3, batch 24950, loss[loss=0.1636, simple_loss=0.2313, pruned_loss=0.04789, over 4820.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2297, pruned_loss=0.04673, over 972417.02 frames.], batch size: 27, lr: 5.27e-04
2022-05-04 16:38:45,652 INFO [train.py:715] (5/8) Epoch 3, batch 25000, loss[loss=0.1275, simple_loss=0.2013, pruned_loss=0.0268, over 4904.00 frames.], tot_loss[loss=0.161, simple_loss=0.2294, pruned_loss=0.04633, over 972410.20 frames.], batch size: 19, lr: 5.27e-04
2022-05-04 16:39:25,199 INFO [train.py:715] (5/8) Epoch 3, batch 25050, loss[loss=0.1331, simple_loss=0.206, pruned_loss=0.03011, over 4929.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2288, pruned_loss=0.04589, over 973086.13 frames.], batch size: 18, lr: 5.27e-04
2022-05-04 16:40:04,366 INFO [train.py:715] (5/8) Epoch 3, batch 25100, loss[loss=0.1377, simple_loss=0.2074, pruned_loss=0.03397, over 4801.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2303, pruned_loss=0.04677, over 973197.24 frames.], batch size: 14, lr: 5.27e-04
2022-05-04 16:40:44,394 INFO [train.py:715] (5/8) Epoch 3, batch 25150, loss[loss=0.1409, simple_loss=0.2075, pruned_loss=0.03714, over 4759.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04674, over 972844.71 frames.], batch size: 18, lr: 5.27e-04
2022-05-04 16:41:23,890 INFO [train.py:715] (5/8) Epoch 3, batch 25200, loss[loss=0.1497, simple_loss=0.2201, pruned_loss=0.03965, over 4908.00 frames.], tot_loss[loss=0.162, simple_loss=0.2301, pruned_loss=0.0469, over 972453.62 frames.], batch size: 18, lr: 5.27e-04
2022-05-04 16:42:03,022 INFO [train.py:715] (5/8) Epoch 3, batch 25250, loss[loss=0.156, simple_loss=0.2218, pruned_loss=0.04514, over 4748.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2303, pruned_loss=0.04701, over 972186.59 frames.], batch size: 16, lr: 5.27e-04
2022-05-04 16:42:43,125 INFO [train.py:715] (5/8) Epoch 3, batch 25300, loss[loss=0.1318, simple_loss=0.1984, pruned_loss=0.0326, over 4943.00 frames.], tot_loss[loss=0.163, simple_loss=0.2309, pruned_loss=0.04758, over 971906.99 frames.], batch size: 21, lr: 5.27e-04
2022-05-04 16:43:22,956 INFO [train.py:715] (5/8) Epoch 3, batch 25350, loss[loss=0.1285, simple_loss=0.1928, pruned_loss=0.03209, over 4788.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2309, pruned_loss=0.04771, over 972084.32 frames.], batch size: 12, lr: 5.26e-04
2022-05-04 16:44:02,969 INFO [train.py:715] (5/8) Epoch 3, batch 25400, loss[loss=0.154, simple_loss=0.2203, pruned_loss=0.04387, over 4833.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2312, pruned_loss=0.04782, over 972214.58 frames.], batch size: 15, lr: 5.26e-04
2022-05-04 16:44:42,160 INFO [train.py:715] (5/8) Epoch 3, batch 25450, loss[loss=0.1761, simple_loss=0.2382, pruned_loss=0.05698, over 4827.00 frames.], tot_loss[loss=0.1641, simple_loss=0.232, pruned_loss=0.04815, over 971839.71 frames.], batch size: 15, lr: 5.26e-04
2022-05-04 16:45:22,339 INFO [train.py:715] (5/8) Epoch 3, batch 25500, loss[loss=0.1465, simple_loss=0.2226, pruned_loss=0.03514, over 4845.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04756, over 971340.61 frames.], batch size: 20, lr: 5.26e-04
2022-05-04 16:46:02,168 INFO [train.py:715] (5/8) Epoch 3, batch 25550, loss[loss=0.1569, simple_loss=0.2249, pruned_loss=0.04452, over 4848.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2305, pruned_loss=0.04706, over 971522.00 frames.], batch size: 30, lr: 5.26e-04
2022-05-04 16:46:41,626 INFO [train.py:715] (5/8) Epoch 3, batch 25600, loss[loss=0.1759, simple_loss=0.2517, pruned_loss=0.05009, over 4777.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2306, pruned_loss=0.04689, over 971673.49 frames.], batch size: 17, lr: 5.26e-04
2022-05-04 16:47:22,008 INFO [train.py:715] (5/8) Epoch 3, batch 25650, loss[loss=0.1863, simple_loss=0.2511, pruned_loss=0.06077, over 4804.00 frames.], tot_loss[loss=0.1628, simple_loss=0.231, pruned_loss=0.04731, over 971737.88 frames.], batch size: 21, lr: 5.26e-04
2022-05-04 16:48:02,205 INFO [train.py:715] (5/8) Epoch 3, batch 25700, loss[loss=0.1645, simple_loss=0.2321, pruned_loss=0.04849, over 4910.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2308, pruned_loss=0.04711, over 971609.04 frames.], batch size: 17, lr: 5.26e-04
2022-05-04 16:48:41,538 INFO [train.py:715] (5/8) Epoch 3, batch 25750, loss[loss=0.1362, simple_loss=0.2128, pruned_loss=0.02981, over 4978.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2311, pruned_loss=0.04698, over 972146.20 frames.], batch size: 15, lr: 5.26e-04
2022-05-04 16:49:21,103 INFO [train.py:715] (5/8) Epoch 3, batch 25800, loss[loss=0.1643, simple_loss=0.225, pruned_loss=0.05187, over 4974.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2308, pruned_loss=0.04648, over 972494.48 frames.], batch size: 14, lr: 5.26e-04
2022-05-04 16:50:01,081 INFO [train.py:715] (5/8) Epoch 3, batch 25850, loss[loss=0.1373, simple_loss=0.2163, pruned_loss=0.02919, over 4972.00 frames.], tot_loss[loss=0.161, simple_loss=0.2303, pruned_loss=0.04586, over 972109.86 frames.], batch size: 24, lr: 5.25e-04
2022-05-04 16:50:39,396 INFO [train.py:715] (5/8) Epoch 3, batch 25900, loss[loss=0.1435, simple_loss=0.2203, pruned_loss=0.03336, over 4940.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2299, pruned_loss=0.04563, over 972355.39 frames.], batch size: 21, lr: 5.25e-04
2022-05-04 16:51:18,327 INFO [train.py:715] (5/8) Epoch 3, batch 25950, loss[loss=0.1765, simple_loss=0.2361, pruned_loss=0.05848, over 4947.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2307, pruned_loss=0.04648, over 972970.98 frames.], batch size: 29, lr: 5.25e-04
2022-05-04 16:51:58,432 INFO [train.py:715] (5/8) Epoch 3, batch 26000, loss[loss=0.1616, simple_loss=0.2186, pruned_loss=0.05234, over 4837.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2311, pruned_loss=0.04718, over 972952.51 frames.], batch size: 12, lr: 5.25e-04
2022-05-04 16:52:37,676 INFO [train.py:715] (5/8) Epoch 3, batch 26050, loss[loss=0.158, simple_loss=0.2287, pruned_loss=0.04363, over 4887.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2309, pruned_loss=0.04698, over 972852.23 frames.], batch size: 16, lr: 5.25e-04
2022-05-04 16:53:16,012 INFO [train.py:715] (5/8) Epoch 3, batch 26100, loss[loss=0.1659, simple_loss=0.2293, pruned_loss=0.05123, over 4960.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04704, over 973087.05 frames.], batch size: 29, lr: 5.25e-04
2022-05-04 16:53:55,502 INFO [train.py:715] (5/8) Epoch 3, batch 26150, loss[loss=0.15, simple_loss=0.2204, pruned_loss=0.03979, over 4910.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04684, over 972863.97 frames.], batch size: 23, lr: 5.25e-04
2022-05-04 16:54:35,542 INFO [train.py:715] (5/8) Epoch 3, batch 26200, loss[loss=0.1843, simple_loss=0.2563, pruned_loss=0.05611, over 4942.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2302, pruned_loss=0.04647, over 972816.19 frames.], batch size: 29, lr: 5.25e-04
2022-05-04 16:55:13,646 INFO [train.py:715] (5/8) Epoch 3, batch 26250, loss[loss=0.1677, simple_loss=0.2328, pruned_loss=0.05128, over 4775.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2309, pruned_loss=0.04668, over 972350.90 frames.], batch size: 14, lr: 5.25e-04
2022-05-04 16:55:52,854 INFO [train.py:715] (5/8) Epoch 3, batch 26300, loss[loss=0.1365, simple_loss=0.2136, pruned_loss=0.02975, over 4927.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.0467, over 972092.98 frames.], batch size: 21, lr: 5.25e-04
2022-05-04 16:56:32,817 INFO [train.py:715] (5/8) Epoch 3, batch 26350, loss[loss=0.1843, simple_loss=0.2406, pruned_loss=0.06395, over 4911.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04677, over 972510.34 frames.], batch size: 17, lr: 5.24e-04
2022-05-04 16:57:12,181 INFO [train.py:715] (5/8) Epoch 3, batch 26400, loss[loss=0.172, simple_loss=0.2369, pruned_loss=0.05356, over 4937.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04657, over 973034.50 frames.], batch size: 39, lr: 5.24e-04
2022-05-04 16:57:51,173 INFO [train.py:715] (5/8) Epoch 3, batch 26450, loss[loss=0.1791, simple_loss=0.2427, pruned_loss=0.05771, over 4976.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2299, pruned_loss=0.04651, over 972842.69 frames.], batch size: 15, lr: 5.24e-04
2022-05-04 16:58:30,425 INFO [train.py:715] (5/8) Epoch 3, batch 26500, loss[loss=0.1565, simple_loss=0.2191, pruned_loss=0.04697, over 4747.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2297, pruned_loss=0.04678, over 972987.63 frames.], batch size: 19, lr: 5.24e-04
2022-05-04 16:59:09,908 INFO [train.py:715] (5/8) Epoch 3, batch 26550, loss[loss=0.1591, simple_loss=0.227, pruned_loss=0.04561, over 4771.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2286, pruned_loss=0.04578, over 973207.71 frames.], batch size: 14, lr: 5.24e-04
2022-05-04 16:59:48,113 INFO [train.py:715] (5/8) Epoch 3, batch 26600, loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.03109, over 4683.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2293, pruned_loss=0.04607, over 973104.80 frames.], batch size: 15, lr: 5.24e-04
2022-05-04 17:00:27,331 INFO [train.py:715] (5/8) Epoch 3, batch 26650, loss[loss=0.1508, simple_loss=0.2249, pruned_loss=0.03838, over 4810.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2293, pruned_loss=0.04568, over 973003.67 frames.], batch size: 26, lr: 5.24e-04
2022-05-04 17:01:07,872 INFO [train.py:715] (5/8) Epoch 3, batch 26700, loss[loss=0.1641, simple_loss=0.2338, pruned_loss=0.04717, over 4849.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2291, pruned_loss=0.04596, over 972589.61 frames.], batch size: 15, lr: 5.24e-04
2022-05-04 17:01:47,355 INFO [train.py:715] (5/8) Epoch 3, batch 26750, loss[loss=0.1479, simple_loss=0.217, pruned_loss=0.03937, over 4820.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2296, pruned_loss=0.04586, over 972721.13 frames.], batch size: 13, lr: 5.24e-04
2022-05-04 17:02:26,599 INFO [train.py:715] (5/8) Epoch 3, batch 26800, loss[loss=0.139, simple_loss=0.2002, pruned_loss=0.03886, over 4904.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2308, pruned_loss=0.04644, over 972876.25 frames.], batch size: 17, lr: 5.24e-04
2022-05-04 17:03:06,720 INFO [train.py:715] (5/8) Epoch 3, batch 26850, loss[loss=0.1846, simple_loss=0.2531, pruned_loss=0.05806, over 4784.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2304, pruned_loss=0.04611, over 972232.49 frames.], batch size: 17, lr: 5.23e-04
2022-05-04 17:03:47,105 INFO [train.py:715] (5/8) Epoch 3, batch 26900, loss[loss=0.1583, simple_loss=0.2227, pruned_loss=0.04691, over 4957.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2289, pruned_loss=0.04548, over 971647.26 frames.], batch size: 15, lr: 5.23e-04
2022-05-04 17:04:26,663 INFO [train.py:715] (5/8) Epoch 3, batch 26950, loss[loss=0.1703, simple_loss=0.2334, pruned_loss=0.05358, over 4866.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2296, pruned_loss=0.04615, over 972523.31 frames.], batch size: 32, lr: 5.23e-04
2022-05-04 17:05:05,427 INFO [train.py:715] (5/8) Epoch 3, batch 27000, loss[loss=0.1513, simple_loss=0.2177, pruned_loss=0.04247, over 4698.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2308, pruned_loss=0.04653, over 972695.73 frames.], batch size: 15, lr: 5.23e-04
2022-05-04 17:05:05,428 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 17:05:14,908 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1134, simple_loss=0.1995, pruned_loss=0.01366, over 914524.00 frames.
2022-05-04 17:05:54,548 INFO [train.py:715] (5/8) Epoch 3, batch 27050, loss[loss=0.1719, simple_loss=0.2397, pruned_loss=0.05198, over 4952.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2311, pruned_loss=0.04682, over 973499.68 frames.], batch size: 14, lr: 5.23e-04
2022-05-04 17:06:34,876 INFO [train.py:715] (5/8) Epoch 3, batch 27100, loss[loss=0.1709, simple_loss=0.2421, pruned_loss=0.04984, over 4808.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2315, pruned_loss=0.04702, over 973132.34 frames.], batch size: 25, lr: 5.23e-04
2022-05-04 17:07:14,167 INFO [train.py:715] (5/8) Epoch 3, batch 27150, loss[loss=0.1295, simple_loss=0.2019, pruned_loss=0.02861, over 4758.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2311, pruned_loss=0.04681, over 973544.91 frames.], batch size: 14, lr: 5.23e-04
2022-05-04 17:07:52,929 INFO [train.py:715] (5/8) Epoch 3, batch 27200, loss[loss=0.1739, simple_loss=0.2401, pruned_loss=0.05386, over 4869.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2306, pruned_loss=0.04645, over 973343.97 frames.], batch size: 20, lr: 5.23e-04
2022-05-04 17:08:32,667 INFO [train.py:715] (5/8) Epoch 3, batch 27250, loss[loss=0.1684, simple_loss=0.2482, pruned_loss=0.0443, over 4902.00 frames.], tot_loss[loss=0.1623, simple_loss=0.231, pruned_loss=0.0468, over 973616.60 frames.], batch size: 19, lr: 5.23e-04
2022-05-04 17:09:12,363 INFO [train.py:715] (5/8) Epoch 3, batch 27300, loss[loss=0.1523, simple_loss=0.2303, pruned_loss=0.03719, over 4890.00 frames.], tot_loss[loss=0.1622, simple_loss=0.231, pruned_loss=0.04668, over 973870.32 frames.], batch size: 19, lr: 5.23e-04
2022-05-04 17:09:51,021 INFO [train.py:715] (5/8) Epoch 3, batch 27350, loss[loss=0.1799, simple_loss=0.2481, pruned_loss=0.05592, over 4825.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2313, pruned_loss=0.04659, over 973221.44 frames.], batch size: 15, lr: 5.22e-04
2022-05-04 17:10:30,268 INFO [train.py:715] (5/8) Epoch 3, batch 27400, loss[loss=0.1828, simple_loss=0.2419, pruned_loss=0.06186, over 4823.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2308, pruned_loss=0.04597, over 973316.98 frames.], batch size: 15, lr: 5.22e-04
2022-05-04 17:11:10,415 INFO [train.py:715] (5/8) Epoch 3, batch 27450, loss[loss=0.1619, simple_loss=0.2317, pruned_loss=0.04608, over 4969.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2296, pruned_loss=0.04546, over 972685.25 frames.], batch size: 35, lr: 5.22e-04
2022-05-04 17:11:49,741 INFO [train.py:715] (5/8) Epoch 3, batch 27500, loss[loss=0.2234, simple_loss=0.2779, pruned_loss=0.08451, over 4737.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2291, pruned_loss=0.04532, over 972572.56 frames.], batch size: 16, lr: 5.22e-04
2022-05-04 17:12:28,639 INFO [train.py:715] (5/8) Epoch 3, batch 27550, loss[loss=0.1668, simple_loss=0.2288, pruned_loss=0.05242, over 4797.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2309, pruned_loss=0.04628, over 972143.07 frames.], batch size: 21, lr: 5.22e-04
2022-05-04 17:13:08,352 INFO [train.py:715] (5/8) Epoch 3, batch 27600, loss[loss=0.1826, simple_loss=0.23, pruned_loss=0.06763, over 4842.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2307, pruned_loss=0.04615, over 971988.17 frames.], batch size: 30, lr: 5.22e-04
2022-05-04 17:13:47,998 INFO [train.py:715] (5/8) Epoch 3, batch 27650, loss[loss=0.1962, simple_loss=0.259, pruned_loss=0.06667, over 4953.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2303, pruned_loss=0.04605, over 973190.46 frames.], batch size: 24, lr: 5.22e-04
2022-05-04 17:14:26,622 INFO [train.py:715] (5/8) Epoch 3, batch 27700, loss[loss=0.1634, simple_loss=0.2317, pruned_loss=0.04754, over 4685.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2308, pruned_loss=0.0461, over 973244.02 frames.], batch size: 15, lr: 5.22e-04
2022-05-04 17:15:06,394 INFO [train.py:715] (5/8) Epoch 3, batch 27750, loss[loss=0.1728, simple_loss=0.2396, pruned_loss=0.05302, over 4929.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2306, pruned_loss=0.04612, over 972809.19 frames.], batch size: 29, lr: 5.22e-04
2022-05-04 17:15:46,349 INFO [train.py:715] (5/8) Epoch 3, batch 27800, loss[loss=0.1918, simple_loss=0.2406, pruned_loss=0.07149, over 4650.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04583, over 971902.94 frames.], batch size: 13, lr: 5.22e-04
2022-05-04 17:16:25,742 INFO [train.py:715] (5/8) Epoch 3, batch 27850, loss[loss=0.1591, simple_loss=0.2279, pruned_loss=0.04511, over 4967.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2306, pruned_loss=0.04626, over 971943.45 frames.], batch size: 28, lr: 5.21e-04
2022-05-04 17:17:04,209 INFO [train.py:715] (5/8) Epoch 3, batch 27900, loss[loss=0.1303, simple_loss=0.2015, pruned_loss=0.02951, over 4989.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2293, pruned_loss=0.04583, over 971752.27 frames.], batch size: 25, lr: 5.21e-04
2022-05-04 17:17:43,814 INFO [train.py:715] (5/8) Epoch 3, batch 27950, loss[loss=0.1412, simple_loss=0.2175, pruned_loss=0.03249, over 4964.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2301, pruned_loss=0.04589, over 972762.37 frames.], batch size: 21, lr: 5.21e-04
2022-05-04 17:18:23,714 INFO [train.py:715] (5/8) Epoch 3, batch 28000, loss[loss=0.1881, simple_loss=0.2468, pruned_loss=0.06471, over 4982.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04601, over 973009.31 frames.], batch size: 15, lr: 5.21e-04
2022-05-04 17:19:02,276 INFO [train.py:715] (5/8) Epoch 3, batch 28050, loss[loss=0.1347, simple_loss=0.2062, pruned_loss=0.03161, over 4954.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2291, pruned_loss=0.04552, over 973445.61 frames.], batch size: 24, lr: 5.21e-04
2022-05-04 17:19:41,710 INFO [train.py:715] (5/8) Epoch 3, batch 28100, loss[loss=0.1852, simple_loss=0.2494, pruned_loss=0.06053, over 4919.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2292, pruned_loss=0.04572, over 973336.12 frames.], batch size: 19, lr: 5.21e-04
2022-05-04 17:20:21,588 INFO [train.py:715] (5/8) Epoch 3, batch 28150, loss[loss=0.1601, simple_loss=0.2232, pruned_loss=0.04845, over 4856.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2286, pruned_loss=0.04539, over 973178.77 frames.], batch size: 30, lr: 5.21e-04
2022-05-04 17:21:00,809 INFO [train.py:715] (5/8) Epoch 3, batch 28200, loss[loss=0.2064, simple_loss=0.2654, pruned_loss=0.07367, over 4702.00 frames.], tot_loss[loss=0.16, simple_loss=0.2289, pruned_loss=0.04555, over 971680.14 frames.], batch size: 15, lr: 5.21e-04
2022-05-04 17:21:39,659 INFO [train.py:715] (5/8) Epoch 3, batch 28250, loss[loss=0.1624, simple_loss=0.235, pruned_loss=0.04493, over 4795.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2284, pruned_loss=0.04509, over 972048.17 frames.], batch size: 18, lr: 5.21e-04
2022-05-04 17:22:18,999 INFO [train.py:715] (5/8) Epoch 3, batch 28300, loss[loss=0.1257, simple_loss=0.2083, pruned_loss=0.02158, over 4835.00 frames.], tot_loss[loss=0.1599, simple_loss=0.229, pruned_loss=0.04539, over 972432.17 frames.], batch size: 26, lr: 5.21e-04
2022-05-04 17:22:58,003 INFO [train.py:715] (5/8) Epoch 3, batch 28350, loss[loss=0.148, simple_loss=0.2173, pruned_loss=0.03936, over 4821.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2295, pruned_loss=0.04559, over 972824.27 frames.], batch size: 27, lr: 5.21e-04
2022-05-04 17:23:37,194 INFO [train.py:715] (5/8) Epoch 3, batch 28400, loss[loss=0.1924, simple_loss=0.2469, pruned_loss=0.06895, over 4868.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2295, pruned_loss=0.046, over 972997.42 frames.], batch size: 20, lr: 5.20e-04
2022-05-04 17:24:15,828 INFO [train.py:715] (5/8) Epoch 3, batch 28450, loss[loss=0.1314, simple_loss=0.1915, pruned_loss=0.03562, over 4787.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04646, over 972992.47 frames.], batch size: 12, lr: 5.20e-04
2022-05-04 17:24:55,565 INFO [train.py:715] (5/8) Epoch 3, batch 28500, loss[loss=0.1876, simple_loss=0.2409, pruned_loss=0.06716, over 4841.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2301, pruned_loss=0.04652, over 972688.83 frames.], batch size: 13, lr: 5.20e-04
2022-05-04 17:25:34,508 INFO [train.py:715] (5/8) Epoch 3, batch 28550, loss[loss=0.1735, simple_loss=0.24, pruned_loss=0.05349, over 4816.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04611, over 973183.33 frames.], batch size: 26, lr: 5.20e-04
2022-05-04 17:26:13,420 INFO [train.py:715] (5/8) Epoch 3, batch 28600, loss[loss=0.1445, simple_loss=0.2206, pruned_loss=0.03416, over 4690.00 frames.], tot_loss[loss=0.1611, simple_loss=0.23, pruned_loss=0.04607, over 972360.98 frames.], batch size: 15, lr: 5.20e-04
2022-05-04 17:26:53,128 INFO [train.py:715] (5/8) Epoch 3, batch 28650, loss[loss=0.1529, simple_loss=0.2335, pruned_loss=0.03609, over 4819.00 frames.], tot_loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04606, over 972279.46 frames.], batch size: 26, lr: 5.20e-04
2022-05-04 17:27:33,011 INFO [train.py:715] (5/8) Epoch 3, batch 28700, loss[loss=0.1549, simple_loss=0.221, pruned_loss=0.04439, over 4822.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2296, pruned_loss=0.04577, over 972714.89 frames.], batch size: 13, lr: 5.20e-04
2022-05-04 17:28:12,157 INFO [train.py:715] (5/8) Epoch 3, batch 28750, loss[loss=0.1812, simple_loss=0.2571, pruned_loss=0.05266, over 4698.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2299, pruned_loss=0.04584, over 973298.93 frames.], batch size: 15, lr: 5.20e-04
2022-05-04 17:28:51,998 INFO [train.py:715] (5/8) Epoch 3, batch 28800, loss[loss=0.1373, simple_loss=0.2046, pruned_loss=0.03498, over 4932.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2296, pruned_loss=0.04579, over 973556.70 frames.], batch size: 29, lr: 5.20e-04
2022-05-04 17:29:32,019 INFO [train.py:715] (5/8) Epoch 3, batch 28850, loss[loss=0.1464, simple_loss=0.2158, pruned_loss=0.03847, over 4984.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04578, over 973274.22 frames.], batch size: 14, lr: 5.20e-04
2022-05-04 17:30:11,198 INFO [train.py:715] (5/8) Epoch 3, batch 28900, loss[loss=0.1216, simple_loss=0.1933, pruned_loss=0.02491, over 4836.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2289, pruned_loss=0.04513, over 973003.60 frames.], batch size: 13, lr: 5.19e-04
2022-05-04 17:30:50,077 INFO [train.py:715] (5/8) Epoch 3, batch 28950, loss[loss=0.1776, simple_loss=0.2604, pruned_loss=0.04736, over 4808.00 frames.], tot_loss[loss=0.16, simple_loss=0.2291, pruned_loss=0.04544, over 973075.90 frames.], batch size: 26, lr: 5.19e-04
2022-05-04 17:31:29,815 INFO [train.py:715] (5/8) Epoch 3, batch 29000, loss[loss=0.1483, simple_loss=0.2115, pruned_loss=0.04258, over 4912.00 frames.], tot_loss[loss=0.1597, simple_loss=0.229, pruned_loss=0.04524, over 972108.20 frames.], batch size: 23, lr: 5.19e-04
2022-05-04 17:32:10,056 INFO [train.py:715] (5/8) Epoch 3, batch 29050, loss[loss=0.1293, simple_loss=0.1885, pruned_loss=0.03509, over 4823.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2277, pruned_loss=0.04475, over 972090.44 frames.], batch size: 13, lr: 5.19e-04
2022-05-04 17:32:48,615 INFO [train.py:715] (5/8) Epoch 3, batch 29100, loss[loss=0.1624, simple_loss=0.2278, pruned_loss=0.0485, over 4875.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2288, pruned_loss=0.04512, over 971880.73 frames.], batch size: 16, lr: 5.19e-04
2022-05-04 17:33:28,198 INFO [train.py:715] (5/8) Epoch 3, batch 29150, loss[loss=0.1397, simple_loss=0.2151, pruned_loss=0.0321, over 4775.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2284, pruned_loss=0.04528, over 972073.37 frames.], batch size: 18, lr: 5.19e-04
2022-05-04 17:34:08,089 INFO [train.py:715] (5/8) Epoch 3, batch 29200, loss[loss=0.1587, simple_loss=0.2235, pruned_loss=0.04697, over 4866.00 frames.], tot_loss[loss=0.159, simple_loss=0.2277, pruned_loss=0.04512, over 972074.94 frames.], batch size: 34, lr: 5.19e-04
2022-05-04 17:34:47,188 INFO [train.py:715] (5/8) Epoch 3, batch 29250, loss[loss=0.1699, simple_loss=0.2266, pruned_loss=0.05659, over 4787.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2271, pruned_loss=0.04493, over 971560.87 frames.], batch size: 14, lr: 5.19e-04
2022-05-04 17:35:26,068 INFO [train.py:715] (5/8) Epoch 3, batch 29300, loss[loss=0.1382, simple_loss=0.202, pruned_loss=0.03726, over 4816.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2273, pruned_loss=0.04513, over 971682.87 frames.], batch size: 12, lr: 5.19e-04
2022-05-04 17:36:06,260 INFO [train.py:715] (5/8) Epoch 3, batch 29350, loss[loss=0.1456, simple_loss=0.2078, pruned_loss=0.04175, over 4789.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2272, pruned_loss=0.04486, over 971276.70 frames.], batch size: 14, lr: 5.19e-04
2022-05-04 17:36:45,934 INFO [train.py:715] (5/8) Epoch 3, batch 29400, loss[loss=0.1717, simple_loss=0.2389, pruned_loss=0.05228, over 4689.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2288, pruned_loss=0.04604, over 970858.84 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:37:24,688 INFO [train.py:715] (5/8) Epoch 3, batch 29450, loss[loss=0.18, simple_loss=0.2455, pruned_loss=0.05721, over 4915.00 frames.], tot_loss[loss=0.161, simple_loss=0.2293, pruned_loss=0.04632, over 970860.51 frames.], batch size: 17, lr: 5.18e-04
2022-05-04 17:38:03,870 INFO [train.py:715] (5/8) Epoch 3, batch 29500, loss[loss=0.1457, simple_loss=0.2184, pruned_loss=0.03654, over 4693.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04602, over 971178.95 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:38:43,450 INFO [train.py:715] (5/8) Epoch 3, batch 29550, loss[loss=0.1345, simple_loss=0.215, pruned_loss=0.02701, over 4761.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2294, pruned_loss=0.04617, over 971616.76 frames.], batch size: 17, lr: 5.18e-04
2022-05-04 17:39:22,772 INFO [train.py:715] (5/8) Epoch 3, batch 29600, loss[loss=0.1687, simple_loss=0.2377, pruned_loss=0.04983, over 4951.00 frames.], tot_loss[loss=0.161, simple_loss=0.2293, pruned_loss=0.04629, over 971670.46 frames.], batch size: 35, lr: 5.18e-04
2022-05-04 17:40:01,836 INFO [train.py:715] (5/8) Epoch 3, batch 29650, loss[loss=0.1504, simple_loss=0.2228, pruned_loss=0.03902, over 4783.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2288, pruned_loss=0.04588, over 971759.40 frames.], batch size: 17, lr: 5.18e-04
2022-05-04 17:40:41,988 INFO [train.py:715] (5/8) Epoch 3, batch 29700, loss[loss=0.1974, simple_loss=0.2639, pruned_loss=0.06551, over 4684.00 frames.], tot_loss[loss=0.16, simple_loss=0.2286, pruned_loss=0.04568, over 971221.14 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:41:22,015 INFO [train.py:715] (5/8) Epoch 3, batch 29750, loss[loss=0.1423, simple_loss=0.2066, pruned_loss=0.03899, over 4781.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2287, pruned_loss=0.04592, over 971455.27 frames.], batch size: 18, lr: 5.18e-04
2022-05-04 17:42:00,529 INFO [train.py:715] (5/8) Epoch 3, batch 29800, loss[loss=0.1972, simple_loss=0.2378, pruned_loss=0.07824, over 4981.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2291, pruned_loss=0.04627, over 971036.29 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:42:40,515 INFO [train.py:715] (5/8) Epoch 3, batch 29850, loss[loss=0.1474, simple_loss=0.2227, pruned_loss=0.03601, over 4782.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2298, pruned_loss=0.04642, over 971309.87 frames.], batch size: 17, lr: 5.18e-04
2022-05-04 17:43:20,046 INFO [train.py:715] (5/8) Epoch 3, batch 29900, loss[loss=0.1684, simple_loss=0.2493, pruned_loss=0.04375, over 4930.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04618, over 971387.73 frames.], batch size: 18, lr: 5.18e-04
2022-05-04 17:43:58,723 INFO [train.py:715] (5/8) Epoch 3, batch 29950, loss[loss=0.1423, simple_loss=0.2143, pruned_loss=0.03515, over 4799.00 frames.], tot_loss[loss=0.161, simple_loss=0.2292, pruned_loss=0.04638, over 971504.19 frames.], batch size: 24, lr: 5.17e-04
2022-05-04 17:44:37,450 INFO [train.py:715] (5/8) Epoch 3, batch 30000, loss[loss=0.1418, simple_loss=0.2233, pruned_loss=0.03012, over 4814.00 frames.], tot_loss[loss=0.161, simple_loss=0.2292, pruned_loss=0.04639, over 971132.24 frames.], batch size: 26, lr: 5.17e-04
2022-05-04 17:44:37,450 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 17:44:47,856 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1135, simple_loss=0.1993, pruned_loss=0.01381, over 914524.00 frames.
2022-05-04 17:45:26,663 INFO [train.py:715] (5/8) Epoch 3, batch 30050, loss[loss=0.1785, simple_loss=0.2618, pruned_loss=0.04759, over 4805.00 frames.], tot_loss[loss=0.1619, simple_loss=0.23, pruned_loss=0.04689, over 971985.50 frames.], batch size: 21, lr: 5.17e-04
2022-05-04 17:46:06,304 INFO [train.py:715] (5/8) Epoch 3, batch 30100, loss[loss=0.1793, simple_loss=0.2449, pruned_loss=0.05686, over 4986.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2302, pruned_loss=0.04718, over 971890.11 frames.], batch size: 28, lr: 5.17e-04
2022-05-04 17:46:46,369 INFO [train.py:715] (5/8) Epoch 3, batch 30150, loss[loss=0.1592, simple_loss=0.2338, pruned_loss=0.04233, over 4895.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2304, pruned_loss=0.04769, over 972135.44 frames.], batch size: 19, lr: 5.17e-04
2022-05-04 17:47:24,500 INFO [train.py:715] (5/8) Epoch 3, batch 30200, loss[loss=0.171, simple_loss=0.249, pruned_loss=0.04647, over 4951.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2302, pruned_loss=0.04755, over 972965.09 frames.], batch size: 21, lr: 5.17e-04
2022-05-04 17:48:04,129 INFO [train.py:715] (5/8) Epoch 3, batch 30250, loss[loss=0.1625, simple_loss=0.2372, pruned_loss=0.04391, over 4972.00 frames.], tot_loss[loss=0.162, simple_loss=0.2298, pruned_loss=0.04717, over 973430.17 frames.], batch size: 28, lr: 5.17e-04
2022-05-04 17:48:44,309 INFO [train.py:715] (5/8) Epoch 3, batch 30300, loss[loss=0.1553, simple_loss=0.2236, pruned_loss=0.04353, over 4922.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2299, pruned_loss=0.0469, over 973478.49 frames.], batch size: 29, lr: 5.17e-04
2022-05-04 17:49:23,078 INFO [train.py:715] (5/8) Epoch 3, batch 30350, loss[loss=0.1587, simple_loss=0.2235, pruned_loss=0.04695, over 4700.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2285, pruned_loss=0.04628, over 973086.58 frames.], batch size: 15, lr: 5.17e-04
2022-05-04 17:50:02,734 INFO [train.py:715] (5/8) Epoch 3, batch 30400, loss[loss=0.1818, simple_loss=0.2571, pruned_loss=0.05326, over 4924.00 frames.], tot_loss[loss=0.1606, simple_loss=0.229, pruned_loss=0.04608, over 973028.79 frames.], batch size: 23, lr: 5.17e-04
2022-05-04 17:50:42,519 INFO [train.py:715] (5/8) Epoch 3, batch 30450, loss[loss=0.1749, simple_loss=0.2423, pruned_loss=0.05381, over 4880.00 frames.], tot_loss[loss=0.1606, simple_loss=0.229, pruned_loss=0.04604, over 973064.65 frames.], batch size: 32, lr: 5.16e-04
2022-05-04 17:51:22,932 INFO [train.py:715] (5/8) Epoch 3, batch 30500, loss[loss=0.1703, simple_loss=0.2453, pruned_loss=0.04768, over 4841.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2279, pruned_loss=0.04528, over 972300.05 frames.], batch size: 30, lr: 5.16e-04
2022-05-04 17:52:02,153 INFO [train.py:715] (5/8) Epoch 3, batch 30550, loss[loss=0.1853, simple_loss=0.2497, pruned_loss=0.06041, over 4775.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2276, pruned_loss=0.04529, over 972701.63 frames.], batch size: 18, lr: 5.16e-04
2022-05-04 17:52:41,685 INFO [train.py:715] (5/8) Epoch 3, batch 30600, loss[loss=0.163, simple_loss=0.2271, pruned_loss=0.04942, over 4695.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2278, pruned_loss=0.04565, over 972111.39 frames.], batch size: 15, lr: 5.16e-04
2022-05-04 17:53:21,640 INFO [train.py:715] (5/8) Epoch 3, batch 30650, loss[loss=0.1952, simple_loss=0.2474, pruned_loss=0.07147, over 4735.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2282, pruned_loss=0.04538, over 972285.62 frames.], batch size: 16, lr: 5.16e-04
2022-05-04 17:54:00,308 INFO [train.py:715] (5/8) Epoch 3, batch 30700, loss[loss=0.1454, simple_loss=0.2138, pruned_loss=0.03853, over 4981.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04528, over 972133.25 frames.], batch size: 28, lr: 5.16e-04
2022-05-04 17:54:39,862 INFO [train.py:715] (5/8) Epoch 3, batch 30750, loss[loss=0.1516, simple_loss=0.2147, pruned_loss=0.04419, over 4865.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2289, pruned_loss=0.04539, over 972554.85 frames.], batch size: 16, lr: 5.16e-04
2022-05-04 17:55:19,268 INFO [train.py:715] (5/8) Epoch 3, batch 30800, loss[loss=0.1406, simple_loss=0.2103, pruned_loss=0.03545, over 4818.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2293, pruned_loss=0.04609, over 972297.45 frames.], batch size: 26, lr: 5.16e-04
2022-05-04 17:55:59,091 INFO [train.py:715] (5/8) Epoch 3, batch 30850, loss[loss=0.2074, simple_loss=0.2501, pruned_loss=0.08239, over 4829.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2292, pruned_loss=0.04594, over 972071.62 frames.], batch size: 13, lr: 5.16e-04
2022-05-04 17:56:37,364 INFO [train.py:715] (5/8) Epoch 3, batch 30900, loss[loss=0.1841, simple_loss=0.251, pruned_loss=0.05861, over 4836.00 frames.], tot_loss[loss=0.1603, simple_loss=0.229, pruned_loss=0.04574, over 971279.61 frames.], batch size: 15, lr: 5.16e-04
2022-05-04 17:57:16,437 INFO [train.py:715] (5/8) Epoch 3, batch 30950, loss[loss=0.1686, simple_loss=0.232, pruned_loss=0.05258, over 4645.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2297, pruned_loss=0.04588, over 971453.15 frames.], batch size: 13, lr: 5.15e-04
2022-05-04 17:57:55,758 INFO [train.py:715] (5/8) Epoch 3, batch 31000, loss[loss=0.1634, simple_loss=0.2284, pruned_loss=0.04922, over 4785.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2302, pruned_loss=0.04573, over 971378.97 frames.], batch size: 14, lr: 5.15e-04
2022-05-04 17:58:35,032 INFO [train.py:715] (5/8) Epoch 3, batch 31050, loss[loss=0.1628, simple_loss=0.2355, pruned_loss=0.04504, over 4969.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2292, pruned_loss=0.04493, over 971434.66 frames.], batch size: 25, lr: 5.15e-04
2022-05-04 17:59:13,606 INFO [train.py:715] (5/8) Epoch 3, batch 31100, loss[loss=0.1567, simple_loss=0.2214, pruned_loss=0.04598, over 4863.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2292, pruned_loss=0.0452, over 971518.46 frames.], batch size: 13, lr: 5.15e-04
2022-05-04 17:59:53,183 INFO [train.py:715] (5/8) Epoch 3, batch 31150, loss[loss=0.1505, simple_loss=0.2124, pruned_loss=0.04427, over 4883.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2294, pruned_loss=0.0454, over 971744.42 frames.], batch size: 16, lr: 5.15e-04
2022-05-04 18:00:32,418 INFO [train.py:715] (5/8) Epoch 3, batch 31200, loss[loss=0.1824, simple_loss=0.2442, pruned_loss=0.06034, over 4829.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.0461, over 971686.20 frames.], batch size: 30, lr: 5.15e-04
2022-05-04 18:01:11,061 INFO [train.py:715] (5/8) Epoch 3, batch 31250, loss[loss=0.1698, simple_loss=0.2373, pruned_loss=0.05115, over 4841.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2306, pruned_loss=0.04647, over 972325.25 frames.], batch size: 15, lr: 5.15e-04
2022-05-04 18:01:50,133 INFO [train.py:715] (5/8) Epoch 3, batch 31300, loss[loss=0.147, simple_loss=0.2225, pruned_loss=0.03573, over 4791.00 frames.], tot_loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04607, over 972050.00 frames.], batch size: 21, lr: 5.15e-04
2022-05-04 18:02:29,482 INFO [train.py:715] (5/8) Epoch 3, batch 31350, loss[loss=0.1611, simple_loss=0.222, pruned_loss=0.0501, over 4801.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2291, pruned_loss=0.04568, over 972491.13 frames.], batch size: 24, lr: 5.15e-04
2022-05-04 18:03:08,645 INFO [train.py:715] (5/8) Epoch 3, batch 31400, loss[loss=0.1306, simple_loss=0.2066, pruned_loss=0.02733, over 4790.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2296, pruned_loss=0.04562, over 972279.23 frames.], batch size: 14, lr: 5.15e-04
2022-05-04 18:03:47,229 INFO [train.py:715] (5/8) Epoch 3, batch 31450, loss[loss=0.1485, simple_loss=0.2161, pruned_loss=0.04045, over 4886.00 frames.], tot_loss[loss=0.1596, simple_loss=0.229, pruned_loss=0.04515, over 972590.05 frames.], batch size: 19, lr: 5.15e-04
2022-05-04 18:04:26,974 INFO [train.py:715] (5/8) Epoch 3, batch 31500, loss[loss=0.1414, simple_loss=0.2177, pruned_loss=0.03254, over 4931.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2288, pruned_loss=0.04518, over 972414.35 frames.], batch size: 23, lr: 5.14e-04
2022-05-04 18:05:06,851 INFO [train.py:715] (5/8) Epoch 3, batch 31550, loss[loss=0.1879, simple_loss=0.2352, pruned_loss=0.07034, over 4851.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2294, pruned_loss=0.04554, over 972274.73 frames.], batch size: 32, lr: 5.14e-04
2022-05-04 18:05:47,988 INFO [train.py:715] (5/8) Epoch 3, batch 31600, loss[loss=0.1872, simple_loss=0.2606, pruned_loss=0.05688, over 4992.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2299, pruned_loss=0.04561, over 973379.52 frames.], batch size: 14, lr: 5.14e-04
2022-05-04 18:06:26,993 INFO [train.py:715] (5/8) Epoch 3, batch 31650, loss[loss=0.132, simple_loss=0.202, pruned_loss=0.03103, over 4799.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2292, pruned_loss=0.04547, over 973526.12 frames.], batch size: 24, lr: 5.14e-04
2022-05-04 18:07:07,176 INFO [train.py:715] (5/8) Epoch 3, batch 31700, loss[loss=0.1739, simple_loss=0.2464, pruned_loss=0.05071, over 4933.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2287, pruned_loss=0.04528, over 974088.29 frames.], batch size: 18, lr: 5.14e-04
2022-05-04 18:07:46,355 INFO [train.py:715] (5/8) Epoch 3, batch 31750, loss[loss=0.1673, simple_loss=0.2393, pruned_loss=0.04762, over 4772.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2282, pruned_loss=0.04505, over 973319.47 frames.], batch size: 18, lr: 5.14e-04
2022-05-04 18:08:24,500 INFO [train.py:715] (5/8) Epoch 3, batch 31800, loss[loss=0.1573, simple_loss=0.2271, pruned_loss=0.04377, over 4910.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04536, over 974214.97 frames.], batch size: 23, lr: 5.14e-04
2022-05-04 18:09:04,270 INFO [train.py:715] (5/8) Epoch 3, batch 31850, loss[loss=0.1351, simple_loss=0.1927, pruned_loss=0.0388, over 4914.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2285, pruned_loss=0.045, over 973986.07 frames.], batch size: 29, lr: 5.14e-04
2022-05-04 18:09:43,772 INFO [train.py:715] (5/8) Epoch 3, batch 31900, loss[loss=0.1426, simple_loss=0.2113, pruned_loss=0.03693, over 4844.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04508, over 974089.56 frames.], batch size: 20, lr: 5.14e-04
2022-05-04 18:10:22,482 INFO [train.py:715] (5/8) Epoch 3, batch 31950, loss[loss=0.1815, simple_loss=0.2433, pruned_loss=0.05987, over 4872.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2277, pruned_loss=0.04488, over 973499.16 frames.], batch size: 32, lr: 5.14e-04
2022-05-04 18:11:01,411 INFO [train.py:715] (5/8) Epoch 3, batch 32000, loss[loss=0.1611, simple_loss=0.2349, pruned_loss=0.04365, over 4824.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04474, over 972680.33 frames.], batch size: 15, lr: 5.14e-04
2022-05-04 18:11:41,009 INFO [train.py:715] (5/8) Epoch 3, batch 32050, loss[loss=0.1358, simple_loss=0.2253, pruned_loss=0.02313, over 4980.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2275, pruned_loss=0.04466, over 972581.12 frames.], batch size: 15, lr: 5.13e-04
2022-05-04 18:12:19,208 INFO [train.py:715] (5/8) Epoch 3, batch 32100, loss[loss=0.1444, simple_loss=0.2184, pruned_loss=0.03521, over 4802.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2278, pruned_loss=0.04496, over 972985.67 frames.], batch size: 25, lr: 5.13e-04
2022-05-04 18:12:58,310 INFO [train.py:715] (5/8) Epoch 3, batch 32150, loss[loss=0.1786, simple_loss=0.2486, pruned_loss=0.0543, over 4934.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.04503, over 972630.25 frames.], batch size: 29, lr: 5.13e-04
2022-05-04 18:13:37,851 INFO [train.py:715] (5/8) Epoch 3, batch 32200, loss[loss=0.2412, simple_loss=0.2936, pruned_loss=0.0944, over 4953.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2281, pruned_loss=0.04485, over 973063.42 frames.], batch size: 15, lr: 5.13e-04
2022-05-04 18:14:16,672 INFO [train.py:715] (5/8) Epoch 3, batch 32250, loss[loss=0.1929, simple_loss=0.2648, pruned_loss=0.06051, over 4940.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2294, pruned_loss=0.04562, over 973004.41 frames.], batch size: 23, lr: 5.13e-04
2022-05-04 18:14:55,236 INFO [train.py:715] (5/8) Epoch 3, batch 32300, loss[loss=0.1498, simple_loss=0.2195, pruned_loss=0.04003, over 4913.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2295, pruned_loss=0.04574, over 972186.82 frames.], batch size: 29, lr: 5.13e-04
2022-05-04 18:15:34,898 INFO [train.py:715] (5/8) Epoch 3, batch 32350, loss[loss=0.1627, simple_loss=0.2377, pruned_loss=0.0439, over 4774.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2293, pruned_loss=0.04566, over 972489.85 frames.], batch size: 17, lr: 5.13e-04
2022-05-04 18:16:14,617 INFO [train.py:715] (5/8) Epoch 3, batch 32400, loss[loss=0.1358, simple_loss=0.2183, pruned_loss=0.02667, over 4942.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2287, pruned_loss=0.04509, over 972179.71 frames.], batch size: 23, lr: 5.13e-04
2022-05-04 18:16:52,599 INFO [train.py:715] (5/8) Epoch 3, batch 32450, loss[loss=0.1467, simple_loss=0.2236, pruned_loss=0.03487, over 4814.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2294, pruned_loss=0.04587, over 972367.30 frames.], batch size: 27, lr: 5.13e-04
2022-05-04 18:17:32,077 INFO [train.py:715] (5/8) Epoch 3, batch 32500, loss[loss=0.1294, simple_loss=0.1938, pruned_loss=0.0325, over 4783.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2285, pruned_loss=0.04514, over 972168.20 frames.], batch size: 14, lr: 5.13e-04
2022-05-04 18:18:11,713 INFO [train.py:715] (5/8) Epoch 3, batch 32550, loss[loss=0.1467, simple_loss=0.2169, pruned_loss=0.0382, over 4960.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2272, pruned_loss=0.04446, over 971925.95 frames.], batch size: 24, lr: 5.12e-04
2022-05-04 18:18:50,229 INFO [train.py:715] (5/8) Epoch 3, batch 32600, loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.03895, over 4854.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04423, over 971528.22 frames.], batch size: 20, lr: 5.12e-04
2022-05-04 18:19:29,060 INFO [train.py:715] (5/8) Epoch 3, batch 32650, loss[loss=0.1416, simple_loss=0.2189, pruned_loss=0.03219, over 4813.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2274, pruned_loss=0.04501, over 972005.91 frames.], batch size: 13, lr: 5.12e-04
2022-05-04 18:20:08,686 INFO [train.py:715] (5/8) Epoch 3, batch 32700, loss[loss=0.1459, simple_loss=0.2189, pruned_loss=0.0365, over 4809.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2274, pruned_loss=0.04494, over 972187.54 frames.], batch size: 26, lr: 5.12e-04
2022-05-04 18:20:47,703 INFO [train.py:715] (5/8) Epoch 3, batch 32750, loss[loss=0.152, simple_loss=0.2245, pruned_loss=0.03978, over 4821.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2272, pruned_loss=0.04472, over 972327.95 frames.], batch size: 26, lr: 5.12e-04
2022-05-04 18:21:26,287 INFO [train.py:715] (5/8) Epoch 3, batch 32800, loss[loss=0.1561, simple_loss=0.2245, pruned_loss=0.04384, over 4792.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2273, pruned_loss=0.04463, over 972576.87 frames.], batch size: 14, lr: 5.12e-04
2022-05-04 18:22:05,407 INFO [train.py:715] (5/8) Epoch 3, batch 32850, loss[loss=0.1578, simple_loss=0.2271, pruned_loss=0.04432, over 4884.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2283, pruned_loss=0.0455, over 972119.79 frames.], batch size: 16, lr: 5.12e-04
2022-05-04 18:22:44,588 INFO [train.py:715] (5/8) Epoch 3, batch 32900, loss[loss=0.1301, simple_loss=0.2105, pruned_loss=0.02487, over 4776.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2275, pruned_loss=0.0449, over 972167.78 frames.], batch size: 17, lr: 5.12e-04
2022-05-04 18:23:23,655 INFO [train.py:715] (5/8) Epoch 3, batch 32950, loss[loss=0.1226, simple_loss=0.1964, pruned_loss=0.02439, over 4881.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04489, over 971878.63 frames.], batch size: 22, lr: 5.12e-04
2022-05-04 18:24:02,386 INFO [train.py:715] (5/8) Epoch 3, batch 33000, loss[loss=0.144, simple_loss=0.2107, pruned_loss=0.0387, over 4788.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2278, pruned_loss=0.04479, over 971403.86 frames.], batch size: 17, lr: 5.12e-04
2022-05-04 18:24:02,387 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 18:24:11,704 INFO [train.py:742] (5/8) Epoch 3, validation: loss=0.1131, simple_loss=0.199, pruned_loss=0.01363, over 914524.00 frames.
2022-05-04 18:24:50,800 INFO [train.py:715] (5/8) Epoch 3, batch 33050, loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03082, over 4689.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2282, pruned_loss=0.04563, over 972259.86 frames.], batch size: 15, lr: 5.12e-04
2022-05-04 18:25:30,710 INFO [train.py:715] (5/8) Epoch 3, batch 33100, loss[loss=0.1384, simple_loss=0.2129, pruned_loss=0.03199, over 4952.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2285, pruned_loss=0.04588, over 971961.81 frames.], batch size: 21, lr: 5.11e-04
2022-05-04 18:26:09,586 INFO [train.py:715] (5/8) Epoch 3, batch 33150, loss[loss=0.1552, simple_loss=0.2169, pruned_loss=0.0468, over 4950.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2287, pruned_loss=0.04597, over 972674.58 frames.], batch size: 21, lr: 5.11e-04
2022-05-04 18:26:48,262 INFO [train.py:715] (5/8) Epoch 3, batch 33200, loss[loss=0.1865, simple_loss=0.2591, pruned_loss=0.05696, over 4896.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2281, pruned_loss=0.04555, over 972276.15 frames.], batch size: 22, lr: 5.11e-04
2022-05-04 18:27:28,161 INFO [train.py:715] (5/8) Epoch 3, batch 33250, loss[loss=0.1541, simple_loss=0.2196, pruned_loss=0.04434, over 4779.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2291, pruned_loss=0.04604, over 972580.54 frames.], batch size: 14, lr: 5.11e-04
2022-05-04 18:28:07,720 INFO [train.py:715] (5/8) Epoch 3, batch 33300, loss[loss=0.1435, simple_loss=0.222, pruned_loss=0.03253, over 4812.00 frames.], tot_loss[loss=0.1602, simple_loss=0.229, pruned_loss=0.04569, over 972312.22 frames.], batch size: 12, lr: 5.11e-04
2022-05-04 18:28:46,235 INFO [train.py:715] (5/8) Epoch 3, batch 33350, loss[loss=0.1481, simple_loss=0.222, pruned_loss=0.03708, over 4739.00 frames.], tot_loss[loss=0.16, simple_loss=0.2288, pruned_loss=0.04564, over 973395.36 frames.], batch size: 16, lr: 5.11e-04
2022-05-04 18:29:25,535 INFO [train.py:715] (5/8) Epoch 3, batch 33400, loss[loss=0.1569, simple_loss=0.2271, pruned_loss=0.04337, over 4958.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2289, pruned_loss=0.04565, over 972867.53 frames.], batch size: 24, lr: 5.11e-04
2022-05-04 18:30:05,188 INFO [train.py:715] (5/8) Epoch 3, batch 33450, loss[loss=0.2057, simple_loss=0.2733, pruned_loss=0.069, over 4790.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2294, pruned_loss=0.04543, over 973171.25 frames.], batch size: 17, lr: 5.11e-04
2022-05-04 18:30:44,206 INFO [train.py:715] (5/8) Epoch 3, batch 33500, loss[loss=0.1711, simple_loss=0.2359, pruned_loss=0.0532, over 4839.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2291, pruned_loss=0.0452, over 972767.08 frames.], batch size: 15, lr: 5.11e-04
2022-05-04 18:31:23,293 INFO [train.py:715] (5/8) Epoch 3, batch 33550, loss[loss=0.1262, simple_loss=0.2004, pruned_loss=0.02604, over 4774.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2294, pruned_loss=0.04537, over 973571.10 frames.], batch size: 18, lr: 5.11e-04
2022-05-04 18:32:03,654 INFO [train.py:715] (5/8) Epoch 3, batch 33600, loss[loss=0.151, simple_loss=0.2246, pruned_loss=0.03867, over 4831.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2289, pruned_loss=0.04516, over 972967.64 frames.], batch size: 26, lr: 5.11e-04
2022-05-04 18:32:43,011 INFO [train.py:715] (5/8) Epoch 3, batch 33650, loss[loss=0.1857, simple_loss=0.2437, pruned_loss=0.06387, over 4744.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2287, pruned_loss=0.04523, over 973018.31 frames.], batch size: 16, lr: 5.10e-04
2022-05-04 18:33:21,657 INFO [train.py:715] (5/8) Epoch 3, batch 33700, loss[loss=0.1656, simple_loss=0.2378, pruned_loss=0.04671, over 4931.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2287, pruned_loss=0.04499, over 972664.89 frames.], batch size: 29, lr: 5.10e-04
2022-05-04 18:34:01,449 INFO [train.py:715] (5/8) Epoch 3, batch 33750, loss[loss=0.1661, simple_loss=0.2237, pruned_loss=0.05431, over 4973.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2285, pruned_loss=0.04469, over 972755.80 frames.], batch size: 35, lr: 5.10e-04
2022-05-04 18:34:40,931 INFO [train.py:715] (5/8) Epoch 3, batch 33800, loss[loss=0.2384, simple_loss=0.3004, pruned_loss=0.08821, over 4811.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2297, pruned_loss=0.04559, over 972279.72 frames.], batch size: 26, lr: 5.10e-04
2022-05-04 18:35:19,311 INFO [train.py:715] (5/8) Epoch 3, batch 33850, loss[loss=0.1848, simple_loss=0.2621, pruned_loss=0.0538, over 4650.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2301, pruned_loss=0.04588, over 972123.36 frames.], batch size: 13, lr: 5.10e-04
2022-05-04 18:35:58,140 INFO [train.py:715] (5/8) Epoch 3, batch 33900, loss[loss=0.1677, simple_loss=0.242, pruned_loss=0.04666, over 4740.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04586, over 971450.60 frames.], batch size: 16, lr: 5.10e-04
2022-05-04 18:36:38,298 INFO [train.py:715] (5/8) Epoch 3, batch 33950, loss[loss=0.1492, simple_loss=0.2217, pruned_loss=0.0384, over 4707.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2295, pruned_loss=0.04577, over 971736.85 frames.], batch size: 15, lr: 5.10e-04
2022-05-04 18:37:17,237 INFO [train.py:715] (5/8) Epoch 3, batch 34000, loss[loss=0.138, simple_loss=0.2136, pruned_loss=0.03115, over 4845.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2288, pruned_loss=0.04538, over 971862.59 frames.], batch size: 13, lr: 5.10e-04
2022-05-04 18:37:55,980 INFO [train.py:715] (5/8) Epoch 3, batch 34050, loss[loss=0.1731, simple_loss=0.2355, pruned_loss=0.05536, over 4984.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2287, pruned_loss=0.04493, over 971689.99 frames.], batch size: 39, lr: 5.10e-04
2022-05-04 18:38:35,310 INFO [train.py:715] (5/8) Epoch 3, batch 34100, loss[loss=0.1581, simple_loss=0.2425, pruned_loss=0.03687, over 4898.00 frames.], tot_loss[loss=0.16, simple_loss=0.2294, pruned_loss=0.04532, over 971475.03 frames.], batch size: 22, lr: 5.10e-04
2022-05-04 18:39:15,278 INFO [train.py:715] (5/8) Epoch 3, batch 34150, loss[loss=0.1534, simple_loss=0.217, pruned_loss=0.04485, over 4826.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2289, pruned_loss=0.04489, over 971702.66 frames.], batch size: 15, lr: 5.10e-04
2022-05-04 18:39:53,555 INFO [train.py:715] (5/8) Epoch 3, batch 34200, loss[loss=0.1285, simple_loss=0.2069, pruned_loss=0.025, over 4963.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2289, pruned_loss=0.04512, over 971764.66 frames.], batch size: 24, lr: 5.09e-04
2022-05-04 18:40:33,001 INFO [train.py:715] (5/8) Epoch 3, batch 34250, loss[loss=0.1369, simple_loss=0.2046, pruned_loss=0.03462, over 4837.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2292, pruned_loss=0.0456, over 972221.23 frames.], batch size: 15, lr: 5.09e-04
2022-05-04 18:41:13,063 INFO [train.py:715] (5/8) Epoch 3, batch 34300, loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03789, over 4954.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2289, pruned_loss=0.04591, over 971713.91 frames.], batch size: 15, lr: 5.09e-04
2022-05-04 18:41:52,488 INFO [train.py:715] (5/8) Epoch 3, batch 34350, loss[loss=0.1262, simple_loss=0.2043, pruned_loss=0.02407, over 4811.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2282, pruned_loss=0.04529, over 971114.70 frames.], batch size: 27, lr: 5.09e-04
2022-05-04 18:42:31,601 INFO [train.py:715] (5/8) Epoch 3, batch 34400, loss[loss=0.179, simple_loss=0.2551, pruned_loss=0.05146, over 4837.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2292, pruned_loss=0.04623, over 970845.02 frames.], batch size: 15, lr: 5.09e-04
2022-05-04 18:43:11,181 INFO [train.py:715] (5/8) Epoch 3, batch 34450, loss[loss=0.1841, simple_loss=0.2538, pruned_loss=0.05721, over 4921.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2299, pruned_loss=0.0462, over 971261.21 frames.], batch size: 39, lr: 5.09e-04
2022-05-04 18:43:51,338 INFO [train.py:715] (5/8) Epoch 3, batch 34500, loss[loss=0.148, simple_loss=0.2308, pruned_loss=0.03257, over 4958.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2297, pruned_loss=0.04575, over 971364.90 frames.], batch size: 39, lr: 5.09e-04
2022-05-04 18:44:29,764 INFO [train.py:715] (5/8) Epoch 3, batch 34550, loss[loss=0.1502, simple_loss=0.2313, pruned_loss=0.03455, over 4883.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04606, over 970930.92 frames.], batch size: 22, lr: 5.09e-04
2022-05-04 18:45:08,814 INFO [train.py:715] (5/8) Epoch 3, batch 34600, loss[loss=0.1225, simple_loss=0.2008, pruned_loss=0.02209, over 4770.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2285, pruned_loss=0.04536, over 971548.25 frames.], batch size: 14, lr: 5.09e-04
2022-05-04 18:45:49,189 INFO [train.py:715] (5/8) Epoch 3, batch 34650, loss[loss=0.1148, simple_loss=0.1877, pruned_loss=0.02099, over 4790.00 frames.], tot_loss[loss=0.1605, simple_loss=0.229, pruned_loss=0.04595, over 971133.13 frames.], batch size: 12, lr: 5.09e-04
2022-05-04 18:46:28,774 INFO [train.py:715] (5/8) Epoch 3, batch 34700, loss[loss=0.165, simple_loss=0.2434, pruned_loss=0.04328, over 4825.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2295, pruned_loss=0.04597, over 972006.74 frames.], batch size: 15, lr: 5.09e-04
2022-05-04 18:47:07,058 INFO [train.py:715] (5/8) Epoch 3, batch 34750, loss[loss=0.171, simple_loss=0.2428, pruned_loss=0.04963, over 4932.00 frames.], tot_loss[loss=0.161, simple_loss=0.2296, pruned_loss=0.04621, over 971521.84 frames.], batch size: 23, lr: 5.08e-04
2022-05-04 18:47:44,751 INFO [train.py:715] (5/8) Epoch 3, batch 34800, loss[loss=0.1275, simple_loss=0.1988, pruned_loss=0.02816, over 4854.00 frames.], tot_loss[loss=0.159, simple_loss=0.2276, pruned_loss=0.04522, over 971195.92 frames.], batch size: 12, lr: 5.08e-04
2022-05-04 18:48:35,137 INFO [train.py:715] (5/8) Epoch 4, batch 0, loss[loss=0.1774, simple_loss=0.2524, pruned_loss=0.05124, over 4761.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2524, pruned_loss=0.05124, over 4761.00 frames.], batch size: 19, lr: 4.78e-04
2022-05-04 18:49:16,503 INFO [train.py:715] (5/8) Epoch 4, batch 50, loss[loss=0.146, simple_loss=0.225, pruned_loss=0.03349, over 4977.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2282, pruned_loss=0.0443, over 219998.45 frames.], batch size: 15, lr: 4.78e-04
2022-05-04 18:49:57,160 INFO [train.py:715] (5/8) Epoch 4, batch 100, loss[loss=0.1593, simple_loss=0.2349, pruned_loss=0.04188, over 4762.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2278, pruned_loss=0.0442, over 387676.62 frames.], batch size: 19, lr: 4.78e-04
2022-05-04 18:50:37,983 INFO [train.py:715] (5/8) Epoch 4, batch 150, loss[loss=0.136, simple_loss=0.2154, pruned_loss=0.02832, over 4814.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2289, pruned_loss=0.04499, over 517545.50 frames.], batch size: 12, lr: 4.78e-04
2022-05-04 18:51:19,048 INFO [train.py:715] (5/8) Epoch 4, batch 200, loss[loss=0.1555, simple_loss=0.2272, pruned_loss=0.04183, over 4885.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2297, pruned_loss=0.04501, over 618299.80 frames.], batch size: 16, lr: 4.78e-04
2022-05-04 18:52:00,238 INFO [train.py:715] (5/8) Epoch 4, batch 250, loss[loss=0.1479, simple_loss=0.2116, pruned_loss=0.0421, over 4927.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2301, pruned_loss=0.0464, over 696168.70 frames.], batch size: 23, lr: 4.77e-04
2022-05-04 18:52:41,177 INFO [train.py:715] (5/8) Epoch 4, batch 300, loss[loss=0.1581, simple_loss=0.2389, pruned_loss=0.03864, over 4703.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2289, pruned_loss=0.046, over 756569.65 frames.], batch size: 15, lr: 4.77e-04
2022-05-04 18:53:22,427 INFO [train.py:715] (5/8) Epoch 4, batch 350, loss[loss=0.1753, simple_loss=0.2511, pruned_loss=0.04977, over 4818.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2288, pruned_loss=0.0454, over 804598.22 frames.], batch size: 12, lr: 4.77e-04
2022-05-04 18:54:04,551 INFO [train.py:715] (5/8) Epoch 4, batch 400, loss[loss=0.1816, simple_loss=0.2433, pruned_loss=0.05994, over 4950.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04603, over 842356.05 frames.], batch size: 15, lr: 4.77e-04
2022-05-04 18:54:45,179 INFO [train.py:715] (5/8) Epoch 4, batch 450, loss[loss=0.1249, simple_loss=0.2023, pruned_loss=0.02372, over 4986.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2294, pruned_loss=0.04544, over 871388.36 frames.], batch size: 25, lr: 4.77e-04
2022-05-04 18:55:26,264 INFO [train.py:715] (5/8) Epoch 4, batch 500, loss[loss=0.1647, simple_loss=0.229, pruned_loss=0.05022, over 4651.00 frames.], tot_loss[loss=0.16, simple_loss=0.2293, pruned_loss=0.04536, over 894235.56 frames.], batch size: 13, lr: 4.77e-04
2022-05-04 18:56:07,507 INFO [train.py:715] (5/8) Epoch 4, batch 550, loss[loss=0.1545, simple_loss=0.222, pruned_loss=0.04348, over 4899.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2301, pruned_loss=0.04548, over 911337.27 frames.], batch size: 18, lr: 4.77e-04
2022-05-04 18:56:48,415 INFO [train.py:715] (5/8) Epoch 4, batch 600, loss[loss=0.1354, simple_loss=0.2179, pruned_loss=0.0264, over 4898.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2298, pruned_loss=0.04573, over 925591.40 frames.], batch size: 19, lr: 4.77e-04
2022-05-04 18:57:28,919 INFO [train.py:715] (5/8) Epoch 4, batch 650, loss[loss=0.1456, simple_loss=0.2109, pruned_loss=0.04017, over 4953.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2291, pruned_loss=0.04563, over 935124.84 frames.], batch size: 29, lr: 4.77e-04
2022-05-04 18:58:09,999 INFO [train.py:715] (5/8) Epoch 4, batch 700, loss[loss=0.1971, simple_loss=0.2665, pruned_loss=0.0639, over 4859.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2284, pruned_loss=0.04534, over 944048.73 frames.], batch size: 20, lr: 4.77e-04
2022-05-04 18:58:51,942 INFO [train.py:715] (5/8) Epoch 4, batch 750, loss[loss=0.1532, simple_loss=0.2101, pruned_loss=0.04817, over 4832.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2288, pruned_loss=0.04565, over 950299.84 frames.], batch size: 13, lr: 4.77e-04
2022-05-04 18:59:33,008 INFO [train.py:715] (5/8) Epoch 4, batch 800, loss[loss=0.179, simple_loss=0.2645, pruned_loss=0.04677, over 4984.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2286, pruned_loss=0.04544, over 955525.89 frames.], batch size: 28, lr: 4.77e-04
2022-05-04 19:00:13,435 INFO [train.py:715] (5/8) Epoch 4, batch 850, loss[loss=0.1907, simple_loss=0.2608, pruned_loss=0.0603, over 4885.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2278, pruned_loss=0.04522, over 958762.94 frames.], batch size: 16, lr: 4.76e-04
2022-05-04 19:00:54,504 INFO [train.py:715] (5/8) Epoch 4, batch 900, loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04004, over 4984.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2279, pruned_loss=0.04499, over 962091.13 frames.], batch size: 28, lr: 4.76e-04
2022-05-04 19:01:35,346 INFO [train.py:715] (5/8) Epoch 4, batch 950, loss[loss=0.1781, simple_loss=0.2367, pruned_loss=0.05974, over 4934.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04492, over 964291.33 frames.], batch size: 39, lr: 4.76e-04
2022-05-04 19:02:16,230 INFO [train.py:715] (5/8) Epoch 4, batch 1000, loss[loss=0.1447, simple_loss=0.2219, pruned_loss=0.03376, over 4812.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2282, pruned_loss=0.04499, over 966231.30 frames.], batch size: 21, lr: 4.76e-04
2022-05-04 19:02:56,937 INFO [train.py:715] (5/8) Epoch 4, batch 1050, loss[loss=0.165, simple_loss=0.2349, pruned_loss=0.04753, over 4942.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2287, pruned_loss=0.04513, over 967657.31 frames.], batch size: 23, lr: 4.76e-04
2022-05-04 19:03:38,129 INFO [train.py:715] (5/8) Epoch 4, batch 1100, loss[loss=0.1451, simple_loss=0.2189, pruned_loss=0.03564, over 4890.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2288, pruned_loss=0.04501, over 968453.04 frames.], batch size: 22, lr: 4.76e-04
2022-05-04 19:04:18,529 INFO [train.py:715] (5/8) Epoch 4, batch 1150, loss[loss=0.1525, simple_loss=0.2179, pruned_loss=0.04355, over 4840.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2295, pruned_loss=0.04571, over 968935.19 frames.], batch size: 30, lr: 4.76e-04
2022-05-04 19:04:58,025 INFO [train.py:715] (5/8) Epoch 4, batch 1200, loss[loss=0.158, simple_loss=0.2196, pruned_loss=0.04824, over 4864.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2299, pruned_loss=0.04597, over 970006.67 frames.], batch size: 20, lr: 4.76e-04
2022-05-04 19:05:38,581 INFO [train.py:715] (5/8) Epoch 4, batch 1250, loss[loss=0.1954, simple_loss=0.2694, pruned_loss=0.06065, over 4950.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2291, pruned_loss=0.04562, over 971020.01 frames.], batch size: 35, lr: 4.76e-04
2022-05-04 19:06:19,652 INFO [train.py:715] (5/8) Epoch 4, batch 1300, loss[loss=0.1969, simple_loss=0.2785, pruned_loss=0.05761, over 4896.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2292, pruned_loss=0.04589, over 971145.11 frames.], batch size: 19, lr: 4.76e-04
2022-05-04 19:06:59,658 INFO [train.py:715] (5/8) Epoch 4, batch 1350, loss[loss=0.1761, simple_loss=0.2553, pruned_loss=0.04846, over 4974.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04532, over 972000.71 frames.], batch size: 40, lr: 4.76e-04
2022-05-04 19:07:40,377 INFO [train.py:715] (5/8) Epoch 4, batch 1400, loss[loss=0.158, simple_loss=0.2243, pruned_loss=0.04584, over 4950.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2288, pruned_loss=0.04517, over 972709.51 frames.], batch size: 35, lr: 4.76e-04
2022-05-04 19:08:21,351 INFO [train.py:715] (5/8) Epoch 4, batch 1450, loss[loss=0.186, simple_loss=0.2522, pruned_loss=0.05989, over 4970.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2287, pruned_loss=0.04545, over 972042.64 frames.], batch size: 15, lr: 4.75e-04
2022-05-04 19:09:02,419 INFO [train.py:715] (5/8) Epoch 4, batch 1500, loss[loss=0.1756, simple_loss=0.2426, pruned_loss=0.05433, over 4767.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2283, pruned_loss=0.04516, over 972571.24 frames.], batch size: 14, lr: 4.75e-04
2022-05-04 19:09:42,045 INFO [train.py:715] (5/8) Epoch 4, batch 1550, loss[loss=0.2035, simple_loss=0.2561, pruned_loss=0.07546, over 4770.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2285, pruned_loss=0.04493, over 971816.25 frames.], batch size: 18, lr: 4.75e-04
2022-05-04 19:10:23,009 INFO [train.py:715] (5/8) Epoch 4, batch 1600, loss[loss=0.1849, simple_loss=0.2401, pruned_loss=0.06489, over 4788.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2279, pruned_loss=0.04457, over 971408.84 frames.], batch size: 17, lr: 4.75e-04
2022-05-04 19:11:04,736 INFO [train.py:715] (5/8) Epoch 4, batch 1650, loss[loss=0.1357, simple_loss=0.2009, pruned_loss=0.03527, over 4808.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2275, pruned_loss=0.04474, over 971394.97 frames.], batch size: 12, lr: 4.75e-04
2022-05-04 19:11:45,100 INFO [train.py:715] (5/8) Epoch 4, batch 1700, loss[loss=0.15, simple_loss=0.2175, pruned_loss=0.04123, over 4790.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04472, over 972034.75 frames.], batch size: 14, lr: 4.75e-04
2022-05-04 19:12:25,111 INFO [train.py:715] (5/8) Epoch 4, batch 1750, loss[loss=0.1663, simple_loss=0.218, pruned_loss=0.05729, over 4899.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2273, pruned_loss=0.04448, over 972730.65 frames.], batch size: 17, lr: 4.75e-04
2022-05-04 19:13:06,314 INFO [train.py:715] (5/8) Epoch 4, batch 1800, loss[loss=0.1308, simple_loss=0.1966, pruned_loss=0.03255, over 4798.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04532, over 973111.52 frames.], batch size: 21, lr: 4.75e-04
2022-05-04 19:13:47,662 INFO [train.py:715] (5/8) Epoch 4, batch 1850, loss[loss=0.1681, simple_loss=0.2279, pruned_loss=0.05417, over 4894.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2279, pruned_loss=0.04535, over 972319.37 frames.], batch size: 18, lr: 4.75e-04
2022-05-04 19:14:27,700 INFO [train.py:715] (5/8) Epoch 4, batch 1900, loss[loss=0.1709, simple_loss=0.2426, pruned_loss=0.04957, over 4881.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2263, pruned_loss=0.04475, over 972521.03 frames.], batch size: 16, lr: 4.75e-04
2022-05-04 19:15:08,449 INFO [train.py:715] (5/8) Epoch 4, batch 1950, loss[loss=0.1282, simple_loss=0.2016, pruned_loss=0.02737, over 4892.00 frames.], tot_loss[loss=0.1573, simple_loss=0.226, pruned_loss=0.04434, over 972232.53 frames.], batch size: 17, lr: 4.75e-04
2022-05-04 19:15:48,966 INFO [train.py:715] (5/8) Epoch 4, batch 2000, loss[loss=0.1436, simple_loss=0.2121, pruned_loss=0.03749, over 4870.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2265, pruned_loss=0.04405, over 972782.52 frames.], batch size: 22, lr: 4.74e-04
2022-05-04 19:16:28,964 INFO [train.py:715] (5/8) Epoch 4, batch 2050, loss[loss=0.156, simple_loss=0.2159, pruned_loss=0.04803, over 4870.00 frames.], tot_loss[loss=0.1578, simple_loss=0.227, pruned_loss=0.04429, over 973039.77 frames.], batch size: 30, lr: 4.74e-04
2022-05-04 19:17:08,513 INFO [train.py:715] (5/8) Epoch 4, batch 2100, loss[loss=0.1534, simple_loss=0.2161, pruned_loss=0.04538, over 4834.00 frames.], tot_loss[loss=0.159, simple_loss=0.2281, pruned_loss=0.04499, over 972927.83 frames.], batch size: 32, lr: 4.74e-04
2022-05-04 19:17:48,264 INFO [train.py:715] (5/8) Epoch 4, batch 2150, loss[loss=0.171, simple_loss=0.2366, pruned_loss=0.05274, over 4866.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2278, pruned_loss=0.04482, over 973160.86 frames.], batch size: 38, lr: 4.74e-04
2022-05-04 19:18:29,065 INFO [train.py:715] (5/8) Epoch 4, batch 2200, loss[loss=0.155, simple_loss=0.2254, pruned_loss=0.04228, over 4754.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2285, pruned_loss=0.04486, over 973511.73 frames.], batch size: 16, lr: 4.74e-04
2022-05-04 19:19:09,439 INFO [train.py:715] (5/8) Epoch 4, batch 2250, loss[loss=0.1821, simple_loss=0.2431, pruned_loss=0.0606, over 4871.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2281, pruned_loss=0.04429, over 973945.18 frames.], batch size: 32, lr: 4.74e-04
2022-05-04 19:19:48,814 INFO [train.py:715] (5/8) Epoch 4, batch 2300, loss[loss=0.1801, simple_loss=0.2498, pruned_loss=0.05516, over 4779.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2274, pruned_loss=0.04402, over 973829.97 frames.], batch size: 17, lr: 4.74e-04
2022-05-04 19:20:28,744 INFO [train.py:715] (5/8) Epoch 4, batch 2350, loss[loss=0.1469, simple_loss=0.2134, pruned_loss=0.04018, over 4775.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04372, over 972675.17 frames.], batch size: 14, lr: 4.74e-04
2022-05-04 19:21:08,831 INFO [train.py:715] (5/8) Epoch 4, batch 2400, loss[loss=0.1305, simple_loss=0.2076, pruned_loss=0.02666, over 4825.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2259, pruned_loss=0.04397, over 972121.65 frames.], batch size: 15, lr: 4.74e-04
2022-05-04 19:21:48,322 INFO [train.py:715] (5/8) Epoch 4, batch 2450, loss[loss=0.1199, simple_loss=0.1897, pruned_loss=0.02509, over 4837.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2261, pruned_loss=0.0441, over 971585.07 frames.], batch size: 30, lr: 4.74e-04
2022-05-04 19:22:28,657 INFO [train.py:715] (5/8) Epoch 4, batch 2500, loss[loss=0.196, simple_loss=0.2773, pruned_loss=0.0574, over 4944.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04345, over 972150.60 frames.], batch size: 21, lr: 4.74e-04
2022-05-04 19:23:09,573 INFO [train.py:715] (5/8) Epoch 4, batch 2550, loss[loss=0.1774, simple_loss=0.2562, pruned_loss=0.0493, over 4856.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04362, over 973154.58 frames.], batch size: 20, lr: 4.74e-04
2022-05-04 19:23:49,881 INFO [train.py:715] (5/8) Epoch 4, batch 2600, loss[loss=0.207, simple_loss=0.2407, pruned_loss=0.08669, over 4902.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04402, over 973708.77 frames.], batch size: 17, lr: 4.73e-04
2022-05-04 19:24:29,133 INFO [train.py:715] (5/8) Epoch 4, batch 2650, loss[loss=0.1383, simple_loss=0.2082, pruned_loss=0.03419, over 4839.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2278, pruned_loss=0.04438, over 973472.63 frames.], batch size: 12, lr: 4.73e-04
2022-05-04 19:25:09,497 INFO [train.py:715] (5/8) Epoch 4, batch 2700, loss[loss=0.1622, simple_loss=0.2304, pruned_loss=0.047, over 4814.00 frames.], tot_loss[loss=0.158, simple_loss=0.2277, pruned_loss=0.04411, over 972588.10 frames.], batch size: 26, lr: 4.73e-04
2022-05-04 19:25:49,761 INFO [train.py:715] (5/8) Epoch 4, batch 2750, loss[loss=0.1774, simple_loss=0.2471, pruned_loss=0.05389, over 4886.00 frames.], tot_loss[loss=0.1573, simple_loss=0.227, pruned_loss=0.04378, over 973124.74 frames.], batch size: 39, lr: 4.73e-04
2022-05-04 19:26:29,538 INFO [train.py:715] (5/8) Epoch 4, batch 2800, loss[loss=0.1809, simple_loss=0.2498, pruned_loss=0.05593, over 4955.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2272, pruned_loss=0.04405, over 973729.98 frames.], batch size: 24, lr: 4.73e-04
2022-05-04 19:27:08,931 INFO [train.py:715] (5/8) Epoch 4, batch 2850, loss[loss=0.1297, simple_loss=0.1997, pruned_loss=0.02988, over 4926.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04359, over 972757.91 frames.], batch size: 23, lr: 4.73e-04
2022-05-04 19:27:49,243 INFO [train.py:715] (5/8) Epoch 4, batch 2900, loss[loss=0.1645, simple_loss=0.2366, pruned_loss=0.04617, over 4860.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04395, over 972835.68 frames.], batch size: 20, lr: 4.73e-04
2022-05-04 19:28:29,131 INFO [train.py:715] (5/8) Epoch 4, batch 2950, loss[loss=0.1474, simple_loss=0.2149, pruned_loss=0.03998, over 4856.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2274, pruned_loss=0.04436, over 972911.74 frames.], batch size: 13, lr: 4.73e-04
2022-05-04 19:29:08,446 INFO [train.py:715] (5/8) Epoch 4, batch 3000, loss[loss=0.1555, simple_loss=0.2273, pruned_loss=0.04185, over 4845.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.0446, over 974194.30 frames.], batch size: 30, lr: 4.73e-04
2022-05-04 19:29:08,447 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 19:29:17,943 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1127, simple_loss=0.1984, pruned_loss=0.01346, over 914524.00 frames.
2022-05-04 19:29:57,092 INFO [train.py:715] (5/8) Epoch 4, batch 3050, loss[loss=0.1508, simple_loss=0.224, pruned_loss=0.03881, over 4911.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2281, pruned_loss=0.04453, over 974121.06 frames.], batch size: 18, lr: 4.73e-04
2022-05-04 19:30:37,132 INFO [train.py:715] (5/8) Epoch 4, batch 3100, loss[loss=0.1544, simple_loss=0.2206, pruned_loss=0.04411, over 4962.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.04388, over 974335.29 frames.], batch size: 35, lr: 4.73e-04
2022-05-04 19:31:17,410 INFO [train.py:715] (5/8) Epoch 4, batch 3150, loss[loss=0.1712, simple_loss=0.232, pruned_loss=0.05517, over 4966.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04378, over 974225.91 frames.], batch size: 15, lr: 4.73e-04
2022-05-04 19:31:57,022 INFO [train.py:715] (5/8) Epoch 4, batch 3200, loss[loss=0.164, simple_loss=0.2317, pruned_loss=0.04817, over 4858.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2283, pruned_loss=0.04425, over 973120.73 frames.], batch size: 39, lr: 4.72e-04
2022-05-04 19:32:36,972 INFO [train.py:715] (5/8) Epoch 4, batch 3250, loss[loss=0.1765, simple_loss=0.2423, pruned_loss=0.05532, over 4894.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2283, pruned_loss=0.04455, over 973392.72 frames.], batch size: 22, lr: 4.72e-04
2022-05-04 19:33:16,910 INFO [train.py:715] (5/8) Epoch 4, batch 3300, loss[loss=0.1559, simple_loss=0.2237, pruned_loss=0.044, over 4777.00 frames.], tot_loss[loss=0.1595, simple_loss=0.229, pruned_loss=0.04501, over 974391.97 frames.], batch size: 14, lr: 4.72e-04
2022-05-04 19:33:56,288 INFO [train.py:715] (5/8) Epoch 4, batch 3350, loss[loss=0.1539, simple_loss=0.2221, pruned_loss=0.04286, over 4962.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.04508, over 974166.34 frames.], batch size: 24, lr: 4.72e-04
2022-05-04 19:34:35,328 INFO [train.py:715] (5/8) Epoch 4, batch 3400, loss[loss=0.1492, simple_loss=0.2165, pruned_loss=0.04095, over 4778.00 frames.], tot_loss[loss=0.1594, simple_loss=0.228, pruned_loss=0.04544, over 973726.47 frames.], batch size: 17, lr: 4.72e-04
2022-05-04 19:35:15,774 INFO [train.py:715] (5/8) Epoch 4, batch 3450, loss[loss=0.1781, simple_loss=0.2447, pruned_loss=0.05576, over 4776.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.04454, over 973086.85 frames.], batch size: 18, lr: 4.72e-04
2022-05-04 19:35:55,187 INFO [train.py:715] (5/8) Epoch 4, batch 3500, loss[loss=0.1669, simple_loss=0.2331, pruned_loss=0.0504, over 4983.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2282, pruned_loss=0.04514, over 973508.35 frames.], batch size: 24, lr: 4.72e-04
2022-05-04 19:36:34,856 INFO [train.py:715] (5/8) Epoch 4, batch 3550, loss[loss=0.1869, simple_loss=0.2568, pruned_loss=0.05847, over 4757.00 frames.], tot_loss[loss=0.16, simple_loss=0.2286, pruned_loss=0.04573, over 972178.16 frames.], batch size: 14, lr: 4.72e-04
2022-05-04 19:37:14,695 INFO [train.py:715] (5/8) Epoch 4, batch 3600, loss[loss=0.1338, simple_loss=0.2068, pruned_loss=0.03045, over 4767.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2285, pruned_loss=0.04559, over 971717.84 frames.], batch size: 12, lr: 4.72e-04
2022-05-04 19:37:54,696 INFO [train.py:715] (5/8) Epoch 4, batch 3650, loss[loss=0.1627, simple_loss=0.2268, pruned_loss=0.04932, over 4860.00 frames.], tot_loss[loss=0.16, simple_loss=0.2287, pruned_loss=0.04566, over 972054.97 frames.], batch size: 20, lr: 4.72e-04
2022-05-04 19:38:34,067 INFO [train.py:715] (5/8) Epoch 4, batch 3700, loss[loss=0.1888, simple_loss=0.2479, pruned_loss=0.06489, over 4932.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2294, pruned_loss=0.04574, over 972215.32 frames.], batch size: 39, lr: 4.72e-04
2022-05-04 19:39:13,347 INFO [train.py:715] (5/8) Epoch 4, batch 3750, loss[loss=0.153, simple_loss=0.2268, pruned_loss=0.03956, over 4889.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2286, pruned_loss=0.04527, over 972254.01 frames.], batch size: 22, lr: 4.72e-04
2022-05-04 19:39:53,215 INFO [train.py:715] (5/8) Epoch 4, batch 3800, loss[loss=0.1437, simple_loss=0.2231, pruned_loss=0.03219, over 4830.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2284, pruned_loss=0.04516, over 971098.07 frames.], batch size: 26, lr: 4.72e-04
2022-05-04 19:40:32,931 INFO [train.py:715] (5/8) Epoch 4, batch 3850, loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.03264, over 4786.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2277, pruned_loss=0.04492, over 970379.75 frames.], batch size: 18, lr: 4.71e-04
2022-05-04 19:41:13,116 INFO [train.py:715] (5/8) Epoch 4, batch 3900, loss[loss=0.159, simple_loss=0.225, pruned_loss=0.04654, over 4867.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2263, pruned_loss=0.04401, over 970766.65 frames.], batch size: 39, lr: 4.71e-04
2022-05-04 19:41:53,255 INFO [train.py:715] (5/8) Epoch 4, batch 3950, loss[loss=0.1381, simple_loss=0.2194, pruned_loss=0.02839, over 4968.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04416, over 970587.95 frames.], batch size: 28, lr: 4.71e-04
2022-05-04 19:42:33,629 INFO [train.py:715] (5/8) Epoch 4, batch 4000, loss[loss=0.1414, simple_loss=0.217, pruned_loss=0.03291, over 4781.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04399, over 970771.82 frames.], batch size: 21, lr: 4.71e-04
2022-05-04 19:43:13,662 INFO [train.py:715] (5/8) Epoch 4, batch 4050, loss[loss=0.162, simple_loss=0.2246, pruned_loss=0.04974, over 4779.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2271, pruned_loss=0.04436, over 970292.43 frames.], batch size: 18, lr: 4.71e-04
2022-05-04 19:43:53,238 INFO [train.py:715] (5/8) Epoch 4, batch 4100, loss[loss=0.181, simple_loss=0.2363, pruned_loss=0.06292, over 4945.00 frames.], tot_loss[loss=0.1577, simple_loss=0.227, pruned_loss=0.04415, over 971010.87 frames.], batch size: 15, lr: 4.71e-04
2022-05-04 19:44:33,946 INFO [train.py:715] (5/8) Epoch 4, batch 4150, loss[loss=0.1446, simple_loss=0.2246, pruned_loss=0.03229, over 4803.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2276, pruned_loss=0.0447, over 971972.40 frames.], batch size: 25, lr: 4.71e-04
2022-05-04 19:45:13,436 INFO [train.py:715] (5/8) Epoch 4, batch 4200, loss[loss=0.1715, simple_loss=0.2377, pruned_loss=0.05268, over 4978.00 frames.], tot_loss[loss=0.158, simple_loss=0.2274, pruned_loss=0.0443, over 972050.30 frames.], batch size: 15, lr: 4.71e-04
2022-05-04 19:45:52,906 INFO [train.py:715] (5/8) Epoch 4, batch 4250, loss[loss=0.1522, simple_loss=0.2224, pruned_loss=0.04101, over 4797.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2275, pruned_loss=0.04388, over 971903.04 frames.], batch size: 17, lr: 4.71e-04
2022-05-04 19:46:33,010 INFO [train.py:715] (5/8) Epoch 4, batch 4300, loss[loss=0.1861, simple_loss=0.2488, pruned_loss=0.0617, over 4814.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2275, pruned_loss=0.0439, over 970989.65 frames.], batch size: 26, lr: 4.71e-04
2022-05-04 19:47:13,032 INFO [train.py:715] (5/8) Epoch 4, batch 4350, loss[loss=0.1595, simple_loss=0.2446, pruned_loss=0.03717, over 4733.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2279, pruned_loss=0.04387, over 971152.77 frames.], batch size: 16, lr: 4.71e-04
2022-05-04 19:47:52,118 INFO [train.py:715] (5/8) Epoch 4, batch 4400, loss[loss=0.1532, simple_loss=0.2193, pruned_loss=0.0435, over 4834.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2282, pruned_loss=0.0442, over 971528.61 frames.], batch size: 15, lr: 4.71e-04
2022-05-04 19:48:31,826 INFO [train.py:715] (5/8) Epoch 4, batch 4450, loss[loss=0.1445, simple_loss=0.2115, pruned_loss=0.03874, over 4851.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04378, over 971397.79 frames.], batch size: 32, lr: 4.70e-04
2022-05-04 19:49:11,999 INFO [train.py:715] (5/8) Epoch 4, batch 4500, loss[loss=0.1673, simple_loss=0.2322, pruned_loss=0.05124, over 4929.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2276, pruned_loss=0.0441, over 971251.11 frames.], batch size: 29, lr: 4.70e-04
2022-05-04 19:49:51,273 INFO [train.py:715] (5/8) Epoch 4, batch 4550, loss[loss=0.1713, simple_loss=0.232, pruned_loss=0.05534, over 4888.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2278, pruned_loss=0.04415, over 971556.94 frames.], batch size: 19, lr: 4.70e-04
2022-05-04 19:50:30,673 INFO [train.py:715] (5/8) Epoch 4, batch 4600, loss[loss=0.1291, simple_loss=0.2117, pruned_loss=0.02331, over 4821.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2283, pruned_loss=0.04419, over 971300.83 frames.], batch size: 27, lr: 4.70e-04
2022-05-04 19:51:10,986 INFO [train.py:715] (5/8) Epoch 4, batch 4650, loss[loss=0.1489, simple_loss=0.2194, pruned_loss=0.0392, over 4774.00 frames.], tot_loss[loss=0.1581, simple_loss=0.228, pruned_loss=0.04409, over 970790.90 frames.], batch size: 14, lr: 4.70e-04
2022-05-04 19:51:51,339 INFO [train.py:715] (5/8) Epoch 4, batch 4700, loss[loss=0.1599, simple_loss=0.2306, pruned_loss=0.04465, over 4968.00 frames.], tot_loss[loss=0.158, simple_loss=0.2277, pruned_loss=0.04417, over 971885.62 frames.], batch size: 24, lr: 4.70e-04
2022-05-04 19:52:31,246 INFO [train.py:715] (5/8) Epoch 4, batch 4750, loss[loss=0.1813, simple_loss=0.2421, pruned_loss=0.06023, over 4961.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04378, over 972065.54 frames.], batch size: 39, lr: 4.70e-04
2022-05-04 19:53:13,033 INFO [train.py:715] (5/8) Epoch 4, batch 4800, loss[loss=0.1662, simple_loss=0.2388, pruned_loss=0.04686, over 4806.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2275, pruned_loss=0.04415, over 972017.52 frames.], batch size: 13, lr: 4.70e-04
2022-05-04 19:53:53,555 INFO [train.py:715] (5/8) Epoch 4, batch 4850, loss[loss=0.1755, simple_loss=0.2506, pruned_loss=0.05017, over 4740.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04414, over 971455.82 frames.], batch size: 16, lr: 4.70e-04
2022-05-04 19:54:32,957 INFO [train.py:715] (5/8) Epoch 4, batch 4900, loss[loss=0.1556, simple_loss=0.2323, pruned_loss=0.03939, over 4969.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04415, over 972238.87 frames.], batch size: 15, lr: 4.70e-04
2022-05-04 19:55:12,347 INFO [train.py:715] (5/8) Epoch 4, batch 4950, loss[loss=0.1655, simple_loss=0.24, pruned_loss=0.04554, over 4742.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.045, over 972099.53 frames.], batch size: 16, lr: 4.70e-04
2022-05-04 19:55:52,409 INFO [train.py:715] (5/8) Epoch 4, batch 5000, loss[loss=0.1667, simple_loss=0.2345, pruned_loss=0.04944, over 4905.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2275, pruned_loss=0.0446, over 971686.88 frames.], batch size: 17, lr: 4.70e-04
2022-05-04 19:56:32,439 INFO [train.py:715] (5/8) Epoch 4, batch 5050, loss[loss=0.135, simple_loss=0.22, pruned_loss=0.02499, over 4986.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2273, pruned_loss=0.04469, over 972971.37 frames.], batch size: 14, lr: 4.69e-04
2022-05-04 19:57:12,344 INFO [train.py:715] (5/8) Epoch 4, batch 5100, loss[loss=0.1401, simple_loss=0.2069, pruned_loss=0.03671, over 4893.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2277, pruned_loss=0.04441, over 973189.11 frames.], batch size: 19, lr: 4.69e-04
2022-05-04 19:57:51,517 INFO [train.py:715] (5/8) Epoch 4, batch 5150, loss[loss=0.1882, simple_loss=0.247, pruned_loss=0.0647, over 4862.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.04434, over 972771.20 frames.], batch size: 30, lr: 4.69e-04
2022-05-04 19:58:31,721 INFO [train.py:715] (5/8) Epoch 4, batch 5200, loss[loss=0.1606, simple_loss=0.239, pruned_loss=0.04112, over 4927.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04362, over 973207.94 frames.], batch size: 18, lr: 4.69e-04
2022-05-04 19:59:11,081 INFO [train.py:715] (5/8) Epoch 4, batch 5250, loss[loss=0.1543, simple_loss=0.2113, pruned_loss=0.04868, over 4826.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2255, pruned_loss=0.04361, over 973083.11 frames.], batch size: 26, lr: 4.69e-04
2022-05-04 19:59:50,709 INFO [train.py:715] (5/8) Epoch 4, batch 5300, loss[loss=0.167, simple_loss=0.2252, pruned_loss=0.05445, over 4646.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2254, pruned_loss=0.04407, over 973072.19 frames.], batch size: 13, lr: 4.69e-04
2022-05-04 20:00:30,978 INFO [train.py:715] (5/8) Epoch 4, batch 5350, loss[loss=0.1765, simple_loss=0.2354, pruned_loss=0.0588, over 4783.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2255, pruned_loss=0.04418, over 972915.27 frames.], batch size: 17, lr: 4.69e-04
2022-05-04 20:01:11,128 INFO [train.py:715] (5/8) Epoch 4, batch 5400, loss[loss=0.1312, simple_loss=0.207, pruned_loss=0.02774, over 4993.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2262, pruned_loss=0.04435, over 972210.54 frames.], batch size: 14, lr: 4.69e-04
2022-05-04 20:01:51,437 INFO [train.py:715] (5/8) Epoch 4, batch 5450, loss[loss=0.1433, simple_loss=0.2063, pruned_loss=0.04012, over 4850.00 frames.], tot_loss[loss=0.157, simple_loss=0.2259, pruned_loss=0.04402, over 972421.92 frames.], batch size: 13, lr: 4.69e-04
2022-05-04 20:02:30,838 INFO [train.py:715] (5/8) Epoch 4, batch 5500, loss[loss=0.1525, simple_loss=0.224, pruned_loss=0.04055, over 4764.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04429, over 972240.91 frames.], batch size: 17, lr: 4.69e-04
2022-05-04 20:03:11,382 INFO [train.py:715] (5/8) Epoch 4, batch 5550, loss[loss=0.1653, simple_loss=0.2383, pruned_loss=0.04613, over 4818.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2271, pruned_loss=0.04418, over 972307.37 frames.], batch size: 25, lr: 4.69e-04
2022-05-04 20:03:51,125 INFO [train.py:715] (5/8) Epoch 4, batch 5600, loss[loss=0.1773, simple_loss=0.2505, pruned_loss=0.05204, over 4750.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04387, over 972717.49 frames.], batch size: 19, lr: 4.69e-04
2022-05-04 20:04:31,007 INFO [train.py:715] (5/8) Epoch 4, batch 5650, loss[loss=0.159, simple_loss=0.2295, pruned_loss=0.04419, over 4786.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2267, pruned_loss=0.04416, over 972477.72 frames.], batch size: 18, lr: 4.68e-04
2022-05-04 20:05:10,988 INFO [train.py:715] (5/8) Epoch 4, batch 5700, loss[loss=0.1753, simple_loss=0.2381, pruned_loss=0.0563, over 4858.00 frames.], tot_loss[loss=0.157, simple_loss=0.2267, pruned_loss=0.04362, over 972809.49 frames.], batch size: 20, lr: 4.68e-04
2022-05-04 20:05:51,204 INFO [train.py:715] (5/8) Epoch 4, batch 5750, loss[loss=0.1787, simple_loss=0.2503, pruned_loss=0.05357, over 4851.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2269, pruned_loss=0.04392, over 972165.73 frames.], batch size: 15, lr: 4.68e-04
2022-05-04 20:06:31,307 INFO [train.py:715] (5/8) Epoch 4, batch 5800, loss[loss=0.1699, simple_loss=0.2349, pruned_loss=0.05243, over 4760.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04376, over 972061.17 frames.], batch size: 16, lr: 4.68e-04
2022-05-04 20:07:10,959 INFO [train.py:715] (5/8) Epoch 4, batch 5850, loss[loss=0.1503, simple_loss=0.2298, pruned_loss=0.0354, over 4886.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.04392, over 972392.91 frames.], batch size: 22, lr: 4.68e-04
2022-05-04 20:07:51,255 INFO [train.py:715] (5/8) Epoch 4, batch 5900, loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03275, over 4768.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2264, pruned_loss=0.04366, over 972256.34 frames.], batch size: 17, lr: 4.68e-04
2022-05-04 20:08:30,934 INFO [train.py:715] (5/8) Epoch 4, batch 5950, loss[loss=0.1283, simple_loss=0.1872, pruned_loss=0.03473, over 4845.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2277, pruned_loss=0.04441, over 971881.67 frames.], batch size: 13, lr: 4.68e-04
2022-05-04 20:09:10,570 INFO [train.py:715] (5/8) Epoch 4, batch 6000, loss[loss=0.1388, simple_loss=0.2085, pruned_loss=0.03453, over 4908.00 frames.], tot_loss[loss=0.1572, simple_loss=0.227, pruned_loss=0.04371, over 972116.03 frames.], batch size: 18, lr: 4.68e-04
2022-05-04 20:09:10,571 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 20:09:20,451 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1124, simple_loss=0.1981, pruned_loss=0.01337, over 914524.00 frames.
2022-05-04 20:10:00,570 INFO [train.py:715] (5/8) Epoch 4, batch 6050, loss[loss=0.1783, simple_loss=0.2501, pruned_loss=0.05323, over 4836.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2283, pruned_loss=0.04455, over 972882.09 frames.], batch size: 12, lr: 4.68e-04
2022-05-04 20:10:40,768 INFO [train.py:715] (5/8) Epoch 4, batch 6100, loss[loss=0.2268, simple_loss=0.2864, pruned_loss=0.08361, over 4953.00 frames.], tot_loss[loss=0.1596, simple_loss=0.229, pruned_loss=0.04509, over 972280.58 frames.], batch size: 15, lr: 4.68e-04
2022-05-04 20:11:21,158 INFO [train.py:715] (5/8) Epoch 4, batch 6150, loss[loss=0.1383, simple_loss=0.2091, pruned_loss=0.03379, over 4832.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2289, pruned_loss=0.04485, over 972152.92 frames.], batch size: 15, lr: 4.68e-04
2022-05-04 20:12:01,191 INFO [train.py:715] (5/8) Epoch 4, batch 6200, loss[loss=0.1509, simple_loss=0.2328, pruned_loss=0.03453, over 4891.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2292, pruned_loss=0.04495, over 972968.40 frames.], batch size: 22, lr: 4.68e-04
2022-05-04 20:12:40,822 INFO [train.py:715] (5/8) Epoch 4, batch 6250, loss[loss=0.1398, simple_loss=0.2137, pruned_loss=0.03293, over 4892.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2282, pruned_loss=0.04461, over 971756.93 frames.], batch size: 19, lr: 4.68e-04
2022-05-04 20:13:21,463 INFO [train.py:715] (5/8) Epoch 4, batch 6300, loss[loss=0.1495, simple_loss=0.2154, pruned_loss=0.04174, over 4942.00 frames.], tot_loss[loss=0.1584, simple_loss=0.228, pruned_loss=0.04442, over 972515.41 frames.], batch size: 14, lr: 4.67e-04
2022-05-04 20:14:00,896 INFO [train.py:715] (5/8) Epoch 4, batch 6350, loss[loss=0.1257, simple_loss=0.2026, pruned_loss=0.02442, over 4696.00 frames.], tot_loss[loss=0.1586, simple_loss=0.228, pruned_loss=0.04457, over 972320.11 frames.], batch size: 15, lr: 4.67e-04
2022-05-04 20:14:41,819 INFO [train.py:715] (5/8) Epoch 4, batch 6400, loss[loss=0.1417, simple_loss=0.1994, pruned_loss=0.04203, over 4980.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2275, pruned_loss=0.04445, over 972919.73 frames.], batch size: 15, lr: 4.67e-04
2022-05-04 20:15:21,559 INFO [train.py:715] (5/8) Epoch 4, batch 6450, loss[loss=0.1903, simple_loss=0.2616, pruned_loss=0.05957, over 4978.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2286, pruned_loss=0.04494, over 973480.79 frames.], batch size: 25, lr: 4.67e-04
2022-05-04 20:16:01,661 INFO [train.py:715] (5/8) Epoch 4, batch 6500, loss[loss=0.1628, simple_loss=0.2252, pruned_loss=0.05022, over 4907.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2287, pruned_loss=0.04525, over 973759.89 frames.], batch size: 17, lr: 4.67e-04
2022-05-04 20:16:41,331 INFO [train.py:715] (5/8) Epoch 4, batch 6550, loss[loss=0.1718, simple_loss=0.2426, pruned_loss=0.05047, over 4958.00 frames.], tot_loss[loss=0.16, simple_loss=0.2292, pruned_loss=0.04538, over 973411.91 frames.], batch size: 21, lr: 4.67e-04
2022-05-04 20:17:20,643 INFO [train.py:715] (5/8) Epoch 4, batch 6600, loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03173, over 4802.00 frames.], tot_loss[loss=0.1586, simple_loss=0.228, pruned_loss=0.04458, over 973385.84 frames.], batch size: 25, lr: 4.67e-04
2022-05-04 20:18:01,335 INFO [train.py:715] (5/8) Epoch 4, batch 6650, loss[loss=0.1546, simple_loss=0.238, pruned_loss=0.03556, over 4822.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2282, pruned_loss=0.0442, over 973231.40 frames.], batch size: 15, lr: 4.67e-04
2022-05-04 20:18:40,886 INFO [train.py:715] (5/8) Epoch 4, batch 6700, loss[loss=0.1469, simple_loss=0.2161, pruned_loss=0.03886, over 4848.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2282, pruned_loss=0.04434, over 972214.72 frames.], batch size: 34, lr: 4.67e-04
2022-05-04 20:19:21,003 INFO [train.py:715] (5/8) Epoch 4, batch 6750, loss[loss=0.1663, simple_loss=0.236, pruned_loss=0.04826, over 4917.00 frames.], tot_loss[loss=0.159, simple_loss=0.2285, pruned_loss=0.04472, over 971145.37 frames.], batch size: 19, lr: 4.67e-04
2022-05-04 20:20:00,762 INFO [train.py:715] (5/8) Epoch 4, batch 6800, loss[loss=0.143, simple_loss=0.2191, pruned_loss=0.03345, over 4923.00 frames.], tot_loss[loss=0.1597, simple_loss=0.229, pruned_loss=0.04517, over 972156.87 frames.], batch size: 18, lr: 4.67e-04
2022-05-04 20:20:40,793 INFO [train.py:715] (5/8) Epoch 4, batch 6850, loss[loss=0.1791, simple_loss=0.2505, pruned_loss=0.05386, over 4874.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2279, pruned_loss=0.04464, over 973527.61 frames.], batch size: 16, lr: 4.67e-04
2022-05-04 20:21:20,095 INFO [train.py:715] (5/8) Epoch 4, batch 6900, loss[loss=0.1531, simple_loss=0.2278, pruned_loss=0.03917, over 4902.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2263, pruned_loss=0.04376, over 973568.89 frames.], batch size: 18, lr: 4.66e-04
2022-05-04 20:21:59,578 INFO [train.py:715] (5/8) Epoch 4, batch 6950, loss[loss=0.1417, simple_loss=0.216, pruned_loss=0.03376, over 4842.00 frames.], tot_loss[loss=0.1573, simple_loss=0.227, pruned_loss=0.04379, over 973672.31 frames.], batch size: 30, lr: 4.66e-04
2022-05-04 20:22:39,322 INFO [train.py:715] (5/8) Epoch 4, batch 7000, loss[loss=0.1407, simple_loss=0.2151, pruned_loss=0.03312, over 4761.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04343, over 973517.30 frames.], batch size: 18, lr: 4.66e-04
2022-05-04 20:23:19,193 INFO [train.py:715] (5/8) Epoch 4, batch 7050, loss[loss=0.141, simple_loss=0.2187, pruned_loss=0.03171, over 4810.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04331, over 972777.57 frames.], batch size: 25, lr: 4.66e-04
2022-05-04 20:23:58,923 INFO [train.py:715] (5/8) Epoch 4, batch 7100, loss[loss=0.1683, simple_loss=0.2494, pruned_loss=0.04361, over 4809.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04354, over 972211.73 frames.], batch size: 24, lr: 4.66e-04
2022-05-04 20:24:39,014 INFO [train.py:715] (5/8) Epoch 4, batch 7150, loss[loss=0.1543, simple_loss=0.2173, pruned_loss=0.04569, over 4811.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2269, pruned_loss=0.04392, over 972153.30 frames.], batch size: 13, lr: 4.66e-04
2022-05-04 20:25:18,945 INFO [train.py:715] (5/8) Epoch 4, batch 7200, loss[loss=0.16, simple_loss=0.2213, pruned_loss=0.04936, over 4848.00 frames.], tot_loss[loss=0.1575, simple_loss=0.227, pruned_loss=0.04401, over 972401.17 frames.], batch size: 30, lr: 4.66e-04
2022-05-04 20:25:59,096 INFO [train.py:715] (5/8) Epoch 4, batch 7250, loss[loss=0.1789, simple_loss=0.24, pruned_loss=0.05894, over 4788.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2275, pruned_loss=0.04413, over 971742.24 frames.], batch size: 18, lr: 4.66e-04
2022-05-04 20:26:38,418 INFO [train.py:715] (5/8) Epoch 4, batch 7300, loss[loss=0.1629, simple_loss=0.236, pruned_loss=0.04496, over 4902.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2273, pruned_loss=0.04349, over 971818.72 frames.], batch size: 17, lr: 4.66e-04
2022-05-04 20:27:18,103 INFO [train.py:715] (5/8) Epoch 4, batch 7350, loss[loss=0.1566, simple_loss=0.2302, pruned_loss=0.04144, over 4986.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2277, pruned_loss=0.0439, over 972701.16 frames.], batch size: 25, lr: 4.66e-04
2022-05-04 20:27:58,073 INFO [train.py:715] (5/8) Epoch 4, batch 7400, loss[loss=0.1374, simple_loss=0.2151, pruned_loss=0.02988, over 4915.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2276, pruned_loss=0.04384, over 972763.32 frames.], batch size: 29, lr: 4.66e-04
2022-05-04 20:28:38,811 INFO [train.py:715] (5/8) Epoch 4, batch 7450, loss[loss=0.1499, simple_loss=0.2114, pruned_loss=0.04425, over 4764.00 frames.], tot_loss[loss=0.158, simple_loss=0.228, pruned_loss=0.044, over 972913.07 frames.], batch size: 19, lr: 4.66e-04
2022-05-04 20:29:18,221 INFO [train.py:715] (5/8) Epoch 4, batch 7500, loss[loss=0.184, simple_loss=0.2513, pruned_loss=0.05834, over 4809.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2269, pruned_loss=0.04348, over 972979.36 frames.], batch size: 14, lr: 4.66e-04
2022-05-04 20:29:58,239 INFO [train.py:715] (5/8) Epoch 4, batch 7550, loss[loss=0.1435, simple_loss=0.2089, pruned_loss=0.03908, over 4970.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2275, pruned_loss=0.04364, over 972981.18 frames.], batch size: 14, lr: 4.65e-04
2022-05-04 20:30:38,892 INFO [train.py:715] (5/8) Epoch 4, batch 7600, loss[loss=0.1215, simple_loss=0.1875, pruned_loss=0.02775, over 4815.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04382, over 973271.40 frames.], batch size: 12, lr: 4.65e-04
2022-05-04 20:31:18,408 INFO [train.py:715] (5/8) Epoch 4, batch 7650, loss[loss=0.1347, simple_loss=0.1974, pruned_loss=0.03598, over 4758.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2266, pruned_loss=0.0436, over 972608.65 frames.], batch size: 12, lr: 4.65e-04
2022-05-04 20:31:58,068 INFO [train.py:715] (5/8) Epoch 4, batch 7700, loss[loss=0.1516, simple_loss=0.2248, pruned_loss=0.03917, over 4957.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04488, over 973148.54 frames.], batch size: 15, lr: 4.65e-04
2022-05-04 20:32:38,167 INFO [train.py:715] (5/8) Epoch 4, batch 7750, loss[loss=0.1382, simple_loss=0.2095, pruned_loss=0.03348, over 4986.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04466, over 974158.91 frames.], batch size: 26, lr: 4.65e-04
2022-05-04 20:33:18,307 INFO [train.py:715] (5/8) Epoch 4, batch 7800, loss[loss=0.1297, simple_loss=0.2033, pruned_loss=0.02802, over 4751.00 frames.], tot_loss[loss=0.1587, simple_loss=0.228, pruned_loss=0.04467, over 974192.68 frames.], batch size: 19, lr: 4.65e-04
2022-05-04 20:33:57,308 INFO [train.py:715] (5/8) Epoch 4, batch 7850, loss[loss=0.2107, simple_loss=0.2601, pruned_loss=0.08066, over 4637.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2283, pruned_loss=0.04496, over 973672.15 frames.], batch size: 13, lr: 4.65e-04
2022-05-04 20:34:36,904 INFO [train.py:715] (5/8) Epoch 4, batch 7900, loss[loss=0.1491, simple_loss=0.2224, pruned_loss=0.03795, over 4945.00 frames.], tot_loss[loss=0.1588, simple_loss=0.228, pruned_loss=0.04484, over 973467.41 frames.], batch size: 39, lr: 4.65e-04
2022-05-04 20:35:16,765 INFO [train.py:715] (5/8) Epoch 4, batch 7950, loss[loss=0.172, simple_loss=0.2532, pruned_loss=0.04543, over 4978.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04422, over 972874.07 frames.], batch size: 15, lr: 4.65e-04
2022-05-04 20:35:56,345 INFO [train.py:715] (5/8) Epoch 4, batch 8000, loss[loss=0.1429, simple_loss=0.2129, pruned_loss=0.03647, over 4819.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2276, pruned_loss=0.04431, over 972987.11 frames.], batch size: 25, lr: 4.65e-04
2022-05-04 20:36:36,311 INFO [train.py:715] (5/8) Epoch 4, batch 8050, loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02798, over 4772.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2287, pruned_loss=0.04447, over 972587.92 frames.], batch size: 12, lr: 4.65e-04
2022-05-04 20:37:16,266 INFO [train.py:715] (5/8) Epoch 4, batch 8100, loss[loss=0.1699, simple_loss=0.2334, pruned_loss=0.05324, over 4856.00 frames.], tot_loss[loss=0.1583, simple_loss=0.228, pruned_loss=0.04432, over 972063.13 frames.], batch size: 15, lr: 4.65e-04
2022-05-04 20:37:56,506 INFO [train.py:715] (5/8) Epoch 4, batch 8150, loss[loss=0.127, simple_loss=0.1932, pruned_loss=0.03035, over 4739.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04439, over 972321.04 frames.], batch size: 12, lr: 4.65e-04
2022-05-04 20:38:35,991 INFO [train.py:715] (5/8) Epoch 4, batch 8200, loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05124, over 4812.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2278, pruned_loss=0.04452, over 973039.24 frames.], batch size: 21, lr: 4.64e-04
2022-05-04 20:39:15,724 INFO [train.py:715] (5/8) Epoch 4, batch 8250, loss[loss=0.1597, simple_loss=0.2223, pruned_loss=0.04857, over 4869.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2283, pruned_loss=0.04462, over 972511.72 frames.], batch size: 32, lr: 4.64e-04
2022-05-04 20:39:55,879 INFO [train.py:715] (5/8) Epoch 4, batch 8300, loss[loss=0.1535, simple_loss=0.216, pruned_loss=0.04554, over 4838.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2273, pruned_loss=0.04403, over 972433.89 frames.], batch size: 30, lr: 4.64e-04
2022-05-04 20:40:35,313 INFO [train.py:715] (5/8) Epoch 4, batch 8350, loss[loss=0.1204, simple_loss=0.191, pruned_loss=0.02489, over 4889.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2273, pruned_loss=0.04376, over 972013.99 frames.], batch size: 16, lr: 4.64e-04
2022-05-04 20:41:15,402 INFO [train.py:715] (5/8) Epoch 4, batch 8400, loss[loss=0.1699, simple_loss=0.2379, pruned_loss=0.05098, over 4863.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04371, over 972147.23 frames.], batch size: 34, lr: 4.64e-04
2022-05-04 20:41:55,743 INFO [train.py:715] (5/8) Epoch 4, batch 8450, loss[loss=0.1575, simple_loss=0.2217, pruned_loss=0.04665, over 4783.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.04347, over 972761.69 frames.], batch size: 17, lr: 4.64e-04
2022-05-04 20:42:35,851 INFO [train.py:715] (5/8) Epoch 4, batch 8500, loss[loss=0.1834, simple_loss=0.2523, pruned_loss=0.05724, over 4893.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04341, over 972627.69 frames.], batch size: 19, lr: 4.64e-04
2022-05-04 20:43:15,261 INFO [train.py:715] (5/8) Epoch 4, batch 8550, loss[loss=0.174, simple_loss=0.2371, pruned_loss=0.05542, over 4767.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2262, pruned_loss=0.04353, over 972651.54 frames.], batch size: 14, lr: 4.64e-04
2022-05-04 20:43:55,080 INFO [train.py:715] (5/8) Epoch 4, batch 8600, loss[loss=0.1438, simple_loss=0.2193, pruned_loss=0.03409, over 4781.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2261, pruned_loss=0.04367, over 972642.44 frames.], batch size: 17, lr: 4.64e-04
2022-05-04 20:44:35,238 INFO [train.py:715] (5/8) Epoch 4, batch 8650, loss[loss=0.141, simple_loss=0.2013, pruned_loss=0.0404, over 4927.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04367, over 972649.49 frames.], batch size: 23, lr: 4.64e-04
2022-05-04 20:45:14,868 INFO [train.py:715] (5/8) Epoch 4, batch 8700, loss[loss=0.1616, simple_loss=0.2211, pruned_loss=0.05103, over 4866.00 frames.], tot_loss[loss=0.1569, simple_loss=0.226, pruned_loss=0.04389, over 972790.86 frames.], batch size: 30, lr: 4.64e-04
2022-05-04 20:45:55,165 INFO [train.py:715] (5/8) Epoch 4, batch 8750, loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03585, over 4761.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2254, pruned_loss=0.04356, over 972285.80 frames.], batch size: 19, lr: 4.64e-04
2022-05-04 20:46:35,395 INFO [train.py:715] (5/8) Epoch 4, batch 8800, loss[loss=0.1324, simple_loss=0.203, pruned_loss=0.03091, over 4957.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2256, pruned_loss=0.04382, over 972932.31 frames.], batch size: 21, lr: 4.63e-04
2022-05-04 20:47:15,432 INFO [train.py:715] (5/8) Epoch 4, batch 8850, loss[loss=0.1889, simple_loss=0.2512, pruned_loss=0.06333, over 4864.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2253, pruned_loss=0.04344, over 972735.72 frames.], batch size: 32, lr: 4.63e-04
2022-05-04 20:47:55,125 INFO [train.py:715] (5/8) Epoch 4, batch 8900, loss[loss=0.1493, simple_loss=0.2179, pruned_loss=0.04035, over 4889.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2253, pruned_loss=0.04356, over 972851.96 frames.], batch size: 16, lr: 4.63e-04
2022-05-04 20:48:34,759 INFO [train.py:715] (5/8) Epoch 4, batch 8950, loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03537, over 4795.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2256, pruned_loss=0.04371, over 972196.16 frames.], batch size: 21, lr: 4.63e-04
2022-05-04 20:49:15,022 INFO [train.py:715] (5/8) Epoch 4, batch 9000, loss[loss=0.1583, simple_loss=0.2251, pruned_loss=0.04574, over 4985.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2255, pruned_loss=0.04393, over 972393.10 frames.], batch size: 14, lr: 4.63e-04
2022-05-04 20:49:15,023 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 20:49:24,977 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1123, simple_loss=0.1979, pruned_loss=0.01336, over 914524.00 frames.
2022-05-04 20:50:05,303 INFO [train.py:715] (5/8) Epoch 4, batch 9050, loss[loss=0.1892, simple_loss=0.2484, pruned_loss=0.06496, over 4692.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2267, pruned_loss=0.0444, over 972078.04 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:50:45,310 INFO [train.py:715] (5/8) Epoch 4, batch 9100, loss[loss=0.1636, simple_loss=0.2399, pruned_loss=0.04369, over 4883.00 frames.], tot_loss[loss=0.1579, simple_loss=0.227, pruned_loss=0.04436, over 972031.21 frames.], batch size: 22, lr: 4.63e-04
2022-05-04 20:51:24,707 INFO [train.py:715] (5/8) Epoch 4, batch 9150, loss[loss=0.1847, simple_loss=0.2406, pruned_loss=0.06442, over 4976.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04357, over 971634.77 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:52:04,885 INFO [train.py:715] (5/8) Epoch 4, batch 9200, loss[loss=0.1643, simple_loss=0.2304, pruned_loss=0.04911, over 4745.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.0437, over 970497.62 frames.], batch size: 16, lr: 4.63e-04
2022-05-04 20:52:45,290 INFO [train.py:715] (5/8) Epoch 4, batch 9250, loss[loss=0.1248, simple_loss=0.1957, pruned_loss=0.02698, over 4988.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2271, pruned_loss=0.0441, over 970929.71 frames.], batch size: 28, lr: 4.63e-04
2022-05-04 20:53:24,536 INFO [train.py:715] (5/8) Epoch 4, batch 9300, loss[loss=0.1944, simple_loss=0.2651, pruned_loss=0.06184, over 4886.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04428, over 970666.69 frames.], batch size: 17, lr: 4.63e-04
2022-05-04 20:54:04,526 INFO [train.py:715] (5/8) Epoch 4, batch 9350, loss[loss=0.1353, simple_loss=0.2072, pruned_loss=0.03169, over 4915.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2281, pruned_loss=0.04452, over 971204.28 frames.], batch size: 18, lr: 4.63e-04
2022-05-04 20:54:44,469 INFO [train.py:715] (5/8) Epoch 4, batch 9400, loss[loss=0.1545, simple_loss=0.2237, pruned_loss=0.04268, over 4882.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2281, pruned_loss=0.04473, over 971384.81 frames.], batch size: 16, lr: 4.63e-04
2022-05-04 20:55:24,001 INFO [train.py:715] (5/8) Epoch 4, batch 9450, loss[loss=0.1528, simple_loss=0.2191, pruned_loss=0.0432, over 4880.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2274, pruned_loss=0.04407, over 971844.58 frames.], batch size: 22, lr: 4.62e-04
2022-05-04 20:56:04,090 INFO [train.py:715] (5/8) Epoch 4, batch 9500, loss[loss=0.1778, simple_loss=0.2526, pruned_loss=0.05155, over 4987.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04371, over 972203.89 frames.], batch size: 25, lr: 4.62e-04
2022-05-04 20:56:44,150 INFO [train.py:715] (5/8) Epoch 4, batch 9550, loss[loss=0.1496, simple_loss=0.2108, pruned_loss=0.0442, over 4755.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2269, pruned_loss=0.04378, over 971902.16 frames.], batch size: 16, lr: 4.62e-04
2022-05-04 20:57:24,667 INFO [train.py:715] (5/8) Epoch 4, batch 9600, loss[loss=0.1766, simple_loss=0.2384, pruned_loss=0.05741, over 4846.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04386, over 971539.07 frames.], batch size: 15, lr: 4.62e-04
2022-05-04 20:58:04,091 INFO [train.py:715] (5/8) Epoch 4, batch 9650, loss[loss=0.138, simple_loss=0.2027, pruned_loss=0.03662, over 4941.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04385, over 971646.71 frames.], batch size: 21, lr: 4.62e-04
2022-05-04 20:58:44,654 INFO [train.py:715] (5/8) Epoch 4, batch 9700, loss[loss=0.1662, simple_loss=0.2377, pruned_loss=0.04731, over 4831.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.0447, over 971448.38 frames.], batch size: 26, lr: 4.62e-04
2022-05-04 20:59:25,194 INFO [train.py:715] (5/8) Epoch 4, batch 9750, loss[loss=0.1377, simple_loss=0.2061, pruned_loss=0.03463, over 4986.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2273, pruned_loss=0.04408, over 972454.05 frames.], batch size: 25, lr: 4.62e-04
2022-05-04 21:00:04,725 INFO [train.py:715] (5/8) Epoch 4, batch 9800, loss[loss=0.1666, simple_loss=0.227, pruned_loss=0.05303, over 4931.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2278, pruned_loss=0.04447, over 972291.57 frames.], batch size: 35, lr: 4.62e-04
2022-05-04 21:00:43,861 INFO [train.py:715] (5/8) Epoch 4, batch 9850, loss[loss=0.1797, simple_loss=0.2411, pruned_loss=0.0591, over 4774.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04408, over 972180.50 frames.], batch size: 19, lr: 4.62e-04
2022-05-04 21:01:23,903 INFO [train.py:715] (5/8) Epoch 4, batch 9900, loss[loss=0.1848, simple_loss=0.2438, pruned_loss=0.06287, over 4866.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2273, pruned_loss=0.04442, over 972620.45 frames.], batch size: 16, lr: 4.62e-04
2022-05-04 21:02:03,375 INFO [train.py:715] (5/8) Epoch 4, batch 9950, loss[loss=0.2187, simple_loss=0.2881, pruned_loss=0.07464, over 4759.00 frames.], tot_loss[loss=0.1575, simple_loss=0.227, pruned_loss=0.04404, over 972967.54 frames.], batch size: 19, lr: 4.62e-04
2022-05-04 21:02:42,750 INFO [train.py:715] (5/8) Epoch 4, batch 10000, loss[loss=0.1535, simple_loss=0.2138, pruned_loss=0.04659, over 4829.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04375, over 974255.21 frames.], batch size: 27, lr: 4.62e-04
2022-05-04 21:03:22,512 INFO [train.py:715] (5/8) Epoch 4, batch 10050, loss[loss=0.2151, simple_loss=0.2767, pruned_loss=0.07674, over 4915.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2279, pruned_loss=0.04484, over 973904.51 frames.], batch size: 18, lr: 4.62e-04
2022-05-04 21:04:02,312 INFO [train.py:715] (5/8) Epoch 4, batch 10100, loss[loss=0.1769, simple_loss=0.2335, pruned_loss=0.0602, over 4842.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2275, pruned_loss=0.04456, over 974497.66 frames.], batch size: 30, lr: 4.61e-04
2022-05-04 21:04:41,556 INFO [train.py:715] (5/8) Epoch 4, batch 10150, loss[loss=0.1358, simple_loss=0.2062, pruned_loss=0.03263, over 4960.00 frames.], tot_loss[loss=0.159, simple_loss=0.2283, pruned_loss=0.04484, over 973743.95 frames.], batch size: 14, lr: 4.61e-04
2022-05-04 21:05:21,476 INFO [train.py:715] (5/8) Epoch 4, batch 10200, loss[loss=0.1634, simple_loss=0.2208, pruned_loss=0.05298, over 4811.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2285, pruned_loss=0.04521, over 974022.51 frames.], batch size: 27, lr: 4.61e-04
2022-05-04 21:06:02,061 INFO [train.py:715] (5/8) Epoch 4, batch 10250, loss[loss=0.1731, simple_loss=0.2342, pruned_loss=0.05596, over 4787.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2287, pruned_loss=0.04509, over 974281.31 frames.], batch size: 18, lr: 4.61e-04
2022-05-04 21:06:41,848 INFO [train.py:715] (5/8) Epoch 4, batch 10300, loss[loss=0.1696, simple_loss=0.2254, pruned_loss=0.05694, over 4752.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2287, pruned_loss=0.04529, over 973093.79 frames.], batch size: 16, lr: 4.61e-04
2022-05-04 21:07:21,506 INFO [train.py:715] (5/8) Epoch 4, batch 10350, loss[loss=0.14, simple_loss=0.2093, pruned_loss=0.03533, over 4834.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2286, pruned_loss=0.04542, over 972448.48 frames.], batch size: 12, lr: 4.61e-04
2022-05-04 21:08:01,702 INFO [train.py:715] (5/8) Epoch 4, batch 10400, loss[loss=0.1442, simple_loss=0.2131, pruned_loss=0.03765, over 4845.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2279, pruned_loss=0.04517, over 972791.04 frames.], batch size: 30, lr: 4.61e-04
2022-05-04 21:08:42,278 INFO [train.py:715] (5/8) Epoch 4, batch 10450, loss[loss=0.1328, simple_loss=0.206, pruned_loss=0.02984, over 4812.00 frames.], tot_loss[loss=0.1591, simple_loss=0.228, pruned_loss=0.04503, over 973119.58 frames.], batch size: 24, lr: 4.61e-04
2022-05-04 21:09:21,888 INFO [train.py:715] (5/8) Epoch 4, batch 10500, loss[loss=0.1621, simple_loss=0.225, pruned_loss=0.04958, over 4789.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.04453, over 972400.19 frames.], batch size: 14, lr: 4.61e-04
2022-05-04 21:10:02,145 INFO [train.py:715] (5/8) Epoch 4, batch 10550, loss[loss=0.1622, simple_loss=0.2359, pruned_loss=0.04426, over 4940.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04416, over 970842.56 frames.], batch size: 23, lr: 4.61e-04
2022-05-04 21:10:42,491 INFO [train.py:715] (5/8) Epoch 4, batch 10600, loss[loss=0.1844, simple_loss=0.2569, pruned_loss=0.05596, over 4981.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04397, over 972001.84 frames.], batch size: 39, lr: 4.61e-04
2022-05-04 21:11:22,293 INFO [train.py:715] (5/8) Epoch 4, batch 10650, loss[loss=0.1526, simple_loss=0.2292, pruned_loss=0.03795, over 4987.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04375, over 972280.27 frames.], batch size: 26, lr: 4.61e-04
2022-05-04 21:12:02,338 INFO [train.py:715] (5/8) Epoch 4, batch 10700, loss[loss=0.157, simple_loss=0.2296, pruned_loss=0.04226, over 4981.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04357, over 971820.19 frames.], batch size: 15, lr: 4.61e-04
2022-05-04 21:12:42,036 INFO [train.py:715] (5/8) Epoch 4, batch 10750, loss[loss=0.1566, simple_loss=0.2362, pruned_loss=0.03853, over 4875.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04408, over 971789.51 frames.], batch size: 20, lr: 4.60e-04
2022-05-04 21:13:22,453 INFO [train.py:715] (5/8) Epoch 4, batch 10800, loss[loss=0.1577, simple_loss=0.2323, pruned_loss=0.04149, over 4931.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2279, pruned_loss=0.04492, over 972391.85 frames.], batch size: 23, lr: 4.60e-04
2022-05-04 21:14:01,770 INFO [train.py:715] (5/8) Epoch 4, batch 10850, loss[loss=0.1607, simple_loss=0.24, pruned_loss=0.04067, over 4962.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2273, pruned_loss=0.04448, over 973787.07 frames.], batch size: 29, lr: 4.60e-04
2022-05-04 21:14:41,703 INFO [train.py:715] (5/8) Epoch 4, batch 10900, loss[loss=0.1394, simple_loss=0.2047, pruned_loss=0.03706, over 4827.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2263, pruned_loss=0.04397, over 972870.63 frames.], batch size: 26, lr: 4.60e-04
2022-05-04 21:15:22,019 INFO [train.py:715] (5/8) Epoch 4, batch 10950, loss[loss=0.1805, simple_loss=0.2601, pruned_loss=0.05041, over 4754.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2252, pruned_loss=0.04307, over 972519.07 frames.], batch size: 16, lr: 4.60e-04
2022-05-04 21:16:01,656 INFO [train.py:715] (5/8) Epoch 4, batch 11000, loss[loss=0.1309, simple_loss=0.2025, pruned_loss=0.02967, over 4770.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2253, pruned_loss=0.04305, over 972408.69 frames.], batch size: 12, lr: 4.60e-04
2022-05-04 21:16:44,079 INFO [train.py:715] (5/8) Epoch 4, batch 11050, loss[loss=0.1404, simple_loss=0.2106, pruned_loss=0.03516, over 4791.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2257, pruned_loss=0.04286, over 972294.12 frames.], batch size: 17, lr: 4.60e-04
2022-05-04 21:17:24,572 INFO [train.py:715] (5/8) Epoch 4, batch 11100, loss[loss=0.173, simple_loss=0.2322, pruned_loss=0.05685, over 4966.00 frames.], tot_loss[loss=0.155, simple_loss=0.225, pruned_loss=0.04245, over 972728.93 frames.], batch size: 35, lr: 4.60e-04
2022-05-04 21:18:07,375 INFO [train.py:715] (5/8) Epoch 4, batch 11150, loss[loss=0.1544, simple_loss=0.2251, pruned_loss=0.04187, over 4832.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2258, pruned_loss=0.04277, over 972485.58 frames.], batch size: 26, lr: 4.60e-04
2022-05-04 21:18:49,589 INFO [train.py:715] (5/8) Epoch 4, batch 11200, loss[loss=0.1564, simple_loss=0.2296, pruned_loss=0.04158, over 4921.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04331, over 972441.84 frames.], batch size: 35, lr: 4.60e-04
2022-05-04 21:19:30,009 INFO [train.py:715] (5/8) Epoch 4, batch 11250, loss[loss=0.128, simple_loss=0.2031, pruned_loss=0.02649, over 4810.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04332, over 973303.01 frames.], batch size: 25, lr: 4.60e-04
2022-05-04 21:20:12,913 INFO [train.py:715] (5/8) Epoch 4, batch 11300, loss[loss=0.1403, simple_loss=0.2153, pruned_loss=0.03262, over 4804.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04359, over 973529.67 frames.], batch size: 21, lr: 4.60e-04
2022-05-04 21:20:52,367 INFO [train.py:715] (5/8) Epoch 4, batch 11350, loss[loss=0.153, simple_loss=0.2143, pruned_loss=0.04586, over 4864.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2257, pruned_loss=0.0438, over 972852.98 frames.], batch size: 32, lr: 4.60e-04
2022-05-04 21:21:31,879 INFO [train.py:715] (5/8) Epoch 4, batch 11400, loss[loss=0.1416, simple_loss=0.2112, pruned_loss=0.03607, over 4970.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04351, over 973158.86 frames.], batch size: 25, lr: 4.59e-04
2022-05-04 21:22:11,705 INFO [train.py:715] (5/8) Epoch 4, batch 11450, loss[loss=0.1545, simple_loss=0.2268, pruned_loss=0.04105, over 4825.00 frames.], tot_loss[loss=0.1559, simple_loss=0.225, pruned_loss=0.0434, over 972606.01 frames.], batch size: 26, lr: 4.59e-04
2022-05-04 21:22:51,368 INFO [train.py:715] (5/8) Epoch 4, batch 11500, loss[loss=0.1676, simple_loss=0.2416, pruned_loss=0.04676, over 4803.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2253, pruned_loss=0.04338, over 972573.91 frames.], batch size: 24, lr: 4.59e-04
2022-05-04 21:23:30,615 INFO [train.py:715] (5/8) Epoch 4, batch 11550, loss[loss=0.1626, simple_loss=0.2347, pruned_loss=0.04521, over 4920.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2249, pruned_loss=0.04295, over 972063.08 frames.], batch size: 18, lr: 4.59e-04
2022-05-04 21:24:09,875 INFO [train.py:715] (5/8) Epoch 4, batch 11600, loss[loss=0.1451, simple_loss=0.2122, pruned_loss=0.03903, over 4958.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.0429, over 972009.86 frames.], batch size: 24, lr: 4.59e-04
2022-05-04 21:24:50,389 INFO [train.py:715] (5/8) Epoch 4, batch 11650, loss[loss=0.1565, simple_loss=0.2318, pruned_loss=0.04065, over 4898.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04272, over 971495.79 frames.], batch size: 17, lr: 4.59e-04
2022-05-04 21:25:30,284 INFO [train.py:715] (5/8) Epoch 4, batch 11700, loss[loss=0.1632, simple_loss=0.2272, pruned_loss=0.04963, over 4953.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2253, pruned_loss=0.04311, over 971552.08 frames.], batch size: 24, lr: 4.59e-04
2022-05-04 21:26:10,261 INFO [train.py:715] (5/8) Epoch 4, batch 11750, loss[loss=0.1506, simple_loss=0.2359, pruned_loss=0.03269, over 4742.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2251, pruned_loss=0.04309, over 972242.75 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:26:50,010 INFO [train.py:715] (5/8) Epoch 4, batch 11800, loss[loss=0.1737, simple_loss=0.2503, pruned_loss=0.04861, over 4878.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04381, over 972158.11 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:27:30,277 INFO [train.py:715] (5/8) Epoch 4, batch 11850, loss[loss=0.1409, simple_loss=0.2111, pruned_loss=0.03529, over 4803.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04398, over 971186.78 frames.], batch size: 24, lr: 4.59e-04
2022-05-04 21:28:09,534 INFO [train.py:715] (5/8) Epoch 4, batch 11900, loss[loss=0.1517, simple_loss=0.221, pruned_loss=0.04119, over 4826.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04388, over 971117.00 frames.], batch size: 26, lr: 4.59e-04
2022-05-04 21:28:49,310 INFO [train.py:715] (5/8) Epoch 4, batch 11950, loss[loss=0.1335, simple_loss=0.2038, pruned_loss=0.03158, over 4872.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2254, pruned_loss=0.04286, over 972250.31 frames.], batch size: 32, lr: 4.59e-04
2022-05-04 21:29:29,766 INFO [train.py:715] (5/8) Epoch 4, batch 12000, loss[loss=0.1518, simple_loss=0.2416, pruned_loss=0.03101, over 4824.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.04308, over 971609.58 frames.], batch size: 25, lr: 4.59e-04
2022-05-04 21:29:29,767 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 21:29:49,525 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1122, simple_loss=0.198, pruned_loss=0.01324, over 914524.00 frames.
2022-05-04 21:30:30,068 INFO [train.py:715] (5/8) Epoch 4, batch 12050, loss[loss=0.1687, simple_loss=0.2391, pruned_loss=0.04921, over 4821.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04384, over 971543.19 frames.], batch size: 15, lr: 4.58e-04
2022-05-04 21:31:09,882 INFO [train.py:715] (5/8) Epoch 4, batch 12100, loss[loss=0.1445, simple_loss=0.2084, pruned_loss=0.04024, over 4808.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.0438, over 971665.12 frames.], batch size: 25, lr: 4.58e-04
2022-05-04 21:31:50,067 INFO [train.py:715] (5/8) Epoch 4, batch 12150, loss[loss=0.1445, simple_loss=0.2239, pruned_loss=0.03252, over 4941.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2278, pruned_loss=0.04419, over 972002.99 frames.], batch size: 21, lr: 4.58e-04
2022-05-04 21:32:30,106 INFO [train.py:715] (5/8) Epoch 4, batch 12200, loss[loss=0.1633, simple_loss=0.238, pruned_loss=0.04429, over 4896.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2278, pruned_loss=0.04432, over 971924.77 frames.], batch size: 39, lr: 4.58e-04
2022-05-04 21:33:10,435 INFO [train.py:715] (5/8) Epoch 4, batch 12250, loss[loss=0.1978, simple_loss=0.2577, pruned_loss=0.06895, over 4908.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.04432, over 971277.01 frames.], batch size: 17, lr: 4.58e-04
2022-05-04 21:33:49,419 INFO [train.py:715] (5/8) Epoch 4, batch 12300, loss[loss=0.1405, simple_loss=0.2146, pruned_loss=0.03316, over 4903.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04415, over 971475.97 frames.], batch size: 17, lr: 4.58e-04
2022-05-04 21:34:29,437 INFO [train.py:715] (5/8) Epoch 4, batch 12350, loss[loss=0.1476, simple_loss=0.2245, pruned_loss=0.03541, over 4838.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2281, pruned_loss=0.04413, over 971856.72 frames.], batch size: 27, lr: 4.58e-04
2022-05-04 21:35:10,028 INFO [train.py:715] (5/8) Epoch 4, batch 12400, loss[loss=0.127, simple_loss=0.2019, pruned_loss=0.0261, over 4876.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2277, pruned_loss=0.04428, over 972456.21 frames.], batch size: 16, lr: 4.58e-04
2022-05-04 21:35:49,238 INFO [train.py:715] (5/8) Epoch 4, batch 12450, loss[loss=0.1416, simple_loss=0.2116, pruned_loss=0.03576, over 4767.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2275, pruned_loss=0.04397, over 972211.00 frames.], batch size: 18, lr: 4.58e-04
2022-05-04 21:36:29,202 INFO [train.py:715] (5/8) Epoch 4, batch 12500, loss[loss=0.1301, simple_loss=0.1997, pruned_loss=0.03031, over 4692.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04403, over 972510.32 frames.], batch size: 15, lr: 4.58e-04
2022-05-04 21:37:08,759 INFO [train.py:715] (5/8) Epoch 4, batch 12550, loss[loss=0.1547, simple_loss=0.2149, pruned_loss=0.04721, over 4775.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04414, over 971983.31 frames.], batch size: 12, lr: 4.58e-04
2022-05-04 21:37:48,546 INFO [train.py:715] (5/8) Epoch 4, batch 12600, loss[loss=0.1681, simple_loss=0.241, pruned_loss=0.04761, over 4931.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.0436, over 972788.11 frames.], batch size: 21, lr: 4.58e-04
2022-05-04 21:38:27,437 INFO [train.py:715] (5/8) Epoch 4, batch 12650, loss[loss=0.165, simple_loss=0.2331, pruned_loss=0.04848, over 4948.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2249, pruned_loss=0.04338, over 972593.58 frames.], batch size: 29, lr: 4.58e-04
2022-05-04 21:39:07,277 INFO [train.py:715] (5/8) Epoch 4, batch 12700, loss[loss=0.1573, simple_loss=0.2278, pruned_loss=0.04337, over 4879.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2253, pruned_loss=0.04364, over 970656.58 frames.], batch size: 16, lr: 4.58e-04
2022-05-04 21:39:47,347 INFO [train.py:715] (5/8) Epoch 4, batch 12750, loss[loss=0.143, simple_loss=0.2079, pruned_loss=0.03901, over 4820.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2254, pruned_loss=0.04378, over 971422.97 frames.], batch size: 26, lr: 4.57e-04
2022-05-04 21:40:29,602 INFO [train.py:715] (5/8) Epoch 4, batch 12800, loss[loss=0.1129, simple_loss=0.1889, pruned_loss=0.0184, over 4836.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04351, over 971811.62 frames.], batch size: 13, lr: 4.57e-04
2022-05-04 21:41:09,006 INFO [train.py:715] (5/8) Epoch 4, batch 12850, loss[loss=0.1457, simple_loss=0.2183, pruned_loss=0.03656, over 4897.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04329, over 972011.74 frames.], batch size: 38, lr: 4.57e-04
2022-05-04 21:41:49,125 INFO [train.py:715] (5/8) Epoch 4, batch 12900, loss[loss=0.1531, simple_loss=0.2216, pruned_loss=0.04228, over 4794.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2259, pruned_loss=0.043, over 971698.76 frames.], batch size: 24, lr: 4.57e-04
2022-05-04 21:42:29,051 INFO [train.py:715] (5/8) Epoch 4, batch 12950, loss[loss=0.1552, simple_loss=0.2262, pruned_loss=0.04215, over 4962.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.04315, over 971634.68 frames.], batch size: 24, lr: 4.57e-04
2022-05-04 21:43:07,918 INFO [train.py:715] (5/8) Epoch 4, batch 13000, loss[loss=0.1432, simple_loss=0.2115, pruned_loss=0.03744, over 4984.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04317, over 972136.79 frames.], batch size: 25, lr: 4.57e-04
2022-05-04 21:43:47,506 INFO [train.py:715] (5/8) Epoch 4, batch 13050, loss[loss=0.1282, simple_loss=0.1987, pruned_loss=0.02891, over 4856.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.04313, over 972841.27 frames.], batch size: 30, lr: 4.57e-04
2022-05-04 21:44:27,466 INFO [train.py:715] (5/8) Epoch 4, batch 13100, loss[loss=0.1438, simple_loss=0.2139, pruned_loss=0.03679, over 4818.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2266, pruned_loss=0.04334, over 971536.33 frames.], batch size: 15, lr: 4.57e-04
2022-05-04 21:45:06,506 INFO [train.py:715] (5/8) Epoch 4, batch 13150, loss[loss=0.155, simple_loss=0.2289, pruned_loss=0.04054, over 4818.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2268, pruned_loss=0.0432, over 970752.70 frames.], batch size: 27, lr: 4.57e-04
2022-05-04 21:45:46,246 INFO [train.py:715] (5/8) Epoch 4, batch 13200, loss[loss=0.1736, simple_loss=0.2418, pruned_loss=0.05265, over 4789.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04332, over 969949.03 frames.], batch size: 14, lr: 4.57e-04
2022-05-04 21:46:26,567 INFO [train.py:715] (5/8) Epoch 4, batch 13250, loss[loss=0.1562, simple_loss=0.2352, pruned_loss=0.03856, over 4826.00 frames.], tot_loss[loss=0.157, simple_loss=0.227, pruned_loss=0.04349, over 970611.12 frames.], batch size: 26, lr: 4.57e-04
2022-05-04 21:47:06,174 INFO [train.py:715] (5/8) Epoch 4, batch 13300, loss[loss=0.1614, simple_loss=0.2287, pruned_loss=0.047, over 4812.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2265, pruned_loss=0.04326, over 969696.26 frames.], batch size: 12, lr: 4.57e-04
2022-05-04 21:47:45,759 INFO [train.py:715] (5/8) Epoch 4, batch 13350, loss[loss=0.1173, simple_loss=0.1878, pruned_loss=0.02346, over 4755.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2262, pruned_loss=0.04282, over 969601.79 frames.], batch size: 12, lr: 4.57e-04
2022-05-04 21:48:25,401 INFO [train.py:715] (5/8) Epoch 4, batch 13400, loss[loss=0.2018, simple_loss=0.2678, pruned_loss=0.06793, over 4976.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04337, over 970332.01 frames.], batch size: 15, lr: 4.56e-04
2022-05-04 21:49:05,435 INFO [train.py:715] (5/8) Epoch 4, batch 13450, loss[loss=0.1734, simple_loss=0.2518, pruned_loss=0.04754, over 4894.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2254, pruned_loss=0.04302, over 971164.07 frames.], batch size: 19, lr: 4.56e-04
2022-05-04 21:49:45,241 INFO [train.py:715] (5/8) Epoch 4, batch 13500, loss[loss=0.145, simple_loss=0.207, pruned_loss=0.04147, over 4904.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04366, over 970847.33 frames.], batch size: 17, lr: 4.56e-04
2022-05-04 21:50:27,089 INFO [train.py:715] (5/8) Epoch 4, batch 13550, loss[loss=0.153, simple_loss=0.225, pruned_loss=0.04047, over 4804.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04367, over 970894.69 frames.], batch size: 21, lr: 4.56e-04
2022-05-04 21:51:07,662 INFO [train.py:715] (5/8) Epoch 4, batch 13600, loss[loss=0.1609, simple_loss=0.2317, pruned_loss=0.04511, over 4867.00 frames.], tot_loss[loss=0.156, simple_loss=0.226, pruned_loss=0.04302, over 970597.51 frames.], batch size: 22, lr: 4.56e-04
2022-05-04 21:51:47,216 INFO [train.py:715] (5/8) Epoch 4, batch 13650, loss[loss=0.159, simple_loss=0.2297, pruned_loss=0.0441, over 4873.00 frames.], tot_loss[loss=0.156, simple_loss=0.2257, pruned_loss=0.04317, over 970988.82 frames.], batch size: 39, lr: 4.56e-04
2022-05-04 21:52:26,527 INFO [train.py:715] (5/8) Epoch 4, batch 13700, loss[loss=0.1621, simple_loss=0.2172, pruned_loss=0.05349, over 4745.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04308, over 972204.81 frames.], batch size: 19, lr: 4.56e-04
2022-05-04 21:53:06,468 INFO [train.py:715] (5/8) Epoch 4, batch 13750, loss[loss=0.148, simple_loss=0.2157, pruned_loss=0.04015, over 4768.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04306, over 972742.67 frames.], batch size: 18, lr: 4.56e-04
2022-05-04 21:53:48,117 INFO [train.py:715] (5/8) Epoch 4, batch 13800, loss[loss=0.1205, simple_loss=0.2008, pruned_loss=0.02015, over 4934.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04355, over 973412.52 frames.], batch size: 23, lr: 4.56e-04
2022-05-04 21:54:29,030 INFO [train.py:715] (5/8) Epoch 4, batch 13850, loss[loss=0.135, simple_loss=0.2117, pruned_loss=0.02916, over 4928.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2248, pruned_loss=0.04299, over 973428.12 frames.], batch size: 21, lr: 4.56e-04
2022-05-04 21:55:10,919 INFO [train.py:715] (5/8) Epoch 4, batch 13900, loss[loss=0.1552, simple_loss=0.2291, pruned_loss=0.04066, over 4885.00 frames.], tot_loss[loss=0.1558, simple_loss=0.225, pruned_loss=0.04329, over 972816.19 frames.], batch size: 22, lr: 4.56e-04
2022-05-04 21:55:52,332 INFO [train.py:715] (5/8) Epoch 4, batch 13950, loss[loss=0.1498, simple_loss=0.2363, pruned_loss=0.03169, over 4934.00 frames.], tot_loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.04283, over 972536.00 frames.], batch size: 29, lr: 4.56e-04
2022-05-04 21:56:31,848 INFO [train.py:715] (5/8) Epoch 4, batch 14000, loss[loss=0.1624, simple_loss=0.2378, pruned_loss=0.04349, over 4931.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04397, over 972923.73 frames.], batch size: 23, lr: 4.56e-04
2022-05-04 21:57:12,921 INFO [train.py:715] (5/8) Epoch 4, batch 14050, loss[loss=0.1542, simple_loss=0.2236, pruned_loss=0.04237, over 4891.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2273, pruned_loss=0.04412, over 971951.07 frames.], batch size: 19, lr: 4.55e-04
2022-05-04 21:57:52,567 INFO [train.py:715] (5/8) Epoch 4, batch 14100, loss[loss=0.1703, simple_loss=0.2385, pruned_loss=0.05106, over 4832.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2273, pruned_loss=0.04397, over 971411.86 frames.], batch size: 15, lr: 4.55e-04
2022-05-04 21:58:32,934 INFO [train.py:715] (5/8) Epoch 4, batch 14150, loss[loss=0.1328, simple_loss=0.2123, pruned_loss=0.02668, over 4959.00 frames.], tot_loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04345, over 971617.37 frames.], batch size: 24, lr: 4.55e-04
2022-05-04 21:59:12,289 INFO [train.py:715] (5/8) Epoch 4, batch 14200, loss[loss=0.1649, simple_loss=0.2313, pruned_loss=0.04929, over 4848.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2266, pruned_loss=0.04328, over 972077.74 frames.], batch size: 12, lr: 4.55e-04
2022-05-04 21:59:51,979 INFO [train.py:715] (5/8) Epoch 4, batch 14250, loss[loss=0.1346, simple_loss=0.2108, pruned_loss=0.02915, over 4937.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.04341, over 971103.09 frames.], batch size: 23, lr: 4.55e-04
2022-05-04 22:00:32,134 INFO [train.py:715] (5/8) Epoch 4, batch 14300, loss[loss=0.1273, simple_loss=0.2043, pruned_loss=0.02515, over 4973.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04359, over 971033.66 frames.], batch size: 28, lr: 4.55e-04
2022-05-04 22:01:10,604 INFO [train.py:715] (5/8) Epoch 4, batch 14350, loss[loss=0.1606, simple_loss=0.2247, pruned_loss=0.04819, over 4633.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04335, over 971796.83 frames.], batch size: 13, lr: 4.55e-04
2022-05-04 22:01:50,875 INFO [train.py:715] (5/8) Epoch 4, batch 14400, loss[loss=0.1453, simple_loss=0.2069, pruned_loss=0.04187, over 4872.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2262, pruned_loss=0.04301, over 971501.33 frames.], batch size: 16, lr: 4.55e-04
2022-05-04 22:02:30,300 INFO [train.py:715] (5/8) Epoch 4, batch 14450, loss[loss=0.164, simple_loss=0.2294, pruned_loss=0.04929, over 4799.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04273, over 971844.14 frames.], batch size: 14, lr: 4.55e-04
2022-05-04 22:03:09,290 INFO [train.py:715] (5/8) Epoch 4, batch 14500, loss[loss=0.1436, simple_loss=0.2143, pruned_loss=0.03645, over 4979.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04342, over 971733.01 frames.], batch size: 25, lr: 4.55e-04
2022-05-04 22:03:48,142 INFO [train.py:715] (5/8) Epoch 4, batch 14550, loss[loss=0.1553, simple_loss=0.2335, pruned_loss=0.0386, over 4844.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.0439, over 971837.98 frames.], batch size: 32, lr: 4.55e-04
2022-05-04 22:04:27,644 INFO [train.py:715] (5/8) Epoch 4, batch 14600, loss[loss=0.1915, simple_loss=0.2603, pruned_loss=0.06137, over 4885.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04385, over 971866.21 frames.], batch size: 39, lr: 4.55e-04
2022-05-04 22:05:07,544 INFO [train.py:715] (5/8) Epoch 4, batch 14650, loss[loss=0.1549, simple_loss=0.2315, pruned_loss=0.03918, over 4971.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2262, pruned_loss=0.04369, over 972022.89 frames.], batch size: 28, lr: 4.55e-04
2022-05-04 22:05:46,292 INFO [train.py:715] (5/8) Epoch 4, batch 14700, loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04146, over 4799.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2258, pruned_loss=0.0435, over 971635.94 frames.], batch size: 21, lr: 4.55e-04
2022-05-04 22:06:26,142 INFO [train.py:715] (5/8) Epoch 4, batch 14750, loss[loss=0.1224, simple_loss=0.1904, pruned_loss=0.02724, over 4838.00 frames.], tot_loss[loss=0.154, simple_loss=0.2234, pruned_loss=0.04226, over 971912.04 frames.], batch size: 13, lr: 4.54e-04
2022-05-04 22:07:06,149 INFO [train.py:715] (5/8) Epoch 4, batch 14800, loss[loss=0.1461, simple_loss=0.2246, pruned_loss=0.03384, over 4951.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2237, pruned_loss=0.04173, over 971915.24 frames.], batch size: 29, lr: 4.54e-04
2022-05-04 22:07:51,025 INFO [train.py:715] (5/8) Epoch 4, batch 14850, loss[loss=0.1669, simple_loss=0.2314, pruned_loss=0.05123, over 4981.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04211, over 972239.22 frames.], batch size: 25, lr: 4.54e-04
2022-05-04 22:08:31,251 INFO [train.py:715] (5/8) Epoch 4, batch 14900, loss[loss=0.1387, simple_loss=0.2092, pruned_loss=0.03409, over 4801.00 frames.], tot_loss[loss=0.154, simple_loss=0.2243, pruned_loss=0.04183, over 972611.68 frames.], batch size: 13, lr: 4.54e-04
2022-05-04 22:09:11,332 INFO [train.py:715] (5/8) Epoch 4, batch 14950, loss[loss=0.1861, simple_loss=0.2371, pruned_loss=0.06756, over 4840.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04223, over 973539.26 frames.], batch size: 30, lr: 4.54e-04
2022-05-04 22:09:51,666 INFO [train.py:715] (5/8) Epoch 4, batch 15000, loss[loss=0.1596, simple_loss=0.2343, pruned_loss=0.04248, over 4963.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04243, over 972571.84 frames.], batch size: 24, lr: 4.54e-04
2022-05-04 22:09:51,667 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 22:10:32,002 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1122, simple_loss=0.1978, pruned_loss=0.01336, over 914524.00 frames.
2022-05-04 22:11:12,732 INFO [train.py:715] (5/8) Epoch 4, batch 15050, loss[loss=0.1435, simple_loss=0.2141, pruned_loss=0.03639, over 4948.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2246, pruned_loss=0.04238, over 972188.33 frames.], batch size: 21, lr: 4.54e-04
2022-05-04 22:11:52,177 INFO [train.py:715] (5/8) Epoch 4, batch 15100, loss[loss=0.153, simple_loss=0.2122, pruned_loss=0.04688, over 4873.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04335, over 972128.64 frames.], batch size: 32, lr: 4.54e-04
2022-05-04 22:12:32,071 INFO [train.py:715] (5/8) Epoch 4, batch 15150, loss[loss=0.1672, simple_loss=0.2317, pruned_loss=0.05134, over 4896.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04314, over 971551.80 frames.], batch size: 19, lr: 4.54e-04
2022-05-04 22:13:12,026 INFO [train.py:715] (5/8) Epoch 4, batch 15200, loss[loss=0.1304, simple_loss=0.2033, pruned_loss=0.02876, over 4972.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04321, over 971993.31 frames.], batch size: 35, lr: 4.54e-04
2022-05-04 22:13:51,745 INFO [train.py:715] (5/8) Epoch 4, batch 15250, loss[loss=0.1495, simple_loss=0.2236, pruned_loss=0.0377, over 4951.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.0435, over 972118.00 frames.], batch size: 21, lr: 4.54e-04
2022-05-04 22:14:31,960 INFO [train.py:715] (5/8) Epoch 4, batch 15300, loss[loss=0.1475, simple_loss=0.2315, pruned_loss=0.03174, over 4921.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.0436, over 971249.40 frames.], batch size: 23, lr: 4.54e-04
2022-05-04 22:15:12,422 INFO [train.py:715] (5/8) Epoch 4, batch 15350, loss[loss=0.1551, simple_loss=0.2201, pruned_loss=0.04504, over 4928.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04354, over 972122.42 frames.], batch size: 23, lr: 4.54e-04
2022-05-04 22:15:52,257 INFO [train.py:715] (5/8) Epoch 4, batch 15400, loss[loss=0.1485, simple_loss=0.2131, pruned_loss=0.04191, over 4779.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04349, over 971224.91 frames.], batch size: 14, lr: 4.53e-04
2022-05-04 22:16:32,479 INFO [train.py:715] (5/8) Epoch 4, batch 15450, loss[loss=0.1404, simple_loss=0.2079, pruned_loss=0.03647, over 4853.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2277, pruned_loss=0.04478, over 971789.61 frames.], batch size: 34, lr: 4.53e-04
2022-05-04 22:17:12,934 INFO [train.py:715] (5/8) Epoch 4, batch 15500, loss[loss=0.1766, simple_loss=0.2471, pruned_loss=0.05306, over 4770.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2287, pruned_loss=0.04543, over 971498.01 frames.], batch size: 17, lr: 4.53e-04
2022-05-04 22:17:53,285 INFO [train.py:715] (5/8) Epoch 4, batch 15550, loss[loss=0.1835, simple_loss=0.2468, pruned_loss=0.06015, over 4915.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.04461, over 971722.30 frames.], batch size: 17, lr: 4.53e-04
2022-05-04 22:18:32,668 INFO [train.py:715] (5/8) Epoch 4, batch 15600, loss[loss=0.2019, simple_loss=0.2495, pruned_loss=0.07717, over 4739.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2277, pruned_loss=0.0447, over 972290.83 frames.], batch size: 16, lr: 4.53e-04
2022-05-04 22:19:13,498 INFO [train.py:715] (5/8) Epoch 4, batch 15650, loss[loss=0.1464, simple_loss=0.2101, pruned_loss=0.04137, over 4847.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04438, over 972674.32 frames.], batch size: 32, lr: 4.53e-04
2022-05-04 22:19:53,087 INFO [train.py:715] (5/8) Epoch 4, batch 15700, loss[loss=0.1708, simple_loss=0.2465, pruned_loss=0.04759, over 4745.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04417, over 972090.91 frames.], batch size: 16, lr: 4.53e-04
2022-05-04 22:20:33,263 INFO [train.py:715] (5/8) Epoch 4, batch 15750, loss[loss=0.2051, simple_loss=0.2551, pruned_loss=0.07761, over 4912.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04403, over 971669.11 frames.], batch size: 17, lr: 4.53e-04
2022-05-04 22:21:12,809 INFO [train.py:715] (5/8) Epoch 4, batch 15800, loss[loss=0.1502, simple_loss=0.2281, pruned_loss=0.03616, over 4883.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2271, pruned_loss=0.04414, over 971516.99 frames.], batch size: 16, lr: 4.53e-04
2022-05-04 22:21:53,779 INFO [train.py:715] (5/8) Epoch 4, batch 15850, loss[loss=0.144, simple_loss=0.2066, pruned_loss=0.04065, over 4852.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2268, pruned_loss=0.04415, over 971576.61 frames.], batch size: 20, lr: 4.53e-04
2022-05-04 22:22:34,971 INFO [train.py:715] (5/8) Epoch 4, batch 15900, loss[loss=0.1417, simple_loss=0.2126, pruned_loss=0.03534, over 4902.00 frames.], tot_loss[loss=0.1574, simple_loss=0.227, pruned_loss=0.04392, over 971966.48 frames.], batch size: 19, lr: 4.53e-04
2022-05-04 22:23:14,300 INFO [train.py:715] (5/8) Epoch 4, batch 15950, loss[loss=0.1566, simple_loss=0.2107, pruned_loss=0.05125, over 4855.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04339, over 971270.50 frames.], batch size: 32, lr: 4.53e-04
2022-05-04 22:23:54,444 INFO [train.py:715] (5/8) Epoch 4, batch 16000, loss[loss=0.159, simple_loss=0.2342, pruned_loss=0.04187, over 4906.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2248, pruned_loss=0.0428, over 970863.76 frames.], batch size: 17, lr: 4.53e-04
2022-05-04 22:24:34,929 INFO [train.py:715] (5/8) Epoch 4, batch 16050, loss[loss=0.1897, simple_loss=0.2646, pruned_loss=0.05737, over 4799.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2253, pruned_loss=0.04324, over 970796.28 frames.], batch size: 25, lr: 4.53e-04
2022-05-04 22:25:14,774 INFO [train.py:715] (5/8) Epoch 4, batch 16100, loss[loss=0.1843, simple_loss=0.2508, pruned_loss=0.05893, over 4708.00 frames.], tot_loss[loss=0.157, simple_loss=0.2262, pruned_loss=0.04396, over 970274.51 frames.], batch size: 15, lr: 4.52e-04
2022-05-04 22:25:54,144 INFO [train.py:715] (5/8) Epoch 4, batch 16150, loss[loss=0.1896, simple_loss=0.2472, pruned_loss=0.06603, over 4843.00 frames.], tot_loss[loss=0.157, simple_loss=0.226, pruned_loss=0.04401, over 971299.40 frames.], batch size: 15, lr: 4.52e-04
2022-05-04 22:26:34,758 INFO [train.py:715] (5/8) Epoch 4, batch 16200, loss[loss=0.135, simple_loss=0.2028, pruned_loss=0.0336, over 4875.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2264, pruned_loss=0.044, over 971405.40 frames.], batch size: 22, lr: 4.52e-04
2022-05-04 22:27:15,075 INFO [train.py:715] (5/8) Epoch 4, batch 16250, loss[loss=0.1268, simple_loss=0.1997, pruned_loss=0.02699, over 4819.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04396, over 971786.73 frames.], batch size: 15, lr: 4.52e-04
2022-05-04 22:27:54,411 INFO [train.py:715] (5/8) Epoch 4, batch 16300, loss[loss=0.1806, simple_loss=0.2443, pruned_loss=0.0584, over 4928.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04412, over 972835.64 frames.], batch size: 39, lr: 4.52e-04
2022-05-04 22:28:34,989 INFO [train.py:715] (5/8) Epoch 4, batch 16350, loss[loss=0.1473, simple_loss=0.2278, pruned_loss=0.03343, over 4922.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04375, over 972237.92 frames.], batch size: 18, lr: 4.52e-04
2022-05-04 22:29:15,663 INFO [train.py:715] (5/8) Epoch 4, batch 16400, loss[loss=0.1549, simple_loss=0.2223, pruned_loss=0.04374, over 4785.00 frames.], tot_loss[loss=0.158, simple_loss=0.2274, pruned_loss=0.0443, over 971988.79 frames.], batch size: 17, lr: 4.52e-04
2022-05-04 22:29:56,020 INFO [train.py:715] (5/8) Epoch 4, batch 16450, loss[loss=0.1542, simple_loss=0.2208, pruned_loss=0.0438, over 4779.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04417, over 971862.21 frames.], batch size: 17, lr: 4.52e-04
2022-05-04 22:30:35,456 INFO [train.py:715] (5/8) Epoch 4, batch 16500, loss[loss=0.1487, simple_loss=0.2089, pruned_loss=0.04421, over 4751.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2263, pruned_loss=0.04381, over 972085.29 frames.], batch size: 16, lr: 4.52e-04
2022-05-04 22:31:15,347 INFO [train.py:715] (5/8) Epoch 4, batch 16550, loss[loss=0.1513, simple_loss=0.2204, pruned_loss=0.04106, over 4857.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04332, over 972248.93 frames.], batch size: 34, lr: 4.52e-04
2022-05-04 22:31:55,173 INFO [train.py:715] (5/8) Epoch 4, batch 16600, loss[loss=0.1683, simple_loss=0.2325, pruned_loss=0.05209, over 4908.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2263, pruned_loss=0.0441, over 971727.64 frames.], batch size: 18, lr: 4.52e-04
2022-05-04 22:32:33,991 INFO [train.py:715] (5/8) Epoch 4, batch 16650, loss[loss=0.1794, simple_loss=0.2575, pruned_loss=0.05067, over 4843.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2263, pruned_loss=0.044, over 971683.08 frames.], batch size: 20, lr: 4.52e-04
2022-05-04 22:33:12,851 INFO [train.py:715] (5/8) Epoch 4, batch 16700, loss[loss=0.1623, simple_loss=0.2456, pruned_loss=0.03951, over 4699.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2261, pruned_loss=0.04361, over 971215.38 frames.], batch size: 15, lr: 4.52e-04
2022-05-04 22:33:52,194 INFO [train.py:715] (5/8) Epoch 4, batch 16750, loss[loss=0.156, simple_loss=0.2387, pruned_loss=0.03663, over 4841.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2258, pruned_loss=0.04371, over 972185.89 frames.], batch size: 20, lr: 4.52e-04
2022-05-04 22:34:31,637 INFO [train.py:715] (5/8) Epoch 4, batch 16800, loss[loss=0.1385, simple_loss=0.218, pruned_loss=0.02948, over 4943.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2259, pruned_loss=0.04367, over 972844.95 frames.], batch size: 29, lr: 4.51e-04
2022-05-04 22:35:10,399 INFO [train.py:715] (5/8) Epoch 4, batch 16850, loss[loss=0.1571, simple_loss=0.2205, pruned_loss=0.04687, over 4831.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2257, pruned_loss=0.0436, over 972704.16 frames.], batch size: 13, lr: 4.51e-04
2022-05-04 22:35:50,737 INFO [train.py:715] (5/8) Epoch 4, batch 16900, loss[loss=0.1263, simple_loss=0.2066, pruned_loss=0.023, over 4757.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04315, over 973104.02 frames.], batch size: 19, lr: 4.51e-04
2022-05-04 22:36:31,087 INFO [train.py:715] (5/8) Epoch 4, batch 16950, loss[loss=0.1567, simple_loss=0.2241, pruned_loss=0.04459, over 4980.00 frames.], tot_loss[loss=0.156, simple_loss=0.2259, pruned_loss=0.04308, over 973038.43 frames.], batch size: 24, lr: 4.51e-04
2022-05-04 22:37:10,624 INFO [train.py:715] (5/8) Epoch 4, batch 17000, loss[loss=0.1834, simple_loss=0.2527, pruned_loss=0.05705, over 4747.00 frames.], tot_loss[loss=0.156, simple_loss=0.2261, pruned_loss=0.0429, over 973285.84 frames.], batch size: 16, lr: 4.51e-04
2022-05-04 22:37:50,453 INFO [train.py:715] (5/8) Epoch 4, batch 17050, loss[loss=0.154, simple_loss=0.2241, pruned_loss=0.04201, over 4821.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2251, pruned_loss=0.04253, over 973795.82 frames.], batch size: 26, lr: 4.51e-04
2022-05-04 22:38:30,859 INFO [train.py:715] (5/8) Epoch 4, batch 17100, loss[loss=0.1371, simple_loss=0.2141, pruned_loss=0.0301, over 4741.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.0426, over 974084.21 frames.], batch size: 16, lr: 4.51e-04
2022-05-04 22:39:10,969 INFO [train.py:715] (5/8) Epoch 4, batch 17150, loss[loss=0.1417, simple_loss=0.218, pruned_loss=0.03274, over 4981.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04336, over 972877.53 frames.], batch size: 25, lr: 4.51e-04
2022-05-04 22:39:50,102 INFO [train.py:715] (5/8) Epoch 4, batch 17200, loss[loss=0.1438, simple_loss=0.2089, pruned_loss=0.03932, over 4932.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04375, over 972818.04 frames.], batch size: 18, lr: 4.51e-04
2022-05-04 22:40:30,247 INFO [train.py:715] (5/8) Epoch 4, batch 17250, loss[loss=0.1585, simple_loss=0.2245, pruned_loss=0.04623, over 4959.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04389, over 973113.77 frames.], batch size: 24, lr: 4.51e-04
2022-05-04 22:41:10,198 INFO [train.py:715] (5/8) Epoch 4, batch 17300, loss[loss=0.1806, simple_loss=0.2478, pruned_loss=0.05664, over 4905.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2272, pruned_loss=0.04417, over 972612.96 frames.], batch size: 17, lr: 4.51e-04
2022-05-04 22:41:49,929 INFO [train.py:715] (5/8) Epoch 4, batch 17350, loss[loss=0.1455, simple_loss=0.2197, pruned_loss=0.03566, over 4964.00 frames.], tot_loss[loss=0.1575, simple_loss=0.227, pruned_loss=0.04398, over 971807.35 frames.], batch size: 24, lr: 4.51e-04
2022-05-04 22:42:29,446 INFO [train.py:715] (5/8) Epoch 4, batch 17400, loss[loss=0.1552, simple_loss=0.2292, pruned_loss=0.04061, over 4901.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2269, pruned_loss=0.04363, over 972162.16 frames.], batch size: 17, lr: 4.51e-04
2022-05-04 22:43:09,755 INFO [train.py:715] (5/8) Epoch 4, batch 17450, loss[loss=0.1468, simple_loss=0.2155, pruned_loss=0.03904, over 4973.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.044, over 971460.34 frames.], batch size: 15, lr: 4.51e-04
2022-05-04 22:43:50,029 INFO [train.py:715] (5/8) Epoch 4, batch 17500, loss[loss=0.1519, simple_loss=0.2359, pruned_loss=0.03392, over 4888.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2287, pruned_loss=0.0446, over 971600.74 frames.], batch size: 22, lr: 4.50e-04
2022-05-04 22:44:29,247 INFO [train.py:715] (5/8) Epoch 4, batch 17550, loss[loss=0.1569, simple_loss=0.2156, pruned_loss=0.04915, over 4840.00 frames.], tot_loss[loss=0.1581, simple_loss=0.228, pruned_loss=0.04412, over 970617.81 frames.], batch size: 15, lr: 4.50e-04
2022-05-04 22:45:09,114 INFO [train.py:715] (5/8) Epoch 4, batch 17600, loss[loss=0.1232, simple_loss=0.1923, pruned_loss=0.02706, over 4967.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2267, pruned_loss=0.04347, over 971470.86 frames.], batch size: 24, lr: 4.50e-04
2022-05-04 22:45:49,512 INFO [train.py:715] (5/8) Epoch 4, batch 17650, loss[loss=0.199, simple_loss=0.26, pruned_loss=0.06906, over 4953.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2263, pruned_loss=0.04338, over 971114.86 frames.], batch size: 35, lr: 4.50e-04
2022-05-04 22:46:29,571 INFO [train.py:715] (5/8) Epoch 4, batch 17700, loss[loss=0.1634, simple_loss=0.2274, pruned_loss=0.04971, over 4942.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04362, over 971373.56 frames.], batch size: 29, lr: 4.50e-04
2022-05-04 22:47:09,161 INFO [train.py:715] (5/8) Epoch 4, batch 17750, loss[loss=0.1409, simple_loss=0.2211, pruned_loss=0.03036, over 4975.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.0433, over 971350.28 frames.], batch size: 28, lr: 4.50e-04
2022-05-04 22:47:49,259 INFO [train.py:715] (5/8) Epoch 4, batch 17800, loss[loss=0.1586, simple_loss=0.2206, pruned_loss=0.04835, over 4700.00 frames.], tot_loss[loss=0.157, simple_loss=0.2267, pruned_loss=0.04363, over 972120.86 frames.], batch size: 15, lr: 4.50e-04
2022-05-04 22:48:29,927 INFO [train.py:715] (5/8) Epoch 4, batch 17850, loss[loss=0.1523, simple_loss=0.2295, pruned_loss=0.03756, over 4771.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04344, over 971609.04 frames.], batch size: 19, lr: 4.50e-04
2022-05-04 22:49:09,030 INFO [train.py:715] (5/8) Epoch 4, batch 17900, loss[loss=0.1354, simple_loss=0.2158, pruned_loss=0.02753, over 4941.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.04384, over 971812.92 frames.], batch size: 23, lr: 4.50e-04
2022-05-04 22:49:49,024 INFO [train.py:715] (5/8) Epoch 4, batch 17950, loss[loss=0.196, simple_loss=0.2525, pruned_loss=0.06975, over 4920.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04359, over 971700.73 frames.], batch size: 18, lr: 4.50e-04
2022-05-04 22:50:29,184 INFO [train.py:715] (5/8) Epoch 4, batch 18000, loss[loss=0.1779, simple_loss=0.2554, pruned_loss=0.05019, over 4942.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2282, pruned_loss=0.04464, over 971761.12 frames.], batch size: 39, lr: 4.50e-04
2022-05-04 22:50:29,184 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 22:50:38,823 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1119, simple_loss=0.1976, pruned_loss=0.01313, over 914524.00 frames.
2022-05-04 22:51:19,285 INFO [train.py:715] (5/8) Epoch 4, batch 18050, loss[loss=0.1802, simple_loss=0.2585, pruned_loss=0.051, over 4820.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2284, pruned_loss=0.04512, over 971118.79 frames.], batch size: 15, lr: 4.50e-04
2022-05-04 22:51:59,526 INFO [train.py:715] (5/8) Epoch 4, batch 18100, loss[loss=0.1596, simple_loss=0.2209, pruned_loss=0.04921, over 4861.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2275, pruned_loss=0.04503, over 971440.46 frames.], batch size: 32, lr: 4.50e-04
2022-05-04 22:52:39,097 INFO [train.py:715] (5/8) Epoch 4, batch 18150, loss[loss=0.1603, simple_loss=0.2199, pruned_loss=0.05038, over 4860.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2272, pruned_loss=0.04476, over 972222.36 frames.], batch size: 30, lr: 4.50e-04
2022-05-04 22:53:19,406 INFO [train.py:715] (5/8) Epoch 4, batch 18200, loss[loss=0.1551, simple_loss=0.2281, pruned_loss=0.04111, over 4863.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2273, pruned_loss=0.04462, over 972486.56 frames.], batch size: 16, lr: 4.49e-04
2022-05-04 22:53:59,870 INFO [train.py:715] (5/8) Epoch 4, batch 18250, loss[loss=0.165, simple_loss=0.2127, pruned_loss=0.05864, over 4991.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2267, pruned_loss=0.04405, over 971879.65 frames.], batch size: 14, lr: 4.49e-04
2022-05-04 22:54:39,570 INFO [train.py:715] (5/8) Epoch 4, batch 18300, loss[loss=0.1689, simple_loss=0.2305, pruned_loss=0.05372, over 4957.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04398, over 971171.10 frames.], batch size: 35, lr: 4.49e-04
2022-05-04 22:55:19,280 INFO [train.py:715] (5/8) Epoch 4, batch 18350, loss[loss=0.182, simple_loss=0.2619, pruned_loss=0.05107, over 4850.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04379, over 970466.46 frames.], batch size: 20, lr: 4.49e-04
2022-05-04 22:56:00,394 INFO [train.py:715] (5/8) Epoch 4, batch 18400, loss[loss=0.1436, simple_loss=0.2146, pruned_loss=0.03634, over 4984.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2274, pruned_loss=0.04468, over 970614.55 frames.], batch size: 16, lr: 4.49e-04
2022-05-04 22:56:40,808 INFO [train.py:715] (5/8) Epoch 4, batch 18450, loss[loss=0.1548, simple_loss=0.2235, pruned_loss=0.04306, over 4937.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2273, pruned_loss=0.04459, over 971369.77 frames.], batch size: 29, lr: 4.49e-04
2022-05-04 22:57:20,898 INFO [train.py:715] (5/8) Epoch 4, batch 18500, loss[loss=0.1464, simple_loss=0.2225, pruned_loss=0.03517, over 4871.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.04435, over 972220.54 frames.], batch size: 20, lr: 4.49e-04
2022-05-04 22:58:01,188 INFO [train.py:715] (5/8) Epoch 4, batch 18550, loss[loss=0.1595, simple_loss=0.2313, pruned_loss=0.04381, over 4781.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.0443, over 971874.08 frames.], batch size: 17, lr: 4.49e-04
2022-05-04 22:58:41,896 INFO [train.py:715] (5/8) Epoch 4, batch 18600, loss[loss=0.1212, simple_loss=0.1917, pruned_loss=0.0254, over 4822.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2266, pruned_loss=0.04362, over 971646.78 frames.], batch size: 12, lr: 4.49e-04
2022-05-04 22:59:21,458 INFO [train.py:715] (5/8) Epoch 4, batch 18650, loss[loss=0.1369, simple_loss=0.2028, pruned_loss=0.03548, over 4833.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04298, over 972247.15 frames.], batch size: 30, lr: 4.49e-04
2022-05-04 23:00:01,607 INFO [train.py:715] (5/8) Epoch 4, batch 18700, loss[loss=0.1925, simple_loss=0.2547, pruned_loss=0.06516, over 4897.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04308, over 971835.53 frames.], batch size: 17, lr: 4.49e-04
2022-05-04 23:00:42,465 INFO [train.py:715] (5/8) Epoch 4, batch 18750, loss[loss=0.1359, simple_loss=0.2082, pruned_loss=0.03178, over 4703.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04266, over 971156.60 frames.], batch size: 15, lr: 4.49e-04
2022-05-04 23:01:21,943 INFO [train.py:715] (5/8) Epoch 4, batch 18800, loss[loss=0.1685, simple_loss=0.2349, pruned_loss=0.05111, over 4935.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04295, over 970628.52 frames.], batch size: 23, lr: 4.49e-04
2022-05-04 23:02:02,023 INFO [train.py:715] (5/8) Epoch 4, batch 18850, loss[loss=0.1362, simple_loss=0.2112, pruned_loss=0.03063, over 4859.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04335, over 970577.56 frames.], batch size: 20, lr: 4.49e-04
2022-05-04 23:02:42,435 INFO [train.py:715] (5/8) Epoch 4, batch 18900, loss[loss=0.1712, simple_loss=0.2345, pruned_loss=0.05397, over 4860.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2266, pruned_loss=0.04314, over 970990.91 frames.], batch size: 32, lr: 4.48e-04
2022-05-04 23:03:22,748 INFO [train.py:715] (5/8) Epoch 4, batch 18950, loss[loss=0.1892, simple_loss=0.249, pruned_loss=0.06464, over 4912.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2272, pruned_loss=0.04351, over 970847.40 frames.], batch size: 18, lr: 4.48e-04
2022-05-04 23:04:01,994 INFO [train.py:715] (5/8) Epoch 4, batch 19000, loss[loss=0.1514, simple_loss=0.2279, pruned_loss=0.03743, over 4784.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2265, pruned_loss=0.04326, over 970813.93 frames.], batch size: 17, lr: 4.48e-04
2022-05-04 23:04:42,500 INFO [train.py:715] (5/8) Epoch 4, batch 19050, loss[loss=0.1718, simple_loss=0.2458, pruned_loss=0.04887, over 4945.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04329, over 970601.36 frames.], batch size: 29, lr: 4.48e-04
2022-05-04 23:05:23,219 INFO [train.py:715] (5/8) Epoch 4, batch 19100, loss[loss=0.1547, simple_loss=0.2285, pruned_loss=0.04041, over 4976.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2275, pruned_loss=0.0439, over 971190.44 frames.], batch size: 35, lr: 4.48e-04
2022-05-04 23:06:03,172 INFO [train.py:715] (5/8) Epoch 4, batch 19150, loss[loss=0.1533, simple_loss=0.2246, pruned_loss=0.04099, over 4952.00 frames.], tot_loss[loss=0.157, simple_loss=0.2269, pruned_loss=0.04358, over 972028.94 frames.], batch size: 29, lr: 4.48e-04
2022-05-04 23:06:43,532 INFO [train.py:715] (5/8) Epoch 4, batch 19200, loss[loss=0.1677, simple_loss=0.2333, pruned_loss=0.0511, over 4940.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04323, over 971378.07 frames.], batch size: 39, lr: 4.48e-04
2022-05-04 23:07:24,310 INFO [train.py:715] (5/8) Epoch 4, batch 19250, loss[loss=0.146, simple_loss=0.2163, pruned_loss=0.03785, over 4860.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04256, over 971538.96 frames.], batch size: 13, lr: 4.48e-04
2022-05-04 23:08:04,908 INFO [train.py:715] (5/8) Epoch 4, batch 19300, loss[loss=0.1224, simple_loss=0.1831, pruned_loss=0.03084, over 4841.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04281, over 971830.64 frames.], batch size: 13, lr: 4.48e-04
2022-05-04 23:08:44,083 INFO [train.py:715] (5/8) Epoch 4, batch 19350, loss[loss=0.146, simple_loss=0.21, pruned_loss=0.041, over 4930.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2254, pruned_loss=0.04255, over 973250.13 frames.], batch size: 23, lr: 4.48e-04
2022-05-04 23:09:24,773 INFO [train.py:715] (5/8) Epoch 4, batch 19400, loss[loss=0.1927, simple_loss=0.257, pruned_loss=0.06425, over 4903.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04195, over 972704.61 frames.], batch size: 17, lr: 4.48e-04
2022-05-04 23:10:06,275 INFO [train.py:715] (5/8) Epoch 4, batch 19450, loss[loss=0.1642, simple_loss=0.2304, pruned_loss=0.04899, over 4777.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2239, pruned_loss=0.04228, over 973405.86 frames.], batch size: 18, lr: 4.48e-04
2022-05-04 23:10:47,438 INFO [train.py:715] (5/8) Epoch 4, batch 19500, loss[loss=0.1511, simple_loss=0.229, pruned_loss=0.03659, over 4882.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2249, pruned_loss=0.04245, over 973453.59 frames.], batch size: 20, lr: 4.48e-04
2022-05-04 23:11:27,087 INFO [train.py:715] (5/8) Epoch 4, batch 19550, loss[loss=0.1494, simple_loss=0.2172, pruned_loss=0.04078, over 4860.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04265, over 972548.99 frames.], batch size: 20, lr: 4.48e-04
2022-05-04 23:12:07,480 INFO [train.py:715] (5/8) Epoch 4, batch 19600, loss[loss=0.1714, simple_loss=0.2351, pruned_loss=0.05388, over 4964.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04305, over 972368.87 frames.], batch size: 35, lr: 4.47e-04
2022-05-04 23:12:47,699 INFO [train.py:715] (5/8) Epoch 4, batch 19650, loss[loss=0.1535, simple_loss=0.229, pruned_loss=0.039, over 4910.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2267, pruned_loss=0.0433, over 972501.44 frames.], batch size: 17, lr: 4.47e-04
2022-05-04 23:13:26,467 INFO [train.py:715] (5/8) Epoch 4, batch 19700, loss[loss=0.161, simple_loss=0.23, pruned_loss=0.04599, over 4956.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2276, pruned_loss=0.04394, over 971837.20 frames.], batch size: 14, lr: 4.47e-04
2022-05-04 23:14:07,146 INFO [train.py:715] (5/8) Epoch 4, batch 19750, loss[loss=0.2302, simple_loss=0.2761, pruned_loss=0.09212, over 4904.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2281, pruned_loss=0.0442, over 972205.48 frames.], batch size: 17, lr: 4.47e-04
2022-05-04 23:14:47,981 INFO [train.py:715] (5/8) Epoch 4, batch 19800, loss[loss=0.1735, simple_loss=0.248, pruned_loss=0.04945, over 4776.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2282, pruned_loss=0.04419, over 972215.86 frames.], batch size: 17, lr: 4.47e-04
2022-05-04 23:15:27,713 INFO [train.py:715] (5/8) Epoch 4, batch 19850, loss[loss=0.1673, simple_loss=0.2348, pruned_loss=0.04991, over 4869.00 frames.], tot_loss[loss=0.157, simple_loss=0.2269, pruned_loss=0.04359, over 972165.69 frames.], batch size: 16, lr: 4.47e-04
2022-05-04 23:16:07,785 INFO [train.py:715] (5/8) Epoch 4, batch 19900, loss[loss=0.1554, simple_loss=0.2279, pruned_loss=0.04143, over 4756.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2269, pruned_loss=0.04312, over 971981.82 frames.], batch size: 19, lr: 4.47e-04
2022-05-04 23:16:47,902 INFO [train.py:715] (5/8) Epoch 4, batch 19950, loss[loss=0.1788, simple_loss=0.2529, pruned_loss=0.05229, over 4780.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2269, pruned_loss=0.04328, over 971629.09 frames.], batch size: 18, lr: 4.47e-04
2022-05-04 23:17:28,070 INFO [train.py:715] (5/8) Epoch 4, batch 20000, loss[loss=0.1535, simple_loss=0.2202, pruned_loss=0.04346, over 4899.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.04323, over 971234.70 frames.], batch size: 19, lr: 4.47e-04
2022-05-04 23:18:06,770 INFO [train.py:715] (5/8) Epoch 4, batch 20050, loss[loss=0.1884, simple_loss=0.2453, pruned_loss=0.06574, over 4763.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04331, over 971726.64 frames.], batch size: 12, lr: 4.47e-04
2022-05-04 23:18:46,563 INFO [train.py:715] (5/8) Epoch 4, batch 20100, loss[loss=0.2585, simple_loss=0.309, pruned_loss=0.104, over 4704.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2271, pruned_loss=0.04395, over 971582.93 frames.], batch size: 15, lr: 4.47e-04
2022-05-04 23:19:26,629 INFO [train.py:715] (5/8) Epoch 4, batch 20150, loss[loss=0.1528, simple_loss=0.2248, pruned_loss=0.04041, over 4912.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04379, over 972308.02 frames.], batch size: 19, lr: 4.47e-04
2022-05-04 23:20:06,050 INFO [train.py:715] (5/8) Epoch 4, batch 20200, loss[loss=0.1562, simple_loss=0.2297, pruned_loss=0.04135, over 4757.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04358, over 972305.85 frames.], batch size: 19, lr: 4.47e-04
2022-05-04 23:20:45,795 INFO [train.py:715] (5/8) Epoch 4, batch 20250, loss[loss=0.1548, simple_loss=0.2226, pruned_loss=0.04349, over 4950.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04363, over 972401.72 frames.], batch size: 35, lr: 4.47e-04
2022-05-04 23:21:26,113 INFO [train.py:715] (5/8) Epoch 4, batch 20300, loss[loss=0.1384, simple_loss=0.2131, pruned_loss=0.03188, over 4822.00 frames.], tot_loss[loss=0.158, simple_loss=0.2273, pruned_loss=0.04442, over 973137.60 frames.], batch size: 27, lr: 4.46e-04
2022-05-04 23:22:06,211 INFO [train.py:715] (5/8) Epoch 4, batch 20350, loss[loss=0.1175, simple_loss=0.1876, pruned_loss=0.02375, over 4797.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2277, pruned_loss=0.04481, over 972429.55 frames.], batch size: 12, lr: 4.46e-04
2022-05-04 23:22:45,051 INFO [train.py:715] (5/8) Epoch 4, batch 20400, loss[loss=0.1688, simple_loss=0.2342, pruned_loss=0.05173, over 4783.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2264, pruned_loss=0.04399, over 972009.78 frames.], batch size: 18, lr: 4.46e-04
2022-05-04 23:23:25,036 INFO [train.py:715] (5/8) Epoch 4, batch 20450, loss[loss=0.149, simple_loss=0.2172, pruned_loss=0.04036, over 4786.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.0447, over 971258.89 frames.], batch size: 18, lr: 4.46e-04
2022-05-04 23:24:04,958 INFO [train.py:715] (5/8) Epoch 4, batch 20500, loss[loss=0.1396, simple_loss=0.2173, pruned_loss=0.03098, over 4836.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2274, pruned_loss=0.04476, over 971540.28 frames.], batch size: 26, lr: 4.46e-04
2022-05-04 23:24:44,751 INFO [train.py:715] (5/8) Epoch 4, batch 20550, loss[loss=0.1409, simple_loss=0.1985, pruned_loss=0.04165, over 4979.00 frames.], tot_loss[loss=0.1582, simple_loss=0.227, pruned_loss=0.04467, over 971763.02 frames.], batch size: 25, lr: 4.46e-04
2022-05-04 23:25:23,721 INFO [train.py:715] (5/8) Epoch 4, batch 20600, loss[loss=0.1805, simple_loss=0.2461, pruned_loss=0.05746, over 4866.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2271, pruned_loss=0.04456, over 970832.66 frames.], batch size: 20, lr: 4.46e-04
2022-05-04 23:26:03,657 INFO [train.py:715] (5/8) Epoch 4, batch 20650, loss[loss=0.1455, simple_loss=0.2133, pruned_loss=0.03883, over 4697.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2265, pruned_loss=0.0446, over 971103.87 frames.], batch size: 15, lr: 4.46e-04
2022-05-04 23:26:44,171 INFO [train.py:715] (5/8) Epoch 4, batch 20700, loss[loss=0.1563, simple_loss=0.2301, pruned_loss=0.04131, over 4915.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2265, pruned_loss=0.04432, over 971510.45 frames.], batch size: 17, lr: 4.46e-04
2022-05-04 23:27:22,804 INFO [train.py:715] (5/8) Epoch 4, batch 20750, loss[loss=0.1619, simple_loss=0.2196, pruned_loss=0.05212, over 4815.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2267, pruned_loss=0.04445, over 971923.01 frames.], batch size: 14, lr: 4.46e-04
2022-05-04 23:28:04,816 INFO [train.py:715] (5/8) Epoch 4, batch 20800, loss[loss=0.1364, simple_loss=0.2045, pruned_loss=0.0341, over 4797.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04388, over 972317.56 frames.], batch size: 25, lr: 4.46e-04
2022-05-04 23:28:44,599 INFO [train.py:715] (5/8) Epoch 4, batch 20850, loss[loss=0.1436, simple_loss=0.2142, pruned_loss=0.03646, over 4926.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2256, pruned_loss=0.04355, over 972466.56 frames.], batch size: 29, lr: 4.46e-04
2022-05-04 23:29:24,438 INFO [train.py:715] (5/8) Epoch 4, batch 20900, loss[loss=0.1468, simple_loss=0.2191, pruned_loss=0.03726, over 4909.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04357, over 972726.64 frames.], batch size: 17, lr: 4.46e-04
2022-05-04 23:30:03,474 INFO [train.py:715] (5/8) Epoch 4, batch 20950, loss[loss=0.1317, simple_loss=0.203, pruned_loss=0.03019, over 4903.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04352, over 973296.27 frames.], batch size: 19, lr: 4.46e-04
2022-05-04 23:30:43,448 INFO [train.py:715] (5/8) Epoch 4, batch 21000, loss[loss=0.1415, simple_loss=0.2184, pruned_loss=0.03228, over 4976.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2267, pruned_loss=0.04326, over 972666.83 frames.], batch size: 25, lr: 4.46e-04
2022-05-04 23:30:43,448 INFO [train.py:733] (5/8) Computing validation loss
2022-05-04 23:30:52,894 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1116, simple_loss=0.1973, pruned_loss=0.01293, over 914524.00 frames.
2022-05-04 23:31:33,187 INFO [train.py:715] (5/8) Epoch 4, batch 21050, loss[loss=0.2011, simple_loss=0.261, pruned_loss=0.07059, over 4705.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04315, over 972450.80 frames.], batch size: 15, lr: 4.45e-04
2022-05-04 23:32:12,984 INFO [train.py:715] (5/8) Epoch 4, batch 21100, loss[loss=0.1715, simple_loss=0.2442, pruned_loss=0.04937, over 4845.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.04385, over 973275.66 frames.], batch size: 20, lr: 4.45e-04
2022-05-04 23:32:52,578 INFO [train.py:715] (5/8) Epoch 4, batch 21150, loss[loss=0.1855, simple_loss=0.238, pruned_loss=0.06649, over 4885.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2261, pruned_loss=0.04373, over 972546.32 frames.], batch size: 16, lr: 4.45e-04
2022-05-04 23:33:32,146 INFO [train.py:715] (5/8) Epoch 4, batch 21200, loss[loss=0.1478, simple_loss=0.2149, pruned_loss=0.04029, over 4908.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04332, over 972344.33 frames.], batch size: 17, lr: 4.45e-04
2022-05-04 23:34:12,365 INFO [train.py:715] (5/8) Epoch 4, batch 21250, loss[loss=0.1722, simple_loss=0.2415, pruned_loss=0.05147, over 4917.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04322, over 971647.97 frames.], batch size: 23, lr: 4.45e-04
2022-05-04 23:34:51,184 INFO [train.py:715] (5/8) Epoch 4, batch 21300, loss[loss=0.1755, simple_loss=0.2416, pruned_loss=0.0547, over 4865.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04362, over 971000.52 frames.], batch size: 32, lr: 4.45e-04
2022-05-04 23:35:30,241 INFO [train.py:715] (5/8) Epoch 4, batch 21350, loss[loss=0.1478, simple_loss=0.2195, pruned_loss=0.03808, over 4968.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.04356, over 971764.37 frames.], batch size: 24, lr: 4.45e-04
2022-05-04 23:36:09,892 INFO [train.py:715] (5/8) Epoch 4, batch 21400, loss[loss=0.1744, simple_loss=0.2351, pruned_loss=0.05687, over 4638.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04336, over 971339.63 frames.], batch size: 13, lr: 4.45e-04
2022-05-04 23:36:49,453 INFO [train.py:715] (5/8) Epoch 4, batch 21450, loss[loss=0.177, simple_loss=0.255, pruned_loss=0.04948, over 4816.00 frames.], tot_loss[loss=0.1577, simple_loss=0.227, pruned_loss=0.04417, over 971721.83 frames.], batch size: 21, lr: 4.45e-04
2022-05-04 23:37:28,645 INFO [train.py:715] (5/8) Epoch 4, batch 21500, loss[loss=0.141, simple_loss=0.2202, pruned_loss=0.03092, over 4978.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04373, over 971831.33 frames.], batch size: 24, lr: 4.45e-04
2022-05-04 23:38:08,472 INFO [train.py:715] (5/8) Epoch 4, batch 21550, loss[loss=0.1697, simple_loss=0.2477, pruned_loss=0.04584, over 4941.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2257, pruned_loss=0.04351, over 972069.57 frames.], batch size: 23, lr: 4.45e-04
2022-05-04 23:38:48,847 INFO [train.py:715] (5/8) Epoch 4, batch 21600, loss[loss=0.1442, simple_loss=0.2145, pruned_loss=0.03696, over 4872.00 frames.], tot_loss[loss=0.1555, simple_loss=0.225, pruned_loss=0.04304, over 971985.25 frames.], batch size: 32, lr: 4.45e-04
2022-05-04 23:39:28,097 INFO [train.py:715] (5/8) Epoch 4, batch 21650, loss[loss=0.2014, simple_loss=0.2767, pruned_loss=0.0631, over 4851.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2252, pruned_loss=0.04325, over 972314.65 frames.], batch size: 20, lr: 4.45e-04
2022-05-04 23:40:08,350 INFO [train.py:715] (5/8) Epoch 4, batch 21700, loss[loss=0.2013, simple_loss=0.2612, pruned_loss=0.07067, over 4704.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04343, over 971260.37 frames.], batch size: 15, lr: 4.45e-04
2022-05-04 23:40:49,361 INFO [train.py:715] (5/8) Epoch 4, batch 21750, loss[loss=0.1664, simple_loss=0.236, pruned_loss=0.04839, over 4646.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.0431, over 971178.61 frames.], batch size: 13, lr: 4.44e-04
2022-05-04 23:41:29,015 INFO [train.py:715] (5/8) Epoch 4, batch 21800, loss[loss=0.1712, simple_loss=0.2412, pruned_loss=0.05057, over 4968.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04311, over 971366.16 frames.], batch size: 35, lr: 4.44e-04
2022-05-04 23:42:08,602 INFO [train.py:715] (5/8) Epoch 4, batch 21850, loss[loss=0.1658, simple_loss=0.2389, pruned_loss=0.04641, over 4865.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04307, over 971957.01 frames.], batch size: 20, lr: 4.44e-04
2022-05-04 23:42:48,650 INFO [train.py:715] (5/8) Epoch 4, batch 21900, loss[loss=0.1832, simple_loss=0.2511, pruned_loss=0.05765, over 4939.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04406, over 972184.41 frames.], batch size: 23, lr: 4.44e-04
2022-05-04 23:43:29,090 INFO [train.py:715] (5/8) Epoch 4, batch 21950, loss[loss=0.1556, simple_loss=0.2196, pruned_loss=0.04579, over 4943.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.04424, over 972260.36 frames.], batch size: 35, lr: 4.44e-04
2022-05-04 23:44:08,291 INFO [train.py:715] (5/8) Epoch 4, batch 22000, loss[loss=0.1286, simple_loss=0.2013, pruned_loss=0.02797, over 4947.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.044, over 972687.67 frames.], batch size: 14, lr: 4.44e-04
2022-05-04 23:44:48,080 INFO [train.py:715] (5/8) Epoch 4, batch 22050, loss[loss=0.1493, simple_loss=0.2193, pruned_loss=0.03964, over 4808.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2266, pruned_loss=0.04407, over 973661.50 frames.], batch size: 26, lr: 4.44e-04
2022-05-04 23:45:28,545 INFO [train.py:715] (5/8) Epoch 4, batch 22100, loss[loss=0.1688, simple_loss=0.2307, pruned_loss=0.05342, over 4943.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2269, pruned_loss=0.04447, over 974299.63 frames.], batch size: 21, lr: 4.44e-04
2022-05-04 23:46:08,388 INFO [train.py:715] (5/8) Epoch 4, batch 22150, loss[loss=0.1255, simple_loss=0.2047, pruned_loss=0.02318, over 4895.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2264, pruned_loss=0.04394, over 973602.55 frames.], batch size: 19, lr: 4.44e-04
2022-05-04 23:46:47,295 INFO [train.py:715] (5/8) Epoch 4, batch 22200, loss[loss=0.1557, simple_loss=0.2241, pruned_loss=0.04367, over 4761.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04359, over 972574.51 frames.], batch size: 16, lr: 4.44e-04
2022-05-04 23:47:27,363 INFO [train.py:715] (5/8) Epoch 4, batch 22250, loss[loss=0.1322, simple_loss=0.2032, pruned_loss=0.03055, over 4931.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2259, pruned_loss=0.04362, over 973753.98 frames.], batch size: 23, lr: 4.44e-04
2022-05-04 23:48:07,759 INFO [train.py:715] (5/8) Epoch 4, batch 22300, loss[loss=0.1562, simple_loss=0.2208, pruned_loss=0.04579, over 4827.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04306, over 974360.90 frames.], batch size: 26, lr: 4.44e-04
2022-05-04 23:48:46,515 INFO [train.py:715] (5/8) Epoch 4, batch 22350, loss[loss=0.1868, simple_loss=0.2583, pruned_loss=0.05769, over 4926.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2261, pruned_loss=0.04314, over 973720.28 frames.], batch size: 18, lr: 4.44e-04
2022-05-04 23:49:25,542 INFO [train.py:715] (5/8) Epoch 4, batch 22400, loss[loss=0.1642, simple_loss=0.227, pruned_loss=0.05071, over 4802.00 frames.], tot_loss[loss=0.156, simple_loss=0.2259, pruned_loss=0.04308, over 972458.81 frames.], batch size: 21, lr: 4.44e-04
2022-05-04 23:50:06,134 INFO [train.py:715] (5/8) Epoch 4, batch 22450, loss[loss=0.1309, simple_loss=0.2104, pruned_loss=0.02566, over 4788.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.04339, over 972087.56 frames.], batch size: 17, lr: 4.44e-04
2022-05-04 23:50:45,320 INFO [train.py:715] (5/8) Epoch 4, batch 22500, loss[loss=0.1864, simple_loss=0.2549, pruned_loss=0.05892, over 4834.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04333, over 971662.63 frames.], batch size: 30, lr: 4.43e-04
2022-05-04 23:51:24,262 INFO [train.py:715] (5/8) Epoch 4, batch 22550, loss[loss=0.124, simple_loss=0.1925, pruned_loss=0.02772, over 4740.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2249, pruned_loss=0.04246, over 971978.95 frames.], batch size: 16, lr: 4.43e-04
2022-05-04 23:52:04,196 INFO [train.py:715] (5/8) Epoch 4, batch 22600, loss[loss=0.1301, simple_loss=0.1974, pruned_loss=0.03139, over 4809.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2246, pruned_loss=0.04258, over 972595.90 frames.], batch size: 13, lr: 4.43e-04
2022-05-04 23:52:44,024 INFO [train.py:715] (5/8) Epoch 4, batch 22650, loss[loss=0.1882, simple_loss=0.2616, pruned_loss=0.05742, over 4942.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04256, over 972812.04 frames.], batch size: 35, lr: 4.43e-04
2022-05-04 23:53:22,947 INFO [train.py:715] (5/8) Epoch 4, batch 22700, loss[loss=0.1728, simple_loss=0.2263, pruned_loss=0.05968, over 4859.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04342, over 973262.97 frames.], batch size: 32, lr: 4.43e-04
2022-05-04 23:54:02,345 INFO [train.py:715] (5/8) Epoch 4, batch 22750, loss[loss=0.1373, simple_loss=0.206, pruned_loss=0.03427, over 4770.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2252, pruned_loss=0.04327, over 973199.05 frames.], batch size: 18, lr: 4.43e-04
2022-05-04 23:54:42,047 INFO [train.py:715] (5/8) Epoch 4, batch 22800, loss[loss=0.1659, simple_loss=0.2358, pruned_loss=0.04798, over 4843.00 frames.], tot_loss[loss=0.155, simple_loss=0.2245, pruned_loss=0.04271, over 973094.83 frames.], batch size: 15, lr: 4.43e-04
2022-05-04 23:55:21,168 INFO [train.py:715] (5/8) Epoch 4, batch 22850, loss[loss=0.1421, simple_loss=0.2188, pruned_loss=0.03269, over 4937.00 frames.], tot_loss[loss=0.1545, simple_loss=0.224, pruned_loss=0.04255, over 972100.88 frames.], batch size: 23, lr: 4.43e-04
2022-05-04 23:55:59,901 INFO [train.py:715] (5/8) Epoch 4, batch 22900, loss[loss=0.1577, simple_loss=0.2381, pruned_loss=0.03867, over 4772.00 frames.], tot_loss[loss=0.155, simple_loss=0.2246, pruned_loss=0.04268, over 971782.39 frames.], batch size: 14, lr: 4.43e-04
2022-05-04 23:56:39,567 INFO [train.py:715] (5/8) Epoch 4, batch 22950, loss[loss=0.1802, simple_loss=0.2475, pruned_loss=0.0565, over 4820.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2253, pruned_loss=0.04304, over 972824.65 frames.], batch size: 26, lr: 4.43e-04
2022-05-04 23:57:19,677 INFO [train.py:715] (5/8) Epoch 4, batch 23000, loss[loss=0.1684, simple_loss=0.24, pruned_loss=0.04844, over 4764.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04281, over 972447.80 frames.], batch size: 19, lr: 4.43e-04
2022-05-04 23:57:58,015 INFO [train.py:715] (5/8) Epoch 4, batch 23050, loss[loss=0.2545, simple_loss=0.3072, pruned_loss=0.1009, over 4872.00 frames.], tot_loss[loss=0.155, simple_loss=0.2244, pruned_loss=0.04278, over 972836.35 frames.], batch size: 20, lr: 4.43e-04
2022-05-04 23:58:37,636 INFO [train.py:715] (5/8) Epoch 4, batch 23100, loss[loss=0.1368, simple_loss=0.2141, pruned_loss=0.02978, over 4881.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2247, pruned_loss=0.04312, over 972388.76 frames.], batch size: 22, lr: 4.43e-04
2022-05-04 23:59:18,025 INFO [train.py:715] (5/8) Epoch 4, batch 23150, loss[loss=0.1344, simple_loss=0.1997, pruned_loss=0.03458, over 4800.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2238, pruned_loss=0.04254, over 971995.70 frames.], batch size: 12, lr: 4.43e-04
2022-05-04 23:59:57,815 INFO [train.py:715] (5/8) Epoch 4, batch 23200, loss[loss=0.1233, simple_loss=0.1887, pruned_loss=0.02891, over 4973.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2238, pruned_loss=0.04274, over 971919.89 frames.], batch size: 28, lr: 4.42e-04
2022-05-05 00:00:36,520 INFO [train.py:715] (5/8) Epoch 4, batch 23250, loss[loss=0.1862, simple_loss=0.2483, pruned_loss=0.06202, over 4784.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2247, pruned_loss=0.04281, over 972606.15 frames.], batch size: 14, lr: 4.42e-04
2022-05-05 00:01:16,399 INFO [train.py:715] (5/8) Epoch 4, batch 23300, loss[loss=0.1638, simple_loss=0.2351, pruned_loss=0.04622, over 4915.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04265, over 973225.04 frames.], batch size: 18, lr: 4.42e-04
2022-05-05 00:01:56,690 INFO [train.py:715] (5/8) Epoch 4, batch 23350, loss[loss=0.1658, simple_loss=0.2261, pruned_loss=0.05275, over 4977.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2243, pruned_loss=0.04248, over 973589.88 frames.], batch size: 35, lr: 4.42e-04
2022-05-05 00:02:35,082 INFO [train.py:715] (5/8) Epoch 4, batch 23400, loss[loss=0.1457, simple_loss=0.2055, pruned_loss=0.04292, over 4777.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04226, over 973283.36 frames.], batch size: 12, lr: 4.42e-04
2022-05-05 00:03:14,413 INFO [train.py:715] (5/8) Epoch 4, batch 23450, loss[loss=0.1487, simple_loss=0.2273, pruned_loss=0.03503, over 4886.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2245, pruned_loss=0.04252, over 972908.82 frames.], batch size: 19, lr: 4.42e-04
2022-05-05 00:03:55,001 INFO [train.py:715] (5/8) Epoch 4, batch 23500, loss[loss=0.1514, simple_loss=0.2188, pruned_loss=0.04197, over 4983.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2243, pruned_loss=0.04243, over 973002.37 frames.], batch size: 15, lr: 4.42e-04
2022-05-05 00:04:33,372 INFO [train.py:715] (5/8) Epoch 4, batch 23550, loss[loss=0.12, simple_loss=0.1914, pruned_loss=0.02427, over 4718.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2235, pruned_loss=0.04195, over 973292.53 frames.], batch size: 12, lr: 4.42e-04
2022-05-05 00:05:12,658 INFO [train.py:715] (5/8) Epoch 4, batch 23600, loss[loss=0.1761, simple_loss=0.2338, pruned_loss=0.05919, over 4968.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2238, pruned_loss=0.04192, over 972929.71 frames.], batch size: 15, lr: 4.42e-04
2022-05-05 00:05:53,472 INFO [train.py:715] (5/8) Epoch 4, batch 23650, loss[loss=0.1661, simple_loss=0.2322, pruned_loss=0.04995, over 4935.00 frames.], tot_loss[loss=0.1542, simple_loss=0.224, pruned_loss=0.04223, over 972404.18 frames.], batch size: 29, lr: 4.42e-04
2022-05-05 00:06:34,864 INFO [train.py:715] (5/8) Epoch 4, batch 23700, loss[loss=0.1585, simple_loss=0.2269, pruned_loss=0.04509, over 4980.00 frames.], tot_loss[loss=0.1552, simple_loss=0.225, pruned_loss=0.04273, over 973048.88 frames.], batch size: 15, lr: 4.42e-04
2022-05-05 00:07:14,372 INFO [train.py:715] (5/8) Epoch 4, batch 23750, loss[loss=0.1574, simple_loss=0.2206, pruned_loss=0.04714, over 4790.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2258, pruned_loss=0.04284, over 972487.00 frames.], batch size: 17, lr: 4.42e-04
2022-05-05 00:07:53,776 INFO [train.py:715] (5/8) Epoch 4, batch 23800, loss[loss=0.1767, simple_loss=0.2242, pruned_loss=0.06455, over 4756.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2268, pruned_loss=0.04328, over 971795.65 frames.], batch size: 19, lr: 4.42e-04
2022-05-05 00:08:34,377 INFO [train.py:715] (5/8) Epoch 4, batch 23850, loss[loss=0.1654, simple_loss=0.2435, pruned_loss=0.0436, over 4922.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2275, pruned_loss=0.04368, over 971985.89 frames.], batch size: 23, lr: 4.42e-04
2022-05-05 00:09:13,909 INFO [train.py:715] (5/8) Epoch 4, batch 23900, loss[loss=0.1389, simple_loss=0.2177, pruned_loss=0.0301, over 4748.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2276, pruned_loss=0.04381, over 972504.39 frames.], batch size: 19, lr: 4.42e-04
2022-05-05 00:09:53,721 INFO [train.py:715] (5/8) Epoch 4, batch 23950, loss[loss=0.1499, simple_loss=0.2226, pruned_loss=0.03861, over 4776.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2271, pruned_loss=0.04376, over 971456.05 frames.], batch size: 12, lr: 4.41e-04
2022-05-05 00:10:34,506 INFO [train.py:715] (5/8) Epoch 4, batch 24000, loss[loss=0.1593, simple_loss=0.2371, pruned_loss=0.04077, over 4928.00 frames.], tot_loss[loss=0.157, simple_loss=0.227, pruned_loss=0.04348, over 971898.22 frames.], batch size: 18, lr: 4.41e-04
2022-05-05 00:10:34,507 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 00:10:44,331 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1115, simple_loss=0.1974, pruned_loss=0.01276, over 914524.00 frames.
2022-05-05 00:11:25,476 INFO [train.py:715] (5/8) Epoch 4, batch 24050, loss[loss=0.1421, simple_loss=0.2117, pruned_loss=0.03622, over 4932.00 frames.], tot_loss[loss=0.157, simple_loss=0.2267, pruned_loss=0.04368, over 971886.48 frames.], batch size: 23, lr: 4.41e-04
2022-05-05 00:12:06,060 INFO [train.py:715] (5/8) Epoch 4, batch 24100, loss[loss=0.1349, simple_loss=0.2127, pruned_loss=0.02859, over 4964.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2282, pruned_loss=0.04437, over 971912.62 frames.], batch size: 28, lr: 4.41e-04
2022-05-05 00:12:45,927 INFO [train.py:715] (5/8) Epoch 4, batch 24150, loss[loss=0.1602, simple_loss=0.2268, pruned_loss=0.04678, over 4986.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2274, pruned_loss=0.04371, over 972035.08 frames.], batch size: 26, lr: 4.41e-04
2022-05-05 00:13:25,912 INFO [train.py:715] (5/8) Epoch 4, batch 24200, loss[loss=0.1498, simple_loss=0.2201, pruned_loss=0.03974, over 4812.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04311, over 972732.61 frames.], batch size: 15, lr: 4.41e-04
2022-05-05 00:14:07,341 INFO [train.py:715] (5/8) Epoch 4, batch 24250, loss[loss=0.1332, simple_loss=0.2038, pruned_loss=0.03129, over 4789.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04296, over 972761.96 frames.], batch size: 21, lr: 4.41e-04
2022-05-05 00:14:46,254 INFO [train.py:715] (5/8) Epoch 4, batch 24300, loss[loss=0.1733, simple_loss=0.2392, pruned_loss=0.05374, over 4828.00 frames.], tot_loss[loss=0.1558, simple_loss=0.226, pruned_loss=0.04275, over 972403.83 frames.], batch size: 15, lr: 4.41e-04
2022-05-05 00:15:26,723 INFO [train.py:715] (5/8) Epoch 4, batch 24350, loss[loss=0.1724, simple_loss=0.2367, pruned_loss=0.05402, over 4822.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2264, pruned_loss=0.04303, over 972581.44 frames.], batch size: 25, lr: 4.41e-04
2022-05-05 00:16:07,661 INFO [train.py:715] (5/8) Epoch 4, batch 24400, loss[loss=0.1441, simple_loss=0.2109, pruned_loss=0.03867, over 4883.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2265, pruned_loss=0.04315, over 972408.45 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:16:47,247 INFO [train.py:715] (5/8) Epoch 4, batch 24450, loss[loss=0.1399, simple_loss=0.2082, pruned_loss=0.03584, over 4845.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2272, pruned_loss=0.04376, over 972508.69 frames.], batch size: 13, lr: 4.41e-04
2022-05-05 00:17:27,007 INFO [train.py:715] (5/8) Epoch 4, batch 24500, loss[loss=0.1551, simple_loss=0.2255, pruned_loss=0.04232, over 4768.00 frames.], tot_loss[loss=0.157, simple_loss=0.227, pruned_loss=0.04347, over 972766.11 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:18:06,875 INFO [train.py:715] (5/8) Epoch 4, batch 24550, loss[loss=0.1734, simple_loss=0.245, pruned_loss=0.05089, over 4980.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2267, pruned_loss=0.04324, over 972193.96 frames.], batch size: 35, lr: 4.41e-04
2022-05-05 00:18:48,106 INFO [train.py:715] (5/8) Epoch 4, batch 24600, loss[loss=0.1131, simple_loss=0.1848, pruned_loss=0.02074, over 4762.00 frames.], tot_loss[loss=0.1559, simple_loss=0.226, pruned_loss=0.0429, over 971236.41 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:19:27,466 INFO [train.py:715] (5/8) Epoch 4, batch 24650, loss[loss=0.1451, simple_loss=0.2125, pruned_loss=0.03886, over 4852.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.0427, over 971435.83 frames.], batch size: 30, lr: 4.41e-04
2022-05-05 00:20:08,194 INFO [train.py:715] (5/8) Epoch 4, batch 24700, loss[loss=0.146, simple_loss=0.225, pruned_loss=0.03349, over 4818.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2252, pruned_loss=0.04289, over 972017.06 frames.], batch size: 27, lr: 4.40e-04
2022-05-05 00:20:49,278 INFO [train.py:715] (5/8) Epoch 4, batch 24750, loss[loss=0.1687, simple_loss=0.2382, pruned_loss=0.04958, over 4896.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04324, over 973152.01 frames.], batch size: 19, lr: 4.40e-04
2022-05-05 00:21:28,791 INFO [train.py:715] (5/8) Epoch 4, batch 24800, loss[loss=0.1562, simple_loss=0.2312, pruned_loss=0.04063, over 4792.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2271, pruned_loss=0.04356, over 973463.06 frames.], batch size: 14, lr: 4.40e-04
2022-05-05 00:22:08,799 INFO [train.py:715] (5/8) Epoch 4, batch 24850, loss[loss=0.1449, simple_loss=0.2097, pruned_loss=0.04002, over 4866.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.04381, over 973242.33 frames.], batch size: 20, lr: 4.40e-04
2022-05-05 00:22:49,057 INFO [train.py:715] (5/8) Epoch 4, batch 24900, loss[loss=0.1408, simple_loss=0.2095, pruned_loss=0.03608, over 4780.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2273, pruned_loss=0.04373, over 973127.47 frames.], batch size: 17, lr: 4.40e-04
2022-05-05 00:23:30,189 INFO [train.py:715] (5/8) Epoch 4, batch 24950, loss[loss=0.181, simple_loss=0.2373, pruned_loss=0.06234, over 4784.00 frames.], tot_loss[loss=0.158, simple_loss=0.2274, pruned_loss=0.04428, over 972588.50 frames.], batch size: 14, lr: 4.40e-04
2022-05-05 00:24:09,091 INFO [train.py:715] (5/8) Epoch 4, batch 25000, loss[loss=0.1493, simple_loss=0.212, pruned_loss=0.04326, over 4931.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2258, pruned_loss=0.04364, over 972633.79 frames.], batch size: 39, lr: 4.40e-04
2022-05-05 00:24:49,332 INFO [train.py:715] (5/8) Epoch 4, batch 25050, loss[loss=0.1574, simple_loss=0.2189, pruned_loss=0.04796, over 4818.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04321, over 973258.06 frames.], batch size: 13, lr: 4.40e-04
2022-05-05 00:25:30,453 INFO [train.py:715] (5/8) Epoch 4, batch 25100, loss[loss=0.1322, simple_loss=0.2138, pruned_loss=0.02531, over 4900.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04287, over 973246.03 frames.], batch size: 19, lr: 4.40e-04
2022-05-05 00:26:10,374 INFO [train.py:715] (5/8) Epoch 4, batch 25150, loss[loss=0.1436, simple_loss=0.2048, pruned_loss=0.04124, over 4916.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04273, over 972320.21 frames.], batch size: 23, lr: 4.40e-04
2022-05-05 00:26:49,793 INFO [train.py:715] (5/8) Epoch 4, batch 25200, loss[loss=0.1451, simple_loss=0.2133, pruned_loss=0.03842, over 4782.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04288, over 972513.46 frames.], batch size: 18, lr: 4.40e-04
2022-05-05 00:27:30,067 INFO [train.py:715] (5/8) Epoch 4, batch 25250, loss[loss=0.1971, simple_loss=0.257, pruned_loss=0.06856, over 4775.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2261, pruned_loss=0.04322, over 972043.83 frames.], batch size: 14, lr: 4.40e-04
2022-05-05 00:28:10,080 INFO [train.py:715] (5/8) Epoch 4, batch 25300, loss[loss=0.1515, simple_loss=0.2234, pruned_loss=0.03976, over 4779.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04319, over 971914.96 frames.], batch size: 19, lr: 4.40e-04
2022-05-05 00:28:47,883 INFO [train.py:715] (5/8) Epoch 4, batch 25350, loss[loss=0.1456, simple_loss=0.22, pruned_loss=0.03565, over 4770.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04389, over 971512.12 frames.], batch size: 17, lr: 4.40e-04
2022-05-05 00:29:26,730 INFO [train.py:715] (5/8) Epoch 4, batch 25400, loss[loss=0.1405, simple_loss=0.2142, pruned_loss=0.03342, over 4855.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2252, pruned_loss=0.04302, over 972361.83 frames.], batch size: 32, lr: 4.40e-04
2022-05-05 00:30:06,397 INFO [train.py:715] (5/8) Epoch 4, batch 25450, loss[loss=0.1678, simple_loss=0.2526, pruned_loss=0.04153, over 4956.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2252, pruned_loss=0.04364, over 971935.36 frames.], batch size: 24, lr: 4.39e-04
2022-05-05 00:30:45,455 INFO [train.py:715] (5/8) Epoch 4, batch 25500, loss[loss=0.134, simple_loss=0.214, pruned_loss=0.02697, over 4802.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2256, pruned_loss=0.04372, over 972226.10 frames.], batch size: 24, lr: 4.39e-04
2022-05-05 00:31:25,315 INFO [train.py:715] (5/8) Epoch 4, batch 25550, loss[loss=0.1655, simple_loss=0.2386, pruned_loss=0.04617, over 4805.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2248, pruned_loss=0.04288, over 971837.09 frames.], batch size: 24, lr: 4.39e-04
2022-05-05 00:32:05,294 INFO [train.py:715] (5/8) Epoch 4, batch 25600, loss[loss=0.1702, simple_loss=0.2478, pruned_loss=0.0463, over 4979.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04308, over 972317.51 frames.], batch size: 25, lr: 4.39e-04
2022-05-05 00:32:45,565 INFO [train.py:715] (5/8) Epoch 4, batch 25650, loss[loss=0.1475, simple_loss=0.2142, pruned_loss=0.04037, over 4751.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.04323, over 973035.35 frames.], batch size: 19, lr: 4.39e-04
2022-05-05 00:33:24,672 INFO [train.py:715] (5/8) Epoch 4, batch 25700, loss[loss=0.1666, simple_loss=0.2438, pruned_loss=0.04468, over 4957.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04284, over 972066.55 frames.], batch size: 21, lr: 4.39e-04
2022-05-05 00:34:04,655 INFO [train.py:715] (5/8) Epoch 4, batch 25750, loss[loss=0.1552, simple_loss=0.2181, pruned_loss=0.04617, over 4799.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04319, over 973681.40 frames.], batch size: 25, lr: 4.39e-04
2022-05-05 00:34:45,100 INFO [train.py:715] (5/8) Epoch 4, batch 25800, loss[loss=0.1476, simple_loss=0.2292, pruned_loss=0.03303, over 4977.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04274, over 974171.40 frames.], batch size: 25, lr: 4.39e-04
2022-05-05 00:35:24,459 INFO [train.py:715] (5/8) Epoch 4, batch 25850, loss[loss=0.1592, simple_loss=0.2213, pruned_loss=0.04856, over 4857.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2253, pruned_loss=0.04306, over 973977.58 frames.], batch size: 20, lr: 4.39e-04
2022-05-05 00:36:03,599 INFO [train.py:715] (5/8) Epoch 4, batch 25900, loss[loss=0.1778, simple_loss=0.2394, pruned_loss=0.05814, over 4965.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2249, pruned_loss=0.04323, over 973577.34 frames.], batch size: 35, lr: 4.39e-04
2022-05-05 00:36:43,852 INFO [train.py:715] (5/8) Epoch 4, batch 25950, loss[loss=0.1912, simple_loss=0.2619, pruned_loss=0.06023, over 4857.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04308, over 974120.83 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:37:24,111 INFO [train.py:715] (5/8) Epoch 4, batch 26000, loss[loss=0.1871, simple_loss=0.2484, pruned_loss=0.06293, over 4888.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2257, pruned_loss=0.04371, over 974170.45 frames.], batch size: 22, lr: 4.39e-04
2022-05-05 00:38:02,817 INFO [train.py:715] (5/8) Epoch 4, batch 26050, loss[loss=0.1589, simple_loss=0.2177, pruned_loss=0.05005, over 4768.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2252, pruned_loss=0.04329, over 973489.99 frames.], batch size: 14, lr: 4.39e-04
2022-05-05 00:38:42,224 INFO [train.py:715] (5/8) Epoch 4, batch 26100, loss[loss=0.1498, simple_loss=0.2311, pruned_loss=0.03421, over 4854.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2254, pruned_loss=0.04343, over 973211.81 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:39:22,688 INFO [train.py:715] (5/8) Epoch 4, batch 26150, loss[loss=0.1623, simple_loss=0.2233, pruned_loss=0.05062, over 4795.00 frames.], tot_loss[loss=0.1561, simple_loss=0.225, pruned_loss=0.04365, over 973028.13 frames.], batch size: 17, lr: 4.39e-04
2022-05-05 00:40:01,757 INFO [train.py:715] (5/8) Epoch 4, batch 26200, loss[loss=0.1419, simple_loss=0.2228, pruned_loss=0.03051, over 4836.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2247, pruned_loss=0.04333, over 973555.06 frames.], batch size: 13, lr: 4.38e-04
2022-05-05 00:40:41,527 INFO [train.py:715] (5/8) Epoch 4, batch 26250, loss[loss=0.1679, simple_loss=0.2375, pruned_loss=0.04921, over 4962.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2251, pruned_loss=0.0433, over 973824.15 frames.], batch size: 24, lr: 4.38e-04
2022-05-05 00:41:21,390 INFO [train.py:715] (5/8) Epoch 4, batch 26300, loss[loss=0.182, simple_loss=0.2503, pruned_loss=0.05684, over 4931.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.0433, over 973709.92 frames.], batch size: 39, lr: 4.38e-04
2022-05-05 00:42:01,535 INFO [train.py:715] (5/8) Epoch 4, batch 26350, loss[loss=0.1514, simple_loss=0.2245, pruned_loss=0.03916, over 4894.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04293, over 974097.81 frames.], batch size: 22, lr: 4.38e-04
2022-05-05 00:42:40,877 INFO [train.py:715] (5/8) Epoch 4, batch 26400, loss[loss=0.1358, simple_loss=0.2127, pruned_loss=0.02943, over 4882.00 frames.], tot_loss[loss=0.1554, simple_loss=0.225, pruned_loss=0.0429, over 975039.47 frames.], batch size: 16, lr: 4.38e-04
2022-05-05 00:43:20,962 INFO [train.py:715] (5/8) Epoch 4, batch 26450, loss[loss=0.1403, simple_loss=0.2204, pruned_loss=0.03006, over 4924.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2253, pruned_loss=0.04277, over 974282.37 frames.], batch size: 21, lr: 4.38e-04
2022-05-05 00:44:01,484 INFO [train.py:715] (5/8) Epoch 4, batch 26500, loss[loss=0.1448, simple_loss=0.2058, pruned_loss=0.04191, over 4985.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2249, pruned_loss=0.04247, over 974537.34 frames.], batch size: 14, lr: 4.38e-04
2022-05-05 00:44:40,386 INFO [train.py:715] (5/8) Epoch 4, batch 26550, loss[loss=0.1623, simple_loss=0.2367, pruned_loss=0.04395, over 4890.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04296, over 974007.19 frames.], batch size: 22, lr: 4.38e-04
2022-05-05 00:45:20,036 INFO [train.py:715] (5/8) Epoch 4, batch 26600, loss[loss=0.1699, simple_loss=0.2414, pruned_loss=0.04919, over 4883.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.043, over 973422.66 frames.], batch size: 39, lr: 4.38e-04
2022-05-05 00:46:00,424 INFO [train.py:715] (5/8) Epoch 4, batch 26650, loss[loss=0.1273, simple_loss=0.2038, pruned_loss=0.02544, over 4807.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2263, pruned_loss=0.04338, over 973153.99 frames.], batch size: 21, lr: 4.38e-04
2022-05-05 00:46:41,228 INFO [train.py:715] (5/8) Epoch 4, batch 26700, loss[loss=0.1602, simple_loss=0.2356, pruned_loss=0.04243, over 4904.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.04309, over 973158.67 frames.], batch size: 19, lr: 4.38e-04
2022-05-05 00:47:20,020 INFO [train.py:715] (5/8) Epoch 4, batch 26750, loss[loss=0.181, simple_loss=0.2391, pruned_loss=0.06151, over 4972.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04262, over 972913.18 frames.], batch size: 14, lr: 4.38e-04
2022-05-05 00:47:59,595 INFO [train.py:715] (5/8) Epoch 4, batch 26800, loss[loss=0.1337, simple_loss=0.2034, pruned_loss=0.03197, over 4740.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2244, pruned_loss=0.04243, over 972659.17 frames.], batch size: 12, lr: 4.38e-04
2022-05-05 00:48:39,808 INFO [train.py:715] (5/8) Epoch 4, batch 26850, loss[loss=0.1148, simple_loss=0.1778, pruned_loss=0.02589, over 4741.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.04315, over 972194.05 frames.], batch size: 12, lr: 4.38e-04
2022-05-05 00:49:18,748 INFO [train.py:715] (5/8) Epoch 4, batch 26900, loss[loss=0.1907, simple_loss=0.2549, pruned_loss=0.06327, over 4924.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2251, pruned_loss=0.04297, over 972158.28 frames.], batch size: 18, lr: 4.38e-04
2022-05-05 00:49:58,559 INFO [train.py:715] (5/8) Epoch 4, batch 26950, loss[loss=0.1537, simple_loss=0.2222, pruned_loss=0.04255, over 4826.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.0434, over 971724.42 frames.], batch size: 13, lr: 4.37e-04
2022-05-05 00:50:38,533 INFO [train.py:715] (5/8) Epoch 4, batch 27000, loss[loss=0.2255, simple_loss=0.2667, pruned_loss=0.09213, over 4996.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2267, pruned_loss=0.04431, over 971739.76 frames.], batch size: 15, lr: 4.37e-04
2022-05-05 00:50:38,533 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 00:50:48,690 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1114, simple_loss=0.197, pruned_loss=0.01284, over 914524.00 frames.
2022-05-05 00:51:28,850 INFO [train.py:715] (5/8) Epoch 4, batch 27050, loss[loss=0.1471, simple_loss=0.2154, pruned_loss=0.03939, over 4853.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2264, pruned_loss=0.04371, over 972203.68 frames.], batch size: 15, lr: 4.37e-04
2022-05-05 00:52:08,419 INFO [train.py:715] (5/8) Epoch 4, batch 27100, loss[loss=0.1784, simple_loss=0.2431, pruned_loss=0.05691, over 4738.00 frames.], tot_loss[loss=0.155, simple_loss=0.2248, pruned_loss=0.04261, over 972304.83 frames.], batch size: 16, lr: 4.37e-04
2022-05-05 00:52:47,726 INFO [train.py:715] (5/8) Epoch 4, batch 27150, loss[loss=0.1413, simple_loss=0.2186, pruned_loss=0.03199, over 4837.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2248, pruned_loss=0.04263, over 972277.16 frames.], batch size: 26, lr: 4.37e-04
2022-05-05 00:53:27,409 INFO [train.py:715] (5/8) Epoch 4, batch 27200, loss[loss=0.1732, simple_loss=0.2391, pruned_loss=0.05366, over 4866.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2252, pruned_loss=0.04297, over 972179.37 frames.], batch size: 16, lr: 4.37e-04
2022-05-05 00:54:07,875 INFO [train.py:715] (5/8) Epoch 4, batch 27250, loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.0315, over 4962.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04334, over 971972.81 frames.], batch size: 24, lr: 4.37e-04
2022-05-05 00:54:46,636 INFO [train.py:715] (5/8) Epoch 4, batch 27300, loss[loss=0.1645, simple_loss=0.2272, pruned_loss=0.05089, over 4784.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2258, pruned_loss=0.04341, over 971690.73 frames.], batch size: 12, lr: 4.37e-04
2022-05-05 00:55:26,631 INFO [train.py:715] (5/8) Epoch 4, batch 27350, loss[loss=0.1623, simple_loss=0.2393, pruned_loss=0.04268, over 4759.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2251, pruned_loss=0.04316, over 971996.18 frames.], batch size: 19, lr: 4.37e-04
2022-05-05 00:56:06,584 INFO [train.py:715] (5/8) Epoch 4, batch 27400, loss[loss=0.164, simple_loss=0.2338, pruned_loss=0.0471, over 4772.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2252, pruned_loss=0.04287, over 972748.17 frames.], batch size: 18, lr: 4.37e-04
2022-05-05 00:56:45,011 INFO [train.py:715] (5/8) Epoch 4, batch 27450, loss[loss=0.1631, simple_loss=0.2275, pruned_loss=0.04935, over 4854.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2251, pruned_loss=0.04268, over 972029.27 frames.], batch size: 32, lr: 4.37e-04
2022-05-05 00:57:24,954 INFO [train.py:715] (5/8) Epoch 4, batch 27500, loss[loss=0.1642, simple_loss=0.2368, pruned_loss=0.04581, over 4927.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04289, over 971969.98 frames.], batch size: 29, lr: 4.37e-04
2022-05-05 00:58:03,976 INFO [train.py:715] (5/8) Epoch 4, batch 27550, loss[loss=0.1815, simple_loss=0.243, pruned_loss=0.05997, over 4901.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04322, over 971029.61 frames.], batch size: 16, lr: 4.37e-04
2022-05-05 00:58:43,890 INFO [train.py:715] (5/8) Epoch 4, batch 27600, loss[loss=0.1832, simple_loss=0.2414, pruned_loss=0.06251, over 4861.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2267, pruned_loss=0.04346, over 970655.49 frames.], batch size: 16, lr: 4.37e-04
2022-05-05 00:59:22,455 INFO [train.py:715] (5/8) Epoch 4, batch 27650, loss[loss=0.1976, simple_loss=0.255, pruned_loss=0.07006, over 4808.00 frames.], tot_loss[loss=0.1568, simple_loss=0.227, pruned_loss=0.04329, over 971846.25 frames.], batch size: 13, lr: 4.37e-04
2022-05-05 01:00:01,781 INFO [train.py:715] (5/8) Epoch 4, batch 27700, loss[loss=0.1414, simple_loss=0.2129, pruned_loss=0.03492, over 4880.00 frames.], tot_loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04339, over 971279.32 frames.], batch size: 16, lr: 4.36e-04
2022-05-05 01:00:41,406 INFO [train.py:715] (5/8) Epoch 4, batch 27750, loss[loss=0.1469, simple_loss=0.2116, pruned_loss=0.04106, over 4771.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2274, pruned_loss=0.0435, over 972222.48 frames.], batch size: 17, lr: 4.36e-04
2022-05-05 01:01:20,723 INFO [train.py:715] (5/8) Epoch 4, batch 27800, loss[loss=0.1098, simple_loss=0.1862, pruned_loss=0.01668, over 4776.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2276, pruned_loss=0.04365, over 971472.92 frames.], batch size: 17, lr: 4.36e-04
2022-05-05 01:01:59,776 INFO [train.py:715] (5/8) Epoch 4, batch 27850, loss[loss=0.1355, simple_loss=0.214, pruned_loss=0.02852, over 4785.00 frames.], tot_loss[loss=0.156, simple_loss=0.226, pruned_loss=0.043, over 971850.14 frames.], batch size: 17, lr: 4.36e-04
2022-05-05 01:02:38,863 INFO [train.py:715] (5/8) Epoch 4, batch 27900, loss[loss=0.1708, simple_loss=0.2288, pruned_loss=0.05645, over 4933.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.04312, over 972076.46 frames.], batch size: 39, lr: 4.36e-04
2022-05-05 01:03:18,309 INFO [train.py:715] (5/8) Epoch 4, batch 27950, loss[loss=0.2086, simple_loss=0.271, pruned_loss=0.07311, over 4746.00 frames.], tot_loss[loss=0.155, simple_loss=0.2252, pruned_loss=0.04238, over 971994.51 frames.], batch size: 14, lr: 4.36e-04
2022-05-05 01:03:57,876 INFO [train.py:715] (5/8) Epoch 4, batch 28000, loss[loss=0.2172, simple_loss=0.2699, pruned_loss=0.08225, over 4865.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2262, pruned_loss=0.04306, over 971778.62 frames.], batch size: 38, lr: 4.36e-04
2022-05-05 01:04:37,836 INFO [train.py:715] (5/8) Epoch 4, batch 28050, loss[loss=0.1375, simple_loss=0.2068, pruned_loss=0.03412, over 4764.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.04369, over 972755.12 frames.], batch size: 19, lr: 4.36e-04
2022-05-05 01:05:17,718 INFO [train.py:715] (5/8) Epoch 4, batch 28100, loss[loss=0.1654, simple_loss=0.2245, pruned_loss=0.05317, over 4970.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04366, over 973167.81 frames.], batch size: 35, lr: 4.36e-04
2022-05-05 01:05:57,312 INFO [train.py:715] (5/8) Epoch 4, batch 28150, loss[loss=0.1314, simple_loss=0.1981, pruned_loss=0.03238, over 4911.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.0428, over 972609.60 frames.], batch size: 18, lr: 4.36e-04
2022-05-05 01:06:36,803 INFO [train.py:715] (5/8) Epoch 4, batch 28200, loss[loss=0.1643, simple_loss=0.2279, pruned_loss=0.05038, over 4855.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2253, pruned_loss=0.0428, over 973009.34 frames.], batch size: 30, lr: 4.36e-04
2022-05-05 01:07:15,869 INFO [train.py:715] (5/8) Epoch 4, batch 28250, loss[loss=0.1544, simple_loss=0.2225, pruned_loss=0.04313, over 4907.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2257, pruned_loss=0.0428, over 973397.35 frames.], batch size: 22, lr: 4.36e-04
2022-05-05 01:07:55,432 INFO [train.py:715] (5/8) Epoch 4, batch 28300, loss[loss=0.1662, simple_loss=0.2371, pruned_loss=0.0476, over 4977.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2266, pruned_loss=0.0429, over 972984.92 frames.], batch size: 15, lr: 4.36e-04
2022-05-05 01:08:34,754 INFO [train.py:715] (5/8) Epoch 4, batch 28350, loss[loss=0.1613, simple_loss=0.2326, pruned_loss=0.04506, over 4929.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2266, pruned_loss=0.04298, over 972864.52 frames.], batch size: 23, lr: 4.36e-04
2022-05-05 01:09:14,655 INFO [train.py:715] (5/8) Epoch 4, batch 28400, loss[loss=0.1404, simple_loss=0.2108, pruned_loss=0.03503, over 4974.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2263, pruned_loss=0.0428, over 973438.13 frames.], batch size: 15, lr: 4.36e-04
2022-05-05 01:09:53,870 INFO [train.py:715] (5/8) Epoch 4, batch 28450, loss[loss=0.1287, simple_loss=0.2046, pruned_loss=0.02643, over 4810.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2261, pruned_loss=0.0425, over 974054.37 frames.], batch size: 26, lr: 4.36e-04
2022-05-05 01:10:32,527 INFO [train.py:715] (5/8) Epoch 4, batch 28500, loss[loss=0.166, simple_loss=0.2357, pruned_loss=0.04814, over 4991.00 frames.], tot_loss[loss=0.1558, simple_loss=0.226, pruned_loss=0.04277, over 974224.95 frames.], batch size: 20, lr: 4.35e-04
2022-05-05 01:11:12,039 INFO [train.py:715] (5/8) Epoch 4, batch 28550, loss[loss=0.1492, simple_loss=0.2232, pruned_loss=0.03765, over 4895.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2245, pruned_loss=0.0422, over 974338.14 frames.], batch size: 22, lr: 4.35e-04
2022-05-05 01:11:51,203 INFO [train.py:715] (5/8) Epoch 4, batch 28600, loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03651, over 4872.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2245, pruned_loss=0.04255, over 973392.93 frames.], batch size: 13, lr: 4.35e-04
2022-05-05 01:12:30,863 INFO [train.py:715] (5/8) Epoch 4, batch 28650, loss[loss=0.1911, simple_loss=0.2497, pruned_loss=0.06628, over 4770.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04319, over 973753.91 frames.], batch size: 17, lr: 4.35e-04
2022-05-05 01:13:10,038 INFO [train.py:715] (5/8) Epoch 4, batch 28700, loss[loss=0.1677, simple_loss=0.2443, pruned_loss=0.04554, over 4805.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04324, over 973627.25 frames.], batch size: 21, lr: 4.35e-04
2022-05-05 01:13:49,555 INFO [train.py:715] (5/8) Epoch 4, batch 28750, loss[loss=0.1325, simple_loss=0.1945, pruned_loss=0.03525, over 4755.00 frames.], tot_loss[loss=0.1555, simple_loss=0.225, pruned_loss=0.04299, over 973627.05 frames.], batch size: 12, lr: 4.35e-04
2022-05-05 01:14:31,713 INFO [train.py:715] (5/8) Epoch 4, batch 28800, loss[loss=0.1665, simple_loss=0.2265, pruned_loss=0.05323, over 4908.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2254, pruned_loss=0.0429, over 973734.38 frames.], batch size: 17, lr: 4.35e-04
2022-05-05 01:15:10,514 INFO [train.py:715] (5/8) Epoch 4, batch 28850, loss[loss=0.1686, simple_loss=0.2523, pruned_loss=0.04242, over 4872.00 frames.], tot_loss[loss=0.155, simple_loss=0.225, pruned_loss=0.04255, over 973145.56 frames.], batch size: 16, lr: 4.35e-04
2022-05-05 01:15:50,212 INFO [train.py:715] (5/8) Epoch 4, batch 28900, loss[loss=0.1242, simple_loss=0.2061, pruned_loss=0.02117, over 4882.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.042, over 973148.20 frames.], batch size: 16, lr: 4.35e-04
2022-05-05 01:16:29,311 INFO [train.py:715] (5/8) Epoch 4, batch 28950, loss[loss=0.1972, simple_loss=0.2563, pruned_loss=0.06901, over 4793.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04281, over 972449.82 frames.], batch size: 21, lr: 4.35e-04
2022-05-05 01:17:08,542 INFO [train.py:715] (5/8) Epoch 4, batch 29000, loss[loss=0.1526, simple_loss=0.2172, pruned_loss=0.04404, over 4854.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2259, pruned_loss=0.0432, over 971995.21 frames.], batch size: 30, lr: 4.35e-04
2022-05-05 01:17:48,159 INFO [train.py:715] (5/8) Epoch 4, batch 29050, loss[loss=0.172, simple_loss=0.2307, pruned_loss=0.05661, over 4852.00 frames.], tot_loss[loss=0.156, simple_loss=0.2257, pruned_loss=0.04319, over 971600.16 frames.], batch size: 32, lr: 4.35e-04
2022-05-05 01:18:28,177 INFO [train.py:715] (5/8) Epoch 4, batch 29100, loss[loss=0.1626, simple_loss=0.2242, pruned_loss=0.05052, over 4681.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04352, over 970760.59 frames.], batch size: 15, lr: 4.35e-04
2022-05-05 01:19:07,855 INFO [train.py:715] (5/8) Epoch 4, batch 29150, loss[loss=0.176, simple_loss=0.2572, pruned_loss=0.04734, over 4888.00 frames.], tot_loss[loss=0.1555, simple_loss=0.225, pruned_loss=0.04299, over 971621.73 frames.], batch size: 19, lr: 4.35e-04
2022-05-05 01:19:46,740 INFO [train.py:715] (5/8) Epoch 4, batch 29200, loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.0446, over 4888.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04309, over 971323.00 frames.], batch size: 22, lr: 4.35e-04
2022-05-05 01:20:26,106 INFO [train.py:715] (5/8) Epoch 4, batch 29250, loss[loss=0.1518, simple_loss=0.2248, pruned_loss=0.03945, over 4944.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04329, over 971530.28 frames.], batch size: 21, lr: 4.34e-04
2022-05-05 01:21:05,004 INFO [train.py:715] (5/8) Epoch 4, batch 29300, loss[loss=0.1465, simple_loss=0.2171, pruned_loss=0.03797, over 4876.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2253, pruned_loss=0.04277, over 972118.21 frames.], batch size: 16, lr: 4.34e-04
2022-05-05 01:21:43,982 INFO [train.py:715] (5/8) Epoch 4, batch 29350, loss[loss=0.1565, simple_loss=0.2302, pruned_loss=0.04133, over 4924.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2252, pruned_loss=0.04251, over 971898.12 frames.], batch size: 39, lr: 4.34e-04
2022-05-05 01:22:22,963 INFO [train.py:715] (5/8) Epoch 4, batch 29400, loss[loss=0.1949, simple_loss=0.2599, pruned_loss=0.06494, over 4700.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04295, over 971200.12 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:23:02,044 INFO [train.py:715] (5/8) Epoch 4, batch 29450, loss[loss=0.1686, simple_loss=0.2413, pruned_loss=0.04797, over 4879.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2252, pruned_loss=0.0429, over 971644.35 frames.], batch size: 16, lr: 4.34e-04
2022-05-05 01:23:41,623 INFO [train.py:715] (5/8) Epoch 4, batch 29500, loss[loss=0.1526, simple_loss=0.2219, pruned_loss=0.0417, over 4772.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2254, pruned_loss=0.04303, over 972395.68 frames.], batch size: 14, lr: 4.34e-04
2022-05-05 01:24:20,879 INFO [train.py:715] (5/8) Epoch 4, batch 29550, loss[loss=0.1492, simple_loss=0.2197, pruned_loss=0.03934, over 4890.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2252, pruned_loss=0.04306, over 971899.11 frames.], batch size: 16, lr: 4.34e-04
2022-05-05 01:25:00,161 INFO [train.py:715] (5/8) Epoch 4, batch 29600, loss[loss=0.1745, simple_loss=0.2391, pruned_loss=0.055, over 4855.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04313, over 971356.30 frames.], batch size: 20, lr: 4.34e-04
2022-05-05 01:25:39,284 INFO [train.py:715] (5/8) Epoch 4, batch 29650, loss[loss=0.2158, simple_loss=0.2812, pruned_loss=0.07522, over 4823.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2255, pruned_loss=0.04333, over 972037.13 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:26:18,053 INFO [train.py:715] (5/8) Epoch 4, batch 29700, loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04285, over 4861.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04359, over 972655.13 frames.], batch size: 32, lr: 4.34e-04
2022-05-05 01:26:57,622 INFO [train.py:715] (5/8) Epoch 4, batch 29750, loss[loss=0.1497, simple_loss=0.2109, pruned_loss=0.04424, over 4848.00 frames.], tot_loss[loss=0.1555, simple_loss=0.225, pruned_loss=0.043, over 973195.20 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:27:36,800 INFO [train.py:715] (5/8) Epoch 4, batch 29800, loss[loss=0.1586, simple_loss=0.228, pruned_loss=0.04463, over 4829.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.04327, over 972897.14 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:28:16,334 INFO [train.py:715] (5/8) Epoch 4, batch 29850, loss[loss=0.1417, simple_loss=0.2201, pruned_loss=0.0317, over 4807.00 frames.], tot_loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.04281, over 972847.60 frames.], batch size: 25, lr: 4.34e-04
2022-05-05 01:28:55,199 INFO [train.py:715] (5/8) Epoch 4, batch 29900, loss[loss=0.117, simple_loss=0.1859, pruned_loss=0.02401, over 4825.00 frames.], tot_loss[loss=0.1555, simple_loss=0.225, pruned_loss=0.04299, over 972370.93 frames.], batch size: 13, lr: 4.34e-04
2022-05-05 01:29:34,840 INFO [train.py:715] (5/8) Epoch 4, batch 29950, loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.0404, over 4986.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.04289, over 971979.30 frames.], batch size: 26, lr: 4.34e-04
2022-05-05 01:30:13,994 INFO [train.py:715] (5/8) Epoch 4, batch 30000, loss[loss=0.1275, simple_loss=0.2057, pruned_loss=0.02464, over 4812.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.04268, over 971762.34 frames.], batch size: 25, lr: 4.34e-04
2022-05-05 01:30:13,995 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 01:30:23,828 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1113, simple_loss=0.1968, pruned_loss=0.01286, over 914524.00 frames.
2022-05-05 01:31:03,995 INFO [train.py:715] (5/8) Epoch 4, batch 30050, loss[loss=0.1536, simple_loss=0.2367, pruned_loss=0.03525, over 4943.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2251, pruned_loss=0.04256, over 971506.86 frames.], batch size: 21, lr: 4.33e-04
2022-05-05 01:31:43,423 INFO [train.py:715] (5/8) Epoch 4, batch 30100, loss[loss=0.1285, simple_loss=0.2054, pruned_loss=0.02585, over 4823.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04243, over 971497.74 frames.], batch size: 26, lr: 4.33e-04
2022-05-05 01:32:23,322 INFO [train.py:715] (5/8) Epoch 4, batch 30150, loss[loss=0.1499, simple_loss=0.2263, pruned_loss=0.03677, over 4911.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2245, pruned_loss=0.04238, over 971942.54 frames.], batch size: 19, lr: 4.33e-04
2022-05-05 01:33:02,790 INFO [train.py:715] (5/8) Epoch 4, batch 30200, loss[loss=0.1802, simple_loss=0.2406, pruned_loss=0.0599, over 4859.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2256, pruned_loss=0.04343, over 972447.70 frames.], batch size: 20, lr: 4.33e-04
2022-05-05 01:33:42,426 INFO [train.py:715] (5/8) Epoch 4, batch 30250, loss[loss=0.1816, simple_loss=0.251, pruned_loss=0.05615, over 4928.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04388, over 972750.74 frames.], batch size: 39, lr: 4.33e-04
2022-05-05 01:34:21,594 INFO [train.py:715] (5/8) Epoch 4, batch 30300, loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02926, over 4860.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2258, pruned_loss=0.04378, over 972265.73 frames.], batch size: 20, lr: 4.33e-04
2022-05-05 01:35:01,077 INFO [train.py:715] (5/8) Epoch 4, batch 30350, loss[loss=0.1914, simple_loss=0.2506, pruned_loss=0.06612, over 4704.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2256, pruned_loss=0.0436, over 972167.50 frames.], batch size: 15, lr: 4.33e-04
2022-05-05 01:35:41,054 INFO [train.py:715] (5/8) Epoch 4, batch 30400, loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03958, over 4754.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2254, pruned_loss=0.04343, over 972749.23 frames.], batch size: 12, lr: 4.33e-04
2022-05-05 01:36:20,214 INFO [train.py:715] (5/8) Epoch 4, batch 30450, loss[loss=0.1726, simple_loss=0.2464, pruned_loss=0.04938, over 4918.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04307, over 973745.24 frames.], batch size: 18, lr: 4.33e-04
2022-05-05 01:36:59,980 INFO [train.py:715] (5/8) Epoch 4, batch 30500, loss[loss=0.1699, simple_loss=0.2411, pruned_loss=0.04936, over 4924.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2261, pruned_loss=0.0432, over 973639.47 frames.], batch size: 29, lr: 4.33e-04
2022-05-05 01:37:40,026 INFO [train.py:715] (5/8) Epoch 4, batch 30550, loss[loss=0.1689, simple_loss=0.24, pruned_loss=0.04895, over 4770.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2259, pruned_loss=0.04315, over 973344.82 frames.], batch size: 17, lr: 4.33e-04
2022-05-05 01:38:19,333 INFO [train.py:715] (5/8) Epoch 4, batch 30600, loss[loss=0.1414, simple_loss=0.2097, pruned_loss=0.03655, over 4811.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2256, pruned_loss=0.04253, over 973247.21 frames.], batch size: 21, lr: 4.33e-04
2022-05-05 01:38:58,940 INFO [train.py:715] (5/8) Epoch 4, batch 30650, loss[loss=0.1534, simple_loss=0.2304, pruned_loss=0.03813, over 4805.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04168, over 972744.96 frames.], batch size: 24, lr: 4.33e-04
2022-05-05 01:39:38,414 INFO [train.py:715] (5/8) Epoch 4, batch 30700, loss[loss=0.1572, simple_loss=0.2222, pruned_loss=0.04614, over 4854.00 frames.], tot_loss[loss=0.1539, simple_loss=0.224, pruned_loss=0.04187, over 972383.04 frames.], batch size: 32, lr: 4.33e-04
2022-05-05 01:40:18,147 INFO [train.py:715] (5/8) Epoch 4, batch 30750, loss[loss=0.1589, simple_loss=0.2211, pruned_loss=0.04835, over 4831.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.0415, over 972551.72 frames.], batch size: 13, lr: 4.33e-04
2022-05-05 01:40:57,684 INFO [train.py:715] (5/8) Epoch 4, batch 30800, loss[loss=0.1783, simple_loss=0.2449, pruned_loss=0.05587, over 4969.00 frames.], tot_loss[loss=0.1536, simple_loss=0.224, pruned_loss=0.04162, over 973658.15 frames.], batch size: 14, lr: 4.32e-04
2022-05-05 01:41:37,510 INFO [train.py:715] (5/8) Epoch 4, batch 30850, loss[loss=0.1902, simple_loss=0.2516, pruned_loss=0.06442, over 4967.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2248, pruned_loss=0.04205, over 973373.01 frames.], batch size: 35, lr: 4.32e-04
2022-05-05 01:42:17,791 INFO [train.py:715] (5/8) Epoch 4, batch 30900, loss[loss=0.1531, simple_loss=0.2265, pruned_loss=0.03984, over 4907.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2261, pruned_loss=0.04305, over 973550.10 frames.], batch size: 39, lr: 4.32e-04
2022-05-05 01:42:57,263 INFO [train.py:715] (5/8) Epoch 4, batch 30950, loss[loss=0.187, simple_loss=0.2708, pruned_loss=0.05161, over 4946.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04327, over 973344.92 frames.], batch size: 29, lr: 4.32e-04
2022-05-05 01:43:36,634 INFO [train.py:715] (5/8) Epoch 4, batch 31000, loss[loss=0.1509, simple_loss=0.2172, pruned_loss=0.04234, over 4696.00 frames.], tot_loss[loss=0.156, simple_loss=0.226, pruned_loss=0.04306, over 973335.69 frames.], batch size: 15, lr: 4.32e-04
2022-05-05 01:44:16,108 INFO [train.py:715] (5/8) Epoch 4, batch 31050, loss[loss=0.1886, simple_loss=0.2568, pruned_loss=0.06022, over 4871.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.04325, over 972609.70 frames.], batch size: 32, lr: 4.32e-04
2022-05-05 01:44:55,521 INFO [train.py:715] (5/8) Epoch 4, batch 31100, loss[loss=0.1551, simple_loss=0.2077, pruned_loss=0.05129, over 4833.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04373, over 971768.38 frames.], batch size: 13, lr: 4.32e-04
2022-05-05 01:45:35,033 INFO [train.py:715] (5/8) Epoch 4, batch 31150, loss[loss=0.1617, simple_loss=0.2317, pruned_loss=0.04583, over 4763.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.04368, over 971792.73 frames.], batch size: 19, lr: 4.32e-04
2022-05-05 01:46:13,900 INFO [train.py:715] (5/8) Epoch 4, batch 31200, loss[loss=0.204, simple_loss=0.2625, pruned_loss=0.07271, over 4777.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.0434, over 971128.30 frames.], batch size: 18, lr: 4.32e-04
2022-05-05 01:46:53,972 INFO [train.py:715] (5/8) Epoch 4, batch 31250, loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04292, over 4930.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2271, pruned_loss=0.04377, over 971425.04 frames.], batch size: 23, lr: 4.32e-04
2022-05-05 01:47:33,182 INFO [train.py:715] (5/8) Epoch 4, batch 31300, loss[loss=0.1668, simple_loss=0.232, pruned_loss=0.05077, over 4872.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2258, pruned_loss=0.04336, over 971055.90 frames.], batch size: 16, lr: 4.32e-04
2022-05-05 01:48:12,188 INFO [train.py:715] (5/8) Epoch 4, batch 31350, loss[loss=0.1329, simple_loss=0.2011, pruned_loss=0.0323, over 4690.00 frames.], tot_loss[loss=0.157, simple_loss=0.2263, pruned_loss=0.04385, over 972229.67 frames.], batch size: 15, lr: 4.32e-04
2022-05-05 01:48:52,070 INFO [train.py:715] (5/8) Epoch 4, batch 31400, loss[loss=0.1448, simple_loss=0.2108, pruned_loss=0.03938, over 4981.00 frames.], tot_loss[loss=0.156, simple_loss=0.2257, pruned_loss=0.04316, over 972392.27 frames.], batch size: 25, lr: 4.32e-04
2022-05-05 01:49:31,805 INFO [train.py:715] (5/8) Epoch 4, batch 31450, loss[loss=0.1619, simple_loss=0.2235, pruned_loss=0.05015, over 4832.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2256, pruned_loss=0.04304, over 971568.41 frames.], batch size: 13, lr: 4.32e-04
2022-05-05 01:50:11,369 INFO [train.py:715] (5/8) Epoch 4, batch 31500, loss[loss=0.1451, simple_loss=0.2178, pruned_loss=0.03624, over 4840.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04338, over 972711.49 frames.], batch size: 30, lr: 4.32e-04
2022-05-05 01:50:51,744 INFO [train.py:715] (5/8) Epoch 4, batch 31550, loss[loss=0.1464, simple_loss=0.2205, pruned_loss=0.03619, over 4832.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2263, pruned_loss=0.04371, over 972701.03 frames.], batch size: 26, lr: 4.32e-04
2022-05-05 01:51:32,265 INFO [train.py:715] (5/8) Epoch 4, batch 31600, loss[loss=0.2006, simple_loss=0.2835, pruned_loss=0.05884, over 4729.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04339, over 972103.44 frames.], batch size: 16, lr: 4.31e-04
2022-05-05 01:52:11,916 INFO [train.py:715] (5/8) Epoch 4, batch 31650, loss[loss=0.1851, simple_loss=0.257, pruned_loss=0.05658, over 4802.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2271, pruned_loss=0.04358, over 972015.07 frames.], batch size: 21, lr: 4.31e-04
2022-05-05 01:52:51,499 INFO [train.py:715] (5/8) Epoch 4, batch 31700, loss[loss=0.2106, simple_loss=0.2749, pruned_loss=0.07317, over 4956.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.04383, over 971800.85 frames.], batch size: 15, lr: 4.31e-04
2022-05-05 01:53:31,555 INFO [train.py:715] (5/8) Epoch 4, batch 31750, loss[loss=0.1552, simple_loss=0.2227, pruned_loss=0.04385, over 4775.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2273, pruned_loss=0.04373, over 971558.96 frames.], batch size: 12, lr: 4.31e-04
2022-05-05 01:54:11,602 INFO [train.py:715] (5/8) Epoch 4, batch 31800, loss[loss=0.1549, simple_loss=0.2216, pruned_loss=0.04413, over 4796.00 frames.], tot_loss[loss=0.1572, simple_loss=0.227, pruned_loss=0.04371, over 970775.71 frames.], batch size: 21, lr: 4.31e-04
2022-05-05 01:54:51,202 INFO [train.py:715] (5/8) Epoch 4, batch 31850, loss[loss=0.1757, simple_loss=0.2495, pruned_loss=0.05098, over 4977.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2276, pruned_loss=0.04393, over 971210.12 frames.], batch size: 35, lr: 4.31e-04
2022-05-05 01:55:30,805 INFO [train.py:715] (5/8) Epoch 4, batch 31900, loss[loss=0.1765, simple_loss=0.2356, pruned_loss=0.05872, over 4897.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2272, pruned_loss=0.0439, over 971880.71 frames.], batch size: 17, lr: 4.31e-04
2022-05-05 01:56:11,027 INFO [train.py:715] (5/8) Epoch 4, batch 31950, loss[loss=0.1515, simple_loss=0.2106, pruned_loss=0.04623, over 4876.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.04348, over 972303.03 frames.], batch size: 32, lr: 4.31e-04
2022-05-05 01:56:50,986 INFO [train.py:715] (5/8) Epoch 4, batch 32000, loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03988, over 4876.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.04349, over 972680.86 frames.], batch size: 22, lr: 4.31e-04
2022-05-05 01:57:30,376 INFO [train.py:715] (5/8) Epoch 4, batch 32050, loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.0328, over 4902.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04381, over 972382.48 frames.], batch size: 19, lr: 4.31e-04
2022-05-05 01:58:10,941 INFO [train.py:715] (5/8) Epoch 4, batch 32100, loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03589, over 4986.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04313, over 973061.02 frames.], batch size: 25, lr: 4.31e-04
2022-05-05 01:58:50,866 INFO [train.py:715] (5/8) Epoch 4, batch 32150, loss[loss=0.1449, simple_loss=0.221, pruned_loss=0.03445, over 4954.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2264, pruned_loss=0.04285, over 971796.79 frames.], batch size: 24, lr: 4.31e-04
2022-05-05 01:59:30,405 INFO [train.py:715] (5/8) Epoch 4, batch 32200, loss[loss=0.137, simple_loss=0.2087, pruned_loss=0.03262, over 4861.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.04269, over 972380.87 frames.], batch size: 13, lr: 4.31e-04
2022-05-05 02:00:10,362 INFO [train.py:715] (5/8) Epoch 4, batch 32250, loss[loss=0.151, simple_loss=0.226, pruned_loss=0.03799, over 4795.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.0428, over 973391.06 frames.], batch size: 21, lr: 4.31e-04
2022-05-05 02:00:51,157 INFO [train.py:715] (5/8) Epoch 4, batch 32300, loss[loss=0.121, simple_loss=0.1897, pruned_loss=0.02614, over 4968.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2257, pruned_loss=0.04264, over 973862.24 frames.], batch size: 14, lr: 4.31e-04
2022-05-05 02:01:31,941 INFO [train.py:715] (5/8) Epoch 4, batch 32350, loss[loss=0.1818, simple_loss=0.2464, pruned_loss=0.05862, over 4960.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2255, pruned_loss=0.04265, over 973005.67 frames.], batch size: 24, lr: 4.31e-04
2022-05-05 02:02:12,274 INFO [train.py:715] (5/8) Epoch 4, batch 32400, loss[loss=0.1276, simple_loss=0.2063, pruned_loss=0.0244, over 4751.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04305, over 972076.86 frames.], batch size: 16, lr: 4.30e-04
2022-05-05 02:02:52,628 INFO [train.py:715] (5/8) Epoch 4, batch 32450, loss[loss=0.1415, simple_loss=0.2129, pruned_loss=0.03501, over 4797.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.0429, over 972235.64 frames.], batch size: 25, lr: 4.30e-04
2022-05-05 02:03:31,862 INFO [train.py:715] (5/8) Epoch 4, batch 32500, loss[loss=0.1068, simple_loss=0.1914, pruned_loss=0.01111, over 4862.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04306, over 972138.61 frames.], batch size: 20, lr: 4.30e-04
2022-05-05 02:04:11,769 INFO [train.py:715] (5/8) Epoch 4, batch 32550, loss[loss=0.1285, simple_loss=0.1985, pruned_loss=0.02923, over 4922.00 frames.], tot_loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.04281, over 972919.64 frames.], batch size: 23, lr: 4.30e-04
2022-05-05 02:04:50,738 INFO [train.py:715] (5/8) Epoch 4, batch 32600, loss[loss=0.1545, simple_loss=0.2245, pruned_loss=0.04229, over 4922.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.0428, over 972113.31 frames.], batch size: 29, lr: 4.30e-04
2022-05-05 02:05:30,803 INFO [train.py:715] (5/8) Epoch 4, batch 32650, loss[loss=0.1802, simple_loss=0.2474, pruned_loss=0.0565, over 4907.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2254, pruned_loss=0.04296, over 972724.76 frames.], batch size: 19, lr: 4.30e-04
2022-05-05 02:06:09,913 INFO [train.py:715] (5/8) Epoch 4, batch 32700, loss[loss=0.1799, simple_loss=0.2393, pruned_loss=0.06023, over 4871.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2252, pruned_loss=0.04308, over 972197.69 frames.], batch size: 20, lr: 4.30e-04
2022-05-05 02:06:49,545 INFO [train.py:715] (5/8) Epoch 4, batch 32750, loss[loss=0.1538, simple_loss=0.2292, pruned_loss=0.03916, over 4823.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04312, over 971105.23 frames.], batch size: 26, lr: 4.30e-04
2022-05-05 02:07:29,259 INFO [train.py:715] (5/8) Epoch 4, batch 32800, loss[loss=0.1297, simple_loss=0.1883, pruned_loss=0.03558, over 4867.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04297, over 971498.34 frames.], batch size: 13, lr: 4.30e-04
2022-05-05 02:08:09,337 INFO [train.py:715] (5/8) Epoch 4, batch 32850, loss[loss=0.156, simple_loss=0.2278, pruned_loss=0.04214, over 4983.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2257, pruned_loss=0.04284, over 971824.42 frames.], batch size: 15, lr: 4.30e-04
2022-05-05 02:08:49,846 INFO [train.py:715] (5/8) Epoch 4, batch 32900, loss[loss=0.1526, simple_loss=0.2309, pruned_loss=0.03719, over 4805.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04289, over 971398.27 frames.], batch size: 21, lr: 4.30e-04
2022-05-05 02:09:30,076 INFO [train.py:715] (5/8) Epoch 4, batch 32950, loss[loss=0.131, simple_loss=0.1977, pruned_loss=0.03215, over 4787.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2261, pruned_loss=0.04306, over 971444.62 frames.], batch size: 12, lr: 4.30e-04
2022-05-05 02:10:10,302 INFO [train.py:715] (5/8) Epoch 4, batch 33000, loss[loss=0.1936, simple_loss=0.2394, pruned_loss=0.0739, over 4735.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04324, over 970566.46 frames.], batch size: 16, lr: 4.30e-04
2022-05-05 02:10:10,303 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 02:10:20,091 INFO [train.py:742] (5/8) Epoch 4, validation: loss=0.1115, simple_loss=0.197, pruned_loss=0.01298, over 914524.00 frames.
2022-05-05 02:11:00,301 INFO [train.py:715] (5/8) Epoch 4, batch 33050, loss[loss=0.149, simple_loss=0.2183, pruned_loss=0.03983, over 4935.00 frames.], tot_loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04341, over 970745.48 frames.], batch size: 23, lr: 4.30e-04
2022-05-05 02:11:40,006 INFO [train.py:715] (5/8) Epoch 4, batch 33100, loss[loss=0.1834, simple_loss=0.2466, pruned_loss=0.06015, over 4897.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04346, over 970266.99 frames.], batch size: 19, lr: 4.30e-04
2022-05-05 02:12:20,026 INFO [train.py:715] (5/8) Epoch 4, batch 33150, loss[loss=0.1587, simple_loss=0.2197, pruned_loss=0.04884, over 4859.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2268, pruned_loss=0.04349, over 970846.06 frames.], batch size: 30, lr: 4.30e-04
2022-05-05 02:13:00,226 INFO [train.py:715] (5/8) Epoch 4, batch 33200, loss[loss=0.1312, simple_loss=0.2006, pruned_loss=0.03087, over 4868.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04332, over 970479.53 frames.], batch size: 20, lr: 4.29e-04
2022-05-05 02:13:40,202 INFO [train.py:715] (5/8) Epoch 4, batch 33250, loss[loss=0.1328, simple_loss=0.206, pruned_loss=0.02982, over 4717.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.04308, over 970579.76 frames.], batch size: 15, lr: 4.29e-04
2022-05-05 02:14:20,214 INFO [train.py:715] (5/8) Epoch 4, batch 33300, loss[loss=0.1413, simple_loss=0.2188, pruned_loss=0.03195, over 4897.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04318, over 971054.86 frames.], batch size: 19, lr: 4.29e-04
2022-05-05 02:14:59,209 INFO [train.py:715] (5/8) Epoch 4, batch 33350, loss[loss=0.1405, simple_loss=0.2112, pruned_loss=0.03494, over 4898.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2266, pruned_loss=0.04322, over 971553.12 frames.], batch size: 19, lr: 4.29e-04
2022-05-05 02:15:38,981 INFO [train.py:715] (5/8) Epoch 4, batch 33400, loss[loss=0.171, simple_loss=0.2519, pruned_loss=0.04511, over 4990.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2267, pruned_loss=0.04294, over 970997.11 frames.], batch size: 20, lr: 4.29e-04
2022-05-05 02:16:18,845 INFO [train.py:715] (5/8) Epoch 4, batch 33450, loss[loss=0.1823, simple_loss=0.2574, pruned_loss=0.05355, over 4946.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2268, pruned_loss=0.0433, over 970811.84 frames.], batch size: 39, lr: 4.29e-04
2022-05-05 02:16:58,396 INFO [train.py:715] (5/8) Epoch 4, batch 33500, loss[loss=0.1376, simple_loss=0.2096, pruned_loss=0.03277, over 4932.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2269, pruned_loss=0.043, over 971196.09 frames.], batch size: 23, lr: 4.29e-04
2022-05-05 02:17:38,200 INFO [train.py:715] (5/8) Epoch 4, batch 33550, loss[loss=0.1596, simple_loss=0.2264, pruned_loss=0.04644, over 4742.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2253, pruned_loss=0.0426, over 971888.17 frames.], batch size: 16, lr: 4.29e-04
2022-05-05 02:18:17,700 INFO [train.py:715] (5/8) Epoch 4, batch 33600, loss[loss=0.1363, simple_loss=0.2028, pruned_loss=0.03496, over 4901.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2256, pruned_loss=0.04268, over 971216.59 frames.], batch size: 17, lr: 4.29e-04
2022-05-05 02:18:57,441 INFO [train.py:715] (5/8) Epoch 4, batch 33650, loss[loss=0.1435, simple_loss=0.2115, pruned_loss=0.03776, over 4930.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2244, pruned_loss=0.042, over 971377.91 frames.], batch size: 29, lr: 4.29e-04
2022-05-05 02:19:36,829 INFO [train.py:715] (5/8) Epoch 4, batch 33700, loss[loss=0.2131, simple_loss=0.2717, pruned_loss=0.07724, over 4880.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04271, over 971479.83 frames.], batch size: 19, lr: 4.29e-04
2022-05-05 02:20:16,624 INFO [train.py:715] (5/8) Epoch 4, batch 33750, loss[loss=0.2087, simple_loss=0.2875, pruned_loss=0.06497, over 4888.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2253, pruned_loss=0.04254, over 971780.82 frames.], batch size: 17, lr: 4.29e-04
2022-05-05 02:20:56,488 INFO [train.py:715] (5/8) Epoch 4, batch 33800, loss[loss=0.1506, simple_loss=0.222, pruned_loss=0.03958, over 4960.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2247, pruned_loss=0.04251, over 972325.37 frames.], batch size: 24, lr: 4.29e-04
2022-05-05 02:21:35,971 INFO [train.py:715] (5/8) Epoch 4, batch 33850, loss[loss=0.1617, simple_loss=0.2365, pruned_loss=0.04341, over 4766.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04292, over 971799.74 frames.], batch size: 18, lr: 4.29e-04
2022-05-05 02:22:15,605 INFO [train.py:715] (5/8) Epoch 4, batch 33900, loss[loss=0.1823, simple_loss=0.2468, pruned_loss=0.0589, over 4975.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2248, pruned_loss=0.04276, over 972911.36 frames.], batch size: 35, lr: 4.29e-04
2022-05-05 02:22:55,359 INFO [train.py:715] (5/8) Epoch 4, batch 33950, loss[loss=0.1506, simple_loss=0.2169, pruned_loss=0.04213, over 4743.00 frames.], tot_loss[loss=0.154, simple_loss=0.2234, pruned_loss=0.04229, over 971946.57 frames.], batch size: 16, lr: 4.29e-04
2022-05-05 02:23:35,326 INFO [train.py:715] (5/8) Epoch 4, batch 34000, loss[loss=0.1867, simple_loss=0.2404, pruned_loss=0.06651, over 4696.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2236, pruned_loss=0.0424, over 972452.06 frames.], batch size: 15, lr: 4.28e-04
2022-05-05 02:24:14,851 INFO [train.py:715] (5/8) Epoch 4, batch 34050, loss[loss=0.1366, simple_loss=0.192, pruned_loss=0.0406, over 4815.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2245, pruned_loss=0.04283, over 972307.73 frames.], batch size: 13, lr: 4.28e-04
2022-05-05 02:24:54,572 INFO [train.py:715] (5/8) Epoch 4, batch 34100, loss[loss=0.1477, simple_loss=0.2229, pruned_loss=0.03624, over 4926.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2244, pruned_loss=0.04261, over 972543.91 frames.], batch size: 23, lr: 4.28e-04
2022-05-05 02:25:34,631 INFO [train.py:715] (5/8) Epoch 4, batch 34150, loss[loss=0.1397, simple_loss=0.2113, pruned_loss=0.03411, over 4806.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2231, pruned_loss=0.0421, over 971976.10 frames.], batch size: 25, lr: 4.28e-04
2022-05-05 02:26:13,486 INFO [train.py:715] (5/8) Epoch 4, batch 34200, loss[loss=0.1382, simple_loss=0.2058, pruned_loss=0.03533, over 4825.00 frames.], tot_loss[loss=0.1531, simple_loss=0.223, pruned_loss=0.04157, over 973378.43 frames.], batch size: 12, lr: 4.28e-04
2022-05-05 02:26:54,317 INFO [train.py:715] (5/8) Epoch 4, batch 34250, loss[loss=0.1725, simple_loss=0.2385, pruned_loss=0.0532, over 4981.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2237, pruned_loss=0.04221, over 973637.02 frames.], batch size: 28, lr: 4.28e-04
2022-05-05 02:27:34,191 INFO [train.py:715] (5/8) Epoch 4, batch 34300, loss[loss=0.1582, simple_loss=0.2253, pruned_loss=0.04555, over 4790.00 frames.], tot_loss[loss=0.155, simple_loss=0.2245, pruned_loss=0.04271, over 973550.15 frames.], batch size: 12, lr: 4.28e-04
2022-05-05 02:28:13,952 INFO [train.py:715] (5/8) Epoch 4, batch 34350, loss[loss=0.1405, simple_loss=0.2168, pruned_loss=0.03207, over 4946.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04221, over 973478.53 frames.], batch size: 35, lr: 4.28e-04
2022-05-05 02:28:53,974 INFO [train.py:715] (5/8) Epoch 4, batch 34400, loss[loss=0.1637, simple_loss=0.2245, pruned_loss=0.0515, over 4882.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2235, pruned_loss=0.04206, over 972691.38 frames.], batch size: 16, lr: 4.28e-04
2022-05-05 02:29:33,808 INFO [train.py:715] (5/8) Epoch 4, batch 34450, loss[loss=0.1476, simple_loss=0.2161, pruned_loss=0.03956, over 4836.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2239, pruned_loss=0.04199, over 973545.39 frames.], batch size: 13, lr: 4.28e-04
2022-05-05 02:30:14,468 INFO [train.py:715] (5/8) Epoch 4, batch 34500, loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03635, over 4845.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2247, pruned_loss=0.04302, over 973596.83 frames.], batch size: 13, lr: 4.28e-04
2022-05-05 02:30:53,316 INFO [train.py:715] (5/8) Epoch 4, batch 34550, loss[loss=0.169, simple_loss=0.2452, pruned_loss=0.04638, over 4748.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2251, pruned_loss=0.04292, over 972778.15 frames.], batch size: 16, lr: 4.28e-04
2022-05-05 02:31:33,260 INFO [train.py:715] (5/8) Epoch 4, batch 34600, loss[loss=0.1419, simple_loss=0.2257, pruned_loss=0.02911, over 4776.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04308, over 973039.47 frames.], batch size: 18, lr: 4.28e-04
2022-05-05 02:32:13,236 INFO [train.py:715] (5/8) Epoch 4, batch 34650, loss[loss=0.162, simple_loss=0.2302, pruned_loss=0.04696, over 4833.00 frames.], tot_loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.04283, over 972926.68 frames.], batch size: 30, lr: 4.28e-04
2022-05-05 02:32:52,590 INFO [train.py:715] (5/8) Epoch 4, batch 34700, loss[loss=0.1479, simple_loss=0.2164, pruned_loss=0.03973, over 4828.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04347, over 972273.97 frames.], batch size: 30, lr: 4.28e-04
2022-05-05 02:33:30,874 INFO [train.py:715] (5/8) Epoch 4, batch 34750, loss[loss=0.1189, simple_loss=0.1994, pruned_loss=0.01922, over 4934.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2265, pruned_loss=0.04354, over 972263.37 frames.], batch size: 23, lr: 4.28e-04
2022-05-05 02:34:07,934 INFO [train.py:715] (5/8) Epoch 4, batch 34800, loss[loss=0.1944, simple_loss=0.2667, pruned_loss=0.06105, over 4883.00 frames.], tot_loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04339, over 973511.88 frames.], batch size: 19, lr: 4.27e-04
2022-05-05 02:34:57,759 INFO [train.py:715] (5/8) Epoch 5, batch 0, loss[loss=0.1494, simple_loss=0.2136, pruned_loss=0.04258, over 4868.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2136, pruned_loss=0.04258, over 4868.00 frames.], batch size: 16, lr: 4.02e-04
2022-05-05 02:35:38,098 INFO [train.py:715] (5/8) Epoch 5, batch 50, loss[loss=0.1521, simple_loss=0.2235, pruned_loss=0.04034, over 4885.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2246, pruned_loss=0.04183, over 218752.90 frames.], batch size: 16, lr: 4.02e-04
2022-05-05 02:36:17,796 INFO [train.py:715] (5/8) Epoch 5, batch 100, loss[loss=0.1197, simple_loss=0.1937, pruned_loss=0.02286, over 4818.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04103, over 386531.24 frames.], batch size: 26, lr: 4.02e-04
2022-05-05 02:36:57,764 INFO [train.py:715] (5/8) Epoch 5, batch 150, loss[loss=0.1558, simple_loss=0.2208, pruned_loss=0.04547, over 4865.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.041, over 516088.53 frames.], batch size: 30, lr: 4.02e-04
2022-05-05 02:37:38,284 INFO [train.py:715] (5/8) Epoch 5, batch 200, loss[loss=0.1636, simple_loss=0.2232, pruned_loss=0.05194, over 4941.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04226, over 616885.96 frames.], batch size: 35, lr: 4.02e-04
2022-05-05 02:38:17,736 INFO [train.py:715] (5/8) Epoch 5, batch 250, loss[loss=0.1569, simple_loss=0.2284, pruned_loss=0.04273, over 4984.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04161, over 695429.16 frames.], batch size: 31, lr: 4.02e-04
2022-05-05 02:38:57,154 INFO [train.py:715] (5/8) Epoch 5, batch 300, loss[loss=0.1337, simple_loss=0.2088, pruned_loss=0.02933, over 4905.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04185, over 756353.32 frames.], batch size: 17, lr: 4.01e-04
2022-05-05 02:39:36,893 INFO [train.py:715] (5/8) Epoch 5, batch 350, loss[loss=0.1949, simple_loss=0.2644, pruned_loss=0.0627, over 4729.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.04157, over 804204.38 frames.], batch size: 16, lr: 4.01e-04
2022-05-05 02:40:16,659 INFO [train.py:715] (5/8) Epoch 5, batch 400, loss[loss=0.1298, simple_loss=0.1951, pruned_loss=0.03224, over 4911.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04183, over 841892.16 frames.], batch size: 18, lr: 4.01e-04
2022-05-05 02:40:56,050 INFO [train.py:715] (5/8) Epoch 5, batch 450, loss[loss=0.1224, simple_loss=0.2106, pruned_loss=0.01711, over 4904.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2231, pruned_loss=0.04131, over 870439.40 frames.], batch size: 18, lr: 4.01e-04
2022-05-05 02:41:35,799 INFO [train.py:715] (5/8) Epoch 5, batch 500, loss[loss=0.1816, simple_loss=0.2623, pruned_loss=0.05049, over 4947.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2243, pruned_loss=0.04168, over 892735.72 frames.], batch size: 39, lr: 4.01e-04
2022-05-05 02:42:15,653 INFO [train.py:715] (5/8) Epoch 5, batch 550, loss[loss=0.1628, simple_loss=0.222, pruned_loss=0.05178, over 4905.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04198, over 910286.98 frames.], batch size: 17, lr: 4.01e-04
2022-05-05 02:42:54,758 INFO [train.py:715] (5/8) Epoch 5, batch 600, loss[loss=0.1262, simple_loss=0.1963, pruned_loss=0.02808, over 4745.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04246, over 923963.56 frames.], batch size: 19, lr: 4.01e-04
2022-05-05 02:43:34,140 INFO [train.py:715] (5/8) Epoch 5, batch 650, loss[loss=0.1552, simple_loss=0.2239, pruned_loss=0.04326, over 4800.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.04222, over 934407.38 frames.], batch size: 25, lr: 4.01e-04
2022-05-05 02:44:13,847 INFO [train.py:715] (5/8) Epoch 5, batch 700, loss[loss=0.14, simple_loss=0.2022, pruned_loss=0.03894, over 4771.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2241, pruned_loss=0.04232, over 943297.80 frames.], batch size: 12, lr: 4.01e-04
2022-05-05 02:44:53,908 INFO [train.py:715] (5/8) Epoch 5, batch 750, loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.0394, over 4847.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2238, pruned_loss=0.04233, over 949913.42 frames.], batch size: 30, lr: 4.01e-04
2022-05-05 02:45:33,280 INFO [train.py:715] (5/8) Epoch 5, batch 800, loss[loss=0.1654, simple_loss=0.2381, pruned_loss=0.04628, over 4970.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04226, over 954645.92 frames.], batch size: 14, lr: 4.01e-04
2022-05-05 02:46:12,786 INFO [train.py:715] (5/8) Epoch 5, batch 850, loss[loss=0.2226, simple_loss=0.2754, pruned_loss=0.08496, over 4694.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2243, pruned_loss=0.0425, over 958406.10 frames.], batch size: 15, lr: 4.01e-04
2022-05-05 02:46:52,362 INFO [train.py:715] (5/8) Epoch 5, batch 900, loss[loss=0.156, simple_loss=0.2207, pruned_loss=0.04562, over 4914.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2237, pruned_loss=0.04195, over 961944.42 frames.], batch size: 18, lr: 4.01e-04
2022-05-05 02:47:31,842 INFO [train.py:715] (5/8) Epoch 5, batch 950, loss[loss=0.169, simple_loss=0.2416, pruned_loss=0.0482, over 4971.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2236, pruned_loss=0.04158, over 964256.89 frames.], batch size: 28, lr: 4.01e-04
2022-05-05 02:48:11,353 INFO [train.py:715] (5/8) Epoch 5, batch 1000, loss[loss=0.1575, simple_loss=0.2214, pruned_loss=0.04676, over 4970.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2247, pruned_loss=0.04199, over 966078.45 frames.], batch size: 35, lr: 4.01e-04
2022-05-05 02:48:50,614 INFO [train.py:715] (5/8) Epoch 5, batch 1050, loss[loss=0.1671, simple_loss=0.2297, pruned_loss=0.05221, over 4906.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2237, pruned_loss=0.04158, over 967045.12 frames.], batch size: 17, lr: 4.01e-04
2022-05-05 02:49:30,324 INFO [train.py:715] (5/8) Epoch 5, batch 1100, loss[loss=0.1308, simple_loss=0.2001, pruned_loss=0.03076, over 4642.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04157, over 968866.62 frames.], batch size: 13, lr: 4.01e-04
2022-05-05 02:50:09,330 INFO [train.py:715] (5/8) Epoch 5, batch 1150, loss[loss=0.154, simple_loss=0.2326, pruned_loss=0.03771, over 4878.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04138, over 969834.75 frames.], batch size: 22, lr: 4.00e-04
2022-05-05 02:50:49,093 INFO [train.py:715] (5/8) Epoch 5, batch 1200, loss[loss=0.1476, simple_loss=0.2229, pruned_loss=0.03614, over 4789.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2237, pruned_loss=0.04164, over 969343.93 frames.], batch size: 14, lr: 4.00e-04
2022-05-05 02:51:29,238 INFO [train.py:715] (5/8) Epoch 5, batch 1250, loss[loss=0.1398, simple_loss=0.2074, pruned_loss=0.03609, over 4855.00 frames.], tot_loss[loss=0.1539, simple_loss=0.224, pruned_loss=0.04186, over 970735.21 frames.], batch size: 32, lr: 4.00e-04
2022-05-05 02:52:08,409 INFO [train.py:715] (5/8) Epoch 5, batch 1300, loss[loss=0.2223, simple_loss=0.2987, pruned_loss=0.07291, over 4881.00 frames.], tot_loss[loss=0.154, simple_loss=0.2241, pruned_loss=0.04195, over 970808.87 frames.], batch size: 19, lr: 4.00e-04
2022-05-05 02:52:48,187 INFO [train.py:715] (5/8) Epoch 5, batch 1350, loss[loss=0.1614, simple_loss=0.2241, pruned_loss=0.0493, over 4834.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2233, pruned_loss=0.04111, over 971352.88 frames.], batch size: 26, lr: 4.00e-04
2022-05-05 02:53:27,485 INFO [train.py:715] (5/8) Epoch 5, batch 1400, loss[loss=0.1593, simple_loss=0.2263, pruned_loss=0.04619, over 4689.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04113, over 971318.38 frames.], batch size: 15, lr: 4.00e-04
2022-05-05 02:54:07,303 INFO [train.py:715] (5/8) Epoch 5, batch 1450, loss[loss=0.1533, simple_loss=0.2207, pruned_loss=0.04297, over 4770.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2235, pruned_loss=0.04109, over 972113.66 frames.], batch size: 19, lr: 4.00e-04
2022-05-05 02:54:46,729 INFO [train.py:715] (5/8) Epoch 5, batch 1500, loss[loss=0.1339, simple_loss=0.1969, pruned_loss=0.03541, over 4845.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2241, pruned_loss=0.04144, over 971627.42 frames.], batch size: 15, lr: 4.00e-04
2022-05-05 02:55:25,724 INFO [train.py:715] (5/8) Epoch 5, batch 1550, loss[loss=0.167, simple_loss=0.2239, pruned_loss=0.05501, over 4806.00 frames.], tot_loss[loss=0.154, simple_loss=0.2246, pruned_loss=0.04166, over 971928.41 frames.], batch size: 13, lr: 4.00e-04
2022-05-05 02:56:05,365 INFO [train.py:715] (5/8) Epoch 5, batch 1600, loss[loss=0.1169, simple_loss=0.1931, pruned_loss=0.02034, over 4787.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04144, over 971963.13 frames.], batch size: 17, lr: 4.00e-04
2022-05-05 02:56:45,701 INFO [train.py:715] (5/8) Epoch 5, batch 1650, loss[loss=0.157, simple_loss=0.232, pruned_loss=0.04103, over 4795.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2249, pruned_loss=0.04201, over 972684.33 frames.], batch size: 18, lr: 4.00e-04
2022-05-05 02:57:24,645 INFO [train.py:715] (5/8) Epoch 5, batch 1700, loss[loss=0.1625, simple_loss=0.2227, pruned_loss=0.0511, over 4801.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2243, pruned_loss=0.04134, over 972630.45 frames.], batch size: 21, lr: 4.00e-04
2022-05-05 02:58:05,303 INFO [train.py:715] (5/8) Epoch 5, batch 1750, loss[loss=0.131, simple_loss=0.2083, pruned_loss=0.02689, over 4817.00 frames.], tot_loss[loss=0.154, simple_loss=0.2247, pruned_loss=0.04165, over 972556.86 frames.], batch size: 21, lr: 4.00e-04
2022-05-05 02:58:45,447 INFO [train.py:715] (5/8) Epoch 5, batch 1800, loss[loss=0.1424, simple_loss=0.2178, pruned_loss=0.03346, over 4832.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04124, over 972291.25 frames.], batch size: 25, lr: 4.00e-04
2022-05-05 02:59:25,895 INFO [train.py:715] (5/8) Epoch 5, batch 1850, loss[loss=0.176, simple_loss=0.247, pruned_loss=0.0525, over 4683.00 frames.], tot_loss[loss=0.153, simple_loss=0.2237, pruned_loss=0.04111, over 972418.43 frames.], batch size: 15, lr: 4.00e-04
2022-05-05 03:00:06,293 INFO [train.py:715] (5/8) Epoch 5, batch 1900, loss[loss=0.1655, simple_loss=0.2224, pruned_loss=0.05427, over 4972.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2245, pruned_loss=0.04142, over 972605.76 frames.], batch size: 35, lr: 4.00e-04
2022-05-05 03:00:46,052 INFO [train.py:715] (5/8) Epoch 5, batch 1950, loss[loss=0.1286, simple_loss=0.1966, pruned_loss=0.03032, over 4950.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2238, pruned_loss=0.04127, over 972866.96 frames.], batch size: 21, lr: 4.00e-04
2022-05-05 03:01:29,146 INFO [train.py:715] (5/8) Epoch 5, batch 2000, loss[loss=0.1548, simple_loss=0.2104, pruned_loss=0.04959, over 4752.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04127, over 972723.70 frames.], batch size: 16, lr: 4.00e-04
2022-05-05 03:02:09,159 INFO [train.py:715] (5/8) Epoch 5, batch 2050, loss[loss=0.1616, simple_loss=0.232, pruned_loss=0.04561, over 4935.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04127, over 972687.31 frames.], batch size: 39, lr: 3.99e-04
2022-05-05 03:02:49,518 INFO [train.py:715] (5/8) Epoch 5, batch 2100, loss[loss=0.1337, simple_loss=0.2096, pruned_loss=0.02887, over 4817.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2244, pruned_loss=0.04202, over 972784.68 frames.], batch size: 26, lr: 3.99e-04
2022-05-05 03:03:30,102 INFO [train.py:715] (5/8) Epoch 5, batch 2150, loss[loss=0.1579, simple_loss=0.2205, pruned_loss=0.04768, over 4970.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2248, pruned_loss=0.04219, over 972358.48 frames.], batch size: 33, lr: 3.99e-04
2022-05-05 03:04:09,666 INFO [train.py:715] (5/8) Epoch 5, batch 2200, loss[loss=0.1513, simple_loss=0.2247, pruned_loss=0.03896, over 4820.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2246, pruned_loss=0.04213, over 972567.92 frames.], batch size: 25, lr: 3.99e-04
2022-05-05 03:04:50,064 INFO [train.py:715] (5/8) Epoch 5, batch 2250, loss[loss=0.1705, simple_loss=0.2313, pruned_loss=0.05487, over 4815.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04255, over 971811.59 frames.], batch size: 15, lr: 3.99e-04
2022-05-05 03:05:30,785 INFO [train.py:715] (5/8) Epoch 5, batch 2300, loss[loss=0.1532, simple_loss=0.2275, pruned_loss=0.03943, over 4894.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.04238, over 971573.67 frames.], batch size: 19, lr: 3.99e-04
2022-05-05 03:06:10,989 INFO [train.py:715] (5/8) Epoch 5, batch 2350, loss[loss=0.1146, simple_loss=0.1947, pruned_loss=0.01729, over 4757.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04156, over 971319.54 frames.], batch size: 19, lr: 3.99e-04
2022-05-05 03:06:51,193 INFO [train.py:715] (5/8) Epoch 5, batch 2400, loss[loss=0.1792, simple_loss=0.2414, pruned_loss=0.05851, over 4973.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.0411, over 972042.15 frames.], batch size: 14, lr: 3.99e-04
2022-05-05 03:07:31,709 INFO [train.py:715] (5/8) Epoch 5, batch 2450, loss[loss=0.1459, simple_loss=0.2193, pruned_loss=0.03628, over 4914.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2235, pruned_loss=0.04119, over 972968.42 frames.], batch size: 23, lr: 3.99e-04
2022-05-05 03:08:12,418 INFO [train.py:715] (5/8) Epoch 5, batch 2500, loss[loss=0.1463, simple_loss=0.2056, pruned_loss=0.04348, over 4854.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04146, over 973209.06 frames.], batch size: 34, lr: 3.99e-04
2022-05-05 03:08:52,449 INFO [train.py:715] (5/8) Epoch 5, batch 2550, loss[loss=0.1712, simple_loss=0.2383, pruned_loss=0.05203, over 4742.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2246, pruned_loss=0.04158, over 972647.94 frames.], batch size: 16, lr: 3.99e-04
2022-05-05 03:09:33,373 INFO [train.py:715] (5/8) Epoch 5, batch 2600, loss[loss=0.142, simple_loss=0.2168, pruned_loss=0.03363, over 4978.00 frames.], tot_loss[loss=0.1533, simple_loss=0.224, pruned_loss=0.04129, over 972575.20 frames.], batch size: 28, lr: 3.99e-04
2022-05-05 03:10:13,555 INFO [train.py:715] (5/8) Epoch 5, batch 2650, loss[loss=0.1134, simple_loss=0.1873, pruned_loss=0.01974, over 4764.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2239, pruned_loss=0.04076, over 972401.90 frames.], batch size: 14, lr: 3.99e-04
2022-05-05 03:10:54,122 INFO [train.py:715] (5/8) Epoch 5, batch 2700, loss[loss=0.1437, simple_loss=0.2208, pruned_loss=0.03333, over 4940.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2247, pruned_loss=0.04104, over 972085.92 frames.], batch size: 29, lr: 3.99e-04
2022-05-05 03:11:34,316 INFO [train.py:715] (5/8) Epoch 5, batch 2750, loss[loss=0.152, simple_loss=0.227, pruned_loss=0.0385, over 4943.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2244, pruned_loss=0.04112, over 971502.65 frames.], batch size: 18, lr: 3.99e-04
2022-05-05 03:12:14,290 INFO [train.py:715] (5/8) Epoch 5, batch 2800, loss[loss=0.1371, simple_loss=0.2066, pruned_loss=0.03385, over 4852.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2249, pruned_loss=0.04129, over 971959.13 frames.], batch size: 20, lr: 3.99e-04
2022-05-05 03:12:54,885 INFO [train.py:715] (5/8) Epoch 5, batch 2850, loss[loss=0.1551, simple_loss=0.2293, pruned_loss=0.04044, over 4903.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2246, pruned_loss=0.04183, over 972944.04 frames.], batch size: 17, lr: 3.99e-04
2022-05-05 03:13:35,010 INFO [train.py:715] (5/8) Epoch 5, batch 2900, loss[loss=0.1482, simple_loss=0.2298, pruned_loss=0.03332, over 4861.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2247, pruned_loss=0.0419, over 972415.87 frames.], batch size: 20, lr: 3.99e-04
2022-05-05 03:14:15,399 INFO [train.py:715] (5/8) Epoch 5, batch 2950, loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03057, over 4887.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04126, over 971982.70 frames.], batch size: 22, lr: 3.98e-04
2022-05-05 03:14:54,477 INFO [train.py:715] (5/8) Epoch 5, batch 3000, loss[loss=0.1657, simple_loss=0.242, pruned_loss=0.04465, over 4785.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04089, over 972184.96 frames.], batch size: 14, lr: 3.98e-04
2022-05-05 03:14:54,477 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 03:15:03,920 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1108, simple_loss=0.1962, pruned_loss=0.01274, over 914524.00 frames.
2022-05-05 03:15:42,395 INFO [train.py:715] (5/8) Epoch 5, batch 3050, loss[loss=0.1289, simple_loss=0.2036, pruned_loss=0.02708, over 4919.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04054, over 972064.42 frames.], batch size: 23, lr: 3.98e-04
2022-05-05 03:16:21,555 INFO [train.py:715] (5/8) Epoch 5, batch 3100, loss[loss=0.1684, simple_loss=0.2301, pruned_loss=0.05337, over 4873.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04082, over 971739.80 frames.], batch size: 20, lr: 3.98e-04
2022-05-05 03:17:00,519 INFO [train.py:715] (5/8) Epoch 5, batch 3150, loss[loss=0.1598, simple_loss=0.2194, pruned_loss=0.05012, over 4825.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04052, over 971301.47 frames.], batch size: 15, lr: 3.98e-04
2022-05-05 03:17:40,035 INFO [train.py:715] (5/8) Epoch 5, batch 3200, loss[loss=0.1492, simple_loss=0.2173, pruned_loss=0.04051, over 4787.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04098, over 972001.82 frames.], batch size: 12, lr: 3.98e-04
2022-05-05 03:18:19,742 INFO [train.py:715] (5/8) Epoch 5, batch 3250, loss[loss=0.138, simple_loss=0.2014, pruned_loss=0.03736, over 4829.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2238, pruned_loss=0.04168, over 972116.65 frames.], batch size: 13, lr: 3.98e-04
2022-05-05 03:18:58,955 INFO [train.py:715] (5/8) Epoch 5, batch 3300, loss[loss=0.1703, simple_loss=0.2462, pruned_loss=0.04723, over 4781.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2245, pruned_loss=0.042, over 972227.55 frames.], batch size: 19, lr: 3.98e-04
2022-05-05 03:19:38,238 INFO [train.py:715] (5/8) Epoch 5, batch 3350, loss[loss=0.1451, simple_loss=0.2145, pruned_loss=0.03789, over 4950.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04204, over 972022.67 frames.], batch size: 21, lr: 3.98e-04
2022-05-05 03:20:17,969 INFO [train.py:715] (5/8) Epoch 5, batch 3400, loss[loss=0.1379, simple_loss=0.2031, pruned_loss=0.03637, over 4802.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04148, over 971554.34 frames.], batch size: 14, lr: 3.98e-04
2022-05-05 03:20:57,513 INFO [train.py:715] (5/8) Epoch 5, batch 3450, loss[loss=0.1442, simple_loss=0.2122, pruned_loss=0.03807, over 4976.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04212, over 972196.22 frames.], batch size: 15, lr: 3.98e-04
2022-05-05 03:21:36,805 INFO [train.py:715] (5/8) Epoch 5, batch 3500, loss[loss=0.1556, simple_loss=0.2213, pruned_loss=0.04498, over 4781.00 frames.], tot_loss[loss=0.155, simple_loss=0.2247, pruned_loss=0.04261, over 971676.06 frames.], batch size: 18, lr: 3.98e-04
2022-05-05 03:22:16,029 INFO [train.py:715] (5/8) Epoch 5, batch 3550, loss[loss=0.1706, simple_loss=0.2493, pruned_loss=0.04597, over 4924.00 frames.], tot_loss[loss=0.154, simple_loss=0.2241, pruned_loss=0.04199, over 972517.87 frames.], batch size: 29, lr: 3.98e-04
2022-05-05 03:22:55,528 INFO [train.py:715] (5/8) Epoch 5, batch 3600, loss[loss=0.1547, simple_loss=0.2248, pruned_loss=0.0423, over 4902.00 frames.], tot_loss[loss=0.1539, simple_loss=0.224, pruned_loss=0.04188, over 971872.82 frames.], batch size: 19, lr: 3.98e-04
2022-05-05 03:23:34,520 INFO [train.py:715] (5/8) Epoch 5, batch 3650, loss[loss=0.1317, simple_loss=0.2159, pruned_loss=0.02372, over 4968.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04136, over 972121.54 frames.], batch size: 28, lr: 3.98e-04
2022-05-05 03:24:13,762 INFO [train.py:715] (5/8) Epoch 5, batch 3700, loss[loss=0.1432, simple_loss=0.222, pruned_loss=0.03223, over 4962.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04068, over 972608.09 frames.], batch size: 15, lr: 3.98e-04
2022-05-05 03:24:53,920 INFO [train.py:715] (5/8) Epoch 5, batch 3750, loss[loss=0.1639, simple_loss=0.2331, pruned_loss=0.04739, over 4811.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04093, over 972356.12 frames.], batch size: 12, lr: 3.98e-04
2022-05-05 03:25:33,697 INFO [train.py:715] (5/8) Epoch 5, batch 3800, loss[loss=0.2051, simple_loss=0.269, pruned_loss=0.07065, over 4955.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.0408, over 972251.96 frames.], batch size: 39, lr: 3.97e-04
2022-05-05 03:26:13,090 INFO [train.py:715] (5/8) Epoch 5, batch 3850, loss[loss=0.1314, simple_loss=0.201, pruned_loss=0.03094, over 4893.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04088, over 972127.02 frames.], batch size: 22, lr: 3.97e-04
2022-05-05 03:26:52,957 INFO [train.py:715] (5/8) Epoch 5, batch 3900, loss[loss=0.1481, simple_loss=0.2211, pruned_loss=0.03758, over 4989.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04081, over 971613.92 frames.], batch size: 25, lr: 3.97e-04
2022-05-05 03:27:32,996 INFO [train.py:715] (5/8) Epoch 5, batch 3950, loss[loss=0.1472, simple_loss=0.2291, pruned_loss=0.03267, over 4765.00 frames.], tot_loss[loss=0.153, simple_loss=0.2235, pruned_loss=0.04127, over 972090.71 frames.], batch size: 14, lr: 3.97e-04
2022-05-05 03:28:13,081 INFO [train.py:715] (5/8) Epoch 5, batch 4000, loss[loss=0.1522, simple_loss=0.2291, pruned_loss=0.03769, over 4808.00 frames.], tot_loss[loss=0.153, simple_loss=0.2239, pruned_loss=0.04105, over 972028.00 frames.], batch size: 25, lr: 3.97e-04
2022-05-05 03:28:53,737 INFO [train.py:715] (5/8) Epoch 5, batch 4050, loss[loss=0.1654, simple_loss=0.2354, pruned_loss=0.04769, over 4900.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2244, pruned_loss=0.04148, over 972009.65 frames.], batch size: 17, lr: 3.97e-04
2022-05-05 03:29:33,845 INFO [train.py:715] (5/8) Epoch 5, batch 4100, loss[loss=0.1566, simple_loss=0.2235, pruned_loss=0.04481, over 4858.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2245, pruned_loss=0.04145, over 971506.22 frames.], batch size: 34, lr: 3.97e-04
2022-05-05 03:30:14,066 INFO [train.py:715] (5/8) Epoch 5, batch 4150, loss[loss=0.1833, simple_loss=0.2615, pruned_loss=0.05252, over 4771.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2248, pruned_loss=0.04151, over 972083.28 frames.], batch size: 18, lr: 3.97e-04
2022-05-05 03:30:53,443 INFO [train.py:715] (5/8) Epoch 5, batch 4200, loss[loss=0.1948, simple_loss=0.2449, pruned_loss=0.07237, over 4966.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2239, pruned_loss=0.04126, over 972604.72 frames.], batch size: 35, lr: 3.97e-04
2022-05-05 03:31:32,790 INFO [train.py:715] (5/8) Epoch 5, batch 4250, loss[loss=0.1651, simple_loss=0.2379, pruned_loss=0.04608, over 4851.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.0416, over 972388.58 frames.], batch size: 20, lr: 3.97e-04
2022-05-05 03:32:12,485 INFO [train.py:715] (5/8) Epoch 5, batch 4300, loss[loss=0.1696, simple_loss=0.2316, pruned_loss=0.05376, over 4840.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04155, over 972744.04 frames.], batch size: 30, lr: 3.97e-04
2022-05-05 03:32:52,100 INFO [train.py:715] (5/8) Epoch 5, batch 4350, loss[loss=0.163, simple_loss=0.2412, pruned_loss=0.04238, over 4887.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.04213, over 973507.42 frames.], batch size: 22, lr: 3.97e-04
2022-05-05 03:33:32,067 INFO [train.py:715] (5/8) Epoch 5, batch 4400, loss[loss=0.1701, simple_loss=0.2335, pruned_loss=0.05338, over 4642.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04188, over 973351.23 frames.], batch size: 13, lr: 3.97e-04
2022-05-05 03:34:10,944 INFO [train.py:715] (5/8) Epoch 5, batch 4450, loss[loss=0.1383, simple_loss=0.1996, pruned_loss=0.03848, over 4857.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.0417, over 973075.98 frames.], batch size: 13, lr: 3.97e-04
2022-05-05 03:34:50,790 INFO [train.py:715] (5/8) Epoch 5, batch 4500, loss[loss=0.1656, simple_loss=0.2336, pruned_loss=0.04886, over 4859.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04092, over 973814.24 frames.], batch size: 32, lr: 3.97e-04
2022-05-05 03:35:30,122 INFO [train.py:715] (5/8) Epoch 5, batch 4550, loss[loss=0.2107, simple_loss=0.2716, pruned_loss=0.07492, over 4792.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2243, pruned_loss=0.04202, over 972855.12 frames.], batch size: 17, lr: 3.97e-04
2022-05-05 03:36:09,740 INFO [train.py:715] (5/8) Epoch 5, batch 4600, loss[loss=0.1567, simple_loss=0.2237, pruned_loss=0.04479, over 4948.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04183, over 972834.26 frames.], batch size: 23, lr: 3.97e-04
2022-05-05 03:36:50,097 INFO [train.py:715] (5/8) Epoch 5, batch 4650, loss[loss=0.1678, simple_loss=0.2442, pruned_loss=0.0457, over 4875.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04181, over 972692.77 frames.], batch size: 32, lr: 3.97e-04
2022-05-05 03:37:30,431 INFO [train.py:715] (5/8) Epoch 5, batch 4700, loss[loss=0.1305, simple_loss=0.1982, pruned_loss=0.03139, over 4893.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04121, over 972765.94 frames.], batch size: 16, lr: 3.96e-04
2022-05-05 03:38:10,932 INFO [train.py:715] (5/8) Epoch 5, batch 4750, loss[loss=0.2061, simple_loss=0.2672, pruned_loss=0.07246, over 4922.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2239, pruned_loss=0.04125, over 972955.76 frames.], batch size: 39, lr: 3.96e-04
2022-05-05 03:38:50,696 INFO [train.py:715] (5/8) Epoch 5, batch 4800, loss[loss=0.1838, simple_loss=0.2508, pruned_loss=0.05839, over 4936.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2236, pruned_loss=0.04165, over 973129.65 frames.], batch size: 23, lr: 3.96e-04
2022-05-05 03:39:31,182 INFO [train.py:715] (5/8) Epoch 5, batch 4850, loss[loss=0.166, simple_loss=0.2332, pruned_loss=0.0494, over 4947.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04178, over 973402.64 frames.], batch size: 24, lr: 3.96e-04
2022-05-05 03:40:11,786 INFO [train.py:715] (5/8) Epoch 5, batch 4900, loss[loss=0.1736, simple_loss=0.2352, pruned_loss=0.05602, over 4971.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2233, pruned_loss=0.04195, over 973631.21 frames.], batch size: 35, lr: 3.96e-04
2022-05-05 03:40:51,915 INFO [train.py:715] (5/8) Epoch 5, batch 4950, loss[loss=0.155, simple_loss=0.2272, pruned_loss=0.04144, over 4693.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2236, pruned_loss=0.04215, over 973090.37 frames.], batch size: 15, lr: 3.96e-04
2022-05-05 03:41:32,221 INFO [train.py:715] (5/8) Epoch 5, batch 5000, loss[loss=0.1653, simple_loss=0.2394, pruned_loss=0.04565, over 4905.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2242, pruned_loss=0.04194, over 972815.52 frames.], batch size: 19, lr: 3.96e-04
2022-05-05 03:42:13,228 INFO [train.py:715] (5/8) Epoch 5, batch 5050, loss[loss=0.1692, simple_loss=0.2301, pruned_loss=0.05414, over 4841.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2244, pruned_loss=0.04234, over 972629.71 frames.], batch size: 30, lr: 3.96e-04
2022-05-05 03:42:52,851 INFO [train.py:715] (5/8) Epoch 5, batch 5100, loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.0386, over 4768.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2256, pruned_loss=0.04284, over 972856.70 frames.], batch size: 14, lr: 3.96e-04
2022-05-05 03:43:32,134 INFO [train.py:715] (5/8) Epoch 5, batch 5150, loss[loss=0.1468, simple_loss=0.2172, pruned_loss=0.03815, over 4972.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.0426, over 972783.71 frames.], batch size: 35, lr: 3.96e-04
2022-05-05 03:44:11,855 INFO [train.py:715] (5/8) Epoch 5, batch 5200, loss[loss=0.122, simple_loss=0.1929, pruned_loss=0.02558, over 4985.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2257, pruned_loss=0.04277, over 973764.04 frames.], batch size: 14, lr: 3.96e-04
2022-05-05 03:44:51,641 INFO [train.py:715] (5/8) Epoch 5, batch 5250, loss[loss=0.1478, simple_loss=0.2216, pruned_loss=0.037, over 4899.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2253, pruned_loss=0.04243, over 973418.70 frames.], batch size: 19, lr: 3.96e-04
2022-05-05 03:45:32,214 INFO [train.py:715] (5/8) Epoch 5, batch 5300, loss[loss=0.1527, simple_loss=0.2194, pruned_loss=0.04301, over 4776.00 frames.], tot_loss[loss=0.155, simple_loss=0.2253, pruned_loss=0.04234, over 973383.36 frames.], batch size: 17, lr: 3.96e-04
2022-05-05 03:46:12,527 INFO [train.py:715] (5/8) Epoch 5, batch 5350, loss[loss=0.1467, simple_loss=0.2018, pruned_loss=0.04578, over 4767.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2242, pruned_loss=0.04174, over 973284.01 frames.], batch size: 12, lr: 3.96e-04
2022-05-05 03:46:52,864 INFO [train.py:715] (5/8) Epoch 5, batch 5400, loss[loss=0.187, simple_loss=0.2569, pruned_loss=0.05852, over 4928.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.04196, over 973201.82 frames.], batch size: 23, lr: 3.96e-04
2022-05-05 03:47:32,578 INFO [train.py:715] (5/8) Epoch 5, batch 5450, loss[loss=0.1493, simple_loss=0.2242, pruned_loss=0.03721, over 4848.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.0416, over 973263.66 frames.], batch size: 32, lr: 3.96e-04
2022-05-05 03:48:12,696 INFO [train.py:715] (5/8) Epoch 5, batch 5500, loss[loss=0.1372, simple_loss=0.207, pruned_loss=0.03374, over 4936.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2249, pruned_loss=0.04209, over 972747.78 frames.], batch size: 29, lr: 3.96e-04
2022-05-05 03:48:53,029 INFO [train.py:715] (5/8) Epoch 5, batch 5550, loss[loss=0.1635, simple_loss=0.2383, pruned_loss=0.04435, over 4874.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04192, over 973725.04 frames.], batch size: 16, lr: 3.96e-04
2022-05-05 03:49:33,408 INFO [train.py:715] (5/8) Epoch 5, batch 5600, loss[loss=0.1675, simple_loss=0.2282, pruned_loss=0.05341, over 4848.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.0413, over 973010.30 frames.], batch size: 32, lr: 3.95e-04
2022-05-05 03:50:13,543 INFO [train.py:715] (5/8) Epoch 5, batch 5650, loss[loss=0.1592, simple_loss=0.2241, pruned_loss=0.04716, over 4774.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.0411, over 973144.77 frames.], batch size: 19, lr: 3.95e-04
2022-05-05 03:50:52,898 INFO [train.py:715] (5/8) Epoch 5, batch 5700, loss[loss=0.1552, simple_loss=0.2265, pruned_loss=0.04195, over 4866.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04127, over 973624.89 frames.], batch size: 22, lr: 3.95e-04
2022-05-05 03:51:33,317 INFO [train.py:715] (5/8) Epoch 5, batch 5750, loss[loss=0.1789, simple_loss=0.2381, pruned_loss=0.05984, over 4922.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04148, over 974319.82 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 03:52:13,226 INFO [train.py:715] (5/8) Epoch 5, batch 5800, loss[loss=0.1435, simple_loss=0.2124, pruned_loss=0.03726, over 4985.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2229, pruned_loss=0.04145, over 974017.83 frames.], batch size: 24, lr: 3.95e-04
2022-05-05 03:52:53,761 INFO [train.py:715] (5/8) Epoch 5, batch 5850, loss[loss=0.1602, simple_loss=0.2384, pruned_loss=0.04106, over 4904.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2234, pruned_loss=0.04122, over 973964.31 frames.], batch size: 19, lr: 3.95e-04
2022-05-05 03:53:33,394 INFO [train.py:715] (5/8) Epoch 5, batch 5900, loss[loss=0.1449, simple_loss=0.2257, pruned_loss=0.03203, over 4929.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2236, pruned_loss=0.04094, over 973326.12 frames.], batch size: 21, lr: 3.95e-04
2022-05-05 03:54:13,784 INFO [train.py:715] (5/8) Epoch 5, batch 5950, loss[loss=0.1532, simple_loss=0.2381, pruned_loss=0.03413, over 4775.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2234, pruned_loss=0.04054, over 972615.81 frames.], batch size: 17, lr: 3.95e-04
2022-05-05 03:54:53,619 INFO [train.py:715] (5/8) Epoch 5, batch 6000, loss[loss=0.1844, simple_loss=0.2654, pruned_loss=0.05168, over 4763.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2238, pruned_loss=0.04078, over 972285.80 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 03:54:53,620 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 03:55:03,071 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1106, simple_loss=0.1959, pruned_loss=0.01263, over 914524.00 frames.
2022-05-05 03:55:42,938 INFO [train.py:715] (5/8) Epoch 5, batch 6050, loss[loss=0.1472, simple_loss=0.2107, pruned_loss=0.04181, over 4845.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2226, pruned_loss=0.04029, over 972379.77 frames.], batch size: 13, lr: 3.95e-04
2022-05-05 03:56:22,017 INFO [train.py:715] (5/8) Epoch 5, batch 6100, loss[loss=0.1413, simple_loss=0.2239, pruned_loss=0.02932, over 4993.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2234, pruned_loss=0.04095, over 971896.55 frames.], batch size: 16, lr: 3.95e-04
2022-05-05 03:57:01,848 INFO [train.py:715] (5/8) Epoch 5, batch 6150, loss[loss=0.1518, simple_loss=0.2236, pruned_loss=0.03995, over 4823.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04108, over 972154.31 frames.], batch size: 26, lr: 3.95e-04
2022-05-05 03:57:40,842 INFO [train.py:715] (5/8) Epoch 5, batch 6200, loss[loss=0.1386, simple_loss=0.204, pruned_loss=0.03658, over 4766.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04133, over 971819.21 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 03:58:21,087 INFO [train.py:715] (5/8) Epoch 5, batch 6250, loss[loss=0.1363, simple_loss=0.2064, pruned_loss=0.03307, over 4777.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04137, over 971617.28 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 03:58:59,732 INFO [train.py:715] (5/8) Epoch 5, batch 6300, loss[loss=0.1386, simple_loss=0.2127, pruned_loss=0.03222, over 4985.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04167, over 971995.22 frames.], batch size: 28, lr: 3.95e-04
2022-05-05 03:59:39,536 INFO [train.py:715] (5/8) Epoch 5, batch 6350, loss[loss=0.152, simple_loss=0.2275, pruned_loss=0.03822, over 4945.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04166, over 972191.05 frames.], batch size: 35, lr: 3.95e-04
2022-05-05 04:00:18,903 INFO [train.py:715] (5/8) Epoch 5, batch 6400, loss[loss=0.1428, simple_loss=0.2139, pruned_loss=0.03585, over 4810.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.04111, over 972226.78 frames.], batch size: 25, lr: 3.95e-04
2022-05-05 04:00:57,766 INFO [train.py:715] (5/8) Epoch 5, batch 6450, loss[loss=0.1606, simple_loss=0.2375, pruned_loss=0.04187, over 4879.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2228, pruned_loss=0.04068, over 973949.30 frames.], batch size: 22, lr: 3.95e-04
2022-05-05 04:01:37,235 INFO [train.py:715] (5/8) Epoch 5, batch 6500, loss[loss=0.1582, simple_loss=0.2391, pruned_loss=0.0387, over 4876.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2235, pruned_loss=0.04084, over 972873.07 frames.], batch size: 16, lr: 3.95e-04
2022-05-05 04:02:16,585 INFO [train.py:715] (5/8) Epoch 5, batch 6550, loss[loss=0.1598, simple_loss=0.2237, pruned_loss=0.04796, over 4974.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04137, over 973020.71 frames.], batch size: 35, lr: 3.94e-04
2022-05-05 04:02:55,728 INFO [train.py:715] (5/8) Epoch 5, batch 6600, loss[loss=0.2642, simple_loss=0.3067, pruned_loss=0.1109, over 4879.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04151, over 972829.40 frames.], batch size: 16, lr: 3.94e-04
2022-05-05 04:03:35,250 INFO [train.py:715] (5/8) Epoch 5, batch 6650, loss[loss=0.1755, simple_loss=0.2443, pruned_loss=0.0534, over 4860.00 frames.], tot_loss[loss=0.1537, simple_loss=0.224, pruned_loss=0.04167, over 973197.38 frames.], batch size: 20, lr: 3.94e-04
2022-05-05 04:04:15,786 INFO [train.py:715] (5/8) Epoch 5, batch 6700, loss[loss=0.1404, simple_loss=0.2104, pruned_loss=0.03526, over 4848.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04162, over 973215.00 frames.], batch size: 34, lr: 3.94e-04
2022-05-05 04:04:56,113 INFO [train.py:715] (5/8) Epoch 5, batch 6750, loss[loss=0.1544, simple_loss=0.227, pruned_loss=0.04085, over 4979.00 frames.], tot_loss[loss=0.153, simple_loss=0.2233, pruned_loss=0.04134, over 972781.00 frames.], batch size: 31, lr: 3.94e-04
2022-05-05 04:05:36,105 INFO [train.py:715] (5/8) Epoch 5, batch 6800, loss[loss=0.1818, simple_loss=0.2399, pruned_loss=0.0619, over 4712.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04096, over 973082.61 frames.], batch size: 15, lr: 3.94e-04
2022-05-05 04:06:16,591 INFO [train.py:715] (5/8) Epoch 5, batch 6850, loss[loss=0.16, simple_loss=0.2262, pruned_loss=0.04689, over 4935.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2229, pruned_loss=0.04075, over 972984.80 frames.], batch size: 39, lr: 3.94e-04
2022-05-05 04:06:56,550 INFO [train.py:715] (5/8) Epoch 5, batch 6900, loss[loss=0.1359, simple_loss=0.2052, pruned_loss=0.03333, over 4821.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04109, over 972826.39 frames.], batch size: 26, lr: 3.94e-04
2022-05-05 04:07:37,125 INFO [train.py:715] (5/8) Epoch 5, batch 6950, loss[loss=0.1331, simple_loss=0.2183, pruned_loss=0.02398, over 4956.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04136, over 973466.03 frames.], batch size: 21, lr: 3.94e-04
2022-05-05 04:08:16,565 INFO [train.py:715] (5/8) Epoch 5, batch 7000, loss[loss=0.1577, simple_loss=0.2324, pruned_loss=0.04153, over 4810.00 frames.], tot_loss[loss=0.154, simple_loss=0.2246, pruned_loss=0.04163, over 972561.43 frames.], batch size: 21, lr: 3.94e-04
2022-05-05 04:08:56,461 INFO [train.py:715] (5/8) Epoch 5, batch 7050, loss[loss=0.2061, simple_loss=0.2657, pruned_loss=0.07322, over 4924.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04131, over 973343.65 frames.], batch size: 39, lr: 3.94e-04
2022-05-05 04:09:36,253 INFO [train.py:715] (5/8) Epoch 5, batch 7100, loss[loss=0.1427, simple_loss=0.2187, pruned_loss=0.03335, over 4879.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04196, over 973638.57 frames.], batch size: 22, lr: 3.94e-04
2022-05-05 04:10:15,689 INFO [train.py:715] (5/8) Epoch 5, batch 7150, loss[loss=0.172, simple_loss=0.2519, pruned_loss=0.04604, over 4840.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2248, pruned_loss=0.04216, over 972584.02 frames.], batch size: 15, lr: 3.94e-04
2022-05-05 04:10:55,645 INFO [train.py:715] (5/8) Epoch 5, batch 7200, loss[loss=0.1627, simple_loss=0.2339, pruned_loss=0.04582, over 4754.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2249, pruned_loss=0.04205, over 972959.04 frames.], batch size: 19, lr: 3.94e-04
2022-05-05 04:11:35,238 INFO [train.py:715] (5/8) Epoch 5, batch 7250, loss[loss=0.1215, simple_loss=0.1919, pruned_loss=0.02559, over 4842.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2245, pruned_loss=0.04129, over 972965.91 frames.], batch size: 13, lr: 3.94e-04
2022-05-05 04:12:15,754 INFO [train.py:715] (5/8) Epoch 5, batch 7300, loss[loss=0.1499, simple_loss=0.2144, pruned_loss=0.0427, over 4829.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04132, over 973027.25 frames.], batch size: 30, lr: 3.94e-04
2022-05-05 04:12:55,316 INFO [train.py:715] (5/8) Epoch 5, batch 7350, loss[loss=0.1329, simple_loss=0.2084, pruned_loss=0.0287, over 4817.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04124, over 972379.10 frames.], batch size: 27, lr: 3.94e-04
2022-05-05 04:13:34,915 INFO [train.py:715] (5/8) Epoch 5, batch 7400, loss[loss=0.1541, simple_loss=0.2257, pruned_loss=0.04129, over 4915.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2241, pruned_loss=0.04132, over 972561.27 frames.], batch size: 29, lr: 3.94e-04
2022-05-05 04:14:14,460 INFO [train.py:715] (5/8) Epoch 5, batch 7450, loss[loss=0.1347, simple_loss=0.2055, pruned_loss=0.03196, over 4928.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2236, pruned_loss=0.04096, over 971805.69 frames.], batch size: 18, lr: 3.93e-04
2022-05-05 04:14:53,550 INFO [train.py:715] (5/8) Epoch 5, batch 7500, loss[loss=0.1799, simple_loss=0.2463, pruned_loss=0.05676, over 4873.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2235, pruned_loss=0.04092, over 971714.73 frames.], batch size: 22, lr: 3.93e-04
2022-05-05 04:15:33,684 INFO [train.py:715] (5/8) Epoch 5, batch 7550, loss[loss=0.158, simple_loss=0.2252, pruned_loss=0.0454, over 4840.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.0408, over 971737.78 frames.], batch size: 30, lr: 3.93e-04
2022-05-05 04:16:13,351 INFO [train.py:715] (5/8) Epoch 5, batch 7600, loss[loss=0.151, simple_loss=0.2235, pruned_loss=0.0392, over 4844.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04081, over 971481.38 frames.], batch size: 15, lr: 3.93e-04
2022-05-05 04:16:53,609 INFO [train.py:715] (5/8) Epoch 5, batch 7650, loss[loss=0.1579, simple_loss=0.2228, pruned_loss=0.04654, over 4775.00 frames.], tot_loss[loss=0.153, simple_loss=0.2238, pruned_loss=0.04108, over 971249.45 frames.], batch size: 17, lr: 3.93e-04
2022-05-05 04:17:33,266 INFO [train.py:715] (5/8) Epoch 5, batch 7700, loss[loss=0.1436, simple_loss=0.2141, pruned_loss=0.0365, over 4968.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04116, over 971668.24 frames.], batch size: 28, lr: 3.93e-04
2022-05-05 04:18:12,776 INFO [train.py:715] (5/8) Epoch 5, batch 7750, loss[loss=0.1482, simple_loss=0.2282, pruned_loss=0.03412, over 4884.00 frames.], tot_loss[loss=0.1521, simple_loss=0.223, pruned_loss=0.04064, over 972205.44 frames.], batch size: 22, lr: 3.93e-04
2022-05-05 04:18:52,925 INFO [train.py:715] (5/8) Epoch 5, batch 7800, loss[loss=0.171, simple_loss=0.2243, pruned_loss=0.05888, over 4987.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2227, pruned_loss=0.04061, over 972027.20 frames.], batch size: 31, lr: 3.93e-04
2022-05-05 04:19:32,129 INFO [train.py:715] (5/8) Epoch 5, batch 7850, loss[loss=0.1137, simple_loss=0.1872, pruned_loss=0.02004, over 4753.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2228, pruned_loss=0.0404, over 972739.08 frames.], batch size: 12, lr: 3.93e-04
2022-05-05 04:20:12,355 INFO [train.py:715] (5/8) Epoch 5, batch 7900, loss[loss=0.1678, simple_loss=0.2415, pruned_loss=0.04702, over 4959.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2231, pruned_loss=0.04081, over 972513.51 frames.], batch size: 35, lr: 3.93e-04
2022-05-05 04:20:51,910 INFO [train.py:715] (5/8) Epoch 5, batch 7950, loss[loss=0.1468, simple_loss=0.214, pruned_loss=0.03977, over 4926.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2235, pruned_loss=0.04106, over 972309.94 frames.], batch size: 23, lr: 3.93e-04
2022-05-05 04:21:32,116 INFO [train.py:715] (5/8) Epoch 5, batch 8000, loss[loss=0.141, simple_loss=0.2237, pruned_loss=0.02914, over 4691.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2243, pruned_loss=0.04167, over 971915.94 frames.], batch size: 15, lr: 3.93e-04
2022-05-05 04:22:11,572 INFO [train.py:715] (5/8) Epoch 5, batch 8050, loss[loss=0.1344, simple_loss=0.2125, pruned_loss=0.02814, over 4915.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2245, pruned_loss=0.0419, over 972376.95 frames.], batch size: 23, lr: 3.93e-04
2022-05-05 04:22:51,023 INFO [train.py:715] (5/8) Epoch 5, batch 8100, loss[loss=0.1262, simple_loss=0.21, pruned_loss=0.02125, over 4848.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2244, pruned_loss=0.04172, over 971725.05 frames.], batch size: 20, lr: 3.93e-04
2022-05-05 04:23:30,811 INFO [train.py:715] (5/8) Epoch 5, batch 8150, loss[loss=0.1454, simple_loss=0.2109, pruned_loss=0.03999, over 4944.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2253, pruned_loss=0.04225, over 972315.95 frames.], batch size: 21, lr: 3.93e-04
2022-05-05 04:24:09,994 INFO [train.py:715] (5/8) Epoch 5, batch 8200, loss[loss=0.1469, simple_loss=0.2194, pruned_loss=0.0372, over 4808.00 frames.], tot_loss[loss=0.1547, simple_loss=0.225, pruned_loss=0.04214, over 971488.82 frames.], batch size: 26, lr: 3.93e-04
2022-05-05 04:24:50,011 INFO [train.py:715] (5/8) Epoch 5, batch 8250, loss[loss=0.1885, simple_loss=0.253, pruned_loss=0.06196, over 4802.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2241, pruned_loss=0.0421, over 972590.01 frames.], batch size: 14, lr: 3.93e-04
2022-05-05 04:25:29,480 INFO [train.py:715] (5/8) Epoch 5, batch 8300, loss[loss=0.15, simple_loss=0.2146, pruned_loss=0.04266, over 4639.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04134, over 972166.76 frames.], batch size: 13, lr: 3.93e-04
2022-05-05 04:26:09,423 INFO [train.py:715] (5/8) Epoch 5, batch 8350, loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.02935, over 4838.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04191, over 971913.13 frames.], batch size: 25, lr: 3.93e-04
2022-05-05 04:26:48,502 INFO [train.py:715] (5/8) Epoch 5, batch 8400, loss[loss=0.1771, simple_loss=0.2502, pruned_loss=0.05204, over 4924.00 frames.], tot_loss[loss=0.154, simple_loss=0.224, pruned_loss=0.04199, over 972589.00 frames.], batch size: 18, lr: 3.92e-04
2022-05-05 04:27:27,550 INFO [train.py:715] (5/8) Epoch 5, batch 8450, loss[loss=0.1825, simple_loss=0.2561, pruned_loss=0.0544, over 4863.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.0415, over 972495.12 frames.], batch size: 38, lr: 3.92e-04
2022-05-05 04:28:06,813 INFO [train.py:715] (5/8) Epoch 5, batch 8500, loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02955, over 4974.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.04194, over 972783.86 frames.], batch size: 35, lr: 3.92e-04
2022-05-05 04:28:45,803 INFO [train.py:715] (5/8) Epoch 5, batch 8550, loss[loss=0.1532, simple_loss=0.222, pruned_loss=0.04221, over 4746.00 frames.], tot_loss[loss=0.154, simple_loss=0.224, pruned_loss=0.042, over 972696.51 frames.], batch size: 16, lr: 3.92e-04
2022-05-05 04:29:25,247 INFO [train.py:715] (5/8) Epoch 5, batch 8600, loss[loss=0.1421, simple_loss=0.2208, pruned_loss=0.0317, over 4833.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2236, pruned_loss=0.04172, over 972698.21 frames.], batch size: 26, lr: 3.92e-04
2022-05-05 04:30:04,413 INFO [train.py:715] (5/8) Epoch 5, batch 8650, loss[loss=0.1315, simple_loss=0.2082, pruned_loss=0.02733, over 4822.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2234, pruned_loss=0.04173, over 971730.09 frames.], batch size: 25, lr: 3.92e-04
2022-05-05 04:30:43,884 INFO [train.py:715] (5/8) Epoch 5, batch 8700, loss[loss=0.1813, simple_loss=0.2476, pruned_loss=0.05748, over 4865.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04184, over 972331.21 frames.], batch size: 16, lr: 3.92e-04
2022-05-05 04:31:23,271 INFO [train.py:715] (5/8) Epoch 5, batch 8750, loss[loss=0.1577, simple_loss=0.2324, pruned_loss=0.04151, over 4990.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04184, over 972577.29 frames.], batch size: 28, lr: 3.92e-04
2022-05-05 04:32:02,279 INFO [train.py:715] (5/8) Epoch 5, batch 8800, loss[loss=0.1286, simple_loss=0.1979, pruned_loss=0.02958, over 4759.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2236, pruned_loss=0.04197, over 972774.43 frames.], batch size: 18, lr: 3.92e-04
2022-05-05 04:32:42,159 INFO [train.py:715] (5/8) Epoch 5, batch 8850, loss[loss=0.1191, simple_loss=0.192, pruned_loss=0.02304, over 4834.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04191, over 973210.13 frames.], batch size: 12, lr: 3.92e-04
2022-05-05 04:33:20,884 INFO [train.py:715] (5/8) Epoch 5, batch 8900, loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.02829, over 4936.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04089, over 972753.23 frames.], batch size: 21, lr: 3.92e-04
2022-05-05 04:33:59,745 INFO [train.py:715] (5/8) Epoch 5, batch 8950, loss[loss=0.1341, simple_loss=0.2199, pruned_loss=0.02421, over 4892.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2228, pruned_loss=0.04123, over 971998.89 frames.], batch size: 22, lr: 3.92e-04
2022-05-05 04:34:39,031 INFO [train.py:715] (5/8) Epoch 5, batch 9000, loss[loss=0.1634, simple_loss=0.2263, pruned_loss=0.0502, over 4756.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04185, over 971856.05 frames.], batch size: 17, lr: 3.92e-04
2022-05-05 04:34:39,032 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 04:34:48,552 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1105, simple_loss=0.196, pruned_loss=0.01252, over 914524.00 frames.
2022-05-05 04:35:28,195 INFO [train.py:715] (5/8) Epoch 5, batch 9050, loss[loss=0.122, simple_loss=0.1909, pruned_loss=0.02654, over 4827.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2237, pruned_loss=0.0421, over 971466.11 frames.], batch size: 13, lr: 3.92e-04
2022-05-05 04:36:07,672 INFO [train.py:715] (5/8) Epoch 5, batch 9100, loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.04168, over 4801.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04184, over 971742.06 frames.], batch size: 24, lr: 3.92e-04
2022-05-05 04:36:46,713 INFO [train.py:715] (5/8) Epoch 5, batch 9150, loss[loss=0.1592, simple_loss=0.2377, pruned_loss=0.04034, over 4795.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04156, over 972119.96 frames.], batch size: 21, lr: 3.92e-04
2022-05-05 04:37:26,204 INFO [train.py:715] (5/8) Epoch 5, batch 9200, loss[loss=0.1948, simple_loss=0.2491, pruned_loss=0.0703, over 4739.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04125, over 972527.89 frames.], batch size: 16, lr: 3.92e-04
2022-05-05 04:38:06,417 INFO [train.py:715] (5/8) Epoch 5, batch 9250, loss[loss=0.1271, simple_loss=0.2062, pruned_loss=0.02394, over 4952.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2233, pruned_loss=0.04107, over 972684.24 frames.], batch size: 24, lr: 3.92e-04
2022-05-05 04:38:45,291 INFO [train.py:715] (5/8) Epoch 5, batch 9300, loss[loss=0.1375, simple_loss=0.2039, pruned_loss=0.0355, over 4914.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2228, pruned_loss=0.04085, over 973293.14 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:39:24,929 INFO [train.py:715] (5/8) Epoch 5, batch 9350, loss[loss=0.1424, simple_loss=0.2155, pruned_loss=0.03459, over 4830.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04087, over 974217.63 frames.], batch size: 13, lr: 3.91e-04
2022-05-05 04:40:04,421 INFO [train.py:715] (5/8) Epoch 5, batch 9400, loss[loss=0.1405, simple_loss=0.2106, pruned_loss=0.03514, over 4691.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2213, pruned_loss=0.04014, over 973161.67 frames.], batch size: 15, lr: 3.91e-04
2022-05-05 04:40:43,714 INFO [train.py:715] (5/8) Epoch 5, batch 9450, loss[loss=0.1313, simple_loss=0.1978, pruned_loss=0.03242, over 4865.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04056, over 973407.07 frames.], batch size: 16, lr: 3.91e-04
2022-05-05 04:41:22,596 INFO [train.py:715] (5/8) Epoch 5, batch 9500, loss[loss=0.1399, simple_loss=0.2169, pruned_loss=0.03141, over 4805.00 frames.], tot_loss[loss=0.152, simple_loss=0.2224, pruned_loss=0.04077, over 973810.06 frames.], batch size: 25, lr: 3.91e-04
2022-05-05 04:42:02,153 INFO [train.py:715] (5/8) Epoch 5, batch 9550, loss[loss=0.1716, simple_loss=0.2324, pruned_loss=0.05539, over 4775.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04115, over 973538.16 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:42:41,919 INFO [train.py:715] (5/8) Epoch 5, batch 9600, loss[loss=0.1316, simple_loss=0.2112, pruned_loss=0.02603, over 4937.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2233, pruned_loss=0.04113, over 972849.81 frames.], batch size: 29, lr: 3.91e-04
2022-05-05 04:43:21,155 INFO [train.py:715] (5/8) Epoch 5, batch 9650, loss[loss=0.1595, simple_loss=0.2393, pruned_loss=0.03988, over 4787.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04141, over 972710.34 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:44:00,814 INFO [train.py:715] (5/8) Epoch 5, batch 9700, loss[loss=0.1603, simple_loss=0.2291, pruned_loss=0.04576, over 4784.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2248, pruned_loss=0.04222, over 973631.37 frames.], batch size: 14, lr: 3.91e-04
2022-05-05 04:44:40,237 INFO [train.py:715] (5/8) Epoch 5, batch 9750, loss[loss=0.1502, simple_loss=0.2197, pruned_loss=0.04038, over 4798.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04179, over 973765.86 frames.], batch size: 21, lr: 3.91e-04
2022-05-05 04:45:19,135 INFO [train.py:715] (5/8) Epoch 5, batch 9800, loss[loss=0.1497, simple_loss=0.2247, pruned_loss=0.03737, over 4895.00 frames.], tot_loss[loss=0.1536, simple_loss=0.224, pruned_loss=0.04157, over 973787.97 frames.], batch size: 19, lr: 3.91e-04
2022-05-05 04:45:58,977 INFO [train.py:715] (5/8) Epoch 5, batch 9850, loss[loss=0.1741, simple_loss=0.2508, pruned_loss=0.04874, over 4833.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.04134, over 973840.33 frames.], batch size: 30, lr: 3.91e-04
2022-05-05 04:46:38,171 INFO [train.py:715] (5/8) Epoch 5, batch 9900, loss[loss=0.1248, simple_loss=0.1965, pruned_loss=0.02656, over 4715.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.0414, over 973530.04 frames.], batch size: 15, lr: 3.91e-04
2022-05-05 04:47:17,938 INFO [train.py:715] (5/8) Epoch 5, batch 9950, loss[loss=0.12, simple_loss=0.1867, pruned_loss=0.0266, over 4981.00 frames.], tot_loss[loss=0.153, simple_loss=0.2237, pruned_loss=0.04117, over 973334.80 frames.], batch size: 14, lr: 3.91e-04
2022-05-05 04:47:59,850 INFO [train.py:715] (5/8) Epoch 5, batch 10000, loss[loss=0.1531, simple_loss=0.2295, pruned_loss=0.03832, over 4768.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.04104, over 972962.60 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:48:39,807 INFO [train.py:715] (5/8) Epoch 5, batch 10050, loss[loss=0.1588, simple_loss=0.2344, pruned_loss=0.04163, over 4772.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2238, pruned_loss=0.04088, over 972517.78 frames.], batch size: 17, lr: 3.91e-04
2022-05-05 04:49:19,415 INFO [train.py:715] (5/8) Epoch 5, batch 10100, loss[loss=0.1627, simple_loss=0.236, pruned_loss=0.0447, over 4769.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2245, pruned_loss=0.04162, over 972060.86 frames.], batch size: 17, lr: 3.91e-04
2022-05-05 04:49:58,584 INFO [train.py:715] (5/8) Epoch 5, batch 10150, loss[loss=0.1305, simple_loss=0.2069, pruned_loss=0.02704, over 4756.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2244, pruned_loss=0.0414, over 972198.95 frames.], batch size: 19, lr: 3.91e-04
2022-05-05 04:50:38,452 INFO [train.py:715] (5/8) Epoch 5, batch 10200, loss[loss=0.1669, simple_loss=0.2301, pruned_loss=0.05183, over 4984.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04133, over 972750.37 frames.], batch size: 14, lr: 3.91e-04
2022-05-05 04:51:17,795 INFO [train.py:715] (5/8) Epoch 5, batch 10250, loss[loss=0.1458, simple_loss=0.2182, pruned_loss=0.03672, over 4972.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04154, over 972852.52 frames.], batch size: 25, lr: 3.90e-04
2022-05-05 04:51:56,801 INFO [train.py:715] (5/8) Epoch 5, batch 10300, loss[loss=0.1585, simple_loss=0.2236, pruned_loss=0.04669, over 4974.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2231, pruned_loss=0.04099, over 972504.03 frames.], batch size: 15, lr: 3.90e-04
2022-05-05 04:52:36,625 INFO [train.py:715] (5/8) Epoch 5, batch 10350, loss[loss=0.1476, simple_loss=0.2271, pruned_loss=0.03404, over 4770.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.0414, over 972339.10 frames.], batch size: 17, lr: 3.90e-04
2022-05-05 04:53:15,664 INFO [train.py:715] (5/8) Epoch 5, batch 10400, loss[loss=0.1453, simple_loss=0.2091, pruned_loss=0.04073, over 4831.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2237, pruned_loss=0.04091, over 973102.45 frames.], batch size: 30, lr: 3.90e-04
2022-05-05 04:53:55,619 INFO [train.py:715] (5/8) Epoch 5, batch 10450, loss[loss=0.1333, simple_loss=0.2116, pruned_loss=0.02747, over 4858.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04107, over 972540.36 frames.], batch size: 22, lr: 3.90e-04
2022-05-05 04:54:35,518 INFO [train.py:715] (5/8) Epoch 5, batch 10500, loss[loss=0.1475, simple_loss=0.217, pruned_loss=0.03898, over 4976.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.04146, over 972161.30 frames.], batch size: 25, lr: 3.90e-04
2022-05-05 04:55:15,980 INFO [train.py:715] (5/8) Epoch 5, batch 10550, loss[loss=0.1362, simple_loss=0.2162, pruned_loss=0.02813, over 4770.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2246, pruned_loss=0.04182, over 972992.37 frames.], batch size: 19, lr: 3.90e-04
2022-05-05 04:55:55,071 INFO [train.py:715] (5/8) Epoch 5, batch 10600, loss[loss=0.1496, simple_loss=0.2256, pruned_loss=0.03674, over 4977.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04162, over 972628.18 frames.], batch size: 25, lr: 3.90e-04
2022-05-05 04:56:34,539 INFO [train.py:715] (5/8) Epoch 5, batch 10650, loss[loss=0.1601, simple_loss=0.2355, pruned_loss=0.04239, over 4781.00 frames.], tot_loss[loss=0.1545, simple_loss=0.225, pruned_loss=0.04197, over 972862.23 frames.], batch size: 18, lr: 3.90e-04
2022-05-05 04:57:14,070 INFO [train.py:715] (5/8) Epoch 5, batch 10700, loss[loss=0.1684, simple_loss=0.2368, pruned_loss=0.05003, over 4856.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2258, pruned_loss=0.04238, over 972623.43 frames.], batch size: 32, lr: 3.90e-04
2022-05-05 04:57:53,026 INFO [train.py:715] (5/8) Epoch 5, batch 10750, loss[loss=0.1688, simple_loss=0.257, pruned_loss=0.04028, over 4892.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2254, pruned_loss=0.04183, over 972156.75 frames.], batch size: 19, lr: 3.90e-04
2022-05-05 04:58:32,275 INFO [train.py:715] (5/8) Epoch 5, batch 10800, loss[loss=0.1617, simple_loss=0.2332, pruned_loss=0.04512, over 4783.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2251, pruned_loss=0.04216, over 972621.99 frames.], batch size: 17, lr: 3.90e-04
2022-05-05 04:59:11,503 INFO [train.py:715] (5/8) Epoch 5, batch 10850, loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03029, over 4854.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.04197, over 972191.39 frames.], batch size: 13, lr: 3.90e-04
2022-05-05 04:59:51,498 INFO [train.py:715] (5/8) Epoch 5, batch 10900, loss[loss=0.1845, simple_loss=0.2697, pruned_loss=0.04967, over 4918.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2255, pruned_loss=0.04193, over 972408.14 frames.], batch size: 18, lr: 3.90e-04
2022-05-05 05:00:30,697 INFO [train.py:715] (5/8) Epoch 5, batch 10950, loss[loss=0.1686, simple_loss=0.2336, pruned_loss=0.05182, over 4822.00 frames.], tot_loss[loss=0.155, simple_loss=0.2257, pruned_loss=0.04215, over 972409.55 frames.], batch size: 13, lr: 3.90e-04
2022-05-05 05:01:10,468 INFO [train.py:715] (5/8) Epoch 5, batch 11000, loss[loss=0.1522, simple_loss=0.2243, pruned_loss=0.04004, over 4870.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2251, pruned_loss=0.04165, over 972084.12 frames.], batch size: 20, lr: 3.90e-04
2022-05-05 05:01:49,963 INFO [train.py:715] (5/8) Epoch 5, batch 11050, loss[loss=0.1368, simple_loss=0.2181, pruned_loss=0.02773, over 4807.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2247, pruned_loss=0.04147, over 973319.68 frames.], batch size: 25, lr: 3.90e-04
2022-05-05 05:02:29,386 INFO [train.py:715] (5/8) Epoch 5, batch 11100, loss[loss=0.1294, simple_loss=0.2059, pruned_loss=0.02642, over 4946.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2241, pruned_loss=0.04126, over 974062.73 frames.], batch size: 29, lr: 3.90e-04
2022-05-05 05:03:08,927 INFO [train.py:715] (5/8) Epoch 5, batch 11150, loss[loss=0.1672, simple_loss=0.2312, pruned_loss=0.05163, over 4778.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2246, pruned_loss=0.04156, over 973922.49 frames.], batch size: 12, lr: 3.90e-04
2022-05-05 05:03:48,020 INFO [train.py:715] (5/8) Epoch 5, batch 11200, loss[loss=0.1416, simple_loss=0.2217, pruned_loss=0.0308, over 4790.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2254, pruned_loss=0.04221, over 972729.30 frames.], batch size: 24, lr: 3.89e-04
2022-05-05 05:04:27,936 INFO [train.py:715] (5/8) Epoch 5, batch 11250, loss[loss=0.1522, simple_loss=0.2051, pruned_loss=0.04968, over 4835.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2252, pruned_loss=0.04228, over 972699.44 frames.], batch size: 13, lr: 3.89e-04
2022-05-05 05:05:07,258 INFO [train.py:715] (5/8) Epoch 5, batch 11300, loss[loss=0.1416, simple_loss=0.21, pruned_loss=0.03654, over 4745.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04256, over 973473.70 frames.], batch size: 16, lr: 3.89e-04
2022-05-05 05:05:46,391 INFO [train.py:715] (5/8) Epoch 5, batch 11350, loss[loss=0.1444, simple_loss=0.2185, pruned_loss=0.03518, over 4976.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.04155, over 972108.03 frames.], batch size: 28, lr: 3.89e-04
2022-05-05 05:06:27,198 INFO [train.py:715] (5/8) Epoch 5, batch 11400, loss[loss=0.1583, simple_loss=0.227, pruned_loss=0.04483, over 4894.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.0408, over 973090.68 frames.], batch size: 22, lr: 3.89e-04
2022-05-05 05:07:07,354 INFO [train.py:715] (5/8) Epoch 5, batch 11450, loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03591, over 4985.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04088, over 972916.75 frames.], batch size: 28, lr: 3.89e-04
2022-05-05 05:07:47,394 INFO [train.py:715] (5/8) Epoch 5, batch 11500, loss[loss=0.1464, simple_loss=0.2078, pruned_loss=0.04247, over 4831.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04043, over 972807.60 frames.], batch size: 30, lr: 3.89e-04
2022-05-05 05:08:27,417 INFO [train.py:715] (5/8) Epoch 5, batch 11550, loss[loss=0.1437, simple_loss=0.2227, pruned_loss=0.03237, over 4921.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.0403, over 972766.67 frames.], batch size: 29, lr: 3.89e-04
2022-05-05 05:09:07,609 INFO [train.py:715] (5/8) Epoch 5, batch 11600, loss[loss=0.121, simple_loss=0.1885, pruned_loss=0.02673, over 4840.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2215, pruned_loss=0.0402, over 971774.63 frames.], batch size: 12, lr: 3.89e-04
2022-05-05 05:09:48,312 INFO [train.py:715] (5/8) Epoch 5, batch 11650, loss[loss=0.175, simple_loss=0.2447, pruned_loss=0.05271, over 4832.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2213, pruned_loss=0.04051, over 972219.38 frames.], batch size: 13, lr: 3.89e-04
2022-05-05 05:10:28,061 INFO [train.py:715] (5/8) Epoch 5, batch 11700, loss[loss=0.1434, simple_loss=0.2189, pruned_loss=0.03391, over 4821.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04039, over 972516.19 frames.], batch size: 26, lr: 3.89e-04
2022-05-05 05:11:08,774 INFO [train.py:715] (5/8) Epoch 5, batch 11750, loss[loss=0.1403, simple_loss=0.2106, pruned_loss=0.03503, over 4873.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04106, over 972519.48 frames.], batch size: 22, lr: 3.89e-04
2022-05-05 05:11:48,920 INFO [train.py:715] (5/8) Epoch 5, batch 11800, loss[loss=0.1175, simple_loss=0.1948, pruned_loss=0.02009, over 4778.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04067, over 971872.73 frames.], batch size: 12, lr: 3.89e-04
2022-05-05 05:12:29,043 INFO [train.py:715] (5/8) Epoch 5, batch 11850, loss[loss=0.1608, simple_loss=0.2338, pruned_loss=0.04388, over 4840.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04055, over 971749.71 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:13:08,179 INFO [train.py:715] (5/8) Epoch 5, batch 11900, loss[loss=0.1528, simple_loss=0.2186, pruned_loss=0.04344, over 4806.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04105, over 971947.58 frames.], batch size: 13, lr: 3.89e-04
2022-05-05 05:13:47,504 INFO [train.py:715] (5/8) Epoch 5, batch 11950, loss[loss=0.1731, simple_loss=0.2322, pruned_loss=0.05703, over 4962.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04097, over 971813.42 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:14:27,512 INFO [train.py:715] (5/8) Epoch 5, batch 12000, loss[loss=0.1351, simple_loss=0.2067, pruned_loss=0.03176, over 4744.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2224, pruned_loss=0.04104, over 971145.97 frames.], batch size: 16, lr: 3.89e-04
2022-05-05 05:14:27,513 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 05:14:37,326 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1103, simple_loss=0.1957, pruned_loss=0.01243, over 914524.00 frames.
2022-05-05 05:15:17,600 INFO [train.py:715] (5/8) Epoch 5, batch 12050, loss[loss=0.1387, simple_loss=0.2165, pruned_loss=0.03044, over 4985.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.04117, over 971411.89 frames.], batch size: 24, lr: 3.89e-04
2022-05-05 05:15:57,244 INFO [train.py:715] (5/8) Epoch 5, batch 12100, loss[loss=0.1675, simple_loss=0.2286, pruned_loss=0.05316, over 4794.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.04109, over 971229.23 frames.], batch size: 14, lr: 3.89e-04
2022-05-05 05:16:36,756 INFO [train.py:715] (5/8) Epoch 5, batch 12150, loss[loss=0.1419, simple_loss=0.2195, pruned_loss=0.03213, over 4683.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2228, pruned_loss=0.04091, over 970139.89 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:17:16,020 INFO [train.py:715] (5/8) Epoch 5, batch 12200, loss[loss=0.1388, simple_loss=0.2085, pruned_loss=0.03457, over 4934.00 frames.], tot_loss[loss=0.153, simple_loss=0.2233, pruned_loss=0.04138, over 970847.32 frames.], batch size: 18, lr: 3.88e-04
2022-05-05 05:17:56,097 INFO [train.py:715] (5/8) Epoch 5, batch 12250, loss[loss=0.1492, simple_loss=0.2175, pruned_loss=0.04051, over 4895.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04103, over 971097.78 frames.], batch size: 17, lr: 3.88e-04
2022-05-05 05:18:35,377 INFO [train.py:715] (5/8) Epoch 5, batch 12300, loss[loss=0.1401, simple_loss=0.2105, pruned_loss=0.03483, over 4960.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04138, over 971725.32 frames.], batch size: 35, lr: 3.88e-04
2022-05-05 05:19:14,278 INFO [train.py:715] (5/8) Epoch 5, batch 12350, loss[loss=0.1459, simple_loss=0.2252, pruned_loss=0.03334, over 4702.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04155, over 971846.63 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:19:53,849 INFO [train.py:715] (5/8) Epoch 5, batch 12400, loss[loss=0.1972, simple_loss=0.2609, pruned_loss=0.06679, over 4904.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04129, over 971960.52 frames.], batch size: 17, lr: 3.88e-04
2022-05-05 05:20:33,433 INFO [train.py:715] (5/8) Epoch 5, batch 12450, loss[loss=0.1564, simple_loss=0.2246, pruned_loss=0.04412, over 4863.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04063, over 972021.56 frames.], batch size: 32, lr: 3.88e-04
2022-05-05 05:21:12,665 INFO [train.py:715] (5/8) Epoch 5, batch 12500, loss[loss=0.1625, simple_loss=0.2227, pruned_loss=0.05116, over 4783.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04057, over 972686.78 frames.], batch size: 14, lr: 3.88e-04
2022-05-05 05:21:51,878 INFO [train.py:715] (5/8) Epoch 5, batch 12550, loss[loss=0.18, simple_loss=0.2416, pruned_loss=0.05919, over 4827.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2225, pruned_loss=0.04083, over 972866.76 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:22:30,627 INFO [train.py:715] (5/8) Epoch 5, batch 12600, loss[loss=0.1796, simple_loss=0.2418, pruned_loss=0.05875, over 4824.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04117, over 972836.25 frames.], batch size: 25, lr: 3.88e-04
2022-05-05 05:23:08,929 INFO [train.py:715] (5/8) Epoch 5, batch 12650, loss[loss=0.1535, simple_loss=0.218, pruned_loss=0.0445, over 4974.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04126, over 972511.95 frames.], batch size: 35, lr: 3.88e-04
2022-05-05 05:23:47,147 INFO [train.py:715] (5/8) Epoch 5, batch 12700, loss[loss=0.1378, simple_loss=0.2106, pruned_loss=0.03244, over 4773.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.04129, over 972566.57 frames.], batch size: 18, lr: 3.88e-04
2022-05-05 05:24:27,019 INFO [train.py:715] (5/8) Epoch 5, batch 12750, loss[loss=0.1592, simple_loss=0.2305, pruned_loss=0.04389, over 4806.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04171, over 972662.54 frames.], batch size: 25, lr: 3.88e-04
2022-05-05 05:25:06,590 INFO [train.py:715] (5/8) Epoch 5, batch 12800, loss[loss=0.1435, simple_loss=0.2019, pruned_loss=0.04253, over 4759.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04163, over 972350.59 frames.], batch size: 19, lr: 3.88e-04
2022-05-05 05:25:46,758 INFO [train.py:715] (5/8) Epoch 5, batch 12850, loss[loss=0.1539, simple_loss=0.2357, pruned_loss=0.03606, over 4937.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04189, over 972891.32 frames.], batch size: 23, lr: 3.88e-04
2022-05-05 05:26:26,307 INFO [train.py:715] (5/8) Epoch 5, batch 12900, loss[loss=0.2176, simple_loss=0.2915, pruned_loss=0.07185, over 4761.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2245, pruned_loss=0.04211, over 972117.43 frames.], batch size: 19, lr: 3.88e-04
2022-05-05 05:27:06,305 INFO [train.py:715] (5/8) Epoch 5, batch 12950, loss[loss=0.1602, simple_loss=0.2332, pruned_loss=0.04362, over 4946.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2247, pruned_loss=0.04216, over 972233.10 frames.], batch size: 29, lr: 3.88e-04
2022-05-05 05:27:45,736 INFO [train.py:715] (5/8) Epoch 5, batch 13000, loss[loss=0.1509, simple_loss=0.2271, pruned_loss=0.03741, over 4941.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04137, over 972475.87 frames.], batch size: 35, lr: 3.88e-04
2022-05-05 05:28:25,611 INFO [train.py:715] (5/8) Epoch 5, batch 13050, loss[loss=0.1578, simple_loss=0.232, pruned_loss=0.04176, over 4933.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.0413, over 971838.13 frames.], batch size: 35, lr: 3.88e-04
2022-05-05 05:29:03,807 INFO [train.py:715] (5/8) Epoch 5, batch 13100, loss[loss=0.1352, simple_loss=0.2109, pruned_loss=0.02972, over 4930.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04098, over 972393.79 frames.], batch size: 23, lr: 3.87e-04
2022-05-05 05:29:42,388 INFO [train.py:715] (5/8) Epoch 5, batch 13150, loss[loss=0.1678, simple_loss=0.2322, pruned_loss=0.05169, over 4921.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.04072, over 972087.47 frames.], batch size: 39, lr: 3.87e-04
2022-05-05 05:30:20,478 INFO [train.py:715] (5/8) Epoch 5, batch 13200, loss[loss=0.1714, simple_loss=0.2545, pruned_loss=0.04416, over 4696.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2235, pruned_loss=0.04041, over 971964.37 frames.], batch size: 15, lr: 3.87e-04
2022-05-05 05:30:58,489 INFO [train.py:715] (5/8) Epoch 5, batch 13250, loss[loss=0.1502, simple_loss=0.2202, pruned_loss=0.04009, over 4815.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.04016, over 972230.19 frames.], batch size: 21, lr: 3.87e-04
2022-05-05 05:31:37,092 INFO [train.py:715] (5/8) Epoch 5, batch 13300, loss[loss=0.147, simple_loss=0.2173, pruned_loss=0.03831, over 4813.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.03974, over 972388.05 frames.], batch size: 26, lr: 3.87e-04
2022-05-05 05:32:14,952 INFO [train.py:715] (5/8) Epoch 5, batch 13350, loss[loss=0.1784, simple_loss=0.2516, pruned_loss=0.05262, over 4907.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04008, over 972115.25 frames.], batch size: 17, lr: 3.87e-04
2022-05-05 05:32:53,086 INFO [train.py:715] (5/8) Epoch 5, batch 13400, loss[loss=0.1131, simple_loss=0.1855, pruned_loss=0.02037, over 4865.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.03998, over 971844.31 frames.], batch size: 20, lr: 3.87e-04
2022-05-05 05:33:30,830 INFO [train.py:715] (5/8) Epoch 5, batch 13450, loss[loss=0.1288, simple_loss=0.2088, pruned_loss=0.02444, over 4979.00 frames.], tot_loss[loss=0.151, simple_loss=0.2223, pruned_loss=0.0398, over 972764.16 frames.], batch size: 24, lr: 3.87e-04
2022-05-05 05:34:09,167 INFO [train.py:715] (5/8) Epoch 5, batch 13500, loss[loss=0.1261, simple_loss=0.213, pruned_loss=0.01961, over 4871.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2231, pruned_loss=0.04026, over 972958.37 frames.], batch size: 16, lr: 3.87e-04
2022-05-05 05:34:47,070 INFO [train.py:715] (5/8) Epoch 5, batch 13550, loss[loss=0.1698, simple_loss=0.2438, pruned_loss=0.04797, over 4950.00 frames.], tot_loss[loss=0.151, simple_loss=0.2225, pruned_loss=0.0398, over 973725.46 frames.], batch size: 29, lr: 3.87e-04
2022-05-05 05:35:24,569 INFO [train.py:715] (5/8) Epoch 5, batch 13600, loss[loss=0.155, simple_loss=0.2186, pruned_loss=0.04575, over 4810.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2232, pruned_loss=0.03986, over 973623.28 frames.], batch size: 13, lr: 3.87e-04
2022-05-05 05:36:03,222 INFO [train.py:715] (5/8) Epoch 5, batch 13650, loss[loss=0.1574, simple_loss=0.2324, pruned_loss=0.04126, over 4791.00 frames.], tot_loss[loss=0.1512, simple_loss=0.223, pruned_loss=0.03968, over 973183.92 frames.], batch size: 18, lr: 3.87e-04
2022-05-05 05:36:41,018 INFO [train.py:715] (5/8) Epoch 5, batch 13700, loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03309, over 4745.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2228, pruned_loss=0.03989, over 972811.69 frames.], batch size: 16, lr: 3.87e-04
2022-05-05 05:37:19,075 INFO [train.py:715] (5/8) Epoch 5, batch 13750, loss[loss=0.1417, simple_loss=0.2155, pruned_loss=0.03397, over 4823.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2227, pruned_loss=0.0401, over 973426.12 frames.], batch size: 15, lr: 3.87e-04
2022-05-05 05:37:56,881 INFO [train.py:715] (5/8) Epoch 5, batch 13800, loss[loss=0.1423, simple_loss=0.2172, pruned_loss=0.03369, over 4976.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.04108, over 973407.61 frames.], batch size: 28, lr: 3.87e-04
2022-05-05 05:38:35,345 INFO [train.py:715] (5/8) Epoch 5, batch 13850, loss[loss=0.132, simple_loss=0.1986, pruned_loss=0.03269, over 4904.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2236, pruned_loss=0.04106, over 972876.24 frames.], batch size: 17, lr: 3.87e-04
2022-05-05 05:39:13,571 INFO [train.py:715] (5/8) Epoch 5, batch 13900, loss[loss=0.1702, simple_loss=0.2347, pruned_loss=0.05289, over 4856.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2234, pruned_loss=0.04063, over 972672.80 frames.], batch size: 32, lr: 3.87e-04
2022-05-05 05:39:51,056 INFO [train.py:715] (5/8) Epoch 5, batch 13950, loss[loss=0.1507, simple_loss=0.2193, pruned_loss=0.04106, over 4905.00 frames.], tot_loss[loss=0.1525, simple_loss=0.224, pruned_loss=0.0405, over 973607.10 frames.], batch size: 18, lr: 3.87e-04
2022-05-05 05:40:29,786 INFO [train.py:715] (5/8) Epoch 5, batch 14000, loss[loss=0.1618, simple_loss=0.2328, pruned_loss=0.04537, over 4924.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2236, pruned_loss=0.04034, over 973634.25 frames.], batch size: 29, lr: 3.87e-04
2022-05-05 05:41:07,813 INFO [train.py:715] (5/8) Epoch 5, batch 14050, loss[loss=0.1465, simple_loss=0.2228, pruned_loss=0.03509, over 4702.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2236, pruned_loss=0.04043, over 973715.39 frames.], batch size: 15, lr: 3.87e-04
2022-05-05 05:41:45,577 INFO [train.py:715] (5/8) Epoch 5, batch 14100, loss[loss=0.1423, simple_loss=0.2213, pruned_loss=0.03163, over 4769.00 frames.], tot_loss[loss=0.152, simple_loss=0.2234, pruned_loss=0.04036, over 974135.78 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:42:23,454 INFO [train.py:715] (5/8) Epoch 5, batch 14150, loss[loss=0.1236, simple_loss=0.1973, pruned_loss=0.02496, over 4801.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2231, pruned_loss=0.04037, over 974436.12 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:43:01,798 INFO [train.py:715] (5/8) Epoch 5, batch 14200, loss[loss=0.1264, simple_loss=0.1935, pruned_loss=0.02965, over 4817.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2236, pruned_loss=0.0408, over 973613.29 frames.], batch size: 26, lr: 3.86e-04
2022-05-05 05:43:40,048 INFO [train.py:715] (5/8) Epoch 5, batch 14250, loss[loss=0.1671, simple_loss=0.2308, pruned_loss=0.0517, over 4888.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2244, pruned_loss=0.04119, over 972790.29 frames.], batch size: 19, lr: 3.86e-04
2022-05-05 05:44:18,049 INFO [train.py:715] (5/8) Epoch 5, batch 14300, loss[loss=0.1463, simple_loss=0.2209, pruned_loss=0.03586, over 4823.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2244, pruned_loss=0.04171, over 972813.59 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:44:56,433 INFO [train.py:715] (5/8) Epoch 5, batch 14350, loss[loss=0.1571, simple_loss=0.2294, pruned_loss=0.04237, over 4966.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2249, pruned_loss=0.04221, over 972400.03 frames.], batch size: 24, lr: 3.86e-04
2022-05-05 05:45:34,229 INFO [train.py:715] (5/8) Epoch 5, batch 14400, loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.05325, over 4699.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.04232, over 971101.69 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:46:11,861 INFO [train.py:715] (5/8) Epoch 5, batch 14450, loss[loss=0.1448, simple_loss=0.2096, pruned_loss=0.03998, over 4837.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04128, over 971204.13 frames.], batch size: 13, lr: 3.86e-04
2022-05-05 05:46:49,660 INFO [train.py:715] (5/8) Epoch 5, batch 14500, loss[loss=0.1796, simple_loss=0.2402, pruned_loss=0.05949, over 4756.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2246, pruned_loss=0.04211, over 971112.83 frames.], batch size: 18, lr: 3.86e-04
2022-05-05 05:47:27,995 INFO [train.py:715] (5/8) Epoch 5, batch 14550, loss[loss=0.1495, simple_loss=0.2287, pruned_loss=0.0352, over 4942.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2237, pruned_loss=0.04174, over 971961.72 frames.], batch size: 29, lr: 3.86e-04
2022-05-05 05:48:06,094 INFO [train.py:715] (5/8) Epoch 5, batch 14600, loss[loss=0.1394, simple_loss=0.2048, pruned_loss=0.03703, over 4975.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2234, pruned_loss=0.04168, over 971574.61 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:48:44,026 INFO [train.py:715] (5/8) Epoch 5, batch 14650, loss[loss=0.1505, simple_loss=0.2283, pruned_loss=0.03634, over 4823.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2235, pruned_loss=0.04165, over 971901.66 frames.], batch size: 26, lr: 3.86e-04
2022-05-05 05:49:22,272 INFO [train.py:715] (5/8) Epoch 5, batch 14700, loss[loss=0.1204, simple_loss=0.1928, pruned_loss=0.02402, over 4858.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04153, over 972420.33 frames.], batch size: 13, lr: 3.86e-04
2022-05-05 05:49:59,644 INFO [train.py:715] (5/8) Epoch 5, batch 14750, loss[loss=0.1297, simple_loss=0.196, pruned_loss=0.03173, over 4903.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04131, over 971685.75 frames.], batch size: 22, lr: 3.86e-04
2022-05-05 05:50:37,675 INFO [train.py:715] (5/8) Epoch 5, batch 14800, loss[loss=0.1553, simple_loss=0.2234, pruned_loss=0.04361, over 4979.00 frames.], tot_loss[loss=0.153, simple_loss=0.2231, pruned_loss=0.04143, over 972828.64 frames.], batch size: 28, lr: 3.86e-04
2022-05-05 05:51:15,492 INFO [train.py:715] (5/8) Epoch 5, batch 14850, loss[loss=0.1733, simple_loss=0.2533, pruned_loss=0.04662, over 4785.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2238, pruned_loss=0.0419, over 972151.85 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:51:54,088 INFO [train.py:715] (5/8) Epoch 5, batch 14900, loss[loss=0.129, simple_loss=0.2064, pruned_loss=0.02582, over 4904.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04138, over 972167.59 frames.], batch size: 19, lr: 3.86e-04
2022-05-05 05:52:32,748 INFO [train.py:715] (5/8) Epoch 5, batch 14950, loss[loss=0.1573, simple_loss=0.2256, pruned_loss=0.04452, over 4781.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2235, pruned_loss=0.04141, over 972241.48 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:53:10,808 INFO [train.py:715] (5/8) Epoch 5, batch 15000, loss[loss=0.1339, simple_loss=0.1995, pruned_loss=0.03415, over 4798.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04153, over 971990.69 frames.], batch size: 13, lr: 3.86e-04
2022-05-05 05:53:10,809 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 05:53:21,082 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1105, simple_loss=0.1958, pruned_loss=0.01261, over 914524.00 frames.
2022-05-05 05:53:58,557 INFO [train.py:715] (5/8) Epoch 5, batch 15050, loss[loss=0.1551, simple_loss=0.2311, pruned_loss=0.03957, over 4942.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.04125, over 972208.19 frames.], batch size: 23, lr: 3.85e-04
2022-05-05 05:54:37,214 INFO [train.py:715] (5/8) Epoch 5, batch 15100, loss[loss=0.1459, simple_loss=0.2225, pruned_loss=0.03462, over 4855.00 frames.], tot_loss[loss=0.153, simple_loss=0.2232, pruned_loss=0.04144, over 972356.92 frames.], batch size: 20, lr: 3.85e-04
2022-05-05 05:55:15,135 INFO [train.py:715] (5/8) Epoch 5, batch 15150, loss[loss=0.1852, simple_loss=0.2567, pruned_loss=0.05689, over 4826.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2244, pruned_loss=0.04201, over 971236.41 frames.], batch size: 26, lr: 3.85e-04
2022-05-05 05:55:53,271 INFO [train.py:715] (5/8) Epoch 5, batch 15200, loss[loss=0.1837, simple_loss=0.2434, pruned_loss=0.06199, over 4827.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2242, pruned_loss=0.04159, over 971855.43 frames.], batch size: 26, lr: 3.85e-04
2022-05-05 05:56:32,187 INFO [train.py:715] (5/8) Epoch 5, batch 15250, loss[loss=0.1453, simple_loss=0.2095, pruned_loss=0.04056, over 4972.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2259, pruned_loss=0.04249, over 971824.99 frames.], batch size: 24, lr: 3.85e-04
2022-05-05 05:57:10,898 INFO [train.py:715] (5/8) Epoch 5, batch 15300, loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03642, over 4947.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2241, pruned_loss=0.04148, over 971416.16 frames.], batch size: 39, lr: 3.85e-04
2022-05-05 05:57:50,138 INFO [train.py:715] (5/8) Epoch 5, batch 15350, loss[loss=0.1445, simple_loss=0.2159, pruned_loss=0.03658, over 4742.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2243, pruned_loss=0.04169, over 972002.12 frames.], batch size: 16, lr: 3.85e-04
2022-05-05 05:58:28,475 INFO [train.py:715] (5/8) Epoch 5, batch 15400, loss[loss=0.1318, simple_loss=0.2034, pruned_loss=0.03007, over 4754.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2238, pruned_loss=0.04162, over 972873.83 frames.], batch size: 16, lr: 3.85e-04
2022-05-05 05:59:07,519 INFO [train.py:715] (5/8) Epoch 5, batch 15450, loss[loss=0.1384, simple_loss=0.2027, pruned_loss=0.03709, over 4973.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04152, over 973037.14 frames.], batch size: 14, lr: 3.85e-04
2022-05-05 05:59:46,050 INFO [train.py:715] (5/8) Epoch 5, batch 15500, loss[loss=0.1519, simple_loss=0.2306, pruned_loss=0.03662, over 4929.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2237, pruned_loss=0.04163, over 972458.39 frames.], batch size: 23, lr: 3.85e-04
2022-05-05 06:00:25,316 INFO [train.py:715] (5/8) Epoch 5, batch 15550, loss[loss=0.1213, simple_loss=0.1956, pruned_loss=0.02346, over 4798.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.04147, over 972793.84 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 06:01:03,325 INFO [train.py:715] (5/8) Epoch 5, batch 15600, loss[loss=0.1468, simple_loss=0.2135, pruned_loss=0.04001, over 4863.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04129, over 973131.64 frames.], batch size: 32, lr: 3.85e-04
2022-05-05 06:01:40,926 INFO [train.py:715] (5/8) Epoch 5, batch 15650, loss[loss=0.1399, simple_loss=0.2094, pruned_loss=0.0352, over 4976.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2233, pruned_loss=0.04164, over 973105.64 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 06:02:18,446 INFO [train.py:715] (5/8) Epoch 5, batch 15700, loss[loss=0.1493, simple_loss=0.2217, pruned_loss=0.03849, over 4825.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2234, pruned_loss=0.04175, over 972531.24 frames.], batch size: 26, lr: 3.85e-04
2022-05-05 06:02:56,464 INFO [train.py:715] (5/8) Epoch 5, batch 15750, loss[loss=0.1584, simple_loss=0.2351, pruned_loss=0.04081, over 4890.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04114, over 972800.17 frames.], batch size: 17, lr: 3.85e-04
2022-05-05 06:03:34,887 INFO [train.py:715] (5/8) Epoch 5, batch 15800, loss[loss=0.1654, simple_loss=0.2342, pruned_loss=0.04829, over 4918.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2236, pruned_loss=0.04143, over 972566.88 frames.], batch size: 17, lr: 3.85e-04
2022-05-05 06:04:12,954 INFO [train.py:715] (5/8) Epoch 5, batch 15850, loss[loss=0.1365, simple_loss=0.2058, pruned_loss=0.03357, over 4848.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04106, over 972609.86 frames.], batch size: 32, lr: 3.85e-04
2022-05-05 06:04:50,528 INFO [train.py:715] (5/8) Epoch 5, batch 15900, loss[loss=0.1752, simple_loss=0.2346, pruned_loss=0.05784, over 4830.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2235, pruned_loss=0.04106, over 972665.97 frames.], batch size: 15, lr: 3.85e-04
2022-05-05 06:05:28,344 INFO [train.py:715] (5/8) Epoch 5, batch 15950, loss[loss=0.1593, simple_loss=0.2313, pruned_loss=0.04361, over 4967.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04117, over 972685.53 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 06:06:05,813 INFO [train.py:715] (5/8) Epoch 5, batch 16000, loss[loss=0.1604, simple_loss=0.2232, pruned_loss=0.0488, over 4803.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04074, over 971984.80 frames.], batch size: 14, lr: 3.85e-04
2022-05-05 06:06:43,536 INFO [train.py:715] (5/8) Epoch 5, batch 16050, loss[loss=0.1338, simple_loss=0.1991, pruned_loss=0.03425, over 4924.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04013, over 972093.28 frames.], batch size: 29, lr: 3.84e-04
2022-05-05 06:07:21,600 INFO [train.py:715] (5/8) Epoch 5, batch 16100, loss[loss=0.149, simple_loss=0.2409, pruned_loss=0.02853, over 4847.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04052, over 972444.46 frames.], batch size: 20, lr: 3.84e-04
2022-05-05 06:08:00,784 INFO [train.py:715] (5/8) Epoch 5, batch 16150, loss[loss=0.1527, simple_loss=0.2145, pruned_loss=0.04548, over 4895.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04084, over 972623.90 frames.], batch size: 19, lr: 3.84e-04
2022-05-05 06:08:39,729 INFO [train.py:715] (5/8) Epoch 5, batch 16200, loss[loss=0.1479, simple_loss=0.2204, pruned_loss=0.03776, over 4965.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2231, pruned_loss=0.04076, over 972974.45 frames.], batch size: 21, lr: 3.84e-04
2022-05-05 06:09:18,290 INFO [train.py:715] (5/8) Epoch 5, batch 16250, loss[loss=0.1218, simple_loss=0.1978, pruned_loss=0.02284, over 4830.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04109, over 973144.80 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:09:56,098 INFO [train.py:715] (5/8) Epoch 5, batch 16300, loss[loss=0.1428, simple_loss=0.2115, pruned_loss=0.03706, over 4846.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2236, pruned_loss=0.04086, over 973091.32 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:10:34,110 INFO [train.py:715] (5/8) Epoch 5, batch 16350, loss[loss=0.1328, simple_loss=0.2022, pruned_loss=0.03167, over 4966.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.04064, over 973160.44 frames.], batch size: 24, lr: 3.84e-04
2022-05-05 06:11:12,494 INFO [train.py:715] (5/8) Epoch 5, batch 16400, loss[loss=0.1831, simple_loss=0.2363, pruned_loss=0.06492, over 4947.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04032, over 972929.85 frames.], batch size: 35, lr: 3.84e-04
2022-05-05 06:11:50,951 INFO [train.py:715] (5/8) Epoch 5, batch 16450, loss[loss=0.1445, simple_loss=0.2073, pruned_loss=0.04087, over 4742.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04062, over 972395.37 frames.], batch size: 16, lr: 3.84e-04
2022-05-05 06:12:30,301 INFO [train.py:715] (5/8) Epoch 5, batch 16500, loss[loss=0.1997, simple_loss=0.259, pruned_loss=0.07019, over 4873.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04036, over 972202.18 frames.], batch size: 30, lr: 3.84e-04
2022-05-05 06:13:08,221 INFO [train.py:715] (5/8) Epoch 5, batch 16550, loss[loss=0.1478, simple_loss=0.2176, pruned_loss=0.03896, over 4779.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04017, over 971804.20 frames.], batch size: 14, lr: 3.84e-04
2022-05-05 06:13:46,906 INFO [train.py:715] (5/8) Epoch 5, batch 16600, loss[loss=0.136, simple_loss=0.2026, pruned_loss=0.03472, over 4959.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04041, over 971511.00 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:14:25,620 INFO [train.py:715] (5/8) Epoch 5, batch 16650, loss[loss=0.1679, simple_loss=0.2539, pruned_loss=0.04098, over 4693.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2223, pruned_loss=0.04078, over 971707.32 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:15:04,296 INFO [train.py:715] (5/8) Epoch 5, batch 16700, loss[loss=0.1621, simple_loss=0.2215, pruned_loss=0.05137, over 4879.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04125, over 971885.77 frames.], batch size: 16, lr: 3.84e-04
2022-05-05 06:15:42,484 INFO [train.py:715] (5/8) Epoch 5, batch 16750, loss[loss=0.1688, simple_loss=0.2335, pruned_loss=0.05207, over 4829.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.041, over 972073.48 frames.], batch size: 26, lr: 3.84e-04
2022-05-05 06:16:20,937 INFO [train.py:715] (5/8) Epoch 5, batch 16800, loss[loss=0.1638, simple_loss=0.2359, pruned_loss=0.04587, over 4881.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04057, over 972163.33 frames.], batch size: 22, lr: 3.84e-04
2022-05-05 06:17:00,069 INFO [train.py:715] (5/8) Epoch 5, batch 16850, loss[loss=0.1302, simple_loss=0.2109, pruned_loss=0.0248, over 4806.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04062, over 972014.69 frames.], batch size: 21, lr: 3.84e-04
2022-05-05 06:17:37,930 INFO [train.py:715] (5/8) Epoch 5, batch 16900, loss[loss=0.1427, simple_loss=0.213, pruned_loss=0.03619, over 4871.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.04147, over 971362.83 frames.], batch size: 16, lr: 3.84e-04
2022-05-05 06:18:16,757 INFO [train.py:715] (5/8) Epoch 5, batch 16950, loss[loss=0.1397, simple_loss=0.2141, pruned_loss=0.03265, over 4987.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2236, pruned_loss=0.04125, over 971253.34 frames.], batch size: 14, lr: 3.84e-04
2022-05-05 06:18:55,163 INFO [train.py:715] (5/8) Epoch 5, batch 17000, loss[loss=0.1256, simple_loss=0.2, pruned_loss=0.02564, over 4766.00 frames.], tot_loss[loss=0.153, simple_loss=0.2239, pruned_loss=0.04105, over 971452.16 frames.], batch size: 18, lr: 3.84e-04
2022-05-05 06:19:33,551 INFO [train.py:715] (5/8) Epoch 5, batch 17050, loss[loss=0.1611, simple_loss=0.2325, pruned_loss=0.04487, over 4795.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2232, pruned_loss=0.04055, over 972068.38 frames.], batch size: 24, lr: 3.83e-04
2022-05-05 06:20:11,943 INFO [train.py:715] (5/8) Epoch 5, batch 17100, loss[loss=0.1762, simple_loss=0.2384, pruned_loss=0.05699, over 4929.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2243, pruned_loss=0.04136, over 972072.48 frames.], batch size: 17, lr: 3.83e-04
2022-05-05 06:20:49,751 INFO [train.py:715] (5/8) Epoch 5, batch 17150, loss[loss=0.1517, simple_loss=0.2208, pruned_loss=0.04133, over 4811.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04105, over 971917.56 frames.], batch size: 25, lr: 3.83e-04
2022-05-05 06:21:27,631 INFO [train.py:715] (5/8) Epoch 5, batch 17200, loss[loss=0.153, simple_loss=0.2213, pruned_loss=0.04235, over 4976.00 frames.], tot_loss[loss=0.153, simple_loss=0.2236, pruned_loss=0.04117, over 971947.73 frames.], batch size: 35, lr: 3.83e-04
2022-05-05 06:22:04,737 INFO [train.py:715] (5/8) Epoch 5, batch 17250, loss[loss=0.152, simple_loss=0.2209, pruned_loss=0.04153, over 4859.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.0415, over 971811.66 frames.], batch size: 32, lr: 3.83e-04
2022-05-05 06:22:42,971 INFO [train.py:715] (5/8) Epoch 5, batch 17300, loss[loss=0.1147, simple_loss=0.1915, pruned_loss=0.01891, over 4883.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04119, over 972738.96 frames.], batch size: 22, lr: 3.83e-04
2022-05-05 06:23:22,501 INFO [train.py:715] (5/8) Epoch 5, batch 17350, loss[loss=0.1483, simple_loss=0.2218, pruned_loss=0.03739, over 4907.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.04137, over 972841.75 frames.], batch size: 18, lr: 3.83e-04
2022-05-05 06:24:00,876 INFO [train.py:715] (5/8) Epoch 5, batch 17400, loss[loss=0.1579, simple_loss=0.2232, pruned_loss=0.04631, over 4965.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.04164, over 972694.72 frames.], batch size: 39, lr: 3.83e-04
2022-05-05 06:24:39,482 INFO [train.py:715] (5/8) Epoch 5, batch 17450, loss[loss=0.1584, simple_loss=0.2338, pruned_loss=0.0415, over 4791.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.0415, over 972212.80 frames.], batch size: 14, lr: 3.83e-04
2022-05-05 06:25:17,958 INFO [train.py:715] (5/8) Epoch 5, batch 17500, loss[loss=0.1587, simple_loss=0.2438, pruned_loss=0.03679, over 4856.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04129, over 972756.93 frames.], batch size: 32, lr: 3.83e-04
2022-05-05 06:25:56,805 INFO [train.py:715] (5/8) Epoch 5, batch 17550, loss[loss=0.1473, simple_loss=0.2123, pruned_loss=0.04113, over 4826.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2239, pruned_loss=0.0417, over 973334.02 frames.], batch size: 30, lr: 3.83e-04
2022-05-05 06:26:35,443 INFO [train.py:715] (5/8) Epoch 5, batch 17600, loss[loss=0.1574, simple_loss=0.2328, pruned_loss=0.04104, over 4982.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.04147, over 973576.63 frames.], batch size: 27, lr: 3.83e-04
2022-05-05 06:27:14,152 INFO [train.py:715] (5/8) Epoch 5, batch 17650, loss[loss=0.1752, simple_loss=0.2423, pruned_loss=0.05406, over 4903.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2243, pruned_loss=0.04154, over 973705.64 frames.], batch size: 17, lr: 3.83e-04
2022-05-05 06:27:52,808 INFO [train.py:715] (5/8) Epoch 5, batch 17700, loss[loss=0.1563, simple_loss=0.2266, pruned_loss=0.04299, over 4898.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2232, pruned_loss=0.04146, over 973992.14 frames.], batch size: 22, lr: 3.83e-04
2022-05-05 06:28:31,727 INFO [train.py:715] (5/8) Epoch 5, batch 17750, loss[loss=0.1375, simple_loss=0.2143, pruned_loss=0.03042, over 4852.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04092, over 974074.49 frames.], batch size: 20, lr: 3.83e-04
2022-05-05 06:29:09,753 INFO [train.py:715] (5/8) Epoch 5, batch 17800, loss[loss=0.1315, simple_loss=0.2105, pruned_loss=0.02622, over 4985.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04062, over 973475.61 frames.], batch size: 25, lr: 3.83e-04
2022-05-05 06:29:48,584 INFO [train.py:715] (5/8) Epoch 5, batch 17850, loss[loss=0.1523, simple_loss=0.234, pruned_loss=0.03532, over 4943.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2227, pruned_loss=0.04041, over 973547.34 frames.], batch size: 29, lr: 3.83e-04
2022-05-05 06:30:27,677 INFO [train.py:715] (5/8) Epoch 5, batch 17900, loss[loss=0.1872, simple_loss=0.263, pruned_loss=0.05567, over 4958.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04004, over 973736.29 frames.], batch size: 24, lr: 3.83e-04
2022-05-05 06:31:06,329 INFO [train.py:715] (5/8) Epoch 5, batch 17950, loss[loss=0.1293, simple_loss=0.2071, pruned_loss=0.02578, over 4957.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03941, over 972970.98 frames.], batch size: 24, lr: 3.83e-04
2022-05-05 06:31:47,054 INFO [train.py:715] (5/8) Epoch 5, batch 18000, loss[loss=0.1583, simple_loss=0.2255, pruned_loss=0.04559, over 4750.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2216, pruned_loss=0.0395, over 972320.97 frames.], batch size: 16, lr: 3.83e-04
2022-05-05 06:31:47,055 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 06:31:59,752 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1102, simple_loss=0.1955, pruned_loss=0.01245, over 914524.00 frames.
2022-05-05 06:32:38,355 INFO [train.py:715] (5/8) Epoch 5, batch 18050, loss[loss=0.1413, simple_loss=0.2114, pruned_loss=0.03562, over 4746.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2209, pruned_loss=0.03911, over 972171.10 frames.], batch size: 19, lr: 3.82e-04
2022-05-05 06:33:17,595 INFO [train.py:715] (5/8) Epoch 5, batch 18100, loss[loss=0.1576, simple_loss=0.2315, pruned_loss=0.04187, over 4953.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2216, pruned_loss=0.03942, over 972858.92 frames.], batch size: 39, lr: 3.82e-04
2022-05-05 06:33:56,333 INFO [train.py:715] (5/8) Epoch 5, batch 18150, loss[loss=0.1532, simple_loss=0.2172, pruned_loss=0.04463, over 4960.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03964, over 972478.70 frames.], batch size: 24, lr: 3.82e-04
2022-05-05 06:34:34,856 INFO [train.py:715] (5/8) Epoch 5, batch 18200, loss[loss=0.163, simple_loss=0.2345, pruned_loss=0.04576, over 4933.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2222, pruned_loss=0.0401, over 972648.22 frames.], batch size: 38, lr: 3.82e-04
2022-05-05 06:35:14,241 INFO [train.py:715] (5/8) Epoch 5, batch 18250, loss[loss=0.2326, simple_loss=0.2927, pruned_loss=0.08628, over 4923.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04093, over 973048.71 frames.], batch size: 23, lr: 3.82e-04
2022-05-05 06:35:53,136 INFO [train.py:715] (5/8) Epoch 5, batch 18300, loss[loss=0.1482, simple_loss=0.2134, pruned_loss=0.04148, over 4792.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04076, over 972380.53 frames.], batch size: 18, lr: 3.82e-04
2022-05-05 06:36:31,709 INFO [train.py:715] (5/8) Epoch 5, batch 18350, loss[loss=0.139, simple_loss=0.21, pruned_loss=0.03404, over 4930.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04083, over 972533.14 frames.], batch size: 23, lr: 3.82e-04
2022-05-05 06:37:09,998 INFO [train.py:715] (5/8) Epoch 5, batch 18400, loss[loss=0.1969, simple_loss=0.2685, pruned_loss=0.06263, over 4918.00 frames.], tot_loss[loss=0.153, simple_loss=0.2237, pruned_loss=0.04112, over 972740.33 frames.], batch size: 39, lr: 3.82e-04
2022-05-05 06:37:49,159 INFO [train.py:715] (5/8) Epoch 5, batch 18450, loss[loss=0.1689, simple_loss=0.2294, pruned_loss=0.05419, over 4712.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2231, pruned_loss=0.04095, over 972281.14 frames.], batch size: 12, lr: 3.82e-04
2022-05-05 06:38:27,816 INFO [train.py:715] (5/8) Epoch 5, batch 18500, loss[loss=0.1301, simple_loss=0.2074, pruned_loss=0.02643, over 4773.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.04062, over 972699.68 frames.], batch size: 17, lr: 3.82e-04
2022-05-05 06:39:06,125 INFO [train.py:715] (5/8) Epoch 5, batch 18550, loss[loss=0.1229, simple_loss=0.2021, pruned_loss=0.02181, over 4878.00 frames.], tot_loss[loss=0.153, simple_loss=0.2238, pruned_loss=0.0411, over 972687.95 frames.], batch size: 22, lr: 3.82e-04
2022-05-05 06:39:45,171 INFO [train.py:715] (5/8) Epoch 5, batch 18600, loss[loss=0.1289, simple_loss=0.2053, pruned_loss=0.02631, over 4938.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04044, over 972916.59 frames.], batch size: 29, lr: 3.82e-04
2022-05-05 06:40:23,779 INFO [train.py:715] (5/8) Epoch 5, batch 18650, loss[loss=0.1393, simple_loss=0.2168, pruned_loss=0.03084, over 4954.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.0401, over 971325.59 frames.], batch size: 24, lr: 3.82e-04
2022-05-05 06:41:01,937 INFO [train.py:715] (5/8) Epoch 5, batch 18700, loss[loss=0.144, simple_loss=0.2105, pruned_loss=0.03882, over 4983.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04025, over 971831.56 frames.], batch size: 25, lr: 3.82e-04
2022-05-05 06:41:40,675 INFO [train.py:715] (5/8) Epoch 5, batch 18750, loss[loss=0.1404, simple_loss=0.194, pruned_loss=0.04344, over 4821.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04078, over 972267.40 frames.], batch size: 13, lr: 3.82e-04
2022-05-05 06:42:19,955 INFO [train.py:715] (5/8) Epoch 5, batch 18800, loss[loss=0.1446, simple_loss=0.2192, pruned_loss=0.03498, over 4867.00 frames.], tot_loss[loss=0.1527, simple_loss=0.223, pruned_loss=0.04121, over 972075.45 frames.], batch size: 22, lr: 3.82e-04
2022-05-05 06:42:59,659 INFO [train.py:715] (5/8) Epoch 5, batch 18850, loss[loss=0.1413, simple_loss=0.2083, pruned_loss=0.03719, over 4846.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04102, over 971512.62 frames.], batch size: 32, lr: 3.82e-04
2022-05-05 06:43:38,446 INFO [train.py:715] (5/8) Epoch 5, batch 18900, loss[loss=0.151, simple_loss=0.2232, pruned_loss=0.03941, over 4989.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04146, over 971916.84 frames.], batch size: 25, lr: 3.82e-04
2022-05-05 06:44:16,643 INFO [train.py:715] (5/8) Epoch 5, batch 18950, loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.0467, over 4766.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04155, over 972427.70 frames.], batch size: 19, lr: 3.82e-04
2022-05-05 06:44:56,114 INFO [train.py:715] (5/8) Epoch 5, batch 19000, loss[loss=0.143, simple_loss=0.2122, pruned_loss=0.0369, over 4766.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04116, over 971904.12 frames.], batch size: 12, lr: 3.82e-04
2022-05-05 06:45:34,092 INFO [train.py:715] (5/8) Epoch 5, batch 19050, loss[loss=0.1478, simple_loss=0.2307, pruned_loss=0.03249, over 4821.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2233, pruned_loss=0.04115, over 971691.20 frames.], batch size: 27, lr: 3.81e-04
2022-05-05 06:46:13,036 INFO [train.py:715] (5/8) Epoch 5, batch 19100, loss[loss=0.1531, simple_loss=0.2198, pruned_loss=0.04318, over 4849.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2231, pruned_loss=0.04158, over 971315.77 frames.], batch size: 30, lr: 3.81e-04
2022-05-05 06:46:52,736 INFO [train.py:715] (5/8) Epoch 5, batch 19150, loss[loss=0.1791, simple_loss=0.2549, pruned_loss=0.05167, over 4779.00 frames.], tot_loss[loss=0.1532, simple_loss=0.223, pruned_loss=0.0417, over 971487.48 frames.], batch size: 18, lr: 3.81e-04
2022-05-05 06:47:31,319 INFO [train.py:715] (5/8) Epoch 5, batch 19200, loss[loss=0.1633, simple_loss=0.238, pruned_loss=0.04427, over 4968.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04104, over 971660.48 frames.], batch size: 40, lr: 3.81e-04
2022-05-05 06:48:10,846 INFO [train.py:715] (5/8) Epoch 5, batch 19250, loss[loss=0.1177, simple_loss=0.1881, pruned_loss=0.02362, over 4785.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2218, pruned_loss=0.04077, over 971580.47 frames.], batch size: 12, lr: 3.81e-04
2022-05-05 06:48:48,906 INFO [train.py:715] (5/8) Epoch 5, batch 19300, loss[loss=0.2045, simple_loss=0.2783, pruned_loss=0.06535, over 4965.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.04115, over 971453.01 frames.], batch size: 24, lr: 3.81e-04
2022-05-05 06:49:27,999 INFO [train.py:715] (5/8) Epoch 5, batch 19350, loss[loss=0.1407, simple_loss=0.2216, pruned_loss=0.02993, over 4757.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04086, over 971611.04 frames.], batch size: 16, lr: 3.81e-04
2022-05-05 06:50:06,758 INFO [train.py:715] (5/8) Epoch 5, batch 19400, loss[loss=0.1749, simple_loss=0.2345, pruned_loss=0.05763, over 4992.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04092, over 971764.26 frames.], batch size: 14, lr: 3.81e-04
2022-05-05 06:50:45,415 INFO [train.py:715] (5/8) Epoch 5, batch 19450, loss[loss=0.1414, simple_loss=0.2227, pruned_loss=0.02998, over 4798.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04101, over 971986.75 frames.], batch size: 21, lr: 3.81e-04
2022-05-05 06:51:25,050 INFO [train.py:715] (5/8) Epoch 5, batch 19500, loss[loss=0.13, simple_loss=0.199, pruned_loss=0.0305, over 4763.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04077, over 972118.75 frames.], batch size: 12, lr: 3.81e-04
2022-05-05 06:52:03,849 INFO [train.py:715] (5/8) Epoch 5, batch 19550, loss[loss=0.1689, simple_loss=0.2349, pruned_loss=0.05144, over 4799.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04125, over 971635.64 frames.], batch size: 21, lr: 3.81e-04
2022-05-05 06:52:42,737 INFO [train.py:715] (5/8) Epoch 5, batch 19600, loss[loss=0.1323, simple_loss=0.2032, pruned_loss=0.03067, over 4854.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04104, over 972060.18 frames.], batch size: 20, lr: 3.81e-04
2022-05-05 06:53:21,191 INFO [train.py:715] (5/8) Epoch 5, batch 19650, loss[loss=0.1977, simple_loss=0.2567, pruned_loss=0.06931, over 4930.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2228, pruned_loss=0.04131, over 972659.54 frames.], batch size: 18, lr: 3.81e-04
2022-05-05 06:54:00,674 INFO [train.py:715] (5/8) Epoch 5, batch 19700, loss[loss=0.1745, simple_loss=0.2451, pruned_loss=0.05199, over 4905.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2216, pruned_loss=0.04065, over 973232.10 frames.], batch size: 17, lr: 3.81e-04
2022-05-05 06:54:39,904 INFO [train.py:715] (5/8) Epoch 5, batch 19750, loss[loss=0.1496, simple_loss=0.2149, pruned_loss=0.04222, over 4833.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.0406, over 972736.72 frames.], batch size: 13, lr: 3.81e-04
2022-05-05 06:55:17,843 INFO [train.py:715] (5/8) Epoch 5, batch 19800, loss[loss=0.1681, simple_loss=0.2449, pruned_loss=0.04559, over 4920.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04046, over 972670.64 frames.], batch size: 18, lr: 3.81e-04
2022-05-05 06:55:56,846 INFO [train.py:715] (5/8) Epoch 5, batch 19850, loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03407, over 4765.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2228, pruned_loss=0.04121, over 971838.19 frames.], batch size: 19, lr: 3.81e-04
2022-05-05 06:56:35,744 INFO [train.py:715] (5/8) Epoch 5, batch 19900, loss[loss=0.1422, simple_loss=0.2155, pruned_loss=0.03442, over 4904.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04131, over 971398.72 frames.], batch size: 17, lr: 3.81e-04
2022-05-05 06:57:14,680 INFO [train.py:715] (5/8) Epoch 5, batch 19950, loss[loss=0.1635, simple_loss=0.2422, pruned_loss=0.04241, over 4825.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04088, over 972068.65 frames.], batch size: 25, lr: 3.81e-04
2022-05-05 06:57:53,094 INFO [train.py:715] (5/8) Epoch 5, batch 20000, loss[loss=0.139, simple_loss=0.219, pruned_loss=0.02949, over 4925.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04055, over 971829.12 frames.], batch size: 21, lr: 3.81e-04
2022-05-05 06:58:32,599 INFO [train.py:715] (5/8) Epoch 5, batch 20050, loss[loss=0.1764, simple_loss=0.247, pruned_loss=0.05296, over 4986.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04052, over 971775.08 frames.], batch size: 20, lr: 3.81e-04
2022-05-05 06:59:12,130 INFO [train.py:715] (5/8) Epoch 5, batch 20100, loss[loss=0.2286, simple_loss=0.2874, pruned_loss=0.08493, over 4917.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2239, pruned_loss=0.04099, over 971344.25 frames.], batch size: 18, lr: 3.80e-04
2022-05-05 06:59:50,437 INFO [train.py:715] (5/8) Epoch 5, batch 20150, loss[loss=0.1458, simple_loss=0.2127, pruned_loss=0.03941, over 4854.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04075, over 971194.60 frames.], batch size: 32, lr: 3.80e-04
2022-05-05 07:00:30,258 INFO [train.py:715] (5/8) Epoch 5, batch 20200, loss[loss=0.1574, simple_loss=0.2321, pruned_loss=0.04134, over 4945.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04045, over 971128.72 frames.], batch size: 21, lr: 3.80e-04
2022-05-05 07:01:09,276 INFO [train.py:715] (5/8) Epoch 5, batch 20250, loss[loss=0.1602, simple_loss=0.232, pruned_loss=0.04417, over 4683.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2209, pruned_loss=0.04004, over 970741.48 frames.], batch size: 15, lr: 3.80e-04
2022-05-05 07:01:47,789 INFO [train.py:715] (5/8) Epoch 5, batch 20300, loss[loss=0.1367, simple_loss=0.216, pruned_loss=0.02872, over 4988.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04032, over 970315.03 frames.], batch size: 28, lr: 3.80e-04
2022-05-05 07:02:25,749 INFO [train.py:715] (5/8) Epoch 5, batch 20350, loss[loss=0.1403, simple_loss=0.2049, pruned_loss=0.03785, over 4806.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04057, over 970009.73 frames.], batch size: 13, lr: 3.80e-04
2022-05-05 07:03:04,305 INFO [train.py:715] (5/8) Epoch 5, batch 20400, loss[loss=0.1173, simple_loss=0.1826, pruned_loss=0.02599, over 4776.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04079, over 969920.27 frames.], batch size: 14, lr: 3.80e-04
2022-05-05 07:03:43,173 INFO [train.py:715] (5/8) Epoch 5, batch 20450, loss[loss=0.1511, simple_loss=0.2306, pruned_loss=0.03577, over 4798.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.0411, over 970540.00 frames.], batch size: 21, lr: 3.80e-04
2022-05-05 07:04:21,312 INFO [train.py:715] (5/8) Epoch 5, batch 20500, loss[loss=0.1573, simple_loss=0.236, pruned_loss=0.03932, over 4895.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04079, over 971162.27 frames.], batch size: 22, lr: 3.80e-04
2022-05-05 07:05:00,717 INFO [train.py:715] (5/8) Epoch 5, batch 20550, loss[loss=0.1481, simple_loss=0.2201, pruned_loss=0.03799, over 4776.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04031, over 970949.14 frames.], batch size: 18, lr: 3.80e-04
2022-05-05 07:05:39,983 INFO [train.py:715] (5/8) Epoch 5, batch 20600, loss[loss=0.1311, simple_loss=0.2039, pruned_loss=0.02915, over 4942.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.0404, over 970741.17 frames.], batch size: 18, lr: 3.80e-04
2022-05-05 07:06:18,975 INFO [train.py:715] (5/8) Epoch 5, batch 20650, loss[loss=0.1717, simple_loss=0.2411, pruned_loss=0.05116, over 4967.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04105, over 971451.94 frames.], batch size: 15, lr: 3.80e-04
2022-05-05 07:06:58,193 INFO [train.py:715] (5/8) Epoch 5, batch 20700, loss[loss=0.1277, simple_loss=0.2068, pruned_loss=0.02433, over 4809.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2227, pruned_loss=0.04142, over 971787.43 frames.], batch size: 27, lr: 3.80e-04
2022-05-05 07:07:36,956 INFO [train.py:715] (5/8) Epoch 5, batch 20750, loss[loss=0.126, simple_loss=0.208, pruned_loss=0.02194, over 4915.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.04126, over 972180.61 frames.], batch size: 18, lr: 3.80e-04
2022-05-05 07:08:16,383 INFO [train.py:715] (5/8) Epoch 5, batch 20800, loss[loss=0.1575, simple_loss=0.2292, pruned_loss=0.04287, over 4861.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.04152, over 972474.83 frames.], batch size: 20, lr: 3.80e-04
2022-05-05 07:08:55,027 INFO [train.py:715] (5/8) Epoch 5, batch 20850, loss[loss=0.1284, simple_loss=0.189, pruned_loss=0.03392, over 4776.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2238, pruned_loss=0.04119, over 972150.27 frames.], batch size: 14, lr: 3.80e-04
2022-05-05 07:09:34,327 INFO [train.py:715] (5/8) Epoch 5, batch 20900, loss[loss=0.1327, simple_loss=0.2083, pruned_loss=0.02851, over 4914.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.04121, over 971671.55 frames.], batch size: 17, lr: 3.80e-04
2022-05-05 07:10:12,903 INFO [train.py:715] (5/8) Epoch 5, batch 20950, loss[loss=0.1203, simple_loss=0.1873, pruned_loss=0.02664, over 4791.00 frames.], tot_loss[loss=0.1518, simple_loss=0.223, pruned_loss=0.04031, over 971944.06 frames.], batch size: 14, lr: 3.80e-04
2022-05-05 07:10:51,486 INFO [train.py:715] (5/8) Epoch 5, batch 21000, loss[loss=0.1366, simple_loss=0.2126, pruned_loss=0.03025, over 4863.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04039, over 972299.32 frames.], batch size: 20, lr: 3.80e-04
2022-05-05 07:10:51,487 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 07:11:01,469 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1101, simple_loss=0.1954, pruned_loss=0.01242, over 914524.00 frames.
2022-05-05 07:11:40,512 INFO [train.py:715] (5/8) Epoch 5, batch 21050, loss[loss=0.136, simple_loss=0.2088, pruned_loss=0.03162, over 4832.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2242, pruned_loss=0.04127, over 972069.22 frames.], batch size: 26, lr: 3.80e-04
2022-05-05 07:12:19,699 INFO [train.py:715] (5/8) Epoch 5, batch 21100, loss[loss=0.1497, simple_loss=0.2234, pruned_loss=0.03801, over 4771.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2242, pruned_loss=0.04144, over 973744.56 frames.], batch size: 14, lr: 3.79e-04
2022-05-05 07:12:58,344 INFO [train.py:715] (5/8) Epoch 5, batch 21150, loss[loss=0.1503, simple_loss=0.2169, pruned_loss=0.04179, over 4802.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2241, pruned_loss=0.04164, over 972995.36 frames.], batch size: 21, lr: 3.79e-04
2022-05-05 07:13:37,165 INFO [train.py:715] (5/8) Epoch 5, batch 21200, loss[loss=0.1561, simple_loss=0.2283, pruned_loss=0.04201, over 4762.00 frames.], tot_loss[loss=0.154, simple_loss=0.2245, pruned_loss=0.04175, over 973151.86 frames.], batch size: 19, lr: 3.79e-04
2022-05-05 07:14:15,842 INFO [train.py:715] (5/8) Epoch 5, batch 21250, loss[loss=0.1638, simple_loss=0.2324, pruned_loss=0.04767, over 4839.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.04151, over 973161.83 frames.], batch size: 32, lr: 3.79e-04
2022-05-05 07:14:54,661 INFO [train.py:715] (5/8) Epoch 5, batch 21300, loss[loss=0.1289, simple_loss=0.2042, pruned_loss=0.02685, over 4824.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04114, over 972842.00 frames.], batch size: 13, lr: 3.79e-04
2022-05-05 07:15:33,335 INFO [train.py:715] (5/8) Epoch 5, batch 21350, loss[loss=0.1569, simple_loss=0.2224, pruned_loss=0.04569, over 4910.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2231, pruned_loss=0.04135, over 972700.82 frames.], batch size: 18, lr: 3.79e-04
2022-05-05 07:16:11,913 INFO [train.py:715] (5/8) Epoch 5, batch 21400, loss[loss=0.1448, simple_loss=0.2111, pruned_loss=0.03923, over 4818.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.0409, over 973012.34 frames.], batch size: 15, lr: 3.79e-04
2022-05-05 07:16:50,973 INFO [train.py:715] (5/8) Epoch 5, batch 21450, loss[loss=0.1706, simple_loss=0.2412, pruned_loss=0.05004, over 4934.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04066, over 973542.69 frames.], batch size: 39, lr: 3.79e-04
2022-05-05 07:17:29,098 INFO [train.py:715] (5/8) Epoch 5, batch 21500, loss[loss=0.1254, simple_loss=0.1977, pruned_loss=0.02651, over 4973.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04038, over 972517.76 frames.], batch size: 28, lr: 3.79e-04
2022-05-05 07:18:08,223 INFO [train.py:715] (5/8) Epoch 5, batch 21550, loss[loss=0.1558, simple_loss=0.2139, pruned_loss=0.04882, over 4840.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2229, pruned_loss=0.04075, over 972772.84 frames.], batch size: 30, lr: 3.79e-04
2022-05-05 07:18:46,748 INFO [train.py:715] (5/8) Epoch 5, batch 21600, loss[loss=0.1675, simple_loss=0.2292, pruned_loss=0.05293, over 4860.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04094, over 972846.61 frames.], batch size: 32, lr: 3.79e-04
2022-05-05 07:19:25,823 INFO [train.py:715] (5/8) Epoch 5, batch 21650, loss[loss=0.1601, simple_loss=0.2297, pruned_loss=0.0452, over 4878.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04068, over 973446.44 frames.], batch size: 32, lr: 3.79e-04
2022-05-05 07:20:04,069 INFO [train.py:715] (5/8) Epoch 5, batch 21700, loss[loss=0.1394, simple_loss=0.2156, pruned_loss=0.0316, over 4919.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04062, over 973361.75 frames.], batch size: 18, lr: 3.79e-04
2022-05-05 07:20:42,463 INFO [train.py:715] (5/8) Epoch 5, batch 21750, loss[loss=0.1932, simple_loss=0.2531, pruned_loss=0.06664, over 4703.00 frames.], tot_loss[loss=0.152, simple_loss=0.2228, pruned_loss=0.04059, over 972559.06 frames.], batch size: 15, lr: 3.79e-04
2022-05-05 07:21:20,820 INFO [train.py:715] (5/8) Epoch 5, batch 21800, loss[loss=0.1365, simple_loss=0.208, pruned_loss=0.03246, over 4953.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04073, over 972802.92 frames.], batch size: 21, lr: 3.79e-04
2022-05-05 07:22:00,030 INFO [train.py:715] (5/8) Epoch 5, batch 21850, loss[loss=0.1533, simple_loss=0.2262, pruned_loss=0.04025, over 4933.00 frames.], tot_loss[loss=0.153, simple_loss=0.2232, pruned_loss=0.04143, over 972420.49 frames.], batch size: 23, lr: 3.79e-04
2022-05-05 07:22:38,257 INFO [train.py:715] (5/8) Epoch 5, batch 21900, loss[loss=0.1581, simple_loss=0.2355, pruned_loss=0.04031, over 4966.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04151, over 972078.39 frames.], batch size: 24, lr: 3.79e-04
2022-05-05 07:23:16,810 INFO [train.py:715] (5/8) Epoch 5, batch 21950, loss[loss=0.16, simple_loss=0.2267, pruned_loss=0.04662, over 4806.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04124, over 972192.14 frames.], batch size: 21, lr: 3.79e-04
2022-05-05 07:23:55,216 INFO [train.py:715] (5/8) Epoch 5, batch 22000, loss[loss=0.1707, simple_loss=0.2415, pruned_loss=0.04992, over 4782.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2223, pruned_loss=0.04072, over 971722.47 frames.], batch size: 18, lr: 3.79e-04
2022-05-05 07:24:34,723 INFO [train.py:715] (5/8) Epoch 5, batch 22050, loss[loss=0.1367, simple_loss=0.206, pruned_loss=0.03371, over 4942.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2218, pruned_loss=0.04054, over 971346.07 frames.], batch size: 29, lr: 3.79e-04
2022-05-05 07:25:13,186 INFO [train.py:715] (5/8) Epoch 5, batch 22100, loss[loss=0.1367, simple_loss=0.2091, pruned_loss=0.03214, over 4780.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2213, pruned_loss=0.04021, over 971743.18 frames.], batch size: 14, lr: 3.79e-04
2022-05-05 07:25:52,415 INFO [train.py:715] (5/8) Epoch 5, batch 22150, loss[loss=0.1428, simple_loss=0.2044, pruned_loss=0.04057, over 4857.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2209, pruned_loss=0.04002, over 971351.44 frames.], batch size: 20, lr: 3.78e-04
2022-05-05 07:26:31,444 INFO [train.py:715] (5/8) Epoch 5, batch 22200, loss[loss=0.166, simple_loss=0.2298, pruned_loss=0.05106, over 4773.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2202, pruned_loss=0.03971, over 970960.67 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:27:11,164 INFO [train.py:715] (5/8) Epoch 5, batch 22250, loss[loss=0.1127, simple_loss=0.1792, pruned_loss=0.02309, over 4810.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2203, pruned_loss=0.03959, over 971099.20 frames.], batch size: 13, lr: 3.78e-04
2022-05-05 07:27:50,341 INFO [train.py:715] (5/8) Epoch 5, batch 22300, loss[loss=0.1632, simple_loss=0.2246, pruned_loss=0.05088, over 4983.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04053, over 971522.78 frames.], batch size: 15, lr: 3.78e-04
2022-05-05 07:28:28,459 INFO [train.py:715] (5/8) Epoch 5, batch 22350, loss[loss=0.1396, simple_loss=0.2086, pruned_loss=0.03529, over 4892.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04028, over 972190.22 frames.], batch size: 17, lr: 3.78e-04
2022-05-05 07:29:06,833 INFO [train.py:715] (5/8) Epoch 5, batch 22400, loss[loss=0.1543, simple_loss=0.2321, pruned_loss=0.03819, over 4731.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04076, over 972620.90 frames.], batch size: 16, lr: 3.78e-04
2022-05-05 07:29:45,743 INFO [train.py:715] (5/8) Epoch 5, batch 22450, loss[loss=0.1515, simple_loss=0.2155, pruned_loss=0.04381, over 4863.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04068, over 973453.76 frames.], batch size: 16, lr: 3.78e-04
2022-05-05 07:30:25,209 INFO [train.py:715] (5/8) Epoch 5, batch 22500, loss[loss=0.1302, simple_loss=0.2093, pruned_loss=0.02553, over 4881.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04056, over 972752.03 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:31:03,488 INFO [train.py:715] (5/8) Epoch 5, batch 22550, loss[loss=0.1456, simple_loss=0.2152, pruned_loss=0.03799, over 4823.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03991, over 972204.68 frames.], batch size: 26, lr: 3.78e-04
2022-05-05 07:31:42,557 INFO [train.py:715] (5/8) Epoch 5, batch 22600, loss[loss=0.1737, simple_loss=0.2357, pruned_loss=0.05582, over 4846.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03987, over 972205.68 frames.], batch size: 20, lr: 3.78e-04
2022-05-05 07:32:21,687 INFO [train.py:715] (5/8) Epoch 5, batch 22650, loss[loss=0.1572, simple_loss=0.2257, pruned_loss=0.04437, over 4891.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04004, over 973138.03 frames.], batch size: 17, lr: 3.78e-04
2022-05-05 07:33:00,844 INFO [train.py:715] (5/8) Epoch 5, batch 22700, loss[loss=0.1325, simple_loss=0.2047, pruned_loss=0.03015, over 4966.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04096, over 972842.49 frames.], batch size: 14, lr: 3.78e-04
2022-05-05 07:33:39,168 INFO [train.py:715] (5/8) Epoch 5, batch 22750, loss[loss=0.1491, simple_loss=0.2309, pruned_loss=0.03364, over 4700.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04066, over 972953.83 frames.], batch size: 15, lr: 3.78e-04
2022-05-05 07:34:18,364 INFO [train.py:715] (5/8) Epoch 5, batch 22800, loss[loss=0.1521, simple_loss=0.2193, pruned_loss=0.04242, over 4981.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04041, over 973533.21 frames.], batch size: 28, lr: 3.78e-04
2022-05-05 07:34:57,942 INFO [train.py:715] (5/8) Epoch 5, batch 22850, loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03389, over 4823.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04071, over 973430.51 frames.], batch size: 26, lr: 3.78e-04
2022-05-05 07:35:36,338 INFO [train.py:715] (5/8) Epoch 5, batch 22900, loss[loss=0.1814, simple_loss=0.2423, pruned_loss=0.06027, over 4850.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2229, pruned_loss=0.04068, over 973752.43 frames.], batch size: 15, lr: 3.78e-04
2022-05-05 07:36:15,067 INFO [train.py:715] (5/8) Epoch 5, batch 22950, loss[loss=0.1428, simple_loss=0.2112, pruned_loss=0.03723, over 4832.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2227, pruned_loss=0.04048, over 973259.27 frames.], batch size: 14, lr: 3.78e-04
2022-05-05 07:36:54,409 INFO [train.py:715] (5/8) Epoch 5, batch 23000, loss[loss=0.1627, simple_loss=0.2227, pruned_loss=0.0513, over 4819.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04048, over 973602.10 frames.], batch size: 26, lr: 3.78e-04
2022-05-05 07:37:33,573 INFO [train.py:715] (5/8) Epoch 5, batch 23050, loss[loss=0.1096, simple_loss=0.1822, pruned_loss=0.01848, over 4951.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.0406, over 974083.90 frames.], batch size: 23, lr: 3.78e-04
2022-05-05 07:38:12,016 INFO [train.py:715] (5/8) Epoch 5, batch 23100, loss[loss=0.1447, simple_loss=0.2011, pruned_loss=0.04415, over 4693.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.04031, over 973511.58 frames.], batch size: 15, lr: 3.78e-04
2022-05-05 07:38:51,178 INFO [train.py:715] (5/8) Epoch 5, batch 23150, loss[loss=0.1623, simple_loss=0.2221, pruned_loss=0.05126, over 4941.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.041, over 973501.54 frames.], batch size: 23, lr: 3.78e-04
2022-05-05 07:39:30,785 INFO [train.py:715] (5/8) Epoch 5, batch 23200, loss[loss=0.1564, simple_loss=0.2325, pruned_loss=0.04017, over 4990.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2224, pruned_loss=0.04119, over 972865.76 frames.], batch size: 28, lr: 3.77e-04
2022-05-05 07:40:09,160 INFO [train.py:715] (5/8) Epoch 5, batch 23250, loss[loss=0.1845, simple_loss=0.2521, pruned_loss=0.05847, over 4948.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04181, over 972732.87 frames.], batch size: 21, lr: 3.77e-04
2022-05-05 07:40:47,782 INFO [train.py:715] (5/8) Epoch 5, batch 23300, loss[loss=0.152, simple_loss=0.2143, pruned_loss=0.04491, over 4844.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04211, over 972607.59 frames.], batch size: 30, lr: 3.77e-04
2022-05-05 07:41:27,166 INFO [train.py:715] (5/8) Epoch 5, batch 23350, loss[loss=0.1533, simple_loss=0.225, pruned_loss=0.04079, over 4980.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2248, pruned_loss=0.04208, over 973393.75 frames.], batch size: 25, lr: 3.77e-04
2022-05-05 07:42:05,801 INFO [train.py:715] (5/8) Epoch 5, batch 23400, loss[loss=0.118, simple_loss=0.197, pruned_loss=0.01947, over 4861.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04152, over 972943.34 frames.], batch size: 12, lr: 3.77e-04
2022-05-05 07:42:44,252 INFO [train.py:715] (5/8) Epoch 5, batch 23450, loss[loss=0.1519, simple_loss=0.2249, pruned_loss=0.03945, over 4843.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2241, pruned_loss=0.04149, over 971862.68 frames.], batch size: 13, lr: 3.77e-04
2022-05-05 07:43:22,950 INFO [train.py:715] (5/8) Epoch 5, batch 23500, loss[loss=0.1486, simple_loss=0.2116, pruned_loss=0.04281, over 4845.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04138, over 971965.98 frames.], batch size: 30, lr: 3.77e-04
2022-05-05 07:44:02,010 INFO [train.py:715] (5/8) Epoch 5, batch 23550, loss[loss=0.1548, simple_loss=0.2135, pruned_loss=0.04807, over 4749.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04117, over 971965.73 frames.], batch size: 12, lr: 3.77e-04
2022-05-05 07:44:40,888 INFO [train.py:715] (5/8) Epoch 5, batch 23600, loss[loss=0.1541, simple_loss=0.2227, pruned_loss=0.04271, over 4972.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04128, over 972034.47 frames.], batch size: 14, lr: 3.77e-04
2022-05-05 07:45:19,394 INFO [train.py:715] (5/8) Epoch 5, batch 23650, loss[loss=0.1488, simple_loss=0.2081, pruned_loss=0.0448, over 4971.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.0409, over 972581.91 frames.], batch size: 15, lr: 3.77e-04
2022-05-05 07:45:58,897 INFO [train.py:715] (5/8) Epoch 5, batch 23700, loss[loss=0.1354, simple_loss=0.2, pruned_loss=0.03543, over 4757.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04128, over 972429.29 frames.], batch size: 19, lr: 3.77e-04
2022-05-05 07:46:37,473 INFO [train.py:715] (5/8) Epoch 5, batch 23750, loss[loss=0.1496, simple_loss=0.2235, pruned_loss=0.03783, over 4976.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2229, pruned_loss=0.04118, over 971997.90 frames.], batch size: 28, lr: 3.77e-04
2022-05-05 07:47:16,504 INFO [train.py:715] (5/8) Epoch 5, batch 23800, loss[loss=0.1235, simple_loss=0.2027, pruned_loss=0.02212, over 4962.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04075, over 972822.29 frames.], batch size: 24, lr: 3.77e-04
2022-05-05 07:47:55,208 INFO [train.py:715] (5/8) Epoch 5, batch 23850, loss[loss=0.1556, simple_loss=0.2385, pruned_loss=0.03633, over 4941.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.0408, over 973804.94 frames.], batch size: 18, lr: 3.77e-04
2022-05-05 07:48:34,416 INFO [train.py:715] (5/8) Epoch 5, batch 23900, loss[loss=0.1558, simple_loss=0.2226, pruned_loss=0.04449, over 4911.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04077, over 973666.89 frames.], batch size: 18, lr: 3.77e-04
2022-05-05 07:49:13,371 INFO [train.py:715] (5/8) Epoch 5, batch 23950, loss[loss=0.1353, simple_loss=0.2001, pruned_loss=0.03521, over 4828.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.0409, over 973150.84 frames.], batch size: 12, lr: 3.77e-04
2022-05-05 07:49:51,794 INFO [train.py:715] (5/8) Epoch 5, batch 24000, loss[loss=0.1726, simple_loss=0.2632, pruned_loss=0.04099, over 4973.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04088, over 972835.66 frames.], batch size: 40, lr: 3.77e-04
2022-05-05 07:49:51,795 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 07:50:02,183 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.11, simple_loss=0.1955, pruned_loss=0.0123, over 914524.00 frames.
2022-05-05 07:50:40,725 INFO [train.py:715] (5/8) Epoch 5, batch 24050, loss[loss=0.137, simple_loss=0.1995, pruned_loss=0.03732, over 4879.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04193, over 972995.73 frames.], batch size: 20, lr: 3.77e-04
2022-05-05 07:51:20,434 INFO [train.py:715] (5/8) Epoch 5, batch 24100, loss[loss=0.158, simple_loss=0.2268, pruned_loss=0.04465, over 4913.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2223, pruned_loss=0.04113, over 973304.10 frames.], batch size: 19, lr: 3.77e-04
2022-05-05 07:51:59,182 INFO [train.py:715] (5/8) Epoch 5, batch 24150, loss[loss=0.1334, simple_loss=0.2123, pruned_loss=0.0273, over 4809.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2213, pruned_loss=0.04019, over 973346.62 frames.], batch size: 25, lr: 3.77e-04
2022-05-05 07:52:37,495 INFO [train.py:715] (5/8) Epoch 5, batch 24200, loss[loss=0.1647, simple_loss=0.2312, pruned_loss=0.04911, over 4858.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03972, over 972906.53 frames.], batch size: 20, lr: 3.77e-04
2022-05-05 07:53:16,810 INFO [train.py:715] (5/8) Epoch 5, batch 24250, loss[loss=0.2241, simple_loss=0.2914, pruned_loss=0.07835, over 4685.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.04002, over 971510.22 frames.], batch size: 15, lr: 3.76e-04
2022-05-05 07:53:55,921 INFO [train.py:715] (5/8) Epoch 5, batch 24300, loss[loss=0.1221, simple_loss=0.2086, pruned_loss=0.01774, over 4830.00 frames.], tot_loss[loss=0.15, simple_loss=0.2206, pruned_loss=0.0397, over 971575.09 frames.], batch size: 13, lr: 3.76e-04
2022-05-05 07:54:34,806 INFO [train.py:715] (5/8) Epoch 5, batch 24350, loss[loss=0.1784, simple_loss=0.2388, pruned_loss=0.05897, over 4862.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2205, pruned_loss=0.03993, over 971956.91 frames.], batch size: 32, lr: 3.76e-04
2022-05-05 07:55:13,056 INFO [train.py:715] (5/8) Epoch 5, batch 24400, loss[loss=0.1483, simple_loss=0.2255, pruned_loss=0.03559, over 4856.00 frames.], tot_loss[loss=0.1509, simple_loss=0.221, pruned_loss=0.04041, over 971952.85 frames.], batch size: 20, lr: 3.76e-04
2022-05-05 07:55:52,740 INFO [train.py:715] (5/8) Epoch 5, batch 24450, loss[loss=0.1544, simple_loss=0.2273, pruned_loss=0.04073, over 4967.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04091, over 972280.97 frames.], batch size: 24, lr: 3.76e-04
2022-05-05 07:56:30,710 INFO [train.py:715] (5/8) Epoch 5, batch 24500, loss[loss=0.1521, simple_loss=0.2287, pruned_loss=0.03779, over 4922.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2226, pruned_loss=0.04102, over 972089.78 frames.], batch size: 29, lr: 3.76e-04
2022-05-05 07:57:09,367 INFO [train.py:715] (5/8) Epoch 5, batch 24550, loss[loss=0.1585, simple_loss=0.2341, pruned_loss=0.04144, over 4889.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04134, over 972341.55 frames.], batch size: 19, lr: 3.76e-04
2022-05-05 07:57:48,727 INFO [train.py:715] (5/8) Epoch 5, batch 24600, loss[loss=0.1757, simple_loss=0.2527, pruned_loss=0.04929, over 4752.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.04138, over 971775.90 frames.], batch size: 16, lr: 3.76e-04
2022-05-05 07:58:27,791 INFO [train.py:715] (5/8) Epoch 5, batch 24650, loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03508, over 4958.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04082, over 972425.44 frames.], batch size: 24, lr: 3.76e-04
2022-05-05 07:59:06,982 INFO [train.py:715] (5/8) Epoch 5, batch 24700, loss[loss=0.1609, simple_loss=0.2323, pruned_loss=0.04476, over 4915.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.04147, over 972607.19 frames.], batch size: 17, lr: 3.76e-04
2022-05-05 07:59:45,116 INFO [train.py:715] (5/8) Epoch 5, batch 24750, loss[loss=0.1468, simple_loss=0.2132, pruned_loss=0.04017, over 4926.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04118, over 972323.28 frames.], batch size: 18, lr: 3.76e-04
2022-05-05 08:00:24,682 INFO [train.py:715] (5/8) Epoch 5, batch 24800, loss[loss=0.1344, simple_loss=0.2069, pruned_loss=0.03095, over 4846.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04055, over 972536.95 frames.], batch size: 32, lr: 3.76e-04
2022-05-05 08:01:03,132 INFO [train.py:715] (5/8) Epoch 5, batch 24850, loss[loss=0.1716, simple_loss=0.2349, pruned_loss=0.05415, over 4980.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2221, pruned_loss=0.0408, over 972529.87 frames.], batch size: 15, lr: 3.76e-04
2022-05-05 08:01:41,875 INFO [train.py:715] (5/8) Epoch 5, batch 24900, loss[loss=0.1938, simple_loss=0.2683, pruned_loss=0.05967, over 4902.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.04054, over 972498.45 frames.], batch size: 19, lr: 3.76e-04
2022-05-05 08:02:21,424 INFO [train.py:715] (5/8) Epoch 5, batch 24950, loss[loss=0.1479, simple_loss=0.2181, pruned_loss=0.03891, over 4827.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04075, over 973310.20 frames.], batch size: 15, lr: 3.76e-04
2022-05-05 08:03:00,475 INFO [train.py:715] (5/8) Epoch 5, batch 25000, loss[loss=0.1437, simple_loss=0.2047, pruned_loss=0.04132, over 4828.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.04001, over 972402.88 frames.], batch size: 30, lr: 3.76e-04
2022-05-05 08:03:39,038 INFO [train.py:715] (5/8) Epoch 5, batch 25050, loss[loss=0.1413, simple_loss=0.2121, pruned_loss=0.03519, over 4870.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03957, over 971791.26 frames.], batch size: 20, lr: 3.76e-04
2022-05-05 08:04:17,283 INFO [train.py:715] (5/8) Epoch 5, batch 25100, loss[loss=0.1155, simple_loss=0.1878, pruned_loss=0.02154, over 4932.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04036, over 971993.93 frames.], batch size: 18, lr: 3.76e-04
2022-05-05 08:04:57,542 INFO [train.py:715] (5/8) Epoch 5, batch 25150, loss[loss=0.1362, simple_loss=0.2117, pruned_loss=0.03031, over 4923.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04039, over 971834.68 frames.], batch size: 23, lr: 3.76e-04
2022-05-05 08:05:35,727 INFO [train.py:715] (5/8) Epoch 5, batch 25200, loss[loss=0.1431, simple_loss=0.2114, pruned_loss=0.03739, over 4799.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.0409, over 971596.80 frames.], batch size: 21, lr: 3.76e-04
2022-05-05 08:06:14,577 INFO [train.py:715] (5/8) Epoch 5, batch 25250, loss[loss=0.1726, simple_loss=0.2329, pruned_loss=0.0561, over 4854.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04064, over 971163.20 frames.], batch size: 30, lr: 3.76e-04
2022-05-05 08:06:53,403 INFO [train.py:715] (5/8) Epoch 5, batch 25300, loss[loss=0.2291, simple_loss=0.29, pruned_loss=0.08407, over 4784.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2231, pruned_loss=0.04094, over 971862.20 frames.], batch size: 14, lr: 3.75e-04
2022-05-05 08:07:31,747 INFO [train.py:715] (5/8) Epoch 5, batch 25350, loss[loss=0.137, simple_loss=0.2061, pruned_loss=0.03394, over 4769.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04091, over 971702.53 frames.], batch size: 12, lr: 3.75e-04
2022-05-05 08:08:10,248 INFO [train.py:715] (5/8) Epoch 5, batch 25400, loss[loss=0.1295, simple_loss=0.2043, pruned_loss=0.02734, over 4748.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04063, over 971977.78 frames.], batch size: 16, lr: 3.75e-04
2022-05-05 08:08:49,164 INFO [train.py:715] (5/8) Epoch 5, batch 25450, loss[loss=0.1298, simple_loss=0.2138, pruned_loss=0.02283, over 4825.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04086, over 972063.90 frames.], batch size: 27, lr: 3.75e-04
2022-05-05 08:09:28,361 INFO [train.py:715] (5/8) Epoch 5, batch 25500, loss[loss=0.1279, simple_loss=0.1906, pruned_loss=0.03259, over 4845.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.0414, over 972143.15 frames.], batch size: 15, lr: 3.75e-04
2022-05-05 08:10:07,142 INFO [train.py:715] (5/8) Epoch 5, batch 25550, loss[loss=0.1436, simple_loss=0.2034, pruned_loss=0.04187, over 4863.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2237, pruned_loss=0.04175, over 972591.61 frames.], batch size: 13, lr: 3.75e-04
2022-05-05 08:10:45,634 INFO [train.py:715] (5/8) Epoch 5, batch 25600, loss[loss=0.1316, simple_loss=0.2013, pruned_loss=0.03099, over 4974.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04124, over 972318.63 frames.], batch size: 28, lr: 3.75e-04
2022-05-05 08:11:24,705 INFO [train.py:715] (5/8) Epoch 5, batch 25650, loss[loss=0.1463, simple_loss=0.2119, pruned_loss=0.04033, over 4931.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04078, over 972538.96 frames.], batch size: 29, lr: 3.75e-04
2022-05-05 08:12:03,093 INFO [train.py:715] (5/8) Epoch 5, batch 25700, loss[loss=0.1745, simple_loss=0.2363, pruned_loss=0.05637, over 4849.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04126, over 972100.18 frames.], batch size: 30, lr: 3.75e-04
2022-05-05 08:12:41,263 INFO [train.py:715] (5/8) Epoch 5, batch 25750, loss[loss=0.1318, simple_loss=0.2028, pruned_loss=0.03037, over 4805.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2247, pruned_loss=0.04214, over 971423.76 frames.], batch size: 21, lr: 3.75e-04
2022-05-05 08:13:20,737 INFO [train.py:715] (5/8) Epoch 5, batch 25800, loss[loss=0.142, simple_loss=0.2117, pruned_loss=0.03612, over 4856.00 frames.], tot_loss[loss=0.1536, simple_loss=0.224, pruned_loss=0.04159, over 971059.84 frames.], batch size: 30, lr: 3.75e-04
2022-05-05 08:13:59,832 INFO [train.py:715] (5/8) Epoch 5, batch 25850, loss[loss=0.1519, simple_loss=0.2284, pruned_loss=0.03767, over 4884.00 frames.], tot_loss[loss=0.152, simple_loss=0.2226, pruned_loss=0.04074, over 971461.88 frames.], batch size: 22, lr: 3.75e-04
2022-05-05 08:14:38,589 INFO [train.py:715] (5/8) Epoch 5, batch 25900, loss[loss=0.1602, simple_loss=0.2218, pruned_loss=0.04926, over 4976.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04093, over 972487.54 frames.], batch size: 31, lr: 3.75e-04
2022-05-05 08:15:17,124 INFO [train.py:715] (5/8) Epoch 5, batch 25950, loss[loss=0.1584, simple_loss=0.2245, pruned_loss=0.04611, over 4903.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.041, over 972603.61 frames.], batch size: 19, lr: 3.75e-04
2022-05-05 08:15:58,602 INFO [train.py:715] (5/8) Epoch 5, batch 26000, loss[loss=0.1558, simple_loss=0.2229, pruned_loss=0.04435, over 4912.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2231, pruned_loss=0.04113, over 971884.89 frames.], batch size: 18, lr: 3.75e-04
2022-05-05 08:16:37,292 INFO [train.py:715] (5/8) Epoch 5, batch 26050, loss[loss=0.1341, simple_loss=0.2138, pruned_loss=0.0272, over 4768.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04055, over 971368.96 frames.], batch size: 17, lr: 3.75e-04
2022-05-05 08:17:15,759 INFO [train.py:715] (5/8) Epoch 5, batch 26100, loss[loss=0.1539, simple_loss=0.2273, pruned_loss=0.04028, over 4920.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04034, over 972105.31 frames.], batch size: 18, lr: 3.75e-04
2022-05-05 08:17:54,716 INFO [train.py:715] (5/8) Epoch 5, batch 26150, loss[loss=0.12, simple_loss=0.1885, pruned_loss=0.02575, over 4985.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04068, over 972144.53 frames.], batch size: 14, lr: 3.75e-04
2022-05-05 08:18:33,047 INFO [train.py:715] (5/8) Epoch 5, batch 26200, loss[loss=0.1675, simple_loss=0.2258, pruned_loss=0.05463, over 4770.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2215, pruned_loss=0.04059, over 972160.13 frames.], batch size: 19, lr: 3.75e-04
2022-05-05 08:19:12,106 INFO [train.py:715] (5/8) Epoch 5, batch 26250, loss[loss=0.1513, simple_loss=0.2192, pruned_loss=0.04168, over 4802.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04052, over 971829.04 frames.], batch size: 21, lr: 3.75e-04
2022-05-05 08:19:51,345 INFO [train.py:715] (5/8) Epoch 5, batch 26300, loss[loss=0.1709, simple_loss=0.251, pruned_loss=0.0454, over 4965.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2215, pruned_loss=0.0404, over 971435.15 frames.], batch size: 24, lr: 3.75e-04
2022-05-05 08:20:30,625 INFO [train.py:715] (5/8) Epoch 5, batch 26350, loss[loss=0.1669, simple_loss=0.2345, pruned_loss=0.04968, over 4848.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04102, over 971944.05 frames.], batch size: 13, lr: 3.74e-04
2022-05-05 08:21:09,423 INFO [train.py:715] (5/8) Epoch 5, batch 26400, loss[loss=0.1551, simple_loss=0.2275, pruned_loss=0.04137, over 4779.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2231, pruned_loss=0.04116, over 972545.40 frames.], batch size: 18, lr: 3.74e-04
2022-05-05 08:21:48,034 INFO [train.py:715] (5/8) Epoch 5, batch 26450, loss[loss=0.1281, simple_loss=0.2042, pruned_loss=0.02595, over 4920.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2228, pruned_loss=0.04085, over 972317.45 frames.], batch size: 18, lr: 3.74e-04
2022-05-05 08:22:26,955 INFO [train.py:715] (5/8) Epoch 5, batch 26500, loss[loss=0.1265, simple_loss=0.2102, pruned_loss=0.02139, over 4928.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04033, over 972564.82 frames.], batch size: 23, lr: 3.74e-04
2022-05-05 08:23:06,041 INFO [train.py:715] (5/8) Epoch 5, batch 26550, loss[loss=0.1706, simple_loss=0.2382, pruned_loss=0.05153, over 4827.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04038, over 972717.59 frames.], batch size: 15, lr: 3.74e-04
2022-05-05 08:23:44,739 INFO [train.py:715] (5/8) Epoch 5, batch 26600, loss[loss=0.1231, simple_loss=0.195, pruned_loss=0.02558, over 4929.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04008, over 971821.98 frames.], batch size: 23, lr: 3.74e-04
2022-05-05 08:24:24,182 INFO [train.py:715] (5/8) Epoch 5, batch 26650, loss[loss=0.1295, simple_loss=0.1988, pruned_loss=0.03007, over 4765.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03994, over 971326.63 frames.], batch size: 17, lr: 3.74e-04
2022-05-05 08:25:02,984 INFO [train.py:715] (5/8) Epoch 5, batch 26700, loss[loss=0.1493, simple_loss=0.2032, pruned_loss=0.04774, over 4975.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04048, over 972702.47 frames.], batch size: 15, lr: 3.74e-04
2022-05-05 08:25:41,810 INFO [train.py:715] (5/8) Epoch 5, batch 26750, loss[loss=0.1355, simple_loss=0.2021, pruned_loss=0.03444, over 4956.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.0402, over 973650.97 frames.], batch size: 21, lr: 3.74e-04
2022-05-05 08:26:20,200 INFO [train.py:715] (5/8) Epoch 5, batch 26800, loss[loss=0.1315, simple_loss=0.2074, pruned_loss=0.02774, over 4938.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2221, pruned_loss=0.04053, over 972948.59 frames.], batch size: 29, lr: 3.74e-04
2022-05-05 08:26:59,360 INFO [train.py:715] (5/8) Epoch 5, batch 26850, loss[loss=0.1659, simple_loss=0.2356, pruned_loss=0.04806, over 4870.00 frames.], tot_loss[loss=0.152, simple_loss=0.2226, pruned_loss=0.04074, over 973597.64 frames.], batch size: 20, lr: 3.74e-04
2022-05-05 08:27:38,337 INFO [train.py:715] (5/8) Epoch 5, batch 26900, loss[loss=0.1542, simple_loss=0.2216, pruned_loss=0.04346, over 4920.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2215, pruned_loss=0.04038, over 973776.16 frames.], batch size: 23, lr: 3.74e-04
2022-05-05 08:28:17,271 INFO [train.py:715] (5/8) Epoch 5, batch 26950, loss[loss=0.1442, simple_loss=0.2177, pruned_loss=0.03532, over 4965.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.04003, over 973825.61 frames.], batch size: 21, lr: 3.74e-04
2022-05-05 08:28:55,973 INFO [train.py:715] (5/8) Epoch 5, batch 27000, loss[loss=0.1643, simple_loss=0.2294, pruned_loss=0.04962, over 4834.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2211, pruned_loss=0.04014, over 973862.98 frames.], batch size: 26, lr: 3.74e-04
2022-05-05 08:28:55,974 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 08:29:05,775 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1098, simple_loss=0.195, pruned_loss=0.01232, over 914524.00 frames.
2022-05-05 08:29:45,276 INFO [train.py:715] (5/8) Epoch 5, batch 27050, loss[loss=0.1599, simple_loss=0.2279, pruned_loss=0.04599, over 4791.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2206, pruned_loss=0.04029, over 972938.95 frames.], batch size: 18, lr: 3.74e-04
2022-05-05 08:30:24,754 INFO [train.py:715] (5/8) Epoch 5, batch 27100, loss[loss=0.1746, simple_loss=0.2356, pruned_loss=0.05677, over 4905.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2206, pruned_loss=0.04032, over 972760.58 frames.], batch size: 17, lr: 3.74e-04
2022-05-05 08:31:04,148 INFO [train.py:715] (5/8) Epoch 5, batch 27150, loss[loss=0.1185, simple_loss=0.1914, pruned_loss=0.02283, over 4692.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2204, pruned_loss=0.04003, over 972647.89 frames.], batch size: 15, lr: 3.74e-04
2022-05-05 08:31:42,962 INFO [train.py:715] (5/8) Epoch 5, batch 27200, loss[loss=0.2134, simple_loss=0.3001, pruned_loss=0.06336, over 4701.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2206, pruned_loss=0.03984, over 972054.45 frames.], batch size: 15, lr: 3.74e-04
2022-05-05 08:32:22,584 INFO [train.py:715] (5/8) Epoch 5, batch 27250, loss[loss=0.126, simple_loss=0.2031, pruned_loss=0.02449, over 4804.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03927, over 972346.52 frames.], batch size: 21, lr: 3.74e-04
2022-05-05 08:33:01,563 INFO [train.py:715] (5/8) Epoch 5, batch 27300, loss[loss=0.1594, simple_loss=0.2198, pruned_loss=0.0495, over 4808.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04038, over 971473.10 frames.], batch size: 13, lr: 3.74e-04
2022-05-05 08:33:40,118 INFO [train.py:715] (5/8) Epoch 5, batch 27350, loss[loss=0.1312, simple_loss=0.1979, pruned_loss=0.03224, over 4948.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03992, over 972035.94 frames.], batch size: 21, lr: 3.74e-04
2022-05-05 08:34:18,991 INFO [train.py:715] (5/8) Epoch 5, batch 27400, loss[loss=0.15, simple_loss=0.2241, pruned_loss=0.03801, over 4776.00 frames.], tot_loss[loss=0.15, simple_loss=0.2207, pruned_loss=0.03967, over 970881.86 frames.], batch size: 17, lr: 3.74e-04
2022-05-05 08:34:58,264 INFO [train.py:715] (5/8) Epoch 5, batch 27450, loss[loss=0.1707, simple_loss=0.2319, pruned_loss=0.05473, over 4875.00 frames.], tot_loss[loss=0.15, simple_loss=0.2207, pruned_loss=0.03967, over 971626.34 frames.], batch size: 16, lr: 3.73e-04
2022-05-05 08:35:38,045 INFO [train.py:715] (5/8) Epoch 5, batch 27500, loss[loss=0.1283, simple_loss=0.2038, pruned_loss=0.02642, over 4839.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.04004, over 971272.08 frames.], batch size: 13, lr: 3.73e-04
2022-05-05 08:36:16,526 INFO [train.py:715] (5/8) Epoch 5, batch 27550, loss[loss=0.1573, simple_loss=0.2359, pruned_loss=0.03937, over 4979.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04022, over 972352.97 frames.], batch size: 24, lr: 3.73e-04
2022-05-05 08:36:55,897 INFO [train.py:715] (5/8) Epoch 5, batch 27600, loss[loss=0.1439, simple_loss=0.2133, pruned_loss=0.03721, over 4763.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03981, over 973174.11 frames.], batch size: 19, lr: 3.73e-04
2022-05-05 08:37:34,976 INFO [train.py:715] (5/8) Epoch 5, batch 27650, loss[loss=0.1944, simple_loss=0.2632, pruned_loss=0.06283, over 4921.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.0396, over 973017.79 frames.], batch size: 18, lr: 3.73e-04
2022-05-05 08:38:13,249 INFO [train.py:715] (5/8) Epoch 5, batch 27700, loss[loss=0.1426, simple_loss=0.2211, pruned_loss=0.03203, over 4906.00 frames.], tot_loss[loss=0.1511, simple_loss=0.222, pruned_loss=0.04012, over 973087.14 frames.], batch size: 19, lr: 3.73e-04
2022-05-05 08:38:52,829 INFO [train.py:715] (5/8) Epoch 5, batch 27750, loss[loss=0.2218, simple_loss=0.2848, pruned_loss=0.07943, over 4941.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04043, over 973636.21 frames.], batch size: 18, lr: 3.73e-04
2022-05-05 08:39:32,591 INFO [train.py:715] (5/8) Epoch 5, batch 27800, loss[loss=0.1478, simple_loss=0.2236, pruned_loss=0.03595, over 4781.00 frames.], tot_loss[loss=0.151, simple_loss=0.2216, pruned_loss=0.04021, over 973008.02 frames.], batch size: 14, lr: 3.73e-04
2022-05-05 08:40:11,944 INFO [train.py:715] (5/8) Epoch 5, batch 27850, loss[loss=0.1345, simple_loss=0.2043, pruned_loss=0.03237, over 4935.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03969, over 971495.72 frames.], batch size: 23, lr: 3.73e-04
2022-05-05 08:40:50,653 INFO [train.py:715] (5/8) Epoch 5, batch 27900, loss[loss=0.1444, simple_loss=0.2292, pruned_loss=0.02976, over 4773.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03968, over 970669.39 frames.], batch size: 17, lr: 3.73e-04
2022-05-05 08:41:29,599 INFO [train.py:715] (5/8) Epoch 5, batch 27950, loss[loss=0.1592, simple_loss=0.2253, pruned_loss=0.04653, over 4888.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2207, pruned_loss=0.03948, over 971689.85 frames.], batch size: 19, lr: 3.73e-04
2022-05-05 08:42:09,041 INFO [train.py:715] (5/8) Epoch 5, batch 28000, loss[loss=0.1489, simple_loss=0.2131, pruned_loss=0.04231, over 4763.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03978, over 972141.36 frames.], batch size: 12, lr: 3.73e-04
2022-05-05 08:42:47,128 INFO [train.py:715] (5/8) Epoch 5, batch 28050, loss[loss=0.1424, simple_loss=0.204, pruned_loss=0.04034, over 4827.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.04124, over 972356.38 frames.], batch size: 12, lr: 3.73e-04
2022-05-05 08:43:25,855 INFO [train.py:715] (5/8) Epoch 5, batch 28100, loss[loss=0.149, simple_loss=0.2213, pruned_loss=0.03836, over 4880.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2226, pruned_loss=0.04144, over 971834.40 frames.], batch size: 22, lr: 3.73e-04
2022-05-05 08:44:04,997 INFO [train.py:715] (5/8) Epoch 5, batch 28150, loss[loss=0.1669, simple_loss=0.2453, pruned_loss=0.04427, over 4929.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.0411, over 972466.16 frames.], batch size: 29, lr: 3.73e-04
2022-05-05 08:44:43,939 INFO [train.py:715] (5/8) Epoch 5, batch 28200, loss[loss=0.1355, simple_loss=0.2188, pruned_loss=0.02611, over 4963.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.0402, over 972798.72 frames.], batch size: 15, lr: 3.73e-04
2022-05-05 08:45:22,623 INFO [train.py:715] (5/8) Epoch 5, batch 28250, loss[loss=0.1375, simple_loss=0.2203, pruned_loss=0.02733, over 4938.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04067, over 972859.01 frames.], batch size: 21, lr: 3.73e-04
2022-05-05 08:46:01,487 INFO [train.py:715] (5/8) Epoch 5, batch 28300, loss[loss=0.1229, simple_loss=0.1992, pruned_loss=0.02335, over 4952.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04103, over 972722.97 frames.], batch size: 14, lr: 3.73e-04
2022-05-05 08:46:39,903 INFO [train.py:715] (5/8) Epoch 5, batch 28350, loss[loss=0.1361, simple_loss=0.2015, pruned_loss=0.03531, over 4926.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2232, pruned_loss=0.04152, over 972849.67 frames.], batch size: 23, lr: 3.73e-04
2022-05-05 08:47:18,554 INFO [train.py:715] (5/8) Epoch 5, batch 28400, loss[loss=0.157, simple_loss=0.2356, pruned_loss=0.03921, over 4919.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.04143, over 972295.08 frames.], batch size: 17, lr: 3.73e-04
2022-05-05 08:47:57,678 INFO [train.py:715] (5/8) Epoch 5, batch 28450, loss[loss=0.1583, simple_loss=0.2321, pruned_loss=0.04218, over 4872.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04154, over 971141.08 frames.], batch size: 32, lr: 3.73e-04
2022-05-05 08:48:36,727 INFO [train.py:715] (5/8) Epoch 5, batch 28500, loss[loss=0.1506, simple_loss=0.2226, pruned_loss=0.03933, over 4779.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.04134, over 971428.85 frames.], batch size: 17, lr: 3.72e-04
2022-05-05 08:49:15,938 INFO [train.py:715] (5/8) Epoch 5, batch 28550, loss[loss=0.1666, simple_loss=0.2288, pruned_loss=0.0522, over 4757.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2232, pruned_loss=0.04151, over 970768.50 frames.], batch size: 12, lr: 3.72e-04
2022-05-05 08:49:54,627 INFO [train.py:715] (5/8) Epoch 5, batch 28600, loss[loss=0.1519, simple_loss=0.223, pruned_loss=0.04042, over 4915.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04115, over 972642.74 frames.], batch size: 21, lr: 3.72e-04
2022-05-05 08:50:34,059 INFO [train.py:715] (5/8) Epoch 5, batch 28650, loss[loss=0.155, simple_loss=0.2245, pruned_loss=0.04273, over 4742.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2233, pruned_loss=0.04107, over 972524.51 frames.], batch size: 16, lr: 3.72e-04
2022-05-05 08:51:12,501 INFO [train.py:715] (5/8) Epoch 5, batch 28700, loss[loss=0.1541, simple_loss=0.2274, pruned_loss=0.04043, over 4818.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04084, over 973464.32 frames.], batch size: 27, lr: 3.72e-04
2022-05-05 08:51:51,352 INFO [train.py:715] (5/8) Epoch 5, batch 28750, loss[loss=0.1672, simple_loss=0.2381, pruned_loss=0.04815, over 4831.00 frames.], tot_loss[loss=0.152, simple_loss=0.2227, pruned_loss=0.04071, over 972387.49 frames.], batch size: 26, lr: 3.72e-04
2022-05-05 08:52:30,119 INFO [train.py:715] (5/8) Epoch 5, batch 28800, loss[loss=0.1568, simple_loss=0.2177, pruned_loss=0.04797, over 4960.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04046, over 973017.52 frames.], batch size: 35, lr: 3.72e-04
2022-05-05 08:53:09,040 INFO [train.py:715] (5/8) Epoch 5, batch 28850, loss[loss=0.1365, simple_loss=0.2151, pruned_loss=0.02893, over 4877.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.03983, over 972846.37 frames.], batch size: 16, lr: 3.72e-04
2022-05-05 08:53:47,816 INFO [train.py:715] (5/8) Epoch 5, batch 28900, loss[loss=0.1611, simple_loss=0.2204, pruned_loss=0.0509, over 4929.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04009, over 971646.30 frames.], batch size: 35, lr: 3.72e-04
2022-05-05 08:54:26,496 INFO [train.py:715] (5/8) Epoch 5, batch 28950, loss[loss=0.1285, simple_loss=0.1964, pruned_loss=0.03025, over 4856.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04037, over 972463.86 frames.], batch size: 20, lr: 3.72e-04
2022-05-05 08:55:05,610 INFO [train.py:715] (5/8) Epoch 5, batch 29000, loss[loss=0.1773, simple_loss=0.2423, pruned_loss=0.05616, over 4791.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04074, over 972876.31 frames.], batch size: 17, lr: 3.72e-04
2022-05-05 08:55:43,859 INFO [train.py:715] (5/8) Epoch 5, batch 29050, loss[loss=0.1396, simple_loss=0.2165, pruned_loss=0.03136, over 4959.00 frames.], tot_loss[loss=0.151, simple_loss=0.2214, pruned_loss=0.04028, over 973802.73 frames.], batch size: 14, lr: 3.72e-04
2022-05-05 08:56:22,923 INFO [train.py:715] (5/8) Epoch 5, batch 29100, loss[loss=0.13, simple_loss=0.2054, pruned_loss=0.02736, over 4813.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2211, pruned_loss=0.04013, over 973920.53 frames.], batch size: 25, lr: 3.72e-04
2022-05-05 08:57:01,739 INFO [train.py:715] (5/8) Epoch 5, batch 29150, loss[loss=0.1532, simple_loss=0.2191, pruned_loss=0.0437, over 4827.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2211, pruned_loss=0.04016, over 973423.80 frames.], batch size: 15, lr: 3.72e-04
2022-05-05 08:57:40,488 INFO [train.py:715] (5/8) Epoch 5, batch 29200, loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03228, over 4972.00 frames.], tot_loss[loss=0.151, simple_loss=0.2211, pruned_loss=0.0405, over 972297.67 frames.], batch size: 15, lr: 3.72e-04
2022-05-05 08:58:19,233 INFO [train.py:715] (5/8) Epoch 5, batch 29250, loss[loss=0.1559, simple_loss=0.2359, pruned_loss=0.03795, over 4874.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03988, over 972067.38 frames.], batch size: 16, lr: 3.72e-04
2022-05-05 08:58:57,799 INFO [train.py:715] (5/8) Epoch 5, batch 29300, loss[loss=0.1408, simple_loss=0.2117, pruned_loss=0.03494, over 4932.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2205, pruned_loss=0.03968, over 972871.70 frames.], batch size: 18, lr: 3.72e-04
2022-05-05 08:59:37,057 INFO [train.py:715] (5/8) Epoch 5, batch 29350, loss[loss=0.1842, simple_loss=0.256, pruned_loss=0.05614, over 4839.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.03948, over 972951.88 frames.], batch size: 15, lr: 3.72e-04
2022-05-05 09:00:15,739 INFO [train.py:715] (5/8) Epoch 5, batch 29400, loss[loss=0.1897, simple_loss=0.2519, pruned_loss=0.06377, over 4860.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2214, pruned_loss=0.03995, over 972505.48 frames.], batch size: 20, lr: 3.72e-04
2022-05-05 09:00:54,489 INFO [train.py:715] (5/8) Epoch 5, batch 29450, loss[loss=0.122, simple_loss=0.1872, pruned_loss=0.02841, over 4846.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2221, pruned_loss=0.04057, over 971757.18 frames.], batch size: 30, lr: 3.72e-04
2022-05-05 09:01:34,120 INFO [train.py:715] (5/8) Epoch 5, batch 29500, loss[loss=0.1549, simple_loss=0.2213, pruned_loss=0.0442, over 4847.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2226, pruned_loss=0.04104, over 972418.61 frames.], batch size: 30, lr: 3.72e-04
2022-05-05 09:02:13,203 INFO [train.py:715] (5/8) Epoch 5, batch 29550, loss[loss=0.1532, simple_loss=0.237, pruned_loss=0.03474, over 4766.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2229, pruned_loss=0.04109, over 972524.46 frames.], batch size: 19, lr: 3.72e-04
2022-05-05 09:02:52,391 INFO [train.py:715] (5/8) Epoch 5, batch 29600, loss[loss=0.1449, simple_loss=0.2095, pruned_loss=0.04016, over 4927.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04109, over 972171.04 frames.], batch size: 18, lr: 3.71e-04
2022-05-05 09:03:31,059 INFO [train.py:715] (5/8) Epoch 5, batch 29650, loss[loss=0.125, simple_loss=0.2029, pruned_loss=0.02356, over 4817.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.04146, over 972498.48 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:04:09,888 INFO [train.py:715] (5/8) Epoch 5, batch 29700, loss[loss=0.1477, simple_loss=0.2315, pruned_loss=0.03192, over 4982.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2225, pruned_loss=0.04092, over 972792.07 frames.], batch size: 28, lr: 3.71e-04
2022-05-05 09:04:48,812 INFO [train.py:715] (5/8) Epoch 5, batch 29750, loss[loss=0.1627, simple_loss=0.2319, pruned_loss=0.04674, over 4946.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04098, over 972796.71 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:05:27,383 INFO [train.py:715] (5/8) Epoch 5, batch 29800, loss[loss=0.1162, simple_loss=0.185, pruned_loss=0.02371, over 4892.00 frames.], tot_loss[loss=0.152, simple_loss=0.2227, pruned_loss=0.04066, over 971994.96 frames.], batch size: 22, lr: 3.71e-04
2022-05-05 09:06:05,624 INFO [train.py:715] (5/8) Epoch 5, batch 29850, loss[loss=0.1416, simple_loss=0.2097, pruned_loss=0.03679, over 4816.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04105, over 972309.99 frames.], batch size: 27, lr: 3.71e-04
2022-05-05 09:06:44,671 INFO [train.py:715] (5/8) Epoch 5, batch 29900, loss[loss=0.1398, simple_loss=0.215, pruned_loss=0.03233, over 4807.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2227, pruned_loss=0.04045, over 972691.54 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:07:24,015 INFO [train.py:715] (5/8) Epoch 5, batch 29950, loss[loss=0.149, simple_loss=0.2211, pruned_loss=0.03848, over 4765.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2233, pruned_loss=0.04055, over 972690.70 frames.], batch size: 18, lr: 3.71e-04
2022-05-05 09:08:02,568 INFO [train.py:715] (5/8) Epoch 5, batch 30000, loss[loss=0.1431, simple_loss=0.2103, pruned_loss=0.03794, over 4748.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04043, over 972537.37 frames.], batch size: 19, lr: 3.71e-04
2022-05-05 09:08:02,569 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 09:08:12,296 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.11, simple_loss=0.1953, pruned_loss=0.01241, over 914524.00 frames.
2022-05-05 09:08:51,329 INFO [train.py:715] (5/8) Epoch 5, batch 30050, loss[loss=0.1407, simple_loss=0.212, pruned_loss=0.03475, over 4921.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04043, over 973437.33 frames.], batch size: 29, lr: 3.71e-04
2022-05-05 09:09:31,491 INFO [train.py:715] (5/8) Epoch 5, batch 30100, loss[loss=0.1659, simple_loss=0.2382, pruned_loss=0.04681, over 4694.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.04031, over 973568.01 frames.], batch size: 15, lr: 3.71e-04
2022-05-05 09:10:10,292 INFO [train.py:715] (5/8) Epoch 5, batch 30150, loss[loss=0.1686, simple_loss=0.2267, pruned_loss=0.05523, over 4736.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2215, pruned_loss=0.04064, over 972336.05 frames.], batch size: 16, lr: 3.71e-04
2022-05-05 09:10:48,820 INFO [train.py:715] (5/8) Epoch 5, batch 30200, loss[loss=0.1553, simple_loss=0.228, pruned_loss=0.04132, over 4986.00 frames.], tot_loss[loss=0.151, simple_loss=0.2212, pruned_loss=0.04045, over 973241.64 frames.], batch size: 35, lr: 3.71e-04
2022-05-05 09:11:27,804 INFO [train.py:715] (5/8) Epoch 5, batch 30250, loss[loss=0.1681, simple_loss=0.2208, pruned_loss=0.05768, over 4970.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2226, pruned_loss=0.04103, over 973419.56 frames.], batch size: 14, lr: 3.71e-04
2022-05-05 09:12:06,780 INFO [train.py:715] (5/8) Epoch 5, batch 30300, loss[loss=0.1649, simple_loss=0.2345, pruned_loss=0.04765, over 4960.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2228, pruned_loss=0.04129, over 973805.16 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:12:45,784 INFO [train.py:715] (5/8) Epoch 5, batch 30350, loss[loss=0.1615, simple_loss=0.2345, pruned_loss=0.04421, over 4697.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2218, pruned_loss=0.04091, over 973771.28 frames.], batch size: 15, lr: 3.71e-04
2022-05-05 09:13:24,286 INFO [train.py:715] (5/8) Epoch 5, batch 30400, loss[loss=0.1281, simple_loss=0.2146, pruned_loss=0.02082, over 4796.00 frames.], tot_loss[loss=0.1519, simple_loss=0.222, pruned_loss=0.04088, over 973478.44 frames.], batch size: 24, lr: 3.71e-04
2022-05-05 09:14:03,373 INFO [train.py:715] (5/8) Epoch 5, batch 30450, loss[loss=0.164, simple_loss=0.2281, pruned_loss=0.04995, over 4926.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2221, pruned_loss=0.04074, over 972948.13 frames.], batch size: 14, lr: 3.71e-04
2022-05-05 09:14:42,246 INFO [train.py:715] (5/8) Epoch 5, batch 30500, loss[loss=0.1215, simple_loss=0.2047, pruned_loss=0.01912, over 4973.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04051, over 974151.59 frames.], batch size: 15, lr: 3.71e-04
2022-05-05 09:15:20,922 INFO [train.py:715] (5/8) Epoch 5, batch 30550, loss[loss=0.1603, simple_loss=0.2266, pruned_loss=0.04705, over 4878.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.04015, over 973966.24 frames.], batch size: 20, lr: 3.71e-04
2022-05-05 09:15:58,927 INFO [train.py:715] (5/8) Epoch 5, batch 30600, loss[loss=0.1955, simple_loss=0.2565, pruned_loss=0.06732, over 4955.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03997, over 975209.22 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:16:37,777 INFO [train.py:715] (5/8) Epoch 5, batch 30650, loss[loss=0.1485, simple_loss=0.2205, pruned_loss=0.03822, over 4943.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04038, over 973819.50 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:17:16,915 INFO [train.py:715] (5/8) Epoch 5, batch 30700, loss[loss=0.122, simple_loss=0.1944, pruned_loss=0.0248, over 4775.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.0403, over 973492.13 frames.], batch size: 12, lr: 3.70e-04
2022-05-05 09:17:55,174 INFO [train.py:715] (5/8) Epoch 5, batch 30750, loss[loss=0.1349, simple_loss=0.2004, pruned_loss=0.03471, over 4770.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2212, pruned_loss=0.0403, over 973037.85 frames.], batch size: 12, lr: 3.70e-04
2022-05-05 09:18:33,969 INFO [train.py:715] (5/8) Epoch 5, batch 30800, loss[loss=0.1236, simple_loss=0.2028, pruned_loss=0.02222, over 4940.00 frames.], tot_loss[loss=0.151, simple_loss=0.2213, pruned_loss=0.04031, over 972584.48 frames.], batch size: 23, lr: 3.70e-04
2022-05-05 09:19:12,985 INFO [train.py:715] (5/8) Epoch 5, batch 30850, loss[loss=0.1397, simple_loss=0.2189, pruned_loss=0.03024, over 4988.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04025, over 972898.54 frames.], batch size: 25, lr: 3.70e-04
2022-05-05 09:19:51,002 INFO [train.py:715] (5/8) Epoch 5, batch 30900, loss[loss=0.1412, simple_loss=0.2122, pruned_loss=0.03511, over 4856.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04039, over 973070.72 frames.], batch size: 13, lr: 3.70e-04
2022-05-05 09:20:29,873 INFO [train.py:715] (5/8) Epoch 5, batch 30950, loss[loss=0.148, simple_loss=0.2175, pruned_loss=0.0393, over 4889.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04038, over 973489.95 frames.], batch size: 19, lr: 3.70e-04
2022-05-05 09:21:09,517 INFO [train.py:715] (5/8) Epoch 5, batch 31000, loss[loss=0.1659, simple_loss=0.24, pruned_loss=0.04594, over 4891.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.04, over 972993.25 frames.], batch size: 17, lr: 3.70e-04
2022-05-05 09:21:48,975 INFO [train.py:715] (5/8) Epoch 5, batch 31050, loss[loss=0.1337, simple_loss=0.2035, pruned_loss=0.03194, over 4859.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2216, pruned_loss=0.03973, over 972939.95 frames.], batch size: 16, lr: 3.70e-04
2022-05-05 09:22:27,592 INFO [train.py:715] (5/8) Epoch 5, batch 31100, loss[loss=0.1681, simple_loss=0.2373, pruned_loss=0.04951, over 4986.00 frames.], tot_loss[loss=0.151, simple_loss=0.2221, pruned_loss=0.03993, over 973542.49 frames.], batch size: 31, lr: 3.70e-04
2022-05-05 09:23:06,678 INFO [train.py:715] (5/8) Epoch 5, batch 31150, loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.0397, over 4976.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.04042, over 973811.02 frames.], batch size: 24, lr: 3.70e-04
2022-05-05 09:23:45,592 INFO [train.py:715] (5/8) Epoch 5, batch 31200, loss[loss=0.1793, simple_loss=0.2486, pruned_loss=0.05501, over 4754.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2216, pruned_loss=0.04024, over 973276.07 frames.], batch size: 19, lr: 3.70e-04
2022-05-05 09:24:24,056 INFO [train.py:715] (5/8) Epoch 5, batch 31250, loss[loss=0.1299, simple_loss=0.2072, pruned_loss=0.02625, over 4800.00 frames.], tot_loss[loss=0.152, simple_loss=0.2223, pruned_loss=0.04082, over 973077.30 frames.], batch size: 24, lr: 3.70e-04
2022-05-05 09:25:02,648 INFO [train.py:715] (5/8) Epoch 5, batch 31300, loss[loss=0.1466, simple_loss=0.2177, pruned_loss=0.0377, over 4989.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2212, pruned_loss=0.04063, over 972558.80 frames.], batch size: 25, lr: 3.70e-04
2022-05-05 09:25:41,536 INFO [train.py:715] (5/8) Epoch 5, batch 31350, loss[loss=0.1598, simple_loss=0.2241, pruned_loss=0.04772, over 4867.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2201, pruned_loss=0.04014, over 972027.57 frames.], batch size: 22, lr: 3.70e-04
2022-05-05 09:26:20,317 INFO [train.py:715] (5/8) Epoch 5, batch 31400, loss[loss=0.1465, simple_loss=0.2192, pruned_loss=0.03689, over 4813.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2201, pruned_loss=0.03985, over 972708.90 frames.], batch size: 27, lr: 3.70e-04
2022-05-05 09:26:59,039 INFO [train.py:715] (5/8) Epoch 5, batch 31450, loss[loss=0.174, simple_loss=0.2455, pruned_loss=0.05122, over 4770.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2205, pruned_loss=0.03983, over 972493.93 frames.], batch size: 14, lr: 3.70e-04
2022-05-05 09:27:37,865 INFO [train.py:715] (5/8) Epoch 5, batch 31500, loss[loss=0.1851, simple_loss=0.2543, pruned_loss=0.058, over 4959.00 frames.], tot_loss[loss=0.15, simple_loss=0.2206, pruned_loss=0.03973, over 973063.03 frames.], batch size: 35, lr: 3.70e-04
2022-05-05 09:28:16,786 INFO [train.py:715] (5/8) Epoch 5, batch 31550, loss[loss=0.1295, simple_loss=0.2029, pruned_loss=0.028, over 4827.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03909, over 973603.47 frames.], batch size: 26, lr: 3.70e-04
2022-05-05 09:28:55,560 INFO [train.py:715] (5/8) Epoch 5, batch 31600, loss[loss=0.1454, simple_loss=0.2153, pruned_loss=0.03773, over 4867.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.03977, over 973360.81 frames.], batch size: 20, lr: 3.70e-04
2022-05-05 09:29:34,422 INFO [train.py:715] (5/8) Epoch 5, batch 31650, loss[loss=0.1441, simple_loss=0.2237, pruned_loss=0.03226, over 4903.00 frames.], tot_loss[loss=0.1509, simple_loss=0.222, pruned_loss=0.03989, over 973495.01 frames.], batch size: 23, lr: 3.70e-04
2022-05-05 09:30:13,322 INFO [train.py:715] (5/8) Epoch 5, batch 31700, loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03396, over 4914.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.03999, over 973235.26 frames.], batch size: 17, lr: 3.70e-04
2022-05-05 09:30:52,059 INFO [train.py:715] (5/8) Epoch 5, batch 31750, loss[loss=0.1825, simple_loss=0.2429, pruned_loss=0.06106, over 4771.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.0401, over 973237.28 frames.], batch size: 18, lr: 3.70e-04
2022-05-05 09:31:31,171 INFO [train.py:715] (5/8) Epoch 5, batch 31800, loss[loss=0.1296, simple_loss=0.2085, pruned_loss=0.02533, over 4701.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04053, over 972550.65 frames.], batch size: 15, lr: 3.69e-04
2022-05-05 09:32:09,903 INFO [train.py:715] (5/8) Epoch 5, batch 31850, loss[loss=0.1579, simple_loss=0.2355, pruned_loss=0.04012, over 4882.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2219, pruned_loss=0.04022, over 972125.34 frames.], batch size: 22, lr: 3.69e-04
2022-05-05 09:32:49,448 INFO [train.py:715] (5/8) Epoch 5, batch 31900, loss[loss=0.123, simple_loss=0.1985, pruned_loss=0.02379, over 4871.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03999, over 972273.68 frames.], batch size: 32, lr: 3.69e-04
2022-05-05 09:33:28,131 INFO [train.py:715] (5/8) Epoch 5, batch 31950, loss[loss=0.124, simple_loss=0.1924, pruned_loss=0.02782, over 4903.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.0403, over 972276.07 frames.], batch size: 19, lr: 3.69e-04
2022-05-05 09:34:06,673 INFO [train.py:715] (5/8) Epoch 5, batch 32000, loss[loss=0.148, simple_loss=0.2185, pruned_loss=0.03871, over 4963.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04054, over 972652.23 frames.], batch size: 35, lr: 3.69e-04
2022-05-05 09:34:45,046 INFO [train.py:715] (5/8) Epoch 5, batch 32050, loss[loss=0.1084, simple_loss=0.1813, pruned_loss=0.01781, over 4704.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04021, over 973024.53 frames.], batch size: 15, lr: 3.69e-04
2022-05-05 09:35:24,095 INFO [train.py:715] (5/8) Epoch 5, batch 32100, loss[loss=0.1648, simple_loss=0.2273, pruned_loss=0.05113, over 4868.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2219, pruned_loss=0.0404, over 972092.37 frames.], batch size: 32, lr: 3.69e-04
2022-05-05 09:36:02,964 INFO [train.py:715] (5/8) Epoch 5, batch 32150, loss[loss=0.1422, simple_loss=0.2171, pruned_loss=0.03367, over 4888.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.04023, over 972001.56 frames.], batch size: 16, lr: 3.69e-04
2022-05-05 09:36:41,522 INFO [train.py:715] (5/8) Epoch 5, batch 32200, loss[loss=0.1742, simple_loss=0.2345, pruned_loss=0.05694, over 4755.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04043, over 971150.67 frames.], batch size: 16, lr: 3.69e-04
2022-05-05 09:37:20,075 INFO [train.py:715] (5/8) Epoch 5, batch 32250, loss[loss=0.1379, simple_loss=0.2057, pruned_loss=0.03511, over 4974.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04035, over 971395.11 frames.], batch size: 14, lr: 3.69e-04
2022-05-05 09:37:59,207 INFO [train.py:715] (5/8) Epoch 5, batch 32300, loss[loss=0.1652, simple_loss=0.231, pruned_loss=0.0497, over 4979.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2213, pruned_loss=0.03991, over 971863.77 frames.], batch size: 15, lr: 3.69e-04
2022-05-05 09:38:37,802 INFO [train.py:715] (5/8) Epoch 5, batch 32350, loss[loss=0.1584, simple_loss=0.2266, pruned_loss=0.04514, over 4876.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.0391, over 973274.29 frames.], batch size: 32, lr: 3.69e-04
2022-05-05 09:39:16,504 INFO [train.py:715] (5/8) Epoch 5, batch 32400, loss[loss=0.127, simple_loss=0.1895, pruned_loss=0.03227, over 4835.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2213, pruned_loss=0.03948, over 972367.35 frames.], batch size: 12, lr: 3.69e-04
2022-05-05 09:39:55,116 INFO [train.py:715] (5/8) Epoch 5, batch 32450, loss[loss=0.1433, simple_loss=0.2144, pruned_loss=0.03612, over 4825.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.03995, over 972462.54 frames.], batch size: 26, lr: 3.69e-04
2022-05-05 09:40:33,913 INFO [train.py:715] (5/8) Epoch 5, batch 32500, loss[loss=0.1643, simple_loss=0.2344, pruned_loss=0.0471, over 4733.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03999, over 971920.87 frames.], batch size: 16, lr: 3.69e-04
2022-05-05 09:41:13,467 INFO [train.py:715] (5/8) Epoch 5, batch 32550, loss[loss=0.1728, simple_loss=0.2371, pruned_loss=0.05423, over 4837.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04031, over 972118.64 frames.], batch size: 26, lr: 3.69e-04
2022-05-05 09:41:51,931 INFO [train.py:715] (5/8) Epoch 5, batch 32600, loss[loss=0.1588, simple_loss=0.2208, pruned_loss=0.04838, over 4922.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.03996, over 972832.69 frames.], batch size: 18, lr: 3.69e-04
2022-05-05 09:42:30,725 INFO [train.py:715] (5/8) Epoch 5, batch 32650, loss[loss=0.1468, simple_loss=0.2175, pruned_loss=0.03807, over 4799.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04043, over 972843.53 frames.], batch size: 25, lr: 3.69e-04
2022-05-05 09:43:09,270 INFO [train.py:715] (5/8) Epoch 5, batch 32700, loss[loss=0.1616, simple_loss=0.2293, pruned_loss=0.04691, over 4904.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04041, over 973121.06 frames.], batch size: 17, lr: 3.69e-04
2022-05-05 09:43:47,571 INFO [train.py:715] (5/8) Epoch 5, batch 32750, loss[loss=0.1363, simple_loss=0.2044, pruned_loss=0.03411, over 4824.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04035, over 973448.58 frames.], batch size: 27, lr: 3.69e-04
2022-05-05 09:44:26,286 INFO [train.py:715] (5/8) Epoch 5, batch 32800, loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.03847, over 4923.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04027, over 973975.14 frames.], batch size: 18, lr: 3.69e-04
2022-05-05 09:45:05,106 INFO [train.py:715] (5/8) Epoch 5, batch 32850, loss[loss=0.1724, simple_loss=0.2447, pruned_loss=0.05004, over 4744.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.04015, over 973358.13 frames.], batch size: 16, lr: 3.69e-04
2022-05-05 09:45:44,050 INFO [train.py:715] (5/8) Epoch 5, batch 32900, loss[loss=0.1259, simple_loss=0.1971, pruned_loss=0.02737, over 4955.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.04022, over 974713.64 frames.], batch size: 24, lr: 3.69e-04
2022-05-05 09:46:22,921 INFO [train.py:715] (5/8) Epoch 5, batch 32950, loss[loss=0.1828, simple_loss=0.2394, pruned_loss=0.0631, over 4765.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2211, pruned_loss=0.04024, over 974654.08 frames.], batch size: 14, lr: 3.68e-04
2022-05-05 09:47:01,973 INFO [train.py:715] (5/8) Epoch 5, batch 33000, loss[loss=0.1996, simple_loss=0.2585, pruned_loss=0.07032, over 4947.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2207, pruned_loss=0.03997, over 974406.66 frames.], batch size: 29, lr: 3.68e-04
2022-05-05 09:47:01,973 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 09:47:11,684 INFO [train.py:742] (5/8) Epoch 5, validation: loss=0.1099, simple_loss=0.1951, pruned_loss=0.01236, over 914524.00 frames.
2022-05-05 09:47:50,704 INFO [train.py:715] (5/8) Epoch 5, batch 33050, loss[loss=0.156, simple_loss=0.2183, pruned_loss=0.04678, over 4922.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2215, pruned_loss=0.04059, over 973984.29 frames.], batch size: 18, lr: 3.68e-04
2022-05-05 09:48:29,614 INFO [train.py:715] (5/8) Epoch 5, batch 33100, loss[loss=0.1381, simple_loss=0.2051, pruned_loss=0.03558, over 4939.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.04113, over 974032.76 frames.], batch size: 23, lr: 3.68e-04
2022-05-05 09:49:07,621 INFO [train.py:715] (5/8) Epoch 5, batch 33150, loss[loss=0.1536, simple_loss=0.2259, pruned_loss=0.0406, over 4986.00 frames.], tot_loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04076, over 973966.43 frames.], batch size: 15, lr: 3.68e-04
2022-05-05 09:49:46,217 INFO [train.py:715] (5/8) Epoch 5, batch 33200, loss[loss=0.1535, simple_loss=0.2223, pruned_loss=0.04241, over 4749.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03992, over 974066.22 frames.], batch size: 16, lr: 3.68e-04
2022-05-05 09:50:25,078 INFO [train.py:715] (5/8) Epoch 5, batch 33250, loss[loss=0.151, simple_loss=0.2367, pruned_loss=0.03263, over 4876.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03976, over 973888.41 frames.], batch size: 22, lr: 3.68e-04
2022-05-05 09:51:03,569 INFO [train.py:715] (5/8) Epoch 5, batch 33300, loss[loss=0.1791, simple_loss=0.2535, pruned_loss=0.05235, over 4872.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03972, over 973807.68 frames.], batch size: 16, lr: 3.68e-04
2022-05-05 09:51:41,938 INFO [train.py:715] (5/8) Epoch 5, batch 33350, loss[loss=0.1497, simple_loss=0.2202, pruned_loss=0.03957, over 4956.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2217, pruned_loss=0.03977, over 973298.65 frames.], batch size: 21, lr: 3.68e-04
2022-05-05 09:52:21,208 INFO [train.py:715] (5/8) Epoch 5, batch 33400, loss[loss=0.1417, simple_loss=0.2168, pruned_loss=0.03328, over 4758.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.0398, over 973484.74 frames.], batch size: 19, lr: 3.68e-04
2022-05-05 09:52:59,900 INFO [train.py:715] (5/8) Epoch 5, batch 33450, loss[loss=0.1531, simple_loss=0.2187, pruned_loss=0.04372, over 4990.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04046, over 973852.54 frames.], batch size: 25, lr: 3.68e-04
2022-05-05 09:53:38,250 INFO [train.py:715] (5/8) Epoch 5, batch 33500, loss[loss=0.146, simple_loss=0.2159, pruned_loss=0.03804, over 4856.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.04059, over 973322.29 frames.], batch size: 20, lr: 3.68e-04
2022-05-05 09:54:16,984 INFO [train.py:715] (5/8) Epoch 5, batch 33550, loss[loss=0.1529, simple_loss=0.22, pruned_loss=0.04288, over 4947.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2229, pruned_loss=0.04037, over 973027.73 frames.], batch size: 39, lr: 3.68e-04
2022-05-05 09:54:55,687 INFO [train.py:715] (5/8) Epoch 5, batch 33600, loss[loss=0.1392, simple_loss=0.2146, pruned_loss=0.03187, over 4867.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.0408, over 972964.66 frames.], batch size: 32, lr: 3.68e-04
2022-05-05 09:55:34,354 INFO [train.py:715] (5/8) Epoch 5, batch 33650, loss[loss=0.1531, simple_loss=0.2274, pruned_loss=0.03938, over 4895.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2233, pruned_loss=0.04055, over 972329.41 frames.], batch size: 23, lr: 3.68e-04
2022-05-05 09:56:12,632 INFO [train.py:715] (5/8) Epoch 5, batch 33700, loss[loss=0.1763, simple_loss=0.2352, pruned_loss=0.05872, over 4984.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2234, pruned_loss=0.04066, over 973243.66 frames.], batch size: 28, lr: 3.68e-04
2022-05-05 09:56:51,512 INFO [train.py:715] (5/8) Epoch 5, batch 33750, loss[loss=0.1579, simple_loss=0.2154, pruned_loss=0.05023, over 4987.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2221, pruned_loss=0.04021, over 974085.32 frames.], batch size: 14, lr: 3.68e-04
2022-05-05 09:57:30,146 INFO [train.py:715] (5/8) Epoch 5, batch 33800, loss[loss=0.1465, simple_loss=0.2156, pruned_loss=0.03865, over 4824.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03994, over 972972.99 frames.], batch size: 13, lr: 3.68e-04
2022-05-05 09:58:09,140 INFO [train.py:715] (5/8) Epoch 5, batch 33850, loss[loss=0.122, simple_loss=0.1996, pruned_loss=0.02215, over 4965.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03951, over 972504.32 frames.], batch size: 28, lr: 3.68e-04
2022-05-05 09:58:47,623 INFO [train.py:715] (5/8) Epoch 5, batch 33900, loss[loss=0.1275, simple_loss=0.2029, pruned_loss=0.02609, over 4814.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03968, over 972471.51 frames.], batch size: 25, lr: 3.68e-04
2022-05-05 09:59:25,959 INFO [train.py:715] (5/8) Epoch 5, batch 33950, loss[loss=0.09796, simple_loss=0.1664, pruned_loss=0.01477, over 4703.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03957, over 972701.89 frames.], batch size: 12, lr: 3.68e-04
2022-05-05 10:00:06,988 INFO [train.py:715] (5/8) Epoch 5, batch 34000, loss[loss=0.1636, simple_loss=0.2372, pruned_loss=0.04504, over 4911.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.03973, over 972876.86 frames.], batch size: 23, lr: 3.68e-04
2022-05-05 10:00:45,229 INFO [train.py:715] (5/8) Epoch 5, batch 34050, loss[loss=0.1679, simple_loss=0.2383, pruned_loss=0.04876, over 4780.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03966, over 972621.31 frames.], batch size: 18, lr: 3.67e-04
2022-05-05 10:01:23,920 INFO [train.py:715] (5/8) Epoch 5, batch 34100, loss[loss=0.1383, simple_loss=0.2082, pruned_loss=0.03424, over 4826.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03971, over 972784.43 frames.], batch size: 15, lr: 3.67e-04
2022-05-05 10:02:02,746 INFO [train.py:715] (5/8) Epoch 5, batch 34150, loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03227, over 4637.00 frames.], tot_loss[loss=0.1502, simple_loss=0.221, pruned_loss=0.03973, over 973187.23 frames.], batch size: 13, lr: 3.67e-04
2022-05-05 10:02:41,107 INFO [train.py:715] (5/8) Epoch 5, batch 34200, loss[loss=0.1381, simple_loss=0.2006, pruned_loss=0.03779, over 4966.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.03902, over 972848.34 frames.], batch size: 15, lr: 3.67e-04
2022-05-05 10:03:20,099 INFO [train.py:715] (5/8) Epoch 5, batch 34250, loss[loss=0.1595, simple_loss=0.2275, pruned_loss=0.04578, over 4956.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2199, pruned_loss=0.03977, over 972022.02 frames.], batch size: 21, lr: 3.67e-04
2022-05-05 10:03:58,245 INFO [train.py:715] (5/8) Epoch 5, batch 34300, loss[loss=0.1735, simple_loss=0.242, pruned_loss=0.05254, over 4796.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2202, pruned_loss=0.03976, over 972768.56 frames.], batch size: 21, lr: 3.67e-04
2022-05-05 10:04:36,914 INFO [train.py:715] (5/8) Epoch 5, batch 34350, loss[loss=0.1335, simple_loss=0.2099, pruned_loss=0.02854, over 4983.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2201, pruned_loss=0.03952, over 972914.87 frames.], batch size: 28, lr: 3.67e-04
2022-05-05 10:05:14,795 INFO [train.py:715] (5/8) Epoch 5, batch 34400, loss[loss=0.1243, simple_loss=0.1995, pruned_loss=0.02453, over 4843.00 frames.], tot_loss[loss=0.1495, simple_loss=0.22, pruned_loss=0.0395, over 972934.71 frames.], batch size: 13, lr: 3.67e-04
2022-05-05 10:05:53,762 INFO [train.py:715] (5/8) Epoch 5, batch 34450, loss[loss=0.1492, simple_loss=0.2326, pruned_loss=0.0329, over 4973.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.0395, over 972839.09 frames.], batch size: 15, lr: 3.67e-04
2022-05-05 10:06:32,735 INFO [train.py:715] (5/8) Epoch 5, batch 34500, loss[loss=0.1324, simple_loss=0.2083, pruned_loss=0.02825, over 4836.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.04, over 972764.82 frames.], batch size: 13, lr: 3.67e-04
2022-05-05 10:07:11,202 INFO [train.py:715] (5/8) Epoch 5, batch 34550, loss[loss=0.1319, simple_loss=0.2055, pruned_loss=0.02914, over 4917.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2213, pruned_loss=0.03993, over 972576.88 frames.], batch size: 17, lr: 3.67e-04
2022-05-05 10:07:49,950 INFO [train.py:715] (5/8) Epoch 5, batch 34600, loss[loss=0.1459, simple_loss=0.2093, pruned_loss=0.04129, over 4889.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03955, over 972372.76 frames.], batch size: 19, lr: 3.67e-04
2022-05-05 10:08:28,653 INFO [train.py:715] (5/8) Epoch 5, batch 34650, loss[loss=0.1724, simple_loss=0.2348, pruned_loss=0.055, over 4959.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03993, over 973181.73 frames.], batch size: 35, lr: 3.67e-04
2022-05-05 10:09:07,579 INFO [train.py:715] (5/8) Epoch 5, batch 34700, loss[loss=0.1067, simple_loss=0.1826, pruned_loss=0.0154, over 4862.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04031, over 973365.16 frames.], batch size: 20, lr: 3.67e-04
2022-05-05 10:09:44,905 INFO [train.py:715] (5/8) Epoch 5, batch 34750, loss[loss=0.1281, simple_loss=0.1926, pruned_loss=0.03178, over 4795.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2223, pruned_loss=0.04113, over 972551.50 frames.], batch size: 13, lr: 3.67e-04
2022-05-05 10:10:21,600 INFO [train.py:715] (5/8) Epoch 5, batch 34800, loss[loss=0.1505, simple_loss=0.215, pruned_loss=0.04298, over 4766.00 frames.], tot_loss[loss=0.1501, simple_loss=0.22, pruned_loss=0.04009, over 969736.87 frames.], batch size: 14, lr: 3.67e-04
2022-05-05 10:11:11,225 INFO [train.py:715] (5/8) Epoch 6, batch 0, loss[loss=0.1835, simple_loss=0.2557, pruned_loss=0.05571, over 4825.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2557, pruned_loss=0.05571, over 4825.00 frames.], batch size: 15, lr: 3.46e-04
2022-05-05 10:11:50,191 INFO [train.py:715] (5/8) Epoch 6, batch 50, loss[loss=0.1457, simple_loss=0.2131, pruned_loss=0.03917, over 4790.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2233, pruned_loss=0.0419, over 219038.55 frames.], batch size: 21, lr: 3.46e-04
2022-05-05 10:12:29,109 INFO [train.py:715] (5/8) Epoch 6, batch 100, loss[loss=0.1699, simple_loss=0.2342, pruned_loss=0.0528, over 4865.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2224, pruned_loss=0.04103, over 386129.69 frames.], batch size: 30, lr: 3.46e-04
2022-05-05 10:13:08,349 INFO [train.py:715] (5/8) Epoch 6, batch 150, loss[loss=0.1652, simple_loss=0.2501, pruned_loss=0.04014, over 4904.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2216, pruned_loss=0.04064, over 516298.33 frames.], batch size: 22, lr: 3.46e-04
2022-05-05 10:13:47,633 INFO [train.py:715] (5/8) Epoch 6, batch 200, loss[loss=0.1552, simple_loss=0.2163, pruned_loss=0.04708, over 4849.00 frames.], tot_loss[loss=0.151, simple_loss=0.2213, pruned_loss=0.04032, over 616598.40 frames.], batch size: 30, lr: 3.45e-04
2022-05-05 10:14:26,642 INFO [train.py:715] (5/8) Epoch 6, batch 250, loss[loss=0.1471, simple_loss=0.2093, pruned_loss=0.04239, over 4879.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2224, pruned_loss=0.04126, over 695605.09 frames.], batch size: 19, lr: 3.45e-04
2022-05-05 10:15:05,460 INFO [train.py:715] (5/8) Epoch 6, batch 300, loss[loss=0.145, simple_loss=0.2162, pruned_loss=0.0369, over 4976.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04058, over 757224.70 frames.], batch size: 25, lr: 3.45e-04
2022-05-05 10:15:44,446 INFO [train.py:715] (5/8) Epoch 6, batch 350, loss[loss=0.1515, simple_loss=0.2332, pruned_loss=0.03488, over 4989.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04014, over 804420.79 frames.], batch size: 20, lr: 3.45e-04
2022-05-05 10:16:23,654 INFO [train.py:715] (5/8) Epoch 6, batch 400, loss[loss=0.1208, simple_loss=0.2046, pruned_loss=0.01854, over 4742.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03994, over 841665.00 frames.], batch size: 16, lr: 3.45e-04
2022-05-05 10:17:02,411 INFO [train.py:715] (5/8) Epoch 6, batch 450, loss[loss=0.1454, simple_loss=0.215, pruned_loss=0.03789, over 4851.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03922, over 870730.78 frames.], batch size: 32, lr: 3.45e-04
2022-05-05 10:17:41,008 INFO [train.py:715] (5/8) Epoch 6, batch 500, loss[loss=0.1771, simple_loss=0.2467, pruned_loss=0.05374, over 4931.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03919, over 892939.75 frames.], batch size: 39, lr: 3.45e-04
2022-05-05 10:18:20,498 INFO [train.py:715] (5/8) Epoch 6, batch 550, loss[loss=0.1294, simple_loss=0.2046, pruned_loss=0.02705, over 4924.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2201, pruned_loss=0.03922, over 910794.77 frames.], batch size: 23, lr: 3.45e-04
2022-05-05 10:18:59,385 INFO [train.py:715] (5/8) Epoch 6, batch 600, loss[loss=0.1771, simple_loss=0.2553, pruned_loss=0.04946, over 4827.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2209, pruned_loss=0.03998, over 924050.94 frames.], batch size: 26, lr: 3.45e-04
2022-05-05 10:19:38,403 INFO [train.py:715] (5/8) Epoch 6, batch 650, loss[loss=0.1472, simple_loss=0.2344, pruned_loss=0.03006, over 4922.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.04001, over 935339.77 frames.], batch size: 29, lr: 3.45e-04
2022-05-05 10:20:17,489 INFO [train.py:715] (5/8) Epoch 6, batch 700, loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02821, over 4967.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2207, pruned_loss=0.03988, over 944179.13 frames.], batch size: 35, lr: 3.45e-04
2022-05-05 10:20:57,080 INFO [train.py:715] (5/8) Epoch 6, batch 750, loss[loss=0.157, simple_loss=0.2205, pruned_loss=0.04676, over 4764.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.03985, over 949949.96 frames.], batch size: 17, lr: 3.45e-04
2022-05-05 10:21:35,855 INFO [train.py:715] (5/8) Epoch 6, batch 800, loss[loss=0.1275, simple_loss=0.2053, pruned_loss=0.0249, over 4779.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.0393, over 954991.17 frames.], batch size: 17, lr: 3.45e-04
2022-05-05 10:22:14,572 INFO [train.py:715] (5/8) Epoch 6, batch 850, loss[loss=0.1596, simple_loss=0.2283, pruned_loss=0.04541, over 4785.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03984, over 958349.18 frames.], batch size: 17, lr: 3.45e-04
2022-05-05 10:22:54,104 INFO [train.py:715] (5/8) Epoch 6, batch 900, loss[loss=0.1355, simple_loss=0.211, pruned_loss=0.02999, over 4794.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2218, pruned_loss=0.03953, over 961779.92 frames.], batch size: 21, lr: 3.45e-04
2022-05-05 10:23:33,398 INFO [train.py:715] (5/8) Epoch 6, batch 950, loss[loss=0.182, simple_loss=0.243, pruned_loss=0.06048, over 4803.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2219, pruned_loss=0.03961, over 963472.94 frames.], batch size: 17, lr: 3.45e-04
2022-05-05 10:24:12,121 INFO [train.py:715] (5/8) Epoch 6, batch 1000, loss[loss=0.1741, simple_loss=0.2315, pruned_loss=0.05839, over 4818.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2217, pruned_loss=0.03977, over 965219.38 frames.], batch size: 25, lr: 3.45e-04
2022-05-05 10:24:51,184 INFO [train.py:715] (5/8) Epoch 6, batch 1050, loss[loss=0.1522, simple_loss=0.2138, pruned_loss=0.04528, over 4862.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2223, pruned_loss=0.03976, over 966626.58 frames.], batch size: 34, lr: 3.45e-04
2022-05-05 10:25:30,704 INFO [train.py:715] (5/8) Epoch 6, batch 1100, loss[loss=0.141, simple_loss=0.2131, pruned_loss=0.03447, over 4948.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.03981, over 968916.72 frames.], batch size: 21, lr: 3.45e-04
2022-05-05 10:26:09,925 INFO [train.py:715] (5/8) Epoch 6, batch 1150, loss[loss=0.1748, simple_loss=0.2381, pruned_loss=0.05581, over 4939.00 frames.], tot_loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.03923, over 970160.48 frames.], batch size: 29, lr: 3.45e-04
2022-05-05 10:26:48,495 INFO [train.py:715] (5/8) Epoch 6, batch 1200, loss[loss=0.1493, simple_loss=0.2269, pruned_loss=0.03587, over 4785.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2212, pruned_loss=0.03922, over 970523.05 frames.], batch size: 18, lr: 3.45e-04
2022-05-05 10:27:28,195 INFO [train.py:715] (5/8) Epoch 6, batch 1250, loss[loss=0.1073, simple_loss=0.1829, pruned_loss=0.01584, over 4824.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03909, over 971107.12 frames.], batch size: 13, lr: 3.45e-04
2022-05-05 10:28:07,472 INFO [train.py:715] (5/8) Epoch 6, batch 1300, loss[loss=0.1583, simple_loss=0.2232, pruned_loss=0.04668, over 4934.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03876, over 970995.94 frames.], batch size: 29, lr: 3.45e-04
2022-05-05 10:28:46,064 INFO [train.py:715] (5/8) Epoch 6, batch 1350, loss[loss=0.1703, simple_loss=0.227, pruned_loss=0.05678, over 4808.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2199, pruned_loss=0.03964, over 971374.34 frames.], batch size: 26, lr: 3.45e-04
2022-05-05 10:29:24,989 INFO [train.py:715] (5/8) Epoch 6, batch 1400, loss[loss=0.1671, simple_loss=0.2476, pruned_loss=0.04334, over 4773.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2203, pruned_loss=0.03949, over 971574.84 frames.], batch size: 14, lr: 3.45e-04
2022-05-05 10:30:04,139 INFO [train.py:715] (5/8) Epoch 6, batch 1450, loss[loss=0.1635, simple_loss=0.2259, pruned_loss=0.05057, over 4987.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2212, pruned_loss=0.03964, over 972760.86 frames.], batch size: 25, lr: 3.44e-04
2022-05-05 10:30:42,813 INFO [train.py:715] (5/8) Epoch 6, batch 1500, loss[loss=0.138, simple_loss=0.2131, pruned_loss=0.03142, over 4801.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03928, over 972562.98 frames.], batch size: 25, lr: 3.44e-04
2022-05-05 10:31:21,216 INFO [train.py:715] (5/8) Epoch 6, batch 1550, loss[loss=0.1481, simple_loss=0.2107, pruned_loss=0.04273, over 4786.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03941, over 972390.22 frames.], batch size: 18, lr: 3.44e-04
2022-05-05 10:32:00,472 INFO [train.py:715] (5/8) Epoch 6, batch 1600, loss[loss=0.1202, simple_loss=0.198, pruned_loss=0.02115, over 4919.00 frames.], tot_loss[loss=0.15, simple_loss=0.2206, pruned_loss=0.03964, over 972796.22 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:32:40,007 INFO [train.py:715] (5/8) Epoch 6, batch 1650, loss[loss=0.1551, simple_loss=0.2266, pruned_loss=0.04183, over 4882.00 frames.], tot_loss[loss=0.15, simple_loss=0.2207, pruned_loss=0.03964, over 972989.73 frames.], batch size: 22, lr: 3.44e-04
2022-05-05 10:33:18,413 INFO [train.py:715] (5/8) Epoch 6, batch 1700, loss[loss=0.1839, simple_loss=0.2419, pruned_loss=0.06293, over 4848.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04008, over 972955.92 frames.], batch size: 30, lr: 3.44e-04
2022-05-05 10:33:57,729 INFO [train.py:715] (5/8) Epoch 6, batch 1750, loss[loss=0.1204, simple_loss=0.1965, pruned_loss=0.02215, over 4932.00 frames.], tot_loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04063, over 972646.45 frames.], batch size: 29, lr: 3.44e-04
2022-05-05 10:34:37,322 INFO [train.py:715] (5/8) Epoch 6, batch 1800, loss[loss=0.117, simple_loss=0.1893, pruned_loss=0.02239, over 4783.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04016, over 972753.77 frames.], batch size: 12, lr: 3.44e-04
2022-05-05 10:35:16,402 INFO [train.py:715] (5/8) Epoch 6, batch 1850, loss[loss=0.18, simple_loss=0.2414, pruned_loss=0.05932, over 4838.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2219, pruned_loss=0.04014, over 973442.33 frames.], batch size: 25, lr: 3.44e-04
2022-05-05 10:35:54,729 INFO [train.py:715] (5/8) Epoch 6, batch 1900, loss[loss=0.1268, simple_loss=0.1959, pruned_loss=0.02881, over 4962.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2218, pruned_loss=0.04055, over 973249.73 frames.], batch size: 14, lr: 3.44e-04
2022-05-05 10:36:34,277 INFO [train.py:715] (5/8) Epoch 6, batch 1950, loss[loss=0.1416, simple_loss=0.2054, pruned_loss=0.03889, over 4831.00 frames.], tot_loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04074, over 973027.03 frames.], batch size: 15, lr: 3.44e-04
2022-05-05 10:37:13,033 INFO [train.py:715] (5/8) Epoch 6, batch 2000, loss[loss=0.1399, simple_loss=0.2221, pruned_loss=0.02888, over 4808.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04106, over 973156.72 frames.], batch size: 25, lr: 3.44e-04
2022-05-05 10:37:52,082 INFO [train.py:715] (5/8) Epoch 6, batch 2050, loss[loss=0.1808, simple_loss=0.2556, pruned_loss=0.05299, over 4942.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04036, over 973791.89 frames.], batch size: 29, lr: 3.44e-04
2022-05-05 10:38:30,927 INFO [train.py:715] (5/8) Epoch 6, batch 2100, loss[loss=0.1346, simple_loss=0.2029, pruned_loss=0.03317, over 4830.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.04011, over 972107.73 frames.], batch size: 30, lr: 3.44e-04
2022-05-05 10:39:10,111 INFO [train.py:715] (5/8) Epoch 6, batch 2150, loss[loss=0.1959, simple_loss=0.2629, pruned_loss=0.06447, over 4793.00 frames.], tot_loss[loss=0.1505, simple_loss=0.221, pruned_loss=0.04, over 972317.72 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:39:49,072 INFO [train.py:715] (5/8) Epoch 6, batch 2200, loss[loss=0.1665, simple_loss=0.2296, pruned_loss=0.05168, over 4951.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03998, over 972507.51 frames.], batch size: 39, lr: 3.44e-04
2022-05-05 10:40:27,527 INFO [train.py:715] (5/8) Epoch 6, batch 2250, loss[loss=0.1651, simple_loss=0.2342, pruned_loss=0.04795, over 4935.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03955, over 972721.91 frames.], batch size: 39, lr: 3.44e-04
2022-05-05 10:41:06,874 INFO [train.py:715] (5/8) Epoch 6, batch 2300, loss[loss=0.123, simple_loss=0.1998, pruned_loss=0.02311, over 4974.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2197, pruned_loss=0.03898, over 972393.75 frames.], batch size: 24, lr: 3.44e-04
2022-05-05 10:41:45,979 INFO [train.py:715] (5/8) Epoch 6, batch 2350, loss[loss=0.1423, simple_loss=0.21, pruned_loss=0.0373, over 4882.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03864, over 972649.53 frames.], batch size: 16, lr: 3.44e-04
2022-05-05 10:42:24,703 INFO [train.py:715] (5/8) Epoch 6, batch 2400, loss[loss=0.156, simple_loss=0.2232, pruned_loss=0.0444, over 4904.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03895, over 972380.67 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:43:03,444 INFO [train.py:715] (5/8) Epoch 6, batch 2450, loss[loss=0.1618, simple_loss=0.2221, pruned_loss=0.05076, over 4906.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2201, pruned_loss=0.03948, over 972643.92 frames.], batch size: 19, lr: 3.44e-04
2022-05-05 10:43:42,677 INFO [train.py:715] (5/8) Epoch 6, batch 2500, loss[loss=0.143, simple_loss=0.2219, pruned_loss=0.03205, over 4867.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2199, pruned_loss=0.03929, over 973262.72 frames.], batch size: 16, lr: 3.44e-04
2022-05-05 10:44:21,857 INFO [train.py:715] (5/8) Epoch 6, batch 2550, loss[loss=0.1468, simple_loss=0.22, pruned_loss=0.03678, over 4880.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2199, pruned_loss=0.03968, over 973156.38 frames.], batch size: 16, lr: 3.44e-04
2022-05-05 10:45:00,765 INFO [train.py:715] (5/8) Epoch 6, batch 2600, loss[loss=0.1798, simple_loss=0.2601, pruned_loss=0.04982, over 4867.00 frames.], tot_loss[loss=0.15, simple_loss=0.2202, pruned_loss=0.03988, over 972838.29 frames.], batch size: 32, lr: 3.44e-04
2022-05-05 10:45:40,392 INFO [train.py:715] (5/8) Epoch 6, batch 2650, loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03356, over 4818.00 frames.], tot_loss[loss=0.1496, simple_loss=0.22, pruned_loss=0.03958, over 973092.08 frames.], batch size: 25, lr: 3.43e-04
2022-05-05 10:46:19,960 INFO [train.py:715] (5/8) Epoch 6, batch 2700, loss[loss=0.1432, simple_loss=0.2056, pruned_loss=0.04038, over 4759.00 frames.], tot_loss[loss=0.1502, simple_loss=0.221, pruned_loss=0.03974, over 972119.55 frames.], batch size: 19, lr: 3.43e-04
2022-05-05 10:46:58,103 INFO [train.py:715] (5/8) Epoch 6, batch 2750, loss[loss=0.1369, simple_loss=0.2143, pruned_loss=0.02977, over 4887.00 frames.], tot_loss[loss=0.15, simple_loss=0.2212, pruned_loss=0.03944, over 973313.95 frames.], batch size: 16, lr: 3.43e-04
2022-05-05 10:47:37,113 INFO [train.py:715] (5/8) Epoch 6, batch 2800, loss[loss=0.152, simple_loss=0.2321, pruned_loss=0.03588, over 4905.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03966, over 972845.08 frames.], batch size: 17, lr: 3.43e-04
2022-05-05 10:48:16,470 INFO [train.py:715] (5/8) Epoch 6, batch 2850, loss[loss=0.165, simple_loss=0.233, pruned_loss=0.0485, over 4787.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03969, over 972728.18 frames.], batch size: 17, lr: 3.43e-04
2022-05-05 10:48:55,297 INFO [train.py:715] (5/8) Epoch 6, batch 2900, loss[loss=0.1288, simple_loss=0.2006, pruned_loss=0.02846, over 4974.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03992, over 972167.44 frames.], batch size: 24, lr: 3.43e-04
2022-05-05 10:49:33,638 INFO [train.py:715] (5/8) Epoch 6, batch 2950, loss[loss=0.1521, simple_loss=0.2188, pruned_loss=0.04267, over 4657.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.04004, over 971141.57 frames.], batch size: 13, lr: 3.43e-04
2022-05-05 10:50:12,863 INFO [train.py:715] (5/8) Epoch 6, batch 3000, loss[loss=0.1363, simple_loss=0.2072, pruned_loss=0.03273, over 4777.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03989, over 971168.55 frames.], batch size: 14, lr: 3.43e-04
2022-05-05 10:50:12,864 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 10:50:22,538 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01223, over 914524.00 frames.
2022-05-05 10:51:02,171 INFO [train.py:715] (5/8) Epoch 6, batch 3050, loss[loss=0.1635, simple_loss=0.2356, pruned_loss=0.04572, over 4815.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.0399, over 971775.70 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 10:51:41,566 INFO [train.py:715] (5/8) Epoch 6, batch 3100, loss[loss=0.1469, simple_loss=0.224, pruned_loss=0.03493, over 4827.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03975, over 971798.09 frames.], batch size: 15, lr: 3.43e-04
2022-05-05 10:52:20,131 INFO [train.py:715] (5/8) Epoch 6, batch 3150, loss[loss=0.1587, simple_loss=0.2509, pruned_loss=0.03323, over 4756.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04023, over 971460.02 frames.], batch size: 19, lr: 3.43e-04
2022-05-05 10:52:58,780 INFO [train.py:715] (5/8) Epoch 6, batch 3200, loss[loss=0.141, simple_loss=0.2095, pruned_loss=0.03627, over 4901.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2212, pruned_loss=0.04026, over 970897.48 frames.], batch size: 23, lr: 3.43e-04
2022-05-05 10:53:38,607 INFO [train.py:715] (5/8) Epoch 6, batch 3250, loss[loss=0.1623, simple_loss=0.2192, pruned_loss=0.0527, over 4851.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03988, over 971873.04 frames.], batch size: 30, lr: 3.43e-04
2022-05-05 10:54:17,333 INFO [train.py:715] (5/8) Epoch 6, batch 3300, loss[loss=0.1691, simple_loss=0.2252, pruned_loss=0.05648, over 4855.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.0398, over 972579.57 frames.], batch size: 30, lr: 3.43e-04
2022-05-05 10:54:55,861 INFO [train.py:715] (5/8) Epoch 6, batch 3350, loss[loss=0.1837, simple_loss=0.2615, pruned_loss=0.05293, over 4974.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2212, pruned_loss=0.03983, over 972185.92 frames.], batch size: 39, lr: 3.43e-04
2022-05-05 10:55:35,256 INFO [train.py:715] (5/8) Epoch 6, batch 3400, loss[loss=0.1616, simple_loss=0.2311, pruned_loss=0.04603, over 4816.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.0397, over 971685.49 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 10:56:14,431 INFO [train.py:715] (5/8) Epoch 6, batch 3450, loss[loss=0.1594, simple_loss=0.231, pruned_loss=0.0439, over 4938.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.03986, over 971922.09 frames.], batch size: 21, lr: 3.43e-04
2022-05-05 10:56:52,541 INFO [train.py:715] (5/8) Epoch 6, batch 3500, loss[loss=0.1469, simple_loss=0.208, pruned_loss=0.0429, over 4804.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.04005, over 971795.28 frames.], batch size: 13, lr: 3.43e-04
2022-05-05 10:57:31,369 INFO [train.py:715] (5/8) Epoch 6, batch 3550, loss[loss=0.1365, simple_loss=0.2093, pruned_loss=0.03184, over 4825.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03958, over 971960.00 frames.], batch size: 25, lr: 3.43e-04
2022-05-05 10:58:10,830 INFO [train.py:715] (5/8) Epoch 6, batch 3600, loss[loss=0.1575, simple_loss=0.2297, pruned_loss=0.04266, over 4776.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.0392, over 971929.95 frames.], batch size: 18, lr: 3.43e-04
2022-05-05 10:58:49,772 INFO [train.py:715] (5/8) Epoch 6, batch 3650, loss[loss=0.1649, simple_loss=0.2386, pruned_loss=0.04567, over 4852.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03954, over 971846.88 frames.], batch size: 20, lr: 3.43e-04
2022-05-05 10:59:27,964 INFO [train.py:715] (5/8) Epoch 6, batch 3700, loss[loss=0.131, simple_loss=0.2065, pruned_loss=0.02768, over 4929.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03958, over 972515.98 frames.], batch size: 29, lr: 3.43e-04
2022-05-05 11:00:07,226 INFO [train.py:715] (5/8) Epoch 6, batch 3750, loss[loss=0.1846, simple_loss=0.2445, pruned_loss=0.06238, over 4968.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03979, over 972049.70 frames.], batch size: 24, lr: 3.43e-04
2022-05-05 11:00:46,316 INFO [train.py:715] (5/8) Epoch 6, batch 3800, loss[loss=0.1417, simple_loss=0.2102, pruned_loss=0.03663, over 4916.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2213, pruned_loss=0.03994, over 972838.32 frames.], batch size: 18, lr: 3.43e-04
2022-05-05 11:01:24,435 INFO [train.py:715] (5/8) Epoch 6, batch 3850, loss[loss=0.1383, simple_loss=0.2159, pruned_loss=0.0304, over 4991.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03942, over 973255.58 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 11:02:03,351 INFO [train.py:715] (5/8) Epoch 6, batch 3900, loss[loss=0.1762, simple_loss=0.2373, pruned_loss=0.05758, over 4831.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2195, pruned_loss=0.03888, over 972588.28 frames.], batch size: 15, lr: 3.42e-04
2022-05-05 11:02:42,645 INFO [train.py:715] (5/8) Epoch 6, batch 3950, loss[loss=0.1519, simple_loss=0.2266, pruned_loss=0.03864, over 4875.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2201, pruned_loss=0.03921, over 973038.19 frames.], batch size: 20, lr: 3.42e-04
2022-05-05 11:03:21,706 INFO [train.py:715] (5/8) Epoch 6, batch 4000, loss[loss=0.157, simple_loss=0.2342, pruned_loss=0.03994, over 4817.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03946, over 972882.67 frames.], batch size: 26, lr: 3.42e-04
2022-05-05 11:04:00,012 INFO [train.py:715] (5/8) Epoch 6, batch 4050, loss[loss=0.1446, simple_loss=0.2157, pruned_loss=0.03677, over 4916.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2193, pruned_loss=0.03869, over 972496.17 frames.], batch size: 18, lr: 3.42e-04
2022-05-05 11:04:39,114 INFO [train.py:715] (5/8) Epoch 6, batch 4100, loss[loss=0.1351, simple_loss=0.1963, pruned_loss=0.03694, over 4923.00 frames.], tot_loss[loss=0.149, simple_loss=0.2197, pruned_loss=0.03919, over 972609.91 frames.], batch size: 18, lr: 3.42e-04
2022-05-05 11:05:17,850 INFO [train.py:715] (5/8) Epoch 6, batch 4150, loss[loss=0.1356, simple_loss=0.2107, pruned_loss=0.03025, over 4949.00 frames.], tot_loss[loss=0.149, simple_loss=0.2198, pruned_loss=0.0391, over 972230.41 frames.], batch size: 39, lr: 3.42e-04
2022-05-05 11:05:56,005 INFO [train.py:715] (5/8) Epoch 6, batch 4200, loss[loss=0.2064, simple_loss=0.2773, pruned_loss=0.06774, over 4911.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.03902, over 972146.50 frames.], batch size: 39, lr: 3.42e-04
2022-05-05 11:06:34,724 INFO [train.py:715] (5/8) Epoch 6, batch 4250, loss[loss=0.1752, simple_loss=0.2484, pruned_loss=0.05097, over 4784.00 frames.], tot_loss[loss=0.149, simple_loss=0.2198, pruned_loss=0.0391, over 972191.41 frames.], batch size: 18, lr: 3.42e-04
2022-05-05 11:07:13,786 INFO [train.py:715] (5/8) Epoch 6, batch 4300, loss[loss=0.1424, simple_loss=0.2227, pruned_loss=0.03104, over 4970.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03941, over 973694.76 frames.], batch size: 24, lr: 3.42e-04
2022-05-05 11:07:52,584 INFO [train.py:715] (5/8) Epoch 6, batch 4350, loss[loss=0.1461, simple_loss=0.2262, pruned_loss=0.03297, over 4944.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03927, over 973893.22 frames.], batch size: 23, lr: 3.42e-04
2022-05-05 11:08:30,487 INFO [train.py:715] (5/8) Epoch 6, batch 4400, loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03981, over 4760.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03895, over 973721.99 frames.], batch size: 14, lr: 3.42e-04
2022-05-05 11:09:08,943 INFO [train.py:715] (5/8) Epoch 6, batch 4450, loss[loss=0.1544, simple_loss=0.2307, pruned_loss=0.03904, over 4804.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.03899, over 973030.70 frames.], batch size: 21, lr: 3.42e-04
2022-05-05 11:09:48,070 INFO [train.py:715] (5/8) Epoch 6, batch 4500, loss[loss=0.1355, simple_loss=0.201, pruned_loss=0.03499, over 4774.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03823, over 972627.59 frames.], batch size: 12, lr: 3.42e-04
2022-05-05 11:10:26,354 INFO [train.py:715] (5/8) Epoch 6, batch 4550, loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03832, over 4969.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03935, over 971237.96 frames.], batch size: 31, lr: 3.42e-04
2022-05-05 11:11:04,819 INFO [train.py:715] (5/8) Epoch 6, batch 4600, loss[loss=0.1812, simple_loss=0.262, pruned_loss=0.0502, over 4970.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2213, pruned_loss=0.0395, over 972679.92 frames.], batch size: 24, lr: 3.42e-04
2022-05-05 11:11:44,224 INFO [train.py:715] (5/8) Epoch 6, batch 4650, loss[loss=0.1421, simple_loss=0.2062, pruned_loss=0.03902, over 4827.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03944, over 972735.24 frames.], batch size: 26, lr: 3.42e-04
2022-05-05 11:12:23,349 INFO [train.py:715] (5/8) Epoch 6, batch 4700, loss[loss=0.1679, simple_loss=0.2374, pruned_loss=0.04923, over 4912.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.03919, over 972265.22 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:13:01,630 INFO [train.py:715] (5/8) Epoch 6, batch 4750, loss[loss=0.1315, simple_loss=0.2081, pruned_loss=0.02743, over 4971.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03917, over 971777.93 frames.], batch size: 28, lr: 3.42e-04
2022-05-05 11:13:40,646 INFO [train.py:715] (5/8) Epoch 6, batch 4800, loss[loss=0.1246, simple_loss=0.2072, pruned_loss=0.02095, over 4942.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03884, over 971549.16 frames.], batch size: 23, lr: 3.42e-04
2022-05-05 11:14:19,737 INFO [train.py:715] (5/8) Epoch 6, batch 4850, loss[loss=0.1492, simple_loss=0.229, pruned_loss=0.03471, over 4767.00 frames.], tot_loss[loss=0.1498, simple_loss=0.221, pruned_loss=0.03926, over 971146.79 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:14:58,283 INFO [train.py:715] (5/8) Epoch 6, batch 4900, loss[loss=0.1547, simple_loss=0.219, pruned_loss=0.04516, over 4937.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2217, pruned_loss=0.0393, over 971212.40 frames.], batch size: 29, lr: 3.42e-04
2022-05-05 11:15:37,163 INFO [train.py:715] (5/8) Epoch 6, batch 4950, loss[loss=0.1332, simple_loss=0.2053, pruned_loss=0.0306, over 4897.00 frames.], tot_loss[loss=0.1492, simple_loss=0.221, pruned_loss=0.03872, over 971732.14 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:16:16,918 INFO [train.py:715] (5/8) Epoch 6, batch 5000, loss[loss=0.1944, simple_loss=0.2644, pruned_loss=0.06223, over 4938.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2217, pruned_loss=0.03926, over 971171.81 frames.], batch size: 21, lr: 3.42e-04
2022-05-05 11:16:55,990 INFO [train.py:715] (5/8) Epoch 6, batch 5050, loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.0412, over 4909.00 frames.], tot_loss[loss=0.1505, simple_loss=0.222, pruned_loss=0.03951, over 972290.57 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:17:34,329 INFO [train.py:715] (5/8) Epoch 6, batch 5100, loss[loss=0.1463, simple_loss=0.2228, pruned_loss=0.03485, over 4878.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2225, pruned_loss=0.03969, over 971909.72 frames.], batch size: 22, lr: 3.42e-04
2022-05-05 11:18:13,254 INFO [train.py:715] (5/8) Epoch 6, batch 5150, loss[loss=0.1568, simple_loss=0.2254, pruned_loss=0.04411, over 4829.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.0396, over 971712.60 frames.], batch size: 26, lr: 3.41e-04
2022-05-05 11:18:52,358 INFO [train.py:715] (5/8) Epoch 6, batch 5200, loss[loss=0.162, simple_loss=0.2265, pruned_loss=0.04877, over 4948.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.0396, over 971821.69 frames.], batch size: 21, lr: 3.41e-04
2022-05-05 11:19:30,491 INFO [train.py:715] (5/8) Epoch 6, batch 5250, loss[loss=0.1211, simple_loss=0.1942, pruned_loss=0.02404, over 4786.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2204, pruned_loss=0.0389, over 972208.95 frames.], batch size: 18, lr: 3.41e-04
2022-05-05 11:20:09,575 INFO [train.py:715] (5/8) Epoch 6, batch 5300, loss[loss=0.1537, simple_loss=0.2214, pruned_loss=0.04306, over 4876.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03831, over 971513.89 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:20:48,894 INFO [train.py:715] (5/8) Epoch 6, batch 5350, loss[loss=0.1482, simple_loss=0.2177, pruned_loss=0.03933, over 4793.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2212, pruned_loss=0.03933, over 971285.08 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:21:27,939 INFO [train.py:715] (5/8) Epoch 6, batch 5400, loss[loss=0.1884, simple_loss=0.2573, pruned_loss=0.05975, over 4847.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03969, over 971608.04 frames.], batch size: 32, lr: 3.41e-04
2022-05-05 11:22:06,519 INFO [train.py:715] (5/8) Epoch 6, batch 5450, loss[loss=0.1322, simple_loss=0.2089, pruned_loss=0.02769, over 4905.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03982, over 970504.74 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:22:45,316 INFO [train.py:715] (5/8) Epoch 6, batch 5500, loss[loss=0.1746, simple_loss=0.2419, pruned_loss=0.0536, over 4768.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03993, over 971184.24 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:23:24,191 INFO [train.py:715] (5/8) Epoch 6, batch 5550, loss[loss=0.1449, simple_loss=0.2232, pruned_loss=0.03334, over 4818.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.03998, over 972329.28 frames.], batch size: 25, lr: 3.41e-04
2022-05-05 11:24:02,782 INFO [train.py:715] (5/8) Epoch 6, batch 5600, loss[loss=0.1771, simple_loss=0.2424, pruned_loss=0.05593, over 4760.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03977, over 973146.49 frames.], batch size: 19, lr: 3.41e-04
2022-05-05 11:24:42,273 INFO [train.py:715] (5/8) Epoch 6, batch 5650, loss[loss=0.1589, simple_loss=0.2231, pruned_loss=0.04737, over 4869.00 frames.], tot_loss[loss=0.1496, simple_loss=0.22, pruned_loss=0.03961, over 972932.54 frames.], batch size: 32, lr: 3.41e-04
2022-05-05 11:25:21,625 INFO [train.py:715] (5/8) Epoch 6, batch 5700, loss[loss=0.1561, simple_loss=0.2351, pruned_loss=0.03852, over 4977.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03879, over 973256.79 frames.], batch size: 20, lr: 3.41e-04
2022-05-05 11:26:00,238 INFO [train.py:715] (5/8) Epoch 6, batch 5750, loss[loss=0.1407, simple_loss=0.2054, pruned_loss=0.038, over 4890.00 frames.], tot_loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.03923, over 972597.58 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:26:38,644 INFO [train.py:715] (5/8) Epoch 6, batch 5800, loss[loss=0.1576, simple_loss=0.2246, pruned_loss=0.04524, over 4881.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2212, pruned_loss=0.03929, over 973776.42 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:27:17,534 INFO [train.py:715] (5/8) Epoch 6, batch 5850, loss[loss=0.1596, simple_loss=0.237, pruned_loss=0.04105, over 4919.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2207, pruned_loss=0.03945, over 974159.77 frames.], batch size: 23, lr: 3.41e-04
2022-05-05 11:27:56,994 INFO [train.py:715] (5/8) Epoch 6, batch 5900, loss[loss=0.1997, simple_loss=0.2638, pruned_loss=0.06776, over 4902.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04009, over 973987.90 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:28:34,908 INFO [train.py:715] (5/8) Epoch 6, batch 5950, loss[loss=0.1375, simple_loss=0.2103, pruned_loss=0.03233, over 4833.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2209, pruned_loss=0.03962, over 972828.65 frames.], batch size: 26, lr: 3.41e-04
2022-05-05 11:29:14,284 INFO [train.py:715] (5/8) Epoch 6, batch 6000, loss[loss=0.1452, simple_loss=0.2206, pruned_loss=0.03492, over 4879.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03989, over 972963.10 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:29:14,285 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 11:29:24,854 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01229, over 914524.00 frames.
2022-05-05 11:30:04,468 INFO [train.py:715] (5/8) Epoch 6, batch 6050, loss[loss=0.1134, simple_loss=0.1788, pruned_loss=0.02403, over 4807.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03963, over 973242.07 frames.], batch size: 12, lr: 3.41e-04
2022-05-05 11:30:43,727 INFO [train.py:715] (5/8) Epoch 6, batch 6100, loss[loss=0.1542, simple_loss=0.219, pruned_loss=0.04471, over 4980.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04003, over 973090.82 frames.], batch size: 39, lr: 3.41e-04
2022-05-05 11:31:23,120 INFO [train.py:715] (5/8) Epoch 6, batch 6150, loss[loss=0.1454, simple_loss=0.215, pruned_loss=0.03788, over 4788.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03948, over 972284.60 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:32:01,617 INFO [train.py:715] (5/8) Epoch 6, batch 6200, loss[loss=0.1797, simple_loss=0.2314, pruned_loss=0.064, over 4637.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03993, over 972679.42 frames.], batch size: 13, lr: 3.41e-04
2022-05-05 11:32:40,935 INFO [train.py:715] (5/8) Epoch 6, batch 6250, loss[loss=0.187, simple_loss=0.2472, pruned_loss=0.06344, over 4989.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03988, over 972306.29 frames.], batch size: 15, lr: 3.41e-04
2022-05-05 11:33:20,233 INFO [train.py:715] (5/8) Epoch 6, batch 6300, loss[loss=0.1694, simple_loss=0.2388, pruned_loss=0.04998, over 4963.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03959, over 972895.50 frames.], batch size: 35, lr: 3.41e-04
2022-05-05 11:33:58,705 INFO [train.py:715] (5/8) Epoch 6, batch 6350, loss[loss=0.1484, simple_loss=0.2164, pruned_loss=0.04016, over 4640.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03981, over 973459.25 frames.], batch size: 13, lr: 3.41e-04
2022-05-05 11:34:37,341 INFO [train.py:715] (5/8) Epoch 6, batch 6400, loss[loss=0.1912, simple_loss=0.2541, pruned_loss=0.06408, over 4709.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2209, pruned_loss=0.03965, over 972903.29 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:35:16,567 INFO [train.py:715] (5/8) Epoch 6, batch 6450, loss[loss=0.1452, simple_loss=0.2209, pruned_loss=0.03476, over 4749.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2205, pruned_loss=0.03969, over 972770.84 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:35:55,386 INFO [train.py:715] (5/8) Epoch 6, batch 6500, loss[loss=0.1472, simple_loss=0.2152, pruned_loss=0.03959, over 4873.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2201, pruned_loss=0.03948, over 973532.91 frames.], batch size: 32, lr: 3.40e-04
2022-05-05 11:36:33,967 INFO [train.py:715] (5/8) Epoch 6, batch 6550, loss[loss=0.1754, simple_loss=0.2447, pruned_loss=0.05303, over 4840.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.03961, over 973654.71 frames.], batch size: 30, lr: 3.40e-04
2022-05-05 11:37:12,774 INFO [train.py:715] (5/8) Epoch 6, batch 6600, loss[loss=0.1359, simple_loss=0.2063, pruned_loss=0.0327, over 4872.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03965, over 973209.86 frames.], batch size: 20, lr: 3.40e-04
2022-05-05 11:37:52,973 INFO [train.py:715] (5/8) Epoch 6, batch 6650, loss[loss=0.1533, simple_loss=0.2226, pruned_loss=0.04204, over 4804.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2214, pruned_loss=0.04044, over 972129.54 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:38:31,784 INFO [train.py:715] (5/8) Epoch 6, batch 6700, loss[loss=0.1734, simple_loss=0.2335, pruned_loss=0.05665, over 4780.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.03998, over 972070.86 frames.], batch size: 18, lr: 3.40e-04
2022-05-05 11:39:10,520 INFO [train.py:715] (5/8) Epoch 6, batch 6750, loss[loss=0.124, simple_loss=0.2036, pruned_loss=0.02217, over 4966.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2215, pruned_loss=0.04032, over 972148.20 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:39:49,805 INFO [train.py:715] (5/8) Epoch 6, batch 6800, loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.0292, over 4950.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03995, over 972077.71 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:40:28,790 INFO [train.py:715] (5/8) Epoch 6, batch 6850, loss[loss=0.1611, simple_loss=0.2287, pruned_loss=0.04672, over 4977.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04007, over 972682.30 frames.], batch size: 25, lr: 3.40e-04
2022-05-05 11:41:06,841 INFO [train.py:715] (5/8) Epoch 6, batch 6900, loss[loss=0.1497, simple_loss=0.2345, pruned_loss=0.0324, over 4962.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.03982, over 973345.05 frames.], batch size: 29, lr: 3.40e-04
2022-05-05 11:41:45,912 INFO [train.py:715] (5/8) Epoch 6, batch 6950, loss[loss=0.1634, simple_loss=0.2362, pruned_loss=0.04532, over 4813.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03978, over 972967.82 frames.], batch size: 26, lr: 3.40e-04
2022-05-05 11:42:25,620 INFO [train.py:715] (5/8) Epoch 6, batch 7000, loss[loss=0.1563, simple_loss=0.2319, pruned_loss=0.0403, over 4812.00 frames.], tot_loss[loss=0.151, simple_loss=0.2221, pruned_loss=0.04001, over 972883.41 frames.], batch size: 21, lr: 3.40e-04
2022-05-05 11:43:04,218 INFO [train.py:715] (5/8) Epoch 6, batch 7050, loss[loss=0.1523, simple_loss=0.2201, pruned_loss=0.04225, over 4957.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04007, over 972407.33 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:43:42,733 INFO [train.py:715] (5/8) Epoch 6, batch 7100, loss[loss=0.1118, simple_loss=0.1843, pruned_loss=0.01966, over 4978.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04014, over 972430.29 frames.], batch size: 14, lr: 3.40e-04
2022-05-05 11:44:25,532 INFO [train.py:715] (5/8) Epoch 6, batch 7150, loss[loss=0.1317, simple_loss=0.2087, pruned_loss=0.02736, over 4769.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03963, over 971888.24 frames.], batch size: 18, lr: 3.40e-04
2022-05-05 11:45:04,231 INFO [train.py:715] (5/8) Epoch 6, batch 7200, loss[loss=0.118, simple_loss=0.19, pruned_loss=0.02298, over 4689.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03985, over 971501.87 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:45:42,695 INFO [train.py:715] (5/8) Epoch 6, batch 7250, loss[loss=0.1306, simple_loss=0.211, pruned_loss=0.02514, over 4871.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2214, pruned_loss=0.04005, over 971961.05 frames.], batch size: 20, lr: 3.40e-04
2022-05-05 11:46:21,449 INFO [train.py:715] (5/8) Epoch 6, batch 7300, loss[loss=0.1527, simple_loss=0.2205, pruned_loss=0.04247, over 4902.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2209, pruned_loss=0.04013, over 972197.96 frames.], batch size: 19, lr: 3.40e-04
2022-05-05 11:47:01,052 INFO [train.py:715] (5/8) Epoch 6, batch 7350, loss[loss=0.1301, simple_loss=0.1998, pruned_loss=0.03018, over 4811.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2214, pruned_loss=0.0402, over 972120.96 frames.], batch size: 26, lr: 3.40e-04
2022-05-05 11:47:38,858 INFO [train.py:715] (5/8) Epoch 6, batch 7400, loss[loss=0.1503, simple_loss=0.2191, pruned_loss=0.04075, over 4801.00 frames.], tot_loss[loss=0.1501, simple_loss=0.221, pruned_loss=0.03964, over 973004.16 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:48:18,377 INFO [train.py:715] (5/8) Epoch 6, batch 7450, loss[loss=0.1523, simple_loss=0.2187, pruned_loss=0.04299, over 4822.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2209, pruned_loss=0.03937, over 972573.41 frames.], batch size: 27, lr: 3.40e-04
2022-05-05 11:48:56,991 INFO [train.py:715] (5/8) Epoch 6, batch 7500, loss[loss=0.1422, simple_loss=0.2112, pruned_loss=0.03658, over 4698.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.0394, over 973135.81 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:49:35,693 INFO [train.py:715] (5/8) Epoch 6, batch 7550, loss[loss=0.1558, simple_loss=0.221, pruned_loss=0.04536, over 4809.00 frames.], tot_loss[loss=0.1503, simple_loss=0.221, pruned_loss=0.03975, over 972818.35 frames.], batch size: 18, lr: 3.40e-04
2022-05-05 11:50:14,634 INFO [train.py:715] (5/8) Epoch 6, batch 7600, loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03336, over 4769.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.03925, over 972537.18 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:50:53,761 INFO [train.py:715] (5/8) Epoch 6, batch 7650, loss[loss=0.1637, simple_loss=0.2286, pruned_loss=0.04939, over 4707.00 frames.], tot_loss[loss=0.1501, simple_loss=0.221, pruned_loss=0.03964, over 972167.56 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:51:33,380 INFO [train.py:715] (5/8) Epoch 6, batch 7700, loss[loss=0.139, simple_loss=0.2058, pruned_loss=0.03614, over 4910.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2209, pruned_loss=0.0397, over 972115.18 frames.], batch size: 19, lr: 3.39e-04
2022-05-05 11:52:11,590 INFO [train.py:715] (5/8) Epoch 6, batch 7750, loss[loss=0.1233, simple_loss=0.1977, pruned_loss=0.02443, over 4786.00 frames.], tot_loss[loss=0.1502, simple_loss=0.221, pruned_loss=0.03971, over 971698.58 frames.], batch size: 18, lr: 3.39e-04
2022-05-05 11:52:51,084 INFO [train.py:715] (5/8) Epoch 6, batch 7800, loss[loss=0.1907, simple_loss=0.2553, pruned_loss=0.063, over 4970.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.0398, over 971389.25 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 11:53:30,018 INFO [train.py:715] (5/8) Epoch 6, batch 7850, loss[loss=0.1486, simple_loss=0.2168, pruned_loss=0.04023, over 4811.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03986, over 970979.43 frames.], batch size: 26, lr: 3.39e-04
2022-05-05 11:54:08,585 INFO [train.py:715] (5/8) Epoch 6, batch 7900, loss[loss=0.1538, simple_loss=0.2356, pruned_loss=0.03597, over 4786.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03947, over 971256.40 frames.], batch size: 18, lr: 3.39e-04
2022-05-05 11:54:47,341 INFO [train.py:715] (5/8) Epoch 6, batch 7950, loss[loss=0.1926, simple_loss=0.2645, pruned_loss=0.06034, over 4955.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.03926, over 972104.63 frames.], batch size: 15, lr: 3.39e-04
2022-05-05 11:55:26,523 INFO [train.py:715] (5/8) Epoch 6, batch 8000, loss[loss=0.1757, simple_loss=0.2488, pruned_loss=0.0513, over 4937.00 frames.], tot_loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.0393, over 972602.76 frames.], batch size: 29, lr: 3.39e-04
2022-05-05 11:56:05,892 INFO [train.py:715] (5/8) Epoch 6, batch 8050, loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.0336, over 4864.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2206, pruned_loss=0.03978, over 972685.55 frames.], batch size: 16, lr: 3.39e-04
2022-05-05 11:56:43,896 INFO [train.py:715] (5/8) Epoch 6, batch 8100, loss[loss=0.1763, simple_loss=0.2446, pruned_loss=0.05401, over 4922.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.04012, over 972646.42 frames.], batch size: 18, lr: 3.39e-04
2022-05-05 11:57:22,883 INFO [train.py:715] (5/8) Epoch 6, batch 8150, loss[loss=0.1876, simple_loss=0.2574, pruned_loss=0.05889, over 4761.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04038, over 972397.46 frames.], batch size: 19, lr: 3.39e-04
2022-05-05 11:58:01,956 INFO [train.py:715] (5/8) Epoch 6, batch 8200, loss[loss=0.1479, simple_loss=0.2041, pruned_loss=0.04585, over 4825.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2219, pruned_loss=0.04016, over 972035.70 frames.], batch size: 12, lr: 3.39e-04
2022-05-05 11:58:41,277 INFO [train.py:715] (5/8) Epoch 6, batch 8250, loss[loss=0.1533, simple_loss=0.2192, pruned_loss=0.04364, over 4755.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03992, over 972532.30 frames.], batch size: 19, lr: 3.39e-04
2022-05-05 11:59:19,577 INFO [train.py:715] (5/8) Epoch 6, batch 8300, loss[loss=0.128, simple_loss=0.2025, pruned_loss=0.02672, over 4784.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03983, over 973215.61 frames.], batch size: 17, lr: 3.39e-04
2022-05-05 11:59:58,759 INFO [train.py:715] (5/8) Epoch 6, batch 8350, loss[loss=0.1306, simple_loss=0.2038, pruned_loss=0.02874, over 4840.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.03983, over 972918.02 frames.], batch size: 13, lr: 3.39e-04
2022-05-05 12:00:37,620 INFO [train.py:715] (5/8) Epoch 6, batch 8400, loss[loss=0.1193, simple_loss=0.1876, pruned_loss=0.02556, over 4728.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.0401, over 972122.65 frames.], batch size: 12, lr: 3.39e-04
2022-05-05 12:01:15,842 INFO [train.py:715] (5/8) Epoch 6, batch 8450, loss[loss=0.1475, simple_loss=0.2132, pruned_loss=0.04085, over 4792.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2209, pruned_loss=0.03998, over 972491.00 frames.], batch size: 21, lr: 3.39e-04
2022-05-05 12:01:54,986 INFO [train.py:715] (5/8) Epoch 6, batch 8500, loss[loss=0.1634, simple_loss=0.2242, pruned_loss=0.05125, over 4841.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2209, pruned_loss=0.04027, over 972805.62 frames.], batch size: 30, lr: 3.39e-04
2022-05-05 12:02:33,547 INFO [train.py:715] (5/8) Epoch 6, batch 8550, loss[loss=0.1638, simple_loss=0.2335, pruned_loss=0.04709, over 4929.00 frames.], tot_loss[loss=0.1507, simple_loss=0.221, pruned_loss=0.04015, over 971848.50 frames.], batch size: 29, lr: 3.39e-04
2022-05-05 12:03:12,439 INFO [train.py:715] (5/8) Epoch 6, batch 8600, loss[loss=0.1307, simple_loss=0.2077, pruned_loss=0.02683, over 4900.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03995, over 971455.92 frames.], batch size: 17, lr: 3.39e-04
2022-05-05 12:03:50,309 INFO [train.py:715] (5/8) Epoch 6, batch 8650, loss[loss=0.1272, simple_loss=0.1924, pruned_loss=0.03101, over 4813.00 frames.], tot_loss[loss=0.151, simple_loss=0.2213, pruned_loss=0.0403, over 971609.41 frames.], batch size: 26, lr: 3.39e-04
2022-05-05 12:04:29,737 INFO [train.py:715] (5/8) Epoch 6, batch 8700, loss[loss=0.1685, simple_loss=0.2482, pruned_loss=0.04437, over 4974.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2216, pruned_loss=0.04069, over 971747.67 frames.], batch size: 28, lr: 3.39e-04
2022-05-05 12:05:08,432 INFO [train.py:715] (5/8) Epoch 6, batch 8750, loss[loss=0.1355, simple_loss=0.2047, pruned_loss=0.03314, over 4867.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2209, pruned_loss=0.04005, over 972433.74 frames.], batch size: 22, lr: 3.39e-04
2022-05-05 12:05:46,862 INFO [train.py:715] (5/8) Epoch 6, batch 8800, loss[loss=0.1348, simple_loss=0.1977, pruned_loss=0.03592, over 4790.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2209, pruned_loss=0.04023, over 972188.71 frames.], batch size: 12, lr: 3.39e-04
2022-05-05 12:06:25,683 INFO [train.py:715] (5/8) Epoch 6, batch 8850, loss[loss=0.1813, simple_loss=0.255, pruned_loss=0.05383, over 4870.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2213, pruned_loss=0.04026, over 972128.53 frames.], batch size: 16, lr: 3.39e-04
2022-05-05 12:07:04,757 INFO [train.py:715] (5/8) Epoch 6, batch 8900, loss[loss=0.1246, simple_loss=0.1904, pruned_loss=0.02943, over 4887.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2204, pruned_loss=0.03969, over 971508.09 frames.], batch size: 32, lr: 3.39e-04
2022-05-05 12:07:44,017 INFO [train.py:715] (5/8) Epoch 6, batch 8950, loss[loss=0.1531, simple_loss=0.2245, pruned_loss=0.04086, over 4822.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2217, pruned_loss=0.04005, over 970832.39 frames.], batch size: 25, lr: 3.38e-04
2022-05-05 12:08:22,490 INFO [train.py:715] (5/8) Epoch 6, batch 9000, loss[loss=0.1618, simple_loss=0.2276, pruned_loss=0.04799, over 4953.00 frames.], tot_loss[loss=0.1507, simple_loss=0.221, pruned_loss=0.04024, over 971309.28 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:08:22,491 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 12:08:35,889 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1094, simple_loss=0.1946, pruned_loss=0.01213, over 914524.00 frames.
2022-05-05 12:09:14,899 INFO [train.py:715] (5/8) Epoch 6, batch 9050, loss[loss=0.1762, simple_loss=0.2479, pruned_loss=0.05229, over 4785.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03987, over 971631.19 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:09:53,935 INFO [train.py:715] (5/8) Epoch 6, batch 9100, loss[loss=0.1483, simple_loss=0.2108, pruned_loss=0.04288, over 4846.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2206, pruned_loss=0.03994, over 971977.35 frames.], batch size: 32, lr: 3.38e-04
2022-05-05 12:10:33,368 INFO [train.py:715] (5/8) Epoch 6, batch 9150, loss[loss=0.1529, simple_loss=0.2289, pruned_loss=0.03845, over 4855.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.0398, over 972207.80 frames.], batch size: 20, lr: 3.38e-04
2022-05-05 12:11:11,396 INFO [train.py:715] (5/8) Epoch 6, batch 9200, loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 4819.00 frames.], tot_loss[loss=0.15, simple_loss=0.2209, pruned_loss=0.03956, over 972757.47 frames.], batch size: 13, lr: 3.38e-04
2022-05-05 12:11:50,805 INFO [train.py:715] (5/8) Epoch 6, batch 9250, loss[loss=0.1431, simple_loss=0.2141, pruned_loss=0.03605, over 4924.00 frames.], tot_loss[loss=0.149, simple_loss=0.2202, pruned_loss=0.03894, over 972647.84 frames.], batch size: 23, lr: 3.38e-04
2022-05-05 12:12:29,885 INFO [train.py:715] (5/8) Epoch 6, batch 9300, loss[loss=0.12, simple_loss=0.1895, pruned_loss=0.02525, over 4977.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.0392, over 972028.72 frames.], batch size: 25, lr: 3.38e-04
2022-05-05 12:13:08,399 INFO [train.py:715] (5/8) Epoch 6, batch 9350, loss[loss=0.1401, simple_loss=0.2107, pruned_loss=0.03474, over 4803.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03921, over 971555.55 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:13:47,632 INFO [train.py:715] (5/8) Epoch 6, batch 9400, loss[loss=0.1526, simple_loss=0.2309, pruned_loss=0.03716, over 4926.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03856, over 972095.87 frames.], batch size: 29, lr: 3.38e-04
2022-05-05 12:14:26,441 INFO [train.py:715] (5/8) Epoch 6, batch 9450, loss[loss=0.1211, simple_loss=0.1954, pruned_loss=0.02346, over 4754.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03897, over 972273.87 frames.], batch size: 12, lr: 3.38e-04
2022-05-05 12:15:05,763 INFO [train.py:715] (5/8) Epoch 6, batch 9500, loss[loss=0.1353, simple_loss=0.2054, pruned_loss=0.03265, over 4922.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2207, pruned_loss=0.03921, over 972765.13 frames.], batch size: 23, lr: 3.38e-04
2022-05-05 12:15:44,435 INFO [train.py:715] (5/8) Epoch 6, batch 9550, loss[loss=0.1563, simple_loss=0.2271, pruned_loss=0.04273, over 4767.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03959, over 972302.30 frames.], batch size: 18, lr: 3.38e-04
2022-05-05 12:16:23,403 INFO [train.py:715] (5/8) Epoch 6, batch 9600, loss[loss=0.1639, simple_loss=0.2373, pruned_loss=0.04526, over 4796.00 frames.], tot_loss[loss=0.1509, simple_loss=0.222, pruned_loss=0.03988, over 972543.12 frames.], batch size: 24, lr: 3.38e-04
2022-05-05 12:17:02,131 INFO [train.py:715] (5/8) Epoch 6, batch 9650, loss[loss=0.1534, simple_loss=0.2253, pruned_loss=0.04075, over 4792.00 frames.], tot_loss[loss=0.1506, simple_loss=0.222, pruned_loss=0.03955, over 972075.31 frames.], batch size: 17, lr: 3.38e-04
2022-05-05 12:17:40,455 INFO [train.py:715] (5/8) Epoch 6, batch 9700, loss[loss=0.1565, simple_loss=0.2309, pruned_loss=0.04102, over 4942.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2218, pruned_loss=0.03929, over 972066.05 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:18:19,756 INFO [train.py:715] (5/8) Epoch 6, batch 9750, loss[loss=0.1638, simple_loss=0.2413, pruned_loss=0.04311, over 4976.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03975, over 971982.65 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:18:59,479 INFO [train.py:715] (5/8) Epoch 6, batch 9800, loss[loss=0.1606, simple_loss=0.2294, pruned_loss=0.04592, over 4660.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03967, over 971382.97 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:19:39,849 INFO [train.py:715] (5/8) Epoch 6, batch 9850, loss[loss=0.1523, simple_loss=0.2263, pruned_loss=0.0392, over 4832.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03958, over 971305.51 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:20:18,999 INFO [train.py:715] (5/8) Epoch 6, batch 9900, loss[loss=0.1497, simple_loss=0.2183, pruned_loss=0.0406, over 4688.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03922, over 971550.04 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:20:59,137 INFO [train.py:715] (5/8) Epoch 6, batch 9950, loss[loss=0.1606, simple_loss=0.2401, pruned_loss=0.04052, over 4919.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2211, pruned_loss=0.03906, over 971290.77 frames.], batch size: 23, lr: 3.38e-04
2022-05-05 12:21:39,157 INFO [train.py:715] (5/8) Epoch 6, batch 10000, loss[loss=0.1475, simple_loss=0.2102, pruned_loss=0.04236, over 4797.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03898, over 971686.28 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:22:17,401 INFO [train.py:715] (5/8) Epoch 6, batch 10050, loss[loss=0.1468, simple_loss=0.2295, pruned_loss=0.03209, over 4802.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2198, pruned_loss=0.03828, over 972278.67 frames.], batch size: 17, lr: 3.38e-04
2022-05-05 12:22:56,775 INFO [train.py:715] (5/8) Epoch 6, batch 10100, loss[loss=0.1564, simple_loss=0.2272, pruned_loss=0.0428, over 4774.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03841, over 971612.59 frames.], batch size: 18, lr: 3.38e-04
2022-05-05 12:23:34,992 INFO [train.py:715] (5/8) Epoch 6, batch 10150, loss[loss=0.1528, simple_loss=0.2132, pruned_loss=0.04619, over 4824.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03883, over 971196.51 frames.], batch size: 12, lr: 3.38e-04
2022-05-05 12:24:14,026 INFO [train.py:715] (5/8) Epoch 6, batch 10200, loss[loss=0.1745, simple_loss=0.237, pruned_loss=0.05602, over 4839.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03908, over 971577.33 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:24:52,552 INFO [train.py:715] (5/8) Epoch 6, batch 10250, loss[loss=0.1325, simple_loss=0.1986, pruned_loss=0.03326, over 4774.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03937, over 970799.42 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:25:31,642 INFO [train.py:715] (5/8) Epoch 6, batch 10300, loss[loss=0.1484, simple_loss=0.2217, pruned_loss=0.0375, over 4918.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03932, over 970995.27 frames.], batch size: 23, lr: 3.37e-04
2022-05-05 12:26:10,141 INFO [train.py:715] (5/8) Epoch 6, batch 10350, loss[loss=0.1869, simple_loss=0.2548, pruned_loss=0.05946, over 4860.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03889, over 970868.68 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:26:49,277 INFO [train.py:715] (5/8) Epoch 6, batch 10400, loss[loss=0.1264, simple_loss=0.2095, pruned_loss=0.02168, over 4810.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2201, pruned_loss=0.03908, over 971524.58 frames.], batch size: 25, lr: 3.37e-04
2022-05-05 12:27:27,709 INFO [train.py:715] (5/8) Epoch 6, batch 10450, loss[loss=0.1473, simple_loss=0.2221, pruned_loss=0.03627, over 4818.00 frames.], tot_loss[loss=0.1492, simple_loss=0.22, pruned_loss=0.03918, over 972558.65 frames.], batch size: 15, lr: 3.37e-04
2022-05-05 12:28:06,362 INFO [train.py:715] (5/8) Epoch 6, batch 10500, loss[loss=0.147, simple_loss=0.2174, pruned_loss=0.03826, over 4912.00 frames.], tot_loss[loss=0.1494, simple_loss=0.22, pruned_loss=0.03943, over 972818.13 frames.], batch size: 29, lr: 3.37e-04
2022-05-05 12:28:45,429 INFO [train.py:715] (5/8) Epoch 6, batch 10550, loss[loss=0.1498, simple_loss=0.2325, pruned_loss=0.03357, over 4917.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03895, over 971594.93 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:29:23,699 INFO [train.py:715] (5/8) Epoch 6, batch 10600, loss[loss=0.1481, simple_loss=0.2205, pruned_loss=0.03787, over 4869.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03845, over 970743.07 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:30:02,908 INFO [train.py:715] (5/8) Epoch 6, batch 10650, loss[loss=0.1157, simple_loss=0.1957, pruned_loss=0.0178, over 4814.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03846, over 971569.17 frames.], batch size: 25, lr: 3.37e-04
2022-05-05 12:30:41,618 INFO [train.py:715] (5/8) Epoch 6, batch 10700, loss[loss=0.2119, simple_loss=0.2654, pruned_loss=0.07926, over 4989.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.0397, over 970906.63 frames.], batch size: 31, lr: 3.37e-04
2022-05-05 12:31:20,569 INFO [train.py:715] (5/8) Epoch 6, batch 10750, loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.03825, over 4817.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03954, over 970846.51 frames.], batch size: 26, lr: 3.37e-04
2022-05-05 12:31:59,030 INFO [train.py:715] (5/8) Epoch 6, batch 10800, loss[loss=0.1639, simple_loss=0.2251, pruned_loss=0.05136, over 4883.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03944, over 970857.59 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:32:37,568 INFO [train.py:715] (5/8) Epoch 6, batch 10850, loss[loss=0.1561, simple_loss=0.2047, pruned_loss=0.0537, over 4816.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04016, over 971265.44 frames.], batch size: 13, lr: 3.37e-04
2022-05-05 12:33:15,993 INFO [train.py:715] (5/8) Epoch 6, batch 10900, loss[loss=0.1411, simple_loss=0.2105, pruned_loss=0.03585, over 4851.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03989, over 971951.93 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:33:54,114 INFO [train.py:715] (5/8) Epoch 6, batch 10950, loss[loss=0.1284, simple_loss=0.2037, pruned_loss=0.02655, over 4982.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03988, over 972239.44 frames.], batch size: 14, lr: 3.37e-04
2022-05-05 12:34:33,264 INFO [train.py:715] (5/8) Epoch 6, batch 11000, loss[loss=0.158, simple_loss=0.2211, pruned_loss=0.04745, over 4780.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.03989, over 972146.34 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:35:11,625 INFO [train.py:715] (5/8) Epoch 6, batch 11050, loss[loss=0.1413, simple_loss=0.2117, pruned_loss=0.03548, over 4843.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03916, over 972344.20 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:35:50,637 INFO [train.py:715] (5/8) Epoch 6, batch 11100, loss[loss=0.123, simple_loss=0.1911, pruned_loss=0.0274, over 4786.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03905, over 973017.55 frames.], batch size: 14, lr: 3.37e-04
2022-05-05 12:36:29,027 INFO [train.py:715] (5/8) Epoch 6, batch 11150, loss[loss=0.1606, simple_loss=0.2188, pruned_loss=0.05122, over 4870.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2202, pruned_loss=0.03863, over 973337.84 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:37:07,407 INFO [train.py:715] (5/8) Epoch 6, batch 11200, loss[loss=0.1559, simple_loss=0.229, pruned_loss=0.04138, over 4870.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03866, over 972790.18 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:37:45,842 INFO [train.py:715] (5/8) Epoch 6, batch 11250, loss[loss=0.1929, simple_loss=0.2545, pruned_loss=0.06565, over 4969.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03879, over 973642.65 frames.], batch size: 40, lr: 3.37e-04
2022-05-05 12:38:24,403 INFO [train.py:715] (5/8) Epoch 6, batch 11300, loss[loss=0.1327, simple_loss=0.2008, pruned_loss=0.03228, over 4906.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2192, pruned_loss=0.03863, over 972917.56 frames.], batch size: 22, lr: 3.37e-04
2022-05-05 12:39:03,682 INFO [train.py:715] (5/8) Epoch 6, batch 11350, loss[loss=0.1981, simple_loss=0.2505, pruned_loss=0.0729, over 4917.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03889, over 972728.70 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:39:42,620 INFO [train.py:715] (5/8) Epoch 6, batch 11400, loss[loss=0.1535, simple_loss=0.22, pruned_loss=0.0435, over 4871.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03899, over 972334.17 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:40:21,680 INFO [train.py:715] (5/8) Epoch 6, batch 11450, loss[loss=0.1681, simple_loss=0.2377, pruned_loss=0.04923, over 4726.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.0393, over 972258.80 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:40:59,949 INFO [train.py:715] (5/8) Epoch 6, batch 11500, loss[loss=0.1378, simple_loss=0.2052, pruned_loss=0.03516, over 4947.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03922, over 972485.17 frames.], batch size: 29, lr: 3.37e-04
2022-05-05 12:41:38,299 INFO [train.py:715] (5/8) Epoch 6, batch 11550, loss[loss=0.1232, simple_loss=0.1884, pruned_loss=0.02899, over 4828.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2199, pruned_loss=0.03919, over 972342.82 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:42:17,676 INFO [train.py:715] (5/8) Epoch 6, batch 11600, loss[loss=0.1702, simple_loss=0.2424, pruned_loss=0.04902, over 4916.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03889, over 972116.91 frames.], batch size: 39, lr: 3.36e-04
2022-05-05 12:42:56,129 INFO [train.py:715] (5/8) Epoch 6, batch 11650, loss[loss=0.137, simple_loss=0.2029, pruned_loss=0.03557, over 4977.00 frames.], tot_loss[loss=0.1494, simple_loss=0.22, pruned_loss=0.03945, over 972060.90 frames.], batch size: 24, lr: 3.36e-04
2022-05-05 12:43:34,995 INFO [train.py:715] (5/8) Epoch 6, batch 11700, loss[loss=0.1541, simple_loss=0.2316, pruned_loss=0.03827, over 4784.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03932, over 972372.14 frames.], batch size: 17, lr: 3.36e-04
2022-05-05 12:44:13,933 INFO [train.py:715] (5/8) Epoch 6, batch 11750, loss[loss=0.1249, simple_loss=0.2031, pruned_loss=0.02331, over 4981.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03913, over 973117.06 frames.], batch size: 25, lr: 3.36e-04
2022-05-05 12:44:53,167 INFO [train.py:715] (5/8) Epoch 6, batch 11800, loss[loss=0.1297, simple_loss=0.1979, pruned_loss=0.03069, over 4863.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03879, over 973681.77 frames.], batch size: 20, lr: 3.36e-04
2022-05-05 12:45:31,847 INFO [train.py:715] (5/8) Epoch 6, batch 11850, loss[loss=0.1475, simple_loss=0.2152, pruned_loss=0.03987, over 4797.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03896, over 973691.52 frames.], batch size: 21, lr: 3.36e-04
2022-05-05 12:46:10,416 INFO [train.py:715] (5/8) Epoch 6, batch 11900, loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03122, over 4771.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.03901, over 973862.20 frames.], batch size: 18, lr: 3.36e-04
2022-05-05 12:46:49,724 INFO [train.py:715] (5/8) Epoch 6, batch 11950, loss[loss=0.1451, simple_loss=0.2125, pruned_loss=0.03879, over 4965.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2208, pruned_loss=0.0389, over 973339.50 frames.], batch size: 24, lr: 3.36e-04
2022-05-05 12:47:28,224 INFO [train.py:715] (5/8) Epoch 6, batch 12000, loss[loss=0.132, simple_loss=0.2073, pruned_loss=0.02832, over 4987.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2208, pruned_loss=0.03879, over 973671.84 frames.], batch size: 25, lr: 3.36e-04
2022-05-05 12:47:28,225 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 12:47:37,945 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1942, pruned_loss=0.01199, over 914524.00 frames.
2022-05-05 12:48:16,697 INFO [train.py:715] (5/8) Epoch 6, batch 12050, loss[loss=0.1664, simple_loss=0.2299, pruned_loss=0.05145, over 4926.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03896, over 973196.83 frames.], batch size: 23, lr: 3.36e-04
2022-05-05 12:48:56,375 INFO [train.py:715] (5/8) Epoch 6, batch 12100, loss[loss=0.1293, simple_loss=0.2001, pruned_loss=0.02928, over 4689.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03943, over 973925.29 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:49:35,321 INFO [train.py:715] (5/8) Epoch 6, batch 12150, loss[loss=0.1552, simple_loss=0.2277, pruned_loss=0.04137, over 4798.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.039, over 974201.61 frames.], batch size: 24, lr: 3.36e-04
2022-05-05 12:50:14,106 INFO [train.py:715] (5/8) Epoch 6, batch 12200, loss[loss=0.1408, simple_loss=0.2112, pruned_loss=0.03516, over 4760.00 frames.], tot_loss[loss=0.1491, simple_loss=0.22, pruned_loss=0.03907, over 973082.67 frames.], batch size: 19, lr: 3.36e-04
2022-05-05 12:50:53,317 INFO [train.py:715] (5/8) Epoch 6, batch 12250, loss[loss=0.144, simple_loss=0.21, pruned_loss=0.03901, over 4864.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03894, over 973197.59 frames.], batch size: 16, lr: 3.36e-04
2022-05-05 12:51:32,109 INFO [train.py:715] (5/8) Epoch 6, batch 12300, loss[loss=0.1264, simple_loss=0.1924, pruned_loss=0.03017, over 4976.00 frames.], tot_loss[loss=0.1494, simple_loss=0.22, pruned_loss=0.03943, over 972776.56 frames.], batch size: 14, lr: 3.36e-04
2022-05-05 12:52:11,891 INFO [train.py:715] (5/8) Epoch 6, batch 12350, loss[loss=0.1577, simple_loss=0.2307, pruned_loss=0.04235, over 4893.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03922, over 973323.93 frames.], batch size: 19, lr: 3.36e-04
2022-05-05 12:52:50,509 INFO [train.py:715] (5/8) Epoch 6, batch 12400, loss[loss=0.1446, simple_loss=0.2123, pruned_loss=0.03848, over 4844.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03928, over 973694.05 frames.], batch size: 32, lr: 3.36e-04
2022-05-05 12:53:29,626 INFO [train.py:715] (5/8) Epoch 6, batch 12450, loss[loss=0.1224, simple_loss=0.2079, pruned_loss=0.01845, over 4794.00 frames.], tot_loss[loss=0.149, simple_loss=0.2202, pruned_loss=0.03895, over 973410.83 frames.], batch size: 21, lr: 3.36e-04
2022-05-05 12:54:08,744 INFO [train.py:715] (5/8) Epoch 6, batch 12500, loss[loss=0.1422, simple_loss=0.2053, pruned_loss=0.03953, over 4864.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03899, over 973467.29 frames.], batch size: 22, lr: 3.36e-04
2022-05-05 12:54:47,050 INFO [train.py:715] (5/8) Epoch 6, batch 12550, loss[loss=0.1881, simple_loss=0.2575, pruned_loss=0.0593, over 4875.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2213, pruned_loss=0.03928, over 973611.75 frames.], batch size: 16, lr: 3.36e-04
2022-05-05 12:55:26,407 INFO [train.py:715] (5/8) Epoch 6, batch 12600, loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03417, over 4860.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2212, pruned_loss=0.03881, over 973014.00 frames.], batch size: 32, lr: 3.36e-04
2022-05-05 12:56:05,095 INFO [train.py:715] (5/8) Epoch 6, batch 12650, loss[loss=0.1298, simple_loss=0.2031, pruned_loss=0.02825, over 4835.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2214, pruned_loss=0.03897, over 973516.59 frames.], batch size: 13, lr: 3.36e-04
2022-05-05 12:56:43,910 INFO [train.py:715] (5/8) Epoch 6, batch 12700, loss[loss=0.1676, simple_loss=0.238, pruned_loss=0.04858, over 4837.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2223, pruned_loss=0.0396, over 973413.77 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:57:22,046 INFO [train.py:715] (5/8) Epoch 6, batch 12750, loss[loss=0.1489, simple_loss=0.2145, pruned_loss=0.04166, over 4699.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2215, pruned_loss=0.0394, over 972471.58 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:58:01,008 INFO [train.py:715] (5/8) Epoch 6, batch 12800, loss[loss=0.1322, simple_loss=0.2095, pruned_loss=0.02746, over 4931.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2222, pruned_loss=0.03974, over 973148.98 frames.], batch size: 23, lr: 3.36e-04
2022-05-05 12:58:39,731 INFO [train.py:715] (5/8) Epoch 6, batch 12850, loss[loss=0.149, simple_loss=0.207, pruned_loss=0.04545, over 4928.00 frames.], tot_loss[loss=0.15, simple_loss=0.2215, pruned_loss=0.03928, over 972721.93 frames.], batch size: 29, lr: 3.35e-04
2022-05-05 12:59:18,388 INFO [train.py:715] (5/8) Epoch 6, batch 12900, loss[loss=0.1279, simple_loss=0.2061, pruned_loss=0.02484, over 4920.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2204, pruned_loss=0.03863, over 972851.16 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 12:59:58,335 INFO [train.py:715] (5/8) Epoch 6, batch 12950, loss[loss=0.1734, simple_loss=0.2337, pruned_loss=0.05655, over 4732.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2199, pruned_loss=0.03848, over 972810.96 frames.], batch size: 16, lr: 3.35e-04
2022-05-05 13:00:37,482 INFO [train.py:715] (5/8) Epoch 6, batch 13000, loss[loss=0.1313, simple_loss=0.211, pruned_loss=0.02581, over 4977.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2202, pruned_loss=0.03844, over 973336.76 frames.], batch size: 25, lr: 3.35e-04
2022-05-05 13:01:16,473 INFO [train.py:715] (5/8) Epoch 6, batch 13050, loss[loss=0.1412, simple_loss=0.2128, pruned_loss=0.0348, over 4757.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03822, over 972317.61 frames.], batch size: 19, lr: 3.35e-04
2022-05-05 13:01:54,765 INFO [train.py:715] (5/8) Epoch 6, batch 13100, loss[loss=0.1584, simple_loss=0.2349, pruned_loss=0.04099, over 4752.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2185, pruned_loss=0.03845, over 971614.70 frames.], batch size: 19, lr: 3.35e-04
2022-05-05 13:02:34,345 INFO [train.py:715] (5/8) Epoch 6, batch 13150, loss[loss=0.1408, simple_loss=0.2104, pruned_loss=0.03557, over 4826.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03937, over 972187.50 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:03:12,922 INFO [train.py:715] (5/8) Epoch 6, batch 13200, loss[loss=0.1682, simple_loss=0.2323, pruned_loss=0.05206, over 4789.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.03953, over 971260.33 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:03:51,764 INFO [train.py:715] (5/8) Epoch 6, batch 13250, loss[loss=0.1684, simple_loss=0.2338, pruned_loss=0.05155, over 4984.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03937, over 971776.57 frames.], batch size: 24, lr: 3.35e-04
2022-05-05 13:04:30,641 INFO [train.py:715] (5/8) Epoch 6, batch 13300, loss[loss=0.1302, simple_loss=0.1957, pruned_loss=0.03231, over 4766.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2189, pruned_loss=0.03843, over 972746.06 frames.], batch size: 14, lr: 3.35e-04
2022-05-05 13:05:09,757 INFO [train.py:715] (5/8) Epoch 6, batch 13350, loss[loss=0.1523, simple_loss=0.2261, pruned_loss=0.03932, over 4786.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03809, over 973866.61 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:05:48,885 INFO [train.py:715] (5/8) Epoch 6, batch 13400, loss[loss=0.1794, simple_loss=0.2404, pruned_loss=0.05921, over 4786.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03839, over 974040.80 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:06:27,483 INFO [train.py:715] (5/8) Epoch 6, batch 13450, loss[loss=0.1607, simple_loss=0.2364, pruned_loss=0.04253, over 4909.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2206, pruned_loss=0.03876, over 974196.84 frames.], batch size: 38, lr: 3.35e-04
2022-05-05 13:07:07,011 INFO [train.py:715] (5/8) Epoch 6, batch 13500, loss[loss=0.172, simple_loss=0.2475, pruned_loss=0.04826, over 4777.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03826, over 972826.59 frames.], batch size: 14, lr: 3.35e-04
2022-05-05 13:07:45,022 INFO [train.py:715] (5/8) Epoch 6, batch 13550, loss[loss=0.1263, simple_loss=0.1976, pruned_loss=0.0275, over 4944.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03845, over 973359.24 frames.], batch size: 21, lr: 3.35e-04
2022-05-05 13:08:23,966 INFO [train.py:715] (5/8) Epoch 6, batch 13600, loss[loss=0.1334, simple_loss=0.2028, pruned_loss=0.03199, over 4814.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2195, pruned_loss=0.0387, over 972805.22 frames.], batch size: 13, lr: 3.35e-04
2022-05-05 13:09:03,111 INFO [train.py:715] (5/8) Epoch 6, batch 13650, loss[loss=0.1259, simple_loss=0.2074, pruned_loss=0.02221, over 4778.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03864, over 973262.45 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:09:42,436 INFO [train.py:715] (5/8) Epoch 6, batch 13700, loss[loss=0.1704, simple_loss=0.2337, pruned_loss=0.05361, over 4965.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03887, over 973851.87 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:10:21,545 INFO [train.py:715] (5/8) Epoch 6, batch 13750, loss[loss=0.1221, simple_loss=0.2011, pruned_loss=0.02159, over 4841.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03871, over 973000.18 frames.], batch size: 32, lr: 3.35e-04
2022-05-05 13:11:00,145 INFO [train.py:715] (5/8) Epoch 6, batch 13800, loss[loss=0.1617, simple_loss=0.2288, pruned_loss=0.04726, over 4912.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03902, over 973586.42 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:11:40,115 INFO [train.py:715] (5/8) Epoch 6, batch 13850, loss[loss=0.1515, simple_loss=0.2197, pruned_loss=0.04166, over 4973.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.03898, over 972743.19 frames.], batch size: 14, lr: 3.35e-04
2022-05-05 13:12:18,448 INFO [train.py:715] (5/8) Epoch 6, batch 13900, loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02926, over 4971.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2195, pruned_loss=0.0391, over 974401.51 frames.], batch size: 31, lr: 3.35e-04
2022-05-05 13:12:57,460 INFO [train.py:715] (5/8) Epoch 6, batch 13950, loss[loss=0.1855, simple_loss=0.2521, pruned_loss=0.05944, over 4745.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.03889, over 974578.34 frames.], batch size: 16, lr: 3.35e-04
2022-05-05 13:13:36,062 INFO [train.py:715] (5/8) Epoch 6, batch 14000, loss[loss=0.1462, simple_loss=0.2193, pruned_loss=0.03658, over 4737.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.03947, over 973367.30 frames.], batch size: 16, lr: 3.35e-04
2022-05-05 13:14:15,110 INFO [train.py:715] (5/8) Epoch 6, batch 14050, loss[loss=0.152, simple_loss=0.2239, pruned_loss=0.04, over 4944.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03932, over 973215.56 frames.], batch size: 29, lr: 3.35e-04
2022-05-05 13:14:53,530 INFO [train.py:715] (5/8) Epoch 6, batch 14100, loss[loss=0.1664, simple_loss=0.2348, pruned_loss=0.04896, over 4814.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03972, over 973329.73 frames.], batch size: 21, lr: 3.35e-04
2022-05-05 13:15:32,018 INFO [train.py:715] (5/8) Epoch 6, batch 14150, loss[loss=0.1433, simple_loss=0.2179, pruned_loss=0.0343, over 4980.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03914, over 973255.53 frames.], batch size: 27, lr: 3.35e-04
2022-05-05 13:16:11,449 INFO [train.py:715] (5/8) Epoch 6, batch 14200, loss[loss=0.1773, simple_loss=0.2538, pruned_loss=0.05036, over 4814.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03932, over 972979.05 frames.], batch size: 27, lr: 3.34e-04
2022-05-05 13:16:50,086 INFO [train.py:715] (5/8) Epoch 6, batch 14250, loss[loss=0.1278, simple_loss=0.2031, pruned_loss=0.02631, over 4743.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03915, over 972281.63 frames.], batch size: 16, lr: 3.34e-04
2022-05-05 13:17:29,126 INFO [train.py:715] (5/8) Epoch 6, batch 14300, loss[loss=0.1575, simple_loss=0.215, pruned_loss=0.04997, over 4965.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03935, over 971341.63 frames.], batch size: 15, lr: 3.34e-04
2022-05-05 13:18:07,580 INFO [train.py:715] (5/8) Epoch 6, batch 14350, loss[loss=0.1784, simple_loss=0.2487, pruned_loss=0.05403, over 4701.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2212, pruned_loss=0.03979, over 971723.85 frames.], batch size: 15, lr: 3.34e-04
2022-05-05 13:18:47,506 INFO [train.py:715] (5/8) Epoch 6, batch 14400, loss[loss=0.1588, simple_loss=0.2291, pruned_loss=0.04424, over 4947.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2208, pruned_loss=0.03998, over 971113.93 frames.], batch size: 21, lr: 3.34e-04
2022-05-05 13:19:25,855 INFO [train.py:715] (5/8) Epoch 6, batch 14450, loss[loss=0.1777, simple_loss=0.2398, pruned_loss=0.05781, over 4952.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2214, pruned_loss=0.03998, over 971324.94 frames.], batch size: 21, lr: 3.34e-04
2022-05-05 13:20:04,246 INFO [train.py:715] (5/8) Epoch 6, batch 14500, loss[loss=0.164, simple_loss=0.2342, pruned_loss=0.04691, over 4772.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2205, pruned_loss=0.03966, over 971461.95 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:20:43,936 INFO [train.py:715] (5/8) Epoch 6, batch 14550, loss[loss=0.1267, simple_loss=0.1977, pruned_loss=0.02785, over 4846.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2193, pruned_loss=0.03903, over 971934.95 frames.], batch size: 13, lr: 3.34e-04
2022-05-05 13:21:22,651 INFO [train.py:715] (5/8) Epoch 6, batch 14600, loss[loss=0.1346, simple_loss=0.2145, pruned_loss=0.0274, over 4772.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03949, over 971911.15 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:22:01,119 INFO [train.py:715] (5/8) Epoch 6, batch 14650, loss[loss=0.1459, simple_loss=0.226, pruned_loss=0.03286, over 4802.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03927, over 970199.00 frames.], batch size: 21, lr: 3.34e-04
2022-05-05 13:22:40,130 INFO [train.py:715] (5/8) Epoch 6, batch 14700, loss[loss=0.1775, simple_loss=0.2464, pruned_loss=0.05425, over 4770.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.039, over 970416.35 frames.], batch size: 19, lr: 3.34e-04
2022-05-05 13:23:19,673 INFO [train.py:715] (5/8) Epoch 6, batch 14750, loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03544, over 4782.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03874, over 970809.55 frames.], batch size: 18, lr: 3.34e-04
2022-05-05 13:23:57,833 INFO [train.py:715] (5/8) Epoch 6, batch 14800, loss[loss=0.1382, simple_loss=0.2035, pruned_loss=0.03643, over 4778.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03896, over 970085.28 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:24:35,995 INFO [train.py:715] (5/8) Epoch 6, batch 14850, loss[loss=0.1415, simple_loss=0.2163, pruned_loss=0.0333, over 4755.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03911, over 970561.46 frames.], batch size: 19, lr: 3.34e-04
2022-05-05 13:25:15,105 INFO [train.py:715] (5/8) Epoch 6, batch 14900, loss[loss=0.1512, simple_loss=0.2173, pruned_loss=0.04249, over 4853.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03923, over 971395.24 frames.], batch size: 32, lr: 3.34e-04
2022-05-05 13:25:53,359 INFO [train.py:715] (5/8) Epoch 6, batch 14950, loss[loss=0.1385, simple_loss=0.2143, pruned_loss=0.03137, over 4887.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.0397, over 972082.89 frames.], batch size: 22, lr: 3.34e-04
2022-05-05 13:26:32,024 INFO [train.py:715] (5/8) Epoch 6, batch 15000, loss[loss=0.1812, simple_loss=0.2446, pruned_loss=0.05894, over 4864.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03945, over 972405.76 frames.], batch size: 32, lr: 3.34e-04
2022-05-05 13:26:32,025 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 13:26:41,818 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1941, pruned_loss=0.01202, over 914524.00 frames.
2022-05-05 13:27:20,601 INFO [train.py:715] (5/8) Epoch 6, batch 15050, loss[loss=0.1838, simple_loss=0.261, pruned_loss=0.05324, over 4781.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2215, pruned_loss=0.03983, over 972204.16 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:27:59,350 INFO [train.py:715] (5/8) Epoch 6, batch 15100, loss[loss=0.142, simple_loss=0.2191, pruned_loss=0.03249, over 4884.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03985, over 972206.31 frames.], batch size: 22, lr: 3.34e-04
2022-05-05 13:28:41,261 INFO [train.py:715] (5/8) Epoch 6, batch 15150, loss[loss=0.1456, simple_loss=0.2145, pruned_loss=0.03833, over 4897.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2219, pruned_loss=0.03963, over 972855.01 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:29:19,831 INFO [train.py:715] (5/8) Epoch 6, batch 15200, loss[loss=0.1421, simple_loss=0.2104, pruned_loss=0.03694, over 4888.00 frames.], tot_loss[loss=0.15, simple_loss=0.2214, pruned_loss=0.03931, over 972777.58 frames.], batch size: 22, lr: 3.34e-04
2022-05-05 13:29:58,374 INFO [train.py:715] (5/8) Epoch 6, batch 15250, loss[loss=0.1324, simple_loss=0.2034, pruned_loss=0.03069, over 4994.00 frames.], tot_loss[loss=0.1495, simple_loss=0.221, pruned_loss=0.03904, over 973329.05 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:30:37,906 INFO [train.py:715] (5/8) Epoch 6, batch 15300, loss[loss=0.1335, simple_loss=0.203, pruned_loss=0.03197, over 4837.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2207, pruned_loss=0.0389, over 972883.73 frames.], batch size: 15, lr: 3.34e-04
2022-05-05 13:31:15,931 INFO [train.py:715] (5/8) Epoch 6, batch 15350, loss[loss=0.1245, simple_loss=0.1937, pruned_loss=0.02765, over 4955.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03901, over 972167.68 frames.], batch size: 15, lr: 3.34e-04
2022-05-05 13:31:54,939 INFO [train.py:715] (5/8) Epoch 6, batch 15400, loss[loss=0.1425, simple_loss=0.2077, pruned_loss=0.03869, over 4777.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2209, pruned_loss=0.03968, over 972794.72 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:32:33,863 INFO [train.py:715] (5/8) Epoch 6, batch 15450, loss[loss=0.1429, simple_loss=0.2196, pruned_loss=0.03306, over 4744.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2209, pruned_loss=0.03936, over 972006.28 frames.], batch size: 16, lr: 3.34e-04
2022-05-05 13:33:13,327 INFO [train.py:715] (5/8) Epoch 6, batch 15500, loss[loss=0.146, simple_loss=0.2018, pruned_loss=0.04507, over 4852.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03921, over 972537.15 frames.], batch size: 13, lr: 3.34e-04
2022-05-05 13:33:51,502 INFO [train.py:715] (5/8) Epoch 6, batch 15550, loss[loss=0.1372, simple_loss=0.2126, pruned_loss=0.03087, over 4946.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03951, over 973626.53 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:34:30,397 INFO [train.py:715] (5/8) Epoch 6, batch 15600, loss[loss=0.148, simple_loss=0.218, pruned_loss=0.039, over 4776.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03985, over 974186.28 frames.], batch size: 17, lr: 3.33e-04
2022-05-05 13:35:09,326 INFO [train.py:715] (5/8) Epoch 6, batch 15650, loss[loss=0.1647, simple_loss=0.2414, pruned_loss=0.04398, over 4991.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2212, pruned_loss=0.03982, over 973485.13 frames.], batch size: 20, lr: 3.33e-04
2022-05-05 13:35:47,368 INFO [train.py:715] (5/8) Epoch 6, batch 15700, loss[loss=0.1606, simple_loss=0.2367, pruned_loss=0.04222, over 4762.00 frames.], tot_loss[loss=0.1501, simple_loss=0.221, pruned_loss=0.03963, over 971939.30 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:36:26,052 INFO [train.py:715] (5/8) Epoch 6, batch 15750, loss[loss=0.1449, simple_loss=0.2113, pruned_loss=0.03926, over 4857.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2208, pruned_loss=0.03978, over 971022.19 frames.], batch size: 32, lr: 3.33e-04
2022-05-05 13:37:04,796 INFO [train.py:715] (5/8) Epoch 6, batch 15800, loss[loss=0.1471, simple_loss=0.2256, pruned_loss=0.03432, over 4789.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.03883, over 971472.43 frames.], batch size: 24, lr: 3.33e-04
2022-05-05 13:37:43,837 INFO [train.py:715] (5/8) Epoch 6, batch 15850, loss[loss=0.1818, simple_loss=0.26, pruned_loss=0.0518, over 4898.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03891, over 972192.01 frames.], batch size: 19, lr: 3.33e-04
2022-05-05 13:38:22,281 INFO [train.py:715] (5/8) Epoch 6, batch 15900, loss[loss=0.1531, simple_loss=0.2291, pruned_loss=0.03848, over 4935.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03877, over 972410.00 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:39:00,646 INFO [train.py:715] (5/8) Epoch 6, batch 15950, loss[loss=0.1549, simple_loss=0.2256, pruned_loss=0.04209, over 4893.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03853, over 972257.18 frames.], batch size: 16, lr: 3.33e-04
2022-05-05 13:39:39,973 INFO [train.py:715] (5/8) Epoch 6, batch 16000, loss[loss=0.1659, simple_loss=0.2367, pruned_loss=0.04752, over 4680.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03824, over 971409.50 frames.], batch size: 15, lr: 3.33e-04
2022-05-05 13:40:18,429 INFO [train.py:715] (5/8) Epoch 6, batch 16050, loss[loss=0.1462, simple_loss=0.2087, pruned_loss=0.04182, over 4917.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.03821, over 970963.43 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:40:56,905 INFO [train.py:715] (5/8) Epoch 6, batch 16100, loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03214, over 4841.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03887, over 971125.99 frames.], batch size: 15, lr: 3.33e-04
2022-05-05 13:41:35,294 INFO [train.py:715] (5/8) Epoch 6, batch 16150, loss[loss=0.1617, simple_loss=0.2301, pruned_loss=0.04668, over 4921.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03876, over 971660.65 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:42:14,795 INFO [train.py:715] (5/8) Epoch 6, batch 16200, loss[loss=0.1421, simple_loss=0.2162, pruned_loss=0.03402, over 4820.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03878, over 972586.55 frames.], batch size: 15, lr: 3.33e-04
2022-05-05 13:42:53,109 INFO [train.py:715] (5/8) Epoch 6, batch 16250, loss[loss=0.218, simple_loss=0.2819, pruned_loss=0.07705, over 4793.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03924, over 972532.73 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:43:31,726 INFO [train.py:715] (5/8) Epoch 6, batch 16300, loss[loss=0.1572, simple_loss=0.2269, pruned_loss=0.04382, over 4871.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.0393, over 971675.27 frames.], batch size: 16, lr: 3.33e-04
2022-05-05 13:44:11,202 INFO [train.py:715] (5/8) Epoch 6, batch 16350, loss[loss=0.1395, simple_loss=0.2147, pruned_loss=0.03215, over 4956.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2214, pruned_loss=0.03944, over 971507.55 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:44:49,507 INFO [train.py:715] (5/8) Epoch 6, batch 16400, loss[loss=0.154, simple_loss=0.2197, pruned_loss=0.04417, over 4988.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03951, over 972409.25 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:45:28,824 INFO [train.py:715] (5/8) Epoch 6, batch 16450, loss[loss=0.196, simple_loss=0.2493, pruned_loss=0.07133, over 4692.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03871, over 972145.51 frames.], batch size: 15, lr: 3.33e-04
2022-05-05 13:46:07,627 INFO [train.py:715] (5/8) Epoch 6, batch 16500, loss[loss=0.1416, simple_loss=0.2241, pruned_loss=0.02953, over 4904.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2197, pruned_loss=0.03891, over 972852.27 frames.], batch size: 39, lr: 3.33e-04
2022-05-05 13:46:46,576 INFO [train.py:715] (5/8) Epoch 6, batch 16550, loss[loss=0.1439, simple_loss=0.2153, pruned_loss=0.03623, over 4830.00 frames.], tot_loss[loss=0.148, simple_loss=0.219, pruned_loss=0.03848, over 973197.60 frames.], batch size: 27, lr: 3.33e-04
2022-05-05 13:47:24,413 INFO [train.py:715] (5/8) Epoch 6, batch 16600, loss[loss=0.1515, simple_loss=0.2203, pruned_loss=0.04132, over 4917.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2193, pruned_loss=0.03899, over 972837.17 frames.], batch size: 39, lr: 3.33e-04
2022-05-05 13:48:03,153 INFO [train.py:715] (5/8) Epoch 6, batch 16650, loss[loss=0.1524, simple_loss=0.2392, pruned_loss=0.03277, over 4889.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.0394, over 972739.39 frames.], batch size: 17, lr: 3.33e-04
2022-05-05 13:48:42,812 INFO [train.py:715] (5/8) Epoch 6, batch 16700, loss[loss=0.1398, simple_loss=0.202, pruned_loss=0.0388, over 4969.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.0392, over 972869.21 frames.], batch size: 35, lr: 3.33e-04
2022-05-05 13:49:21,220 INFO [train.py:715] (5/8) Epoch 6, batch 16750, loss[loss=0.1552, simple_loss=0.2264, pruned_loss=0.04199, over 4983.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03898, over 972636.55 frames.], batch size: 25, lr: 3.33e-04
2022-05-05 13:50:00,118 INFO [train.py:715] (5/8) Epoch 6, batch 16800, loss[loss=0.1442, simple_loss=0.2198, pruned_loss=0.03425, over 4828.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03896, over 972320.02 frames.], batch size: 26, lr: 3.33e-04
2022-05-05 13:50:39,325 INFO [train.py:715] (5/8) Epoch 6, batch 16850, loss[loss=0.1546, simple_loss=0.2244, pruned_loss=0.04239, over 4988.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03901, over 972427.10 frames.], batch size: 20, lr: 3.33e-04
2022-05-05 13:51:19,121 INFO [train.py:715] (5/8) Epoch 6, batch 16900, loss[loss=0.1714, simple_loss=0.2462, pruned_loss=0.04827, over 4959.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03897, over 973220.74 frames.], batch size: 15, lr: 3.32e-04
2022-05-05 13:51:57,173 INFO [train.py:715] (5/8) Epoch 6, batch 16950, loss[loss=0.1735, simple_loss=0.2578, pruned_loss=0.04461, over 4912.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.03943, over 972202.11 frames.], batch size: 17, lr: 3.32e-04
2022-05-05 13:52:36,228 INFO [train.py:715] (5/8) Epoch 6, batch 17000, loss[loss=0.1779, simple_loss=0.2507, pruned_loss=0.05254, over 4901.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03921, over 971927.60 frames.], batch size: 39, lr: 3.32e-04
2022-05-05 13:53:15,747 INFO [train.py:715] (5/8) Epoch 6, batch 17050, loss[loss=0.1413, simple_loss=0.221, pruned_loss=0.03074, over 4884.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2218, pruned_loss=0.03932, over 972577.58 frames.], batch size: 22, lr: 3.32e-04
2022-05-05 13:53:53,901 INFO [train.py:715] (5/8) Epoch 6, batch 17100, loss[loss=0.1347, simple_loss=0.2161, pruned_loss=0.02671, over 4917.00 frames.], tot_loss[loss=0.1508, simple_loss=0.222, pruned_loss=0.03979, over 972826.74 frames.], batch size: 23, lr: 3.32e-04
2022-05-05 13:54:32,774 INFO [train.py:715] (5/8) Epoch 6, batch 17150, loss[loss=0.113, simple_loss=0.1923, pruned_loss=0.01687, over 4896.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03984, over 972255.81 frames.], batch size: 22, lr: 3.32e-04
2022-05-05 13:55:11,749 INFO [train.py:715] (5/8) Epoch 6, batch 17200, loss[loss=0.163, simple_loss=0.2358, pruned_loss=0.04514, over 4818.00 frames.], tot_loss[loss=0.1508, simple_loss=0.222, pruned_loss=0.03981, over 972322.58 frames.], batch size: 27, lr: 3.32e-04
2022-05-05 13:55:51,111 INFO [train.py:715] (5/8) Epoch 6, batch 17250, loss[loss=0.1642, simple_loss=0.2337, pruned_loss=0.04739, over 4778.00 frames.], tot_loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03938, over 971948.23 frames.], batch size: 18, lr: 3.32e-04
2022-05-05 13:56:29,075 INFO [train.py:715] (5/8) Epoch 6, batch 17300, loss[loss=0.1155, simple_loss=0.1868, pruned_loss=0.02216, over 4815.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03894, over 972275.19 frames.], batch size: 12, lr: 3.32e-04
2022-05-05 13:57:07,890 INFO [train.py:715] (5/8) Epoch 6, batch 17350, loss[loss=0.1577, simple_loss=0.2199, pruned_loss=0.04769, over 4955.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2206, pruned_loss=0.03883, over 972559.30 frames.], batch size: 35, lr: 3.32e-04
2022-05-05 13:57:47,278 INFO [train.py:715] (5/8) Epoch 6, batch 17400, loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03845, over 4848.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2211, pruned_loss=0.03917, over 972606.92 frames.], batch size: 32, lr: 3.32e-04
2022-05-05 13:58:26,212 INFO [train.py:715] (5/8) Epoch 6, batch 17450, loss[loss=0.1409, simple_loss=0.2102, pruned_loss=0.03582, over 4768.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2207, pruned_loss=0.0386, over 973554.34 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 13:59:04,828 INFO [train.py:715] (5/8) Epoch 6, batch 17500, loss[loss=0.1411, simple_loss=0.2181, pruned_loss=0.03208, over 4802.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03897, over 973531.37 frames.], batch size: 24, lr: 3.32e-04
2022-05-05 13:59:43,981 INFO [train.py:715] (5/8) Epoch 6, batch 17550, loss[loss=0.1469, simple_loss=0.2175, pruned_loss=0.0382, over 4952.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03905, over 973189.82 frames.], batch size: 24, lr: 3.32e-04
2022-05-05 14:00:23,862 INFO [train.py:715] (5/8) Epoch 6, batch 17600, loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02841, over 4918.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03874, over 972775.21 frames.], batch size: 19, lr: 3.32e-04
2022-05-05 14:01:01,423 INFO [train.py:715] (5/8) Epoch 6, batch 17650, loss[loss=0.1644, simple_loss=0.2285, pruned_loss=0.0501, over 4865.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03839, over 972461.95 frames.], batch size: 32, lr: 3.32e-04
2022-05-05 14:01:40,864 INFO [train.py:715] (5/8) Epoch 6, batch 17700, loss[loss=0.1373, simple_loss=0.2097, pruned_loss=0.03248, over 4961.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03827, over 972809.41 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 14:02:20,249 INFO [train.py:715] (5/8) Epoch 6, batch 17750, loss[loss=0.1732, simple_loss=0.2394, pruned_loss=0.05352, over 4978.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03849, over 972909.83 frames.], batch size: 39, lr: 3.32e-04
2022-05-05 14:02:58,604 INFO [train.py:715] (5/8) Epoch 6, batch 17800, loss[loss=0.1355, simple_loss=0.2024, pruned_loss=0.03432, over 4867.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03896, over 972975.88 frames.], batch size: 38, lr: 3.32e-04
2022-05-05 14:03:37,538 INFO [train.py:715] (5/8) Epoch 6, batch 17850, loss[loss=0.127, simple_loss=0.2068, pruned_loss=0.0236, over 4807.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03858, over 973512.20 frames.], batch size: 26, lr: 3.32e-04
2022-05-05 14:04:16,744 INFO [train.py:715] (5/8) Epoch 6, batch 17900, loss[loss=0.1961, simple_loss=0.2568, pruned_loss=0.06773, over 4828.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2202, pruned_loss=0.03836, over 973312.69 frames.], batch size: 15, lr: 3.32e-04
2022-05-05 14:04:56,309 INFO [train.py:715] (5/8) Epoch 6, batch 17950, loss[loss=0.1618, simple_loss=0.2251, pruned_loss=0.04923, over 4973.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2197, pruned_loss=0.03798, over 972819.80 frames.], batch size: 35, lr: 3.32e-04
2022-05-05 14:05:34,139 INFO [train.py:715] (5/8) Epoch 6, batch 18000, loss[loss=0.1671, simple_loss=0.2248, pruned_loss=0.05474, over 4991.00 frames.], tot_loss[loss=0.1484, simple_loss=0.22, pruned_loss=0.0384, over 973022.25 frames.], batch size: 15, lr: 3.32e-04
2022-05-05 14:05:34,140 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 14:05:43,883 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1939, pruned_loss=0.0118, over 914524.00 frames.
2022-05-05 14:06:22,337 INFO [train.py:715] (5/8) Epoch 6, batch 18050, loss[loss=0.1498, simple_loss=0.2159, pruned_loss=0.0418, over 4739.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03824, over 972430.30 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 14:07:01,818 INFO [train.py:715] (5/8) Epoch 6, batch 18100, loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03628, over 4842.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2188, pruned_loss=0.03814, over 972347.07 frames.], batch size: 15, lr: 3.32e-04
2022-05-05 14:07:41,269 INFO [train.py:715] (5/8) Epoch 6, batch 18150, loss[loss=0.153, simple_loss=0.2326, pruned_loss=0.03671, over 4777.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03885, over 972915.09 frames.], batch size: 18, lr: 3.32e-04
2022-05-05 14:08:19,363 INFO [train.py:715] (5/8) Epoch 6, batch 18200, loss[loss=0.1247, simple_loss=0.1964, pruned_loss=0.02647, over 4789.00 frames.], tot_loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.03872, over 972313.58 frames.], batch size: 12, lr: 3.32e-04
2022-05-05 14:08:58,862 INFO [train.py:715] (5/8) Epoch 6, batch 18250, loss[loss=0.1348, simple_loss=0.2079, pruned_loss=0.03081, over 4891.00 frames.], tot_loss[loss=0.149, simple_loss=0.2203, pruned_loss=0.03886, over 973454.18 frames.], batch size: 22, lr: 3.31e-04
2022-05-05 14:09:38,213 INFO [train.py:715] (5/8) Epoch 6, batch 18300, loss[loss=0.166, simple_loss=0.2266, pruned_loss=0.05274, over 4897.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03855, over 972870.63 frames.], batch size: 17, lr: 3.31e-04
2022-05-05 14:10:17,260 INFO [train.py:715] (5/8) Epoch 6, batch 18350, loss[loss=0.1644, simple_loss=0.2244, pruned_loss=0.05217, over 4952.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03857, over 972715.04 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:10:55,622 INFO [train.py:715] (5/8) Epoch 6, batch 18400, loss[loss=0.1581, simple_loss=0.2313, pruned_loss=0.04246, over 4832.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03896, over 972786.63 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:11:34,890 INFO [train.py:715] (5/8) Epoch 6, batch 18450, loss[loss=0.139, simple_loss=0.2103, pruned_loss=0.03383, over 4984.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03874, over 973349.91 frames.], batch size: 25, lr: 3.31e-04
2022-05-05 14:12:14,317 INFO [train.py:715] (5/8) Epoch 6, batch 18500, loss[loss=0.1515, simple_loss=0.2086, pruned_loss=0.04726, over 4993.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03886, over 973391.09 frames.], batch size: 14, lr: 3.31e-04
2022-05-05 14:12:52,317 INFO [train.py:715] (5/8) Epoch 6, batch 18550, loss[loss=0.1426, simple_loss=0.217, pruned_loss=0.03405, over 4836.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.0389, over 973129.24 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:13:31,752 INFO [train.py:715] (5/8) Epoch 6, batch 18600, loss[loss=0.1533, simple_loss=0.2231, pruned_loss=0.04178, over 4922.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03866, over 973077.02 frames.], batch size: 23, lr: 3.31e-04
2022-05-05 14:14:10,848 INFO [train.py:715] (5/8) Epoch 6, batch 18650, loss[loss=0.1539, simple_loss=0.2283, pruned_loss=0.0398, over 4943.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03908, over 972948.79 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:14:50,390 INFO [train.py:715] (5/8) Epoch 6, batch 18700, loss[loss=0.1338, simple_loss=0.2121, pruned_loss=0.02774, over 4645.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03946, over 972541.94 frames.], batch size: 13, lr: 3.31e-04
2022-05-05 14:15:28,528 INFO [train.py:715] (5/8) Epoch 6, batch 18750, loss[loss=0.1312, simple_loss=0.2118, pruned_loss=0.02524, over 4892.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03923, over 971851.26 frames.], batch size: 19, lr: 3.31e-04
2022-05-05 14:16:07,705 INFO [train.py:715] (5/8) Epoch 6, batch 18800, loss[loss=0.194, simple_loss=0.2608, pruned_loss=0.06367, over 4832.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03884, over 972264.20 frames.], batch size: 30, lr: 3.31e-04
2022-05-05 14:16:47,206 INFO [train.py:715] (5/8) Epoch 6, batch 18850, loss[loss=0.1917, simple_loss=0.2568, pruned_loss=0.06323, over 4975.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2217, pruned_loss=0.03928, over 973193.75 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:17:25,254 INFO [train.py:715] (5/8) Epoch 6, batch 18900, loss[loss=0.1231, simple_loss=0.1925, pruned_loss=0.02682, over 4808.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2213, pruned_loss=0.03894, over 972993.59 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:18:04,842 INFO [train.py:715] (5/8) Epoch 6, batch 18950, loss[loss=0.1354, simple_loss=0.2153, pruned_loss=0.02775, over 4799.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2213, pruned_loss=0.03863, over 973578.44 frames.], batch size: 25, lr: 3.31e-04
2022-05-05 14:18:43,970 INFO [train.py:715] (5/8) Epoch 6, batch 19000, loss[loss=0.1451, simple_loss=0.2155, pruned_loss=0.03739, over 4939.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2216, pruned_loss=0.0386, over 973699.60 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:19:23,156 INFO [train.py:715] (5/8) Epoch 6, batch 19050, loss[loss=0.1929, simple_loss=0.2612, pruned_loss=0.06227, over 4793.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2211, pruned_loss=0.03831, over 973421.80 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:20:01,544 INFO [train.py:715] (5/8) Epoch 6, batch 19100, loss[loss=0.1384, simple_loss=0.2168, pruned_loss=0.02996, over 4831.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2213, pruned_loss=0.03843, over 973782.83 frames.], batch size: 12, lr: 3.31e-04
2022-05-05 14:20:40,516 INFO [train.py:715] (5/8) Epoch 6, batch 19150, loss[loss=0.1333, simple_loss=0.2124, pruned_loss=0.02706, over 4906.00 frames.], tot_loss[loss=0.149, simple_loss=0.2209, pruned_loss=0.03852, over 974666.34 frames.], batch size: 19, lr: 3.31e-04
2022-05-05 14:21:20,170 INFO [train.py:715] (5/8) Epoch 6, batch 19200, loss[loss=0.1773, simple_loss=0.2369, pruned_loss=0.05886, over 4938.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03878, over 974622.93 frames.], batch size: 35, lr: 3.31e-04
2022-05-05 14:21:58,237 INFO [train.py:715] (5/8) Epoch 6, batch 19250, loss[loss=0.1336, simple_loss=0.199, pruned_loss=0.0341, over 4758.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2198, pruned_loss=0.03831, over 973831.95 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:22:37,149 INFO [train.py:715] (5/8) Epoch 6, batch 19300, loss[loss=0.1298, simple_loss=0.1966, pruned_loss=0.03152, over 4765.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03871, over 973025.10 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:23:16,401 INFO [train.py:715] (5/8) Epoch 6, batch 19350, loss[loss=0.1576, simple_loss=0.2346, pruned_loss=0.04026, over 4804.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2208, pruned_loss=0.03872, over 973098.78 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:23:54,992 INFO [train.py:715] (5/8) Epoch 6, batch 19400, loss[loss=0.1435, simple_loss=0.2181, pruned_loss=0.03442, over 4854.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03881, over 972463.15 frames.], batch size: 30, lr: 3.31e-04
2022-05-05 14:24:33,670 INFO [train.py:715] (5/8) Epoch 6, batch 19450, loss[loss=0.1675, simple_loss=0.218, pruned_loss=0.05856, over 4712.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2195, pruned_loss=0.03905, over 971399.25 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:25:13,067 INFO [train.py:715] (5/8) Epoch 6, batch 19500, loss[loss=0.1553, simple_loss=0.222, pruned_loss=0.04432, over 4929.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2188, pruned_loss=0.03837, over 972597.68 frames.], batch size: 39, lr: 3.31e-04
2022-05-05 14:25:51,972 INFO [train.py:715] (5/8) Epoch 6, batch 19550, loss[loss=0.1448, simple_loss=0.2185, pruned_loss=0.03558, over 4764.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.03794, over 971831.49 frames.], batch size: 19, lr: 3.31e-04
2022-05-05 14:26:30,333 INFO [train.py:715] (5/8) Epoch 6, batch 19600, loss[loss=0.1357, simple_loss=0.2078, pruned_loss=0.03175, over 4830.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2183, pruned_loss=0.03854, over 972510.59 frames.], batch size: 25, lr: 3.31e-04
2022-05-05 14:27:09,232 INFO [train.py:715] (5/8) Epoch 6, batch 19650, loss[loss=0.1711, simple_loss=0.2418, pruned_loss=0.05018, over 4825.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03867, over 973090.25 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:27:48,352 INFO [train.py:715] (5/8) Epoch 6, batch 19700, loss[loss=0.1181, simple_loss=0.1871, pruned_loss=0.02453, over 4813.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2188, pruned_loss=0.03846, over 971711.04 frames.], batch size: 13, lr: 3.30e-04
2022-05-05 14:28:27,133 INFO [train.py:715] (5/8) Epoch 6, batch 19750, loss[loss=0.1749, simple_loss=0.2479, pruned_loss=0.051, over 4783.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03837, over 971362.18 frames.], batch size: 14, lr: 3.30e-04
2022-05-05 14:29:05,245 INFO [train.py:715] (5/8) Epoch 6, batch 19800, loss[loss=0.1286, simple_loss=0.1969, pruned_loss=0.03015, over 4954.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03864, over 971323.69 frames.], batch size: 35, lr: 3.30e-04
2022-05-05 14:29:44,599 INFO [train.py:715] (5/8) Epoch 6, batch 19850, loss[loss=0.1485, simple_loss=0.2104, pruned_loss=0.04334, over 4965.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2184, pruned_loss=0.03797, over 971311.57 frames.], batch size: 35, lr: 3.30e-04
2022-05-05 14:30:24,342 INFO [train.py:715] (5/8) Epoch 6, batch 19900, loss[loss=0.1533, simple_loss=0.2278, pruned_loss=0.03935, over 4791.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2188, pruned_loss=0.03797, over 971487.44 frames.], batch size: 18, lr: 3.30e-04
2022-05-05 14:31:02,426 INFO [train.py:715] (5/8) Epoch 6, batch 19950, loss[loss=0.1129, simple_loss=0.1917, pruned_loss=0.01704, over 4803.00 frames.], tot_loss[loss=0.1473, simple_loss=0.219, pruned_loss=0.03778, over 972107.24 frames.], batch size: 24, lr: 3.30e-04
2022-05-05 14:31:41,549 INFO [train.py:715] (5/8) Epoch 6, batch 20000, loss[loss=0.1495, simple_loss=0.2287, pruned_loss=0.03518, over 4816.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03837, over 971732.20 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:32:21,022 INFO [train.py:715] (5/8) Epoch 6, batch 20050, loss[loss=0.1433, simple_loss=0.2135, pruned_loss=0.03659, over 4871.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03835, over 971478.41 frames.], batch size: 32, lr: 3.30e-04
2022-05-05 14:32:59,451 INFO [train.py:715] (5/8) Epoch 6, batch 20100, loss[loss=0.1881, simple_loss=0.2618, pruned_loss=0.05723, over 4791.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2188, pruned_loss=0.03827, over 970763.40 frames.], batch size: 14, lr: 3.30e-04
2022-05-05 14:33:38,526 INFO [train.py:715] (5/8) Epoch 6, batch 20150, loss[loss=0.1485, simple_loss=0.2314, pruned_loss=0.03279, over 4956.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03845, over 970757.73 frames.], batch size: 21, lr: 3.30e-04
2022-05-05 14:34:17,810 INFO [train.py:715] (5/8) Epoch 6, batch 20200, loss[loss=0.1274, simple_loss=0.1894, pruned_loss=0.03266, over 4685.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03899, over 971217.51 frames.], batch size: 12, lr: 3.30e-04
2022-05-05 14:34:56,736 INFO [train.py:715] (5/8) Epoch 6, batch 20250, loss[loss=0.2163, simple_loss=0.2618, pruned_loss=0.08538, over 4852.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2202, pruned_loss=0.03942, over 971069.09 frames.], batch size: 30, lr: 3.30e-04
2022-05-05 14:35:35,498 INFO [train.py:715] (5/8) Epoch 6, batch 20300, loss[loss=0.1473, simple_loss=0.2122, pruned_loss=0.04115, over 4871.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03914, over 971291.04 frames.], batch size: 32, lr: 3.30e-04
2022-05-05 14:36:14,861 INFO [train.py:715] (5/8) Epoch 6, batch 20350, loss[loss=0.134, simple_loss=0.2088, pruned_loss=0.02966, over 4818.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.0386, over 970415.24 frames.], batch size: 26, lr: 3.30e-04
2022-05-05 14:36:54,306 INFO [train.py:715] (5/8) Epoch 6, batch 20400, loss[loss=0.1975, simple_loss=0.2778, pruned_loss=0.05858, over 4904.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2192, pruned_loss=0.03871, over 971180.73 frames.], batch size: 17, lr: 3.30e-04
2022-05-05 14:37:32,664 INFO [train.py:715] (5/8) Epoch 6, batch 20450, loss[loss=0.1381, simple_loss=0.2097, pruned_loss=0.03325, over 4888.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03864, over 971587.20 frames.], batch size: 32, lr: 3.30e-04
2022-05-05 14:38:11,467 INFO [train.py:715] (5/8) Epoch 6, batch 20500, loss[loss=0.1465, simple_loss=0.208, pruned_loss=0.04255, over 4885.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03867, over 971928.66 frames.], batch size: 16, lr: 3.30e-04
2022-05-05 14:38:50,533 INFO [train.py:715] (5/8) Epoch 6, batch 20550, loss[loss=0.1902, simple_loss=0.2643, pruned_loss=0.05804, over 4842.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03935, over 971632.41 frames.], batch size: 15, lr: 3.30e-04
2022-05-05 14:39:29,695 INFO [train.py:715] (5/8) Epoch 6, batch 20600, loss[loss=0.1872, simple_loss=0.2715, pruned_loss=0.0514, over 4775.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.0396, over 972372.53 frames.], batch size: 18, lr: 3.30e-04
2022-05-05 14:40:07,959 INFO [train.py:715] (5/8) Epoch 6, batch 20650, loss[loss=0.154, simple_loss=0.2251, pruned_loss=0.04147, over 4831.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03961, over 972714.05 frames.], batch size: 27, lr: 3.30e-04
2022-05-05 14:40:46,652 INFO [train.py:715] (5/8) Epoch 6, batch 20700, loss[loss=0.1242, simple_loss=0.1967, pruned_loss=0.02588, over 4923.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03969, over 972943.19 frames.], batch size: 23, lr: 3.30e-04
2022-05-05 14:41:25,992 INFO [train.py:715] (5/8) Epoch 6, batch 20750, loss[loss=0.1595, simple_loss=0.2377, pruned_loss=0.04065, over 4948.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2221, pruned_loss=0.03989, over 972811.03 frames.], batch size: 21, lr: 3.30e-04
2022-05-05 14:42:04,393 INFO [train.py:715] (5/8) Epoch 6, batch 20800, loss[loss=0.1384, simple_loss=0.2085, pruned_loss=0.03414, over 4851.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03965, over 973145.79 frames.], batch size: 30, lr: 3.30e-04
2022-05-05 14:42:43,607 INFO [train.py:715] (5/8) Epoch 6, batch 20850, loss[loss=0.168, simple_loss=0.2277, pruned_loss=0.05412, over 4942.00 frames.], tot_loss[loss=0.1501, simple_loss=0.221, pruned_loss=0.03963, over 973026.94 frames.], batch size: 35, lr: 3.30e-04
2022-05-05 14:43:22,881 INFO [train.py:715] (5/8) Epoch 6, batch 20900, loss[loss=0.1335, simple_loss=0.2157, pruned_loss=0.02568, over 4835.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03929, over 972360.10 frames.], batch size: 26, lr: 3.30e-04
2022-05-05 14:44:02,110 INFO [train.py:715] (5/8) Epoch 6, batch 20950, loss[loss=0.1417, simple_loss=0.2027, pruned_loss=0.04032, over 4929.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.03929, over 972655.79 frames.], batch size: 23, lr: 3.30e-04
2022-05-05 14:44:40,094 INFO [train.py:715] (5/8) Epoch 6, batch 21000, loss[loss=0.1757, simple_loss=0.2464, pruned_loss=0.05256, over 4847.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03925, over 972728.13 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 14:44:40,094 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 14:44:51,876 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01192, over 914524.00 frames.
2022-05-05 14:45:30,115 INFO [train.py:715] (5/8) Epoch 6, batch 21050, loss[loss=0.1704, simple_loss=0.2545, pruned_loss=0.04319, over 4881.00 frames.], tot_loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.0387, over 971722.71 frames.], batch size: 32, lr: 3.29e-04
2022-05-05 14:46:09,485 INFO [train.py:715] (5/8) Epoch 6, batch 21100, loss[loss=0.1607, simple_loss=0.2196, pruned_loss=0.05088, over 4743.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03885, over 972135.44 frames.], batch size: 14, lr: 3.29e-04
2022-05-05 14:46:48,887 INFO [train.py:715] (5/8) Epoch 6, batch 21150, loss[loss=0.1525, simple_loss=0.2267, pruned_loss=0.03912, over 4784.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03837, over 972797.93 frames.], batch size: 18, lr: 3.29e-04
2022-05-05 14:47:27,343 INFO [train.py:715] (5/8) Epoch 6, batch 21200, loss[loss=0.1409, simple_loss=0.2123, pruned_loss=0.03476, over 4906.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03855, over 973656.41 frames.], batch size: 39, lr: 3.29e-04
2022-05-05 14:48:06,353 INFO [train.py:715] (5/8) Epoch 6, batch 21250, loss[loss=0.1459, simple_loss=0.2198, pruned_loss=0.03604, over 4794.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03851, over 972878.33 frames.], batch size: 21, lr: 3.29e-04
2022-05-05 14:48:45,977 INFO [train.py:715] (5/8) Epoch 6, batch 21300, loss[loss=0.1841, simple_loss=0.2546, pruned_loss=0.05679, over 4946.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03849, over 972935.10 frames.], batch size: 29, lr: 3.29e-04
2022-05-05 14:49:24,955 INFO [train.py:715] (5/8) Epoch 6, batch 21350, loss[loss=0.1347, simple_loss=0.2076, pruned_loss=0.0309, over 4739.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03816, over 974272.80 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:50:03,788 INFO [train.py:715] (5/8) Epoch 6, batch 21400, loss[loss=0.1455, simple_loss=0.2234, pruned_loss=0.03384, over 4854.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2186, pruned_loss=0.03804, over 974036.80 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 14:50:42,550 INFO [train.py:715] (5/8) Epoch 6, batch 21450, loss[loss=0.1228, simple_loss=0.2036, pruned_loss=0.02103, over 4859.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03817, over 973884.74 frames.], batch size: 22, lr: 3.29e-04
2022-05-05 14:51:21,821 INFO [train.py:715] (5/8) Epoch 6, batch 21500, loss[loss=0.1425, simple_loss=0.2177, pruned_loss=0.03367, over 4820.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03866, over 973795.40 frames.], batch size: 25, lr: 3.29e-04
2022-05-05 14:52:00,293 INFO [train.py:715] (5/8) Epoch 6, batch 21550, loss[loss=0.1452, simple_loss=0.2152, pruned_loss=0.0376, over 4986.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03847, over 974533.90 frames.], batch size: 26, lr: 3.29e-04
2022-05-05 14:52:39,313 INFO [train.py:715] (5/8) Epoch 6, batch 21600, loss[loss=0.1503, simple_loss=0.2196, pruned_loss=0.0405, over 4964.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2199, pruned_loss=0.03841, over 974176.55 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 14:53:18,465 INFO [train.py:715] (5/8) Epoch 6, batch 21650, loss[loss=0.1423, simple_loss=0.2205, pruned_loss=0.03204, over 4940.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03887, over 973965.57 frames.], batch size: 29, lr: 3.29e-04
2022-05-05 14:53:57,743 INFO [train.py:715] (5/8) Epoch 6, batch 21700, loss[loss=0.1303, simple_loss=0.2064, pruned_loss=0.02711, over 4865.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03861, over 973676.83 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:54:36,455 INFO [train.py:715] (5/8) Epoch 6, batch 21750, loss[loss=0.1284, simple_loss=0.1945, pruned_loss=0.03117, over 4783.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03887, over 973338.58 frames.], batch size: 14, lr: 3.29e-04
2022-05-05 14:55:15,315 INFO [train.py:715] (5/8) Epoch 6, batch 21800, loss[loss=0.1375, simple_loss=0.2081, pruned_loss=0.03348, over 4881.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03903, over 974004.53 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:55:54,105 INFO [train.py:715] (5/8) Epoch 6, batch 21850, loss[loss=0.1514, simple_loss=0.231, pruned_loss=0.03591, over 4808.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03922, over 974049.66 frames.], batch size: 25, lr: 3.29e-04
2022-05-05 14:56:32,646 INFO [train.py:715] (5/8) Epoch 6, batch 21900, loss[loss=0.133, simple_loss=0.2045, pruned_loss=0.03077, over 4740.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.03889, over 974270.90 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:57:11,519 INFO [train.py:715] (5/8) Epoch 6, batch 21950, loss[loss=0.1396, simple_loss=0.2026, pruned_loss=0.0383, over 4874.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.03927, over 974095.10 frames.], batch size: 30, lr: 3.29e-04
2022-05-05 14:57:50,235 INFO [train.py:715] (5/8) Epoch 6, batch 22000, loss[loss=0.1654, simple_loss=0.244, pruned_loss=0.04342, over 4874.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2199, pruned_loss=0.03926, over 974834.99 frames.], batch size: 22, lr: 3.29e-04
2022-05-05 14:58:29,942 INFO [train.py:715] (5/8) Epoch 6, batch 22050, loss[loss=0.178, simple_loss=0.2521, pruned_loss=0.05198, over 4886.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2193, pruned_loss=0.03884, over 974318.12 frames.], batch size: 22, lr: 3.29e-04
2022-05-05 14:59:08,261 INFO [train.py:715] (5/8) Epoch 6, batch 22100, loss[loss=0.1634, simple_loss=0.2283, pruned_loss=0.04922, over 4926.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03857, over 973933.73 frames.], batch size: 18, lr: 3.29e-04
2022-05-05 14:59:47,062 INFO [train.py:715] (5/8) Epoch 6, batch 22150, loss[loss=0.1457, simple_loss=0.2242, pruned_loss=0.0336, over 4819.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03858, over 974549.86 frames.], batch size: 27, lr: 3.29e-04
2022-05-05 15:00:26,256 INFO [train.py:715] (5/8) Epoch 6, batch 22200, loss[loss=0.1252, simple_loss=0.1947, pruned_loss=0.02781, over 4755.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2195, pruned_loss=0.03862, over 973578.47 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 15:01:04,921 INFO [train.py:715] (5/8) Epoch 6, batch 22250, loss[loss=0.1428, simple_loss=0.2055, pruned_loss=0.04004, over 4848.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.0392, over 973546.30 frames.], batch size: 32, lr: 3.29e-04
2022-05-05 15:01:43,598 INFO [train.py:715] (5/8) Epoch 6, batch 22300, loss[loss=0.1717, simple_loss=0.2348, pruned_loss=0.05428, over 4761.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03912, over 974016.54 frames.], batch size: 19, lr: 3.29e-04
2022-05-05 15:02:22,657 INFO [train.py:715] (5/8) Epoch 6, batch 22350, loss[loss=0.157, simple_loss=0.2241, pruned_loss=0.04496, over 4979.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03902, over 974206.42 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 15:03:02,004 INFO [train.py:715] (5/8) Epoch 6, batch 22400, loss[loss=0.1249, simple_loss=0.1969, pruned_loss=0.02643, over 4820.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03894, over 974175.20 frames.], batch size: 13, lr: 3.29e-04
2022-05-05 15:03:40,491 INFO [train.py:715] (5/8) Epoch 6, batch 22450, loss[loss=0.1629, simple_loss=0.2298, pruned_loss=0.04801, over 4940.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03907, over 974798.35 frames.], batch size: 23, lr: 3.28e-04
2022-05-05 15:04:19,439 INFO [train.py:715] (5/8) Epoch 6, batch 22500, loss[loss=0.1686, simple_loss=0.2574, pruned_loss=0.03989, over 4780.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.03962, over 973255.31 frames.], batch size: 14, lr: 3.28e-04
2022-05-05 15:04:58,758 INFO [train.py:715] (5/8) Epoch 6, batch 22550, loss[loss=0.1571, simple_loss=0.2271, pruned_loss=0.04352, over 4985.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03947, over 972428.62 frames.], batch size: 25, lr: 3.28e-04
2022-05-05 15:05:37,177 INFO [train.py:715] (5/8) Epoch 6, batch 22600, loss[loss=0.1609, simple_loss=0.2291, pruned_loss=0.0464, over 4859.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03955, over 973193.42 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:06:16,006 INFO [train.py:715] (5/8) Epoch 6, batch 22650, loss[loss=0.1446, simple_loss=0.2191, pruned_loss=0.03504, over 4861.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2208, pruned_loss=0.03914, over 973856.99 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:06:54,604 INFO [train.py:715] (5/8) Epoch 6, batch 22700, loss[loss=0.1717, simple_loss=0.2352, pruned_loss=0.05415, over 4819.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2209, pruned_loss=0.0387, over 972999.10 frames.], batch size: 27, lr: 3.28e-04
2022-05-05 15:07:33,405 INFO [train.py:715] (5/8) Epoch 6, batch 22750, loss[loss=0.1451, simple_loss=0.2179, pruned_loss=0.03617, over 4869.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2215, pruned_loss=0.03936, over 973049.46 frames.], batch size: 32, lr: 3.28e-04
2022-05-05 15:08:11,868 INFO [train.py:715] (5/8) Epoch 6, batch 22800, loss[loss=0.1584, simple_loss=0.2106, pruned_loss=0.05309, over 4881.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2224, pruned_loss=0.03993, over 972528.52 frames.], batch size: 16, lr: 3.28e-04
2022-05-05 15:08:50,376 INFO [train.py:715] (5/8) Epoch 6, batch 22850, loss[loss=0.1338, simple_loss=0.2037, pruned_loss=0.03193, over 4864.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2216, pruned_loss=0.03942, over 972366.83 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:09:29,028 INFO [train.py:715] (5/8) Epoch 6, batch 22900, loss[loss=0.1802, simple_loss=0.2418, pruned_loss=0.05934, over 4892.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03906, over 972147.23 frames.], batch size: 22, lr: 3.28e-04
2022-05-05 15:10:08,156 INFO [train.py:715] (5/8) Epoch 6, batch 22950, loss[loss=0.161, simple_loss=0.2193, pruned_loss=0.05134, over 4793.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03892, over 972501.89 frames.], batch size: 18, lr: 3.28e-04
2022-05-05 15:10:46,572 INFO [train.py:715] (5/8) Epoch 6, batch 23000, loss[loss=0.1253, simple_loss=0.2056, pruned_loss=0.02255, over 4894.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03894, over 973352.50 frames.], batch size: 19, lr: 3.28e-04
2022-05-05 15:11:25,826 INFO [train.py:715] (5/8) Epoch 6, batch 23050, loss[loss=0.1339, simple_loss=0.2122, pruned_loss=0.0278, over 4923.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2206, pruned_loss=0.03856, over 972766.16 frames.], batch size: 29, lr: 3.28e-04
2022-05-05 15:12:05,299 INFO [train.py:715] (5/8) Epoch 6, batch 23100, loss[loss=0.164, simple_loss=0.2372, pruned_loss=0.0454, over 4945.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2201, pruned_loss=0.0384, over 972775.19 frames.], batch size: 21, lr: 3.28e-04
2022-05-05 15:12:46,119 INFO [train.py:715] (5/8) Epoch 6, batch 23150, loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03086, over 4819.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2201, pruned_loss=0.03837, over 972458.56 frames.], batch size: 27, lr: 3.28e-04
2022-05-05 15:13:25,466 INFO [train.py:715] (5/8) Epoch 6, batch 23200, loss[loss=0.1582, simple_loss=0.2339, pruned_loss=0.04129, over 4776.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2201, pruned_loss=0.03819, over 971599.53 frames.], batch size: 18, lr: 3.28e-04
2022-05-05 15:14:04,866 INFO [train.py:715] (5/8) Epoch 6, batch 23250, loss[loss=0.1721, simple_loss=0.2403, pruned_loss=0.052, over 4835.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2203, pruned_loss=0.03848, over 971564.10 frames.], batch size: 15, lr: 3.28e-04
2022-05-05 15:14:43,524 INFO [train.py:715] (5/8) Epoch 6, batch 23300, loss[loss=0.1487, simple_loss=0.2139, pruned_loss=0.04172, over 4964.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03875, over 971599.02 frames.], batch size: 24, lr: 3.28e-04
2022-05-05 15:15:21,521 INFO [train.py:715] (5/8) Epoch 6, batch 23350, loss[loss=0.1376, simple_loss=0.2061, pruned_loss=0.03452, over 4816.00 frames.], tot_loss[loss=0.149, simple_loss=0.2202, pruned_loss=0.03893, over 972042.87 frames.], batch size: 25, lr: 3.28e-04
2022-05-05 15:16:00,567 INFO [train.py:715] (5/8) Epoch 6, batch 23400, loss[loss=0.142, simple_loss=0.2167, pruned_loss=0.0336, over 4952.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2199, pruned_loss=0.03872, over 971938.66 frames.], batch size: 35, lr: 3.28e-04
2022-05-05 15:16:40,146 INFO [train.py:715] (5/8) Epoch 6, batch 23450, loss[loss=0.1372, simple_loss=0.2076, pruned_loss=0.0334, over 4848.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03843, over 971928.10 frames.], batch size: 32, lr: 3.28e-04
2022-05-05 15:17:19,121 INFO [train.py:715] (5/8) Epoch 6, batch 23500, loss[loss=0.1745, simple_loss=0.2523, pruned_loss=0.04832, over 4829.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2195, pruned_loss=0.03791, over 972365.85 frames.], batch size: 15, lr: 3.28e-04
2022-05-05 15:17:58,301 INFO [train.py:715] (5/8) Epoch 6, batch 23550, loss[loss=0.1354, simple_loss=0.1934, pruned_loss=0.03866, over 4663.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03811, over 972375.42 frames.], batch size: 14, lr: 3.28e-04
2022-05-05 15:18:37,513 INFO [train.py:715] (5/8) Epoch 6, batch 23600, loss[loss=0.1809, simple_loss=0.2453, pruned_loss=0.05822, over 4865.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2201, pruned_loss=0.03868, over 971702.14 frames.], batch size: 16, lr: 3.28e-04
2022-05-05 15:19:16,253 INFO [train.py:715] (5/8) Epoch 6, batch 23650, loss[loss=0.1256, simple_loss=0.2126, pruned_loss=0.01925, over 4980.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.0387, over 971280.78 frames.], batch size: 24, lr: 3.28e-04
2022-05-05 15:19:54,389 INFO [train.py:715] (5/8) Epoch 6, batch 23700, loss[loss=0.1478, simple_loss=0.2265, pruned_loss=0.03455, over 4834.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2205, pruned_loss=0.03852, over 971895.79 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:20:33,413 INFO [train.py:715] (5/8) Epoch 6, batch 23750, loss[loss=0.1537, simple_loss=0.2221, pruned_loss=0.04264, over 4880.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03873, over 971504.25 frames.], batch size: 32, lr: 3.28e-04
2022-05-05 15:21:12,835 INFO [train.py:715] (5/8) Epoch 6, batch 23800, loss[loss=0.157, simple_loss=0.2284, pruned_loss=0.04276, over 4856.00 frames.], tot_loss[loss=0.149, simple_loss=0.2199, pruned_loss=0.03904, over 971591.12 frames.], batch size: 32, lr: 3.28e-04
2022-05-05 15:21:51,201 INFO [train.py:715] (5/8) Epoch 6, batch 23850, loss[loss=0.123, simple_loss=0.1984, pruned_loss=0.0238, over 4810.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03899, over 972907.65 frames.], batch size: 21, lr: 3.27e-04
2022-05-05 15:22:29,814 INFO [train.py:715] (5/8) Epoch 6, batch 23900, loss[loss=0.1349, simple_loss=0.2144, pruned_loss=0.02767, over 4877.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03869, over 972829.67 frames.], batch size: 22, lr: 3.27e-04
2022-05-05 15:23:08,544 INFO [train.py:715] (5/8) Epoch 6, batch 23950, loss[loss=0.127, simple_loss=0.202, pruned_loss=0.02595, over 4897.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03927, over 973695.36 frames.], batch size: 17, lr: 3.27e-04
2022-05-05 15:23:47,218 INFO [train.py:715] (5/8) Epoch 6, batch 24000, loss[loss=0.1404, simple_loss=0.2031, pruned_loss=0.03886, over 4822.00 frames.], tot_loss[loss=0.15, simple_loss=0.2208, pruned_loss=0.03958, over 973139.72 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:23:47,218 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 15:23:58,202 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01195, over 914524.00 frames.
2022-05-05 15:24:36,965 INFO [train.py:715] (5/8) Epoch 6, batch 24050, loss[loss=0.1677, simple_loss=0.2415, pruned_loss=0.04692, over 4931.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03962, over 972792.69 frames.], batch size: 23, lr: 3.27e-04
2022-05-05 15:25:15,030 INFO [train.py:715] (5/8) Epoch 6, batch 24100, loss[loss=0.1432, simple_loss=0.2168, pruned_loss=0.03476, over 4768.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2204, pruned_loss=0.03956, over 971668.66 frames.], batch size: 18, lr: 3.27e-04
2022-05-05 15:25:53,705 INFO [train.py:715] (5/8) Epoch 6, batch 24150, loss[loss=0.131, simple_loss=0.2074, pruned_loss=0.02733, over 4946.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.03899, over 971579.84 frames.], batch size: 21, lr: 3.27e-04
2022-05-05 15:26:32,798 INFO [train.py:715] (5/8) Epoch 6, batch 24200, loss[loss=0.1175, simple_loss=0.1885, pruned_loss=0.02327, over 4802.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03862, over 971538.45 frames.], batch size: 24, lr: 3.27e-04
2022-05-05 15:27:10,718 INFO [train.py:715] (5/8) Epoch 6, batch 24250, loss[loss=0.1355, simple_loss=0.2035, pruned_loss=0.03374, over 4843.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2189, pruned_loss=0.03846, over 971721.60 frames.], batch size: 32, lr: 3.27e-04
2022-05-05 15:27:49,114 INFO [train.py:715] (5/8) Epoch 6, batch 24300, loss[loss=0.1691, simple_loss=0.2339, pruned_loss=0.05214, over 4872.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03851, over 972960.23 frames.], batch size: 30, lr: 3.27e-04
2022-05-05 15:28:28,042 INFO [train.py:715] (5/8) Epoch 6, batch 24350, loss[loss=0.1679, simple_loss=0.2386, pruned_loss=0.04855, over 4960.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03858, over 973391.83 frames.], batch size: 21, lr: 3.27e-04
2022-05-05 15:29:07,159 INFO [train.py:715] (5/8) Epoch 6, batch 24400, loss[loss=0.1338, simple_loss=0.2002, pruned_loss=0.03369, over 4956.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03801, over 972726.47 frames.], batch size: 35, lr: 3.27e-04
2022-05-05 15:29:45,508 INFO [train.py:715] (5/8) Epoch 6, batch 24450, loss[loss=0.1497, simple_loss=0.2229, pruned_loss=0.03823, over 4965.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03813, over 973447.04 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:30:24,118 INFO [train.py:715] (5/8) Epoch 6, batch 24500, loss[loss=0.1549, simple_loss=0.221, pruned_loss=0.04442, over 4872.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2188, pruned_loss=0.03805, over 972531.14 frames.], batch size: 32, lr: 3.27e-04
2022-05-05 15:31:03,937 INFO [train.py:715] (5/8) Epoch 6, batch 24550, loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02974, over 4960.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2181, pruned_loss=0.038, over 971864.28 frames.], batch size: 35, lr: 3.27e-04
2022-05-05 15:31:42,160 INFO [train.py:715] (5/8) Epoch 6, batch 24600, loss[loss=0.102, simple_loss=0.1651, pruned_loss=0.0195, over 4993.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2184, pruned_loss=0.03807, over 971567.96 frames.], batch size: 14, lr: 3.27e-04
2022-05-05 15:32:21,360 INFO [train.py:715] (5/8) Epoch 6, batch 24650, loss[loss=0.1672, simple_loss=0.2346, pruned_loss=0.04989, over 4822.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.03827, over 971441.10 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:33:00,612 INFO [train.py:715] (5/8) Epoch 6, batch 24700, loss[loss=0.1389, simple_loss=0.214, pruned_loss=0.03192, over 4790.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.03795, over 972334.05 frames.], batch size: 12, lr: 3.27e-04
2022-05-05 15:33:39,473 INFO [train.py:715] (5/8) Epoch 6, batch 24750, loss[loss=0.1567, simple_loss=0.2306, pruned_loss=0.04141, over 4985.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.0385, over 972784.02 frames.], batch size: 16, lr: 3.27e-04
2022-05-05 15:34:17,834 INFO [train.py:715] (5/8) Epoch 6, batch 24800, loss[loss=0.1424, simple_loss=0.2104, pruned_loss=0.03725, over 4981.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.0378, over 974118.41 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:34:56,837 INFO [train.py:715] (5/8) Epoch 6, batch 24850, loss[loss=0.1512, simple_loss=0.2275, pruned_loss=0.03751, over 4962.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2203, pruned_loss=0.03821, over 973874.66 frames.], batch size: 39, lr: 3.27e-04
2022-05-05 15:35:36,647 INFO [train.py:715] (5/8) Epoch 6, batch 24900, loss[loss=0.1585, simple_loss=0.2395, pruned_loss=0.03873, over 4794.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2189, pruned_loss=0.03741, over 972997.36 frames.], batch size: 14, lr: 3.27e-04
2022-05-05 15:36:14,918 INFO [train.py:715] (5/8) Epoch 6, batch 24950, loss[loss=0.1178, simple_loss=0.192, pruned_loss=0.02177, over 4856.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2187, pruned_loss=0.03738, over 973092.42 frames.], batch size: 13, lr: 3.27e-04
2022-05-05 15:36:53,555 INFO [train.py:715] (5/8) Epoch 6, batch 25000, loss[loss=0.1424, simple_loss=0.2181, pruned_loss=0.03331, over 4955.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2195, pruned_loss=0.03768, over 973579.51 frames.], batch size: 29, lr: 3.27e-04
2022-05-05 15:37:32,636 INFO [train.py:715] (5/8) Epoch 6, batch 25050, loss[loss=0.1439, simple_loss=0.223, pruned_loss=0.03238, over 4960.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2189, pruned_loss=0.0372, over 972706.23 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:38:11,570 INFO [train.py:715] (5/8) Epoch 6, batch 25100, loss[loss=0.1236, simple_loss=0.1971, pruned_loss=0.02505, over 4888.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03794, over 972494.48 frames.], batch size: 22, lr: 3.27e-04
2022-05-05 15:38:50,094 INFO [train.py:715] (5/8) Epoch 6, batch 25150, loss[loss=0.1526, simple_loss=0.2163, pruned_loss=0.04438, over 4827.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03838, over 972570.53 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:39:28,931 INFO [train.py:715] (5/8) Epoch 6, batch 25200, loss[loss=0.1443, simple_loss=0.2214, pruned_loss=0.03355, over 4773.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.0383, over 971904.25 frames.], batch size: 12, lr: 3.27e-04
2022-05-05 15:40:07,779 INFO [train.py:715] (5/8) Epoch 6, batch 25250, loss[loss=0.1452, simple_loss=0.2083, pruned_loss=0.04101, over 4826.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03816, over 971461.35 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:40:46,084 INFO [train.py:715] (5/8) Epoch 6, batch 25300, loss[loss=0.1608, simple_loss=0.2193, pruned_loss=0.05116, over 4869.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03831, over 970513.35 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:41:24,367 INFO [train.py:715] (5/8) Epoch 6, batch 25350, loss[loss=0.1415, simple_loss=0.2208, pruned_loss=0.03109, over 4857.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03829, over 971457.95 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:42:03,174 INFO [train.py:715] (5/8) Epoch 6, batch 25400, loss[loss=0.1547, simple_loss=0.2354, pruned_loss=0.03704, over 4764.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03825, over 971214.13 frames.], batch size: 17, lr: 3.26e-04
2022-05-05 15:42:41,994 INFO [train.py:715] (5/8) Epoch 6, batch 25450, loss[loss=0.1365, simple_loss=0.2177, pruned_loss=0.02769, over 4897.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03833, over 972204.00 frames.], batch size: 17, lr: 3.26e-04
2022-05-05 15:43:20,090 INFO [train.py:715] (5/8) Epoch 6, batch 25500, loss[loss=0.1545, simple_loss=0.2252, pruned_loss=0.04192, over 4884.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03831, over 972609.33 frames.], batch size: 16, lr: 3.26e-04
2022-05-05 15:43:58,582 INFO [train.py:715] (5/8) Epoch 6, batch 25550, loss[loss=0.1529, simple_loss=0.2193, pruned_loss=0.04321, over 4750.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.0386, over 972106.22 frames.], batch size: 19, lr: 3.26e-04
2022-05-05 15:44:37,703 INFO [train.py:715] (5/8) Epoch 6, batch 25600, loss[loss=0.1561, simple_loss=0.2297, pruned_loss=0.04128, over 4969.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03841, over 971859.98 frames.], batch size: 14, lr: 3.26e-04
2022-05-05 15:45:15,936 INFO [train.py:715] (5/8) Epoch 6, batch 25650, loss[loss=0.1617, simple_loss=0.2307, pruned_loss=0.04633, over 4892.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03854, over 971529.71 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:45:54,739 INFO [train.py:715] (5/8) Epoch 6, batch 25700, loss[loss=0.1574, simple_loss=0.2229, pruned_loss=0.04599, over 4819.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03827, over 970194.10 frames.], batch size: 25, lr: 3.26e-04
2022-05-05 15:46:34,044 INFO [train.py:715] (5/8) Epoch 6, batch 25750, loss[loss=0.1509, simple_loss=0.2285, pruned_loss=0.03663, over 4812.00 frames.], tot_loss[loss=0.1478, simple_loss=0.219, pruned_loss=0.03824, over 970264.64 frames.], batch size: 25, lr: 3.26e-04
2022-05-05 15:47:12,319 INFO [train.py:715] (5/8) Epoch 6, batch 25800, loss[loss=0.1274, simple_loss=0.2085, pruned_loss=0.02316, over 4829.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03781, over 970864.36 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:47:50,576 INFO [train.py:715] (5/8) Epoch 6, batch 25850, loss[loss=0.1746, simple_loss=0.2462, pruned_loss=0.05152, over 4802.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03793, over 971290.54 frames.], batch size: 21, lr: 3.26e-04
2022-05-05 15:48:29,220 INFO [train.py:715] (5/8) Epoch 6, batch 25900, loss[loss=0.1538, simple_loss=0.2273, pruned_loss=0.04013, over 4749.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03781, over 972254.66 frames.], batch size: 16, lr: 3.26e-04
2022-05-05 15:49:08,367 INFO [train.py:715] (5/8) Epoch 6, batch 25950, loss[loss=0.1542, simple_loss=0.2287, pruned_loss=0.03985, over 4770.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03799, over 972340.36 frames.], batch size: 18, lr: 3.26e-04
2022-05-05 15:49:46,039 INFO [train.py:715] (5/8) Epoch 6, batch 26000, loss[loss=0.1706, simple_loss=0.2358, pruned_loss=0.0527, over 4696.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.03835, over 972924.90 frames.], batch size: 15, lr: 3.26e-04
2022-05-05 15:50:24,228 INFO [train.py:715] (5/8) Epoch 6, batch 26050, loss[loss=0.1605, simple_loss=0.2304, pruned_loss=0.04531, over 4824.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03843, over 972189.86 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:51:03,219 INFO [train.py:715] (5/8) Epoch 6, batch 26100, loss[loss=0.1331, simple_loss=0.2011, pruned_loss=0.03257, over 4920.00 frames.], tot_loss[loss=0.1472, simple_loss=0.218, pruned_loss=0.03814, over 971924.06 frames.], batch size: 18, lr: 3.26e-04
2022-05-05 15:51:41,622 INFO [train.py:715] (5/8) Epoch 6, batch 26150, loss[loss=0.1216, simple_loss=0.2001, pruned_loss=0.02155, over 4867.00 frames.], tot_loss[loss=0.147, simple_loss=0.2179, pruned_loss=0.03806, over 972664.24 frames.], batch size: 22, lr: 3.26e-04
2022-05-05 15:52:20,122 INFO [train.py:715] (5/8) Epoch 6, batch 26200, loss[loss=0.17, simple_loss=0.2235, pruned_loss=0.05822, over 4814.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2179, pruned_loss=0.03817, over 972471.01 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:52:58,596 INFO [train.py:715] (5/8) Epoch 6, batch 26250, loss[loss=0.1543, simple_loss=0.2222, pruned_loss=0.04325, over 4871.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2184, pruned_loss=0.03804, over 971902.64 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:53:37,251 INFO [train.py:715] (5/8) Epoch 6, batch 26300, loss[loss=0.128, simple_loss=0.198, pruned_loss=0.02902, over 4747.00 frames.], tot_loss[loss=0.1477, simple_loss=0.219, pruned_loss=0.03821, over 971767.55 frames.], batch size: 16, lr: 3.26e-04
2022-05-05 15:54:15,324 INFO [train.py:715] (5/8) Epoch 6, batch 26350, loss[loss=0.1704, simple_loss=0.2425, pruned_loss=0.04911, over 4965.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03851, over 970196.76 frames.], batch size: 39, lr: 3.26e-04
2022-05-05 15:54:53,793 INFO [train.py:715] (5/8) Epoch 6, batch 26400, loss[loss=0.1375, simple_loss=0.2141, pruned_loss=0.03038, over 4965.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03886, over 970955.12 frames.], batch size: 24, lr: 3.26e-04
2022-05-05 15:55:33,107 INFO [train.py:715] (5/8) Epoch 6, batch 26450, loss[loss=0.1662, simple_loss=0.219, pruned_loss=0.05676, over 4780.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03873, over 971651.22 frames.], batch size: 14, lr: 3.26e-04
2022-05-05 15:56:11,693 INFO [train.py:715] (5/8) Epoch 6, batch 26500, loss[loss=0.1331, simple_loss=0.2111, pruned_loss=0.02753, over 4895.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2201, pruned_loss=0.03881, over 971769.07 frames.], batch size: 22, lr: 3.26e-04
2022-05-05 15:56:50,069 INFO [train.py:715] (5/8) Epoch 6, batch 26550, loss[loss=0.1303, simple_loss=0.195, pruned_loss=0.03281, over 4830.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2185, pruned_loss=0.03822, over 972025.41 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:57:28,900 INFO [train.py:715] (5/8) Epoch 6, batch 26600, loss[loss=0.1741, simple_loss=0.2455, pruned_loss=0.05134, over 4906.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2194, pruned_loss=0.03884, over 973356.27 frames.], batch size: 17, lr: 3.26e-04
2022-05-05 15:58:07,540 INFO [train.py:715] (5/8) Epoch 6, batch 26650, loss[loss=0.1473, simple_loss=0.2167, pruned_loss=0.03899, over 4809.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2191, pruned_loss=0.03875, over 973909.47 frames.], batch size: 21, lr: 3.26e-04
2022-05-05 15:58:46,268 INFO [train.py:715] (5/8) Epoch 6, batch 26700, loss[loss=0.1463, simple_loss=0.2239, pruned_loss=0.03439, over 4928.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2196, pruned_loss=0.03891, over 974319.15 frames.], batch size: 23, lr: 3.25e-04
2022-05-05 15:59:24,554 INFO [train.py:715] (5/8) Epoch 6, batch 26750, loss[loss=0.1394, simple_loss=0.2103, pruned_loss=0.03429, over 4800.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03887, over 973441.58 frames.], batch size: 14, lr: 3.25e-04
2022-05-05 16:00:03,783 INFO [train.py:715] (5/8) Epoch 6, batch 26800, loss[loss=0.1497, simple_loss=0.2255, pruned_loss=0.03698, over 4822.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03867, over 973091.13 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 16:00:41,899 INFO [train.py:715] (5/8) Epoch 6, batch 26850, loss[loss=0.1467, simple_loss=0.2199, pruned_loss=0.03675, over 4740.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03838, over 973713.88 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:01:20,552 INFO [train.py:715] (5/8) Epoch 6, batch 26900, loss[loss=0.1337, simple_loss=0.2038, pruned_loss=0.03176, over 4944.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03785, over 973289.82 frames.], batch size: 29, lr: 3.25e-04
2022-05-05 16:01:59,792 INFO [train.py:715] (5/8) Epoch 6, batch 26950, loss[loss=0.1497, simple_loss=0.2202, pruned_loss=0.03962, over 4929.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03823, over 972372.71 frames.], batch size: 17, lr: 3.25e-04
2022-05-05 16:02:39,038 INFO [train.py:715] (5/8) Epoch 6, batch 27000, loss[loss=0.1519, simple_loss=0.2283, pruned_loss=0.03774, over 4804.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2196, pruned_loss=0.03845, over 972225.66 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:02:39,038 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 16:02:48,795 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.01188, over 914524.00 frames.
2022-05-05 16:03:28,074 INFO [train.py:715] (5/8) Epoch 6, batch 27050, loss[loss=0.1406, simple_loss=0.2158, pruned_loss=0.03263, over 4820.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03809, over 972783.06 frames.], batch size: 26, lr: 3.25e-04
2022-05-05 16:04:06,805 INFO [train.py:715] (5/8) Epoch 6, batch 27100, loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03323, over 4753.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03832, over 973220.36 frames.], batch size: 19, lr: 3.25e-04
2022-05-05 16:04:45,440 INFO [train.py:715] (5/8) Epoch 6, batch 27150, loss[loss=0.1219, simple_loss=0.195, pruned_loss=0.0244, over 4926.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.0387, over 973710.97 frames.], batch size: 29, lr: 3.25e-04
2022-05-05 16:05:25,175 INFO [train.py:715] (5/8) Epoch 6, batch 27200, loss[loss=0.1559, simple_loss=0.2186, pruned_loss=0.04656, over 4755.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03879, over 973565.59 frames.], batch size: 19, lr: 3.25e-04
2022-05-05 16:06:03,411 INFO [train.py:715] (5/8) Epoch 6, batch 27250, loss[loss=0.1431, simple_loss=0.2084, pruned_loss=0.03885, over 4821.00 frames.], tot_loss[loss=0.149, simple_loss=0.2199, pruned_loss=0.03906, over 973285.41 frames.], batch size: 13, lr: 3.25e-04
2022-05-05 16:06:43,062 INFO [train.py:715] (5/8) Epoch 6, batch 27300, loss[loss=0.1357, simple_loss=0.2085, pruned_loss=0.03146, over 4804.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03861, over 973257.14 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:07:22,054 INFO [train.py:715] (5/8) Epoch 6, batch 27350, loss[loss=0.1723, simple_loss=0.2436, pruned_loss=0.05054, over 4836.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2195, pruned_loss=0.03909, over 973648.47 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 16:08:01,164 INFO [train.py:715] (5/8) Epoch 6, batch 27400, loss[loss=0.1228, simple_loss=0.1958, pruned_loss=0.02495, over 4834.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2195, pruned_loss=0.03884, over 973170.07 frames.], batch size: 26, lr: 3.25e-04
2022-05-05 16:08:39,771 INFO [train.py:715] (5/8) Epoch 6, batch 27450, loss[loss=0.1733, simple_loss=0.2481, pruned_loss=0.04925, over 4880.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03843, over 972573.15 frames.], batch size: 39, lr: 3.25e-04
2022-05-05 16:09:18,812 INFO [train.py:715] (5/8) Epoch 6, batch 27500, loss[loss=0.1451, simple_loss=0.2272, pruned_loss=0.03148, over 4926.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2195, pruned_loss=0.03839, over 972538.99 frames.], batch size: 23, lr: 3.25e-04
2022-05-05 16:09:58,186 INFO [train.py:715] (5/8) Epoch 6, batch 27550, loss[loss=0.1716, simple_loss=0.2497, pruned_loss=0.04671, over 4906.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2205, pruned_loss=0.03871, over 972605.51 frames.], batch size: 19, lr: 3.25e-04
2022-05-05 16:10:36,911 INFO [train.py:715] (5/8) Epoch 6, batch 27600, loss[loss=0.1361, simple_loss=0.2006, pruned_loss=0.03577, over 4788.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03786, over 971849.76 frames.], batch size: 18, lr: 3.25e-04
2022-05-05 16:11:15,425 INFO [train.py:715] (5/8) Epoch 6, batch 27650, loss[loss=0.1717, simple_loss=0.2441, pruned_loss=0.04963, over 4943.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03799, over 972159.47 frames.], batch size: 39, lr: 3.25e-04
2022-05-05 16:11:54,437 INFO [train.py:715] (5/8) Epoch 6, batch 27700, loss[loss=0.1361, simple_loss=0.2112, pruned_loss=0.03051, over 4905.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2195, pruned_loss=0.03835, over 971539.45 frames.], batch size: 19, lr: 3.25e-04
2022-05-05 16:12:32,980 INFO [train.py:715] (5/8) Epoch 6, batch 27750, loss[loss=0.1482, simple_loss=0.2133, pruned_loss=0.04152, over 4744.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03813, over 972671.80 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:13:12,186 INFO [train.py:715] (5/8) Epoch 6, batch 27800, loss[loss=0.1508, simple_loss=0.2279, pruned_loss=0.03682, over 4739.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03848, over 972140.07 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:13:51,238 INFO [train.py:715] (5/8) Epoch 6, batch 27850, loss[loss=0.1363, simple_loss=0.2089, pruned_loss=0.03182, over 4770.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03885, over 972789.25 frames.], batch size: 14, lr: 3.25e-04
2022-05-05 16:14:30,896 INFO [train.py:715] (5/8) Epoch 6, batch 27900, loss[loss=0.1176, simple_loss=0.1926, pruned_loss=0.0213, over 4970.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03837, over 973257.48 frames.], batch size: 35, lr: 3.25e-04
2022-05-05 16:15:09,372 INFO [train.py:715] (5/8) Epoch 6, batch 27950, loss[loss=0.1752, simple_loss=0.2426, pruned_loss=0.05392, over 4806.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03865, over 972468.38 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:15:48,252 INFO [train.py:715] (5/8) Epoch 6, batch 28000, loss[loss=0.1368, simple_loss=0.2071, pruned_loss=0.03322, over 4765.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03854, over 972274.49 frames.], batch size: 14, lr: 3.25e-04
2022-05-05 16:16:27,393 INFO [train.py:715] (5/8) Epoch 6, batch 28050, loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03115, over 4811.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03853, over 972473.03 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:17:06,024 INFO [train.py:715] (5/8) Epoch 6, batch 28100, loss[loss=0.1523, simple_loss=0.226, pruned_loss=0.03926, over 4830.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03889, over 971585.41 frames.], batch size: 12, lr: 3.25e-04
2022-05-05 16:17:44,948 INFO [train.py:715] (5/8) Epoch 6, batch 28150, loss[loss=0.1401, simple_loss=0.2053, pruned_loss=0.0375, over 4982.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03824, over 972973.41 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:18:24,088 INFO [train.py:715] (5/8) Epoch 6, batch 28200, loss[loss=0.1732, simple_loss=0.2377, pruned_loss=0.05435, over 4978.00 frames.], tot_loss[loss=0.1484, simple_loss=0.22, pruned_loss=0.03837, over 973186.72 frames.], batch size: 28, lr: 3.24e-04
2022-05-05 16:19:03,410 INFO [train.py:715] (5/8) Epoch 6, batch 28250, loss[loss=0.1365, simple_loss=0.2151, pruned_loss=0.02894, over 4878.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03842, over 972896.36 frames.], batch size: 22, lr: 3.24e-04
2022-05-05 16:19:41,789 INFO [train.py:715] (5/8) Epoch 6, batch 28300, loss[loss=0.1565, simple_loss=0.2136, pruned_loss=0.04967, over 4910.00 frames.], tot_loss[loss=0.148, simple_loss=0.2197, pruned_loss=0.03817, over 973022.98 frames.], batch size: 17, lr: 3.24e-04
2022-05-05 16:20:20,027 INFO [train.py:715] (5/8) Epoch 6, batch 28350, loss[loss=0.1488, simple_loss=0.2292, pruned_loss=0.03416, over 4938.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2201, pruned_loss=0.03836, over 972697.79 frames.], batch size: 29, lr: 3.24e-04
2022-05-05 16:20:59,872 INFO [train.py:715] (5/8) Epoch 6, batch 28400, loss[loss=0.1391, simple_loss=0.2235, pruned_loss=0.02739, over 4940.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2204, pruned_loss=0.03858, over 973064.33 frames.], batch size: 29, lr: 3.24e-04
2022-05-05 16:21:38,666 INFO [train.py:715] (5/8) Epoch 6, batch 28450, loss[loss=0.1671, simple_loss=0.2238, pruned_loss=0.05523, over 4978.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03892, over 972533.80 frames.], batch size: 35, lr: 3.24e-04
2022-05-05 16:22:17,506 INFO [train.py:715] (5/8) Epoch 6, batch 28500, loss[loss=0.1519, simple_loss=0.236, pruned_loss=0.03385, over 4919.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03888, over 972445.45 frames.], batch size: 23, lr: 3.24e-04
2022-05-05 16:22:56,650 INFO [train.py:715] (5/8) Epoch 6, batch 28550, loss[loss=0.1452, simple_loss=0.2224, pruned_loss=0.03402, over 4989.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2204, pruned_loss=0.03855, over 972388.82 frames.], batch size: 26, lr: 3.24e-04
2022-05-05 16:23:36,111 INFO [train.py:715] (5/8) Epoch 6, batch 28600, loss[loss=0.1053, simple_loss=0.172, pruned_loss=0.01934, over 4847.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2201, pruned_loss=0.03805, over 972349.52 frames.], batch size: 12, lr: 3.24e-04
2022-05-05 16:24:14,189 INFO [train.py:715] (5/8) Epoch 6, batch 28650, loss[loss=0.1318, simple_loss=0.2047, pruned_loss=0.02948, over 4893.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2203, pruned_loss=0.03833, over 972253.40 frames.], batch size: 19, lr: 3.24e-04
2022-05-05 16:24:52,990 INFO [train.py:715] (5/8) Epoch 6, batch 28700, loss[loss=0.1423, simple_loss=0.2154, pruned_loss=0.03456, over 4974.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2203, pruned_loss=0.03816, over 972322.24 frames.], batch size: 28, lr: 3.24e-04
2022-05-05 16:25:32,173 INFO [train.py:715] (5/8) Epoch 6, batch 28750, loss[loss=0.1614, simple_loss=0.2169, pruned_loss=0.05295, over 4775.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2202, pruned_loss=0.03823, over 972598.92 frames.], batch size: 17, lr: 3.24e-04
2022-05-05 16:26:10,896 INFO [train.py:715] (5/8) Epoch 6, batch 28800, loss[loss=0.1884, simple_loss=0.2749, pruned_loss=0.05095, over 4830.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2215, pruned_loss=0.03846, over 973265.04 frames.], batch size: 27, lr: 3.24e-04
2022-05-05 16:26:49,767 INFO [train.py:715] (5/8) Epoch 6, batch 28850, loss[loss=0.1535, simple_loss=0.2224, pruned_loss=0.04226, over 4843.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2208, pruned_loss=0.03821, over 973103.54 frames.], batch size: 30, lr: 3.24e-04
2022-05-05 16:27:28,067 INFO [train.py:715] (5/8) Epoch 6, batch 28900, loss[loss=0.1634, simple_loss=0.2272, pruned_loss=0.04977, over 4988.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2205, pruned_loss=0.03797, over 973607.03 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:28:07,514 INFO [train.py:715] (5/8) Epoch 6, batch 28950, loss[loss=0.1455, simple_loss=0.2125, pruned_loss=0.03931, over 4922.00 frames.], tot_loss[loss=0.148, simple_loss=0.22, pruned_loss=0.03801, over 973662.33 frames.], batch size: 29, lr: 3.24e-04
2022-05-05 16:28:45,748 INFO [train.py:715] (5/8) Epoch 6, batch 29000, loss[loss=0.132, simple_loss=0.2134, pruned_loss=0.02533, over 4895.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2201, pruned_loss=0.03827, over 973891.09 frames.], batch size: 22, lr: 3.24e-04
2022-05-05 16:29:23,902 INFO [train.py:715] (5/8) Epoch 6, batch 29050, loss[loss=0.1622, simple_loss=0.222, pruned_loss=0.05123, over 4926.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2207, pruned_loss=0.0388, over 974289.58 frames.], batch size: 18, lr: 3.24e-04
2022-05-05 16:30:02,951 INFO [train.py:715] (5/8) Epoch 6, batch 29100, loss[loss=0.1383, simple_loss=0.2172, pruned_loss=0.0297, over 4837.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2201, pruned_loss=0.0387, over 973901.80 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:30:41,836 INFO [train.py:715] (5/8) Epoch 6, batch 29150, loss[loss=0.1902, simple_loss=0.2524, pruned_loss=0.06403, over 4787.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03909, over 973748.74 frames.], batch size: 14, lr: 3.24e-04
2022-05-05 16:31:20,669 INFO [train.py:715] (5/8) Epoch 6, batch 29200, loss[loss=0.1837, simple_loss=0.2594, pruned_loss=0.05407, over 4933.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03926, over 972699.19 frames.], batch size: 23, lr: 3.24e-04
2022-05-05 16:31:59,885 INFO [train.py:715] (5/8) Epoch 6, batch 29250, loss[loss=0.1402, simple_loss=0.211, pruned_loss=0.03464, over 4774.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03891, over 973126.93 frames.], batch size: 12, lr: 3.24e-04
2022-05-05 16:32:39,921 INFO [train.py:715] (5/8) Epoch 6, batch 29300, loss[loss=0.1278, simple_loss=0.2092, pruned_loss=0.02317, over 4986.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03887, over 973327.84 frames.], batch size: 27, lr: 3.24e-04
2022-05-05 16:33:18,205 INFO [train.py:715] (5/8) Epoch 6, batch 29350, loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.04065, over 4922.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03858, over 973545.17 frames.], batch size: 23, lr: 3.24e-04
2022-05-05 16:33:57,192 INFO [train.py:715] (5/8) Epoch 6, batch 29400, loss[loss=0.1654, simple_loss=0.2423, pruned_loss=0.0443, over 4807.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.03922, over 973116.26 frames.], batch size: 26, lr: 3.24e-04
2022-05-05 16:34:36,595 INFO [train.py:715] (5/8) Epoch 6, batch 29450, loss[loss=0.1536, simple_loss=0.221, pruned_loss=0.04316, over 4914.00 frames.], tot_loss[loss=0.15, simple_loss=0.2208, pruned_loss=0.03962, over 972422.69 frames.], batch size: 29, lr: 3.24e-04
2022-05-05 16:35:15,803 INFO [train.py:715] (5/8) Epoch 6, batch 29500, loss[loss=0.1691, simple_loss=0.2307, pruned_loss=0.05374, over 4880.00 frames.], tot_loss[loss=0.1491, simple_loss=0.22, pruned_loss=0.03915, over 972618.38 frames.], batch size: 16, lr: 3.24e-04
2022-05-05 16:35:53,790 INFO [train.py:715] (5/8) Epoch 6, batch 29550, loss[loss=0.171, simple_loss=0.249, pruned_loss=0.04651, over 4757.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.0378, over 972898.89 frames.], batch size: 16, lr: 3.24e-04
2022-05-05 16:36:33,142 INFO [train.py:715] (5/8) Epoch 6, batch 29600, loss[loss=0.1544, simple_loss=0.2303, pruned_loss=0.03925, over 4891.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.03769, over 972571.53 frames.], batch size: 19, lr: 3.24e-04
2022-05-05 16:37:12,530 INFO [train.py:715] (5/8) Epoch 6, batch 29650, loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02909, over 4836.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03791, over 971971.43 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:37:51,065 INFO [train.py:715] (5/8) Epoch 6, batch 29700, loss[loss=0.1389, simple_loss=0.2074, pruned_loss=0.03515, over 4924.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03811, over 972671.13 frames.], batch size: 23, lr: 3.23e-04
2022-05-05 16:38:29,762 INFO [train.py:715] (5/8) Epoch 6, batch 29750, loss[loss=0.1294, simple_loss=0.2078, pruned_loss=0.02553, over 4918.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03812, over 972494.84 frames.], batch size: 23, lr: 3.23e-04
2022-05-05 16:39:08,775 INFO [train.py:715] (5/8) Epoch 6, batch 29800, loss[loss=0.1352, simple_loss=0.2035, pruned_loss=0.03341, over 4953.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03737, over 972671.74 frames.], batch size: 21, lr: 3.23e-04
2022-05-05 16:39:48,203 INFO [train.py:715] (5/8) Epoch 6, batch 29850, loss[loss=0.157, simple_loss=0.2245, pruned_loss=0.04473, over 4788.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2186, pruned_loss=0.03806, over 973185.20 frames.], batch size: 17, lr: 3.23e-04
2022-05-05 16:40:26,713 INFO [train.py:715] (5/8) Epoch 6, batch 29900, loss[loss=0.1275, simple_loss=0.1984, pruned_loss=0.02834, over 4880.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03817, over 973044.86 frames.], batch size: 16, lr: 3.23e-04
2022-05-05 16:41:05,700 INFO [train.py:715] (5/8) Epoch 6, batch 29950, loss[loss=0.1638, simple_loss=0.2366, pruned_loss=0.04548, over 4758.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03787, over 973121.68 frames.], batch size: 19, lr: 3.23e-04
2022-05-05 16:41:45,053 INFO [train.py:715] (5/8) Epoch 6, batch 30000, loss[loss=0.1379, simple_loss=0.2183, pruned_loss=0.02873, over 4831.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03768, over 972865.58 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:41:45,053 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 16:41:54,714 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.0119, over 914524.00 frames.
2022-05-05 16:42:34,423 INFO [train.py:715] (5/8) Epoch 6, batch 30050, loss[loss=0.1605, simple_loss=0.2378, pruned_loss=0.04158, over 4992.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2195, pruned_loss=0.03791, over 973509.08 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:43:12,813 INFO [train.py:715] (5/8) Epoch 6, batch 30100, loss[loss=0.1276, simple_loss=0.2012, pruned_loss=0.02701, over 4868.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2198, pruned_loss=0.03794, over 972774.98 frames.], batch size: 20, lr: 3.23e-04
2022-05-05 16:43:51,566 INFO [train.py:715] (5/8) Epoch 6, batch 30150, loss[loss=0.1612, simple_loss=0.2383, pruned_loss=0.04202, over 4811.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03854, over 971603.16 frames.], batch size: 25, lr: 3.23e-04
2022-05-05 16:44:30,965 INFO [train.py:715] (5/8) Epoch 6, batch 30200, loss[loss=0.1608, simple_loss=0.2222, pruned_loss=0.04969, over 4942.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2204, pruned_loss=0.03885, over 971868.16 frames.], batch size: 29, lr: 3.23e-04
2022-05-05 16:45:10,342 INFO [train.py:715] (5/8) Epoch 6, batch 30250, loss[loss=0.1217, simple_loss=0.1964, pruned_loss=0.02348, over 4826.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03892, over 972573.39 frames.], batch size: 12, lr: 3.23e-04
2022-05-05 16:45:48,512 INFO [train.py:715] (5/8) Epoch 6, batch 30300, loss[loss=0.1637, simple_loss=0.2331, pruned_loss=0.04712, over 4985.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03872, over 972516.13 frames.], batch size: 20, lr: 3.23e-04
2022-05-05 16:46:27,515 INFO [train.py:715] (5/8) Epoch 6, batch 30350, loss[loss=0.1527, simple_loss=0.2239, pruned_loss=0.04077, over 4774.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03913, over 971957.01 frames.], batch size: 17, lr: 3.23e-04
2022-05-05 16:47:06,585 INFO [train.py:715] (5/8) Epoch 6, batch 30400, loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03729, over 4926.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03903, over 971829.02 frames.], batch size: 23, lr: 3.23e-04
2022-05-05 16:47:45,261 INFO [train.py:715] (5/8) Epoch 6, batch 30450, loss[loss=0.1266, simple_loss=0.201, pruned_loss=0.0261, over 4753.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03789, over 972263.53 frames.], batch size: 19, lr: 3.23e-04
2022-05-05 16:48:23,949 INFO [train.py:715] (5/8) Epoch 6, batch 30500, loss[loss=0.1312, simple_loss=0.2008, pruned_loss=0.03076, over 4702.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03876, over 972467.48 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:49:02,695 INFO [train.py:715] (5/8) Epoch 6, batch 30550, loss[loss=0.1335, simple_loss=0.2135, pruned_loss=0.02676, over 4814.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03824, over 972078.18 frames.], batch size: 14, lr: 3.23e-04
2022-05-05 16:49:41,851 INFO [train.py:715] (5/8) Epoch 6, batch 30600, loss[loss=0.1307, simple_loss=0.2117, pruned_loss=0.02487, over 4862.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03792, over 971999.47 frames.], batch size: 20, lr: 3.23e-04
2022-05-05 16:50:20,376 INFO [train.py:715] (5/8) Epoch 6, batch 30650, loss[loss=0.2103, simple_loss=0.2885, pruned_loss=0.06608, over 4985.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03809, over 971908.39 frames.], batch size: 28, lr: 3.23e-04
2022-05-05 16:50:59,233 INFO [train.py:715] (5/8) Epoch 6, batch 30700, loss[loss=0.203, simple_loss=0.2655, pruned_loss=0.07021, over 4850.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03811, over 972222.13 frames.], batch size: 34, lr: 3.23e-04
2022-05-05 16:51:38,189 INFO [train.py:715] (5/8) Epoch 6, batch 30750, loss[loss=0.1341, simple_loss=0.2114, pruned_loss=0.02843, over 4832.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03825, over 972147.44 frames.], batch size: 30, lr: 3.23e-04
2022-05-05 16:52:17,034 INFO [train.py:715] (5/8) Epoch 6, batch 30800, loss[loss=0.1473, simple_loss=0.2251, pruned_loss=0.03478, over 4896.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03786, over 972034.15 frames.], batch size: 17, lr: 3.23e-04
2022-05-05 16:52:55,438 INFO [train.py:715] (5/8) Epoch 6, batch 30850, loss[loss=0.1292, simple_loss=0.2057, pruned_loss=0.02631, over 4816.00 frames.], tot_loss[loss=0.1466, simple_loss=0.218, pruned_loss=0.0376, over 972209.01 frames.], batch size: 27, lr: 3.23e-04
2022-05-05 16:53:34,168 INFO [train.py:715] (5/8) Epoch 6, batch 30900, loss[loss=0.1403, simple_loss=0.2, pruned_loss=0.04034, over 4793.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03748, over 971975.01 frames.], batch size: 24, lr: 3.23e-04
2022-05-05 16:54:13,772 INFO [train.py:715] (5/8) Epoch 6, batch 30950, loss[loss=0.1445, simple_loss=0.2179, pruned_loss=0.03556, over 4902.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.03723, over 973213.19 frames.], batch size: 17, lr: 3.23e-04
2022-05-05 16:54:51,907 INFO [train.py:715] (5/8) Epoch 6, batch 31000, loss[loss=0.1355, simple_loss=0.2069, pruned_loss=0.03205, over 4859.00 frames.], tot_loss[loss=0.147, simple_loss=0.2188, pruned_loss=0.0376, over 972204.82 frames.], batch size: 32, lr: 3.23e-04
2022-05-05 16:55:30,911 INFO [train.py:715] (5/8) Epoch 6, batch 31050, loss[loss=0.1813, simple_loss=0.2446, pruned_loss=0.05895, over 4833.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2188, pruned_loss=0.03778, over 972142.38 frames.], batch size: 32, lr: 3.23e-04
2022-05-05 16:56:10,164 INFO [train.py:715] (5/8) Epoch 6, batch 31100, loss[loss=0.1502, simple_loss=0.237, pruned_loss=0.03171, over 4970.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03839, over 972138.58 frames.], batch size: 28, lr: 3.22e-04
2022-05-05 16:56:51,376 INFO [train.py:715] (5/8) Epoch 6, batch 31150, loss[loss=0.1228, simple_loss=0.1841, pruned_loss=0.03077, over 4835.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.0386, over 972161.27 frames.], batch size: 13, lr: 3.22e-04
2022-05-05 16:57:30,156 INFO [train.py:715] (5/8) Epoch 6, batch 31200, loss[loss=0.132, simple_loss=0.2111, pruned_loss=0.02643, over 4790.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03792, over 971528.74 frames.], batch size: 18, lr: 3.22e-04
2022-05-05 16:58:09,411 INFO [train.py:715] (5/8) Epoch 6, batch 31250, loss[loss=0.1484, simple_loss=0.2217, pruned_loss=0.03756, over 4861.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2195, pruned_loss=0.03872, over 971161.77 frames.], batch size: 20, lr: 3.22e-04
2022-05-05 16:58:48,245 INFO [train.py:715] (5/8) Epoch 6, batch 31300, loss[loss=0.1595, simple_loss=0.2301, pruned_loss=0.04443, over 4932.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2184, pruned_loss=0.03815, over 971301.84 frames.], batch size: 29, lr: 3.22e-04
2022-05-05 16:59:27,120 INFO [train.py:715] (5/8) Epoch 6, batch 31350, loss[loss=0.1784, simple_loss=0.237, pruned_loss=0.05989, over 4957.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2187, pruned_loss=0.03837, over 970614.69 frames.], batch size: 15, lr: 3.22e-04
2022-05-05 17:00:06,354 INFO [train.py:715] (5/8) Epoch 6, batch 31400, loss[loss=0.1578, simple_loss=0.2347, pruned_loss=0.04041, over 4973.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03828, over 970623.25 frames.], batch size: 39, lr: 3.22e-04
2022-05-05 17:00:45,701 INFO [train.py:715] (5/8) Epoch 6, batch 31450, loss[loss=0.1426, simple_loss=0.2171, pruned_loss=0.03407, over 4778.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03786, over 970834.96 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:01:23,994 INFO [train.py:715] (5/8) Epoch 6, batch 31500, loss[loss=0.1157, simple_loss=0.1948, pruned_loss=0.01832, over 4812.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2196, pruned_loss=0.03797, over 971688.87 frames.], batch size: 27, lr: 3.22e-04
2022-05-05 17:02:02,412 INFO [train.py:715] (5/8) Epoch 6, batch 31550, loss[loss=0.1805, simple_loss=0.249, pruned_loss=0.05599, over 4963.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03839, over 972056.60 frames.], batch size: 15, lr: 3.22e-04
2022-05-05 17:02:41,953 INFO [train.py:715] (5/8) Epoch 6, batch 31600, loss[loss=0.1426, simple_loss=0.2162, pruned_loss=0.03449, over 4791.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03811, over 972329.87 frames.], batch size: 18, lr: 3.22e-04
2022-05-05 17:03:21,196 INFO [train.py:715] (5/8) Epoch 6, batch 31650, loss[loss=0.1515, simple_loss=0.2191, pruned_loss=0.04192, over 4742.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03852, over 972387.98 frames.], batch size: 19, lr: 3.22e-04
2022-05-05 17:03:59,732 INFO [train.py:715] (5/8) Epoch 6, batch 31700, loss[loss=0.1603, simple_loss=0.24, pruned_loss=0.04036, over 4770.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03829, over 972237.27 frames.], batch size: 17, lr: 3.22e-04
2022-05-05 17:04:38,254 INFO [train.py:715] (5/8) Epoch 6, batch 31750, loss[loss=0.1286, simple_loss=0.2012, pruned_loss=0.02801, over 4927.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2197, pruned_loss=0.03837, over 972514.80 frames.], batch size: 18, lr: 3.22e-04
2022-05-05 17:05:17,758 INFO [train.py:715] (5/8) Epoch 6, batch 31800, loss[loss=0.1649, simple_loss=0.2348, pruned_loss=0.0475, over 4857.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03813, over 972069.30 frames.], batch size: 20, lr: 3.22e-04
2022-05-05 17:05:56,240 INFO [train.py:715] (5/8) Epoch 6, batch 31850, loss[loss=0.1176, simple_loss=0.1978, pruned_loss=0.01868, over 4771.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03792, over 972297.41 frames.], batch size: 19, lr: 3.22e-04
2022-05-05 17:06:34,777 INFO [train.py:715] (5/8) Epoch 6, batch 31900, loss[loss=0.1609, simple_loss=0.239, pruned_loss=0.04141, over 4752.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2188, pruned_loss=0.03801, over 972309.40 frames.], batch size: 16, lr: 3.22e-04
2022-05-05 17:07:13,869 INFO [train.py:715] (5/8) Epoch 6, batch 31950, loss[loss=0.1733, simple_loss=0.2481, pruned_loss=0.04919, over 4908.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03772, over 971638.51 frames.], batch size: 17, lr: 3.22e-04
2022-05-05 17:07:52,487 INFO [train.py:715] (5/8) Epoch 6, batch 32000, loss[loss=0.1838, simple_loss=0.2594, pruned_loss=0.05415, over 4938.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03837, over 971673.49 frames.], batch size: 21, lr: 3.22e-04
2022-05-05 17:08:31,939 INFO [train.py:715] (5/8) Epoch 6, batch 32050, loss[loss=0.1204, simple_loss=0.1957, pruned_loss=0.02258, over 4773.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.03917, over 971578.04 frames.], batch size: 18, lr: 3.22e-04
2022-05-05 17:09:11,463 INFO [train.py:715] (5/8) Epoch 6, batch 32100, loss[loss=0.1323, simple_loss=0.2082, pruned_loss=0.02818, over 4964.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03858, over 971005.69 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:09:50,461 INFO [train.py:715] (5/8) Epoch 6, batch 32150, loss[loss=0.1222, simple_loss=0.2007, pruned_loss=0.0219, over 4822.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2187, pruned_loss=0.03816, over 971525.44 frames.], batch size: 27, lr: 3.22e-04
2022-05-05 17:10:28,955 INFO [train.py:715] (5/8) Epoch 6, batch 32200, loss[loss=0.1561, simple_loss=0.2386, pruned_loss=0.03678, over 4980.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03786, over 971508.47 frames.], batch size: 25, lr: 3.22e-04
2022-05-05 17:11:08,026 INFO [train.py:715] (5/8) Epoch 6, batch 32250, loss[loss=0.1609, simple_loss=0.2316, pruned_loss=0.04512, over 4819.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03771, over 971724.75 frames.], batch size: 27, lr: 3.22e-04
2022-05-05 17:11:46,850 INFO [train.py:715] (5/8) Epoch 6, batch 32300, loss[loss=0.1327, simple_loss=0.2059, pruned_loss=0.02975, over 4946.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.03799, over 972646.71 frames.], batch size: 23, lr: 3.22e-04
2022-05-05 17:12:26,140 INFO [train.py:715] (5/8) Epoch 6, batch 32350, loss[loss=0.1581, simple_loss=0.2306, pruned_loss=0.04283, over 4813.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03821, over 972700.84 frames.], batch size: 25, lr: 3.22e-04
2022-05-05 17:13:04,502 INFO [train.py:715] (5/8) Epoch 6, batch 32400, loss[loss=0.1668, simple_loss=0.2433, pruned_loss=0.04515, over 4853.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2192, pruned_loss=0.03784, over 972889.19 frames.], batch size: 20, lr: 3.22e-04
2022-05-05 17:13:43,921 INFO [train.py:715] (5/8) Epoch 6, batch 32450, loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02868, over 4840.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03819, over 971897.23 frames.], batch size: 26, lr: 3.22e-04
2022-05-05 17:14:23,268 INFO [train.py:715] (5/8) Epoch 6, batch 32500, loss[loss=0.1311, simple_loss=0.2093, pruned_loss=0.02644, over 4970.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03864, over 972159.62 frames.], batch size: 31, lr: 3.22e-04
2022-05-05 17:15:01,982 INFO [train.py:715] (5/8) Epoch 6, batch 32550, loss[loss=0.1194, simple_loss=0.1928, pruned_loss=0.02303, over 4787.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03903, over 972042.42 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:15:40,778 INFO [train.py:715] (5/8) Epoch 6, batch 32600, loss[loss=0.1213, simple_loss=0.1942, pruned_loss=0.0242, over 4763.00 frames.], tot_loss[loss=0.1485, simple_loss=0.22, pruned_loss=0.03853, over 972230.78 frames.], batch size: 19, lr: 3.21e-04
2022-05-05 17:16:19,209 INFO [train.py:715] (5/8) Epoch 6, batch 32650, loss[loss=0.1568, simple_loss=0.2301, pruned_loss=0.04175, over 4751.00 frames.], tot_loss[loss=0.1485, simple_loss=0.22, pruned_loss=0.03851, over 972148.82 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:16:57,839 INFO [train.py:715] (5/8) Epoch 6, batch 32700, loss[loss=0.1646, simple_loss=0.2302, pruned_loss=0.04946, over 4831.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03856, over 972379.22 frames.], batch size: 15, lr: 3.21e-04
2022-05-05 17:17:35,886 INFO [train.py:715] (5/8) Epoch 6, batch 32750, loss[loss=0.1378, simple_loss=0.2137, pruned_loss=0.03098, over 4700.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2196, pruned_loss=0.03846, over 972481.85 frames.], batch size: 15, lr: 3.21e-04
2022-05-05 17:18:14,603 INFO [train.py:715] (5/8) Epoch 6, batch 32800, loss[loss=0.1365, simple_loss=0.2063, pruned_loss=0.03337, over 4917.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03835, over 972585.56 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:18:53,198 INFO [train.py:715] (5/8) Epoch 6, batch 32850, loss[loss=0.152, simple_loss=0.2205, pruned_loss=0.04175, over 4847.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03758, over 972376.09 frames.], batch size: 30, lr: 3.21e-04
2022-05-05 17:19:31,604 INFO [train.py:715] (5/8) Epoch 6, batch 32900, loss[loss=0.1281, simple_loss=0.2028, pruned_loss=0.02671, over 4806.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2185, pruned_loss=0.038, over 972581.48 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:20:09,697 INFO [train.py:715] (5/8) Epoch 6, batch 32950, loss[loss=0.132, simple_loss=0.1994, pruned_loss=0.03232, over 4849.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03801, over 973138.42 frames.], batch size: 20, lr: 3.21e-04
2022-05-05 17:20:48,506 INFO [train.py:715] (5/8) Epoch 6, batch 33000, loss[loss=0.1346, simple_loss=0.1998, pruned_loss=0.03472, over 4739.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2177, pruned_loss=0.03755, over 972733.13 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:20:48,507 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 17:20:58,110 INFO [train.py:742] (5/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1938, pruned_loss=0.01183, over 914524.00 frames.
2022-05-05 17:21:36,674 INFO [train.py:715] (5/8) Epoch 6, batch 33050, loss[loss=0.1346, simple_loss=0.2143, pruned_loss=0.02745, over 4730.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 971821.46 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:22:15,262 INFO [train.py:715] (5/8) Epoch 6, batch 33100, loss[loss=0.1206, simple_loss=0.1867, pruned_loss=0.02727, over 4780.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03665, over 971066.66 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:22:53,009 INFO [train.py:715] (5/8) Epoch 6, batch 33150, loss[loss=0.1346, simple_loss=0.2099, pruned_loss=0.02965, over 4808.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.0371, over 971371.01 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:23:31,897 INFO [train.py:715] (5/8) Epoch 6, batch 33200, loss[loss=0.1729, simple_loss=0.2408, pruned_loss=0.05255, over 4820.00 frames.], tot_loss[loss=0.1477, simple_loss=0.219, pruned_loss=0.03818, over 971265.81 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:24:10,785 INFO [train.py:715] (5/8) Epoch 6, batch 33250, loss[loss=0.1549, simple_loss=0.2112, pruned_loss=0.04932, over 4762.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03814, over 971180.68 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:24:49,863 INFO [train.py:715] (5/8) Epoch 6, batch 33300, loss[loss=0.1647, simple_loss=0.2338, pruned_loss=0.04775, over 4763.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03853, over 971916.61 frames.], batch size: 19, lr: 3.21e-04
2022-05-05 17:25:28,468 INFO [train.py:715] (5/8) Epoch 6, batch 33350, loss[loss=0.1428, simple_loss=0.223, pruned_loss=0.03125, over 4979.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03836, over 972294.60 frames.], batch size: 25, lr: 3.21e-04
2022-05-05 17:26:07,933 INFO [train.py:715] (5/8) Epoch 6, batch 33400, loss[loss=0.1686, simple_loss=0.2418, pruned_loss=0.04769, over 4918.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03808, over 972256.25 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:26:47,025 INFO [train.py:715] (5/8) Epoch 6, batch 33450, loss[loss=0.1508, simple_loss=0.2249, pruned_loss=0.03839, over 4854.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03829, over 972156.40 frames.], batch size: 32, lr: 3.21e-04
2022-05-05 17:27:25,290 INFO [train.py:715] (5/8) Epoch 6, batch 33500, loss[loss=0.1366, simple_loss=0.1994, pruned_loss=0.03683, over 4981.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2202, pruned_loss=0.03843, over 972732.50 frames.], batch size: 24, lr: 3.21e-04
2022-05-05 17:28:04,313 INFO [train.py:715] (5/8) Epoch 6, batch 33550, loss[loss=0.1389, simple_loss=0.2178, pruned_loss=0.02998, over 4709.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03843, over 972277.65 frames.], batch size: 15, lr: 3.21e-04
2022-05-05 17:28:43,736 INFO [train.py:715] (5/8) Epoch 6, batch 33600, loss[loss=0.1319, simple_loss=0.202, pruned_loss=0.03093, over 4828.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03803, over 972668.12 frames.], batch size: 24, lr: 3.21e-04
2022-05-05 17:29:22,676 INFO [train.py:715] (5/8) Epoch 6, batch 33650, loss[loss=0.1867, simple_loss=0.252, pruned_loss=0.06067, over 4917.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03773, over 972867.50 frames.], batch size: 39, lr: 3.21e-04
2022-05-05 17:30:01,274 INFO [train.py:715] (5/8) Epoch 6, batch 33700, loss[loss=0.1884, simple_loss=0.2489, pruned_loss=0.0639, over 4853.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03706, over 972304.80 frames.], batch size: 30, lr: 3.21e-04
2022-05-05 17:30:39,882 INFO [train.py:715] (5/8) Epoch 6, batch 33750, loss[loss=0.1527, simple_loss=0.2276, pruned_loss=0.03893, over 4993.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2188, pruned_loss=0.0373, over 972334.96 frames.], batch size: 20, lr: 3.21e-04
2022-05-05 17:31:19,208 INFO [train.py:715] (5/8) Epoch 6, batch 33800, loss[loss=0.1845, simple_loss=0.2655, pruned_loss=0.05174, over 4899.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03767, over 972639.98 frames.], batch size: 17, lr: 3.21e-04
2022-05-05 17:31:58,018 INFO [train.py:715] (5/8) Epoch 6, batch 33850, loss[loss=0.1537, simple_loss=0.2215, pruned_loss=0.04298, over 4775.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2192, pruned_loss=0.03762, over 971848.62 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:32:36,705 INFO [train.py:715] (5/8) Epoch 6, batch 33900, loss[loss=0.1504, simple_loss=0.2263, pruned_loss=0.03721, over 4749.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03749, over 971969.36 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:33:16,047 INFO [train.py:715] (5/8) Epoch 6, batch 33950, loss[loss=0.1272, simple_loss=0.205, pruned_loss=0.02472, over 4964.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03753, over 971935.14 frames.], batch size: 14, lr: 3.21e-04
2022-05-05 17:33:55,029 INFO [train.py:715] (5/8) Epoch 6, batch 34000, loss[loss=0.1625, simple_loss=0.2236, pruned_loss=0.05069, over 4917.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03755, over 971519.22 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:34:33,702 INFO [train.py:715] (5/8) Epoch 6, batch 34050, loss[loss=0.1346, simple_loss=0.2173, pruned_loss=0.02598, over 4813.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03748, over 971951.63 frames.], batch size: 21, lr: 3.21e-04
2022-05-05 17:35:12,980 INFO [train.py:715] (5/8) Epoch 6, batch 34100, loss[loss=0.1368, simple_loss=0.2125, pruned_loss=0.03051, over 4902.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2196, pruned_loss=0.0385, over 972808.37 frames.], batch size: 17, lr: 3.20e-04
2022-05-05 17:35:51,936 INFO [train.py:715] (5/8) Epoch 6, batch 34150, loss[loss=0.1503, simple_loss=0.2262, pruned_loss=0.03717, over 4792.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03827, over 972631.50 frames.], batch size: 18, lr: 3.20e-04
2022-05-05 17:36:30,535 INFO [train.py:715] (5/8) Epoch 6, batch 34200, loss[loss=0.1336, simple_loss=0.206, pruned_loss=0.03055, over 4956.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03774, over 971517.65 frames.], batch size: 35, lr: 3.20e-04
2022-05-05 17:37:09,177 INFO [train.py:715] (5/8) Epoch 6, batch 34250, loss[loss=0.1712, simple_loss=0.2334, pruned_loss=0.0545, over 4889.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03892, over 972456.51 frames.], batch size: 19, lr: 3.20e-04
2022-05-05 17:37:48,388 INFO [train.py:715] (5/8) Epoch 6, batch 34300, loss[loss=0.1616, simple_loss=0.2291, pruned_loss=0.04711, over 4925.00 frames.], tot_loss[loss=0.1485, simple_loss=0.22, pruned_loss=0.03849, over 972488.45 frames.], batch size: 29, lr: 3.20e-04
2022-05-05 17:38:26,981 INFO [train.py:715] (5/8) Epoch 6, batch 34350, loss[loss=0.1736, simple_loss=0.2394, pruned_loss=0.05391, over 4772.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2195, pruned_loss=0.0378, over 972875.69 frames.], batch size: 17, lr: 3.20e-04
2022-05-05 17:39:05,618 INFO [train.py:715] (5/8) Epoch 6, batch 34400, loss[loss=0.1624, simple_loss=0.2444, pruned_loss=0.04021, over 4931.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.0374, over 973833.98 frames.], batch size: 17, lr: 3.20e-04
2022-05-05 17:39:45,298 INFO [train.py:715] (5/8) Epoch 6, batch 34450, loss[loss=0.187, simple_loss=0.2404, pruned_loss=0.06678, over 4927.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03752, over 973575.12 frames.], batch size: 39, lr: 3.20e-04
2022-05-05 17:40:24,041 INFO [train.py:715] (5/8) Epoch 6, batch 34500, loss[loss=0.1808, simple_loss=0.2469, pruned_loss=0.0574, over 4902.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03857, over 973161.90 frames.], batch size: 39, lr: 3.20e-04
2022-05-05 17:41:02,891 INFO [train.py:715] (5/8) Epoch 6, batch 34550, loss[loss=0.1629, simple_loss=0.2362, pruned_loss=0.04479, over 4946.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03819, over 972743.56 frames.], batch size: 21, lr: 3.20e-04
2022-05-05 17:41:41,805 INFO [train.py:715] (5/8) Epoch 6, batch 34600, loss[loss=0.1348, simple_loss=0.2017, pruned_loss=0.03398, over 4913.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2201, pruned_loss=0.03818, over 972767.97 frames.], batch size: 29, lr: 3.20e-04
2022-05-05 17:42:20,616 INFO [train.py:715] (5/8) Epoch 6, batch 34650, loss[loss=0.1324, simple_loss=0.2098, pruned_loss=0.02751, over 4939.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03824, over 972835.94 frames.], batch size: 21, lr: 3.20e-04
2022-05-05 17:42:59,316 INFO [train.py:715] (5/8) Epoch 6, batch 34700, loss[loss=0.1463, simple_loss=0.206, pruned_loss=0.04334, over 4833.00 frames.], tot_loss[loss=0.1483, simple_loss=0.22, pruned_loss=0.03827, over 972307.46 frames.], batch size: 32, lr: 3.20e-04
2022-05-05 17:43:37,146 INFO [train.py:715] (5/8) Epoch 6, batch 34750, loss[loss=0.1652, simple_loss=0.2248, pruned_loss=0.05278, over 4765.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03844, over 972942.73 frames.], batch size: 16, lr: 3.20e-04
2022-05-05 17:44:13,983 INFO [train.py:715] (5/8) Epoch 6, batch 34800, loss[loss=0.1254, simple_loss=0.2047, pruned_loss=0.0231, over 4938.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2183, pruned_loss=0.03809, over 972597.05 frames.], batch size: 18, lr: 3.20e-04
2022-05-05 17:45:04,007 INFO [train.py:715] (5/8) Epoch 7, batch 0, loss[loss=0.1429, simple_loss=0.206, pruned_loss=0.03986, over 4884.00 frames.], tot_loss[loss=0.1429, simple_loss=0.206, pruned_loss=0.03986, over 4884.00 frames.], batch size: 32, lr: 3.03e-04
2022-05-05 17:45:42,573 INFO [train.py:715] (5/8) Epoch 7, batch 50, loss[loss=0.1289, simple_loss=0.1977, pruned_loss=0.03002, over 4983.00 frames.], tot_loss[loss=0.15, simple_loss=0.2199, pruned_loss=0.04003, over 219549.65 frames.], batch size: 15, lr: 3.03e-04
2022-05-05 17:46:21,361 INFO [train.py:715] (5/8) Epoch 7, batch 100, loss[loss=0.1681, simple_loss=0.2353, pruned_loss=0.0504, over 4909.00 frames.], tot_loss[loss=0.1475, simple_loss=0.219, pruned_loss=0.03802, over 386420.33 frames.], batch size: 17, lr: 3.03e-04
2022-05-05 17:47:00,259 INFO [train.py:715] (5/8) Epoch 7, batch 150, loss[loss=0.1574, simple_loss=0.2348, pruned_loss=0.04002, over 4931.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03734, over 516268.56 frames.], batch size: 29, lr: 3.03e-04
2022-05-05 17:47:39,937 INFO [train.py:715] (5/8) Epoch 7, batch 200, loss[loss=0.1438, simple_loss=0.2109, pruned_loss=0.03833, over 4961.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03793, over 617557.80 frames.], batch size: 35, lr: 3.03e-04
2022-05-05 17:48:18,721 INFO [train.py:715] (5/8) Epoch 7, batch 250, loss[loss=0.1241, simple_loss=0.1977, pruned_loss=0.02522, over 4820.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03813, over 695716.40 frames.], batch size: 25, lr: 3.03e-04
2022-05-05 17:48:58,165 INFO [train.py:715] (5/8) Epoch 7, batch 300, loss[loss=0.1554, simple_loss=0.2306, pruned_loss=0.04016, over 4817.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03752, over 756921.10 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 17:49:36,847 INFO [train.py:715] (5/8) Epoch 7, batch 350, loss[loss=0.1556, simple_loss=0.2276, pruned_loss=0.04175, over 4850.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.0374, over 804916.88 frames.], batch size: 20, lr: 3.02e-04
2022-05-05 17:50:16,224 INFO [train.py:715] (5/8) Epoch 7, batch 400, loss[loss=0.1796, simple_loss=0.2579, pruned_loss=0.05065, over 4850.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.0375, over 842227.20 frames.], batch size: 20, lr: 3.02e-04
2022-05-05 17:50:54,885 INFO [train.py:715] (5/8) Epoch 7, batch 450, loss[loss=0.1119, simple_loss=0.1834, pruned_loss=0.02024, over 4792.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.0371, over 871230.70 frames.], batch size: 14, lr: 3.02e-04
2022-05-05 17:51:33,767 INFO [train.py:715] (5/8) Epoch 7, batch 500, loss[loss=0.1244, simple_loss=0.2008, pruned_loss=0.02396, over 4788.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03687, over 892644.08 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 17:52:12,472 INFO [train.py:715] (5/8) Epoch 7, batch 550, loss[loss=0.1471, simple_loss=0.2131, pruned_loss=0.04051, over 4811.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2183, pruned_loss=0.03795, over 910109.22 frames.], batch size: 25, lr: 3.02e-04
2022-05-05 17:52:51,635 INFO [train.py:715] (5/8) Epoch 7, batch 600, loss[loss=0.1356, simple_loss=0.2084, pruned_loss=0.03138, over 4929.00 frames.], tot_loss[loss=0.1482, simple_loss=0.219, pruned_loss=0.03873, over 923787.00 frames.], batch size: 23, lr: 3.02e-04
2022-05-05 17:53:29,945 INFO [train.py:715] (5/8) Epoch 7, batch 650, loss[loss=0.1645, simple_loss=0.2323, pruned_loss=0.04833, over 4828.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03846, over 934797.69 frames.], batch size: 12, lr: 3.02e-04
2022-05-05 17:54:08,326 INFO [train.py:715] (5/8) Epoch 7, batch 700, loss[loss=0.1393, simple_loss=0.2067, pruned_loss=0.03592, over 4829.00 frames.], tot_loss[loss=0.1474, simple_loss=0.219, pruned_loss=0.03788, over 943744.99 frames.], batch size: 27, lr: 3.02e-04
2022-05-05 17:54:47,594 INFO [train.py:715] (5/8) Epoch 7, batch 750, loss[loss=0.174, simple_loss=0.249, pruned_loss=0.04948, over 4904.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03746, over 949557.32 frames.], batch size: 19, lr: 3.02e-04
2022-05-05 17:55:26,299 INFO [train.py:715] (5/8) Epoch 7, batch 800, loss[loss=0.1782, simple_loss=0.2487, pruned_loss=0.05383, over 4916.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03781, over 955040.41 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 17:56:04,984 INFO [train.py:715] (5/8) Epoch 7, batch 850, loss[loss=0.1413, simple_loss=0.2062, pruned_loss=0.03825, over 4951.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2201, pruned_loss=0.03823, over 960074.43 frames.], batch size: 23, lr: 3.02e-04
2022-05-05 17:56:44,239 INFO [train.py:715] (5/8) Epoch 7, batch 900, loss[loss=0.1123, simple_loss=0.183, pruned_loss=0.02081, over 4947.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03869, over 963000.98 frames.], batch size: 21, lr: 3.02e-04
2022-05-05 17:57:23,221 INFO [train.py:715] (5/8) Epoch 7, batch 950, loss[loss=0.1798, simple_loss=0.2454, pruned_loss=0.05709, over 4892.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03835, over 965358.46 frames.], batch size: 22, lr: 3.02e-04
2022-05-05 17:58:01,722 INFO [train.py:715] (5/8) Epoch 7, batch 1000, loss[loss=0.1617, simple_loss=0.2275, pruned_loss=0.04797, over 4948.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2187, pruned_loss=0.03817, over 967176.63 frames.], batch size: 35, lr: 3.02e-04
2022-05-05 17:58:40,406 INFO [train.py:715] (5/8) Epoch 7, batch 1050, loss[loss=0.1196, simple_loss=0.1968, pruned_loss=0.02117, over 4839.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2177, pruned_loss=0.03768, over 968069.33 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 17:59:19,624 INFO [train.py:715] (5/8) Epoch 7, batch 1100, loss[loss=0.1442, simple_loss=0.2149, pruned_loss=0.03676, over 4988.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.0377, over 968540.51 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 17:59:57,782 INFO [train.py:715] (5/8) Epoch 7, batch 1150, loss[loss=0.1285, simple_loss=0.2006, pruned_loss=0.02816, over 4816.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2175, pruned_loss=0.03771, over 969967.96 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 18:00:36,964 INFO [train.py:715] (5/8) Epoch 7, batch 1200, loss[loss=0.1255, simple_loss=0.2021, pruned_loss=0.02442, over 4974.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03779, over 970456.70 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 18:01:16,051 INFO [train.py:715] (5/8) Epoch 7, batch 1250, loss[loss=0.1116, simple_loss=0.1871, pruned_loss=0.01805, over 4803.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03712, over 970029.10 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 18:01:55,179 INFO [train.py:715] (5/8) Epoch 7, batch 1300, loss[loss=0.1683, simple_loss=0.2462, pruned_loss=0.04523, over 4905.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03769, over 970554.58 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 18:02:33,763 INFO [train.py:715] (5/8) Epoch 7, batch 1350, loss[loss=0.1458, simple_loss=0.2142, pruned_loss=0.03869, over 4923.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.03747, over 970712.05 frames.], batch size: 18, lr: 3.02e-04
2022-05-05 18:03:12,553 INFO [train.py:715] (5/8) Epoch 7, batch 1400, loss[loss=0.1546, simple_loss=0.2336, pruned_loss=0.03781, over 4916.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.0371, over 971186.52 frames.], batch size: 18, lr: 3.02e-04
2022-05-05 18:03:51,641 INFO [train.py:715] (5/8) Epoch 7, batch 1450, loss[loss=0.1611, simple_loss=0.2311, pruned_loss=0.04562, over 4921.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03764, over 971774.62 frames.], batch size: 18, lr: 3.02e-04
2022-05-05 18:04:29,770 INFO [train.py:715] (5/8) Epoch 7, batch 1500, loss[loss=0.1471, simple_loss=0.2136, pruned_loss=0.0403, over 4986.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03774, over 971736.96 frames.], batch size: 25, lr: 3.02e-04
2022-05-05 18:05:08,980 INFO [train.py:715] (5/8) Epoch 7, batch 1550, loss[loss=0.1625, simple_loss=0.233, pruned_loss=0.04601, over 4866.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03755, over 971968.42 frames.], batch size: 20, lr: 3.02e-04
2022-05-05 18:05:47,787 INFO [train.py:715] (5/8) Epoch 7, batch 1600, loss[loss=0.1558, simple_loss=0.2347, pruned_loss=0.0385, over 4968.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03763, over 973353.55 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 18:06:26,680 INFO [train.py:715] (5/8) Epoch 7, batch 1650, loss[loss=0.1634, simple_loss=0.2243, pruned_loss=0.05121, over 4867.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03852, over 973334.91 frames.], batch size: 38, lr: 3.02e-04
2022-05-05 18:07:05,257 INFO [train.py:715] (5/8) Epoch 7, batch 1700, loss[loss=0.1534, simple_loss=0.2284, pruned_loss=0.03921, over 4985.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03833, over 973623.74 frames.], batch size: 26, lr: 3.02e-04
2022-05-05 18:07:44,161 INFO [train.py:715] (5/8) Epoch 7, batch 1750, loss[loss=0.1552, simple_loss=0.2216, pruned_loss=0.04434, over 4961.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03768, over 973372.85 frames.], batch size: 35, lr: 3.02e-04
2022-05-05 18:08:24,137 INFO [train.py:715] (5/8) Epoch 7, batch 1800, loss[loss=0.139, simple_loss=0.2101, pruned_loss=0.03397, over 4900.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03807, over 973190.91 frames.], batch size: 22, lr: 3.02e-04
2022-05-05 18:09:03,071 INFO [train.py:715] (5/8) Epoch 7, batch 1850, loss[loss=0.1457, simple_loss=0.2212, pruned_loss=0.03514, over 4899.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.038, over 973103.22 frames.], batch size: 16, lr: 3.02e-04
2022-05-05 18:09:41,926 INFO [train.py:715] (5/8) Epoch 7, batch 1900, loss[loss=0.1623, simple_loss=0.2181, pruned_loss=0.05326, over 4982.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2178, pruned_loss=0.03777, over 972658.46 frames.], batch size: 33, lr: 3.01e-04
2022-05-05 18:10:20,113 INFO [train.py:715] (5/8) Epoch 7, batch 1950, loss[loss=0.1519, simple_loss=0.2232, pruned_loss=0.04023, over 4867.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.0375, over 972837.49 frames.], batch size: 16, lr: 3.01e-04
2022-05-05 18:10:59,289 INFO [train.py:715] (5/8) Epoch 7, batch 2000, loss[loss=0.1565, simple_loss=0.2198, pruned_loss=0.04662, over 4761.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03752, over 972634.40 frames.], batch size: 16, lr: 3.01e-04
2022-05-05 18:11:37,486 INFO [train.py:715] (5/8) Epoch 7, batch 2050, loss[loss=0.194, simple_loss=0.2571, pruned_loss=0.06543, over 4773.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03736, over 972664.99 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:12:16,137 INFO [train.py:715] (5/8) Epoch 7, batch 2100, loss[loss=0.1366, simple_loss=0.2066, pruned_loss=0.0333, over 4878.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03777, over 972538.10 frames.], batch size: 22, lr: 3.01e-04
2022-05-05 18:12:54,591 INFO [train.py:715] (5/8) Epoch 7, batch 2150, loss[loss=0.1147, simple_loss=0.1831, pruned_loss=0.02317, over 4774.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.0374, over 973340.69 frames.], batch size: 12, lr: 3.01e-04
2022-05-05 18:13:32,799 INFO [train.py:715] (5/8) Epoch 7, batch 2200, loss[loss=0.1462, simple_loss=0.2193, pruned_loss=0.03659, over 4837.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03787, over 973246.43 frames.], batch size: 27, lr: 3.01e-04
2022-05-05 18:14:11,048 INFO [train.py:715] (5/8) Epoch 7, batch 2250, loss[loss=0.1466, simple_loss=0.2252, pruned_loss=0.03397, over 4961.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2189, pruned_loss=0.03769, over 973227.58 frames.], batch size: 24, lr: 3.01e-04
2022-05-05 18:14:50,047 INFO [train.py:715] (5/8) Epoch 7, batch 2300, loss[loss=0.162, simple_loss=0.2335, pruned_loss=0.0452, over 4840.00 frames.], tot_loss[loss=0.147, simple_loss=0.2188, pruned_loss=0.03763, over 973078.93 frames.], batch size: 30, lr: 3.01e-04
2022-05-05 18:15:29,527 INFO [train.py:715] (5/8) Epoch 7, batch 2350, loss[loss=0.1515, simple_loss=0.2312, pruned_loss=0.0359, over 4859.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03817, over 973040.82 frames.], batch size: 20, lr: 3.01e-04
2022-05-05 18:16:08,316 INFO [train.py:715] (5/8) Epoch 7, batch 2400, loss[loss=0.1171, simple_loss=0.1924, pruned_loss=0.0209, over 4809.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03807, over 972833.01 frames.], batch size: 13, lr: 3.01e-04
2022-05-05 18:16:46,788 INFO [train.py:715] (5/8) Epoch 7, batch 2450, loss[loss=0.1266, simple_loss=0.2034, pruned_loss=0.02495, over 4918.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03795, over 972194.39 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:17:25,559 INFO [train.py:715] (5/8) Epoch 7, batch 2500, loss[loss=0.1359, simple_loss=0.2141, pruned_loss=0.02884, over 4912.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03746, over 972708.20 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:18:03,862 INFO [train.py:715] (5/8) Epoch 7, batch 2550, loss[loss=0.1144, simple_loss=0.1835, pruned_loss=0.02269, over 4968.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03773, over 972910.86 frames.], batch size: 25, lr: 3.01e-04
2022-05-05 18:18:42,384 INFO [train.py:715] (5/8) Epoch 7, batch 2600, loss[loss=0.1729, simple_loss=0.236, pruned_loss=0.05488, over 4776.00 frames.], tot_loss[loss=0.1473, simple_loss=0.219, pruned_loss=0.03784, over 972528.95 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:19:21,118 INFO [train.py:715] (5/8) Epoch 7, batch 2650, loss[loss=0.1377, simple_loss=0.2163, pruned_loss=0.02951, over 4919.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03804, over 972815.75 frames.], batch size: 23, lr: 3.01e-04
2022-05-05 18:19:59,709 INFO [train.py:715] (5/8) Epoch 7, batch 2700, loss[loss=0.1528, simple_loss=0.2296, pruned_loss=0.03802, over 4865.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2187, pruned_loss=0.03744, over 972861.60 frames.], batch size: 20, lr: 3.01e-04
2022-05-05 18:20:37,585 INFO [train.py:715] (5/8) Epoch 7, batch 2750, loss[loss=0.1533, simple_loss=0.2212, pruned_loss=0.04265, over 4681.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03789, over 972827.08 frames.], batch size: 15, lr: 3.01e-04
2022-05-05 18:21:16,388 INFO [train.py:715] (5/8) Epoch 7, batch 2800, loss[loss=0.1655, simple_loss=0.2356, pruned_loss=0.04772, over 4894.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03772, over 973248.36 frames.], batch size: 17, lr: 3.01e-04
2022-05-05 18:21:55,733 INFO [train.py:715] (5/8) Epoch 7, batch 2850, loss[loss=0.1603, simple_loss=0.2322, pruned_loss=0.04418, over 4917.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03749, over 972725.28 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:22:35,310 INFO [train.py:715] (5/8) Epoch 7, batch 2900, loss[loss=0.1277, simple_loss=0.1991, pruned_loss=0.0281, over 4977.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03696, over 971867.44 frames.], batch size: 40, lr: 3.01e-04
2022-05-05 18:23:14,209 INFO [train.py:715] (5/8) Epoch 7, batch 2950, loss[loss=0.1404, simple_loss=0.2084, pruned_loss=0.03618, over 4980.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03697, over 972118.38 frames.], batch size: 28, lr: 3.01e-04
2022-05-05 18:23:53,378 INFO [train.py:715] (5/8) Epoch 7, batch 3000, loss[loss=0.1459, simple_loss=0.2256, pruned_loss=0.03316, over 4939.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03739, over 972039.16 frames.], batch size: 21, lr: 3.01e-04
2022-05-05 18:23:53,379 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 18:24:04,766 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1084, simple_loss=0.1933, pruned_loss=0.01171, over 914524.00 frames.
2022-05-05 18:24:44,250 INFO [train.py:715] (5/8) Epoch 7, batch 3050, loss[loss=0.1413, simple_loss=0.2195, pruned_loss=0.03156, over 4828.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03731, over 972169.64 frames.], batch size: 26, lr: 3.01e-04
2022-05-05 18:25:23,062 INFO [train.py:715] (5/8) Epoch 7, batch 3100, loss[loss=0.1672, simple_loss=0.231, pruned_loss=0.05171, over 4903.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.03769, over 972226.94 frames.], batch size: 17, lr: 3.01e-04
2022-05-05 18:26:01,759 INFO [train.py:715] (5/8) Epoch 7, batch 3150, loss[loss=0.1398, simple_loss=0.2191, pruned_loss=0.03029, over 4828.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2188, pruned_loss=0.03838, over 972954.66 frames.], batch size: 26, lr: 3.01e-04
2022-05-05 18:26:39,661 INFO [train.py:715] (5/8) Epoch 7, batch 3200, loss[loss=0.1412, simple_loss=0.2026, pruned_loss=0.03989, over 4915.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03854, over 972603.88 frames.], batch size: 17, lr: 3.01e-04
2022-05-05 18:27:17,886 INFO [train.py:715] (5/8) Epoch 7, batch 3250, loss[loss=0.1302, simple_loss=0.211, pruned_loss=0.0247, over 4842.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.03847, over 972878.90 frames.], batch size: 13, lr: 3.01e-04
2022-05-05 18:27:56,434 INFO [train.py:715] (5/8) Epoch 7, batch 3300, loss[loss=0.1939, simple_loss=0.2708, pruned_loss=0.05854, over 4785.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2179, pruned_loss=0.0379, over 972601.16 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:28:35,031 INFO [train.py:715] (5/8) Epoch 7, batch 3350, loss[loss=0.158, simple_loss=0.2326, pruned_loss=0.04173, over 4970.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03805, over 972837.92 frames.], batch size: 35, lr: 3.01e-04
2022-05-05 18:29:13,823 INFO [train.py:715] (5/8) Epoch 7, batch 3400, loss[loss=0.1581, simple_loss=0.2352, pruned_loss=0.04055, over 4939.00 frames.], tot_loss[loss=0.1477, simple_loss=0.219, pruned_loss=0.03817, over 973216.12 frames.], batch size: 29, lr: 3.01e-04
2022-05-05 18:29:52,250 INFO [train.py:715] (5/8) Epoch 7, batch 3450, loss[loss=0.1227, simple_loss=0.1921, pruned_loss=0.0266, over 4748.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.03745, over 973075.27 frames.], batch size: 16, lr: 3.01e-04
2022-05-05 18:30:31,304 INFO [train.py:715] (5/8) Epoch 7, batch 3500, loss[loss=0.1401, simple_loss=0.2063, pruned_loss=0.03691, over 4846.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03762, over 972273.78 frames.], batch size: 13, lr: 3.01e-04
2022-05-05 18:31:09,923 INFO [train.py:715] (5/8) Epoch 7, batch 3550, loss[loss=0.125, simple_loss=0.1984, pruned_loss=0.02574, over 4988.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03752, over 972050.32 frames.], batch size: 20, lr: 3.00e-04
2022-05-05 18:31:48,694 INFO [train.py:715] (5/8) Epoch 7, batch 3600, loss[loss=0.1306, simple_loss=0.1999, pruned_loss=0.03058, over 4874.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03741, over 972040.94 frames.], batch size: 22, lr: 3.00e-04
2022-05-05 18:32:27,423 INFO [train.py:715] (5/8) Epoch 7, batch 3650, loss[loss=0.167, simple_loss=0.2452, pruned_loss=0.04443, over 4927.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2167, pruned_loss=0.03706, over 972303.87 frames.], batch size: 18, lr: 3.00e-04
2022-05-05 18:33:06,463 INFO [train.py:715] (5/8) Epoch 7, batch 3700, loss[loss=0.1402, simple_loss=0.2091, pruned_loss=0.03564, over 4744.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2164, pruned_loss=0.03698, over 973073.07 frames.], batch size: 16, lr: 3.00e-04
2022-05-05 18:33:45,233 INFO [train.py:715] (5/8) Epoch 7, batch 3750, loss[loss=0.1743, simple_loss=0.2325, pruned_loss=0.05809, over 4919.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2169, pruned_loss=0.03727, over 972914.03 frames.], batch size: 18, lr: 3.00e-04
2022-05-05 18:34:23,491 INFO [train.py:715] (5/8) Epoch 7, batch 3800, loss[loss=0.1475, simple_loss=0.2143, pruned_loss=0.04031, over 4917.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2167, pruned_loss=0.03701, over 973498.29 frames.], batch size: 23, lr: 3.00e-04
2022-05-05 18:35:01,654 INFO [train.py:715] (5/8) Epoch 7, batch 3850, loss[loss=0.1395, simple_loss=0.212, pruned_loss=0.03354, over 4771.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2167, pruned_loss=0.03728, over 973198.54 frames.], batch size: 18, lr: 3.00e-04
2022-05-05 18:35:39,926 INFO [train.py:715] (5/8) Epoch 7, batch 3900, loss[loss=0.1455, simple_loss=0.2126, pruned_loss=0.03915, over 4783.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2168, pruned_loss=0.03742, over 972709.12 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:36:18,412 INFO [train.py:715] (5/8) Epoch 7, batch 3950, loss[loss=0.1552, simple_loss=0.222, pruned_loss=0.04425, over 4928.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03785, over 972154.37 frames.], batch size: 39, lr: 3.00e-04
2022-05-05 18:36:57,037 INFO [train.py:715] (5/8) Epoch 7, batch 4000, loss[loss=0.1355, simple_loss=0.2104, pruned_loss=0.03028, over 4921.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03744, over 972099.12 frames.], batch size: 18, lr: 3.00e-04
2022-05-05 18:37:35,135 INFO [train.py:715] (5/8) Epoch 7, batch 4050, loss[loss=0.1188, simple_loss=0.1917, pruned_loss=0.02297, over 4923.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2182, pruned_loss=0.03713, over 972379.75 frames.], batch size: 23, lr: 3.00e-04
2022-05-05 18:38:14,045 INFO [train.py:715] (5/8) Epoch 7, batch 4100, loss[loss=0.1725, simple_loss=0.2547, pruned_loss=0.04516, over 4883.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.03701, over 971588.63 frames.], batch size: 39, lr: 3.00e-04
2022-05-05 18:38:52,567 INFO [train.py:715] (5/8) Epoch 7, batch 4150, loss[loss=0.1358, simple_loss=0.2078, pruned_loss=0.03188, over 4800.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2186, pruned_loss=0.03703, over 970966.09 frames.], batch size: 21, lr: 3.00e-04
2022-05-05 18:39:31,258 INFO [train.py:715] (5/8) Epoch 7, batch 4200, loss[loss=0.1358, simple_loss=0.215, pruned_loss=0.02829, over 4916.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.0368, over 971255.46 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:40:09,112 INFO [train.py:715] (5/8) Epoch 7, batch 4250, loss[loss=0.1688, simple_loss=0.2595, pruned_loss=0.03905, over 4857.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03728, over 971157.60 frames.], batch size: 20, lr: 3.00e-04
2022-05-05 18:40:47,951 INFO [train.py:715] (5/8) Epoch 7, batch 4300, loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03575, over 4869.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03749, over 971898.47 frames.], batch size: 20, lr: 3.00e-04
2022-05-05 18:41:28,766 INFO [train.py:715] (5/8) Epoch 7, batch 4350, loss[loss=0.1422, simple_loss=0.2121, pruned_loss=0.03619, over 4857.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03778, over 972997.75 frames.], batch size: 30, lr: 3.00e-04
2022-05-05 18:42:07,270 INFO [train.py:715] (5/8) Epoch 7, batch 4400, loss[loss=0.1641, simple_loss=0.2253, pruned_loss=0.05149, over 4875.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03783, over 972382.57 frames.], batch size: 32, lr: 3.00e-04
2022-05-05 18:42:46,326 INFO [train.py:715] (5/8) Epoch 7, batch 4450, loss[loss=0.1268, simple_loss=0.2029, pruned_loss=0.0254, over 4934.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03808, over 972623.50 frames.], batch size: 23, lr: 3.00e-04
2022-05-05 18:43:25,193 INFO [train.py:715] (5/8) Epoch 7, batch 4500, loss[loss=0.1452, simple_loss=0.2116, pruned_loss=0.03939, over 4831.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.03773, over 971905.42 frames.], batch size: 12, lr: 3.00e-04
2022-05-05 18:44:03,952 INFO [train.py:715] (5/8) Epoch 7, batch 4550, loss[loss=0.1612, simple_loss=0.212, pruned_loss=0.05515, over 4824.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03758, over 971826.90 frames.], batch size: 12, lr: 3.00e-04
2022-05-05 18:44:42,554 INFO [train.py:715] (5/8) Epoch 7, batch 4600, loss[loss=0.1732, simple_loss=0.247, pruned_loss=0.04965, over 4914.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03743, over 971465.52 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:45:21,325 INFO [train.py:715] (5/8) Epoch 7, batch 4650, loss[loss=0.1565, simple_loss=0.2222, pruned_loss=0.0454, over 4837.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03811, over 972154.74 frames.], batch size: 15, lr: 3.00e-04
2022-05-05 18:45:59,787 INFO [train.py:715] (5/8) Epoch 7, batch 4700, loss[loss=0.1547, simple_loss=0.2249, pruned_loss=0.04229, over 4884.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2176, pruned_loss=0.03762, over 972187.89 frames.], batch size: 16, lr: 3.00e-04
2022-05-05 18:46:37,972 INFO [train.py:715] (5/8) Epoch 7, batch 4750, loss[loss=0.136, simple_loss=0.2021, pruned_loss=0.03499, over 4760.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2175, pruned_loss=0.03744, over 972920.43 frames.], batch size: 12, lr: 3.00e-04
2022-05-05 18:47:17,154 INFO [train.py:715] (5/8) Epoch 7, batch 4800, loss[loss=0.1436, simple_loss=0.2173, pruned_loss=0.03494, over 4877.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03706, over 972274.56 frames.], batch size: 22, lr: 3.00e-04
2022-05-05 18:47:55,562 INFO [train.py:715] (5/8) Epoch 7, batch 4850, loss[loss=0.1898, simple_loss=0.2605, pruned_loss=0.05961, over 4781.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.03772, over 972231.66 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:48:34,303 INFO [train.py:715] (5/8) Epoch 7, batch 4900, loss[loss=0.1943, simple_loss=0.252, pruned_loss=0.06825, over 4815.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.03741, over 972231.37 frames.], batch size: 13, lr: 3.00e-04
2022-05-05 18:49:12,734 INFO [train.py:715] (5/8) Epoch 7, batch 4950, loss[loss=0.1291, simple_loss=0.2015, pruned_loss=0.02836, over 4954.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.03736, over 971815.33 frames.], batch size: 39, lr: 3.00e-04
2022-05-05 18:49:51,777 INFO [train.py:715] (5/8) Epoch 7, batch 5000, loss[loss=0.1572, simple_loss=0.218, pruned_loss=0.04821, over 4856.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2172, pruned_loss=0.03731, over 971384.09 frames.], batch size: 30, lr: 3.00e-04
2022-05-05 18:50:30,773 INFO [train.py:715] (5/8) Epoch 7, batch 5050, loss[loss=0.1221, simple_loss=0.2027, pruned_loss=0.02077, over 4754.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03675, over 972036.48 frames.], batch size: 16, lr: 3.00e-04
2022-05-05 18:51:09,370 INFO [train.py:715] (5/8) Epoch 7, batch 5100, loss[loss=0.1363, simple_loss=0.202, pruned_loss=0.03531, over 4751.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.03777, over 972302.42 frames.], batch size: 19, lr: 3.00e-04
2022-05-05 18:51:48,429 INFO [train.py:715] (5/8) Epoch 7, batch 5150, loss[loss=0.1543, simple_loss=0.2244, pruned_loss=0.04214, over 4843.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03808, over 972300.71 frames.], batch size: 20, lr: 3.00e-04
2022-05-05 18:52:27,135 INFO [train.py:715] (5/8) Epoch 7, batch 5200, loss[loss=0.1407, simple_loss=0.2093, pruned_loss=0.036, over 4832.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2177, pruned_loss=0.03764, over 972470.16 frames.], batch size: 15, lr: 2.99e-04
2022-05-05 18:53:06,163 INFO [train.py:715] (5/8) Epoch 7, batch 5250, loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 4793.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03783, over 972559.62 frames.], batch size: 17, lr: 2.99e-04
2022-05-05 18:53:44,791 INFO [train.py:715] (5/8) Epoch 7, batch 5300, loss[loss=0.133, simple_loss=0.2044, pruned_loss=0.03079, over 4930.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03783, over 971390.26 frames.], batch size: 23, lr: 2.99e-04
2022-05-05 18:54:24,157 INFO [train.py:715] (5/8) Epoch 7, batch 5350, loss[loss=0.1432, simple_loss=0.2109, pruned_loss=0.03775, over 4854.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03751, over 971261.50 frames.], batch size: 20, lr: 2.99e-04
2022-05-05 18:55:02,366 INFO [train.py:715] (5/8) Epoch 7, batch 5400, loss[loss=0.2237, simple_loss=0.2859, pruned_loss=0.08074, over 4883.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03806, over 970684.08 frames.], batch size: 16, lr: 2.99e-04
2022-05-05 18:55:41,211 INFO [train.py:715] (5/8) Epoch 7, batch 5450, loss[loss=0.1449, simple_loss=0.2222, pruned_loss=0.03383, over 4915.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03788, over 971020.67 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 18:56:20,339 INFO [train.py:715] (5/8) Epoch 7, batch 5500, loss[loss=0.1463, simple_loss=0.2137, pruned_loss=0.03939, over 4918.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03745, over 971948.08 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 18:56:59,121 INFO [train.py:715] (5/8) Epoch 7, batch 5550, loss[loss=0.1578, simple_loss=0.2461, pruned_loss=0.03472, over 4913.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03714, over 972202.52 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 18:57:38,239 INFO [train.py:715] (5/8) Epoch 7, batch 5600, loss[loss=0.149, simple_loss=0.2308, pruned_loss=0.03355, over 4822.00 frames.], tot_loss[loss=0.1458, simple_loss=0.217, pruned_loss=0.03728, over 971969.75 frames.], batch size: 25, lr: 2.99e-04
2022-05-05 18:58:17,279 INFO [train.py:715] (5/8) Epoch 7, batch 5650, loss[loss=0.1466, simple_loss=0.2082, pruned_loss=0.04251, over 4792.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2175, pruned_loss=0.03764, over 972361.81 frames.], batch size: 17, lr: 2.99e-04
2022-05-05 18:58:56,367 INFO [train.py:715] (5/8) Epoch 7, batch 5700, loss[loss=0.2099, simple_loss=0.2627, pruned_loss=0.07856, over 4906.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.0378, over 972213.27 frames.], batch size: 39, lr: 2.99e-04
2022-05-05 18:59:34,747 INFO [train.py:715] (5/8) Epoch 7, batch 5750, loss[loss=0.1446, simple_loss=0.2201, pruned_loss=0.0346, over 4965.00 frames.], tot_loss[loss=0.1457, simple_loss=0.217, pruned_loss=0.03714, over 972831.36 frames.], batch size: 28, lr: 2.99e-04
2022-05-05 19:00:12,899 INFO [train.py:715] (5/8) Epoch 7, batch 5800, loss[loss=0.1303, simple_loss=0.2006, pruned_loss=0.02994, over 4947.00 frames.], tot_loss[loss=0.146, simple_loss=0.2173, pruned_loss=0.03737, over 972811.28 frames.], batch size: 21, lr: 2.99e-04
2022-05-05 19:00:52,628 INFO [train.py:715] (5/8) Epoch 7, batch 5850, loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03527, over 4914.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03704, over 972535.59 frames.], batch size: 23, lr: 2.99e-04
2022-05-05 19:01:30,924 INFO [train.py:715] (5/8) Epoch 7, batch 5900, loss[loss=0.1295, simple_loss=0.1975, pruned_loss=0.03078, over 4829.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03691, over 972736.49 frames.], batch size: 13, lr: 2.99e-04
2022-05-05 19:02:09,959 INFO [train.py:715] (5/8) Epoch 7, batch 5950, loss[loss=0.1504, simple_loss=0.2177, pruned_loss=0.04153, over 4780.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03667, over 972056.50 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 19:02:48,383 INFO [train.py:715] (5/8) Epoch 7, batch 6000, loss[loss=0.1673, simple_loss=0.2406, pruned_loss=0.04706, over 4803.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03665, over 971758.55 frames.], batch size: 24, lr: 2.99e-04
2022-05-05 19:02:48,384 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 19:02:58,047 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1933, pruned_loss=0.0119, over 914524.00 frames.
2022-05-05 19:03:36,916 INFO [train.py:715] (5/8) Epoch 7, batch 6050, loss[loss=0.1482, simple_loss=0.2176, pruned_loss=0.03939, over 4885.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03666, over 972020.32 frames.], batch size: 19, lr: 2.99e-04
2022-05-05 19:04:16,080 INFO [train.py:715] (5/8) Epoch 7, batch 6100, loss[loss=0.136, simple_loss=0.225, pruned_loss=0.02354, over 4799.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03665, over 972116.55 frames.], batch size: 21, lr: 2.99e-04
2022-05-05 19:04:55,379 INFO [train.py:715] (5/8) Epoch 7, batch 6150, loss[loss=0.1587, simple_loss=0.232, pruned_loss=0.04268, over 4980.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03723, over 972434.00 frames.], batch size: 25, lr: 2.99e-04
2022-05-05 19:05:33,828 INFO [train.py:715] (5/8) Epoch 7, batch 6200, loss[loss=0.155, simple_loss=0.2243, pruned_loss=0.04287, over 4853.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.03739, over 973343.18 frames.], batch size: 16, lr: 2.99e-04
2022-05-05 19:06:13,680 INFO [train.py:715] (5/8) Epoch 7, batch 6250, loss[loss=0.1618, simple_loss=0.2496, pruned_loss=0.03698, over 4877.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03728, over 972871.33 frames.], batch size: 22, lr: 2.99e-04
2022-05-05 19:06:52,573 INFO [train.py:715] (5/8) Epoch 7, batch 6300, loss[loss=0.1405, simple_loss=0.2125, pruned_loss=0.03421, over 4957.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03722, over 972516.27 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 19:07:30,973 INFO [train.py:715] (5/8) Epoch 7, batch 6350, loss[loss=0.1506, simple_loss=0.2297, pruned_loss=0.03576, over 4807.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03716, over 971599.54 frames.], batch size: 25, lr: 2.99e-04
2022-05-05 19:08:10,030 INFO [train.py:715] (5/8) Epoch 7, batch 6400, loss[loss=0.1287, simple_loss=0.1971, pruned_loss=0.03016, over 4798.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03717, over 971849.35 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 19:08:49,045 INFO [train.py:715] (5/8) Epoch 7, batch 6450, loss[loss=0.2062, simple_loss=0.2705, pruned_loss=0.07095, over 4904.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2183, pruned_loss=0.03792, over 972400.19 frames.], batch size: 17, lr: 2.99e-04
2022-05-05 19:09:27,584 INFO [train.py:715] (5/8) Epoch 7, batch 6500, loss[loss=0.1561, simple_loss=0.223, pruned_loss=0.04459, over 4939.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03783, over 972743.18 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 19:10:06,573 INFO [train.py:715] (5/8) Epoch 7, batch 6550, loss[loss=0.1334, simple_loss=0.1956, pruned_loss=0.03554, over 4799.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03849, over 972397.44 frames.], batch size: 12, lr: 2.99e-04
2022-05-05 19:10:46,393 INFO [train.py:715] (5/8) Epoch 7, batch 6600, loss[loss=0.1412, simple_loss=0.2209, pruned_loss=0.03075, over 4855.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03836, over 972017.62 frames.], batch size: 15, lr: 2.99e-04
2022-05-05 19:11:25,240 INFO [train.py:715] (5/8) Epoch 7, batch 6650, loss[loss=0.1448, simple_loss=0.2042, pruned_loss=0.04269, over 4944.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03744, over 972352.47 frames.], batch size: 23, lr: 2.99e-04
2022-05-05 19:12:04,485 INFO [train.py:715] (5/8) Epoch 7, batch 6700, loss[loss=0.1916, simple_loss=0.2641, pruned_loss=0.05953, over 4867.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03711, over 972235.83 frames.], batch size: 16, lr: 2.99e-04
2022-05-05 19:12:43,222 INFO [train.py:715] (5/8) Epoch 7, batch 6750, loss[loss=0.158, simple_loss=0.224, pruned_loss=0.04604, over 4961.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03681, over 971555.21 frames.], batch size: 35, lr: 2.99e-04
2022-05-05 19:13:22,215 INFO [train.py:715] (5/8) Epoch 7, batch 6800, loss[loss=0.1537, simple_loss=0.2202, pruned_loss=0.04366, over 4928.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03692, over 972865.17 frames.], batch size: 29, lr: 2.99e-04
2022-05-05 19:14:00,585 INFO [train.py:715] (5/8) Epoch 7, batch 6850, loss[loss=0.1203, simple_loss=0.1929, pruned_loss=0.02384, over 4769.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2171, pruned_loss=0.03676, over 972589.73 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 19:14:39,177 INFO [train.py:715] (5/8) Epoch 7, batch 6900, loss[loss=0.1119, simple_loss=0.1801, pruned_loss=0.02186, over 4795.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2166, pruned_loss=0.03657, over 972353.23 frames.], batch size: 12, lr: 2.98e-04
2022-05-05 19:15:18,697 INFO [train.py:715] (5/8) Epoch 7, batch 6950, loss[loss=0.13, simple_loss=0.2109, pruned_loss=0.02454, over 4826.00 frames.], tot_loss[loss=0.1455, simple_loss=0.217, pruned_loss=0.03703, over 971460.79 frames.], batch size: 27, lr: 2.98e-04
2022-05-05 19:15:56,859 INFO [train.py:715] (5/8) Epoch 7, batch 7000, loss[loss=0.1232, simple_loss=0.2041, pruned_loss=0.02112, over 4870.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2189, pruned_loss=0.03786, over 972142.55 frames.], batch size: 20, lr: 2.98e-04
2022-05-05 19:16:35,558 INFO [train.py:715] (5/8) Epoch 7, batch 7050, loss[loss=0.1179, simple_loss=0.1947, pruned_loss=0.02051, over 4978.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03742, over 972090.32 frames.], batch size: 24, lr: 2.98e-04
2022-05-05 19:17:14,120 INFO [train.py:715] (5/8) Epoch 7, batch 7100, loss[loss=0.1706, simple_loss=0.2389, pruned_loss=0.05117, over 4961.00 frames.], tot_loss[loss=0.147, simple_loss=0.2185, pruned_loss=0.03774, over 972339.09 frames.], batch size: 35, lr: 2.98e-04
2022-05-05 19:17:52,399 INFO [train.py:715] (5/8) Epoch 7, batch 7150, loss[loss=0.146, simple_loss=0.2132, pruned_loss=0.03937, over 4774.00 frames.], tot_loss[loss=0.1466, simple_loss=0.218, pruned_loss=0.03761, over 970985.24 frames.], batch size: 17, lr: 2.98e-04
2022-05-05 19:18:31,019 INFO [train.py:715] (5/8) Epoch 7, batch 7200, loss[loss=0.1866, simple_loss=0.2455, pruned_loss=0.06388, over 4986.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03755, over 971602.38 frames.], batch size: 14, lr: 2.98e-04
2022-05-05 19:19:10,025 INFO [train.py:715] (5/8) Epoch 7, batch 7250, loss[loss=0.1505, simple_loss=0.2312, pruned_loss=0.03488, over 4915.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03776, over 972557.31 frames.], batch size: 29, lr: 2.98e-04
2022-05-05 19:19:49,673 INFO [train.py:715] (5/8) Epoch 7, batch 7300, loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03314, over 4954.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03777, over 972531.93 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:20:28,207 INFO [train.py:715] (5/8) Epoch 7, batch 7350, loss[loss=0.2011, simple_loss=0.27, pruned_loss=0.06611, over 4782.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03808, over 972037.89 frames.], batch size: 18, lr: 2.98e-04
2022-05-05 19:21:06,663 INFO [train.py:715] (5/8) Epoch 7, batch 7400, loss[loss=0.1332, simple_loss=0.2088, pruned_loss=0.02879, over 4836.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03723, over 971520.79 frames.], batch size: 30, lr: 2.98e-04
2022-05-05 19:21:45,792 INFO [train.py:715] (5/8) Epoch 7, batch 7450, loss[loss=0.1164, simple_loss=0.1872, pruned_loss=0.02278, over 4859.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03709, over 971036.87 frames.], batch size: 20, lr: 2.98e-04
2022-05-05 19:22:23,999 INFO [train.py:715] (5/8) Epoch 7, batch 7500, loss[loss=0.1537, simple_loss=0.2324, pruned_loss=0.03755, over 4827.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03737, over 970561.06 frames.], batch size: 13, lr: 2.98e-04
2022-05-05 19:23:02,796 INFO [train.py:715] (5/8) Epoch 7, batch 7550, loss[loss=0.1536, simple_loss=0.2266, pruned_loss=0.04029, over 4756.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03762, over 970765.53 frames.], batch size: 12, lr: 2.98e-04
2022-05-05 19:23:41,662 INFO [train.py:715] (5/8) Epoch 7, batch 7600, loss[loss=0.1757, simple_loss=0.2436, pruned_loss=0.0539, over 4952.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03749, over 971608.84 frames.], batch size: 35, lr: 2.98e-04
2022-05-05 19:24:20,770 INFO [train.py:715] (5/8) Epoch 7, batch 7650, loss[loss=0.1525, simple_loss=0.2193, pruned_loss=0.04281, over 4893.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03744, over 971188.66 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:24:59,079 INFO [train.py:715] (5/8) Epoch 7, batch 7700, loss[loss=0.1517, simple_loss=0.2216, pruned_loss=0.04091, over 4705.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2172, pruned_loss=0.0373, over 971757.58 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:25:38,045 INFO [train.py:715] (5/8) Epoch 7, batch 7750, loss[loss=0.1552, simple_loss=0.2188, pruned_loss=0.04585, over 4923.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2188, pruned_loss=0.03823, over 972865.77 frames.], batch size: 39, lr: 2.98e-04
2022-05-05 19:26:17,069 INFO [train.py:715] (5/8) Epoch 7, batch 7800, loss[loss=0.1771, simple_loss=0.2357, pruned_loss=0.05921, over 4918.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03839, over 973229.66 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:26:55,228 INFO [train.py:715] (5/8) Epoch 7, batch 7850, loss[loss=0.1267, simple_loss=0.1968, pruned_loss=0.02826, over 4847.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2187, pruned_loss=0.03825, over 973329.98 frames.], batch size: 13, lr: 2.98e-04
2022-05-05 19:27:34,425 INFO [train.py:715] (5/8) Epoch 7, batch 7900, loss[loss=0.1628, simple_loss=0.2409, pruned_loss=0.04232, over 4828.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2193, pruned_loss=0.03852, over 972755.92 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:28:13,172 INFO [train.py:715] (5/8) Epoch 7, batch 7950, loss[loss=0.1887, simple_loss=0.2534, pruned_loss=0.06197, over 4694.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2199, pruned_loss=0.03873, over 971424.59 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:28:52,648 INFO [train.py:715] (5/8) Epoch 7, batch 8000, loss[loss=0.1293, simple_loss=0.2069, pruned_loss=0.02578, over 4879.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.0382, over 971634.72 frames.], batch size: 16, lr: 2.98e-04
2022-05-05 19:29:30,737 INFO [train.py:715] (5/8) Epoch 7, batch 8050, loss[loss=0.1545, simple_loss=0.2266, pruned_loss=0.04124, over 4814.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03837, over 972220.17 frames.], batch size: 25, lr: 2.98e-04
2022-05-05 19:30:09,296 INFO [train.py:715] (5/8) Epoch 7, batch 8100, loss[loss=0.1415, simple_loss=0.2189, pruned_loss=0.03199, over 4968.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03826, over 971465.07 frames.], batch size: 24, lr: 2.98e-04
2022-05-05 19:30:48,379 INFO [train.py:715] (5/8) Epoch 7, batch 8150, loss[loss=0.1523, simple_loss=0.2164, pruned_loss=0.04405, over 4986.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2184, pruned_loss=0.03822, over 972516.11 frames.], batch size: 35, lr: 2.98e-04
2022-05-05 19:31:26,682 INFO [train.py:715] (5/8) Epoch 7, batch 8200, loss[loss=0.1353, simple_loss=0.218, pruned_loss=0.02634, over 4808.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03784, over 972585.75 frames.], batch size: 26, lr: 2.98e-04
2022-05-05 19:32:05,127 INFO [train.py:715] (5/8) Epoch 7, batch 8250, loss[loss=0.1556, simple_loss=0.2315, pruned_loss=0.03981, over 4809.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.0373, over 972253.31 frames.], batch size: 21, lr: 2.98e-04
2022-05-05 19:32:43,780 INFO [train.py:715] (5/8) Epoch 7, batch 8300, loss[loss=0.127, simple_loss=0.2026, pruned_loss=0.02564, over 4770.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03699, over 972678.47 frames.], batch size: 12, lr: 2.98e-04
2022-05-05 19:33:22,690 INFO [train.py:715] (5/8) Epoch 7, batch 8350, loss[loss=0.1436, simple_loss=0.2241, pruned_loss=0.03155, over 4872.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03754, over 972624.45 frames.], batch size: 22, lr: 2.98e-04
2022-05-05 19:34:00,642 INFO [train.py:715] (5/8) Epoch 7, batch 8400, loss[loss=0.1309, simple_loss=0.1986, pruned_loss=0.03156, over 4853.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.0379, over 972561.24 frames.], batch size: 30, lr: 2.98e-04
2022-05-05 19:34:39,717 INFO [train.py:715] (5/8) Epoch 7, batch 8450, loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03232, over 4973.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03742, over 972585.70 frames.], batch size: 25, lr: 2.98e-04
2022-05-05 19:35:18,876 INFO [train.py:715] (5/8) Epoch 7, batch 8500, loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03291, over 4910.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.0371, over 972352.75 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:35:58,055 INFO [train.py:715] (5/8) Epoch 7, batch 8550, loss[loss=0.144, simple_loss=0.2182, pruned_loss=0.03493, over 4755.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03735, over 972219.15 frames.], batch size: 18, lr: 2.97e-04
2022-05-05 19:36:36,295 INFO [train.py:715] (5/8) Epoch 7, batch 8600, loss[loss=0.1589, simple_loss=0.2249, pruned_loss=0.04639, over 4721.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03694, over 972099.94 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:37:14,959 INFO [train.py:715] (5/8) Epoch 7, batch 8650, loss[loss=0.1382, simple_loss=0.2044, pruned_loss=0.03596, over 4973.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03636, over 972143.86 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:37:54,307 INFO [train.py:715] (5/8) Epoch 7, batch 8700, loss[loss=0.1365, simple_loss=0.2015, pruned_loss=0.03578, over 4766.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03711, over 972935.69 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:38:32,517 INFO [train.py:715] (5/8) Epoch 7, batch 8750, loss[loss=0.1452, simple_loss=0.2238, pruned_loss=0.03329, over 4891.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2171, pruned_loss=0.03707, over 972700.28 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:39:11,384 INFO [train.py:715] (5/8) Epoch 7, batch 8800, loss[loss=0.1248, simple_loss=0.183, pruned_loss=0.03328, over 4952.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03696, over 972277.10 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:39:50,318 INFO [train.py:715] (5/8) Epoch 7, batch 8850, loss[loss=0.1463, simple_loss=0.2132, pruned_loss=0.0397, over 4789.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03741, over 972233.01 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:40:30,012 INFO [train.py:715] (5/8) Epoch 7, batch 8900, loss[loss=0.1696, simple_loss=0.2345, pruned_loss=0.05229, over 4906.00 frames.], tot_loss[loss=0.146, simple_loss=0.2178, pruned_loss=0.03711, over 972218.69 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:41:08,237 INFO [train.py:715] (5/8) Epoch 7, batch 8950, loss[loss=0.1409, simple_loss=0.215, pruned_loss=0.03344, over 4872.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03694, over 972335.18 frames.], batch size: 13, lr: 2.97e-04
2022-05-05 19:41:46,835 INFO [train.py:715] (5/8) Epoch 7, batch 9000, loss[loss=0.1392, simple_loss=0.224, pruned_loss=0.02725, over 4794.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2176, pruned_loss=0.03665, over 971690.85 frames.], batch size: 18, lr: 2.97e-04
2022-05-05 19:41:46,835 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 19:41:56,559 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1932, pruned_loss=0.01192, over 914524.00 frames.
2022-05-05 19:42:35,338 INFO [train.py:715] (5/8) Epoch 7, batch 9050, loss[loss=0.1378, simple_loss=0.2143, pruned_loss=0.03061, over 4836.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03644, over 972695.21 frames.], batch size: 15, lr: 2.97e-04
2022-05-05 19:43:15,395 INFO [train.py:715] (5/8) Epoch 7, batch 9100, loss[loss=0.1444, simple_loss=0.2203, pruned_loss=0.03429, over 4829.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03751, over 972798.60 frames.], batch size: 30, lr: 2.97e-04
2022-05-05 19:43:54,070 INFO [train.py:715] (5/8) Epoch 7, batch 9150, loss[loss=0.1476, simple_loss=0.234, pruned_loss=0.03058, over 4935.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03741, over 972117.53 frames.], batch size: 23, lr: 2.97e-04
2022-05-05 19:44:32,871 INFO [train.py:715] (5/8) Epoch 7, batch 9200, loss[loss=0.1616, simple_loss=0.2343, pruned_loss=0.0444, over 4856.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03699, over 973870.97 frames.], batch size: 20, lr: 2.97e-04
2022-05-05 19:45:12,206 INFO [train.py:715] (5/8) Epoch 7, batch 9250, loss[loss=0.1426, simple_loss=0.2236, pruned_loss=0.03078, over 4923.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2188, pruned_loss=0.03743, over 973779.18 frames.], batch size: 17, lr: 2.97e-04
2022-05-05 19:45:51,291 INFO [train.py:715] (5/8) Epoch 7, batch 9300, loss[loss=0.1101, simple_loss=0.1819, pruned_loss=0.01912, over 4752.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2186, pruned_loss=0.03732, over 973879.90 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:46:30,348 INFO [train.py:715] (5/8) Epoch 7, batch 9350, loss[loss=0.1294, simple_loss=0.2119, pruned_loss=0.02344, over 4735.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03744, over 973295.26 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:47:08,480 INFO [train.py:715] (5/8) Epoch 7, batch 9400, loss[loss=0.1695, simple_loss=0.234, pruned_loss=0.05253, over 4843.00 frames.], tot_loss[loss=0.147, simple_loss=0.2188, pruned_loss=0.0376, over 973359.90 frames.], batch size: 15, lr: 2.97e-04
2022-05-05 19:47:48,271 INFO [train.py:715] (5/8) Epoch 7, batch 9450, loss[loss=0.1454, simple_loss=0.2136, pruned_loss=0.0386, over 4965.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03859, over 972888.06 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:48:27,278 INFO [train.py:715] (5/8) Epoch 7, batch 9500, loss[loss=0.1405, simple_loss=0.2177, pruned_loss=0.03168, over 4791.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03884, over 972855.22 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:49:05,878 INFO [train.py:715] (5/8) Epoch 7, batch 9550, loss[loss=0.1373, simple_loss=0.1982, pruned_loss=0.03813, over 4964.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03869, over 972636.65 frames.], batch size: 15, lr: 2.97e-04
2022-05-05 19:49:44,839 INFO [train.py:715] (5/8) Epoch 7, batch 9600, loss[loss=0.1423, simple_loss=0.2083, pruned_loss=0.0382, over 4840.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03827, over 972160.48 frames.], batch size: 32, lr: 2.97e-04
2022-05-05 19:50:23,440 INFO [train.py:715] (5/8) Epoch 7, batch 9650, loss[loss=0.1371, simple_loss=0.2079, pruned_loss=0.03314, over 4867.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03813, over 972581.32 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:51:02,959 INFO [train.py:715] (5/8) Epoch 7, batch 9700, loss[loss=0.1633, simple_loss=0.2412, pruned_loss=0.04272, over 4949.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2193, pruned_loss=0.03775, over 973724.55 frames.], batch size: 29, lr: 2.97e-04
2022-05-05 19:51:41,571 INFO [train.py:715] (5/8) Epoch 7, batch 9750, loss[loss=0.1302, simple_loss=0.2044, pruned_loss=0.02804, over 4780.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03766, over 973340.51 frames.], batch size: 17, lr: 2.97e-04
2022-05-05 19:52:20,960 INFO [train.py:715] (5/8) Epoch 7, batch 9800, loss[loss=0.149, simple_loss=0.2155, pruned_loss=0.04127, over 4881.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03778, over 972429.64 frames.], batch size: 32, lr: 2.97e-04
2022-05-05 19:52:59,042 INFO [train.py:715] (5/8) Epoch 7, batch 9850, loss[loss=0.1714, simple_loss=0.2291, pruned_loss=0.05684, over 4988.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2189, pruned_loss=0.03798, over 972583.99 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:53:37,273 INFO [train.py:715] (5/8) Epoch 7, batch 9900, loss[loss=0.1425, simple_loss=0.2156, pruned_loss=0.03465, over 4817.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03762, over 973537.14 frames.], batch size: 27, lr: 2.97e-04
2022-05-05 19:54:16,173 INFO [train.py:715] (5/8) Epoch 7, batch 9950, loss[loss=0.1106, simple_loss=0.1755, pruned_loss=0.02287, over 4752.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03744, over 972610.55 frames.], batch size: 12, lr: 2.97e-04
2022-05-05 19:54:55,286 INFO [train.py:715] (5/8) Epoch 7, batch 10000, loss[loss=0.1465, simple_loss=0.2189, pruned_loss=0.03702, over 4934.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.0376, over 973131.99 frames.], batch size: 23, lr: 2.97e-04
2022-05-05 19:55:33,965 INFO [train.py:715] (5/8) Epoch 7, batch 10050, loss[loss=0.1314, simple_loss=0.2128, pruned_loss=0.02498, over 4742.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.0374, over 973117.60 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:56:12,504 INFO [train.py:715] (5/8) Epoch 7, batch 10100, loss[loss=0.1511, simple_loss=0.2181, pruned_loss=0.04205, over 4974.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03723, over 973246.34 frames.], batch size: 39, lr: 2.97e-04
2022-05-05 19:56:51,798 INFO [train.py:715] (5/8) Epoch 7, batch 10150, loss[loss=0.1649, simple_loss=0.2341, pruned_loss=0.04784, over 4781.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03737, over 972930.24 frames.], batch size: 18, lr: 2.97e-04
2022-05-05 19:57:30,413 INFO [train.py:715] (5/8) Epoch 7, batch 10200, loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03483, over 4913.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03692, over 973356.96 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:58:09,059 INFO [train.py:715] (5/8) Epoch 7, batch 10250, loss[loss=0.1626, simple_loss=0.2183, pruned_loss=0.05344, over 4774.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03738, over 973162.95 frames.], batch size: 14, lr: 2.96e-04
2022-05-05 19:58:48,252 INFO [train.py:715] (5/8) Epoch 7, batch 10300, loss[loss=0.1384, simple_loss=0.2063, pruned_loss=0.03522, over 4846.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.0373, over 972668.94 frames.], batch size: 32, lr: 2.96e-04
2022-05-05 19:59:26,899 INFO [train.py:715] (5/8) Epoch 7, batch 10350, loss[loss=0.1508, simple_loss=0.2168, pruned_loss=0.04242, over 4871.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2184, pruned_loss=0.03789, over 972710.02 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:00:05,911 INFO [train.py:715] (5/8) Epoch 7, batch 10400, loss[loss=0.1408, simple_loss=0.2081, pruned_loss=0.03679, over 4775.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03758, over 972625.33 frames.], batch size: 14, lr: 2.96e-04
2022-05-05 20:00:44,692 INFO [train.py:715] (5/8) Epoch 7, batch 10450, loss[loss=0.133, simple_loss=0.201, pruned_loss=0.03252, over 4808.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03774, over 972377.52 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:01:24,295 INFO [train.py:715] (5/8) Epoch 7, batch 10500, loss[loss=0.1343, simple_loss=0.2044, pruned_loss=0.03213, over 4748.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.03739, over 972250.64 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:02:03,022 INFO [train.py:715] (5/8) Epoch 7, batch 10550, loss[loss=0.1605, simple_loss=0.2318, pruned_loss=0.04462, over 4705.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03708, over 971341.54 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:02:41,164 INFO [train.py:715] (5/8) Epoch 7, batch 10600, loss[loss=0.1219, simple_loss=0.1994, pruned_loss=0.02218, over 4802.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2178, pruned_loss=0.03685, over 971329.62 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:03:20,355 INFO [train.py:715] (5/8) Epoch 7, batch 10650, loss[loss=0.1333, simple_loss=0.2122, pruned_loss=0.02717, over 4811.00 frames.], tot_loss[loss=0.146, simple_loss=0.2181, pruned_loss=0.03693, over 971434.90 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:03:59,396 INFO [train.py:715] (5/8) Epoch 7, batch 10700, loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03528, over 4901.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2178, pruned_loss=0.03651, over 971101.12 frames.], batch size: 22, lr: 2.96e-04
2022-05-05 20:04:38,882 INFO [train.py:715] (5/8) Epoch 7, batch 10750, loss[loss=0.1526, simple_loss=0.2163, pruned_loss=0.0444, over 4967.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03708, over 971680.01 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:05:17,664 INFO [train.py:715] (5/8) Epoch 7, batch 10800, loss[loss=0.1286, simple_loss=0.1994, pruned_loss=0.02889, over 4985.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03703, over 971991.62 frames.], batch size: 25, lr: 2.96e-04
2022-05-05 20:05:57,422 INFO [train.py:715] (5/8) Epoch 7, batch 10850, loss[loss=0.1341, simple_loss=0.1898, pruned_loss=0.03926, over 4816.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03658, over 972329.24 frames.], batch size: 13, lr: 2.96e-04
2022-05-05 20:06:35,666 INFO [train.py:715] (5/8) Epoch 7, batch 10900, loss[loss=0.1631, simple_loss=0.2306, pruned_loss=0.04779, over 4871.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2171, pruned_loss=0.03633, over 972383.06 frames.], batch size: 32, lr: 2.96e-04
2022-05-05 20:07:14,755 INFO [train.py:715] (5/8) Epoch 7, batch 10950, loss[loss=0.1806, simple_loss=0.2467, pruned_loss=0.05727, over 4900.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03717, over 973218.49 frames.], batch size: 19, lr: 2.96e-04
2022-05-05 20:07:53,906 INFO [train.py:715] (5/8) Epoch 7, batch 11000, loss[loss=0.1682, simple_loss=0.2323, pruned_loss=0.05209, over 4985.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03721, over 973643.81 frames.], batch size: 28, lr: 2.96e-04
2022-05-05 20:08:32,747 INFO [train.py:715] (5/8) Epoch 7, batch 11050, loss[loss=0.1679, simple_loss=0.2343, pruned_loss=0.05082, over 4957.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03705, over 973500.07 frames.], batch size: 35, lr: 2.96e-04
2022-05-05 20:09:11,470 INFO [train.py:715] (5/8) Epoch 7, batch 11100, loss[loss=0.1744, simple_loss=0.2521, pruned_loss=0.04835, over 4779.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03691, over 973229.23 frames.], batch size: 17, lr: 2.96e-04
2022-05-05 20:09:50,083 INFO [train.py:715] (5/8) Epoch 7, batch 11150, loss[loss=0.1793, simple_loss=0.2397, pruned_loss=0.05942, over 4933.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.0371, over 973241.99 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:10:29,709 INFO [train.py:715] (5/8) Epoch 7, batch 11200, loss[loss=0.1312, simple_loss=0.202, pruned_loss=0.03026, over 4761.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2183, pruned_loss=0.03728, over 973151.22 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:11:08,078 INFO [train.py:715] (5/8) Epoch 7, batch 11250, loss[loss=0.133, simple_loss=0.2123, pruned_loss=0.02685, over 4811.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.0376, over 972213.67 frames.], batch size: 25, lr: 2.96e-04
2022-05-05 20:11:46,239 INFO [train.py:715] (5/8) Epoch 7, batch 11300, loss[loss=0.1601, simple_loss=0.2307, pruned_loss=0.04479, over 4893.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03767, over 972688.41 frames.], batch size: 32, lr: 2.96e-04
2022-05-05 20:12:25,979 INFO [train.py:715] (5/8) Epoch 7, batch 11350, loss[loss=0.1504, simple_loss=0.2248, pruned_loss=0.03801, over 4979.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03697, over 972525.67 frames.], batch size: 40, lr: 2.96e-04
2022-05-05 20:13:04,522 INFO [train.py:715] (5/8) Epoch 7, batch 11400, loss[loss=0.1645, simple_loss=0.2279, pruned_loss=0.05054, over 4921.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.0366, over 972366.44 frames.], batch size: 39, lr: 2.96e-04
2022-05-05 20:13:43,553 INFO [train.py:715] (5/8) Epoch 7, batch 11450, loss[loss=0.1269, simple_loss=0.1979, pruned_loss=0.02792, over 4772.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03629, over 972429.16 frames.], batch size: 12, lr: 2.96e-04
2022-05-05 20:14:22,145 INFO [train.py:715] (5/8) Epoch 7, batch 11500, loss[loss=0.1639, simple_loss=0.2229, pruned_loss=0.05246, over 4688.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03707, over 972900.21 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:15:01,729 INFO [train.py:715] (5/8) Epoch 7, batch 11550, loss[loss=0.1454, simple_loss=0.2098, pruned_loss=0.0405, over 4854.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03708, over 972814.53 frames.], batch size: 13, lr: 2.96e-04
2022-05-05 20:15:39,999 INFO [train.py:715] (5/8) Epoch 7, batch 11600, loss[loss=0.1483, simple_loss=0.2138, pruned_loss=0.04143, over 4787.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.03685, over 972402.47 frames.], batch size: 14, lr: 2.96e-04
2022-05-05 20:16:18,808 INFO [train.py:715] (5/8) Epoch 7, batch 11650, loss[loss=0.1167, simple_loss=0.1909, pruned_loss=0.02128, over 4953.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03633, over 972366.64 frames.], batch size: 24, lr: 2.96e-04
2022-05-05 20:16:58,203 INFO [train.py:715] (5/8) Epoch 7, batch 11700, loss[loss=0.1515, simple_loss=0.2238, pruned_loss=0.03956, over 4821.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03631, over 972458.19 frames.], batch size: 26, lr: 2.96e-04
2022-05-05 20:17:36,280 INFO [train.py:715] (5/8) Epoch 7, batch 11750, loss[loss=0.1456, simple_loss=0.2227, pruned_loss=0.03428, over 4837.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03619, over 972503.32 frames.], batch size: 25, lr: 2.96e-04
2022-05-05 20:18:15,076 INFO [train.py:715] (5/8) Epoch 7, batch 11800, loss[loss=0.1274, simple_loss=0.2009, pruned_loss=0.02699, over 4858.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03661, over 972246.94 frames.], batch size: 32, lr: 2.96e-04
2022-05-05 20:18:54,266 INFO [train.py:715] (5/8) Epoch 7, batch 11850, loss[loss=0.1436, simple_loss=0.2181, pruned_loss=0.03456, over 4759.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03644, over 971835.07 frames.], batch size: 19, lr: 2.96e-04
2022-05-05 20:19:32,625 INFO [train.py:715] (5/8) Epoch 7, batch 11900, loss[loss=0.1726, simple_loss=0.2368, pruned_loss=0.05423, over 4897.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03668, over 972213.73 frames.], batch size: 22, lr: 2.96e-04
2022-05-05 20:20:11,921 INFO [train.py:715] (5/8) Epoch 7, batch 11950, loss[loss=0.1555, simple_loss=0.2222, pruned_loss=0.04435, over 4748.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03646, over 971714.19 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:20:50,619 INFO [train.py:715] (5/8) Epoch 7, batch 12000, loss[loss=0.1298, simple_loss=0.1965, pruned_loss=0.03149, over 4739.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2169, pruned_loss=0.03619, over 971624.55 frames.], batch size: 16, lr: 2.95e-04
2022-05-05 20:20:50,620 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 20:21:00,227 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.108, simple_loss=0.193, pruned_loss=0.01154, over 914524.00 frames.
2022-05-05 20:21:38,891 INFO [train.py:715] (5/8) Epoch 7, batch 12050, loss[loss=0.1365, simple_loss=0.2132, pruned_loss=0.02988, over 4830.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2175, pruned_loss=0.0366, over 971594.33 frames.], batch size: 26, lr: 2.95e-04
2022-05-05 20:22:18,261 INFO [train.py:715] (5/8) Epoch 7, batch 12100, loss[loss=0.1583, simple_loss=0.2265, pruned_loss=0.045, over 4815.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03722, over 972330.36 frames.], batch size: 21, lr: 2.95e-04
2022-05-05 20:22:56,854 INFO [train.py:715] (5/8) Epoch 7, batch 12150, loss[loss=0.1471, simple_loss=0.2145, pruned_loss=0.03987, over 4982.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03746, over 971798.02 frames.], batch size: 28, lr: 2.95e-04
2022-05-05 20:23:35,617 INFO [train.py:715] (5/8) Epoch 7, batch 12200, loss[loss=0.1296, simple_loss=0.1918, pruned_loss=0.03366, over 4968.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.03731, over 972294.80 frames.], batch size: 24, lr: 2.95e-04
2022-05-05 20:24:14,745 INFO [train.py:715] (5/8) Epoch 7, batch 12250, loss[loss=0.1451, simple_loss=0.2153, pruned_loss=0.03749, over 4928.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03676, over 973245.21 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:24:53,359 INFO [train.py:715] (5/8) Epoch 7, batch 12300, loss[loss=0.1437, simple_loss=0.2195, pruned_loss=0.03398, over 4929.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03682, over 972939.94 frames.], batch size: 38, lr: 2.95e-04
2022-05-05 20:25:35,089 INFO [train.py:715] (5/8) Epoch 7, batch 12350, loss[loss=0.1612, simple_loss=0.2323, pruned_loss=0.0451, over 4799.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03679, over 973137.90 frames.], batch size: 21, lr: 2.95e-04
2022-05-05 20:26:13,786 INFO [train.py:715] (5/8) Epoch 7, batch 12400, loss[loss=0.1333, simple_loss=0.2125, pruned_loss=0.02708, over 4782.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03669, over 973524.97 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:26:53,003 INFO [train.py:715] (5/8) Epoch 7, batch 12450, loss[loss=0.1407, simple_loss=0.2146, pruned_loss=0.03339, over 4904.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03713, over 972990.22 frames.], batch size: 22, lr: 2.95e-04
2022-05-05 20:27:31,401 INFO [train.py:715] (5/8) Epoch 7, batch 12500, loss[loss=0.1735, simple_loss=0.2331, pruned_loss=0.05689, over 4851.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2179, pruned_loss=0.03794, over 973191.69 frames.], batch size: 32, lr: 2.95e-04
2022-05-05 20:28:10,095 INFO [train.py:715] (5/8) Epoch 7, batch 12550, loss[loss=0.1333, simple_loss=0.2117, pruned_loss=0.02752, over 4837.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2183, pruned_loss=0.0382, over 973229.24 frames.], batch size: 15, lr: 2.95e-04
2022-05-05 20:28:49,194 INFO [train.py:715] (5/8) Epoch 7, batch 12600, loss[loss=0.112, simple_loss=0.1849, pruned_loss=0.01952, over 4780.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2186, pruned_loss=0.03806, over 973707.80 frames.], batch size: 12, lr: 2.95e-04
2022-05-05 20:29:27,375 INFO [train.py:715] (5/8) Epoch 7, batch 12650, loss[loss=0.1444, simple_loss=0.2082, pruned_loss=0.04028, over 4828.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03758, over 973211.12 frames.], batch size: 13, lr: 2.95e-04
2022-05-05 20:30:06,577 INFO [train.py:715] (5/8) Epoch 7, batch 12700, loss[loss=0.1348, simple_loss=0.2113, pruned_loss=0.02914, over 4867.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03745, over 972616.69 frames.], batch size: 39, lr: 2.95e-04
2022-05-05 20:30:44,739 INFO [train.py:715] (5/8) Epoch 7, batch 12750, loss[loss=0.1602, simple_loss=0.2194, pruned_loss=0.05052, over 4978.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03756, over 972299.79 frames.], batch size: 35, lr: 2.95e-04
2022-05-05 20:31:23,967 INFO [train.py:715] (5/8) Epoch 7, batch 12800, loss[loss=0.1174, simple_loss=0.1976, pruned_loss=0.01858, over 4913.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03691, over 972603.47 frames.], batch size: 29, lr: 2.95e-04
2022-05-05 20:32:02,915 INFO [train.py:715] (5/8) Epoch 7, batch 12850, loss[loss=0.1446, simple_loss=0.2247, pruned_loss=0.03222, over 4982.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03687, over 972124.89 frames.], batch size: 24, lr: 2.95e-04
2022-05-05 20:32:41,511 INFO [train.py:715] (5/8) Epoch 7, batch 12900, loss[loss=0.1456, simple_loss=0.2146, pruned_loss=0.03831, over 4945.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.03749, over 972315.42 frames.], batch size: 35, lr: 2.95e-04
2022-05-05 20:33:20,983 INFO [train.py:715] (5/8) Epoch 7, batch 12950, loss[loss=0.1389, simple_loss=0.2061, pruned_loss=0.03588, over 4880.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03742, over 972746.98 frames.], batch size: 16, lr: 2.95e-04
2022-05-05 20:33:59,930 INFO [train.py:715] (5/8) Epoch 7, batch 13000, loss[loss=0.1462, simple_loss=0.2184, pruned_loss=0.03702, over 4986.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2179, pruned_loss=0.03745, over 973594.06 frames.], batch size: 15, lr: 2.95e-04
2022-05-05 20:34:38,877 INFO [train.py:715] (5/8) Epoch 7, batch 13050, loss[loss=0.1445, simple_loss=0.2105, pruned_loss=0.0393, over 4949.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03733, over 972625.18 frames.], batch size: 35, lr: 2.95e-04
2022-05-05 20:35:17,656 INFO [train.py:715] (5/8) Epoch 7, batch 13100, loss[loss=0.1205, simple_loss=0.1916, pruned_loss=0.0247, over 4989.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.03691, over 972588.13 frames.], batch size: 20, lr: 2.95e-04
2022-05-05 20:35:57,325 INFO [train.py:715] (5/8) Epoch 7, batch 13150, loss[loss=0.1742, simple_loss=0.236, pruned_loss=0.0562, over 4691.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 972979.54 frames.], batch size: 15, lr: 2.95e-04
2022-05-05 20:36:35,852 INFO [train.py:715] (5/8) Epoch 7, batch 13200, loss[loss=0.1239, simple_loss=0.1857, pruned_loss=0.03105, over 4817.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03655, over 972285.75 frames.], batch size: 12, lr: 2.95e-04
2022-05-05 20:37:15,490 INFO [train.py:715] (5/8) Epoch 7, batch 13250, loss[loss=0.1663, simple_loss=0.2311, pruned_loss=0.05075, over 4910.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03653, over 972518.05 frames.], batch size: 17, lr: 2.95e-04
2022-05-05 20:37:54,875 INFO [train.py:715] (5/8) Epoch 7, batch 13300, loss[loss=0.1414, simple_loss=0.2027, pruned_loss=0.0401, over 4830.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03645, over 972315.70 frames.], batch size: 30, lr: 2.95e-04
2022-05-05 20:38:33,805 INFO [train.py:715] (5/8) Epoch 7, batch 13350, loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.03922, over 4809.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.0362, over 972046.83 frames.], batch size: 26, lr: 2.95e-04
2022-05-05 20:39:12,811 INFO [train.py:715] (5/8) Epoch 7, batch 13400, loss[loss=0.1583, simple_loss=0.2295, pruned_loss=0.0435, over 4773.00 frames.], tot_loss[loss=0.146, simple_loss=0.2182, pruned_loss=0.03687, over 972287.27 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:39:51,469 INFO [train.py:715] (5/8) Epoch 7, batch 13450, loss[loss=0.1535, simple_loss=0.2251, pruned_loss=0.04099, over 4777.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.0373, over 972347.34 frames.], batch size: 17, lr: 2.95e-04
2022-05-05 20:40:30,902 INFO [train.py:715] (5/8) Epoch 7, batch 13500, loss[loss=0.1462, simple_loss=0.2232, pruned_loss=0.03459, over 4850.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03715, over 972597.89 frames.], batch size: 13, lr: 2.95e-04
2022-05-05 20:41:09,547 INFO [train.py:715] (5/8) Epoch 7, batch 13550, loss[loss=0.1541, simple_loss=0.2219, pruned_loss=0.04317, over 4906.00 frames.], tot_loss[loss=0.1457, simple_loss=0.217, pruned_loss=0.03722, over 972376.21 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:41:48,023 INFO [train.py:715] (5/8) Epoch 7, batch 13600, loss[loss=0.1664, simple_loss=0.2381, pruned_loss=0.04736, over 4930.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2177, pruned_loss=0.0374, over 972049.77 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:42:26,946 INFO [train.py:715] (5/8) Epoch 7, batch 13650, loss[loss=0.1333, simple_loss=0.2042, pruned_loss=0.03119, over 4928.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03712, over 971592.93 frames.], batch size: 23, lr: 2.95e-04
2022-05-05 20:43:05,965 INFO [train.py:715] (5/8) Epoch 7, batch 13700, loss[loss=0.1572, simple_loss=0.2245, pruned_loss=0.0449, over 4861.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03681, over 971346.08 frames.], batch size: 32, lr: 2.95e-04
2022-05-05 20:43:44,943 INFO [train.py:715] (5/8) Epoch 7, batch 13750, loss[loss=0.172, simple_loss=0.232, pruned_loss=0.05603, over 4924.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03732, over 971712.93 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:44:23,923 INFO [train.py:715] (5/8) Epoch 7, batch 13800, loss[loss=0.1209, simple_loss=0.1898, pruned_loss=0.02603, over 4850.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2178, pruned_loss=0.03757, over 971039.97 frames.], batch size: 30, lr: 2.94e-04
2022-05-05 20:45:03,233 INFO [train.py:715] (5/8) Epoch 7, batch 13850, loss[loss=0.1518, simple_loss=0.2239, pruned_loss=0.0398, over 4813.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2177, pruned_loss=0.03761, over 970936.60 frames.], batch size: 21, lr: 2.94e-04
2022-05-05 20:45:41,499 INFO [train.py:715] (5/8) Epoch 7, batch 13900, loss[loss=0.1499, simple_loss=0.2255, pruned_loss=0.03711, over 4926.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2169, pruned_loss=0.03697, over 971402.04 frames.], batch size: 23, lr: 2.94e-04
2022-05-05 20:46:20,517 INFO [train.py:715] (5/8) Epoch 7, batch 13950, loss[loss=0.144, simple_loss=0.2155, pruned_loss=0.03624, over 4932.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03675, over 971910.92 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:46:59,561 INFO [train.py:715] (5/8) Epoch 7, batch 14000, loss[loss=0.1402, simple_loss=0.2095, pruned_loss=0.03549, over 4857.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03691, over 971943.79 frames.], batch size: 20, lr: 2.94e-04
2022-05-05 20:47:38,923 INFO [train.py:715] (5/8) Epoch 7, batch 14050, loss[loss=0.1602, simple_loss=0.226, pruned_loss=0.04716, over 4819.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2178, pruned_loss=0.0377, over 971909.99 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 20:48:18,051 INFO [train.py:715] (5/8) Epoch 7, batch 14100, loss[loss=0.1468, simple_loss=0.2222, pruned_loss=0.03571, over 4769.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03743, over 972208.15 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 20:48:56,864 INFO [train.py:715] (5/8) Epoch 7, batch 14150, loss[loss=0.1858, simple_loss=0.247, pruned_loss=0.06227, over 4771.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2176, pruned_loss=0.0377, over 972866.58 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 20:49:36,151 INFO [train.py:715] (5/8) Epoch 7, batch 14200, loss[loss=0.1712, simple_loss=0.2349, pruned_loss=0.05381, over 4796.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03802, over 972280.18 frames.], batch size: 24, lr: 2.94e-04
2022-05-05 20:50:14,409 INFO [train.py:715] (5/8) Epoch 7, batch 14250, loss[loss=0.1218, simple_loss=0.1992, pruned_loss=0.02225, over 4948.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.0382, over 972508.54 frames.], batch size: 23, lr: 2.94e-04
2022-05-05 20:50:53,730 INFO [train.py:715] (5/8) Epoch 7, batch 14300, loss[loss=0.172, simple_loss=0.2387, pruned_loss=0.05262, over 4845.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2182, pruned_loss=0.03842, over 971651.52 frames.], batch size: 30, lr: 2.94e-04
2022-05-05 20:51:33,006 INFO [train.py:715] (5/8) Epoch 7, batch 14350, loss[loss=0.1494, simple_loss=0.2256, pruned_loss=0.03659, over 4936.00 frames.], tot_loss[loss=0.147, simple_loss=0.2179, pruned_loss=0.0381, over 971489.93 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:52:12,026 INFO [train.py:715] (5/8) Epoch 7, batch 14400, loss[loss=0.1243, simple_loss=0.2047, pruned_loss=0.02196, over 4754.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03767, over 972333.27 frames.], batch size: 19, lr: 2.94e-04
2022-05-05 20:52:50,728 INFO [train.py:715] (5/8) Epoch 7, batch 14450, loss[loss=0.1359, simple_loss=0.2114, pruned_loss=0.03017, over 4632.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.0383, over 971527.57 frames.], batch size: 13, lr: 2.94e-04
2022-05-05 20:53:29,521 INFO [train.py:715] (5/8) Epoch 7, batch 14500, loss[loss=0.1213, simple_loss=0.1935, pruned_loss=0.02454, over 4783.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03773, over 972752.38 frames.], batch size: 14, lr: 2.94e-04
2022-05-05 20:54:09,107 INFO [train.py:715] (5/8) Epoch 7, batch 14550, loss[loss=0.1455, simple_loss=0.2261, pruned_loss=0.03247, over 4810.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03805, over 972419.79 frames.], batch size: 25, lr: 2.94e-04
2022-05-05 20:54:47,910 INFO [train.py:715] (5/8) Epoch 7, batch 14600, loss[loss=0.1399, simple_loss=0.217, pruned_loss=0.03142, over 4915.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03778, over 972794.77 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:55:26,850 INFO [train.py:715] (5/8) Epoch 7, batch 14650, loss[loss=0.1543, simple_loss=0.2313, pruned_loss=0.03859, over 4918.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03744, over 972005.82 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:56:05,808 INFO [train.py:715] (5/8) Epoch 7, batch 14700, loss[loss=0.1584, simple_loss=0.2154, pruned_loss=0.05071, over 4923.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03741, over 972233.48 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:56:44,941 INFO [train.py:715] (5/8) Epoch 7, batch 14750, loss[loss=0.1336, simple_loss=0.2035, pruned_loss=0.03189, over 4805.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03732, over 971903.29 frames.], batch size: 21, lr: 2.94e-04
2022-05-05 20:57:23,493 INFO [train.py:715] (5/8) Epoch 7, batch 14800, loss[loss=0.1714, simple_loss=0.2365, pruned_loss=0.0531, over 4876.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03734, over 972238.60 frames.], batch size: 22, lr: 2.94e-04
2022-05-05 20:58:03,006 INFO [train.py:715] (5/8) Epoch 7, batch 14850, loss[loss=0.1558, simple_loss=0.2363, pruned_loss=0.03762, over 4904.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.03744, over 972824.38 frames.], batch size: 19, lr: 2.94e-04
2022-05-05 20:58:41,952 INFO [train.py:715] (5/8) Epoch 7, batch 14900, loss[loss=0.1467, simple_loss=0.2323, pruned_loss=0.03057, over 4791.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03753, over 972439.08 frames.], batch size: 24, lr: 2.94e-04
2022-05-05 20:59:20,317 INFO [train.py:715] (5/8) Epoch 7, batch 14950, loss[loss=0.1574, simple_loss=0.2141, pruned_loss=0.05037, over 4797.00 frames.], tot_loss[loss=0.1469, simple_loss=0.218, pruned_loss=0.03793, over 972015.27 frames.], batch size: 14, lr: 2.94e-04
2022-05-05 20:59:59,926 INFO [train.py:715] (5/8) Epoch 7, batch 15000, loss[loss=0.1694, simple_loss=0.2401, pruned_loss=0.04932, over 4939.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.0379, over 971868.59 frames.], batch size: 23, lr: 2.94e-04
2022-05-05 20:59:59,927 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 21:00:14,353 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1083, simple_loss=0.1931, pruned_loss=0.01175, over 914524.00 frames.
2022-05-05 21:00:53,497 INFO [train.py:715] (5/8) Epoch 7, batch 15050, loss[loss=0.1506, simple_loss=0.2218, pruned_loss=0.03966, over 4745.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.03797, over 971706.71 frames.], batch size: 19, lr: 2.94e-04
2022-05-05 21:01:32,728 INFO [train.py:715] (5/8) Epoch 7, batch 15100, loss[loss=0.1257, simple_loss=0.2033, pruned_loss=0.02406, over 4820.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03785, over 971816.79 frames.], batch size: 26, lr: 2.94e-04
2022-05-05 21:02:11,974 INFO [train.py:715] (5/8) Epoch 7, batch 15150, loss[loss=0.1363, simple_loss=0.2121, pruned_loss=0.03026, over 4984.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03799, over 972993.79 frames.], batch size: 25, lr: 2.94e-04
2022-05-05 21:02:50,723 INFO [train.py:715] (5/8) Epoch 7, batch 15200, loss[loss=0.1345, simple_loss=0.2014, pruned_loss=0.03384, over 4922.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.03791, over 971938.66 frames.], batch size: 22, lr: 2.94e-04
2022-05-05 21:03:30,196 INFO [train.py:715] (5/8) Epoch 7, batch 15250, loss[loss=0.1219, simple_loss=0.1894, pruned_loss=0.02715, over 4746.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2175, pruned_loss=0.03739, over 971813.01 frames.], batch size: 16, lr: 2.94e-04
2022-05-05 21:04:09,389 INFO [train.py:715] (5/8) Epoch 7, batch 15300, loss[loss=0.116, simple_loss=0.186, pruned_loss=0.02298, over 4836.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2171, pruned_loss=0.03728, over 971754.84 frames.], batch size: 13, lr: 2.94e-04
2022-05-05 21:04:48,395 INFO [train.py:715] (5/8) Epoch 7, batch 15350, loss[loss=0.1809, simple_loss=0.2538, pruned_loss=0.05404, over 4915.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2179, pruned_loss=0.03761, over 971478.52 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 21:05:27,509 INFO [train.py:715] (5/8) Epoch 7, batch 15400, loss[loss=0.1657, simple_loss=0.2353, pruned_loss=0.04802, over 4916.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03818, over 971082.76 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 21:06:05,999 INFO [train.py:715] (5/8) Epoch 7, batch 15450, loss[loss=0.1455, simple_loss=0.2281, pruned_loss=0.03148, over 4827.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03804, over 972161.03 frames.], batch size: 13, lr: 2.94e-04
2022-05-05 21:06:45,044 INFO [train.py:715] (5/8) Epoch 7, batch 15500, loss[loss=0.1486, simple_loss=0.2212, pruned_loss=0.03803, over 4960.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.0379, over 971927.37 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:07:23,163 INFO [train.py:715] (5/8) Epoch 7, batch 15550, loss[loss=0.2118, simple_loss=0.2855, pruned_loss=0.06902, over 4695.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03777, over 971717.13 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:08:02,568 INFO [train.py:715] (5/8) Epoch 7, batch 15600, loss[loss=0.1683, simple_loss=0.2337, pruned_loss=0.05142, over 4791.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2189, pruned_loss=0.03738, over 970901.03 frames.], batch size: 14, lr: 2.93e-04
2022-05-05 21:08:42,086 INFO [train.py:715] (5/8) Epoch 7, batch 15650, loss[loss=0.1266, simple_loss=0.1992, pruned_loss=0.02696, over 4975.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03685, over 970443.52 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:09:20,364 INFO [train.py:715] (5/8) Epoch 7, batch 15700, loss[loss=0.1663, simple_loss=0.2462, pruned_loss=0.04321, over 4780.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03732, over 970904.64 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:09:59,357 INFO [train.py:715] (5/8) Epoch 7, batch 15750, loss[loss=0.124, simple_loss=0.194, pruned_loss=0.02699, over 4816.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03778, over 971610.27 frames.], batch size: 25, lr: 2.93e-04
2022-05-05 21:10:39,020 INFO [train.py:715] (5/8) Epoch 7, batch 15800, loss[loss=0.1444, simple_loss=0.2238, pruned_loss=0.03253, over 4914.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03762, over 972174.06 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:11:18,131 INFO [train.py:715] (5/8) Epoch 7, batch 15850, loss[loss=0.1482, simple_loss=0.2365, pruned_loss=0.02992, over 4984.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03776, over 972879.78 frames.], batch size: 25, lr: 2.93e-04
2022-05-05 21:11:57,175 INFO [train.py:715] (5/8) Epoch 7, batch 15900, loss[loss=0.1448, simple_loss=0.2196, pruned_loss=0.03497, over 4944.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03737, over 973805.36 frames.], batch size: 35, lr: 2.93e-04
2022-05-05 21:12:36,476 INFO [train.py:715] (5/8) Epoch 7, batch 15950, loss[loss=0.1472, simple_loss=0.2143, pruned_loss=0.04, over 4833.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03704, over 973837.97 frames.], batch size: 26, lr: 2.93e-04
2022-05-05 21:13:15,931 INFO [train.py:715] (5/8) Epoch 7, batch 16000, loss[loss=0.1174, simple_loss=0.1836, pruned_loss=0.02565, over 4780.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03703, over 973842.25 frames.], batch size: 12, lr: 2.93e-04
2022-05-05 21:13:54,027 INFO [train.py:715] (5/8) Epoch 7, batch 16050, loss[loss=0.1476, simple_loss=0.2197, pruned_loss=0.03777, over 4688.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2169, pruned_loss=0.03712, over 974176.59 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:14:33,354 INFO [train.py:715] (5/8) Epoch 7, batch 16100, loss[loss=0.1458, simple_loss=0.2209, pruned_loss=0.03538, over 4978.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2169, pruned_loss=0.03701, over 973350.12 frames.], batch size: 31, lr: 2.93e-04
2022-05-05 21:15:12,278 INFO [train.py:715] (5/8) Epoch 7, batch 16150, loss[loss=0.1501, simple_loss=0.2232, pruned_loss=0.03853, over 4945.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03714, over 973177.22 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:15:50,929 INFO [train.py:715] (5/8) Epoch 7, batch 16200, loss[loss=0.1335, simple_loss=0.2097, pruned_loss=0.02862, over 4760.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03652, over 973496.63 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:16:30,079 INFO [train.py:715] (5/8) Epoch 7, batch 16250, loss[loss=0.1614, simple_loss=0.2297, pruned_loss=0.04651, over 4903.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03662, over 973681.89 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:17:08,724 INFO [train.py:715] (5/8) Epoch 7, batch 16300, loss[loss=0.1643, simple_loss=0.2308, pruned_loss=0.04894, over 4849.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.0367, over 973122.36 frames.], batch size: 30, lr: 2.93e-04
2022-05-05 21:17:48,271 INFO [train.py:715] (5/8) Epoch 7, batch 16350, loss[loss=0.1145, simple_loss=0.1814, pruned_loss=0.02386, over 4938.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03716, over 973904.34 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:18:26,609 INFO [train.py:715] (5/8) Epoch 7, batch 16400, loss[loss=0.1275, simple_loss=0.2063, pruned_loss=0.02439, over 4857.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03738, over 973740.23 frames.], batch size: 20, lr: 2.93e-04
2022-05-05 21:19:05,504 INFO [train.py:715] (5/8) Epoch 7, batch 16450, loss[loss=0.148, simple_loss=0.2178, pruned_loss=0.03912, over 4914.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03748, over 973955.88 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:19:44,557 INFO [train.py:715] (5/8) Epoch 7, batch 16500, loss[loss=0.1621, simple_loss=0.2208, pruned_loss=0.0517, over 4782.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03765, over 973500.06 frames.], batch size: 14, lr: 2.93e-04
2022-05-05 21:20:22,827 INFO [train.py:715] (5/8) Epoch 7, batch 16550, loss[loss=0.1591, simple_loss=0.238, pruned_loss=0.04007, over 4986.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03787, over 973280.72 frames.], batch size: 33, lr: 2.93e-04
2022-05-05 21:21:02,231 INFO [train.py:715] (5/8) Epoch 7, batch 16600, loss[loss=0.1338, simple_loss=0.2043, pruned_loss=0.03172, over 4776.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03759, over 972957.97 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:21:41,396 INFO [train.py:715] (5/8) Epoch 7, batch 16650, loss[loss=0.1468, simple_loss=0.232, pruned_loss=0.0308, over 4861.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2191, pruned_loss=0.03758, over 972585.14 frames.], batch size: 20, lr: 2.93e-04
2022-05-05 21:22:20,543 INFO [train.py:715] (5/8) Epoch 7, batch 16700, loss[loss=0.1487, simple_loss=0.2149, pruned_loss=0.04124, over 4753.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.0379, over 972383.83 frames.], batch size: 16, lr: 2.93e-04
2022-05-05 21:22:59,812 INFO [train.py:715] (5/8) Epoch 7, batch 16750, loss[loss=0.1612, simple_loss=0.2293, pruned_loss=0.04656, over 4887.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03764, over 973336.00 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:23:38,669 INFO [train.py:715] (5/8) Epoch 7, batch 16800, loss[loss=0.1169, simple_loss=0.1909, pruned_loss=0.02146, over 4936.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.0366, over 973347.69 frames.], batch size: 23, lr: 2.93e-04
2022-05-05 21:24:17,713 INFO [train.py:715] (5/8) Epoch 7, batch 16850, loss[loss=0.1592, simple_loss=0.2356, pruned_loss=0.04138, over 4964.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03686, over 973223.37 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:24:56,998 INFO [train.py:715] (5/8) Epoch 7, batch 16900, loss[loss=0.1542, simple_loss=0.232, pruned_loss=0.03819, over 4830.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03748, over 971766.13 frames.], batch size: 25, lr: 2.93e-04
2022-05-05 21:25:36,247 INFO [train.py:715] (5/8) Epoch 7, batch 16950, loss[loss=0.1386, simple_loss=0.2103, pruned_loss=0.03349, over 4946.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03723, over 971675.85 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:26:14,895 INFO [train.py:715] (5/8) Epoch 7, batch 17000, loss[loss=0.1444, simple_loss=0.2267, pruned_loss=0.03106, over 4879.00 frames.], tot_loss[loss=0.1454, simple_loss=0.217, pruned_loss=0.0369, over 972223.58 frames.], batch size: 32, lr: 2.93e-04
2022-05-05 21:26:54,052 INFO [train.py:715] (5/8) Epoch 7, batch 17050, loss[loss=0.1369, simple_loss=0.1983, pruned_loss=0.03775, over 4900.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.03706, over 971783.49 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:27:32,506 INFO [train.py:715] (5/8) Epoch 7, batch 17100, loss[loss=0.1467, simple_loss=0.2159, pruned_loss=0.03871, over 4794.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03712, over 971368.74 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:28:11,646 INFO [train.py:715] (5/8) Epoch 7, batch 17150, loss[loss=0.1367, simple_loss=0.2048, pruned_loss=0.03431, over 4917.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03739, over 972583.19 frames.], batch size: 23, lr: 2.93e-04
2022-05-05 21:28:50,901 INFO [train.py:715] (5/8) Epoch 7, batch 17200, loss[loss=0.1821, simple_loss=0.2516, pruned_loss=0.05631, over 4690.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03712, over 972359.33 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:29:29,221 INFO [train.py:715] (5/8) Epoch 7, batch 17250, loss[loss=0.1371, simple_loss=0.2128, pruned_loss=0.03067, over 4906.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03725, over 972528.31 frames.], batch size: 18, lr: 2.92e-04
2022-05-05 21:30:08,293 INFO [train.py:715] (5/8) Epoch 7, batch 17300, loss[loss=0.1588, simple_loss=0.2306, pruned_loss=0.04351, over 4695.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2175, pruned_loss=0.0367, over 971869.45 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:30:46,575 INFO [train.py:715] (5/8) Epoch 7, batch 17350, loss[loss=0.1576, simple_loss=0.2216, pruned_loss=0.04684, over 4881.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.0369, over 971300.77 frames.], batch size: 22, lr: 2.92e-04
2022-05-05 21:31:25,651 INFO [train.py:715] (5/8) Epoch 7, batch 17400, loss[loss=0.154, simple_loss=0.2182, pruned_loss=0.04486, over 4883.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03657, over 972226.82 frames.], batch size: 22, lr: 2.92e-04
2022-05-05 21:32:04,440 INFO [train.py:715] (5/8) Epoch 7, batch 17450, loss[loss=0.1461, simple_loss=0.224, pruned_loss=0.03407, over 4896.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03655, over 972076.40 frames.], batch size: 19, lr: 2.92e-04
2022-05-05 21:32:43,217 INFO [train.py:715] (5/8) Epoch 7, batch 17500, loss[loss=0.1486, simple_loss=0.2236, pruned_loss=0.03681, over 4759.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03678, over 971813.35 frames.], batch size: 16, lr: 2.92e-04
2022-05-05 21:33:22,412 INFO [train.py:715] (5/8) Epoch 7, batch 17550, loss[loss=0.138, simple_loss=0.2194, pruned_loss=0.02833, over 4789.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.0366, over 970476.90 frames.], batch size: 17, lr: 2.92e-04
2022-05-05 21:34:00,740 INFO [train.py:715] (5/8) Epoch 7, batch 17600, loss[loss=0.1647, simple_loss=0.2171, pruned_loss=0.05617, over 4701.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2181, pruned_loss=0.0365, over 971569.67 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:34:39,809 INFO [train.py:715] (5/8) Epoch 7, batch 17650, loss[loss=0.1581, simple_loss=0.2346, pruned_loss=0.04076, over 4953.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03595, over 972425.07 frames.], batch size: 35, lr: 2.92e-04
2022-05-05 21:35:19,109 INFO [train.py:715] (5/8) Epoch 7, batch 17700, loss[loss=0.1941, simple_loss=0.2709, pruned_loss=0.05864, over 4872.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03569, over 972797.95 frames.], batch size: 20, lr: 2.92e-04
2022-05-05 21:35:58,206 INFO [train.py:715] (5/8) Epoch 7, batch 17750, loss[loss=0.1665, simple_loss=0.2304, pruned_loss=0.05135, over 4849.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03599, over 973826.94 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:36:37,513 INFO [train.py:715] (5/8) Epoch 7, batch 17800, loss[loss=0.153, simple_loss=0.2281, pruned_loss=0.0389, over 4987.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03681, over 973337.31 frames.], batch size: 25, lr: 2.92e-04
2022-05-05 21:37:16,003 INFO [train.py:715] (5/8) Epoch 7, batch 17850, loss[loss=0.1547, simple_loss=0.2159, pruned_loss=0.04678, over 4847.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03688, over 972505.16 frames.], batch size: 32, lr: 2.92e-04
2022-05-05 21:37:55,634 INFO [train.py:715] (5/8) Epoch 7, batch 17900, loss[loss=0.1478, simple_loss=0.2175, pruned_loss=0.03903, over 4821.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03775, over 972145.83 frames.], batch size: 25, lr: 2.92e-04
2022-05-05 21:38:34,075 INFO [train.py:715] (5/8) Epoch 7, batch 17950, loss[loss=0.1338, simple_loss=0.2089, pruned_loss=0.02939, over 4911.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03779, over 972175.60 frames.], batch size: 23, lr: 2.92e-04
2022-05-05 21:39:13,132 INFO [train.py:715] (5/8) Epoch 7, batch 18000, loss[loss=0.1403, simple_loss=0.2201, pruned_loss=0.03027, over 4942.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03742, over 970714.99 frames.], batch size: 39, lr: 2.92e-04
2022-05-05 21:39:13,132 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 21:39:22,793 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1081, simple_loss=0.193, pruned_loss=0.01158, over 914524.00 frames.
2022-05-05 21:40:01,810 INFO [train.py:715] (5/8) Epoch 7, batch 18050, loss[loss=0.1447, simple_loss=0.2218, pruned_loss=0.03375, over 4978.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.0378, over 970613.35 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:40:41,007 INFO [train.py:715] (5/8) Epoch 7, batch 18100, loss[loss=0.1173, simple_loss=0.1929, pruned_loss=0.02079, over 4937.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.0376, over 971640.95 frames.], batch size: 29, lr: 2.92e-04
2022-05-05 21:41:19,568 INFO [train.py:715] (5/8) Epoch 7, batch 18150, loss[loss=0.1832, simple_loss=0.2509, pruned_loss=0.05773, over 4731.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2178, pruned_loss=0.03774, over 971621.79 frames.], batch size: 16, lr: 2.92e-04
2022-05-05 21:41:57,881 INFO [train.py:715] (5/8) Epoch 7, batch 18200, loss[loss=0.1529, simple_loss=0.2208, pruned_loss=0.04252, over 4916.00 frames.], tot_loss[loss=0.1466, simple_loss=0.218, pruned_loss=0.03762, over 972128.84 frames.], batch size: 17, lr: 2.92e-04
2022-05-05 21:42:36,255 INFO [train.py:715] (5/8) Epoch 7, batch 18250, loss[loss=0.1624, simple_loss=0.2318, pruned_loss=0.04649, over 4934.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2186, pruned_loss=0.03806, over 972278.23 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:43:15,542 INFO [train.py:715] (5/8) Epoch 7, batch 18300, loss[loss=0.1597, simple_loss=0.2218, pruned_loss=0.04881, over 4807.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.0386, over 971951.11 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:43:53,555 INFO [train.py:715] (5/8) Epoch 7, batch 18350, loss[loss=0.1438, simple_loss=0.2059, pruned_loss=0.04086, over 4743.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03812, over 971652.34 frames.], batch size: 16, lr: 2.92e-04
2022-05-05 21:44:31,936 INFO [train.py:715] (5/8) Epoch 7, batch 18400, loss[loss=0.1578, simple_loss=0.223, pruned_loss=0.04628, over 4842.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2188, pruned_loss=0.03808, over 972556.10 frames.], batch size: 30, lr: 2.92e-04
2022-05-05 21:45:11,787 INFO [train.py:715] (5/8) Epoch 7, batch 18450, loss[loss=0.1445, simple_loss=0.2083, pruned_loss=0.04029, over 4855.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2186, pruned_loss=0.03819, over 973373.73 frames.], batch size: 13, lr: 2.92e-04
2022-05-05 21:45:50,714 INFO [train.py:715] (5/8) Epoch 7, batch 18500, loss[loss=0.1434, simple_loss=0.2095, pruned_loss=0.03865, over 4898.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03767, over 972824.22 frames.], batch size: 19, lr: 2.92e-04
2022-05-05 21:46:29,378 INFO [train.py:715] (5/8) Epoch 7, batch 18550, loss[loss=0.1522, simple_loss=0.2233, pruned_loss=0.04055, over 4882.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.038, over 972550.72 frames.], batch size: 22, lr: 2.92e-04
2022-05-05 21:47:08,451 INFO [train.py:715] (5/8) Epoch 7, batch 18600, loss[loss=0.1739, simple_loss=0.2479, pruned_loss=0.04999, over 4948.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03779, over 972733.72 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:47:47,273 INFO [train.py:715] (5/8) Epoch 7, batch 18650, loss[loss=0.1493, simple_loss=0.2124, pruned_loss=0.04309, over 4850.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03789, over 972473.87 frames.], batch size: 34, lr: 2.92e-04
2022-05-05 21:48:25,124 INFO [train.py:715] (5/8) Epoch 7, batch 18700, loss[loss=0.1502, simple_loss=0.2275, pruned_loss=0.03639, over 4772.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03762, over 973001.10 frames.], batch size: 18, lr: 2.92e-04
2022-05-05 21:49:03,391 INFO [train.py:715] (5/8) Epoch 7, batch 18750, loss[loss=0.1349, simple_loss=0.204, pruned_loss=0.03287, over 4830.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03761, over 972995.98 frames.], batch size: 30, lr: 2.92e-04
2022-05-05 21:49:42,761 INFO [train.py:715] (5/8) Epoch 7, batch 18800, loss[loss=0.1534, simple_loss=0.2319, pruned_loss=0.03748, over 4796.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03791, over 972356.89 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:50:21,359 INFO [train.py:715] (5/8) Epoch 7, batch 18850, loss[loss=0.1556, simple_loss=0.2366, pruned_loss=0.03731, over 4956.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03671, over 971941.17 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:50:59,415 INFO [train.py:715] (5/8) Epoch 7, batch 18900, loss[loss=0.1491, simple_loss=0.2143, pruned_loss=0.04194, over 4810.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2174, pruned_loss=0.03635, over 972260.00 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:51:36,460 INFO [train.py:715] (5/8) Epoch 7, batch 18950, loss[loss=0.1673, simple_loss=0.2361, pruned_loss=0.04924, over 4758.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2183, pruned_loss=0.03719, over 972377.26 frames.], batch size: 16, lr: 2.92e-04
2022-05-05 21:52:14,914 INFO [train.py:715] (5/8) Epoch 7, batch 19000, loss[loss=0.1532, simple_loss=0.2285, pruned_loss=0.03894, over 4906.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2178, pruned_loss=0.0366, over 972686.26 frames.], batch size: 18, lr: 2.92e-04
2022-05-05 21:52:52,517 INFO [train.py:715] (5/8) Epoch 7, batch 19050, loss[loss=0.1168, simple_loss=0.1838, pruned_loss=0.02486, over 4917.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03681, over 973013.88 frames.], batch size: 23, lr: 2.91e-04
2022-05-05 21:53:30,742 INFO [train.py:715] (5/8) Epoch 7, batch 19100, loss[loss=0.1299, simple_loss=0.2041, pruned_loss=0.02784, over 4951.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03689, over 973060.38 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 21:54:09,412 INFO [train.py:715] (5/8) Epoch 7, batch 19150, loss[loss=0.1322, simple_loss=0.2124, pruned_loss=0.026, over 4794.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03672, over 972411.32 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 21:54:47,124 INFO [train.py:715] (5/8) Epoch 7, batch 19200, loss[loss=0.1259, simple_loss=0.1948, pruned_loss=0.02848, over 4812.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03666, over 971604.65 frames.], batch size: 13, lr: 2.91e-04
2022-05-05 21:55:24,839 INFO [train.py:715] (5/8) Epoch 7, batch 19250, loss[loss=0.1729, simple_loss=0.2413, pruned_loss=0.05228, over 4953.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 971248.99 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 21:56:02,878 INFO [train.py:715] (5/8) Epoch 7, batch 19300, loss[loss=0.1473, simple_loss=0.2233, pruned_loss=0.03564, over 4867.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2189, pruned_loss=0.03741, over 972757.03 frames.], batch size: 34, lr: 2.91e-04
2022-05-05 21:56:41,358 INFO [train.py:715] (5/8) Epoch 7, batch 19350, loss[loss=0.1561, simple_loss=0.2248, pruned_loss=0.04374, over 4972.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2169, pruned_loss=0.03699, over 972694.16 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 21:57:18,829 INFO [train.py:715] (5/8) Epoch 7, batch 19400, loss[loss=0.1401, simple_loss=0.2079, pruned_loss=0.03615, over 4664.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.0364, over 972426.04 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 21:57:56,263 INFO [train.py:715] (5/8) Epoch 7, batch 19450, loss[loss=0.1594, simple_loss=0.2306, pruned_loss=0.04406, over 4901.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03662, over 972956.05 frames.], batch size: 19, lr: 2.91e-04
2022-05-05 21:58:34,322 INFO [train.py:715] (5/8) Epoch 7, batch 19500, loss[loss=0.1379, simple_loss=0.204, pruned_loss=0.03592, over 4904.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 972912.26 frames.], batch size: 17, lr: 2.91e-04
2022-05-05 21:59:11,841 INFO [train.py:715] (5/8) Epoch 7, batch 19550, loss[loss=0.1384, simple_loss=0.2206, pruned_loss=0.02813, over 4783.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.03725, over 973095.61 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 21:59:49,563 INFO [train.py:715] (5/8) Epoch 7, batch 19600, loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03373, over 4953.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03778, over 972152.59 frames.], batch size: 39, lr: 2.91e-04
2022-05-05 22:00:27,123 INFO [train.py:715] (5/8) Epoch 7, batch 19650, loss[loss=0.1294, simple_loss=0.2113, pruned_loss=0.02371, over 4880.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03699, over 971773.02 frames.], batch size: 16, lr: 2.91e-04
2022-05-05 22:01:05,537 INFO [train.py:715] (5/8) Epoch 7, batch 19700, loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03169, over 4905.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03711, over 972248.33 frames.], batch size: 18, lr: 2.91e-04
2022-05-05 22:01:42,745 INFO [train.py:715] (5/8) Epoch 7, batch 19750, loss[loss=0.1708, simple_loss=0.2404, pruned_loss=0.0506, over 4970.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2166, pruned_loss=0.03688, over 972569.10 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 22:02:20,221 INFO [train.py:715] (5/8) Epoch 7, batch 19800, loss[loss=0.1499, simple_loss=0.2206, pruned_loss=0.03953, over 4910.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2167, pruned_loss=0.03681, over 972770.32 frames.], batch size: 19, lr: 2.91e-04
2022-05-05 22:02:58,033 INFO [train.py:715] (5/8) Epoch 7, batch 19850, loss[loss=0.1528, simple_loss=0.2237, pruned_loss=0.04095, over 4947.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03714, over 972382.44 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 22:03:35,858 INFO [train.py:715] (5/8) Epoch 7, batch 19900, loss[loss=0.1604, simple_loss=0.2393, pruned_loss=0.04069, over 4781.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03708, over 973038.59 frames.], batch size: 17, lr: 2.91e-04
2022-05-05 22:04:12,820 INFO [train.py:715] (5/8) Epoch 7, batch 19950, loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03376, over 4765.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.0373, over 973373.12 frames.], batch size: 19, lr: 2.91e-04
2022-05-05 22:04:50,680 INFO [train.py:715] (5/8) Epoch 7, batch 20000, loss[loss=0.1774, simple_loss=0.2362, pruned_loss=0.05927, over 4984.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03717, over 973426.11 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 22:05:28,963 INFO [train.py:715] (5/8) Epoch 7, batch 20050, loss[loss=0.1398, simple_loss=0.2068, pruned_loss=0.03639, over 4987.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.037, over 972760.08 frames.], batch size: 27, lr: 2.91e-04
2022-05-05 22:06:06,295 INFO [train.py:715] (5/8) Epoch 7, batch 20100, loss[loss=0.1519, simple_loss=0.2316, pruned_loss=0.0361, over 4869.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2191, pruned_loss=0.03739, over 972372.18 frames.], batch size: 22, lr: 2.91e-04
2022-05-05 22:06:43,746 INFO [train.py:715] (5/8) Epoch 7, batch 20150, loss[loss=0.1279, simple_loss=0.2091, pruned_loss=0.02332, over 4969.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2188, pruned_loss=0.03746, over 972306.01 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 22:07:21,914 INFO [train.py:715] (5/8) Epoch 7, batch 20200, loss[loss=0.1454, simple_loss=0.2204, pruned_loss=0.03519, over 4972.00 frames.], tot_loss[loss=0.1468, simple_loss=0.219, pruned_loss=0.03732, over 972955.11 frames.], batch size: 35, lr: 2.91e-04
2022-05-05 22:08:00,054 INFO [train.py:715] (5/8) Epoch 7, batch 20250, loss[loss=0.1647, simple_loss=0.2387, pruned_loss=0.04536, over 4707.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03683, over 972294.26 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 22:08:37,464 INFO [train.py:715] (5/8) Epoch 7, batch 20300, loss[loss=0.1391, simple_loss=0.2061, pruned_loss=0.03602, over 4985.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03672, over 972523.14 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 22:09:17,216 INFO [train.py:715] (5/8) Epoch 7, batch 20350, loss[loss=0.1435, simple_loss=0.212, pruned_loss=0.03747, over 4656.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.0372, over 972067.89 frames.], batch size: 13, lr: 2.91e-04
2022-05-05 22:09:55,129 INFO [train.py:715] (5/8) Epoch 7, batch 20400, loss[loss=0.1486, simple_loss=0.2273, pruned_loss=0.03497, over 4969.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03705, over 971736.75 frames.], batch size: 35, lr: 2.91e-04
2022-05-05 22:10:33,046 INFO [train.py:715] (5/8) Epoch 7, batch 20450, loss[loss=0.1486, simple_loss=0.2169, pruned_loss=0.04014, over 4969.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.0371, over 971317.88 frames.], batch size: 35, lr: 2.91e-04
2022-05-05 22:11:10,606 INFO [train.py:715] (5/8) Epoch 7, batch 20500, loss[loss=0.1619, simple_loss=0.2451, pruned_loss=0.03936, over 4937.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 971367.05 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 22:11:48,691 INFO [train.py:715] (5/8) Epoch 7, batch 20550, loss[loss=0.1663, simple_loss=0.2556, pruned_loss=0.03853, over 4804.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03738, over 971488.30 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 22:12:26,843 INFO [train.py:715] (5/8) Epoch 7, batch 20600, loss[loss=0.1222, simple_loss=0.1966, pruned_loss=0.02389, over 4828.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2187, pruned_loss=0.03738, over 972675.54 frames.], batch size: 13, lr: 2.91e-04
2022-05-05 22:13:04,069 INFO [train.py:715] (5/8) Epoch 7, batch 20650, loss[loss=0.1107, simple_loss=0.1924, pruned_loss=0.01451, over 4816.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2185, pruned_loss=0.03702, over 972706.35 frames.], batch size: 25, lr: 2.91e-04
2022-05-05 22:13:41,770 INFO [train.py:715] (5/8) Epoch 7, batch 20700, loss[loss=0.1808, simple_loss=0.2527, pruned_loss=0.05448, over 4954.00 frames.], tot_loss[loss=0.147, simple_loss=0.2191, pruned_loss=0.03744, over 973113.32 frames.], batch size: 39, lr: 2.91e-04
2022-05-05 22:14:19,742 INFO [train.py:715] (5/8) Epoch 7, batch 20750, loss[loss=0.1501, simple_loss=0.2204, pruned_loss=0.03994, over 4884.00 frames.], tot_loss[loss=0.1466, simple_loss=0.219, pruned_loss=0.03714, over 972875.22 frames.], batch size: 22, lr: 2.91e-04
2022-05-05 22:14:57,389 INFO [train.py:715] (5/8) Epoch 7, batch 20800, loss[loss=0.1358, simple_loss=0.2083, pruned_loss=0.03161, over 4976.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2183, pruned_loss=0.03717, over 972639.91 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 22:15:34,692 INFO [train.py:715] (5/8) Epoch 7, batch 20850, loss[loss=0.1589, simple_loss=0.2298, pruned_loss=0.04404, over 4936.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03698, over 972244.39 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:16:13,018 INFO [train.py:715] (5/8) Epoch 7, batch 20900, loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03148, over 4781.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03689, over 972093.30 frames.], batch size: 14, lr: 2.90e-04
2022-05-05 22:16:50,910 INFO [train.py:715] (5/8) Epoch 7, batch 20950, loss[loss=0.1601, simple_loss=0.2276, pruned_loss=0.04632, over 4837.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03664, over 972496.21 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:17:29,166 INFO [train.py:715] (5/8) Epoch 7, batch 21000, loss[loss=0.1256, simple_loss=0.2092, pruned_loss=0.02099, over 4794.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2187, pruned_loss=0.03718, over 973335.12 frames.], batch size: 24, lr: 2.90e-04
2022-05-05 22:17:29,167 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 22:17:39,072 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1082, simple_loss=0.193, pruned_loss=0.01169, over 914524.00 frames.
2022-05-05 22:18:17,065 INFO [train.py:715] (5/8) Epoch 7, batch 21050, loss[loss=0.1522, simple_loss=0.2265, pruned_loss=0.03896, over 4749.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2184, pruned_loss=0.03688, over 972849.90 frames.], batch size: 19, lr: 2.90e-04
2022-05-05 22:18:54,964 INFO [train.py:715] (5/8) Epoch 7, batch 21100, loss[loss=0.1612, simple_loss=0.2455, pruned_loss=0.03844, over 4924.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2183, pruned_loss=0.03663, over 972865.76 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:19:32,990 INFO [train.py:715] (5/8) Epoch 7, batch 21150, loss[loss=0.1287, simple_loss=0.206, pruned_loss=0.02575, over 4981.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2186, pruned_loss=0.03678, over 971811.82 frames.], batch size: 28, lr: 2.90e-04
2022-05-05 22:20:10,777 INFO [train.py:715] (5/8) Epoch 7, batch 21200, loss[loss=0.1371, simple_loss=0.214, pruned_loss=0.03015, over 4938.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2187, pruned_loss=0.03687, over 971946.65 frames.], batch size: 29, lr: 2.90e-04
2022-05-05 22:20:49,001 INFO [train.py:715] (5/8) Epoch 7, batch 21250, loss[loss=0.1428, simple_loss=0.2228, pruned_loss=0.03137, over 4923.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2186, pruned_loss=0.03684, over 971440.46 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:21:27,130 INFO [train.py:715] (5/8) Epoch 7, batch 21300, loss[loss=0.1523, simple_loss=0.2348, pruned_loss=0.03489, over 4937.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2185, pruned_loss=0.03701, over 972093.10 frames.], batch size: 23, lr: 2.90e-04
2022-05-05 22:22:04,502 INFO [train.py:715] (5/8) Epoch 7, batch 21350, loss[loss=0.1462, simple_loss=0.2222, pruned_loss=0.03511, over 4951.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2185, pruned_loss=0.03683, over 972196.00 frames.], batch size: 39, lr: 2.90e-04
2022-05-05 22:22:42,287 INFO [train.py:715] (5/8) Epoch 7, batch 21400, loss[loss=0.1504, simple_loss=0.2153, pruned_loss=0.04272, over 4973.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2187, pruned_loss=0.03725, over 972380.40 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:23:20,549 INFO [train.py:715] (5/8) Epoch 7, batch 21450, loss[loss=0.1524, simple_loss=0.2242, pruned_loss=0.04028, over 4953.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2194, pruned_loss=0.03756, over 972337.02 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:23:58,722 INFO [train.py:715] (5/8) Epoch 7, batch 21500, loss[loss=0.1413, simple_loss=0.2223, pruned_loss=0.03019, over 4874.00 frames.], tot_loss[loss=0.1455, simple_loss=0.218, pruned_loss=0.03651, over 972422.54 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:24:36,576 INFO [train.py:715] (5/8) Epoch 7, batch 21550, loss[loss=0.183, simple_loss=0.2603, pruned_loss=0.05292, over 4961.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2178, pruned_loss=0.0365, over 973442.52 frames.], batch size: 39, lr: 2.90e-04
2022-05-05 22:25:14,831 INFO [train.py:715] (5/8) Epoch 7, batch 21600, loss[loss=0.1574, simple_loss=0.2276, pruned_loss=0.04361, over 4844.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03701, over 973151.51 frames.], batch size: 30, lr: 2.90e-04
2022-05-05 22:25:53,301 INFO [train.py:715] (5/8) Epoch 7, batch 21650, loss[loss=0.1526, simple_loss=0.2295, pruned_loss=0.0379, over 4892.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2183, pruned_loss=0.03663, over 972940.35 frames.], batch size: 22, lr: 2.90e-04
2022-05-05 22:26:30,668 INFO [train.py:715] (5/8) Epoch 7, batch 21700, loss[loss=0.1463, simple_loss=0.2164, pruned_loss=0.03806, over 4961.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2186, pruned_loss=0.0368, over 972633.69 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:27:08,759 INFO [train.py:715] (5/8) Epoch 7, batch 21750, loss[loss=0.1368, simple_loss=0.213, pruned_loss=0.03029, over 4938.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2183, pruned_loss=0.03634, over 973865.62 frames.], batch size: 29, lr: 2.90e-04
2022-05-05 22:27:46,871 INFO [train.py:715] (5/8) Epoch 7, batch 21800, loss[loss=0.1415, simple_loss=0.2187, pruned_loss=0.03216, over 4950.00 frames.], tot_loss[loss=0.145, simple_loss=0.2179, pruned_loss=0.03605, over 973941.16 frames.], batch size: 21, lr: 2.90e-04
2022-05-05 22:28:24,963 INFO [train.py:715] (5/8) Epoch 7, batch 21850, loss[loss=0.1434, simple_loss=0.2114, pruned_loss=0.03773, over 4828.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03652, over 974160.77 frames.], batch size: 30, lr: 2.90e-04
2022-05-05 22:29:02,873 INFO [train.py:715] (5/8) Epoch 7, batch 21900, loss[loss=0.1573, simple_loss=0.2363, pruned_loss=0.03913, over 4816.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03623, over 973842.21 frames.], batch size: 26, lr: 2.90e-04
2022-05-05 22:29:40,814 INFO [train.py:715] (5/8) Epoch 7, batch 21950, loss[loss=0.1317, simple_loss=0.2083, pruned_loss=0.02754, over 4779.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03585, over 973029.40 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:30:19,542 INFO [train.py:715] (5/8) Epoch 7, batch 22000, loss[loss=0.2073, simple_loss=0.2795, pruned_loss=0.0675, over 4749.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03647, over 972767.24 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:30:57,078 INFO [train.py:715] (5/8) Epoch 7, batch 22050, loss[loss=0.1216, simple_loss=0.1914, pruned_loss=0.02587, over 4857.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03639, over 973688.43 frames.], batch size: 13, lr: 2.90e-04
2022-05-05 22:31:35,217 INFO [train.py:715] (5/8) Epoch 7, batch 22100, loss[loss=0.1557, simple_loss=0.2261, pruned_loss=0.04264, over 4899.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.03646, over 973051.19 frames.], batch size: 22, lr: 2.90e-04
2022-05-05 22:32:13,475 INFO [train.py:715] (5/8) Epoch 7, batch 22150, loss[loss=0.1494, simple_loss=0.2185, pruned_loss=0.04019, over 4898.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03675, over 973487.63 frames.], batch size: 19, lr: 2.90e-04
2022-05-05 22:32:51,984 INFO [train.py:715] (5/8) Epoch 7, batch 22200, loss[loss=0.1377, simple_loss=0.2157, pruned_loss=0.0299, over 4911.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2174, pruned_loss=0.03623, over 972718.94 frames.], batch size: 39, lr: 2.90e-04
2022-05-05 22:33:29,481 INFO [train.py:715] (5/8) Epoch 7, batch 22250, loss[loss=0.169, simple_loss=0.2591, pruned_loss=0.0394, over 4909.00 frames.], tot_loss[loss=0.145, simple_loss=0.2176, pruned_loss=0.03619, over 973399.66 frames.], batch size: 19, lr: 2.90e-04
2022-05-05 22:34:07,237 INFO [train.py:715] (5/8) Epoch 7, batch 22300, loss[loss=0.1288, simple_loss=0.2124, pruned_loss=0.02263, over 4976.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2175, pruned_loss=0.03602, over 973350.90 frames.], batch size: 28, lr: 2.90e-04
2022-05-05 22:34:45,534 INFO [train.py:715] (5/8) Epoch 7, batch 22350, loss[loss=0.1295, simple_loss=0.2087, pruned_loss=0.02514, over 4884.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2189, pruned_loss=0.03663, over 973327.46 frames.], batch size: 22, lr: 2.90e-04
2022-05-05 22:35:22,812 INFO [train.py:715] (5/8) Epoch 7, batch 22400, loss[loss=0.1546, simple_loss=0.2265, pruned_loss=0.04131, over 4733.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2194, pruned_loss=0.03712, over 972766.28 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:36:00,505 INFO [train.py:715] (5/8) Epoch 7, batch 22450, loss[loss=0.1405, simple_loss=0.2112, pruned_loss=0.03486, over 4935.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2192, pruned_loss=0.03684, over 972231.05 frames.], batch size: 21, lr: 2.90e-04
2022-05-05 22:36:38,650 INFO [train.py:715] (5/8) Epoch 7, batch 22500, loss[loss=0.1158, simple_loss=0.1914, pruned_loss=0.02006, over 4775.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2181, pruned_loss=0.03677, over 972074.29 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:37:16,689 INFO [train.py:715] (5/8) Epoch 7, batch 22550, loss[loss=0.1479, simple_loss=0.2214, pruned_loss=0.03725, over 4875.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2183, pruned_loss=0.03727, over 972760.19 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:37:54,354 INFO [train.py:715] (5/8) Epoch 7, batch 22600, loss[loss=0.1324, simple_loss=0.2055, pruned_loss=0.02966, over 4901.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03748, over 972623.25 frames.], batch size: 17, lr: 2.90e-04
2022-05-05 22:38:32,387 INFO [train.py:715] (5/8) Epoch 7, batch 22650, loss[loss=0.1382, simple_loss=0.2104, pruned_loss=0.033, over 4919.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03699, over 971801.33 frames.], batch size: 17, lr: 2.90e-04
2022-05-05 22:39:10,750 INFO [train.py:715] (5/8) Epoch 7, batch 22700, loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.03463, over 4903.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2185, pruned_loss=0.03702, over 972315.62 frames.], batch size: 22, lr: 2.89e-04
2022-05-05 22:39:48,096 INFO [train.py:715] (5/8) Epoch 7, batch 22750, loss[loss=0.1749, simple_loss=0.2412, pruned_loss=0.05425, over 4905.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2199, pruned_loss=0.03783, over 972734.57 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:40:25,727 INFO [train.py:715] (5/8) Epoch 7, batch 22800, loss[loss=0.1207, simple_loss=0.1857, pruned_loss=0.02786, over 4824.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2202, pruned_loss=0.03827, over 972826.22 frames.], batch size: 13, lr: 2.89e-04
2022-05-05 22:41:03,918 INFO [train.py:715] (5/8) Epoch 7, batch 22850, loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02938, over 4873.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.03809, over 973192.18 frames.], batch size: 22, lr: 2.89e-04
2022-05-05 22:41:41,491 INFO [train.py:715] (5/8) Epoch 7, batch 22900, loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03578, over 4890.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03781, over 973296.85 frames.], batch size: 22, lr: 2.89e-04
2022-05-05 22:42:19,137 INFO [train.py:715] (5/8) Epoch 7, batch 22950, loss[loss=0.1639, simple_loss=0.2308, pruned_loss=0.04845, over 4977.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03717, over 973978.34 frames.], batch size: 28, lr: 2.89e-04
2022-05-05 22:42:57,045 INFO [train.py:715] (5/8) Epoch 7, batch 23000, loss[loss=0.1502, simple_loss=0.2216, pruned_loss=0.03943, over 4828.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03693, over 973172.50 frames.], batch size: 26, lr: 2.89e-04
2022-05-05 22:43:35,193 INFO [train.py:715] (5/8) Epoch 7, batch 23050, loss[loss=0.1499, simple_loss=0.2264, pruned_loss=0.03669, over 4804.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03642, over 972922.52 frames.], batch size: 21, lr: 2.89e-04
2022-05-05 22:44:12,639 INFO [train.py:715] (5/8) Epoch 7, batch 23100, loss[loss=0.1564, simple_loss=0.2214, pruned_loss=0.04566, over 4870.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03679, over 972284.45 frames.], batch size: 32, lr: 2.89e-04
2022-05-05 22:44:49,935 INFO [train.py:715] (5/8) Epoch 7, batch 23150, loss[loss=0.1385, simple_loss=0.2123, pruned_loss=0.03234, over 4825.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.0364, over 971866.16 frames.], batch size: 26, lr: 2.89e-04
2022-05-05 22:45:28,253 INFO [train.py:715] (5/8) Epoch 7, batch 23200, loss[loss=0.1519, simple_loss=0.2164, pruned_loss=0.04373, over 4836.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2158, pruned_loss=0.03594, over 971815.48 frames.], batch size: 32, lr: 2.89e-04
2022-05-05 22:46:06,321 INFO [train.py:715] (5/8) Epoch 7, batch 23250, loss[loss=0.132, simple_loss=0.2016, pruned_loss=0.03121, over 4767.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03644, over 971014.77 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:46:43,801 INFO [train.py:715] (5/8) Epoch 7, batch 23300, loss[loss=0.1341, simple_loss=0.2069, pruned_loss=0.03069, over 4935.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03636, over 971980.23 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 22:47:22,580 INFO [train.py:715] (5/8) Epoch 7, batch 23350, loss[loss=0.1515, simple_loss=0.226, pruned_loss=0.03849, over 4792.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.0364, over 972290.26 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:48:01,697 INFO [train.py:715] (5/8) Epoch 7, batch 23400, loss[loss=0.1447, simple_loss=0.2196, pruned_loss=0.03493, over 4955.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03594, over 972779.47 frames.], batch size: 29, lr: 2.89e-04
2022-05-05 22:48:40,125 INFO [train.py:715] (5/8) Epoch 7, batch 23450, loss[loss=0.1506, simple_loss=0.2164, pruned_loss=0.04243, over 4980.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03655, over 972197.26 frames.], batch size: 28, lr: 2.89e-04
2022-05-05 22:49:18,248 INFO [train.py:715] (5/8) Epoch 7, batch 23500, loss[loss=0.1367, simple_loss=0.2089, pruned_loss=0.03218, over 4759.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03616, over 971915.87 frames.], batch size: 19, lr: 2.89e-04
2022-05-05 22:49:56,228 INFO [train.py:715] (5/8) Epoch 7, batch 23550, loss[loss=0.1467, simple_loss=0.2131, pruned_loss=0.04013, over 4845.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03713, over 971661.41 frames.], batch size: 30, lr: 2.89e-04
2022-05-05 22:50:34,438 INFO [train.py:715] (5/8) Epoch 7, batch 23600, loss[loss=0.1464, simple_loss=0.2095, pruned_loss=0.04165, over 4925.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2172, pruned_loss=0.03696, over 972144.62 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 22:51:11,416 INFO [train.py:715] (5/8) Epoch 7, batch 23650, loss[loss=0.1671, simple_loss=0.2325, pruned_loss=0.0508, over 4900.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03726, over 972113.39 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:51:49,265 INFO [train.py:715] (5/8) Epoch 7, batch 23700, loss[loss=0.1621, simple_loss=0.2293, pruned_loss=0.04746, over 4831.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03696, over 972089.55 frames.], batch size: 15, lr: 2.89e-04
2022-05-05 22:52:27,395 INFO [train.py:715] (5/8) Epoch 7, batch 23750, loss[loss=0.1747, simple_loss=0.2557, pruned_loss=0.04688, over 4887.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2171, pruned_loss=0.03702, over 971529.39 frames.], batch size: 19, lr: 2.89e-04
2022-05-05 22:53:04,575 INFO [train.py:715] (5/8) Epoch 7, batch 23800, loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04246, over 4835.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03659, over 971793.85 frames.], batch size: 13, lr: 2.89e-04
2022-05-05 22:53:42,350 INFO [train.py:715] (5/8) Epoch 7, batch 23850, loss[loss=0.1573, simple_loss=0.2231, pruned_loss=0.04569, over 4987.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03689, over 971635.21 frames.], batch size: 14, lr: 2.89e-04
2022-05-05 22:54:21,021 INFO [train.py:715] (5/8) Epoch 7, batch 23900, loss[loss=0.1154, simple_loss=0.1848, pruned_loss=0.023, over 4751.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03668, over 971077.52 frames.], batch size: 16, lr: 2.89e-04
2022-05-05 22:54:59,165 INFO [train.py:715] (5/8) Epoch 7, batch 23950, loss[loss=0.1307, simple_loss=0.2102, pruned_loss=0.02562, over 4932.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03671, over 971622.94 frames.], batch size: 29, lr: 2.89e-04
2022-05-05 22:55:36,637 INFO [train.py:715] (5/8) Epoch 7, batch 24000, loss[loss=0.1536, simple_loss=0.218, pruned_loss=0.04458, over 4854.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03633, over 971204.84 frames.], batch size: 15, lr: 2.89e-04
2022-05-05 22:55:36,637 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 22:55:46,186 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.108, simple_loss=0.1929, pruned_loss=0.01156, over 914524.00 frames.
2022-05-05 22:56:23,727 INFO [train.py:715] (5/8) Epoch 7, batch 24050, loss[loss=0.1249, simple_loss=0.2066, pruned_loss=0.02164, over 4782.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2171, pruned_loss=0.03674, over 970888.70 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:57:02,032 INFO [train.py:715] (5/8) Epoch 7, batch 24100, loss[loss=0.1436, simple_loss=0.2137, pruned_loss=0.03675, over 4987.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03677, over 971681.99 frames.], batch size: 14, lr: 2.89e-04
2022-05-05 22:57:40,438 INFO [train.py:715] (5/8) Epoch 7, batch 24150, loss[loss=0.1539, simple_loss=0.2265, pruned_loss=0.04063, over 4935.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2163, pruned_loss=0.03671, over 971617.84 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 22:58:18,172 INFO [train.py:715] (5/8) Epoch 7, batch 24200, loss[loss=0.1424, simple_loss=0.2117, pruned_loss=0.03658, over 4788.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2165, pruned_loss=0.03685, over 971971.26 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:58:55,938 INFO [train.py:715] (5/8) Epoch 7, batch 24250, loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03624, over 4899.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03638, over 971606.67 frames.], batch size: 19, lr: 2.89e-04
2022-05-05 22:59:34,585 INFO [train.py:715] (5/8) Epoch 7, batch 24300, loss[loss=0.1391, simple_loss=0.2145, pruned_loss=0.03182, over 4933.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03679, over 972429.47 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 23:00:12,423 INFO [train.py:715] (5/8) Epoch 7, batch 24350, loss[loss=0.1279, simple_loss=0.1946, pruned_loss=0.03058, over 4804.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03665, over 971043.06 frames.], batch size: 12, lr: 2.89e-04
2022-05-05 23:00:50,088 INFO [train.py:715] (5/8) Epoch 7, batch 24400, loss[loss=0.1495, simple_loss=0.2222, pruned_loss=0.03845, over 4886.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03655, over 972353.15 frames.], batch size: 22, lr: 2.89e-04
2022-05-05 23:01:28,244 INFO [train.py:715] (5/8) Epoch 7, batch 24450, loss[loss=0.1832, simple_loss=0.2591, pruned_loss=0.05367, over 4918.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03641, over 972178.59 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 23:02:06,217 INFO [train.py:715] (5/8) Epoch 7, batch 24500, loss[loss=0.1611, simple_loss=0.2236, pruned_loss=0.0493, over 4964.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03691, over 972211.38 frames.], batch size: 24, lr: 2.89e-04
2022-05-05 23:02:43,833 INFO [train.py:715] (5/8) Epoch 7, batch 24550, loss[loss=0.1481, simple_loss=0.2233, pruned_loss=0.03642, over 4848.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03699, over 972774.03 frames.], batch size: 30, lr: 2.88e-04
2022-05-05 23:03:22,003 INFO [train.py:715] (5/8) Epoch 7, batch 24600, loss[loss=0.1426, simple_loss=0.2068, pruned_loss=0.03922, over 4974.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03689, over 972999.34 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:04:01,122 INFO [train.py:715] (5/8) Epoch 7, batch 24650, loss[loss=0.1836, simple_loss=0.2548, pruned_loss=0.05621, over 4754.00 frames.], tot_loss[loss=0.1448, simple_loss=0.217, pruned_loss=0.03634, over 972552.27 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:04:39,572 INFO [train.py:715] (5/8) Epoch 7, batch 24700, loss[loss=0.1096, simple_loss=0.1874, pruned_loss=0.01589, over 4798.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03622, over 972683.12 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:05:17,696 INFO [train.py:715] (5/8) Epoch 7, batch 24750, loss[loss=0.1649, simple_loss=0.2389, pruned_loss=0.0455, over 4886.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03604, over 972758.92 frames.], batch size: 22, lr: 2.88e-04
2022-05-05 23:05:56,160 INFO [train.py:715] (5/8) Epoch 7, batch 24800, loss[loss=0.1409, simple_loss=0.2044, pruned_loss=0.03871, over 4743.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.0363, over 972215.37 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:06:35,234 INFO [train.py:715] (5/8) Epoch 7, batch 24850, loss[loss=0.1523, simple_loss=0.2269, pruned_loss=0.03889, over 4961.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03619, over 972063.46 frames.], batch size: 35, lr: 2.88e-04
2022-05-05 23:07:13,826 INFO [train.py:715] (5/8) Epoch 7, batch 24900, loss[loss=0.1836, simple_loss=0.2519, pruned_loss=0.05764, over 4836.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.03599, over 973003.92 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:07:53,089 INFO [train.py:715] (5/8) Epoch 7, batch 24950, loss[loss=0.1566, simple_loss=0.2219, pruned_loss=0.04565, over 4790.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2171, pruned_loss=0.03618, over 973217.79 frames.], batch size: 17, lr: 2.88e-04
2022-05-05 23:08:32,939 INFO [train.py:715] (5/8) Epoch 7, batch 25000, loss[loss=0.1564, simple_loss=0.239, pruned_loss=0.03685, over 4785.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2177, pruned_loss=0.0363, over 972718.25 frames.], batch size: 18, lr: 2.88e-04
2022-05-05 23:09:12,209 INFO [train.py:715] (5/8) Epoch 7, batch 25050, loss[loss=0.1272, simple_loss=0.1936, pruned_loss=0.03038, over 4792.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03652, over 973044.56 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:09:51,231 INFO [train.py:715] (5/8) Epoch 7, batch 25100, loss[loss=0.1225, simple_loss=0.1897, pruned_loss=0.02762, over 4971.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03675, over 972661.67 frames.], batch size: 14, lr: 2.88e-04
2022-05-05 23:10:31,397 INFO [train.py:715] (5/8) Epoch 7, batch 25150, loss[loss=0.1701, simple_loss=0.225, pruned_loss=0.05767, over 4848.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2167, pruned_loss=0.03691, over 973419.85 frames.], batch size: 13, lr: 2.88e-04
2022-05-05 23:11:11,711 INFO [train.py:715] (5/8) Epoch 7, batch 25200, loss[loss=0.1331, simple_loss=0.2023, pruned_loss=0.03194, over 4984.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2165, pruned_loss=0.0368, over 972709.03 frames.], batch size: 25, lr: 2.88e-04
2022-05-05 23:11:51,358 INFO [train.py:715] (5/8) Epoch 7, batch 25250, loss[loss=0.1571, simple_loss=0.23, pruned_loss=0.04205, over 4875.00 frames.], tot_loss[loss=0.1457, simple_loss=0.217, pruned_loss=0.03721, over 972535.70 frames.], batch size: 22, lr: 2.88e-04
2022-05-05 23:12:31,932 INFO [train.py:715] (5/8) Epoch 7, batch 25300, loss[loss=0.114, simple_loss=0.1903, pruned_loss=0.01888, over 4769.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03738, over 973177.99 frames.], batch size: 12, lr: 2.88e-04
2022-05-05 23:13:13,662 INFO [train.py:715] (5/8) Epoch 7, batch 25350, loss[loss=0.1634, simple_loss=0.2262, pruned_loss=0.05026, over 4798.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03681, over 972748.77 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:13:55,232 INFO [train.py:715] (5/8) Epoch 7, batch 25400, loss[loss=0.1437, simple_loss=0.2241, pruned_loss=0.03164, over 4973.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03713, over 972641.05 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:14:36,166 INFO [train.py:715] (5/8) Epoch 7, batch 25450, loss[loss=0.1378, simple_loss=0.22, pruned_loss=0.02785, over 4791.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03669, over 972817.40 frames.], batch size: 21, lr: 2.88e-04
2022-05-05 23:15:18,366 INFO [train.py:715] (5/8) Epoch 7, batch 25500, loss[loss=0.1613, simple_loss=0.2308, pruned_loss=0.0459, over 4834.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03657, over 972884.18 frames.], batch size: 20, lr: 2.88e-04
2022-05-05 23:16:00,248 INFO [train.py:715] (5/8) Epoch 7, batch 25550, loss[loss=0.1602, simple_loss=0.2246, pruned_loss=0.04791, over 4823.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 972506.00 frames.], batch size: 13, lr: 2.88e-04
2022-05-05 23:16:41,007 INFO [train.py:715] (5/8) Epoch 7, batch 25600, loss[loss=0.1246, simple_loss=0.1972, pruned_loss=0.02601, over 4764.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.0371, over 972513.10 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:17:22,270 INFO [train.py:715] (5/8) Epoch 7, batch 25650, loss[loss=0.1335, simple_loss=0.2122, pruned_loss=0.02743, over 4810.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03615, over 971634.68 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:18:03,672 INFO [train.py:715] (5/8) Epoch 7, batch 25700, loss[loss=0.132, simple_loss=0.2094, pruned_loss=0.02735, over 4847.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.03616, over 970120.90 frames.], batch size: 13, lr: 2.88e-04
2022-05-05 23:18:45,503 INFO [train.py:715] (5/8) Epoch 7, batch 25750, loss[loss=0.1565, simple_loss=0.2358, pruned_loss=0.03858, over 4913.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03688, over 971235.77 frames.], batch size: 18, lr: 2.88e-04
2022-05-05 23:19:26,138 INFO [train.py:715] (5/8) Epoch 7, batch 25800, loss[loss=0.1092, simple_loss=0.1746, pruned_loss=0.02189, over 4857.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03629, over 972058.30 frames.], batch size: 12, lr: 2.88e-04
2022-05-05 23:20:08,459 INFO [train.py:715] (5/8) Epoch 7, batch 25850, loss[loss=0.164, simple_loss=0.229, pruned_loss=0.04953, over 4928.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03652, over 972820.28 frames.], batch size: 17, lr: 2.88e-04
2022-05-05 23:20:50,390 INFO [train.py:715] (5/8) Epoch 7, batch 25900, loss[loss=0.1385, simple_loss=0.2066, pruned_loss=0.03523, over 4793.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03654, over 972810.22 frames.], batch size: 24, lr: 2.88e-04
2022-05-05 23:21:31,302 INFO [train.py:715] (5/8) Epoch 7, batch 25950, loss[loss=0.1663, simple_loss=0.2296, pruned_loss=0.05153, over 4873.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03699, over 972842.57 frames.], batch size: 32, lr: 2.88e-04
2022-05-05 23:22:12,745 INFO [train.py:715] (5/8) Epoch 7, batch 26000, loss[loss=0.1425, simple_loss=0.2208, pruned_loss=0.0321, over 4749.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03653, over 972119.37 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:22:54,195 INFO [train.py:715] (5/8) Epoch 7, batch 26050, loss[loss=0.1553, simple_loss=0.2301, pruned_loss=0.04025, over 4988.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03576, over 971619.91 frames.], batch size: 31, lr: 2.88e-04
2022-05-05 23:23:36,129 INFO [train.py:715] (5/8) Epoch 7, batch 26100, loss[loss=0.1549, simple_loss=0.2283, pruned_loss=0.04076, over 4920.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2169, pruned_loss=0.03623, over 971937.32 frames.], batch size: 18, lr: 2.88e-04
2022-05-05 23:24:16,473 INFO [train.py:715] (5/8) Epoch 7, batch 26150, loss[loss=0.1809, simple_loss=0.2492, pruned_loss=0.0563, over 4870.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03604, over 972158.26 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:24:57,987 INFO [train.py:715] (5/8) Epoch 7, batch 26200, loss[loss=0.157, simple_loss=0.2336, pruned_loss=0.04021, over 4845.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03632, over 971754.30 frames.], batch size: 20, lr: 2.88e-04
2022-05-05 23:25:39,234 INFO [train.py:715] (5/8) Epoch 7, batch 26250, loss[loss=0.1267, simple_loss=0.2038, pruned_loss=0.02477, over 4946.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.0359, over 972011.65 frames.], batch size: 29, lr: 2.88e-04
2022-05-05 23:26:19,600 INFO [train.py:715] (5/8) Epoch 7, batch 26300, loss[loss=0.1437, simple_loss=0.2171, pruned_loss=0.03514, over 4784.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03643, over 972805.37 frames.], batch size: 17, lr: 2.88e-04
2022-05-05 23:26:59,780 INFO [train.py:715] (5/8) Epoch 7, batch 26350, loss[loss=0.1525, simple_loss=0.2244, pruned_loss=0.04035, over 4947.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03614, over 972836.66 frames.], batch size: 29, lr: 2.88e-04
2022-05-05 23:27:40,231 INFO [train.py:715] (5/8) Epoch 7, batch 26400, loss[loss=0.1361, simple_loss=0.2111, pruned_loss=0.03051, over 4882.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03627, over 972647.69 frames.], batch size: 16, lr: 2.87e-04
2022-05-05 23:28:20,879 INFO [train.py:715] (5/8) Epoch 7, batch 26450, loss[loss=0.1539, simple_loss=0.2235, pruned_loss=0.04215, over 4913.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03663, over 972736.75 frames.], batch size: 22, lr: 2.87e-04
2022-05-05 23:29:00,625 INFO [train.py:715] (5/8) Epoch 7, batch 26500, loss[loss=0.124, simple_loss=0.1956, pruned_loss=0.02627, over 4975.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03642, over 972601.95 frames.], batch size: 15, lr: 2.87e-04
2022-05-05 23:29:40,313 INFO [train.py:715] (5/8) Epoch 7, batch 26550, loss[loss=0.1558, simple_loss=0.2409, pruned_loss=0.03531, over 4831.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03628, over 972289.63 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:30:20,786 INFO [train.py:715] (5/8) Epoch 7, batch 26600, loss[loss=0.1551, simple_loss=0.2279, pruned_loss=0.04115, over 4745.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03631, over 972029.70 frames.], batch size: 16, lr: 2.87e-04
2022-05-05 23:31:00,458 INFO [train.py:715] (5/8) Epoch 7, batch 26650, loss[loss=0.1487, simple_loss=0.2177, pruned_loss=0.03986, over 4777.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03673, over 970947.97 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:31:40,552 INFO [train.py:715] (5/8) Epoch 7, batch 26700, loss[loss=0.1333, simple_loss=0.2166, pruned_loss=0.02493, over 4765.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.037, over 971234.58 frames.], batch size: 19, lr: 2.87e-04
2022-05-05 23:32:21,232 INFO [train.py:715] (5/8) Epoch 7, batch 26750, loss[loss=0.1464, simple_loss=0.2146, pruned_loss=0.0391, over 4956.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03748, over 971721.23 frames.], batch size: 24, lr: 2.87e-04
2022-05-05 23:33:01,187 INFO [train.py:715] (5/8) Epoch 7, batch 26800, loss[loss=0.1168, simple_loss=0.1865, pruned_loss=0.02352, over 4769.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03741, over 971488.95 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:33:40,968 INFO [train.py:715] (5/8) Epoch 7, batch 26850, loss[loss=0.1081, simple_loss=0.182, pruned_loss=0.01703, over 4937.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03753, over 971733.77 frames.], batch size: 29, lr: 2.87e-04
2022-05-05 23:34:21,586 INFO [train.py:715] (5/8) Epoch 7, batch 26900, loss[loss=0.1929, simple_loss=0.2628, pruned_loss=0.06154, over 4765.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03738, over 972158.20 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:35:02,618 INFO [train.py:715] (5/8) Epoch 7, batch 26950, loss[loss=0.164, simple_loss=0.2296, pruned_loss=0.04922, over 4949.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03727, over 971947.58 frames.], batch size: 24, lr: 2.87e-04
2022-05-05 23:35:42,948 INFO [train.py:715] (5/8) Epoch 7, batch 27000, loss[loss=0.1333, simple_loss=0.2, pruned_loss=0.03323, over 4829.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.03747, over 971392.23 frames.], batch size: 26, lr: 2.87e-04
2022-05-05 23:35:42,949 INFO [train.py:733] (5/8) Computing validation loss
2022-05-05 23:35:52,667 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.108, simple_loss=0.1928, pruned_loss=0.01156, over 914524.00 frames.
2022-05-05 23:36:33,213 INFO [train.py:715] (5/8) Epoch 7, batch 27050, loss[loss=0.1495, simple_loss=0.2214, pruned_loss=0.03882, over 4830.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03731, over 972225.98 frames.], batch size: 15, lr: 2.87e-04
2022-05-05 23:37:14,390 INFO [train.py:715] (5/8) Epoch 7, batch 27100, loss[loss=0.1359, simple_loss=0.2057, pruned_loss=0.03311, over 4968.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2181, pruned_loss=0.03686, over 972612.04 frames.], batch size: 24, lr: 2.87e-04
2022-05-05 23:37:56,258 INFO [train.py:715] (5/8) Epoch 7, batch 27150, loss[loss=0.1506, simple_loss=0.2138, pruned_loss=0.04367, over 4882.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03674, over 971730.07 frames.], batch size: 32, lr: 2.87e-04
2022-05-05 23:38:37,508 INFO [train.py:715] (5/8) Epoch 7, batch 27200, loss[loss=0.1332, simple_loss=0.2036, pruned_loss=0.03141, over 4770.00 frames.], tot_loss[loss=0.1451, simple_loss=0.217, pruned_loss=0.03662, over 971666.45 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:39:18,965 INFO [train.py:715] (5/8) Epoch 7, batch 27250, loss[loss=0.1596, simple_loss=0.2262, pruned_loss=0.04651, over 4775.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03669, over 972031.35 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:40:00,801 INFO [train.py:715] (5/8) Epoch 7, batch 27300, loss[loss=0.1693, simple_loss=0.2373, pruned_loss=0.05059, over 4836.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03704, over 971588.29 frames.], batch size: 26, lr: 2.87e-04
2022-05-05 23:40:41,767 INFO [train.py:715] (5/8) Epoch 7, batch 27350, loss[loss=0.1547, simple_loss=0.2342, pruned_loss=0.03761, over 4780.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03714, over 971511.80 frames.], batch size: 17, lr: 2.87e-04
2022-05-05 23:41:23,059 INFO [train.py:715] (5/8) Epoch 7, batch 27400, loss[loss=0.1738, simple_loss=0.2449, pruned_loss=0.05136, over 4798.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03732, over 971119.24 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:42:04,102 INFO [train.py:715] (5/8) Epoch 7, batch 27450, loss[loss=0.1453, simple_loss=0.2043, pruned_loss=0.04313, over 4920.00 frames.], tot_loss[loss=0.146, simple_loss=0.2181, pruned_loss=0.03696, over 971077.70 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:42:45,309 INFO [train.py:715] (5/8) Epoch 7, batch 27500, loss[loss=0.1731, simple_loss=0.2266, pruned_loss=0.05982, over 4752.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03652, over 971154.23 frames.], batch size: 16, lr: 2.87e-04
2022-05-05 23:43:25,877 INFO [train.py:715] (5/8) Epoch 7, batch 27550, loss[loss=0.1494, simple_loss=0.2226, pruned_loss=0.03808, over 4959.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03698, over 972530.50 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:44:06,397 INFO [train.py:715] (5/8) Epoch 7, batch 27600, loss[loss=0.1125, simple_loss=0.191, pruned_loss=0.01706, over 4948.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2186, pruned_loss=0.03711, over 973184.37 frames.], batch size: 29, lr: 2.87e-04
2022-05-05 23:44:47,789 INFO [train.py:715] (5/8) Epoch 7, batch 27650, loss[loss=0.1676, simple_loss=0.2466, pruned_loss=0.04429, over 4899.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2183, pruned_loss=0.03728, over 972621.37 frames.], batch size: 39, lr: 2.87e-04
2022-05-05 23:45:28,506 INFO [train.py:715] (5/8) Epoch 7, batch 27700, loss[loss=0.1436, simple_loss=0.2057, pruned_loss=0.04076, over 4969.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.037, over 972615.80 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:46:09,245 INFO [train.py:715] (5/8) Epoch 7, batch 27750, loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03559, over 4762.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03673, over 972555.84 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:46:50,125 INFO [train.py:715] (5/8) Epoch 7, batch 27800, loss[loss=0.1451, simple_loss=0.2062, pruned_loss=0.04197, over 4856.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03726, over 972294.36 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:47:31,341 INFO [train.py:715] (5/8) Epoch 7, batch 27850, loss[loss=0.1765, simple_loss=0.2414, pruned_loss=0.05581, over 4926.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03758, over 971757.08 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:48:11,404 INFO [train.py:715] (5/8) Epoch 7, batch 27900, loss[loss=0.1302, simple_loss=0.1936, pruned_loss=0.03345, over 4782.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03779, over 971791.73 frames.], batch size: 12, lr: 2.87e-04
2022-05-05 23:48:52,366 INFO [train.py:715] (5/8) Epoch 7, batch 27950, loss[loss=0.1334, simple_loss=0.2059, pruned_loss=0.03044, over 4813.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03721, over 972261.32 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:49:33,554 INFO [train.py:715] (5/8) Epoch 7, batch 28000, loss[loss=0.1312, simple_loss=0.206, pruned_loss=0.02816, over 4903.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03692, over 974162.19 frames.], batch size: 17, lr: 2.87e-04
2022-05-05 23:50:14,245 INFO [train.py:715] (5/8) Epoch 7, batch 28050, loss[loss=0.1579, simple_loss=0.2217, pruned_loss=0.04706, over 4751.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03686, over 973777.00 frames.], batch size: 16, lr: 2.87e-04
2022-05-05 23:50:54,406 INFO [train.py:715] (5/8) Epoch 7, batch 28100, loss[loss=0.1441, simple_loss=0.2006, pruned_loss=0.0438, over 4974.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03699, over 972992.24 frames.], batch size: 15, lr: 2.87e-04
2022-05-05 23:51:35,205 INFO [train.py:715] (5/8) Epoch 7, batch 28150, loss[loss=0.1399, simple_loss=0.2091, pruned_loss=0.03533, over 4786.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03723, over 972538.70 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:52:16,646 INFO [train.py:715] (5/8) Epoch 7, batch 28200, loss[loss=0.1157, simple_loss=0.1922, pruned_loss=0.0196, over 4764.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03688, over 972661.36 frames.], batch size: 19, lr: 2.87e-04
2022-05-05 23:52:56,852 INFO [train.py:715] (5/8) Epoch 7, batch 28250, loss[loss=0.1719, simple_loss=0.2289, pruned_loss=0.05746, over 4796.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03741, over 972556.97 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:53:38,387 INFO [train.py:715] (5/8) Epoch 7, batch 28300, loss[loss=0.1633, simple_loss=0.2227, pruned_loss=0.0519, over 4856.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03743, over 973115.30 frames.], batch size: 13, lr: 2.86e-04
2022-05-05 23:54:21,485 INFO [train.py:715] (5/8) Epoch 7, batch 28350, loss[loss=0.1463, simple_loss=0.2184, pruned_loss=0.0371, over 4987.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03731, over 973795.27 frames.], batch size: 25, lr: 2.86e-04
2022-05-05 23:55:01,296 INFO [train.py:715] (5/8) Epoch 7, batch 28400, loss[loss=0.1563, simple_loss=0.219, pruned_loss=0.0468, over 4847.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03736, over 973224.51 frames.], batch size: 32, lr: 2.86e-04
2022-05-05 23:55:40,831 INFO [train.py:715] (5/8) Epoch 7, batch 28450, loss[loss=0.1579, simple_loss=0.2354, pruned_loss=0.04015, over 4796.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03648, over 972611.57 frames.], batch size: 21, lr: 2.86e-04
2022-05-05 23:56:20,934 INFO [train.py:715] (5/8) Epoch 7, batch 28500, loss[loss=0.1561, simple_loss=0.2273, pruned_loss=0.04249, over 4884.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03596, over 972844.70 frames.], batch size: 22, lr: 2.86e-04
2022-05-05 23:57:01,424 INFO [train.py:715] (5/8) Epoch 7, batch 28550, loss[loss=0.1397, simple_loss=0.2112, pruned_loss=0.03415, over 4887.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03625, over 973108.42 frames.], batch size: 22, lr: 2.86e-04
2022-05-05 23:57:41,417 INFO [train.py:715] (5/8) Epoch 7, batch 28600, loss[loss=0.1782, simple_loss=0.2322, pruned_loss=0.06209, over 4881.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.0371, over 974140.05 frames.], batch size: 38, lr: 2.86e-04
2022-05-05 23:58:21,637 INFO [train.py:715] (5/8) Epoch 7, batch 28650, loss[loss=0.1672, simple_loss=0.2322, pruned_loss=0.0511, over 4862.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03673, over 974201.37 frames.], batch size: 30, lr: 2.86e-04
2022-05-05 23:59:03,072 INFO [train.py:715] (5/8) Epoch 7, batch 28700, loss[loss=0.1384, simple_loss=0.2146, pruned_loss=0.03105, over 4844.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2169, pruned_loss=0.03676, over 973764.72 frames.], batch size: 15, lr: 2.86e-04
2022-05-05 23:59:43,954 INFO [train.py:715] (5/8) Epoch 7, batch 28750, loss[loss=0.195, simple_loss=0.2515, pruned_loss=0.06928, over 4933.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03722, over 972795.26 frames.], batch size: 39, lr: 2.86e-04
2022-05-06 00:00:24,187 INFO [train.py:715] (5/8) Epoch 7, batch 28800, loss[loss=0.1421, simple_loss=0.2116, pruned_loss=0.03631, over 4972.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03673, over 972068.01 frames.], batch size: 35, lr: 2.86e-04
2022-05-06 00:01:04,805 INFO [train.py:715] (5/8) Epoch 7, batch 28850, loss[loss=0.1444, simple_loss=0.2102, pruned_loss=0.03923, over 4737.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2169, pruned_loss=0.03677, over 971142.17 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:01:45,175 INFO [train.py:715] (5/8) Epoch 7, batch 28900, loss[loss=0.1439, simple_loss=0.2113, pruned_loss=0.03823, over 4776.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.0369, over 971502.44 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:02:24,695 INFO [train.py:715] (5/8) Epoch 7, batch 28950, loss[loss=0.1238, simple_loss=0.1937, pruned_loss=0.02695, over 4770.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03658, over 971645.76 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:03:04,253 INFO [train.py:715] (5/8) Epoch 7, batch 29000, loss[loss=0.148, simple_loss=0.2278, pruned_loss=0.0341, over 4922.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2162, pruned_loss=0.03628, over 972153.57 frames.], batch size: 29, lr: 2.86e-04
2022-05-06 00:03:44,911 INFO [train.py:715] (5/8) Epoch 7, batch 29050, loss[loss=0.139, simple_loss=0.2116, pruned_loss=0.03319, over 4757.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03642, over 971579.12 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:04:24,480 INFO [train.py:715] (5/8) Epoch 7, batch 29100, loss[loss=0.175, simple_loss=0.2589, pruned_loss=0.04555, over 4854.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03629, over 971554.33 frames.], batch size: 20, lr: 2.86e-04
2022-05-06 00:05:04,255 INFO [train.py:715] (5/8) Epoch 7, batch 29150, loss[loss=0.1333, simple_loss=0.2058, pruned_loss=0.03035, over 4758.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03689, over 971342.89 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:05:44,146 INFO [train.py:715] (5/8) Epoch 7, batch 29200, loss[loss=0.147, simple_loss=0.2172, pruned_loss=0.03843, over 4822.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2162, pruned_loss=0.03664, over 970760.50 frames.], batch size: 15, lr: 2.86e-04
2022-05-06 00:06:24,420 INFO [train.py:715] (5/8) Epoch 7, batch 29250, loss[loss=0.1796, simple_loss=0.2393, pruned_loss=0.05993, over 4790.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03658, over 971155.42 frames.], batch size: 21, lr: 2.86e-04
2022-05-06 00:07:04,325 INFO [train.py:715] (5/8) Epoch 7, batch 29300, loss[loss=0.1328, simple_loss=0.2092, pruned_loss=0.02817, over 4818.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2169, pruned_loss=0.03714, over 971488.40 frames.], batch size: 25, lr: 2.86e-04
2022-05-06 00:07:44,017 INFO [train.py:715] (5/8) Epoch 7, batch 29350, loss[loss=0.1276, simple_loss=0.1986, pruned_loss=0.02833, over 4942.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03717, over 972680.72 frames.], batch size: 35, lr: 2.86e-04
2022-05-06 00:08:24,285 INFO [train.py:715] (5/8) Epoch 7, batch 29400, loss[loss=0.1359, simple_loss=0.2104, pruned_loss=0.03066, over 4970.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03735, over 973005.16 frames.], batch size: 24, lr: 2.86e-04
2022-05-06 00:09:03,566 INFO [train.py:715] (5/8) Epoch 7, batch 29450, loss[loss=0.1537, simple_loss=0.2225, pruned_loss=0.04241, over 4943.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.03708, over 973447.67 frames.], batch size: 29, lr: 2.86e-04
2022-05-06 00:09:43,846 INFO [train.py:715] (5/8) Epoch 7, batch 29500, loss[loss=0.1302, simple_loss=0.1955, pruned_loss=0.03245, over 4852.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03684, over 973582.60 frames.], batch size: 13, lr: 2.86e-04
2022-05-06 00:10:23,570 INFO [train.py:715] (5/8) Epoch 7, batch 29550, loss[loss=0.1395, simple_loss=0.2176, pruned_loss=0.03075, over 4823.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03698, over 973426.19 frames.], batch size: 27, lr: 2.86e-04
2022-05-06 00:11:03,252 INFO [train.py:715] (5/8) Epoch 7, batch 29600, loss[loss=0.134, simple_loss=0.1988, pruned_loss=0.03465, over 4867.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03757, over 973397.80 frames.], batch size: 20, lr: 2.86e-04
2022-05-06 00:11:43,210 INFO [train.py:715] (5/8) Epoch 7, batch 29650, loss[loss=0.1506, simple_loss=0.2223, pruned_loss=0.03945, over 4914.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03725, over 973402.36 frames.], batch size: 39, lr: 2.86e-04
2022-05-06 00:12:23,005 INFO [train.py:715] (5/8) Epoch 7, batch 29700, loss[loss=0.1487, simple_loss=0.2141, pruned_loss=0.0417, over 4896.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03721, over 973219.88 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:13:02,661 INFO [train.py:715] (5/8) Epoch 7, batch 29750, loss[loss=0.1289, simple_loss=0.1985, pruned_loss=0.02958, over 4782.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.037, over 973060.16 frames.], batch size: 17, lr: 2.86e-04
2022-05-06 00:13:42,294 INFO [train.py:715] (5/8) Epoch 7, batch 29800, loss[loss=0.1423, simple_loss=0.2155, pruned_loss=0.0345, over 4729.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03752, over 973108.76 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:14:22,416 INFO [train.py:715] (5/8) Epoch 7, batch 29850, loss[loss=0.1382, simple_loss=0.2048, pruned_loss=0.03577, over 4950.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03754, over 973634.10 frames.], batch size: 21, lr: 2.86e-04
2022-05-06 00:15:02,280 INFO [train.py:715] (5/8) Epoch 7, batch 29900, loss[loss=0.1244, simple_loss=0.2094, pruned_loss=0.01976, over 4815.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2186, pruned_loss=0.0373, over 972613.77 frames.], batch size: 21, lr: 2.86e-04
2022-05-06 00:15:41,859 INFO [train.py:715] (5/8) Epoch 7, batch 29950, loss[loss=0.1273, simple_loss=0.2029, pruned_loss=0.02585, over 4809.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03699, over 973035.45 frames.], batch size: 17, lr: 2.86e-04
2022-05-06 00:16:21,223 INFO [train.py:715] (5/8) Epoch 7, batch 30000, loss[loss=0.1458, simple_loss=0.2277, pruned_loss=0.03198, over 4928.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03622, over 973253.48 frames.], batch size: 29, lr: 2.86e-04
2022-05-06 00:16:21,224 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 00:16:41,746 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.1081, simple_loss=0.1929, pruned_loss=0.01164, over 914524.00 frames.
2022-05-06 00:17:21,553 INFO [train.py:715] (5/8) Epoch 7, batch 30050, loss[loss=0.1433, simple_loss=0.2114, pruned_loss=0.03764, over 4761.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03663, over 972997.49 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:18:00,837 INFO [train.py:715] (5/8) Epoch 7, batch 30100, loss[loss=0.135, simple_loss=0.2018, pruned_loss=0.03412, over 4752.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03714, over 972780.95 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:18:40,785 INFO [train.py:715] (5/8) Epoch 7, batch 30150, loss[loss=0.135, simple_loss=0.2161, pruned_loss=0.02698, over 4812.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03708, over 972262.95 frames.], batch size: 26, lr: 2.86e-04
2022-05-06 00:19:20,431 INFO [train.py:715] (5/8) Epoch 7, batch 30200, loss[loss=0.1349, simple_loss=0.2037, pruned_loss=0.03304, over 4861.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03735, over 973176.23 frames.], batch size: 20, lr: 2.85e-04
2022-05-06 00:20:00,687 INFO [train.py:715] (5/8) Epoch 7, batch 30250, loss[loss=0.1496, simple_loss=0.2165, pruned_loss=0.04132, over 4967.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03675, over 973913.16 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:20:39,865 INFO [train.py:715] (5/8) Epoch 7, batch 30300, loss[loss=0.1399, simple_loss=0.2119, pruned_loss=0.03393, over 4970.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2177, pruned_loss=0.03675, over 974684.94 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:21:19,494 INFO [train.py:715] (5/8) Epoch 7, batch 30350, loss[loss=0.1381, simple_loss=0.2078, pruned_loss=0.03416, over 4758.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2181, pruned_loss=0.03678, over 973683.47 frames.], batch size: 19, lr: 2.85e-04
2022-05-06 00:21:58,988 INFO [train.py:715] (5/8) Epoch 7, batch 30400, loss[loss=0.1438, simple_loss=0.2257, pruned_loss=0.03102, over 4763.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2177, pruned_loss=0.03628, over 973512.34 frames.], batch size: 17, lr: 2.85e-04
2022-05-06 00:22:38,979 INFO [train.py:715] (5/8) Epoch 7, batch 30450, loss[loss=0.1277, simple_loss=0.2017, pruned_loss=0.02686, over 4957.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2176, pruned_loss=0.03625, over 973126.00 frames.], batch size: 29, lr: 2.85e-04
2022-05-06 00:23:18,896 INFO [train.py:715] (5/8) Epoch 7, batch 30500, loss[loss=0.1521, simple_loss=0.2162, pruned_loss=0.04401, over 4738.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03675, over 972637.25 frames.], batch size: 16, lr: 2.85e-04
2022-05-06 00:23:58,831 INFO [train.py:715] (5/8) Epoch 7, batch 30550, loss[loss=0.1211, simple_loss=0.194, pruned_loss=0.02411, over 4982.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.0367, over 972261.88 frames.], batch size: 35, lr: 2.85e-04
2022-05-06 00:24:38,530 INFO [train.py:715] (5/8) Epoch 7, batch 30600, loss[loss=0.1446, simple_loss=0.2141, pruned_loss=0.03757, over 4744.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2174, pruned_loss=0.03635, over 972642.16 frames.], batch size: 16, lr: 2.85e-04
2022-05-06 00:25:18,166 INFO [train.py:715] (5/8) Epoch 7, batch 30650, loss[loss=0.1461, simple_loss=0.2138, pruned_loss=0.03918, over 4962.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03645, over 972972.71 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:25:57,785 INFO [train.py:715] (5/8) Epoch 7, batch 30700, loss[loss=0.1096, simple_loss=0.1718, pruned_loss=0.0237, over 4778.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03595, over 972686.84 frames.], batch size: 12, lr: 2.85e-04
2022-05-06 00:26:36,841 INFO [train.py:715] (5/8) Epoch 7, batch 30750, loss[loss=0.1254, simple_loss=0.2024, pruned_loss=0.02414, over 4826.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03623, over 973010.17 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:27:15,904 INFO [train.py:715] (5/8) Epoch 7, batch 30800, loss[loss=0.1603, simple_loss=0.2339, pruned_loss=0.04339, over 4931.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03672, over 972747.90 frames.], batch size: 39, lr: 2.85e-04
2022-05-06 00:27:55,686 INFO [train.py:715] (5/8) Epoch 7, batch 30850, loss[loss=0.1638, simple_loss=0.2442, pruned_loss=0.04177, over 4816.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2174, pruned_loss=0.0364, over 972819.70 frames.], batch size: 26, lr: 2.85e-04
2022-05-06 00:28:35,194 INFO [train.py:715] (5/8) Epoch 7, batch 30900, loss[loss=0.1314, simple_loss=0.2078, pruned_loss=0.02753, over 4815.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03597, over 973220.80 frames.], batch size: 27, lr: 2.85e-04
2022-05-06 00:29:15,590 INFO [train.py:715] (5/8) Epoch 7, batch 30950, loss[loss=0.1301, simple_loss=0.2096, pruned_loss=0.02529, over 4826.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03618, over 973132.95 frames.], batch size: 26, lr: 2.85e-04
2022-05-06 00:29:54,978 INFO [train.py:715] (5/8) Epoch 7, batch 31000, loss[loss=0.1482, simple_loss=0.2091, pruned_loss=0.04364, over 4786.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03642, over 972712.50 frames.], batch size: 14, lr: 2.85e-04
2022-05-06 00:30:34,536 INFO [train.py:715] (5/8) Epoch 7, batch 31050, loss[loss=0.158, simple_loss=0.2343, pruned_loss=0.04089, over 4772.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03664, over 972664.45 frames.], batch size: 17, lr: 2.85e-04
2022-05-06 00:31:14,373 INFO [train.py:715] (5/8) Epoch 7, batch 31100, loss[loss=0.1767, simple_loss=0.2423, pruned_loss=0.05562, over 4928.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03646, over 972636.80 frames.], batch size: 29, lr: 2.85e-04
2022-05-06 00:31:54,493 INFO [train.py:715] (5/8) Epoch 7, batch 31150, loss[loss=0.149, simple_loss=0.2085, pruned_loss=0.04476, over 4893.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03737, over 972581.24 frames.], batch size: 32, lr: 2.85e-04
2022-05-06 00:32:33,846 INFO [train.py:715] (5/8) Epoch 7, batch 31200, loss[loss=0.1386, simple_loss=0.2045, pruned_loss=0.03636, over 4812.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03684, over 971307.17 frames.], batch size: 25, lr: 2.85e-04
2022-05-06 00:33:13,812 INFO [train.py:715] (5/8) Epoch 7, batch 31250, loss[loss=0.1493, simple_loss=0.2174, pruned_loss=0.04061, over 4776.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03642, over 971275.39 frames.], batch size: 18, lr: 2.85e-04
2022-05-06 00:33:54,541 INFO [train.py:715] (5/8) Epoch 7, batch 31300, loss[loss=0.1504, simple_loss=0.2274, pruned_loss=0.0367, over 4693.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03608, over 970921.60 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:34:34,133 INFO [train.py:715] (5/8) Epoch 7, batch 31350, loss[loss=0.1373, simple_loss=0.1993, pruned_loss=0.03764, over 4960.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.036, over 970871.08 frames.], batch size: 14, lr: 2.85e-04
2022-05-06 00:35:14,069 INFO [train.py:715] (5/8) Epoch 7, batch 31400, loss[loss=0.1454, simple_loss=0.2228, pruned_loss=0.03396, over 4877.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03608, over 971408.64 frames.], batch size: 16, lr: 2.85e-04
2022-05-06 00:35:53,412 INFO [train.py:715] (5/8) Epoch 7, batch 31450, loss[loss=0.1449, simple_loss=0.2204, pruned_loss=0.03468, over 4857.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03628, over 971674.52 frames.], batch size: 30, lr: 2.85e-04
2022-05-06 00:36:33,194 INFO [train.py:715] (5/8) Epoch 7, batch 31500, loss[loss=0.1365, simple_loss=0.2164, pruned_loss=0.02832, over 4980.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.03652, over 971742.44 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:37:12,316 INFO [train.py:715] (5/8) Epoch 7, batch 31550, loss[loss=0.1478, simple_loss=0.214, pruned_loss=0.04076, over 4711.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2161, pruned_loss=0.03655, over 972300.30 frames.], batch size: 12, lr: 2.85e-04
2022-05-06 00:37:52,277 INFO [train.py:715] (5/8) Epoch 7, batch 31600, loss[loss=0.1362, simple_loss=0.211, pruned_loss=0.03072, over 4780.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.0362, over 972543.74 frames.], batch size: 17, lr: 2.85e-04
2022-05-06 00:38:32,104 INFO [train.py:715] (5/8) Epoch 7, batch 31650, loss[loss=0.1483, simple_loss=0.2398, pruned_loss=0.02839, over 4966.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03613, over 971840.36 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:39:11,524 INFO [train.py:715] (5/8) Epoch 7, batch 31700, loss[loss=0.1305, simple_loss=0.2108, pruned_loss=0.02508, over 4953.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2153, pruned_loss=0.03602, over 971441.15 frames.], batch size: 21, lr: 2.85e-04
2022-05-06 00:39:51,223 INFO [train.py:715] (5/8) Epoch 7, batch 31750, loss[loss=0.1256, simple_loss=0.2034, pruned_loss=0.02394, over 4959.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2169, pruned_loss=0.03714, over 971447.23 frames.], batch size: 21, lr: 2.85e-04
2022-05-06 00:40:30,494 INFO [train.py:715] (5/8) Epoch 7, batch 31800, loss[loss=0.1328, simple_loss=0.2112, pruned_loss=0.02719, over 4968.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2173, pruned_loss=0.03753, over 971540.00 frames.], batch size: 21, lr: 2.85e-04
2022-05-06 00:41:09,607 INFO [train.py:715] (5/8) Epoch 7, batch 31850, loss[loss=0.1771, simple_loss=0.2469, pruned_loss=0.05363, over 4744.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03732, over 971669.11 frames.], batch size: 16, lr: 2.85e-04
2022-05-06 00:41:49,864 INFO [train.py:715] (5/8) Epoch 7, batch 31900, loss[loss=0.1411, simple_loss=0.2171, pruned_loss=0.03251, over 4892.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03718, over 972108.48 frames.], batch size: 17, lr: 2.85e-04
2022-05-06 00:42:30,602 INFO [train.py:715] (5/8) Epoch 7, batch 31950, loss[loss=0.1628, simple_loss=0.2373, pruned_loss=0.04414, over 4859.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03651, over 971424.69 frames.], batch size: 30, lr: 2.85e-04
2022-05-06 00:43:11,068 INFO [train.py:715] (5/8) Epoch 7, batch 32000, loss[loss=0.1193, simple_loss=0.1886, pruned_loss=0.02498, over 4637.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03587, over 971724.00 frames.], batch size: 13, lr: 2.85e-04
2022-05-06 00:43:50,734 INFO [train.py:715] (5/8) Epoch 7, batch 32050, loss[loss=0.1654, simple_loss=0.2265, pruned_loss=0.05215, over 4961.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03574, over 971575.10 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:44:30,681 INFO [train.py:715] (5/8) Epoch 7, batch 32100, loss[loss=0.1244, simple_loss=0.2046, pruned_loss=0.0221, over 4762.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03591, over 972161.02 frames.], batch size: 19, lr: 2.85e-04
2022-05-06 00:45:10,477 INFO [train.py:715] (5/8) Epoch 7, batch 32150, loss[loss=0.1471, simple_loss=0.2099, pruned_loss=0.04211, over 4797.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.0357, over 972487.69 frames.], batch size: 24, lr: 2.84e-04
2022-05-06 00:45:50,032 INFO [train.py:715] (5/8) Epoch 7, batch 32200, loss[loss=0.1356, simple_loss=0.2048, pruned_loss=0.03323, over 4801.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03557, over 971736.94 frames.], batch size: 24, lr: 2.84e-04
2022-05-06 00:46:29,881 INFO [train.py:715] (5/8) Epoch 7, batch 32250, loss[loss=0.1863, simple_loss=0.2433, pruned_loss=0.06467, over 4880.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03586, over 971101.72 frames.], batch size: 32, lr: 2.84e-04
2022-05-06 00:47:09,673 INFO [train.py:715] (5/8) Epoch 7, batch 32300, loss[loss=0.1206, simple_loss=0.1885, pruned_loss=0.02636, over 4693.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03631, over 970512.31 frames.], batch size: 15, lr: 2.84e-04
2022-05-06 00:47:50,012 INFO [train.py:715] (5/8) Epoch 7, batch 32350, loss[loss=0.166, simple_loss=0.2383, pruned_loss=0.04683, over 4967.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03675, over 971830.44 frames.], batch size: 24, lr: 2.84e-04
2022-05-06 00:48:29,371 INFO [train.py:715] (5/8) Epoch 7, batch 32400, loss[loss=0.1315, simple_loss=0.2072, pruned_loss=0.02792, over 4956.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03617, over 971927.20 frames.], batch size: 21, lr: 2.84e-04
2022-05-06 00:49:09,264 INFO [train.py:715] (5/8) Epoch 7, batch 32450, loss[loss=0.1431, simple_loss=0.2237, pruned_loss=0.03131, over 4809.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2175, pruned_loss=0.03663, over 971264.23 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 00:49:48,737 INFO [train.py:715] (5/8) Epoch 7, batch 32500, loss[loss=0.1191, simple_loss=0.1851, pruned_loss=0.02652, over 4855.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03656, over 971865.91 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 00:50:28,299 INFO [train.py:715] (5/8) Epoch 7, batch 32550, loss[loss=0.148, simple_loss=0.221, pruned_loss=0.03749, over 4816.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03711, over 971245.75 frames.], batch size: 26, lr: 2.84e-04
2022-05-06 00:51:08,054 INFO [train.py:715] (5/8) Epoch 7, batch 32600, loss[loss=0.1411, simple_loss=0.2148, pruned_loss=0.0337, over 4801.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03661, over 970845.20 frames.], batch size: 25, lr: 2.84e-04
2022-05-06 00:51:47,564 INFO [train.py:715] (5/8) Epoch 7, batch 32650, loss[loss=0.1279, simple_loss=0.2029, pruned_loss=0.02646, over 4887.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03717, over 972159.46 frames.], batch size: 16, lr: 2.84e-04
2022-05-06 00:52:27,384 INFO [train.py:715] (5/8) Epoch 7, batch 32700, loss[loss=0.1878, simple_loss=0.2479, pruned_loss=0.06389, over 4791.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03726, over 973126.28 frames.], batch size: 17, lr: 2.84e-04
2022-05-06 00:53:06,818 INFO [train.py:715] (5/8) Epoch 7, batch 32750, loss[loss=0.1741, simple_loss=0.2471, pruned_loss=0.05059, over 4871.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03698, over 973066.26 frames.], batch size: 20, lr: 2.84e-04
2022-05-06 00:53:47,304 INFO [train.py:715] (5/8) Epoch 7, batch 32800, loss[loss=0.1526, simple_loss=0.2255, pruned_loss=0.03989, over 4740.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03678, over 972550.62 frames.], batch size: 16, lr: 2.84e-04
2022-05-06 00:54:27,995 INFO [train.py:715] (5/8) Epoch 7, batch 32850, loss[loss=0.1422, simple_loss=0.2171, pruned_loss=0.03368, over 4808.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03646, over 972172.23 frames.], batch size: 25, lr: 2.84e-04
2022-05-06 00:55:08,133 INFO [train.py:715] (5/8) Epoch 7, batch 32900, loss[loss=0.1499, simple_loss=0.2238, pruned_loss=0.038, over 4899.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03669, over 971673.64 frames.], batch size: 22, lr: 2.84e-04
2022-05-06 00:55:48,469 INFO [train.py:715] (5/8) Epoch 7, batch 32950, loss[loss=0.1576, simple_loss=0.2288, pruned_loss=0.04324, over 4931.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03673, over 972871.61 frames.], batch size: 29, lr: 2.84e-04
2022-05-06 00:56:28,433 INFO [train.py:715] (5/8) Epoch 7, batch 33000, loss[loss=0.1387, simple_loss=0.2067, pruned_loss=0.03537, over 4791.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03631, over 973818.02 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 00:56:28,433 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 00:56:38,007 INFO [train.py:742] (5/8) Epoch 7, validation: loss=0.108, simple_loss=0.1927, pruned_loss=0.01164, over 914524.00 frames.
2022-05-06 00:57:17,536 INFO [train.py:715] (5/8) Epoch 7, batch 33050, loss[loss=0.1484, simple_loss=0.2141, pruned_loss=0.04136, over 4779.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03612, over 972954.93 frames.], batch size: 12, lr: 2.84e-04
2022-05-06 00:57:57,502 INFO [train.py:715] (5/8) Epoch 7, batch 33100, loss[loss=0.1035, simple_loss=0.1693, pruned_loss=0.01887, over 4823.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03598, over 973393.16 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 00:58:36,953 INFO [train.py:715] (5/8) Epoch 7, batch 33150, loss[loss=0.1348, simple_loss=0.2117, pruned_loss=0.02894, over 4910.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03669, over 971971.01 frames.], batch size: 18, lr: 2.84e-04
2022-05-06 00:59:16,723 INFO [train.py:715] (5/8) Epoch 7, batch 33200, loss[loss=0.1481, simple_loss=0.2159, pruned_loss=0.04016, over 4985.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03671, over 971542.36 frames.], batch size: 31, lr: 2.84e-04
2022-05-06 00:59:56,297 INFO [train.py:715] (5/8) Epoch 7, batch 33250, loss[loss=0.1371, simple_loss=0.215, pruned_loss=0.02958, over 4767.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03646, over 971867.79 frames.], batch size: 19, lr: 2.84e-04
2022-05-06 01:00:35,761 INFO [train.py:715] (5/8) Epoch 7, batch 33300, loss[loss=0.146, simple_loss=0.2118, pruned_loss=0.04012, over 4885.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03575, over 972086.32 frames.], batch size: 22, lr: 2.84e-04
2022-05-06 01:01:15,283 INFO [train.py:715] (5/8) Epoch 7, batch 33350, loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03526, over 4958.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.0362, over 971982.32 frames.], batch size: 29, lr: 2.84e-04
2022-05-06 01:01:55,579 INFO [train.py:715] (5/8) Epoch 7, batch 33400, loss[loss=0.1277, simple_loss=0.201, pruned_loss=0.02721, over 4983.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03636, over 972335.36 frames.], batch size: 28, lr: 2.84e-04
2022-05-06 01:02:35,667 INFO [train.py:715] (5/8) Epoch 7, batch 33450, loss[loss=0.1528, simple_loss=0.2244, pruned_loss=0.04056, over 4789.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.0363, over 971969.68 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 01:03:16,255 INFO [train.py:715] (5/8) Epoch 7, batch 33500, loss[loss=0.1132, simple_loss=0.1756, pruned_loss=0.02537, over 4758.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03695, over 971244.45 frames.], batch size: 12, lr: 2.84e-04
2022-05-06 01:03:56,833 INFO [train.py:715] (5/8) Epoch 7, batch 33550, loss[loss=0.1189, simple_loss=0.1888, pruned_loss=0.02454, over 4833.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03733, over 971027.45 frames.], batch size: 26, lr: 2.84e-04
2022-05-06 01:04:37,438 INFO [train.py:715] (5/8) Epoch 7, batch 33600, loss[loss=0.1351, simple_loss=0.2097, pruned_loss=0.0303, over 4829.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03704, over 969854.47 frames.], batch size: 30, lr: 2.84e-04
2022-05-06 01:05:17,936 INFO [train.py:715] (5/8) Epoch 7, batch 33650, loss[loss=0.1317, simple_loss=0.2082, pruned_loss=0.02763, over 4872.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03696, over 970869.09 frames.], batch size: 22, lr: 2.84e-04
2022-05-06 01:05:57,812 INFO [train.py:715] (5/8) Epoch 7, batch 33700, loss[loss=0.1128, simple_loss=0.1865, pruned_loss=0.01951, over 4787.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03676, over 970538.70 frames.], batch size: 18, lr: 2.84e-04
2022-05-06 01:06:37,962 INFO [train.py:715] (5/8) Epoch 7, batch 33750, loss[loss=0.1533, simple_loss=0.2321, pruned_loss=0.03721, over 4793.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.0369, over 970502.40 frames.], batch size: 21, lr: 2.84e-04
2022-05-06 01:07:17,444 INFO [train.py:715] (5/8) Epoch 7, batch 33800, loss[loss=0.1642, simple_loss=0.2307, pruned_loss=0.04881, over 4923.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03693, over 970156.39 frames.], batch size: 18, lr: 2.84e-04
2022-05-06 01:07:58,046 INFO [train.py:715] (5/8) Epoch 7, batch 33850, loss[loss=0.164, simple_loss=0.2209, pruned_loss=0.05353, over 4846.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03665, over 970150.10 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 01:08:37,724 INFO [train.py:715] (5/8) Epoch 7, batch 33900, loss[loss=0.1206, simple_loss=0.1963, pruned_loss=0.02243, over 4644.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03661, over 970169.89 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 01:09:17,827 INFO [train.py:715] (5/8) Epoch 7, batch 33950, loss[loss=0.1312, simple_loss=0.2138, pruned_loss=0.02433, over 4806.00 frames.], tot_loss[loss=0.1457, simple_loss=0.218, pruned_loss=0.03676, over 970971.33 frames.], batch size: 25, lr: 2.84e-04
2022-05-06 01:09:57,286 INFO [train.py:715] (5/8) Epoch 7, batch 34000, loss[loss=0.181, simple_loss=0.2537, pruned_loss=0.05413, over 4811.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2185, pruned_loss=0.0371, over 971942.54 frames.], batch size: 21, lr: 2.84e-04
2022-05-06 01:10:37,473 INFO [train.py:715] (5/8) Epoch 7, batch 34050, loss[loss=0.1847, simple_loss=0.2445, pruned_loss=0.06248, over 4746.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2187, pruned_loss=0.03725, over 972050.39 frames.], batch size: 16, lr: 2.84e-04
2022-05-06 01:11:17,477 INFO [train.py:715] (5/8) Epoch 7, batch 34100, loss[loss=0.1593, simple_loss=0.222, pruned_loss=0.04834, over 4805.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2189, pruned_loss=0.03738, over 970773.73 frames.], batch size: 14, lr: 2.83e-04
2022-05-06 01:11:56,983 INFO [train.py:715] (5/8) Epoch 7, batch 34150, loss[loss=0.1419, simple_loss=0.2105, pruned_loss=0.03662, over 4832.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03686, over 971709.29 frames.], batch size: 15, lr: 2.83e-04
2022-05-06 01:12:37,405 INFO [train.py:715] (5/8) Epoch 7, batch 34200, loss[loss=0.1781, simple_loss=0.2409, pruned_loss=0.05765, over 4815.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.03661, over 971956.54 frames.], batch size: 21, lr: 2.83e-04
2022-05-06 01:13:17,637 INFO [train.py:715] (5/8) Epoch 7, batch 34250, loss[loss=0.1107, simple_loss=0.1815, pruned_loss=0.01994, over 4829.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.03664, over 971755.56 frames.], batch size: 26, lr: 2.83e-04
2022-05-06 01:13:58,298 INFO [train.py:715] (5/8) Epoch 7, batch 34300, loss[loss=0.1814, simple_loss=0.2479, pruned_loss=0.0574, over 4855.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.03634, over 971800.17 frames.], batch size: 20, lr: 2.83e-04
2022-05-06 01:14:38,114 INFO [train.py:715] (5/8) Epoch 7, batch 34350, loss[loss=0.1806, simple_loss=0.2439, pruned_loss=0.05862, over 4808.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03634, over 973073.10 frames.], batch size: 21, lr: 2.83e-04
2022-05-06 01:15:18,246 INFO [train.py:715] (5/8) Epoch 7, batch 34400, loss[loss=0.1369, simple_loss=0.2073, pruned_loss=0.03329, over 4930.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03721, over 972393.84 frames.], batch size: 23, lr: 2.83e-04
2022-05-06 01:15:58,917 INFO [train.py:715] (5/8) Epoch 7, batch 34450, loss[loss=0.1557, simple_loss=0.225, pruned_loss=0.0432, over 4976.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03718, over 971884.70 frames.], batch size: 39, lr: 2.83e-04
2022-05-06 01:16:38,145 INFO [train.py:715] (5/8) Epoch 7, batch 34500, loss[loss=0.1267, simple_loss=0.2033, pruned_loss=0.02505, over 4801.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03761, over 971650.76 frames.], batch size: 14, lr: 2.83e-04
2022-05-06 01:17:18,208 INFO [train.py:715] (5/8) Epoch 7, batch 34550, loss[loss=0.1755, simple_loss=0.25, pruned_loss=0.05052, over 4778.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2193, pruned_loss=0.03798, over 972349.23 frames.], batch size: 17, lr: 2.83e-04
2022-05-06 01:17:58,848 INFO [train.py:715] (5/8) Epoch 7, batch 34600, loss[loss=0.1388, simple_loss=0.2156, pruned_loss=0.03102, over 4780.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03742, over 971732.41 frames.], batch size: 18, lr: 2.83e-04
2022-05-06 01:18:38,814 INFO [train.py:715] (5/8) Epoch 7, batch 34650, loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03693, over 4851.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.0371, over 972246.33 frames.], batch size: 13, lr: 2.83e-04
2022-05-06 01:19:19,028 INFO [train.py:715] (5/8) Epoch 7, batch 34700, loss[loss=0.1569, simple_loss=0.2366, pruned_loss=0.03859, over 4706.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03693, over 971508.94 frames.], batch size: 15, lr: 2.83e-04
2022-05-06 01:19:57,504 INFO [train.py:715] (5/8) Epoch 7, batch 34750, loss[loss=0.167, simple_loss=0.2358, pruned_loss=0.0491, over 4865.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2179, pruned_loss=0.03744, over 971415.33 frames.], batch size: 32, lr: 2.83e-04
2022-05-06 01:20:35,931 INFO [train.py:715] (5/8) Epoch 7, batch 34800, loss[loss=0.1507, simple_loss=0.215, pruned_loss=0.04323, over 4926.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2168, pruned_loss=0.03722, over 970959.86 frames.], batch size: 18, lr: 2.83e-04
2022-05-06 01:21:27,012 INFO [train.py:715] (5/8) Epoch 8, batch 0, loss[loss=0.1637, simple_loss=0.2282, pruned_loss=0.04961, over 4868.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2282, pruned_loss=0.04961, over 4868.00 frames.], batch size: 16, lr: 2.69e-04
2022-05-06 01:22:06,298 INFO [train.py:715] (5/8) Epoch 8, batch 50, loss[loss=0.1406, simple_loss=0.2052, pruned_loss=0.03801, over 4847.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2149, pruned_loss=0.03662, over 218770.87 frames.], batch size: 30, lr: 2.69e-04
2022-05-06 01:22:47,067 INFO [train.py:715] (5/8) Epoch 8, batch 100, loss[loss=0.1384, simple_loss=0.2142, pruned_loss=0.03127, over 4931.00 frames.], tot_loss[loss=0.1433, simple_loss=0.215, pruned_loss=0.03581, over 386299.50 frames.], batch size: 39, lr: 2.69e-04
2022-05-06 01:23:26,801 INFO [train.py:715] (5/8) Epoch 8, batch 150, loss[loss=0.1389, simple_loss=0.2079, pruned_loss=0.03494, over 4788.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2161, pruned_loss=0.0366, over 515955.03 frames.], batch size: 17, lr: 2.69e-04
2022-05-06 01:24:07,303 INFO [train.py:715] (5/8) Epoch 8, batch 200, loss[loss=0.1388, simple_loss=0.2083, pruned_loss=0.03469, over 4768.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2159, pruned_loss=0.03644, over 617957.91 frames.], batch size: 18, lr: 2.69e-04
2022-05-06 01:24:47,114 INFO [train.py:715] (5/8) Epoch 8, batch 250, loss[loss=0.1738, simple_loss=0.2383, pruned_loss=0.05464, over 4921.00 frames.], tot_loss[loss=0.144, simple_loss=0.2152, pruned_loss=0.03644, over 696929.70 frames.], batch size: 18, lr: 2.69e-04
2022-05-06 01:25:27,374 INFO [train.py:715] (5/8) Epoch 8, batch 300, loss[loss=0.1405, simple_loss=0.2057, pruned_loss=0.03764, over 4986.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.0362, over 758592.28 frames.], batch size: 15, lr: 2.69e-04
2022-05-06 01:26:07,156 INFO [train.py:715] (5/8) Epoch 8, batch 350, loss[loss=0.1492, simple_loss=0.2165, pruned_loss=0.04095, over 4821.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2169, pruned_loss=0.03707, over 805682.06 frames.], batch size: 13, lr: 2.69e-04
2022-05-06 01:26:46,034 INFO [train.py:715] (5/8) Epoch 8, batch 400, loss[loss=0.1512, simple_loss=0.2189, pruned_loss=0.04178, over 4955.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03752, over 842313.06 frames.], batch size: 35, lr: 2.69e-04
2022-05-06 01:27:26,634 INFO [train.py:715] (5/8) Epoch 8, batch 450, loss[loss=0.1604, simple_loss=0.2222, pruned_loss=0.04931, over 4946.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03713, over 870563.13 frames.], batch size: 29, lr: 2.69e-04
2022-05-06 01:28:06,606 INFO [train.py:715] (5/8) Epoch 8, batch 500, loss[loss=0.1522, simple_loss=0.2116, pruned_loss=0.04642, over 4777.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 893656.40 frames.], batch size: 18, lr: 2.69e-04
2022-05-06 01:28:47,242 INFO [train.py:715] (5/8) Epoch 8, batch 550, loss[loss=0.1717, simple_loss=0.2412, pruned_loss=0.05109, over 4918.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03755, over 911381.07 frames.], batch size: 29, lr: 2.69e-04
2022-05-06 01:29:26,912 INFO [train.py:715] (5/8) Epoch 8, batch 600, loss[loss=0.1572, simple_loss=0.2231, pruned_loss=0.04565, over 4986.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03718, over 924624.16 frames.], batch size: 28, lr: 2.69e-04
2022-05-06 01:30:07,130 INFO [train.py:715] (5/8) Epoch 8, batch 650, loss[loss=0.1633, simple_loss=0.2285, pruned_loss=0.04904, over 4833.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2175, pruned_loss=0.03654, over 935134.93 frames.], batch size: 26, lr: 2.68e-04
2022-05-06 01:30:47,386 INFO [train.py:715] (5/8) Epoch 8, batch 700, loss[loss=0.1342, simple_loss=0.2073, pruned_loss=0.03058, over 4824.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2164, pruned_loss=0.03615, over 943605.89 frames.], batch size: 13, lr: 2.68e-04
2022-05-06 01:31:27,081 INFO [train.py:715] (5/8) Epoch 8, batch 750, loss[loss=0.1357, simple_loss=0.2148, pruned_loss=0.02828, over 4942.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.0362, over 950443.67 frames.], batch size: 23, lr: 2.68e-04
2022-05-06 01:32:07,142 INFO [train.py:715] (5/8) Epoch 8, batch 800, loss[loss=0.1316, simple_loss=0.2099, pruned_loss=0.02665, over 4952.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03606, over 955226.56 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:32:47,135 INFO [train.py:715] (5/8) Epoch 8, batch 850, loss[loss=0.1417, simple_loss=0.2126, pruned_loss=0.03541, over 4985.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03579, over 959097.17 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:33:28,548 INFO [train.py:715] (5/8) Epoch 8, batch 900, loss[loss=0.1499, simple_loss=0.2235, pruned_loss=0.0381, over 4897.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2172, pruned_loss=0.0363, over 962400.20 frames.], batch size: 29, lr: 2.68e-04
2022-05-06 01:34:08,657 INFO [train.py:715] (5/8) Epoch 8, batch 950, loss[loss=0.1303, simple_loss=0.2035, pruned_loss=0.02855, over 4979.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 964760.77 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:34:49,699 INFO [train.py:715] (5/8) Epoch 8, batch 1000, loss[loss=0.1428, simple_loss=0.2229, pruned_loss=0.03134, over 4921.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03698, over 965654.95 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:35:30,786 INFO [train.py:715] (5/8) Epoch 8, batch 1050, loss[loss=0.1488, simple_loss=0.2188, pruned_loss=0.03944, over 4834.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03642, over 966763.48 frames.], batch size: 32, lr: 2.68e-04
2022-05-06 01:36:11,901 INFO [train.py:715] (5/8) Epoch 8, batch 1100, loss[loss=0.1606, simple_loss=0.24, pruned_loss=0.04065, over 4968.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03597, over 967206.63 frames.], batch size: 28, lr: 2.68e-04
2022-05-06 01:36:52,406 INFO [train.py:715] (5/8) Epoch 8, batch 1150, loss[loss=0.1597, simple_loss=0.234, pruned_loss=0.04272, over 4890.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03614, over 968965.37 frames.], batch size: 22, lr: 2.68e-04
2022-05-06 01:37:33,430 INFO [train.py:715] (5/8) Epoch 8, batch 1200, loss[loss=0.1359, simple_loss=0.2001, pruned_loss=0.03584, over 4836.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03583, over 969483.65 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:38:14,756 INFO [train.py:715] (5/8) Epoch 8, batch 1250, loss[loss=0.1417, simple_loss=0.2178, pruned_loss=0.03276, over 4979.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03586, over 969672.31 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:38:55,086 INFO [train.py:715] (5/8) Epoch 8, batch 1300, loss[loss=0.1273, simple_loss=0.1997, pruned_loss=0.02749, over 4957.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03531, over 970437.15 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:39:36,448 INFO [train.py:715] (5/8) Epoch 8, batch 1350, loss[loss=0.169, simple_loss=0.2474, pruned_loss=0.04531, over 4825.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03534, over 970784.87 frames.], batch size: 25, lr: 2.68e-04
2022-05-06 01:40:17,101 INFO [train.py:715] (5/8) Epoch 8, batch 1400, loss[loss=0.1482, simple_loss=0.2166, pruned_loss=0.03987, over 4829.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03555, over 971707.23 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:40:57,930 INFO [train.py:715] (5/8) Epoch 8, batch 1450, loss[loss=0.1606, simple_loss=0.2345, pruned_loss=0.04337, over 4885.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03618, over 972001.58 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:41:37,777 INFO [train.py:715] (5/8) Epoch 8, batch 1500, loss[loss=0.1275, simple_loss=0.2076, pruned_loss=0.02369, over 4803.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03613, over 971601.24 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:42:20,410 INFO [train.py:715] (5/8) Epoch 8, batch 1550, loss[loss=0.1286, simple_loss=0.2157, pruned_loss=0.02076, over 4894.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03598, over 971533.71 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:43:00,534 INFO [train.py:715] (5/8) Epoch 8, batch 1600, loss[loss=0.1417, simple_loss=0.2267, pruned_loss=0.02837, over 4805.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03632, over 972572.57 frames.], batch size: 25, lr: 2.68e-04
2022-05-06 01:43:39,973 INFO [train.py:715] (5/8) Epoch 8, batch 1650, loss[loss=0.1435, simple_loss=0.2264, pruned_loss=0.03032, over 4783.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03669, over 972409.71 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:44:20,194 INFO [train.py:715] (5/8) Epoch 8, batch 1700, loss[loss=0.1414, simple_loss=0.2155, pruned_loss=0.03371, over 4790.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.03615, over 972057.68 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:44:59,607 INFO [train.py:715] (5/8) Epoch 8, batch 1750, loss[loss=0.1356, simple_loss=0.2085, pruned_loss=0.03139, over 4821.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03592, over 972275.30 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:45:39,056 INFO [train.py:715] (5/8) Epoch 8, batch 1800, loss[loss=0.1456, simple_loss=0.223, pruned_loss=0.03417, over 4750.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03588, over 971822.05 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:46:18,113 INFO [train.py:715] (5/8) Epoch 8, batch 1850, loss[loss=0.1274, simple_loss=0.1982, pruned_loss=0.02837, over 4893.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03615, over 972113.88 frames.], batch size: 22, lr: 2.68e-04
2022-05-06 01:46:57,511 INFO [train.py:715] (5/8) Epoch 8, batch 1900, loss[loss=0.1376, simple_loss=0.2093, pruned_loss=0.03299, over 4939.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2152, pruned_loss=0.03578, over 972411.49 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:47:37,010 INFO [train.py:715] (5/8) Epoch 8, batch 1950, loss[loss=0.1413, simple_loss=0.2248, pruned_loss=0.02889, over 4980.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2147, pruned_loss=0.03574, over 972395.69 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:48:16,130 INFO [train.py:715] (5/8) Epoch 8, batch 2000, loss[loss=0.1658, simple_loss=0.2388, pruned_loss=0.04641, over 4777.00 frames.], tot_loss[loss=0.144, simple_loss=0.2157, pruned_loss=0.03614, over 971473.16 frames.], batch size: 14, lr: 2.68e-04
2022-05-06 01:48:56,160 INFO [train.py:715] (5/8) Epoch 8, batch 2050, loss[loss=0.142, simple_loss=0.2031, pruned_loss=0.0404, over 4870.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03648, over 971340.40 frames.], batch size: 32, lr: 2.68e-04
2022-05-06 01:49:35,102 INFO [train.py:715] (5/8) Epoch 8, batch 2100, loss[loss=0.1418, simple_loss=0.2135, pruned_loss=0.03509, over 4965.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2153, pruned_loss=0.03643, over 970958.19 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:50:14,046 INFO [train.py:715] (5/8) Epoch 8, batch 2150, loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02894, over 4805.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2153, pruned_loss=0.03577, over 971118.84 frames.], batch size: 12, lr: 2.68e-04
2022-05-06 01:50:53,037 INFO [train.py:715] (5/8) Epoch 8, batch 2200, loss[loss=0.1804, simple_loss=0.2477, pruned_loss=0.05657, over 4970.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2151, pruned_loss=0.03584, over 972659.41 frames.], batch size: 25, lr: 2.68e-04
2022-05-06 01:51:32,659 INFO [train.py:715] (5/8) Epoch 8, batch 2250, loss[loss=0.1435, simple_loss=0.2179, pruned_loss=0.0346, over 4832.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2143, pruned_loss=0.03543, over 973147.46 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:52:12,077 INFO [train.py:715] (5/8) Epoch 8, batch 2300, loss[loss=0.1506, simple_loss=0.2223, pruned_loss=0.03947, over 4780.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2138, pruned_loss=0.03547, over 972339.70 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:52:50,789 INFO [train.py:715] (5/8) Epoch 8, batch 2350, loss[loss=0.1361, simple_loss=0.2089, pruned_loss=0.03166, over 4929.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2151, pruned_loss=0.03586, over 972179.95 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:53:30,854 INFO [train.py:715] (5/8) Epoch 8, batch 2400, loss[loss=0.1416, simple_loss=0.2133, pruned_loss=0.0349, over 4904.00 frames.], tot_loss[loss=0.143, simple_loss=0.2146, pruned_loss=0.03567, over 971675.82 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:54:10,336 INFO [train.py:715] (5/8) Epoch 8, batch 2450, loss[loss=0.154, simple_loss=0.2221, pruned_loss=0.04291, over 4987.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2157, pruned_loss=0.03627, over 971938.24 frames.], batch size: 31, lr: 2.68e-04
2022-05-06 01:54:49,891 INFO [train.py:715] (5/8) Epoch 8, batch 2500, loss[loss=0.1469, simple_loss=0.2318, pruned_loss=0.03097, over 4641.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03603, over 971866.94 frames.], batch size: 13, lr: 2.68e-04
2022-05-06 01:55:28,676 INFO [train.py:715] (5/8) Epoch 8, batch 2550, loss[loss=0.1447, simple_loss=0.2197, pruned_loss=0.03485, over 4900.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03617, over 971788.90 frames.], batch size: 17, lr: 2.68e-04
2022-05-06 01:56:08,306 INFO [train.py:715] (5/8) Epoch 8, batch 2600, loss[loss=0.1514, simple_loss=0.2168, pruned_loss=0.04296, over 4857.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03626, over 972990.74 frames.], batch size: 32, lr: 2.68e-04
2022-05-06 01:56:47,553 INFO [train.py:715] (5/8) Epoch 8, batch 2650, loss[loss=0.132, simple_loss=0.2043, pruned_loss=0.02985, over 4946.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03562, over 972593.58 frames.], batch size: 23, lr: 2.68e-04
2022-05-06 01:57:27,028 INFO [train.py:715] (5/8) Epoch 8, batch 2700, loss[loss=0.147, simple_loss=0.2153, pruned_loss=0.03934, over 4980.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03645, over 972115.49 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:58:06,371 INFO [train.py:715] (5/8) Epoch 8, batch 2750, loss[loss=0.142, simple_loss=0.2121, pruned_loss=0.03599, over 4826.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03634, over 972238.30 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 01:58:45,748 INFO [train.py:715] (5/8) Epoch 8, batch 2800, loss[loss=0.1291, simple_loss=0.203, pruned_loss=0.02757, over 4847.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03637, over 972001.65 frames.], batch size: 12, lr: 2.67e-04
2022-05-06 01:59:24,993 INFO [train.py:715] (5/8) Epoch 8, batch 2850, loss[loss=0.1458, simple_loss=0.2214, pruned_loss=0.03506, over 4860.00 frames.], tot_loss[loss=0.1444, simple_loss=0.217, pruned_loss=0.03594, over 971641.60 frames.], batch size: 20, lr: 2.67e-04
2022-05-06 02:00:03,842 INFO [train.py:715] (5/8) Epoch 8, batch 2900, loss[loss=0.1349, simple_loss=0.2208, pruned_loss=0.02448, over 4924.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03557, over 971908.42 frames.], batch size: 23, lr: 2.67e-04
2022-05-06 02:00:43,810 INFO [train.py:715] (5/8) Epoch 8, batch 2950, loss[loss=0.1212, simple_loss=0.196, pruned_loss=0.02317, over 4936.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03574, over 972561.17 frames.], batch size: 23, lr: 2.67e-04
2022-05-06 02:01:22,467 INFO [train.py:715] (5/8) Epoch 8, batch 3000, loss[loss=0.1687, simple_loss=0.2308, pruned_loss=0.05331, over 4775.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03535, over 972447.08 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:01:22,468 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 02:01:32,131 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
2022-05-06 02:02:11,364 INFO [train.py:715] (5/8) Epoch 8, batch 3050, loss[loss=0.1293, simple_loss=0.1994, pruned_loss=0.02958, over 4817.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03576, over 971878.17 frames.], batch size: 21, lr: 2.67e-04
2022-05-06 02:02:50,367 INFO [train.py:715] (5/8) Epoch 8, batch 3100, loss[loss=0.1734, simple_loss=0.2339, pruned_loss=0.05642, over 4852.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03579, over 972240.17 frames.], batch size: 30, lr: 2.67e-04
2022-05-06 02:03:29,329 INFO [train.py:715] (5/8) Epoch 8, batch 3150, loss[loss=0.1332, simple_loss=0.2084, pruned_loss=0.02894, over 4822.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.0361, over 972274.99 frames.], batch size: 26, lr: 2.67e-04
2022-05-06 02:04:09,017 INFO [train.py:715] (5/8) Epoch 8, batch 3200, loss[loss=0.1233, simple_loss=0.2033, pruned_loss=0.02167, over 4916.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03601, over 972683.27 frames.], batch size: 23, lr: 2.67e-04
2022-05-06 02:04:48,448 INFO [train.py:715] (5/8) Epoch 8, batch 3250, loss[loss=0.1492, simple_loss=0.2181, pruned_loss=0.04015, over 4923.00 frames.], tot_loss[loss=0.1448, simple_loss=0.217, pruned_loss=0.03627, over 972911.19 frames.], batch size: 23, lr: 2.67e-04
2022-05-06 02:05:28,483 INFO [train.py:715] (5/8) Epoch 8, batch 3300, loss[loss=0.1522, simple_loss=0.2237, pruned_loss=0.04032, over 4813.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03605, over 973020.46 frames.], batch size: 25, lr: 2.67e-04
2022-05-06 02:06:08,838 INFO [train.py:715] (5/8) Epoch 8, batch 3350, loss[loss=0.1495, simple_loss=0.2143, pruned_loss=0.04233, over 4916.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03649, over 972099.45 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:06:49,938 INFO [train.py:715] (5/8) Epoch 8, batch 3400, loss[loss=0.1584, simple_loss=0.2228, pruned_loss=0.04702, over 4902.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03598, over 972604.14 frames.], batch size: 29, lr: 2.67e-04
2022-05-06 02:07:30,800 INFO [train.py:715] (5/8) Epoch 8, batch 3450, loss[loss=0.1538, simple_loss=0.2304, pruned_loss=0.03859, over 4753.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03667, over 971621.49 frames.], batch size: 19, lr: 2.67e-04
2022-05-06 02:08:11,011 INFO [train.py:715] (5/8) Epoch 8, batch 3500, loss[loss=0.1357, simple_loss=0.2026, pruned_loss=0.03445, over 4910.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03645, over 971958.13 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:08:52,347 INFO [train.py:715] (5/8) Epoch 8, batch 3550, loss[loss=0.1488, simple_loss=0.2296, pruned_loss=0.03395, over 4827.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03684, over 972566.82 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:09:33,202 INFO [train.py:715] (5/8) Epoch 8, batch 3600, loss[loss=0.137, simple_loss=0.2082, pruned_loss=0.03293, over 4898.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03644, over 970911.95 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:10:13,455 INFO [train.py:715] (5/8) Epoch 8, batch 3650, loss[loss=0.1512, simple_loss=0.2293, pruned_loss=0.03652, over 4915.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03637, over 971967.86 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:10:53,935 INFO [train.py:715] (5/8) Epoch 8, batch 3700, loss[loss=0.1621, simple_loss=0.2308, pruned_loss=0.04671, over 4981.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2171, pruned_loss=0.03629, over 972002.21 frames.], batch size: 25, lr: 2.67e-04
2022-05-06 02:11:34,285 INFO [train.py:715] (5/8) Epoch 8, batch 3750, loss[loss=0.12, simple_loss=0.1917, pruned_loss=0.02414, over 4839.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03571, over 972823.20 frames.], batch size: 30, lr: 2.67e-04
2022-05-06 02:12:13,641 INFO [train.py:715] (5/8) Epoch 8, batch 3800, loss[loss=0.124, simple_loss=0.2103, pruned_loss=0.01882, over 4756.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03575, over 972530.38 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:12:54,033 INFO [train.py:715] (5/8) Epoch 8, batch 3850, loss[loss=0.1412, simple_loss=0.2015, pruned_loss=0.04048, over 4752.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03564, over 972652.71 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:13:34,221 INFO [train.py:715] (5/8) Epoch 8, batch 3900, loss[loss=0.1212, simple_loss=0.1918, pruned_loss=0.02531, over 4914.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03625, over 972508.34 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:14:14,990 INFO [train.py:715] (5/8) Epoch 8, batch 3950, loss[loss=0.13, simple_loss=0.2093, pruned_loss=0.02539, over 4881.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03652, over 972085.76 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:14:54,902 INFO [train.py:715] (5/8) Epoch 8, batch 4000, loss[loss=0.165, simple_loss=0.2402, pruned_loss=0.04487, over 4970.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03641, over 972212.13 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:15:35,359 INFO [train.py:715] (5/8) Epoch 8, batch 4050, loss[loss=0.1493, simple_loss=0.2188, pruned_loss=0.03997, over 4810.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03623, over 972540.37 frames.], batch size: 26, lr: 2.67e-04
2022-05-06 02:16:16,176 INFO [train.py:715] (5/8) Epoch 8, batch 4100, loss[loss=0.1197, simple_loss=0.2029, pruned_loss=0.01829, over 4926.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03578, over 972601.45 frames.], batch size: 29, lr: 2.67e-04
2022-05-06 02:16:55,925 INFO [train.py:715] (5/8) Epoch 8, batch 4150, loss[loss=0.1431, simple_loss=0.2139, pruned_loss=0.03614, over 4821.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03596, over 972314.37 frames.], batch size: 21, lr: 2.67e-04
2022-05-06 02:17:35,659 INFO [train.py:715] (5/8) Epoch 8, batch 4200, loss[loss=0.1445, simple_loss=0.214, pruned_loss=0.03756, over 4765.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.03566, over 972053.26 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:18:15,232 INFO [train.py:715] (5/8) Epoch 8, batch 4250, loss[loss=0.1579, simple_loss=0.2333, pruned_loss=0.04126, over 4708.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03612, over 971343.80 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:18:54,986 INFO [train.py:715] (5/8) Epoch 8, batch 4300, loss[loss=0.1472, simple_loss=0.2156, pruned_loss=0.03943, over 4902.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03664, over 971082.77 frames.], batch size: 19, lr: 2.67e-04
2022-05-06 02:19:34,151 INFO [train.py:715] (5/8) Epoch 8, batch 4350, loss[loss=0.1627, simple_loss=0.2304, pruned_loss=0.0475, over 4964.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03612, over 970622.82 frames.], batch size: 35, lr: 2.67e-04
2022-05-06 02:20:13,543 INFO [train.py:715] (5/8) Epoch 8, batch 4400, loss[loss=0.1494, simple_loss=0.2232, pruned_loss=0.03781, over 4961.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03638, over 970911.99 frames.], batch size: 24, lr: 2.67e-04
2022-05-06 02:20:53,462 INFO [train.py:715] (5/8) Epoch 8, batch 4450, loss[loss=0.1363, simple_loss=0.2076, pruned_loss=0.03249, over 4990.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03594, over 972285.11 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:21:33,237 INFO [train.py:715] (5/8) Epoch 8, batch 4500, loss[loss=0.112, simple_loss=0.1771, pruned_loss=0.02347, over 4981.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03638, over 972285.73 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:22:12,201 INFO [train.py:715] (5/8) Epoch 8, batch 4550, loss[loss=0.1348, simple_loss=0.2133, pruned_loss=0.02812, over 4766.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03671, over 972239.81 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:22:52,184 INFO [train.py:715] (5/8) Epoch 8, batch 4600, loss[loss=0.1424, simple_loss=0.2186, pruned_loss=0.03311, over 4928.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03611, over 972176.36 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:23:31,719 INFO [train.py:715] (5/8) Epoch 8, batch 4650, loss[loss=0.1544, simple_loss=0.2131, pruned_loss=0.04787, over 4915.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03663, over 971079.91 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:24:11,300 INFO [train.py:715] (5/8) Epoch 8, batch 4700, loss[loss=0.1687, simple_loss=0.2266, pruned_loss=0.05537, over 4840.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03782, over 971314.68 frames.], batch size: 30, lr: 2.67e-04
2022-05-06 02:24:50,830 INFO [train.py:715] (5/8) Epoch 8, batch 4750, loss[loss=0.1356, simple_loss=0.2115, pruned_loss=0.02988, over 4864.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2172, pruned_loss=0.03758, over 971267.29 frames.], batch size: 20, lr: 2.67e-04
2022-05-06 02:25:30,486 INFO [train.py:715] (5/8) Epoch 8, batch 4800, loss[loss=0.1398, simple_loss=0.2145, pruned_loss=0.03253, over 4989.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2168, pruned_loss=0.03725, over 971999.46 frames.], batch size: 24, lr: 2.67e-04
2022-05-06 02:26:10,387 INFO [train.py:715] (5/8) Epoch 8, batch 4850, loss[loss=0.1313, simple_loss=0.1921, pruned_loss=0.03523, over 4895.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03648, over 971788.84 frames.], batch size: 22, lr: 2.66e-04
2022-05-06 02:26:49,515 INFO [train.py:715] (5/8) Epoch 8, batch 4900, loss[loss=0.1763, simple_loss=0.2516, pruned_loss=0.05049, over 4956.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03587, over 972205.23 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:27:29,275 INFO [train.py:715] (5/8) Epoch 8, batch 4950, loss[loss=0.1169, simple_loss=0.1834, pruned_loss=0.02521, over 4756.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03649, over 971351.41 frames.], batch size: 12, lr: 2.66e-04
2022-05-06 02:28:08,942 INFO [train.py:715] (5/8) Epoch 8, batch 5000, loss[loss=0.1214, simple_loss=0.19, pruned_loss=0.02633, over 4894.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03658, over 971947.01 frames.], batch size: 22, lr: 2.66e-04
2022-05-06 02:28:47,811 INFO [train.py:715] (5/8) Epoch 8, batch 5050, loss[loss=0.1526, simple_loss=0.2197, pruned_loss=0.04271, over 4978.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03674, over 973036.66 frames.], batch size: 31, lr: 2.66e-04
2022-05-06 02:29:26,960 INFO [train.py:715] (5/8) Epoch 8, batch 5100, loss[loss=0.1737, simple_loss=0.2382, pruned_loss=0.05464, over 4988.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03666, over 973323.16 frames.], batch size: 39, lr: 2.66e-04
2022-05-06 02:30:06,423 INFO [train.py:715] (5/8) Epoch 8, batch 5150, loss[loss=0.1243, simple_loss=0.1985, pruned_loss=0.02505, over 4752.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03611, over 973261.23 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:30:45,327 INFO [train.py:715] (5/8) Epoch 8, batch 5200, loss[loss=0.1257, simple_loss=0.2022, pruned_loss=0.0246, over 4790.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03605, over 972576.17 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:31:24,025 INFO [train.py:715] (5/8) Epoch 8, batch 5250, loss[loss=0.1698, simple_loss=0.2459, pruned_loss=0.04681, over 4982.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2178, pruned_loss=0.03642, over 972313.35 frames.], batch size: 31, lr: 2.66e-04
2022-05-06 02:32:04,133 INFO [train.py:715] (5/8) Epoch 8, batch 5300, loss[loss=0.142, simple_loss=0.2155, pruned_loss=0.0342, over 4920.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03645, over 972932.74 frames.], batch size: 29, lr: 2.66e-04
2022-05-06 02:32:43,756 INFO [train.py:715] (5/8) Epoch 8, batch 5350, loss[loss=0.1328, simple_loss=0.2029, pruned_loss=0.03139, over 4985.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03643, over 973706.30 frames.], batch size: 35, lr: 2.66e-04
2022-05-06 02:33:23,693 INFO [train.py:715] (5/8) Epoch 8, batch 5400, loss[loss=0.1661, simple_loss=0.2367, pruned_loss=0.04779, over 4893.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03654, over 973704.31 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:34:04,179 INFO [train.py:715] (5/8) Epoch 8, batch 5450, loss[loss=0.1261, simple_loss=0.2049, pruned_loss=0.02365, over 4829.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03615, over 973239.26 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:34:44,674 INFO [train.py:715] (5/8) Epoch 8, batch 5500, loss[loss=0.1373, simple_loss=0.2072, pruned_loss=0.03372, over 4847.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03591, over 973215.03 frames.], batch size: 13, lr: 2.66e-04
2022-05-06 02:35:24,969 INFO [train.py:715] (5/8) Epoch 8, batch 5550, loss[loss=0.1386, simple_loss=0.2048, pruned_loss=0.03622, over 4828.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03627, over 971467.92 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:36:04,809 INFO [train.py:715] (5/8) Epoch 8, batch 5600, loss[loss=0.1443, simple_loss=0.2091, pruned_loss=0.03975, over 4835.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03678, over 971708.31 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:36:44,875 INFO [train.py:715] (5/8) Epoch 8, batch 5650, loss[loss=0.1535, simple_loss=0.2217, pruned_loss=0.04271, over 4811.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2174, pruned_loss=0.03645, over 972435.36 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:37:24,000 INFO [train.py:715] (5/8) Epoch 8, batch 5700, loss[loss=0.1261, simple_loss=0.2011, pruned_loss=0.02553, over 4762.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03629, over 972144.24 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:38:03,513 INFO [train.py:715] (5/8) Epoch 8, batch 5750, loss[loss=0.1286, simple_loss=0.1989, pruned_loss=0.02917, over 4890.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03619, over 971429.03 frames.], batch size: 17, lr: 2.66e-04
2022-05-06 02:38:42,300 INFO [train.py:715] (5/8) Epoch 8, batch 5800, loss[loss=0.1638, simple_loss=0.2326, pruned_loss=0.04743, over 4840.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2178, pruned_loss=0.03674, over 971624.72 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:39:21,797 INFO [train.py:715] (5/8) Epoch 8, batch 5850, loss[loss=0.1575, simple_loss=0.23, pruned_loss=0.04248, over 4686.00 frames.], tot_loss[loss=0.1451, simple_loss=0.217, pruned_loss=0.03663, over 972245.79 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:40:00,569 INFO [train.py:715] (5/8) Epoch 8, batch 5900, loss[loss=0.1402, simple_loss=0.2148, pruned_loss=0.03278, over 4956.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03588, over 972007.52 frames.], batch size: 21, lr: 2.66e-04
2022-05-06 02:40:40,147 INFO [train.py:715] (5/8) Epoch 8, batch 5950, loss[loss=0.1459, simple_loss=0.2162, pruned_loss=0.03784, over 4843.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03626, over 972217.85 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:41:20,031 INFO [train.py:715] (5/8) Epoch 8, batch 6000, loss[loss=0.1359, simple_loss=0.212, pruned_loss=0.02987, over 4924.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.0358, over 972195.35 frames.], batch size: 39, lr: 2.66e-04
2022-05-06 02:41:20,032 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 02:41:29,607 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1921, pruned_loss=0.01146, over 914524.00 frames.
2022-05-06 02:42:09,066 INFO [train.py:715] (5/8) Epoch 8, batch 6050, loss[loss=0.1342, simple_loss=0.2055, pruned_loss=0.03145, over 4747.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03606, over 972467.57 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:42:48,767 INFO [train.py:715] (5/8) Epoch 8, batch 6100, loss[loss=0.1246, simple_loss=0.2001, pruned_loss=0.02452, over 4922.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03569, over 972637.09 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:43:28,430 INFO [train.py:715] (5/8) Epoch 8, batch 6150, loss[loss=0.1672, simple_loss=0.2401, pruned_loss=0.0472, over 4890.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2172, pruned_loss=0.03604, over 972502.19 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:44:08,981 INFO [train.py:715] (5/8) Epoch 8, batch 6200, loss[loss=0.1461, simple_loss=0.2091, pruned_loss=0.04155, over 4938.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2174, pruned_loss=0.03608, over 972525.42 frames.], batch size: 21, lr: 2.66e-04
2022-05-06 02:44:49,470 INFO [train.py:715] (5/8) Epoch 8, batch 6250, loss[loss=0.1328, simple_loss=0.2021, pruned_loss=0.03182, over 4812.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2171, pruned_loss=0.03633, over 972670.01 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:45:29,139 INFO [train.py:715] (5/8) Epoch 8, batch 6300, loss[loss=0.1376, simple_loss=0.2065, pruned_loss=0.03442, over 4892.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.0358, over 972009.06 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:46:08,060 INFO [train.py:715] (5/8) Epoch 8, batch 6350, loss[loss=0.1373, simple_loss=0.2057, pruned_loss=0.03441, over 4809.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03599, over 971766.87 frames.], batch size: 14, lr: 2.66e-04
2022-05-06 02:46:47,828 INFO [train.py:715] (5/8) Epoch 8, batch 6400, loss[loss=0.1413, simple_loss=0.2044, pruned_loss=0.03907, over 4874.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.0358, over 972247.12 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:47:27,065 INFO [train.py:715] (5/8) Epoch 8, batch 6450, loss[loss=0.1256, simple_loss=0.2016, pruned_loss=0.02478, over 4799.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03606, over 972296.75 frames.], batch size: 21, lr: 2.66e-04
2022-05-06 02:48:06,516 INFO [train.py:715] (5/8) Epoch 8, batch 6500, loss[loss=0.1596, simple_loss=0.2344, pruned_loss=0.04241, over 4842.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03562, over 972250.77 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:48:45,638 INFO [train.py:715] (5/8) Epoch 8, batch 6550, loss[loss=0.1614, simple_loss=0.2165, pruned_loss=0.05312, over 4991.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03617, over 972995.11 frames.], batch size: 14, lr: 2.66e-04
2022-05-06 02:49:25,321 INFO [train.py:715] (5/8) Epoch 8, batch 6600, loss[loss=0.1324, simple_loss=0.1952, pruned_loss=0.03484, over 4859.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03586, over 973984.39 frames.], batch size: 32, lr: 2.66e-04
2022-05-06 02:50:04,619 INFO [train.py:715] (5/8) Epoch 8, batch 6650, loss[loss=0.1486, simple_loss=0.2328, pruned_loss=0.03216, over 4960.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.0356, over 974167.11 frames.], batch size: 21, lr: 2.66e-04
2022-05-06 02:50:43,402 INFO [train.py:715] (5/8) Epoch 8, batch 6700, loss[loss=0.1618, simple_loss=0.2371, pruned_loss=0.04321, over 4981.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03579, over 973699.63 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:51:23,631 INFO [train.py:715] (5/8) Epoch 8, batch 6750, loss[loss=0.1513, simple_loss=0.2302, pruned_loss=0.03624, over 4921.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03594, over 972896.97 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:52:03,055 INFO [train.py:715] (5/8) Epoch 8, batch 6800, loss[loss=0.1537, simple_loss=0.2296, pruned_loss=0.03892, over 4875.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03653, over 973271.74 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:52:42,028 INFO [train.py:715] (5/8) Epoch 8, batch 6850, loss[loss=0.1593, simple_loss=0.2266, pruned_loss=0.04595, over 4764.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03577, over 972737.73 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:53:21,945 INFO [train.py:715] (5/8) Epoch 8, batch 6900, loss[loss=0.1315, simple_loss=0.2089, pruned_loss=0.02702, over 4754.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.0353, over 972568.49 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:54:02,355 INFO [train.py:715] (5/8) Epoch 8, batch 6950, loss[loss=0.1574, simple_loss=0.2258, pruned_loss=0.04451, over 4778.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03549, over 972294.01 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:54:42,173 INFO [train.py:715] (5/8) Epoch 8, batch 7000, loss[loss=0.1353, simple_loss=0.1956, pruned_loss=0.0375, over 4960.00 frames.], tot_loss[loss=0.1431, simple_loss=0.215, pruned_loss=0.0356, over 972270.61 frames.], batch size: 35, lr: 2.65e-04
2022-05-06 02:55:21,781 INFO [train.py:715] (5/8) Epoch 8, batch 7050, loss[loss=0.1232, simple_loss=0.1862, pruned_loss=0.03009, over 4876.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2144, pruned_loss=0.03543, over 972412.83 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 02:56:01,471 INFO [train.py:715] (5/8) Epoch 8, batch 7100, loss[loss=0.1529, simple_loss=0.2309, pruned_loss=0.03752, over 4932.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2139, pruned_loss=0.03528, over 972176.38 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 02:56:41,141 INFO [train.py:715] (5/8) Epoch 8, batch 7150, loss[loss=0.1152, simple_loss=0.1877, pruned_loss=0.02133, over 4789.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.03503, over 971011.09 frames.], batch size: 12, lr: 2.65e-04
2022-05-06 02:57:20,443 INFO [train.py:715] (5/8) Epoch 8, batch 7200, loss[loss=0.173, simple_loss=0.2489, pruned_loss=0.04852, over 4980.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2142, pruned_loss=0.03539, over 970797.65 frames.], batch size: 25, lr: 2.65e-04
2022-05-06 02:57:59,448 INFO [train.py:715] (5/8) Epoch 8, batch 7250, loss[loss=0.1739, simple_loss=0.2478, pruned_loss=0.05, over 4880.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03544, over 970652.83 frames.], batch size: 22, lr: 2.65e-04
2022-05-06 02:58:39,554 INFO [train.py:715] (5/8) Epoch 8, batch 7300, loss[loss=0.1355, simple_loss=0.2015, pruned_loss=0.03469, over 4701.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03576, over 971303.33 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 02:59:18,929 INFO [train.py:715] (5/8) Epoch 8, batch 7350, loss[loss=0.1461, simple_loss=0.2148, pruned_loss=0.03874, over 4904.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03591, over 972349.82 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 02:59:58,519 INFO [train.py:715] (5/8) Epoch 8, batch 7400, loss[loss=0.1463, simple_loss=0.2121, pruned_loss=0.04031, over 4848.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03663, over 972576.21 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:00:38,453 INFO [train.py:715] (5/8) Epoch 8, batch 7450, loss[loss=0.2032, simple_loss=0.2707, pruned_loss=0.06782, over 4782.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.0363, over 972618.59 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:01:18,182 INFO [train.py:715] (5/8) Epoch 8, batch 7500, loss[loss=0.1656, simple_loss=0.2469, pruned_loss=0.04214, over 4795.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03626, over 972724.89 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:01:57,872 INFO [train.py:715] (5/8) Epoch 8, batch 7550, loss[loss=0.1277, simple_loss=0.2051, pruned_loss=0.02513, over 4824.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03662, over 972311.30 frames.], batch size: 13, lr: 2.65e-04
2022-05-06 03:02:37,819 INFO [train.py:715] (5/8) Epoch 8, batch 7600, loss[loss=0.1655, simple_loss=0.2277, pruned_loss=0.05159, over 4971.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03635, over 972537.90 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:03:17,987 INFO [train.py:715] (5/8) Epoch 8, batch 7650, loss[loss=0.1554, simple_loss=0.2307, pruned_loss=0.04002, over 4778.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03591, over 972703.94 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:03:57,438 INFO [train.py:715] (5/8) Epoch 8, batch 7700, loss[loss=0.158, simple_loss=0.2286, pruned_loss=0.04367, over 4979.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03634, over 972820.52 frames.], batch size: 14, lr: 2.65e-04
2022-05-06 03:04:36,610 INFO [train.py:715] (5/8) Epoch 8, batch 7750, loss[loss=0.1701, simple_loss=0.2329, pruned_loss=0.05366, over 4826.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2174, pruned_loss=0.03663, over 972281.55 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:05:16,798 INFO [train.py:715] (5/8) Epoch 8, batch 7800, loss[loss=0.1326, simple_loss=0.212, pruned_loss=0.02654, over 4942.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2184, pruned_loss=0.03698, over 972033.16 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 03:05:56,865 INFO [train.py:715] (5/8) Epoch 8, batch 7850, loss[loss=0.1427, simple_loss=0.2121, pruned_loss=0.03667, over 4835.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03624, over 970872.10 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:06:35,513 INFO [train.py:715] (5/8) Epoch 8, batch 7900, loss[loss=0.1411, simple_loss=0.2228, pruned_loss=0.0297, over 4915.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2156, pruned_loss=0.03612, over 971044.37 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:07:15,005 INFO [train.py:715] (5/8) Epoch 8, batch 7950, loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02841, over 4834.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03621, over 971404.75 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:07:54,690 INFO [train.py:715] (5/8) Epoch 8, batch 8000, loss[loss=0.1467, simple_loss=0.217, pruned_loss=0.0382, over 4785.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.0365, over 972322.97 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:08:33,646 INFO [train.py:715] (5/8) Epoch 8, batch 8050, loss[loss=0.1305, simple_loss=0.2098, pruned_loss=0.02556, over 4765.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2168, pruned_loss=0.03615, over 972010.86 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:09:12,022 INFO [train.py:715] (5/8) Epoch 8, batch 8100, loss[loss=0.1609, simple_loss=0.2316, pruned_loss=0.0451, over 4792.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2174, pruned_loss=0.03618, over 971988.12 frames.], batch size: 24, lr: 2.65e-04
2022-05-06 03:09:51,246 INFO [train.py:715] (5/8) Epoch 8, batch 8150, loss[loss=0.1453, simple_loss=0.2231, pruned_loss=0.03377, over 4902.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03536, over 972804.03 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:10:31,280 INFO [train.py:715] (5/8) Epoch 8, batch 8200, loss[loss=0.134, simple_loss=0.2013, pruned_loss=0.03335, over 4880.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.03564, over 972627.85 frames.], batch size: 22, lr: 2.65e-04
2022-05-06 03:11:09,920 INFO [train.py:715] (5/8) Epoch 8, batch 8250, loss[loss=0.1508, simple_loss=0.2322, pruned_loss=0.03472, over 4912.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03596, over 972499.01 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:11:48,871 INFO [train.py:715] (5/8) Epoch 8, batch 8300, loss[loss=0.1524, simple_loss=0.2191, pruned_loss=0.04282, over 4928.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03525, over 972905.55 frames.], batch size: 39, lr: 2.65e-04
2022-05-06 03:12:28,297 INFO [train.py:715] (5/8) Epoch 8, batch 8350, loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03814, over 4790.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03565, over 973066.22 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:13:07,310 INFO [train.py:715] (5/8) Epoch 8, batch 8400, loss[loss=0.1603, simple_loss=0.2362, pruned_loss=0.04217, over 4743.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03604, over 972596.09 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:13:45,967 INFO [train.py:715] (5/8) Epoch 8, batch 8450, loss[loss=0.1389, simple_loss=0.2142, pruned_loss=0.03175, over 4875.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03643, over 972735.44 frames.], batch size: 32, lr: 2.65e-04
2022-05-06 03:14:25,533 INFO [train.py:715] (5/8) Epoch 8, batch 8500, loss[loss=0.1674, simple_loss=0.2398, pruned_loss=0.04755, over 4903.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03617, over 972922.70 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:15:05,500 INFO [train.py:715] (5/8) Epoch 8, batch 8550, loss[loss=0.1447, simple_loss=0.2278, pruned_loss=0.03082, over 4783.00 frames.], tot_loss[loss=0.1444, simple_loss=0.217, pruned_loss=0.0359, over 973128.14 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:15:44,164 INFO [train.py:715] (5/8) Epoch 8, batch 8600, loss[loss=0.1178, simple_loss=0.1837, pruned_loss=0.02594, over 4937.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2171, pruned_loss=0.0358, over 972675.33 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 03:16:23,281 INFO [train.py:715] (5/8) Epoch 8, batch 8650, loss[loss=0.1484, simple_loss=0.2213, pruned_loss=0.03775, over 4907.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2173, pruned_loss=0.036, over 972472.00 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:17:02,900 INFO [train.py:715] (5/8) Epoch 8, batch 8700, loss[loss=0.1397, simple_loss=0.2106, pruned_loss=0.03433, over 4790.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03592, over 972489.48 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:17:41,699 INFO [train.py:715] (5/8) Epoch 8, batch 8750, loss[loss=0.1577, simple_loss=0.2382, pruned_loss=0.03858, over 4757.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03593, over 971877.03 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:18:20,672 INFO [train.py:715] (5/8) Epoch 8, batch 8800, loss[loss=0.15, simple_loss=0.2183, pruned_loss=0.04091, over 4978.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03644, over 972691.54 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:19:00,217 INFO [train.py:715] (5/8) Epoch 8, batch 8850, loss[loss=0.1157, simple_loss=0.1881, pruned_loss=0.0217, over 4949.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03664, over 972308.45 frames.], batch size: 21, lr: 2.65e-04
2022-05-06 03:19:39,728 INFO [train.py:715] (5/8) Epoch 8, batch 8900, loss[loss=0.1313, simple_loss=0.2007, pruned_loss=0.03094, over 4736.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03621, over 972370.30 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:20:18,231 INFO [train.py:715] (5/8) Epoch 8, batch 8950, loss[loss=0.1375, simple_loss=0.21, pruned_loss=0.03245, over 4859.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03613, over 972638.30 frames.], batch size: 20, lr: 2.65e-04
2022-05-06 03:20:57,339 INFO [train.py:715] (5/8) Epoch 8, batch 9000, loss[loss=0.1119, simple_loss=0.1829, pruned_loss=0.02047, over 4885.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03598, over 972902.68 frames.], batch size: 22, lr: 2.65e-04
2022-05-06 03:20:57,340 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 03:21:06,880 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1922, pruned_loss=0.01144, over 914524.00 frames.
2022-05-06 03:21:46,744 INFO [train.py:715] (5/8) Epoch 8, batch 9050, loss[loss=0.1353, simple_loss=0.2033, pruned_loss=0.03366, over 4843.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2152, pruned_loss=0.0355, over 971688.37 frames.], batch size: 20, lr: 2.65e-04
2022-05-06 03:22:26,223 INFO [train.py:715] (5/8) Epoch 8, batch 9100, loss[loss=0.1623, simple_loss=0.2241, pruned_loss=0.05022, over 4961.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03564, over 971628.65 frames.], batch size: 35, lr: 2.65e-04
2022-05-06 03:23:05,920 INFO [train.py:715] (5/8) Epoch 8, batch 9150, loss[loss=0.1653, simple_loss=0.2324, pruned_loss=0.04913, over 4984.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03546, over 972266.30 frames.], batch size: 39, lr: 2.64e-04
2022-05-06 03:23:44,125 INFO [train.py:715] (5/8) Epoch 8, batch 9200, loss[loss=0.1526, simple_loss=0.221, pruned_loss=0.0421, over 4897.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03495, over 971930.16 frames.], batch size: 39, lr: 2.64e-04
2022-05-06 03:24:23,666 INFO [train.py:715] (5/8) Epoch 8, batch 9250, loss[loss=0.1396, simple_loss=0.2144, pruned_loss=0.03239, over 4871.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03548, over 972847.42 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:25:03,200 INFO [train.py:715] (5/8) Epoch 8, batch 9300, loss[loss=0.1396, simple_loss=0.2067, pruned_loss=0.03623, over 4763.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03627, over 972510.79 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:25:42,062 INFO [train.py:715] (5/8) Epoch 8, batch 9350, loss[loss=0.1511, simple_loss=0.2235, pruned_loss=0.03938, over 4974.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03588, over 972972.19 frames.], batch size: 39, lr: 2.64e-04
2022-05-06 03:26:20,915 INFO [train.py:715] (5/8) Epoch 8, batch 9400, loss[loss=0.1219, simple_loss=0.1966, pruned_loss=0.02355, over 4876.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.0357, over 974006.72 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:27:00,378 INFO [train.py:715] (5/8) Epoch 8, batch 9450, loss[loss=0.1399, simple_loss=0.2222, pruned_loss=0.02884, over 4857.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.0356, over 974483.64 frames.], batch size: 20, lr: 2.64e-04
2022-05-06 03:27:40,541 INFO [train.py:715] (5/8) Epoch 8, batch 9500, loss[loss=0.1587, simple_loss=0.2248, pruned_loss=0.04634, over 4919.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03571, over 974117.63 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:28:21,697 INFO [train.py:715] (5/8) Epoch 8, batch 9550, loss[loss=0.1664, simple_loss=0.2334, pruned_loss=0.0497, over 4986.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.0357, over 974393.62 frames.], batch size: 26, lr: 2.64e-04
2022-05-06 03:29:01,736 INFO [train.py:715] (5/8) Epoch 8, batch 9600, loss[loss=0.1696, simple_loss=0.2348, pruned_loss=0.05222, over 4786.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03607, over 973782.57 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:29:41,771 INFO [train.py:715] (5/8) Epoch 8, batch 9650, loss[loss=0.1643, simple_loss=0.2379, pruned_loss=0.04531, over 4909.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03594, over 973365.64 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:30:21,098 INFO [train.py:715] (5/8) Epoch 8, batch 9700, loss[loss=0.1479, simple_loss=0.2171, pruned_loss=0.03932, over 4973.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03618, over 972847.81 frames.], batch size: 24, lr: 2.64e-04
2022-05-06 03:30:59,863 INFO [train.py:715] (5/8) Epoch 8, batch 9750, loss[loss=0.1514, simple_loss=0.232, pruned_loss=0.03536, over 4821.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03602, over 973185.52 frames.], batch size: 25, lr: 2.64e-04
2022-05-06 03:31:39,478 INFO [train.py:715] (5/8) Epoch 8, batch 9800, loss[loss=0.1529, simple_loss=0.2185, pruned_loss=0.04365, over 4875.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03578, over 973116.59 frames.], batch size: 32, lr: 2.64e-04
2022-05-06 03:32:18,971 INFO [train.py:715] (5/8) Epoch 8, batch 9850, loss[loss=0.1285, simple_loss=0.2101, pruned_loss=0.02345, over 4809.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2165, pruned_loss=0.03551, over 972828.25 frames.], batch size: 24, lr: 2.64e-04
2022-05-06 03:32:58,277 INFO [train.py:715] (5/8) Epoch 8, batch 9900, loss[loss=0.1513, simple_loss=0.2286, pruned_loss=0.03704, over 4952.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03538, over 972653.04 frames.], batch size: 35, lr: 2.64e-04
2022-05-06 03:33:37,622 INFO [train.py:715] (5/8) Epoch 8, batch 9950, loss[loss=0.1504, simple_loss=0.2251, pruned_loss=0.03784, over 4819.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.0357, over 973282.93 frames.], batch size: 26, lr: 2.64e-04
2022-05-06 03:34:17,532 INFO [train.py:715] (5/8) Epoch 8, batch 10000, loss[loss=0.1536, simple_loss=0.2287, pruned_loss=0.0393, over 4785.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2169, pruned_loss=0.03568, over 972900.66 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:34:56,513 INFO [train.py:715] (5/8) Epoch 8, batch 10050, loss[loss=0.1938, simple_loss=0.2425, pruned_loss=0.07261, over 4798.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03607, over 972561.41 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:35:35,064 INFO [train.py:715] (5/8) Epoch 8, batch 10100, loss[loss=0.1408, simple_loss=0.2323, pruned_loss=0.02466, over 4767.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03593, over 972655.59 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:36:15,140 INFO [train.py:715] (5/8) Epoch 8, batch 10150, loss[loss=0.1782, simple_loss=0.2406, pruned_loss=0.05792, over 4754.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03628, over 972154.91 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:36:55,128 INFO [train.py:715] (5/8) Epoch 8, batch 10200, loss[loss=0.1483, simple_loss=0.2291, pruned_loss=0.03379, over 4899.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03619, over 972484.47 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:37:34,624 INFO [train.py:715] (5/8) Epoch 8, batch 10250, loss[loss=0.155, simple_loss=0.2242, pruned_loss=0.04293, over 4787.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03595, over 973352.05 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:38:14,430 INFO [train.py:715] (5/8) Epoch 8, batch 10300, loss[loss=0.1332, simple_loss=0.2029, pruned_loss=0.03173, over 4960.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.0364, over 973576.44 frames.], batch size: 24, lr: 2.64e-04
2022-05-06 03:38:53,949 INFO [train.py:715] (5/8) Epoch 8, batch 10350, loss[loss=0.1288, simple_loss=0.2037, pruned_loss=0.027, over 4931.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03615, over 973093.64 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:39:32,638 INFO [train.py:715] (5/8) Epoch 8, batch 10400, loss[loss=0.129, simple_loss=0.209, pruned_loss=0.02447, over 4829.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.03605, over 972939.91 frames.], batch size: 27, lr: 2.64e-04
2022-05-06 03:40:12,244 INFO [train.py:715] (5/8) Epoch 8, batch 10450, loss[loss=0.1537, simple_loss=0.218, pruned_loss=0.04471, over 4913.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2161, pruned_loss=0.03614, over 973034.92 frames.], batch size: 29, lr: 2.64e-04
2022-05-06 03:40:51,307 INFO [train.py:715] (5/8) Epoch 8, batch 10500, loss[loss=0.1593, simple_loss=0.2247, pruned_loss=0.047, over 4868.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2156, pruned_loss=0.03613, over 973077.42 frames.], batch size: 20, lr: 2.64e-04
2022-05-06 03:41:30,155 INFO [train.py:715] (5/8) Epoch 8, batch 10550, loss[loss=0.1391, simple_loss=0.2138, pruned_loss=0.03223, over 4815.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03625, over 972704.25 frames.], batch size: 12, lr: 2.64e-04
2022-05-06 03:42:08,777 INFO [train.py:715] (5/8) Epoch 8, batch 10600, loss[loss=0.155, simple_loss=0.2235, pruned_loss=0.04324, over 4880.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03638, over 973242.28 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:42:48,073 INFO [train.py:715] (5/8) Epoch 8, batch 10650, loss[loss=0.1204, simple_loss=0.1993, pruned_loss=0.02069, over 4910.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.0364, over 973022.68 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:43:27,255 INFO [train.py:715] (5/8) Epoch 8, batch 10700, loss[loss=0.1347, simple_loss=0.1976, pruned_loss=0.03589, over 4961.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03598, over 973212.96 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:44:06,352 INFO [train.py:715] (5/8) Epoch 8, batch 10750, loss[loss=0.1124, simple_loss=0.1792, pruned_loss=0.02278, over 4767.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03619, over 972309.15 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:44:46,294 INFO [train.py:715] (5/8) Epoch 8, batch 10800, loss[loss=0.1401, simple_loss=0.2031, pruned_loss=0.03856, over 4696.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2157, pruned_loss=0.03606, over 972419.58 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:45:26,102 INFO [train.py:715] (5/8) Epoch 8, batch 10850, loss[loss=0.1368, simple_loss=0.2075, pruned_loss=0.03312, over 4837.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03541, over 972656.96 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:46:05,370 INFO [train.py:715] (5/8) Epoch 8, batch 10900, loss[loss=0.1521, simple_loss=0.2375, pruned_loss=0.03332, over 4775.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03597, over 972910.93 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:46:44,374 INFO [train.py:715] (5/8) Epoch 8, batch 10950, loss[loss=0.1374, simple_loss=0.2004, pruned_loss=0.03723, over 4844.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03602, over 972185.21 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:47:24,373 INFO [train.py:715] (5/8) Epoch 8, batch 11000, loss[loss=0.1338, simple_loss=0.2062, pruned_loss=0.03067, over 4817.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2161, pruned_loss=0.0363, over 972719.21 frames.], batch size: 25, lr: 2.64e-04
2022-05-06 03:48:03,908 INFO [train.py:715] (5/8) Epoch 8, batch 11050, loss[loss=0.113, simple_loss=0.1925, pruned_loss=0.01677, over 4952.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03574, over 973004.79 frames.], batch size: 29, lr: 2.64e-04
2022-05-06 03:48:42,670 INFO [train.py:715] (5/8) Epoch 8, batch 11100, loss[loss=0.1094, simple_loss=0.1819, pruned_loss=0.01847, over 4940.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2143, pruned_loss=0.03533, over 973365.40 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:49:22,144 INFO [train.py:715] (5/8) Epoch 8, batch 11150, loss[loss=0.1177, simple_loss=0.1911, pruned_loss=0.02216, over 4854.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2148, pruned_loss=0.03547, over 972359.43 frames.], batch size: 13, lr: 2.64e-04
2022-05-06 03:50:01,938 INFO [train.py:715] (5/8) Epoch 8, batch 11200, loss[loss=0.1604, simple_loss=0.2336, pruned_loss=0.04364, over 4909.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2155, pruned_loss=0.03604, over 972993.42 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:50:40,565 INFO [train.py:715] (5/8) Epoch 8, batch 11250, loss[loss=0.1203, simple_loss=0.1978, pruned_loss=0.0214, over 4795.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03564, over 972067.31 frames.], batch size: 24, lr: 2.64e-04
2022-05-06 03:51:19,591 INFO [train.py:715] (5/8) Epoch 8, batch 11300, loss[loss=0.1369, simple_loss=0.2037, pruned_loss=0.03506, over 4862.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03561, over 972334.21 frames.], batch size: 32, lr: 2.64e-04
2022-05-06 03:51:58,926 INFO [train.py:715] (5/8) Epoch 8, batch 11350, loss[loss=0.1575, simple_loss=0.2494, pruned_loss=0.0328, over 4962.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03572, over 972681.20 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 03:52:37,406 INFO [train.py:715] (5/8) Epoch 8, batch 11400, loss[loss=0.1305, simple_loss=0.2114, pruned_loss=0.02486, over 4819.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03565, over 973107.96 frames.], batch size: 25, lr: 2.63e-04
2022-05-06 03:53:16,047 INFO [train.py:715] (5/8) Epoch 8, batch 11450, loss[loss=0.1243, simple_loss=0.2009, pruned_loss=0.02387, over 4827.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.0356, over 972692.25 frames.], batch size: 27, lr: 2.63e-04
2022-05-06 03:53:55,351 INFO [train.py:715] (5/8) Epoch 8, batch 11500, loss[loss=0.1509, simple_loss=0.2141, pruned_loss=0.0439, over 4975.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03601, over 972033.82 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 03:54:34,454 INFO [train.py:715] (5/8) Epoch 8, batch 11550, loss[loss=0.1387, simple_loss=0.2172, pruned_loss=0.03011, over 4795.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03611, over 972597.68 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 03:55:13,508 INFO [train.py:715] (5/8) Epoch 8, batch 11600, loss[loss=0.1228, simple_loss=0.1977, pruned_loss=0.02394, over 4983.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03613, over 972648.24 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 03:55:53,443 INFO [train.py:715] (5/8) Epoch 8, batch 11650, loss[loss=0.1098, simple_loss=0.18, pruned_loss=0.01984, over 4778.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2175, pruned_loss=0.03652, over 972666.75 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 03:56:33,835 INFO [train.py:715] (5/8) Epoch 8, batch 11700, loss[loss=0.1358, simple_loss=0.2034, pruned_loss=0.03407, over 4892.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.0362, over 972595.19 frames.], batch size: 16, lr: 2.63e-04
2022-05-06 03:57:13,266 INFO [train.py:715] (5/8) Epoch 8, batch 11750, loss[loss=0.1293, simple_loss=0.2023, pruned_loss=0.02819, over 4981.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.0364, over 972807.14 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 03:57:52,304 INFO [train.py:715] (5/8) Epoch 8, batch 11800, loss[loss=0.1308, simple_loss=0.2034, pruned_loss=0.02907, over 4788.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03631, over 972961.24 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 03:58:32,048 INFO [train.py:715] (5/8) Epoch 8, batch 11850, loss[loss=0.1566, simple_loss=0.2216, pruned_loss=0.04574, over 4845.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03594, over 972498.40 frames.], batch size: 30, lr: 2.63e-04
2022-05-06 03:59:11,745 INFO [train.py:715] (5/8) Epoch 8, batch 11900, loss[loss=0.149, simple_loss=0.2191, pruned_loss=0.03944, over 4888.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03645, over 972352.87 frames.], batch size: 19, lr: 2.63e-04
2022-05-06 03:59:51,344 INFO [train.py:715] (5/8) Epoch 8, batch 11950, loss[loss=0.1376, simple_loss=0.2086, pruned_loss=0.03334, over 4825.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03578, over 971894.55 frames.], batch size: 27, lr: 2.63e-04
2022-05-06 04:00:30,529 INFO [train.py:715] (5/8) Epoch 8, batch 12000, loss[loss=0.1362, simple_loss=0.2068, pruned_loss=0.0328, over 4866.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.0364, over 972906.84 frames.], batch size: 32, lr: 2.63e-04
2022-05-06 04:00:30,530 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 04:00:40,090 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
2022-05-06 04:01:19,841 INFO [train.py:715] (5/8) Epoch 8, batch 12050, loss[loss=0.1066, simple_loss=0.1723, pruned_loss=0.02049, over 4844.00 frames.], tot_loss[loss=0.144, simple_loss=0.2158, pruned_loss=0.03608, over 972155.28 frames.], batch size: 13, lr: 2.63e-04
2022-05-06 04:01:59,445 INFO [train.py:715] (5/8) Epoch 8, batch 12100, loss[loss=0.1448, simple_loss=0.2179, pruned_loss=0.03592, over 4857.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03661, over 972015.48 frames.], batch size: 32, lr: 2.63e-04
2022-05-06 04:02:38,518 INFO [train.py:715] (5/8) Epoch 8, batch 12150, loss[loss=0.169, simple_loss=0.2353, pruned_loss=0.05141, over 4860.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03582, over 972701.66 frames.], batch size: 32, lr: 2.63e-04
2022-05-06 04:03:17,589 INFO [train.py:715] (5/8) Epoch 8, batch 12200, loss[loss=0.1047, simple_loss=0.1633, pruned_loss=0.02303, over 4757.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03561, over 972074.32 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 04:03:57,161 INFO [train.py:715] (5/8) Epoch 8, batch 12250, loss[loss=0.1431, simple_loss=0.2293, pruned_loss=0.02846, over 4731.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2157, pruned_loss=0.03476, over 972192.60 frames.], batch size: 16, lr: 2.63e-04
2022-05-06 04:04:36,391 INFO [train.py:715] (5/8) Epoch 8, batch 12300, loss[loss=0.1462, simple_loss=0.2244, pruned_loss=0.03402, over 4876.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.03525, over 972405.32 frames.], batch size: 22, lr: 2.63e-04
2022-05-06 04:05:15,232 INFO [train.py:715] (5/8) Epoch 8, batch 12350, loss[loss=0.1506, simple_loss=0.2149, pruned_loss=0.04314, over 4694.00 frames.], tot_loss[loss=0.1432, simple_loss=0.216, pruned_loss=0.03515, over 971830.13 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 04:05:54,658 INFO [train.py:715] (5/8) Epoch 8, batch 12400, loss[loss=0.1219, simple_loss=0.1916, pruned_loss=0.02607, over 4842.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03562, over 972155.54 frames.], batch size: 13, lr: 2.63e-04
2022-05-06 04:06:34,252 INFO [train.py:715] (5/8) Epoch 8, batch 12450, loss[loss=0.1369, simple_loss=0.2185, pruned_loss=0.02764, over 4824.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2176, pruned_loss=0.03657, over 972193.18 frames.], batch size: 27, lr: 2.63e-04
2022-05-06 04:07:13,256 INFO [train.py:715] (5/8) Epoch 8, batch 12500, loss[loss=0.1608, simple_loss=0.2261, pruned_loss=0.04773, over 4960.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03694, over 973122.09 frames.], batch size: 39, lr: 2.63e-04
2022-05-06 04:07:52,123 INFO [train.py:715] (5/8) Epoch 8, batch 12550, loss[loss=0.1436, simple_loss=0.2101, pruned_loss=0.03853, over 4875.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03649, over 973584.83 frames.], batch size: 32, lr: 2.63e-04
2022-05-06 04:08:31,830 INFO [train.py:715] (5/8) Epoch 8, batch 12600, loss[loss=0.139, simple_loss=0.202, pruned_loss=0.03795, over 4781.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03669, over 973449.70 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 04:09:10,878 INFO [train.py:715] (5/8) Epoch 8, batch 12650, loss[loss=0.163, simple_loss=0.2349, pruned_loss=0.04554, over 4968.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03623, over 973304.41 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 04:09:50,738 INFO [train.py:715] (5/8) Epoch 8, batch 12700, loss[loss=0.1287, simple_loss=0.1978, pruned_loss=0.02982, over 4796.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03578, over 973830.64 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 04:10:30,123 INFO [train.py:715] (5/8) Epoch 8, batch 12750, loss[loss=0.2053, simple_loss=0.2862, pruned_loss=0.06224, over 4821.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03575, over 973194.30 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 04:11:10,320 INFO [train.py:715] (5/8) Epoch 8, batch 12800, loss[loss=0.1582, simple_loss=0.2295, pruned_loss=0.04349, over 4976.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03564, over 973615.99 frames.], batch size: 33, lr: 2.63e-04
2022-05-06 04:11:48,982 INFO [train.py:715] (5/8) Epoch 8, batch 12850, loss[loss=0.1214, simple_loss=0.1932, pruned_loss=0.0248, over 4938.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2167, pruned_loss=0.03558, over 973723.42 frames.], batch size: 21, lr: 2.63e-04
2022-05-06 04:12:28,014 INFO [train.py:715] (5/8) Epoch 8, batch 12900, loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03385, over 4883.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03614, over 973937.83 frames.], batch size: 16, lr: 2.63e-04
2022-05-06 04:13:07,522 INFO [train.py:715] (5/8) Epoch 8, batch 12950, loss[loss=0.1723, simple_loss=0.2336, pruned_loss=0.05547, over 4960.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03604, over 973975.94 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 04:13:46,911 INFO [train.py:715] (5/8) Epoch 8, batch 13000, loss[loss=0.1511, simple_loss=0.2205, pruned_loss=0.04086, over 4938.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03606, over 973291.40 frames.], batch size: 21, lr: 2.63e-04
2022-05-06 04:14:26,215 INFO [train.py:715] (5/8) Epoch 8, batch 13050, loss[loss=0.1469, simple_loss=0.2069, pruned_loss=0.04341, over 4764.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03589, over 972982.85 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 04:15:05,642 INFO [train.py:715] (5/8) Epoch 8, batch 13100, loss[loss=0.1804, simple_loss=0.2649, pruned_loss=0.04794, over 4978.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03544, over 972628.87 frames.], batch size: 25, lr: 2.63e-04
2022-05-06 04:15:45,374 INFO [train.py:715] (5/8) Epoch 8, batch 13150, loss[loss=0.1442, simple_loss=0.2169, pruned_loss=0.03578, over 4855.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.0358, over 972671.09 frames.], batch size: 30, lr: 2.63e-04
2022-05-06 04:16:24,326 INFO [train.py:715] (5/8) Epoch 8, batch 13200, loss[loss=0.1269, simple_loss=0.2044, pruned_loss=0.02466, over 4975.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03594, over 971746.94 frames.], batch size: 25, lr: 2.63e-04
2022-05-06 04:17:03,714 INFO [train.py:715] (5/8) Epoch 8, batch 13250, loss[loss=0.1397, simple_loss=0.2171, pruned_loss=0.03118, over 4960.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.0355, over 971275.69 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 04:17:43,332 INFO [train.py:715] (5/8) Epoch 8, batch 13300, loss[loss=0.1893, simple_loss=0.2601, pruned_loss=0.05926, over 4920.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.0354, over 972313.32 frames.], batch size: 18, lr: 2.63e-04
2022-05-06 04:18:22,354 INFO [train.py:715] (5/8) Epoch 8, batch 13350, loss[loss=0.1518, simple_loss=0.2288, pruned_loss=0.03739, over 4970.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03533, over 972332.88 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 04:19:00,999 INFO [train.py:715] (5/8) Epoch 8, batch 13400, loss[loss=0.149, simple_loss=0.2302, pruned_loss=0.03392, over 4873.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03494, over 972099.92 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:19:39,799 INFO [train.py:715] (5/8) Epoch 8, batch 13450, loss[loss=0.1427, simple_loss=0.2136, pruned_loss=0.03589, over 4814.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.0356, over 971850.96 frames.], batch size: 27, lr: 2.63e-04
2022-05-06 04:20:19,853 INFO [train.py:715] (5/8) Epoch 8, batch 13500, loss[loss=0.1189, simple_loss=0.1938, pruned_loss=0.02199, over 4982.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.0352, over 972190.05 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 04:20:58,643 INFO [train.py:715] (5/8) Epoch 8, batch 13550, loss[loss=0.1678, simple_loss=0.2408, pruned_loss=0.04745, over 4936.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2164, pruned_loss=0.03533, over 972305.00 frames.], batch size: 39, lr: 2.62e-04
2022-05-06 04:21:37,840 INFO [train.py:715] (5/8) Epoch 8, batch 13600, loss[loss=0.142, simple_loss=0.22, pruned_loss=0.03202, over 4944.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.0354, over 971968.04 frames.], batch size: 29, lr: 2.62e-04
2022-05-06 04:22:16,975 INFO [train.py:715] (5/8) Epoch 8, batch 13650, loss[loss=0.1866, simple_loss=0.2499, pruned_loss=0.06169, over 4760.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03593, over 971382.68 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:22:56,126 INFO [train.py:715] (5/8) Epoch 8, batch 13700, loss[loss=0.1517, simple_loss=0.225, pruned_loss=0.0392, over 4851.00 frames.], tot_loss[loss=0.144, simple_loss=0.2166, pruned_loss=0.03577, over 971669.72 frames.], batch size: 30, lr: 2.62e-04
2022-05-06 04:23:34,768 INFO [train.py:715] (5/8) Epoch 8, batch 13750, loss[loss=0.1385, simple_loss=0.2079, pruned_loss=0.03452, over 4806.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03582, over 971822.60 frames.], batch size: 21, lr: 2.62e-04
2022-05-06 04:24:13,493 INFO [train.py:715] (5/8) Epoch 8, batch 13800, loss[loss=0.1322, simple_loss=0.2148, pruned_loss=0.02477, over 4781.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03573, over 971931.42 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:24:52,945 INFO [train.py:715] (5/8) Epoch 8, batch 13850, loss[loss=0.1767, simple_loss=0.2422, pruned_loss=0.05564, over 4747.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03562, over 972412.34 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:25:31,238 INFO [train.py:715] (5/8) Epoch 8, batch 13900, loss[loss=0.1256, simple_loss=0.2106, pruned_loss=0.02032, over 4888.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2173, pruned_loss=0.03618, over 973179.24 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:26:10,332 INFO [train.py:715] (5/8) Epoch 8, batch 13950, loss[loss=0.1595, simple_loss=0.2322, pruned_loss=0.04344, over 4842.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03693, over 973712.46 frames.], batch size: 15, lr: 2.62e-04
2022-05-06 04:26:49,428 INFO [train.py:715] (5/8) Epoch 8, batch 14000, loss[loss=0.1429, simple_loss=0.198, pruned_loss=0.04389, over 4823.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03651, over 973832.28 frames.], batch size: 13, lr: 2.62e-04
2022-05-06 04:27:28,485 INFO [train.py:715] (5/8) Epoch 8, batch 14050, loss[loss=0.1353, simple_loss=0.2192, pruned_loss=0.02569, over 4881.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03685, over 973853.21 frames.], batch size: 22, lr: 2.62e-04
2022-05-06 04:28:06,678 INFO [train.py:715] (5/8) Epoch 8, batch 14100, loss[loss=0.1715, simple_loss=0.2476, pruned_loss=0.0477, over 4911.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03672, over 973138.18 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:28:45,331 INFO [train.py:715] (5/8) Epoch 8, batch 14150, loss[loss=0.1449, simple_loss=0.2261, pruned_loss=0.03183, over 4835.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03679, over 973525.40 frames.], batch size: 26, lr: 2.62e-04
2022-05-06 04:29:25,593 INFO [train.py:715] (5/8) Epoch 8, batch 14200, loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.0335, over 4875.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03615, over 972661.62 frames.], batch size: 22, lr: 2.62e-04
2022-05-06 04:30:04,163 INFO [train.py:715] (5/8) Epoch 8, batch 14250, loss[loss=0.1291, simple_loss=0.2053, pruned_loss=0.02648, over 4828.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2164, pruned_loss=0.03648, over 972468.61 frames.], batch size: 30, lr: 2.62e-04
2022-05-06 04:30:44,068 INFO [train.py:715] (5/8) Epoch 8, batch 14300, loss[loss=0.137, simple_loss=0.2161, pruned_loss=0.02892, over 4900.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03619, over 972314.64 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:31:23,528 INFO [train.py:715] (5/8) Epoch 8, batch 14350, loss[loss=0.1692, simple_loss=0.2509, pruned_loss=0.04372, over 4977.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03593, over 972774.20 frames.], batch size: 15, lr: 2.62e-04
2022-05-06 04:32:02,825 INFO [train.py:715] (5/8) Epoch 8, batch 14400, loss[loss=0.1321, simple_loss=0.2091, pruned_loss=0.02755, over 4898.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2169, pruned_loss=0.03628, over 972924.68 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:32:41,515 INFO [train.py:715] (5/8) Epoch 8, batch 14450, loss[loss=0.1416, simple_loss=0.2192, pruned_loss=0.03201, over 4850.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03601, over 973224.62 frames.], batch size: 20, lr: 2.62e-04
2022-05-06 04:33:20,779 INFO [train.py:715] (5/8) Epoch 8, batch 14500, loss[loss=0.1476, simple_loss=0.2178, pruned_loss=0.03873, over 4776.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2178, pruned_loss=0.03662, over 971861.38 frames.], batch size: 14, lr: 2.62e-04
2022-05-06 04:34:00,251 INFO [train.py:715] (5/8) Epoch 8, batch 14550, loss[loss=0.1493, simple_loss=0.2195, pruned_loss=0.03957, over 4908.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2178, pruned_loss=0.03657, over 972225.86 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:34:38,288 INFO [train.py:715] (5/8) Epoch 8, batch 14600, loss[loss=0.131, simple_loss=0.2036, pruned_loss=0.02914, over 4927.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.0366, over 971459.50 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:35:17,875 INFO [train.py:715] (5/8) Epoch 8, batch 14650, loss[loss=0.1512, simple_loss=0.2283, pruned_loss=0.03708, over 4924.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2162, pruned_loss=0.03643, over 972006.88 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:35:57,138 INFO [train.py:715] (5/8) Epoch 8, batch 14700, loss[loss=0.1456, simple_loss=0.2155, pruned_loss=0.0379, over 4928.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03659, over 972391.77 frames.], batch size: 21, lr: 2.62e-04
2022-05-06 04:36:35,955 INFO [train.py:715] (5/8) Epoch 8, batch 14750, loss[loss=0.1739, simple_loss=0.2417, pruned_loss=0.05307, over 4944.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03637, over 972826.09 frames.], batch size: 35, lr: 2.62e-04
2022-05-06 04:37:14,351 INFO [train.py:715] (5/8) Epoch 8, batch 14800, loss[loss=0.1638, simple_loss=0.2343, pruned_loss=0.04666, over 4961.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03644, over 973535.73 frames.], batch size: 39, lr: 2.62e-04
2022-05-06 04:37:54,163 INFO [train.py:715] (5/8) Epoch 8, batch 14850, loss[loss=0.1461, simple_loss=0.2331, pruned_loss=0.02949, over 4788.00 frames.], tot_loss[loss=0.144, simple_loss=0.2165, pruned_loss=0.03574, over 973695.12 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:38:33,084 INFO [train.py:715] (5/8) Epoch 8, batch 14900, loss[loss=0.1501, simple_loss=0.2277, pruned_loss=0.03623, over 4788.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2173, pruned_loss=0.03602, over 974005.61 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:39:11,870 INFO [train.py:715] (5/8) Epoch 8, batch 14950, loss[loss=0.1333, simple_loss=0.21, pruned_loss=0.02833, over 4811.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2174, pruned_loss=0.03606, over 974613.19 frames.], batch size: 25, lr: 2.62e-04
2022-05-06 04:39:51,073 INFO [train.py:715] (5/8) Epoch 8, batch 15000, loss[loss=0.1263, simple_loss=0.1945, pruned_loss=0.02905, over 4771.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2172, pruned_loss=0.03612, over 973632.89 frames.], batch size: 12, lr: 2.62e-04
2022-05-06 04:39:51,074 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 04:40:00,791 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1921, pruned_loss=0.01153, over 914524.00 frames.
2022-05-06 04:40:40,556 INFO [train.py:715] (5/8) Epoch 8, batch 15050, loss[loss=0.1486, simple_loss=0.2356, pruned_loss=0.03074, over 4896.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03622, over 973340.50 frames.], batch size: 22, lr: 2.62e-04
2022-05-06 04:41:19,875 INFO [train.py:715] (5/8) Epoch 8, batch 15100, loss[loss=0.1423, simple_loss=0.2035, pruned_loss=0.04051, over 4872.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03628, over 973277.10 frames.], batch size: 13, lr: 2.62e-04
2022-05-06 04:41:59,413 INFO [train.py:715] (5/8) Epoch 8, batch 15150, loss[loss=0.1356, simple_loss=0.2123, pruned_loss=0.0295, over 4982.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03648, over 972733.78 frames.], batch size: 28, lr: 2.62e-04
2022-05-06 04:42:38,832 INFO [train.py:715] (5/8) Epoch 8, batch 15200, loss[loss=0.1203, simple_loss=0.2037, pruned_loss=0.01844, over 4959.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2175, pruned_loss=0.03617, over 973086.78 frames.], batch size: 24, lr: 2.62e-04
2022-05-06 04:43:18,559 INFO [train.py:715] (5/8) Epoch 8, batch 15250, loss[loss=0.1484, simple_loss=0.226, pruned_loss=0.03545, over 4919.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03587, over 972173.05 frames.], batch size: 29, lr: 2.62e-04
2022-05-06 04:43:58,535 INFO [train.py:715] (5/8) Epoch 8, batch 15300, loss[loss=0.1523, simple_loss=0.2273, pruned_loss=0.03868, over 4854.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03697, over 972395.29 frames.], batch size: 20, lr: 2.62e-04
2022-05-06 04:44:37,108 INFO [train.py:715] (5/8) Epoch 8, batch 15350, loss[loss=0.146, simple_loss=0.2136, pruned_loss=0.03922, over 4943.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2183, pruned_loss=0.03725, over 973690.22 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:45:16,994 INFO [train.py:715] (5/8) Epoch 8, batch 15400, loss[loss=0.1683, simple_loss=0.2355, pruned_loss=0.05054, over 4923.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03757, over 973345.62 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:45:55,981 INFO [train.py:715] (5/8) Epoch 8, batch 15450, loss[loss=0.1143, simple_loss=0.178, pruned_loss=0.0253, over 4821.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03719, over 973726.08 frames.], batch size: 13, lr: 2.62e-04
2022-05-06 04:46:34,941 INFO [train.py:715] (5/8) Epoch 8, batch 15500, loss[loss=0.1325, simple_loss=0.203, pruned_loss=0.03102, over 4940.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03685, over 972874.86 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:47:13,679 INFO [train.py:715] (5/8) Epoch 8, batch 15550, loss[loss=0.1519, simple_loss=0.2348, pruned_loss=0.03454, over 4909.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03654, over 972439.48 frames.], batch size: 18, lr: 2.62e-04
2022-05-06 04:47:52,419 INFO [train.py:715] (5/8) Epoch 8, batch 15600, loss[loss=0.132, simple_loss=0.2002, pruned_loss=0.03187, over 4766.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03645, over 972937.17 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:48:32,585 INFO [train.py:715] (5/8) Epoch 8, batch 15650, loss[loss=0.1284, simple_loss=0.1962, pruned_loss=0.03026, over 4934.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03598, over 973215.82 frames.], batch size: 29, lr: 2.62e-04
2022-05-06 04:49:11,087 INFO [train.py:715] (5/8) Epoch 8, batch 15700, loss[loss=0.1133, simple_loss=0.1843, pruned_loss=0.02117, over 4762.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03571, over 972172.89 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:49:50,913 INFO [train.py:715] (5/8) Epoch 8, batch 15750, loss[loss=0.1551, simple_loss=0.2287, pruned_loss=0.0407, over 4969.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03586, over 971699.78 frames.], batch size: 24, lr: 2.62e-04
2022-05-06 04:50:30,388 INFO [train.py:715] (5/8) Epoch 8, batch 15800, loss[loss=0.1391, simple_loss=0.2111, pruned_loss=0.03356, over 4688.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03549, over 972250.65 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 04:51:09,451 INFO [train.py:715] (5/8) Epoch 8, batch 15850, loss[loss=0.1811, simple_loss=0.2457, pruned_loss=0.05827, over 4889.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03546, over 972508.43 frames.], batch size: 39, lr: 2.61e-04
2022-05-06 04:51:48,552 INFO [train.py:715] (5/8) Epoch 8, batch 15900, loss[loss=0.1335, simple_loss=0.2097, pruned_loss=0.02864, over 4930.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03542, over 972116.03 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 04:52:27,777 INFO [train.py:715] (5/8) Epoch 8, batch 15950, loss[loss=0.1473, simple_loss=0.229, pruned_loss=0.03283, over 4857.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2159, pruned_loss=0.03519, over 972112.55 frames.], batch size: 20, lr: 2.61e-04
2022-05-06 04:53:07,056 INFO [train.py:715] (5/8) Epoch 8, batch 16000, loss[loss=0.1493, simple_loss=0.2064, pruned_loss=0.04615, over 4930.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03513, over 971932.57 frames.], batch size: 39, lr: 2.61e-04
2022-05-06 04:53:45,654 INFO [train.py:715] (5/8) Epoch 8, batch 16050, loss[loss=0.1705, simple_loss=0.2445, pruned_loss=0.04826, over 4753.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2163, pruned_loss=0.0352, over 971105.41 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 04:54:25,523 INFO [train.py:715] (5/8) Epoch 8, batch 16100, loss[loss=0.1614, simple_loss=0.2299, pruned_loss=0.04647, over 4979.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.0351, over 970861.57 frames.], batch size: 28, lr: 2.61e-04
2022-05-06 04:55:04,002 INFO [train.py:715] (5/8) Epoch 8, batch 16150, loss[loss=0.1245, simple_loss=0.2149, pruned_loss=0.01707, over 4926.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03527, over 971674.99 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 04:55:43,545 INFO [train.py:715] (5/8) Epoch 8, batch 16200, loss[loss=0.1323, simple_loss=0.1944, pruned_loss=0.03511, over 4782.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03512, over 972423.96 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 04:56:21,929 INFO [train.py:715] (5/8) Epoch 8, batch 16250, loss[loss=0.136, simple_loss=0.2033, pruned_loss=0.03438, over 4779.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03475, over 972431.53 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 04:57:01,391 INFO [train.py:715] (5/8) Epoch 8, batch 16300, loss[loss=0.1524, simple_loss=0.2308, pruned_loss=0.03705, over 4896.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03504, over 972532.57 frames.], batch size: 22, lr: 2.61e-04
2022-05-06 04:57:40,825 INFO [train.py:715] (5/8) Epoch 8, batch 16350, loss[loss=0.1454, simple_loss=0.215, pruned_loss=0.03789, over 4785.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03463, over 972823.76 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 04:58:19,596 INFO [train.py:715] (5/8) Epoch 8, batch 16400, loss[loss=0.1386, simple_loss=0.2196, pruned_loss=0.02874, over 4965.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03495, over 972352.44 frames.], batch size: 24, lr: 2.61e-04
2022-05-06 04:58:58,711 INFO [train.py:715] (5/8) Epoch 8, batch 16450, loss[loss=0.1501, simple_loss=0.2171, pruned_loss=0.04151, over 4932.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03511, over 972847.03 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 04:59:37,556 INFO [train.py:715] (5/8) Epoch 8, batch 16500, loss[loss=0.1472, simple_loss=0.2113, pruned_loss=0.04154, over 4910.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03514, over 972417.48 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 05:00:17,262 INFO [train.py:715] (5/8) Epoch 8, batch 16550, loss[loss=0.1293, simple_loss=0.2176, pruned_loss=0.02047, over 4968.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03456, over 971571.85 frames.], batch size: 28, lr: 2.61e-04
2022-05-06 05:00:56,283 INFO [train.py:715] (5/8) Epoch 8, batch 16600, loss[loss=0.1494, simple_loss=0.228, pruned_loss=0.03539, over 4821.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03558, over 971197.43 frames.], batch size: 26, lr: 2.61e-04
2022-05-06 05:01:35,314 INFO [train.py:715] (5/8) Epoch 8, batch 16650, loss[loss=0.1195, simple_loss=0.1966, pruned_loss=0.02118, over 4981.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.0354, over 971765.49 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 05:02:14,553 INFO [train.py:715] (5/8) Epoch 8, batch 16700, loss[loss=0.1816, simple_loss=0.2567, pruned_loss=0.0532, over 4787.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03527, over 971103.47 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 05:02:53,473 INFO [train.py:715] (5/8) Epoch 8, batch 16750, loss[loss=0.1342, simple_loss=0.1997, pruned_loss=0.03432, over 4827.00 frames.], tot_loss[loss=0.142, simple_loss=0.2139, pruned_loss=0.03508, over 971160.72 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:03:33,068 INFO [train.py:715] (5/8) Epoch 8, batch 16800, loss[loss=0.1402, simple_loss=0.223, pruned_loss=0.02872, over 4804.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.03502, over 971887.70 frames.], batch size: 26, lr: 2.61e-04
2022-05-06 05:04:12,044 INFO [train.py:715] (5/8) Epoch 8, batch 16850, loss[loss=0.1439, simple_loss=0.2221, pruned_loss=0.0329, over 4902.00 frames.], tot_loss[loss=0.142, simple_loss=0.2137, pruned_loss=0.0351, over 972186.32 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 05:04:51,957 INFO [train.py:715] (5/8) Epoch 8, batch 16900, loss[loss=0.1432, simple_loss=0.2085, pruned_loss=0.03896, over 4985.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2141, pruned_loss=0.03525, over 972416.19 frames.], batch size: 28, lr: 2.61e-04
2022-05-06 05:05:30,451 INFO [train.py:715] (5/8) Epoch 8, batch 16950, loss[loss=0.1828, simple_loss=0.2716, pruned_loss=0.04697, over 4908.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.035, over 972566.33 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 05:06:10,148 INFO [train.py:715] (5/8) Epoch 8, batch 17000, loss[loss=0.1212, simple_loss=0.1957, pruned_loss=0.02335, over 4892.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03497, over 972423.42 frames.], batch size: 19, lr: 2.61e-04
2022-05-06 05:06:49,662 INFO [train.py:715] (5/8) Epoch 8, batch 17050, loss[loss=0.1462, simple_loss=0.2017, pruned_loss=0.04535, over 4686.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2148, pruned_loss=0.03596, over 972684.65 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 05:07:28,335 INFO [train.py:715] (5/8) Epoch 8, batch 17100, loss[loss=0.1467, simple_loss=0.2289, pruned_loss=0.03229, over 4759.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03603, over 972249.25 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 05:08:08,032 INFO [train.py:715] (5/8) Epoch 8, batch 17150, loss[loss=0.1414, simple_loss=0.2099, pruned_loss=0.03641, over 4929.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03638, over 973212.86 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 05:08:47,210 INFO [train.py:715] (5/8) Epoch 8, batch 17200, loss[loss=0.1291, simple_loss=0.2123, pruned_loss=0.02293, over 4962.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03661, over 974027.99 frames.], batch size: 24, lr: 2.61e-04
2022-05-06 05:09:26,325 INFO [train.py:715] (5/8) Epoch 8, batch 17250, loss[loss=0.172, simple_loss=0.2441, pruned_loss=0.04989, over 4716.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03647, over 972711.48 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 05:10:04,659 INFO [train.py:715] (5/8) Epoch 8, batch 17300, loss[loss=0.1318, simple_loss=0.1972, pruned_loss=0.03316, over 4786.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.0367, over 972774.35 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 05:10:44,495 INFO [train.py:715] (5/8) Epoch 8, batch 17350, loss[loss=0.1433, simple_loss=0.2131, pruned_loss=0.03678, over 4892.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03636, over 973308.55 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 05:11:23,595 INFO [train.py:715] (5/8) Epoch 8, batch 17400, loss[loss=0.1307, simple_loss=0.2091, pruned_loss=0.02612, over 4988.00 frames.], tot_loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.03567, over 973570.31 frames.], batch size: 25, lr: 2.61e-04
2022-05-06 05:12:02,694 INFO [train.py:715] (5/8) Epoch 8, batch 17450, loss[loss=0.1746, simple_loss=0.2503, pruned_loss=0.04948, over 4897.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03593, over 972642.46 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 05:12:42,123 INFO [train.py:715] (5/8) Epoch 8, batch 17500, loss[loss=0.1511, simple_loss=0.2318, pruned_loss=0.03516, over 4767.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2154, pruned_loss=0.03583, over 972605.58 frames.], batch size: 18, lr: 2.61e-04
2022-05-06 05:13:23,168 INFO [train.py:715] (5/8) Epoch 8, batch 17550, loss[loss=0.1579, simple_loss=0.2388, pruned_loss=0.03851, over 4901.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03614, over 972081.68 frames.], batch size: 22, lr: 2.61e-04
2022-05-06 05:14:02,978 INFO [train.py:715] (5/8) Epoch 8, batch 17600, loss[loss=0.1086, simple_loss=0.1834, pruned_loss=0.01691, over 4965.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03561, over 972953.04 frames.], batch size: 35, lr: 2.61e-04
2022-05-06 05:14:41,725 INFO [train.py:715] (5/8) Epoch 8, batch 17650, loss[loss=0.1726, simple_loss=0.2386, pruned_loss=0.05331, over 4783.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03553, over 972706.73 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 05:15:22,863 INFO [train.py:715] (5/8) Epoch 8, batch 17700, loss[loss=0.1542, simple_loss=0.2329, pruned_loss=0.03777, over 4892.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03471, over 972561.66 frames.], batch size: 19, lr: 2.61e-04
2022-05-06 05:16:02,813 INFO [train.py:715] (5/8) Epoch 8, batch 17750, loss[loss=0.132, simple_loss=0.2005, pruned_loss=0.03176, over 4946.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03469, over 973247.20 frames.], batch size: 21, lr: 2.61e-04
2022-05-06 05:16:43,291 INFO [train.py:715] (5/8) Epoch 8, batch 17800, loss[loss=0.1118, simple_loss=0.1834, pruned_loss=0.02012, over 4772.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03524, over 972867.99 frames.], batch size: 12, lr: 2.61e-04
2022-05-06 05:17:23,945 INFO [train.py:715] (5/8) Epoch 8, batch 17850, loss[loss=0.147, simple_loss=0.2205, pruned_loss=0.03671, over 4957.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03524, over 972823.80 frames.], batch size: 35, lr: 2.61e-04
2022-05-06 05:18:04,812 INFO [train.py:715] (5/8) Epoch 8, batch 17900, loss[loss=0.1351, simple_loss=0.2066, pruned_loss=0.03178, over 4963.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03469, over 972547.63 frames.], batch size: 24, lr: 2.61e-04
2022-05-06 05:18:46,218 INFO [train.py:715] (5/8) Epoch 8, batch 17950, loss[loss=0.1513, simple_loss=0.2293, pruned_loss=0.03665, over 4882.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.0356, over 972649.16 frames.], batch size: 22, lr: 2.61e-04
2022-05-06 05:19:26,621 INFO [train.py:715] (5/8) Epoch 8, batch 18000, loss[loss=0.1226, simple_loss=0.1903, pruned_loss=0.02744, over 4810.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03626, over 972843.69 frames.], batch size: 21, lr: 2.61e-04
2022-05-06 05:19:26,621 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 05:19:36,397 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1919, pruned_loss=0.01138, over 914524.00 frames.
2022-05-06 05:20:17,013 INFO [train.py:715] (5/8) Epoch 8, batch 18050, loss[loss=0.1141, simple_loss=0.1814, pruned_loss=0.02343, over 4863.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2155, pruned_loss=0.03616, over 972077.89 frames.], batch size: 32, lr: 2.60e-04
2022-05-06 05:20:59,051 INFO [train.py:715] (5/8) Epoch 8, batch 18100, loss[loss=0.1381, simple_loss=0.2209, pruned_loss=0.02764, over 4800.00 frames.], tot_loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03618, over 971238.19 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:21:40,102 INFO [train.py:715] (5/8) Epoch 8, batch 18150, loss[loss=0.1359, simple_loss=0.2035, pruned_loss=0.03413, over 4926.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03621, over 971499.27 frames.], batch size: 23, lr: 2.60e-04
2022-05-06 05:22:21,015 INFO [train.py:715] (5/8) Epoch 8, batch 18200, loss[loss=0.1405, simple_loss=0.2205, pruned_loss=0.03019, over 4743.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.0362, over 971095.48 frames.], batch size: 19, lr: 2.60e-04
2022-05-06 05:23:02,792 INFO [train.py:715] (5/8) Epoch 8, batch 18250, loss[loss=0.1207, simple_loss=0.1948, pruned_loss=0.02329, over 4932.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2161, pruned_loss=0.03687, over 971033.09 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:23:43,816 INFO [train.py:715] (5/8) Epoch 8, batch 18300, loss[loss=0.1677, simple_loss=0.234, pruned_loss=0.05066, over 4787.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.0371, over 971069.34 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:24:25,289 INFO [train.py:715] (5/8) Epoch 8, batch 18350, loss[loss=0.1584, simple_loss=0.2302, pruned_loss=0.04334, over 4785.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03688, over 970722.69 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:25:06,143 INFO [train.py:715] (5/8) Epoch 8, batch 18400, loss[loss=0.1379, simple_loss=0.2126, pruned_loss=0.03158, over 4819.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03622, over 971602.94 frames.], batch size: 26, lr: 2.60e-04
2022-05-06 05:25:47,831 INFO [train.py:715] (5/8) Epoch 8, batch 18450, loss[loss=0.146, simple_loss=0.2236, pruned_loss=0.03426, over 4772.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03652, over 971420.74 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:26:28,558 INFO [train.py:715] (5/8) Epoch 8, batch 18500, loss[loss=0.1026, simple_loss=0.1748, pruned_loss=0.01525, over 4794.00 frames.], tot_loss[loss=0.1448, simple_loss=0.217, pruned_loss=0.03629, over 970431.11 frames.], batch size: 12, lr: 2.60e-04
2022-05-06 05:27:08,964 INFO [train.py:715] (5/8) Epoch 8, batch 18550, loss[loss=0.1518, simple_loss=0.2172, pruned_loss=0.04317, over 4929.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.0361, over 971530.55 frames.], batch size: 39, lr: 2.60e-04
2022-05-06 05:27:50,213 INFO [train.py:715] (5/8) Epoch 8, batch 18600, loss[loss=0.161, simple_loss=0.2255, pruned_loss=0.04827, over 4851.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03591, over 971461.46 frames.], batch size: 32, lr: 2.60e-04
2022-05-06 05:28:30,416 INFO [train.py:715] (5/8) Epoch 8, batch 18650, loss[loss=0.1555, simple_loss=0.2411, pruned_loss=0.03494, over 4924.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03596, over 971229.66 frames.], batch size: 29, lr: 2.60e-04
2022-05-06 05:29:09,921 INFO [train.py:715] (5/8) Epoch 8, batch 18700, loss[loss=0.1713, simple_loss=0.2394, pruned_loss=0.05162, over 4870.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03571, over 971713.33 frames.], batch size: 30, lr: 2.60e-04
2022-05-06 05:29:49,892 INFO [train.py:715] (5/8) Epoch 8, batch 18750, loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02806, over 4778.00 frames.], tot_loss[loss=0.144, simple_loss=0.2166, pruned_loss=0.03571, over 971732.99 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:30:30,984 INFO [train.py:715] (5/8) Epoch 8, batch 18800, loss[loss=0.1253, simple_loss=0.1994, pruned_loss=0.02565, over 4846.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03587, over 971611.30 frames.], batch size: 32, lr: 2.60e-04
2022-05-06 05:31:10,610 INFO [train.py:715] (5/8) Epoch 8, batch 18850, loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.03773, over 4938.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03563, over 971760.25 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:31:50,013 INFO [train.py:715] (5/8) Epoch 8, batch 18900, loss[loss=0.1478, simple_loss=0.2234, pruned_loss=0.0361, over 4885.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03579, over 972413.18 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:32:30,289 INFO [train.py:715] (5/8) Epoch 8, batch 18950, loss[loss=0.1108, simple_loss=0.189, pruned_loss=0.01632, over 4830.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03548, over 972785.64 frames.], batch size: 27, lr: 2.60e-04
2022-05-06 05:33:10,171 INFO [train.py:715] (5/8) Epoch 8, batch 19000, loss[loss=0.1293, simple_loss=0.2056, pruned_loss=0.02655, over 4866.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03515, over 972877.61 frames.], batch size: 22, lr: 2.60e-04
2022-05-06 05:33:50,105 INFO [train.py:715] (5/8) Epoch 8, batch 19050, loss[loss=0.1278, simple_loss=0.2166, pruned_loss=0.01946, over 4821.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2153, pruned_loss=0.0348, over 972885.63 frames.], batch size: 27, lr: 2.60e-04
2022-05-06 05:34:31,416 INFO [train.py:715] (5/8) Epoch 8, batch 19100, loss[loss=0.1393, simple_loss=0.2177, pruned_loss=0.03046, over 4793.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03497, over 972995.69 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:35:13,331 INFO [train.py:715] (5/8) Epoch 8, batch 19150, loss[loss=0.126, simple_loss=0.2052, pruned_loss=0.02342, over 4802.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03497, over 972725.79 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:35:55,001 INFO [train.py:715] (5/8) Epoch 8, batch 19200, loss[loss=0.1687, simple_loss=0.2358, pruned_loss=0.05082, over 4889.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03523, over 972227.73 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:36:35,258 INFO [train.py:715] (5/8) Epoch 8, batch 19250, loss[loss=0.1791, simple_loss=0.2414, pruned_loss=0.05841, over 4916.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03579, over 972304.98 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:37:17,450 INFO [train.py:715] (5/8) Epoch 8, batch 19300, loss[loss=0.1119, simple_loss=0.1904, pruned_loss=0.01663, over 4960.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03537, over 971916.23 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:37:58,604 INFO [train.py:715] (5/8) Epoch 8, batch 19350, loss[loss=0.1513, simple_loss=0.2269, pruned_loss=0.03785, over 4927.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03499, over 972367.68 frames.], batch size: 29, lr: 2.60e-04
2022-05-06 05:38:39,847 INFO [train.py:715] (5/8) Epoch 8, batch 19400, loss[loss=0.1531, simple_loss=0.2152, pruned_loss=0.04555, over 4977.00 frames.], tot_loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03449, over 972470.85 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:39:21,786 INFO [train.py:715] (5/8) Epoch 8, batch 19450, loss[loss=0.1316, simple_loss=0.2075, pruned_loss=0.02787, over 4860.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03474, over 972656.02 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:40:03,290 INFO [train.py:715] (5/8) Epoch 8, batch 19500, loss[loss=0.1441, simple_loss=0.2065, pruned_loss=0.04086, over 4932.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03477, over 973044.12 frames.], batch size: 23, lr: 2.60e-04
2022-05-06 05:40:44,581 INFO [train.py:715] (5/8) Epoch 8, batch 19550, loss[loss=0.1804, simple_loss=0.2477, pruned_loss=0.05654, over 4971.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2167, pruned_loss=0.03546, over 972548.29 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:41:25,033 INFO [train.py:715] (5/8) Epoch 8, batch 19600, loss[loss=0.1458, simple_loss=0.2162, pruned_loss=0.03774, over 4990.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2164, pruned_loss=0.03546, over 972132.95 frames.], batch size: 25, lr: 2.60e-04
2022-05-06 05:42:06,557 INFO [train.py:715] (5/8) Epoch 8, batch 19650, loss[loss=0.1362, simple_loss=0.2188, pruned_loss=0.02677, over 4901.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03543, over 971722.50 frames.], batch size: 29, lr: 2.60e-04
2022-05-06 05:42:47,225 INFO [train.py:715] (5/8) Epoch 8, batch 19700, loss[loss=0.1385, simple_loss=0.2067, pruned_loss=0.03516, over 4881.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03592, over 972319.90 frames.], batch size: 19, lr: 2.60e-04
2022-05-06 05:43:28,185 INFO [train.py:715] (5/8) Epoch 8, batch 19750, loss[loss=0.1387, simple_loss=0.2198, pruned_loss=0.02876, over 4756.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03528, over 972006.11 frames.], batch size: 19, lr: 2.60e-04
2022-05-06 05:44:09,856 INFO [train.py:715] (5/8) Epoch 8, batch 19800, loss[loss=0.1404, simple_loss=0.2115, pruned_loss=0.03465, over 4967.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2154, pruned_loss=0.03579, over 972152.51 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:44:50,899 INFO [train.py:715] (5/8) Epoch 8, batch 19850, loss[loss=0.1447, simple_loss=0.2188, pruned_loss=0.03531, over 4967.00 frames.], tot_loss[loss=0.143, simple_loss=0.2146, pruned_loss=0.03563, over 972008.01 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:45:31,215 INFO [train.py:715] (5/8) Epoch 8, batch 19900, loss[loss=0.1509, simple_loss=0.2169, pruned_loss=0.04244, over 4971.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03533, over 972141.16 frames.], batch size: 31, lr: 2.60e-04
2022-05-06 05:46:10,974 INFO [train.py:715] (5/8) Epoch 8, batch 19950, loss[loss=0.1491, simple_loss=0.2151, pruned_loss=0.04155, over 4867.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03561, over 973091.33 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:46:51,595 INFO [train.py:715] (5/8) Epoch 8, batch 20000, loss[loss=0.1739, simple_loss=0.2579, pruned_loss=0.04496, over 4952.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2149, pruned_loss=0.03559, over 973386.06 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:47:32,112 INFO [train.py:715] (5/8) Epoch 8, batch 20050, loss[loss=0.1502, simple_loss=0.2187, pruned_loss=0.04083, over 4841.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03533, over 973367.22 frames.], batch size: 30, lr: 2.60e-04
2022-05-06 05:48:12,623 INFO [train.py:715] (5/8) Epoch 8, batch 20100, loss[loss=0.1296, simple_loss=0.1997, pruned_loss=0.02977, over 4888.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03546, over 973596.40 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:48:53,760 INFO [train.py:715] (5/8) Epoch 8, batch 20150, loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.0327, over 4947.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03478, over 973652.02 frames.], batch size: 35, lr: 2.60e-04
2022-05-06 05:49:34,573 INFO [train.py:715] (5/8) Epoch 8, batch 20200, loss[loss=0.1636, simple_loss=0.2313, pruned_loss=0.04793, over 4686.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03489, over 973546.48 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:50:15,438 INFO [train.py:715] (5/8) Epoch 8, batch 20250, loss[loss=0.1388, simple_loss=0.2107, pruned_loss=0.03339, over 4821.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03531, over 973295.53 frames.], batch size: 25, lr: 2.60e-04
2022-05-06 05:50:56,711 INFO [train.py:715] (5/8) Epoch 8, batch 20300, loss[loss=0.1333, simple_loss=0.217, pruned_loss=0.02477, over 4801.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03524, over 973010.65 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:51:37,708 INFO [train.py:715] (5/8) Epoch 8, batch 20350, loss[loss=0.14, simple_loss=0.2264, pruned_loss=0.02677, over 4907.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.0351, over 972681.59 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 05:52:18,257 INFO [train.py:715] (5/8) Epoch 8, batch 20400, loss[loss=0.1605, simple_loss=0.2366, pruned_loss=0.04217, over 4940.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03538, over 972135.09 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 05:52:58,519 INFO [train.py:715] (5/8) Epoch 8, batch 20450, loss[loss=0.142, simple_loss=0.2115, pruned_loss=0.0362, over 4781.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03544, over 972765.13 frames.], batch size: 12, lr: 2.59e-04
2022-05-06 05:53:39,595 INFO [train.py:715] (5/8) Epoch 8, batch 20500, loss[loss=0.1428, simple_loss=0.211, pruned_loss=0.03727, over 4974.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03544, over 972409.87 frames.], batch size: 33, lr: 2.59e-04
2022-05-06 05:54:20,095 INFO [train.py:715] (5/8) Epoch 8, batch 20550, loss[loss=0.1289, simple_loss=0.202, pruned_loss=0.02787, over 4909.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03583, over 972694.81 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 05:55:00,455 INFO [train.py:715] (5/8) Epoch 8, batch 20600, loss[loss=0.1523, simple_loss=0.2283, pruned_loss=0.03817, over 4990.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03576, over 973273.79 frames.], batch size: 16, lr: 2.59e-04
2022-05-06 05:55:41,415 INFO [train.py:715] (5/8) Epoch 8, batch 20650, loss[loss=0.1568, simple_loss=0.2282, pruned_loss=0.04269, over 4904.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03584, over 973601.85 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 05:56:22,562 INFO [train.py:715] (5/8) Epoch 8, batch 20700, loss[loss=0.1529, simple_loss=0.2225, pruned_loss=0.04167, over 4975.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03593, over 973885.97 frames.], batch size: 28, lr: 2.59e-04
2022-05-06 05:57:02,761 INFO [train.py:715] (5/8) Epoch 8, batch 20750, loss[loss=0.1356, simple_loss=0.2057, pruned_loss=0.03274, over 4990.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03572, over 973155.50 frames.], batch size: 25, lr: 2.59e-04
2022-05-06 05:57:42,971 INFO [train.py:715] (5/8) Epoch 8, batch 20800, loss[loss=0.1555, simple_loss=0.2284, pruned_loss=0.04134, over 4987.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03576, over 972543.00 frames.], batch size: 26, lr: 2.59e-04
2022-05-06 05:58:24,022 INFO [train.py:715] (5/8) Epoch 8, batch 20850, loss[loss=0.1762, simple_loss=0.2323, pruned_loss=0.05998, over 4755.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03517, over 972070.93 frames.], batch size: 16, lr: 2.59e-04
2022-05-06 05:59:04,425 INFO [train.py:715] (5/8) Epoch 8, batch 20900, loss[loss=0.1427, simple_loss=0.212, pruned_loss=0.03674, over 4888.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03519, over 972078.48 frames.], batch size: 22, lr: 2.59e-04
2022-05-06 05:59:43,027 INFO [train.py:715] (5/8) Epoch 8, batch 20950, loss[loss=0.1528, simple_loss=0.2108, pruned_loss=0.04746, over 4950.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03544, over 971748.83 frames.], batch size: 39, lr: 2.59e-04
2022-05-06 06:00:22,703 INFO [train.py:715] (5/8) Epoch 8, batch 21000, loss[loss=0.1265, simple_loss=0.1948, pruned_loss=0.02911, over 4771.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03594, over 971605.36 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 06:00:22,704 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 06:00:32,254 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 06:01:12,647 INFO [train.py:715] (5/8) Epoch 8, batch 21050, loss[loss=0.1164, simple_loss=0.1937, pruned_loss=0.0195, over 4936.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03572, over 972741.30 frames.], batch size: 29, lr: 2.59e-04
2022-05-06 06:01:52,989 INFO [train.py:715] (5/8) Epoch 8, batch 21100, loss[loss=0.1678, simple_loss=0.2468, pruned_loss=0.04441, over 4881.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03578, over 972181.59 frames.], batch size: 32, lr: 2.59e-04
2022-05-06 06:02:31,461 INFO [train.py:715] (5/8) Epoch 8, batch 21150, loss[loss=0.1588, simple_loss=0.2265, pruned_loss=0.04548, over 4849.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03533, over 972045.38 frames.], batch size: 34, lr: 2.59e-04
2022-05-06 06:03:10,261 INFO [train.py:715] (5/8) Epoch 8, batch 21200, loss[loss=0.1546, simple_loss=0.2241, pruned_loss=0.04249, over 4781.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.0358, over 972278.55 frames.], batch size: 14, lr: 2.59e-04
2022-05-06 06:03:49,969 INFO [train.py:715] (5/8) Epoch 8, batch 21250, loss[loss=0.1383, simple_loss=0.2239, pruned_loss=0.02636, over 4944.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03509, over 972868.48 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:04:29,232 INFO [train.py:715] (5/8) Epoch 8, batch 21300, loss[loss=0.1369, simple_loss=0.2115, pruned_loss=0.03117, over 4774.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03509, over 972439.81 frames.], batch size: 14, lr: 2.59e-04
2022-05-06 06:05:07,760 INFO [train.py:715] (5/8) Epoch 8, batch 21350, loss[loss=0.1286, simple_loss=0.2, pruned_loss=0.02857, over 4814.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03439, over 972949.39 frames.], batch size: 25, lr: 2.59e-04
2022-05-06 06:05:47,407 INFO [train.py:715] (5/8) Epoch 8, batch 21400, loss[loss=0.1558, simple_loss=0.2034, pruned_loss=0.05403, over 4804.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03473, over 973019.15 frames.], batch size: 12, lr: 2.59e-04
2022-05-06 06:06:27,493 INFO [train.py:715] (5/8) Epoch 8, batch 21450, loss[loss=0.135, simple_loss=0.2167, pruned_loss=0.02665, over 4904.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.03503, over 972359.69 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:07:06,787 INFO [train.py:715] (5/8) Epoch 8, batch 21500, loss[loss=0.1348, simple_loss=0.2035, pruned_loss=0.03305, over 4788.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.0351, over 972134.03 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:07:45,791 INFO [train.py:715] (5/8) Epoch 8, batch 21550, loss[loss=0.1317, simple_loss=0.2013, pruned_loss=0.03106, over 4906.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03571, over 972577.59 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:08:25,813 INFO [train.py:715] (5/8) Epoch 8, batch 21600, loss[loss=0.1178, simple_loss=0.1865, pruned_loss=0.02451, over 4774.00 frames.], tot_loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03585, over 973291.54 frames.], batch size: 12, lr: 2.59e-04
2022-05-06 06:09:04,794 INFO [train.py:715] (5/8) Epoch 8, batch 21650, loss[loss=0.1508, simple_loss=0.2325, pruned_loss=0.03453, over 4972.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03583, over 972773.37 frames.], batch size: 28, lr: 2.59e-04
2022-05-06 06:09:43,493 INFO [train.py:715] (5/8) Epoch 8, batch 21700, loss[loss=0.1348, simple_loss=0.2065, pruned_loss=0.03149, over 4834.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03577, over 972218.35 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:10:23,860 INFO [train.py:715] (5/8) Epoch 8, batch 21750, loss[loss=0.1611, simple_loss=0.2265, pruned_loss=0.04786, over 4933.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03588, over 973218.34 frames.], batch size: 29, lr: 2.59e-04
2022-05-06 06:11:03,699 INFO [train.py:715] (5/8) Epoch 8, batch 21800, loss[loss=0.1717, simple_loss=0.2462, pruned_loss=0.04857, over 4974.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03599, over 973574.05 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:11:42,812 INFO [train.py:715] (5/8) Epoch 8, batch 21850, loss[loss=0.1313, simple_loss=0.2032, pruned_loss=0.0297, over 4965.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03563, over 973581.79 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:12:21,177 INFO [train.py:715] (5/8) Epoch 8, batch 21900, loss[loss=0.1308, simple_loss=0.2111, pruned_loss=0.02519, over 4796.00 frames.], tot_loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.0357, over 972914.93 frames.], batch size: 24, lr: 2.59e-04
2022-05-06 06:13:00,616 INFO [train.py:715] (5/8) Epoch 8, batch 21950, loss[loss=0.1271, simple_loss=0.2137, pruned_loss=0.02028, over 4869.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03563, over 973610.95 frames.], batch size: 20, lr: 2.59e-04
2022-05-06 06:13:39,698 INFO [train.py:715] (5/8) Epoch 8, batch 22000, loss[loss=0.126, simple_loss=0.2078, pruned_loss=0.02208, over 4931.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03523, over 973931.22 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:14:18,327 INFO [train.py:715] (5/8) Epoch 8, batch 22050, loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02949, over 4921.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03482, over 973378.01 frames.], batch size: 29, lr: 2.59e-04
2022-05-06 06:14:58,045 INFO [train.py:715] (5/8) Epoch 8, batch 22100, loss[loss=0.1401, simple_loss=0.2209, pruned_loss=0.02963, over 4837.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03484, over 972494.99 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:15:37,420 INFO [train.py:715] (5/8) Epoch 8, batch 22150, loss[loss=0.1367, simple_loss=0.2142, pruned_loss=0.02957, over 4948.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.03528, over 972768.13 frames.], batch size: 29, lr: 2.59e-04
2022-05-06 06:16:16,517 INFO [train.py:715] (5/8) Epoch 8, batch 22200, loss[loss=0.1542, simple_loss=0.2226, pruned_loss=0.04289, over 4764.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03555, over 973071.13 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 06:16:55,348 INFO [train.py:715] (5/8) Epoch 8, batch 22250, loss[loss=0.1782, simple_loss=0.261, pruned_loss=0.04773, over 4799.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.03512, over 972935.96 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:17:34,566 INFO [train.py:715] (5/8) Epoch 8, batch 22300, loss[loss=0.1674, simple_loss=0.2363, pruned_loss=0.04922, over 4774.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2172, pruned_loss=0.03553, over 972623.51 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:18:13,308 INFO [train.py:715] (5/8) Epoch 8, batch 22350, loss[loss=0.1506, simple_loss=0.2264, pruned_loss=0.0374, over 4841.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2172, pruned_loss=0.03581, over 972498.81 frames.], batch size: 13, lr: 2.59e-04
2022-05-06 06:18:51,905 INFO [train.py:715] (5/8) Epoch 8, batch 22400, loss[loss=0.1522, simple_loss=0.2237, pruned_loss=0.0403, over 4752.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2169, pruned_loss=0.03586, over 972496.96 frames.], batch size: 14, lr: 2.59e-04
2022-05-06 06:19:31,234 INFO [train.py:715] (5/8) Epoch 8, batch 22450, loss[loss=0.1298, simple_loss=0.2027, pruned_loss=0.02841, over 4955.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03559, over 972465.21 frames.], batch size: 39, lr: 2.59e-04
2022-05-06 06:20:10,735 INFO [train.py:715] (5/8) Epoch 8, batch 22500, loss[loss=0.1198, simple_loss=0.1891, pruned_loss=0.02523, over 4754.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03548, over 972246.55 frames.], batch size: 16, lr: 2.59e-04
2022-05-06 06:20:49,338 INFO [train.py:715] (5/8) Epoch 8, batch 22550, loss[loss=0.1541, simple_loss=0.2199, pruned_loss=0.04414, over 4862.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.0354, over 972240.20 frames.], batch size: 20, lr: 2.59e-04
2022-05-06 06:21:28,253 INFO [train.py:715] (5/8) Epoch 8, batch 22600, loss[loss=0.1414, simple_loss=0.2161, pruned_loss=0.0333, over 4828.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.0357, over 972800.66 frames.], batch size: 27, lr: 2.59e-04
2022-05-06 06:22:07,733 INFO [train.py:715] (5/8) Epoch 8, batch 22650, loss[loss=0.1199, simple_loss=0.1974, pruned_loss=0.02125, over 4988.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03538, over 972074.25 frames.], batch size: 28, lr: 2.58e-04
2022-05-06 06:22:46,456 INFO [train.py:715] (5/8) Epoch 8, batch 22700, loss[loss=0.1326, simple_loss=0.2149, pruned_loss=0.02513, over 4878.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03569, over 971212.68 frames.], batch size: 20, lr: 2.58e-04
2022-05-06 06:23:24,776 INFO [train.py:715] (5/8) Epoch 8, batch 22750, loss[loss=0.16, simple_loss=0.2274, pruned_loss=0.04627, over 4771.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03602, over 971652.34 frames.], batch size: 14, lr: 2.58e-04
2022-05-06 06:24:04,593 INFO [train.py:715] (5/8) Epoch 8, batch 22800, loss[loss=0.1272, simple_loss=0.2034, pruned_loss=0.02549, over 4823.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03509, over 972176.43 frames.], batch size: 26, lr: 2.58e-04
2022-05-06 06:24:43,767 INFO [train.py:715] (5/8) Epoch 8, batch 22850, loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03472, over 4980.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03514, over 972838.11 frames.], batch size: 35, lr: 2.58e-04
2022-05-06 06:25:22,841 INFO [train.py:715] (5/8) Epoch 8, batch 22900, loss[loss=0.1437, simple_loss=0.2184, pruned_loss=0.03455, over 4771.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03562, over 972587.24 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:26:01,956 INFO [train.py:715] (5/8) Epoch 8, batch 22950, loss[loss=0.153, simple_loss=0.2335, pruned_loss=0.03622, over 4908.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03618, over 973916.45 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:26:41,733 INFO [train.py:715] (5/8) Epoch 8, batch 23000, loss[loss=0.1482, simple_loss=0.2208, pruned_loss=0.03776, over 4893.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03587, over 973091.41 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:27:20,528 INFO [train.py:715] (5/8) Epoch 8, batch 23050, loss[loss=0.1651, simple_loss=0.2363, pruned_loss=0.0469, over 4935.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03546, over 972880.11 frames.], batch size: 39, lr: 2.58e-04
2022-05-06 06:27:59,220 INFO [train.py:715] (5/8) Epoch 8, batch 23100, loss[loss=0.1414, simple_loss=0.2194, pruned_loss=0.03174, over 4944.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03533, over 973072.70 frames.], batch size: 21, lr: 2.58e-04
2022-05-06 06:28:39,376 INFO [train.py:715] (5/8) Epoch 8, batch 23150, loss[loss=0.135, simple_loss=0.2069, pruned_loss=0.03156, over 4977.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03559, over 972809.48 frames.], batch size: 28, lr: 2.58e-04
2022-05-06 06:29:18,752 INFO [train.py:715] (5/8) Epoch 8, batch 23200, loss[loss=0.1597, simple_loss=0.2393, pruned_loss=0.04001, over 4974.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03622, over 973358.92 frames.], batch size: 24, lr: 2.58e-04
2022-05-06 06:29:57,395 INFO [train.py:715] (5/8) Epoch 8, batch 23250, loss[loss=0.1344, simple_loss=0.2049, pruned_loss=0.03191, over 4987.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03581, over 972518.29 frames.], batch size: 28, lr: 2.58e-04
2022-05-06 06:30:36,512 INFO [train.py:715] (5/8) Epoch 8, batch 23300, loss[loss=0.1414, simple_loss=0.2174, pruned_loss=0.03272, over 4801.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03585, over 972575.54 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:31:16,260 INFO [train.py:715] (5/8) Epoch 8, batch 23350, loss[loss=0.1558, simple_loss=0.2236, pruned_loss=0.044, over 4748.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03643, over 972879.93 frames.], batch size: 16, lr: 2.58e-04
2022-05-06 06:31:55,023 INFO [train.py:715] (5/8) Epoch 8, batch 23400, loss[loss=0.1422, simple_loss=0.211, pruned_loss=0.03674, over 4850.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03568, over 972589.92 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:32:33,887 INFO [train.py:715] (5/8) Epoch 8, batch 23450, loss[loss=0.16, simple_loss=0.2151, pruned_loss=0.05244, over 4828.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03594, over 972979.96 frames.], batch size: 30, lr: 2.58e-04
2022-05-06 06:33:13,363 INFO [train.py:715] (5/8) Epoch 8, batch 23500, loss[loss=0.1125, simple_loss=0.1855, pruned_loss=0.01976, over 4858.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03553, over 973432.01 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:33:52,529 INFO [train.py:715] (5/8) Epoch 8, batch 23550, loss[loss=0.168, simple_loss=0.244, pruned_loss=0.04597, over 4844.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2165, pruned_loss=0.03547, over 972816.35 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:34:31,316 INFO [train.py:715] (5/8) Epoch 8, batch 23600, loss[loss=0.1255, simple_loss=0.1963, pruned_loss=0.02732, over 4919.00 frames.], tot_loss[loss=0.1432, simple_loss=0.216, pruned_loss=0.03517, over 972844.46 frames.], batch size: 29, lr: 2.58e-04
2022-05-06 06:35:10,239 INFO [train.py:715] (5/8) Epoch 8, batch 23650, loss[loss=0.1687, simple_loss=0.2381, pruned_loss=0.04964, over 4870.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03542, over 972923.96 frames.], batch size: 20, lr: 2.58e-04
2022-05-06 06:35:50,045 INFO [train.py:715] (5/8) Epoch 8, batch 23700, loss[loss=0.1512, simple_loss=0.2196, pruned_loss=0.04144, over 4976.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03609, over 973273.84 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:36:28,663 INFO [train.py:715] (5/8) Epoch 8, batch 23750, loss[loss=0.1331, simple_loss=0.2122, pruned_loss=0.02698, over 4929.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03604, over 973552.82 frames.], batch size: 23, lr: 2.58e-04
2022-05-06 06:37:07,511 INFO [train.py:715] (5/8) Epoch 8, batch 23800, loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.04126, over 4765.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03596, over 973687.62 frames.], batch size: 18, lr: 2.58e-04
2022-05-06 06:37:46,980 INFO [train.py:715] (5/8) Epoch 8, batch 23850, loss[loss=0.1258, simple_loss=0.2016, pruned_loss=0.02499, over 4815.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03576, over 973962.58 frames.], batch size: 12, lr: 2.58e-04
2022-05-06 06:38:26,639 INFO [train.py:715] (5/8) Epoch 8, batch 23900, loss[loss=0.124, simple_loss=0.2026, pruned_loss=0.02266, over 4694.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03541, over 972857.14 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:39:05,504 INFO [train.py:715] (5/8) Epoch 8, batch 23950, loss[loss=0.1235, simple_loss=0.2043, pruned_loss=0.02135, over 4840.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03569, over 972318.99 frames.], batch size: 20, lr: 2.58e-04
2022-05-06 06:39:44,887 INFO [train.py:715] (5/8) Epoch 8, batch 24000, loss[loss=0.1528, simple_loss=0.2282, pruned_loss=0.03868, over 4922.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03582, over 971837.59 frames.], batch size: 23, lr: 2.58e-04
2022-05-06 06:39:44,887 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 06:39:54,530 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1075, simple_loss=0.192, pruned_loss=0.01146, over 914524.00 frames.
2022-05-06 06:40:33,718 INFO [train.py:715] (5/8) Epoch 8, batch 24050, loss[loss=0.1318, simple_loss=0.2142, pruned_loss=0.02471, over 4907.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.03583, over 972803.52 frames.], batch size: 18, lr: 2.58e-04
2022-05-06 06:41:13,150 INFO [train.py:715] (5/8) Epoch 8, batch 24100, loss[loss=0.1724, simple_loss=0.24, pruned_loss=0.05245, over 4829.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03604, over 973465.17 frames.], batch size: 30, lr: 2.58e-04
2022-05-06 06:41:52,113 INFO [train.py:715] (5/8) Epoch 8, batch 24150, loss[loss=0.1171, simple_loss=0.1952, pruned_loss=0.01951, over 4945.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03598, over 973353.23 frames.], batch size: 24, lr: 2.58e-04
2022-05-06 06:42:31,048 INFO [train.py:715] (5/8) Epoch 8, batch 24200, loss[loss=0.1229, simple_loss=0.1995, pruned_loss=0.02317, over 4812.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03577, over 973544.07 frames.], batch size: 21, lr: 2.58e-04
2022-05-06 06:43:11,237 INFO [train.py:715] (5/8) Epoch 8, batch 24250, loss[loss=0.1507, simple_loss=0.2197, pruned_loss=0.04088, over 4840.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03589, over 973883.33 frames.], batch size: 20, lr: 2.58e-04
2022-05-06 06:43:50,602 INFO [train.py:715] (5/8) Epoch 8, batch 24300, loss[loss=0.139, simple_loss=0.2282, pruned_loss=0.02494, over 4835.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03602, over 973546.17 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:44:29,315 INFO [train.py:715] (5/8) Epoch 8, batch 24350, loss[loss=0.129, simple_loss=0.2141, pruned_loss=0.02199, over 4765.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.0356, over 973290.25 frames.], batch size: 12, lr: 2.58e-04
2022-05-06 06:45:08,117 INFO [train.py:715] (5/8) Epoch 8, batch 24400, loss[loss=0.1375, simple_loss=0.2169, pruned_loss=0.02901, over 4896.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03568, over 973187.27 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:45:47,152 INFO [train.py:715] (5/8) Epoch 8, batch 24450, loss[loss=0.1343, simple_loss=0.2047, pruned_loss=0.03196, over 4733.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.0352, over 972326.19 frames.], batch size: 16, lr: 2.58e-04
2022-05-06 06:46:26,136 INFO [train.py:715] (5/8) Epoch 8, batch 24500, loss[loss=0.1658, simple_loss=0.2456, pruned_loss=0.04296, over 4767.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03493, over 973276.49 frames.], batch size: 14, lr: 2.58e-04
2022-05-06 06:47:04,983 INFO [train.py:715] (5/8) Epoch 8, batch 24550, loss[loss=0.1321, simple_loss=0.1942, pruned_loss=0.03497, over 4879.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03518, over 973723.53 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:47:44,926 INFO [train.py:715] (5/8) Epoch 8, batch 24600, loss[loss=0.1655, simple_loss=0.2288, pruned_loss=0.05115, over 4698.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03532, over 973525.32 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:48:24,234 INFO [train.py:715] (5/8) Epoch 8, batch 24650, loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03767, over 4762.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03535, over 973458.65 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:49:02,873 INFO [train.py:715] (5/8) Epoch 8, batch 24700, loss[loss=0.1218, simple_loss=0.202, pruned_loss=0.02081, over 4791.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03537, over 973166.17 frames.], batch size: 13, lr: 2.58e-04
2022-05-06 06:49:42,048 INFO [train.py:715] (5/8) Epoch 8, batch 24750, loss[loss=0.1369, simple_loss=0.2042, pruned_loss=0.03483, over 4846.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2158, pruned_loss=0.03601, over 972832.58 frames.], batch size: 30, lr: 2.58e-04
2022-05-06 06:50:21,621 INFO [train.py:715] (5/8) Epoch 8, batch 24800, loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03376, over 4901.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03656, over 973501.37 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:51:00,472 INFO [train.py:715] (5/8) Epoch 8, batch 24850, loss[loss=0.1414, simple_loss=0.2195, pruned_loss=0.03168, over 4846.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03637, over 973522.04 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:51:39,140 INFO [train.py:715] (5/8) Epoch 8, batch 24900, loss[loss=0.1678, simple_loss=0.2396, pruned_loss=0.048, over 4840.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03587, over 973138.46 frames.], batch size: 30, lr: 2.58e-04
2022-05-06 06:52:19,142 INFO [train.py:715] (5/8) Epoch 8, batch 24950, loss[loss=0.1359, simple_loss=0.2108, pruned_loss=0.03054, over 4934.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.0358, over 973441.29 frames.], batch size: 29, lr: 2.58e-04
2022-05-06 06:52:58,629 INFO [train.py:715] (5/8) Epoch 8, batch 25000, loss[loss=0.1496, simple_loss=0.212, pruned_loss=0.04359, over 4843.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03541, over 973912.82 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 06:53:37,562 INFO [train.py:715] (5/8) Epoch 8, batch 25050, loss[loss=0.1406, simple_loss=0.2166, pruned_loss=0.03228, over 4886.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03606, over 973284.98 frames.], batch size: 22, lr: 2.57e-04
2022-05-06 06:54:16,390 INFO [train.py:715] (5/8) Epoch 8, batch 25100, loss[loss=0.1332, simple_loss=0.1953, pruned_loss=0.03561, over 4784.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03597, over 973537.33 frames.], batch size: 14, lr: 2.57e-04
2022-05-06 06:54:55,808 INFO [train.py:715] (5/8) Epoch 8, batch 25150, loss[loss=0.1465, simple_loss=0.2143, pruned_loss=0.03939, over 4788.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2141, pruned_loss=0.0353, over 972731.09 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 06:55:34,831 INFO [train.py:715] (5/8) Epoch 8, batch 25200, loss[loss=0.1671, simple_loss=0.2386, pruned_loss=0.0478, over 4964.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03505, over 972326.79 frames.], batch size: 40, lr: 2.57e-04
2022-05-06 06:56:13,818 INFO [train.py:715] (5/8) Epoch 8, batch 25250, loss[loss=0.1818, simple_loss=0.239, pruned_loss=0.06223, over 4792.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03525, over 972713.73 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 06:56:53,389 INFO [train.py:715] (5/8) Epoch 8, batch 25300, loss[loss=0.1436, simple_loss=0.2098, pruned_loss=0.03865, over 4934.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03565, over 971938.18 frames.], batch size: 29, lr: 2.57e-04
2022-05-06 06:57:32,352 INFO [train.py:715] (5/8) Epoch 8, batch 25350, loss[loss=0.1516, simple_loss=0.2185, pruned_loss=0.04232, over 4879.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03586, over 972193.06 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 06:58:11,168 INFO [train.py:715] (5/8) Epoch 8, batch 25400, loss[loss=0.1357, simple_loss=0.2141, pruned_loss=0.02865, over 4789.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03573, over 971091.97 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 06:58:50,228 INFO [train.py:715] (5/8) Epoch 8, batch 25450, loss[loss=0.1402, simple_loss=0.2117, pruned_loss=0.03434, over 4923.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03587, over 971023.26 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 06:59:30,372 INFO [train.py:715] (5/8) Epoch 8, batch 25500, loss[loss=0.1557, simple_loss=0.231, pruned_loss=0.04019, over 4896.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.0353, over 972123.55 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:00:12,394 INFO [train.py:715] (5/8) Epoch 8, batch 25550, loss[loss=0.1472, simple_loss=0.2203, pruned_loss=0.03702, over 4877.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03529, over 971410.46 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:00:51,652 INFO [train.py:715] (5/8) Epoch 8, batch 25600, loss[loss=0.1482, simple_loss=0.2364, pruned_loss=0.02999, over 4866.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.0353, over 971397.63 frames.], batch size: 20, lr: 2.57e-04
2022-05-06 07:01:30,733 INFO [train.py:715] (5/8) Epoch 8, batch 25650, loss[loss=0.1494, simple_loss=0.2173, pruned_loss=0.04077, over 4853.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03499, over 971379.69 frames.], batch size: 20, lr: 2.57e-04
2022-05-06 07:02:09,696 INFO [train.py:715] (5/8) Epoch 8, batch 25700, loss[loss=0.1604, simple_loss=0.2309, pruned_loss=0.04491, over 4956.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03509, over 971613.62 frames.], batch size: 35, lr: 2.57e-04
2022-05-06 07:02:48,863 INFO [train.py:715] (5/8) Epoch 8, batch 25750, loss[loss=0.17, simple_loss=0.2391, pruned_loss=0.05046, over 4790.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03477, over 972323.99 frames.], batch size: 23, lr: 2.57e-04
2022-05-06 07:03:27,690 INFO [train.py:715] (5/8) Epoch 8, batch 25800, loss[loss=0.1567, simple_loss=0.2319, pruned_loss=0.04077, over 4776.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03474, over 972187.07 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:04:06,653 INFO [train.py:715] (5/8) Epoch 8, batch 25850, loss[loss=0.1426, simple_loss=0.1953, pruned_loss=0.04492, over 4878.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03479, over 972351.84 frames.], batch size: 22, lr: 2.57e-04
2022-05-06 07:04:45,937 INFO [train.py:715] (5/8) Epoch 8, batch 25900, loss[loss=0.1433, simple_loss=0.2245, pruned_loss=0.031, over 4882.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03531, over 972621.56 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:05:24,604 INFO [train.py:715] (5/8) Epoch 8, batch 25950, loss[loss=0.1261, simple_loss=0.1967, pruned_loss=0.02773, over 4839.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03506, over 973001.82 frames.], batch size: 13, lr: 2.57e-04
2022-05-06 07:06:03,739 INFO [train.py:715] (5/8) Epoch 8, batch 26000, loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02957, over 4690.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03555, over 972335.04 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:06:42,906 INFO [train.py:715] (5/8) Epoch 8, batch 26050, loss[loss=0.1404, simple_loss=0.2149, pruned_loss=0.03291, over 4984.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2149, pruned_loss=0.03578, over 971433.89 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:07:21,668 INFO [train.py:715] (5/8) Epoch 8, batch 26100, loss[loss=0.1403, simple_loss=0.2106, pruned_loss=0.035, over 4918.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2147, pruned_loss=0.03556, over 972044.96 frames.], batch size: 23, lr: 2.57e-04
2022-05-06 07:08:01,299 INFO [train.py:715] (5/8) Epoch 8, batch 26150, loss[loss=0.1467, simple_loss=0.2004, pruned_loss=0.04653, over 4839.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03549, over 971934.06 frames.], batch size: 13, lr: 2.57e-04
2022-05-06 07:08:40,493 INFO [train.py:715] (5/8) Epoch 8, batch 26200, loss[loss=0.1093, simple_loss=0.1806, pruned_loss=0.01897, over 4698.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03543, over 971845.31 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:09:19,621 INFO [train.py:715] (5/8) Epoch 8, batch 26250, loss[loss=0.1353, simple_loss=0.1961, pruned_loss=0.03727, over 4963.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03528, over 971781.47 frames.], batch size: 35, lr: 2.57e-04
2022-05-06 07:09:57,935 INFO [train.py:715] (5/8) Epoch 8, batch 26300, loss[loss=0.153, simple_loss=0.2267, pruned_loss=0.0397, over 4784.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03541, over 971487.19 frames.], batch size: 14, lr: 2.57e-04
2022-05-06 07:10:37,571 INFO [train.py:715] (5/8) Epoch 8, batch 26350, loss[loss=0.1566, simple_loss=0.2211, pruned_loss=0.04609, over 4897.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03575, over 971333.41 frames.], batch size: 32, lr: 2.57e-04
2022-05-06 07:11:16,885 INFO [train.py:715] (5/8) Epoch 8, batch 26400, loss[loss=0.1241, simple_loss=0.2037, pruned_loss=0.02221, over 4724.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03566, over 971565.07 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:11:55,836 INFO [train.py:715] (5/8) Epoch 8, batch 26450, loss[loss=0.1192, simple_loss=0.1918, pruned_loss=0.02335, over 4846.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2167, pruned_loss=0.0359, over 971961.86 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:12:34,670 INFO [train.py:715] (5/8) Epoch 8, batch 26500, loss[loss=0.1558, simple_loss=0.2205, pruned_loss=0.04556, over 4742.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.0361, over 972163.81 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:13:13,272 INFO [train.py:715] (5/8) Epoch 8, batch 26550, loss[loss=0.1565, simple_loss=0.227, pruned_loss=0.04299, over 4815.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03566, over 972742.26 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:13:52,654 INFO [train.py:715] (5/8) Epoch 8, batch 26600, loss[loss=0.1413, simple_loss=0.2191, pruned_loss=0.03175, over 4756.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03564, over 973223.86 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:14:30,714 INFO [train.py:715] (5/8) Epoch 8, batch 26650, loss[loss=0.16, simple_loss=0.2353, pruned_loss=0.04235, over 4774.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.0358, over 973344.38 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 07:15:10,077 INFO [train.py:715] (5/8) Epoch 8, batch 26700, loss[loss=0.1548, simple_loss=0.2204, pruned_loss=0.04459, over 4804.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03503, over 972611.19 frames.], batch size: 21, lr: 2.57e-04
2022-05-06 07:15:49,151 INFO [train.py:715] (5/8) Epoch 8, batch 26750, loss[loss=0.1414, simple_loss=0.2196, pruned_loss=0.03165, over 4833.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03533, over 973200.67 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:16:27,933 INFO [train.py:715] (5/8) Epoch 8, batch 26800, loss[loss=0.1607, simple_loss=0.2367, pruned_loss=0.04234, over 4773.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.0352, over 972471.51 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:17:07,165 INFO [train.py:715] (5/8) Epoch 8, batch 26850, loss[loss=0.1693, simple_loss=0.2324, pruned_loss=0.05307, over 4984.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03511, over 972079.38 frames.], batch size: 39, lr: 2.57e-04
2022-05-06 07:17:46,412 INFO [train.py:715] (5/8) Epoch 8, batch 26900, loss[loss=0.1294, simple_loss=0.1964, pruned_loss=0.03126, over 4782.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.0353, over 972049.22 frames.], batch size: 14, lr: 2.57e-04
2022-05-06 07:18:25,463 INFO [train.py:715] (5/8) Epoch 8, batch 26950, loss[loss=0.1492, simple_loss=0.2124, pruned_loss=0.04304, over 4696.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03551, over 971943.07 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:19:04,350 INFO [train.py:715] (5/8) Epoch 8, batch 27000, loss[loss=0.1303, simple_loss=0.2142, pruned_loss=0.0232, over 4812.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03586, over 972880.81 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:19:04,351 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 07:19:13,678 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 07:19:52,527 INFO [train.py:715] (5/8) Epoch 8, batch 27050, loss[loss=0.1356, simple_loss=0.2011, pruned_loss=0.03502, over 4804.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03626, over 972962.24 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:20:31,870 INFO [train.py:715] (5/8) Epoch 8, batch 27100, loss[loss=0.1758, simple_loss=0.2503, pruned_loss=0.05067, over 4837.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.0359, over 971691.50 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:21:10,970 INFO [train.py:715] (5/8) Epoch 8, batch 27150, loss[loss=0.116, simple_loss=0.178, pruned_loss=0.02698, over 4762.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03626, over 971461.95 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:21:49,182 INFO [train.py:715] (5/8) Epoch 8, batch 27200, loss[loss=0.1286, simple_loss=0.1884, pruned_loss=0.03435, over 4861.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2161, pruned_loss=0.03668, over 971324.01 frames.], batch size: 32, lr: 2.57e-04
2022-05-06 07:22:28,509 INFO [train.py:715] (5/8) Epoch 8, batch 27250, loss[loss=0.1465, simple_loss=0.2258, pruned_loss=0.03364, over 4785.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2159, pruned_loss=0.03666, over 972001.43 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 07:23:07,825 INFO [train.py:715] (5/8) Epoch 8, batch 27300, loss[loss=0.1788, simple_loss=0.2608, pruned_loss=0.04836, over 4807.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03601, over 972414.35 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:23:46,493 INFO [train.py:715] (5/8) Epoch 8, batch 27350, loss[loss=0.1217, simple_loss=0.1889, pruned_loss=0.02721, over 4819.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03631, over 973061.95 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:24:25,182 INFO [train.py:715] (5/8) Epoch 8, batch 27400, loss[loss=0.1178, simple_loss=0.1906, pruned_loss=0.02254, over 4826.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03609, over 972736.92 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:25:04,323 INFO [train.py:715] (5/8) Epoch 8, batch 27450, loss[loss=0.1329, simple_loss=0.2093, pruned_loss=0.02827, over 4923.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2171, pruned_loss=0.03614, over 973015.84 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:25:43,015 INFO [train.py:715] (5/8) Epoch 8, batch 27500, loss[loss=0.166, simple_loss=0.2281, pruned_loss=0.05198, over 4829.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03615, over 973555.59 frames.], batch size: 30, lr: 2.56e-04
2022-05-06 07:26:21,670 INFO [train.py:715] (5/8) Epoch 8, batch 27550, loss[loss=0.1306, simple_loss=0.2097, pruned_loss=0.02574, over 4772.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2171, pruned_loss=0.03597, over 973479.95 frames.], batch size: 17, lr: 2.56e-04
2022-05-06 07:27:01,332 INFO [train.py:715] (5/8) Epoch 8, batch 27600, loss[loss=0.1426, simple_loss=0.2104, pruned_loss=0.03736, over 4769.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03612, over 973021.94 frames.], batch size: 19, lr: 2.56e-04
2022-05-06 07:27:40,425 INFO [train.py:715] (5/8) Epoch 8, batch 27650, loss[loss=0.1269, simple_loss=0.1986, pruned_loss=0.02757, over 4824.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03626, over 972783.43 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:28:19,091 INFO [train.py:715] (5/8) Epoch 8, batch 27700, loss[loss=0.1299, simple_loss=0.211, pruned_loss=0.02439, over 4784.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03577, over 971729.44 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:28:58,322 INFO [train.py:715] (5/8) Epoch 8, batch 27750, loss[loss=0.1512, simple_loss=0.2303, pruned_loss=0.03605, over 4957.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03565, over 971559.73 frames.], batch size: 28, lr: 2.56e-04
2022-05-06 07:29:38,020 INFO [train.py:715] (5/8) Epoch 8, batch 27800, loss[loss=0.1122, simple_loss=0.1918, pruned_loss=0.01633, over 4800.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03549, over 972229.63 frames.], batch size: 21, lr: 2.56e-04
2022-05-06 07:30:16,790 INFO [train.py:715] (5/8) Epoch 8, batch 27850, loss[loss=0.1409, simple_loss=0.2099, pruned_loss=0.03595, over 4765.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.036, over 972808.77 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:30:54,916 INFO [train.py:715] (5/8) Epoch 8, batch 27900, loss[loss=0.1479, simple_loss=0.2135, pruned_loss=0.04118, over 4946.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03589, over 972096.01 frames.], batch size: 35, lr: 2.56e-04
2022-05-06 07:31:34,146 INFO [train.py:715] (5/8) Epoch 8, batch 27950, loss[loss=0.1178, simple_loss=0.1851, pruned_loss=0.02526, over 4819.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03582, over 972663.24 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:32:13,474 INFO [train.py:715] (5/8) Epoch 8, batch 28000, loss[loss=0.1556, simple_loss=0.2293, pruned_loss=0.04098, over 4940.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03476, over 972740.27 frames.], batch size: 21, lr: 2.56e-04
2022-05-06 07:32:51,688 INFO [train.py:715] (5/8) Epoch 8, batch 28050, loss[loss=0.1579, simple_loss=0.2475, pruned_loss=0.03418, over 4902.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03516, over 972673.59 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:33:31,447 INFO [train.py:715] (5/8) Epoch 8, batch 28100, loss[loss=0.1322, simple_loss=0.1968, pruned_loss=0.03384, over 4975.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03579, over 973253.54 frames.], batch size: 28, lr: 2.56e-04
2022-05-06 07:34:10,512 INFO [train.py:715] (5/8) Epoch 8, batch 28150, loss[loss=0.1384, simple_loss=0.2033, pruned_loss=0.03671, over 4838.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.0357, over 973255.02 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:34:49,971 INFO [train.py:715] (5/8) Epoch 8, batch 28200, loss[loss=0.1599, simple_loss=0.2292, pruned_loss=0.04526, over 4812.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03555, over 972438.08 frames.], batch size: 25, lr: 2.56e-04
2022-05-06 07:35:29,401 INFO [train.py:715] (5/8) Epoch 8, batch 28250, loss[loss=0.1334, simple_loss=0.1966, pruned_loss=0.03506, over 4655.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2143, pruned_loss=0.03541, over 972378.85 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:36:09,674 INFO [train.py:715] (5/8) Epoch 8, batch 28300, loss[loss=0.1498, simple_loss=0.2265, pruned_loss=0.03656, over 4975.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2148, pruned_loss=0.03538, over 972588.00 frames.], batch size: 24, lr: 2.56e-04
2022-05-06 07:36:49,589 INFO [train.py:715] (5/8) Epoch 8, batch 28350, loss[loss=0.1206, simple_loss=0.1893, pruned_loss=0.02597, over 4978.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03528, over 971750.34 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:37:28,935 INFO [train.py:715] (5/8) Epoch 8, batch 28400, loss[loss=0.1429, simple_loss=0.2186, pruned_loss=0.03361, over 4948.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03591, over 971668.03 frames.], batch size: 24, lr: 2.56e-04
2022-05-06 07:38:08,994 INFO [train.py:715] (5/8) Epoch 8, batch 28450, loss[loss=0.1392, simple_loss=0.208, pruned_loss=0.03516, over 4769.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03615, over 971833.24 frames.], batch size: 12, lr: 2.56e-04
2022-05-06 07:38:48,156 INFO [train.py:715] (5/8) Epoch 8, batch 28500, loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04261, over 4983.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03666, over 972157.10 frames.], batch size: 31, lr: 2.56e-04
2022-05-06 07:39:26,864 INFO [train.py:715] (5/8) Epoch 8, batch 28550, loss[loss=0.143, simple_loss=0.2256, pruned_loss=0.03018, over 4780.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03659, over 972204.98 frames.], batch size: 17, lr: 2.56e-04
2022-05-06 07:40:05,722 INFO [train.py:715] (5/8) Epoch 8, batch 28600, loss[loss=0.1149, simple_loss=0.1816, pruned_loss=0.02416, over 4788.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03593, over 971500.25 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:40:45,400 INFO [train.py:715] (5/8) Epoch 8, batch 28650, loss[loss=0.155, simple_loss=0.2252, pruned_loss=0.04234, over 4828.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03603, over 971774.83 frames.], batch size: 26, lr: 2.56e-04
2022-05-06 07:41:24,251 INFO [train.py:715] (5/8) Epoch 8, batch 28700, loss[loss=0.1645, simple_loss=0.2349, pruned_loss=0.04701, over 4981.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2169, pruned_loss=0.03569, over 972576.54 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:42:02,600 INFO [train.py:715] (5/8) Epoch 8, batch 28750, loss[loss=0.1315, simple_loss=0.2099, pruned_loss=0.02654, over 4814.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03535, over 972677.58 frames.], batch size: 27, lr: 2.56e-04
2022-05-06 07:42:42,146 INFO [train.py:715] (5/8) Epoch 8, batch 28800, loss[loss=0.1363, simple_loss=0.2124, pruned_loss=0.03013, over 4943.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03479, over 972664.90 frames.], batch size: 29, lr: 2.56e-04
2022-05-06 07:43:21,535 INFO [train.py:715] (5/8) Epoch 8, batch 28850, loss[loss=0.1832, simple_loss=0.2407, pruned_loss=0.06286, over 4963.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03512, over 973322.26 frames.], batch size: 24, lr: 2.56e-04
2022-05-06 07:44:00,545 INFO [train.py:715] (5/8) Epoch 8, batch 28900, loss[loss=0.1583, simple_loss=0.2235, pruned_loss=0.04654, over 4926.00 frames.], tot_loss[loss=0.1428, simple_loss=0.216, pruned_loss=0.03475, over 972576.36 frames.], batch size: 23, lr: 2.56e-04
2022-05-06 07:44:39,169 INFO [train.py:715] (5/8) Epoch 8, batch 28950, loss[loss=0.1323, simple_loss=0.1909, pruned_loss=0.03683, over 4822.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2156, pruned_loss=0.035, over 972490.00 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:45:18,516 INFO [train.py:715] (5/8) Epoch 8, batch 29000, loss[loss=0.1429, simple_loss=0.2096, pruned_loss=0.03815, over 4776.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2153, pruned_loss=0.03467, over 972512.55 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:45:57,178 INFO [train.py:715] (5/8) Epoch 8, batch 29050, loss[loss=0.1586, simple_loss=0.2255, pruned_loss=0.04585, over 4833.00 frames.], tot_loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.0346, over 972394.94 frames.], batch size: 25, lr: 2.56e-04
2022-05-06 07:46:36,418 INFO [train.py:715] (5/8) Epoch 8, batch 29100, loss[loss=0.1077, simple_loss=0.1795, pruned_loss=0.01798, over 4860.00 frames.], tot_loss[loss=0.1419, simple_loss=0.215, pruned_loss=0.03446, over 971710.97 frames.], batch size: 32, lr: 2.56e-04
2022-05-06 07:47:14,940 INFO [train.py:715] (5/8) Epoch 8, batch 29150, loss[loss=0.1299, simple_loss=0.206, pruned_loss=0.02685, over 4768.00 frames.], tot_loss[loss=0.142, simple_loss=0.2152, pruned_loss=0.03438, over 972252.14 frames.], batch size: 17, lr: 2.56e-04
2022-05-06 07:47:54,241 INFO [train.py:715] (5/8) Epoch 8, batch 29200, loss[loss=0.1337, simple_loss=0.2055, pruned_loss=0.03093, over 4897.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03443, over 972014.60 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:48:32,864 INFO [train.py:715] (5/8) Epoch 8, batch 29250, loss[loss=0.1367, simple_loss=0.2124, pruned_loss=0.03045, over 4760.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03448, over 971934.06 frames.], batch size: 19, lr: 2.56e-04
2022-05-06 07:49:11,137 INFO [train.py:715] (5/8) Epoch 8, batch 29300, loss[loss=0.133, simple_loss=0.2065, pruned_loss=0.02981, over 4789.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03478, over 971418.65 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:49:50,318 INFO [train.py:715] (5/8) Epoch 8, batch 29350, loss[loss=0.1222, simple_loss=0.2064, pruned_loss=0.01904, over 4867.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03467, over 971576.32 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:50:29,147 INFO [train.py:715] (5/8) Epoch 8, batch 29400, loss[loss=0.1324, simple_loss=0.2086, pruned_loss=0.02813, over 4867.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03473, over 972245.76 frames.], batch size: 20, lr: 2.56e-04
2022-05-06 07:51:08,794 INFO [train.py:715] (5/8) Epoch 8, batch 29450, loss[loss=0.1103, simple_loss=0.1831, pruned_loss=0.01872, over 4751.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03475, over 972645.17 frames.], batch size: 16, lr: 2.56e-04
2022-05-06 07:51:48,079 INFO [train.py:715] (5/8) Epoch 8, batch 29500, loss[loss=0.1231, simple_loss=0.1979, pruned_loss=0.0241, over 4859.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03541, over 971843.23 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:52:27,548 INFO [train.py:715] (5/8) Epoch 8, batch 29550, loss[loss=0.1317, simple_loss=0.2134, pruned_loss=0.02503, over 4812.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.03522, over 972481.05 frames.], batch size: 21, lr: 2.56e-04
2022-05-06 07:53:06,112 INFO [train.py:715] (5/8) Epoch 8, batch 29600, loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03835, over 4846.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.0354, over 972420.80 frames.], batch size: 30, lr: 2.56e-04
2022-05-06 07:53:45,379 INFO [train.py:715] (5/8) Epoch 8, batch 29650, loss[loss=0.1454, simple_loss=0.2156, pruned_loss=0.03758, over 4649.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03519, over 972785.87 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:54:24,984 INFO [train.py:715] (5/8) Epoch 8, batch 29700, loss[loss=0.1679, simple_loss=0.234, pruned_loss=0.05088, over 4939.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03535, over 971774.22 frames.], batch size: 35, lr: 2.56e-04
2022-05-06 07:55:03,539 INFO [train.py:715] (5/8) Epoch 8, batch 29750, loss[loss=0.145, simple_loss=0.2269, pruned_loss=0.03154, over 4943.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03537, over 971932.52 frames.], batch size: 29, lr: 2.56e-04
2022-05-06 07:55:42,375 INFO [train.py:715] (5/8) Epoch 8, batch 29800, loss[loss=0.1558, simple_loss=0.2252, pruned_loss=0.04325, over 4929.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03548, over 973143.42 frames.], batch size: 29, lr: 2.55e-04
2022-05-06 07:56:21,281 INFO [train.py:715] (5/8) Epoch 8, batch 29850, loss[loss=0.1349, simple_loss=0.2001, pruned_loss=0.03486, over 4970.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03479, over 972858.52 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 07:57:00,650 INFO [train.py:715] (5/8) Epoch 8, batch 29900, loss[loss=0.1667, simple_loss=0.2464, pruned_loss=0.04346, over 4803.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03515, over 972469.12 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 07:57:39,540 INFO [train.py:715] (5/8) Epoch 8, batch 29950, loss[loss=0.113, simple_loss=0.1815, pruned_loss=0.02227, over 4701.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03507, over 972031.74 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 07:58:18,653 INFO [train.py:715] (5/8) Epoch 8, batch 30000, loss[loss=0.152, simple_loss=0.2244, pruned_loss=0.03985, over 4731.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03522, over 971394.55 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 07:58:18,653 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 07:58:28,239 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1918, pruned_loss=0.01141, over 914524.00 frames.
2022-05-06 07:59:07,024 INFO [train.py:715] (5/8) Epoch 8, batch 30050, loss[loss=0.1655, simple_loss=0.2353, pruned_loss=0.04783, over 4838.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03566, over 971951.91 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 07:59:46,356 INFO [train.py:715] (5/8) Epoch 8, batch 30100, loss[loss=0.175, simple_loss=0.2492, pruned_loss=0.05041, over 4691.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03524, over 971533.80 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:00:25,654 INFO [train.py:715] (5/8) Epoch 8, batch 30150, loss[loss=0.1622, simple_loss=0.2262, pruned_loss=0.04915, over 4888.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03599, over 971569.65 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:01:04,253 INFO [train.py:715] (5/8) Epoch 8, batch 30200, loss[loss=0.1467, simple_loss=0.2211, pruned_loss=0.03615, over 4909.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03608, over 971891.38 frames.], batch size: 38, lr: 2.55e-04
2022-05-06 08:01:43,183 INFO [train.py:715] (5/8) Epoch 8, batch 30250, loss[loss=0.1483, simple_loss=0.2262, pruned_loss=0.03526, over 4775.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03605, over 971827.80 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:02:22,868 INFO [train.py:715] (5/8) Epoch 8, batch 30300, loss[loss=0.1391, simple_loss=0.2191, pruned_loss=0.02954, over 4988.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03586, over 971997.53 frames.], batch size: 28, lr: 2.55e-04
2022-05-06 08:03:01,868 INFO [train.py:715] (5/8) Epoch 8, batch 30350, loss[loss=0.1503, simple_loss=0.2065, pruned_loss=0.04708, over 4776.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.0353, over 971916.36 frames.], batch size: 12, lr: 2.55e-04
2022-05-06 08:03:40,560 INFO [train.py:715] (5/8) Epoch 8, batch 30400, loss[loss=0.1314, simple_loss=0.1968, pruned_loss=0.03299, over 4853.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03512, over 971779.03 frames.], batch size: 30, lr: 2.55e-04
2022-05-06 08:04:19,870 INFO [train.py:715] (5/8) Epoch 8, batch 30450, loss[loss=0.1464, simple_loss=0.2227, pruned_loss=0.03503, over 4967.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03501, over 972291.12 frames.], batch size: 24, lr: 2.55e-04
2022-05-06 08:04:58,850 INFO [train.py:715] (5/8) Epoch 8, batch 30500, loss[loss=0.1625, simple_loss=0.2255, pruned_loss=0.04972, over 4899.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03603, over 972538.37 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:05:37,496 INFO [train.py:715] (5/8) Epoch 8, batch 30550, loss[loss=0.1332, simple_loss=0.2034, pruned_loss=0.03147, over 4843.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03573, over 971683.93 frames.], batch size: 30, lr: 2.55e-04
2022-05-06 08:06:16,534 INFO [train.py:715] (5/8) Epoch 8, batch 30600, loss[loss=0.1169, simple_loss=0.1855, pruned_loss=0.02418, over 4900.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03562, over 972431.36 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:06:56,266 INFO [train.py:715] (5/8) Epoch 8, batch 30650, loss[loss=0.1587, simple_loss=0.2325, pruned_loss=0.04248, over 4753.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03555, over 972406.28 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 08:07:35,449 INFO [train.py:715] (5/8) Epoch 8, batch 30700, loss[loss=0.1297, simple_loss=0.209, pruned_loss=0.02518, over 4866.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03518, over 971805.88 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 08:08:15,325 INFO [train.py:715] (5/8) Epoch 8, batch 30750, loss[loss=0.1382, simple_loss=0.2121, pruned_loss=0.03217, over 4804.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03522, over 971867.85 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:08:55,446 INFO [train.py:715] (5/8) Epoch 8, batch 30800, loss[loss=0.1367, simple_loss=0.2081, pruned_loss=0.03266, over 4784.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03523, over 971847.68 frames.], batch size: 14, lr: 2.55e-04
2022-05-06 08:09:33,879 INFO [train.py:715] (5/8) Epoch 8, batch 30850, loss[loss=0.1279, simple_loss=0.2085, pruned_loss=0.02367, over 4809.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03482, over 970871.80 frames.], batch size: 25, lr: 2.55e-04
2022-05-06 08:10:12,782 INFO [train.py:715] (5/8) Epoch 8, batch 30900, loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03403, over 4978.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03468, over 970930.48 frames.], batch size: 25, lr: 2.55e-04
2022-05-06 08:10:52,557 INFO [train.py:715] (5/8) Epoch 8, batch 30950, loss[loss=0.1629, simple_loss=0.2354, pruned_loss=0.04517, over 4796.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03515, over 972273.90 frames.], batch size: 24, lr: 2.55e-04
2022-05-06 08:11:32,558 INFO [train.py:715] (5/8) Epoch 8, batch 31000, loss[loss=0.1702, simple_loss=0.2471, pruned_loss=0.04667, over 4924.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03506, over 972968.27 frames.], batch size: 18, lr: 2.55e-04
2022-05-06 08:12:11,802 INFO [train.py:715] (5/8) Epoch 8, batch 31050, loss[loss=0.1508, simple_loss=0.2232, pruned_loss=0.03918, over 4929.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03513, over 972117.95 frames.], batch size: 18, lr: 2.55e-04
2022-05-06 08:12:51,407 INFO [train.py:715] (5/8) Epoch 8, batch 31100, loss[loss=0.1223, simple_loss=0.1952, pruned_loss=0.02465, over 4985.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03552, over 972296.23 frames.], batch size: 26, lr: 2.55e-04
2022-05-06 08:13:30,938 INFO [train.py:715] (5/8) Epoch 8, batch 31150, loss[loss=0.1456, simple_loss=0.2185, pruned_loss=0.0363, over 4694.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.0355, over 971294.34 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:14:09,967 INFO [train.py:715] (5/8) Epoch 8, batch 31200, loss[loss=0.1218, simple_loss=0.1862, pruned_loss=0.02873, over 4776.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03548, over 971169.01 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:14:48,713 INFO [train.py:715] (5/8) Epoch 8, batch 31250, loss[loss=0.1056, simple_loss=0.1797, pruned_loss=0.01577, over 4778.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03584, over 970531.96 frames.], batch size: 12, lr: 2.55e-04
2022-05-06 08:15:28,180 INFO [train.py:715] (5/8) Epoch 8, batch 31300, loss[loss=0.14, simple_loss=0.2193, pruned_loss=0.03038, over 4932.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03556, over 970832.49 frames.], batch size: 23, lr: 2.55e-04
2022-05-06 08:16:07,666 INFO [train.py:715] (5/8) Epoch 8, batch 31350, loss[loss=0.138, simple_loss=0.2095, pruned_loss=0.03331, over 4885.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03536, over 971466.44 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:16:46,297 INFO [train.py:715] (5/8) Epoch 8, batch 31400, loss[loss=0.1458, simple_loss=0.22, pruned_loss=0.03581, over 4944.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03564, over 971383.79 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:17:25,750 INFO [train.py:715] (5/8) Epoch 8, batch 31450, loss[loss=0.1871, simple_loss=0.2504, pruned_loss=0.06194, over 4827.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03603, over 971517.32 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:18:05,888 INFO [train.py:715] (5/8) Epoch 8, batch 31500, loss[loss=0.1587, simple_loss=0.2295, pruned_loss=0.04389, over 4835.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.036, over 972092.64 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:18:45,116 INFO [train.py:715] (5/8) Epoch 8, batch 31550, loss[loss=0.1592, simple_loss=0.2226, pruned_loss=0.04788, over 4839.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.03581, over 972672.95 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 08:19:24,100 INFO [train.py:715] (5/8) Epoch 8, batch 31600, loss[loss=0.1458, simple_loss=0.224, pruned_loss=0.03382, over 4950.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.03526, over 972149.23 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:20:03,753 INFO [train.py:715] (5/8) Epoch 8, batch 31650, loss[loss=0.1254, simple_loss=0.2068, pruned_loss=0.02198, over 4989.00 frames.], tot_loss[loss=0.144, simple_loss=0.2166, pruned_loss=0.03575, over 972178.55 frames.], batch size: 26, lr: 2.55e-04
2022-05-06 08:20:43,074 INFO [train.py:715] (5/8) Epoch 8, batch 31700, loss[loss=0.1342, simple_loss=0.2053, pruned_loss=0.03152, over 4986.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2163, pruned_loss=0.03554, over 971715.36 frames.], batch size: 27, lr: 2.55e-04
2022-05-06 08:21:22,752 INFO [train.py:715] (5/8) Epoch 8, batch 31750, loss[loss=0.1351, simple_loss=0.215, pruned_loss=0.02758, over 4781.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03576, over 972019.74 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:22:01,966 INFO [train.py:715] (5/8) Epoch 8, batch 31800, loss[loss=0.133, simple_loss=0.2133, pruned_loss=0.02634, over 4971.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03528, over 972879.77 frames.], batch size: 25, lr: 2.55e-04
2022-05-06 08:22:41,009 INFO [train.py:715] (5/8) Epoch 8, batch 31850, loss[loss=0.1518, simple_loss=0.2181, pruned_loss=0.04277, over 4857.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03519, over 972604.19 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 08:23:19,917 INFO [train.py:715] (5/8) Epoch 8, batch 31900, loss[loss=0.1924, simple_loss=0.2591, pruned_loss=0.06282, over 4752.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03528, over 972434.55 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 08:23:58,316 INFO [train.py:715] (5/8) Epoch 8, batch 31950, loss[loss=0.1368, simple_loss=0.1959, pruned_loss=0.03887, over 4816.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03559, over 972967.17 frames.], batch size: 13, lr: 2.55e-04
2022-05-06 08:24:37,604 INFO [train.py:715] (5/8) Epoch 8, batch 32000, loss[loss=0.1634, simple_loss=0.2228, pruned_loss=0.052, over 4757.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03544, over 972963.95 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:25:17,171 INFO [train.py:715] (5/8) Epoch 8, batch 32050, loss[loss=0.1349, simple_loss=0.1975, pruned_loss=0.03615, over 4819.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2154, pruned_loss=0.03465, over 973109.53 frames.], batch size: 13, lr: 2.55e-04
2022-05-06 08:25:55,735 INFO [train.py:715] (5/8) Epoch 8, batch 32100, loss[loss=0.1477, simple_loss=0.2327, pruned_loss=0.03134, over 4827.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03504, over 973661.53 frames.], batch size: 26, lr: 2.55e-04
2022-05-06 08:26:34,465 INFO [train.py:715] (5/8) Epoch 8, batch 32150, loss[loss=0.1338, simple_loss=0.2052, pruned_loss=0.03117, over 4974.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03515, over 974257.44 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:27:14,043 INFO [train.py:715] (5/8) Epoch 8, batch 32200, loss[loss=0.1155, simple_loss=0.1935, pruned_loss=0.01873, over 4830.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03499, over 973684.41 frames.], batch size: 25, lr: 2.54e-04
2022-05-06 08:27:52,859 INFO [train.py:715] (5/8) Epoch 8, batch 32250, loss[loss=0.1617, simple_loss=0.2348, pruned_loss=0.04431, over 4760.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03476, over 972485.33 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:28:32,330 INFO [train.py:715] (5/8) Epoch 8, batch 32300, loss[loss=0.1217, simple_loss=0.1905, pruned_loss=0.02641, over 4839.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.0345, over 972764.44 frames.], batch size: 27, lr: 2.54e-04
2022-05-06 08:29:11,541 INFO [train.py:715] (5/8) Epoch 8, batch 32350, loss[loss=0.1592, simple_loss=0.2203, pruned_loss=0.04903, over 4830.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03448, over 972507.76 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:29:51,457 INFO [train.py:715] (5/8) Epoch 8, batch 32400, loss[loss=0.1369, simple_loss=0.1979, pruned_loss=0.03795, over 4759.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03475, over 972974.27 frames.], batch size: 16, lr: 2.54e-04
2022-05-06 08:30:30,380 INFO [train.py:715] (5/8) Epoch 8, batch 32450, loss[loss=0.1259, simple_loss=0.2062, pruned_loss=0.02284, over 4842.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03513, over 973486.76 frames.], batch size: 26, lr: 2.54e-04
2022-05-06 08:31:09,401 INFO [train.py:715] (5/8) Epoch 8, batch 32500, loss[loss=0.1989, simple_loss=0.2737, pruned_loss=0.06203, over 4865.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03516, over 974115.22 frames.], batch size: 20, lr: 2.54e-04
2022-05-06 08:31:48,951 INFO [train.py:715] (5/8) Epoch 8, batch 32550, loss[loss=0.1808, simple_loss=0.241, pruned_loss=0.06035, over 4704.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03489, over 973297.66 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:32:27,500 INFO [train.py:715] (5/8) Epoch 8, batch 32600, loss[loss=0.1357, simple_loss=0.2141, pruned_loss=0.02864, over 4974.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03517, over 972656.16 frames.], batch size: 24, lr: 2.54e-04
2022-05-06 08:33:06,727 INFO [train.py:715] (5/8) Epoch 8, batch 32650, loss[loss=0.1518, simple_loss=0.216, pruned_loss=0.04376, over 4783.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03479, over 972035.47 frames.], batch size: 17, lr: 2.54e-04
2022-05-06 08:33:45,979 INFO [train.py:715] (5/8) Epoch 8, batch 32700, loss[loss=0.1183, simple_loss=0.1997, pruned_loss=0.01845, over 4773.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03461, over 972734.76 frames.], batch size: 17, lr: 2.54e-04
2022-05-06 08:34:26,177 INFO [train.py:715] (5/8) Epoch 8, batch 32750, loss[loss=0.1608, simple_loss=0.2214, pruned_loss=0.05011, over 4845.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03479, over 973164.68 frames.], batch size: 30, lr: 2.54e-04
2022-05-06 08:35:04,665 INFO [train.py:715] (5/8) Epoch 8, batch 32800, loss[loss=0.1332, simple_loss=0.2113, pruned_loss=0.02756, over 4809.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.0355, over 972872.25 frames.], batch size: 25, lr: 2.54e-04
2022-05-06 08:35:43,309 INFO [train.py:715] (5/8) Epoch 8, batch 32850, loss[loss=0.1823, simple_loss=0.2437, pruned_loss=0.06041, over 4873.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.035, over 972356.63 frames.], batch size: 16, lr: 2.54e-04
2022-05-06 08:36:22,461 INFO [train.py:715] (5/8) Epoch 8, batch 32900, loss[loss=0.1729, simple_loss=0.2326, pruned_loss=0.05657, over 4737.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.0351, over 972291.97 frames.], batch size: 16, lr: 2.54e-04
2022-05-06 08:37:00,743 INFO [train.py:715] (5/8) Epoch 8, batch 32950, loss[loss=0.1474, simple_loss=0.2167, pruned_loss=0.03908, over 4991.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03517, over 972694.34 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:37:39,628 INFO [train.py:715] (5/8) Epoch 8, batch 33000, loss[loss=0.1336, simple_loss=0.2122, pruned_loss=0.02749, over 4830.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03485, over 972978.60 frames.], batch size: 26, lr: 2.54e-04
2022-05-06 08:37:39,628 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 08:37:52,640 INFO [train.py:742] (5/8) Epoch 8, validation: loss=0.1071, simple_loss=0.1917, pruned_loss=0.01126, over 914524.00 frames.
2022-05-06 08:38:31,973 INFO [train.py:715] (5/8) Epoch 8, batch 33050, loss[loss=0.1089, simple_loss=0.1851, pruned_loss=0.01636, over 4827.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03499, over 973496.42 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:39:10,828 INFO [train.py:715] (5/8) Epoch 8, batch 33100, loss[loss=0.1806, simple_loss=0.2414, pruned_loss=0.05986, over 4975.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03517, over 973177.55 frames.], batch size: 35, lr: 2.54e-04
2022-05-06 08:39:50,123 INFO [train.py:715] (5/8) Epoch 8, batch 33150, loss[loss=0.1736, simple_loss=0.2353, pruned_loss=0.05592, over 4785.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03503, over 972176.23 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:40:28,831 INFO [train.py:715] (5/8) Epoch 8, batch 33200, loss[loss=0.1298, simple_loss=0.2012, pruned_loss=0.02918, over 4786.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03503, over 971474.46 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:41:08,503 INFO [train.py:715] (5/8) Epoch 8, batch 33250, loss[loss=0.1436, simple_loss=0.2191, pruned_loss=0.0341, over 4957.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03491, over 972633.04 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:41:48,101 INFO [train.py:715] (5/8) Epoch 8, batch 33300, loss[loss=0.2317, simple_loss=0.2943, pruned_loss=0.08451, over 4982.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03533, over 972341.84 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:42:26,898 INFO [train.py:715] (5/8) Epoch 8, batch 33350, loss[loss=0.1586, simple_loss=0.239, pruned_loss=0.03914, over 4799.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03503, over 971608.37 frames.], batch size: 24, lr: 2.54e-04
2022-05-06 08:43:06,260 INFO [train.py:715] (5/8) Epoch 8, batch 33400, loss[loss=0.1754, simple_loss=0.2434, pruned_loss=0.05367, over 4823.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03491, over 970607.30 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:43:45,175 INFO [train.py:715] (5/8) Epoch 8, batch 33450, loss[loss=0.1596, simple_loss=0.2225, pruned_loss=0.04832, over 4903.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03461, over 970770.97 frames.], batch size: 17, lr: 2.54e-04
2022-05-06 08:44:24,008 INFO [train.py:715] (5/8) Epoch 8, batch 33500, loss[loss=0.1609, simple_loss=0.2359, pruned_loss=0.04291, over 4751.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03485, over 971733.86 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:45:05,006 INFO [train.py:715] (5/8) Epoch 8, batch 33550, loss[loss=0.19, simple_loss=0.2563, pruned_loss=0.06185, over 4699.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03463, over 971189.82 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:45:44,462 INFO [train.py:715] (5/8) Epoch 8, batch 33600, loss[loss=0.1462, simple_loss=0.2087, pruned_loss=0.04188, over 4959.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03459, over 971440.81 frames.], batch size: 31, lr: 2.54e-04
2022-05-06 08:46:23,908 INFO [train.py:715] (5/8) Epoch 8, batch 33650, loss[loss=0.2068, simple_loss=0.2882, pruned_loss=0.06277, over 4941.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2152, pruned_loss=0.03473, over 972131.51 frames.], batch size: 29, lr: 2.54e-04
2022-05-06 08:47:02,972 INFO [train.py:715] (5/8) Epoch 8, batch 33700, loss[loss=0.1316, simple_loss=0.2079, pruned_loss=0.02764, over 4894.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03503, over 971959.07 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:47:41,967 INFO [train.py:715] (5/8) Epoch 8, batch 33750, loss[loss=0.1398, simple_loss=0.2154, pruned_loss=0.03214, over 4973.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2159, pruned_loss=0.03518, over 973411.15 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:48:20,685 INFO [train.py:715] (5/8) Epoch 8, batch 33800, loss[loss=0.1347, simple_loss=0.2019, pruned_loss=0.03376, over 4802.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03482, over 972139.34 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:48:59,303 INFO [train.py:715] (5/8) Epoch 8, batch 33850, loss[loss=0.1597, simple_loss=0.2293, pruned_loss=0.04507, over 4961.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03529, over 972031.32 frames.], batch size: 39, lr: 2.54e-04
2022-05-06 08:49:38,115 INFO [train.py:715] (5/8) Epoch 8, batch 33900, loss[loss=0.1934, simple_loss=0.2483, pruned_loss=0.06927, over 4754.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03533, over 971894.54 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:50:17,036 INFO [train.py:715] (5/8) Epoch 8, batch 33950, loss[loss=0.1345, simple_loss=0.214, pruned_loss=0.02747, over 4863.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03579, over 971451.32 frames.], batch size: 30, lr: 2.54e-04
2022-05-06 08:50:56,632 INFO [train.py:715] (5/8) Epoch 8, batch 34000, loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.028, over 4946.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03556, over 971622.54 frames.], batch size: 23, lr: 2.54e-04
2022-05-06 08:51:35,548 INFO [train.py:715] (5/8) Epoch 8, batch 34050, loss[loss=0.1446, simple_loss=0.2178, pruned_loss=0.03574, over 4976.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03543, over 971130.86 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:52:14,816 INFO [train.py:715] (5/8) Epoch 8, batch 34100, loss[loss=0.1427, simple_loss=0.2168, pruned_loss=0.03428, over 4960.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03558, over 971309.21 frames.], batch size: 24, lr: 2.54e-04
2022-05-06 08:52:53,779 INFO [train.py:715] (5/8) Epoch 8, batch 34150, loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.0289, over 4932.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03509, over 972236.63 frames.], batch size: 23, lr: 2.54e-04
2022-05-06 08:53:32,399 INFO [train.py:715] (5/8) Epoch 8, batch 34200, loss[loss=0.1734, simple_loss=0.2362, pruned_loss=0.05533, over 4842.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03513, over 972027.14 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:54:11,300 INFO [train.py:715] (5/8) Epoch 8, batch 34250, loss[loss=0.1361, simple_loss=0.1997, pruned_loss=0.03621, over 4796.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03557, over 972519.12 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:54:50,274 INFO [train.py:715] (5/8) Epoch 8, batch 34300, loss[loss=0.1193, simple_loss=0.1932, pruned_loss=0.02274, over 4840.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03572, over 973408.81 frames.], batch size: 20, lr: 2.54e-04
2022-05-06 08:55:29,024 INFO [train.py:715] (5/8) Epoch 8, batch 34350, loss[loss=0.1535, simple_loss=0.2186, pruned_loss=0.04423, over 4841.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03548, over 973300.74 frames.], batch size: 30, lr: 2.54e-04
2022-05-06 08:56:07,452 INFO [train.py:715] (5/8) Epoch 8, batch 34400, loss[loss=0.1068, simple_loss=0.1854, pruned_loss=0.01416, over 4783.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03559, over 972759.94 frames.], batch size: 23, lr: 2.54e-04
2022-05-06 08:56:46,675 INFO [train.py:715] (5/8) Epoch 8, batch 34450, loss[loss=0.1168, simple_loss=0.1964, pruned_loss=0.0186, over 4752.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03572, over 972337.68 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:57:26,046 INFO [train.py:715] (5/8) Epoch 8, batch 34500, loss[loss=0.1506, simple_loss=0.2275, pruned_loss=0.03685, over 4749.00 frames.], tot_loss[loss=0.144, simple_loss=0.217, pruned_loss=0.03551, over 971959.94 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:58:04,289 INFO [train.py:715] (5/8) Epoch 8, batch 34550, loss[loss=0.1164, simple_loss=0.1926, pruned_loss=0.02006, over 4981.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2174, pruned_loss=0.03602, over 972101.72 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:58:42,923 INFO [train.py:715] (5/8) Epoch 8, batch 34600, loss[loss=0.122, simple_loss=0.1969, pruned_loss=0.02354, over 4936.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2167, pruned_loss=0.03576, over 972596.81 frames.], batch size: 29, lr: 2.54e-04
2022-05-06 08:59:21,843 INFO [train.py:715] (5/8) Epoch 8, batch 34650, loss[loss=0.1357, simple_loss=0.2122, pruned_loss=0.02966, over 4979.00 frames.], tot_loss[loss=0.144, simple_loss=0.2169, pruned_loss=0.03557, over 972358.39 frames.], batch size: 25, lr: 2.53e-04
2022-05-06 09:00:01,503 INFO [train.py:715] (5/8) Epoch 8, batch 34700, loss[loss=0.1561, simple_loss=0.219, pruned_loss=0.04661, over 4815.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03535, over 971377.24 frames.], batch size: 25, lr: 2.53e-04
2022-05-06 09:00:38,661 INFO [train.py:715] (5/8) Epoch 8, batch 34750, loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03818, over 4819.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.03545, over 971794.65 frames.], batch size: 21, lr: 2.53e-04
2022-05-06 09:01:15,266 INFO [train.py:715] (5/8) Epoch 8, batch 34800, loss[loss=0.1305, simple_loss=0.2044, pruned_loss=0.02826, over 4912.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03567, over 971006.45 frames.], batch size: 18, lr: 2.53e-04
2022-05-06 09:02:04,640 INFO [train.py:715] (5/8) Epoch 9, batch 0, loss[loss=0.1429, simple_loss=0.2226, pruned_loss=0.03163, over 4814.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2226, pruned_loss=0.03163, over 4814.00 frames.], batch size: 27, lr: 2.42e-04
2022-05-06 09:02:43,991 INFO [train.py:715] (5/8) Epoch 9, batch 50, loss[loss=0.134, simple_loss=0.2069, pruned_loss=0.03053, over 4848.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2197, pruned_loss=0.03784, over 220078.03 frames.], batch size: 30, lr: 2.41e-04
2022-05-06 09:03:23,607 INFO [train.py:715] (5/8) Epoch 9, batch 100, loss[loss=0.1497, simple_loss=0.2265, pruned_loss=0.03647, over 4944.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03656, over 386889.90 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:04:02,102 INFO [train.py:715] (5/8) Epoch 9, batch 150, loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02845, over 4885.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03558, over 518057.87 frames.], batch size: 16, lr: 2.41e-04
2022-05-06 09:04:42,539 INFO [train.py:715] (5/8) Epoch 9, batch 200, loss[loss=0.1511, simple_loss=0.2202, pruned_loss=0.04106, over 4971.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03534, over 619485.77 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:05:21,803 INFO [train.py:715] (5/8) Epoch 9, batch 250, loss[loss=0.1185, simple_loss=0.1939, pruned_loss=0.02154, over 4926.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03455, over 697618.33 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:06:01,092 INFO [train.py:715] (5/8) Epoch 9, batch 300, loss[loss=0.138, simple_loss=0.2075, pruned_loss=0.0343, over 4771.00 frames.], tot_loss[loss=0.142, simple_loss=0.2142, pruned_loss=0.03491, over 757862.27 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:06:40,657 INFO [train.py:715] (5/8) Epoch 9, batch 350, loss[loss=0.1245, simple_loss=0.1951, pruned_loss=0.02697, over 4779.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03477, over 805290.45 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:07:20,400 INFO [train.py:715] (5/8) Epoch 9, batch 400, loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03036, over 4799.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.035, over 842240.98 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:07:59,732 INFO [train.py:715] (5/8) Epoch 9, batch 450, loss[loss=0.149, simple_loss=0.2186, pruned_loss=0.03971, over 4650.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03513, over 869893.33 frames.], batch size: 13, lr: 2.41e-04
2022-05-06 09:08:38,885 INFO [train.py:715] (5/8) Epoch 9, batch 500, loss[loss=0.1742, simple_loss=0.2356, pruned_loss=0.0564, over 4782.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2138, pruned_loss=0.03484, over 892490.50 frames.], batch size: 17, lr: 2.41e-04
2022-05-06 09:09:19,201 INFO [train.py:715] (5/8) Epoch 9, batch 550, loss[loss=0.1131, simple_loss=0.194, pruned_loss=0.01604, over 4921.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03447, over 909473.44 frames.], batch size: 23, lr: 2.41e-04
2022-05-06 09:09:58,808 INFO [train.py:715] (5/8) Epoch 9, batch 600, loss[loss=0.1638, simple_loss=0.23, pruned_loss=0.04877, over 4838.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03485, over 924289.97 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:10:37,824 INFO [train.py:715] (5/8) Epoch 9, batch 650, loss[loss=0.1235, simple_loss=0.1998, pruned_loss=0.02365, over 4895.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03423, over 935113.57 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:11:16,916 INFO [train.py:715] (5/8) Epoch 9, batch 700, loss[loss=0.1575, simple_loss=0.2145, pruned_loss=0.05025, over 4957.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2138, pruned_loss=0.03489, over 943246.57 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:11:56,396 INFO [train.py:715] (5/8) Epoch 9, batch 750, loss[loss=0.1285, simple_loss=0.2037, pruned_loss=0.0267, over 4985.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03543, over 949931.06 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:12:35,538 INFO [train.py:715] (5/8) Epoch 9, batch 800, loss[loss=0.1395, simple_loss=0.2314, pruned_loss=0.02379, over 4904.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.03497, over 955005.37 frames.], batch size: 23, lr: 2.41e-04
2022-05-06 09:13:14,317 INFO [train.py:715] (5/8) Epoch 9, batch 850, loss[loss=0.113, simple_loss=0.1834, pruned_loss=0.02127, over 4810.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03518, over 959112.05 frames.], batch size: 12, lr: 2.41e-04
2022-05-06 09:13:53,317 INFO [train.py:715] (5/8) Epoch 9, batch 900, loss[loss=0.1378, simple_loss=0.213, pruned_loss=0.03135, over 4927.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2135, pruned_loss=0.03483, over 961632.07 frames.], batch size: 29, lr: 2.41e-04
2022-05-06 09:14:32,594 INFO [train.py:715] (5/8) Epoch 9, batch 950, loss[loss=0.1844, simple_loss=0.266, pruned_loss=0.05142, over 4764.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03535, over 964716.35 frames.], batch size: 17, lr: 2.41e-04
2022-05-06 09:15:12,211 INFO [train.py:715] (5/8) Epoch 9, batch 1000, loss[loss=0.1828, simple_loss=0.2506, pruned_loss=0.05748, over 4880.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03528, over 966939.59 frames.], batch size: 16, lr: 2.41e-04
2022-05-06 09:15:50,365 INFO [train.py:715] (5/8) Epoch 9, batch 1050, loss[loss=0.1132, simple_loss=0.178, pruned_loss=0.02423, over 4839.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03513, over 968504.86 frames.], batch size: 30, lr: 2.41e-04
2022-05-06 09:16:30,509 INFO [train.py:715] (5/8) Epoch 9, batch 1100, loss[loss=0.1289, simple_loss=0.1969, pruned_loss=0.03045, over 4982.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03508, over 969242.32 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:17:10,346 INFO [train.py:715] (5/8) Epoch 9, batch 1150, loss[loss=0.1456, simple_loss=0.2076, pruned_loss=0.04182, over 4746.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03543, over 969998.38 frames.], batch size: 12, lr: 2.41e-04
2022-05-06 09:17:49,483 INFO [train.py:715] (5/8) Epoch 9, batch 1200, loss[loss=0.1499, simple_loss=0.2273, pruned_loss=0.0363, over 4950.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03511, over 971202.73 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:18:28,817 INFO [train.py:715] (5/8) Epoch 9, batch 1250, loss[loss=0.1406, simple_loss=0.2071, pruned_loss=0.03704, over 4793.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.0349, over 971782.21 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:19:08,558 INFO [train.py:715] (5/8) Epoch 9, batch 1300, loss[loss=0.1163, simple_loss=0.1926, pruned_loss=0.01997, over 4889.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03492, over 972267.82 frames.], batch size: 22, lr: 2.41e-04
2022-05-06 09:19:48,097 INFO [train.py:715] (5/8) Epoch 9, batch 1350, loss[loss=0.1315, simple_loss=0.2144, pruned_loss=0.02426, over 4897.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03531, over 972663.69 frames.], batch size: 22, lr: 2.41e-04
2022-05-06 09:20:26,896 INFO [train.py:715] (5/8) Epoch 9, batch 1400, loss[loss=0.123, simple_loss=0.2038, pruned_loss=0.02114, over 4945.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03522, over 972061.59 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:21:06,500 INFO [train.py:715] (5/8) Epoch 9, batch 1450, loss[loss=0.1451, simple_loss=0.2259, pruned_loss=0.03213, over 4817.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03469, over 971467.37 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:21:45,311 INFO [train.py:715] (5/8) Epoch 9, batch 1500, loss[loss=0.1528, simple_loss=0.2228, pruned_loss=0.04139, over 4837.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03492, over 971933.19 frames.], batch size: 30, lr: 2.41e-04
2022-05-06 09:22:24,146 INFO [train.py:715] (5/8) Epoch 9, batch 1550, loss[loss=0.1261, simple_loss=0.2026, pruned_loss=0.0248, over 4698.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03508, over 972551.13 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:23:03,175 INFO [train.py:715] (5/8) Epoch 9, batch 1600, loss[loss=0.1208, simple_loss=0.1917, pruned_loss=0.02498, over 4693.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03512, over 971631.14 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:23:42,085 INFO [train.py:715] (5/8) Epoch 9, batch 1650, loss[loss=0.159, simple_loss=0.2237, pruned_loss=0.04717, over 4982.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03569, over 971770.98 frames.], batch size: 33, lr: 2.41e-04
2022-05-06 09:24:21,072 INFO [train.py:715] (5/8) Epoch 9, batch 1700, loss[loss=0.1151, simple_loss=0.1843, pruned_loss=0.02296, over 4770.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.0353, over 972160.76 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:25:00,143 INFO [train.py:715] (5/8) Epoch 9, batch 1750, loss[loss=0.1384, simple_loss=0.2131, pruned_loss=0.03181, over 4976.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03506, over 972578.58 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:25:39,672 INFO [train.py:715] (5/8) Epoch 9, batch 1800, loss[loss=0.1363, simple_loss=0.207, pruned_loss=0.03283, over 4908.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03517, over 974267.99 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:26:18,853 INFO [train.py:715] (5/8) Epoch 9, batch 1850, loss[loss=0.1297, simple_loss=0.1971, pruned_loss=0.03119, over 4988.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03565, over 974254.24 frames.], batch size: 28, lr: 2.41e-04
2022-05-06 09:26:57,981 INFO [train.py:715] (5/8) Epoch 9, batch 1900, loss[loss=0.1052, simple_loss=0.1776, pruned_loss=0.01644, over 4780.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03542, over 974221.37 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:27:37,987 INFO [train.py:715] (5/8) Epoch 9, batch 1950, loss[loss=0.1674, simple_loss=0.2296, pruned_loss=0.05255, over 4695.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03533, over 973753.32 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:28:17,649 INFO [train.py:715] (5/8) Epoch 9, batch 2000, loss[loss=0.1125, simple_loss=0.1849, pruned_loss=0.02006, over 4778.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03594, over 972988.59 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:28:56,804 INFO [train.py:715] (5/8) Epoch 9, batch 2050, loss[loss=0.1617, simple_loss=0.2238, pruned_loss=0.04976, over 4856.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03656, over 973106.38 frames.], batch size: 20, lr: 2.41e-04
2022-05-06 09:29:35,325 INFO [train.py:715] (5/8) Epoch 9, batch 2100, loss[loss=0.1576, simple_loss=0.2355, pruned_loss=0.03984, over 4695.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03593, over 972733.27 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:30:14,644 INFO [train.py:715] (5/8) Epoch 9, batch 2150, loss[loss=0.1253, simple_loss=0.1953, pruned_loss=0.0277, over 4912.00 frames.], tot_loss[loss=0.143, simple_loss=0.2148, pruned_loss=0.03561, over 972161.66 frames.], batch size: 17, lr: 2.41e-04
2022-05-06 09:30:53,733 INFO [train.py:715] (5/8) Epoch 9, batch 2200, loss[loss=0.1234, simple_loss=0.1942, pruned_loss=0.02627, over 4692.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2142, pruned_loss=0.03535, over 972110.12 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:31:32,489 INFO [train.py:715] (5/8) Epoch 9, batch 2250, loss[loss=0.15, simple_loss=0.2312, pruned_loss=0.03438, over 4966.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03523, over 972095.46 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:32:11,658 INFO [train.py:715] (5/8) Epoch 9, batch 2300, loss[loss=0.1434, simple_loss=0.2176, pruned_loss=0.03461, over 4945.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.03535, over 971979.92 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:32:50,741 INFO [train.py:715] (5/8) Epoch 9, batch 2350, loss[loss=0.1425, simple_loss=0.2103, pruned_loss=0.03733, over 4809.00 frames.], tot_loss[loss=0.142, simple_loss=0.2139, pruned_loss=0.03505, over 971980.07 frames.], batch size: 13, lr: 2.41e-04
2022-05-06 09:33:30,100 INFO [train.py:715] (5/8) Epoch 9, batch 2400, loss[loss=0.1152, simple_loss=0.1962, pruned_loss=0.01713, over 4846.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03448, over 972553.00 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:34:08,885 INFO [train.py:715] (5/8) Epoch 9, batch 2450, loss[loss=0.142, simple_loss=0.2125, pruned_loss=0.03572, over 4910.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2131, pruned_loss=0.03451, over 971939.42 frames.], batch size: 39, lr: 2.41e-04
2022-05-06 09:34:48,500 INFO [train.py:715] (5/8) Epoch 9, batch 2500, loss[loss=0.1397, simple_loss=0.2114, pruned_loss=0.03402, over 4928.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03506, over 971797.58 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:35:27,019 INFO [train.py:715] (5/8) Epoch 9, batch 2550, loss[loss=0.1114, simple_loss=0.1808, pruned_loss=0.02101, over 4940.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03445, over 972308.66 frames.], batch size: 29, lr: 2.41e-04
2022-05-06 09:36:06,039 INFO [train.py:715] (5/8) Epoch 9, batch 2600, loss[loss=0.1184, simple_loss=0.1915, pruned_loss=0.02268, over 4776.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.0344, over 972456.56 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:36:45,108 INFO [train.py:715] (5/8) Epoch 9, batch 2650, loss[loss=0.1551, simple_loss=0.2246, pruned_loss=0.04276, over 4833.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03429, over 971487.16 frames.], batch size: 13, lr: 2.41e-04
2022-05-06 09:37:24,473 INFO [train.py:715] (5/8) Epoch 9, batch 2700, loss[loss=0.1512, simple_loss=0.2244, pruned_loss=0.03901, over 4699.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.0342, over 971547.62 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:38:03,293 INFO [train.py:715] (5/8) Epoch 9, batch 2750, loss[loss=0.1189, simple_loss=0.2034, pruned_loss=0.01725, over 4948.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.034, over 971040.76 frames.], batch size: 23, lr: 2.40e-04
2022-05-06 09:38:42,263 INFO [train.py:715] (5/8) Epoch 9, batch 2800, loss[loss=0.1386, simple_loss=0.1999, pruned_loss=0.03862, over 4854.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03399, over 971755.27 frames.], batch size: 32, lr: 2.40e-04
2022-05-06 09:39:21,839 INFO [train.py:715] (5/8) Epoch 9, batch 2850, loss[loss=0.1653, simple_loss=0.2247, pruned_loss=0.0529, over 4770.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03389, over 970877.93 frames.], batch size: 14, lr: 2.40e-04
2022-05-06 09:40:00,913 INFO [train.py:715] (5/8) Epoch 9, batch 2900, loss[loss=0.1388, simple_loss=0.2031, pruned_loss=0.03727, over 4788.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03421, over 971137.21 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 09:40:39,676 INFO [train.py:715] (5/8) Epoch 9, batch 2950, loss[loss=0.1255, simple_loss=0.2031, pruned_loss=0.02395, over 4923.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03421, over 972166.63 frames.], batch size: 23, lr: 2.40e-04
2022-05-06 09:41:18,903 INFO [train.py:715] (5/8) Epoch 9, batch 3000, loss[loss=0.1272, simple_loss=0.1982, pruned_loss=0.0281, over 4747.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03493, over 971948.17 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:41:18,903 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 09:41:28,535 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1915, pruned_loss=0.01118, over 914524.00 frames.
2022-05-06 09:42:08,252 INFO [train.py:715] (5/8) Epoch 9, batch 3050, loss[loss=0.1356, simple_loss=0.2046, pruned_loss=0.0333, over 4840.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2148, pruned_loss=0.03427, over 971899.12 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:42:47,736 INFO [train.py:715] (5/8) Epoch 9, batch 3100, loss[loss=0.1262, simple_loss=0.2045, pruned_loss=0.0239, over 4894.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2143, pruned_loss=0.03375, over 972466.99 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 09:43:27,212 INFO [train.py:715] (5/8) Epoch 9, batch 3150, loss[loss=0.1273, simple_loss=0.1932, pruned_loss=0.03067, over 4702.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03387, over 971832.85 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:44:06,423 INFO [train.py:715] (5/8) Epoch 9, batch 3200, loss[loss=0.149, simple_loss=0.2281, pruned_loss=0.03491, over 4865.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03436, over 971490.18 frames.], batch size: 20, lr: 2.40e-04
2022-05-06 09:44:45,579 INFO [train.py:715] (5/8) Epoch 9, batch 3250, loss[loss=0.1305, simple_loss=0.1987, pruned_loss=0.03115, over 4863.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03454, over 971792.52 frames.], batch size: 20, lr: 2.40e-04
2022-05-06 09:45:24,837 INFO [train.py:715] (5/8) Epoch 9, batch 3300, loss[loss=0.1426, simple_loss=0.207, pruned_loss=0.03912, over 4963.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03446, over 971815.40 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:46:03,682 INFO [train.py:715] (5/8) Epoch 9, batch 3350, loss[loss=0.141, simple_loss=0.2116, pruned_loss=0.03516, over 4795.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03456, over 972310.09 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 09:46:42,964 INFO [train.py:715] (5/8) Epoch 9, batch 3400, loss[loss=0.1205, simple_loss=0.2048, pruned_loss=0.01813, over 4777.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03451, over 971479.61 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 09:47:22,089 INFO [train.py:715] (5/8) Epoch 9, batch 3450, loss[loss=0.1729, simple_loss=0.2378, pruned_loss=0.05397, over 4712.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.0353, over 971461.43 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:48:00,726 INFO [train.py:715] (5/8) Epoch 9, batch 3500, loss[loss=0.1528, simple_loss=0.2182, pruned_loss=0.04372, over 4817.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03539, over 971764.47 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 09:48:40,283 INFO [train.py:715] (5/8) Epoch 9, batch 3550, loss[loss=0.1466, simple_loss=0.2122, pruned_loss=0.04049, over 4694.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03545, over 970750.56 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:49:19,727 INFO [train.py:715] (5/8) Epoch 9, batch 3600, loss[loss=0.159, simple_loss=0.2379, pruned_loss=0.0401, over 4919.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03523, over 971318.23 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:49:59,014 INFO [train.py:715] (5/8) Epoch 9, batch 3650, loss[loss=0.1389, simple_loss=0.2147, pruned_loss=0.03156, over 4894.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03535, over 970792.36 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 09:50:37,658 INFO [train.py:715] (5/8) Epoch 9, batch 3700, loss[loss=0.1107, simple_loss=0.1927, pruned_loss=0.01436, over 4934.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03535, over 970794.53 frames.], batch size: 23, lr: 2.40e-04
2022-05-06 09:51:17,144 INFO [train.py:715] (5/8) Epoch 9, batch 3750, loss[loss=0.1167, simple_loss=0.1858, pruned_loss=0.02377, over 4861.00 frames.], tot_loss[loss=0.1427, simple_loss=0.215, pruned_loss=0.03524, over 970919.04 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 09:51:56,920 INFO [train.py:715] (5/8) Epoch 9, batch 3800, loss[loss=0.1396, simple_loss=0.2184, pruned_loss=0.03039, over 4945.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03539, over 971095.53 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 09:52:35,336 INFO [train.py:715] (5/8) Epoch 9, batch 3850, loss[loss=0.2125, simple_loss=0.2896, pruned_loss=0.06768, over 4806.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03549, over 970998.71 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 09:53:14,339 INFO [train.py:715] (5/8) Epoch 9, batch 3900, loss[loss=0.1662, simple_loss=0.2432, pruned_loss=0.04462, over 4863.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03569, over 970811.76 frames.], batch size: 32, lr: 2.40e-04
2022-05-06 09:53:53,826 INFO [train.py:715] (5/8) Epoch 9, batch 3950, loss[loss=0.169, simple_loss=0.2397, pruned_loss=0.0492, over 4868.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03568, over 971146.50 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:54:33,400 INFO [train.py:715] (5/8) Epoch 9, batch 4000, loss[loss=0.134, simple_loss=0.2088, pruned_loss=0.02964, over 4951.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03584, over 972119.57 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 09:55:12,123 INFO [train.py:715] (5/8) Epoch 9, batch 4050, loss[loss=0.1601, simple_loss=0.2338, pruned_loss=0.04316, over 4912.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.0357, over 972572.66 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 09:55:52,105 INFO [train.py:715] (5/8) Epoch 9, batch 4100, loss[loss=0.15, simple_loss=0.2154, pruned_loss=0.04229, over 4860.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03544, over 972885.67 frames.], batch size: 32, lr: 2.40e-04
2022-05-06 09:56:30,805 INFO [train.py:715] (5/8) Epoch 9, batch 4150, loss[loss=0.1285, simple_loss=0.2028, pruned_loss=0.02705, over 4894.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.03531, over 972781.60 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:57:10,159 INFO [train.py:715] (5/8) Epoch 9, batch 4200, loss[loss=0.1274, simple_loss=0.1997, pruned_loss=0.02751, over 4904.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2148, pruned_loss=0.03544, over 973066.02 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 09:57:49,720 INFO [train.py:715] (5/8) Epoch 9, batch 4250, loss[loss=0.1351, simple_loss=0.2011, pruned_loss=0.0345, over 4816.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03579, over 973265.66 frames.], batch size: 13, lr: 2.40e-04
2022-05-06 09:58:29,616 INFO [train.py:715] (5/8) Epoch 9, batch 4300, loss[loss=0.1667, simple_loss=0.2455, pruned_loss=0.04389, over 4906.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.03544, over 974138.99 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 09:59:09,595 INFO [train.py:715] (5/8) Epoch 9, batch 4350, loss[loss=0.1477, simple_loss=0.2158, pruned_loss=0.03985, over 4887.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03499, over 973449.18 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:59:48,191 INFO [train.py:715] (5/8) Epoch 9, batch 4400, loss[loss=0.1553, simple_loss=0.219, pruned_loss=0.04586, over 4968.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.0346, over 973301.16 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 10:00:27,687 INFO [train.py:715] (5/8) Epoch 9, batch 4450, loss[loss=0.1328, simple_loss=0.2093, pruned_loss=0.02817, over 4820.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03454, over 972562.84 frames.], batch size: 26, lr: 2.40e-04
2022-05-06 10:01:06,476 INFO [train.py:715] (5/8) Epoch 9, batch 4500, loss[loss=0.1303, simple_loss=0.1952, pruned_loss=0.03272, over 4889.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03421, over 972229.26 frames.], batch size: 22, lr: 2.40e-04
2022-05-06 10:01:45,448 INFO [train.py:715] (5/8) Epoch 9, batch 4550, loss[loss=0.1751, simple_loss=0.2489, pruned_loss=0.05072, over 4909.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03405, over 972531.25 frames.], batch size: 39, lr: 2.40e-04
2022-05-06 10:02:24,724 INFO [train.py:715] (5/8) Epoch 9, batch 4600, loss[loss=0.1203, simple_loss=0.1874, pruned_loss=0.02664, over 4957.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03384, over 972215.04 frames.], batch size: 29, lr: 2.40e-04
2022-05-06 10:03:04,291 INFO [train.py:715] (5/8) Epoch 9, batch 4650, loss[loss=0.1304, simple_loss=0.2066, pruned_loss=0.02708, over 4959.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03377, over 971700.92 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 10:03:43,899 INFO [train.py:715] (5/8) Epoch 9, batch 4700, loss[loss=0.1399, simple_loss=0.2057, pruned_loss=0.03705, over 4742.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03455, over 972866.07 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 10:04:22,845 INFO [train.py:715] (5/8) Epoch 9, batch 4750, loss[loss=0.1389, simple_loss=0.204, pruned_loss=0.03688, over 4949.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.0342, over 972621.20 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 10:05:02,420 INFO [train.py:715] (5/8) Epoch 9, batch 4800, loss[loss=0.1188, simple_loss=0.1992, pruned_loss=0.01923, over 4757.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03478, over 972888.19 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 10:05:41,419 INFO [train.py:715] (5/8) Epoch 9, batch 4850, loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04794, over 4909.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.0347, over 972802.21 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 10:06:20,852 INFO [train.py:715] (5/8) Epoch 9, batch 4900, loss[loss=0.1296, simple_loss=0.2067, pruned_loss=0.02627, over 4753.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03458, over 973072.64 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 10:06:59,736 INFO [train.py:715] (5/8) Epoch 9, batch 4950, loss[loss=0.1072, simple_loss=0.1719, pruned_loss=0.02131, over 4800.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03455, over 972312.73 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 10:07:39,113 INFO [train.py:715] (5/8) Epoch 9, batch 5000, loss[loss=0.1653, simple_loss=0.2381, pruned_loss=0.04629, over 4813.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03444, over 972447.88 frames.], batch size: 26, lr: 2.40e-04
2022-05-06 10:08:18,414 INFO [train.py:715] (5/8) Epoch 9, batch 5050, loss[loss=0.1201, simple_loss=0.1832, pruned_loss=0.02848, over 4738.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03454, over 972605.73 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 10:08:57,170 INFO [train.py:715] (5/8) Epoch 9, batch 5100, loss[loss=0.1346, simple_loss=0.2156, pruned_loss=0.02678, over 4699.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03446, over 972409.18 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 10:09:36,559 INFO [train.py:715] (5/8) Epoch 9, batch 5150, loss[loss=0.1517, simple_loss=0.2213, pruned_loss=0.04105, over 4768.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03441, over 972306.37 frames.], batch size: 14, lr: 2.40e-04
2022-05-06 10:10:15,462 INFO [train.py:715] (5/8) Epoch 9, batch 5200, loss[loss=0.1257, simple_loss=0.2006, pruned_loss=0.02539, over 4962.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03393, over 972083.43 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 10:10:54,747 INFO [train.py:715] (5/8) Epoch 9, batch 5250, loss[loss=0.1352, simple_loss=0.2155, pruned_loss=0.02747, over 4806.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03395, over 971029.53 frames.], batch size: 26, lr: 2.40e-04
2022-05-06 10:11:33,954 INFO [train.py:715] (5/8) Epoch 9, batch 5300, loss[loss=0.1209, simple_loss=0.1952, pruned_loss=0.02327, over 4934.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03424, over 969976.54 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:12:13,443 INFO [train.py:715] (5/8) Epoch 9, batch 5350, loss[loss=0.1265, simple_loss=0.2004, pruned_loss=0.02631, over 4984.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.0339, over 970973.25 frames.], batch size: 28, lr: 2.39e-04
2022-05-06 10:12:52,101 INFO [train.py:715] (5/8) Epoch 9, batch 5400, loss[loss=0.1385, simple_loss=0.2005, pruned_loss=0.0383, over 4839.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2149, pruned_loss=0.03446, over 972586.10 frames.], batch size: 32, lr: 2.39e-04
2022-05-06 10:13:30,896 INFO [train.py:715] (5/8) Epoch 9, batch 5450, loss[loss=0.1356, simple_loss=0.2107, pruned_loss=0.03023, over 4874.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2155, pruned_loss=0.03446, over 972631.43 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:14:10,209 INFO [train.py:715] (5/8) Epoch 9, batch 5500, loss[loss=0.1258, simple_loss=0.2045, pruned_loss=0.02354, over 4829.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03412, over 972736.16 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:14:49,295 INFO [train.py:715] (5/8) Epoch 9, batch 5550, loss[loss=0.119, simple_loss=0.2078, pruned_loss=0.01517, over 4818.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03423, over 973111.67 frames.], batch size: 25, lr: 2.39e-04
2022-05-06 10:15:28,465 INFO [train.py:715] (5/8) Epoch 9, batch 5600, loss[loss=0.1462, simple_loss=0.2255, pruned_loss=0.03349, over 4939.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03453, over 973505.80 frames.], batch size: 29, lr: 2.39e-04
2022-05-06 10:16:07,455 INFO [train.py:715] (5/8) Epoch 9, batch 5650, loss[loss=0.1365, simple_loss=0.2067, pruned_loss=0.03316, over 4901.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2153, pruned_loss=0.03473, over 973684.48 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:16:47,096 INFO [train.py:715] (5/8) Epoch 9, batch 5700, loss[loss=0.1397, simple_loss=0.2217, pruned_loss=0.02885, over 4920.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03512, over 973760.76 frames.], batch size: 18, lr: 2.39e-04
2022-05-06 10:17:26,139 INFO [train.py:715] (5/8) Epoch 9, batch 5750, loss[loss=0.1013, simple_loss=0.1684, pruned_loss=0.01707, over 4843.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03509, over 973456.86 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:18:04,786 INFO [train.py:715] (5/8) Epoch 9, batch 5800, loss[loss=0.1559, simple_loss=0.2198, pruned_loss=0.04599, over 4923.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03545, over 972302.67 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:18:44,315 INFO [train.py:715] (5/8) Epoch 9, batch 5850, loss[loss=0.1316, simple_loss=0.2101, pruned_loss=0.02654, over 4826.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03556, over 972364.65 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:19:23,125 INFO [train.py:715] (5/8) Epoch 9, batch 5900, loss[loss=0.1809, simple_loss=0.2461, pruned_loss=0.0579, over 4827.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03551, over 972435.64 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:20:02,776 INFO [train.py:715] (5/8) Epoch 9, batch 5950, loss[loss=0.1291, simple_loss=0.202, pruned_loss=0.02812, over 4748.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03536, over 973335.07 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:20:41,533 INFO [train.py:715] (5/8) Epoch 9, batch 6000, loss[loss=0.1484, simple_loss=0.2174, pruned_loss=0.03968, over 4964.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03493, over 973520.24 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:20:41,534 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 10:20:51,193 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
2022-05-06 10:21:30,899 INFO [train.py:715] (5/8) Epoch 9, batch 6050, loss[loss=0.1338, simple_loss=0.2125, pruned_loss=0.02758, over 4871.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03471, over 973105.31 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:22:10,769 INFO [train.py:715] (5/8) Epoch 9, batch 6100, loss[loss=0.1123, simple_loss=0.1884, pruned_loss=0.01809, over 4926.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.0348, over 973451.52 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:22:49,971 INFO [train.py:715] (5/8) Epoch 9, batch 6150, loss[loss=0.1507, simple_loss=0.22, pruned_loss=0.0407, over 4942.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2151, pruned_loss=0.03415, over 973612.92 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:23:28,784 INFO [train.py:715] (5/8) Epoch 9, batch 6200, loss[loss=0.1349, simple_loss=0.2053, pruned_loss=0.0322, over 4931.00 frames.], tot_loss[loss=0.141, simple_loss=0.2142, pruned_loss=0.0339, over 972943.22 frames.], batch size: 18, lr: 2.39e-04
2022-05-06 10:24:08,425 INFO [train.py:715] (5/8) Epoch 9, batch 6250, loss[loss=0.1241, simple_loss=0.2132, pruned_loss=0.01752, over 4979.00 frames.], tot_loss[loss=0.1406, simple_loss=0.214, pruned_loss=0.03358, over 972132.53 frames.], batch size: 28, lr: 2.39e-04
2022-05-06 10:24:47,200 INFO [train.py:715] (5/8) Epoch 9, batch 6300, loss[loss=0.1405, simple_loss=0.2141, pruned_loss=0.03345, over 4697.00 frames.], tot_loss[loss=0.1408, simple_loss=0.214, pruned_loss=0.03378, over 971553.50 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:25:26,318 INFO [train.py:715] (5/8) Epoch 9, batch 6350, loss[loss=0.1125, simple_loss=0.195, pruned_loss=0.01495, over 4980.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.0341, over 971896.16 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:26:05,951 INFO [train.py:715] (5/8) Epoch 9, batch 6400, loss[loss=0.1222, simple_loss=0.1967, pruned_loss=0.02384, over 4937.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03448, over 971661.97 frames.], batch size: 29, lr: 2.39e-04
2022-05-06 10:26:46,098 INFO [train.py:715] (5/8) Epoch 9, batch 6450, loss[loss=0.1366, simple_loss=0.2214, pruned_loss=0.0259, over 4888.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03462, over 972463.23 frames.], batch size: 22, lr: 2.39e-04
2022-05-06 10:27:25,423 INFO [train.py:715] (5/8) Epoch 9, batch 6500, loss[loss=0.1562, simple_loss=0.2296, pruned_loss=0.04136, over 4893.00 frames.], tot_loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03459, over 973172.48 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:28:04,255 INFO [train.py:715] (5/8) Epoch 9, batch 6550, loss[loss=0.134, simple_loss=0.2049, pruned_loss=0.03152, over 4968.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03462, over 972842.95 frames.], batch size: 35, lr: 2.39e-04
2022-05-06 10:28:44,035 INFO [train.py:715] (5/8) Epoch 9, batch 6600, loss[loss=0.1513, simple_loss=0.2355, pruned_loss=0.03354, over 4955.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03522, over 973222.34 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:29:23,594 INFO [train.py:715] (5/8) Epoch 9, batch 6650, loss[loss=0.1511, simple_loss=0.2209, pruned_loss=0.04069, over 4886.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03476, over 973060.50 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:30:02,748 INFO [train.py:715] (5/8) Epoch 9, batch 6700, loss[loss=0.1251, simple_loss=0.203, pruned_loss=0.02363, over 4796.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03484, over 972908.84 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:30:44,170 INFO [train.py:715] (5/8) Epoch 9, batch 6750, loss[loss=0.1758, simple_loss=0.2429, pruned_loss=0.05437, over 4877.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03467, over 972311.49 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:31:23,603 INFO [train.py:715] (5/8) Epoch 9, batch 6800, loss[loss=0.1813, simple_loss=0.2499, pruned_loss=0.05632, over 4860.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03456, over 972528.84 frames.], batch size: 38, lr: 2.39e-04
2022-05-06 10:32:02,562 INFO [train.py:715] (5/8) Epoch 9, batch 6850, loss[loss=0.1196, simple_loss=0.1905, pruned_loss=0.02431, over 4934.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03369, over 973076.21 frames.], batch size: 23, lr: 2.39e-04
2022-05-06 10:32:40,755 INFO [train.py:715] (5/8) Epoch 9, batch 6900, loss[loss=0.1342, simple_loss=0.1991, pruned_loss=0.0347, over 4873.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03359, over 973072.63 frames.], batch size: 20, lr: 2.39e-04
2022-05-06 10:33:20,058 INFO [train.py:715] (5/8) Epoch 9, batch 6950, loss[loss=0.1478, simple_loss=0.2161, pruned_loss=0.03981, over 4828.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.03337, over 972149.52 frames.], batch size: 30, lr: 2.39e-04
2022-05-06 10:33:59,862 INFO [train.py:715] (5/8) Epoch 9, batch 7000, loss[loss=0.1513, simple_loss=0.2151, pruned_loss=0.04378, over 4880.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03362, over 972075.45 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:34:38,726 INFO [train.py:715] (5/8) Epoch 9, batch 7050, loss[loss=0.1439, simple_loss=0.2213, pruned_loss=0.03327, over 4937.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03423, over 972370.50 frames.], batch size: 23, lr: 2.39e-04
2022-05-06 10:35:17,346 INFO [train.py:715] (5/8) Epoch 9, batch 7100, loss[loss=0.1409, simple_loss=0.2131, pruned_loss=0.03439, over 4919.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03435, over 973004.27 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:35:56,809 INFO [train.py:715] (5/8) Epoch 9, batch 7150, loss[loss=0.1189, simple_loss=0.1971, pruned_loss=0.02035, over 4688.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03422, over 972683.38 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:36:35,504 INFO [train.py:715] (5/8) Epoch 9, batch 7200, loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03277, over 4774.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03445, over 972400.25 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:37:14,247 INFO [train.py:715] (5/8) Epoch 9, batch 7250, loss[loss=0.1565, simple_loss=0.2268, pruned_loss=0.04312, over 4920.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2132, pruned_loss=0.03432, over 972518.16 frames.], batch size: 29, lr: 2.39e-04
2022-05-06 10:37:53,495 INFO [train.py:715] (5/8) Epoch 9, batch 7300, loss[loss=0.1339, simple_loss=0.1928, pruned_loss=0.03745, over 4828.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03487, over 972920.55 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:38:32,800 INFO [train.py:715] (5/8) Epoch 9, batch 7350, loss[loss=0.1242, simple_loss=0.1991, pruned_loss=0.02469, over 4794.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03443, over 972416.21 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:39:11,299 INFO [train.py:715] (5/8) Epoch 9, batch 7400, loss[loss=0.1353, simple_loss=0.2062, pruned_loss=0.03219, over 4871.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03523, over 972853.38 frames.], batch size: 30, lr: 2.39e-04
2022-05-06 10:39:50,257 INFO [train.py:715] (5/8) Epoch 9, batch 7450, loss[loss=0.1283, simple_loss=0.2018, pruned_loss=0.02744, over 4737.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03567, over 972668.93 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:40:30,202 INFO [train.py:715] (5/8) Epoch 9, batch 7500, loss[loss=0.1667, simple_loss=0.2378, pruned_loss=0.04786, over 4884.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03603, over 972953.87 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:41:09,246 INFO [train.py:715] (5/8) Epoch 9, batch 7550, loss[loss=0.1577, simple_loss=0.24, pruned_loss=0.03772, over 4916.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03574, over 973262.88 frames.], batch size: 23, lr: 2.39e-04
2022-05-06 10:41:48,087 INFO [train.py:715] (5/8) Epoch 9, batch 7600, loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.0288, over 4815.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03586, over 973034.96 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:42:27,544 INFO [train.py:715] (5/8) Epoch 9, batch 7650, loss[loss=0.1306, simple_loss=0.1991, pruned_loss=0.03108, over 4847.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03558, over 973420.09 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:43:06,739 INFO [train.py:715] (5/8) Epoch 9, batch 7700, loss[loss=0.1269, simple_loss=0.1959, pruned_loss=0.02892, over 4789.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03522, over 972288.56 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:43:45,563 INFO [train.py:715] (5/8) Epoch 9, batch 7750, loss[loss=0.147, simple_loss=0.2227, pruned_loss=0.03563, over 4856.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03508, over 972673.75 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:44:24,376 INFO [train.py:715] (5/8) Epoch 9, batch 7800, loss[loss=0.1305, simple_loss=0.1937, pruned_loss=0.0336, over 4818.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03471, over 972638.09 frames.], batch size: 13, lr: 2.39e-04
2022-05-06 10:45:04,415 INFO [train.py:715] (5/8) Epoch 9, batch 7850, loss[loss=0.1628, simple_loss=0.2419, pruned_loss=0.04186, over 4773.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03479, over 972601.93 frames.], batch size: 18, lr: 2.39e-04
2022-05-06 10:45:43,393 INFO [train.py:715] (5/8) Epoch 9, batch 7900, loss[loss=0.1547, simple_loss=0.2262, pruned_loss=0.04161, over 4936.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03505, over 972619.45 frames.], batch size: 29, lr: 2.39e-04
2022-05-06 10:46:21,528 INFO [train.py:715] (5/8) Epoch 9, batch 7950, loss[loss=0.1068, simple_loss=0.1708, pruned_loss=0.02139, over 4750.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03531, over 972419.99 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:47:00,914 INFO [train.py:715] (5/8) Epoch 9, batch 8000, loss[loss=0.1131, simple_loss=0.1882, pruned_loss=0.01903, over 4993.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03551, over 972655.27 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 10:47:39,936 INFO [train.py:715] (5/8) Epoch 9, batch 8050, loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03295, over 4855.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.0353, over 973894.31 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 10:48:18,557 INFO [train.py:715] (5/8) Epoch 9, batch 8100, loss[loss=0.135, simple_loss=0.2112, pruned_loss=0.02938, over 4953.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03535, over 973237.74 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 10:48:57,110 INFO [train.py:715] (5/8) Epoch 9, batch 8150, loss[loss=0.1173, simple_loss=0.1947, pruned_loss=0.01998, over 4902.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03539, over 973495.92 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 10:49:36,458 INFO [train.py:715] (5/8) Epoch 9, batch 8200, loss[loss=0.1563, simple_loss=0.2308, pruned_loss=0.04088, over 4829.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03573, over 972909.96 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 10:50:15,123 INFO [train.py:715] (5/8) Epoch 9, batch 8250, loss[loss=0.1418, simple_loss=0.2158, pruned_loss=0.03394, over 4919.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03552, over 972787.61 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 10:50:53,695 INFO [train.py:715] (5/8) Epoch 9, batch 8300, loss[loss=0.1473, simple_loss=0.2267, pruned_loss=0.03399, over 4986.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03531, over 973154.82 frames.], batch size: 25, lr: 2.38e-04
2022-05-06 10:51:32,738 INFO [train.py:715] (5/8) Epoch 9, batch 8350, loss[loss=0.1356, simple_loss=0.2108, pruned_loss=0.03017, over 4777.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03506, over 971863.96 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 10:52:12,414 INFO [train.py:715] (5/8) Epoch 9, batch 8400, loss[loss=0.1511, simple_loss=0.2209, pruned_loss=0.04062, over 4994.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03539, over 972786.89 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 10:52:50,770 INFO [train.py:715] (5/8) Epoch 9, batch 8450, loss[loss=0.1641, simple_loss=0.2364, pruned_loss=0.04592, over 4953.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2139, pruned_loss=0.0349, over 972631.11 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 10:53:29,411 INFO [train.py:715] (5/8) Epoch 9, batch 8500, loss[loss=0.1529, simple_loss=0.2209, pruned_loss=0.04251, over 4847.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2135, pruned_loss=0.03493, over 971511.38 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 10:54:08,957 INFO [train.py:715] (5/8) Epoch 9, batch 8550, loss[loss=0.1633, simple_loss=0.2385, pruned_loss=0.04403, over 4941.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2138, pruned_loss=0.03495, over 971650.27 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 10:54:48,127 INFO [train.py:715] (5/8) Epoch 9, batch 8600, loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03274, over 4913.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03502, over 971492.88 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 10:55:26,985 INFO [train.py:715] (5/8) Epoch 9, batch 8650, loss[loss=0.1286, simple_loss=0.2044, pruned_loss=0.02635, over 4926.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03502, over 972262.29 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 10:56:06,798 INFO [train.py:715] (5/8) Epoch 9, batch 8700, loss[loss=0.1439, simple_loss=0.2332, pruned_loss=0.02731, over 4778.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2143, pruned_loss=0.03547, over 972568.81 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 10:56:46,699 INFO [train.py:715] (5/8) Epoch 9, batch 8750, loss[loss=0.1191, simple_loss=0.1928, pruned_loss=0.02272, over 4928.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03524, over 972951.84 frames.], batch size: 29, lr: 2.38e-04
2022-05-06 10:57:25,007 INFO [train.py:715] (5/8) Epoch 9, batch 8800, loss[loss=0.1626, simple_loss=0.2286, pruned_loss=0.04828, over 4824.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03462, over 972194.70 frames.], batch size: 30, lr: 2.38e-04
2022-05-06 10:58:04,393 INFO [train.py:715] (5/8) Epoch 9, batch 8850, loss[loss=0.1676, simple_loss=0.2353, pruned_loss=0.04997, over 4812.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03446, over 971799.90 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 10:58:43,838 INFO [train.py:715] (5/8) Epoch 9, batch 8900, loss[loss=0.1498, simple_loss=0.2256, pruned_loss=0.037, over 4915.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03421, over 971757.27 frames.], batch size: 19, lr: 2.38e-04
2022-05-06 10:59:22,968 INFO [train.py:715] (5/8) Epoch 9, batch 8950, loss[loss=0.1219, simple_loss=0.1939, pruned_loss=0.02495, over 4992.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03432, over 972183.81 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:00:01,615 INFO [train.py:715] (5/8) Epoch 9, batch 9000, loss[loss=0.1443, simple_loss=0.2152, pruned_loss=0.03668, over 4806.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03478, over 971971.47 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 11:00:01,616 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 11:00:11,231 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
2022-05-06 11:00:49,915 INFO [train.py:715] (5/8) Epoch 9, batch 9050, loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 4763.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03467, over 972044.96 frames.], batch size: 19, lr: 2.38e-04
2022-05-06 11:01:30,080 INFO [train.py:715] (5/8) Epoch 9, batch 9100, loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03761, over 4911.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03555, over 972028.10 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:02:09,667 INFO [train.py:715] (5/8) Epoch 9, batch 9150, loss[loss=0.12, simple_loss=0.191, pruned_loss=0.02446, over 4880.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2158, pruned_loss=0.03502, over 971708.85 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 11:02:48,634 INFO [train.py:715] (5/8) Epoch 9, batch 9200, loss[loss=0.1712, simple_loss=0.2376, pruned_loss=0.05244, over 4773.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03578, over 971131.41 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:03:28,185 INFO [train.py:715] (5/8) Epoch 9, batch 9250, loss[loss=0.1299, simple_loss=0.2062, pruned_loss=0.0268, over 4977.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03505, over 971858.65 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 11:04:07,598 INFO [train.py:715] (5/8) Epoch 9, batch 9300, loss[loss=0.145, simple_loss=0.2164, pruned_loss=0.03678, over 4960.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03493, over 972130.97 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 11:04:46,766 INFO [train.py:715] (5/8) Epoch 9, batch 9350, loss[loss=0.1507, simple_loss=0.2259, pruned_loss=0.03778, over 4917.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03502, over 972007.51 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 11:05:25,228 INFO [train.py:715] (5/8) Epoch 9, batch 9400, loss[loss=0.1116, simple_loss=0.1765, pruned_loss=0.0234, over 4831.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03488, over 971445.38 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 11:06:05,136 INFO [train.py:715] (5/8) Epoch 9, batch 9450, loss[loss=0.1449, simple_loss=0.2193, pruned_loss=0.03522, over 4939.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03442, over 971753.69 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 11:06:44,276 INFO [train.py:715] (5/8) Epoch 9, batch 9500, loss[loss=0.1528, simple_loss=0.2225, pruned_loss=0.0415, over 4884.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03389, over 972455.61 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:07:22,928 INFO [train.py:715] (5/8) Epoch 9, batch 9550, loss[loss=0.1344, simple_loss=0.1976, pruned_loss=0.03562, over 4707.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03415, over 972162.20 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:08:02,126 INFO [train.py:715] (5/8) Epoch 9, batch 9600, loss[loss=0.1345, simple_loss=0.2101, pruned_loss=0.02947, over 4800.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03376, over 971121.75 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:08:41,396 INFO [train.py:715] (5/8) Epoch 9, batch 9650, loss[loss=0.1331, simple_loss=0.2018, pruned_loss=0.0322, over 4818.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03447, over 971102.92 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:09:20,425 INFO [train.py:715] (5/8) Epoch 9, batch 9700, loss[loss=0.1618, simple_loss=0.2353, pruned_loss=0.04415, over 4743.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03461, over 971060.31 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 11:09:58,453 INFO [train.py:715] (5/8) Epoch 9, batch 9750, loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04255, over 4867.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03466, over 972054.25 frames.], batch size: 38, lr: 2.38e-04
2022-05-06 11:10:38,590 INFO [train.py:715] (5/8) Epoch 9, batch 9800, loss[loss=0.1493, simple_loss=0.229, pruned_loss=0.03486, over 4923.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.0348, over 971909.30 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:11:18,275 INFO [train.py:715] (5/8) Epoch 9, batch 9850, loss[loss=0.1455, simple_loss=0.2071, pruned_loss=0.04192, over 4981.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03499, over 972344.78 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:11:56,611 INFO [train.py:715] (5/8) Epoch 9, batch 9900, loss[loss=0.1413, simple_loss=0.2095, pruned_loss=0.03649, over 4829.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2149, pruned_loss=0.03431, over 972653.38 frames.], batch size: 26, lr: 2.38e-04
2022-05-06 11:12:35,820 INFO [train.py:715] (5/8) Epoch 9, batch 9950, loss[loss=0.1399, simple_loss=0.2172, pruned_loss=0.03134, over 4744.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2159, pruned_loss=0.03517, over 973466.89 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 11:13:15,753 INFO [train.py:715] (5/8) Epoch 9, batch 10000, loss[loss=0.1142, simple_loss=0.1907, pruned_loss=0.01885, over 4936.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03442, over 972651.28 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:13:55,091 INFO [train.py:715] (5/8) Epoch 9, batch 10050, loss[loss=0.1388, simple_loss=0.2038, pruned_loss=0.03693, over 4773.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03454, over 972611.77 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:14:33,374 INFO [train.py:715] (5/8) Epoch 9, batch 10100, loss[loss=0.1419, simple_loss=0.2222, pruned_loss=0.03078, over 4901.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03462, over 972793.72 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:15:12,911 INFO [train.py:715] (5/8) Epoch 9, batch 10150, loss[loss=0.1776, simple_loss=0.2431, pruned_loss=0.05603, over 4974.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03484, over 972001.18 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:15:52,570 INFO [train.py:715] (5/8) Epoch 9, batch 10200, loss[loss=0.1724, simple_loss=0.2456, pruned_loss=0.04955, over 4989.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03442, over 971693.39 frames.], batch size: 20, lr: 2.38e-04
2022-05-06 11:16:31,360 INFO [train.py:715] (5/8) Epoch 9, batch 10250, loss[loss=0.1547, simple_loss=0.2293, pruned_loss=0.04008, over 4877.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03463, over 971683.70 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:17:10,102 INFO [train.py:715] (5/8) Epoch 9, batch 10300, loss[loss=0.1323, simple_loss=0.2019, pruned_loss=0.03135, over 4755.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03439, over 972158.78 frames.], batch size: 19, lr: 2.38e-04
2022-05-06 11:17:49,727 INFO [train.py:715] (5/8) Epoch 9, batch 10350, loss[loss=0.1492, simple_loss=0.2197, pruned_loss=0.03939, over 4958.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03432, over 972311.68 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 11:18:28,422 INFO [train.py:715] (5/8) Epoch 9, batch 10400, loss[loss=0.1329, simple_loss=0.203, pruned_loss=0.03134, over 4890.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03482, over 971997.55 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:19:06,741 INFO [train.py:715] (5/8) Epoch 9, batch 10450, loss[loss=0.1336, simple_loss=0.2114, pruned_loss=0.0279, over 4875.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03499, over 972232.23 frames.], batch size: 20, lr: 2.38e-04
2022-05-06 11:19:45,850 INFO [train.py:715] (5/8) Epoch 9, batch 10500, loss[loss=0.1275, simple_loss=0.2021, pruned_loss=0.02648, over 4788.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.0351, over 971981.08 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:20:25,290 INFO [train.py:715] (5/8) Epoch 9, batch 10550, loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03087, over 4966.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.0342, over 971197.84 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 11:21:04,102 INFO [train.py:715] (5/8) Epoch 9, batch 10600, loss[loss=0.1621, simple_loss=0.2239, pruned_loss=0.05017, over 4960.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03444, over 972341.89 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:21:42,610 INFO [train.py:715] (5/8) Epoch 9, batch 10650, loss[loss=0.17, simple_loss=0.2418, pruned_loss=0.04912, over 4866.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.0352, over 972847.59 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:22:21,916 INFO [train.py:715] (5/8) Epoch 9, batch 10700, loss[loss=0.1552, simple_loss=0.2118, pruned_loss=0.0493, over 4830.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.0352, over 972432.52 frames.], batch size: 30, lr: 2.37e-04
2022-05-06 11:23:01,947 INFO [train.py:715] (5/8) Epoch 9, batch 10750, loss[loss=0.1881, simple_loss=0.266, pruned_loss=0.0551, over 4693.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03491, over 971926.51 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:23:40,542 INFO [train.py:715] (5/8) Epoch 9, batch 10800, loss[loss=0.1321, simple_loss=0.2093, pruned_loss=0.02747, over 4910.00 frames.], tot_loss[loss=0.1421, simple_loss=0.214, pruned_loss=0.03511, over 971263.54 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:24:20,020 INFO [train.py:715] (5/8) Epoch 9, batch 10850, loss[loss=0.1444, simple_loss=0.2148, pruned_loss=0.03693, over 4831.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.03541, over 972081.29 frames.], batch size: 27, lr: 2.37e-04
2022-05-06 11:24:59,850 INFO [train.py:715] (5/8) Epoch 9, batch 10900, loss[loss=0.138, simple_loss=0.1967, pruned_loss=0.03961, over 4965.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2143, pruned_loss=0.03522, over 971971.19 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:25:40,159 INFO [train.py:715] (5/8) Epoch 9, batch 10950, loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03229, over 4976.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2138, pruned_loss=0.03532, over 972081.15 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:26:20,014 INFO [train.py:715] (5/8) Epoch 9, batch 11000, loss[loss=0.1326, simple_loss=0.2056, pruned_loss=0.02983, over 4780.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.035, over 971953.23 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:27:00,851 INFO [train.py:715] (5/8) Epoch 9, batch 11050, loss[loss=0.09981, simple_loss=0.1767, pruned_loss=0.01145, over 4815.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2135, pruned_loss=0.03487, over 971431.35 frames.], batch size: 13, lr: 2.37e-04
2022-05-06 11:27:42,119 INFO [train.py:715] (5/8) Epoch 9, batch 11100, loss[loss=0.1519, simple_loss=0.2313, pruned_loss=0.03627, over 4952.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03545, over 972207.46 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:28:22,782 INFO [train.py:715] (5/8) Epoch 9, batch 11150, loss[loss=0.1395, simple_loss=0.2061, pruned_loss=0.03647, over 4848.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03541, over 972221.24 frames.], batch size: 32, lr: 2.37e-04
2022-05-06 11:29:03,600 INFO [train.py:715] (5/8) Epoch 9, batch 11200, loss[loss=0.1245, simple_loss=0.1996, pruned_loss=0.02473, over 4743.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03563, over 971920.73 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:29:45,085 INFO [train.py:715] (5/8) Epoch 9, batch 11250, loss[loss=0.1305, simple_loss=0.2047, pruned_loss=0.02817, over 4856.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.03499, over 972026.72 frames.], batch size: 20, lr: 2.37e-04
2022-05-06 11:30:26,204 INFO [train.py:715] (5/8) Epoch 9, batch 11300, loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03094, over 4887.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03476, over 972110.43 frames.], batch size: 22, lr: 2.37e-04
2022-05-06 11:31:06,657 INFO [train.py:715] (5/8) Epoch 9, batch 11350, loss[loss=0.1322, simple_loss=0.2038, pruned_loss=0.0303, over 4933.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03447, over 972221.66 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:31:47,932 INFO [train.py:715] (5/8) Epoch 9, batch 11400, loss[loss=0.1376, simple_loss=0.2161, pruned_loss=0.02952, over 4941.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03433, over 972244.19 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:32:29,496 INFO [train.py:715] (5/8) Epoch 9, batch 11450, loss[loss=0.1333, simple_loss=0.2007, pruned_loss=0.03297, over 4989.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03472, over 972724.67 frames.], batch size: 25, lr: 2.37e-04
2022-05-06 11:33:10,076 INFO [train.py:715] (5/8) Epoch 9, batch 11500, loss[loss=0.1236, simple_loss=0.1957, pruned_loss=0.02571, over 4796.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03468, over 972496.94 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:33:50,771 INFO [train.py:715] (5/8) Epoch 9, batch 11550, loss[loss=0.1476, simple_loss=0.2146, pruned_loss=0.04028, over 4782.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03455, over 972754.95 frames.], batch size: 12, lr: 2.37e-04
2022-05-06 11:34:32,087 INFO [train.py:715] (5/8) Epoch 9, batch 11600, loss[loss=0.16, simple_loss=0.219, pruned_loss=0.05052, over 4832.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03455, over 972887.42 frames.], batch size: 13, lr: 2.37e-04
2022-05-06 11:35:13,602 INFO [train.py:715] (5/8) Epoch 9, batch 11650, loss[loss=0.1557, simple_loss=0.2226, pruned_loss=0.0444, over 4971.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.0342, over 972666.39 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:35:53,523 INFO [train.py:715] (5/8) Epoch 9, batch 11700, loss[loss=0.13, simple_loss=0.1992, pruned_loss=0.0304, over 4781.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03431, over 972530.97 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:36:34,965 INFO [train.py:715] (5/8) Epoch 9, batch 11750, loss[loss=0.1448, simple_loss=0.2256, pruned_loss=0.03198, over 4931.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03407, over 973370.72 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:37:16,469 INFO [train.py:715] (5/8) Epoch 9, batch 11800, loss[loss=0.1527, simple_loss=0.2198, pruned_loss=0.04284, over 4955.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03426, over 974295.99 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:37:56,812 INFO [train.py:715] (5/8) Epoch 9, batch 11850, loss[loss=0.1498, simple_loss=0.2127, pruned_loss=0.04342, over 4817.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03407, over 972975.74 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:38:37,232 INFO [train.py:715] (5/8) Epoch 9, batch 11900, loss[loss=0.1259, simple_loss=0.2054, pruned_loss=0.0232, over 4818.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2133, pruned_loss=0.03451, over 973650.45 frames.], batch size: 27, lr: 2.37e-04
2022-05-06 11:39:18,261 INFO [train.py:715] (5/8) Epoch 9, batch 11950, loss[loss=0.1664, simple_loss=0.2418, pruned_loss=0.04553, over 4903.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03458, over 973502.34 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:39:59,370 INFO [train.py:715] (5/8) Epoch 9, batch 12000, loss[loss=0.1433, simple_loss=0.2241, pruned_loss=0.03129, over 4931.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03496, over 973970.25 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:39:59,370 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 11:40:09,084 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.107, simple_loss=0.1913, pruned_loss=0.01136, over 914524.00 frames.
2022-05-06 11:40:50,126 INFO [train.py:715] (5/8) Epoch 9, batch 12050, loss[loss=0.1175, simple_loss=0.1919, pruned_loss=0.02159, over 4842.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03494, over 973975.98 frames.], batch size: 30, lr: 2.37e-04
2022-05-06 11:41:29,628 INFO [train.py:715] (5/8) Epoch 9, batch 12100, loss[loss=0.1144, simple_loss=0.1948, pruned_loss=0.01701, over 4849.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03467, over 973290.69 frames.], batch size: 13, lr: 2.37e-04
2022-05-06 11:42:10,006 INFO [train.py:715] (5/8) Epoch 9, batch 12150, loss[loss=0.1171, simple_loss=0.1884, pruned_loss=0.02287, over 4842.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.0348, over 973897.71 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:42:50,009 INFO [train.py:715] (5/8) Epoch 9, batch 12200, loss[loss=0.1406, simple_loss=0.2158, pruned_loss=0.03273, over 4863.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2142, pruned_loss=0.03503, over 973323.97 frames.], batch size: 20, lr: 2.37e-04
2022-05-06 11:43:29,295 INFO [train.py:715] (5/8) Epoch 9, batch 12250, loss[loss=0.1482, simple_loss=0.2305, pruned_loss=0.03298, over 4797.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03516, over 973101.65 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:44:08,223 INFO [train.py:715] (5/8) Epoch 9, batch 12300, loss[loss=0.142, simple_loss=0.2076, pruned_loss=0.03824, over 4971.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03507, over 973340.24 frames.], batch size: 35, lr: 2.37e-04
2022-05-06 11:44:47,991 INFO [train.py:715] (5/8) Epoch 9, batch 12350, loss[loss=0.1766, simple_loss=0.239, pruned_loss=0.05703, over 4848.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.035, over 973155.51 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:45:28,031 INFO [train.py:715] (5/8) Epoch 9, batch 12400, loss[loss=0.1595, simple_loss=0.2408, pruned_loss=0.03912, over 4754.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03432, over 972939.35 frames.], batch size: 19, lr: 2.37e-04
2022-05-06 11:46:07,545 INFO [train.py:715] (5/8) Epoch 9, batch 12450, loss[loss=0.1348, simple_loss=0.2033, pruned_loss=0.03317, over 4871.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03436, over 972503.47 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:46:47,602 INFO [train.py:715] (5/8) Epoch 9, batch 12500, loss[loss=0.126, simple_loss=0.1971, pruned_loss=0.02748, over 4931.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03457, over 972318.59 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:47:27,736 INFO [train.py:715] (5/8) Epoch 9, batch 12550, loss[loss=0.1348, simple_loss=0.2009, pruned_loss=0.03433, over 4915.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03491, over 972189.80 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:48:07,695 INFO [train.py:715] (5/8) Epoch 9, batch 12600, loss[loss=0.141, simple_loss=0.2175, pruned_loss=0.03229, over 4901.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03442, over 971239.26 frames.], batch size: 19, lr: 2.37e-04
2022-05-06 11:48:46,466 INFO [train.py:715] (5/8) Epoch 9, batch 12650, loss[loss=0.1613, simple_loss=0.2374, pruned_loss=0.04259, over 4871.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03468, over 972413.32 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:49:26,600 INFO [train.py:715] (5/8) Epoch 9, batch 12700, loss[loss=0.131, simple_loss=0.2013, pruned_loss=0.03038, over 4803.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03482, over 972695.68 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:50:06,591 INFO [train.py:715] (5/8) Epoch 9, batch 12750, loss[loss=0.1526, simple_loss=0.2355, pruned_loss=0.03482, over 4797.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03449, over 971946.39 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:50:45,759 INFO [train.py:715] (5/8) Epoch 9, batch 12800, loss[loss=0.1185, simple_loss=0.1951, pruned_loss=0.02096, over 4926.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03481, over 972880.04 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:51:25,603 INFO [train.py:715] (5/8) Epoch 9, batch 12850, loss[loss=0.1337, simple_loss=0.2144, pruned_loss=0.02652, over 4785.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03511, over 972273.29 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:52:05,499 INFO [train.py:715] (5/8) Epoch 9, batch 12900, loss[loss=0.1418, simple_loss=0.2125, pruned_loss=0.03553, over 4888.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03572, over 972834.22 frames.], batch size: 19, lr: 2.37e-04
2022-05-06 11:52:45,475 INFO [train.py:715] (5/8) Epoch 9, batch 12950, loss[loss=0.1217, simple_loss=0.202, pruned_loss=0.02071, over 4791.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03588, over 972963.74 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:53:24,502 INFO [train.py:715] (5/8) Epoch 9, batch 13000, loss[loss=0.1226, simple_loss=0.1895, pruned_loss=0.02792, over 4798.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03579, over 973195.29 frames.], batch size: 12, lr: 2.37e-04
2022-05-06 11:54:04,860 INFO [train.py:715] (5/8) Epoch 9, batch 13050, loss[loss=0.1469, simple_loss=0.2228, pruned_loss=0.03549, over 4868.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03596, over 972363.49 frames.], batch size: 22, lr: 2.37e-04
2022-05-06 11:54:44,622 INFO [train.py:715] (5/8) Epoch 9, batch 13100, loss[loss=0.127, simple_loss=0.2013, pruned_loss=0.02631, over 4859.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03581, over 972579.04 frames.], batch size: 20, lr: 2.37e-04
2022-05-06 11:55:23,866 INFO [train.py:715] (5/8) Epoch 9, batch 13150, loss[loss=0.1438, simple_loss=0.2084, pruned_loss=0.03961, over 4748.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2161, pruned_loss=0.03558, over 972093.99 frames.], batch size: 19, lr: 2.37e-04
2022-05-06 11:56:03,855 INFO [train.py:715] (5/8) Epoch 9, batch 13200, loss[loss=0.1427, simple_loss=0.2064, pruned_loss=0.03952, over 4886.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03553, over 971712.22 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:56:44,165 INFO [train.py:715] (5/8) Epoch 9, batch 13250, loss[loss=0.1288, simple_loss=0.2027, pruned_loss=0.02741, over 4964.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03478, over 972313.32 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:57:23,741 INFO [train.py:715] (5/8) Epoch 9, batch 13300, loss[loss=0.1576, simple_loss=0.2278, pruned_loss=0.04371, over 4960.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03483, over 972203.88 frames.], batch size: 28, lr: 2.37e-04
2022-05-06 11:58:03,445 INFO [train.py:715] (5/8) Epoch 9, batch 13350, loss[loss=0.1461, simple_loss=0.2334, pruned_loss=0.02943, over 4934.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03438, over 972091.63 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:58:43,523 INFO [train.py:715] (5/8) Epoch 9, batch 13400, loss[loss=0.1132, simple_loss=0.1922, pruned_loss=0.0171, over 4983.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03416, over 972284.87 frames.], batch size: 28, lr: 2.37e-04
2022-05-06 11:59:23,794 INFO [train.py:715] (5/8) Epoch 9, batch 13450, loss[loss=0.1381, simple_loss=0.2065, pruned_loss=0.03481, over 4860.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03424, over 971889.98 frames.], batch size: 34, lr: 2.36e-04
2022-05-06 12:00:02,968 INFO [train.py:715] (5/8) Epoch 9, batch 13500, loss[loss=0.1614, simple_loss=0.2232, pruned_loss=0.04984, over 4821.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03412, over 972222.47 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:00:42,983 INFO [train.py:715] (5/8) Epoch 9, batch 13550, loss[loss=0.1347, simple_loss=0.202, pruned_loss=0.0337, over 4885.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03437, over 972352.07 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:01:22,499 INFO [train.py:715] (5/8) Epoch 9, batch 13600, loss[loss=0.122, simple_loss=0.1969, pruned_loss=0.02354, over 4809.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03415, over 971859.35 frames.], batch size: 25, lr: 2.36e-04
2022-05-06 12:02:01,621 INFO [train.py:715] (5/8) Epoch 9, batch 13650, loss[loss=0.1328, simple_loss=0.2139, pruned_loss=0.02585, over 4968.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.0334, over 972346.24 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:02:40,851 INFO [train.py:715] (5/8) Epoch 9, batch 13700, loss[loss=0.1544, simple_loss=0.2354, pruned_loss=0.0367, over 4904.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03327, over 972660.12 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:03:20,734 INFO [train.py:715] (5/8) Epoch 9, batch 13750, loss[loss=0.1428, simple_loss=0.2229, pruned_loss=0.0313, over 4833.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03361, over 972607.27 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:03:59,886 INFO [train.py:715] (5/8) Epoch 9, batch 13800, loss[loss=0.1507, simple_loss=0.2342, pruned_loss=0.03358, over 4947.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03362, over 971573.32 frames.], batch size: 21, lr: 2.36e-04
2022-05-06 12:04:38,381 INFO [train.py:715] (5/8) Epoch 9, batch 13850, loss[loss=0.1385, simple_loss=0.2088, pruned_loss=0.03404, over 4978.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.0336, over 972839.12 frames.], batch size: 25, lr: 2.36e-04
2022-05-06 12:05:17,812 INFO [train.py:715] (5/8) Epoch 9, batch 13900, loss[loss=0.1754, simple_loss=0.2458, pruned_loss=0.05254, over 4978.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03403, over 972513.79 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:05:57,956 INFO [train.py:715] (5/8) Epoch 9, batch 13950, loss[loss=0.1586, simple_loss=0.2265, pruned_loss=0.04531, over 4781.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03401, over 972579.21 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:06:36,916 INFO [train.py:715] (5/8) Epoch 9, batch 14000, loss[loss=0.1386, simple_loss=0.2007, pruned_loss=0.03823, over 4702.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03463, over 972325.85 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:07:16,029 INFO [train.py:715] (5/8) Epoch 9, batch 14050, loss[loss=0.2242, simple_loss=0.2846, pruned_loss=0.08196, over 4896.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03469, over 971721.01 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:07:55,562 INFO [train.py:715] (5/8) Epoch 9, batch 14100, loss[loss=0.1354, simple_loss=0.2045, pruned_loss=0.03315, over 4847.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.0354, over 971861.27 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:08:35,131 INFO [train.py:715] (5/8) Epoch 9, batch 14150, loss[loss=0.123, simple_loss=0.2042, pruned_loss=0.02095, over 4958.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2164, pruned_loss=0.03539, over 972575.03 frames.], batch size: 28, lr: 2.36e-04
2022-05-06 12:09:14,477 INFO [train.py:715] (5/8) Epoch 9, batch 14200, loss[loss=0.1735, simple_loss=0.2473, pruned_loss=0.04989, over 4818.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03564, over 972468.66 frames.], batch size: 25, lr: 2.36e-04
2022-05-06 12:09:53,804 INFO [train.py:715] (5/8) Epoch 9, batch 14250, loss[loss=0.1338, simple_loss=0.2097, pruned_loss=0.02893, over 4926.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2165, pruned_loss=0.03552, over 972914.39 frames.], batch size: 29, lr: 2.36e-04
2022-05-06 12:10:33,297 INFO [train.py:715] (5/8) Epoch 9, batch 14300, loss[loss=0.1484, simple_loss=0.2092, pruned_loss=0.0438, over 4733.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2163, pruned_loss=0.03555, over 972827.01 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:11:11,974 INFO [train.py:715] (5/8) Epoch 9, batch 14350, loss[loss=0.1215, simple_loss=0.1888, pruned_loss=0.02715, over 4930.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.036, over 972718.53 frames.], batch size: 23, lr: 2.36e-04
2022-05-06 12:11:50,596 INFO [train.py:715] (5/8) Epoch 9, batch 14400, loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.0431, over 4992.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03598, over 973098.76 frames.], batch size: 20, lr: 2.36e-04
2022-05-06 12:12:30,353 INFO [train.py:715] (5/8) Epoch 9, batch 14450, loss[loss=0.1389, simple_loss=0.2172, pruned_loss=0.0303, over 4945.00 frames.], tot_loss[loss=0.1452, simple_loss=0.218, pruned_loss=0.03623, over 972532.14 frames.], batch size: 23, lr: 2.36e-04
2022-05-06 12:13:09,686 INFO [train.py:715] (5/8) Epoch 9, batch 14500, loss[loss=0.1334, simple_loss=0.2028, pruned_loss=0.03204, over 4835.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2174, pruned_loss=0.03604, over 972232.11 frames.], batch size: 26, lr: 2.36e-04
2022-05-06 12:13:48,633 INFO [train.py:715] (5/8) Epoch 9, batch 14550, loss[loss=0.1699, simple_loss=0.2307, pruned_loss=0.05456, over 4942.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03574, over 972783.29 frames.], batch size: 35, lr: 2.36e-04
2022-05-06 12:14:27,681 INFO [train.py:715] (5/8) Epoch 9, batch 14600, loss[loss=0.1414, simple_loss=0.2018, pruned_loss=0.04053, over 4917.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03543, over 973286.46 frames.], batch size: 29, lr: 2.36e-04
2022-05-06 12:15:07,385 INFO [train.py:715] (5/8) Epoch 9, batch 14650, loss[loss=0.1643, simple_loss=0.2325, pruned_loss=0.04807, over 4770.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03573, over 972344.70 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:15:45,916 INFO [train.py:715] (5/8) Epoch 9, batch 14700, loss[loss=0.1424, simple_loss=0.2126, pruned_loss=0.03614, over 4915.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03557, over 971914.86 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:16:27,517 INFO [train.py:715] (5/8) Epoch 9, batch 14750, loss[loss=0.1291, simple_loss=0.2051, pruned_loss=0.0266, over 4851.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03514, over 972420.72 frames.], batch size: 30, lr: 2.36e-04
2022-05-06 12:17:06,567 INFO [train.py:715] (5/8) Epoch 9, batch 14800, loss[loss=0.1549, simple_loss=0.2323, pruned_loss=0.03875, over 4927.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03487, over 972339.24 frames.], batch size: 23, lr: 2.36e-04
2022-05-06 12:17:45,495 INFO [train.py:715] (5/8) Epoch 9, batch 14850, loss[loss=0.1282, simple_loss=0.2043, pruned_loss=0.02609, over 4851.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03481, over 971718.63 frames.], batch size: 20, lr: 2.36e-04
2022-05-06 12:18:24,546 INFO [train.py:715] (5/8) Epoch 9, batch 14900, loss[loss=0.1501, simple_loss=0.2186, pruned_loss=0.04077, over 4974.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03484, over 972617.33 frames.], batch size: 28, lr: 2.36e-04
2022-05-06 12:19:03,081 INFO [train.py:715] (5/8) Epoch 9, batch 14950, loss[loss=0.1278, simple_loss=0.1953, pruned_loss=0.03018, over 4957.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03481, over 973163.41 frames.], batch size: 24, lr: 2.36e-04
2022-05-06 12:19:42,675 INFO [train.py:715] (5/8) Epoch 9, batch 15000, loss[loss=0.1712, simple_loss=0.2546, pruned_loss=0.04393, over 4928.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03564, over 972663.96 frames.], batch size: 21, lr: 2.36e-04
2022-05-06 12:19:42,676 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 12:19:52,343 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1071, simple_loss=0.1915, pruned_loss=0.01139, over 914524.00 frames.
2022-05-06 12:20:32,095 INFO [train.py:715] (5/8) Epoch 9, batch 15050, loss[loss=0.1599, simple_loss=0.2233, pruned_loss=0.04829, over 4932.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03511, over 973556.66 frames.], batch size: 35, lr: 2.36e-04
2022-05-06 12:21:11,095 INFO [train.py:715] (5/8) Epoch 9, batch 15100, loss[loss=0.1429, simple_loss=0.2181, pruned_loss=0.03388, over 4788.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03518, over 973341.40 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:21:50,201 INFO [train.py:715] (5/8) Epoch 9, batch 15150, loss[loss=0.1105, simple_loss=0.1837, pruned_loss=0.01862, over 4854.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03514, over 972837.31 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:22:30,009 INFO [train.py:715] (5/8) Epoch 9, batch 15200, loss[loss=0.1399, simple_loss=0.2072, pruned_loss=0.03628, over 4978.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03434, over 972626.70 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:23:09,313 INFO [train.py:715] (5/8) Epoch 9, batch 15250, loss[loss=0.1457, simple_loss=0.2197, pruned_loss=0.03579, over 4931.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2135, pruned_loss=0.03466, over 972010.31 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:23:48,050 INFO [train.py:715] (5/8) Epoch 9, batch 15300, loss[loss=0.1199, simple_loss=0.2048, pruned_loss=0.01748, over 4897.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03509, over 972625.14 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:24:27,150 INFO [train.py:715] (5/8) Epoch 9, batch 15350, loss[loss=0.1556, simple_loss=0.228, pruned_loss=0.04162, over 4936.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03485, over 972871.17 frames.], batch size: 29, lr: 2.36e-04
2022-05-06 12:25:06,183 INFO [train.py:715] (5/8) Epoch 9, batch 15400, loss[loss=0.1095, simple_loss=0.1889, pruned_loss=0.015, over 4935.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03476, over 972883.08 frames.], batch size: 23, lr: 2.36e-04
2022-05-06 12:25:44,959 INFO [train.py:715] (5/8) Epoch 9, batch 15450, loss[loss=0.1609, simple_loss=0.2347, pruned_loss=0.04351, over 4746.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.0342, over 972007.89 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:26:23,386 INFO [train.py:715] (5/8) Epoch 9, batch 15500, loss[loss=0.144, simple_loss=0.2103, pruned_loss=0.03883, over 4976.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03455, over 971879.69 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:27:03,114 INFO [train.py:715] (5/8) Epoch 9, batch 15550, loss[loss=0.1642, simple_loss=0.2342, pruned_loss=0.0471, over 4964.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2129, pruned_loss=0.03435, over 971780.22 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:27:41,876 INFO [train.py:715] (5/8) Epoch 9, batch 15600, loss[loss=0.1104, simple_loss=0.1751, pruned_loss=0.0228, over 4637.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.0345, over 971573.79 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:28:20,224 INFO [train.py:715] (5/8) Epoch 9, batch 15650, loss[loss=0.125, simple_loss=0.1943, pruned_loss=0.02785, over 4793.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.034, over 971573.25 frames.], batch size: 25, lr: 2.36e-04
2022-05-06 12:28:59,315 INFO [train.py:715] (5/8) Epoch 9, batch 15700, loss[loss=0.1129, simple_loss=0.1839, pruned_loss=0.02093, over 4786.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03362, over 971270.93 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:29:39,071 INFO [train.py:715] (5/8) Epoch 9, batch 15750, loss[loss=0.1158, simple_loss=0.1908, pruned_loss=0.02043, over 4844.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03366, over 970974.20 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:30:17,865 INFO [train.py:715] (5/8) Epoch 9, batch 15800, loss[loss=0.1381, simple_loss=0.2159, pruned_loss=0.03017, over 4895.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03401, over 971079.43 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:30:56,796 INFO [train.py:715] (5/8) Epoch 9, batch 15850, loss[loss=0.1409, simple_loss=0.2057, pruned_loss=0.03807, over 4868.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03372, over 971960.34 frames.], batch size: 32, lr: 2.36e-04
2022-05-06 12:31:36,416 INFO [train.py:715] (5/8) Epoch 9, batch 15900, loss[loss=0.19, simple_loss=0.2602, pruned_loss=0.05986, over 4953.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.0338, over 971896.07 frames.], batch size: 21, lr: 2.36e-04
2022-05-06 12:32:15,976 INFO [train.py:715] (5/8) Epoch 9, batch 15950, loss[loss=0.1514, simple_loss=0.221, pruned_loss=0.04092, over 4878.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03375, over 971950.64 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:32:54,618 INFO [train.py:715] (5/8) Epoch 9, batch 16000, loss[loss=0.1373, simple_loss=0.2073, pruned_loss=0.03371, over 4987.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03339, over 972452.45 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:33:33,295 INFO [train.py:715] (5/8) Epoch 9, batch 16050, loss[loss=0.1325, simple_loss=0.2038, pruned_loss=0.03059, over 4976.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03438, over 972266.23 frames.], batch size: 24, lr: 2.36e-04
2022-05-06 12:34:12,505 INFO [train.py:715] (5/8) Epoch 9, batch 16100, loss[loss=0.136, simple_loss=0.1987, pruned_loss=0.03664, over 4959.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2148, pruned_loss=0.03405, over 971965.17 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:34:51,591 INFO [train.py:715] (5/8) Epoch 9, batch 16150, loss[loss=0.1681, simple_loss=0.238, pruned_loss=0.04906, over 4977.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2142, pruned_loss=0.03362, over 972412.58 frames.], batch size: 24, lr: 2.36e-04
2022-05-06 12:35:30,768 INFO [train.py:715] (5/8) Epoch 9, batch 16200, loss[loss=0.1393, simple_loss=0.2134, pruned_loss=0.03261, over 4775.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2143, pruned_loss=0.03378, over 972909.20 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:36:10,109 INFO [train.py:715] (5/8) Epoch 9, batch 16250, loss[loss=0.1279, simple_loss=0.1967, pruned_loss=0.02958, over 4967.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2149, pruned_loss=0.03401, over 973538.90 frames.], batch size: 35, lr: 2.35e-04
2022-05-06 12:36:49,784 INFO [train.py:715] (5/8) Epoch 9, batch 16300, loss[loss=0.1162, simple_loss=0.1903, pruned_loss=0.02099, over 4980.00 frames.], tot_loss[loss=0.141, simple_loss=0.2146, pruned_loss=0.0337, over 973657.43 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:37:27,728 INFO [train.py:715] (5/8) Epoch 9, batch 16350, loss[loss=0.1425, simple_loss=0.23, pruned_loss=0.02748, over 4971.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2149, pruned_loss=0.03421, over 973160.32 frames.], batch size: 24, lr: 2.35e-04
2022-05-06 12:38:07,160 INFO [train.py:715] (5/8) Epoch 9, batch 16400, loss[loss=0.1424, simple_loss=0.2296, pruned_loss=0.02757, over 4877.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03473, over 973026.88 frames.], batch size: 22, lr: 2.35e-04
2022-05-06 12:38:47,053 INFO [train.py:715] (5/8) Epoch 9, batch 16450, loss[loss=0.1867, simple_loss=0.2443, pruned_loss=0.06456, over 4778.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03468, over 972099.24 frames.], batch size: 18, lr: 2.35e-04
2022-05-06 12:39:25,804 INFO [train.py:715] (5/8) Epoch 9, batch 16500, loss[loss=0.1393, simple_loss=0.2117, pruned_loss=0.03341, over 4690.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2151, pruned_loss=0.03455, over 971643.18 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:40:04,383 INFO [train.py:715] (5/8) Epoch 9, batch 16550, loss[loss=0.1349, simple_loss=0.208, pruned_loss=0.03091, over 4827.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03489, over 972461.00 frames.], batch size: 12, lr: 2.35e-04
2022-05-06 12:40:43,845 INFO [train.py:715] (5/8) Epoch 9, batch 16600, loss[loss=0.1184, simple_loss=0.1898, pruned_loss=0.02349, over 4761.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03524, over 972681.23 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:41:23,434 INFO [train.py:715] (5/8) Epoch 9, batch 16650, loss[loss=0.1523, simple_loss=0.2199, pruned_loss=0.04234, over 4930.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03568, over 971950.18 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 12:42:02,349 INFO [train.py:715] (5/8) Epoch 9, batch 16700, loss[loss=0.1407, simple_loss=0.2177, pruned_loss=0.03183, over 4848.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03588, over 972377.13 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:42:41,614 INFO [train.py:715] (5/8) Epoch 9, batch 16750, loss[loss=0.1625, simple_loss=0.2333, pruned_loss=0.04586, over 4973.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03513, over 972031.48 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:43:21,410 INFO [train.py:715] (5/8) Epoch 9, batch 16800, loss[loss=0.1104, simple_loss=0.1734, pruned_loss=0.02375, over 4815.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03495, over 971323.70 frames.], batch size: 13, lr: 2.35e-04
2022-05-06 12:44:01,033 INFO [train.py:715] (5/8) Epoch 9, batch 16850, loss[loss=0.1317, simple_loss=0.2032, pruned_loss=0.03012, over 4852.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03513, over 971572.45 frames.], batch size: 13, lr: 2.35e-04
2022-05-06 12:44:40,453 INFO [train.py:715] (5/8) Epoch 9, batch 16900, loss[loss=0.1197, simple_loss=0.1955, pruned_loss=0.02192, over 4850.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.0349, over 971539.87 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:45:20,533 INFO [train.py:715] (5/8) Epoch 9, batch 16950, loss[loss=0.1447, simple_loss=0.2103, pruned_loss=0.03951, over 4741.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03508, over 971671.58 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:46:00,233 INFO [train.py:715] (5/8) Epoch 9, batch 17000, loss[loss=0.1531, simple_loss=0.221, pruned_loss=0.04261, over 4879.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03512, over 972089.81 frames.], batch size: 32, lr: 2.35e-04
2022-05-06 12:46:38,805 INFO [train.py:715] (5/8) Epoch 9, batch 17050, loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03193, over 4811.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03531, over 972331.48 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 12:47:18,388 INFO [train.py:715] (5/8) Epoch 9, batch 17100, loss[loss=0.1592, simple_loss=0.2351, pruned_loss=0.04159, over 4919.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03509, over 972915.99 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:47:58,063 INFO [train.py:715] (5/8) Epoch 9, batch 17150, loss[loss=0.1508, simple_loss=0.2206, pruned_loss=0.04052, over 4976.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03484, over 973051.21 frames.], batch size: 35, lr: 2.35e-04
2022-05-06 12:48:37,321 INFO [train.py:715] (5/8) Epoch 9, batch 17200, loss[loss=0.1722, simple_loss=0.2528, pruned_loss=0.04574, over 4887.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03516, over 972814.06 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 12:49:15,994 INFO [train.py:715] (5/8) Epoch 9, batch 17250, loss[loss=0.1337, simple_loss=0.2148, pruned_loss=0.02628, over 4790.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03516, over 972545.54 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:49:54,884 INFO [train.py:715] (5/8) Epoch 9, batch 17300, loss[loss=0.1354, simple_loss=0.206, pruned_loss=0.03246, over 4985.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03482, over 973360.80 frames.], batch size: 28, lr: 2.35e-04
2022-05-06 12:50:33,971 INFO [train.py:715] (5/8) Epoch 9, batch 17350, loss[loss=0.2169, simple_loss=0.2895, pruned_loss=0.07215, over 4948.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03503, over 973168.01 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 12:51:13,078 INFO [train.py:715] (5/8) Epoch 9, batch 17400, loss[loss=0.1512, simple_loss=0.2108, pruned_loss=0.04585, over 4859.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03534, over 973329.71 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:51:52,391 INFO [train.py:715] (5/8) Epoch 9, batch 17450, loss[loss=0.1568, simple_loss=0.2342, pruned_loss=0.03972, over 4938.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03533, over 973543.26 frames.], batch size: 21, lr: 2.35e-04
2022-05-06 12:52:31,597 INFO [train.py:715] (5/8) Epoch 9, batch 17500, loss[loss=0.1118, simple_loss=0.1743, pruned_loss=0.02462, over 4761.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03503, over 972458.88 frames.], batch size: 12, lr: 2.35e-04
2022-05-06 12:53:10,812 INFO [train.py:715] (5/8) Epoch 9, batch 17550, loss[loss=0.1481, simple_loss=0.2273, pruned_loss=0.03448, over 4894.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03517, over 971978.50 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 12:53:49,892 INFO [train.py:715] (5/8) Epoch 9, batch 17600, loss[loss=0.1556, simple_loss=0.2293, pruned_loss=0.0409, over 4817.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03535, over 972244.23 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:54:29,582 INFO [train.py:715] (5/8) Epoch 9, batch 17650, loss[loss=0.1435, simple_loss=0.2212, pruned_loss=0.0329, over 4784.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2164, pruned_loss=0.03562, over 972154.05 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 12:55:08,478 INFO [train.py:715] (5/8) Epoch 9, batch 17700, loss[loss=0.1429, simple_loss=0.2078, pruned_loss=0.03901, over 4800.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03528, over 971642.83 frames.], batch size: 21, lr: 2.35e-04
2022-05-06 12:55:47,742 INFO [train.py:715] (5/8) Epoch 9, batch 17750, loss[loss=0.1494, simple_loss=0.2262, pruned_loss=0.03626, over 4881.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.0354, over 972213.42 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:56:27,545 INFO [train.py:715] (5/8) Epoch 9, batch 17800, loss[loss=0.142, simple_loss=0.2103, pruned_loss=0.03683, over 4941.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03513, over 972162.54 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:57:06,521 INFO [train.py:715] (5/8) Epoch 9, batch 17850, loss[loss=0.1622, simple_loss=0.2267, pruned_loss=0.04891, over 4743.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03515, over 972489.46 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:57:45,749 INFO [train.py:715] (5/8) Epoch 9, batch 17900, loss[loss=0.1553, simple_loss=0.2235, pruned_loss=0.04352, over 4817.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03455, over 972078.68 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 12:58:25,609 INFO [train.py:715] (5/8) Epoch 9, batch 17950, loss[loss=0.1792, simple_loss=0.2404, pruned_loss=0.05899, over 4986.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03471, over 972803.74 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:59:04,970 INFO [train.py:715] (5/8) Epoch 9, batch 18000, loss[loss=0.1154, simple_loss=0.1919, pruned_loss=0.01944, over 4851.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03434, over 972671.21 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:59:04,971 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 12:59:14,501 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
2022-05-06 12:59:53,969 INFO [train.py:715] (5/8) Epoch 9, batch 18050, loss[loss=0.1371, simple_loss=0.2081, pruned_loss=0.03301, over 4750.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03445, over 972368.04 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 13:00:33,791 INFO [train.py:715] (5/8) Epoch 9, batch 18100, loss[loss=0.1551, simple_loss=0.2327, pruned_loss=0.03878, over 4790.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.0352, over 971407.70 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 13:01:13,062 INFO [train.py:715] (5/8) Epoch 9, batch 18150, loss[loss=0.1273, simple_loss=0.2058, pruned_loss=0.02433, over 4973.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03573, over 972021.11 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 13:01:52,673 INFO [train.py:715] (5/8) Epoch 9, batch 18200, loss[loss=0.1187, simple_loss=0.1862, pruned_loss=0.02557, over 4822.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03566, over 972152.10 frames.], batch size: 13, lr: 2.35e-04
2022-05-06 13:02:31,901 INFO [train.py:715] (5/8) Epoch 9, batch 18250, loss[loss=0.147, simple_loss=0.2288, pruned_loss=0.03258, over 4826.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2175, pruned_loss=0.03593, over 972654.09 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 13:03:11,078 INFO [train.py:715] (5/8) Epoch 9, batch 18300, loss[loss=0.1727, simple_loss=0.2329, pruned_loss=0.05621, over 4885.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03593, over 972014.09 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 13:03:50,425 INFO [train.py:715] (5/8) Epoch 9, batch 18350, loss[loss=0.1369, simple_loss=0.199, pruned_loss=0.03734, over 4808.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03558, over 971017.66 frames.], batch size: 26, lr: 2.35e-04
2022-05-06 13:04:29,595 INFO [train.py:715] (5/8) Epoch 9, batch 18400, loss[loss=0.1446, simple_loss=0.2219, pruned_loss=0.03359, over 4978.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2174, pruned_loss=0.0358, over 971515.53 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 13:05:08,637 INFO [train.py:715] (5/8) Epoch 9, batch 18450, loss[loss=0.1278, simple_loss=0.2042, pruned_loss=0.02566, over 4707.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.03561, over 971250.59 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 13:05:47,599 INFO [train.py:715] (5/8) Epoch 9, batch 18500, loss[loss=0.1438, simple_loss=0.2212, pruned_loss=0.03318, over 4922.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03532, over 970886.45 frames.], batch size: 23, lr: 2.35e-04
2022-05-06 13:06:26,995 INFO [train.py:715] (5/8) Epoch 9, batch 18550, loss[loss=0.1119, simple_loss=0.186, pruned_loss=0.01889, over 4899.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2158, pruned_loss=0.03494, over 971989.94 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 13:07:06,065 INFO [train.py:715] (5/8) Epoch 9, batch 18600, loss[loss=0.1309, simple_loss=0.1981, pruned_loss=0.03184, over 4818.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03509, over 972202.15 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 13:07:44,915 INFO [train.py:715] (5/8) Epoch 9, batch 18650, loss[loss=0.1388, simple_loss=0.2047, pruned_loss=0.03645, over 4978.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03535, over 972069.83 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 13:08:24,472 INFO [train.py:715] (5/8) Epoch 9, batch 18700, loss[loss=0.1296, simple_loss=0.1936, pruned_loss=0.03284, over 4925.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.03536, over 970982.41 frames.], batch size: 23, lr: 2.35e-04
2022-05-06 13:09:03,184 INFO [train.py:715] (5/8) Epoch 9, batch 18750, loss[loss=0.1622, simple_loss=0.2331, pruned_loss=0.04561, over 4983.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2163, pruned_loss=0.0353, over 971276.26 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 13:09:42,756 INFO [train.py:715] (5/8) Epoch 9, batch 18800, loss[loss=0.1258, simple_loss=0.2046, pruned_loss=0.02356, over 4702.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2156, pruned_loss=0.03485, over 971095.59 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 13:10:21,586 INFO [train.py:715] (5/8) Epoch 9, batch 18850, loss[loss=0.1487, simple_loss=0.2164, pruned_loss=0.04049, over 4835.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03492, over 971520.30 frames.], batch size: 30, lr: 2.35e-04
2022-05-06 13:11:00,817 INFO [train.py:715] (5/8) Epoch 9, batch 18900, loss[loss=0.1255, simple_loss=0.1942, pruned_loss=0.02839, over 4980.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03479, over 972189.24 frames.], batch size: 28, lr: 2.35e-04
2022-05-06 13:11:40,159 INFO [train.py:715] (5/8) Epoch 9, batch 18950, loss[loss=0.115, simple_loss=0.1882, pruned_loss=0.0209, over 4913.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03501, over 973180.39 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 13:12:18,866 INFO [train.py:715] (5/8) Epoch 9, batch 19000, loss[loss=0.1224, simple_loss=0.2031, pruned_loss=0.02079, over 4958.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03447, over 972097.99 frames.], batch size: 24, lr: 2.35e-04
2022-05-06 13:12:58,958 INFO [train.py:715] (5/8) Epoch 9, batch 19050, loss[loss=0.1419, simple_loss=0.2057, pruned_loss=0.03908, over 4880.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03389, over 972500.95 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:13:38,427 INFO [train.py:715] (5/8) Epoch 9, batch 19100, loss[loss=0.1407, simple_loss=0.2185, pruned_loss=0.03145, over 4792.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03407, over 972191.61 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:14:17,259 INFO [train.py:715] (5/8) Epoch 9, batch 19150, loss[loss=0.1488, simple_loss=0.2177, pruned_loss=0.03993, over 4966.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.03394, over 972581.03 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:14:57,087 INFO [train.py:715] (5/8) Epoch 9, batch 19200, loss[loss=0.141, simple_loss=0.2217, pruned_loss=0.03017, over 4785.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03359, over 971334.31 frames.], batch size: 14, lr: 2.34e-04
2022-05-06 13:15:36,593 INFO [train.py:715] (5/8) Epoch 9, batch 19250, loss[loss=0.126, simple_loss=0.2056, pruned_loss=0.0232, over 4950.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.0335, over 971313.54 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:16:15,483 INFO [train.py:715] (5/8) Epoch 9, batch 19300, loss[loss=0.1515, simple_loss=0.2185, pruned_loss=0.04229, over 4824.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03356, over 972190.47 frames.], batch size: 30, lr: 2.34e-04
2022-05-06 13:16:54,061 INFO [train.py:715] (5/8) Epoch 9, batch 19350, loss[loss=0.1488, simple_loss=0.2207, pruned_loss=0.03846, over 4803.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03364, over 972230.33 frames.], batch size: 26, lr: 2.34e-04
2022-05-06 13:17:34,088 INFO [train.py:715] (5/8) Epoch 9, batch 19400, loss[loss=0.1275, simple_loss=0.2028, pruned_loss=0.02612, over 4872.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03396, over 972246.08 frames.], batch size: 22, lr: 2.34e-04
2022-05-06 13:18:13,120 INFO [train.py:715] (5/8) Epoch 9, batch 19450, loss[loss=0.1293, simple_loss=0.1991, pruned_loss=0.02974, over 4824.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03476, over 972622.15 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:18:51,811 INFO [train.py:715] (5/8) Epoch 9, batch 19500, loss[loss=0.122, simple_loss=0.194, pruned_loss=0.02496, over 4861.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2132, pruned_loss=0.03465, over 971576.86 frames.], batch size: 20, lr: 2.34e-04
2022-05-06 13:19:30,940 INFO [train.py:715] (5/8) Epoch 9, batch 19550, loss[loss=0.1392, simple_loss=0.2183, pruned_loss=0.03008, over 4696.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2136, pruned_loss=0.0347, over 972123.46 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:20:10,202 INFO [train.py:715] (5/8) Epoch 9, batch 19600, loss[loss=0.1871, simple_loss=0.2529, pruned_loss=0.06068, over 4751.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2137, pruned_loss=0.03506, over 971464.70 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:20:48,781 INFO [train.py:715] (5/8) Epoch 9, batch 19650, loss[loss=0.1352, simple_loss=0.2154, pruned_loss=0.02748, over 4906.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03498, over 971504.77 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:21:27,272 INFO [train.py:715] (5/8) Epoch 9, batch 19700, loss[loss=0.1697, simple_loss=0.2404, pruned_loss=0.04954, over 4849.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2136, pruned_loss=0.03469, over 971763.17 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:22:07,182 INFO [train.py:715] (5/8) Epoch 9, batch 19750, loss[loss=0.1407, simple_loss=0.207, pruned_loss=0.03719, over 4955.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.0348, over 971643.32 frames.], batch size: 35, lr: 2.34e-04
2022-05-06 13:22:46,851 INFO [train.py:715] (5/8) Epoch 9, batch 19800, loss[loss=0.133, simple_loss=0.2155, pruned_loss=0.02523, over 4894.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03442, over 971151.20 frames.], batch size: 22, lr: 2.34e-04
2022-05-06 13:23:26,647 INFO [train.py:715] (5/8) Epoch 9, batch 19850, loss[loss=0.1128, simple_loss=0.1752, pruned_loss=0.02515, over 4730.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03404, over 971962.80 frames.], batch size: 12, lr: 2.34e-04
2022-05-06 13:24:06,290 INFO [train.py:715] (5/8) Epoch 9, batch 19900, loss[loss=0.1272, simple_loss=0.1943, pruned_loss=0.03007, over 4935.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03448, over 972025.74 frames.], batch size: 23, lr: 2.34e-04
2022-05-06 13:24:45,453 INFO [train.py:715] (5/8) Epoch 9, batch 19950, loss[loss=0.1433, simple_loss=0.2191, pruned_loss=0.03375, over 4973.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2135, pruned_loss=0.03466, over 972393.56 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:25:24,504 INFO [train.py:715] (5/8) Epoch 9, batch 20000, loss[loss=0.128, simple_loss=0.2082, pruned_loss=0.02393, over 4787.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2136, pruned_loss=0.03482, over 972102.15 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:26:02,952 INFO [train.py:715] (5/8) Epoch 9, batch 20050, loss[loss=0.1254, simple_loss=0.2071, pruned_loss=0.02189, over 4907.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03459, over 971560.31 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:26:42,420 INFO [train.py:715] (5/8) Epoch 9, batch 20100, loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02824, over 4942.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03521, over 972042.59 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:27:21,489 INFO [train.py:715] (5/8) Epoch 9, batch 20150, loss[loss=0.1104, simple_loss=0.1838, pruned_loss=0.01855, over 4837.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03465, over 972176.32 frames.], batch size: 30, lr: 2.34e-04
2022-05-06 13:27:59,970 INFO [train.py:715] (5/8) Epoch 9, batch 20200, loss[loss=0.142, simple_loss=0.2167, pruned_loss=0.03364, over 4840.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03419, over 972102.89 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:28:39,474 INFO [train.py:715] (5/8) Epoch 9, batch 20250, loss[loss=0.1593, simple_loss=0.2319, pruned_loss=0.04334, over 4737.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2136, pruned_loss=0.03459, over 971954.53 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:29:18,327 INFO [train.py:715] (5/8) Epoch 9, batch 20300, loss[loss=0.152, simple_loss=0.2299, pruned_loss=0.03705, over 4941.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03453, over 973297.53 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:29:57,719 INFO [train.py:715] (5/8) Epoch 9, batch 20350, loss[loss=0.1493, simple_loss=0.2129, pruned_loss=0.04291, over 4775.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03451, over 972184.27 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:30:37,216 INFO [train.py:715] (5/8) Epoch 9, batch 20400, loss[loss=0.1266, simple_loss=0.212, pruned_loss=0.02064, over 4805.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03406, over 971864.71 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:31:17,106 INFO [train.py:715] (5/8) Epoch 9, batch 20450, loss[loss=0.117, simple_loss=0.1923, pruned_loss=0.02089, over 4918.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2145, pruned_loss=0.03401, over 970901.83 frames.], batch size: 29, lr: 2.34e-04
2022-05-06 13:31:56,613 INFO [train.py:715] (5/8) Epoch 9, batch 20500, loss[loss=0.1185, simple_loss=0.1926, pruned_loss=0.02223, over 4905.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03387, over 970805.98 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:32:35,665 INFO [train.py:715] (5/8) Epoch 9, batch 20550, loss[loss=0.1306, simple_loss=0.2037, pruned_loss=0.02869, over 4780.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03377, over 971736.13 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:33:14,860 INFO [train.py:715] (5/8) Epoch 9, batch 20600, loss[loss=0.1647, simple_loss=0.2399, pruned_loss=0.04471, over 4942.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03465, over 971942.47 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:33:53,310 INFO [train.py:715] (5/8) Epoch 9, batch 20650, loss[loss=0.1643, simple_loss=0.2366, pruned_loss=0.04603, over 4729.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2146, pruned_loss=0.0343, over 972320.04 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:34:32,417 INFO [train.py:715] (5/8) Epoch 9, batch 20700, loss[loss=0.1235, simple_loss=0.1914, pruned_loss=0.02779, over 4775.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.0338, over 973217.75 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:35:11,248 INFO [train.py:715] (5/8) Epoch 9, batch 20750, loss[loss=0.1496, simple_loss=0.2325, pruned_loss=0.03335, over 4967.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03408, over 973461.01 frames.], batch size: 25, lr: 2.34e-04
2022-05-06 13:35:50,838 INFO [train.py:715] (5/8) Epoch 9, batch 20800, loss[loss=0.1296, simple_loss=0.1995, pruned_loss=0.0299, over 4862.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.03428, over 973137.46 frames.], batch size: 22, lr: 2.34e-04
2022-05-06 13:36:30,206 INFO [train.py:715] (5/8) Epoch 9, batch 20850, loss[loss=0.1604, simple_loss=0.2363, pruned_loss=0.04222, over 4839.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03431, over 971999.46 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:37:09,647 INFO [train.py:715] (5/8) Epoch 9, batch 20900, loss[loss=0.1185, simple_loss=0.1879, pruned_loss=0.02452, over 4814.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03441, over 971746.62 frames.], batch size: 12, lr: 2.34e-04
2022-05-06 13:37:49,143 INFO [train.py:715] (5/8) Epoch 9, batch 20950, loss[loss=0.1604, simple_loss=0.243, pruned_loss=0.03889, over 4972.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03462, over 971659.68 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:38:28,443 INFO [train.py:715] (5/8) Epoch 9, batch 21000, loss[loss=0.1798, simple_loss=0.2587, pruned_loss=0.05039, over 4805.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03437, over 971703.62 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:38:28,444 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 13:38:38,082 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1912, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 13:39:17,240 INFO [train.py:715] (5/8) Epoch 9, batch 21050, loss[loss=0.1226, simple_loss=0.1951, pruned_loss=0.02509, over 4756.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03402, over 971494.70 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:39:56,156 INFO [train.py:715] (5/8) Epoch 9, batch 21100, loss[loss=0.1519, simple_loss=0.2273, pruned_loss=0.03821, over 4904.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03506, over 972238.83 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:40:35,518 INFO [train.py:715] (5/8) Epoch 9, batch 21150, loss[loss=0.1427, simple_loss=0.2134, pruned_loss=0.03601, over 4835.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03534, over 971060.96 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:41:14,527 INFO [train.py:715] (5/8) Epoch 9, batch 21200, loss[loss=0.1116, simple_loss=0.1844, pruned_loss=0.01936, over 4777.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03538, over 971393.89 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:41:54,098 INFO [train.py:715] (5/8) Epoch 9, batch 21250, loss[loss=0.1472, simple_loss=0.2309, pruned_loss=0.03178, over 4807.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.0353, over 971935.27 frames.], batch size: 25, lr: 2.34e-04
2022-05-06 13:42:32,488 INFO [train.py:715] (5/8) Epoch 9, batch 21300, loss[loss=0.1705, simple_loss=0.23, pruned_loss=0.05551, over 4934.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03524, over 972261.55 frames.], batch size: 39, lr: 2.34e-04
2022-05-06 13:43:11,098 INFO [train.py:715] (5/8) Epoch 9, batch 21350, loss[loss=0.1659, simple_loss=0.2382, pruned_loss=0.04676, over 4685.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03506, over 971567.59 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:43:50,032 INFO [train.py:715] (5/8) Epoch 9, batch 21400, loss[loss=0.1831, simple_loss=0.2544, pruned_loss=0.05584, over 4974.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03526, over 971381.25 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:44:28,774 INFO [train.py:715] (5/8) Epoch 9, batch 21450, loss[loss=0.167, simple_loss=0.2333, pruned_loss=0.05032, over 4704.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03514, over 970871.97 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:45:07,167 INFO [train.py:715] (5/8) Epoch 9, batch 21500, loss[loss=0.1702, simple_loss=0.2386, pruned_loss=0.05095, over 4861.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03453, over 970209.02 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:45:46,281 INFO [train.py:715] (5/8) Epoch 9, batch 21550, loss[loss=0.1303, simple_loss=0.2061, pruned_loss=0.02726, over 4814.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03407, over 970313.35 frames.], batch size: 27, lr: 2.34e-04
2022-05-06 13:46:25,000 INFO [train.py:715] (5/8) Epoch 9, batch 21600, loss[loss=0.1226, simple_loss=0.201, pruned_loss=0.02211, over 4776.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 970713.97 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:47:04,090 INFO [train.py:715] (5/8) Epoch 9, batch 21650, loss[loss=0.2517, simple_loss=0.3195, pruned_loss=0.09199, over 4803.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03409, over 971831.59 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:47:43,366 INFO [train.py:715] (5/8) Epoch 9, batch 21700, loss[loss=0.1691, simple_loss=0.2492, pruned_loss=0.04455, over 4829.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03424, over 972562.28 frames.], batch size: 26, lr: 2.34e-04
2022-05-06 13:48:22,454 INFO [train.py:715] (5/8) Epoch 9, batch 21750, loss[loss=0.1367, simple_loss=0.2113, pruned_loss=0.03105, over 4953.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03415, over 973268.31 frames.], batch size: 35, lr: 2.34e-04
2022-05-06 13:49:01,561 INFO [train.py:715] (5/8) Epoch 9, batch 21800, loss[loss=0.1393, simple_loss=0.2136, pruned_loss=0.03246, over 4855.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03435, over 972737.76 frames.], batch size: 32, lr: 2.34e-04
2022-05-06 13:49:41,088 INFO [train.py:715] (5/8) Epoch 9, batch 21850, loss[loss=0.1489, simple_loss=0.2278, pruned_loss=0.03503, over 4949.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2128, pruned_loss=0.03393, over 973190.74 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:50:20,437 INFO [train.py:715] (5/8) Epoch 9, batch 21900, loss[loss=0.1501, simple_loss=0.2231, pruned_loss=0.03858, over 4862.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03404, over 973203.46 frames.], batch size: 20, lr: 2.33e-04
2022-05-06 13:50:59,007 INFO [train.py:715] (5/8) Epoch 9, batch 21950, loss[loss=0.1291, simple_loss=0.1982, pruned_loss=0.02997, over 4765.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03392, over 973635.09 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 13:51:37,910 INFO [train.py:715] (5/8) Epoch 9, batch 22000, loss[loss=0.1705, simple_loss=0.236, pruned_loss=0.05253, over 4960.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2133, pruned_loss=0.03442, over 973740.48 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 13:52:16,810 INFO [train.py:715] (5/8) Epoch 9, batch 22050, loss[loss=0.1108, simple_loss=0.1914, pruned_loss=0.01505, over 4798.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.0342, over 973056.99 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 13:52:56,514 INFO [train.py:715] (5/8) Epoch 9, batch 22100, loss[loss=0.1226, simple_loss=0.1962, pruned_loss=0.02445, over 4851.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03416, over 971940.24 frames.], batch size: 30, lr: 2.33e-04
2022-05-06 13:53:35,797 INFO [train.py:715] (5/8) Epoch 9, batch 22150, loss[loss=0.1537, simple_loss=0.2278, pruned_loss=0.03979, over 4771.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03411, over 971649.71 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 13:54:14,966 INFO [train.py:715] (5/8) Epoch 9, batch 22200, loss[loss=0.1344, simple_loss=0.2113, pruned_loss=0.0287, over 4938.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03399, over 971774.06 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 13:54:54,444 INFO [train.py:715] (5/8) Epoch 9, batch 22250, loss[loss=0.1719, simple_loss=0.2485, pruned_loss=0.04764, over 4776.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03415, over 971031.22 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 13:55:33,230 INFO [train.py:715] (5/8) Epoch 9, batch 22300, loss[loss=0.1578, simple_loss=0.2245, pruned_loss=0.04555, over 4770.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03454, over 971283.82 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 13:56:11,832 INFO [train.py:715] (5/8) Epoch 9, batch 22350, loss[loss=0.1464, simple_loss=0.2187, pruned_loss=0.03704, over 4833.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2156, pruned_loss=0.03499, over 971758.38 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:56:50,720 INFO [train.py:715] (5/8) Epoch 9, batch 22400, loss[loss=0.1391, simple_loss=0.2072, pruned_loss=0.0355, over 4831.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03488, over 970884.20 frames.], batch size: 13, lr: 2.33e-04
2022-05-06 13:57:29,424 INFO [train.py:715] (5/8) Epoch 9, batch 22450, loss[loss=0.1495, simple_loss=0.2157, pruned_loss=0.04168, over 4690.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03512, over 972048.19 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:58:08,127 INFO [train.py:715] (5/8) Epoch 9, batch 22500, loss[loss=0.1437, simple_loss=0.2174, pruned_loss=0.03502, over 4787.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03436, over 971690.72 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 13:58:47,016 INFO [train.py:715] (5/8) Epoch 9, batch 22550, loss[loss=0.1581, simple_loss=0.2221, pruned_loss=0.04711, over 4928.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03477, over 972453.44 frames.], batch size: 23, lr: 2.33e-04
2022-05-06 13:59:26,037 INFO [train.py:715] (5/8) Epoch 9, batch 22600, loss[loss=0.1352, simple_loss=0.2026, pruned_loss=0.03389, over 4979.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03426, over 972030.89 frames.], batch size: 24, lr: 2.33e-04
2022-05-06 14:00:05,201 INFO [train.py:715] (5/8) Epoch 9, batch 22650, loss[loss=0.1776, simple_loss=0.2467, pruned_loss=0.05428, over 4828.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03448, over 971772.89 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:00:44,242 INFO [train.py:715] (5/8) Epoch 9, batch 22700, loss[loss=0.122, simple_loss=0.1964, pruned_loss=0.02381, over 4693.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03536, over 971662.78 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:01:26,074 INFO [train.py:715] (5/8) Epoch 9, batch 22750, loss[loss=0.1293, simple_loss=0.2017, pruned_loss=0.0285, over 4956.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2157, pruned_loss=0.03497, over 971728.61 frames.], batch size: 35, lr: 2.33e-04
2022-05-06 14:02:04,853 INFO [train.py:715] (5/8) Epoch 9, batch 22800, loss[loss=0.141, simple_loss=0.2057, pruned_loss=0.03813, over 4880.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03428, over 972254.27 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 14:02:44,149 INFO [train.py:715] (5/8) Epoch 9, batch 22850, loss[loss=0.1642, simple_loss=0.2385, pruned_loss=0.04497, over 4846.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.035, over 972129.24 frames.], batch size: 34, lr: 2.33e-04
2022-05-06 14:03:22,718 INFO [train.py:715] (5/8) Epoch 9, batch 22900, loss[loss=0.1265, simple_loss=0.202, pruned_loss=0.02553, over 4977.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.0349, over 971557.90 frames.], batch size: 24, lr: 2.33e-04
2022-05-06 14:04:01,802 INFO [train.py:715] (5/8) Epoch 9, batch 22950, loss[loss=0.1416, simple_loss=0.2071, pruned_loss=0.0381, over 4945.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03489, over 972286.51 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:04:40,858 INFO [train.py:715] (5/8) Epoch 9, batch 23000, loss[loss=0.1293, simple_loss=0.2072, pruned_loss=0.02575, over 4918.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03463, over 972384.06 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:05:20,249 INFO [train.py:715] (5/8) Epoch 9, batch 23050, loss[loss=0.1251, simple_loss=0.1962, pruned_loss=0.02699, over 4980.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.0343, over 972550.03 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:05:59,521 INFO [train.py:715] (5/8) Epoch 9, batch 23100, loss[loss=0.1364, simple_loss=0.2023, pruned_loss=0.0353, over 4868.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03377, over 971811.03 frames.], batch size: 22, lr: 2.33e-04
2022-05-06 14:06:38,546 INFO [train.py:715] (5/8) Epoch 9, batch 23150, loss[loss=0.1392, simple_loss=0.2057, pruned_loss=0.03636, over 4970.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03392, over 972442.89 frames.], batch size: 35, lr: 2.33e-04
2022-05-06 14:07:18,153 INFO [train.py:715] (5/8) Epoch 9, batch 23200, loss[loss=0.1413, simple_loss=0.206, pruned_loss=0.03831, over 4889.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03453, over 972167.59 frames.], batch size: 32, lr: 2.33e-04
2022-05-06 14:07:57,913 INFO [train.py:715] (5/8) Epoch 9, batch 23250, loss[loss=0.1551, simple_loss=0.2239, pruned_loss=0.04314, over 4907.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03478, over 972564.16 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:08:37,682 INFO [train.py:715] (5/8) Epoch 9, batch 23300, loss[loss=0.1381, simple_loss=0.2206, pruned_loss=0.02781, over 4777.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.035, over 972136.85 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:09:17,440 INFO [train.py:715] (5/8) Epoch 9, batch 23350, loss[loss=0.1359, simple_loss=0.2215, pruned_loss=0.02516, over 4822.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.0353, over 971605.57 frames.], batch size: 25, lr: 2.33e-04
2022-05-06 14:09:56,734 INFO [train.py:715] (5/8) Epoch 9, batch 23400, loss[loss=0.1277, simple_loss=0.2043, pruned_loss=0.02554, over 4877.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03483, over 971828.96 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 14:10:35,592 INFO [train.py:715] (5/8) Epoch 9, batch 23450, loss[loss=0.1041, simple_loss=0.1748, pruned_loss=0.01676, over 4914.00 frames.], tot_loss[loss=0.1419, simple_loss=0.214, pruned_loss=0.03492, over 971117.75 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:11:14,355 INFO [train.py:715] (5/8) Epoch 9, batch 23500, loss[loss=0.1533, simple_loss=0.2256, pruned_loss=0.04044, over 4687.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03453, over 970895.94 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:11:52,877 INFO [train.py:715] (5/8) Epoch 9, batch 23550, loss[loss=0.1218, simple_loss=0.1926, pruned_loss=0.02547, over 4947.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03404, over 971110.31 frames.], batch size: 23, lr: 2.33e-04
2022-05-06 14:12:32,346 INFO [train.py:715] (5/8) Epoch 9, batch 23600, loss[loss=0.121, simple_loss=0.1951, pruned_loss=0.02345, over 4921.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03369, over 971932.02 frames.], batch size: 29, lr: 2.33e-04
2022-05-06 14:13:11,496 INFO [train.py:715] (5/8) Epoch 9, batch 23650, loss[loss=0.1325, simple_loss=0.2015, pruned_loss=0.03177, over 4844.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03431, over 971377.99 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:13:50,876 INFO [train.py:715] (5/8) Epoch 9, batch 23700, loss[loss=0.1383, simple_loss=0.2175, pruned_loss=0.02956, over 4942.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 972258.38 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:14:30,051 INFO [train.py:715] (5/8) Epoch 9, batch 23750, loss[loss=0.1407, simple_loss=0.2174, pruned_loss=0.03201, over 4748.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03457, over 972725.21 frames.], batch size: 19, lr: 2.33e-04
2022-05-06 14:15:09,283 INFO [train.py:715] (5/8) Epoch 9, batch 23800, loss[loss=0.158, simple_loss=0.2249, pruned_loss=0.04554, over 4982.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03482, over 972806.35 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:15:48,391 INFO [train.py:715] (5/8) Epoch 9, batch 23850, loss[loss=0.1579, simple_loss=0.2234, pruned_loss=0.04626, over 4695.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03441, over 972040.83 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:16:27,642 INFO [train.py:715] (5/8) Epoch 9, batch 23900, loss[loss=0.1523, simple_loss=0.2263, pruned_loss=0.03911, over 4963.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03454, over 972233.32 frames.], batch size: 24, lr: 2.33e-04
2022-05-06 14:17:06,535 INFO [train.py:715] (5/8) Epoch 9, batch 23950, loss[loss=0.1816, simple_loss=0.2437, pruned_loss=0.05973, over 4798.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03435, over 971687.23 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:17:45,501 INFO [train.py:715] (5/8) Epoch 9, batch 24000, loss[loss=0.1504, simple_loss=0.2172, pruned_loss=0.04186, over 4843.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.034, over 971911.70 frames.], batch size: 32, lr: 2.33e-04
2022-05-06 14:17:45,502 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 14:17:55,355 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1913, pruned_loss=0.01128, over 914524.00 frames.
2022-05-06 14:18:34,690 INFO [train.py:715] (5/8) Epoch 9, batch 24050, loss[loss=0.1334, simple_loss=0.2045, pruned_loss=0.03111, over 4955.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.0337, over 972008.63 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:19:14,962 INFO [train.py:715] (5/8) Epoch 9, batch 24100, loss[loss=0.1224, simple_loss=0.2019, pruned_loss=0.02147, over 4926.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03327, over 972360.51 frames.], batch size: 23, lr: 2.33e-04
2022-05-06 14:19:54,476 INFO [train.py:715] (5/8) Epoch 9, batch 24150, loss[loss=0.1256, simple_loss=0.1983, pruned_loss=0.02647, over 4800.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03358, over 972075.85 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:20:33,564 INFO [train.py:715] (5/8) Epoch 9, batch 24200, loss[loss=0.1398, simple_loss=0.2014, pruned_loss=0.03906, over 4802.00 frames.], tot_loss[loss=0.1398, simple_loss=0.212, pruned_loss=0.0338, over 971934.15 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:21:12,482 INFO [train.py:715] (5/8) Epoch 9, batch 24250, loss[loss=0.1195, simple_loss=0.1929, pruned_loss=0.02306, over 4827.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2119, pruned_loss=0.03372, over 972062.80 frames.], batch size: 26, lr: 2.33e-04
2022-05-06 14:21:52,132 INFO [train.py:715] (5/8) Epoch 9, batch 24300, loss[loss=0.1652, simple_loss=0.2453, pruned_loss=0.04259, over 4752.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03351, over 971866.68 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 14:22:31,314 INFO [train.py:715] (5/8) Epoch 9, batch 24350, loss[loss=0.1455, simple_loss=0.2142, pruned_loss=0.03844, over 4767.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03344, over 972732.14 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:23:10,724 INFO [train.py:715] (5/8) Epoch 9, batch 24400, loss[loss=0.159, simple_loss=0.2341, pruned_loss=0.04201, over 4852.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.0332, over 972579.42 frames.], batch size: 20, lr: 2.33e-04
2022-05-06 14:23:50,612 INFO [train.py:715] (5/8) Epoch 9, batch 24450, loss[loss=0.1435, simple_loss=0.2255, pruned_loss=0.03072, over 4821.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03324, over 972408.18 frames.], batch size: 27, lr: 2.33e-04
2022-05-06 14:24:30,636 INFO [train.py:715] (5/8) Epoch 9, batch 24500, loss[loss=0.1339, simple_loss=0.2122, pruned_loss=0.02785, over 4934.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.0332, over 971919.51 frames.], batch size: 29, lr: 2.33e-04
2022-05-06 14:25:10,996 INFO [train.py:715] (5/8) Epoch 9, batch 24550, loss[loss=0.1164, simple_loss=0.1967, pruned_loss=0.01802, over 4846.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03362, over 971434.90 frames.], batch size: 20, lr: 2.33e-04
2022-05-06 14:25:50,741 INFO [train.py:715] (5/8) Epoch 9, batch 24600, loss[loss=0.1216, simple_loss=0.2018, pruned_loss=0.02065, over 4747.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03394, over 972015.21 frames.], batch size: 19, lr: 2.33e-04
2022-05-06 14:26:30,714 INFO [train.py:715] (5/8) Epoch 9, batch 24650, loss[loss=0.1758, simple_loss=0.2659, pruned_loss=0.04283, over 4782.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03423, over 972768.62 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:27:09,791 INFO [train.py:715] (5/8) Epoch 9, batch 24700, loss[loss=0.1564, simple_loss=0.2236, pruned_loss=0.04461, over 4941.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03419, over 972575.75 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:27:48,505 INFO [train.py:715] (5/8) Epoch 9, batch 24750, loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03489, over 4828.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03415, over 972148.30 frames.], batch size: 13, lr: 2.33e-04
2022-05-06 14:28:28,023 INFO [train.py:715] (5/8) Epoch 9, batch 24800, loss[loss=0.1187, simple_loss=0.1905, pruned_loss=0.02346, over 4942.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2147, pruned_loss=0.03421, over 972316.22 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:29:07,569 INFO [train.py:715] (5/8) Epoch 9, batch 24850, loss[loss=0.1363, simple_loss=0.206, pruned_loss=0.0333, over 4780.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03381, over 972112.02 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:29:46,968 INFO [train.py:715] (5/8) Epoch 9, batch 24900, loss[loss=0.139, simple_loss=0.2142, pruned_loss=0.0319, over 4691.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03388, over 971856.47 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:30:26,387 INFO [train.py:715] (5/8) Epoch 9, batch 24950, loss[loss=0.1782, simple_loss=0.2359, pruned_loss=0.06024, over 4852.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03392, over 972163.12 frames.], batch size: 32, lr: 2.32e-04
2022-05-06 14:31:06,083 INFO [train.py:715] (5/8) Epoch 9, batch 25000, loss[loss=0.1367, simple_loss=0.2235, pruned_loss=0.02496, over 4804.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03354, over 972966.31 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:31:44,920 INFO [train.py:715] (5/8) Epoch 9, batch 25050, loss[loss=0.1528, simple_loss=0.228, pruned_loss=0.03882, over 4917.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03415, over 972796.16 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:32:24,414 INFO [train.py:715] (5/8) Epoch 9, batch 25100, loss[loss=0.1569, simple_loss=0.2215, pruned_loss=0.0461, over 4806.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03432, over 972306.21 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 14:33:03,523 INFO [train.py:715] (5/8) Epoch 9, batch 25150, loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03718, over 4986.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03438, over 972625.68 frames.], batch size: 27, lr: 2.32e-04
2022-05-06 14:33:42,580 INFO [train.py:715] (5/8) Epoch 9, batch 25200, loss[loss=0.1261, simple_loss=0.2086, pruned_loss=0.02179, over 4845.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03445, over 972738.10 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:34:21,838 INFO [train.py:715] (5/8) Epoch 9, batch 25250, loss[loss=0.1456, simple_loss=0.2215, pruned_loss=0.03484, over 4824.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03474, over 972415.50 frames.], batch size: 26, lr: 2.32e-04
2022-05-06 14:35:00,581 INFO [train.py:715] (5/8) Epoch 9, batch 25300, loss[loss=0.1261, simple_loss=0.1968, pruned_loss=0.02771, over 4802.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03471, over 971786.54 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:35:40,265 INFO [train.py:715] (5/8) Epoch 9, batch 25350, loss[loss=0.1425, simple_loss=0.2194, pruned_loss=0.0328, over 4692.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03473, over 971510.33 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:36:20,107 INFO [train.py:715] (5/8) Epoch 9, batch 25400, loss[loss=0.1257, simple_loss=0.1981, pruned_loss=0.02663, over 4804.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.0348, over 971604.81 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:37:00,344 INFO [train.py:715] (5/8) Epoch 9, batch 25450, loss[loss=0.1506, simple_loss=0.2293, pruned_loss=0.03597, over 4900.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03508, over 971247.78 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:37:38,911 INFO [train.py:715] (5/8) Epoch 9, batch 25500, loss[loss=0.1537, simple_loss=0.2312, pruned_loss=0.03812, over 4929.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03474, over 971034.53 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:38:18,074 INFO [train.py:715] (5/8) Epoch 9, batch 25550, loss[loss=0.1612, simple_loss=0.232, pruned_loss=0.04522, over 4830.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03477, over 971288.33 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:38:57,224 INFO [train.py:715] (5/8) Epoch 9, batch 25600, loss[loss=0.1455, simple_loss=0.2105, pruned_loss=0.04023, over 4915.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03484, over 970469.00 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:39:36,161 INFO [train.py:715] (5/8) Epoch 9, batch 25650, loss[loss=0.1111, simple_loss=0.1869, pruned_loss=0.01761, over 4786.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03424, over 971570.30 frames.], batch size: 12, lr: 2.32e-04
2022-05-06 14:40:15,295 INFO [train.py:715] (5/8) Epoch 9, batch 25700, loss[loss=0.1408, simple_loss=0.2081, pruned_loss=0.03678, over 4962.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03429, over 971386.68 frames.], batch size: 35, lr: 2.32e-04
2022-05-06 14:40:54,415 INFO [train.py:715] (5/8) Epoch 9, batch 25750, loss[loss=0.1408, simple_loss=0.2213, pruned_loss=0.03014, over 4893.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03465, over 971814.24 frames.], batch size: 32, lr: 2.32e-04
2022-05-06 14:41:33,410 INFO [train.py:715] (5/8) Epoch 9, batch 25800, loss[loss=0.1249, simple_loss=0.1944, pruned_loss=0.02765, over 4776.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.0344, over 971732.03 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:42:13,627 INFO [train.py:715] (5/8) Epoch 9, batch 25850, loss[loss=0.1453, simple_loss=0.2242, pruned_loss=0.03322, over 4898.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03447, over 972736.83 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:42:53,071 INFO [train.py:715] (5/8) Epoch 9, batch 25900, loss[loss=0.1151, simple_loss=0.1953, pruned_loss=0.01741, over 4808.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03429, over 973535.95 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 14:43:32,745 INFO [train.py:715] (5/8) Epoch 9, batch 25950, loss[loss=0.1555, simple_loss=0.2306, pruned_loss=0.0402, over 4698.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2146, pruned_loss=0.03428, over 973484.67 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:44:11,975 INFO [train.py:715] (5/8) Epoch 9, batch 26000, loss[loss=0.1135, simple_loss=0.1921, pruned_loss=0.01744, over 4987.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 972859.58 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 14:44:51,305 INFO [train.py:715] (5/8) Epoch 9, batch 26050, loss[loss=0.1544, simple_loss=0.2154, pruned_loss=0.04672, over 4732.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03398, over 972426.45 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:45:30,098 INFO [train.py:715] (5/8) Epoch 9, batch 26100, loss[loss=0.1809, simple_loss=0.2475, pruned_loss=0.05713, over 4894.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03396, over 971855.73 frames.], batch size: 39, lr: 2.32e-04
2022-05-06 14:46:09,803 INFO [train.py:715] (5/8) Epoch 9, batch 26150, loss[loss=0.1286, simple_loss=0.2007, pruned_loss=0.02827, over 4846.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2136, pruned_loss=0.03463, over 971506.75 frames.], batch size: 13, lr: 2.32e-04
2022-05-06 14:46:50,050 INFO [train.py:715] (5/8) Epoch 9, batch 26200, loss[loss=0.122, simple_loss=0.2017, pruned_loss=0.02116, over 4641.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03447, over 971402.92 frames.], batch size: 13, lr: 2.32e-04
2022-05-06 14:47:29,914 INFO [train.py:715] (5/8) Epoch 9, batch 26250, loss[loss=0.1719, simple_loss=0.2572, pruned_loss=0.04327, over 4958.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03384, over 972209.30 frames.], batch size: 24, lr: 2.32e-04
2022-05-06 14:48:09,843 INFO [train.py:715] (5/8) Epoch 9, batch 26300, loss[loss=0.1591, simple_loss=0.231, pruned_loss=0.04357, over 4784.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03447, over 972984.82 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:48:49,364 INFO [train.py:715] (5/8) Epoch 9, batch 26350, loss[loss=0.1356, simple_loss=0.2145, pruned_loss=0.02838, over 4868.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03449, over 973112.64 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:49:28,726 INFO [train.py:715] (5/8) Epoch 9, batch 26400, loss[loss=0.172, simple_loss=0.2316, pruned_loss=0.05618, over 4918.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03445, over 973290.24 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 14:50:07,636 INFO [train.py:715] (5/8) Epoch 9, batch 26450, loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.0306, over 4890.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2143, pruned_loss=0.03451, over 972914.00 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:50:46,955 INFO [train.py:715] (5/8) Epoch 9, batch 26500, loss[loss=0.1313, simple_loss=0.2029, pruned_loss=0.02985, over 4756.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03415, over 973049.15 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:51:26,797 INFO [train.py:715] (5/8) Epoch 9, batch 26550, loss[loss=0.1235, simple_loss=0.1963, pruned_loss=0.02532, over 4920.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03407, over 972526.30 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:52:06,133 INFO [train.py:715] (5/8) Epoch 9, batch 26600, loss[loss=0.1414, simple_loss=0.2222, pruned_loss=0.03027, over 4890.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03451, over 973012.30 frames.], batch size: 22, lr: 2.32e-04
2022-05-06 14:52:46,086 INFO [train.py:715] (5/8) Epoch 9, batch 26650, loss[loss=0.1836, simple_loss=0.2514, pruned_loss=0.05788, over 4694.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.0341, over 973142.43 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:53:25,378 INFO [train.py:715] (5/8) Epoch 9, batch 26700, loss[loss=0.1209, simple_loss=0.1877, pruned_loss=0.02703, over 4830.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03424, over 972809.50 frames.], batch size: 13, lr: 2.32e-04
2022-05-06 14:54:04,745 INFO [train.py:715] (5/8) Epoch 9, batch 26750, loss[loss=0.1194, simple_loss=0.1996, pruned_loss=0.01963, over 4876.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03395, over 972871.77 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:54:43,923 INFO [train.py:715] (5/8) Epoch 9, batch 26800, loss[loss=0.1375, simple_loss=0.2067, pruned_loss=0.03417, over 4770.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03465, over 972051.03 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:55:22,920 INFO [train.py:715] (5/8) Epoch 9, batch 26850, loss[loss=0.1176, simple_loss=0.1914, pruned_loss=0.02188, over 4791.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03484, over 971490.81 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 14:56:02,399 INFO [train.py:715] (5/8) Epoch 9, batch 26900, loss[loss=0.1663, simple_loss=0.23, pruned_loss=0.05125, over 4745.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03452, over 972730.97 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:56:42,230 INFO [train.py:715] (5/8) Epoch 9, batch 26950, loss[loss=0.1356, simple_loss=0.2077, pruned_loss=0.03173, over 4903.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03478, over 972653.02 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:57:21,398 INFO [train.py:715] (5/8) Epoch 9, batch 27000, loss[loss=0.1367, simple_loss=0.2061, pruned_loss=0.03368, over 4685.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03455, over 971819.04 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:57:21,398 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 14:57:30,963 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
2022-05-06 14:58:10,505 INFO [train.py:715] (5/8) Epoch 9, batch 27050, loss[loss=0.1178, simple_loss=0.1846, pruned_loss=0.02551, over 4885.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03421, over 971461.55 frames.], batch size: 22, lr: 2.32e-04
2022-05-06 14:58:50,082 INFO [train.py:715] (5/8) Epoch 9, batch 27100, loss[loss=0.1431, simple_loss=0.2228, pruned_loss=0.03166, over 4758.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03385, over 970493.79 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:59:30,121 INFO [train.py:715] (5/8) Epoch 9, batch 27150, loss[loss=0.1561, simple_loss=0.2274, pruned_loss=0.04243, over 4782.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2132, pruned_loss=0.03434, over 970009.13 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 15:00:09,247 INFO [train.py:715] (5/8) Epoch 9, batch 27200, loss[loss=0.1417, simple_loss=0.2037, pruned_loss=0.03988, over 4777.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03459, over 970397.20 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 15:00:48,162 INFO [train.py:715] (5/8) Epoch 9, batch 27250, loss[loss=0.1244, simple_loss=0.1926, pruned_loss=0.02814, over 4821.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03426, over 971299.16 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 15:01:27,382 INFO [train.py:715] (5/8) Epoch 9, batch 27300, loss[loss=0.1418, simple_loss=0.219, pruned_loss=0.03231, over 4949.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03389, over 971711.29 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 15:02:06,269 INFO [train.py:715] (5/8) Epoch 9, batch 27350, loss[loss=0.147, simple_loss=0.219, pruned_loss=0.03753, over 4912.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03421, over 972036.30 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 15:02:45,299 INFO [train.py:715] (5/8) Epoch 9, batch 27400, loss[loss=0.1386, simple_loss=0.2109, pruned_loss=0.03314, over 4968.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2149, pruned_loss=0.03439, over 973553.88 frames.], batch size: 24, lr: 2.32e-04
2022-05-06 15:03:24,466 INFO [train.py:715] (5/8) Epoch 9, batch 27450, loss[loss=0.189, simple_loss=0.2602, pruned_loss=0.0589, over 4802.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03429, over 972899.38 frames.], batch size: 24, lr: 2.32e-04
2022-05-06 15:04:03,431 INFO [train.py:715] (5/8) Epoch 9, batch 27500, loss[loss=0.1362, simple_loss=0.2067, pruned_loss=0.03284, over 4875.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.0344, over 972732.03 frames.], batch size: 20, lr: 2.32e-04
2022-05-06 15:04:42,460 INFO [train.py:715] (5/8) Epoch 9, batch 27550, loss[loss=0.1403, simple_loss=0.2283, pruned_loss=0.0262, over 4986.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03474, over 973431.59 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 15:05:21,387 INFO [train.py:715] (5/8) Epoch 9, batch 27600, loss[loss=0.1684, simple_loss=0.228, pruned_loss=0.0544, over 4854.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03452, over 972703.39 frames.], batch size: 38, lr: 2.32e-04
2022-05-06 15:06:00,164 INFO [train.py:715] (5/8) Epoch 9, batch 27650, loss[loss=0.1531, simple_loss=0.2133, pruned_loss=0.04643, over 4848.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.0349, over 973041.43 frames.], batch size: 32, lr: 2.32e-04
2022-05-06 15:06:39,016 INFO [train.py:715] (5/8) Epoch 9, batch 27700, loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03283, over 4910.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03477, over 974081.91 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 15:07:18,263 INFO [train.py:715] (5/8) Epoch 9, batch 27750, loss[loss=0.1488, simple_loss=0.2217, pruned_loss=0.03792, over 4817.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03481, over 974711.75 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:07:57,613 INFO [train.py:715] (5/8) Epoch 9, batch 27800, loss[loss=0.1421, simple_loss=0.2195, pruned_loss=0.03238, over 4979.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.0342, over 974388.76 frames.], batch size: 28, lr: 2.31e-04
2022-05-06 15:08:36,545 INFO [train.py:715] (5/8) Epoch 9, batch 27850, loss[loss=0.1491, simple_loss=0.231, pruned_loss=0.0336, over 4902.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03418, over 974569.07 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:09:16,414 INFO [train.py:715] (5/8) Epoch 9, batch 27900, loss[loss=0.1412, simple_loss=0.2061, pruned_loss=0.03816, over 4776.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03473, over 973668.01 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:09:54,910 INFO [train.py:715] (5/8) Epoch 9, batch 27950, loss[loss=0.1146, simple_loss=0.1979, pruned_loss=0.01563, over 4934.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03435, over 972819.45 frames.], batch size: 29, lr: 2.31e-04
2022-05-06 15:10:34,266 INFO [train.py:715] (5/8) Epoch 9, batch 28000, loss[loss=0.148, simple_loss=0.2182, pruned_loss=0.03892, over 4985.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03439, over 973515.75 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:11:13,571 INFO [train.py:715] (5/8) Epoch 9, batch 28050, loss[loss=0.1693, simple_loss=0.2264, pruned_loss=0.05607, over 4923.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03444, over 973226.22 frames.], batch size: 23, lr: 2.31e-04
2022-05-06 15:11:52,642 INFO [train.py:715] (5/8) Epoch 9, batch 28100, loss[loss=0.1532, simple_loss=0.2239, pruned_loss=0.0413, over 4825.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03472, over 973424.98 frames.], batch size: 26, lr: 2.31e-04
2022-05-06 15:12:31,905 INFO [train.py:715] (5/8) Epoch 9, batch 28150, loss[loss=0.1469, simple_loss=0.2139, pruned_loss=0.03996, over 4983.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03499, over 973223.53 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:13:10,820 INFO [train.py:715] (5/8) Epoch 9, batch 28200, loss[loss=0.1156, simple_loss=0.1891, pruned_loss=0.02105, over 4814.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03514, over 973089.89 frames.], batch size: 26, lr: 2.31e-04
2022-05-06 15:13:50,264 INFO [train.py:715] (5/8) Epoch 9, batch 28250, loss[loss=0.139, simple_loss=0.2172, pruned_loss=0.03036, over 4928.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2153, pruned_loss=0.03479, over 972269.62 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:14:28,525 INFO [train.py:715] (5/8) Epoch 9, batch 28300, loss[loss=0.103, simple_loss=0.1788, pruned_loss=0.01355, over 4813.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.035, over 972148.74 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:15:07,475 INFO [train.py:715] (5/8) Epoch 9, batch 28350, loss[loss=0.1499, simple_loss=0.2113, pruned_loss=0.0443, over 4977.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03514, over 972213.13 frames.], batch size: 33, lr: 2.31e-04
2022-05-06 15:15:46,871 INFO [train.py:715] (5/8) Epoch 9, batch 28400, loss[loss=0.1747, simple_loss=0.2396, pruned_loss=0.05483, over 4792.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.0349, over 972197.56 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:16:25,948 INFO [train.py:715] (5/8) Epoch 9, batch 28450, loss[loss=0.137, simple_loss=0.2038, pruned_loss=0.03507, over 4964.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03431, over 972055.96 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:17:04,385 INFO [train.py:715] (5/8) Epoch 9, batch 28500, loss[loss=0.1306, simple_loss=0.1974, pruned_loss=0.03189, over 4891.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03455, over 972541.34 frames.], batch size: 19, lr: 2.31e-04
2022-05-06 15:17:43,520 INFO [train.py:715] (5/8) Epoch 9, batch 28550, loss[loss=0.1192, simple_loss=0.1981, pruned_loss=0.02018, over 4961.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03399, over 972625.53 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:18:22,911 INFO [train.py:715] (5/8) Epoch 9, batch 28600, loss[loss=0.1354, simple_loss=0.2043, pruned_loss=0.03324, over 4957.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.0343, over 973104.29 frames.], batch size: 23, lr: 2.31e-04
2022-05-06 15:19:01,328 INFO [train.py:715] (5/8) Epoch 9, batch 28650, loss[loss=0.1353, simple_loss=0.2071, pruned_loss=0.03172, over 4904.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03441, over 972530.64 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:19:40,172 INFO [train.py:715] (5/8) Epoch 9, batch 28700, loss[loss=0.1707, simple_loss=0.2401, pruned_loss=0.05065, over 4972.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2147, pruned_loss=0.03423, over 972337.65 frames.], batch size: 35, lr: 2.31e-04
2022-05-06 15:20:19,620 INFO [train.py:715] (5/8) Epoch 9, batch 28750, loss[loss=0.2108, simple_loss=0.2454, pruned_loss=0.08812, over 4828.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03429, over 973219.68 frames.], batch size: 13, lr: 2.31e-04
2022-05-06 15:20:58,321 INFO [train.py:715] (5/8) Epoch 9, batch 28800, loss[loss=0.1277, simple_loss=0.2053, pruned_loss=0.02507, over 4773.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03431, over 972300.48 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:21:36,720 INFO [train.py:715] (5/8) Epoch 9, batch 28850, loss[loss=0.1393, simple_loss=0.2082, pruned_loss=0.03515, over 4778.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03429, over 972992.87 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:22:16,101 INFO [train.py:715] (5/8) Epoch 9, batch 28900, loss[loss=0.123, simple_loss=0.1965, pruned_loss=0.02473, over 4804.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03382, over 972893.30 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:22:55,364 INFO [train.py:715] (5/8) Epoch 9, batch 28950, loss[loss=0.1351, simple_loss=0.1974, pruned_loss=0.03644, over 4858.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03367, over 972190.67 frames.], batch size: 32, lr: 2.31e-04
2022-05-06 15:23:33,682 INFO [train.py:715] (5/8) Epoch 9, batch 29000, loss[loss=0.154, simple_loss=0.2159, pruned_loss=0.04601, over 4948.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03373, over 972661.16 frames.], batch size: 35, lr: 2.31e-04
2022-05-06 15:24:12,155 INFO [train.py:715] (5/8) Epoch 9, batch 29050, loss[loss=0.1214, simple_loss=0.1914, pruned_loss=0.02571, over 4951.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.03357, over 973236.02 frames.], batch size: 24, lr: 2.31e-04
2022-05-06 15:24:51,097 INFO [train.py:715] (5/8) Epoch 9, batch 29100, loss[loss=0.1578, simple_loss=0.2238, pruned_loss=0.04591, over 4789.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.03371, over 972463.58 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:25:30,247 INFO [train.py:715] (5/8) Epoch 9, batch 29150, loss[loss=0.1237, simple_loss=0.1862, pruned_loss=0.03058, over 4807.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03421, over 972291.99 frames.], batch size: 12, lr: 2.31e-04
2022-05-06 15:26:09,094 INFO [train.py:715] (5/8) Epoch 9, batch 29200, loss[loss=0.1264, simple_loss=0.1978, pruned_loss=0.02751, over 4984.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03433, over 972704.81 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:26:48,459 INFO [train.py:715] (5/8) Epoch 9, batch 29250, loss[loss=0.1434, simple_loss=0.2212, pruned_loss=0.03279, over 4933.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03422, over 973137.48 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:27:27,197 INFO [train.py:715] (5/8) Epoch 9, batch 29300, loss[loss=0.1133, simple_loss=0.1792, pruned_loss=0.02365, over 4801.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03471, over 973770.52 frames.], batch size: 12, lr: 2.31e-04
2022-05-06 15:28:06,267 INFO [train.py:715] (5/8) Epoch 9, batch 29350, loss[loss=0.1323, simple_loss=0.2111, pruned_loss=0.02681, over 4885.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03464, over 972813.64 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:28:45,210 INFO [train.py:715] (5/8) Epoch 9, batch 29400, loss[loss=0.1533, simple_loss=0.2314, pruned_loss=0.03756, over 4871.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03524, over 972823.62 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:29:23,946 INFO [train.py:715] (5/8) Epoch 9, batch 29450, loss[loss=0.1151, simple_loss=0.1938, pruned_loss=0.01823, over 4813.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03499, over 973090.60 frames.], batch size: 27, lr: 2.31e-04
2022-05-06 15:30:02,403 INFO [train.py:715] (5/8) Epoch 9, batch 29500, loss[loss=0.1668, simple_loss=0.2339, pruned_loss=0.04991, over 4694.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03499, over 972762.21 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:30:41,337 INFO [train.py:715] (5/8) Epoch 9, batch 29550, loss[loss=0.1361, simple_loss=0.226, pruned_loss=0.02311, over 4816.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03474, over 973209.02 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:31:20,277 INFO [train.py:715] (5/8) Epoch 9, batch 29600, loss[loss=0.135, simple_loss=0.2182, pruned_loss=0.02588, over 4742.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03485, over 971492.07 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:31:59,538 INFO [train.py:715] (5/8) Epoch 9, batch 29650, loss[loss=0.1613, simple_loss=0.2449, pruned_loss=0.03889, over 4742.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03525, over 972816.26 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:32:39,147 INFO [train.py:715] (5/8) Epoch 9, batch 29700, loss[loss=0.1339, simple_loss=0.2176, pruned_loss=0.02503, over 4817.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03505, over 972727.65 frames.], batch size: 27, lr: 2.31e-04
2022-05-06 15:33:17,089 INFO [train.py:715] (5/8) Epoch 9, batch 29750, loss[loss=0.1351, simple_loss=0.2066, pruned_loss=0.03183, over 4776.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03531, over 973159.51 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:33:55,772 INFO [train.py:715] (5/8) Epoch 9, batch 29800, loss[loss=0.1934, simple_loss=0.2696, pruned_loss=0.05858, over 4951.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03523, over 972260.83 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:34:34,891 INFO [train.py:715] (5/8) Epoch 9, batch 29850, loss[loss=0.1599, simple_loss=0.2377, pruned_loss=0.04104, over 4953.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2153, pruned_loss=0.03479, over 972129.95 frames.], batch size: 29, lr: 2.31e-04
2022-05-06 15:35:13,058 INFO [train.py:715] (5/8) Epoch 9, batch 29900, loss[loss=0.1414, simple_loss=0.2197, pruned_loss=0.03153, over 4818.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2148, pruned_loss=0.03432, over 972453.94 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:35:52,534 INFO [train.py:715] (5/8) Epoch 9, batch 29950, loss[loss=0.1334, simple_loss=0.2081, pruned_loss=0.0294, over 4861.00 frames.], tot_loss[loss=0.1417, simple_loss=0.215, pruned_loss=0.03423, over 973177.84 frames.], batch size: 30, lr: 2.31e-04
2022-05-06 15:36:31,404 INFO [train.py:715] (5/8) Epoch 9, batch 30000, loss[loss=0.164, simple_loss=0.2189, pruned_loss=0.05461, over 4782.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03367, over 972270.45 frames.], batch size: 12, lr: 2.31e-04
2022-05-06 15:36:31,405 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 15:36:40,919 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1911, pruned_loss=0.01124, over 914524.00 frames.
2022-05-06 15:37:20,160 INFO [train.py:715] (5/8) Epoch 9, batch 30050, loss[loss=0.1285, simple_loss=0.2017, pruned_loss=0.02767, over 4870.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2145, pruned_loss=0.03399, over 972499.07 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:37:58,804 INFO [train.py:715] (5/8) Epoch 9, batch 30100, loss[loss=0.1856, simple_loss=0.2504, pruned_loss=0.06039, over 4708.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2144, pruned_loss=0.03404, over 971133.81 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:38:38,124 INFO [train.py:715] (5/8) Epoch 9, batch 30150, loss[loss=0.1374, simple_loss=0.2154, pruned_loss=0.02973, over 4904.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03437, over 971187.29 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:39:17,506 INFO [train.py:715] (5/8) Epoch 9, batch 30200, loss[loss=0.1123, simple_loss=0.1769, pruned_loss=0.02384, over 4868.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03415, over 971048.63 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:39:56,687 INFO [train.py:715] (5/8) Epoch 9, batch 30250, loss[loss=0.1442, simple_loss=0.2145, pruned_loss=0.03698, over 4786.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03412, over 972706.10 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:40:35,246 INFO [train.py:715] (5/8) Epoch 9, batch 30300, loss[loss=0.1366, simple_loss=0.2087, pruned_loss=0.03226, over 4899.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.0336, over 973169.26 frames.], batch size: 19, lr: 2.31e-04
2022-05-06 15:41:14,056 INFO [train.py:715] (5/8) Epoch 9, batch 30350, loss[loss=0.1421, simple_loss=0.213, pruned_loss=0.03563, over 4902.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03411, over 972328.67 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:41:53,484 INFO [train.py:715] (5/8) Epoch 9, batch 30400, loss[loss=0.1376, simple_loss=0.2124, pruned_loss=0.03135, over 4813.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03429, over 971504.81 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:42:32,292 INFO [train.py:715] (5/8) Epoch 9, batch 30450, loss[loss=0.12, simple_loss=0.1991, pruned_loss=0.02049, over 4887.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03397, over 972143.57 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:43:10,916 INFO [train.py:715] (5/8) Epoch 9, batch 30500, loss[loss=0.125, simple_loss=0.1958, pruned_loss=0.02705, over 4900.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03463, over 971535.50 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:43:49,986 INFO [train.py:715] (5/8) Epoch 9, batch 30550, loss[loss=0.1527, simple_loss=0.2214, pruned_loss=0.042, over 4961.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03505, over 971946.93 frames.], batch size: 35, lr: 2.31e-04
2022-05-06 15:44:28,846 INFO [train.py:715] (5/8) Epoch 9, batch 30600, loss[loss=0.1409, simple_loss=0.2193, pruned_loss=0.03122, over 4948.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03511, over 971642.67 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:45:06,879 INFO [train.py:715] (5/8) Epoch 9, batch 30650, loss[loss=0.1485, simple_loss=0.2105, pruned_loss=0.0433, over 4842.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03481, over 971875.80 frames.], batch size: 30, lr: 2.31e-04
2022-05-06 15:45:45,879 INFO [train.py:715] (5/8) Epoch 9, batch 30700, loss[loss=0.1486, simple_loss=0.2176, pruned_loss=0.03976, over 4812.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03452, over 971906.47 frames.], batch size: 24, lr: 2.30e-04
2022-05-06 15:46:27,570 INFO [train.py:715] (5/8) Epoch 9, batch 30750, loss[loss=0.167, simple_loss=0.2396, pruned_loss=0.04713, over 4722.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03472, over 970692.91 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 15:47:06,255 INFO [train.py:715] (5/8) Epoch 9, batch 30800, loss[loss=0.1214, simple_loss=0.1954, pruned_loss=0.0237, over 4985.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03474, over 970998.24 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 15:47:44,602 INFO [train.py:715] (5/8) Epoch 9, batch 30850, loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03729, over 4774.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03467, over 971052.96 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 15:48:23,856 INFO [train.py:715] (5/8) Epoch 9, batch 30900, loss[loss=0.1555, simple_loss=0.2184, pruned_loss=0.04633, over 4785.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.0345, over 972028.79 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 15:49:03,044 INFO [train.py:715] (5/8) Epoch 9, batch 30950, loss[loss=0.1556, simple_loss=0.2221, pruned_loss=0.04458, over 4914.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03429, over 971610.21 frames.], batch size: 18, lr: 2.30e-04
2022-05-06 15:49:41,533 INFO [train.py:715] (5/8) Epoch 9, batch 31000, loss[loss=0.1664, simple_loss=0.2265, pruned_loss=0.05313, over 4849.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.0339, over 972645.37 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 15:50:20,507 INFO [train.py:715] (5/8) Epoch 9, batch 31050, loss[loss=0.1488, simple_loss=0.2265, pruned_loss=0.03557, over 4807.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03425, over 971125.66 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 15:50:59,764 INFO [train.py:715] (5/8) Epoch 9, batch 31100, loss[loss=0.1985, simple_loss=0.2656, pruned_loss=0.06574, over 4749.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.0346, over 971863.33 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 15:51:38,436 INFO [train.py:715] (5/8) Epoch 9, batch 31150, loss[loss=0.1118, simple_loss=0.184, pruned_loss=0.01986, over 4756.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03487, over 971342.32 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 15:52:17,018 INFO [train.py:715] (5/8) Epoch 9, batch 31200, loss[loss=0.1301, simple_loss=0.2055, pruned_loss=0.02734, over 4941.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03454, over 972088.44 frames.], batch size: 23, lr: 2.30e-04
2022-05-06 15:52:56,546 INFO [train.py:715] (5/8) Epoch 9, batch 31250, loss[loss=0.1287, simple_loss=0.2103, pruned_loss=0.02351, over 4920.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03414, over 972033.35 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 15:53:35,999 INFO [train.py:715] (5/8) Epoch 9, batch 31300, loss[loss=0.149, simple_loss=0.2051, pruned_loss=0.04651, over 4951.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03418, over 972207.57 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 15:54:14,967 INFO [train.py:715] (5/8) Epoch 9, batch 31350, loss[loss=0.148, simple_loss=0.2204, pruned_loss=0.0378, over 4920.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.03378, over 972104.53 frames.], batch size: 18, lr: 2.30e-04
2022-05-06 15:54:53,756 INFO [train.py:715] (5/8) Epoch 9, batch 31400, loss[loss=0.1539, simple_loss=0.2172, pruned_loss=0.04528, over 4753.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03343, over 971561.07 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 15:55:32,698 INFO [train.py:715] (5/8) Epoch 9, batch 31450, loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.03659, over 4861.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03369, over 972138.09 frames.], batch size: 34, lr: 2.30e-04
2022-05-06 15:56:11,770 INFO [train.py:715] (5/8) Epoch 9, batch 31500, loss[loss=0.1552, simple_loss=0.2175, pruned_loss=0.04647, over 4839.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03359, over 972083.02 frames.], batch size: 30, lr: 2.30e-04
2022-05-06 15:56:50,181 INFO [train.py:715] (5/8) Epoch 9, batch 31550, loss[loss=0.1357, simple_loss=0.2105, pruned_loss=0.03047, over 4847.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03379, over 972389.44 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 15:57:29,719 INFO [train.py:715] (5/8) Epoch 9, batch 31600, loss[loss=0.1711, simple_loss=0.233, pruned_loss=0.05454, over 4789.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03428, over 971629.99 frames.], batch size: 24, lr: 2.30e-04
2022-05-06 15:58:09,720 INFO [train.py:715] (5/8) Epoch 9, batch 31650, loss[loss=0.1332, simple_loss=0.2092, pruned_loss=0.02857, over 4871.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03438, over 971531.81 frames.], batch size: 20, lr: 2.30e-04
2022-05-06 15:58:48,438 INFO [train.py:715] (5/8) Epoch 9, batch 31700, loss[loss=0.1195, simple_loss=0.1931, pruned_loss=0.02294, over 4840.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03419, over 971465.08 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 15:59:27,450 INFO [train.py:715] (5/8) Epoch 9, batch 31750, loss[loss=0.1496, simple_loss=0.2255, pruned_loss=0.03686, over 4896.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03474, over 971424.80 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 16:00:06,075 INFO [train.py:715] (5/8) Epoch 9, batch 31800, loss[loss=0.1462, simple_loss=0.2149, pruned_loss=0.03876, over 4888.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03444, over 971633.33 frames.], batch size: 32, lr: 2.30e-04
2022-05-06 16:00:45,143 INFO [train.py:715] (5/8) Epoch 9, batch 31850, loss[loss=0.14, simple_loss=0.2141, pruned_loss=0.03299, over 4911.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03466, over 971816.67 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:01:23,637 INFO [train.py:715] (5/8) Epoch 9, batch 31900, loss[loss=0.1477, simple_loss=0.224, pruned_loss=0.03568, over 4898.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03474, over 970984.48 frames.], batch size: 22, lr: 2.30e-04
2022-05-06 16:02:02,944 INFO [train.py:715] (5/8) Epoch 9, batch 31950, loss[loss=0.15, simple_loss=0.2195, pruned_loss=0.0402, over 4858.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03482, over 970838.81 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 16:02:42,216 INFO [train.py:715] (5/8) Epoch 9, batch 32000, loss[loss=0.1565, simple_loss=0.2215, pruned_loss=0.0458, over 4959.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03411, over 970767.59 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:03:20,778 INFO [train.py:715] (5/8) Epoch 9, batch 32050, loss[loss=0.1279, simple_loss=0.1923, pruned_loss=0.03175, over 4857.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03413, over 971800.09 frames.], batch size: 20, lr: 2.30e-04
2022-05-06 16:03:59,264 INFO [train.py:715] (5/8) Epoch 9, batch 32100, loss[loss=0.1201, simple_loss=0.1944, pruned_loss=0.02283, over 4773.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03397, over 972197.39 frames.], batch size: 12, lr: 2.30e-04
2022-05-06 16:04:38,259 INFO [train.py:715] (5/8) Epoch 9, batch 32150, loss[loss=0.1244, simple_loss=0.204, pruned_loss=0.02241, over 4775.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03325, over 972171.59 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:05:17,701 INFO [train.py:715] (5/8) Epoch 9, batch 32200, loss[loss=0.1228, simple_loss=0.188, pruned_loss=0.02878, over 4833.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03313, over 971719.77 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 16:05:55,460 INFO [train.py:715] (5/8) Epoch 9, batch 32250, loss[loss=0.1418, simple_loss=0.2153, pruned_loss=0.03411, over 4919.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03359, over 971906.77 frames.], batch size: 39, lr: 2.30e-04
2022-05-06 16:06:34,663 INFO [train.py:715] (5/8) Epoch 9, batch 32300, loss[loss=0.1311, simple_loss=0.2078, pruned_loss=0.02722, over 4981.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03312, over 972474.74 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 16:07:13,840 INFO [train.py:715] (5/8) Epoch 9, batch 32350, loss[loss=0.1247, simple_loss=0.2055, pruned_loss=0.02199, over 4797.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.0335, over 972864.77 frames.], batch size: 24, lr: 2.30e-04
2022-05-06 16:07:52,331 INFO [train.py:715] (5/8) Epoch 9, batch 32400, loss[loss=0.12, simple_loss=0.1942, pruned_loss=0.02288, over 4933.00 frames.], tot_loss[loss=0.14, simple_loss=0.2134, pruned_loss=0.03337, over 972970.78 frames.], batch size: 29, lr: 2.30e-04
2022-05-06 16:08:31,414 INFO [train.py:715] (5/8) Epoch 9, batch 32450, loss[loss=0.1307, simple_loss=0.2003, pruned_loss=0.03053, over 4819.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03405, over 973737.38 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:09:10,514 INFO [train.py:715] (5/8) Epoch 9, batch 32500, loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04415, over 4902.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03423, over 974317.25 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 16:09:49,358 INFO [train.py:715] (5/8) Epoch 9, batch 32550, loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02947, over 4926.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03407, over 973916.03 frames.], batch size: 23, lr: 2.30e-04
2022-05-06 16:10:27,861 INFO [train.py:715] (5/8) Epoch 9, batch 32600, loss[loss=0.1469, simple_loss=0.22, pruned_loss=0.03691, over 4939.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03404, over 974119.54 frames.], batch size: 39, lr: 2.30e-04
2022-05-06 16:11:06,892 INFO [train.py:715] (5/8) Epoch 9, batch 32650, loss[loss=0.125, simple_loss=0.2068, pruned_loss=0.02163, over 4824.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03417, over 973348.63 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 16:11:45,870 INFO [train.py:715] (5/8) Epoch 9, batch 32700, loss[loss=0.1249, simple_loss=0.2017, pruned_loss=0.02406, over 4809.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2144, pruned_loss=0.03386, over 973100.05 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 16:12:24,793 INFO [train.py:715] (5/8) Epoch 9, batch 32750, loss[loss=0.1446, simple_loss=0.2143, pruned_loss=0.03746, over 4793.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.0336, over 972576.91 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:13:03,520 INFO [train.py:715] (5/8) Epoch 9, batch 32800, loss[loss=0.1641, simple_loss=0.2321, pruned_loss=0.04812, over 4843.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2146, pruned_loss=0.03402, over 971913.67 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:13:42,564 INFO [train.py:715] (5/8) Epoch 9, batch 32850, loss[loss=0.1349, simple_loss=0.2065, pruned_loss=0.03166, over 4861.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2147, pruned_loss=0.03428, over 971937.96 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 16:14:21,301 INFO [train.py:715] (5/8) Epoch 9, batch 32900, loss[loss=0.159, simple_loss=0.224, pruned_loss=0.04703, over 4985.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03443, over 971509.56 frames.], batch size: 33, lr: 2.30e-04
2022-05-06 16:14:59,681 INFO [train.py:715] (5/8) Epoch 9, batch 32950, loss[loss=0.1338, simple_loss=0.2098, pruned_loss=0.02894, over 4821.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03426, over 971128.77 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 16:15:38,638 INFO [train.py:715] (5/8) Epoch 9, batch 33000, loss[loss=0.1496, simple_loss=0.2166, pruned_loss=0.04128, over 4968.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03378, over 972070.12 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:15:38,639 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 16:15:48,000 INFO [train.py:742] (5/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1913, pruned_loss=0.01119, over 914524.00 frames.
2022-05-06 16:16:27,262 INFO [train.py:715] (5/8) Epoch 9, batch 33050, loss[loss=0.1345, simple_loss=0.2058, pruned_loss=0.03165, over 4744.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03351, over 972999.49 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 16:17:06,454 INFO [train.py:715] (5/8) Epoch 9, batch 33100, loss[loss=0.133, simple_loss=0.1991, pruned_loss=0.03343, over 4969.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.0334, over 973736.92 frames.], batch size: 35, lr: 2.30e-04
2022-05-06 16:17:45,624 INFO [train.py:715] (5/8) Epoch 9, batch 33150, loss[loss=0.1571, simple_loss=0.2312, pruned_loss=0.04145, over 4956.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.0335, over 973945.64 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:18:25,450 INFO [train.py:715] (5/8) Epoch 9, batch 33200, loss[loss=0.1598, simple_loss=0.2259, pruned_loss=0.04686, over 4760.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03405, over 973127.74 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 16:19:04,995 INFO [train.py:715] (5/8) Epoch 9, batch 33250, loss[loss=0.1174, simple_loss=0.1987, pruned_loss=0.01808, over 4829.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03378, over 973037.78 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:19:44,051 INFO [train.py:715] (5/8) Epoch 9, batch 33300, loss[loss=0.1444, simple_loss=0.2295, pruned_loss=0.0296, over 4835.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03377, over 973297.30 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 16:20:23,549 INFO [train.py:715] (5/8) Epoch 9, batch 33350, loss[loss=0.1498, simple_loss=0.2198, pruned_loss=0.03994, over 4959.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03455, over 972982.16 frames.], batch size: 35, lr: 2.30e-04
2022-05-06 16:21:03,297 INFO [train.py:715] (5/8) Epoch 9, batch 33400, loss[loss=0.1631, simple_loss=0.2396, pruned_loss=0.0433, over 4931.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2143, pruned_loss=0.0338, over 973781.06 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:21:43,052 INFO [train.py:715] (5/8) Epoch 9, batch 33450, loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02992, over 4925.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03413, over 972949.26 frames.], batch size: 18, lr: 2.30e-04
2022-05-06 16:22:22,075 INFO [train.py:715] (5/8) Epoch 9, batch 33500, loss[loss=0.1848, simple_loss=0.248, pruned_loss=0.06075, over 4975.00 frames.], tot_loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03453, over 973362.49 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:23:00,824 INFO [train.py:715] (5/8) Epoch 9, batch 33550, loss[loss=0.1318, simple_loss=0.2161, pruned_loss=0.0237, over 4817.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03418, over 973030.93 frames.], batch size: 27, lr: 2.30e-04
2022-05-06 16:23:40,547 INFO [train.py:715] (5/8) Epoch 9, batch 33600, loss[loss=0.1318, simple_loss=0.1963, pruned_loss=0.03368, over 4830.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03405, over 972760.74 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 16:24:19,320 INFO [train.py:715] (5/8) Epoch 9, batch 33650, loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03445, over 4933.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03423, over 972780.30 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:24:58,231 INFO [train.py:715] (5/8) Epoch 9, batch 33700, loss[loss=0.1397, simple_loss=0.2215, pruned_loss=0.02895, over 4916.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03396, over 972068.72 frames.], batch size: 18, lr: 2.29e-04
2022-05-06 16:25:37,406 INFO [train.py:715] (5/8) Epoch 9, batch 33750, loss[loss=0.1388, simple_loss=0.208, pruned_loss=0.03486, over 4985.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2137, pruned_loss=0.03365, over 973080.88 frames.], batch size: 28, lr: 2.29e-04
2022-05-06 16:26:16,197 INFO [train.py:715] (5/8) Epoch 9, batch 33800, loss[loss=0.1583, simple_loss=0.2286, pruned_loss=0.04402, over 4839.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2133, pruned_loss=0.03322, over 972837.80 frames.], batch size: 20, lr: 2.29e-04
2022-05-06 16:26:54,912 INFO [train.py:715] (5/8) Epoch 9, batch 33850, loss[loss=0.1592, simple_loss=0.2293, pruned_loss=0.04457, over 4764.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03372, over 973062.67 frames.], batch size: 16, lr: 2.29e-04
2022-05-06 16:27:33,753 INFO [train.py:715] (5/8) Epoch 9, batch 33900, loss[loss=0.1472, simple_loss=0.217, pruned_loss=0.0387, over 4771.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2145, pruned_loss=0.03368, over 972225.37 frames.], batch size: 14, lr: 2.29e-04
2022-05-06 16:28:13,481 INFO [train.py:715] (5/8) Epoch 9, batch 33950, loss[loss=0.1219, simple_loss=0.2055, pruned_loss=0.0192, over 4756.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2149, pruned_loss=0.03375, over 971220.77 frames.], batch size: 19, lr: 2.29e-04
2022-05-06 16:28:52,281 INFO [train.py:715] (5/8) Epoch 9, batch 34000, loss[loss=0.1317, simple_loss=0.2091, pruned_loss=0.02716, over 4872.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03376, over 971218.00 frames.], batch size: 19, lr: 2.29e-04
2022-05-06 16:29:31,510 INFO [train.py:715] (5/8) Epoch 9, batch 34050, loss[loss=0.1442, simple_loss=0.2131, pruned_loss=0.03762, over 4837.00 frames.], tot_loss[loss=0.141, simple_loss=0.2143, pruned_loss=0.03389, over 972716.72 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:30:09,974 INFO [train.py:715] (5/8) Epoch 9, batch 34100, loss[loss=0.1415, simple_loss=0.2102, pruned_loss=0.03641, over 4866.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2143, pruned_loss=0.0337, over 972940.75 frames.], batch size: 32, lr: 2.29e-04
2022-05-06 16:30:49,070 INFO [train.py:715] (5/8) Epoch 9, batch 34150, loss[loss=0.1394, simple_loss=0.2238, pruned_loss=0.02748, over 4937.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2137, pruned_loss=0.03332, over 972065.17 frames.], batch size: 23, lr: 2.29e-04
2022-05-06 16:31:27,539 INFO [train.py:715] (5/8) Epoch 9, batch 34200, loss[loss=0.1282, simple_loss=0.2029, pruned_loss=0.02676, over 4977.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03327, over 972113.94 frames.], batch size: 24, lr: 2.29e-04
2022-05-06 16:32:05,772 INFO [train.py:715] (5/8) Epoch 9, batch 34250, loss[loss=0.1578, simple_loss=0.2308, pruned_loss=0.04241, over 4835.00 frames.], tot_loss[loss=0.14, simple_loss=0.2135, pruned_loss=0.03322, over 972542.22 frames.], batch size: 30, lr: 2.29e-04
2022-05-06 16:32:45,091 INFO [train.py:715] (5/8) Epoch 9, batch 34300, loss[loss=0.1447, simple_loss=0.2197, pruned_loss=0.03486, over 4979.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2152, pruned_loss=0.03392, over 973611.81 frames.], batch size: 35, lr: 2.29e-04
2022-05-06 16:33:23,850 INFO [train.py:715] (5/8) Epoch 9, batch 34350, loss[loss=0.1636, simple_loss=0.2311, pruned_loss=0.04808, over 4898.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2149, pruned_loss=0.03394, over 973765.58 frames.], batch size: 19, lr: 2.29e-04
2022-05-06 16:34:02,523 INFO [train.py:715] (5/8) Epoch 9, batch 34400, loss[loss=0.1575, simple_loss=0.2344, pruned_loss=0.04028, over 4760.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2151, pruned_loss=0.03406, over 974273.58 frames.], batch size: 19, lr: 2.29e-04
2022-05-06 16:34:41,410 INFO [train.py:715] (5/8) Epoch 9, batch 34450, loss[loss=0.1518, simple_loss=0.2345, pruned_loss=0.03453, over 4907.00 frames.], tot_loss[loss=0.1417, simple_loss=0.215, pruned_loss=0.0342, over 974621.84 frames.], batch size: 17, lr: 2.29e-04
2022-05-06 16:35:20,339 INFO [train.py:715] (5/8) Epoch 9, batch 34500, loss[loss=0.1363, simple_loss=0.2175, pruned_loss=0.02748, over 4800.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2148, pruned_loss=0.03367, over 974654.40 frames.], batch size: 13, lr: 2.29e-04
2022-05-06 16:35:59,374 INFO [train.py:715] (5/8) Epoch 9, batch 34550, loss[loss=0.1554, simple_loss=0.2215, pruned_loss=0.04468, over 4860.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2153, pruned_loss=0.03429, over 974323.09 frames.], batch size: 32, lr: 2.29e-04
2022-05-06 16:36:38,007 INFO [train.py:715] (5/8) Epoch 9, batch 34600, loss[loss=0.1555, simple_loss=0.2324, pruned_loss=0.0393, over 4963.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2151, pruned_loss=0.03438, over 973379.77 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:37:17,108 INFO [train.py:715] (5/8) Epoch 9, batch 34650, loss[loss=0.1186, simple_loss=0.1898, pruned_loss=0.02371, over 4901.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2147, pruned_loss=0.03436, over 972893.79 frames.], batch size: 19, lr: 2.29e-04
2022-05-06 16:37:56,492 INFO [train.py:715] (5/8) Epoch 9, batch 34700, loss[loss=0.14, simple_loss=0.2092, pruned_loss=0.03546, over 4981.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2151, pruned_loss=0.03452, over 973258.93 frames.], batch size: 24, lr: 2.29e-04
2022-05-06 16:38:34,783 INFO [train.py:715] (5/8) Epoch 9, batch 34750, loss[loss=0.1071, simple_loss=0.1845, pruned_loss=0.01488, over 4806.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03451, over 972063.93 frames.], batch size: 12, lr: 2.29e-04
2022-05-06 16:39:12,243 INFO [train.py:715] (5/8) Epoch 9, batch 34800, loss[loss=0.1144, simple_loss=0.1898, pruned_loss=0.01955, over 4741.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03357, over 970265.11 frames.], batch size: 12, lr: 2.29e-04
2022-05-06 16:40:01,152 INFO [train.py:715] (5/8) Epoch 10, batch 0, loss[loss=0.163, simple_loss=0.2402, pruned_loss=0.0429, over 4967.00 frames.], tot_loss[loss=0.163, simple_loss=0.2402, pruned_loss=0.0429, over 4967.00 frames.], batch size: 39, lr: 2.19e-04
2022-05-06 16:40:41,025 INFO [train.py:715] (5/8) Epoch 10, batch 50, loss[loss=0.1554, simple_loss=0.2323, pruned_loss=0.0393, over 4921.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2139, pruned_loss=0.03512, over 219643.53 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:41:20,748 INFO [train.py:715] (5/8) Epoch 10, batch 100, loss[loss=0.1269, simple_loss=0.2049, pruned_loss=0.02452, over 4939.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03513, over 387107.31 frames.], batch size: 23, lr: 2.19e-04
2022-05-06 16:42:00,748 INFO [train.py:715] (5/8) Epoch 10, batch 150, loss[loss=0.1442, simple_loss=0.2119, pruned_loss=0.03826, over 4830.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.0338, over 516164.99 frames.], batch size: 13, lr: 2.19e-04
2022-05-06 16:42:41,339 INFO [train.py:715] (5/8) Epoch 10, batch 200, loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03254, over 4843.00 frames.], tot_loss[loss=0.142, simple_loss=0.2151, pruned_loss=0.03451, over 616189.75 frames.], batch size: 34, lr: 2.19e-04
2022-05-06 16:43:22,395 INFO [train.py:715] (5/8) Epoch 10, batch 250, loss[loss=0.1765, simple_loss=0.2449, pruned_loss=0.05401, over 4794.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.0335, over 695542.12 frames.], batch size: 24, lr: 2.19e-04
2022-05-06 16:44:03,224 INFO [train.py:715] (5/8) Epoch 10, batch 300, loss[loss=0.1442, simple_loss=0.2296, pruned_loss=0.0294, over 4765.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2139, pruned_loss=0.0337, over 756331.82 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:44:43,669 INFO [train.py:715] (5/8) Epoch 10, batch 350, loss[loss=0.1774, simple_loss=0.2359, pruned_loss=0.05947, over 4842.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03352, over 805056.32 frames.], batch size: 30, lr: 2.19e-04
2022-05-06 16:45:25,025 INFO [train.py:715] (5/8) Epoch 10, batch 400, loss[loss=0.1751, simple_loss=0.2609, pruned_loss=0.04467, over 4939.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03322, over 843091.20 frames.], batch size: 21, lr: 2.19e-04
2022-05-06 16:46:06,715 INFO [train.py:715] (5/8) Epoch 10, batch 450, loss[loss=0.1202, simple_loss=0.1992, pruned_loss=0.02057, over 4918.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.0331, over 870930.18 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:46:47,449 INFO [train.py:715] (5/8) Epoch 10, batch 500, loss[loss=0.1191, simple_loss=0.1906, pruned_loss=0.02375, over 4893.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03297, over 893270.51 frames.], batch size: 22, lr: 2.19e-04
2022-05-06 16:47:28,880 INFO [train.py:715] (5/8) Epoch 10, batch 550, loss[loss=0.1341, simple_loss=0.2062, pruned_loss=0.03098, over 4804.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03321, over 911284.08 frames.], batch size: 25, lr: 2.19e-04
2022-05-06 16:48:10,022 INFO [train.py:715] (5/8) Epoch 10, batch 600, loss[loss=0.1382, simple_loss=0.2093, pruned_loss=0.03356, over 4823.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03378, over 924842.52 frames.], batch size: 27, lr: 2.19e-04
2022-05-06 16:48:50,532 INFO [train.py:715] (5/8) Epoch 10, batch 650, loss[loss=0.1404, simple_loss=0.211, pruned_loss=0.03488, over 4940.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03386, over 935863.55 frames.], batch size: 23, lr: 2.19e-04
2022-05-06 16:49:31,190 INFO [train.py:715] (5/8) Epoch 10, batch 700, loss[loss=0.1955, simple_loss=0.2667, pruned_loss=0.06211, over 4751.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03416, over 944446.08 frames.], batch size: 19, lr: 2.19e-04
2022-05-06 16:50:12,728 INFO [train.py:715] (5/8) Epoch 10, batch 750, loss[loss=0.1194, simple_loss=0.1936, pruned_loss=0.02261, over 4821.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03458, over 950652.36 frames.], batch size: 13, lr: 2.19e-04
2022-05-06 16:50:54,000 INFO [train.py:715] (5/8) Epoch 10, batch 800, loss[loss=0.1445, simple_loss=0.2144, pruned_loss=0.03733, over 4817.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03454, over 956540.47 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 16:51:34,412 INFO [train.py:715] (5/8) Epoch 10, batch 850, loss[loss=0.1663, simple_loss=0.2458, pruned_loss=0.04337, over 4896.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03416, over 959795.05 frames.], batch size: 39, lr: 2.19e-04
2022-05-06 16:52:15,215 INFO [train.py:715] (5/8) Epoch 10, batch 900, loss[loss=0.1519, simple_loss=0.2243, pruned_loss=0.03974, over 4958.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03373, over 962012.98 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 16:52:55,734 INFO [train.py:715] (5/8) Epoch 10, batch 950, loss[loss=0.1025, simple_loss=0.177, pruned_loss=0.01397, over 4820.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03335, over 965259.46 frames.], batch size: 26, lr: 2.19e-04
2022-05-06 16:53:35,732 INFO [train.py:715] (5/8) Epoch 10, batch 1000, loss[loss=0.1426, simple_loss=0.2178, pruned_loss=0.03376, over 4972.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03341, over 967058.85 frames.], batch size: 24, lr: 2.19e-04
2022-05-06 16:54:14,956 INFO [train.py:715] (5/8) Epoch 10, batch 1050, loss[loss=0.1592, simple_loss=0.2427, pruned_loss=0.03785, over 4747.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 967260.73 frames.], batch size: 16, lr: 2.19e-04
2022-05-06 16:54:55,329 INFO [train.py:715] (5/8) Epoch 10, batch 1100, loss[loss=0.1281, simple_loss=0.2093, pruned_loss=0.02344, over 4921.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03339, over 968079.40 frames.], batch size: 29, lr: 2.19e-04
2022-05-06 16:55:34,626 INFO [train.py:715] (5/8) Epoch 10, batch 1150, loss[loss=0.1318, simple_loss=0.2086, pruned_loss=0.02749, over 4808.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03293, over 968963.18 frames.], batch size: 24, lr: 2.19e-04
2022-05-06 16:56:13,828 INFO [train.py:715] (5/8) Epoch 10, batch 1200, loss[loss=0.1485, simple_loss=0.2218, pruned_loss=0.03764, over 4772.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03296, over 969252.61 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:56:53,601 INFO [train.py:715] (5/8) Epoch 10, batch 1250, loss[loss=0.1227, simple_loss=0.1948, pruned_loss=0.02535, over 4642.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03328, over 969533.64 frames.], batch size: 13, lr: 2.19e-04
2022-05-06 16:57:32,221 INFO [train.py:715] (5/8) Epoch 10, batch 1300, loss[loss=0.1456, simple_loss=0.2132, pruned_loss=0.03898, over 4829.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03342, over 970682.53 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 16:58:11,019 INFO [train.py:715] (5/8) Epoch 10, batch 1350, loss[loss=0.1241, simple_loss=0.1864, pruned_loss=0.0309, over 4808.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03352, over 970689.27 frames.], batch size: 12, lr: 2.19e-04
2022-05-06 16:58:49,193 INFO [train.py:715] (5/8) Epoch 10, batch 1400, loss[loss=0.1454, simple_loss=0.2154, pruned_loss=0.03772, over 4987.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2118, pruned_loss=0.03347, over 971215.77 frames.], batch size: 14, lr: 2.19e-04
2022-05-06 16:59:28,743 INFO [train.py:715] (5/8) Epoch 10, batch 1450, loss[loss=0.1426, simple_loss=0.2193, pruned_loss=0.033, over 4877.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2117, pruned_loss=0.03364, over 972791.80 frames.], batch size: 22, lr: 2.19e-04
2022-05-06 17:00:07,714 INFO [train.py:715] (5/8) Epoch 10, batch 1500, loss[loss=0.1409, simple_loss=0.2106, pruned_loss=0.03557, over 4898.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03414, over 972752.60 frames.], batch size: 22, lr: 2.19e-04
2022-05-06 17:00:46,473 INFO [train.py:715] (5/8) Epoch 10, batch 1550, loss[loss=0.1196, simple_loss=0.1896, pruned_loss=0.02481, over 4824.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03419, over 972316.93 frames.], batch size: 27, lr: 2.19e-04
2022-05-06 17:01:25,570 INFO [train.py:715] (5/8) Epoch 10, batch 1600, loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03206, over 4964.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03388, over 971635.61 frames.], batch size: 14, lr: 2.19e-04
2022-05-06 17:02:04,987 INFO [train.py:715] (5/8) Epoch 10, batch 1650, loss[loss=0.1286, simple_loss=0.2097, pruned_loss=0.02376, over 4691.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03484, over 971673.67 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 17:02:43,708 INFO [train.py:715] (5/8) Epoch 10, batch 1700, loss[loss=0.1787, simple_loss=0.2542, pruned_loss=0.05164, over 4896.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03505, over 972229.85 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 17:03:22,054 INFO [train.py:715] (5/8) Epoch 10, batch 1750, loss[loss=0.1332, simple_loss=0.2059, pruned_loss=0.03025, over 4906.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03485, over 972951.17 frames.], batch size: 19, lr: 2.19e-04
2022-05-06 17:04:02,176 INFO [train.py:715] (5/8) Epoch 10, batch 1800, loss[loss=0.1351, simple_loss=0.2119, pruned_loss=0.0291, over 4956.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03482, over 973079.09 frames.], batch size: 21, lr: 2.19e-04
2022-05-06 17:04:41,812 INFO [train.py:715] (5/8) Epoch 10, batch 1850, loss[loss=0.1293, simple_loss=0.2193, pruned_loss=0.01961, over 4796.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.034, over 973364.77 frames.], batch size: 21, lr: 2.19e-04
2022-05-06 17:05:20,549 INFO [train.py:715] (5/8) Epoch 10, batch 1900, loss[loss=0.1535, simple_loss=0.2201, pruned_loss=0.0435, over 4832.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03398, over 974031.28 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 17:05:59,510 INFO [train.py:715] (5/8) Epoch 10, batch 1950, loss[loss=0.163, simple_loss=0.2225, pruned_loss=0.05171, over 4855.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2127, pruned_loss=0.03428, over 972800.55 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:06:39,836 INFO [train.py:715] (5/8) Epoch 10, batch 2000, loss[loss=0.1388, simple_loss=0.2053, pruned_loss=0.03619, over 4985.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03415, over 973089.01 frames.], batch size: 35, lr: 2.18e-04
2022-05-06 17:07:19,134 INFO [train.py:715] (5/8) Epoch 10, batch 2050, loss[loss=0.1581, simple_loss=0.2304, pruned_loss=0.04296, over 4830.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03404, over 972941.65 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:07:57,714 INFO [train.py:715] (5/8) Epoch 10, batch 2100, loss[loss=0.1153, simple_loss=0.1869, pruned_loss=0.02181, over 4940.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03408, over 972451.78 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:08:37,348 INFO [train.py:715] (5/8) Epoch 10, batch 2150, loss[loss=0.1629, simple_loss=0.2364, pruned_loss=0.04471, over 4971.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03446, over 972221.65 frames.], batch size: 14, lr: 2.18e-04
2022-05-06 17:09:16,485 INFO [train.py:715] (5/8) Epoch 10, batch 2200, loss[loss=0.1555, simple_loss=0.2259, pruned_loss=0.04257, over 4771.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2136, pruned_loss=0.03459, over 971772.45 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:09:55,192 INFO [train.py:715] (5/8) Epoch 10, batch 2250, loss[loss=0.1222, simple_loss=0.1999, pruned_loss=0.02218, over 4952.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03461, over 972793.81 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:10:33,966 INFO [train.py:715] (5/8) Epoch 10, batch 2300, loss[loss=0.1514, simple_loss=0.2238, pruned_loss=0.03953, over 4904.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03439, over 971870.56 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:11:13,694 INFO [train.py:715] (5/8) Epoch 10, batch 2350, loss[loss=0.1361, simple_loss=0.2019, pruned_loss=0.03512, over 4824.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03339, over 972044.75 frames.], batch size: 14, lr: 2.18e-04
2022-05-06 17:11:52,498 INFO [train.py:715] (5/8) Epoch 10, batch 2400, loss[loss=0.1406, simple_loss=0.2143, pruned_loss=0.03345, over 4930.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2123, pruned_loss=0.03372, over 972695.20 frames.], batch size: 29, lr: 2.18e-04
2022-05-06 17:12:31,234 INFO [train.py:715] (5/8) Epoch 10, batch 2450, loss[loss=0.1425, simple_loss=0.2184, pruned_loss=0.03324, over 4823.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.0334, over 972678.04 frames.], batch size: 27, lr: 2.18e-04
2022-05-06 17:13:10,536 INFO [train.py:715] (5/8) Epoch 10, batch 2500, loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03573, over 4839.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03336, over 972967.63 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:13:49,920 INFO [train.py:715] (5/8) Epoch 10, batch 2550, loss[loss=0.1486, simple_loss=0.2254, pruned_loss=0.03591, over 4743.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03326, over 973480.30 frames.], batch size: 16, lr: 2.18e-04
2022-05-06 17:14:29,341 INFO [train.py:715] (5/8) Epoch 10, batch 2600, loss[loss=0.1204, simple_loss=0.1845, pruned_loss=0.02813, over 4831.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03391, over 973146.27 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:15:08,460 INFO [train.py:715] (5/8) Epoch 10, batch 2650, loss[loss=0.1645, simple_loss=0.2271, pruned_loss=0.05091, over 4747.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03445, over 973036.89 frames.], batch size: 16, lr: 2.18e-04
2022-05-06 17:15:47,656 INFO [train.py:715] (5/8) Epoch 10, batch 2700, loss[loss=0.1343, simple_loss=0.2095, pruned_loss=0.02958, over 4846.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03371, over 972902.43 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:16:26,374 INFO [train.py:715] (5/8) Epoch 10, batch 2750, loss[loss=0.1564, simple_loss=0.2111, pruned_loss=0.05082, over 4890.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03329, over 973082.43 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:17:05,076 INFO [train.py:715] (5/8) Epoch 10, batch 2800, loss[loss=0.1563, simple_loss=0.227, pruned_loss=0.0428, over 4790.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03336, over 973671.22 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:17:43,818 INFO [train.py:715] (5/8) Epoch 10, batch 2850, loss[loss=0.1594, simple_loss=0.2293, pruned_loss=0.04471, over 4875.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03314, over 973345.74 frames.], batch size: 16, lr: 2.18e-04
2022-05-06 17:18:23,065 INFO [train.py:715] (5/8) Epoch 10, batch 2900, loss[loss=0.1539, simple_loss=0.2303, pruned_loss=0.03876, over 4788.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03284, over 973240.10 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:19:02,251 INFO [train.py:715] (5/8) Epoch 10, batch 2950, loss[loss=0.1338, simple_loss=0.2038, pruned_loss=0.03188, over 4907.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03351, over 973544.28 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:19:40,635 INFO [train.py:715] (5/8) Epoch 10, batch 3000, loss[loss=0.1452, simple_loss=0.2214, pruned_loss=0.03453, over 4905.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.0339, over 972245.82 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:19:40,635 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 17:19:50,100 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01113, over 914524.00 frames.
2022-05-06 17:20:28,626 INFO [train.py:715] (5/8) Epoch 10, batch 3050, loss[loss=0.1248, simple_loss=0.1991, pruned_loss=0.0253, over 4860.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03349, over 972867.31 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:21:07,571 INFO [train.py:715] (5/8) Epoch 10, batch 3100, loss[loss=0.1429, simple_loss=0.2203, pruned_loss=0.0328, over 4766.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03354, over 972400.96 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:21:46,721 INFO [train.py:715] (5/8) Epoch 10, batch 3150, loss[loss=0.1279, simple_loss=0.1981, pruned_loss=0.02885, over 4845.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2134, pruned_loss=0.03319, over 973067.30 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:22:25,536 INFO [train.py:715] (5/8) Epoch 10, batch 3200, loss[loss=0.1298, simple_loss=0.202, pruned_loss=0.0288, over 4976.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2142, pruned_loss=0.03353, over 973279.04 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:23:03,969 INFO [train.py:715] (5/8) Epoch 10, batch 3250, loss[loss=0.1634, simple_loss=0.2444, pruned_loss=0.04114, over 4805.00 frames.], tot_loss[loss=0.141, simple_loss=0.2147, pruned_loss=0.03366, over 972390.03 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:23:44,493 INFO [train.py:715] (5/8) Epoch 10, batch 3300, loss[loss=0.1549, simple_loss=0.2217, pruned_loss=0.04404, over 4880.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2153, pruned_loss=0.03404, over 972313.31 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:24:24,218 INFO [train.py:715] (5/8) Epoch 10, batch 3350, loss[loss=0.1322, simple_loss=0.2112, pruned_loss=0.02665, over 4779.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2145, pruned_loss=0.0335, over 972995.15 frames.], batch size: 14, lr: 2.18e-04
2022-05-06 17:25:04,071 INFO [train.py:715] (5/8) Epoch 10, batch 3400, loss[loss=0.1552, simple_loss=0.2304, pruned_loss=0.04002, over 4856.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2143, pruned_loss=0.03349, over 972970.70 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:25:44,884 INFO [train.py:715] (5/8) Epoch 10, batch 3450, loss[loss=0.1448, simple_loss=0.2194, pruned_loss=0.03512, over 4786.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2142, pruned_loss=0.03311, over 972725.63 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:26:26,603 INFO [train.py:715] (5/8) Epoch 10, batch 3500, loss[loss=0.1354, simple_loss=0.2187, pruned_loss=0.02608, over 4804.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2127, pruned_loss=0.03258, over 972727.30 frames.], batch size: 25, lr: 2.18e-04
2022-05-06 17:27:07,262 INFO [train.py:715] (5/8) Epoch 10, batch 3550, loss[loss=0.1496, simple_loss=0.2261, pruned_loss=0.03652, over 4922.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2129, pruned_loss=0.03307, over 972571.08 frames.], batch size: 29, lr: 2.18e-04
2022-05-06 17:27:48,539 INFO [train.py:715] (5/8) Epoch 10, batch 3600, loss[loss=0.1332, simple_loss=0.201, pruned_loss=0.03271, over 4838.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03349, over 972670.57 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:28:29,171 INFO [train.py:715] (5/8) Epoch 10, batch 3650, loss[loss=0.1808, simple_loss=0.2403, pruned_loss=0.06061, over 4808.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.0337, over 972935.77 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:29:10,566 INFO [train.py:715] (5/8) Epoch 10, batch 3700, loss[loss=0.1315, simple_loss=0.2118, pruned_loss=0.0256, over 4807.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03346, over 972825.89 frames.], batch size: 25, lr: 2.18e-04
2022-05-06 17:29:51,155 INFO [train.py:715] (5/8) Epoch 10, batch 3750, loss[loss=0.112, simple_loss=0.1833, pruned_loss=0.02037, over 4801.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03377, over 973047.16 frames.], batch size: 12, lr: 2.18e-04
2022-05-06 17:30:32,380 INFO [train.py:715] (5/8) Epoch 10, batch 3800, loss[loss=0.1335, simple_loss=0.2064, pruned_loss=0.03031, over 4692.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03404, over 973502.38 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:31:13,747 INFO [train.py:715] (5/8) Epoch 10, batch 3850, loss[loss=0.1267, simple_loss=0.1965, pruned_loss=0.02844, over 4879.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03408, over 973406.35 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:31:54,700 INFO [train.py:715] (5/8) Epoch 10, batch 3900, loss[loss=0.134, simple_loss=0.2065, pruned_loss=0.03073, over 4881.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2131, pruned_loss=0.03436, over 973402.12 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:32:36,892 INFO [train.py:715] (5/8) Epoch 10, batch 3950, loss[loss=0.1521, simple_loss=0.2254, pruned_loss=0.03936, over 4972.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03454, over 973271.57 frames.], batch size: 39, lr: 2.18e-04
2022-05-06 17:33:16,172 INFO [train.py:715] (5/8) Epoch 10, batch 4000, loss[loss=0.1681, simple_loss=0.2179, pruned_loss=0.05921, over 4746.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03504, over 973394.93 frames.], batch size: 16, lr: 2.18e-04
2022-05-06 17:33:55,834 INFO [train.py:715] (5/8) Epoch 10, batch 4050, loss[loss=0.126, simple_loss=0.2024, pruned_loss=0.02475, over 4917.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03446, over 972439.36 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:34:34,557 INFO [train.py:715] (5/8) Epoch 10, batch 4100, loss[loss=0.1293, simple_loss=0.205, pruned_loss=0.02677, over 4839.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03434, over 971885.09 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:35:13,432 INFO [train.py:715] (5/8) Epoch 10, batch 4150, loss[loss=0.125, simple_loss=0.204, pruned_loss=0.02296, over 4750.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03432, over 972426.68 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:35:52,988 INFO [train.py:715] (5/8) Epoch 10, batch 4200, loss[loss=0.1583, simple_loss=0.2246, pruned_loss=0.04598, over 4938.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03443, over 972703.78 frames.], batch size: 29, lr: 2.18e-04
2022-05-06 17:36:31,673 INFO [train.py:715] (5/8) Epoch 10, batch 4250, loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04377, over 4974.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03425, over 972781.01 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:37:10,485 INFO [train.py:715] (5/8) Epoch 10, batch 4300, loss[loss=0.1568, simple_loss=0.238, pruned_loss=0.03783, over 4917.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03419, over 972557.71 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:37:49,692 INFO [train.py:715] (5/8) Epoch 10, batch 4350, loss[loss=0.1722, simple_loss=0.2328, pruned_loss=0.05578, over 4797.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03444, over 972265.38 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:38:28,647 INFO [train.py:715] (5/8) Epoch 10, batch 4400, loss[loss=0.181, simple_loss=0.2455, pruned_loss=0.05823, over 4844.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03464, over 971407.99 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:39:07,610 INFO [train.py:715] (5/8) Epoch 10, batch 4450, loss[loss=0.1307, simple_loss=0.2088, pruned_loss=0.02626, over 4814.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03456, over 972018.01 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:39:46,320 INFO [train.py:715] (5/8) Epoch 10, batch 4500, loss[loss=0.1341, simple_loss=0.21, pruned_loss=0.0291, over 4859.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.0345, over 970803.54 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:40:25,795 INFO [train.py:715] (5/8) Epoch 10, batch 4550, loss[loss=0.1246, simple_loss=0.2059, pruned_loss=0.02159, over 4974.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.03395, over 971325.09 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:41:04,677 INFO [train.py:715] (5/8) Epoch 10, batch 4600, loss[loss=0.1536, simple_loss=0.2268, pruned_loss=0.0402, over 4910.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.0336, over 971738.76 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:41:43,576 INFO [train.py:715] (5/8) Epoch 10, batch 4650, loss[loss=0.1227, simple_loss=0.2034, pruned_loss=0.02096, over 4988.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03408, over 971958.24 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:42:23,828 INFO [train.py:715] (5/8) Epoch 10, batch 4700, loss[loss=0.1421, simple_loss=0.2228, pruned_loss=0.03073, over 4828.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.03423, over 971891.60 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:43:03,974 INFO [train.py:715] (5/8) Epoch 10, batch 4750, loss[loss=0.1502, simple_loss=0.2135, pruned_loss=0.04349, over 4863.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2125, pruned_loss=0.03387, over 971917.27 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:43:43,160 INFO [train.py:715] (5/8) Epoch 10, batch 4800, loss[loss=0.121, simple_loss=0.1817, pruned_loss=0.03014, over 4837.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.0335, over 972560.32 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:44:22,998 INFO [train.py:715] (5/8) Epoch 10, batch 4850, loss[loss=0.1629, simple_loss=0.2279, pruned_loss=0.04897, over 4977.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03328, over 971815.88 frames.], batch size: 28, lr: 2.18e-04
2022-05-06 17:45:02,946 INFO [train.py:715] (5/8) Epoch 10, batch 4900, loss[loss=0.1223, simple_loss=0.2029, pruned_loss=0.02084, over 4884.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03372, over 971538.42 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:45:42,396 INFO [train.py:715] (5/8) Epoch 10, batch 4950, loss[loss=0.1532, simple_loss=0.2244, pruned_loss=0.04099, over 4803.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03361, over 971960.59 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:46:21,437 INFO [train.py:715] (5/8) Epoch 10, batch 5000, loss[loss=0.1493, simple_loss=0.2187, pruned_loss=0.03998, over 4791.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03389, over 972423.66 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:47:00,597 INFO [train.py:715] (5/8) Epoch 10, batch 5050, loss[loss=0.1574, simple_loss=0.2398, pruned_loss=0.03753, over 4837.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03388, over 972878.36 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:47:39,527 INFO [train.py:715] (5/8) Epoch 10, batch 5100, loss[loss=0.163, simple_loss=0.2376, pruned_loss=0.04416, over 4698.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03403, over 972278.81 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:48:18,816 INFO [train.py:715] (5/8) Epoch 10, batch 5150, loss[loss=0.1236, simple_loss=0.1921, pruned_loss=0.02755, over 4842.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.034, over 972804.62 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:48:58,650 INFO [train.py:715] (5/8) Epoch 10, batch 5200, loss[loss=0.1347, simple_loss=0.2095, pruned_loss=0.02999, over 4745.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.0341, over 972295.29 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 17:49:38,487 INFO [train.py:715] (5/8) Epoch 10, batch 5250, loss[loss=0.1515, simple_loss=0.2107, pruned_loss=0.04615, over 4828.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03397, over 972277.92 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 17:50:17,869 INFO [train.py:715] (5/8) Epoch 10, batch 5300, loss[loss=0.1532, simple_loss=0.2302, pruned_loss=0.03808, over 4902.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.0339, over 973100.96 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 17:50:57,207 INFO [train.py:715] (5/8) Epoch 10, batch 5350, loss[loss=0.1665, simple_loss=0.2287, pruned_loss=0.05219, over 4925.00 frames.], tot_loss[loss=0.1408, simple_loss=0.214, pruned_loss=0.03383, over 973126.00 frames.], batch size: 29, lr: 2.17e-04
2022-05-06 17:51:37,037 INFO [train.py:715] (5/8) Epoch 10, batch 5400, loss[loss=0.1297, simple_loss=0.1943, pruned_loss=0.03258, over 4875.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2155, pruned_loss=0.03392, over 972957.87 frames.], batch size: 32, lr: 2.17e-04
2022-05-06 17:52:16,955 INFO [train.py:715] (5/8) Epoch 10, batch 5450, loss[loss=0.1216, simple_loss=0.1913, pruned_loss=0.02594, over 4959.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2152, pruned_loss=0.0336, over 973024.58 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 17:52:56,361 INFO [train.py:715] (5/8) Epoch 10, batch 5500, loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03722, over 4809.00 frames.], tot_loss[loss=0.142, simple_loss=0.216, pruned_loss=0.03407, over 972638.41 frames.], batch size: 13, lr: 2.17e-04
2022-05-06 17:53:36,118 INFO [train.py:715] (5/8) Epoch 10, batch 5550, loss[loss=0.2029, simple_loss=0.2651, pruned_loss=0.07033, over 4957.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2162, pruned_loss=0.03481, over 973127.34 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 17:54:16,069 INFO [train.py:715] (5/8) Epoch 10, batch 5600, loss[loss=0.123, simple_loss=0.1996, pruned_loss=0.02323, over 4989.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03436, over 973433.47 frames.], batch size: 28, lr: 2.17e-04
2022-05-06 17:54:55,827 INFO [train.py:715] (5/8) Epoch 10, batch 5650, loss[loss=0.1379, simple_loss=0.215, pruned_loss=0.03042, over 4896.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03449, over 973530.83 frames.], batch size: 39, lr: 2.17e-04
2022-05-06 17:55:34,995 INFO [train.py:715] (5/8) Epoch 10, batch 5700, loss[loss=0.1467, simple_loss=0.2157, pruned_loss=0.03882, over 4916.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03393, over 973317.50 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 17:56:15,038 INFO [train.py:715] (5/8) Epoch 10, batch 5750, loss[loss=0.1229, simple_loss=0.1986, pruned_loss=0.02357, over 4816.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2137, pruned_loss=0.03371, over 972838.83 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 17:56:54,702 INFO [train.py:715] (5/8) Epoch 10, batch 5800, loss[loss=0.1383, simple_loss=0.2195, pruned_loss=0.0286, over 4938.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03358, over 973004.28 frames.], batch size: 23, lr: 2.17e-04
2022-05-06 17:57:34,224 INFO [train.py:715] (5/8) Epoch 10, batch 5850, loss[loss=0.1403, simple_loss=0.2111, pruned_loss=0.03471, over 4942.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03386, over 972711.52 frames.], batch size: 23, lr: 2.17e-04
2022-05-06 17:58:14,043 INFO [train.py:715] (5/8) Epoch 10, batch 5900, loss[loss=0.1392, simple_loss=0.2085, pruned_loss=0.03494, over 4956.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03422, over 972335.25 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 17:58:53,782 INFO [train.py:715] (5/8) Epoch 10, batch 5950, loss[loss=0.1503, simple_loss=0.2306, pruned_loss=0.03503, over 4982.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03381, over 971164.02 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 17:59:33,444 INFO [train.py:715] (5/8) Epoch 10, batch 6000, loss[loss=0.144, simple_loss=0.2004, pruned_loss=0.04378, over 4956.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03404, over 971591.70 frames.], batch size: 31, lr: 2.17e-04
2022-05-06 17:59:33,445 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 17:59:42,752 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1067, simple_loss=0.1909, pruned_loss=0.01126, over 914524.00 frames.
2022-05-06 18:00:22,325 INFO [train.py:715] (5/8) Epoch 10, batch 6050, loss[loss=0.1413, simple_loss=0.2109, pruned_loss=0.03584, over 4858.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.03378, over 971215.81 frames.], batch size: 32, lr: 2.17e-04
2022-05-06 18:01:00,744 INFO [train.py:715] (5/8) Epoch 10, batch 6100, loss[loss=0.1602, simple_loss=0.234, pruned_loss=0.0432, over 4909.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03387, over 972051.73 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:01:40,207 INFO [train.py:715] (5/8) Epoch 10, batch 6150, loss[loss=0.138, simple_loss=0.2041, pruned_loss=0.03597, over 4832.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03331, over 972178.46 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:02:20,068 INFO [train.py:715] (5/8) Epoch 10, batch 6200, loss[loss=0.1419, simple_loss=0.2063, pruned_loss=0.03879, over 4777.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 972274.35 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:02:59,936 INFO [train.py:715] (5/8) Epoch 10, batch 6250, loss[loss=0.1335, simple_loss=0.2041, pruned_loss=0.03146, over 4960.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03274, over 972882.29 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 18:03:39,467 INFO [train.py:715] (5/8) Epoch 10, batch 6300, loss[loss=0.1368, simple_loss=0.2035, pruned_loss=0.03509, over 4949.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03294, over 973491.88 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 18:04:19,281 INFO [train.py:715] (5/8) Epoch 10, batch 6350, loss[loss=0.1483, simple_loss=0.213, pruned_loss=0.04183, over 4928.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03258, over 972970.05 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:04:58,324 INFO [train.py:715] (5/8) Epoch 10, batch 6400, loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03082, over 4868.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03261, over 972939.80 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:05:36,733 INFO [train.py:715] (5/8) Epoch 10, batch 6450, loss[loss=0.1639, simple_loss=0.229, pruned_loss=0.04941, over 4732.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03299, over 973335.20 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:06:15,659 INFO [train.py:715] (5/8) Epoch 10, batch 6500, loss[loss=0.147, simple_loss=0.2162, pruned_loss=0.03884, over 4743.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03317, over 972539.02 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:06:54,773 INFO [train.py:715] (5/8) Epoch 10, batch 6550, loss[loss=0.1494, simple_loss=0.2277, pruned_loss=0.03558, over 4858.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03274, over 972767.62 frames.], batch size: 20, lr: 2.17e-04
2022-05-06 18:07:33,916 INFO [train.py:715] (5/8) Epoch 10, batch 6600, loss[loss=0.149, simple_loss=0.2182, pruned_loss=0.03995, over 4892.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03274, over 973019.24 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:08:12,470 INFO [train.py:715] (5/8) Epoch 10, batch 6650, loss[loss=0.1609, simple_loss=0.2381, pruned_loss=0.04186, over 4983.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03289, over 973119.66 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:08:52,598 INFO [train.py:715] (5/8) Epoch 10, batch 6700, loss[loss=0.1309, simple_loss=0.1995, pruned_loss=0.0312, over 4927.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03396, over 971916.95 frames.], batch size: 23, lr: 2.17e-04
2022-05-06 18:09:31,853 INFO [train.py:715] (5/8) Epoch 10, batch 6750, loss[loss=0.1191, simple_loss=0.1968, pruned_loss=0.0207, over 4957.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03407, over 972195.82 frames.], batch size: 24, lr: 2.17e-04
2022-05-06 18:10:10,541 INFO [train.py:715] (5/8) Epoch 10, batch 6800, loss[loss=0.138, simple_loss=0.2062, pruned_loss=0.03494, over 4949.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03392, over 972321.08 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 18:10:50,411 INFO [train.py:715] (5/8) Epoch 10, batch 6850, loss[loss=0.1498, simple_loss=0.2284, pruned_loss=0.03558, over 4955.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03365, over 972079.30 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:11:29,655 INFO [train.py:715] (5/8) Epoch 10, batch 6900, loss[loss=0.1393, simple_loss=0.2053, pruned_loss=0.03667, over 4986.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03345, over 972735.52 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:12:08,733 INFO [train.py:715] (5/8) Epoch 10, batch 6950, loss[loss=0.1351, simple_loss=0.2063, pruned_loss=0.03194, over 4801.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03338, over 971646.63 frames.], batch size: 24, lr: 2.17e-04
2022-05-06 18:12:48,641 INFO [train.py:715] (5/8) Epoch 10, batch 7000, loss[loss=0.1731, simple_loss=0.2339, pruned_loss=0.05614, over 4900.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03323, over 971504.73 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:13:28,548 INFO [train.py:715] (5/8) Epoch 10, batch 7050, loss[loss=0.1306, simple_loss=0.2091, pruned_loss=0.02608, over 4695.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03274, over 972162.35 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:14:07,758 INFO [train.py:715] (5/8) Epoch 10, batch 7100, loss[loss=0.1502, simple_loss=0.228, pruned_loss=0.03616, over 4830.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03337, over 972107.84 frames.], batch size: 13, lr: 2.17e-04
2022-05-06 18:14:46,899 INFO [train.py:715] (5/8) Epoch 10, batch 7150, loss[loss=0.1419, simple_loss=0.2108, pruned_loss=0.03653, over 4805.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03326, over 970952.31 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:15:26,294 INFO [train.py:715] (5/8) Epoch 10, batch 7200, loss[loss=0.1278, simple_loss=0.2032, pruned_loss=0.02614, over 4871.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03329, over 971978.90 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:16:05,420 INFO [train.py:715] (5/8) Epoch 10, batch 7250, loss[loss=0.1165, simple_loss=0.1916, pruned_loss=0.02065, over 4950.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03302, over 972067.31 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:16:44,408 INFO [train.py:715] (5/8) Epoch 10, batch 7300, loss[loss=0.1481, simple_loss=0.2164, pruned_loss=0.03986, over 4818.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03329, over 972262.68 frames.], batch size: 27, lr: 2.17e-04
2022-05-06 18:17:23,331 INFO [train.py:715] (5/8) Epoch 10, batch 7350, loss[loss=0.1524, simple_loss=0.2266, pruned_loss=0.03906, over 4981.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03406, over 973459.09 frames.], batch size: 31, lr: 2.17e-04
2022-05-06 18:18:02,742 INFO [train.py:715] (5/8) Epoch 10, batch 7400, loss[loss=0.1297, simple_loss=0.2111, pruned_loss=0.02416, over 4747.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03369, over 973644.61 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:18:41,884 INFO [train.py:715] (5/8) Epoch 10, batch 7450, loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03307, over 4918.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03385, over 973706.86 frames.], batch size: 17, lr: 2.17e-04
2022-05-06 18:19:20,014 INFO [train.py:715] (5/8) Epoch 10, batch 7500, loss[loss=0.1689, simple_loss=0.2446, pruned_loss=0.04657, over 4823.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03424, over 973229.67 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:19:59,644 INFO [train.py:715] (5/8) Epoch 10, batch 7550, loss[loss=0.116, simple_loss=0.1794, pruned_loss=0.02634, over 4920.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03418, over 973831.87 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:20:38,458 INFO [train.py:715] (5/8) Epoch 10, batch 7600, loss[loss=0.1497, simple_loss=0.233, pruned_loss=0.03323, over 4892.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03424, over 974083.39 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:21:17,036 INFO [train.py:715] (5/8) Epoch 10, batch 7650, loss[loss=0.1516, simple_loss=0.2335, pruned_loss=0.0349, over 4884.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03386, over 973171.63 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:21:56,435 INFO [train.py:715] (5/8) Epoch 10, batch 7700, loss[loss=0.132, simple_loss=0.2173, pruned_loss=0.02334, over 4763.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03387, over 973159.50 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:22:35,791 INFO [train.py:715] (5/8) Epoch 10, batch 7750, loss[loss=0.1369, simple_loss=0.2081, pruned_loss=0.03285, over 4948.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03381, over 972823.05 frames.], batch size: 29, lr: 2.17e-04
2022-05-06 18:23:15,171 INFO [train.py:715] (5/8) Epoch 10, batch 7800, loss[loss=0.1303, simple_loss=0.202, pruned_loss=0.02926, over 4792.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03395, over 972177.55 frames.], batch size: 17, lr: 2.17e-04
2022-05-06 18:23:53,544 INFO [train.py:715] (5/8) Epoch 10, batch 7850, loss[loss=0.1235, simple_loss=0.2069, pruned_loss=0.02001, over 4753.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03351, over 972230.01 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:24:33,023 INFO [train.py:715] (5/8) Epoch 10, batch 7900, loss[loss=0.1491, simple_loss=0.2156, pruned_loss=0.04134, over 4853.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2138, pruned_loss=0.03372, over 972543.41 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:25:12,543 INFO [train.py:715] (5/8) Epoch 10, batch 7950, loss[loss=0.1448, simple_loss=0.2149, pruned_loss=0.03734, over 4970.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03308, over 973475.96 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:25:51,361 INFO [train.py:715] (5/8) Epoch 10, batch 8000, loss[loss=0.1269, simple_loss=0.2023, pruned_loss=0.02571, over 4965.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03324, over 972733.95 frames.], batch size: 28, lr: 2.17e-04
2022-05-06 18:26:30,785 INFO [train.py:715] (5/8) Epoch 10, batch 8050, loss[loss=0.1919, simple_loss=0.2495, pruned_loss=0.06715, over 4846.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03343, over 971801.29 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:27:10,427 INFO [train.py:715] (5/8) Epoch 10, batch 8100, loss[loss=0.1539, simple_loss=0.2254, pruned_loss=0.04117, over 4982.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03316, over 972341.55 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 18:27:49,300 INFO [train.py:715] (5/8) Epoch 10, batch 8150, loss[loss=0.1529, simple_loss=0.2274, pruned_loss=0.03918, over 4852.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03341, over 973234.99 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:28:27,913 INFO [train.py:715] (5/8) Epoch 10, batch 8200, loss[loss=0.1519, simple_loss=0.2141, pruned_loss=0.04482, over 4698.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03364, over 971861.68 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:29:07,588 INFO [train.py:715] (5/8) Epoch 10, batch 8250, loss[loss=0.1593, simple_loss=0.2271, pruned_loss=0.04573, over 4899.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03378, over 972245.46 frames.], batch size: 17, lr: 2.17e-04
2022-05-06 18:29:46,988 INFO [train.py:715] (5/8) Epoch 10, batch 8300, loss[loss=0.1255, simple_loss=0.2046, pruned_loss=0.02325, over 4815.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03358, over 971740.02 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 18:30:25,733 INFO [train.py:715] (5/8) Epoch 10, batch 8350, loss[loss=0.1281, simple_loss=0.2023, pruned_loss=0.02695, over 4990.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03357, over 972144.57 frames.], batch size: 27, lr: 2.17e-04
2022-05-06 18:31:05,469 INFO [train.py:715] (5/8) Epoch 10, batch 8400, loss[loss=0.1521, simple_loss=0.231, pruned_loss=0.03659, over 4855.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03396, over 971988.80 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:31:44,982 INFO [train.py:715] (5/8) Epoch 10, batch 8450, loss[loss=0.1265, simple_loss=0.2047, pruned_loss=0.02414, over 4923.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03377, over 972054.38 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:32:23,258 INFO [train.py:715] (5/8) Epoch 10, batch 8500, loss[loss=0.1179, simple_loss=0.1934, pruned_loss=0.02123, over 4978.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03393, over 972095.25 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:33:02,052 INFO [train.py:715] (5/8) Epoch 10, batch 8550, loss[loss=0.1518, simple_loss=0.2264, pruned_loss=0.03863, over 4983.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.0344, over 972372.89 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:33:41,303 INFO [train.py:715] (5/8) Epoch 10, batch 8600, loss[loss=0.1351, simple_loss=0.2181, pruned_loss=0.02601, over 4795.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03409, over 971646.33 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:34:19,984 INFO [train.py:715] (5/8) Epoch 10, batch 8650, loss[loss=0.1411, simple_loss=0.2172, pruned_loss=0.0325, over 4930.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03401, over 971655.02 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:34:58,632 INFO [train.py:715] (5/8) Epoch 10, batch 8700, loss[loss=0.1365, simple_loss=0.2168, pruned_loss=0.02813, over 4913.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03373, over 972309.80 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:35:37,458 INFO [train.py:715] (5/8) Epoch 10, batch 8750, loss[loss=0.1653, simple_loss=0.245, pruned_loss=0.04283, over 4776.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03382, over 972098.52 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:36:15,826 INFO [train.py:715] (5/8) Epoch 10, batch 8800, loss[loss=0.1419, simple_loss=0.2175, pruned_loss=0.03316, over 4821.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03339, over 972346.91 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:36:54,706 INFO [train.py:715] (5/8) Epoch 10, batch 8850, loss[loss=0.1584, simple_loss=0.2386, pruned_loss=0.03911, over 4870.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.0336, over 971784.85 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:37:34,275 INFO [train.py:715] (5/8) Epoch 10, batch 8900, loss[loss=0.1496, simple_loss=0.2231, pruned_loss=0.03806, over 4922.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03332, over 972492.74 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:38:13,788 INFO [train.py:715] (5/8) Epoch 10, batch 8950, loss[loss=0.1539, simple_loss=0.2269, pruned_loss=0.04047, over 4986.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03369, over 972127.47 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:38:53,303 INFO [train.py:715] (5/8) Epoch 10, batch 9000, loss[loss=0.135, simple_loss=0.2101, pruned_loss=0.02999, over 4982.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03382, over 971881.12 frames.], batch size: 25, lr: 2.16e-04
2022-05-06 18:38:53,304 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 18:39:02,857 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1907, pruned_loss=0.01106, over 914524.00 frames.
2022-05-06 18:39:42,084 INFO [train.py:715] (5/8) Epoch 10, batch 9050, loss[loss=0.1445, simple_loss=0.2096, pruned_loss=0.03972, over 4873.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03329, over 972125.50 frames.], batch size: 20, lr: 2.16e-04
2022-05-06 18:40:21,167 INFO [train.py:715] (5/8) Epoch 10, batch 9100, loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02967, over 4980.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03344, over 971285.39 frames.], batch size: 14, lr: 2.16e-04
2022-05-06 18:41:01,495 INFO [train.py:715] (5/8) Epoch 10, batch 9150, loss[loss=0.1293, simple_loss=0.1963, pruned_loss=0.03116, over 4880.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03313, over 972146.22 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 18:41:41,014 INFO [train.py:715] (5/8) Epoch 10, batch 9200, loss[loss=0.148, simple_loss=0.2137, pruned_loss=0.04119, over 4910.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03367, over 972409.37 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:42:20,460 INFO [train.py:715] (5/8) Epoch 10, batch 9250, loss[loss=0.1832, simple_loss=0.2441, pruned_loss=0.0611, over 4772.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03445, over 972924.47 frames.], batch size: 14, lr: 2.16e-04
2022-05-06 18:43:00,282 INFO [train.py:715] (5/8) Epoch 10, batch 9300, loss[loss=0.125, simple_loss=0.1957, pruned_loss=0.02712, over 4865.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03438, over 972933.33 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 18:43:39,883 INFO [train.py:715] (5/8) Epoch 10, batch 9350, loss[loss=0.1213, simple_loss=0.1954, pruned_loss=0.02356, over 4887.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03398, over 971977.67 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:44:19,393 INFO [train.py:715] (5/8) Epoch 10, batch 9400, loss[loss=0.1354, simple_loss=0.2246, pruned_loss=0.02314, over 4906.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03437, over 972695.17 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 18:44:58,980 INFO [train.py:715] (5/8) Epoch 10, batch 9450, loss[loss=0.1119, simple_loss=0.1833, pruned_loss=0.02024, over 4862.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03427, over 971766.54 frames.], batch size: 12, lr: 2.16e-04
2022-05-06 18:45:38,376 INFO [train.py:715] (5/8) Epoch 10, batch 9500, loss[loss=0.1138, simple_loss=0.1907, pruned_loss=0.01846, over 4924.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03405, over 972065.04 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:46:17,352 INFO [train.py:715] (5/8) Epoch 10, batch 9550, loss[loss=0.1272, simple_loss=0.2025, pruned_loss=0.02596, over 4765.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.0341, over 972517.95 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:46:55,764 INFO [train.py:715] (5/8) Epoch 10, batch 9600, loss[loss=0.1358, simple_loss=0.2161, pruned_loss=0.0277, over 4894.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03451, over 973012.48 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 18:47:34,905 INFO [train.py:715] (5/8) Epoch 10, batch 9650, loss[loss=0.147, simple_loss=0.2222, pruned_loss=0.03586, over 4872.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03431, over 973033.83 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:48:14,557 INFO [train.py:715] (5/8) Epoch 10, batch 9700, loss[loss=0.1478, simple_loss=0.2301, pruned_loss=0.0328, over 4854.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03376, over 972263.77 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 18:48:52,975 INFO [train.py:715] (5/8) Epoch 10, batch 9750, loss[loss=0.1434, simple_loss=0.2285, pruned_loss=0.02918, over 4752.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03381, over 972216.19 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:49:32,212 INFO [train.py:715] (5/8) Epoch 10, batch 9800, loss[loss=0.1211, simple_loss=0.1977, pruned_loss=0.02226, over 4783.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03388, over 972491.70 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:50:11,747 INFO [train.py:715] (5/8) Epoch 10, batch 9850, loss[loss=0.1353, simple_loss=0.2099, pruned_loss=0.03029, over 4946.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03405, over 972457.70 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:50:51,054 INFO [train.py:715] (5/8) Epoch 10, batch 9900, loss[loss=0.1304, simple_loss=0.2007, pruned_loss=0.03003, over 4973.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2133, pruned_loss=0.03425, over 970926.68 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:51:30,063 INFO [train.py:715] (5/8) Epoch 10, batch 9950, loss[loss=0.1212, simple_loss=0.1982, pruned_loss=0.02213, over 4825.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03447, over 971240.80 frames.], batch size: 26, lr: 2.16e-04
2022-05-06 18:52:10,258 INFO [train.py:715] (5/8) Epoch 10, batch 10000, loss[loss=0.1327, simple_loss=0.1982, pruned_loss=0.03354, over 4900.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03416, over 971811.12 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:52:49,842 INFO [train.py:715] (5/8) Epoch 10, batch 10050, loss[loss=0.1442, simple_loss=0.2188, pruned_loss=0.03482, over 4818.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03391, over 971679.25 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 18:53:27,869 INFO [train.py:715] (5/8) Epoch 10, batch 10100, loss[loss=0.1392, simple_loss=0.195, pruned_loss=0.04167, over 4833.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03445, over 972121.80 frames.], batch size: 26, lr: 2.16e-04
2022-05-06 18:54:06,606 INFO [train.py:715] (5/8) Epoch 10, batch 10150, loss[loss=0.1289, simple_loss=0.2018, pruned_loss=0.02804, over 4977.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03412, over 972840.20 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:54:46,536 INFO [train.py:715] (5/8) Epoch 10, batch 10200, loss[loss=0.1352, simple_loss=0.2146, pruned_loss=0.02792, over 4972.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03372, over 972799.54 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:55:25,656 INFO [train.py:715] (5/8) Epoch 10, batch 10250, loss[loss=0.1391, simple_loss=0.2145, pruned_loss=0.03191, over 4838.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03337, over 972738.42 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 18:56:04,509 INFO [train.py:715] (5/8) Epoch 10, batch 10300, loss[loss=0.1678, simple_loss=0.2365, pruned_loss=0.04952, over 4934.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.0337, over 972092.72 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:56:44,439 INFO [train.py:715] (5/8) Epoch 10, batch 10350, loss[loss=0.1406, simple_loss=0.2108, pruned_loss=0.03522, over 4934.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03361, over 972095.02 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:57:24,437 INFO [train.py:715] (5/8) Epoch 10, batch 10400, loss[loss=0.1593, simple_loss=0.2268, pruned_loss=0.04586, over 4904.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03371, over 972561.88 frames.], batch size: 22, lr: 2.16e-04
2022-05-06 18:58:02,841 INFO [train.py:715] (5/8) Epoch 10, batch 10450, loss[loss=0.1244, simple_loss=0.2004, pruned_loss=0.02421, over 4916.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03336, over 971296.44 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:58:41,113 INFO [train.py:715] (5/8) Epoch 10, batch 10500, loss[loss=0.1531, simple_loss=0.2298, pruned_loss=0.03824, over 4956.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.0332, over 971680.28 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:59:20,259 INFO [train.py:715] (5/8) Epoch 10, batch 10550, loss[loss=0.1626, simple_loss=0.234, pruned_loss=0.04561, over 4947.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03307, over 972350.01 frames.], batch size: 21, lr: 2.16e-04
2022-05-06 18:59:59,203 INFO [train.py:715] (5/8) Epoch 10, batch 10600, loss[loss=0.1351, simple_loss=0.2148, pruned_loss=0.02773, over 4889.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03335, over 973419.23 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 19:00:37,418 INFO [train.py:715] (5/8) Epoch 10, batch 10650, loss[loss=0.1523, simple_loss=0.2267, pruned_loss=0.03894, over 4714.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03293, over 972751.54 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 19:01:16,839 INFO [train.py:715] (5/8) Epoch 10, batch 10700, loss[loss=0.1707, simple_loss=0.2328, pruned_loss=0.05428, over 4963.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03378, over 972637.32 frames.], batch size: 35, lr: 2.16e-04
2022-05-06 19:01:56,164 INFO [train.py:715] (5/8) Epoch 10, batch 10750, loss[loss=0.1196, simple_loss=0.1918, pruned_loss=0.0237, over 4767.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03332, over 973023.99 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:02:34,990 INFO [train.py:715] (5/8) Epoch 10, batch 10800, loss[loss=0.1158, simple_loss=0.1901, pruned_loss=0.02081, over 4961.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2125, pruned_loss=0.03381, over 972256.21 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 19:03:13,438 INFO [train.py:715] (5/8) Epoch 10, batch 10850, loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02983, over 4781.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03404, over 971723.99 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 19:03:52,880 INFO [train.py:715] (5/8) Epoch 10, batch 10900, loss[loss=0.1411, simple_loss=0.2061, pruned_loss=0.03803, over 4932.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03401, over 971772.92 frames.], batch size: 21, lr: 2.16e-04
2022-05-06 19:04:31,790 INFO [train.py:715] (5/8) Epoch 10, batch 10950, loss[loss=0.1288, simple_loss=0.2026, pruned_loss=0.02751, over 4872.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03364, over 971958.83 frames.], batch size: 32, lr: 2.16e-04
2022-05-06 19:05:10,344 INFO [train.py:715] (5/8) Epoch 10, batch 11000, loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03532, over 4838.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03352, over 971464.91 frames.], batch size: 20, lr: 2.16e-04
2022-05-06 19:05:49,497 INFO [train.py:715] (5/8) Epoch 10, batch 11050, loss[loss=0.1261, simple_loss=0.2026, pruned_loss=0.02479, over 4947.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03297, over 971656.71 frames.], batch size: 29, lr: 2.16e-04
2022-05-06 19:06:29,280 INFO [train.py:715] (5/8) Epoch 10, batch 11100, loss[loss=0.1108, simple_loss=0.1909, pruned_loss=0.01538, over 4951.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03238, over 972548.32 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 19:07:07,073 INFO [train.py:715] (5/8) Epoch 10, batch 11150, loss[loss=0.1451, simple_loss=0.2182, pruned_loss=0.03594, over 4760.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03323, over 972171.71 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 19:07:46,334 INFO [train.py:715] (5/8) Epoch 10, batch 11200, loss[loss=0.124, simple_loss=0.203, pruned_loss=0.02256, over 4932.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03313, over 971440.04 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 19:08:25,400 INFO [train.py:715] (5/8) Epoch 10, batch 11250, loss[loss=0.1548, simple_loss=0.2288, pruned_loss=0.04038, over 4831.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03345, over 971445.32 frames.], batch size: 25, lr: 2.16e-04
2022-05-06 19:09:03,753 INFO [train.py:715] (5/8) Epoch 10, batch 11300, loss[loss=0.116, simple_loss=0.1913, pruned_loss=0.02035, over 4926.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03306, over 971936.62 frames.], batch size: 29, lr: 2.16e-04
2022-05-06 19:09:42,489 INFO [train.py:715] (5/8) Epoch 10, batch 11350, loss[loss=0.1331, simple_loss=0.2054, pruned_loss=0.03036, over 4931.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03285, over 972548.09 frames.], batch size: 29, lr: 2.16e-04
2022-05-06 19:10:21,470 INFO [train.py:715] (5/8) Epoch 10, batch 11400, loss[loss=0.1452, simple_loss=0.2218, pruned_loss=0.03431, over 4780.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03314, over 972250.13 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 19:11:00,936 INFO [train.py:715] (5/8) Epoch 10, batch 11450, loss[loss=0.1842, simple_loss=0.2418, pruned_loss=0.06334, over 4852.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03351, over 972876.70 frames.], batch size: 32, lr: 2.16e-04
2022-05-06 19:11:38,820 INFO [train.py:715] (5/8) Epoch 10, batch 11500, loss[loss=0.1579, simple_loss=0.2331, pruned_loss=0.0413, over 4746.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03346, over 971844.19 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:12:17,873 INFO [train.py:715] (5/8) Epoch 10, batch 11550, loss[loss=0.1516, simple_loss=0.2312, pruned_loss=0.036, over 4880.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03335, over 971917.95 frames.], batch size: 22, lr: 2.16e-04
2022-05-06 19:12:57,423 INFO [train.py:715] (5/8) Epoch 10, batch 11600, loss[loss=0.1404, simple_loss=0.2086, pruned_loss=0.03604, over 4949.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.0332, over 972011.80 frames.], batch size: 35, lr: 2.16e-04
2022-05-06 19:13:35,824 INFO [train.py:715] (5/8) Epoch 10, batch 11650, loss[loss=0.1443, simple_loss=0.2173, pruned_loss=0.03567, over 4785.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2129, pruned_loss=0.0329, over 972171.42 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 19:14:14,880 INFO [train.py:715] (5/8) Epoch 10, batch 11700, loss[loss=0.1313, simple_loss=0.2097, pruned_loss=0.02646, over 4917.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2129, pruned_loss=0.03285, over 972117.72 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 19:14:53,448 INFO [train.py:715] (5/8) Epoch 10, batch 11750, loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03742, over 4958.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03334, over 971673.85 frames.], batch size: 31, lr: 2.15e-04
2022-05-06 19:15:32,370 INFO [train.py:715] (5/8) Epoch 10, batch 11800, loss[loss=0.1458, simple_loss=0.2159, pruned_loss=0.03785, over 4929.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.0336, over 972409.87 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:16:10,394 INFO [train.py:715] (5/8) Epoch 10, batch 11850, loss[loss=0.1354, simple_loss=0.208, pruned_loss=0.03143, over 4811.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03393, over 972551.05 frames.], batch size: 13, lr: 2.15e-04
2022-05-06 19:16:49,162 INFO [train.py:715] (5/8) Epoch 10, batch 11900, loss[loss=0.126, simple_loss=0.1983, pruned_loss=0.02686, over 4839.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03369, over 972621.96 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:17:30,482 INFO [train.py:715] (5/8) Epoch 10, batch 11950, loss[loss=0.1102, simple_loss=0.1752, pruned_loss=0.02257, over 4983.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03392, over 972466.30 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:18:09,365 INFO [train.py:715] (5/8) Epoch 10, batch 12000, loss[loss=0.1505, simple_loss=0.217, pruned_loss=0.04205, over 4850.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03381, over 973257.78 frames.], batch size: 32, lr: 2.15e-04
2022-05-06 19:18:09,366 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 19:18:19,016 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01105, over 914524.00 frames.
2022-05-06 19:18:57,892 INFO [train.py:715] (5/8) Epoch 10, batch 12050, loss[loss=0.1742, simple_loss=0.2344, pruned_loss=0.05703, over 4973.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03415, over 973532.46 frames.], batch size: 31, lr: 2.15e-04
2022-05-06 19:19:37,113 INFO [train.py:715] (5/8) Epoch 10, batch 12100, loss[loss=0.1196, simple_loss=0.1913, pruned_loss=0.02391, over 4928.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03366, over 973000.32 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:20:16,374 INFO [train.py:715] (5/8) Epoch 10, batch 12150, loss[loss=0.132, simple_loss=0.209, pruned_loss=0.02754, over 4793.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03328, over 973363.92 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:20:55,541 INFO [train.py:715] (5/8) Epoch 10, batch 12200, loss[loss=0.1611, simple_loss=0.2335, pruned_loss=0.04431, over 4894.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03287, over 972789.46 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:21:34,084 INFO [train.py:715] (5/8) Epoch 10, batch 12250, loss[loss=0.1614, simple_loss=0.2312, pruned_loss=0.04585, over 4829.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03282, over 972473.95 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:22:13,027 INFO [train.py:715] (5/8) Epoch 10, batch 12300, loss[loss=0.143, simple_loss=0.2226, pruned_loss=0.03168, over 4991.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.0336, over 971956.71 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:22:51,958 INFO [train.py:715] (5/8) Epoch 10, batch 12350, loss[loss=0.1468, simple_loss=0.2151, pruned_loss=0.03928, over 4882.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03383, over 972202.00 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:23:30,789 INFO [train.py:715] (5/8) Epoch 10, batch 12400, loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02928, over 4875.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.0337, over 971500.11 frames.], batch size: 20, lr: 2.15e-04
2022-05-06 19:24:09,216 INFO [train.py:715] (5/8) Epoch 10, batch 12450, loss[loss=0.1011, simple_loss=0.1654, pruned_loss=0.01842, over 4740.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03324, over 971845.31 frames.], batch size: 12, lr: 2.15e-04
2022-05-06 19:24:48,248 INFO [train.py:715] (5/8) Epoch 10, batch 12500, loss[loss=0.1385, simple_loss=0.2139, pruned_loss=0.03158, over 4759.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03339, over 971955.85 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:25:27,026 INFO [train.py:715] (5/8) Epoch 10, batch 12550, loss[loss=0.1339, simple_loss=0.2042, pruned_loss=0.03184, over 4877.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03382, over 971837.85 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:26:05,180 INFO [train.py:715] (5/8) Epoch 10, batch 12600, loss[loss=0.1223, simple_loss=0.204, pruned_loss=0.02029, over 4913.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2124, pruned_loss=0.03387, over 971886.24 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:26:43,470 INFO [train.py:715] (5/8) Epoch 10, batch 12650, loss[loss=0.1322, simple_loss=0.198, pruned_loss=0.03322, over 4981.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03353, over 971569.84 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:27:22,407 INFO [train.py:715] (5/8) Epoch 10, batch 12700, loss[loss=0.1354, simple_loss=0.208, pruned_loss=0.03138, over 4802.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03389, over 971672.27 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:28:00,754 INFO [train.py:715] (5/8) Epoch 10, batch 12750, loss[loss=0.1076, simple_loss=0.1782, pruned_loss=0.01847, over 4977.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03347, over 972558.15 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:28:39,214 INFO [train.py:715] (5/8) Epoch 10, batch 12800, loss[loss=0.1529, simple_loss=0.2278, pruned_loss=0.039, over 4792.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03313, over 972689.40 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:29:18,644 INFO [train.py:715] (5/8) Epoch 10, batch 12850, loss[loss=0.1578, simple_loss=0.2225, pruned_loss=0.04657, over 4783.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03347, over 973147.95 frames.], batch size: 17, lr: 2.15e-04
2022-05-06 19:29:57,808 INFO [train.py:715] (5/8) Epoch 10, batch 12900, loss[loss=0.1221, simple_loss=0.1992, pruned_loss=0.02252, over 4811.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03349, over 972964.81 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:30:36,228 INFO [train.py:715] (5/8) Epoch 10, batch 12950, loss[loss=0.1416, simple_loss=0.2143, pruned_loss=0.03452, over 4959.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03299, over 972215.95 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:31:14,797 INFO [train.py:715] (5/8) Epoch 10, batch 13000, loss[loss=0.1197, simple_loss=0.1961, pruned_loss=0.0217, over 4755.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03273, over 971745.67 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:31:54,373 INFO [train.py:715] (5/8) Epoch 10, batch 13050, loss[loss=0.1405, simple_loss=0.2138, pruned_loss=0.03361, over 4816.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03238, over 972513.06 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:32:32,859 INFO [train.py:715] (5/8) Epoch 10, batch 13100, loss[loss=0.1549, simple_loss=0.2241, pruned_loss=0.0429, over 4753.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.0326, over 972333.33 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:33:11,983 INFO [train.py:715] (5/8) Epoch 10, batch 13150, loss[loss=0.1578, simple_loss=0.2214, pruned_loss=0.04709, over 4848.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03269, over 973101.96 frames.], batch size: 30, lr: 2.15e-04
2022-05-06 19:33:51,012 INFO [train.py:715] (5/8) Epoch 10, batch 13200, loss[loss=0.1328, simple_loss=0.214, pruned_loss=0.02574, over 4886.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03285, over 973677.16 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:34:30,051 INFO [train.py:715] (5/8) Epoch 10, batch 13250, loss[loss=0.116, simple_loss=0.1979, pruned_loss=0.01709, over 4975.00 frames.], tot_loss[loss=0.139, simple_loss=0.2115, pruned_loss=0.03321, over 973656.45 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:35:08,698 INFO [train.py:715] (5/8) Epoch 10, batch 13300, loss[loss=0.1259, simple_loss=0.1989, pruned_loss=0.02647, over 4764.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03314, over 973156.87 frames.], batch size: 17, lr: 2.15e-04
2022-05-06 19:35:47,100 INFO [train.py:715] (5/8) Epoch 10, batch 13350, loss[loss=0.1491, simple_loss=0.2216, pruned_loss=0.03831, over 4815.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03355, over 972724.98 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:36:26,373 INFO [train.py:715] (5/8) Epoch 10, batch 13400, loss[loss=0.1288, simple_loss=0.2099, pruned_loss=0.02388, over 4773.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03319, over 973151.74 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:37:04,722 INFO [train.py:715] (5/8) Epoch 10, batch 13450, loss[loss=0.1368, simple_loss=0.1949, pruned_loss=0.03934, over 4990.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03261, over 972329.42 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:37:42,963 INFO [train.py:715] (5/8) Epoch 10, batch 13500, loss[loss=0.1481, simple_loss=0.2229, pruned_loss=0.03665, over 4760.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03258, over 972533.18 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:38:22,033 INFO [train.py:715] (5/8) Epoch 10, batch 13550, loss[loss=0.1579, simple_loss=0.2299, pruned_loss=0.04297, over 4767.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03272, over 971865.33 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:39:00,608 INFO [train.py:715] (5/8) Epoch 10, batch 13600, loss[loss=0.1454, simple_loss=0.2197, pruned_loss=0.03553, over 4968.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03276, over 972075.20 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:39:39,006 INFO [train.py:715] (5/8) Epoch 10, batch 13650, loss[loss=0.103, simple_loss=0.1718, pruned_loss=0.01706, over 4813.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03311, over 971912.34 frames.], batch size: 12, lr: 2.15e-04
2022-05-06 19:40:17,576 INFO [train.py:715] (5/8) Epoch 10, batch 13700, loss[loss=0.1442, simple_loss=0.2315, pruned_loss=0.02846, over 4850.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03292, over 972556.54 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:40:57,644 INFO [train.py:715] (5/8) Epoch 10, batch 13750, loss[loss=0.158, simple_loss=0.2328, pruned_loss=0.04163, over 4976.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03303, over 972227.62 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:41:37,007 INFO [train.py:715] (5/8) Epoch 10, batch 13800, loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03013, over 4891.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03336, over 971795.90 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:42:15,512 INFO [train.py:715] (5/8) Epoch 10, batch 13850, loss[loss=0.1373, simple_loss=0.206, pruned_loss=0.03427, over 4933.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03368, over 972047.23 frames.], batch size: 35, lr: 2.15e-04
2022-05-06 19:42:55,147 INFO [train.py:715] (5/8) Epoch 10, batch 13900, loss[loss=0.1619, simple_loss=0.2297, pruned_loss=0.0471, over 4945.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03325, over 971596.67 frames.], batch size: 39, lr: 2.15e-04
2022-05-06 19:43:33,822 INFO [train.py:715] (5/8) Epoch 10, batch 13950, loss[loss=0.1143, simple_loss=0.1889, pruned_loss=0.01983, over 4744.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03307, over 972273.87 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:44:12,829 INFO [train.py:715] (5/8) Epoch 10, batch 14000, loss[loss=0.1481, simple_loss=0.2272, pruned_loss=0.03447, over 4917.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03306, over 972497.90 frames.], batch size: 39, lr: 2.15e-04
2022-05-06 19:44:51,235 INFO [train.py:715] (5/8) Epoch 10, batch 14050, loss[loss=0.1279, simple_loss=0.2001, pruned_loss=0.02782, over 4758.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03325, over 972432.84 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:45:30,764 INFO [train.py:715] (5/8) Epoch 10, batch 14100, loss[loss=0.155, simple_loss=0.2332, pruned_loss=0.03844, over 4872.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03347, over 973023.17 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:46:09,124 INFO [train.py:715] (5/8) Epoch 10, batch 14150, loss[loss=0.1557, simple_loss=0.2195, pruned_loss=0.04592, over 4983.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03334, over 973224.97 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:46:47,031 INFO [train.py:715] (5/8) Epoch 10, batch 14200, loss[loss=0.1322, simple_loss=0.211, pruned_loss=0.02669, over 4893.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.0335, over 972926.62 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:47:26,631 INFO [train.py:715] (5/8) Epoch 10, batch 14250, loss[loss=0.125, simple_loss=0.2023, pruned_loss=0.02388, over 4811.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03403, over 971831.16 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:48:05,007 INFO [train.py:715] (5/8) Epoch 10, batch 14300, loss[loss=0.1268, simple_loss=0.1964, pruned_loss=0.02861, over 4904.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03407, over 971588.43 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:48:43,126 INFO [train.py:715] (5/8) Epoch 10, batch 14350, loss[loss=0.1644, simple_loss=0.2438, pruned_loss=0.04252, over 4880.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03384, over 972690.45 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:49:21,565 INFO [train.py:715] (5/8) Epoch 10, batch 14400, loss[loss=0.1494, simple_loss=0.2255, pruned_loss=0.03662, over 4867.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03408, over 972420.08 frames.], batch size: 20, lr: 2.15e-04
2022-05-06 19:50:01,193 INFO [train.py:715] (5/8) Epoch 10, batch 14450, loss[loss=0.1497, simple_loss=0.2274, pruned_loss=0.03601, over 4878.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.0338, over 972221.43 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:50:39,561 INFO [train.py:715] (5/8) Epoch 10, batch 14500, loss[loss=0.1442, simple_loss=0.2231, pruned_loss=0.03268, over 4951.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03388, over 972544.40 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:51:17,696 INFO [train.py:715] (5/8) Epoch 10, batch 14550, loss[loss=0.1443, simple_loss=0.2242, pruned_loss=0.03216, over 4916.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03378, over 972815.49 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:51:57,345 INFO [train.py:715] (5/8) Epoch 10, batch 14600, loss[loss=0.1458, simple_loss=0.2205, pruned_loss=0.03557, over 4922.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03412, over 973078.23 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:52:35,981 INFO [train.py:715] (5/8) Epoch 10, batch 14650, loss[loss=0.123, simple_loss=0.2043, pruned_loss=0.02084, over 4876.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03343, over 971485.24 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:53:14,371 INFO [train.py:715] (5/8) Epoch 10, batch 14700, loss[loss=0.1414, simple_loss=0.2216, pruned_loss=0.03058, over 4743.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03362, over 971481.39 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:53:53,325 INFO [train.py:715] (5/8) Epoch 10, batch 14750, loss[loss=0.1388, simple_loss=0.2166, pruned_loss=0.03047, over 4837.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03316, over 971627.31 frames.], batch size: 13, lr: 2.15e-04
2022-05-06 19:54:33,137 INFO [train.py:715] (5/8) Epoch 10, batch 14800, loss[loss=0.1127, simple_loss=0.1874, pruned_loss=0.01902, over 4986.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03308, over 971471.40 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:55:12,160 INFO [train.py:715] (5/8) Epoch 10, batch 14850, loss[loss=0.1271, simple_loss=0.2015, pruned_loss=0.02637, over 4880.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03342, over 971798.06 frames.], batch size: 30, lr: 2.15e-04
2022-05-06 19:55:50,174 INFO [train.py:715] (5/8) Epoch 10, batch 14900, loss[loss=0.1333, simple_loss=0.205, pruned_loss=0.0308, over 4905.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03295, over 972557.00 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:56:30,314 INFO [train.py:715] (5/8) Epoch 10, batch 14950, loss[loss=0.1583, simple_loss=0.2288, pruned_loss=0.04393, over 4787.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03314, over 971889.89 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:57:09,836 INFO [train.py:715] (5/8) Epoch 10, batch 15000, loss[loss=0.1818, simple_loss=0.2615, pruned_loss=0.05108, over 4794.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03345, over 971780.75 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:57:09,836 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 19:57:19,461 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
2022-05-06 19:57:59,086 INFO [train.py:715] (5/8) Epoch 10, batch 15050, loss[loss=0.1476, simple_loss=0.2149, pruned_loss=0.04012, over 4986.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2124, pruned_loss=0.03386, over 973273.20 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:58:38,144 INFO [train.py:715] (5/8) Epoch 10, batch 15100, loss[loss=0.1522, simple_loss=0.2215, pruned_loss=0.04147, over 4815.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2126, pruned_loss=0.03412, over 973462.66 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:59:17,365 INFO [train.py:715] (5/8) Epoch 10, batch 15150, loss[loss=0.1552, simple_loss=0.2272, pruned_loss=0.04161, over 4835.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03406, over 972489.64 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 19:59:56,360 INFO [train.py:715] (5/8) Epoch 10, batch 15200, loss[loss=0.1383, simple_loss=0.2045, pruned_loss=0.036, over 4830.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2122, pruned_loss=0.03379, over 972034.75 frames.], batch size: 27, lr: 2.14e-04
2022-05-06 20:00:35,741 INFO [train.py:715] (5/8) Epoch 10, batch 15250, loss[loss=0.1244, simple_loss=0.1951, pruned_loss=0.0269, over 4811.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2124, pruned_loss=0.03403, over 972236.04 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:01:14,784 INFO [train.py:715] (5/8) Epoch 10, batch 15300, loss[loss=0.1148, simple_loss=0.1901, pruned_loss=0.01974, over 4754.00 frames.], tot_loss[loss=0.1401, simple_loss=0.212, pruned_loss=0.03414, over 971657.43 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:01:54,057 INFO [train.py:715] (5/8) Epoch 10, batch 15350, loss[loss=0.1435, simple_loss=0.2094, pruned_loss=0.03883, over 4980.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2125, pruned_loss=0.03409, over 972157.00 frames.], batch size: 31, lr: 2.14e-04
2022-05-06 20:02:34,122 INFO [train.py:715] (5/8) Epoch 10, batch 15400, loss[loss=0.1559, simple_loss=0.2162, pruned_loss=0.04781, over 4787.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2119, pruned_loss=0.03358, over 971652.29 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:03:13,391 INFO [train.py:715] (5/8) Epoch 10, batch 15450, loss[loss=0.1223, simple_loss=0.1975, pruned_loss=0.02355, over 4979.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03369, over 971499.81 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:03:53,466 INFO [train.py:715] (5/8) Epoch 10, batch 15500, loss[loss=0.1408, simple_loss=0.2174, pruned_loss=0.0321, over 4918.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.0335, over 971753.52 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:04:32,470 INFO [train.py:715] (5/8) Epoch 10, batch 15550, loss[loss=0.1506, simple_loss=0.2178, pruned_loss=0.04168, over 4841.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.0332, over 971809.47 frames.], batch size: 30, lr: 2.14e-04
2022-05-06 20:05:11,886 INFO [train.py:715] (5/8) Epoch 10, batch 15600, loss[loss=0.1303, simple_loss=0.2032, pruned_loss=0.02876, over 4783.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03348, over 971932.24 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:05:50,243 INFO [train.py:715] (5/8) Epoch 10, batch 15650, loss[loss=0.1135, simple_loss=0.1978, pruned_loss=0.01457, over 4820.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03332, over 972437.33 frames.], batch size: 26, lr: 2.14e-04
2022-05-06 20:06:28,931 INFO [train.py:715] (5/8) Epoch 10, batch 15700, loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02943, over 4934.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03336, over 972404.25 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:07:08,405 INFO [train.py:715] (5/8) Epoch 10, batch 15750, loss[loss=0.162, simple_loss=0.238, pruned_loss=0.04304, over 4915.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03319, over 971660.00 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:07:46,970 INFO [train.py:715] (5/8) Epoch 10, batch 15800, loss[loss=0.1663, simple_loss=0.2313, pruned_loss=0.05068, over 4832.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.0329, over 971661.31 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:08:26,772 INFO [train.py:715] (5/8) Epoch 10, batch 15850, loss[loss=0.1156, simple_loss=0.1826, pruned_loss=0.02432, over 4941.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03243, over 972115.89 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:09:05,640 INFO [train.py:715] (5/8) Epoch 10, batch 15900, loss[loss=0.1487, simple_loss=0.222, pruned_loss=0.03769, over 4962.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03265, over 971380.08 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:09:44,835 INFO [train.py:715] (5/8) Epoch 10, batch 15950, loss[loss=0.1561, simple_loss=0.2286, pruned_loss=0.04177, over 4967.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03257, over 971785.46 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:10:23,753 INFO [train.py:715] (5/8) Epoch 10, batch 16000, loss[loss=0.1205, simple_loss=0.1921, pruned_loss=0.02448, over 4829.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03271, over 972025.77 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:11:02,642 INFO [train.py:715] (5/8) Epoch 10, batch 16050, loss[loss=0.1298, simple_loss=0.2059, pruned_loss=0.0269, over 4880.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03297, over 971866.73 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:11:41,915 INFO [train.py:715] (5/8) Epoch 10, batch 16100, loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.04744, over 4867.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03271, over 971476.75 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:12:21,142 INFO [train.py:715] (5/8) Epoch 10, batch 16150, loss[loss=0.1237, simple_loss=0.1957, pruned_loss=0.02584, over 4899.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03297, over 971485.26 frames.], batch size: 22, lr: 2.14e-04
2022-05-06 20:13:01,112 INFO [train.py:715] (5/8) Epoch 10, batch 16200, loss[loss=0.1496, simple_loss=0.2177, pruned_loss=0.04073, over 4932.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03316, over 972334.36 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:13:40,648 INFO [train.py:715] (5/8) Epoch 10, batch 16250, loss[loss=0.143, simple_loss=0.2111, pruned_loss=0.03748, over 4889.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03323, over 972628.59 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:14:19,863 INFO [train.py:715] (5/8) Epoch 10, batch 16300, loss[loss=0.1406, simple_loss=0.2198, pruned_loss=0.03066, over 4905.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.0328, over 973051.73 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:14:59,865 INFO [train.py:715] (5/8) Epoch 10, batch 16350, loss[loss=0.1252, simple_loss=0.2112, pruned_loss=0.01962, over 4846.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03296, over 971123.69 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:15:39,244 INFO [train.py:715] (5/8) Epoch 10, batch 16400, loss[loss=0.1432, simple_loss=0.2197, pruned_loss=0.03334, over 4868.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03299, over 971052.21 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:16:18,979 INFO [train.py:715] (5/8) Epoch 10, batch 16450, loss[loss=0.1428, simple_loss=0.2201, pruned_loss=0.03274, over 4976.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03337, over 972021.56 frames.], batch size: 25, lr: 2.14e-04
2022-05-06 20:16:57,468 INFO [train.py:715] (5/8) Epoch 10, batch 16500, loss[loss=0.122, simple_loss=0.1894, pruned_loss=0.02727, over 4859.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03316, over 971701.77 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:17:36,173 INFO [train.py:715] (5/8) Epoch 10, batch 16550, loss[loss=0.1405, simple_loss=0.208, pruned_loss=0.03645, over 4754.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03332, over 971880.12 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:18:15,832 INFO [train.py:715] (5/8) Epoch 10, batch 16600, loss[loss=0.1493, simple_loss=0.231, pruned_loss=0.03385, over 4981.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03367, over 972549.55 frames.], batch size: 25, lr: 2.14e-04
2022-05-06 20:18:54,010 INFO [train.py:715] (5/8) Epoch 10, batch 16650, loss[loss=0.1722, simple_loss=0.245, pruned_loss=0.04969, over 4945.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03396, over 972274.47 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:19:33,368 INFO [train.py:715] (5/8) Epoch 10, batch 16700, loss[loss=0.1824, simple_loss=0.259, pruned_loss=0.05297, over 4863.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03481, over 972544.42 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:20:12,353 INFO [train.py:715] (5/8) Epoch 10, batch 16750, loss[loss=0.1534, simple_loss=0.2259, pruned_loss=0.04047, over 4756.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03403, over 971305.16 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:20:52,525 INFO [train.py:715] (5/8) Epoch 10, batch 16800, loss[loss=0.1556, simple_loss=0.222, pruned_loss=0.0446, over 4791.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03386, over 970827.04 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:21:31,847 INFO [train.py:715] (5/8) Epoch 10, batch 16850, loss[loss=0.1295, simple_loss=0.203, pruned_loss=0.02804, over 4765.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03371, over 971594.24 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:22:11,648 INFO [train.py:715] (5/8) Epoch 10, batch 16900, loss[loss=0.1409, simple_loss=0.2257, pruned_loss=0.02802, over 4873.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03352, over 971620.30 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:22:51,672 INFO [train.py:715] (5/8) Epoch 10, batch 16950, loss[loss=0.2169, simple_loss=0.2911, pruned_loss=0.07134, over 4978.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03379, over 972448.52 frames.], batch size: 39, lr: 2.14e-04
2022-05-06 20:23:29,921 INFO [train.py:715] (5/8) Epoch 10, batch 17000, loss[loss=0.1453, simple_loss=0.2318, pruned_loss=0.02942, over 4840.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03363, over 972040.00 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:24:09,513 INFO [train.py:715] (5/8) Epoch 10, batch 17050, loss[loss=0.156, simple_loss=0.2293, pruned_loss=0.04141, over 4946.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2141, pruned_loss=0.0335, over 973325.50 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:24:48,214 INFO [train.py:715] (5/8) Epoch 10, batch 17100, loss[loss=0.1405, simple_loss=0.2175, pruned_loss=0.03177, over 4923.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2149, pruned_loss=0.03417, over 973720.61 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:25:27,434 INFO [train.py:715] (5/8) Epoch 10, batch 17150, loss[loss=0.1239, simple_loss=0.1925, pruned_loss=0.0276, over 4917.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2139, pruned_loss=0.0336, over 972724.02 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:26:07,399 INFO [train.py:715] (5/8) Epoch 10, batch 17200, loss[loss=0.1144, simple_loss=0.1886, pruned_loss=0.02008, over 4985.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03351, over 972644.87 frames.], batch size: 28, lr: 2.14e-04
2022-05-06 20:26:47,008 INFO [train.py:715] (5/8) Epoch 10, batch 17250, loss[loss=0.1498, simple_loss=0.2215, pruned_loss=0.03902, over 4766.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03328, over 972819.02 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:27:26,664 INFO [train.py:715] (5/8) Epoch 10, batch 17300, loss[loss=0.1516, simple_loss=0.2169, pruned_loss=0.04311, over 4966.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03388, over 972827.05 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:28:05,423 INFO [train.py:715] (5/8) Epoch 10, batch 17350, loss[loss=0.1305, simple_loss=0.2034, pruned_loss=0.02885, over 4932.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2138, pruned_loss=0.03362, over 973268.40 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:28:44,828 INFO [train.py:715] (5/8) Epoch 10, batch 17400, loss[loss=0.1236, simple_loss=0.206, pruned_loss=0.02062, over 4741.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2135, pruned_loss=0.03333, over 971813.37 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:29:24,006 INFO [train.py:715] (5/8) Epoch 10, batch 17450, loss[loss=0.1036, simple_loss=0.1797, pruned_loss=0.0138, over 4790.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03326, over 972281.38 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:30:02,999 INFO [train.py:715] (5/8) Epoch 10, batch 17500, loss[loss=0.1378, simple_loss=0.2131, pruned_loss=0.03129, over 4916.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2137, pruned_loss=0.03352, over 972283.23 frames.], batch size: 39, lr: 2.14e-04
2022-05-06 20:30:42,989 INFO [train.py:715] (5/8) Epoch 10, batch 17550, loss[loss=0.1237, simple_loss=0.2024, pruned_loss=0.02248, over 4895.00 frames.], tot_loss[loss=0.14, simple_loss=0.2138, pruned_loss=0.03317, over 972169.64 frames.], batch size: 22, lr: 2.14e-04
2022-05-06 20:31:21,944 INFO [train.py:715] (5/8) Epoch 10, batch 17600, loss[loss=0.1078, simple_loss=0.1799, pruned_loss=0.01785, over 4930.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03306, over 972151.52 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:32:01,506 INFO [train.py:715] (5/8) Epoch 10, batch 17650, loss[loss=0.145, simple_loss=0.2342, pruned_loss=0.02788, over 4904.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2123, pruned_loss=0.0323, over 972402.39 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:32:40,266 INFO [train.py:715] (5/8) Epoch 10, batch 17700, loss[loss=0.1806, simple_loss=0.2494, pruned_loss=0.05591, over 4915.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2133, pruned_loss=0.03278, over 972678.81 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:33:20,043 INFO [train.py:715] (5/8) Epoch 10, batch 17750, loss[loss=0.1441, simple_loss=0.2173, pruned_loss=0.03547, over 4985.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2138, pruned_loss=0.03323, over 972385.07 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:33:59,766 INFO [train.py:715] (5/8) Epoch 10, batch 17800, loss[loss=0.1562, simple_loss=0.2318, pruned_loss=0.04034, over 4923.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2132, pruned_loss=0.03307, over 972953.80 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:34:38,713 INFO [train.py:715] (5/8) Epoch 10, batch 17850, loss[loss=0.1505, simple_loss=0.2287, pruned_loss=0.03617, over 4931.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2128, pruned_loss=0.03299, over 973102.78 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:35:18,468 INFO [train.py:715] (5/8) Epoch 10, batch 17900, loss[loss=0.1426, simple_loss=0.218, pruned_loss=0.03363, over 4961.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.0327, over 972717.09 frames.], batch size: 24, lr: 2.14e-04
2022-05-06 20:35:57,401 INFO [train.py:715] (5/8) Epoch 10, batch 17950, loss[loss=0.1319, simple_loss=0.205, pruned_loss=0.02937, over 4925.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03279, over 972207.37 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:36:36,020 INFO [train.py:715] (5/8) Epoch 10, batch 18000, loss[loss=0.1414, simple_loss=0.2083, pruned_loss=0.0372, over 4819.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03309, over 972436.98 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:36:36,021 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 20:36:45,528 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
2022-05-06 20:37:24,880 INFO [train.py:715] (5/8) Epoch 10, batch 18050, loss[loss=0.1245, simple_loss=0.1922, pruned_loss=0.02839, over 4827.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03336, over 972414.73 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:38:03,973 INFO [train.py:715] (5/8) Epoch 10, batch 18100, loss[loss=0.1215, simple_loss=0.1969, pruned_loss=0.02301, over 4700.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03303, over 972176.61 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:38:43,262 INFO [train.py:715] (5/8) Epoch 10, batch 18150, loss[loss=0.1314, simple_loss=0.2014, pruned_loss=0.03074, over 4819.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03276, over 973234.92 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:39:21,944 INFO [train.py:715] (5/8) Epoch 10, batch 18200, loss[loss=0.1441, simple_loss=0.2145, pruned_loss=0.03683, over 4967.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03281, over 973137.93 frames.], batch size: 35, lr: 2.14e-04
2022-05-06 20:40:00,620 INFO [train.py:715] (5/8) Epoch 10, batch 18250, loss[loss=0.1522, simple_loss=0.2196, pruned_loss=0.04241, over 4779.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03305, over 972666.54 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:40:40,107 INFO [train.py:715] (5/8) Epoch 10, batch 18300, loss[loss=0.1119, simple_loss=0.188, pruned_loss=0.01788, over 4969.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2115, pruned_loss=0.03319, over 972917.86 frames.], batch size: 35, lr: 2.14e-04
2022-05-06 20:41:19,470 INFO [train.py:715] (5/8) Epoch 10, batch 18350, loss[loss=0.143, simple_loss=0.2148, pruned_loss=0.03565, over 4772.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03285, over 972835.79 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:41:57,960 INFO [train.py:715] (5/8) Epoch 10, batch 18400, loss[loss=0.1169, simple_loss=0.1887, pruned_loss=0.02254, over 4783.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03326, over 972525.87 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:42:37,147 INFO [train.py:715] (5/8) Epoch 10, batch 18450, loss[loss=0.1523, simple_loss=0.2267, pruned_loss=0.03897, over 4820.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.03361, over 972386.34 frames.], batch size: 27, lr: 2.14e-04
2022-05-06 20:43:16,002 INFO [train.py:715] (5/8) Epoch 10, batch 18500, loss[loss=0.1417, simple_loss=0.2148, pruned_loss=0.03432, over 4984.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03327, over 973040.46 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:43:55,526 INFO [train.py:715] (5/8) Epoch 10, batch 18550, loss[loss=0.143, simple_loss=0.2304, pruned_loss=0.02783, over 4806.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03321, over 973194.57 frames.], batch size: 12, lr: 2.13e-04
2022-05-06 20:44:33,845 INFO [train.py:715] (5/8) Epoch 10, batch 18600, loss[loss=0.1305, simple_loss=0.1966, pruned_loss=0.03225, over 4827.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03316, over 973518.70 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 20:45:13,253 INFO [train.py:715] (5/8) Epoch 10, batch 18650, loss[loss=0.1546, simple_loss=0.2278, pruned_loss=0.04067, over 4803.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03337, over 973843.53 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 20:45:52,991 INFO [train.py:715] (5/8) Epoch 10, batch 18700, loss[loss=0.1767, simple_loss=0.2552, pruned_loss=0.04914, over 4964.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2138, pruned_loss=0.03369, over 973144.87 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 20:46:31,252 INFO [train.py:715] (5/8) Epoch 10, batch 18750, loss[loss=0.1498, simple_loss=0.2213, pruned_loss=0.03909, over 4980.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03411, over 973120.89 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 20:47:10,631 INFO [train.py:715] (5/8) Epoch 10, batch 18800, loss[loss=0.1868, simple_loss=0.2621, pruned_loss=0.0558, over 4963.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03415, over 973562.44 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 20:47:50,112 INFO [train.py:715] (5/8) Epoch 10, batch 18850, loss[loss=0.1881, simple_loss=0.2427, pruned_loss=0.06672, over 4871.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03411, over 973609.85 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:48:29,009 INFO [train.py:715] (5/8) Epoch 10, batch 18900, loss[loss=0.1624, simple_loss=0.2185, pruned_loss=0.0531, over 4900.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03407, over 972661.52 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 20:49:08,062 INFO [train.py:715] (5/8) Epoch 10, batch 18950, loss[loss=0.1652, simple_loss=0.2468, pruned_loss=0.04183, over 4746.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2147, pruned_loss=0.0343, over 972384.67 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 20:49:48,333 INFO [train.py:715] (5/8) Epoch 10, batch 19000, loss[loss=0.1251, simple_loss=0.2036, pruned_loss=0.02331, over 4807.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03381, over 971146.16 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 20:50:27,640 INFO [train.py:715] (5/8) Epoch 10, batch 19050, loss[loss=0.1372, simple_loss=0.2194, pruned_loss=0.0275, over 4859.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03335, over 971334.90 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 20:51:06,450 INFO [train.py:715] (5/8) Epoch 10, batch 19100, loss[loss=0.1838, simple_loss=0.2718, pruned_loss=0.04793, over 4896.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.03294, over 971210.35 frames.], batch size: 17, lr: 2.13e-04
2022-05-06 20:51:46,323 INFO [train.py:715] (5/8) Epoch 10, batch 19150, loss[loss=0.1327, simple_loss=0.2085, pruned_loss=0.02848, over 4754.00 frames.], tot_loss[loss=0.14, simple_loss=0.2135, pruned_loss=0.03326, over 970823.14 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:52:26,495 INFO [train.py:715] (5/8) Epoch 10, batch 19200, loss[loss=0.1105, simple_loss=0.1856, pruned_loss=0.01771, over 4770.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2129, pruned_loss=0.0331, over 971222.04 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 20:53:06,170 INFO [train.py:715] (5/8) Epoch 10, batch 19250, loss[loss=0.1548, simple_loss=0.2183, pruned_loss=0.04562, over 4872.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03317, over 971419.00 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 20:53:46,065 INFO [train.py:715] (5/8) Epoch 10, batch 19300, loss[loss=0.1152, simple_loss=0.1887, pruned_loss=0.02084, over 4762.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03289, over 970387.01 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:54:26,471 INFO [train.py:715] (5/8) Epoch 10, batch 19350, loss[loss=0.1334, simple_loss=0.2052, pruned_loss=0.03079, over 4788.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03273, over 970583.07 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 20:55:06,650 INFO [train.py:715] (5/8) Epoch 10, batch 19400, loss[loss=0.1346, simple_loss=0.1952, pruned_loss=0.03702, over 4840.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03287, over 971274.10 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 20:55:45,795 INFO [train.py:715] (5/8) Epoch 10, batch 19450, loss[loss=0.1561, simple_loss=0.2262, pruned_loss=0.04304, over 4934.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03343, over 972700.12 frames.], batch size: 39, lr: 2.13e-04
2022-05-06 20:56:25,407 INFO [train.py:715] (5/8) Epoch 10, batch 19500, loss[loss=0.1573, simple_loss=0.2375, pruned_loss=0.03849, over 4702.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.0332, over 972220.35 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 20:57:04,607 INFO [train.py:715] (5/8) Epoch 10, batch 19550, loss[loss=0.1252, simple_loss=0.1912, pruned_loss=0.02956, over 4822.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03366, over 972599.22 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 20:57:43,330 INFO [train.py:715] (5/8) Epoch 10, batch 19600, loss[loss=0.1326, simple_loss=0.2016, pruned_loss=0.03178, over 4883.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.03372, over 972284.02 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 20:58:22,306 INFO [train.py:715] (5/8) Epoch 10, batch 19650, loss[loss=0.129, simple_loss=0.1982, pruned_loss=0.02986, over 4807.00 frames.], tot_loss[loss=0.14, simple_loss=0.2122, pruned_loss=0.03387, over 972450.05 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 20:59:01,958 INFO [train.py:715] (5/8) Epoch 10, batch 19700, loss[loss=0.1559, simple_loss=0.224, pruned_loss=0.04389, over 4978.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03341, over 971711.61 frames.], batch size: 28, lr: 2.13e-04
2022-05-06 20:59:41,295 INFO [train.py:715] (5/8) Epoch 10, batch 19750, loss[loss=0.151, simple_loss=0.2273, pruned_loss=0.03738, over 4756.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2121, pruned_loss=0.03351, over 972263.08 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:00:19,620 INFO [train.py:715] (5/8) Epoch 10, batch 19800, loss[loss=0.1433, simple_loss=0.2031, pruned_loss=0.04173, over 4810.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03371, over 971760.86 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:00:59,242 INFO [train.py:715] (5/8) Epoch 10, batch 19850, loss[loss=0.09944, simple_loss=0.1785, pruned_loss=0.01017, over 4813.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03317, over 971587.11 frames.], batch size: 12, lr: 2.13e-04
2022-05-06 21:01:38,757 INFO [train.py:715] (5/8) Epoch 10, batch 19900, loss[loss=0.1247, simple_loss=0.1964, pruned_loss=0.02652, over 4839.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03285, over 972068.94 frames.], batch size: 30, lr: 2.13e-04
2022-05-06 21:02:19,890 INFO [train.py:715] (5/8) Epoch 10, batch 19950, loss[loss=0.1296, simple_loss=0.2035, pruned_loss=0.02784, over 4867.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03313, over 972050.25 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 21:02:58,931 INFO [train.py:715] (5/8) Epoch 10, batch 20000, loss[loss=0.139, simple_loss=0.2127, pruned_loss=0.03261, over 4847.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03302, over 972213.09 frames.], batch size: 27, lr: 2.13e-04
2022-05-06 21:03:37,942 INFO [train.py:715] (5/8) Epoch 10, batch 20050, loss[loss=0.1337, simple_loss=0.2195, pruned_loss=0.02397, over 4961.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03317, over 972698.37 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:04:17,424 INFO [train.py:715] (5/8) Epoch 10, batch 20100, loss[loss=0.1423, simple_loss=0.2162, pruned_loss=0.03426, over 4805.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03303, over 972366.53 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 21:04:55,527 INFO [train.py:715] (5/8) Epoch 10, batch 20150, loss[loss=0.1622, simple_loss=0.2397, pruned_loss=0.04234, over 4784.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03344, over 972310.18 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:05:34,944 INFO [train.py:715] (5/8) Epoch 10, batch 20200, loss[loss=0.1439, simple_loss=0.2194, pruned_loss=0.03415, over 4862.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03368, over 971445.35 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 21:06:13,958 INFO [train.py:715] (5/8) Epoch 10, batch 20250, loss[loss=0.1544, simple_loss=0.2257, pruned_loss=0.04157, over 4683.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03447, over 971791.51 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:06:52,617 INFO [train.py:715] (5/8) Epoch 10, batch 20300, loss[loss=0.1598, simple_loss=0.2243, pruned_loss=0.04772, over 4962.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03437, over 971426.19 frames.], batch size: 39, lr: 2.13e-04
2022-05-06 21:07:31,400 INFO [train.py:715] (5/8) Epoch 10, batch 20350, loss[loss=0.1254, simple_loss=0.1947, pruned_loss=0.02805, over 4968.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03416, over 971565.30 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:08:10,506 INFO [train.py:715] (5/8) Epoch 10, batch 20400, loss[loss=0.1509, simple_loss=0.2246, pruned_loss=0.03857, over 4849.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03397, over 973089.52 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 21:08:49,426 INFO [train.py:715] (5/8) Epoch 10, batch 20450, loss[loss=0.1117, simple_loss=0.1877, pruned_loss=0.01778, over 4888.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03431, over 973639.71 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 21:09:27,877 INFO [train.py:715] (5/8) Epoch 10, batch 20500, loss[loss=0.1294, simple_loss=0.2056, pruned_loss=0.02662, over 4762.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03415, over 973877.42 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:10:06,955 INFO [train.py:715] (5/8) Epoch 10, batch 20550, loss[loss=0.1256, simple_loss=0.1953, pruned_loss=0.02791, over 4756.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.0346, over 973432.47 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:10:46,030 INFO [train.py:715] (5/8) Epoch 10, batch 20600, loss[loss=0.136, simple_loss=0.1989, pruned_loss=0.03656, over 4824.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.0347, over 972759.08 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:11:25,460 INFO [train.py:715] (5/8) Epoch 10, batch 20650, loss[loss=0.1241, simple_loss=0.1892, pruned_loss=0.02944, over 4790.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03457, over 972433.02 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:12:04,252 INFO [train.py:715] (5/8) Epoch 10, batch 20700, loss[loss=0.1402, simple_loss=0.2188, pruned_loss=0.03078, over 4700.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03339, over 971957.41 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:12:44,587 INFO [train.py:715] (5/8) Epoch 10, batch 20750, loss[loss=0.1447, simple_loss=0.2125, pruned_loss=0.03848, over 4818.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03373, over 971646.47 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 21:13:24,571 INFO [train.py:715] (5/8) Epoch 10, batch 20800, loss[loss=0.1628, simple_loss=0.2294, pruned_loss=0.04805, over 4988.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03311, over 971240.93 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:14:03,351 INFO [train.py:715] (5/8) Epoch 10, batch 20850, loss[loss=0.1636, simple_loss=0.2437, pruned_loss=0.04175, over 4810.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2122, pruned_loss=0.03382, over 972058.59 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:14:43,296 INFO [train.py:715] (5/8) Epoch 10, batch 20900, loss[loss=0.1642, simple_loss=0.2357, pruned_loss=0.04634, over 4961.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03308, over 972891.85 frames.], batch size: 39, lr: 2.13e-04
2022-05-06 21:15:23,751 INFO [train.py:715] (5/8) Epoch 10, batch 20950, loss[loss=0.1483, simple_loss=0.2206, pruned_loss=0.03805, over 4976.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03343, over 973062.36 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:16:02,698 INFO [train.py:715] (5/8) Epoch 10, batch 21000, loss[loss=0.1813, simple_loss=0.2538, pruned_loss=0.05442, over 4962.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03383, over 973391.87 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 21:16:02,699 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 21:16:12,202 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
2022-05-06 21:16:51,729 INFO [train.py:715] (5/8) Epoch 10, batch 21050, loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03105, over 4975.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2125, pruned_loss=0.0339, over 973575.03 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 21:17:32,549 INFO [train.py:715] (5/8) Epoch 10, batch 21100, loss[loss=0.136, simple_loss=0.2149, pruned_loss=0.02853, over 4967.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03354, over 973779.38 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:18:14,010 INFO [train.py:715] (5/8) Epoch 10, batch 21150, loss[loss=0.1514, simple_loss=0.2279, pruned_loss=0.03747, over 4921.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03329, over 972940.36 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 21:18:55,100 INFO [train.py:715] (5/8) Epoch 10, batch 21200, loss[loss=0.1484, simple_loss=0.2263, pruned_loss=0.03525, over 4864.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03318, over 973218.19 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 21:19:35,766 INFO [train.py:715] (5/8) Epoch 10, batch 21250, loss[loss=0.1678, simple_loss=0.254, pruned_loss=0.04078, over 4822.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2121, pruned_loss=0.03345, over 972988.12 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:20:17,431 INFO [train.py:715] (5/8) Epoch 10, batch 21300, loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03348, over 4871.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03383, over 972848.69 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 21:20:58,695 INFO [train.py:715] (5/8) Epoch 10, batch 21350, loss[loss=0.1294, simple_loss=0.2043, pruned_loss=0.02729, over 4991.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03378, over 973708.01 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 21:21:39,104 INFO [train.py:715] (5/8) Epoch 10, batch 21400, loss[loss=0.1427, simple_loss=0.2104, pruned_loss=0.03755, over 4860.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03406, over 974302.27 frames.], batch size: 30, lr: 2.13e-04
2022-05-06 21:22:20,538 INFO [train.py:715] (5/8) Epoch 10, batch 21450, loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03006, over 4814.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.0338, over 973449.17 frames.], batch size: 27, lr: 2.13e-04
2022-05-06 21:23:02,352 INFO [train.py:715] (5/8) Epoch 10, batch 21500, loss[loss=0.146, simple_loss=0.2212, pruned_loss=0.03535, over 4992.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.0334, over 973681.29 frames.], batch size: 28, lr: 2.13e-04
2022-05-06 21:23:43,377 INFO [train.py:715] (5/8) Epoch 10, batch 21550, loss[loss=0.1266, simple_loss=0.2072, pruned_loss=0.02298, over 4784.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03345, over 972916.46 frames.], batch size: 17, lr: 2.13e-04
2022-05-06 21:24:24,263 INFO [train.py:715] (5/8) Epoch 10, batch 21600, loss[loss=0.1226, simple_loss=0.203, pruned_loss=0.02111, over 4868.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03355, over 972465.00 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 21:25:06,207 INFO [train.py:715] (5/8) Epoch 10, batch 21650, loss[loss=0.1539, simple_loss=0.2242, pruned_loss=0.04182, over 4902.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03342, over 972779.72 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:25:47,747 INFO [train.py:715] (5/8) Epoch 10, batch 21700, loss[loss=0.1746, simple_loss=0.2333, pruned_loss=0.05791, over 4722.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03349, over 972266.09 frames.], batch size: 12, lr: 2.13e-04
2022-05-06 21:26:28,007 INFO [train.py:715] (5/8) Epoch 10, batch 21750, loss[loss=0.1767, simple_loss=0.2551, pruned_loss=0.04915, over 4977.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03364, over 972154.51 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:27:08,993 INFO [train.py:715] (5/8) Epoch 10, batch 21800, loss[loss=0.1435, simple_loss=0.2213, pruned_loss=0.03287, over 4834.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2117, pruned_loss=0.03344, over 972150.80 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:27:50,695 INFO [train.py:715] (5/8) Epoch 10, batch 21850, loss[loss=0.1127, simple_loss=0.1838, pruned_loss=0.02076, over 4808.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03326, over 971731.60 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 21:28:31,163 INFO [train.py:715] (5/8) Epoch 10, batch 21900, loss[loss=0.1359, simple_loss=0.2148, pruned_loss=0.02851, over 4930.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.0332, over 970780.59 frames.], batch size: 39, lr: 2.13e-04
2022-05-06 21:29:11,916 INFO [train.py:715] (5/8) Epoch 10, batch 21950, loss[loss=0.1266, simple_loss=0.1983, pruned_loss=0.0275, over 4817.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03284, over 970395.56 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:29:53,131 INFO [train.py:715] (5/8) Epoch 10, batch 22000, loss[loss=0.1284, simple_loss=0.2068, pruned_loss=0.02501, over 4954.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03341, over 971889.00 frames.], batch size: 23, lr: 2.12e-04
2022-05-06 21:30:33,463 INFO [train.py:715] (5/8) Epoch 10, batch 22050, loss[loss=0.1387, simple_loss=0.2152, pruned_loss=0.03107, over 4910.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03302, over 971123.04 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:31:14,082 INFO [train.py:715] (5/8) Epoch 10, batch 22100, loss[loss=0.1153, simple_loss=0.1788, pruned_loss=0.02592, over 4770.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03277, over 970967.26 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:31:54,943 INFO [train.py:715] (5/8) Epoch 10, batch 22150, loss[loss=0.1455, simple_loss=0.2106, pruned_loss=0.04022, over 4771.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03362, over 971032.39 frames.], batch size: 17, lr: 2.12e-04
2022-05-06 21:32:35,991 INFO [train.py:715] (5/8) Epoch 10, batch 22200, loss[loss=0.1284, simple_loss=0.2047, pruned_loss=0.02601, over 4823.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03354, over 970407.40 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:33:16,083 INFO [train.py:715] (5/8) Epoch 10, batch 22250, loss[loss=0.1622, simple_loss=0.2329, pruned_loss=0.04572, over 4855.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.0337, over 970759.51 frames.], batch size: 20, lr: 2.12e-04
2022-05-06 21:33:56,741 INFO [train.py:715] (5/8) Epoch 10, batch 22300, loss[loss=0.1342, simple_loss=0.2059, pruned_loss=0.03128, over 4915.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2128, pruned_loss=0.03384, over 971406.64 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:34:37,775 INFO [train.py:715] (5/8) Epoch 10, batch 22350, loss[loss=0.1263, simple_loss=0.1987, pruned_loss=0.02691, over 4742.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03368, over 971119.47 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:35:17,620 INFO [train.py:715] (5/8) Epoch 10, batch 22400, loss[loss=0.1164, simple_loss=0.1877, pruned_loss=0.02258, over 4792.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03403, over 970421.33 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:35:56,790 INFO [train.py:715] (5/8) Epoch 10, batch 22450, loss[loss=0.1477, simple_loss=0.2112, pruned_loss=0.04206, over 4773.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03445, over 971797.42 frames.], batch size: 17, lr: 2.12e-04
2022-05-06 21:36:36,739 INFO [train.py:715] (5/8) Epoch 10, batch 22500, loss[loss=0.1305, simple_loss=0.1962, pruned_loss=0.03237, over 4872.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03381, over 972354.21 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:37:17,614 INFO [train.py:715] (5/8) Epoch 10, batch 22550, loss[loss=0.1196, simple_loss=0.194, pruned_loss=0.02263, over 4821.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03345, over 972882.09 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:37:56,430 INFO [train.py:715] (5/8) Epoch 10, batch 22600, loss[loss=0.176, simple_loss=0.2367, pruned_loss=0.05759, over 4841.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03362, over 972036.99 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:38:37,512 INFO [train.py:715] (5/8) Epoch 10, batch 22650, loss[loss=0.1232, simple_loss=0.1921, pruned_loss=0.02719, over 4922.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03348, over 972205.74 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:39:19,365 INFO [train.py:715] (5/8) Epoch 10, batch 22700, loss[loss=0.1684, simple_loss=0.2309, pruned_loss=0.05297, over 4855.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03349, over 971840.29 frames.], batch size: 30, lr: 2.12e-04
2022-05-06 21:40:00,099 INFO [train.py:715] (5/8) Epoch 10, batch 22750, loss[loss=0.1312, simple_loss=0.2027, pruned_loss=0.02982, over 4971.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03395, over 972024.71 frames.], batch size: 31, lr: 2.12e-04
2022-05-06 21:40:41,327 INFO [train.py:715] (5/8) Epoch 10, batch 22800, loss[loss=0.169, simple_loss=0.2355, pruned_loss=0.05131, over 4907.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2146, pruned_loss=0.03398, over 972434.28 frames.], batch size: 39, lr: 2.12e-04
2022-05-06 21:41:22,877 INFO [train.py:715] (5/8) Epoch 10, batch 22850, loss[loss=0.1245, simple_loss=0.1927, pruned_loss=0.02814, over 4763.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03367, over 972287.62 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:42:04,581 INFO [train.py:715] (5/8) Epoch 10, batch 22900, loss[loss=0.1122, simple_loss=0.1803, pruned_loss=0.02206, over 4774.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03348, over 971754.91 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:42:45,051 INFO [train.py:715] (5/8) Epoch 10, batch 22950, loss[loss=0.1525, simple_loss=0.2323, pruned_loss=0.03636, over 4833.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03301, over 971438.06 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:43:27,077 INFO [train.py:715] (5/8) Epoch 10, batch 23000, loss[loss=0.1528, simple_loss=0.2213, pruned_loss=0.04217, over 4840.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03275, over 971689.27 frames.], batch size: 30, lr: 2.12e-04
2022-05-06 21:44:09,138 INFO [train.py:715] (5/8) Epoch 10, batch 23050, loss[loss=0.1194, simple_loss=0.1962, pruned_loss=0.02134, over 4900.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03317, over 972083.10 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:44:49,656 INFO [train.py:715] (5/8) Epoch 10, batch 23100, loss[loss=0.1255, simple_loss=0.2016, pruned_loss=0.02469, over 4985.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.0332, over 972533.12 frames.], batch size: 28, lr: 2.12e-04
2022-05-06 21:45:30,869 INFO [train.py:715] (5/8) Epoch 10, batch 23150, loss[loss=0.1942, simple_loss=0.263, pruned_loss=0.06268, over 4787.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03346, over 972051.95 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 21:46:12,874 INFO [train.py:715] (5/8) Epoch 10, batch 23200, loss[loss=0.1333, simple_loss=0.2053, pruned_loss=0.03068, over 4840.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03335, over 971661.14 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:46:54,161 INFO [train.py:715] (5/8) Epoch 10, batch 23250, loss[loss=0.1593, simple_loss=0.2174, pruned_loss=0.05058, over 4979.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03388, over 972037.10 frames.], batch size: 35, lr: 2.12e-04
2022-05-06 21:47:34,833 INFO [train.py:715] (5/8) Epoch 10, batch 23300, loss[loss=0.1276, simple_loss=0.193, pruned_loss=0.03108, over 4908.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03412, over 971682.67 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:48:16,723 INFO [train.py:715] (5/8) Epoch 10, batch 23350, loss[loss=0.1199, simple_loss=0.2019, pruned_loss=0.01895, over 4982.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03392, over 972331.32 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:48:58,860 INFO [train.py:715] (5/8) Epoch 10, batch 23400, loss[loss=0.1392, simple_loss=0.2131, pruned_loss=0.03265, over 4932.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03327, over 972813.87 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:49:39,771 INFO [train.py:715] (5/8) Epoch 10, batch 23450, loss[loss=0.1445, simple_loss=0.2206, pruned_loss=0.03424, over 4806.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03358, over 972642.69 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 21:50:20,133 INFO [train.py:715] (5/8) Epoch 10, batch 23500, loss[loss=0.1391, simple_loss=0.2161, pruned_loss=0.03104, over 4866.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03384, over 972375.22 frames.], batch size: 13, lr: 2.12e-04
2022-05-06 21:51:02,209 INFO [train.py:715] (5/8) Epoch 10, batch 23550, loss[loss=0.132, simple_loss=0.2098, pruned_loss=0.02709, over 4872.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03355, over 972017.93 frames.], batch size: 38, lr: 2.12e-04
2022-05-06 21:51:43,362 INFO [train.py:715] (5/8) Epoch 10, batch 23600, loss[loss=0.1151, simple_loss=0.1974, pruned_loss=0.01638, over 4908.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.0333, over 971536.32 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:52:23,126 INFO [train.py:715] (5/8) Epoch 10, batch 23650, loss[loss=0.1532, simple_loss=0.215, pruned_loss=0.0457, over 4864.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03317, over 972074.11 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 21:53:03,659 INFO [train.py:715] (5/8) Epoch 10, batch 23700, loss[loss=0.1546, simple_loss=0.2197, pruned_loss=0.04468, over 4911.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03356, over 970890.90 frames.], batch size: 38, lr: 2.12e-04
2022-05-06 21:53:44,223 INFO [train.py:715] (5/8) Epoch 10, batch 23750, loss[loss=0.1237, simple_loss=0.2014, pruned_loss=0.02297, over 4911.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03331, over 971316.03 frames.], batch size: 17, lr: 2.12e-04
2022-05-06 21:54:24,360 INFO [train.py:715] (5/8) Epoch 10, batch 23800, loss[loss=0.1318, simple_loss=0.2069, pruned_loss=0.02841, over 4959.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03308, over 971473.93 frames.], batch size: 24, lr: 2.12e-04
2022-05-06 21:55:04,949 INFO [train.py:715] (5/8) Epoch 10, batch 23850, loss[loss=0.1489, simple_loss=0.2102, pruned_loss=0.04378, over 4860.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03333, over 971910.21 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:55:46,221 INFO [train.py:715] (5/8) Epoch 10, batch 23900, loss[loss=0.1264, simple_loss=0.2043, pruned_loss=0.02429, over 4986.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03399, over 972060.72 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:56:25,855 INFO [train.py:715] (5/8) Epoch 10, batch 23950, loss[loss=0.1531, simple_loss=0.2447, pruned_loss=0.03072, over 4849.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03398, over 971617.47 frames.], batch size: 20, lr: 2.12e-04
2022-05-06 21:57:06,221 INFO [train.py:715] (5/8) Epoch 10, batch 24000, loss[loss=0.1763, simple_loss=0.2371, pruned_loss=0.05771, over 4813.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03395, over 972386.44 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:57:06,222 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 21:57:15,893 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1061, simple_loss=0.1905, pruned_loss=0.01087, over 914524.00 frames.
2022-05-06 21:57:55,805 INFO [train.py:715] (5/8) Epoch 10, batch 24050, loss[loss=0.1402, simple_loss=0.221, pruned_loss=0.02974, over 4793.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03364, over 971851.48 frames.], batch size: 17, lr: 2.12e-04
2022-05-06 21:58:36,848 INFO [train.py:715] (5/8) Epoch 10, batch 24100, loss[loss=0.09983, simple_loss=0.1761, pruned_loss=0.01178, over 4803.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03376, over 972377.08 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:59:18,108 INFO [train.py:715] (5/8) Epoch 10, batch 24150, loss[loss=0.1459, simple_loss=0.2115, pruned_loss=0.0401, over 4895.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03435, over 972535.06 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 21:59:57,435 INFO [train.py:715] (5/8) Epoch 10, batch 24200, loss[loss=0.1239, simple_loss=0.1989, pruned_loss=0.02443, over 4861.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2118, pruned_loss=0.03355, over 971950.16 frames.], batch size: 20, lr: 2.12e-04
2022-05-06 22:00:38,181 INFO [train.py:715] (5/8) Epoch 10, batch 24250, loss[loss=0.1355, simple_loss=0.2151, pruned_loss=0.02796, over 4806.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03376, over 972440.37 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 22:01:19,301 INFO [train.py:715] (5/8) Epoch 10, batch 24300, loss[loss=0.1333, simple_loss=0.2116, pruned_loss=0.02751, over 4804.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03361, over 971614.76 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 22:01:59,414 INFO [train.py:715] (5/8) Epoch 10, batch 24350, loss[loss=0.1277, simple_loss=0.1999, pruned_loss=0.02771, over 4937.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03275, over 972058.72 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 22:02:39,458 INFO [train.py:715] (5/8) Epoch 10, batch 24400, loss[loss=0.1656, simple_loss=0.2303, pruned_loss=0.05046, over 4967.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03306, over 973077.59 frames.], batch size: 28, lr: 2.12e-04
2022-05-06 22:03:20,173 INFO [train.py:715] (5/8) Epoch 10, batch 24450, loss[loss=0.1592, simple_loss=0.2274, pruned_loss=0.04552, over 4936.00 frames.], tot_loss[loss=0.139, simple_loss=0.2116, pruned_loss=0.0332, over 973321.31 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 22:04:01,144 INFO [train.py:715] (5/8) Epoch 10, batch 24500, loss[loss=0.1409, simple_loss=0.213, pruned_loss=0.0344, over 4951.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03375, over 973307.82 frames.], batch size: 24, lr: 2.12e-04
2022-05-06 22:04:40,221 INFO [train.py:715] (5/8) Epoch 10, batch 24550, loss[loss=0.1333, simple_loss=0.2118, pruned_loss=0.02737, over 4868.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03368, over 973927.03 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 22:05:20,206 INFO [train.py:715] (5/8) Epoch 10, batch 24600, loss[loss=0.1097, simple_loss=0.1799, pruned_loss=0.01978, over 4872.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2125, pruned_loss=0.03392, over 974430.23 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 22:06:00,577 INFO [train.py:715] (5/8) Epoch 10, batch 24650, loss[loss=0.1112, simple_loss=0.1886, pruned_loss=0.01683, over 4819.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03332, over 973427.20 frames.], batch size: 27, lr: 2.12e-04
2022-05-06 22:06:39,584 INFO [train.py:715] (5/8) Epoch 10, batch 24700, loss[loss=0.1324, simple_loss=0.204, pruned_loss=0.03041, over 4977.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03363, over 972491.75 frames.], batch size: 39, lr: 2.12e-04
2022-05-06 22:07:18,185 INFO [train.py:715] (5/8) Epoch 10, batch 24750, loss[loss=0.1339, simple_loss=0.217, pruned_loss=0.02542, over 4858.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03367, over 973174.07 frames.], batch size: 20, lr: 2.12e-04
2022-05-06 22:07:57,673 INFO [train.py:715] (5/8) Epoch 10, batch 24800, loss[loss=0.1078, simple_loss=0.1822, pruned_loss=0.01672, over 4832.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03353, over 972618.89 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 22:08:36,820 INFO [train.py:715] (5/8) Epoch 10, batch 24850, loss[loss=0.182, simple_loss=0.2526, pruned_loss=0.05568, over 4859.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03389, over 972733.82 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 22:09:14,894 INFO [train.py:715] (5/8) Epoch 10, batch 24900, loss[loss=0.1397, simple_loss=0.2089, pruned_loss=0.03525, over 4881.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03329, over 972823.49 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 22:09:54,523 INFO [train.py:715] (5/8) Epoch 10, batch 24950, loss[loss=0.1329, simple_loss=0.21, pruned_loss=0.0279, over 4995.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03302, over 972515.81 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 22:10:34,373 INFO [train.py:715] (5/8) Epoch 10, batch 25000, loss[loss=0.1677, simple_loss=0.2317, pruned_loss=0.05188, over 4773.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03328, over 972673.53 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 22:11:13,225 INFO [train.py:715] (5/8) Epoch 10, batch 25050, loss[loss=0.1417, simple_loss=0.2073, pruned_loss=0.03802, over 4870.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03326, over 972593.66 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 22:11:52,695 INFO [train.py:715] (5/8) Epoch 10, batch 25100, loss[loss=0.1027, simple_loss=0.1659, pruned_loss=0.01978, over 4770.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.0327, over 972968.78 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 22:12:32,717 INFO [train.py:715] (5/8) Epoch 10, batch 25150, loss[loss=0.1377, simple_loss=0.2151, pruned_loss=0.03016, over 4803.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03246, over 972895.00 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 22:13:12,208 INFO [train.py:715] (5/8) Epoch 10, batch 25200, loss[loss=0.1144, simple_loss=0.192, pruned_loss=0.01836, over 4867.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03306, over 973186.06 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 22:13:50,342 INFO [train.py:715] (5/8) Epoch 10, batch 25250, loss[loss=0.1252, simple_loss=0.1976, pruned_loss=0.02644, over 4776.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03302, over 972819.47 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 22:14:29,217 INFO [train.py:715] (5/8) Epoch 10, batch 25300, loss[loss=0.1028, simple_loss=0.1733, pruned_loss=0.01618, over 4934.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03318, over 973955.91 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 22:15:08,861 INFO [train.py:715] (5/8) Epoch 10, batch 25350, loss[loss=0.1469, simple_loss=0.2334, pruned_loss=0.03014, over 4803.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03277, over 973037.30 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 22:15:47,379 INFO [train.py:715] (5/8) Epoch 10, batch 25400, loss[loss=0.1358, simple_loss=0.2131, pruned_loss=0.02923, over 4876.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03274, over 972270.41 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 22:16:26,236 INFO [train.py:715] (5/8) Epoch 10, batch 25450, loss[loss=0.1559, simple_loss=0.2185, pruned_loss=0.04664, over 4854.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03296, over 971983.85 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 22:17:06,159 INFO [train.py:715] (5/8) Epoch 10, batch 25500, loss[loss=0.1283, simple_loss=0.2, pruned_loss=0.02832, over 4753.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03286, over 971642.66 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:17:45,979 INFO [train.py:715] (5/8) Epoch 10, batch 25550, loss[loss=0.1444, simple_loss=0.2143, pruned_loss=0.03727, over 4880.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03306, over 972157.31 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:18:24,958 INFO [train.py:715] (5/8) Epoch 10, batch 25600, loss[loss=0.152, simple_loss=0.2285, pruned_loss=0.03776, over 4984.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03312, over 973058.04 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 22:19:05,110 INFO [train.py:715] (5/8) Epoch 10, batch 25650, loss[loss=0.1221, simple_loss=0.1917, pruned_loss=0.02625, over 4827.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.03346, over 972488.53 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:19:45,485 INFO [train.py:715] (5/8) Epoch 10, batch 25700, loss[loss=0.1244, simple_loss=0.1893, pruned_loss=0.02978, over 4733.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03388, over 972764.82 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:20:25,349 INFO [train.py:715] (5/8) Epoch 10, batch 25750, loss[loss=0.1294, simple_loss=0.1986, pruned_loss=0.03011, over 4754.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2143, pruned_loss=0.03364, over 972419.62 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:21:04,757 INFO [train.py:715] (5/8) Epoch 10, batch 25800, loss[loss=0.1276, simple_loss=0.2029, pruned_loss=0.02614, over 4782.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03367, over 972043.11 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:21:45,291 INFO [train.py:715] (5/8) Epoch 10, batch 25850, loss[loss=0.1408, simple_loss=0.2117, pruned_loss=0.03494, over 4780.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2139, pruned_loss=0.0332, over 971293.90 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:22:25,222 INFO [train.py:715] (5/8) Epoch 10, batch 25900, loss[loss=0.1237, simple_loss=0.1945, pruned_loss=0.02647, over 4908.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.03314, over 972302.47 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:23:03,942 INFO [train.py:715] (5/8) Epoch 10, batch 25950, loss[loss=0.132, simple_loss=0.215, pruned_loss=0.02454, over 4807.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03304, over 971244.51 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:23:42,717 INFO [train.py:715] (5/8) Epoch 10, batch 26000, loss[loss=0.1228, simple_loss=0.1952, pruned_loss=0.02515, over 4821.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03336, over 971129.54 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:24:21,987 INFO [train.py:715] (5/8) Epoch 10, batch 26050, loss[loss=0.1341, simple_loss=0.204, pruned_loss=0.03214, over 4925.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.0335, over 970732.29 frames.], batch size: 29, lr: 2.11e-04
2022-05-06 22:25:00,974 INFO [train.py:715] (5/8) Epoch 10, batch 26100, loss[loss=0.1157, simple_loss=0.183, pruned_loss=0.02422, over 4852.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03339, over 971749.02 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 22:25:40,338 INFO [train.py:715] (5/8) Epoch 10, batch 26150, loss[loss=0.1358, simple_loss=0.2045, pruned_loss=0.03356, over 4912.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03336, over 972558.16 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:26:21,097 INFO [train.py:715] (5/8) Epoch 10, batch 26200, loss[loss=0.1135, simple_loss=0.1881, pruned_loss=0.0195, over 4814.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03264, over 972832.36 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:27:00,350 INFO [train.py:715] (5/8) Epoch 10, batch 26250, loss[loss=0.1361, simple_loss=0.2186, pruned_loss=0.02684, over 4934.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2107, pruned_loss=0.03284, over 972651.87 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:27:40,000 INFO [train.py:715] (5/8) Epoch 10, batch 26300, loss[loss=0.1622, simple_loss=0.2252, pruned_loss=0.04966, over 4949.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2108, pruned_loss=0.0332, over 972239.93 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:28:19,566 INFO [train.py:715] (5/8) Epoch 10, batch 26350, loss[loss=0.1245, simple_loss=0.1953, pruned_loss=0.02685, over 4819.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2113, pruned_loss=0.03326, over 971957.57 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:28:59,165 INFO [train.py:715] (5/8) Epoch 10, batch 26400, loss[loss=0.1438, simple_loss=0.2124, pruned_loss=0.03761, over 4645.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2106, pruned_loss=0.03278, over 972595.26 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:29:38,869 INFO [train.py:715] (5/8) Epoch 10, batch 26450, loss[loss=0.1872, simple_loss=0.2445, pruned_loss=0.06497, over 4891.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2107, pruned_loss=0.03309, over 972160.22 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:30:18,683 INFO [train.py:715] (5/8) Epoch 10, batch 26500, loss[loss=0.1285, simple_loss=0.1988, pruned_loss=0.02909, over 4979.00 frames.], tot_loss[loss=0.1386, simple_loss=0.211, pruned_loss=0.03308, over 971982.05 frames.], batch size: 28, lr: 2.11e-04
2022-05-06 22:30:59,097 INFO [train.py:715] (5/8) Epoch 10, batch 26550, loss[loss=0.159, simple_loss=0.2311, pruned_loss=0.04349, over 4892.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03338, over 972681.90 frames.], batch size: 22, lr: 2.11e-04
2022-05-06 22:31:37,639 INFO [train.py:715] (5/8) Epoch 10, batch 26600, loss[loss=0.1248, simple_loss=0.1918, pruned_loss=0.02888, over 4794.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2118, pruned_loss=0.03357, over 971469.25 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:32:17,160 INFO [train.py:715] (5/8) Epoch 10, batch 26650, loss[loss=0.1467, simple_loss=0.225, pruned_loss=0.03418, over 4902.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2122, pruned_loss=0.03394, over 972113.27 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:32:56,672 INFO [train.py:715] (5/8) Epoch 10, batch 26700, loss[loss=0.1257, simple_loss=0.1954, pruned_loss=0.02798, over 4945.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2119, pruned_loss=0.0336, over 972483.99 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:33:36,176 INFO [train.py:715] (5/8) Epoch 10, batch 26750, loss[loss=0.131, simple_loss=0.2066, pruned_loss=0.02766, over 4904.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03348, over 972516.26 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:34:14,862 INFO [train.py:715] (5/8) Epoch 10, batch 26800, loss[loss=0.1374, simple_loss=0.2217, pruned_loss=0.02651, over 4955.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03366, over 971892.46 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:34:54,618 INFO [train.py:715] (5/8) Epoch 10, batch 26850, loss[loss=0.1369, simple_loss=0.209, pruned_loss=0.03244, over 4809.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 972858.17 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:35:34,125 INFO [train.py:715] (5/8) Epoch 10, batch 26900, loss[loss=0.1409, simple_loss=0.2048, pruned_loss=0.03851, over 4983.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03372, over 973020.38 frames.], batch size: 28, lr: 2.11e-04
2022-05-06 22:36:12,942 INFO [train.py:715] (5/8) Epoch 10, batch 26950, loss[loss=0.1392, simple_loss=0.2032, pruned_loss=0.03756, over 4653.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03369, over 973189.37 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:36:51,894 INFO [train.py:715] (5/8) Epoch 10, batch 27000, loss[loss=0.1513, simple_loss=0.2314, pruned_loss=0.03561, over 4891.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03358, over 973314.55 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:36:51,894 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 22:37:01,643 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
2022-05-06 22:37:41,074 INFO [train.py:715] (5/8) Epoch 10, batch 27050, loss[loss=0.1408, simple_loss=0.2064, pruned_loss=0.03755, over 4759.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03357, over 973773.32 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:38:21,002 INFO [train.py:715] (5/8) Epoch 10, batch 27100, loss[loss=0.1463, simple_loss=0.2088, pruned_loss=0.04191, over 4952.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03343, over 973073.96 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:38:59,617 INFO [train.py:715] (5/8) Epoch 10, batch 27150, loss[loss=0.1467, simple_loss=0.2121, pruned_loss=0.04068, over 4908.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03362, over 972509.45 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:39:38,786 INFO [train.py:715] (5/8) Epoch 10, batch 27200, loss[loss=0.1335, simple_loss=0.1981, pruned_loss=0.03449, over 4863.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03329, over 972119.36 frames.], batch size: 32, lr: 2.11e-04
2022-05-06 22:40:18,814 INFO [train.py:715] (5/8) Epoch 10, batch 27250, loss[loss=0.1198, simple_loss=0.1982, pruned_loss=0.02067, over 4807.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03287, over 971508.80 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:40:58,234 INFO [train.py:715] (5/8) Epoch 10, batch 27300, loss[loss=0.1463, simple_loss=0.2263, pruned_loss=0.03316, over 4807.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03314, over 971498.84 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:41:36,434 INFO [train.py:715] (5/8) Epoch 10, batch 27350, loss[loss=0.1621, simple_loss=0.2245, pruned_loss=0.04986, over 4776.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.0329, over 971833.79 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:42:15,730 INFO [train.py:715] (5/8) Epoch 10, batch 27400, loss[loss=0.1633, simple_loss=0.2332, pruned_loss=0.04669, over 4839.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03271, over 971376.05 frames.], batch size: 30, lr: 2.11e-04
2022-05-06 22:42:55,895 INFO [train.py:715] (5/8) Epoch 10, batch 27450, loss[loss=0.1332, simple_loss=0.2108, pruned_loss=0.02778, over 4938.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03304, over 971583.92 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 22:43:34,162 INFO [train.py:715] (5/8) Epoch 10, batch 27500, loss[loss=0.143, simple_loss=0.2164, pruned_loss=0.03482, over 4977.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03281, over 972358.39 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:44:13,413 INFO [train.py:715] (5/8) Epoch 10, batch 27550, loss[loss=0.1557, simple_loss=0.2274, pruned_loss=0.04205, over 4910.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.0335, over 973320.48 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:44:52,782 INFO [train.py:715] (5/8) Epoch 10, batch 27600, loss[loss=0.1311, simple_loss=0.2064, pruned_loss=0.02785, over 4847.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03332, over 973345.53 frames.], batch size: 32, lr: 2.11e-04
2022-05-06 22:45:32,112 INFO [train.py:715] (5/8) Epoch 10, batch 27650, loss[loss=0.1831, simple_loss=0.2512, pruned_loss=0.05753, over 4880.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03303, over 974107.95 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 22:46:11,031 INFO [train.py:715] (5/8) Epoch 10, batch 27700, loss[loss=0.1273, simple_loss=0.1949, pruned_loss=0.02983, over 4754.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03283, over 972659.83 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:46:51,027 INFO [train.py:715] (5/8) Epoch 10, batch 27750, loss[loss=0.1151, simple_loss=0.1822, pruned_loss=0.02399, over 4822.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03264, over 972382.91 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:47:31,100 INFO [train.py:715] (5/8) Epoch 10, batch 27800, loss[loss=0.1055, simple_loss=0.1778, pruned_loss=0.01663, over 4911.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.0325, over 972490.16 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:48:10,305 INFO [train.py:715] (5/8) Epoch 10, batch 27850, loss[loss=0.1703, simple_loss=0.2546, pruned_loss=0.04301, over 4950.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03237, over 972432.63 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:48:50,677 INFO [train.py:715] (5/8) Epoch 10, batch 27900, loss[loss=0.118, simple_loss=0.1937, pruned_loss=0.02114, over 4785.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03251, over 971141.26 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:49:34,037 INFO [train.py:715] (5/8) Epoch 10, batch 27950, loss[loss=0.1432, simple_loss=0.2067, pruned_loss=0.03984, over 4856.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03237, over 971057.76 frames.], batch size: 30, lr: 2.11e-04
2022-05-06 22:50:13,531 INFO [train.py:715] (5/8) Epoch 10, batch 28000, loss[loss=0.1331, simple_loss=0.2039, pruned_loss=0.03115, over 4924.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03296, over 971770.17 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 22:50:53,592 INFO [train.py:715] (5/8) Epoch 10, batch 28050, loss[loss=0.1366, simple_loss=0.2047, pruned_loss=0.03424, over 4854.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03325, over 971135.39 frames.], batch size: 30, lr: 2.11e-04
2022-05-06 22:51:34,464 INFO [train.py:715] (5/8) Epoch 10, batch 28100, loss[loss=0.1235, simple_loss=0.2007, pruned_loss=0.02315, over 4935.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03318, over 971790.84 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 22:52:15,139 INFO [train.py:715] (5/8) Epoch 10, batch 28150, loss[loss=0.1457, simple_loss=0.2271, pruned_loss=0.03213, over 4797.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03346, over 971934.17 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:52:54,868 INFO [train.py:715] (5/8) Epoch 10, batch 28200, loss[loss=0.1455, simple_loss=0.2188, pruned_loss=0.03609, over 4775.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03358, over 971468.07 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:53:35,214 INFO [train.py:715] (5/8) Epoch 10, batch 28250, loss[loss=0.1387, simple_loss=0.2152, pruned_loss=0.03114, over 4841.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03385, over 971864.42 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:54:16,801 INFO [train.py:715] (5/8) Epoch 10, batch 28300, loss[loss=0.1346, simple_loss=0.2037, pruned_loss=0.03281, over 4984.00 frames.], tot_loss[loss=0.141, simple_loss=0.2142, pruned_loss=0.03393, over 971646.50 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:54:56,903 INFO [train.py:715] (5/8) Epoch 10, batch 28350, loss[loss=0.1276, simple_loss=0.2004, pruned_loss=0.02741, over 4919.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.0346, over 971963.80 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:55:37,452 INFO [train.py:715] (5/8) Epoch 10, batch 28400, loss[loss=0.1356, simple_loss=0.2042, pruned_loss=0.03345, over 4875.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03486, over 972058.54 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:56:19,123 INFO [train.py:715] (5/8) Epoch 10, batch 28450, loss[loss=0.115, simple_loss=0.1808, pruned_loss=0.02462, over 4784.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03431, over 971890.02 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:57:00,138 INFO [train.py:715] (5/8) Epoch 10, batch 28500, loss[loss=0.1285, simple_loss=0.2011, pruned_loss=0.02795, over 4989.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2128, pruned_loss=0.03391, over 972475.27 frames.], batch size: 26, lr: 2.11e-04
2022-05-06 22:57:40,544 INFO [train.py:715] (5/8) Epoch 10, batch 28550, loss[loss=0.1683, simple_loss=0.2419, pruned_loss=0.0474, over 4847.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03418, over 972491.57 frames.], batch size: 34, lr: 2.11e-04
2022-05-06 22:58:21,442 INFO [train.py:715] (5/8) Epoch 10, batch 28600, loss[loss=0.1418, simple_loss=0.2151, pruned_loss=0.03418, over 4820.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03405, over 972175.62 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:59:03,591 INFO [train.py:715] (5/8) Epoch 10, batch 28650, loss[loss=0.1296, simple_loss=0.208, pruned_loss=0.02561, over 4819.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03395, over 972448.33 frames.], batch size: 27, lr: 2.11e-04
2022-05-06 22:59:43,741 INFO [train.py:715] (5/8) Epoch 10, batch 28700, loss[loss=0.1145, simple_loss=0.1953, pruned_loss=0.01689, over 4823.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03364, over 972688.07 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 23:00:24,814 INFO [train.py:715] (5/8) Epoch 10, batch 28750, loss[loss=0.1303, simple_loss=0.2046, pruned_loss=0.02797, over 4877.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03329, over 971365.22 frames.], batch size: 32, lr: 2.11e-04
2022-05-06 23:01:05,929 INFO [train.py:715] (5/8) Epoch 10, batch 28800, loss[loss=0.118, simple_loss=0.1935, pruned_loss=0.02126, over 4881.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03305, over 970396.67 frames.], batch size: 22, lr: 2.11e-04
2022-05-06 23:01:46,831 INFO [train.py:715] (5/8) Epoch 10, batch 28850, loss[loss=0.1654, simple_loss=0.2401, pruned_loss=0.04535, over 4938.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03297, over 970513.25 frames.], batch size: 39, lr: 2.11e-04
2022-05-06 23:02:27,345 INFO [train.py:715] (5/8) Epoch 10, batch 28900, loss[loss=0.1313, simple_loss=0.2069, pruned_loss=0.02782, over 4745.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03339, over 971429.23 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 23:03:08,206 INFO [train.py:715] (5/8) Epoch 10, batch 28950, loss[loss=0.1633, simple_loss=0.2336, pruned_loss=0.04654, over 4917.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03362, over 972349.77 frames.], batch size: 39, lr: 2.11e-04
2022-05-06 23:03:49,284 INFO [train.py:715] (5/8) Epoch 10, batch 29000, loss[loss=0.1509, simple_loss=0.2077, pruned_loss=0.04706, over 4855.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03363, over 972126.25 frames.], batch size: 30, lr: 2.11e-04
2022-05-06 23:04:28,427 INFO [train.py:715] (5/8) Epoch 10, batch 29050, loss[loss=0.1684, simple_loss=0.2448, pruned_loss=0.04598, over 4844.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03356, over 972400.44 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:05:07,299 INFO [train.py:715] (5/8) Epoch 10, batch 29100, loss[loss=0.1369, simple_loss=0.2185, pruned_loss=0.02766, over 4922.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03365, over 972667.16 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:05:47,480 INFO [train.py:715] (5/8) Epoch 10, batch 29150, loss[loss=0.1249, simple_loss=0.1935, pruned_loss=0.02817, over 4805.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03323, over 972726.60 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:06:27,774 INFO [train.py:715] (5/8) Epoch 10, batch 29200, loss[loss=0.1353, simple_loss=0.2113, pruned_loss=0.02967, over 4911.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03355, over 972784.02 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:07:06,674 INFO [train.py:715] (5/8) Epoch 10, batch 29250, loss[loss=0.1117, simple_loss=0.1982, pruned_loss=0.01258, over 4850.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03325, over 971893.46 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:07:46,921 INFO [train.py:715] (5/8) Epoch 10, batch 29300, loss[loss=0.1474, simple_loss=0.2265, pruned_loss=0.03416, over 4797.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03294, over 971874.04 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:08:27,017 INFO [train.py:715] (5/8) Epoch 10, batch 29350, loss[loss=0.1301, simple_loss=0.2072, pruned_loss=0.02651, over 4934.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03286, over 971987.92 frames.], batch size: 29, lr: 2.10e-04
2022-05-06 23:09:06,021 INFO [train.py:715] (5/8) Epoch 10, batch 29400, loss[loss=0.1054, simple_loss=0.1748, pruned_loss=0.01806, over 4838.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03281, over 971540.88 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:09:45,802 INFO [train.py:715] (5/8) Epoch 10, batch 29450, loss[loss=0.1516, simple_loss=0.2162, pruned_loss=0.04354, over 4833.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03279, over 971324.00 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:10:26,003 INFO [train.py:715] (5/8) Epoch 10, batch 29500, loss[loss=0.1462, simple_loss=0.2154, pruned_loss=0.03854, over 4854.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.03359, over 970861.79 frames.], batch size: 34, lr: 2.10e-04
2022-05-06 23:11:05,703 INFO [train.py:715] (5/8) Epoch 10, batch 29550, loss[loss=0.1457, simple_loss=0.2182, pruned_loss=0.03665, over 4838.00 frames.], tot_loss[loss=0.1395, simple_loss=0.212, pruned_loss=0.03344, over 970767.76 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:11:44,342 INFO [train.py:715] (5/8) Epoch 10, batch 29600, loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02995, over 4743.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03412, over 970765.95 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:12:24,000 INFO [train.py:715] (5/8) Epoch 10, batch 29650, loss[loss=0.1925, simple_loss=0.2475, pruned_loss=0.06879, over 4842.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03352, over 970336.40 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:13:03,435 INFO [train.py:715] (5/8) Epoch 10, batch 29700, loss[loss=0.1372, simple_loss=0.2136, pruned_loss=0.03043, over 4976.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03351, over 970879.64 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:13:42,105 INFO [train.py:715] (5/8) Epoch 10, batch 29750, loss[loss=0.1363, simple_loss=0.2148, pruned_loss=0.02891, over 4807.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03362, over 970629.88 frames.], batch size: 25, lr: 2.10e-04
2022-05-06 23:14:21,081 INFO [train.py:715] (5/8) Epoch 10, batch 29800, loss[loss=0.1578, simple_loss=0.2213, pruned_loss=0.04715, over 4865.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03395, over 970209.15 frames.], batch size: 20, lr: 2.10e-04
2022-05-06 23:15:00,554 INFO [train.py:715] (5/8) Epoch 10, batch 29850, loss[loss=0.1612, simple_loss=0.2358, pruned_loss=0.04325, over 4834.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03399, over 970740.16 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:15:39,438 INFO [train.py:715] (5/8) Epoch 10, batch 29900, loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.0343, over 4870.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03373, over 971354.83 frames.], batch size: 32, lr: 2.10e-04
2022-05-06 23:16:17,893 INFO [train.py:715] (5/8) Epoch 10, batch 29950, loss[loss=0.1825, simple_loss=0.252, pruned_loss=0.05654, over 4847.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03394, over 971901.15 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:16:57,114 INFO [train.py:715] (5/8) Epoch 10, batch 30000, loss[loss=0.1285, simple_loss=0.2025, pruned_loss=0.02731, over 4941.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03365, over 971177.88 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:16:57,115 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 23:17:06,541 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01106, over 914524.00 frames.
2022-05-06 23:17:46,311 INFO [train.py:715] (5/8) Epoch 10, batch 30050, loss[loss=0.152, simple_loss=0.2169, pruned_loss=0.04351, over 4689.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03356, over 971711.55 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:18:25,802 INFO [train.py:715] (5/8) Epoch 10, batch 30100, loss[loss=0.1127, simple_loss=0.1895, pruned_loss=0.01794, over 4758.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03349, over 971307.25 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:19:04,198 INFO [train.py:715] (5/8) Epoch 10, batch 30150, loss[loss=0.1465, simple_loss=0.2185, pruned_loss=0.03722, over 4846.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03358, over 971740.12 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:19:44,547 INFO [train.py:715] (5/8) Epoch 10, batch 30200, loss[loss=0.1343, simple_loss=0.2054, pruned_loss=0.03158, over 4782.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03335, over 972674.16 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:20:24,570 INFO [train.py:715] (5/8) Epoch 10, batch 30250, loss[loss=0.1221, simple_loss=0.191, pruned_loss=0.02661, over 4941.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03326, over 972644.20 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:21:02,961 INFO [train.py:715] (5/8) Epoch 10, batch 30300, loss[loss=0.1416, simple_loss=0.2076, pruned_loss=0.03776, over 4908.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03328, over 973114.02 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:21:41,377 INFO [train.py:715] (5/8) Epoch 10, batch 30350, loss[loss=0.1317, simple_loss=0.205, pruned_loss=0.02915, over 4849.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2115, pruned_loss=0.03313, over 973050.50 frames.], batch size: 32, lr: 2.10e-04
2022-05-06 23:22:21,181 INFO [train.py:715] (5/8) Epoch 10, batch 30400, loss[loss=0.1428, simple_loss=0.217, pruned_loss=0.03432, over 4763.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03355, over 972770.69 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:23:00,548 INFO [train.py:715] (5/8) Epoch 10, batch 30450, loss[loss=0.1479, simple_loss=0.2165, pruned_loss=0.03961, over 4990.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03404, over 973717.78 frames.], batch size: 28, lr: 2.10e-04
2022-05-06 23:23:38,705 INFO [train.py:715] (5/8) Epoch 10, batch 30500, loss[loss=0.1412, simple_loss=0.2188, pruned_loss=0.0318, over 4814.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03383, over 972770.95 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:24:18,302 INFO [train.py:715] (5/8) Epoch 10, batch 30550, loss[loss=0.1501, simple_loss=0.2108, pruned_loss=0.04465, over 4757.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03357, over 973214.20 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:24:57,943 INFO [train.py:715] (5/8) Epoch 10, batch 30600, loss[loss=0.1219, simple_loss=0.1985, pruned_loss=0.02269, over 4895.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03301, over 973160.07 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:25:36,405 INFO [train.py:715] (5/8) Epoch 10, batch 30650, loss[loss=0.1204, simple_loss=0.1893, pruned_loss=0.0257, over 4802.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.0329, over 972636.26 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:26:15,886 INFO [train.py:715] (5/8) Epoch 10, batch 30700, loss[loss=0.1114, simple_loss=0.1873, pruned_loss=0.01776, over 4924.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2104, pruned_loss=0.03231, over 973066.62 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:26:55,010 INFO [train.py:715] (5/8) Epoch 10, batch 30750, loss[loss=0.143, simple_loss=0.2162, pruned_loss=0.03489, over 4884.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03275, over 974016.06 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:27:33,901 INFO [train.py:715] (5/8) Epoch 10, batch 30800, loss[loss=0.1571, simple_loss=0.2378, pruned_loss=0.0382, over 4790.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03306, over 972778.99 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:28:12,410 INFO [train.py:715] (5/8) Epoch 10, batch 30850, loss[loss=0.1195, simple_loss=0.1897, pruned_loss=0.02463, over 4793.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03316, over 972245.28 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:28:52,163 INFO [train.py:715] (5/8) Epoch 10, batch 30900, loss[loss=0.1404, simple_loss=0.2149, pruned_loss=0.03301, over 4925.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03297, over 972044.88 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:29:32,112 INFO [train.py:715] (5/8) Epoch 10, batch 30950, loss[loss=0.186, simple_loss=0.2349, pruned_loss=0.06848, over 4875.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03304, over 971769.69 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:30:11,646 INFO [train.py:715] (5/8) Epoch 10, batch 31000, loss[loss=0.161, simple_loss=0.2355, pruned_loss=0.04322, over 4849.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2132, pruned_loss=0.03315, over 972343.19 frames.], batch size: 20, lr: 2.10e-04
2022-05-06 23:30:50,341 INFO [train.py:715] (5/8) Epoch 10, batch 31050, loss[loss=0.1425, simple_loss=0.2202, pruned_loss=0.03242, over 4771.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2133, pruned_loss=0.03323, over 972358.75 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:31:29,592 INFO [train.py:715] (5/8) Epoch 10, batch 31100, loss[loss=0.1268, simple_loss=0.203, pruned_loss=0.02526, over 4855.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2138, pruned_loss=0.03374, over 972779.56 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:32:09,326 INFO [train.py:715] (5/8) Epoch 10, batch 31150, loss[loss=0.1603, simple_loss=0.2331, pruned_loss=0.04379, over 4744.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03327, over 972070.10 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:32:47,336 INFO [train.py:715] (5/8) Epoch 10, batch 31200, loss[loss=0.1265, simple_loss=0.1983, pruned_loss=0.02735, over 4851.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03355, over 972612.33 frames.], batch size: 20, lr: 2.10e-04
2022-05-06 23:33:26,826 INFO [train.py:715] (5/8) Epoch 10, batch 31250, loss[loss=0.1251, simple_loss=0.1965, pruned_loss=0.02685, over 4974.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03343, over 972437.70 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:34:06,249 INFO [train.py:715] (5/8) Epoch 10, batch 31300, loss[loss=0.115, simple_loss=0.1935, pruned_loss=0.0182, over 4884.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03405, over 972769.02 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:34:45,237 INFO [train.py:715] (5/8) Epoch 10, batch 31350, loss[loss=0.1556, simple_loss=0.2363, pruned_loss=0.0374, over 4775.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03398, over 971564.30 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:35:23,741 INFO [train.py:715] (5/8) Epoch 10, batch 31400, loss[loss=0.1068, simple_loss=0.184, pruned_loss=0.01482, over 4777.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03391, over 971302.87 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:36:02,749 INFO [train.py:715] (5/8) Epoch 10, batch 31450, loss[loss=0.1566, simple_loss=0.2343, pruned_loss=0.03944, over 4941.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03349, over 971352.03 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:36:42,173 INFO [train.py:715] (5/8) Epoch 10, batch 31500, loss[loss=0.1271, simple_loss=0.2102, pruned_loss=0.02205, over 4957.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03353, over 971942.01 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:37:19,852 INFO [train.py:715] (5/8) Epoch 10, batch 31550, loss[loss=0.1428, simple_loss=0.2093, pruned_loss=0.03815, over 4743.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03381, over 971162.36 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:37:58,955 INFO [train.py:715] (5/8) Epoch 10, batch 31600, loss[loss=0.1245, simple_loss=0.2044, pruned_loss=0.02228, over 4818.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03412, over 971306.84 frames.], batch size: 25, lr: 2.10e-04
2022-05-06 23:38:38,094 INFO [train.py:715] (5/8) Epoch 10, batch 31650, loss[loss=0.1488, simple_loss=0.2159, pruned_loss=0.04084, over 4907.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.0345, over 971049.27 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:39:17,241 INFO [train.py:715] (5/8) Epoch 10, batch 31700, loss[loss=0.1479, simple_loss=0.2181, pruned_loss=0.03889, over 4836.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03391, over 971753.49 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:39:55,908 INFO [train.py:715] (5/8) Epoch 10, batch 31750, loss[loss=0.1698, simple_loss=0.2499, pruned_loss=0.04487, over 4918.00 frames.], tot_loss[loss=0.1409, simple_loss=0.214, pruned_loss=0.03392, over 971581.80 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:40:34,951 INFO [train.py:715] (5/8) Epoch 10, batch 31800, loss[loss=0.1296, simple_loss=0.2035, pruned_loss=0.02787, over 4821.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03359, over 971591.49 frames.], batch size: 13, lr: 2.10e-04
2022-05-06 23:41:14,307 INFO [train.py:715] (5/8) Epoch 10, batch 31850, loss[loss=0.1736, simple_loss=0.2566, pruned_loss=0.04528, over 4816.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2137, pruned_loss=0.03369, over 972706.38 frames.], batch size: 27, lr: 2.10e-04
2022-05-06 23:41:52,371 INFO [train.py:715] (5/8) Epoch 10, batch 31900, loss[loss=0.1519, simple_loss=0.2196, pruned_loss=0.04204, over 4986.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 972813.02 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:42:31,524 INFO [train.py:715] (5/8) Epoch 10, batch 31950, loss[loss=0.1301, simple_loss=0.2093, pruned_loss=0.02545, over 4930.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03326, over 972644.83 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:43:10,929 INFO [train.py:715] (5/8) Epoch 10, batch 32000, loss[loss=0.1306, simple_loss=0.2039, pruned_loss=0.0286, over 4938.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03334, over 972699.69 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:43:49,599 INFO [train.py:715] (5/8) Epoch 10, batch 32050, loss[loss=0.1311, simple_loss=0.2068, pruned_loss=0.02766, over 4808.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03307, over 972259.32 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:44:27,916 INFO [train.py:715] (5/8) Epoch 10, batch 32100, loss[loss=0.1421, simple_loss=0.2159, pruned_loss=0.03416, over 4802.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03254, over 972110.45 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:45:06,913 INFO [train.py:715] (5/8) Epoch 10, batch 32150, loss[loss=0.1569, simple_loss=0.2461, pruned_loss=0.03382, over 4907.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03207, over 972486.02 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:45:45,855 INFO [train.py:715] (5/8) Epoch 10, batch 32200, loss[loss=0.1518, simple_loss=0.2336, pruned_loss=0.03499, over 4864.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03309, over 972401.15 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:46:23,727 INFO [train.py:715] (5/8) Epoch 10, batch 32250, loss[loss=0.1076, simple_loss=0.1847, pruned_loss=0.01527, over 4938.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03311, over 973199.83 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:47:02,887 INFO [train.py:715] (5/8) Epoch 10, batch 32300, loss[loss=0.1281, simple_loss=0.1968, pruned_loss=0.02972, over 4788.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03294, over 972372.37 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:47:42,099 INFO [train.py:715] (5/8) Epoch 10, batch 32350, loss[loss=0.1397, simple_loss=0.2136, pruned_loss=0.03287, over 4807.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03284, over 971729.12 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:48:20,901 INFO [train.py:715] (5/8) Epoch 10, batch 32400, loss[loss=0.1198, simple_loss=0.1998, pruned_loss=0.01989, over 4774.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.033, over 971092.82 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:48:59,311 INFO [train.py:715] (5/8) Epoch 10, batch 32450, loss[loss=0.1298, simple_loss=0.2026, pruned_loss=0.02855, over 4789.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03263, over 970953.76 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:49:38,630 INFO [train.py:715] (5/8) Epoch 10, batch 32500, loss[loss=0.144, simple_loss=0.2126, pruned_loss=0.03769, over 4882.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03234, over 970440.66 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:50:18,345 INFO [train.py:715] (5/8) Epoch 10, batch 32550, loss[loss=0.1442, simple_loss=0.2204, pruned_loss=0.03407, over 4936.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03215, over 970288.68 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:50:56,263 INFO [train.py:715] (5/8) Epoch 10, batch 32600, loss[loss=0.1101, simple_loss=0.183, pruned_loss=0.0186, over 4911.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03206, over 969682.67 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:51:35,796 INFO [train.py:715] (5/8) Epoch 10, batch 32650, loss[loss=0.1502, simple_loss=0.2093, pruned_loss=0.04554, over 4823.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03248, over 970599.83 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:52:15,565 INFO [train.py:715] (5/8) Epoch 10, batch 32700, loss[loss=0.137, simple_loss=0.2141, pruned_loss=0.02998, over 4944.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03284, over 971162.84 frames.], batch size: 21, lr: 2.09e-04
2022-05-06 23:52:53,820 INFO [train.py:715] (5/8) Epoch 10, batch 32750, loss[loss=0.1534, simple_loss=0.2278, pruned_loss=0.03944, over 4689.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03271, over 971517.50 frames.], batch size: 15, lr: 2.09e-04
2022-05-06 23:53:34,507 INFO [train.py:715] (5/8) Epoch 10, batch 32800, loss[loss=0.1159, simple_loss=0.2006, pruned_loss=0.01562, over 4802.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03275, over 971805.73 frames.], batch size: 25, lr: 2.09e-04
2022-05-06 23:54:14,773 INFO [train.py:715] (5/8) Epoch 10, batch 32850, loss[loss=0.1269, simple_loss=0.2027, pruned_loss=0.02557, over 4808.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03304, over 972428.61 frames.], batch size: 25, lr: 2.09e-04
2022-05-06 23:54:54,886 INFO [train.py:715] (5/8) Epoch 10, batch 32900, loss[loss=0.162, simple_loss=0.2315, pruned_loss=0.04623, over 4968.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03362, over 972527.90 frames.], batch size: 35, lr: 2.09e-04
2022-05-06 23:55:34,226 INFO [train.py:715] (5/8) Epoch 10, batch 32950, loss[loss=0.1255, simple_loss=0.1959, pruned_loss=0.02757, over 4902.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2119, pruned_loss=0.03373, over 972212.73 frames.], batch size: 17, lr: 2.09e-04
2022-05-06 23:56:14,907 INFO [train.py:715] (5/8) Epoch 10, batch 33000, loss[loss=0.1389, simple_loss=0.2059, pruned_loss=0.03593, over 4795.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2116, pruned_loss=0.03365, over 972460.87 frames.], batch size: 18, lr: 2.09e-04
2022-05-06 23:56:14,908 INFO [train.py:733] (5/8) Computing validation loss
2022-05-06 23:56:24,575 INFO [train.py:742] (5/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1905, pruned_loss=0.01103, over 914524.00 frames.
2022-05-06 23:57:03,962 INFO [train.py:715] (5/8) Epoch 10, batch 33050, loss[loss=0.1723, simple_loss=0.2441, pruned_loss=0.05021, over 4754.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2126, pruned_loss=0.03436, over 973110.75 frames.], batch size: 19, lr: 2.09e-04
2022-05-06 23:57:43,743 INFO [train.py:715] (5/8) Epoch 10, batch 33100, loss[loss=0.1243, simple_loss=0.1959, pruned_loss=0.02637, over 4853.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2126, pruned_loss=0.03405, over 972342.23 frames.], batch size: 20, lr: 2.09e-04
2022-05-06 23:58:21,687 INFO [train.py:715] (5/8) Epoch 10, batch 33150, loss[loss=0.1435, simple_loss=0.2132, pruned_loss=0.03687, over 4816.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.03356, over 971587.28 frames.], batch size: 27, lr: 2.09e-04
2022-05-06 23:59:00,821 INFO [train.py:715] (5/8) Epoch 10, batch 33200, loss[loss=0.1634, simple_loss=0.2414, pruned_loss=0.04268, over 4916.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03345, over 971916.13 frames.], batch size: 18, lr: 2.09e-04
2022-05-06 23:59:40,447 INFO [train.py:715] (5/8) Epoch 10, batch 33250, loss[loss=0.1451, simple_loss=0.2235, pruned_loss=0.03333, over 4877.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03365, over 971622.37 frames.], batch size: 22, lr: 2.09e-04
2022-05-07 00:00:18,375 INFO [train.py:715] (5/8) Epoch 10, batch 33300, loss[loss=0.1483, simple_loss=0.2212, pruned_loss=0.03771, over 4830.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.034, over 971563.96 frames.], batch size: 26, lr: 2.09e-04
2022-05-07 00:00:57,771 INFO [train.py:715] (5/8) Epoch 10, batch 33350, loss[loss=0.139, simple_loss=0.2025, pruned_loss=0.03779, over 4888.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03431, over 972594.10 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:01:37,017 INFO [train.py:715] (5/8) Epoch 10, batch 33400, loss[loss=0.1213, simple_loss=0.1885, pruned_loss=0.02709, over 4804.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03397, over 973949.28 frames.], batch size: 12, lr: 2.09e-04
2022-05-07 00:02:16,544 INFO [train.py:715] (5/8) Epoch 10, batch 33450, loss[loss=0.1212, simple_loss=0.2014, pruned_loss=0.02051, over 4945.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03384, over 973393.21 frames.], batch size: 23, lr: 2.09e-04
2022-05-07 00:02:54,365 INFO [train.py:715] (5/8) Epoch 10, batch 33500, loss[loss=0.1262, simple_loss=0.2063, pruned_loss=0.02308, over 4987.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03392, over 973034.43 frames.], batch size: 28, lr: 2.09e-04
2022-05-07 00:03:33,960 INFO [train.py:715] (5/8) Epoch 10, batch 33550, loss[loss=0.1226, simple_loss=0.1955, pruned_loss=0.0248, over 4811.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03369, over 973139.04 frames.], batch size: 21, lr: 2.09e-04
2022-05-07 00:04:13,562 INFO [train.py:715] (5/8) Epoch 10, batch 33600, loss[loss=0.133, simple_loss=0.2169, pruned_loss=0.02457, over 4975.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03306, over 972851.22 frames.], batch size: 25, lr: 2.09e-04
2022-05-07 00:04:52,113 INFO [train.py:715] (5/8) Epoch 10, batch 33650, loss[loss=0.1462, simple_loss=0.2205, pruned_loss=0.03597, over 4904.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.0329, over 971951.60 frames.], batch size: 17, lr: 2.09e-04
2022-05-07 00:05:30,843 INFO [train.py:715] (5/8) Epoch 10, batch 33700, loss[loss=0.1459, simple_loss=0.2199, pruned_loss=0.03596, over 4765.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03316, over 971870.94 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:06:10,497 INFO [train.py:715] (5/8) Epoch 10, batch 33750, loss[loss=0.1324, simple_loss=0.2051, pruned_loss=0.02984, over 4775.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.0333, over 971302.82 frames.], batch size: 17, lr: 2.09e-04
2022-05-07 00:06:50,168 INFO [train.py:715] (5/8) Epoch 10, batch 33800, loss[loss=0.178, simple_loss=0.2344, pruned_loss=0.06085, over 4829.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03349, over 972412.34 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:07:29,176 INFO [train.py:715] (5/8) Epoch 10, batch 33850, loss[loss=0.1256, simple_loss=0.2023, pruned_loss=0.02449, over 4984.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.0332, over 972182.09 frames.], batch size: 24, lr: 2.09e-04
2022-05-07 00:08:08,838 INFO [train.py:715] (5/8) Epoch 10, batch 33900, loss[loss=0.1303, simple_loss=0.2001, pruned_loss=0.03021, over 4774.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03347, over 972364.39 frames.], batch size: 18, lr: 2.09e-04
2022-05-07 00:08:48,749 INFO [train.py:715] (5/8) Epoch 10, batch 33950, loss[loss=0.1111, simple_loss=0.1771, pruned_loss=0.02253, over 4791.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03347, over 971298.72 frames.], batch size: 17, lr: 2.09e-04
2022-05-07 00:09:27,304 INFO [train.py:715] (5/8) Epoch 10, batch 34000, loss[loss=0.1561, simple_loss=0.232, pruned_loss=0.04013, over 4923.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03368, over 971325.52 frames.], batch size: 18, lr: 2.09e-04
2022-05-07 00:10:06,613 INFO [train.py:715] (5/8) Epoch 10, batch 34050, loss[loss=0.1333, simple_loss=0.2178, pruned_loss=0.02444, over 4993.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03324, over 971520.03 frames.], batch size: 14, lr: 2.09e-04
2022-05-07 00:10:45,876 INFO [train.py:715] (5/8) Epoch 10, batch 34100, loss[loss=0.1239, simple_loss=0.1967, pruned_loss=0.02551, over 4783.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03329, over 970800.61 frames.], batch size: 14, lr: 2.09e-04
2022-05-07 00:11:25,359 INFO [train.py:715] (5/8) Epoch 10, batch 34150, loss[loss=0.1537, simple_loss=0.2324, pruned_loss=0.03748, over 4867.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03303, over 971219.42 frames.], batch size: 16, lr: 2.09e-04
2022-05-07 00:12:04,925 INFO [train.py:715] (5/8) Epoch 10, batch 34200, loss[loss=0.187, simple_loss=0.2623, pruned_loss=0.05583, over 4772.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03335, over 971593.38 frames.], batch size: 18, lr: 2.09e-04
2022-05-07 00:12:44,143 INFO [train.py:715] (5/8) Epoch 10, batch 34250, loss[loss=0.1292, simple_loss=0.2144, pruned_loss=0.02197, over 4974.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03285, over 972261.47 frames.], batch size: 28, lr: 2.09e-04
2022-05-07 00:13:23,646 INFO [train.py:715] (5/8) Epoch 10, batch 34300, loss[loss=0.1455, simple_loss=0.2261, pruned_loss=0.03248, over 4766.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03322, over 972291.00 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:14:03,552 INFO [train.py:715] (5/8) Epoch 10, batch 34350, loss[loss=0.1219, simple_loss=0.204, pruned_loss=0.01987, over 4750.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03273, over 971453.07 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:14:43,432 INFO [train.py:715] (5/8) Epoch 10, batch 34400, loss[loss=0.135, simple_loss=0.2147, pruned_loss=0.02765, over 4886.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03292, over 971452.45 frames.], batch size: 22, lr: 2.09e-04
2022-05-07 00:15:23,583 INFO [train.py:715] (5/8) Epoch 10, batch 34450, loss[loss=0.1294, simple_loss=0.2016, pruned_loss=0.02862, over 4649.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03294, over 971977.67 frames.], batch size: 13, lr: 2.09e-04
2022-05-07 00:16:03,653 INFO [train.py:715] (5/8) Epoch 10, batch 34500, loss[loss=0.1085, simple_loss=0.1803, pruned_loss=0.01837, over 4892.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03287, over 972527.62 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:16:42,849 INFO [train.py:715] (5/8) Epoch 10, batch 34550, loss[loss=0.1557, simple_loss=0.2209, pruned_loss=0.04523, over 4800.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03326, over 972333.09 frames.], batch size: 24, lr: 2.09e-04
2022-05-07 00:17:23,150 INFO [train.py:715] (5/8) Epoch 10, batch 34600, loss[loss=0.151, simple_loss=0.2182, pruned_loss=0.04192, over 4961.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03334, over 973493.29 frames.], batch size: 39, lr: 2.09e-04
2022-05-07 00:18:03,611 INFO [train.py:715] (5/8) Epoch 10, batch 34650, loss[loss=0.1382, simple_loss=0.2093, pruned_loss=0.03356, over 4742.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03388, over 972827.32 frames.], batch size: 16, lr: 2.09e-04
2022-05-07 00:18:42,651 INFO [train.py:715] (5/8) Epoch 10, batch 34700, loss[loss=0.137, simple_loss=0.2052, pruned_loss=0.03434, over 4799.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03366, over 972881.47 frames.], batch size: 14, lr: 2.09e-04
2022-05-07 00:19:21,231 INFO [train.py:715] (5/8) Epoch 10, batch 34750, loss[loss=0.1357, simple_loss=0.2128, pruned_loss=0.02929, over 4964.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03315, over 972709.82 frames.], batch size: 24, lr: 2.09e-04
2022-05-07 00:19:57,687 INFO [train.py:715] (5/8) Epoch 10, batch 34800, loss[loss=0.1556, simple_loss=0.218, pruned_loss=0.04657, over 4779.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2109, pruned_loss=0.03282, over 971427.08 frames.], batch size: 12, lr: 2.09e-04
2022-05-07 00:20:47,591 INFO [train.py:715] (5/8) Epoch 11, batch 0, loss[loss=0.1887, simple_loss=0.2607, pruned_loss=0.05842, over 4825.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2607, pruned_loss=0.05842, over 4825.00 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:21:26,498 INFO [train.py:715] (5/8) Epoch 11, batch 50, loss[loss=0.1416, simple_loss=0.2238, pruned_loss=0.02971, over 4947.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03278, over 220176.68 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:22:06,396 INFO [train.py:715] (5/8) Epoch 11, batch 100, loss[loss=0.1644, simple_loss=0.2245, pruned_loss=0.05214, over 4784.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.0326, over 386238.23 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:22:46,273 INFO [train.py:715] (5/8) Epoch 11, batch 150, loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03839, over 4914.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03204, over 515899.55 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:23:26,828 INFO [train.py:715] (5/8) Epoch 11, batch 200, loss[loss=0.1412, simple_loss=0.2198, pruned_loss=0.0313, over 4924.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03198, over 618069.29 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:24:06,701 INFO [train.py:715] (5/8) Epoch 11, batch 250, loss[loss=0.1305, simple_loss=0.1977, pruned_loss=0.0316, over 4876.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03237, over 696695.99 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:24:45,520 INFO [train.py:715] (5/8) Epoch 11, batch 300, loss[loss=0.1231, simple_loss=0.2012, pruned_loss=0.02249, over 4914.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.033, over 757881.52 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:25:26,104 INFO [train.py:715] (5/8) Epoch 11, batch 350, loss[loss=0.1274, simple_loss=0.1961, pruned_loss=0.02936, over 4857.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03297, over 805961.02 frames.], batch size: 13, lr: 2.00e-04
2022-05-07 00:26:05,776 INFO [train.py:715] (5/8) Epoch 11, batch 400, loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.03894, over 4960.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03316, over 843488.94 frames.], batch size: 35, lr: 2.00e-04
2022-05-07 00:26:46,459 INFO [train.py:715] (5/8) Epoch 11, batch 450, loss[loss=0.1182, simple_loss=0.193, pruned_loss=0.02167, over 4761.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03293, over 871746.31 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:27:27,785 INFO [train.py:715] (5/8) Epoch 11, batch 500, loss[loss=0.1544, simple_loss=0.2191, pruned_loss=0.04487, over 4818.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03329, over 894374.02 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:28:09,385 INFO [train.py:715] (5/8) Epoch 11, batch 550, loss[loss=0.1464, simple_loss=0.2065, pruned_loss=0.04315, over 4871.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03331, over 911967.55 frames.], batch size: 20, lr: 2.00e-04
2022-05-07 00:28:50,701 INFO [train.py:715] (5/8) Epoch 11, batch 600, loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.03776, over 4931.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03356, over 925813.18 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:29:32,039 INFO [train.py:715] (5/8) Epoch 11, batch 650, loss[loss=0.1351, simple_loss=0.2132, pruned_loss=0.02852, over 4978.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03313, over 936103.68 frames.], batch size: 28, lr: 2.00e-04
2022-05-07 00:30:13,300 INFO [train.py:715] (5/8) Epoch 11, batch 700, loss[loss=0.1325, simple_loss=0.2082, pruned_loss=0.0284, over 4968.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03342, over 944517.04 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:30:54,882 INFO [train.py:715] (5/8) Epoch 11, batch 750, loss[loss=0.1329, simple_loss=0.2125, pruned_loss=0.02658, over 4800.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03296, over 951371.06 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:31:36,036 INFO [train.py:715] (5/8) Epoch 11, batch 800, loss[loss=0.151, simple_loss=0.2216, pruned_loss=0.04022, over 4874.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.0332, over 955407.54 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:32:16,760 INFO [train.py:715] (5/8) Epoch 11, batch 850, loss[loss=0.1201, simple_loss=0.2012, pruned_loss=0.0195, over 4875.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03324, over 957998.66 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:32:58,360 INFO [train.py:715] (5/8) Epoch 11, batch 900, loss[loss=0.1272, simple_loss=0.1867, pruned_loss=0.03381, over 4768.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03305, over 961256.53 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:33:38,987 INFO [train.py:715] (5/8) Epoch 11, batch 950, loss[loss=0.1177, simple_loss=0.1921, pruned_loss=0.02165, over 4927.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03302, over 963668.85 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:34:19,480 INFO [train.py:715] (5/8) Epoch 11, batch 1000, loss[loss=0.1749, simple_loss=0.2565, pruned_loss=0.04669, over 4885.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03294, over 965881.19 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:34:58,892 INFO [train.py:715] (5/8) Epoch 11, batch 1050, loss[loss=0.1239, simple_loss=0.1997, pruned_loss=0.02399, over 4768.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03351, over 966701.11 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:35:41,048 INFO [train.py:715] (5/8) Epoch 11, batch 1100, loss[loss=0.1567, simple_loss=0.2287, pruned_loss=0.04237, over 4985.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03297, over 968649.31 frames.], batch size: 35, lr: 2.00e-04
2022-05-07 00:36:20,718 INFO [train.py:715] (5/8) Epoch 11, batch 1150, loss[loss=0.1286, simple_loss=0.2058, pruned_loss=0.02572, over 4943.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03283, over 969371.81 frames.], batch size: 29, lr: 2.00e-04
2022-05-07 00:37:00,329 INFO [train.py:715] (5/8) Epoch 11, batch 1200, loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03589, over 4779.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03345, over 969662.74 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:37:39,162 INFO [train.py:715] (5/8) Epoch 11, batch 1250, loss[loss=0.1372, simple_loss=0.2232, pruned_loss=0.02561, over 4803.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03297, over 969669.95 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:38:18,008 INFO [train.py:715] (5/8) Epoch 11, batch 1300, loss[loss=0.1368, simple_loss=0.1962, pruned_loss=0.03866, over 4866.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03334, over 970076.38 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:38:56,861 INFO [train.py:715] (5/8) Epoch 11, batch 1350, loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03297, over 4906.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2103, pruned_loss=0.03233, over 970614.09 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:39:35,880 INFO [train.py:715] (5/8) Epoch 11, batch 1400, loss[loss=0.1243, simple_loss=0.1968, pruned_loss=0.02584, over 4749.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03216, over 971891.93 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:40:14,714 INFO [train.py:715] (5/8) Epoch 11, batch 1450, loss[loss=0.1333, simple_loss=0.2132, pruned_loss=0.02669, over 4892.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03235, over 972929.94 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:40:53,350 INFO [train.py:715] (5/8) Epoch 11, batch 1500, loss[loss=0.105, simple_loss=0.1775, pruned_loss=0.01624, over 4935.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03256, over 972878.24 frames.], batch size: 29, lr: 2.00e-04
2022-05-07 00:41:31,713 INFO [train.py:715] (5/8) Epoch 11, batch 1550, loss[loss=0.131, simple_loss=0.2008, pruned_loss=0.03064, over 4837.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03295, over 973580.27 frames.], batch size: 30, lr: 2.00e-04
2022-05-07 00:42:10,770 INFO [train.py:715] (5/8) Epoch 11, batch 1600, loss[loss=0.1222, simple_loss=0.1953, pruned_loss=0.02454, over 4814.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03311, over 972441.96 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:42:49,743 INFO [train.py:715] (5/8) Epoch 11, batch 1650, loss[loss=0.1218, simple_loss=0.2004, pruned_loss=0.02159, over 4971.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03275, over 972341.72 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:43:28,108 INFO [train.py:715] (5/8) Epoch 11, batch 1700, loss[loss=0.1101, simple_loss=0.1749, pruned_loss=0.02269, over 4757.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03237, over 972529.37 frames.], batch size: 12, lr: 2.00e-04
2022-05-07 00:44:07,380 INFO [train.py:715] (5/8) Epoch 11, batch 1750, loss[loss=0.1059, simple_loss=0.1799, pruned_loss=0.01593, over 4803.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03242, over 972977.00 frames.], batch size: 24, lr: 2.00e-04
2022-05-07 00:44:46,268 INFO [train.py:715] (5/8) Epoch 11, batch 1800, loss[loss=0.1513, simple_loss=0.2194, pruned_loss=0.04163, over 4977.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03325, over 973263.82 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:45:25,303 INFO [train.py:715] (5/8) Epoch 11, batch 1850, loss[loss=0.1384, simple_loss=0.2148, pruned_loss=0.03102, over 4967.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2121, pruned_loss=0.03344, over 972485.81 frames.], batch size: 24, lr: 2.00e-04
2022-05-07 00:46:04,484 INFO [train.py:715] (5/8) Epoch 11, batch 1900, loss[loss=0.1326, simple_loss=0.1981, pruned_loss=0.03358, over 4765.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.0328, over 972454.92 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:46:43,765 INFO [train.py:715] (5/8) Epoch 11, batch 1950, loss[loss=0.1372, simple_loss=0.2196, pruned_loss=0.02737, over 4858.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03303, over 972259.51 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:47:23,299 INFO [train.py:715] (5/8) Epoch 11, batch 2000, loss[loss=0.1171, simple_loss=0.1967, pruned_loss=0.0187, over 4753.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03346, over 971569.67 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:48:01,929 INFO [train.py:715] (5/8) Epoch 11, batch 2050, loss[loss=0.1386, simple_loss=0.2175, pruned_loss=0.02985, over 4873.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03337, over 972773.57 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:48:41,073 INFO [train.py:715] (5/8) Epoch 11, batch 2100, loss[loss=0.1297, simple_loss=0.2079, pruned_loss=0.02569, over 4976.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03306, over 973358.40 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:49:20,361 INFO [train.py:715] (5/8) Epoch 11, batch 2150, loss[loss=0.124, simple_loss=0.199, pruned_loss=0.02448, over 4937.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03295, over 973206.44 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:49:59,563 INFO [train.py:715] (5/8) Epoch 11, batch 2200, loss[loss=0.1742, simple_loss=0.2333, pruned_loss=0.05758, over 4923.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.0329, over 973462.93 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:50:38,221 INFO [train.py:715] (5/8) Epoch 11, batch 2250, loss[loss=0.1551, simple_loss=0.2382, pruned_loss=0.03603, over 4748.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03313, over 973329.33 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:51:17,279 INFO [train.py:715] (5/8) Epoch 11, batch 2300, loss[loss=0.1644, simple_loss=0.23, pruned_loss=0.04946, over 4964.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03339, over 973933.30 frames.], batch size: 35, lr: 2.00e-04
2022-05-07 00:51:56,679 INFO [train.py:715] (5/8) Epoch 11, batch 2350, loss[loss=0.1396, simple_loss=0.2188, pruned_loss=0.03017, over 4794.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03295, over 973740.59 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:52:35,082 INFO [train.py:715] (5/8) Epoch 11, batch 2400, loss[loss=0.191, simple_loss=0.2376, pruned_loss=0.07222, over 4742.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03374, over 973190.93 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:53:14,456 INFO [train.py:715] (5/8) Epoch 11, batch 2450, loss[loss=0.1161, simple_loss=0.1957, pruned_loss=0.01829, over 4852.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03378, over 972570.28 frames.], batch size: 20, lr: 2.00e-04
2022-05-07 00:53:54,032 INFO [train.py:715] (5/8) Epoch 11, batch 2500, loss[loss=0.1345, simple_loss=0.2122, pruned_loss=0.02839, over 4904.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03345, over 973000.61 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:54:33,180 INFO [train.py:715] (5/8) Epoch 11, batch 2550, loss[loss=0.1401, simple_loss=0.207, pruned_loss=0.03662, over 4854.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03323, over 973203.93 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 00:55:12,421 INFO [train.py:715] (5/8) Epoch 11, batch 2600, loss[loss=0.1226, simple_loss=0.2012, pruned_loss=0.02201, over 4987.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03301, over 972780.57 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:55:51,261 INFO [train.py:715] (5/8) Epoch 11, batch 2650, loss[loss=0.1321, simple_loss=0.2098, pruned_loss=0.02723, over 4887.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03315, over 972718.75 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:56:30,346 INFO [train.py:715] (5/8) Epoch 11, batch 2700, loss[loss=0.1262, simple_loss=0.1935, pruned_loss=0.02943, over 4890.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03302, over 972942.54 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:57:09,094 INFO [train.py:715] (5/8) Epoch 11, batch 2750, loss[loss=0.1082, simple_loss=0.1817, pruned_loss=0.01739, over 4901.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03293, over 972910.52 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:57:48,076 INFO [train.py:715] (5/8) Epoch 11, batch 2800, loss[loss=0.1606, simple_loss=0.229, pruned_loss=0.04611, over 4928.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03359, over 973203.33 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:58:27,250 INFO [train.py:715] (5/8) Epoch 11, batch 2850, loss[loss=0.1375, simple_loss=0.2058, pruned_loss=0.03455, over 4917.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.0336, over 972826.73 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:59:05,706 INFO [train.py:715] (5/8) Epoch 11, batch 2900, loss[loss=0.1358, simple_loss=0.2045, pruned_loss=0.03359, over 4993.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.0334, over 972872.21 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:59:45,166 INFO [train.py:715] (5/8) Epoch 11, batch 2950, loss[loss=0.1395, simple_loss=0.2182, pruned_loss=0.03044, over 4922.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03314, over 972133.17 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 01:00:25,028 INFO [train.py:715] (5/8) Epoch 11, batch 3000, loss[loss=0.1615, simple_loss=0.2309, pruned_loss=0.04603, over 4989.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03337, over 972534.36 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 01:00:25,029 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 01:00:34,771 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01097, over 914524.00 frames.
2022-05-07 01:01:14,747 INFO [train.py:715] (5/8) Epoch 11, batch 3050, loss[loss=0.1418, simple_loss=0.2215, pruned_loss=0.03106, over 4882.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.03314, over 973108.20 frames.], batch size: 38, lr: 2.00e-04
2022-05-07 01:01:54,018 INFO [train.py:715] (5/8) Epoch 11, batch 3100, loss[loss=0.114, simple_loss=0.193, pruned_loss=0.01747, over 4823.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03323, over 973499.74 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 01:02:34,090 INFO [train.py:715] (5/8) Epoch 11, batch 3150, loss[loss=0.1686, simple_loss=0.2462, pruned_loss=0.0455, over 4837.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03344, over 973791.48 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 01:03:13,127 INFO [train.py:715] (5/8) Epoch 11, batch 3200, loss[loss=0.1831, simple_loss=0.2603, pruned_loss=0.05297, over 4852.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03343, over 972848.98 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 01:03:52,800 INFO [train.py:715] (5/8) Epoch 11, batch 3250, loss[loss=0.1485, simple_loss=0.2329, pruned_loss=0.03202, over 4761.00 frames.], tot_loss[loss=0.1407, simple_loss=0.214, pruned_loss=0.03374, over 973612.06 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 01:04:31,534 INFO [train.py:715] (5/8) Epoch 11, batch 3300, loss[loss=0.149, simple_loss=0.2316, pruned_loss=0.03322, over 4902.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03406, over 973711.92 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 01:05:10,791 INFO [train.py:715] (5/8) Epoch 11, batch 3350, loss[loss=0.1315, simple_loss=0.1958, pruned_loss=0.03364, over 4783.00 frames.], tot_loss[loss=0.1407, simple_loss=0.214, pruned_loss=0.03371, over 973831.23 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 01:05:50,445 INFO [train.py:715] (5/8) Epoch 11, batch 3400, loss[loss=0.1442, simple_loss=0.2169, pruned_loss=0.03574, over 4884.00 frames.], tot_loss[loss=0.141, simple_loss=0.2145, pruned_loss=0.03374, over 974442.37 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 01:06:29,434 INFO [train.py:715] (5/8) Epoch 11, batch 3450, loss[loss=0.1284, simple_loss=0.2097, pruned_loss=0.02354, over 4983.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03369, over 973341.59 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 01:07:08,298 INFO [train.py:715] (5/8) Epoch 11, batch 3500, loss[loss=0.1778, simple_loss=0.2526, pruned_loss=0.05154, over 4971.00 frames.], tot_loss[loss=0.142, simple_loss=0.2151, pruned_loss=0.03443, over 973077.04 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:07:47,577 INFO [train.py:715] (5/8) Epoch 11, batch 3550, loss[loss=0.1363, simple_loss=0.2253, pruned_loss=0.02372, over 4840.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03391, over 972772.96 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:08:27,194 INFO [train.py:715] (5/8) Epoch 11, batch 3600, loss[loss=0.1245, simple_loss=0.2025, pruned_loss=0.02324, over 4912.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03403, over 972951.31 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:09:05,513 INFO [train.py:715] (5/8) Epoch 11, batch 3650, loss[loss=0.1196, simple_loss=0.1936, pruned_loss=0.0228, over 4983.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03358, over 972359.08 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:09:45,169 INFO [train.py:715] (5/8) Epoch 11, batch 3700, loss[loss=0.129, simple_loss=0.1995, pruned_loss=0.02927, over 4632.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.03349, over 972021.50 frames.], batch size: 13, lr: 1.99e-04
2022-05-07 01:10:24,603 INFO [train.py:715] (5/8) Epoch 11, batch 3750, loss[loss=0.1499, simple_loss=0.2194, pruned_loss=0.04016, over 4983.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2111, pruned_loss=0.03294, over 972129.88 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:11:03,048 INFO [train.py:715] (5/8) Epoch 11, batch 3800, loss[loss=0.1225, simple_loss=0.2017, pruned_loss=0.02168, over 4982.00 frames.], tot_loss[loss=0.138, simple_loss=0.2106, pruned_loss=0.03271, over 971213.51 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:11:42,113 INFO [train.py:715] (5/8) Epoch 11, batch 3850, loss[loss=0.1455, simple_loss=0.2256, pruned_loss=0.0327, over 4795.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2113, pruned_loss=0.03295, over 971451.25 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:12:21,421 INFO [train.py:715] (5/8) Epoch 11, batch 3900, loss[loss=0.1074, simple_loss=0.1834, pruned_loss=0.01571, over 4825.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03263, over 971583.48 frames.], batch size: 27, lr: 1.99e-04
2022-05-07 01:13:01,146 INFO [train.py:715] (5/8) Epoch 11, batch 3950, loss[loss=0.1579, simple_loss=0.2289, pruned_loss=0.04348, over 4917.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03279, over 972326.53 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:13:39,995 INFO [train.py:715] (5/8) Epoch 11, batch 4000, loss[loss=0.136, simple_loss=0.2123, pruned_loss=0.02989, over 4810.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03251, over 972977.02 frames.], batch size: 25, lr: 1.99e-04
2022-05-07 01:14:19,834 INFO [train.py:715] (5/8) Epoch 11, batch 4050, loss[loss=0.1503, simple_loss=0.2216, pruned_loss=0.03948, over 4765.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03262, over 972793.30 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:14:59,479 INFO [train.py:715] (5/8) Epoch 11, batch 4100, loss[loss=0.1246, simple_loss=0.2046, pruned_loss=0.02235, over 4926.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03215, over 972332.92 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:15:38,033 INFO [train.py:715] (5/8) Epoch 11, batch 4150, loss[loss=0.1234, simple_loss=0.1949, pruned_loss=0.02588, over 4929.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03203, over 972457.77 frames.], batch size: 23, lr: 1.99e-04
2022-05-07 01:16:16,417 INFO [train.py:715] (5/8) Epoch 11, batch 4200, loss[loss=0.1375, simple_loss=0.2072, pruned_loss=0.03389, over 4937.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03246, over 972388.28 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:16:56,659 INFO [train.py:715] (5/8) Epoch 11, batch 4250, loss[loss=0.164, simple_loss=0.2414, pruned_loss=0.04331, over 4821.00 frames.], tot_loss[loss=0.1394, simple_loss=0.213, pruned_loss=0.03293, over 971556.40 frames.], batch size: 27, lr: 1.99e-04
2022-05-07 01:17:36,659 INFO [train.py:715] (5/8) Epoch 11, batch 4300, loss[loss=0.1373, simple_loss=0.2111, pruned_loss=0.03179, over 4763.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2134, pruned_loss=0.03318, over 971895.62 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:18:15,822 INFO [train.py:715] (5/8) Epoch 11, batch 4350, loss[loss=0.1299, simple_loss=0.1995, pruned_loss=0.03016, over 4797.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2129, pruned_loss=0.03248, over 971906.41 frames.], batch size: 17, lr: 1.99e-04
2022-05-07 01:18:56,182 INFO [train.py:715] (5/8) Epoch 11, batch 4400, loss[loss=0.1124, simple_loss=0.1887, pruned_loss=0.01798, over 4808.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03262, over 970663.38 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:19:36,293 INFO [train.py:715] (5/8) Epoch 11, batch 4450, loss[loss=0.155, simple_loss=0.2376, pruned_loss=0.03623, over 4732.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.03279, over 970909.27 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:20:15,926 INFO [train.py:715] (5/8) Epoch 11, batch 4500, loss[loss=0.1298, simple_loss=0.2069, pruned_loss=0.02638, over 4752.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.03283, over 971466.24 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:20:55,940 INFO [train.py:715] (5/8) Epoch 11, batch 4550, loss[loss=0.1472, simple_loss=0.2266, pruned_loss=0.03389, over 4919.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03323, over 970985.32 frames.], batch size: 17, lr: 1.99e-04
2022-05-07 01:21:35,994 INFO [train.py:715] (5/8) Epoch 11, batch 4600, loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03546, over 4889.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03313, over 971675.63 frames.], batch size: 22, lr: 1.99e-04
2022-05-07 01:22:15,463 INFO [train.py:715] (5/8) Epoch 11, batch 4650, loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03826, over 4827.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03315, over 971521.85 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:22:55,177 INFO [train.py:715] (5/8) Epoch 11, batch 4700, loss[loss=0.1253, simple_loss=0.2012, pruned_loss=0.02474, over 4766.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03379, over 971655.75 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:23:35,352 INFO [train.py:715] (5/8) Epoch 11, batch 4750, loss[loss=0.1308, simple_loss=0.2133, pruned_loss=0.02421, over 4829.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2132, pruned_loss=0.03316, over 971767.81 frames.], batch size: 27, lr: 1.99e-04
2022-05-07 01:24:15,524 INFO [train.py:715] (5/8) Epoch 11, batch 4800, loss[loss=0.1467, simple_loss=0.2225, pruned_loss=0.03544, over 4865.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2139, pruned_loss=0.03351, over 972550.05 frames.], batch size: 32, lr: 1.99e-04
2022-05-07 01:24:55,133 INFO [train.py:715] (5/8) Epoch 11, batch 4850, loss[loss=0.1418, simple_loss=0.2199, pruned_loss=0.0319, over 4897.00 frames.], tot_loss[loss=0.14, simple_loss=0.2134, pruned_loss=0.03326, over 972763.74 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:25:34,922 INFO [train.py:715] (5/8) Epoch 11, batch 4900, loss[loss=0.1609, simple_loss=0.2334, pruned_loss=0.04423, over 4977.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03342, over 972381.64 frames.], batch size: 31, lr: 1.99e-04
2022-05-07 01:26:14,639 INFO [train.py:715] (5/8) Epoch 11, batch 4950, loss[loss=0.1288, simple_loss=0.2097, pruned_loss=0.02397, over 4989.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.03351, over 973322.75 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:26:53,442 INFO [train.py:715] (5/8) Epoch 11, batch 5000, loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.04114, over 4778.00 frames.], tot_loss[loss=0.14, simple_loss=0.2136, pruned_loss=0.03314, over 973051.31 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:27:31,884 INFO [train.py:715] (5/8) Epoch 11, batch 5050, loss[loss=0.1329, simple_loss=0.2097, pruned_loss=0.02809, over 4833.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2132, pruned_loss=0.03304, over 972599.92 frames.], batch size: 27, lr: 1.99e-04
2022-05-07 01:28:11,141 INFO [train.py:715] (5/8) Epoch 11, batch 5100, loss[loss=0.1587, simple_loss=0.2218, pruned_loss=0.04778, over 4806.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03291, over 972654.20 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:28:50,278 INFO [train.py:715] (5/8) Epoch 11, batch 5150, loss[loss=0.1288, simple_loss=0.2046, pruned_loss=0.02655, over 4660.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2138, pruned_loss=0.03329, over 973019.52 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:29:29,203 INFO [train.py:715] (5/8) Epoch 11, batch 5200, loss[loss=0.1244, simple_loss=0.1948, pruned_loss=0.02698, over 4902.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2134, pruned_loss=0.03322, over 973513.32 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:30:08,609 INFO [train.py:715] (5/8) Epoch 11, batch 5250, loss[loss=0.1242, simple_loss=0.1925, pruned_loss=0.02793, over 4786.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03346, over 973307.60 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:30:48,291 INFO [train.py:715] (5/8) Epoch 11, batch 5300, loss[loss=0.1348, simple_loss=0.2065, pruned_loss=0.03162, over 4897.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03355, over 974139.23 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:31:27,443 INFO [train.py:715] (5/8) Epoch 11, batch 5350, loss[loss=0.1653, simple_loss=0.2292, pruned_loss=0.05067, over 4821.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03322, over 974242.70 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:32:06,512 INFO [train.py:715] (5/8) Epoch 11, batch 5400, loss[loss=0.1351, simple_loss=0.2055, pruned_loss=0.03232, over 4803.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03291, over 973831.29 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:32:45,900 INFO [train.py:715] (5/8) Epoch 11, batch 5450, loss[loss=0.1266, simple_loss=0.2058, pruned_loss=0.02365, over 4781.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03297, over 973398.43 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:33:25,397 INFO [train.py:715] (5/8) Epoch 11, batch 5500, loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02898, over 4841.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2131, pruned_loss=0.03305, over 973705.37 frames.], batch size: 20, lr: 1.99e-04
2022-05-07 01:34:04,252 INFO [train.py:715] (5/8) Epoch 11, batch 5550, loss[loss=0.169, simple_loss=0.233, pruned_loss=0.05254, over 4782.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03332, over 972897.28 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:34:42,706 INFO [train.py:715] (5/8) Epoch 11, batch 5600, loss[loss=0.157, simple_loss=0.2277, pruned_loss=0.04317, over 4913.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03317, over 972601.63 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:35:22,172 INFO [train.py:715] (5/8) Epoch 11, batch 5650, loss[loss=0.14, simple_loss=0.2057, pruned_loss=0.03713, over 4781.00 frames.], tot_loss[loss=0.139, simple_loss=0.2126, pruned_loss=0.03275, over 972670.87 frames.], batch size: 17, lr: 1.99e-04
2022-05-07 01:36:01,614 INFO [train.py:715] (5/8) Epoch 11, batch 5700, loss[loss=0.1673, simple_loss=0.2363, pruned_loss=0.04913, over 4758.00 frames.], tot_loss[loss=0.1394, simple_loss=0.213, pruned_loss=0.03288, over 972765.25 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:36:40,400 INFO [train.py:715] (5/8) Epoch 11, batch 5750, loss[loss=0.1314, simple_loss=0.2028, pruned_loss=0.02994, over 4785.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03255, over 972142.12 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:37:19,376 INFO [train.py:715] (5/8) Epoch 11, batch 5800, loss[loss=0.147, simple_loss=0.2271, pruned_loss=0.03341, over 4965.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03298, over 972158.96 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:37:58,487 INFO [train.py:715] (5/8) Epoch 11, batch 5850, loss[loss=0.139, simple_loss=0.2034, pruned_loss=0.03726, over 4897.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03258, over 972774.58 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:38:37,496 INFO [train.py:715] (5/8) Epoch 11, batch 5900, loss[loss=0.1448, simple_loss=0.2246, pruned_loss=0.03251, over 4833.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03253, over 972655.34 frames.], batch size: 30, lr: 1.99e-04
2022-05-07 01:39:16,657 INFO [train.py:715] (5/8) Epoch 11, batch 5950, loss[loss=0.1145, simple_loss=0.1925, pruned_loss=0.0183, over 4937.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03289, over 972200.40 frames.], batch size: 29, lr: 1.99e-04
2022-05-07 01:39:56,444 INFO [train.py:715] (5/8) Epoch 11, batch 6000, loss[loss=0.1546, simple_loss=0.2276, pruned_loss=0.04078, over 4775.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03248, over 971223.31 frames.], batch size: 17, lr: 1.99e-04
2022-05-07 01:39:56,445 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 01:40:06,014 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1901, pruned_loss=0.01082, over 914524.00 frames.
2022-05-07 01:40:45,576 INFO [train.py:715] (5/8) Epoch 11, batch 6050, loss[loss=0.1293, simple_loss=0.1987, pruned_loss=0.02992, over 4906.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03254, over 971861.68 frames.], batch size: 23, lr: 1.99e-04
2022-05-07 01:41:24,987 INFO [train.py:715] (5/8) Epoch 11, batch 6100, loss[loss=0.1217, simple_loss=0.2115, pruned_loss=0.01595, over 4965.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03269, over 971512.19 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:42:03,736 INFO [train.py:715] (5/8) Epoch 11, batch 6150, loss[loss=0.1414, simple_loss=0.2095, pruned_loss=0.03667, over 4835.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.0334, over 971931.46 frames.], batch size: 30, lr: 1.99e-04
2022-05-07 01:42:43,200 INFO [train.py:715] (5/8) Epoch 11, batch 6200, loss[loss=0.1644, simple_loss=0.2325, pruned_loss=0.04816, over 4969.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03321, over 972289.92 frames.], batch size: 35, lr: 1.99e-04
2022-05-07 01:43:22,230 INFO [train.py:715] (5/8) Epoch 11, batch 6250, loss[loss=0.1612, simple_loss=0.234, pruned_loss=0.04422, over 4903.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03316, over 972842.36 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:44:01,026 INFO [train.py:715] (5/8) Epoch 11, batch 6300, loss[loss=0.1424, simple_loss=0.2208, pruned_loss=0.03205, over 4938.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03313, over 973669.40 frames.], batch size: 23, lr: 1.99e-04
2022-05-07 01:44:39,692 INFO [train.py:715] (5/8) Epoch 11, batch 6350, loss[loss=0.1378, simple_loss=0.2174, pruned_loss=0.02911, over 4985.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.0325, over 972645.80 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:45:20,272 INFO [train.py:715] (5/8) Epoch 11, batch 6400, loss[loss=0.1183, simple_loss=0.1906, pruned_loss=0.02304, over 4776.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.0328, over 971571.54 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:45:59,615 INFO [train.py:715] (5/8) Epoch 11, batch 6450, loss[loss=0.1467, simple_loss=0.2152, pruned_loss=0.03915, over 4992.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.0326, over 972032.91 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:46:38,690 INFO [train.py:715] (5/8) Epoch 11, batch 6500, loss[loss=0.1393, simple_loss=0.2109, pruned_loss=0.0338, over 4853.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2107, pruned_loss=0.03278, over 971737.48 frames.], batch size: 13, lr: 1.99e-04
2022-05-07 01:47:18,036 INFO [train.py:715] (5/8) Epoch 11, batch 6550, loss[loss=0.1385, simple_loss=0.2177, pruned_loss=0.02964, over 4944.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2101, pruned_loss=0.03262, over 972548.53 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:47:58,217 INFO [train.py:715] (5/8) Epoch 11, batch 6600, loss[loss=0.1554, simple_loss=0.2215, pruned_loss=0.04469, over 4694.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.033, over 972444.71 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:48:38,342 INFO [train.py:715] (5/8) Epoch 11, batch 6650, loss[loss=0.1579, simple_loss=0.2323, pruned_loss=0.04178, over 4808.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03293, over 972530.42 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:49:17,553 INFO [train.py:715] (5/8) Epoch 11, batch 6700, loss[loss=0.1532, simple_loss=0.2153, pruned_loss=0.04554, over 4879.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03308, over 972859.60 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:49:57,812 INFO [train.py:715] (5/8) Epoch 11, batch 6750, loss[loss=0.1907, simple_loss=0.2523, pruned_loss=0.06455, over 4855.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03325, over 973162.18 frames.], batch size: 32, lr: 1.99e-04
2022-05-07 01:50:37,608 INFO [train.py:715] (5/8) Epoch 11, batch 6800, loss[loss=0.1382, simple_loss=0.2135, pruned_loss=0.03141, over 4969.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03299, over 973370.39 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:51:16,477 INFO [train.py:715] (5/8) Epoch 11, batch 6850, loss[loss=0.1314, simple_loss=0.2119, pruned_loss=0.02548, over 4922.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03287, over 972965.41 frames.], batch size: 23, lr: 1.99e-04
2022-05-07 01:51:55,545 INFO [train.py:715] (5/8) Epoch 11, batch 6900, loss[loss=0.1361, simple_loss=0.2084, pruned_loss=0.03189, over 4938.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03258, over 973346.95 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:52:34,233 INFO [train.py:715] (5/8) Epoch 11, batch 6950, loss[loss=0.1193, simple_loss=0.1941, pruned_loss=0.02227, over 4791.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03236, over 973598.97 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:53:13,692 INFO [train.py:715] (5/8) Epoch 11, batch 7000, loss[loss=0.1551, simple_loss=0.2264, pruned_loss=0.04196, over 4830.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03285, over 973488.10 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:53:52,255 INFO [train.py:715] (5/8) Epoch 11, batch 7050, loss[loss=0.1755, simple_loss=0.2385, pruned_loss=0.05623, over 4853.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03308, over 973068.33 frames.], batch size: 30, lr: 1.99e-04
2022-05-07 01:54:31,696 INFO [train.py:715] (5/8) Epoch 11, batch 7100, loss[loss=0.1571, simple_loss=0.2385, pruned_loss=0.03785, over 4801.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03294, over 973097.34 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:55:10,747 INFO [train.py:715] (5/8) Epoch 11, batch 7150, loss[loss=0.1353, simple_loss=0.2127, pruned_loss=0.0289, over 4809.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03267, over 972686.75 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:55:49,509 INFO [train.py:715] (5/8) Epoch 11, batch 7200, loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03521, over 4766.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03293, over 972208.60 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:56:28,451 INFO [train.py:715] (5/8) Epoch 11, batch 7250, loss[loss=0.1525, simple_loss=0.2245, pruned_loss=0.04024, over 4746.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03214, over 971884.15 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:57:07,429 INFO [train.py:715] (5/8) Epoch 11, batch 7300, loss[loss=0.1556, simple_loss=0.2326, pruned_loss=0.03924, over 4974.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03211, over 972516.61 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:57:46,539 INFO [train.py:715] (5/8) Epoch 11, batch 7350, loss[loss=0.1664, simple_loss=0.2302, pruned_loss=0.05127, over 4790.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03219, over 972160.89 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:58:25,306 INFO [train.py:715] (5/8) Epoch 11, batch 7400, loss[loss=0.1528, simple_loss=0.2224, pruned_loss=0.0416, over 4956.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03267, over 971936.04 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 01:59:04,702 INFO [train.py:715] (5/8) Epoch 11, batch 7450, loss[loss=0.1646, simple_loss=0.2416, pruned_loss=0.0438, over 4896.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03318, over 972090.82 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 01:59:43,842 INFO [train.py:715] (5/8) Epoch 11, batch 7500, loss[loss=0.1312, simple_loss=0.2107, pruned_loss=0.02584, over 4785.00 frames.], tot_loss[loss=0.1394, simple_loss=0.213, pruned_loss=0.03287, over 973074.16 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:00:23,089 INFO [train.py:715] (5/8) Epoch 11, batch 7550, loss[loss=0.1528, simple_loss=0.2245, pruned_loss=0.04051, over 4922.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2132, pruned_loss=0.03305, over 973523.66 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:01:02,845 INFO [train.py:715] (5/8) Epoch 11, batch 7600, loss[loss=0.1369, simple_loss=0.1991, pruned_loss=0.03734, over 4773.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.0324, over 972269.86 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:01:42,512 INFO [train.py:715] (5/8) Epoch 11, batch 7650, loss[loss=0.1271, simple_loss=0.2078, pruned_loss=0.02324, over 4813.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03246, over 971820.48 frames.], batch size: 27, lr: 1.98e-04
2022-05-07 02:02:22,053 INFO [train.py:715] (5/8) Epoch 11, batch 7700, loss[loss=0.1713, simple_loss=0.236, pruned_loss=0.05326, over 4834.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03284, over 971685.38 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:03:01,233 INFO [train.py:715] (5/8) Epoch 11, batch 7750, loss[loss=0.1297, simple_loss=0.1997, pruned_loss=0.02981, over 4851.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03251, over 971503.78 frames.], batch size: 34, lr: 1.98e-04
2022-05-07 02:03:40,566 INFO [train.py:715] (5/8) Epoch 11, batch 7800, loss[loss=0.1739, simple_loss=0.2348, pruned_loss=0.05646, over 4825.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03334, over 971797.95 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:04:19,852 INFO [train.py:715] (5/8) Epoch 11, batch 7850, loss[loss=0.1404, simple_loss=0.1965, pruned_loss=0.0422, over 4836.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03325, over 972412.01 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:04:58,991 INFO [train.py:715] (5/8) Epoch 11, batch 7900, loss[loss=0.1769, simple_loss=0.2441, pruned_loss=0.0549, over 4982.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03295, over 972456.51 frames.], batch size: 35, lr: 1.98e-04
2022-05-07 02:05:37,728 INFO [train.py:715] (5/8) Epoch 11, batch 7950, loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03115, over 4880.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03266, over 973533.06 frames.], batch size: 22, lr: 1.98e-04
2022-05-07 02:06:18,359 INFO [train.py:715] (5/8) Epoch 11, batch 8000, loss[loss=0.1712, simple_loss=0.2477, pruned_loss=0.04734, over 4892.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03281, over 973764.50 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:06:57,624 INFO [train.py:715] (5/8) Epoch 11, batch 8050, loss[loss=0.1409, simple_loss=0.2145, pruned_loss=0.03367, over 4871.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03266, over 973620.10 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:07:37,877 INFO [train.py:715] (5/8) Epoch 11, batch 8100, loss[loss=0.1269, simple_loss=0.1997, pruned_loss=0.02705, over 4810.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03297, over 972613.91 frames.], batch size: 25, lr: 1.98e-04
2022-05-07 02:08:17,869 INFO [train.py:715] (5/8) Epoch 11, batch 8150, loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02912, over 4906.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2112, pruned_loss=0.03311, over 973303.19 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:08:57,395 INFO [train.py:715] (5/8) Epoch 11, batch 8200, loss[loss=0.1406, simple_loss=0.2128, pruned_loss=0.03423, over 4901.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03341, over 972461.15 frames.], batch size: 22, lr: 1.98e-04
2022-05-07 02:09:36,727 INFO [train.py:715] (5/8) Epoch 11, batch 8250, loss[loss=0.1477, simple_loss=0.2231, pruned_loss=0.03613, over 4697.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03295, over 972353.82 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:10:15,059 INFO [train.py:715] (5/8) Epoch 11, batch 8300, loss[loss=0.1516, simple_loss=0.2165, pruned_loss=0.04335, over 4975.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03295, over 972664.41 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:10:54,958 INFO [train.py:715] (5/8) Epoch 11, batch 8350, loss[loss=0.1686, simple_loss=0.241, pruned_loss=0.0481, over 4945.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03282, over 972643.60 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:11:34,526 INFO [train.py:715] (5/8) Epoch 11, batch 8400, loss[loss=0.1241, simple_loss=0.2008, pruned_loss=0.0237, over 4920.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2135, pruned_loss=0.03347, over 972739.35 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:12:13,501 INFO [train.py:715] (5/8) Epoch 11, batch 8450, loss[loss=0.1181, simple_loss=0.1962, pruned_loss=0.02006, over 4983.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03342, over 972463.98 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:12:52,199 INFO [train.py:715] (5/8) Epoch 11, batch 8500, loss[loss=0.1182, simple_loss=0.1893, pruned_loss=0.02354, over 4814.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03371, over 973334.90 frames.], batch size: 26, lr: 1.98e-04
2022-05-07 02:13:32,004 INFO [train.py:715] (5/8) Epoch 11, batch 8550, loss[loss=0.1188, simple_loss=0.1903, pruned_loss=0.02361, over 4776.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03356, over 973452.99 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:14:11,212 INFO [train.py:715] (5/8) Epoch 11, batch 8600, loss[loss=0.1407, simple_loss=0.215, pruned_loss=0.03313, over 4858.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03396, over 973197.03 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:14:49,548 INFO [train.py:715] (5/8) Epoch 11, batch 8650, loss[loss=0.1393, simple_loss=0.2092, pruned_loss=0.03467, over 4847.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03372, over 971931.96 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:15:29,402 INFO [train.py:715] (5/8) Epoch 11, batch 8700, loss[loss=0.1354, simple_loss=0.2057, pruned_loss=0.03261, over 4789.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03323, over 971922.01 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:16:08,720 INFO [train.py:715] (5/8) Epoch 11, batch 8750, loss[loss=0.1375, simple_loss=0.2175, pruned_loss=0.02877, over 4969.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03302, over 972323.79 frames.], batch size: 35, lr: 1.98e-04
2022-05-07 02:16:47,704 INFO [train.py:715] (5/8) Epoch 11, batch 8800, loss[loss=0.136, simple_loss=0.2042, pruned_loss=0.03395, over 4787.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2105, pruned_loss=0.03268, over 972000.71 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:17:26,836 INFO [train.py:715] (5/8) Epoch 11, batch 8850, loss[loss=0.1378, simple_loss=0.2162, pruned_loss=0.02973, over 4929.00 frames.], tot_loss[loss=0.1385, simple_loss=0.211, pruned_loss=0.03304, over 971472.17 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:18:06,536 INFO [train.py:715] (5/8) Epoch 11, batch 8900, loss[loss=0.1523, simple_loss=0.2294, pruned_loss=0.0376, over 4828.00 frames.], tot_loss[loss=0.1384, simple_loss=0.211, pruned_loss=0.03288, over 972090.67 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:18:46,168 INFO [train.py:715] (5/8) Epoch 11, batch 8950, loss[loss=0.1234, simple_loss=0.197, pruned_loss=0.02496, over 4785.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03274, over 972554.30 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:19:25,276 INFO [train.py:715] (5/8) Epoch 11, batch 9000, loss[loss=0.1383, simple_loss=0.2135, pruned_loss=0.03156, over 4932.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03295, over 973019.03 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:19:25,277 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 02:19:34,856 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.011, over 914524.00 frames.
2022-05-07 02:20:13,749 INFO [train.py:715] (5/8) Epoch 11, batch 9050, loss[loss=0.1258, simple_loss=0.194, pruned_loss=0.02879, over 4945.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03283, over 973453.31 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:20:55,920 INFO [train.py:715] (5/8) Epoch 11, batch 9100, loss[loss=0.1895, simple_loss=0.2538, pruned_loss=0.06261, over 4852.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03329, over 972358.88 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:21:35,543 INFO [train.py:715] (5/8) Epoch 11, batch 9150, loss[loss=0.1412, simple_loss=0.2178, pruned_loss=0.03225, over 4843.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03346, over 971920.81 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:22:15,054 INFO [train.py:715] (5/8) Epoch 11, batch 9200, loss[loss=0.1414, simple_loss=0.2222, pruned_loss=0.03032, over 4754.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03352, over 971418.49 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:22:54,634 INFO [train.py:715] (5/8) Epoch 11, batch 9250, loss[loss=0.1689, simple_loss=0.2413, pruned_loss=0.04822, over 4958.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03332, over 972179.45 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:23:33,871 INFO [train.py:715] (5/8) Epoch 11, batch 9300, loss[loss=0.1404, simple_loss=0.2198, pruned_loss=0.03051, over 4734.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03333, over 971905.84 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:24:12,708 INFO [train.py:715] (5/8) Epoch 11, batch 9350, loss[loss=0.1373, simple_loss=0.1993, pruned_loss=0.03768, over 4979.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2132, pruned_loss=0.03305, over 972006.50 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:24:51,485 INFO [train.py:715] (5/8) Epoch 11, batch 9400, loss[loss=0.136, simple_loss=0.2029, pruned_loss=0.03455, over 4889.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03316, over 970897.95 frames.], batch size: 32, lr: 1.98e-04
2022-05-07 02:25:31,000 INFO [train.py:715] (5/8) Epoch 11, batch 9450, loss[loss=0.124, simple_loss=0.2025, pruned_loss=0.02275, over 4798.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03294, over 971382.40 frames.], batch size: 13, lr: 1.98e-04
2022-05-07 02:26:10,041 INFO [train.py:715] (5/8) Epoch 11, batch 9500, loss[loss=0.1363, simple_loss=0.2145, pruned_loss=0.02911, over 4970.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03295, over 971420.94 frames.], batch size: 35, lr: 1.98e-04
2022-05-07 02:26:48,572 INFO [train.py:715] (5/8) Epoch 11, batch 9550, loss[loss=0.1412, simple_loss=0.2221, pruned_loss=0.03013, over 4933.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03215, over 971180.52 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:27:28,235 INFO [train.py:715] (5/8) Epoch 11, batch 9600, loss[loss=0.1606, simple_loss=0.2291, pruned_loss=0.046, over 4861.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03213, over 971322.96 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:28:07,060 INFO [train.py:715] (5/8) Epoch 11, batch 9650, loss[loss=0.1058, simple_loss=0.1756, pruned_loss=0.01804, over 4785.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03219, over 972153.39 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:28:45,587 INFO [train.py:715] (5/8) Epoch 11, batch 9700, loss[loss=0.1508, simple_loss=0.219, pruned_loss=0.04127, over 4890.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03223, over 971921.23 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:29:24,590 INFO [train.py:715] (5/8) Epoch 11, batch 9750, loss[loss=0.1479, simple_loss=0.2172, pruned_loss=0.03934, over 4808.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03197, over 971736.05 frames.], batch size: 27, lr: 1.98e-04
2022-05-07 02:30:03,699 INFO [train.py:715] (5/8) Epoch 11, batch 9800, loss[loss=0.159, simple_loss=0.2263, pruned_loss=0.04585, over 4939.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03218, over 972940.68 frames.], batch size: 24, lr: 1.98e-04
2022-05-07 02:30:43,326 INFO [train.py:715] (5/8) Epoch 11, batch 9850, loss[loss=0.1215, simple_loss=0.2061, pruned_loss=0.01849, over 4987.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03256, over 974152.04 frames.], batch size: 25, lr: 1.98e-04
2022-05-07 02:31:22,284 INFO [train.py:715] (5/8) Epoch 11, batch 9900, loss[loss=0.1187, simple_loss=0.1905, pruned_loss=0.02352, over 4793.00 frames.], tot_loss[loss=0.1395, simple_loss=0.213, pruned_loss=0.03301, over 974586.55 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:32:02,527 INFO [train.py:715] (5/8) Epoch 11, batch 9950, loss[loss=0.1329, simple_loss=0.2233, pruned_loss=0.02126, over 4950.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2132, pruned_loss=0.03296, over 974242.10 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:32:41,853 INFO [train.py:715] (5/8) Epoch 11, batch 10000, loss[loss=0.1463, simple_loss=0.2155, pruned_loss=0.0385, over 4985.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2131, pruned_loss=0.03291, over 974653.38 frames.], batch size: 31, lr: 1.98e-04
2022-05-07 02:33:21,581 INFO [train.py:715] (5/8) Epoch 11, batch 10050, loss[loss=0.1081, simple_loss=0.1793, pruned_loss=0.01846, over 4905.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.0331, over 974941.16 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:33:59,721 INFO [train.py:715] (5/8) Epoch 11, batch 10100, loss[loss=0.1306, simple_loss=0.2098, pruned_loss=0.02571, over 4857.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2136, pruned_loss=0.03337, over 974509.23 frames.], batch size: 38, lr: 1.98e-04
2022-05-07 02:34:38,756 INFO [train.py:715] (5/8) Epoch 11, batch 10150, loss[loss=0.1261, simple_loss=0.1984, pruned_loss=0.02692, over 4858.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03331, over 974036.87 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:35:17,189 INFO [train.py:715] (5/8) Epoch 11, batch 10200, loss[loss=0.1542, simple_loss=0.2181, pruned_loss=0.04516, over 4776.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03307, over 973234.14 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:35:55,358 INFO [train.py:715] (5/8) Epoch 11, batch 10250, loss[loss=0.1588, simple_loss=0.2342, pruned_loss=0.0417, over 4703.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03315, over 972796.97 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:36:34,757 INFO [train.py:715] (5/8) Epoch 11, batch 10300, loss[loss=0.127, simple_loss=0.2037, pruned_loss=0.02517, over 4953.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.0328, over 972569.58 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:37:13,485 INFO [train.py:715] (5/8) Epoch 11, batch 10350, loss[loss=0.1531, simple_loss=0.2323, pruned_loss=0.03699, over 4761.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03277, over 972891.43 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:37:52,306 INFO [train.py:715] (5/8) Epoch 11, batch 10400, loss[loss=0.1278, simple_loss=0.2062, pruned_loss=0.02477, over 4859.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03272, over 972576.36 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:38:30,786 INFO [train.py:715] (5/8) Epoch 11, batch 10450, loss[loss=0.1183, simple_loss=0.2, pruned_loss=0.0183, over 4855.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03289, over 972530.65 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:39:09,427 INFO [train.py:715] (5/8) Epoch 11, batch 10500, loss[loss=0.142, simple_loss=0.2219, pruned_loss=0.03103, over 4982.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03297, over 973154.94 frames.], batch size: 25, lr: 1.98e-04
2022-05-07 02:39:48,485 INFO [train.py:715] (5/8) Epoch 11, batch 10550, loss[loss=0.1116, simple_loss=0.1823, pruned_loss=0.02045, over 4798.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03233, over 972890.27 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:40:27,833 INFO [train.py:715] (5/8) Epoch 11, batch 10600, loss[loss=0.15, simple_loss=0.2158, pruned_loss=0.0421, over 4774.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03191, over 972956.95 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:41:06,621 INFO [train.py:715] (5/8) Epoch 11, batch 10650, loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03719, over 4944.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03182, over 973238.50 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:41:45,851 INFO [train.py:715] (5/8) Epoch 11, batch 10700, loss[loss=0.1306, simple_loss=0.2119, pruned_loss=0.0247, over 4893.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.032, over 973358.18 frames.], batch size: 22, lr: 1.98e-04
2022-05-07 02:42:25,052 INFO [train.py:715] (5/8) Epoch 11, batch 10750, loss[loss=0.1592, simple_loss=0.2393, pruned_loss=0.03958, over 4976.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.0323, over 973214.24 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:43:03,974 INFO [train.py:715] (5/8) Epoch 11, batch 10800, loss[loss=0.1411, simple_loss=0.2088, pruned_loss=0.03671, over 4951.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03206, over 973174.55 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:43:43,679 INFO [train.py:715] (5/8) Epoch 11, batch 10850, loss[loss=0.1195, simple_loss=0.1837, pruned_loss=0.02763, over 4840.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03255, over 972943.44 frames.], batch size: 13, lr: 1.98e-04
2022-05-07 02:44:23,474 INFO [train.py:715] (5/8) Epoch 11, batch 10900, loss[loss=0.1364, simple_loss=0.2246, pruned_loss=0.02407, over 4937.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03233, over 972803.85 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:45:02,832 INFO [train.py:715] (5/8) Epoch 11, batch 10950, loss[loss=0.1506, simple_loss=0.223, pruned_loss=0.03906, over 4812.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.032, over 972404.32 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:45:42,048 INFO [train.py:715] (5/8) Epoch 11, batch 11000, loss[loss=0.1314, simple_loss=0.2074, pruned_loss=0.02768, over 4756.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03213, over 972651.74 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:46:21,451 INFO [train.py:715] (5/8) Epoch 11, batch 11050, loss[loss=0.1403, simple_loss=0.2082, pruned_loss=0.0362, over 4902.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03182, over 973023.37 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:47:00,458 INFO [train.py:715] (5/8) Epoch 11, batch 11100, loss[loss=0.1225, simple_loss=0.1948, pruned_loss=0.02505, over 4962.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03182, over 972959.51 frames.], batch size: 24, lr: 1.98e-04
2022-05-07 02:47:39,068 INFO [train.py:715] (5/8) Epoch 11, batch 11150, loss[loss=0.1459, simple_loss=0.2224, pruned_loss=0.03476, over 4742.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03177, over 972431.23 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:48:18,473 INFO [train.py:715] (5/8) Epoch 11, batch 11200, loss[loss=0.1585, simple_loss=0.2364, pruned_loss=0.04029, over 4909.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03213, over 972737.96 frames.], batch size: 38, lr: 1.98e-04
2022-05-07 02:48:57,591 INFO [train.py:715] (5/8) Epoch 11, batch 11250, loss[loss=0.1332, simple_loss=0.2103, pruned_loss=0.02804, over 4899.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03249, over 972797.73 frames.], batch size: 22, lr: 1.98e-04
2022-05-07 02:49:35,931 INFO [train.py:715] (5/8) Epoch 11, batch 11300, loss[loss=0.1931, simple_loss=0.268, pruned_loss=0.05912, over 4849.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03225, over 972980.87 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:50:14,830 INFO [train.py:715] (5/8) Epoch 11, batch 11350, loss[loss=0.1342, simple_loss=0.2139, pruned_loss=0.02724, over 4808.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03196, over 973096.32 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 02:50:54,371 INFO [train.py:715] (5/8) Epoch 11, batch 11400, loss[loss=0.1527, simple_loss=0.2297, pruned_loss=0.03784, over 4752.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03212, over 971517.25 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 02:51:32,953 INFO [train.py:715] (5/8) Epoch 11, batch 11450, loss[loss=0.1544, simple_loss=0.2247, pruned_loss=0.04203, over 4835.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03244, over 971611.68 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 02:52:11,285 INFO [train.py:715] (5/8) Epoch 11, batch 11500, loss[loss=0.1314, simple_loss=0.2043, pruned_loss=0.02921, over 4838.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03265, over 971644.81 frames.], batch size: 26, lr: 1.97e-04
2022-05-07 02:52:50,110 INFO [train.py:715] (5/8) Epoch 11, batch 11550, loss[loss=0.1431, simple_loss=0.2212, pruned_loss=0.03244, over 4707.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03254, over 972241.37 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 02:53:29,303 INFO [train.py:715] (5/8) Epoch 11, batch 11600, loss[loss=0.1457, simple_loss=0.2109, pruned_loss=0.0402, over 4966.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03281, over 972579.31 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 02:54:08,231 INFO [train.py:715] (5/8) Epoch 11, batch 11650, loss[loss=0.1537, simple_loss=0.2305, pruned_loss=0.03844, over 4751.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03231, over 972266.97 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 02:54:46,494 INFO [train.py:715] (5/8) Epoch 11, batch 11700, loss[loss=0.1249, simple_loss=0.1972, pruned_loss=0.02628, over 4855.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03198, over 971603.78 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 02:55:25,411 INFO [train.py:715] (5/8) Epoch 11, batch 11750, loss[loss=0.1255, simple_loss=0.1935, pruned_loss=0.02872, over 4781.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03219, over 971286.30 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 02:56:04,628 INFO [train.py:715] (5/8) Epoch 11, batch 11800, loss[loss=0.1378, simple_loss=0.2078, pruned_loss=0.03391, over 4756.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.0323, over 971345.74 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 02:56:43,716 INFO [train.py:715] (5/8) Epoch 11, batch 11850, loss[loss=0.1143, simple_loss=0.179, pruned_loss=0.02481, over 4767.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03212, over 971008.00 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 02:57:23,412 INFO [train.py:715] (5/8) Epoch 11, batch 11900, loss[loss=0.1423, simple_loss=0.2213, pruned_loss=0.03165, over 4810.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03214, over 970863.50 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 02:58:03,752 INFO [train.py:715] (5/8) Epoch 11, batch 11950, loss[loss=0.1438, simple_loss=0.2203, pruned_loss=0.03363, over 4725.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03206, over 970709.43 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 02:58:43,549 INFO [train.py:715] (5/8) Epoch 11, batch 12000, loss[loss=0.1347, simple_loss=0.2113, pruned_loss=0.02907, over 4804.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03227, over 971201.47 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 02:58:43,549 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 02:58:53,274 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01096, over 914524.00 frames.
2022-05-07 02:59:33,213 INFO [train.py:715] (5/8) Epoch 11, batch 12050, loss[loss=0.1256, simple_loss=0.1979, pruned_loss=0.02661, over 4988.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03238, over 971700.57 frames.], batch size: 25, lr: 1.97e-04
2022-05-07 03:00:12,648 INFO [train.py:715] (5/8) Epoch 11, batch 12100, loss[loss=0.1495, simple_loss=0.21, pruned_loss=0.04448, over 4966.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03252, over 972356.08 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:00:51,871 INFO [train.py:715] (5/8) Epoch 11, batch 12150, loss[loss=0.1463, simple_loss=0.2073, pruned_loss=0.04267, over 4872.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03229, over 972978.92 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:01:31,400 INFO [train.py:715] (5/8) Epoch 11, batch 12200, loss[loss=0.1371, simple_loss=0.2084, pruned_loss=0.03291, over 4983.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03205, over 973186.57 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:02:09,901 INFO [train.py:715] (5/8) Epoch 11, batch 12250, loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03508, over 4824.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.0326, over 972960.57 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:02:49,516 INFO [train.py:715] (5/8) Epoch 11, batch 12300, loss[loss=0.1391, simple_loss=0.2202, pruned_loss=0.02899, over 4839.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03285, over 971542.02 frames.], batch size: 26, lr: 1.97e-04
2022-05-07 03:03:29,334 INFO [train.py:715] (5/8) Epoch 11, batch 12350, loss[loss=0.1124, simple_loss=0.1809, pruned_loss=0.02201, over 4975.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03291, over 971875.49 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 03:04:08,692 INFO [train.py:715] (5/8) Epoch 11, batch 12400, loss[loss=0.1272, simple_loss=0.194, pruned_loss=0.03018, over 4927.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03219, over 972079.36 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 03:04:46,933 INFO [train.py:715] (5/8) Epoch 11, batch 12450, loss[loss=0.1329, simple_loss=0.21, pruned_loss=0.02789, over 4794.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03207, over 971743.23 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:05:26,163 INFO [train.py:715] (5/8) Epoch 11, batch 12500, loss[loss=0.1333, simple_loss=0.2103, pruned_loss=0.02821, over 4907.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03191, over 971974.55 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:06:05,432 INFO [train.py:715] (5/8) Epoch 11, batch 12550, loss[loss=0.1514, simple_loss=0.2212, pruned_loss=0.04081, over 4757.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03204, over 972217.93 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:06:44,092 INFO [train.py:715] (5/8) Epoch 11, batch 12600, loss[loss=0.129, simple_loss=0.1984, pruned_loss=0.02975, over 4737.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03259, over 972926.75 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:07:23,080 INFO [train.py:715] (5/8) Epoch 11, batch 12650, loss[loss=0.1616, simple_loss=0.227, pruned_loss=0.04813, over 4815.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03229, over 972406.06 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:08:02,194 INFO [train.py:715] (5/8) Epoch 11, batch 12700, loss[loss=0.1253, simple_loss=0.2028, pruned_loss=0.02391, over 4987.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03264, over 971580.35 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:08:40,888 INFO [train.py:715] (5/8) Epoch 11, batch 12750, loss[loss=0.1492, simple_loss=0.2262, pruned_loss=0.03609, over 4983.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03262, over 970938.98 frames.], batch size: 20, lr: 1.97e-04
2022-05-07 03:09:19,302 INFO [train.py:715] (5/8) Epoch 11, batch 12800, loss[loss=0.1468, simple_loss=0.2218, pruned_loss=0.03587, over 4769.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2122, pruned_loss=0.03254, over 971021.81 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:09:58,876 INFO [train.py:715] (5/8) Epoch 11, batch 12850, loss[loss=0.1731, simple_loss=0.2493, pruned_loss=0.04849, over 4754.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2133, pruned_loss=0.03305, over 970850.61 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:10:38,289 INFO [train.py:715] (5/8) Epoch 11, batch 12900, loss[loss=0.1707, simple_loss=0.2333, pruned_loss=0.05405, over 4858.00 frames.], tot_loss[loss=0.139, simple_loss=0.2127, pruned_loss=0.03266, over 970794.70 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:11:17,929 INFO [train.py:715] (5/8) Epoch 11, batch 12950, loss[loss=0.142, simple_loss=0.2155, pruned_loss=0.03428, over 4934.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03305, over 971570.82 frames.], batch size: 29, lr: 1.97e-04
2022-05-07 03:11:56,709 INFO [train.py:715] (5/8) Epoch 11, batch 13000, loss[loss=0.1482, simple_loss=0.2211, pruned_loss=0.03765, over 4962.00 frames.], tot_loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.03279, over 971360.78 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:12:36,382 INFO [train.py:715] (5/8) Epoch 11, batch 13050, loss[loss=0.1231, simple_loss=0.1931, pruned_loss=0.02651, over 4779.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.0329, over 971833.67 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:13:15,472 INFO [train.py:715] (5/8) Epoch 11, batch 13100, loss[loss=0.1053, simple_loss=0.1799, pruned_loss=0.01534, over 4856.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.0329, over 971656.48 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 03:13:53,584 INFO [train.py:715] (5/8) Epoch 11, batch 13150, loss[loss=0.1378, simple_loss=0.2145, pruned_loss=0.03051, over 4751.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03248, over 972306.33 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:14:32,699 INFO [train.py:715] (5/8) Epoch 11, batch 13200, loss[loss=0.1523, simple_loss=0.2206, pruned_loss=0.04206, over 4878.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.033, over 972453.57 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:15:11,058 INFO [train.py:715] (5/8) Epoch 11, batch 13250, loss[loss=0.1508, simple_loss=0.2198, pruned_loss=0.04085, over 4940.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03296, over 971685.12 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:15:50,454 INFO [train.py:715] (5/8) Epoch 11, batch 13300, loss[loss=0.1467, simple_loss=0.2211, pruned_loss=0.0362, over 4879.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.0325, over 972612.24 frames.], batch size: 30, lr: 1.97e-04
2022-05-07 03:16:29,354 INFO [train.py:715] (5/8) Epoch 11, batch 13350, loss[loss=0.1531, simple_loss=0.2357, pruned_loss=0.03529, over 4865.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03245, over 972657.20 frames.], batch size: 30, lr: 1.97e-04
2022-05-07 03:17:08,599 INFO [train.py:715] (5/8) Epoch 11, batch 13400, loss[loss=0.1208, simple_loss=0.1818, pruned_loss=0.02987, over 4845.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.0322, over 972531.24 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 03:17:47,311 INFO [train.py:715] (5/8) Epoch 11, batch 13450, loss[loss=0.1399, simple_loss=0.2133, pruned_loss=0.03328, over 4876.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03292, over 972085.21 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:18:26,312 INFO [train.py:715] (5/8) Epoch 11, batch 13500, loss[loss=0.1735, simple_loss=0.2402, pruned_loss=0.05339, over 4877.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03263, over 972732.93 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:19:05,027 INFO [train.py:715] (5/8) Epoch 11, batch 13550, loss[loss=0.1407, simple_loss=0.2109, pruned_loss=0.03529, over 4746.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03322, over 972875.13 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:19:44,149 INFO [train.py:715] (5/8) Epoch 11, batch 13600, loss[loss=0.1279, simple_loss=0.1991, pruned_loss=0.02838, over 4942.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03347, over 973313.27 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 03:20:22,540 INFO [train.py:715] (5/8) Epoch 11, batch 13650, loss[loss=0.1041, simple_loss=0.179, pruned_loss=0.01457, over 4751.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03317, over 972864.78 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:21:00,719 INFO [train.py:715] (5/8) Epoch 11, batch 13700, loss[loss=0.1266, simple_loss=0.1946, pruned_loss=0.02929, over 4980.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2119, pruned_loss=0.03371, over 973388.84 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 03:21:39,795 INFO [train.py:715] (5/8) Epoch 11, batch 13750, loss[loss=0.1157, simple_loss=0.19, pruned_loss=0.02071, over 4985.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2115, pruned_loss=0.03343, over 973812.79 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:22:19,173 INFO [train.py:715] (5/8) Epoch 11, batch 13800, loss[loss=0.1307, simple_loss=0.1915, pruned_loss=0.03493, over 4821.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2117, pruned_loss=0.03356, over 973476.04 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:22:57,644 INFO [train.py:715] (5/8) Epoch 11, batch 13850, loss[loss=0.1272, simple_loss=0.1979, pruned_loss=0.02831, over 4827.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2119, pruned_loss=0.03398, over 973159.56 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:23:37,054 INFO [train.py:715] (5/8) Epoch 11, batch 13900, loss[loss=0.1448, simple_loss=0.2041, pruned_loss=0.04274, over 4818.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2123, pruned_loss=0.03377, over 973204.54 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:24:15,993 INFO [train.py:715] (5/8) Epoch 11, batch 13950, loss[loss=0.1319, simple_loss=0.2154, pruned_loss=0.02416, over 4797.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.0337, over 972739.28 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:24:55,160 INFO [train.py:715] (5/8) Epoch 11, batch 14000, loss[loss=0.1382, simple_loss=0.2062, pruned_loss=0.03514, over 4979.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03342, over 972494.79 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:25:34,610 INFO [train.py:715] (5/8) Epoch 11, batch 14050, loss[loss=0.1264, simple_loss=0.2065, pruned_loss=0.02314, over 4702.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03352, over 972388.61 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:26:14,333 INFO [train.py:715] (5/8) Epoch 11, batch 14100, loss[loss=0.1306, simple_loss=0.2102, pruned_loss=0.02552, over 4815.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03363, over 971564.14 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:26:53,604 INFO [train.py:715] (5/8) Epoch 11, batch 14150, loss[loss=0.1566, simple_loss=0.2339, pruned_loss=0.03963, over 4802.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03322, over 972563.46 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 03:27:32,867 INFO [train.py:715] (5/8) Epoch 11, batch 14200, loss[loss=0.1469, simple_loss=0.2202, pruned_loss=0.03676, over 4834.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.0336, over 972831.95 frames.], batch size: 30, lr: 1.97e-04
2022-05-07 03:28:13,017 INFO [train.py:715] (5/8) Epoch 11, batch 14250, loss[loss=0.1125, simple_loss=0.1873, pruned_loss=0.01887, over 4801.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03336, over 972018.88 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:28:53,020 INFO [train.py:715] (5/8) Epoch 11, batch 14300, loss[loss=0.1176, simple_loss=0.19, pruned_loss=0.02266, over 4955.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03302, over 971764.08 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 03:29:32,292 INFO [train.py:715] (5/8) Epoch 11, batch 14350, loss[loss=0.1601, simple_loss=0.2241, pruned_loss=0.04801, over 4970.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03319, over 971375.56 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:30:12,238 INFO [train.py:715] (5/8) Epoch 11, batch 14400, loss[loss=0.1113, simple_loss=0.1877, pruned_loss=0.01745, over 4969.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03262, over 971670.52 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:30:52,513 INFO [train.py:715] (5/8) Epoch 11, batch 14450, loss[loss=0.1378, simple_loss=0.217, pruned_loss=0.02927, over 4984.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03248, over 972343.84 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:31:31,924 INFO [train.py:715] (5/8) Epoch 11, batch 14500, loss[loss=0.1271, simple_loss=0.2017, pruned_loss=0.02626, over 4796.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03275, over 972150.29 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:32:11,422 INFO [train.py:715] (5/8) Epoch 11, batch 14550, loss[loss=0.124, simple_loss=0.2004, pruned_loss=0.0238, over 4961.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03222, over 972903.09 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:32:51,265 INFO [train.py:715] (5/8) Epoch 11, batch 14600, loss[loss=0.1455, simple_loss=0.2172, pruned_loss=0.03695, over 4965.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03209, over 973221.87 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:33:30,635 INFO [train.py:715] (5/8) Epoch 11, batch 14650, loss[loss=0.14, simple_loss=0.2159, pruned_loss=0.03208, over 4861.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03221, over 972216.29 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:34:09,053 INFO [train.py:715] (5/8) Epoch 11, batch 14700, loss[loss=0.1638, simple_loss=0.2448, pruned_loss=0.04142, over 4785.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03217, over 972403.60 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:34:48,549 INFO [train.py:715] (5/8) Epoch 11, batch 14750, loss[loss=0.1469, simple_loss=0.2302, pruned_loss=0.03185, over 4893.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03233, over 972594.55 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:35:27,679 INFO [train.py:715] (5/8) Epoch 11, batch 14800, loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03651, over 4635.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03228, over 972680.20 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:36:06,360 INFO [train.py:715] (5/8) Epoch 11, batch 14850, loss[loss=0.1158, simple_loss=0.1901, pruned_loss=0.02077, over 4683.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03241, over 972498.71 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:36:45,862 INFO [train.py:715] (5/8) Epoch 11, batch 14900, loss[loss=0.1138, simple_loss=0.1873, pruned_loss=0.02016, over 4862.00 frames.], tot_loss[loss=0.139, simple_loss=0.2126, pruned_loss=0.03271, over 972097.82 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:37:25,087 INFO [train.py:715] (5/8) Epoch 11, batch 14950, loss[loss=0.1493, simple_loss=0.2285, pruned_loss=0.03508, over 4978.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.0325, over 972018.82 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:38:03,588 INFO [train.py:715] (5/8) Epoch 11, batch 15000, loss[loss=0.1529, simple_loss=0.2235, pruned_loss=0.04116, over 4778.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03242, over 972208.98 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:38:03,589 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 03:38:13,229 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.106, simple_loss=0.1901, pruned_loss=0.01091, over 914524.00 frames.
2022-05-07 03:38:52,000 INFO [train.py:715] (5/8) Epoch 11, batch 15050, loss[loss=0.1232, simple_loss=0.2018, pruned_loss=0.02226, over 4921.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2126, pruned_loss=0.03253, over 972606.59 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:39:30,962 INFO [train.py:715] (5/8) Epoch 11, batch 15100, loss[loss=0.1411, simple_loss=0.2211, pruned_loss=0.03057, over 4907.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2124, pruned_loss=0.03241, over 972930.85 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:40:10,672 INFO [train.py:715] (5/8) Epoch 11, batch 15150, loss[loss=0.1732, simple_loss=0.2536, pruned_loss=0.04636, over 4966.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2118, pruned_loss=0.03204, over 972376.68 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:40:49,841 INFO [train.py:715] (5/8) Epoch 11, batch 15200, loss[loss=0.1404, simple_loss=0.2147, pruned_loss=0.03306, over 4827.00 frames.], tot_loss[loss=0.138, simple_loss=0.2119, pruned_loss=0.03207, over 972746.91 frames.], batch size: 26, lr: 1.97e-04
2022-05-07 03:41:28,409 INFO [train.py:715] (5/8) Epoch 11, batch 15250, loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02933, over 4955.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.03306, over 972423.95 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:42:07,670 INFO [train.py:715] (5/8) Epoch 11, batch 15300, loss[loss=0.1654, simple_loss=0.2356, pruned_loss=0.04761, over 4910.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2134, pruned_loss=0.03315, over 971922.32 frames.], batch size: 39, lr: 1.97e-04
2022-05-07 03:42:46,993 INFO [train.py:715] (5/8) Epoch 11, batch 15350, loss[loss=0.171, simple_loss=0.2461, pruned_loss=0.04793, over 4751.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2137, pruned_loss=0.03353, over 971405.22 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 03:43:25,863 INFO [train.py:715] (5/8) Epoch 11, batch 15400, loss[loss=0.1161, simple_loss=0.1863, pruned_loss=0.02295, over 4789.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2139, pruned_loss=0.03354, over 970985.12 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 03:44:04,606 INFO [train.py:715] (5/8) Epoch 11, batch 15450, loss[loss=0.1116, simple_loss=0.1881, pruned_loss=0.01757, over 4982.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.03297, over 971929.91 frames.], batch size: 28, lr: 1.96e-04
2022-05-07 03:44:44,027 INFO [train.py:715] (5/8) Epoch 11, batch 15500, loss[loss=0.1719, simple_loss=0.2373, pruned_loss=0.05326, over 4978.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03352, over 972614.47 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 03:45:23,171 INFO [train.py:715] (5/8) Epoch 11, batch 15550, loss[loss=0.156, simple_loss=0.2289, pruned_loss=0.0415, over 4778.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03384, over 971766.49 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:46:01,707 INFO [train.py:715] (5/8) Epoch 11, batch 15600, loss[loss=0.1405, simple_loss=0.2143, pruned_loss=0.03338, over 4792.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03362, over 972507.51 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:46:40,879 INFO [train.py:715] (5/8) Epoch 11, batch 15650, loss[loss=0.09167, simple_loss=0.1581, pruned_loss=0.01264, over 4810.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03325, over 972348.46 frames.], batch size: 12, lr: 1.96e-04
2022-05-07 03:47:19,840 INFO [train.py:715] (5/8) Epoch 11, batch 15700, loss[loss=0.1559, simple_loss=0.2301, pruned_loss=0.04087, over 4905.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03334, over 972165.25 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:47:58,648 INFO [train.py:715] (5/8) Epoch 11, batch 15750, loss[loss=0.1424, simple_loss=0.2078, pruned_loss=0.03845, over 4883.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03309, over 972150.42 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 03:48:37,394 INFO [train.py:715] (5/8) Epoch 11, batch 15800, loss[loss=0.1238, simple_loss=0.2126, pruned_loss=0.0175, over 4805.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.0331, over 971484.29 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 03:49:16,754 INFO [train.py:715] (5/8) Epoch 11, batch 15850, loss[loss=0.134, simple_loss=0.2205, pruned_loss=0.02373, over 4815.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03309, over 971259.13 frames.], batch size: 27, lr: 1.96e-04
2022-05-07 03:49:55,696 INFO [train.py:715] (5/8) Epoch 11, batch 15900, loss[loss=0.1215, simple_loss=0.1926, pruned_loss=0.02521, over 4737.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03288, over 971144.42 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 03:50:34,612 INFO [train.py:715] (5/8) Epoch 11, batch 15950, loss[loss=0.1298, simple_loss=0.2021, pruned_loss=0.02876, over 4833.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03296, over 971582.89 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 03:51:13,824 INFO [train.py:715] (5/8) Epoch 11, batch 16000, loss[loss=0.1912, simple_loss=0.2734, pruned_loss=0.0545, over 4907.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03259, over 972333.91 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:51:53,249 INFO [train.py:715] (5/8) Epoch 11, batch 16050, loss[loss=0.113, simple_loss=0.1841, pruned_loss=0.02096, over 4796.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03256, over 971893.59 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 03:52:31,937 INFO [train.py:715] (5/8) Epoch 11, batch 16100, loss[loss=0.1149, simple_loss=0.1881, pruned_loss=0.0208, over 4948.00 frames.], tot_loss[loss=0.138, simple_loss=0.2108, pruned_loss=0.0326, over 972603.10 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 03:53:10,815 INFO [train.py:715] (5/8) Epoch 11, batch 16150, loss[loss=0.1391, simple_loss=0.2222, pruned_loss=0.02802, over 4816.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03163, over 973036.75 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 03:53:50,404 INFO [train.py:715] (5/8) Epoch 11, batch 16200, loss[loss=0.1393, simple_loss=0.2045, pruned_loss=0.03708, over 4780.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.032, over 972420.81 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:54:29,884 INFO [train.py:715] (5/8) Epoch 11, batch 16250, loss[loss=0.1608, simple_loss=0.2309, pruned_loss=0.04535, over 4850.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03191, over 971634.12 frames.], batch size: 34, lr: 1.96e-04
2022-05-07 03:55:08,234 INFO [train.py:715] (5/8) Epoch 11, batch 16300, loss[loss=0.1779, simple_loss=0.2392, pruned_loss=0.05827, over 4837.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03237, over 971643.85 frames.], batch size: 30, lr: 1.96e-04
2022-05-07 03:55:47,431 INFO [train.py:715] (5/8) Epoch 11, batch 16350, loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03796, over 4857.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03238, over 971633.18 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 03:56:26,682 INFO [train.py:715] (5/8) Epoch 11, batch 16400, loss[loss=0.1361, simple_loss=0.2044, pruned_loss=0.03392, over 4960.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03278, over 971769.97 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 03:57:05,178 INFO [train.py:715] (5/8) Epoch 11, batch 16450, loss[loss=0.1437, simple_loss=0.2041, pruned_loss=0.04161, over 4839.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 972470.98 frames.], batch size: 30, lr: 1.96e-04
2022-05-07 03:57:44,148 INFO [train.py:715] (5/8) Epoch 11, batch 16500, loss[loss=0.1208, simple_loss=0.1898, pruned_loss=0.02587, over 4803.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03332, over 971723.85 frames.], batch size: 12, lr: 1.96e-04
2022-05-07 03:58:23,673 INFO [train.py:715] (5/8) Epoch 11, batch 16550, loss[loss=0.138, simple_loss=0.2071, pruned_loss=0.03452, over 4916.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03304, over 972179.99 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 03:59:02,826 INFO [train.py:715] (5/8) Epoch 11, batch 16600, loss[loss=0.1586, simple_loss=0.2326, pruned_loss=0.04236, over 4916.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03363, over 971685.45 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 03:59:41,210 INFO [train.py:715] (5/8) Epoch 11, batch 16650, loss[loss=0.1573, simple_loss=0.2263, pruned_loss=0.04413, over 4865.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03346, over 971168.39 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 04:00:20,432 INFO [train.py:715] (5/8) Epoch 11, batch 16700, loss[loss=0.1418, simple_loss=0.2198, pruned_loss=0.03196, over 4898.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03314, over 971322.49 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 04:00:59,408 INFO [train.py:715] (5/8) Epoch 11, batch 16750, loss[loss=0.128, simple_loss=0.2032, pruned_loss=0.02642, over 4774.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03353, over 971396.23 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:01:38,342 INFO [train.py:715] (5/8) Epoch 11, batch 16800, loss[loss=0.1583, simple_loss=0.2202, pruned_loss=0.04826, over 4984.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03337, over 971371.41 frames.], batch size: 35, lr: 1.96e-04
2022-05-07 04:02:17,994 INFO [train.py:715] (5/8) Epoch 11, batch 16850, loss[loss=0.1468, simple_loss=0.2154, pruned_loss=0.03906, over 4692.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03352, over 971743.72 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:02:57,559 INFO [train.py:715] (5/8) Epoch 11, batch 16900, loss[loss=0.145, simple_loss=0.213, pruned_loss=0.03855, over 4798.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03297, over 972273.42 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:03:37,028 INFO [train.py:715] (5/8) Epoch 11, batch 16950, loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03784, over 4815.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.0328, over 972652.93 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 04:04:15,765 INFO [train.py:715] (5/8) Epoch 11, batch 17000, loss[loss=0.15, simple_loss=0.2187, pruned_loss=0.04065, over 4963.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03233, over 973608.13 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:04:55,494 INFO [train.py:715] (5/8) Epoch 11, batch 17050, loss[loss=0.1489, simple_loss=0.2084, pruned_loss=0.04472, over 4900.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03257, over 973406.14 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:05:38,132 INFO [train.py:715] (5/8) Epoch 11, batch 17100, loss[loss=0.1681, simple_loss=0.2484, pruned_loss=0.04387, over 4913.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03244, over 972654.75 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:06:17,134 INFO [train.py:715] (5/8) Epoch 11, batch 17150, loss[loss=0.1173, simple_loss=0.1957, pruned_loss=0.01942, over 4849.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.0322, over 972255.54 frames.], batch size: 30, lr: 1.96e-04
2022-05-07 04:06:56,397 INFO [train.py:715] (5/8) Epoch 11, batch 17200, loss[loss=0.1485, simple_loss=0.2353, pruned_loss=0.03086, over 4800.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03271, over 973154.93 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 04:07:35,863 INFO [train.py:715] (5/8) Epoch 11, batch 17250, loss[loss=0.1664, simple_loss=0.2336, pruned_loss=0.04962, over 4861.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03278, over 973586.22 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 04:08:14,914 INFO [train.py:715] (5/8) Epoch 11, batch 17300, loss[loss=0.1588, simple_loss=0.2397, pruned_loss=0.03897, over 4934.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.0324, over 973787.82 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 04:08:53,648 INFO [train.py:715] (5/8) Epoch 11, batch 17350, loss[loss=0.1435, simple_loss=0.2054, pruned_loss=0.04079, over 4782.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03207, over 973246.47 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:09:33,978 INFO [train.py:715] (5/8) Epoch 11, batch 17400, loss[loss=0.124, simple_loss=0.1966, pruned_loss=0.02567, over 4859.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03189, over 973012.98 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:10:14,472 INFO [train.py:715] (5/8) Epoch 11, batch 17450, loss[loss=0.1369, simple_loss=0.2088, pruned_loss=0.03247, over 4863.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03199, over 973104.85 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:10:53,785 INFO [train.py:715] (5/8) Epoch 11, batch 17500, loss[loss=0.1378, simple_loss=0.2172, pruned_loss=0.02924, over 4961.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03236, over 973923.81 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:11:33,222 INFO [train.py:715] (5/8) Epoch 11, batch 17550, loss[loss=0.1137, simple_loss=0.195, pruned_loss=0.01623, over 4949.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2128, pruned_loss=0.03266, over 973384.03 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:12:12,579 INFO [train.py:715] (5/8) Epoch 11, batch 17600, loss[loss=0.1521, simple_loss=0.2276, pruned_loss=0.03824, over 4770.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03239, over 973339.89 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:12:51,731 INFO [train.py:715] (5/8) Epoch 11, batch 17650, loss[loss=0.1218, simple_loss=0.2069, pruned_loss=0.01831, over 4977.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03203, over 973826.56 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:13:29,968 INFO [train.py:715] (5/8) Epoch 11, batch 17700, loss[loss=0.1329, simple_loss=0.2084, pruned_loss=0.02874, over 4961.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03281, over 973989.43 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:14:09,452 INFO [train.py:715] (5/8) Epoch 11, batch 17750, loss[loss=0.1303, simple_loss=0.2086, pruned_loss=0.02599, over 4765.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03293, over 973339.14 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:14:49,014 INFO [train.py:715] (5/8) Epoch 11, batch 17800, loss[loss=0.1108, simple_loss=0.1824, pruned_loss=0.01964, over 4976.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03297, over 973358.83 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:15:27,265 INFO [train.py:715] (5/8) Epoch 11, batch 17850, loss[loss=0.1495, simple_loss=0.2323, pruned_loss=0.03335, over 4929.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03263, over 973786.10 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 04:16:06,255 INFO [train.py:715] (5/8) Epoch 11, batch 17900, loss[loss=0.1292, simple_loss=0.201, pruned_loss=0.02867, over 4767.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03216, over 973079.20 frames.], batch size: 12, lr: 1.96e-04
2022-05-07 04:16:45,880 INFO [train.py:715] (5/8) Epoch 11, batch 17950, loss[loss=0.1374, simple_loss=0.215, pruned_loss=0.02989, over 4836.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03151, over 972769.29 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 04:17:24,869 INFO [train.py:715] (5/8) Epoch 11, batch 18000, loss[loss=0.1322, simple_loss=0.2118, pruned_loss=0.02628, over 4768.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03184, over 973314.90 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:17:24,870 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 04:17:34,461 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.01092, over 914524.00 frames.
2022-05-07 04:18:14,136 INFO [train.py:715] (5/8) Epoch 11, batch 18050, loss[loss=0.1245, simple_loss=0.2013, pruned_loss=0.02388, over 4785.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03208, over 971851.78 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:18:53,409 INFO [train.py:715] (5/8) Epoch 11, batch 18100, loss[loss=0.1382, simple_loss=0.2064, pruned_loss=0.035, over 4747.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03278, over 971781.06 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:19:32,617 INFO [train.py:715] (5/8) Epoch 11, batch 18150, loss[loss=0.1189, simple_loss=0.1889, pruned_loss=0.02441, over 4963.00 frames.], tot_loss[loss=0.1395, simple_loss=0.213, pruned_loss=0.03299, over 972849.86 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:20:12,191 INFO [train.py:715] (5/8) Epoch 11, batch 18200, loss[loss=0.168, simple_loss=0.2358, pruned_loss=0.05013, over 4985.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03352, over 973479.61 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:20:50,625 INFO [train.py:715] (5/8) Epoch 11, batch 18250, loss[loss=0.1418, simple_loss=0.2204, pruned_loss=0.03161, over 4760.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03346, over 973399.07 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 04:21:29,928 INFO [train.py:715] (5/8) Epoch 11, batch 18300, loss[loss=0.1369, simple_loss=0.219, pruned_loss=0.02737, over 4781.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 973197.01 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:22:09,172 INFO [train.py:715] (5/8) Epoch 11, batch 18350, loss[loss=0.1056, simple_loss=0.1824, pruned_loss=0.0144, over 4915.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03315, over 972923.61 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:22:47,571 INFO [train.py:715] (5/8) Epoch 11, batch 18400, loss[loss=0.129, simple_loss=0.2, pruned_loss=0.02898, over 4950.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2134, pruned_loss=0.03302, over 973479.42 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 04:23:25,986 INFO [train.py:715] (5/8) Epoch 11, batch 18450, loss[loss=0.1416, simple_loss=0.212, pruned_loss=0.03559, over 4867.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03266, over 972619.21 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:24:05,021 INFO [train.py:715] (5/8) Epoch 11, batch 18500, loss[loss=0.132, simple_loss=0.2081, pruned_loss=0.02799, over 4788.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03221, over 972692.66 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:24:44,459 INFO [train.py:715] (5/8) Epoch 11, batch 18550, loss[loss=0.144, simple_loss=0.2274, pruned_loss=0.03031, over 4886.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03267, over 972923.31 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 04:25:22,563 INFO [train.py:715] (5/8) Epoch 11, batch 18600, loss[loss=0.126, simple_loss=0.2019, pruned_loss=0.02509, over 4831.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03247, over 972527.56 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 04:26:01,408 INFO [train.py:715] (5/8) Epoch 11, batch 18650, loss[loss=0.1449, simple_loss=0.2215, pruned_loss=0.0341, over 4830.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03236, over 971952.49 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:26:40,664 INFO [train.py:715] (5/8) Epoch 11, batch 18700, loss[loss=0.1334, simple_loss=0.2127, pruned_loss=0.02709, over 4809.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.0322, over 972436.74 frames.], batch size: 27, lr: 1.96e-04
2022-05-07 04:27:18,908 INFO [train.py:715] (5/8) Epoch 11, batch 18750, loss[loss=0.1738, simple_loss=0.2553, pruned_loss=0.04614, over 4965.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03213, over 972686.25 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:27:57,975 INFO [train.py:715] (5/8) Epoch 11, batch 18800, loss[loss=0.1433, simple_loss=0.2198, pruned_loss=0.03334, over 4976.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.0319, over 971864.42 frames.], batch size: 35, lr: 1.96e-04
2022-05-07 04:28:36,589 INFO [train.py:715] (5/8) Epoch 11, batch 18850, loss[loss=0.137, simple_loss=0.216, pruned_loss=0.02899, over 4799.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03149, over 972870.01 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 04:29:16,483 INFO [train.py:715] (5/8) Epoch 11, batch 18900, loss[loss=0.1264, simple_loss=0.2042, pruned_loss=0.02432, over 4945.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03181, over 972718.68 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:29:55,265 INFO [train.py:715] (5/8) Epoch 11, batch 18950, loss[loss=0.1199, simple_loss=0.1973, pruned_loss=0.02128, over 4748.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03255, over 972347.36 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:30:34,363 INFO [train.py:715] (5/8) Epoch 11, batch 19000, loss[loss=0.1603, simple_loss=0.2477, pruned_loss=0.03643, over 4882.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2124, pruned_loss=0.03251, over 971924.79 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 04:31:13,457 INFO [train.py:715] (5/8) Epoch 11, batch 19050, loss[loss=0.1708, simple_loss=0.2429, pruned_loss=0.04933, over 4775.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2129, pruned_loss=0.03268, over 972455.01 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:31:52,053 INFO [train.py:715] (5/8) Epoch 11, batch 19100, loss[loss=0.1621, simple_loss=0.2347, pruned_loss=0.04477, over 4753.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.0327, over 972300.35 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:32:31,178 INFO [train.py:715] (5/8) Epoch 11, batch 19150, loss[loss=0.1375, simple_loss=0.2141, pruned_loss=0.03051, over 4940.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03294, over 972404.20 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 04:33:10,097 INFO [train.py:715] (5/8) Epoch 11, batch 19200, loss[loss=0.1322, simple_loss=0.2173, pruned_loss=0.02352, over 4790.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03223, over 972831.30 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:33:49,484 INFO [train.py:715] (5/8) Epoch 11, batch 19250, loss[loss=0.1286, simple_loss=0.197, pruned_loss=0.03008, over 4905.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03195, over 972993.19 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:34:27,828 INFO [train.py:715] (5/8) Epoch 11, batch 19300, loss[loss=0.151, simple_loss=0.2244, pruned_loss=0.03884, over 4889.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03231, over 972443.14 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:35:06,980 INFO [train.py:715] (5/8) Epoch 11, batch 19350, loss[loss=0.1229, simple_loss=0.2002, pruned_loss=0.02285, over 4896.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03193, over 971384.59 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 04:35:46,159 INFO [train.py:715] (5/8) Epoch 11, batch 19400, loss[loss=0.1137, simple_loss=0.1945, pruned_loss=0.01641, over 4868.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.0324, over 971693.83 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 04:36:24,108 INFO [train.py:715] (5/8) Epoch 11, batch 19450, loss[loss=0.1449, simple_loss=0.2098, pruned_loss=0.04003, over 4920.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03206, over 972011.59 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 04:37:03,252 INFO [train.py:715] (5/8) Epoch 11, batch 19500, loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03845, over 4975.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03192, over 972337.88 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:37:42,220 INFO [train.py:715] (5/8) Epoch 11, batch 19550, loss[loss=0.1217, simple_loss=0.175, pruned_loss=0.03418, over 4799.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2099, pruned_loss=0.03217, over 972042.37 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 04:38:20,965 INFO [train.py:715] (5/8) Epoch 11, batch 19600, loss[loss=0.124, simple_loss=0.1981, pruned_loss=0.02493, over 4871.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03158, over 972044.55 frames.], batch size: 32, lr: 1.95e-04
2022-05-07 04:38:59,545 INFO [train.py:715] (5/8) Epoch 11, batch 19650, loss[loss=0.1291, simple_loss=0.2072, pruned_loss=0.02556, over 4832.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03194, over 971755.14 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:39:38,343 INFO [train.py:715] (5/8) Epoch 11, batch 19700, loss[loss=0.1592, simple_loss=0.2325, pruned_loss=0.04292, over 4886.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03201, over 972376.18 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 04:40:17,420 INFO [train.py:715] (5/8) Epoch 11, batch 19750, loss[loss=0.1275, simple_loss=0.2096, pruned_loss=0.02275, over 4827.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03257, over 972604.97 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 04:40:55,506 INFO [train.py:715] (5/8) Epoch 11, batch 19800, loss[loss=0.1335, simple_loss=0.2105, pruned_loss=0.02822, over 4862.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03264, over 972707.37 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 04:41:35,006 INFO [train.py:715] (5/8) Epoch 11, batch 19850, loss[loss=0.1255, simple_loss=0.2055, pruned_loss=0.02275, over 4957.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03232, over 971258.21 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 04:42:14,371 INFO [train.py:715] (5/8) Epoch 11, batch 19900, loss[loss=0.1289, simple_loss=0.2093, pruned_loss=0.02423, over 4950.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03281, over 970923.84 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:42:53,604 INFO [train.py:715] (5/8) Epoch 11, batch 19950, loss[loss=0.1167, simple_loss=0.1953, pruned_loss=0.01902, over 4830.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03271, over 970317.16 frames.], batch size: 13, lr: 1.95e-04
2022-05-07 04:43:32,801 INFO [train.py:715] (5/8) Epoch 11, batch 20000, loss[loss=0.1585, simple_loss=0.2191, pruned_loss=0.04894, over 4708.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03261, over 969218.97 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:44:11,786 INFO [train.py:715] (5/8) Epoch 11, batch 20050, loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03179, over 4859.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03233, over 969886.87 frames.], batch size: 39, lr: 1.95e-04
2022-05-07 04:44:51,035 INFO [train.py:715] (5/8) Epoch 11, batch 20100, loss[loss=0.1532, simple_loss=0.2315, pruned_loss=0.03742, over 4882.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03225, over 971100.26 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 04:45:29,366 INFO [train.py:715] (5/8) Epoch 11, batch 20150, loss[loss=0.158, simple_loss=0.2199, pruned_loss=0.04808, over 4799.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03308, over 971458.74 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 04:46:08,144 INFO [train.py:715] (5/8) Epoch 11, batch 20200, loss[loss=0.1506, simple_loss=0.2208, pruned_loss=0.04025, over 4795.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03324, over 971352.91 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 04:46:46,987 INFO [train.py:715] (5/8) Epoch 11, batch 20250, loss[loss=0.1255, simple_loss=0.2013, pruned_loss=0.02486, over 4777.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03303, over 971680.85 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 04:47:25,731 INFO [train.py:715] (5/8) Epoch 11, batch 20300, loss[loss=0.1331, simple_loss=0.2165, pruned_loss=0.02489, over 4794.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03286, over 971482.50 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 04:48:04,826 INFO [train.py:715] (5/8) Epoch 11, batch 20350, loss[loss=0.1295, simple_loss=0.21, pruned_loss=0.02451, over 4778.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03269, over 970688.02 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 04:48:43,795 INFO [train.py:715] (5/8) Epoch 11, batch 20400, loss[loss=0.1312, simple_loss=0.211, pruned_loss=0.02567, over 4820.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03264, over 970655.89 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 04:49:23,228 INFO [train.py:715] (5/8) Epoch 11, batch 20450, loss[loss=0.1267, simple_loss=0.1969, pruned_loss=0.02825, over 4797.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03276, over 971090.00 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 04:50:01,758 INFO [train.py:715] (5/8) Epoch 11, batch 20500, loss[loss=0.1299, simple_loss=0.21, pruned_loss=0.02491, over 4928.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2131, pruned_loss=0.03325, over 971040.70 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:50:41,079 INFO [train.py:715] (5/8) Epoch 11, batch 20550, loss[loss=0.1414, simple_loss=0.2062, pruned_loss=0.03835, over 4853.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03259, over 971730.72 frames.], batch size: 32, lr: 1.95e-04
2022-05-07 04:51:19,712 INFO [train.py:715] (5/8) Epoch 11, batch 20600, loss[loss=0.1232, simple_loss=0.204, pruned_loss=0.02119, over 4974.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2122, pruned_loss=0.03223, over 971929.78 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:51:57,488 INFO [train.py:715] (5/8) Epoch 11, batch 20650, loss[loss=0.1663, simple_loss=0.2353, pruned_loss=0.04863, over 4797.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2129, pruned_loss=0.03264, over 972556.03 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:52:36,867 INFO [train.py:715] (5/8) Epoch 11, batch 20700, loss[loss=0.1201, simple_loss=0.1884, pruned_loss=0.0259, over 4790.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03267, over 972460.64 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:53:16,098 INFO [train.py:715] (5/8) Epoch 11, batch 20750, loss[loss=0.1559, simple_loss=0.232, pruned_loss=0.03991, over 4769.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2128, pruned_loss=0.03297, over 972724.53 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:53:54,802 INFO [train.py:715] (5/8) Epoch 11, batch 20800, loss[loss=0.1538, simple_loss=0.2292, pruned_loss=0.03915, over 4809.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03242, over 972485.45 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 04:54:33,170 INFO [train.py:715] (5/8) Epoch 11, batch 20850, loss[loss=0.1251, simple_loss=0.1992, pruned_loss=0.02549, over 4858.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03245, over 972445.85 frames.], batch size: 20, lr: 1.95e-04
2022-05-07 04:55:12,417 INFO [train.py:715] (5/8) Epoch 11, batch 20900, loss[loss=0.129, simple_loss=0.1983, pruned_loss=0.02981, over 4753.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03241, over 972455.46 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:55:52,028 INFO [train.py:715] (5/8) Epoch 11, batch 20950, loss[loss=0.1607, simple_loss=0.2287, pruned_loss=0.04635, over 4811.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2124, pruned_loss=0.03258, over 972457.05 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 04:56:30,993 INFO [train.py:715] (5/8) Epoch 11, batch 21000, loss[loss=0.1319, simple_loss=0.2092, pruned_loss=0.02734, over 4834.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.03293, over 972545.71 frames.], batch size: 13, lr: 1.95e-04
2022-05-07 04:56:30,994 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 04:56:40,630 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01097, over 914524.00 frames.
2022-05-07 04:57:20,096 INFO [train.py:715] (5/8) Epoch 11, batch 21050, loss[loss=0.1402, simple_loss=0.2138, pruned_loss=0.03324, over 4791.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03303, over 972553.12 frames.], batch size: 13, lr: 1.95e-04
2022-05-07 04:57:59,831 INFO [train.py:715] (5/8) Epoch 11, batch 21100, loss[loss=0.1321, simple_loss=0.2086, pruned_loss=0.02778, over 4908.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03282, over 973105.08 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 04:58:38,862 INFO [train.py:715] (5/8) Epoch 11, batch 21150, loss[loss=0.1232, simple_loss=0.1921, pruned_loss=0.02711, over 4772.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03284, over 972955.11 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 04:59:18,201 INFO [train.py:715] (5/8) Epoch 11, batch 21200, loss[loss=0.1367, simple_loss=0.2152, pruned_loss=0.02909, over 4895.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03282, over 973227.31 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 04:59:56,326 INFO [train.py:715] (5/8) Epoch 11, batch 21250, loss[loss=0.1456, simple_loss=0.2208, pruned_loss=0.03521, over 4849.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 972893.85 frames.], batch size: 34, lr: 1.95e-04
2022-05-07 05:00:35,638 INFO [train.py:715] (5/8) Epoch 11, batch 21300, loss[loss=0.1173, simple_loss=0.2008, pruned_loss=0.01694, over 4929.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03198, over 973302.90 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:01:15,026 INFO [train.py:715] (5/8) Epoch 11, batch 21350, loss[loss=0.1389, simple_loss=0.2277, pruned_loss=0.02503, over 4824.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03193, over 973868.36 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 05:01:53,535 INFO [train.py:715] (5/8) Epoch 11, batch 21400, loss[loss=0.1486, simple_loss=0.2142, pruned_loss=0.04153, over 4771.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03231, over 973547.08 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:02:32,176 INFO [train.py:715] (5/8) Epoch 11, batch 21450, loss[loss=0.1197, simple_loss=0.1945, pruned_loss=0.02241, over 4818.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.0324, over 972836.52 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:03:11,027 INFO [train.py:715] (5/8) Epoch 11, batch 21500, loss[loss=0.1351, simple_loss=0.2183, pruned_loss=0.02594, over 4781.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03232, over 972855.80 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:03:50,385 INFO [train.py:715] (5/8) Epoch 11, batch 21550, loss[loss=0.1325, simple_loss=0.2039, pruned_loss=0.0306, over 4845.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03193, over 971832.15 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:04:28,679 INFO [train.py:715] (5/8) Epoch 11, batch 21600, loss[loss=0.1367, simple_loss=0.2119, pruned_loss=0.0308, over 4936.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03187, over 972287.50 frames.], batch size: 23, lr: 1.95e-04
2022-05-07 05:05:07,528 INFO [train.py:715] (5/8) Epoch 11, batch 21650, loss[loss=0.1498, simple_loss=0.2076, pruned_loss=0.04599, over 4759.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03242, over 972195.73 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:05:47,577 INFO [train.py:715] (5/8) Epoch 11, batch 21700, loss[loss=0.1687, simple_loss=0.2369, pruned_loss=0.0502, over 4926.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03288, over 973213.78 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:06:26,870 INFO [train.py:715] (5/8) Epoch 11, batch 21750, loss[loss=0.1591, simple_loss=0.2401, pruned_loss=0.03908, over 4808.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03306, over 973331.10 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 05:07:07,060 INFO [train.py:715] (5/8) Epoch 11, batch 21800, loss[loss=0.1455, simple_loss=0.2271, pruned_loss=0.03197, over 4846.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03294, over 972781.46 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:07:46,733 INFO [train.py:715] (5/8) Epoch 11, batch 21850, loss[loss=0.1492, simple_loss=0.2276, pruned_loss=0.0354, over 4798.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03302, over 971724.59 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 05:08:27,224 INFO [train.py:715] (5/8) Epoch 11, batch 21900, loss[loss=0.1322, simple_loss=0.2077, pruned_loss=0.02838, over 4895.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03325, over 971394.21 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:09:06,440 INFO [train.py:715] (5/8) Epoch 11, batch 21950, loss[loss=0.1244, simple_loss=0.1975, pruned_loss=0.02562, over 4934.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03325, over 971800.52 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:09:46,763 INFO [train.py:715] (5/8) Epoch 11, batch 22000, loss[loss=0.1233, simple_loss=0.1919, pruned_loss=0.02738, over 4693.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03288, over 972268.74 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:10:27,230 INFO [train.py:715] (5/8) Epoch 11, batch 22050, loss[loss=0.1276, simple_loss=0.2041, pruned_loss=0.02553, over 4768.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03246, over 972295.92 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:11:05,497 INFO [train.py:715] (5/8) Epoch 11, batch 22100, loss[loss=0.1363, simple_loss=0.2117, pruned_loss=0.03048, over 4896.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.0321, over 972651.69 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:11:45,098 INFO [train.py:715] (5/8) Epoch 11, batch 22150, loss[loss=0.1494, simple_loss=0.2215, pruned_loss=0.03869, over 4691.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.0322, over 972750.16 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:12:24,689 INFO [train.py:715] (5/8) Epoch 11, batch 22200, loss[loss=0.1602, simple_loss=0.2272, pruned_loss=0.04666, over 4849.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03242, over 972835.77 frames.], batch size: 34, lr: 1.95e-04
2022-05-07 05:13:03,455 INFO [train.py:715] (5/8) Epoch 11, batch 22250, loss[loss=0.1451, simple_loss=0.2205, pruned_loss=0.03484, over 4880.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2103, pruned_loss=0.03234, over 972402.87 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 05:13:41,886 INFO [train.py:715] (5/8) Epoch 11, batch 22300, loss[loss=0.115, simple_loss=0.1941, pruned_loss=0.01789, over 4848.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03219, over 971434.01 frames.], batch size: 20, lr: 1.95e-04
2022-05-07 05:14:21,103 INFO [train.py:715] (5/8) Epoch 11, batch 22350, loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03027, over 4885.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03243, over 971031.41 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 05:15:00,557 INFO [train.py:715] (5/8) Epoch 11, batch 22400, loss[loss=0.1329, simple_loss=0.2012, pruned_loss=0.03227, over 4987.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03247, over 971161.34 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:15:38,490 INFO [train.py:715] (5/8) Epoch 11, batch 22450, loss[loss=0.1294, simple_loss=0.2082, pruned_loss=0.02533, over 4925.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2103, pruned_loss=0.03259, over 971671.80 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:16:18,411 INFO [train.py:715] (5/8) Epoch 11, batch 22500, loss[loss=0.131, simple_loss=0.2027, pruned_loss=0.0296, over 4779.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03238, over 971922.18 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 05:16:57,485 INFO [train.py:715] (5/8) Epoch 11, batch 22550, loss[loss=0.1195, simple_loss=0.1949, pruned_loss=0.02209, over 4770.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03278, over 971787.60 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:17:36,656 INFO [train.py:715] (5/8) Epoch 11, batch 22600, loss[loss=0.1192, simple_loss=0.191, pruned_loss=0.02369, over 4970.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03249, over 972352.83 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 05:18:15,027 INFO [train.py:715] (5/8) Epoch 11, batch 22650, loss[loss=0.1609, simple_loss=0.2366, pruned_loss=0.04259, over 4886.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03297, over 972112.84 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:18:54,213 INFO [train.py:715] (5/8) Epoch 11, batch 22700, loss[loss=0.1751, simple_loss=0.245, pruned_loss=0.05261, over 4753.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03277, over 972004.30 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:19:34,077 INFO [train.py:715] (5/8) Epoch 11, batch 22750, loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.0308, over 4816.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03245, over 972334.12 frames.], batch size: 27, lr: 1.95e-04
2022-05-07 05:20:12,495 INFO [train.py:715] (5/8) Epoch 11, batch 22800, loss[loss=0.1218, simple_loss=0.2024, pruned_loss=0.02056, over 4944.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03276, over 972877.90 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 05:20:52,294 INFO [train.py:715] (5/8) Epoch 11, batch 22850, loss[loss=0.1176, simple_loss=0.1823, pruned_loss=0.02645, over 4791.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03302, over 972993.07 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:21:31,220 INFO [train.py:715] (5/8) Epoch 11, batch 22900, loss[loss=0.1504, simple_loss=0.2239, pruned_loss=0.03848, over 4840.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03326, over 972912.12 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:22:10,211 INFO [train.py:715] (5/8) Epoch 11, batch 22950, loss[loss=0.1676, simple_loss=0.2342, pruned_loss=0.05044, over 4974.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03363, over 973281.60 frames.], batch size: 35, lr: 1.95e-04
2022-05-07 05:22:48,359 INFO [train.py:715] (5/8) Epoch 11, batch 23000, loss[loss=0.1239, simple_loss=0.2054, pruned_loss=0.02124, over 4939.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03343, over 974069.60 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:23:27,327 INFO [train.py:715] (5/8) Epoch 11, batch 23050, loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03027, over 4988.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03336, over 973606.39 frames.], batch size: 28, lr: 1.95e-04
2022-05-07 05:24:06,662 INFO [train.py:715] (5/8) Epoch 11, batch 23100, loss[loss=0.1202, simple_loss=0.1915, pruned_loss=0.02448, over 4768.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03317, over 973048.20 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 05:24:44,410 INFO [train.py:715] (5/8) Epoch 11, batch 23150, loss[loss=0.1458, simple_loss=0.2203, pruned_loss=0.03565, over 4808.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03288, over 973007.17 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 05:25:23,978 INFO [train.py:715] (5/8) Epoch 11, batch 23200, loss[loss=0.1396, simple_loss=0.215, pruned_loss=0.03213, over 4743.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03308, over 972264.92 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:26:02,909 INFO [train.py:715] (5/8) Epoch 11, batch 23250, loss[loss=0.1493, simple_loss=0.2262, pruned_loss=0.03623, over 4833.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03265, over 972308.02 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:26:41,984 INFO [train.py:715] (5/8) Epoch 11, batch 23300, loss[loss=0.1409, simple_loss=0.1918, pruned_loss=0.045, over 4803.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03273, over 972549.15 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:27:20,073 INFO [train.py:715] (5/8) Epoch 11, batch 23350, loss[loss=0.1413, simple_loss=0.2068, pruned_loss=0.03787, over 4771.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03309, over 972896.46 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 05:27:59,122 INFO [train.py:715] (5/8) Epoch 11, batch 23400, loss[loss=0.1259, simple_loss=0.2115, pruned_loss=0.02018, over 4762.00 frames.], tot_loss[loss=0.139, simple_loss=0.2114, pruned_loss=0.03326, over 972980.81 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:28:38,744 INFO [train.py:715] (5/8) Epoch 11, batch 23450, loss[loss=0.1254, simple_loss=0.1988, pruned_loss=0.02597, over 4985.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03292, over 972645.72 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 05:29:16,868 INFO [train.py:715] (5/8) Epoch 11, batch 23500, loss[loss=0.1425, simple_loss=0.2206, pruned_loss=0.03221, over 4829.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03283, over 972939.82 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 05:29:55,782 INFO [train.py:715] (5/8) Epoch 11, batch 23550, loss[loss=0.1511, simple_loss=0.2246, pruned_loss=0.03882, over 4886.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03321, over 972316.11 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:30:34,764 INFO [train.py:715] (5/8) Epoch 11, batch 23600, loss[loss=0.1614, simple_loss=0.2364, pruned_loss=0.04325, over 4773.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03346, over 972716.46 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:31:14,124 INFO [train.py:715] (5/8) Epoch 11, batch 23650, loss[loss=0.1489, simple_loss=0.2178, pruned_loss=0.03996, over 4824.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03315, over 972732.97 frames.], batch size: 30, lr: 1.94e-04
2022-05-07 05:31:51,830 INFO [train.py:715] (5/8) Epoch 11, batch 23700, loss[loss=0.1424, simple_loss=0.2191, pruned_loss=0.03284, over 4862.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03298, over 972886.94 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 05:32:30,817 INFO [train.py:715] (5/8) Epoch 11, batch 23750, loss[loss=0.1057, simple_loss=0.174, pruned_loss=0.01868, over 4870.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.0334, over 972441.47 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 05:33:09,309 INFO [train.py:715] (5/8) Epoch 11, batch 23800, loss[loss=0.1441, simple_loss=0.2287, pruned_loss=0.02973, over 4777.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03369, over 972848.27 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:33:46,737 INFO [train.py:715] (5/8) Epoch 11, batch 23850, loss[loss=0.1429, simple_loss=0.223, pruned_loss=0.03144, over 4915.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03373, over 971820.75 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:34:24,311 INFO [train.py:715] (5/8) Epoch 11, batch 23900, loss[loss=0.1157, simple_loss=0.1876, pruned_loss=0.02188, over 4959.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03318, over 972630.75 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:35:01,655 INFO [train.py:715] (5/8) Epoch 11, batch 23950, loss[loss=0.1684, simple_loss=0.2383, pruned_loss=0.0492, over 4790.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03315, over 971715.90 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:35:39,343 INFO [train.py:715] (5/8) Epoch 11, batch 24000, loss[loss=0.1389, simple_loss=0.2084, pruned_loss=0.0347, over 4989.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.0334, over 971130.48 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:35:39,343 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 05:35:48,812 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01092, over 914524.00 frames.
2022-05-07 05:36:27,136 INFO [train.py:715] (5/8) Epoch 11, batch 24050, loss[loss=0.1214, simple_loss=0.1817, pruned_loss=0.03053, over 4956.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03264, over 971309.37 frames.], batch size: 31, lr: 1.94e-04
2022-05-07 05:37:04,267 INFO [train.py:715] (5/8) Epoch 11, batch 24100, loss[loss=0.1766, simple_loss=0.2276, pruned_loss=0.06278, over 4773.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.0328, over 972441.36 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:37:42,094 INFO [train.py:715] (5/8) Epoch 11, batch 24150, loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03024, over 4755.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03266, over 972937.20 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:38:20,367 INFO [train.py:715] (5/8) Epoch 11, batch 24200, loss[loss=0.1378, simple_loss=0.2246, pruned_loss=0.02554, over 4830.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03289, over 973067.79 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 05:38:57,453 INFO [train.py:715] (5/8) Epoch 11, batch 24250, loss[loss=0.1565, simple_loss=0.2311, pruned_loss=0.04093, over 4937.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03219, over 972619.91 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:39:35,484 INFO [train.py:715] (5/8) Epoch 11, batch 24300, loss[loss=0.157, simple_loss=0.219, pruned_loss=0.04753, over 4853.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03207, over 973063.84 frames.], batch size: 32, lr: 1.94e-04
2022-05-07 05:40:13,073 INFO [train.py:715] (5/8) Epoch 11, batch 24350, loss[loss=0.1148, simple_loss=0.2013, pruned_loss=0.01418, over 4949.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2121, pruned_loss=0.03239, over 973046.00 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:40:50,678 INFO [train.py:715] (5/8) Epoch 11, batch 24400, loss[loss=0.1141, simple_loss=0.1933, pruned_loss=0.01745, over 4857.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2113, pruned_loss=0.03173, over 973345.02 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 05:41:28,272 INFO [train.py:715] (5/8) Epoch 11, batch 24450, loss[loss=0.1525, simple_loss=0.2311, pruned_loss=0.03693, over 4981.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03125, over 973222.77 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 05:42:06,387 INFO [train.py:715] (5/8) Epoch 11, batch 24500, loss[loss=0.1127, simple_loss=0.1955, pruned_loss=0.01498, over 4819.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.0312, over 973475.99 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 05:42:45,027 INFO [train.py:715] (5/8) Epoch 11, batch 24550, loss[loss=0.1654, simple_loss=0.2489, pruned_loss=0.04091, over 4781.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03153, over 973440.39 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:43:23,051 INFO [train.py:715] (5/8) Epoch 11, batch 24600, loss[loss=0.1555, simple_loss=0.2331, pruned_loss=0.03899, over 4915.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03189, over 973165.81 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:44:01,527 INFO [train.py:715] (5/8) Epoch 11, batch 24650, loss[loss=0.1253, simple_loss=0.2041, pruned_loss=0.02324, over 4735.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03199, over 973129.27 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:44:39,863 INFO [train.py:715] (5/8) Epoch 11, batch 24700, loss[loss=0.1413, simple_loss=0.212, pruned_loss=0.03527, over 4808.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03228, over 973438.79 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 05:45:18,489 INFO [train.py:715] (5/8) Epoch 11, batch 24750, loss[loss=0.1219, simple_loss=0.2014, pruned_loss=0.02118, over 4752.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03209, over 973148.64 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:45:56,383 INFO [train.py:715] (5/8) Epoch 11, batch 24800, loss[loss=0.1409, simple_loss=0.2089, pruned_loss=0.03646, over 4933.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.0321, over 973567.67 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:46:34,703 INFO [train.py:715] (5/8) Epoch 11, batch 24850, loss[loss=0.1436, simple_loss=0.2078, pruned_loss=0.03967, over 4910.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03237, over 972798.76 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:47:13,630 INFO [train.py:715] (5/8) Epoch 11, batch 24900, loss[loss=0.1133, simple_loss=0.1949, pruned_loss=0.01585, over 4959.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03265, over 972270.15 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:47:51,694 INFO [train.py:715] (5/8) Epoch 11, batch 24950, loss[loss=0.1642, simple_loss=0.2378, pruned_loss=0.04527, over 4770.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03273, over 972818.53 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:48:30,023 INFO [train.py:715] (5/8) Epoch 11, batch 25000, loss[loss=0.1393, simple_loss=0.2057, pruned_loss=0.03648, over 4972.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03253, over 973106.61 frames.], batch size: 28, lr: 1.94e-04
2022-05-07 05:49:08,319 INFO [train.py:715] (5/8) Epoch 11, batch 25050, loss[loss=0.1173, simple_loss=0.1837, pruned_loss=0.02544, over 4748.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03269, over 972730.02 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:49:49,679 INFO [train.py:715] (5/8) Epoch 11, batch 25100, loss[loss=0.1677, simple_loss=0.2332, pruned_loss=0.05109, over 4978.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03236, over 973726.72 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 05:50:27,839 INFO [train.py:715] (5/8) Epoch 11, batch 25150, loss[loss=0.1543, simple_loss=0.2217, pruned_loss=0.04346, over 4864.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03256, over 973803.39 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 05:51:06,431 INFO [train.py:715] (5/8) Epoch 11, batch 25200, loss[loss=0.1694, simple_loss=0.2382, pruned_loss=0.05025, over 4956.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03241, over 973878.66 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:51:45,283 INFO [train.py:715] (5/8) Epoch 11, batch 25250, loss[loss=0.1533, simple_loss=0.232, pruned_loss=0.03731, over 4694.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03248, over 973020.53 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:52:23,562 INFO [train.py:715] (5/8) Epoch 11, batch 25300, loss[loss=0.1293, simple_loss=0.2008, pruned_loss=0.02894, over 4886.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03218, over 972617.66 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:53:01,961 INFO [train.py:715] (5/8) Epoch 11, batch 25350, loss[loss=0.1565, simple_loss=0.2278, pruned_loss=0.04258, over 4684.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03213, over 971970.38 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:53:40,600 INFO [train.py:715] (5/8) Epoch 11, batch 25400, loss[loss=0.1432, simple_loss=0.2167, pruned_loss=0.0348, over 4813.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03222, over 970929.95 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 05:54:19,418 INFO [train.py:715] (5/8) Epoch 11, batch 25450, loss[loss=0.1444, simple_loss=0.2186, pruned_loss=0.03515, over 4748.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03235, over 971887.53 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:54:57,470 INFO [train.py:715] (5/8) Epoch 11, batch 25500, loss[loss=0.1396, simple_loss=0.205, pruned_loss=0.03712, over 4982.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03224, over 971663.06 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:55:36,081 INFO [train.py:715] (5/8) Epoch 11, batch 25550, loss[loss=0.1441, simple_loss=0.2282, pruned_loss=0.03001, over 4957.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03226, over 971976.40 frames.], batch size: 39, lr: 1.94e-04
2022-05-07 05:56:15,316 INFO [train.py:715] (5/8) Epoch 11, batch 25600, loss[loss=0.1445, simple_loss=0.2189, pruned_loss=0.03508, over 4952.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03237, over 972159.51 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:56:53,593 INFO [train.py:715] (5/8) Epoch 11, batch 25650, loss[loss=0.1366, simple_loss=0.2184, pruned_loss=0.02736, over 4880.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03219, over 971905.26 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:57:31,750 INFO [train.py:715] (5/8) Epoch 11, batch 25700, loss[loss=0.116, simple_loss=0.1958, pruned_loss=0.01809, over 4763.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03197, over 971653.89 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:58:10,580 INFO [train.py:715] (5/8) Epoch 11, batch 25750, loss[loss=0.1474, simple_loss=0.2183, pruned_loss=0.03825, over 4917.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03248, over 971074.84 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:58:48,901 INFO [train.py:715] (5/8) Epoch 11, batch 25800, loss[loss=0.1563, simple_loss=0.2323, pruned_loss=0.0402, over 4895.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03277, over 971152.76 frames.], batch size: 32, lr: 1.94e-04
2022-05-07 05:59:26,904 INFO [train.py:715] (5/8) Epoch 11, batch 25850, loss[loss=0.1088, simple_loss=0.1882, pruned_loss=0.01472, over 4905.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03291, over 972276.91 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:00:05,561 INFO [train.py:715] (5/8) Epoch 11, batch 25900, loss[loss=0.12, simple_loss=0.1834, pruned_loss=0.02828, over 4778.00 frames.], tot_loss[loss=0.138, simple_loss=0.2105, pruned_loss=0.0327, over 972656.05 frames.], batch size: 12, lr: 1.94e-04
2022-05-07 06:00:44,268 INFO [train.py:715] (5/8) Epoch 11, batch 25950, loss[loss=0.1232, simple_loss=0.2012, pruned_loss=0.02262, over 4775.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2105, pruned_loss=0.03252, over 972807.77 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 06:01:22,318 INFO [train.py:715] (5/8) Epoch 11, batch 26000, loss[loss=0.1314, simple_loss=0.202, pruned_loss=0.03046, over 4958.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03243, over 972038.27 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:02:00,400 INFO [train.py:715] (5/8) Epoch 11, batch 26050, loss[loss=0.1393, simple_loss=0.223, pruned_loss=0.02777, over 4951.00 frames.], tot_loss[loss=0.1383, simple_loss=0.211, pruned_loss=0.03275, over 972371.46 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:02:38,953 INFO [train.py:715] (5/8) Epoch 11, batch 26100, loss[loss=0.1546, simple_loss=0.2304, pruned_loss=0.03936, over 4881.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2112, pruned_loss=0.03307, over 971407.51 frames.], batch size: 39, lr: 1.94e-04
2022-05-07 06:03:17,344 INFO [train.py:715] (5/8) Epoch 11, batch 26150, loss[loss=0.1182, simple_loss=0.1897, pruned_loss=0.02335, over 4787.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2115, pruned_loss=0.03344, over 970972.29 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:03:55,313 INFO [train.py:715] (5/8) Epoch 11, batch 26200, loss[loss=0.1373, simple_loss=0.2096, pruned_loss=0.03249, over 4826.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03364, over 970193.54 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:04:32,930 INFO [train.py:715] (5/8) Epoch 11, batch 26250, loss[loss=0.1253, simple_loss=0.2042, pruned_loss=0.02321, over 4853.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03319, over 970616.00 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 06:05:10,977 INFO [train.py:715] (5/8) Epoch 11, batch 26300, loss[loss=0.1551, simple_loss=0.2227, pruned_loss=0.04377, over 4946.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03303, over 970754.34 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:05:48,409 INFO [train.py:715] (5/8) Epoch 11, batch 26350, loss[loss=0.1443, simple_loss=0.2228, pruned_loss=0.03286, over 4749.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03238, over 971482.57 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:06:25,428 INFO [train.py:715] (5/8) Epoch 11, batch 26400, loss[loss=0.1436, simple_loss=0.2202, pruned_loss=0.03354, over 4824.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03241, over 971367.43 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:07:03,857 INFO [train.py:715] (5/8) Epoch 11, batch 26450, loss[loss=0.1171, simple_loss=0.1861, pruned_loss=0.02409, over 4782.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03288, over 971599.46 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 06:07:41,340 INFO [train.py:715] (5/8) Epoch 11, batch 26500, loss[loss=0.1361, simple_loss=0.2077, pruned_loss=0.03226, over 4975.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03252, over 971747.42 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:08:19,082 INFO [train.py:715] (5/8) Epoch 11, batch 26550, loss[loss=0.1073, simple_loss=0.1829, pruned_loss=0.01585, over 4815.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03238, over 971970.76 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 06:08:56,820 INFO [train.py:715] (5/8) Epoch 11, batch 26600, loss[loss=0.1314, simple_loss=0.2104, pruned_loss=0.02615, over 4861.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03261, over 973027.58 frames.], batch size: 30, lr: 1.94e-04
2022-05-07 06:09:34,845 INFO [train.py:715] (5/8) Epoch 11, batch 26650, loss[loss=0.1311, simple_loss=0.2019, pruned_loss=0.03021, over 4743.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03209, over 972974.92 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:10:12,910 INFO [train.py:715] (5/8) Epoch 11, batch 26700, loss[loss=0.1718, simple_loss=0.2328, pruned_loss=0.05542, over 4902.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03274, over 972836.50 frames.], batch size: 38, lr: 1.94e-04
2022-05-07 06:10:49,897 INFO [train.py:715] (5/8) Epoch 11, batch 26750, loss[loss=0.119, simple_loss=0.1967, pruned_loss=0.02067, over 4797.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03289, over 973924.50 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 06:11:28,540 INFO [train.py:715] (5/8) Epoch 11, batch 26800, loss[loss=0.1792, simple_loss=0.2472, pruned_loss=0.05556, over 4855.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03285, over 973780.33 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 06:12:06,143 INFO [train.py:715] (5/8) Epoch 11, batch 26850, loss[loss=0.1313, simple_loss=0.2083, pruned_loss=0.0272, over 4811.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03233, over 973442.83 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:12:43,630 INFO [train.py:715] (5/8) Epoch 11, batch 26900, loss[loss=0.1361, simple_loss=0.2154, pruned_loss=0.02843, over 4799.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03214, over 972090.08 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:13:21,270 INFO [train.py:715] (5/8) Epoch 11, batch 26950, loss[loss=0.1399, simple_loss=0.2115, pruned_loss=0.03419, over 4845.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03276, over 972357.11 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:13:59,655 INFO [train.py:715] (5/8) Epoch 11, batch 27000, loss[loss=0.1616, simple_loss=0.2243, pruned_loss=0.04944, over 4836.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03261, over 972587.22 frames.], batch size: 32, lr: 1.94e-04
2022-05-07 06:13:59,655 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 06:14:09,117 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 06:14:47,548 INFO [train.py:715] (5/8) Epoch 11, batch 27050, loss[loss=0.1456, simple_loss=0.2248, pruned_loss=0.03325, over 4868.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03189, over 973060.31 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 06:15:25,150 INFO [train.py:715] (5/8) Epoch 11, batch 27100, loss[loss=0.1449, simple_loss=0.2248, pruned_loss=0.03245, over 4773.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03209, over 971801.51 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 06:16:02,383 INFO [train.py:715] (5/8) Epoch 11, batch 27150, loss[loss=0.1571, simple_loss=0.2164, pruned_loss=0.04885, over 4985.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03174, over 972114.94 frames.], batch size: 31, lr: 1.94e-04
2022-05-07 06:16:41,020 INFO [train.py:715] (5/8) Epoch 11, batch 27200, loss[loss=0.1603, simple_loss=0.2236, pruned_loss=0.04846, over 4937.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03208, over 971680.69 frames.], batch size: 23, lr: 1.94e-04
2022-05-07 06:17:18,730 INFO [train.py:715] (5/8) Epoch 11, batch 27250, loss[loss=0.1529, simple_loss=0.2223, pruned_loss=0.04177, over 4957.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03281, over 972655.99 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 06:17:56,618 INFO [train.py:715] (5/8) Epoch 11, batch 27300, loss[loss=0.1242, simple_loss=0.1967, pruned_loss=0.02586, over 4953.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03274, over 973083.43 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:18:34,289 INFO [train.py:715] (5/8) Epoch 11, batch 27350, loss[loss=0.1617, simple_loss=0.2303, pruned_loss=0.04655, over 4836.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03263, over 972269.86 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:19:13,064 INFO [train.py:715] (5/8) Epoch 11, batch 27400, loss[loss=0.1147, simple_loss=0.1952, pruned_loss=0.01715, over 4814.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03248, over 972713.11 frames.], batch size: 27, lr: 1.94e-04
2022-05-07 06:19:50,857 INFO [train.py:715] (5/8) Epoch 11, batch 27450, loss[loss=0.1501, simple_loss=0.2074, pruned_loss=0.04639, over 4989.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.0326, over 971623.48 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 06:20:28,120 INFO [train.py:715] (5/8) Epoch 11, batch 27500, loss[loss=0.1313, simple_loss=0.2005, pruned_loss=0.03111, over 4844.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03242, over 971796.14 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 06:21:07,285 INFO [train.py:715] (5/8) Epoch 11, batch 27550, loss[loss=0.1385, simple_loss=0.2052, pruned_loss=0.03589, over 4758.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03281, over 972188.13 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:21:45,752 INFO [train.py:715] (5/8) Epoch 11, batch 27600, loss[loss=0.1442, simple_loss=0.2248, pruned_loss=0.03186, over 4842.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03268, over 972246.45 frames.], batch size: 30, lr: 1.94e-04
2022-05-07 06:22:23,476 INFO [train.py:715] (5/8) Epoch 11, batch 27650, loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03399, over 4783.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03243, over 971302.13 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 06:23:01,300 INFO [train.py:715] (5/8) Epoch 11, batch 27700, loss[loss=0.1191, simple_loss=0.1843, pruned_loss=0.02694, over 4852.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03272, over 972189.90 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 06:23:39,626 INFO [train.py:715] (5/8) Epoch 11, batch 27750, loss[loss=0.1229, simple_loss=0.1903, pruned_loss=0.02777, over 4770.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03249, over 971746.04 frames.], batch size: 12, lr: 1.94e-04
2022-05-07 06:24:17,574 INFO [train.py:715] (5/8) Epoch 11, batch 27800, loss[loss=0.1584, simple_loss=0.2202, pruned_loss=0.04836, over 4873.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03309, over 971150.11 frames.], batch size: 32, lr: 1.93e-04
2022-05-07 06:24:54,557 INFO [train.py:715] (5/8) Epoch 11, batch 27850, loss[loss=0.1298, simple_loss=0.2064, pruned_loss=0.02662, over 4951.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03303, over 972384.28 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:25:32,919 INFO [train.py:715] (5/8) Epoch 11, batch 27900, loss[loss=0.1105, simple_loss=0.1764, pruned_loss=0.02235, over 4750.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2106, pruned_loss=0.03249, over 971875.89 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 06:26:10,974 INFO [train.py:715] (5/8) Epoch 11, batch 27950, loss[loss=0.1442, simple_loss=0.2176, pruned_loss=0.0354, over 4820.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03271, over 972628.27 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 06:26:48,583 INFO [train.py:715] (5/8) Epoch 11, batch 28000, loss[loss=0.1341, simple_loss=0.2178, pruned_loss=0.0252, over 4750.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2104, pruned_loss=0.03231, over 972304.13 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 06:27:26,139 INFO [train.py:715] (5/8) Epoch 11, batch 28050, loss[loss=0.1202, simple_loss=0.1967, pruned_loss=0.02183, over 4786.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03241, over 973538.60 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:28:04,142 INFO [train.py:715] (5/8) Epoch 11, batch 28100, loss[loss=0.1322, simple_loss=0.2075, pruned_loss=0.02842, over 4788.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03207, over 973729.72 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:28:41,422 INFO [train.py:715] (5/8) Epoch 11, batch 28150, loss[loss=0.122, simple_loss=0.1924, pruned_loss=0.0258, over 4981.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03237, over 974613.21 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:29:18,869 INFO [train.py:715] (5/8) Epoch 11, batch 28200, loss[loss=0.1252, simple_loss=0.2053, pruned_loss=0.02259, over 4987.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03277, over 975033.22 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:29:57,423 INFO [train.py:715] (5/8) Epoch 11, batch 28250, loss[loss=0.1119, simple_loss=0.1827, pruned_loss=0.02052, over 4813.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03261, over 974095.02 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:30:34,927 INFO [train.py:715] (5/8) Epoch 11, batch 28300, loss[loss=0.1117, simple_loss=0.1951, pruned_loss=0.01412, over 4969.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03176, over 973918.12 frames.], batch size: 28, lr: 1.93e-04
2022-05-07 06:31:12,830 INFO [train.py:715] (5/8) Epoch 11, batch 28350, loss[loss=0.1266, simple_loss=0.1999, pruned_loss=0.02668, over 4859.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03216, over 973824.13 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 06:31:50,525 INFO [train.py:715] (5/8) Epoch 11, batch 28400, loss[loss=0.1591, simple_loss=0.218, pruned_loss=0.0501, over 4836.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03277, over 974138.64 frames.], batch size: 32, lr: 1.93e-04
2022-05-07 06:32:28,899 INFO [train.py:715] (5/8) Epoch 11, batch 28450, loss[loss=0.1381, simple_loss=0.2195, pruned_loss=0.02839, over 4989.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03256, over 974169.74 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:33:06,937 INFO [train.py:715] (5/8) Epoch 11, batch 28500, loss[loss=0.1414, simple_loss=0.2176, pruned_loss=0.03261, over 4735.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03243, over 973658.71 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 06:33:44,632 INFO [train.py:715] (5/8) Epoch 11, batch 28550, loss[loss=0.1173, simple_loss=0.1854, pruned_loss=0.02465, over 4795.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03224, over 973333.48 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:34:23,469 INFO [train.py:715] (5/8) Epoch 11, batch 28600, loss[loss=0.1631, simple_loss=0.2357, pruned_loss=0.04524, over 4829.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03277, over 972900.17 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:35:01,435 INFO [train.py:715] (5/8) Epoch 11, batch 28650, loss[loss=0.1149, simple_loss=0.1924, pruned_loss=0.0187, over 4839.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03279, over 972836.37 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 06:35:39,422 INFO [train.py:715] (5/8) Epoch 11, batch 28700, loss[loss=0.1529, simple_loss=0.2239, pruned_loss=0.04098, over 4981.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03297, over 973247.34 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:36:17,176 INFO [train.py:715] (5/8) Epoch 11, batch 28750, loss[loss=0.1498, simple_loss=0.228, pruned_loss=0.03577, over 4788.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.0328, over 972848.28 frames.], batch size: 23, lr: 1.93e-04
2022-05-07 06:36:55,924 INFO [train.py:715] (5/8) Epoch 11, batch 28800, loss[loss=0.1535, simple_loss=0.2291, pruned_loss=0.039, over 4890.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03329, over 971863.09 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:37:33,392 INFO [train.py:715] (5/8) Epoch 11, batch 28850, loss[loss=0.1435, simple_loss=0.2125, pruned_loss=0.03731, over 4934.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2118, pruned_loss=0.03331, over 972023.90 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 06:38:10,807 INFO [train.py:715] (5/8) Epoch 11, batch 28900, loss[loss=0.149, simple_loss=0.2257, pruned_loss=0.03617, over 4969.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03317, over 972813.13 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:38:49,568 INFO [train.py:715] (5/8) Epoch 11, batch 28950, loss[loss=0.1259, simple_loss=0.2085, pruned_loss=0.02169, over 4986.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03299, over 973383.97 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:39:27,039 INFO [train.py:715] (5/8) Epoch 11, batch 29000, loss[loss=0.1332, simple_loss=0.2103, pruned_loss=0.02803, over 4939.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03359, over 973409.98 frames.], batch size: 23, lr: 1.93e-04
2022-05-07 06:40:04,957 INFO [train.py:715] (5/8) Epoch 11, batch 29050, loss[loss=0.1559, simple_loss=0.2299, pruned_loss=0.04094, over 4784.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03341, over 972525.28 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 06:40:42,751 INFO [train.py:715] (5/8) Epoch 11, batch 29100, loss[loss=0.1389, simple_loss=0.2136, pruned_loss=0.03212, over 4826.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03352, over 972056.45 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:41:21,083 INFO [train.py:715] (5/8) Epoch 11, batch 29150, loss[loss=0.1202, simple_loss=0.1969, pruned_loss=0.02178, over 4765.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03318, over 971628.59 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:41:58,819 INFO [train.py:715] (5/8) Epoch 11, batch 29200, loss[loss=0.1384, simple_loss=0.219, pruned_loss=0.0289, over 4792.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03279, over 972388.47 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 06:42:36,370 INFO [train.py:715] (5/8) Epoch 11, batch 29250, loss[loss=0.1205, simple_loss=0.1918, pruned_loss=0.02453, over 4822.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2131, pruned_loss=0.033, over 971694.06 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:43:15,063 INFO [train.py:715] (5/8) Epoch 11, batch 29300, loss[loss=0.1292, simple_loss=0.2043, pruned_loss=0.02706, over 4864.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2134, pruned_loss=0.03323, over 971227.17 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 06:43:53,137 INFO [train.py:715] (5/8) Epoch 11, batch 29350, loss[loss=0.1157, simple_loss=0.196, pruned_loss=0.01768, over 4989.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2128, pruned_loss=0.03301, over 970790.38 frames.], batch size: 28, lr: 1.93e-04
2022-05-07 06:44:30,900 INFO [train.py:715] (5/8) Epoch 11, batch 29400, loss[loss=0.1229, simple_loss=0.2026, pruned_loss=0.02156, over 4812.00 frames.], tot_loss[loss=0.1395, simple_loss=0.213, pruned_loss=0.03294, over 970644.12 frames.], batch size: 27, lr: 1.93e-04
2022-05-07 06:45:08,811 INFO [train.py:715] (5/8) Epoch 11, batch 29450, loss[loss=0.1369, simple_loss=0.2122, pruned_loss=0.03079, over 4819.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03288, over 970628.22 frames.], batch size: 27, lr: 1.93e-04
2022-05-07 06:45:46,709 INFO [train.py:715] (5/8) Epoch 11, batch 29500, loss[loss=0.1189, simple_loss=0.1906, pruned_loss=0.02358, over 4774.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03297, over 971072.77 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 06:46:25,302 INFO [train.py:715] (5/8) Epoch 11, batch 29550, loss[loss=0.1525, simple_loss=0.2376, pruned_loss=0.03372, over 4823.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03259, over 972139.85 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:47:02,907 INFO [train.py:715] (5/8) Epoch 11, batch 29600, loss[loss=0.1266, simple_loss=0.2048, pruned_loss=0.02416, over 4946.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03249, over 971558.72 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 06:47:41,473 INFO [train.py:715] (5/8) Epoch 11, batch 29650, loss[loss=0.1515, simple_loss=0.2182, pruned_loss=0.04234, over 4861.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03266, over 971531.59 frames.], batch size: 32, lr: 1.93e-04
2022-05-07 06:48:19,466 INFO [train.py:715] (5/8) Epoch 11, batch 29700, loss[loss=0.139, simple_loss=0.216, pruned_loss=0.031, over 4810.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03364, over 972266.86 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:48:57,624 INFO [train.py:715] (5/8) Epoch 11, batch 29750, loss[loss=0.1431, simple_loss=0.2187, pruned_loss=0.0337, over 4807.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03308, over 972923.63 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:49:35,435 INFO [train.py:715] (5/8) Epoch 11, batch 29800, loss[loss=0.1368, simple_loss=0.2172, pruned_loss=0.02826, over 4941.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03306, over 973151.11 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:50:13,827 INFO [train.py:715] (5/8) Epoch 11, batch 29850, loss[loss=0.1807, simple_loss=0.2448, pruned_loss=0.05831, over 4955.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2131, pruned_loss=0.0331, over 972992.26 frames.], batch size: 39, lr: 1.93e-04
2022-05-07 06:50:52,362 INFO [train.py:715] (5/8) Epoch 11, batch 29900, loss[loss=0.1574, simple_loss=0.2281, pruned_loss=0.04333, over 4818.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03283, over 973466.10 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:51:29,990 INFO [train.py:715] (5/8) Epoch 11, batch 29950, loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02819, over 4912.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03279, over 972875.83 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 06:52:08,178 INFO [train.py:715] (5/8) Epoch 11, batch 30000, loss[loss=0.1428, simple_loss=0.2192, pruned_loss=0.03323, over 4928.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2124, pruned_loss=0.03251, over 973111.19 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 06:52:08,179 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 06:52:17,626 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01095, over 914524.00 frames.
2022-05-07 06:52:56,515 INFO [train.py:715] (5/8) Epoch 11, batch 30050, loss[loss=0.1561, simple_loss=0.2252, pruned_loss=0.0435, over 4707.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03257, over 973420.21 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:53:34,389 INFO [train.py:715] (5/8) Epoch 11, batch 30100, loss[loss=0.1254, simple_loss=0.1946, pruned_loss=0.0281, over 4988.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03255, over 972804.67 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:54:13,053 INFO [train.py:715] (5/8) Epoch 11, batch 30150, loss[loss=0.1422, simple_loss=0.2132, pruned_loss=0.03567, over 4903.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03317, over 972865.99 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:54:50,401 INFO [train.py:715] (5/8) Epoch 11, batch 30200, loss[loss=0.1658, simple_loss=0.2294, pruned_loss=0.05113, over 4901.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03278, over 972770.55 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:55:29,245 INFO [train.py:715] (5/8) Epoch 11, batch 30250, loss[loss=0.1544, simple_loss=0.2283, pruned_loss=0.04019, over 4970.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.0331, over 972892.79 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:56:07,230 INFO [train.py:715] (5/8) Epoch 11, batch 30300, loss[loss=0.1165, simple_loss=0.1958, pruned_loss=0.01863, over 4791.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03299, over 973079.28 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:56:45,178 INFO [train.py:715] (5/8) Epoch 11, batch 30350, loss[loss=0.1152, simple_loss=0.1985, pruned_loss=0.01594, over 4933.00 frames.], tot_loss[loss=0.14, simple_loss=0.2134, pruned_loss=0.03335, over 972754.83 frames.], batch size: 23, lr: 1.93e-04
2022-05-07 06:57:23,262 INFO [train.py:715] (5/8) Epoch 11, batch 30400, loss[loss=0.1327, simple_loss=0.213, pruned_loss=0.02621, over 4977.00 frames.], tot_loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.03271, over 971765.03 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 06:58:01,501 INFO [train.py:715] (5/8) Epoch 11, batch 30450, loss[loss=0.1388, simple_loss=0.2137, pruned_loss=0.03196, over 4833.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.0325, over 971683.91 frames.], batch size: 32, lr: 1.93e-04
2022-05-07 06:58:39,332 INFO [train.py:715] (5/8) Epoch 11, batch 30500, loss[loss=0.1304, simple_loss=0.2062, pruned_loss=0.02727, over 4966.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03313, over 972093.08 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 06:59:17,144 INFO [train.py:715] (5/8) Epoch 11, batch 30550, loss[loss=0.1478, simple_loss=0.2292, pruned_loss=0.03322, over 4777.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03305, over 972134.16 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:59:56,406 INFO [train.py:715] (5/8) Epoch 11, batch 30600, loss[loss=0.1151, simple_loss=0.1962, pruned_loss=0.01701, over 4815.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03324, over 972452.51 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 07:00:35,034 INFO [train.py:715] (5/8) Epoch 11, batch 30650, loss[loss=0.1303, simple_loss=0.2077, pruned_loss=0.02642, over 4960.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03302, over 971538.14 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 07:01:13,829 INFO [train.py:715] (5/8) Epoch 11, batch 30700, loss[loss=0.141, simple_loss=0.206, pruned_loss=0.03802, over 4862.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03266, over 971902.91 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 07:01:52,335 INFO [train.py:715] (5/8) Epoch 11, batch 30750, loss[loss=0.1869, simple_loss=0.2538, pruned_loss=0.05994, over 4904.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.0331, over 971977.12 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:02:30,947 INFO [train.py:715] (5/8) Epoch 11, batch 30800, loss[loss=0.1197, simple_loss=0.2019, pruned_loss=0.01874, over 4880.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2104, pruned_loss=0.03258, over 971815.52 frames.], batch size: 22, lr: 1.93e-04
2022-05-07 07:03:09,708 INFO [train.py:715] (5/8) Epoch 11, batch 30850, loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03132, over 4758.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03254, over 972172.49 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 07:03:48,267 INFO [train.py:715] (5/8) Epoch 11, batch 30900, loss[loss=0.1455, simple_loss=0.218, pruned_loss=0.03646, over 4916.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03233, over 973248.45 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:04:27,073 INFO [train.py:715] (5/8) Epoch 11, batch 30950, loss[loss=0.1302, simple_loss=0.1948, pruned_loss=0.03276, over 4816.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2108, pruned_loss=0.03269, over 973072.97 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 07:05:06,006 INFO [train.py:715] (5/8) Epoch 11, batch 31000, loss[loss=0.1243, simple_loss=0.2024, pruned_loss=0.02307, over 4816.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03285, over 972093.28 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 07:05:44,522 INFO [train.py:715] (5/8) Epoch 11, batch 31050, loss[loss=0.1462, simple_loss=0.2065, pruned_loss=0.04296, over 4927.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03275, over 971492.71 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 07:06:23,342 INFO [train.py:715] (5/8) Epoch 11, batch 31100, loss[loss=0.1422, simple_loss=0.2232, pruned_loss=0.03058, over 4802.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03247, over 971341.74 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 07:07:01,740 INFO [train.py:715] (5/8) Epoch 11, batch 31150, loss[loss=0.1268, simple_loss=0.1999, pruned_loss=0.02687, over 4797.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03253, over 971249.06 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 07:07:39,379 INFO [train.py:715] (5/8) Epoch 11, batch 31200, loss[loss=0.15, simple_loss=0.2191, pruned_loss=0.04043, over 4787.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2111, pruned_loss=0.03285, over 971458.81 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:08:17,481 INFO [train.py:715] (5/8) Epoch 11, batch 31250, loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02851, over 4828.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2113, pruned_loss=0.03275, over 971822.61 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 07:08:55,764 INFO [train.py:715] (5/8) Epoch 11, batch 31300, loss[loss=0.1425, simple_loss=0.2206, pruned_loss=0.03215, over 4809.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03275, over 972042.05 frames.], batch size: 27, lr: 1.93e-04
2022-05-07 07:09:33,560 INFO [train.py:715] (5/8) Epoch 11, batch 31350, loss[loss=0.1386, simple_loss=0.2248, pruned_loss=0.02617, over 4794.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03277, over 972762.96 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 07:10:10,908 INFO [train.py:715] (5/8) Epoch 11, batch 31400, loss[loss=0.1348, simple_loss=0.217, pruned_loss=0.02635, over 4803.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03236, over 973245.47 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 07:10:48,405 INFO [train.py:715] (5/8) Epoch 11, batch 31450, loss[loss=0.1264, simple_loss=0.2068, pruned_loss=0.02302, over 4807.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03201, over 973022.92 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 07:11:26,019 INFO [train.py:715] (5/8) Epoch 11, batch 31500, loss[loss=0.1467, simple_loss=0.2255, pruned_loss=0.03395, over 4765.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03206, over 973168.16 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 07:12:03,665 INFO [train.py:715] (5/8) Epoch 11, batch 31550, loss[loss=0.131, simple_loss=0.2079, pruned_loss=0.02703, over 4988.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03192, over 973954.99 frames.], batch size: 28, lr: 1.93e-04
2022-05-07 07:12:41,668 INFO [train.py:715] (5/8) Epoch 11, batch 31600, loss[loss=0.1362, simple_loss=0.1981, pruned_loss=0.03715, over 4815.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.0328, over 974069.59 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 07:13:19,756 INFO [train.py:715] (5/8) Epoch 11, batch 31650, loss[loss=0.1118, simple_loss=0.1938, pruned_loss=0.01492, over 4854.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2129, pruned_loss=0.03309, over 973713.86 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 07:13:57,688 INFO [train.py:715] (5/8) Epoch 11, batch 31700, loss[loss=0.1099, simple_loss=0.1812, pruned_loss=0.0193, over 4956.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03284, over 973515.68 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 07:14:35,212 INFO [train.py:715] (5/8) Epoch 11, batch 31750, loss[loss=0.1599, simple_loss=0.2306, pruned_loss=0.04461, over 4838.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03275, over 973538.82 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 07:15:14,060 INFO [train.py:715] (5/8) Epoch 11, batch 31800, loss[loss=0.1343, simple_loss=0.2064, pruned_loss=0.03107, over 4978.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03222, over 974359.07 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 07:15:52,638 INFO [train.py:715] (5/8) Epoch 11, batch 31850, loss[loss=0.1656, simple_loss=0.2304, pruned_loss=0.05045, over 4885.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2126, pruned_loss=0.03225, over 974422.18 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 07:16:30,870 INFO [train.py:715] (5/8) Epoch 11, batch 31900, loss[loss=0.1488, simple_loss=0.2191, pruned_loss=0.03924, over 4768.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2132, pruned_loss=0.03284, over 973593.80 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 07:17:09,162 INFO [train.py:715] (5/8) Epoch 11, batch 31950, loss[loss=0.1423, simple_loss=0.2269, pruned_loss=0.02879, over 4915.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2121, pruned_loss=0.03216, over 973331.55 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 07:17:47,943 INFO [train.py:715] (5/8) Epoch 11, batch 32000, loss[loss=0.1714, simple_loss=0.2473, pruned_loss=0.04773, over 4987.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.0322, over 973841.12 frames.], batch size: 28, lr: 1.93e-04
2022-05-07 07:18:26,169 INFO [train.py:715] (5/8) Epoch 11, batch 32050, loss[loss=0.1325, simple_loss=0.2105, pruned_loss=0.02727, over 4958.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 973147.36 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 07:19:04,553 INFO [train.py:715] (5/8) Epoch 11, batch 32100, loss[loss=0.131, simple_loss=0.2024, pruned_loss=0.02983, over 4781.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03178, over 972827.95 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:19:42,570 INFO [train.py:715] (5/8) Epoch 11, batch 32150, loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03523, over 4944.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.0321, over 972495.39 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:20:19,991 INFO [train.py:715] (5/8) Epoch 11, batch 32200, loss[loss=0.1187, simple_loss=0.1894, pruned_loss=0.02398, over 4941.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03213, over 972706.86 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:20:57,515 INFO [train.py:715] (5/8) Epoch 11, batch 32250, loss[loss=0.1748, simple_loss=0.2412, pruned_loss=0.05417, over 4869.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2101, pruned_loss=0.03225, over 973328.06 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:21:35,348 INFO [train.py:715] (5/8) Epoch 11, batch 32300, loss[loss=0.1197, simple_loss=0.2001, pruned_loss=0.01958, over 4763.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03203, over 973152.34 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:22:13,997 INFO [train.py:715] (5/8) Epoch 11, batch 32350, loss[loss=0.1481, simple_loss=0.2165, pruned_loss=0.03981, over 4764.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03217, over 973150.42 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:22:51,416 INFO [train.py:715] (5/8) Epoch 11, batch 32400, loss[loss=0.1609, simple_loss=0.2299, pruned_loss=0.04593, over 4820.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03242, over 972996.02 frames.], batch size: 25, lr: 1.92e-04
2022-05-07 07:23:29,418 INFO [train.py:715] (5/8) Epoch 11, batch 32450, loss[loss=0.1404, simple_loss=0.2175, pruned_loss=0.03167, over 4906.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03239, over 972441.91 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:24:07,458 INFO [train.py:715] (5/8) Epoch 11, batch 32500, loss[loss=0.1148, simple_loss=0.1908, pruned_loss=0.01941, over 4889.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03232, over 972153.23 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:24:45,517 INFO [train.py:715] (5/8) Epoch 11, batch 32550, loss[loss=0.1561, simple_loss=0.2303, pruned_loss=0.04094, over 4848.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.0327, over 972057.23 frames.], batch size: 30, lr: 1.92e-04
2022-05-07 07:25:23,172 INFO [train.py:715] (5/8) Epoch 11, batch 32600, loss[loss=0.1241, simple_loss=0.1917, pruned_loss=0.02829, over 4802.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03268, over 971607.72 frames.], batch size: 24, lr: 1.92e-04
2022-05-07 07:26:01,258 INFO [train.py:715] (5/8) Epoch 11, batch 32650, loss[loss=0.1427, simple_loss=0.2172, pruned_loss=0.03407, over 4962.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 971538.54 frames.], batch size: 35, lr: 1.92e-04
2022-05-07 07:26:39,445 INFO [train.py:715] (5/8) Epoch 11, batch 32700, loss[loss=0.1229, simple_loss=0.1984, pruned_loss=0.02368, over 4975.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03196, over 971300.95 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:27:16,890 INFO [train.py:715] (5/8) Epoch 11, batch 32750, loss[loss=0.134, simple_loss=0.2129, pruned_loss=0.02751, over 4921.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03191, over 972243.55 frames.], batch size: 29, lr: 1.92e-04
2022-05-07 07:27:55,657 INFO [train.py:715] (5/8) Epoch 11, batch 32800, loss[loss=0.1247, simple_loss=0.1956, pruned_loss=0.02687, over 4956.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2115, pruned_loss=0.03176, over 972105.44 frames.], batch size: 24, lr: 1.92e-04
2022-05-07 07:28:35,368 INFO [train.py:715] (5/8) Epoch 11, batch 32850, loss[loss=0.1253, simple_loss=0.201, pruned_loss=0.02483, over 4880.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03172, over 971496.10 frames.], batch size: 22, lr: 1.92e-04
2022-05-07 07:29:13,922 INFO [train.py:715] (5/8) Epoch 11, batch 32900, loss[loss=0.1337, simple_loss=0.2149, pruned_loss=0.02627, over 4982.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.0319, over 971331.84 frames.], batch size: 25, lr: 1.92e-04
2022-05-07 07:29:52,133 INFO [train.py:715] (5/8) Epoch 11, batch 32950, loss[loss=0.1064, simple_loss=0.1797, pruned_loss=0.0165, over 4767.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03167, over 971504.17 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:30:31,048 INFO [train.py:715] (5/8) Epoch 11, batch 33000, loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03447, over 4825.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03143, over 971705.47 frames.], batch size: 30, lr: 1.92e-04
2022-05-07 07:30:31,049 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 07:30:40,493 INFO [train.py:742] (5/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1899, pruned_loss=0.0109, over 914524.00 frames.
2022-05-07 07:31:19,416 INFO [train.py:715] (5/8) Epoch 11, batch 33050, loss[loss=0.1676, simple_loss=0.2394, pruned_loss=0.04788, over 4838.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.0313, over 971848.21 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:32:00,920 INFO [train.py:715] (5/8) Epoch 11, batch 33100, loss[loss=0.1584, simple_loss=0.2287, pruned_loss=0.04403, over 4874.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03172, over 971762.93 frames.], batch size: 22, lr: 1.92e-04
2022-05-07 07:32:38,878 INFO [train.py:715] (5/8) Epoch 11, batch 33150, loss[loss=0.1522, simple_loss=0.2217, pruned_loss=0.04136, over 4781.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03175, over 971837.22 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:33:17,492 INFO [train.py:715] (5/8) Epoch 11, batch 33200, loss[loss=0.1516, simple_loss=0.2334, pruned_loss=0.03488, over 4919.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.032, over 971788.23 frames.], batch size: 39, lr: 1.92e-04
2022-05-07 07:33:56,618 INFO [train.py:715] (5/8) Epoch 11, batch 33250, loss[loss=0.1326, simple_loss=0.203, pruned_loss=0.03108, over 4828.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03243, over 972460.03 frames.], batch size: 26, lr: 1.92e-04
2022-05-07 07:34:35,410 INFO [train.py:715] (5/8) Epoch 11, batch 33300, loss[loss=0.1466, simple_loss=0.2216, pruned_loss=0.03583, over 4823.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2124, pruned_loss=0.03244, over 972808.54 frames.], batch size: 27, lr: 1.92e-04
2022-05-07 07:35:13,284 INFO [train.py:715] (5/8) Epoch 11, batch 33350, loss[loss=0.1451, simple_loss=0.2147, pruned_loss=0.03777, over 4858.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03265, over 973030.47 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:35:51,702 INFO [train.py:715] (5/8) Epoch 11, batch 33400, loss[loss=0.1209, simple_loss=0.1937, pruned_loss=0.02401, over 4917.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.033, over 972867.65 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:36:30,392 INFO [train.py:715] (5/8) Epoch 11, batch 33450, loss[loss=0.1459, simple_loss=0.2266, pruned_loss=0.03262, over 4945.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03243, over 971725.15 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:37:08,730 INFO [train.py:715] (5/8) Epoch 11, batch 33500, loss[loss=0.1451, simple_loss=0.2257, pruned_loss=0.03224, over 4913.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03243, over 971998.89 frames.], batch size: 22, lr: 1.92e-04
2022-05-07 07:37:47,175 INFO [train.py:715] (5/8) Epoch 11, batch 33550, loss[loss=0.1103, simple_loss=0.1839, pruned_loss=0.01837, over 4797.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03231, over 971436.07 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:38:25,761 INFO [train.py:715] (5/8) Epoch 11, batch 33600, loss[loss=0.1347, simple_loss=0.2119, pruned_loss=0.0288, over 4693.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03235, over 971812.53 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:39:04,166 INFO [train.py:715] (5/8) Epoch 11, batch 33650, loss[loss=0.1078, simple_loss=0.1782, pruned_loss=0.01874, over 4781.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03221, over 971650.99 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:39:42,291 INFO [train.py:715] (5/8) Epoch 11, batch 33700, loss[loss=0.1518, simple_loss=0.2164, pruned_loss=0.0436, over 4842.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03215, over 972269.56 frames.], batch size: 32, lr: 1.92e-04
2022-05-07 07:40:20,577 INFO [train.py:715] (5/8) Epoch 11, batch 33750, loss[loss=0.1235, simple_loss=0.2038, pruned_loss=0.02162, over 4977.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2108, pruned_loss=0.03128, over 972493.66 frames.], batch size: 24, lr: 1.92e-04
2022-05-07 07:40:59,159 INFO [train.py:715] (5/8) Epoch 11, batch 33800, loss[loss=0.1742, simple_loss=0.2486, pruned_loss=0.04992, over 4945.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.0317, over 972961.79 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:41:37,147 INFO [train.py:715] (5/8) Epoch 11, batch 33850, loss[loss=0.1547, simple_loss=0.2225, pruned_loss=0.04339, over 4950.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03153, over 973710.41 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:42:15,181 INFO [train.py:715] (5/8) Epoch 11, batch 33900, loss[loss=0.1301, simple_loss=0.2078, pruned_loss=0.02613, over 4797.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03173, over 973532.40 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:42:53,933 INFO [train.py:715] (5/8) Epoch 11, batch 33950, loss[loss=0.1215, simple_loss=0.1956, pruned_loss=0.0237, over 4935.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03184, over 973102.38 frames.], batch size: 29, lr: 1.92e-04
2022-05-07 07:43:32,251 INFO [train.py:715] (5/8) Epoch 11, batch 34000, loss[loss=0.1264, simple_loss=0.2042, pruned_loss=0.0243, over 4783.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03211, over 972025.07 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:44:10,350 INFO [train.py:715] (5/8) Epoch 11, batch 34050, loss[loss=0.1314, simple_loss=0.2111, pruned_loss=0.02582, over 4772.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.0317, over 971916.43 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:44:48,874 INFO [train.py:715] (5/8) Epoch 11, batch 34100, loss[loss=0.1257, simple_loss=0.2017, pruned_loss=0.02488, over 4783.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.0319, over 970313.67 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:45:27,613 INFO [train.py:715] (5/8) Epoch 11, batch 34150, loss[loss=0.146, simple_loss=0.2167, pruned_loss=0.03764, over 4892.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03214, over 971015.17 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:46:05,701 INFO [train.py:715] (5/8) Epoch 11, batch 34200, loss[loss=0.1221, simple_loss=0.2038, pruned_loss=0.02018, over 4851.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03194, over 971316.22 frames.], batch size: 20, lr: 1.92e-04
2022-05-07 07:46:44,125 INFO [train.py:715] (5/8) Epoch 11, batch 34250, loss[loss=0.138, simple_loss=0.2067, pruned_loss=0.03459, over 4803.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03241, over 971971.16 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:47:23,288 INFO [train.py:715] (5/8) Epoch 11, batch 34300, loss[loss=0.1214, simple_loss=0.2076, pruned_loss=0.01759, over 4962.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2122, pruned_loss=0.03255, over 971374.70 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:48:01,580 INFO [train.py:715] (5/8) Epoch 11, batch 34350, loss[loss=0.1392, simple_loss=0.2034, pruned_loss=0.03753, over 4774.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03301, over 972203.02 frames.], batch size: 12, lr: 1.92e-04
2022-05-07 07:48:40,022 INFO [train.py:715] (5/8) Epoch 11, batch 34400, loss[loss=0.1461, simple_loss=0.2135, pruned_loss=0.03936, over 4974.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03269, over 972684.24 frames.], batch size: 35, lr: 1.92e-04
2022-05-07 07:49:18,673 INFO [train.py:715] (5/8) Epoch 11, batch 34450, loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03342, over 4772.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03259, over 972540.64 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:49:57,850 INFO [train.py:715] (5/8) Epoch 11, batch 34500, loss[loss=0.1243, simple_loss=0.2015, pruned_loss=0.02352, over 4828.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03273, over 972861.57 frames.], batch size: 26, lr: 1.92e-04
2022-05-07 07:50:35,958 INFO [train.py:715] (5/8) Epoch 11, batch 34550, loss[loss=0.1271, simple_loss=0.1982, pruned_loss=0.02803, over 4941.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2124, pruned_loss=0.03256, over 972755.53 frames.], batch size: 35, lr: 1.92e-04
2022-05-07 07:51:12,742 INFO [train.py:715] (5/8) Epoch 11, batch 34600, loss[loss=0.1437, simple_loss=0.222, pruned_loss=0.03267, over 4940.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03242, over 972982.69 frames.], batch size: 29, lr: 1.92e-04
2022-05-07 07:51:50,532 INFO [train.py:715] (5/8) Epoch 11, batch 34650, loss[loss=0.1963, simple_loss=0.2766, pruned_loss=0.05802, over 4861.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03246, over 972731.88 frames.], batch size: 20, lr: 1.92e-04
2022-05-07 07:52:27,797 INFO [train.py:715] (5/8) Epoch 11, batch 34700, loss[loss=0.1243, simple_loss=0.207, pruned_loss=0.02077, over 4989.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.0332, over 972512.63 frames.], batch size: 28, lr: 1.92e-04
2022-05-07 07:53:04,318 INFO [train.py:715] (5/8) Epoch 11, batch 34750, loss[loss=0.1413, simple_loss=0.2071, pruned_loss=0.03772, over 4982.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03278, over 972255.62 frames.], batch size: 31, lr: 1.92e-04
2022-05-07 07:53:39,318 INFO [train.py:715] (5/8) Epoch 11, batch 34800, loss[loss=0.1262, simple_loss=0.1947, pruned_loss=0.02886, over 4926.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03245, over 972223.67 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:54:26,265 INFO [train.py:715] (5/8) Epoch 12, batch 0, loss[loss=0.1267, simple_loss=0.2043, pruned_loss=0.02455, over 4883.00 frames.], tot_loss[loss=0.1267, simple_loss=0.2043, pruned_loss=0.02455, over 4883.00 frames.], batch size: 22, lr: 1.85e-04
2022-05-07 07:55:04,630 INFO [train.py:715] (5/8) Epoch 12, batch 50, loss[loss=0.1715, simple_loss=0.2392, pruned_loss=0.05194, over 4908.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2125, pruned_loss=0.03441, over 219044.83 frames.], batch size: 39, lr: 1.85e-04
2022-05-07 07:55:42,694 INFO [train.py:715] (5/8) Epoch 12, batch 100, loss[loss=0.1449, simple_loss=0.2208, pruned_loss=0.03444, over 4755.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2103, pruned_loss=0.0327, over 385728.17 frames.], batch size: 19, lr: 1.85e-04
2022-05-07 07:56:21,320 INFO [train.py:715] (5/8) Epoch 12, batch 150, loss[loss=0.1411, simple_loss=0.2253, pruned_loss=0.02847, over 4813.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2112, pruned_loss=0.03315, over 515778.63 frames.], batch size: 26, lr: 1.85e-04
2022-05-07 07:56:59,064 INFO [train.py:715] (5/8) Epoch 12, batch 200, loss[loss=0.1605, simple_loss=0.248, pruned_loss=0.03648, over 4807.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03321, over 617707.68 frames.], batch size: 15, lr: 1.85e-04
2022-05-07 07:57:38,280 INFO [train.py:715] (5/8) Epoch 12, batch 250, loss[loss=0.122, simple_loss=0.1948, pruned_loss=0.02459, over 4880.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03293, over 695369.52 frames.], batch size: 16, lr: 1.85e-04
2022-05-07 07:58:16,541 INFO [train.py:715] (5/8) Epoch 12, batch 300, loss[loss=0.1359, simple_loss=0.2052, pruned_loss=0.03333, over 4818.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2108, pruned_loss=0.03274, over 756327.65 frames.], batch size: 27, lr: 1.84e-04
2022-05-07 07:58:54,471 INFO [train.py:715] (5/8) Epoch 12, batch 350, loss[loss=0.1311, simple_loss=0.2096, pruned_loss=0.02626, over 4818.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2117, pruned_loss=0.0333, over 804984.74 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 07:59:32,945 INFO [train.py:715] (5/8) Epoch 12, batch 400, loss[loss=0.108, simple_loss=0.1775, pruned_loss=0.01925, over 4770.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.03327, over 841580.26 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:00:10,577 INFO [train.py:715] (5/8) Epoch 12, batch 450, loss[loss=0.1311, simple_loss=0.1995, pruned_loss=0.03133, over 4892.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2112, pruned_loss=0.03314, over 870431.08 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:00:48,788 INFO [train.py:715] (5/8) Epoch 12, batch 500, loss[loss=0.1338, simple_loss=0.2056, pruned_loss=0.03096, over 4892.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03278, over 892990.18 frames.], batch size: 32, lr: 1.84e-04
2022-05-07 08:01:26,233 INFO [train.py:715] (5/8) Epoch 12, batch 550, loss[loss=0.1383, simple_loss=0.2083, pruned_loss=0.0342, over 4870.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03318, over 910795.36 frames.], batch size: 20, lr: 1.84e-04
2022-05-07 08:02:04,574 INFO [train.py:715] (5/8) Epoch 12, batch 600, loss[loss=0.1499, simple_loss=0.2146, pruned_loss=0.04264, over 4961.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03324, over 925184.23 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:02:41,617 INFO [train.py:715] (5/8) Epoch 12, batch 650, loss[loss=0.1931, simple_loss=0.2544, pruned_loss=0.0659, over 4789.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03365, over 935607.26 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:03:20,187 INFO [train.py:715] (5/8) Epoch 12, batch 700, loss[loss=0.1141, simple_loss=0.1926, pruned_loss=0.01785, over 4876.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03358, over 943728.19 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:03:58,807 INFO [train.py:715] (5/8) Epoch 12, batch 750, loss[loss=0.1433, simple_loss=0.2146, pruned_loss=0.03597, over 4960.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03286, over 951149.81 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:04:37,571 INFO [train.py:715] (5/8) Epoch 12, batch 800, loss[loss=0.1537, simple_loss=0.2333, pruned_loss=0.037, over 4904.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.0323, over 955595.80 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:05:16,050 INFO [train.py:715] (5/8) Epoch 12, batch 850, loss[loss=0.1507, simple_loss=0.2222, pruned_loss=0.03957, over 4689.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03241, over 959042.86 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:05:54,151 INFO [train.py:715] (5/8) Epoch 12, batch 900, loss[loss=0.1103, simple_loss=0.1913, pruned_loss=0.01463, over 4825.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03187, over 962242.16 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:06:32,490 INFO [train.py:715] (5/8) Epoch 12, batch 950, loss[loss=0.1245, simple_loss=0.1981, pruned_loss=0.02547, over 4961.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03143, over 964350.63 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:07:09,849 INFO [train.py:715] (5/8) Epoch 12, batch 1000, loss[loss=0.1399, simple_loss=0.2114, pruned_loss=0.03425, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03224, over 966347.38 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:07:47,342 INFO [train.py:715] (5/8) Epoch 12, batch 1050, loss[loss=0.1539, simple_loss=0.2256, pruned_loss=0.04106, over 4902.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03175, over 967042.45 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:08:25,194 INFO [train.py:715] (5/8) Epoch 12, batch 1100, loss[loss=0.1421, simple_loss=0.2158, pruned_loss=0.03422, over 4973.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 969707.61 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:09:03,089 INFO [train.py:715] (5/8) Epoch 12, batch 1150, loss[loss=0.1899, simple_loss=0.2631, pruned_loss=0.05835, over 4960.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03238, over 969352.62 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:09:41,431 INFO [train.py:715] (5/8) Epoch 12, batch 1200, loss[loss=0.1166, simple_loss=0.1907, pruned_loss=0.02128, over 4918.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03231, over 969771.44 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:10:18,738 INFO [train.py:715] (5/8) Epoch 12, batch 1250, loss[loss=0.1547, simple_loss=0.2231, pruned_loss=0.0432, over 4930.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03264, over 970736.63 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:10:56,844 INFO [train.py:715] (5/8) Epoch 12, batch 1300, loss[loss=0.1784, simple_loss=0.2462, pruned_loss=0.05529, over 4768.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03269, over 971416.28 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:11:33,986 INFO [train.py:715] (5/8) Epoch 12, batch 1350, loss[loss=0.1406, simple_loss=0.209, pruned_loss=0.03613, over 4965.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03274, over 971475.81 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:12:12,111 INFO [train.py:715] (5/8) Epoch 12, batch 1400, loss[loss=0.1228, simple_loss=0.1902, pruned_loss=0.02766, over 4863.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.03278, over 972267.56 frames.], batch size: 20, lr: 1.84e-04
2022-05-07 08:12:49,762 INFO [train.py:715] (5/8) Epoch 12, batch 1450, loss[loss=0.139, simple_loss=0.2095, pruned_loss=0.03424, over 4922.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03226, over 971863.54 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:13:27,680 INFO [train.py:715] (5/8) Epoch 12, batch 1500, loss[loss=0.1108, simple_loss=0.1871, pruned_loss=0.01722, over 4851.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03194, over 972553.89 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:14:05,277 INFO [train.py:715] (5/8) Epoch 12, batch 1550, loss[loss=0.1303, simple_loss=0.2157, pruned_loss=0.02243, over 4900.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03196, over 972223.75 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:14:42,471 INFO [train.py:715] (5/8) Epoch 12, batch 1600, loss[loss=0.1225, simple_loss=0.1906, pruned_loss=0.02713, over 4914.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.0315, over 971532.93 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:15:20,489 INFO [train.py:715] (5/8) Epoch 12, batch 1650, loss[loss=0.1349, simple_loss=0.2013, pruned_loss=0.03427, over 4850.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03159, over 972872.36 frames.], batch size: 30, lr: 1.84e-04
2022-05-07 08:15:57,868 INFO [train.py:715] (5/8) Epoch 12, batch 1700, loss[loss=0.1207, simple_loss=0.1878, pruned_loss=0.02681, over 4874.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03147, over 972781.55 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:16:35,314 INFO [train.py:715] (5/8) Epoch 12, batch 1750, loss[loss=0.1636, simple_loss=0.2408, pruned_loss=0.04317, over 4979.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.0323, over 973022.51 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:17:12,473 INFO [train.py:715] (5/8) Epoch 12, batch 1800, loss[loss=0.1274, simple_loss=0.1975, pruned_loss=0.02862, over 4983.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03251, over 973013.29 frames.], batch size: 28, lr: 1.84e-04
2022-05-07 08:17:50,169 INFO [train.py:715] (5/8) Epoch 12, batch 1850, loss[loss=0.1383, simple_loss=0.213, pruned_loss=0.03183, over 4949.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03202, over 973022.11 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:18:27,660 INFO [train.py:715] (5/8) Epoch 12, batch 1900, loss[loss=0.118, simple_loss=0.1982, pruned_loss=0.01888, over 4763.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03133, over 972566.21 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:19:05,285 INFO [train.py:715] (5/8) Epoch 12, batch 1950, loss[loss=0.1496, simple_loss=0.2334, pruned_loss=0.03295, over 4947.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03107, over 972239.52 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:19:43,102 INFO [train.py:715] (5/8) Epoch 12, batch 2000, loss[loss=0.136, simple_loss=0.209, pruned_loss=0.03154, over 4944.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03177, over 972234.74 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:20:21,264 INFO [train.py:715] (5/8) Epoch 12, batch 2050, loss[loss=0.1053, simple_loss=0.174, pruned_loss=0.01833, over 4736.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03147, over 971735.34 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:20:59,321 INFO [train.py:715] (5/8) Epoch 12, batch 2100, loss[loss=0.1582, simple_loss=0.2281, pruned_loss=0.04419, over 4975.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03181, over 972291.22 frames.], batch size: 28, lr: 1.84e-04
2022-05-07 08:21:36,625 INFO [train.py:715] (5/8) Epoch 12, batch 2150, loss[loss=0.1266, simple_loss=0.1998, pruned_loss=0.0267, over 4761.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03236, over 972311.87 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:22:14,598 INFO [train.py:715] (5/8) Epoch 12, batch 2200, loss[loss=0.1668, simple_loss=0.2342, pruned_loss=0.04973, over 4959.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03275, over 972188.28 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:22:52,522 INFO [train.py:715] (5/8) Epoch 12, batch 2250, loss[loss=0.1391, simple_loss=0.216, pruned_loss=0.0311, over 4754.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03238, over 972125.04 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:23:30,602 INFO [train.py:715] (5/8) Epoch 12, batch 2300, loss[loss=0.1258, simple_loss=0.2037, pruned_loss=0.02398, over 4735.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03198, over 971374.57 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:24:07,788 INFO [train.py:715] (5/8) Epoch 12, batch 2350, loss[loss=0.1314, simple_loss=0.2104, pruned_loss=0.02616, over 4877.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03164, over 971678.88 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:24:45,330 INFO [train.py:715] (5/8) Epoch 12, batch 2400, loss[loss=0.1244, simple_loss=0.1916, pruned_loss=0.02862, over 4991.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03162, over 972449.26 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:25:23,252 INFO [train.py:715] (5/8) Epoch 12, batch 2450, loss[loss=0.1373, simple_loss=0.2053, pruned_loss=0.03469, over 4842.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03157, over 971792.93 frames.], batch size: 30, lr: 1.84e-04
2022-05-07 08:26:00,043 INFO [train.py:715] (5/8) Epoch 12, batch 2500, loss[loss=0.1573, simple_loss=0.244, pruned_loss=0.03526, over 4808.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03144, over 971936.95 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:26:38,143 INFO [train.py:715] (5/8) Epoch 12, batch 2550, loss[loss=0.1437, simple_loss=0.2151, pruned_loss=0.03617, over 4976.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03136, over 971268.49 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:27:15,554 INFO [train.py:715] (5/8) Epoch 12, batch 2600, loss[loss=0.1152, simple_loss=0.1982, pruned_loss=0.01613, over 4815.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03146, over 971743.56 frames.], batch size: 26, lr: 1.84e-04
2022-05-07 08:27:54,371 INFO [train.py:715] (5/8) Epoch 12, batch 2650, loss[loss=0.1474, simple_loss=0.2206, pruned_loss=0.03706, over 4697.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03128, over 972304.08 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:28:32,744 INFO [train.py:715] (5/8) Epoch 12, batch 2700, loss[loss=0.123, simple_loss=0.1933, pruned_loss=0.02633, over 4988.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03133, over 972604.94 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:29:11,535 INFO [train.py:715] (5/8) Epoch 12, batch 2750, loss[loss=0.1304, simple_loss=0.2003, pruned_loss=0.03024, over 4827.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03107, over 972871.51 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:29:50,412 INFO [train.py:715] (5/8) Epoch 12, batch 2800, loss[loss=0.1362, simple_loss=0.2251, pruned_loss=0.0237, over 4800.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2104, pruned_loss=0.03119, over 972169.10 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:30:28,422 INFO [train.py:715] (5/8) Epoch 12, batch 2850, loss[loss=0.1228, simple_loss=0.192, pruned_loss=0.02684, over 4752.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.0314, over 972482.01 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:31:07,089 INFO [train.py:715] (5/8) Epoch 12, batch 2900, loss[loss=0.1199, simple_loss=0.1879, pruned_loss=0.02593, over 4908.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03184, over 972955.47 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:31:45,562 INFO [train.py:715] (5/8) Epoch 12, batch 2950, loss[loss=0.1688, simple_loss=0.2413, pruned_loss=0.04817, over 4880.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03202, over 973143.11 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:32:24,277 INFO [train.py:715] (5/8) Epoch 12, batch 3000, loss[loss=0.1741, simple_loss=0.2347, pruned_loss=0.05681, over 4946.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.0321, over 973402.13 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:32:24,277 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 08:32:33,756 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01082, over 914524.00 frames.
2022-05-07 08:33:11,809 INFO [train.py:715] (5/8) Epoch 12, batch 3050, loss[loss=0.1138, simple_loss=0.1867, pruned_loss=0.02043, over 4953.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03151, over 973170.74 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:33:49,495 INFO [train.py:715] (5/8) Epoch 12, batch 3100, loss[loss=0.1299, simple_loss=0.2084, pruned_loss=0.0257, over 4764.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03166, over 972507.55 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:34:27,408 INFO [train.py:715] (5/8) Epoch 12, batch 3150, loss[loss=0.1761, simple_loss=0.2557, pruned_loss=0.04829, over 4805.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03185, over 971931.64 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:35:05,544 INFO [train.py:715] (5/8) Epoch 12, batch 3200, loss[loss=0.1501, simple_loss=0.2282, pruned_loss=0.036, over 4845.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03212, over 972423.00 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:35:43,249 INFO [train.py:715] (5/8) Epoch 12, batch 3250, loss[loss=0.1689, simple_loss=0.221, pruned_loss=0.05833, over 4870.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03205, over 971915.72 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:36:21,484 INFO [train.py:715] (5/8) Epoch 12, batch 3300, loss[loss=0.1049, simple_loss=0.179, pruned_loss=0.01544, over 4755.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03134, over 972020.94 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:36:59,237 INFO [train.py:715] (5/8) Epoch 12, batch 3350, loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02841, over 4756.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03201, over 972797.63 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:37:37,376 INFO [train.py:715] (5/8) Epoch 12, batch 3400, loss[loss=0.1228, simple_loss=0.1947, pruned_loss=0.02543, over 4820.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03209, over 973430.36 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:38:14,960 INFO [train.py:715] (5/8) Epoch 12, batch 3450, loss[loss=0.1585, simple_loss=0.2252, pruned_loss=0.0459, over 4844.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03269, over 972938.56 frames.], batch size: 30, lr: 1.84e-04
2022-05-07 08:38:52,884 INFO [train.py:715] (5/8) Epoch 12, batch 3500, loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02882, over 4796.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03245, over 972454.06 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:39:31,086 INFO [train.py:715] (5/8) Epoch 12, batch 3550, loss[loss=0.1446, simple_loss=0.2225, pruned_loss=0.03335, over 4935.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03205, over 972856.53 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:40:08,795 INFO [train.py:715] (5/8) Epoch 12, batch 3600, loss[loss=0.1405, simple_loss=0.2166, pruned_loss=0.03224, over 4982.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03179, over 972522.27 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:40:46,533 INFO [train.py:715] (5/8) Epoch 12, batch 3650, loss[loss=0.1293, simple_loss=0.21, pruned_loss=0.0243, over 4946.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03166, over 973489.85 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:41:24,468 INFO [train.py:715] (5/8) Epoch 12, batch 3700, loss[loss=0.113, simple_loss=0.1883, pruned_loss=0.01884, over 4842.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2099, pruned_loss=0.03211, over 974022.64 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:42:02,374 INFO [train.py:715] (5/8) Epoch 12, batch 3750, loss[loss=0.129, simple_loss=0.2025, pruned_loss=0.0277, over 4936.00 frames.], tot_loss[loss=0.137, simple_loss=0.2097, pruned_loss=0.0321, over 973041.35 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:42:40,470 INFO [train.py:715] (5/8) Epoch 12, batch 3800, loss[loss=0.1212, simple_loss=0.1924, pruned_loss=0.02502, over 4983.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03224, over 973115.93 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:43:18,089 INFO [train.py:715] (5/8) Epoch 12, batch 3850, loss[loss=0.1316, simple_loss=0.1972, pruned_loss=0.03298, over 4696.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2099, pruned_loss=0.03214, over 973037.56 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:43:55,565 INFO [train.py:715] (5/8) Epoch 12, batch 3900, loss[loss=0.1467, simple_loss=0.2252, pruned_loss=0.03413, over 4885.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2094, pruned_loss=0.0318, over 972284.87 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:44:33,441 INFO [train.py:715] (5/8) Epoch 12, batch 3950, loss[loss=0.1431, simple_loss=0.2341, pruned_loss=0.02602, over 4683.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03193, over 972483.18 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:45:11,212 INFO [train.py:715] (5/8) Epoch 12, batch 4000, loss[loss=0.1344, simple_loss=0.2076, pruned_loss=0.03065, over 4744.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.0321, over 972442.67 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:45:49,153 INFO [train.py:715] (5/8) Epoch 12, batch 4050, loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03531, over 4809.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03225, over 972976.61 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:46:27,044 INFO [train.py:715] (5/8) Epoch 12, batch 4100, loss[loss=0.1303, simple_loss=0.1915, pruned_loss=0.03453, over 4854.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03233, over 972704.56 frames.], batch size: 32, lr: 1.84e-04
2022-05-07 08:47:05,070 INFO [train.py:715] (5/8) Epoch 12, batch 4150, loss[loss=0.1329, simple_loss=0.216, pruned_loss=0.02491, over 4828.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03272, over 973110.81 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:47:43,032 INFO [train.py:715] (5/8) Epoch 12, batch 4200, loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03873, over 4914.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03253, over 973408.31 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:48:20,658 INFO [train.py:715] (5/8) Epoch 12, batch 4250, loss[loss=0.1279, simple_loss=0.2045, pruned_loss=0.02564, over 4936.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03232, over 973583.77 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:48:58,347 INFO [train.py:715] (5/8) Epoch 12, batch 4300, loss[loss=0.1454, simple_loss=0.2268, pruned_loss=0.03201, over 4902.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03256, over 973080.12 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:49:37,514 INFO [train.py:715] (5/8) Epoch 12, batch 4350, loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04109, over 4987.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2114, pruned_loss=0.03305, over 973777.13 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:50:16,265 INFO [train.py:715] (5/8) Epoch 12, batch 4400, loss[loss=0.1331, simple_loss=0.2019, pruned_loss=0.03218, over 4824.00 frames.], tot_loss[loss=0.1382, simple_loss=0.211, pruned_loss=0.03268, over 974015.28 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:50:54,765 INFO [train.py:715] (5/8) Epoch 12, batch 4450, loss[loss=0.1321, simple_loss=0.203, pruned_loss=0.03057, over 4853.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03244, over 972790.39 frames.], batch size: 32, lr: 1.84e-04
2022-05-07 08:51:33,202 INFO [train.py:715] (5/8) Epoch 12, batch 4500, loss[loss=0.1303, simple_loss=0.1947, pruned_loss=0.03291, over 4688.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03227, over 972332.79 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:52:12,280 INFO [train.py:715] (5/8) Epoch 12, batch 4550, loss[loss=0.1309, simple_loss=0.2014, pruned_loss=0.03017, over 4915.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03248, over 972647.95 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:52:50,491 INFO [train.py:715] (5/8) Epoch 12, batch 4600, loss[loss=0.1568, simple_loss=0.2405, pruned_loss=0.03652, over 4922.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03236, over 973038.51 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:53:29,039 INFO [train.py:715] (5/8) Epoch 12, batch 4650, loss[loss=0.1709, simple_loss=0.2435, pruned_loss=0.04917, over 4918.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03281, over 972823.46 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:54:07,728 INFO [train.py:715] (5/8) Epoch 12, batch 4700, loss[loss=0.1438, simple_loss=0.2218, pruned_loss=0.03291, over 4762.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03284, over 972866.11 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:54:46,298 INFO [train.py:715] (5/8) Epoch 12, batch 4750, loss[loss=0.1385, simple_loss=0.2022, pruned_loss=0.03742, over 4810.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03247, over 972371.26 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:55:25,000 INFO [train.py:715] (5/8) Epoch 12, batch 4800, loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02953, over 4847.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03276, over 972540.71 frames.], batch size: 30, lr: 1.84e-04
2022-05-07 08:56:03,562 INFO [train.py:715] (5/8) Epoch 12, batch 4850, loss[loss=0.1012, simple_loss=0.1748, pruned_loss=0.01379, over 4729.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03243, over 973214.81 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:56:42,593 INFO [train.py:715] (5/8) Epoch 12, batch 4900, loss[loss=0.1199, simple_loss=0.1863, pruned_loss=0.02677, over 4862.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03264, over 973459.33 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 08:57:20,603 INFO [train.py:715] (5/8) Epoch 12, batch 4950, loss[loss=0.1501, simple_loss=0.2364, pruned_loss=0.03192, over 4777.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03259, over 971598.22 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 08:57:58,207 INFO [train.py:715] (5/8) Epoch 12, batch 5000, loss[loss=0.1181, simple_loss=0.1895, pruned_loss=0.02341, over 4908.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03248, over 971787.90 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 08:58:36,393 INFO [train.py:715] (5/8) Epoch 12, batch 5050, loss[loss=0.1317, simple_loss=0.2096, pruned_loss=0.02687, over 4992.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.0321, over 972164.47 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 08:59:13,985 INFO [train.py:715] (5/8) Epoch 12, batch 5100, loss[loss=0.128, simple_loss=0.2062, pruned_loss=0.02494, over 4928.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2102, pruned_loss=0.03239, over 971738.36 frames.], batch size: 23, lr: 1.83e-04
2022-05-07 08:59:52,112 INFO [train.py:715] (5/8) Epoch 12, batch 5150, loss[loss=0.1292, simple_loss=0.2147, pruned_loss=0.02189, over 4975.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2099, pruned_loss=0.0322, over 971809.79 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:00:30,012 INFO [train.py:715] (5/8) Epoch 12, batch 5200, loss[loss=0.1309, simple_loss=0.1958, pruned_loss=0.03299, over 4980.00 frames.], tot_loss[loss=0.136, simple_loss=0.2091, pruned_loss=0.03144, over 970581.89 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:01:08,126 INFO [train.py:715] (5/8) Epoch 12, batch 5250, loss[loss=0.1484, simple_loss=0.2083, pruned_loss=0.04429, over 4773.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03147, over 970680.17 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:01:45,992 INFO [train.py:715] (5/8) Epoch 12, batch 5300, loss[loss=0.1405, simple_loss=0.2077, pruned_loss=0.0367, over 4806.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2091, pruned_loss=0.0316, over 970305.88 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:02:24,111 INFO [train.py:715] (5/8) Epoch 12, batch 5350, loss[loss=0.1475, simple_loss=0.2187, pruned_loss=0.03815, over 4949.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03161, over 971338.48 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:03:02,672 INFO [train.py:715] (5/8) Epoch 12, batch 5400, loss[loss=0.1272, simple_loss=0.2028, pruned_loss=0.02585, over 4935.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2096, pruned_loss=0.03198, over 971151.66 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:03:40,515 INFO [train.py:715] (5/8) Epoch 12, batch 5450, loss[loss=0.1226, simple_loss=0.1969, pruned_loss=0.02411, over 4905.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2091, pruned_loss=0.03135, over 971552.79 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:04:18,719 INFO [train.py:715] (5/8) Epoch 12, batch 5500, loss[loss=0.1184, simple_loss=0.1961, pruned_loss=0.02032, over 4867.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03138, over 971847.65 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:04:56,507 INFO [train.py:715] (5/8) Epoch 12, batch 5550, loss[loss=0.1144, simple_loss=0.187, pruned_loss=0.02085, over 4844.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.0314, over 972151.12 frames.], batch size: 34, lr: 1.83e-04
2022-05-07 09:05:35,154 INFO [train.py:715] (5/8) Epoch 12, batch 5600, loss[loss=0.1117, simple_loss=0.1892, pruned_loss=0.0171, over 4889.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03114, over 973659.88 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:06:12,949 INFO [train.py:715] (5/8) Epoch 12, batch 5650, loss[loss=0.1405, simple_loss=0.2115, pruned_loss=0.03475, over 4976.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0308, over 973456.56 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:06:50,901 INFO [train.py:715] (5/8) Epoch 12, batch 5700, loss[loss=0.1273, simple_loss=0.2022, pruned_loss=0.02622, over 4911.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.0311, over 973785.11 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:07:29,807 INFO [train.py:715] (5/8) Epoch 12, batch 5750, loss[loss=0.1378, simple_loss=0.2137, pruned_loss=0.03092, over 4959.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2118, pruned_loss=0.0319, over 974857.47 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:08:07,980 INFO [train.py:715] (5/8) Epoch 12, batch 5800, loss[loss=0.1356, simple_loss=0.2112, pruned_loss=0.03002, over 4966.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03183, over 973676.09 frames.], batch size: 35, lr: 1.83e-04
2022-05-07 09:08:46,181 INFO [train.py:715] (5/8) Epoch 12, batch 5850, loss[loss=0.1371, simple_loss=0.2035, pruned_loss=0.03531, over 4835.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2124, pruned_loss=0.03175, over 974759.60 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:09:24,396 INFO [train.py:715] (5/8) Epoch 12, batch 5900, loss[loss=0.1534, simple_loss=0.2218, pruned_loss=0.04252, over 4897.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2119, pruned_loss=0.03168, over 973648.03 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:10:02,493 INFO [train.py:715] (5/8) Epoch 12, batch 5950, loss[loss=0.1309, simple_loss=0.2099, pruned_loss=0.02599, over 4789.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2116, pruned_loss=0.03149, over 973263.23 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:10:40,374 INFO [train.py:715] (5/8) Epoch 12, batch 6000, loss[loss=0.1293, simple_loss=0.2055, pruned_loss=0.02654, over 4867.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.0323, over 973286.19 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:10:40,374 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 09:10:49,853 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01086, over 914524.00 frames.
2022-05-07 09:11:28,466 INFO [train.py:715] (5/8) Epoch 12, batch 6050, loss[loss=0.1248, simple_loss=0.1942, pruned_loss=0.02767, over 4914.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03221, over 972842.93 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:12:07,174 INFO [train.py:715] (5/8) Epoch 12, batch 6100, loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03183, over 4855.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03184, over 973715.91 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:12:46,248 INFO [train.py:715] (5/8) Epoch 12, batch 6150, loss[loss=0.1302, simple_loss=0.2105, pruned_loss=0.02496, over 4874.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03134, over 973342.42 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:13:24,044 INFO [train.py:715] (5/8) Epoch 12, batch 6200, loss[loss=0.1607, simple_loss=0.2338, pruned_loss=0.04378, over 4743.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03175, over 973367.29 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:14:02,109 INFO [train.py:715] (5/8) Epoch 12, batch 6250, loss[loss=0.1238, simple_loss=0.1896, pruned_loss=0.02905, over 4773.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03157, over 972469.15 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:14:42,631 INFO [train.py:715] (5/8) Epoch 12, batch 6300, loss[loss=0.1467, simple_loss=0.2264, pruned_loss=0.03353, over 4942.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03179, over 972591.04 frames.], batch size: 39, lr: 1.83e-04
2022-05-07 09:15:20,410 INFO [train.py:715] (5/8) Epoch 12, batch 6350, loss[loss=0.1478, simple_loss=0.2139, pruned_loss=0.04084, over 4957.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03172, over 971935.38 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:15:58,260 INFO [train.py:715] (5/8) Epoch 12, batch 6400, loss[loss=0.1348, simple_loss=0.2185, pruned_loss=0.02554, over 4797.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03191, over 972177.60 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:16:36,188 INFO [train.py:715] (5/8) Epoch 12, batch 6450, loss[loss=0.1586, simple_loss=0.2398, pruned_loss=0.03872, over 4904.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03217, over 972787.21 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:17:14,181 INFO [train.py:715] (5/8) Epoch 12, batch 6500, loss[loss=0.1522, simple_loss=0.2192, pruned_loss=0.04261, over 4762.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03247, over 972349.70 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:17:51,826 INFO [train.py:715] (5/8) Epoch 12, batch 6550, loss[loss=0.1121, simple_loss=0.1836, pruned_loss=0.02034, over 4822.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03229, over 972908.26 frames.], batch size: 26, lr: 1.83e-04
2022-05-07 09:18:29,930 INFO [train.py:715] (5/8) Epoch 12, batch 6600, loss[loss=0.1431, simple_loss=0.2177, pruned_loss=0.03422, over 4958.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03254, over 972799.89 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:19:08,078 INFO [train.py:715] (5/8) Epoch 12, batch 6650, loss[loss=0.1398, simple_loss=0.215, pruned_loss=0.03227, over 4853.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03207, over 972448.34 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:19:46,571 INFO [train.py:715] (5/8) Epoch 12, batch 6700, loss[loss=0.131, simple_loss=0.212, pruned_loss=0.02497, over 4788.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03213, over 972406.95 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:20:24,046 INFO [train.py:715] (5/8) Epoch 12, batch 6750, loss[loss=0.1203, simple_loss=0.2018, pruned_loss=0.01937, over 4991.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03173, over 972104.04 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:21:02,174 INFO [train.py:715] (5/8) Epoch 12, batch 6800, loss[loss=0.1306, simple_loss=0.2116, pruned_loss=0.02484, over 4764.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03146, over 971926.08 frames.], batch size: 12, lr: 1.83e-04
2022-05-07 09:21:40,238 INFO [train.py:715] (5/8) Epoch 12, batch 6850, loss[loss=0.1326, simple_loss=0.1991, pruned_loss=0.03304, over 4827.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03096, over 971926.99 frames.], batch size: 12, lr: 1.83e-04
2022-05-07 09:22:18,034 INFO [train.py:715] (5/8) Epoch 12, batch 6900, loss[loss=0.1331, simple_loss=0.2065, pruned_loss=0.02985, over 4765.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03113, over 971840.58 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:22:56,143 INFO [train.py:715] (5/8) Epoch 12, batch 6950, loss[loss=0.1411, simple_loss=0.2079, pruned_loss=0.03711, over 4897.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03125, over 971414.59 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:23:34,138 INFO [train.py:715] (5/8) Epoch 12, batch 7000, loss[loss=0.1718, simple_loss=0.2412, pruned_loss=0.05122, over 4952.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.0322, over 970696.03 frames.], batch size: 35, lr: 1.83e-04
2022-05-07 09:24:12,556 INFO [train.py:715] (5/8) Epoch 12, batch 7050, loss[loss=0.1502, simple_loss=0.2266, pruned_loss=0.03687, over 4807.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03233, over 971009.28 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:24:50,037 INFO [train.py:715] (5/8) Epoch 12, batch 7100, loss[loss=0.1212, simple_loss=0.2051, pruned_loss=0.01863, over 4754.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03208, over 970531.68 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:25:28,612 INFO [train.py:715] (5/8) Epoch 12, batch 7150, loss[loss=0.1395, simple_loss=0.2261, pruned_loss=0.02643, over 4808.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2099, pruned_loss=0.0321, over 971725.76 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:26:06,441 INFO [train.py:715] (5/8) Epoch 12, batch 7200, loss[loss=0.155, simple_loss=0.2375, pruned_loss=0.03622, over 4955.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03178, over 971535.18 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:26:44,291 INFO [train.py:715] (5/8) Epoch 12, batch 7250, loss[loss=0.1576, simple_loss=0.225, pruned_loss=0.04504, over 4883.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03216, over 971977.75 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:27:22,552 INFO [train.py:715] (5/8) Epoch 12, batch 7300, loss[loss=0.1441, simple_loss=0.2048, pruned_loss=0.04171, over 4785.00 frames.], tot_loss[loss=0.137, simple_loss=0.2099, pruned_loss=0.03203, over 972275.08 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:28:00,296 INFO [train.py:715] (5/8) Epoch 12, batch 7350, loss[loss=0.1257, simple_loss=0.1979, pruned_loss=0.02675, over 4986.00 frames.], tot_loss[loss=0.1363, simple_loss=0.209, pruned_loss=0.03176, over 972469.72 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:28:38,319 INFO [train.py:715] (5/8) Epoch 12, batch 7400, loss[loss=0.1703, simple_loss=0.2253, pruned_loss=0.0576, over 4964.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2097, pruned_loss=0.03228, over 972031.51 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:29:16,071 INFO [train.py:715] (5/8) Epoch 12, batch 7450, loss[loss=0.1316, simple_loss=0.2008, pruned_loss=0.03122, over 4874.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2094, pruned_loss=0.03186, over 972492.28 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:29:54,162 INFO [train.py:715] (5/8) Epoch 12, batch 7500, loss[loss=0.1593, simple_loss=0.2397, pruned_loss=0.03943, over 4695.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2095, pruned_loss=0.03193, over 973193.52 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:30:32,182 INFO [train.py:715] (5/8) Epoch 12, batch 7550, loss[loss=0.1188, simple_loss=0.1958, pruned_loss=0.02086, over 4825.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03191, over 973136.73 frames.], batch size: 26, lr: 1.83e-04
2022-05-07 09:31:10,032 INFO [train.py:715] (5/8) Epoch 12, batch 7600, loss[loss=0.1383, simple_loss=0.214, pruned_loss=0.0313, over 4755.00 frames.], tot_loss[loss=0.136, simple_loss=0.2091, pruned_loss=0.0314, over 972676.53 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:31:48,260 INFO [train.py:715] (5/8) Epoch 12, batch 7650, loss[loss=0.1278, simple_loss=0.2058, pruned_loss=0.02485, over 4935.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03123, over 972706.51 frames.], batch size: 39, lr: 1.83e-04
2022-05-07 09:32:26,438 INFO [train.py:715] (5/8) Epoch 12, batch 7700, loss[loss=0.1133, simple_loss=0.1863, pruned_loss=0.02015, over 4986.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03126, over 973140.11 frames.], batch size: 20, lr: 1.83e-04
2022-05-07 09:33:04,637 INFO [train.py:715] (5/8) Epoch 12, batch 7750, loss[loss=0.1378, simple_loss=0.2101, pruned_loss=0.03277, over 4790.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.0312, over 973896.15 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:33:42,404 INFO [train.py:715] (5/8) Epoch 12, batch 7800, loss[loss=0.1318, simple_loss=0.1992, pruned_loss=0.03227, over 4781.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03194, over 973623.46 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:34:20,596 INFO [train.py:715] (5/8) Epoch 12, batch 7850, loss[loss=0.1348, simple_loss=0.2046, pruned_loss=0.03251, over 4983.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03205, over 973681.08 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:34:58,402 INFO [train.py:715] (5/8) Epoch 12, batch 7900, loss[loss=0.134, simple_loss=0.2173, pruned_loss=0.0253, over 4803.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.0318, over 973011.23 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:35:36,648 INFO [train.py:715] (5/8) Epoch 12, batch 7950, loss[loss=0.1782, simple_loss=0.2516, pruned_loss=0.05234, over 4777.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03214, over 972049.54 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:36:14,622 INFO [train.py:715] (5/8) Epoch 12, batch 8000, loss[loss=0.1521, simple_loss=0.2302, pruned_loss=0.03704, over 4881.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03172, over 972486.41 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:36:53,081 INFO [train.py:715] (5/8) Epoch 12, batch 8050, loss[loss=0.1601, simple_loss=0.2195, pruned_loss=0.05034, over 4858.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03228, over 973279.90 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:37:31,432 INFO [train.py:715] (5/8) Epoch 12, batch 8100, loss[loss=0.1589, simple_loss=0.2328, pruned_loss=0.04247, over 4785.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03273, over 973044.94 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:38:09,021 INFO [train.py:715] (5/8) Epoch 12, batch 8150, loss[loss=0.1337, simple_loss=0.2, pruned_loss=0.03369, over 4879.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2107, pruned_loss=0.03291, over 973543.41 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:38:47,284 INFO [train.py:715] (5/8) Epoch 12, batch 8200, loss[loss=0.1233, simple_loss=0.1987, pruned_loss=0.02394, over 4982.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2111, pruned_loss=0.03285, over 973191.93 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:39:25,280 INFO [train.py:715] (5/8) Epoch 12, batch 8250, loss[loss=0.1126, simple_loss=0.1762, pruned_loss=0.02449, over 4971.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03397, over 973211.86 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:40:03,012 INFO [train.py:715] (5/8) Epoch 12, batch 8300, loss[loss=0.1311, simple_loss=0.21, pruned_loss=0.02613, over 4809.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03359, over 972199.71 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:40:41,111 INFO [train.py:715] (5/8) Epoch 12, batch 8350, loss[loss=0.1597, simple_loss=0.2269, pruned_loss=0.04623, over 4856.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03338, over 972234.28 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:41:19,298 INFO [train.py:715] (5/8) Epoch 12, batch 8400, loss[loss=0.1241, simple_loss=0.1962, pruned_loss=0.02596, over 4829.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.0332, over 972089.24 frames.], batch size: 26, lr: 1.83e-04
2022-05-07 09:41:57,372 INFO [train.py:715] (5/8) Epoch 12, batch 8450, loss[loss=0.1474, simple_loss=0.2182, pruned_loss=0.03827, over 4975.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03278, over 972525.40 frames.], batch size: 35, lr: 1.83e-04
2022-05-07 09:42:34,901 INFO [train.py:715] (5/8) Epoch 12, batch 8500, loss[loss=0.1202, simple_loss=0.1899, pruned_loss=0.02524, over 4755.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03262, over 972334.86 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:43:13,187 INFO [train.py:715] (5/8) Epoch 12, batch 8550, loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03769, over 4932.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03329, over 972665.33 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:43:51,186 INFO [train.py:715] (5/8) Epoch 12, batch 8600, loss[loss=0.1775, simple_loss=0.2433, pruned_loss=0.05584, over 4888.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03358, over 971986.36 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:44:28,879 INFO [train.py:715] (5/8) Epoch 12, batch 8650, loss[loss=0.1398, simple_loss=0.2145, pruned_loss=0.0325, over 4896.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03294, over 972543.37 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:45:07,104 INFO [train.py:715] (5/8) Epoch 12, batch 8700, loss[loss=0.1477, simple_loss=0.2163, pruned_loss=0.03957, over 4818.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03273, over 972488.58 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:45:45,270 INFO [train.py:715] (5/8) Epoch 12, batch 8750, loss[loss=0.1416, simple_loss=0.2116, pruned_loss=0.0358, over 4829.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03252, over 972158.40 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:46:23,701 INFO [train.py:715] (5/8) Epoch 12, batch 8800, loss[loss=0.1065, simple_loss=0.1716, pruned_loss=0.02074, over 4812.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03249, over 972000.67 frames.], batch size: 12, lr: 1.83e-04
2022-05-07 09:47:01,615 INFO [train.py:715] (5/8) Epoch 12, batch 8850, loss[loss=0.1447, simple_loss=0.2211, pruned_loss=0.03414, over 4792.00 frames.], tot_loss[loss=0.1384, simple_loss=0.211, pruned_loss=0.03289, over 972516.07 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:47:40,606 INFO [train.py:715] (5/8) Epoch 12, batch 8900, loss[loss=0.1156, simple_loss=0.1796, pruned_loss=0.02582, over 4827.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2105, pruned_loss=0.0326, over 972187.80 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:48:20,144 INFO [train.py:715] (5/8) Epoch 12, batch 8950, loss[loss=0.1499, simple_loss=0.2091, pruned_loss=0.0454, over 4840.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03274, over 971871.83 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:48:58,104 INFO [train.py:715] (5/8) Epoch 12, batch 9000, loss[loss=0.1504, simple_loss=0.2156, pruned_loss=0.04258, over 4924.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03292, over 970776.55 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:48:58,105 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 09:49:07,570 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1898, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 09:49:45,344 INFO [train.py:715] (5/8) Epoch 12, batch 9050, loss[loss=0.1446, simple_loss=0.2192, pruned_loss=0.03497, over 4813.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03303, over 969851.46 frames.], batch size: 27, lr: 1.83e-04
2022-05-07 09:50:23,564 INFO [train.py:715] (5/8) Epoch 12, batch 9100, loss[loss=0.1481, simple_loss=0.2189, pruned_loss=0.03872, over 4918.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03329, over 970566.52 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:51:01,823 INFO [train.py:715] (5/8) Epoch 12, batch 9150, loss[loss=0.1455, simple_loss=0.2243, pruned_loss=0.0333, over 4914.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03293, over 970743.96 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:51:39,540 INFO [train.py:715] (5/8) Epoch 12, batch 9200, loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03649, over 4831.00 frames.], tot_loss[loss=0.139, simple_loss=0.2114, pruned_loss=0.0333, over 971078.94 frames.], batch size: 30, lr: 1.83e-04
2022-05-07 09:52:17,394 INFO [train.py:715] (5/8) Epoch 12, batch 9250, loss[loss=0.1602, simple_loss=0.2386, pruned_loss=0.04091, over 4921.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03313, over 972363.62 frames.], batch size: 23, lr: 1.83e-04
2022-05-07 09:52:55,472 INFO [train.py:715] (5/8) Epoch 12, batch 9300, loss[loss=0.1302, simple_loss=0.199, pruned_loss=0.03066, over 4949.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03304, over 972155.24 frames.], batch size: 29, lr: 1.83e-04
2022-05-07 09:53:33,065 INFO [train.py:715] (5/8) Epoch 12, batch 9350, loss[loss=0.107, simple_loss=0.1783, pruned_loss=0.01788, over 4772.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2117, pruned_loss=0.03333, over 972146.21 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:54:10,843 INFO [train.py:715] (5/8) Epoch 12, batch 9400, loss[loss=0.1288, simple_loss=0.2015, pruned_loss=0.02805, over 4838.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03331, over 972198.18 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:54:48,556 INFO [train.py:715] (5/8) Epoch 12, batch 9450, loss[loss=0.1526, simple_loss=0.2253, pruned_loss=0.03996, over 4986.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03262, over 972684.49 frames.], batch size: 28, lr: 1.83e-04
2022-05-07 09:55:26,595 INFO [train.py:715] (5/8) Epoch 12, batch 9500, loss[loss=0.1347, simple_loss=0.1958, pruned_loss=0.03678, over 4841.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03319, over 972399.27 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:56:04,148 INFO [train.py:715] (5/8) Epoch 12, batch 9550, loss[loss=0.1464, simple_loss=0.2212, pruned_loss=0.03586, over 4841.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03265, over 971219.55 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 09:56:41,641 INFO [train.py:715] (5/8) Epoch 12, batch 9600, loss[loss=0.1347, simple_loss=0.2056, pruned_loss=0.03195, over 4699.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03225, over 971386.54 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 09:57:19,885 INFO [train.py:715] (5/8) Epoch 12, batch 9650, loss[loss=0.1282, simple_loss=0.2017, pruned_loss=0.02738, over 4915.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2101, pruned_loss=0.0322, over 971682.18 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 09:57:57,755 INFO [train.py:715] (5/8) Epoch 12, batch 9700, loss[loss=0.1363, simple_loss=0.2124, pruned_loss=0.03016, over 4879.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2098, pruned_loss=0.03217, over 972236.64 frames.], batch size: 20, lr: 1.82e-04
2022-05-07 09:58:35,536 INFO [train.py:715] (5/8) Epoch 12, batch 9750, loss[loss=0.1544, simple_loss=0.2239, pruned_loss=0.04245, over 4870.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03172, over 972441.64 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 09:59:13,484 INFO [train.py:715] (5/8) Epoch 12, batch 9800, loss[loss=0.1253, simple_loss=0.1904, pruned_loss=0.03011, over 4848.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03179, over 972007.07 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 09:59:52,000 INFO [train.py:715] (5/8) Epoch 12, batch 9850, loss[loss=0.1582, simple_loss=0.2373, pruned_loss=0.03949, over 4877.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03184, over 972093.77 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:00:29,633 INFO [train.py:715] (5/8) Epoch 12, batch 9900, loss[loss=0.1387, simple_loss=0.2026, pruned_loss=0.03738, over 4793.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03195, over 972247.91 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:01:07,864 INFO [train.py:715] (5/8) Epoch 12, batch 9950, loss[loss=0.1226, simple_loss=0.1933, pruned_loss=0.02601, over 4788.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03167, over 972652.07 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 10:01:46,618 INFO [train.py:715] (5/8) Epoch 12, batch 10000, loss[loss=0.1345, simple_loss=0.2155, pruned_loss=0.0268, over 4826.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03114, over 973043.16 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:02:25,149 INFO [train.py:715] (5/8) Epoch 12, batch 10050, loss[loss=0.14, simple_loss=0.2149, pruned_loss=0.03254, over 4911.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03102, over 972813.38 frames.], batch size: 39, lr: 1.82e-04
2022-05-07 10:03:03,488 INFO [train.py:715] (5/8) Epoch 12, batch 10100, loss[loss=0.192, simple_loss=0.2677, pruned_loss=0.05813, over 4984.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03118, over 971904.35 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:03:41,895 INFO [train.py:715] (5/8) Epoch 12, batch 10150, loss[loss=0.1316, simple_loss=0.2001, pruned_loss=0.03156, over 4680.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03178, over 971666.10 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:04:20,550 INFO [train.py:715] (5/8) Epoch 12, batch 10200, loss[loss=0.1394, simple_loss=0.2111, pruned_loss=0.03383, over 4865.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03167, over 972808.22 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:04:57,863 INFO [train.py:715] (5/8) Epoch 12, batch 10250, loss[loss=0.1499, simple_loss=0.2284, pruned_loss=0.0357, over 4801.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03184, over 972398.25 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:05:36,037 INFO [train.py:715] (5/8) Epoch 12, batch 10300, loss[loss=0.1291, simple_loss=0.1989, pruned_loss=0.02967, over 4981.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03134, over 972742.90 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:06:14,196 INFO [train.py:715] (5/8) Epoch 12, batch 10350, loss[loss=0.1369, simple_loss=0.2069, pruned_loss=0.03341, over 4785.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 971537.11 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:06:52,241 INFO [train.py:715] (5/8) Epoch 12, batch 10400, loss[loss=0.12, simple_loss=0.1993, pruned_loss=0.02034, over 4826.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03173, over 971430.37 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:07:29,797 INFO [train.py:715] (5/8) Epoch 12, batch 10450, loss[loss=0.1319, simple_loss=0.2129, pruned_loss=0.02544, over 4817.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.0316, over 971405.33 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:08:07,727 INFO [train.py:715] (5/8) Epoch 12, batch 10500, loss[loss=0.1624, simple_loss=0.2339, pruned_loss=0.04544, over 4933.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.0313, over 972052.01 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:08:46,134 INFO [train.py:715] (5/8) Epoch 12, batch 10550, loss[loss=0.1634, simple_loss=0.2347, pruned_loss=0.04601, over 4777.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03109, over 971881.28 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:09:23,509 INFO [train.py:715] (5/8) Epoch 12, batch 10600, loss[loss=0.1539, simple_loss=0.2193, pruned_loss=0.04423, over 4836.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03152, over 972811.21 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:10:01,497 INFO [train.py:715] (5/8) Epoch 12, batch 10650, loss[loss=0.1506, simple_loss=0.2322, pruned_loss=0.03449, over 4971.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03127, over 972588.27 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:10:39,354 INFO [train.py:715] (5/8) Epoch 12, batch 10700, loss[loss=0.1343, simple_loss=0.2123, pruned_loss=0.02811, over 4791.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03158, over 971462.04 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:11:16,858 INFO [train.py:715] (5/8) Epoch 12, batch 10750, loss[loss=0.1584, simple_loss=0.2314, pruned_loss=0.04271, over 4783.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03154, over 972063.74 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:11:54,744 INFO [train.py:715] (5/8) Epoch 12, batch 10800, loss[loss=0.131, simple_loss=0.2046, pruned_loss=0.02869, over 4966.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03134, over 971675.80 frames.], batch size: 28, lr: 1.82e-04
2022-05-07 10:12:32,734 INFO [train.py:715] (5/8) Epoch 12, batch 10850, loss[loss=0.13, simple_loss=0.2056, pruned_loss=0.02715, over 4802.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03141, over 972984.49 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:13:11,527 INFO [train.py:715] (5/8) Epoch 12, batch 10900, loss[loss=0.135, simple_loss=0.2292, pruned_loss=0.0204, over 4828.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03181, over 973200.57 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:13:48,733 INFO [train.py:715] (5/8) Epoch 12, batch 10950, loss[loss=0.13, simple_loss=0.2049, pruned_loss=0.02753, over 4846.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03201, over 973084.72 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:14:26,875 INFO [train.py:715] (5/8) Epoch 12, batch 11000, loss[loss=0.1321, simple_loss=0.2042, pruned_loss=0.02999, over 4861.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03163, over 971986.84 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:15:05,146 INFO [train.py:715] (5/8) Epoch 12, batch 11050, loss[loss=0.1476, simple_loss=0.2246, pruned_loss=0.03523, over 4907.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03106, over 972667.84 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:15:42,772 INFO [train.py:715] (5/8) Epoch 12, batch 11100, loss[loss=0.1614, simple_loss=0.2147, pruned_loss=0.05409, over 4839.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 973121.61 frames.], batch size: 30, lr: 1.82e-04
2022-05-07 10:16:21,273 INFO [train.py:715] (5/8) Epoch 12, batch 11150, loss[loss=0.1574, simple_loss=0.2392, pruned_loss=0.0378, over 4906.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03101, over 972016.35 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:16:58,890 INFO [train.py:715] (5/8) Epoch 12, batch 11200, loss[loss=0.1247, simple_loss=0.1917, pruned_loss=0.02881, over 4915.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03106, over 971800.84 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:17:36,988 INFO [train.py:715] (5/8) Epoch 12, batch 11250, loss[loss=0.1065, simple_loss=0.1749, pruned_loss=0.01905, over 4759.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03148, over 971283.77 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 10:18:14,709 INFO [train.py:715] (5/8) Epoch 12, batch 11300, loss[loss=0.1307, simple_loss=0.2076, pruned_loss=0.02689, over 4814.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03099, over 971071.13 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:18:51,980 INFO [train.py:715] (5/8) Epoch 12, batch 11350, loss[loss=0.13, simple_loss=0.2137, pruned_loss=0.02316, over 4763.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03074, over 971294.97 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:19:30,200 INFO [train.py:715] (5/8) Epoch 12, batch 11400, loss[loss=0.1292, simple_loss=0.2009, pruned_loss=0.02875, over 4811.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03125, over 971556.60 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 10:20:07,742 INFO [train.py:715] (5/8) Epoch 12, batch 11450, loss[loss=0.1398, simple_loss=0.212, pruned_loss=0.03376, over 4919.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03123, over 971873.13 frames.], batch size: 39, lr: 1.82e-04
2022-05-07 10:20:45,257 INFO [train.py:715] (5/8) Epoch 12, batch 11500, loss[loss=0.1295, simple_loss=0.2058, pruned_loss=0.02659, over 4778.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2091, pruned_loss=0.03131, over 971875.05 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:21:23,003 INFO [train.py:715] (5/8) Epoch 12, batch 11550, loss[loss=0.1623, simple_loss=0.2427, pruned_loss=0.04096, over 4961.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03128, over 971975.57 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:22:01,393 INFO [train.py:715] (5/8) Epoch 12, batch 11600, loss[loss=0.1358, simple_loss=0.2189, pruned_loss=0.02637, over 4874.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03132, over 973083.15 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:22:38,881 INFO [train.py:715] (5/8) Epoch 12, batch 11650, loss[loss=0.1293, simple_loss=0.2007, pruned_loss=0.02895, over 4842.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03158, over 971766.87 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:23:16,091 INFO [train.py:715] (5/8) Epoch 12, batch 11700, loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03186, over 4888.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03156, over 971391.69 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:23:53,750 INFO [train.py:715] (5/8) Epoch 12, batch 11750, loss[loss=0.2083, simple_loss=0.2499, pruned_loss=0.08334, over 4781.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03163, over 971667.47 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:24:31,082 INFO [train.py:715] (5/8) Epoch 12, batch 11800, loss[loss=0.1458, simple_loss=0.2081, pruned_loss=0.0417, over 4981.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03199, over 973164.54 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:25:08,778 INFO [train.py:715] (5/8) Epoch 12, batch 11850, loss[loss=0.1181, simple_loss=0.1909, pruned_loss=0.02271, over 4944.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2097, pruned_loss=0.0319, over 973060.21 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:25:46,626 INFO [train.py:715] (5/8) Epoch 12, batch 11900, loss[loss=0.1646, simple_loss=0.2251, pruned_loss=0.05207, over 4974.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03198, over 973720.89 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:26:24,515 INFO [train.py:715] (5/8) Epoch 12, batch 11950, loss[loss=0.134, simple_loss=0.2151, pruned_loss=0.02648, over 4810.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03197, over 973164.03 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:27:01,977 INFO [train.py:715] (5/8) Epoch 12, batch 12000, loss[loss=0.1182, simple_loss=0.1953, pruned_loss=0.02059, over 4936.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03187, over 973337.61 frames.], batch size: 23, lr: 1.82e-04
2022-05-07 10:27:01,978 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 10:27:11,324 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1058, simple_loss=0.1897, pruned_loss=0.01095, over 914524.00 frames.
2022-05-07 10:27:50,014 INFO [train.py:715] (5/8) Epoch 12, batch 12050, loss[loss=0.1389, simple_loss=0.2203, pruned_loss=0.02877, over 4818.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03176, over 972828.22 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:28:29,093 INFO [train.py:715] (5/8) Epoch 12, batch 12100, loss[loss=0.1337, simple_loss=0.2057, pruned_loss=0.03085, over 4890.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03182, over 972808.87 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:29:08,846 INFO [train.py:715] (5/8) Epoch 12, batch 12150, loss[loss=0.1275, simple_loss=0.211, pruned_loss=0.022, over 4963.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03217, over 973292.93 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:29:47,130 INFO [train.py:715] (5/8) Epoch 12, batch 12200, loss[loss=0.1402, simple_loss=0.2273, pruned_loss=0.02654, over 4920.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03156, over 973720.42 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:30:25,384 INFO [train.py:715] (5/8) Epoch 12, batch 12250, loss[loss=0.1211, simple_loss=0.1961, pruned_loss=0.02306, over 4980.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03154, over 973631.81 frames.], batch size: 28, lr: 1.82e-04
2022-05-07 10:31:04,238 INFO [train.py:715] (5/8) Epoch 12, batch 12300, loss[loss=0.1129, simple_loss=0.1873, pruned_loss=0.01927, over 4979.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03197, over 973839.23 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:31:42,814 INFO [train.py:715] (5/8) Epoch 12, batch 12350, loss[loss=0.1615, simple_loss=0.2204, pruned_loss=0.05131, over 4985.00 frames.], tot_loss[loss=0.137, simple_loss=0.2098, pruned_loss=0.03212, over 974128.65 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:32:20,261 INFO [train.py:715] (5/8) Epoch 12, batch 12400, loss[loss=0.1486, simple_loss=0.2219, pruned_loss=0.03768, over 4837.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2098, pruned_loss=0.03195, over 973417.20 frames.], batch size: 30, lr: 1.82e-04
2022-05-07 10:32:57,986 INFO [train.py:715] (5/8) Epoch 12, batch 12450, loss[loss=0.1286, simple_loss=0.1972, pruned_loss=0.02998, over 4939.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03249, over 973199.06 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:33:36,208 INFO [train.py:715] (5/8) Epoch 12, batch 12500, loss[loss=0.1287, simple_loss=0.2006, pruned_loss=0.02846, over 4707.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03197, over 972712.46 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:34:13,318 INFO [train.py:715] (5/8) Epoch 12, batch 12550, loss[loss=0.1568, simple_loss=0.2232, pruned_loss=0.04518, over 4948.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.0324, over 972755.47 frames.], batch size: 29, lr: 1.82e-04
2022-05-07 10:34:51,154 INFO [train.py:715] (5/8) Epoch 12, batch 12600, loss[loss=0.1542, simple_loss=0.2352, pruned_loss=0.03653, over 4916.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03263, over 971933.38 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:35:28,922 INFO [train.py:715] (5/8) Epoch 12, batch 12650, loss[loss=0.1229, simple_loss=0.1993, pruned_loss=0.02322, over 4978.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03304, over 972315.83 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:36:06,673 INFO [train.py:715] (5/8) Epoch 12, batch 12700, loss[loss=0.1434, simple_loss=0.2011, pruned_loss=0.04281, over 4768.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03326, over 971840.27 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:36:44,127 INFO [train.py:715] (5/8) Epoch 12, batch 12750, loss[loss=0.1474, simple_loss=0.2243, pruned_loss=0.03522, over 4972.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03221, over 972024.79 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:37:22,154 INFO [train.py:715] (5/8) Epoch 12, batch 12800, loss[loss=0.1282, simple_loss=0.1973, pruned_loss=0.02956, over 4856.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03288, over 971687.48 frames.], batch size: 20, lr: 1.82e-04
2022-05-07 10:38:00,585 INFO [train.py:715] (5/8) Epoch 12, batch 12850, loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04213, over 4780.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.0328, over 972353.05 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:38:37,911 INFO [train.py:715] (5/8) Epoch 12, batch 12900, loss[loss=0.1489, simple_loss=0.2266, pruned_loss=0.03557, over 4768.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03253, over 971652.43 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:39:15,003 INFO [train.py:715] (5/8) Epoch 12, batch 12950, loss[loss=0.1461, simple_loss=0.22, pruned_loss=0.03606, over 4959.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03256, over 972116.10 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:39:52,997 INFO [train.py:715] (5/8) Epoch 12, batch 13000, loss[loss=0.1847, simple_loss=0.2407, pruned_loss=0.06432, over 4768.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03222, over 972098.55 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:40:30,779 INFO [train.py:715] (5/8) Epoch 12, batch 13050, loss[loss=0.1261, simple_loss=0.201, pruned_loss=0.02564, over 4809.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03264, over 971641.18 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:41:08,531 INFO [train.py:715] (5/8) Epoch 12, batch 13100, loss[loss=0.1717, simple_loss=0.2453, pruned_loss=0.04904, over 4796.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03238, over 971282.69 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:41:46,122 INFO [train.py:715] (5/8) Epoch 12, batch 13150, loss[loss=0.1242, simple_loss=0.2014, pruned_loss=0.0235, over 4756.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.0323, over 970856.63 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:42:23,788 INFO [train.py:715] (5/8) Epoch 12, batch 13200, loss[loss=0.1626, simple_loss=0.2309, pruned_loss=0.04719, over 4986.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03259, over 971043.56 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:43:01,014 INFO [train.py:715] (5/8) Epoch 12, batch 13250, loss[loss=0.1524, simple_loss=0.2214, pruned_loss=0.04175, over 4843.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03285, over 970408.96 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:43:38,187 INFO [train.py:715] (5/8) Epoch 12, batch 13300, loss[loss=0.1458, simple_loss=0.2211, pruned_loss=0.03529, over 4828.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03272, over 971110.79 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:44:16,078 INFO [train.py:715] (5/8) Epoch 12, batch 13350, loss[loss=0.125, simple_loss=0.2032, pruned_loss=0.02343, over 4971.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03277, over 971793.85 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:44:54,315 INFO [train.py:715] (5/8) Epoch 12, batch 13400, loss[loss=0.09683, simple_loss=0.1661, pruned_loss=0.01379, over 4790.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.03231, over 972261.73 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:45:31,692 INFO [train.py:715] (5/8) Epoch 12, batch 13450, loss[loss=0.1238, simple_loss=0.1917, pruned_loss=0.02794, over 4871.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03223, over 971664.85 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:46:09,030 INFO [train.py:715] (5/8) Epoch 12, batch 13500, loss[loss=0.1253, simple_loss=0.2068, pruned_loss=0.02191, over 4965.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03201, over 972254.13 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:46:47,474 INFO [train.py:715] (5/8) Epoch 12, batch 13550, loss[loss=0.1211, simple_loss=0.1934, pruned_loss=0.02439, over 4767.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03216, over 971490.20 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:47:24,688 INFO [train.py:715] (5/8) Epoch 12, batch 13600, loss[loss=0.1832, simple_loss=0.2496, pruned_loss=0.05844, over 4943.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03224, over 971871.36 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:48:02,573 INFO [train.py:715] (5/8) Epoch 12, batch 13650, loss[loss=0.1225, simple_loss=0.1965, pruned_loss=0.02427, over 4880.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03134, over 971891.31 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:48:40,710 INFO [train.py:715] (5/8) Epoch 12, batch 13700, loss[loss=0.1277, simple_loss=0.1968, pruned_loss=0.02931, over 4801.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03102, over 971862.47 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:49:18,441 INFO [train.py:715] (5/8) Epoch 12, batch 13750, loss[loss=0.1355, simple_loss=0.2016, pruned_loss=0.03475, over 4789.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03159, over 971332.87 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:49:56,508 INFO [train.py:715] (5/8) Epoch 12, batch 13800, loss[loss=0.1223, simple_loss=0.1904, pruned_loss=0.02705, over 4844.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.0315, over 970974.84 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 10:50:34,449 INFO [train.py:715] (5/8) Epoch 12, batch 13850, loss[loss=0.135, simple_loss=0.2005, pruned_loss=0.03475, over 4904.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03184, over 971935.26 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:51:12,970 INFO [train.py:715] (5/8) Epoch 12, batch 13900, loss[loss=0.1162, simple_loss=0.1918, pruned_loss=0.02036, over 4986.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03193, over 973710.54 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:51:50,186 INFO [train.py:715] (5/8) Epoch 12, batch 13950, loss[loss=0.1376, simple_loss=0.2188, pruned_loss=0.02821, over 4898.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03205, over 973663.84 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:52:28,377 INFO [train.py:715] (5/8) Epoch 12, batch 14000, loss[loss=0.1642, simple_loss=0.215, pruned_loss=0.05674, over 4981.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03227, over 973890.51 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:53:06,889 INFO [train.py:715] (5/8) Epoch 12, batch 14050, loss[loss=0.1207, simple_loss=0.1814, pruned_loss=0.03005, over 4825.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03194, over 973543.17 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:53:44,260 INFO [train.py:715] (5/8) Epoch 12, batch 14100, loss[loss=0.1449, simple_loss=0.214, pruned_loss=0.03787, over 4832.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 973794.38 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:54:21,695 INFO [train.py:715] (5/8) Epoch 12, batch 14150, loss[loss=0.1539, simple_loss=0.2201, pruned_loss=0.04386, over 4855.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 973419.70 frames.], batch size: 30, lr: 1.82e-04
2022-05-07 10:55:00,104 INFO [train.py:715] (5/8) Epoch 12, batch 14200, loss[loss=0.1243, simple_loss=0.195, pruned_loss=0.02683, over 4816.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03253, over 973861.33 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:55:38,425 INFO [train.py:715] (5/8) Epoch 12, batch 14250, loss[loss=0.1316, simple_loss=0.2094, pruned_loss=0.02693, over 4939.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2104, pruned_loss=0.03258, over 972744.52 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 10:56:18,083 INFO [train.py:715] (5/8) Epoch 12, batch 14300, loss[loss=0.1392, simple_loss=0.215, pruned_loss=0.03168, over 4760.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03234, over 973145.62 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 10:56:56,582 INFO [train.py:715] (5/8) Epoch 12, batch 14350, loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03174, over 4923.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03254, over 972257.71 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 10:57:35,967 INFO [train.py:715] (5/8) Epoch 12, batch 14400, loss[loss=0.1206, simple_loss=0.1958, pruned_loss=0.02265, over 4931.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03254, over 971639.45 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 10:58:14,113 INFO [train.py:715] (5/8) Epoch 12, batch 14450, loss[loss=0.1365, simple_loss=0.2089, pruned_loss=0.03204, over 4910.00 frames.], tot_loss[loss=0.138, simple_loss=0.2108, pruned_loss=0.03257, over 972353.48 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 10:58:53,036 INFO [train.py:715] (5/8) Epoch 12, batch 14500, loss[loss=0.156, simple_loss=0.2377, pruned_loss=0.0371, over 4855.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03219, over 971401.30 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 10:59:32,145 INFO [train.py:715] (5/8) Epoch 12, batch 14550, loss[loss=0.1337, simple_loss=0.2048, pruned_loss=0.03125, over 4805.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03224, over 971698.92 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:00:11,029 INFO [train.py:715] (5/8) Epoch 12, batch 14600, loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.0384, over 4923.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03207, over 971555.02 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:00:49,645 INFO [train.py:715] (5/8) Epoch 12, batch 14650, loss[loss=0.1282, simple_loss=0.206, pruned_loss=0.02522, over 4801.00 frames.], tot_loss[loss=0.137, simple_loss=0.21, pruned_loss=0.03202, over 970980.46 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:01:27,544 INFO [train.py:715] (5/8) Epoch 12, batch 14700, loss[loss=0.1193, simple_loss=0.1818, pruned_loss=0.02837, over 4975.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2102, pruned_loss=0.03263, over 970394.85 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:02:06,071 INFO [train.py:715] (5/8) Epoch 12, batch 14750, loss[loss=0.1155, simple_loss=0.1939, pruned_loss=0.01854, over 4835.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03214, over 971229.08 frames.], batch size: 26, lr: 1.81e-04
2022-05-07 11:02:43,582 INFO [train.py:715] (5/8) Epoch 12, batch 14800, loss[loss=0.1469, simple_loss=0.227, pruned_loss=0.03341, over 4826.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03221, over 971846.50 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:03:21,327 INFO [train.py:715] (5/8) Epoch 12, batch 14850, loss[loss=0.1413, simple_loss=0.2162, pruned_loss=0.03318, over 4765.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03235, over 971507.07 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:03:59,688 INFO [train.py:715] (5/8) Epoch 12, batch 14900, loss[loss=0.1322, simple_loss=0.202, pruned_loss=0.03119, over 4818.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03188, over 971257.77 frames.], batch size: 27, lr: 1.81e-04
2022-05-07 11:04:38,247 INFO [train.py:715] (5/8) Epoch 12, batch 14950, loss[loss=0.1109, simple_loss=0.1846, pruned_loss=0.01855, over 4876.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03232, over 971907.03 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:05:15,439 INFO [train.py:715] (5/8) Epoch 12, batch 15000, loss[loss=0.1352, simple_loss=0.2001, pruned_loss=0.03515, over 4823.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03196, over 972136.14 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:05:15,439 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 11:05:25,069 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 11:06:02,917 INFO [train.py:715] (5/8) Epoch 12, batch 15050, loss[loss=0.1215, simple_loss=0.2022, pruned_loss=0.02035, over 4878.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03165, over 972194.56 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:06:41,208 INFO [train.py:715] (5/8) Epoch 12, batch 15100, loss[loss=0.1475, simple_loss=0.232, pruned_loss=0.03148, over 4787.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03186, over 972284.28 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:07:20,388 INFO [train.py:715] (5/8) Epoch 12, batch 15150, loss[loss=0.1146, simple_loss=0.1773, pruned_loss=0.02592, over 4767.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03206, over 971886.15 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:07:58,862 INFO [train.py:715] (5/8) Epoch 12, batch 15200, loss[loss=0.1225, simple_loss=0.2014, pruned_loss=0.02178, over 4935.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03236, over 971704.28 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:08:37,646 INFO [train.py:715] (5/8) Epoch 12, batch 15250, loss[loss=0.168, simple_loss=0.2321, pruned_loss=0.05195, over 4921.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03235, over 971304.26 frames.], batch size: 39, lr: 1.81e-04
2022-05-07 11:09:16,366 INFO [train.py:715] (5/8) Epoch 12, batch 15300, loss[loss=0.1334, simple_loss=0.2005, pruned_loss=0.03317, over 4770.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2127, pruned_loss=0.03248, over 971398.79 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:09:54,568 INFO [train.py:715] (5/8) Epoch 12, batch 15350, loss[loss=0.1483, simple_loss=0.2138, pruned_loss=0.04138, over 4948.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2128, pruned_loss=0.0329, over 971625.53 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:10:31,952 INFO [train.py:715] (5/8) Epoch 12, batch 15400, loss[loss=0.1515, simple_loss=0.2178, pruned_loss=0.04255, over 4761.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2132, pruned_loss=0.03302, over 971388.40 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:11:09,687 INFO [train.py:715] (5/8) Epoch 12, batch 15450, loss[loss=0.1134, simple_loss=0.1907, pruned_loss=0.0181, over 4752.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03289, over 971719.27 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:11:48,438 INFO [train.py:715] (5/8) Epoch 12, batch 15500, loss[loss=0.1306, simple_loss=0.2072, pruned_loss=0.02701, over 4829.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2124, pruned_loss=0.03221, over 971139.91 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:12:26,564 INFO [train.py:715] (5/8) Epoch 12, batch 15550, loss[loss=0.1488, simple_loss=0.2268, pruned_loss=0.03543, over 4895.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03188, over 971241.39 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:13:04,459 INFO [train.py:715] (5/8) Epoch 12, batch 15600, loss[loss=0.1475, simple_loss=0.2205, pruned_loss=0.0373, over 4771.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03185, over 971377.82 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:13:42,237 INFO [train.py:715] (5/8) Epoch 12, batch 15650, loss[loss=0.119, simple_loss=0.1955, pruned_loss=0.02127, over 4898.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03165, over 972880.60 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:14:20,673 INFO [train.py:715] (5/8) Epoch 12, batch 15700, loss[loss=0.1138, simple_loss=0.184, pruned_loss=0.02177, over 4832.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03116, over 972272.21 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:14:58,369 INFO [train.py:715] (5/8) Epoch 12, batch 15750, loss[loss=0.1192, simple_loss=0.1931, pruned_loss=0.02261, over 4891.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.0317, over 972563.70 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:15:36,103 INFO [train.py:715] (5/8) Epoch 12, batch 15800, loss[loss=0.1151, simple_loss=0.1915, pruned_loss=0.01932, over 4873.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03164, over 973615.05 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:16:14,196 INFO [train.py:715] (5/8) Epoch 12, batch 15850, loss[loss=0.1369, simple_loss=0.2162, pruned_loss=0.02877, over 4813.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 973598.48 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:16:51,695 INFO [train.py:715] (5/8) Epoch 12, batch 15900, loss[loss=0.1187, simple_loss=0.1923, pruned_loss=0.02254, over 4927.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03167, over 973797.43 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:17:29,508 INFO [train.py:715] (5/8) Epoch 12, batch 15950, loss[loss=0.1442, simple_loss=0.2235, pruned_loss=0.03243, over 4826.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03158, over 973610.04 frames.], batch size: 26, lr: 1.81e-04
2022-05-07 11:18:07,569 INFO [train.py:715] (5/8) Epoch 12, batch 16000, loss[loss=0.1334, simple_loss=0.2125, pruned_loss=0.02714, over 4826.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03141, over 973469.51 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:18:47,330 INFO [train.py:715] (5/8) Epoch 12, batch 16050, loss[loss=0.1539, simple_loss=0.2333, pruned_loss=0.03728, over 4704.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03184, over 973007.48 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:19:25,277 INFO [train.py:715] (5/8) Epoch 12, batch 16100, loss[loss=0.1215, simple_loss=0.2016, pruned_loss=0.02069, over 4816.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03213, over 972375.19 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:20:04,189 INFO [train.py:715] (5/8) Epoch 12, batch 16150, loss[loss=0.1741, simple_loss=0.2353, pruned_loss=0.05644, over 4833.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03223, over 971629.10 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:20:43,068 INFO [train.py:715] (5/8) Epoch 12, batch 16200, loss[loss=0.1277, simple_loss=0.1947, pruned_loss=0.03037, over 4735.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03187, over 971810.25 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:21:21,842 INFO [train.py:715] (5/8) Epoch 12, batch 16250, loss[loss=0.1482, simple_loss=0.2159, pruned_loss=0.04018, over 4913.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03208, over 972516.91 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:21:59,696 INFO [train.py:715] (5/8) Epoch 12, batch 16300, loss[loss=0.1151, simple_loss=0.2028, pruned_loss=0.01371, over 4788.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03158, over 972102.30 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:22:37,476 INFO [train.py:715] (5/8) Epoch 12, batch 16350, loss[loss=0.1531, simple_loss=0.2203, pruned_loss=0.043, over 4862.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.0318, over 971709.42 frames.], batch size: 30, lr: 1.81e-04
2022-05-07 11:23:16,251 INFO [train.py:715] (5/8) Epoch 12, batch 16400, loss[loss=0.1334, simple_loss=0.205, pruned_loss=0.03091, over 4857.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03202, over 971587.42 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:23:54,211 INFO [train.py:715] (5/8) Epoch 12, batch 16450, loss[loss=0.1418, simple_loss=0.2122, pruned_loss=0.03571, over 4851.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03207, over 970903.32 frames.], batch size: 32, lr: 1.81e-04
2022-05-07 11:24:33,096 INFO [train.py:715] (5/8) Epoch 12, batch 16500, loss[loss=0.1509, simple_loss=0.2235, pruned_loss=0.0391, over 4706.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03165, over 971008.72 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:25:12,170 INFO [train.py:715] (5/8) Epoch 12, batch 16550, loss[loss=0.1413, simple_loss=0.2073, pruned_loss=0.03763, over 4818.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03234, over 970224.67 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:25:51,305 INFO [train.py:715] (5/8) Epoch 12, batch 16600, loss[loss=0.1374, simple_loss=0.2144, pruned_loss=0.03022, over 4767.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.0321, over 970301.64 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:26:29,844 INFO [train.py:715] (5/8) Epoch 12, batch 16650, loss[loss=0.1606, simple_loss=0.2271, pruned_loss=0.047, over 4921.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03247, over 970384.91 frames.], batch size: 29, lr: 1.81e-04
2022-05-07 11:27:08,909 INFO [train.py:715] (5/8) Epoch 12, batch 16700, loss[loss=0.1657, simple_loss=0.2291, pruned_loss=0.05117, over 4844.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.0325, over 970356.26 frames.], batch size: 30, lr: 1.81e-04
2022-05-07 11:27:48,109 INFO [train.py:715] (5/8) Epoch 12, batch 16750, loss[loss=0.1378, simple_loss=0.2037, pruned_loss=0.03599, over 4891.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03209, over 970954.94 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:28:26,498 INFO [train.py:715] (5/8) Epoch 12, batch 16800, loss[loss=0.1307, simple_loss=0.2113, pruned_loss=0.02507, over 4963.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03223, over 971585.34 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:29:05,272 INFO [train.py:715] (5/8) Epoch 12, batch 16850, loss[loss=0.1495, simple_loss=0.2298, pruned_loss=0.03461, over 4971.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03235, over 971485.37 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:29:44,425 INFO [train.py:715] (5/8) Epoch 12, batch 16900, loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03919, over 4984.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03237, over 971186.76 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:30:24,179 INFO [train.py:715] (5/8) Epoch 12, batch 16950, loss[loss=0.1303, simple_loss=0.2039, pruned_loss=0.02834, over 4906.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03218, over 971077.68 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:31:02,693 INFO [train.py:715] (5/8) Epoch 12, batch 17000, loss[loss=0.1257, simple_loss=0.2016, pruned_loss=0.0249, over 4839.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03207, over 972130.06 frames.], batch size: 26, lr: 1.81e-04
2022-05-07 11:31:40,878 INFO [train.py:715] (5/8) Epoch 12, batch 17050, loss[loss=0.1421, simple_loss=0.2177, pruned_loss=0.03329, over 4874.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03173, over 972096.38 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:32:19,761 INFO [train.py:715] (5/8) Epoch 12, batch 17100, loss[loss=0.1539, simple_loss=0.2387, pruned_loss=0.03452, over 4783.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03158, over 972147.30 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:32:58,565 INFO [train.py:715] (5/8) Epoch 12, batch 17150, loss[loss=0.1224, simple_loss=0.2004, pruned_loss=0.02223, over 4791.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2113, pruned_loss=0.03176, over 972804.58 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:33:37,597 INFO [train.py:715] (5/8) Epoch 12, batch 17200, loss[loss=0.1176, simple_loss=0.1915, pruned_loss=0.02188, over 4869.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03148, over 972522.63 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:34:16,026 INFO [train.py:715] (5/8) Epoch 12, batch 17250, loss[loss=0.1437, simple_loss=0.2181, pruned_loss=0.03466, over 4827.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2119, pruned_loss=0.03166, over 971830.15 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:34:54,493 INFO [train.py:715] (5/8) Epoch 12, batch 17300, loss[loss=0.1149, simple_loss=0.1976, pruned_loss=0.01612, over 4988.00 frames.], tot_loss[loss=0.1377, simple_loss=0.212, pruned_loss=0.03169, over 972528.23 frames.], batch size: 28, lr: 1.81e-04
2022-05-07 11:35:32,126 INFO [train.py:715] (5/8) Epoch 12, batch 17350, loss[loss=0.1414, simple_loss=0.2099, pruned_loss=0.03641, over 4703.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2121, pruned_loss=0.03206, over 971568.37 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:36:10,078 INFO [train.py:715] (5/8) Epoch 12, batch 17400, loss[loss=0.1206, simple_loss=0.2034, pruned_loss=0.01894, over 4831.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03228, over 971368.84 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:36:47,844 INFO [train.py:715] (5/8) Epoch 12, batch 17450, loss[loss=0.1447, simple_loss=0.2235, pruned_loss=0.03295, over 4705.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03161, over 971251.79 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:37:26,179 INFO [train.py:715] (5/8) Epoch 12, batch 17500, loss[loss=0.1291, simple_loss=0.2057, pruned_loss=0.02627, over 4949.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03211, over 971719.37 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:38:04,042 INFO [train.py:715] (5/8) Epoch 12, batch 17550, loss[loss=0.136, simple_loss=0.2215, pruned_loss=0.02521, over 4955.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03192, over 971967.37 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:38:42,239 INFO [train.py:715] (5/8) Epoch 12, batch 17600, loss[loss=0.1321, simple_loss=0.1975, pruned_loss=0.03331, over 4644.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03148, over 972048.61 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:39:19,885 INFO [train.py:715] (5/8) Epoch 12, batch 17650, loss[loss=0.1217, simple_loss=0.1973, pruned_loss=0.02303, over 4977.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.0314, over 973242.20 frames.], batch size: 28, lr: 1.81e-04
2022-05-07 11:39:57,990 INFO [train.py:715] (5/8) Epoch 12, batch 17700, loss[loss=0.1458, simple_loss=0.2222, pruned_loss=0.03474, over 4984.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03175, over 972815.88 frames.], batch size: 27, lr: 1.81e-04
2022-05-07 11:40:36,848 INFO [train.py:715] (5/8) Epoch 12, batch 17750, loss[loss=0.1299, simple_loss=0.206, pruned_loss=0.02694, over 4759.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.0323, over 972338.02 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:41:15,689 INFO [train.py:715] (5/8) Epoch 12, batch 17800, loss[loss=0.1422, simple_loss=0.2159, pruned_loss=0.03421, over 4771.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03233, over 973128.64 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:41:54,188 INFO [train.py:715] (5/8) Epoch 12, batch 17850, loss[loss=0.1671, simple_loss=0.2238, pruned_loss=0.05517, over 4744.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03224, over 974025.91 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:42:32,958 INFO [train.py:715] (5/8) Epoch 12, batch 17900, loss[loss=0.154, simple_loss=0.2419, pruned_loss=0.03303, over 4833.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03205, over 972855.82 frames.], batch size: 26, lr: 1.81e-04
2022-05-07 11:43:10,437 INFO [train.py:715] (5/8) Epoch 12, batch 17950, loss[loss=0.1202, simple_loss=0.1993, pruned_loss=0.02056, over 4810.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03184, over 972664.24 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:43:48,628 INFO [train.py:715] (5/8) Epoch 12, batch 18000, loss[loss=0.1335, simple_loss=0.2092, pruned_loss=0.0289, over 4834.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.03115, over 973220.45 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:43:48,629 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 11:43:58,181 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.011, over 914524.00 frames.
2022-05-07 11:44:36,606 INFO [train.py:715] (5/8) Epoch 12, batch 18050, loss[loss=0.1433, simple_loss=0.2214, pruned_loss=0.03257, over 4934.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03163, over 972910.56 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:45:14,476 INFO [train.py:715] (5/8) Epoch 12, batch 18100, loss[loss=0.1388, simple_loss=0.1951, pruned_loss=0.04118, over 4776.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03195, over 971604.22 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:45:52,625 INFO [train.py:715] (5/8) Epoch 12, batch 18150, loss[loss=0.1449, simple_loss=0.2149, pruned_loss=0.03748, over 4940.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03236, over 972607.04 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:46:30,451 INFO [train.py:715] (5/8) Epoch 12, batch 18200, loss[loss=0.1228, simple_loss=0.1959, pruned_loss=0.02482, over 4979.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03217, over 973819.67 frames.], batch size: 28, lr: 1.81e-04
2022-05-07 11:47:08,251 INFO [train.py:715] (5/8) Epoch 12, batch 18250, loss[loss=0.154, simple_loss=0.2384, pruned_loss=0.03476, over 4783.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03224, over 973315.56 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:47:46,408 INFO [train.py:715] (5/8) Epoch 12, batch 18300, loss[loss=0.1226, simple_loss=0.2057, pruned_loss=0.01977, over 4934.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03171, over 973199.38 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:48:24,292 INFO [train.py:715] (5/8) Epoch 12, batch 18350, loss[loss=0.1379, simple_loss=0.2141, pruned_loss=0.03091, over 4898.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.0313, over 972363.47 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:49:02,250 INFO [train.py:715] (5/8) Epoch 12, batch 18400, loss[loss=0.1415, simple_loss=0.2152, pruned_loss=0.03395, over 4829.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03138, over 972931.14 frames.], batch size: 30, lr: 1.81e-04
2022-05-07 11:49:39,750 INFO [train.py:715] (5/8) Epoch 12, batch 18450, loss[loss=0.1205, simple_loss=0.1947, pruned_loss=0.0231, over 4898.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03125, over 973494.69 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:50:17,836 INFO [train.py:715] (5/8) Epoch 12, batch 18500, loss[loss=0.1551, simple_loss=0.2215, pruned_loss=0.04436, over 4788.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03096, over 972383.95 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:50:55,664 INFO [train.py:715] (5/8) Epoch 12, batch 18550, loss[loss=0.1262, simple_loss=0.1991, pruned_loss=0.02662, over 4799.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03084, over 972870.52 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:51:33,500 INFO [train.py:715] (5/8) Epoch 12, batch 18600, loss[loss=0.1426, simple_loss=0.223, pruned_loss=0.0311, over 4811.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03119, over 972376.97 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:52:11,113 INFO [train.py:715] (5/8) Epoch 12, batch 18650, loss[loss=0.1031, simple_loss=0.173, pruned_loss=0.01661, over 4808.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03092, over 972108.25 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:52:48,672 INFO [train.py:715] (5/8) Epoch 12, batch 18700, loss[loss=0.139, simple_loss=0.2082, pruned_loss=0.03484, over 4776.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03093, over 972401.23 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:53:26,073 INFO [train.py:715] (5/8) Epoch 12, batch 18750, loss[loss=0.1294, simple_loss=0.2067, pruned_loss=0.0261, over 4950.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03068, over 972262.57 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:54:04,013 INFO [train.py:715] (5/8) Epoch 12, batch 18800, loss[loss=0.1241, simple_loss=0.189, pruned_loss=0.02956, over 4653.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03087, over 972004.60 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:54:41,889 INFO [train.py:715] (5/8) Epoch 12, batch 18850, loss[loss=0.1599, simple_loss=0.2333, pruned_loss=0.04323, over 4805.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 972165.95 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:55:19,707 INFO [train.py:715] (5/8) Epoch 12, batch 18900, loss[loss=0.1747, simple_loss=0.2399, pruned_loss=0.05477, over 4992.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.0318, over 972103.27 frames.], batch size: 14, lr: 1.81e-04
2022-05-07 11:55:57,998 INFO [train.py:715] (5/8) Epoch 12, batch 18950, loss[loss=0.1108, simple_loss=0.188, pruned_loss=0.01686, over 4816.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03165, over 971151.85 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:56:35,807 INFO [train.py:715] (5/8) Epoch 12, batch 19000, loss[loss=0.1086, simple_loss=0.1904, pruned_loss=0.0134, over 4815.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03141, over 971187.30 frames.], batch size: 27, lr: 1.81e-04
2022-05-07 11:57:13,288 INFO [train.py:715] (5/8) Epoch 12, batch 19050, loss[loss=0.1318, simple_loss=0.2162, pruned_loss=0.0237, over 4942.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03139, over 970874.74 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 11:57:50,568 INFO [train.py:715] (5/8) Epoch 12, batch 19100, loss[loss=0.1348, simple_loss=0.215, pruned_loss=0.02735, over 4773.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03138, over 971434.34 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 11:58:28,559 INFO [train.py:715] (5/8) Epoch 12, batch 19150, loss[loss=0.1541, simple_loss=0.217, pruned_loss=0.04556, over 4941.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03172, over 971631.87 frames.], batch size: 35, lr: 1.80e-04
2022-05-07 11:59:07,192 INFO [train.py:715] (5/8) Epoch 12, batch 19200, loss[loss=0.1361, simple_loss=0.2114, pruned_loss=0.03037, over 4936.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03189, over 972218.78 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 11:59:45,241 INFO [train.py:715] (5/8) Epoch 12, batch 19250, loss[loss=0.1215, simple_loss=0.2003, pruned_loss=0.02135, over 4815.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03199, over 972307.29 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:00:23,721 INFO [train.py:715] (5/8) Epoch 12, batch 19300, loss[loss=0.1317, simple_loss=0.209, pruned_loss=0.02714, over 4826.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03178, over 971842.79 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:01:01,910 INFO [train.py:715] (5/8) Epoch 12, batch 19350, loss[loss=0.12, simple_loss=0.1997, pruned_loss=0.02012, over 4884.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03173, over 972184.39 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:01:39,912 INFO [train.py:715] (5/8) Epoch 12, batch 19400, loss[loss=0.1537, simple_loss=0.2204, pruned_loss=0.04344, over 4758.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03148, over 972196.59 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:02:17,950 INFO [train.py:715] (5/8) Epoch 12, batch 19450, loss[loss=0.1447, simple_loss=0.2218, pruned_loss=0.03379, over 4860.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03112, over 972191.76 frames.], batch size: 22, lr: 1.80e-04
2022-05-07 12:02:56,771 INFO [train.py:715] (5/8) Epoch 12, batch 19500, loss[loss=0.1863, simple_loss=0.2562, pruned_loss=0.05822, over 4947.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.0311, over 972483.13 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:03:35,595 INFO [train.py:715] (5/8) Epoch 12, batch 19550, loss[loss=0.1304, simple_loss=0.1969, pruned_loss=0.0319, over 4662.00 frames.], tot_loss[loss=0.136, simple_loss=0.2088, pruned_loss=0.03154, over 971449.54 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:04:14,317 INFO [train.py:715] (5/8) Epoch 12, batch 19600, loss[loss=0.1399, simple_loss=0.2048, pruned_loss=0.03746, over 4903.00 frames.], tot_loss[loss=0.1361, simple_loss=0.209, pruned_loss=0.0316, over 971808.74 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:04:53,462 INFO [train.py:715] (5/8) Epoch 12, batch 19650, loss[loss=0.1258, simple_loss=0.2003, pruned_loss=0.02567, over 4975.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03172, over 972243.25 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:05:32,630 INFO [train.py:715] (5/8) Epoch 12, batch 19700, loss[loss=0.1237, simple_loss=0.1943, pruned_loss=0.02653, over 4888.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03179, over 972740.17 frames.], batch size: 38, lr: 1.80e-04
2022-05-07 12:06:12,004 INFO [train.py:715] (5/8) Epoch 12, batch 19750, loss[loss=0.1337, simple_loss=0.2017, pruned_loss=0.03288, over 4788.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03188, over 972678.50 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:06:52,639 INFO [train.py:715] (5/8) Epoch 12, batch 19800, loss[loss=0.1876, simple_loss=0.2587, pruned_loss=0.05822, over 4837.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2114, pruned_loss=0.03168, over 972602.17 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:07:33,085 INFO [train.py:715] (5/8) Epoch 12, batch 19850, loss[loss=0.1339, simple_loss=0.2146, pruned_loss=0.02664, over 4909.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03211, over 972603.86 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:08:14,256 INFO [train.py:715] (5/8) Epoch 12, batch 19900, loss[loss=0.125, simple_loss=0.2043, pruned_loss=0.02283, over 4787.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2114, pruned_loss=0.03161, over 971882.23 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:08:54,594 INFO [train.py:715] (5/8) Epoch 12, batch 19950, loss[loss=0.1291, simple_loss=0.1902, pruned_loss=0.034, over 4976.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03167, over 972399.79 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:09:35,207 INFO [train.py:715] (5/8) Epoch 12, batch 20000, loss[loss=0.1302, simple_loss=0.1987, pruned_loss=0.03082, over 4895.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03179, over 971918.79 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:10:15,439 INFO [train.py:715] (5/8) Epoch 12, batch 20050, loss[loss=0.1204, simple_loss=0.1966, pruned_loss=0.02206, over 4861.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.0316, over 972687.14 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:10:55,688 INFO [train.py:715] (5/8) Epoch 12, batch 20100, loss[loss=0.1667, simple_loss=0.2279, pruned_loss=0.05273, over 4701.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03196, over 973258.77 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:11:35,654 INFO [train.py:715] (5/8) Epoch 12, batch 20150, loss[loss=0.1167, simple_loss=0.1874, pruned_loss=0.02301, over 4991.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03174, over 973058.53 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:12:16,045 INFO [train.py:715] (5/8) Epoch 12, batch 20200, loss[loss=0.1511, simple_loss=0.2358, pruned_loss=0.03323, over 4930.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03209, over 973703.16 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:12:56,153 INFO [train.py:715] (5/8) Epoch 12, batch 20250, loss[loss=0.1219, simple_loss=0.1955, pruned_loss=0.02418, over 4798.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03164, over 974031.85 frames.], batch size: 25, lr: 1.80e-04
2022-05-07 12:13:36,209 INFO [train.py:715] (5/8) Epoch 12, batch 20300, loss[loss=0.1389, simple_loss=0.2072, pruned_loss=0.03524, over 4910.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 973856.43 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:14:16,798 INFO [train.py:715] (5/8) Epoch 12, batch 20350, loss[loss=0.1305, simple_loss=0.2062, pruned_loss=0.02742, over 4920.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03152, over 972904.76 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:14:56,468 INFO [train.py:715] (5/8) Epoch 12, batch 20400, loss[loss=0.1204, simple_loss=0.1913, pruned_loss=0.02479, over 4942.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.0314, over 973183.66 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:15:36,232 INFO [train.py:715] (5/8) Epoch 12, batch 20450, loss[loss=0.1064, simple_loss=0.1754, pruned_loss=0.01871, over 4817.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03099, over 972160.89 frames.], batch size: 25, lr: 1.80e-04
2022-05-07 12:16:15,880 INFO [train.py:715] (5/8) Epoch 12, batch 20500, loss[loss=0.1397, simple_loss=0.2164, pruned_loss=0.03148, over 4821.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03068, over 971875.75 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:16:56,322 INFO [train.py:715] (5/8) Epoch 12, batch 20550, loss[loss=0.1279, simple_loss=0.2141, pruned_loss=0.02081, over 4790.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.0306, over 971167.43 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:17:36,241 INFO [train.py:715] (5/8) Epoch 12, batch 20600, loss[loss=0.1144, simple_loss=0.1846, pruned_loss=0.0221, over 4975.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03114, over 972120.31 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:18:15,187 INFO [train.py:715] (5/8) Epoch 12, batch 20650, loss[loss=0.1306, simple_loss=0.2041, pruned_loss=0.02858, over 4922.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03158, over 973286.14 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:18:54,296 INFO [train.py:715] (5/8) Epoch 12, batch 20700, loss[loss=0.1176, simple_loss=0.1964, pruned_loss=0.01943, over 4782.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03132, over 972862.99 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:19:32,273 INFO [train.py:715] (5/8) Epoch 12, batch 20750, loss[loss=0.1331, simple_loss=0.2063, pruned_loss=0.02992, over 4913.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03192, over 972487.89 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:20:10,574 INFO [train.py:715] (5/8) Epoch 12, batch 20800, loss[loss=0.1411, simple_loss=0.2195, pruned_loss=0.03136, over 4774.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03221, over 972221.70 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:20:48,326 INFO [train.py:715] (5/8) Epoch 12, batch 20850, loss[loss=0.1529, simple_loss=0.2266, pruned_loss=0.03957, over 4903.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03236, over 972006.01 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:21:26,467 INFO [train.py:715] (5/8) Epoch 12, batch 20900, loss[loss=0.1302, simple_loss=0.2103, pruned_loss=0.02508, over 4815.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03204, over 972160.78 frames.], batch size: 27, lr: 1.80e-04
2022-05-07 12:22:04,011 INFO [train.py:715] (5/8) Epoch 12, batch 20950, loss[loss=0.1482, simple_loss=0.2202, pruned_loss=0.0381, over 4918.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 971943.69 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:22:41,374 INFO [train.py:715] (5/8) Epoch 12, batch 21000, loss[loss=0.1275, simple_loss=0.2011, pruned_loss=0.02694, over 4976.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03223, over 972580.58 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:22:41,375 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 12:22:50,899 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 12:23:28,721 INFO [train.py:715] (5/8) Epoch 12, batch 21050, loss[loss=0.1259, simple_loss=0.2045, pruned_loss=0.02367, over 4853.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03217, over 971956.78 frames.], batch size: 34, lr: 1.80e-04
2022-05-07 12:24:06,827 INFO [train.py:715] (5/8) Epoch 12, batch 21100, loss[loss=0.1504, simple_loss=0.2217, pruned_loss=0.03953, over 4783.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03195, over 971600.53 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:24:44,630 INFO [train.py:715] (5/8) Epoch 12, batch 21150, loss[loss=0.1447, simple_loss=0.2186, pruned_loss=0.03539, over 4963.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03183, over 972512.73 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:25:22,418 INFO [train.py:715] (5/8) Epoch 12, batch 21200, loss[loss=0.1102, simple_loss=0.1808, pruned_loss=0.01979, over 4938.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03204, over 972604.95 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:26:00,693 INFO [train.py:715] (5/8) Epoch 12, batch 21250, loss[loss=0.117, simple_loss=0.1972, pruned_loss=0.01837, over 4877.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03164, over 972712.09 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:26:39,510 INFO [train.py:715] (5/8) Epoch 12, batch 21300, loss[loss=0.1093, simple_loss=0.181, pruned_loss=0.01884, over 4822.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03156, over 972368.37 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:27:17,264 INFO [train.py:715] (5/8) Epoch 12, batch 21350, loss[loss=0.1217, simple_loss=0.1913, pruned_loss=0.02601, over 4775.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03121, over 971877.27 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:27:56,358 INFO [train.py:715] (5/8) Epoch 12, batch 21400, loss[loss=0.1305, simple_loss=0.2084, pruned_loss=0.02626, over 4781.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.0311, over 971778.21 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:28:35,912 INFO [train.py:715] (5/8) Epoch 12, batch 21450, loss[loss=0.1509, simple_loss=0.2198, pruned_loss=0.04097, over 4756.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.0315, over 970964.60 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:29:14,510 INFO [train.py:715] (5/8) Epoch 12, batch 21500, loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.0342, over 4890.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03146, over 971395.21 frames.], batch size: 22, lr: 1.80e-04
2022-05-07 12:29:53,098 INFO [train.py:715] (5/8) Epoch 12, batch 21550, loss[loss=0.1721, simple_loss=0.251, pruned_loss=0.04661, over 4892.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.0311, over 971783.92 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:30:31,273 INFO [train.py:715] (5/8) Epoch 12, batch 21600, loss[loss=0.1393, simple_loss=0.2189, pruned_loss=0.02985, over 4940.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03174, over 972334.75 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:31:09,733 INFO [train.py:715] (5/8) Epoch 12, batch 21650, loss[loss=0.1172, simple_loss=0.1967, pruned_loss=0.01887, over 4928.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03188, over 971807.05 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:31:46,933 INFO [train.py:715] (5/8) Epoch 12, batch 21700, loss[loss=0.1271, simple_loss=0.2021, pruned_loss=0.0261, over 4699.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03238, over 971600.43 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:32:25,495 INFO [train.py:715] (5/8) Epoch 12, batch 21750, loss[loss=0.1394, simple_loss=0.2175, pruned_loss=0.03064, over 4974.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03251, over 972822.54 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:33:04,219 INFO [train.py:715] (5/8) Epoch 12, batch 21800, loss[loss=0.1193, simple_loss=0.1974, pruned_loss=0.02062, over 4976.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 972659.12 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:33:42,110 INFO [train.py:715] (5/8) Epoch 12, batch 21850, loss[loss=0.1391, simple_loss=0.2069, pruned_loss=0.03558, over 4879.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03152, over 971976.13 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:34:19,726 INFO [train.py:715] (5/8) Epoch 12, batch 21900, loss[loss=0.1226, simple_loss=0.1959, pruned_loss=0.02463, over 4913.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03161, over 971399.99 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:34:58,474 INFO [train.py:715] (5/8) Epoch 12, batch 21950, loss[loss=0.1164, simple_loss=0.1968, pruned_loss=0.01802, over 4746.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03138, over 970895.59 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:35:37,476 INFO [train.py:715] (5/8) Epoch 12, batch 22000, loss[loss=0.1485, simple_loss=0.2144, pruned_loss=0.04133, over 4760.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03157, over 971330.41 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:36:15,711 INFO [train.py:715] (5/8) Epoch 12, batch 22050, loss[loss=0.1531, simple_loss=0.2255, pruned_loss=0.04034, over 4782.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03183, over 971617.77 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:36:54,704 INFO [train.py:715] (5/8) Epoch 12, batch 22100, loss[loss=0.1322, simple_loss=0.2027, pruned_loss=0.03084, over 4801.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03123, over 970896.15 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:37:33,659 INFO [train.py:715] (5/8) Epoch 12, batch 22150, loss[loss=0.1103, simple_loss=0.1808, pruned_loss=0.01993, over 4648.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03152, over 970565.03 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:38:11,933 INFO [train.py:715] (5/8) Epoch 12, batch 22200, loss[loss=0.1619, simple_loss=0.2178, pruned_loss=0.05294, over 4881.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03147, over 970446.59 frames.], batch size: 32, lr: 1.80e-04
2022-05-07 12:38:49,699 INFO [train.py:715] (5/8) Epoch 12, batch 22250, loss[loss=0.1495, simple_loss=0.2254, pruned_loss=0.03674, over 4817.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03156, over 971575.03 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:39:30,402 INFO [train.py:715] (5/8) Epoch 12, batch 22300, loss[loss=0.1451, simple_loss=0.2193, pruned_loss=0.0355, over 4793.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03177, over 972276.71 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:40:08,653 INFO [train.py:715] (5/8) Epoch 12, batch 22350, loss[loss=0.1321, simple_loss=0.204, pruned_loss=0.03007, over 4910.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03187, over 972783.19 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:40:46,759 INFO [train.py:715] (5/8) Epoch 12, batch 22400, loss[loss=0.1171, simple_loss=0.1944, pruned_loss=0.01995, over 4798.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03165, over 971288.47 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:41:25,341 INFO [train.py:715] (5/8) Epoch 12, batch 22450, loss[loss=0.1349, simple_loss=0.2058, pruned_loss=0.03197, over 4991.00 frames.], tot_loss[loss=0.1369, simple_loss=0.211, pruned_loss=0.03146, over 971428.67 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:42:03,781 INFO [train.py:715] (5/8) Epoch 12, batch 22500, loss[loss=0.1603, simple_loss=0.2345, pruned_loss=0.04307, over 4935.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03138, over 971541.37 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:42:42,486 INFO [train.py:715] (5/8) Epoch 12, batch 22550, loss[loss=0.169, simple_loss=0.2337, pruned_loss=0.05219, over 4695.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03188, over 971884.51 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:43:20,634 INFO [train.py:715] (5/8) Epoch 12, batch 22600, loss[loss=0.1717, simple_loss=0.2468, pruned_loss=0.04832, over 4896.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03218, over 972214.53 frames.], batch size: 38, lr: 1.80e-04
2022-05-07 12:43:58,689 INFO [train.py:715] (5/8) Epoch 12, batch 22650, loss[loss=0.147, simple_loss=0.2162, pruned_loss=0.0389, over 4853.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03272, over 972364.02 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:44:36,593 INFO [train.py:715] (5/8) Epoch 12, batch 22700, loss[loss=0.1464, simple_loss=0.2309, pruned_loss=0.03095, over 4871.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03261, over 972306.66 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:45:14,816 INFO [train.py:715] (5/8) Epoch 12, batch 22750, loss[loss=0.1286, simple_loss=0.2026, pruned_loss=0.02729, over 4981.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03218, over 972335.59 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:45:53,322 INFO [train.py:715] (5/8) Epoch 12, batch 22800, loss[loss=0.1504, simple_loss=0.2272, pruned_loss=0.03676, over 4926.00 frames.], tot_loss[loss=0.1379, simple_loss=0.212, pruned_loss=0.03188, over 971737.58 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:46:32,312 INFO [train.py:715] (5/8) Epoch 12, batch 22850, loss[loss=0.1695, simple_loss=0.2431, pruned_loss=0.04795, over 4773.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2111, pruned_loss=0.03119, over 971171.01 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:47:10,524 INFO [train.py:715] (5/8) Epoch 12, batch 22900, loss[loss=0.1374, simple_loss=0.2088, pruned_loss=0.03297, over 4752.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03113, over 971022.65 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:47:48,404 INFO [train.py:715] (5/8) Epoch 12, batch 22950, loss[loss=0.1298, simple_loss=0.2112, pruned_loss=0.02424, over 4867.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03109, over 971530.01 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:48:26,681 INFO [train.py:715] (5/8) Epoch 12, batch 23000, loss[loss=0.1678, simple_loss=0.2371, pruned_loss=0.04928, over 4946.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03117, over 971419.88 frames.], batch size: 35, lr: 1.80e-04
2022-05-07 12:49:04,949 INFO [train.py:715] (5/8) Epoch 12, batch 23050, loss[loss=0.14, simple_loss=0.2174, pruned_loss=0.03136, over 4876.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03147, over 971593.26 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:49:43,056 INFO [train.py:715] (5/8) Epoch 12, batch 23100, loss[loss=0.1294, simple_loss=0.2057, pruned_loss=0.02656, over 4891.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03148, over 971963.57 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:50:21,954 INFO [train.py:715] (5/8) Epoch 12, batch 23150, loss[loss=0.1423, simple_loss=0.2126, pruned_loss=0.03597, over 4892.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03149, over 972072.96 frames.], batch size: 22, lr: 1.80e-04
2022-05-07 12:51:01,023 INFO [train.py:715] (5/8) Epoch 12, batch 23200, loss[loss=0.1464, simple_loss=0.2196, pruned_loss=0.03658, over 4816.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03138, over 973000.47 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:51:39,415 INFO [train.py:715] (5/8) Epoch 12, batch 23250, loss[loss=0.1388, simple_loss=0.2207, pruned_loss=0.02845, over 4696.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03129, over 973631.97 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:52:17,109 INFO [train.py:715] (5/8) Epoch 12, batch 23300, loss[loss=0.1179, simple_loss=0.1969, pruned_loss=0.01943, over 4755.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03098, over 973484.20 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:52:55,810 INFO [train.py:715] (5/8) Epoch 12, batch 23350, loss[loss=0.1416, simple_loss=0.2212, pruned_loss=0.03097, over 4794.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03152, over 973912.60 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:53:33,837 INFO [train.py:715] (5/8) Epoch 12, batch 23400, loss[loss=0.1493, simple_loss=0.2152, pruned_loss=0.04166, over 4849.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03195, over 973458.75 frames.], batch size: 32, lr: 1.80e-04
2022-05-07 12:54:11,386 INFO [train.py:715] (5/8) Epoch 12, batch 23450, loss[loss=0.1495, simple_loss=0.2098, pruned_loss=0.04459, over 4768.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03202, over 973023.02 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:54:49,572 INFO [train.py:715] (5/8) Epoch 12, batch 23500, loss[loss=0.165, simple_loss=0.2518, pruned_loss=0.03906, over 4960.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2118, pruned_loss=0.03178, over 972564.43 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:55:28,411 INFO [train.py:715] (5/8) Epoch 12, batch 23550, loss[loss=0.1183, simple_loss=0.2056, pruned_loss=0.01547, over 4823.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2116, pruned_loss=0.03166, over 972263.45 frames.], batch size: 25, lr: 1.80e-04
2022-05-07 12:56:07,099 INFO [train.py:715] (5/8) Epoch 12, batch 23600, loss[loss=0.1821, simple_loss=0.2461, pruned_loss=0.05902, over 4988.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03134, over 973373.84 frames.], batch size: 33, lr: 1.80e-04
2022-05-07 12:56:45,798 INFO [train.py:715] (5/8) Epoch 12, batch 23650, loss[loss=0.1371, simple_loss=0.2151, pruned_loss=0.02955, over 4933.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.0318, over 973850.33 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:57:24,209 INFO [train.py:715] (5/8) Epoch 12, batch 23700, loss[loss=0.127, simple_loss=0.1958, pruned_loss=0.02914, over 4926.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2123, pruned_loss=0.03251, over 973864.54 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:58:02,489 INFO [train.py:715] (5/8) Epoch 12, batch 23750, loss[loss=0.1285, simple_loss=0.2102, pruned_loss=0.02337, over 4834.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03188, over 973630.92 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:58:41,203 INFO [train.py:715] (5/8) Epoch 12, batch 23800, loss[loss=0.1522, simple_loss=0.227, pruned_loss=0.03868, over 4783.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03215, over 973128.52 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:59:20,121 INFO [train.py:715] (5/8) Epoch 12, batch 23850, loss[loss=0.1223, simple_loss=0.2001, pruned_loss=0.02221, over 4823.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03183, over 971810.61 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:59:59,698 INFO [train.py:715] (5/8) Epoch 12, batch 23900, loss[loss=0.1285, simple_loss=0.194, pruned_loss=0.03155, over 4862.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03155, over 972534.40 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 13:00:39,415 INFO [train.py:715] (5/8) Epoch 12, batch 23950, loss[loss=0.1439, simple_loss=0.2126, pruned_loss=0.03762, over 4839.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03167, over 971678.66 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:01:18,254 INFO [train.py:715] (5/8) Epoch 12, batch 24000, loss[loss=0.1331, simple_loss=0.2095, pruned_loss=0.0284, over 4783.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03174, over 972531.47 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:01:18,255 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 13:01:27,802 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1895, pruned_loss=0.01071, over 914524.00 frames.
2022-05-07 13:02:06,830 INFO [train.py:715] (5/8) Epoch 12, batch 24050, loss[loss=0.1243, simple_loss=0.1929, pruned_loss=0.02784, over 4865.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.0318, over 973031.94 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:02:47,353 INFO [train.py:715] (5/8) Epoch 12, batch 24100, loss[loss=0.1405, simple_loss=0.2107, pruned_loss=0.03518, over 4984.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03165, over 972882.10 frames.], batch size: 33, lr: 1.79e-04
2022-05-07 13:03:27,828 INFO [train.py:715] (5/8) Epoch 12, batch 24150, loss[loss=0.1301, simple_loss=0.2041, pruned_loss=0.02805, over 4958.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 972362.38 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:04:07,865 INFO [train.py:715] (5/8) Epoch 12, batch 24200, loss[loss=0.1252, simple_loss=0.1961, pruned_loss=0.02716, over 4827.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03076, over 972239.58 frames.], batch size: 26, lr: 1.79e-04
2022-05-07 13:04:47,989 INFO [train.py:715] (5/8) Epoch 12, batch 24250, loss[loss=0.1494, simple_loss=0.2199, pruned_loss=0.03951, over 4981.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03054, over 973514.03 frames.], batch size: 28, lr: 1.79e-04
2022-05-07 13:05:28,029 INFO [train.py:715] (5/8) Epoch 12, batch 24300, loss[loss=0.1459, simple_loss=0.2334, pruned_loss=0.02925, over 4982.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03085, over 973724.47 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:06:07,758 INFO [train.py:715] (5/8) Epoch 12, batch 24350, loss[loss=0.1272, simple_loss=0.1967, pruned_loss=0.02879, over 4881.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03115, over 973552.13 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:06:47,578 INFO [train.py:715] (5/8) Epoch 12, batch 24400, loss[loss=0.1221, simple_loss=0.1966, pruned_loss=0.02385, over 4902.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.0314, over 972430.39 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:07:27,539 INFO [train.py:715] (5/8) Epoch 12, batch 24450, loss[loss=0.1576, simple_loss=0.2365, pruned_loss=0.03939, over 4826.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03135, over 972522.75 frames.], batch size: 26, lr: 1.79e-04
2022-05-07 13:08:07,312 INFO [train.py:715] (5/8) Epoch 12, batch 24500, loss[loss=0.1584, simple_loss=0.2309, pruned_loss=0.04296, over 4954.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03172, over 973509.62 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:08:46,553 INFO [train.py:715] (5/8) Epoch 12, batch 24550, loss[loss=0.1089, simple_loss=0.1913, pruned_loss=0.01325, over 4806.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03177, over 973169.93 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:09:26,205 INFO [train.py:715] (5/8) Epoch 12, batch 24600, loss[loss=0.1419, simple_loss=0.2155, pruned_loss=0.03412, over 4861.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03221, over 972154.00 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:10:05,928 INFO [train.py:715] (5/8) Epoch 12, batch 24650, loss[loss=0.1445, simple_loss=0.2153, pruned_loss=0.03685, over 4985.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03189, over 972063.07 frames.], batch size: 28, lr: 1.79e-04
2022-05-07 13:10:45,634 INFO [train.py:715] (5/8) Epoch 12, batch 24700, loss[loss=0.1398, simple_loss=0.2149, pruned_loss=0.03238, over 4970.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03202, over 972020.12 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:11:24,792 INFO [train.py:715] (5/8) Epoch 12, batch 24750, loss[loss=0.1578, simple_loss=0.2281, pruned_loss=0.04372, over 4876.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03242, over 972507.25 frames.], batch size: 38, lr: 1.79e-04
2022-05-07 13:12:05,000 INFO [train.py:715] (5/8) Epoch 12, batch 24800, loss[loss=0.1703, simple_loss=0.2608, pruned_loss=0.03996, over 4829.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03237, over 972568.52 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:12:44,865 INFO [train.py:715] (5/8) Epoch 12, batch 24850, loss[loss=0.1359, simple_loss=0.2034, pruned_loss=0.03423, over 4796.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03257, over 972069.22 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:13:24,110 INFO [train.py:715] (5/8) Epoch 12, batch 24900, loss[loss=0.1219, simple_loss=0.1946, pruned_loss=0.02458, over 4980.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03209, over 972404.75 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:14:03,441 INFO [train.py:715] (5/8) Epoch 12, batch 24950, loss[loss=0.1502, simple_loss=0.2289, pruned_loss=0.03569, over 4783.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03232, over 972377.74 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:14:42,358 INFO [train.py:715] (5/8) Epoch 12, batch 25000, loss[loss=0.172, simple_loss=0.2384, pruned_loss=0.0528, over 4871.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03242, over 972262.76 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 13:15:20,411 INFO [train.py:715] (5/8) Epoch 12, batch 25050, loss[loss=0.1719, simple_loss=0.2429, pruned_loss=0.05043, over 4990.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03215, over 973139.15 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:15:58,462 INFO [train.py:715] (5/8) Epoch 12, batch 25100, loss[loss=0.134, simple_loss=0.2185, pruned_loss=0.02477, over 4927.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03169, over 972843.86 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:16:36,853 INFO [train.py:715] (5/8) Epoch 12, batch 25150, loss[loss=0.146, simple_loss=0.2157, pruned_loss=0.03816, over 4988.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.0316, over 973475.17 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:17:15,106 INFO [train.py:715] (5/8) Epoch 12, batch 25200, loss[loss=0.1358, simple_loss=0.222, pruned_loss=0.02481, over 4770.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03173, over 973223.43 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:17:52,724 INFO [train.py:715] (5/8) Epoch 12, batch 25250, loss[loss=0.1596, simple_loss=0.2253, pruned_loss=0.0469, over 4849.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03197, over 971984.56 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:18:30,735 INFO [train.py:715] (5/8) Epoch 12, batch 25300, loss[loss=0.1573, simple_loss=0.2236, pruned_loss=0.04553, over 4859.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03263, over 971230.62 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:19:08,817 INFO [train.py:715] (5/8) Epoch 12, batch 25350, loss[loss=0.1341, simple_loss=0.2101, pruned_loss=0.02908, over 4689.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03299, over 971049.12 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:19:47,791 INFO [train.py:715] (5/8) Epoch 12, batch 25400, loss[loss=0.1246, simple_loss=0.1977, pruned_loss=0.02577, over 4930.00 frames.], tot_loss[loss=0.1397, simple_loss=0.212, pruned_loss=0.03364, over 971176.65 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:20:26,680 INFO [train.py:715] (5/8) Epoch 12, batch 25450, loss[loss=0.1569, simple_loss=0.2388, pruned_loss=0.03745, over 4976.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03325, over 971572.64 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:21:06,564 INFO [train.py:715] (5/8) Epoch 12, batch 25500, loss[loss=0.1427, simple_loss=0.2017, pruned_loss=0.04181, over 4900.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03289, over 971135.07 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:21:45,632 INFO [train.py:715] (5/8) Epoch 12, batch 25550, loss[loss=0.1399, simple_loss=0.2133, pruned_loss=0.03328, over 4888.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03244, over 971014.59 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:22:23,735 INFO [train.py:715] (5/8) Epoch 12, batch 25600, loss[loss=0.1191, simple_loss=0.1926, pruned_loss=0.02278, over 4911.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03174, over 971032.19 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:23:02,064 INFO [train.py:715] (5/8) Epoch 12, batch 25650, loss[loss=0.1602, simple_loss=0.231, pruned_loss=0.0447, over 4750.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03176, over 970753.91 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:23:40,757 INFO [train.py:715] (5/8) Epoch 12, batch 25700, loss[loss=0.1617, simple_loss=0.2298, pruned_loss=0.0468, over 4707.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03172, over 970787.49 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:24:19,542 INFO [train.py:715] (5/8) Epoch 12, batch 25750, loss[loss=0.1272, simple_loss=0.2048, pruned_loss=0.0248, over 4941.00 frames.], tot_loss[loss=0.136, simple_loss=0.2092, pruned_loss=0.03139, over 970042.64 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:24:58,010 INFO [train.py:715] (5/8) Epoch 12, batch 25800, loss[loss=0.1523, simple_loss=0.2171, pruned_loss=0.04377, over 4742.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03129, over 969948.40 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:25:36,921 INFO [train.py:715] (5/8) Epoch 12, batch 25850, loss[loss=0.1609, simple_loss=0.2168, pruned_loss=0.05249, over 4829.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03142, over 969967.37 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:26:15,480 INFO [train.py:715] (5/8) Epoch 12, batch 25900, loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04137, over 4809.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.0318, over 970193.93 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:26:53,772 INFO [train.py:715] (5/8) Epoch 12, batch 25950, loss[loss=0.1323, simple_loss=0.2074, pruned_loss=0.02864, over 4910.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2096, pruned_loss=0.03186, over 970914.58 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:27:31,255 INFO [train.py:715] (5/8) Epoch 12, batch 26000, loss[loss=0.1554, simple_loss=0.2254, pruned_loss=0.04267, over 4764.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 971178.96 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:28:09,532 INFO [train.py:715] (5/8) Epoch 12, batch 26050, loss[loss=0.1434, simple_loss=0.2167, pruned_loss=0.03506, over 4959.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03172, over 971589.15 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:28:48,386 INFO [train.py:715] (5/8) Epoch 12, batch 26100, loss[loss=0.1388, simple_loss=0.2226, pruned_loss=0.0275, over 4984.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03235, over 971270.63 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:29:27,201 INFO [train.py:715] (5/8) Epoch 12, batch 26150, loss[loss=0.1912, simple_loss=0.2562, pruned_loss=0.06309, over 4842.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03213, over 971613.98 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:30:06,152 INFO [train.py:715] (5/8) Epoch 12, batch 26200, loss[loss=0.1579, simple_loss=0.2201, pruned_loss=0.04782, over 4973.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03183, over 971053.47 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:30:44,508 INFO [train.py:715] (5/8) Epoch 12, batch 26250, loss[loss=0.119, simple_loss=0.1884, pruned_loss=0.02479, over 4839.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03132, over 971147.06 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:31:23,012 INFO [train.py:715] (5/8) Epoch 12, batch 26300, loss[loss=0.1615, simple_loss=0.2244, pruned_loss=0.04927, over 4860.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03145, over 970815.31 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:32:02,153 INFO [train.py:715] (5/8) Epoch 12, batch 26350, loss[loss=0.1528, simple_loss=0.2261, pruned_loss=0.03974, over 4868.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03126, over 971613.60 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:32:40,222 INFO [train.py:715] (5/8) Epoch 12, batch 26400, loss[loss=0.1259, simple_loss=0.2065, pruned_loss=0.02268, over 4934.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.032, over 972977.43 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:33:18,355 INFO [train.py:715] (5/8) Epoch 12, batch 26450, loss[loss=0.1843, simple_loss=0.2699, pruned_loss=0.04933, over 4856.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03247, over 971982.07 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:33:56,291 INFO [train.py:715] (5/8) Epoch 12, batch 26500, loss[loss=0.1209, simple_loss=0.1965, pruned_loss=0.02264, over 4948.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03259, over 972125.13 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:34:34,592 INFO [train.py:715] (5/8) Epoch 12, batch 26550, loss[loss=0.1436, simple_loss=0.2209, pruned_loss=0.0332, over 4797.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03237, over 972724.81 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:35:12,934 INFO [train.py:715] (5/8) Epoch 12, batch 26600, loss[loss=0.1325, simple_loss=0.2097, pruned_loss=0.02763, over 4757.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.0321, over 973363.87 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:35:51,456 INFO [train.py:715] (5/8) Epoch 12, batch 26650, loss[loss=0.125, simple_loss=0.2037, pruned_loss=0.02314, over 4810.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03229, over 972655.95 frames.], batch size: 26, lr: 1.79e-04
2022-05-07 13:36:30,042 INFO [train.py:715] (5/8) Epoch 12, batch 26700, loss[loss=0.1732, simple_loss=0.2401, pruned_loss=0.05315, over 4844.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03273, over 972675.62 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:37:08,438 INFO [train.py:715] (5/8) Epoch 12, batch 26750, loss[loss=0.1267, simple_loss=0.2022, pruned_loss=0.02559, over 4782.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03214, over 972619.26 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:37:47,908 INFO [train.py:715] (5/8) Epoch 12, batch 26800, loss[loss=0.1244, simple_loss=0.2019, pruned_loss=0.02344, over 4902.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03199, over 972169.89 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 13:38:27,724 INFO [train.py:715] (5/8) Epoch 12, batch 26850, loss[loss=0.1437, simple_loss=0.2193, pruned_loss=0.0341, over 4840.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 972212.65 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:39:07,107 INFO [train.py:715] (5/8) Epoch 12, batch 26900, loss[loss=0.157, simple_loss=0.2293, pruned_loss=0.04237, over 4877.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03181, over 972172.02 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:39:45,935 INFO [train.py:715] (5/8) Epoch 12, batch 26950, loss[loss=0.1332, simple_loss=0.2125, pruned_loss=0.02697, over 4933.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03185, over 971906.54 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:40:25,466 INFO [train.py:715] (5/8) Epoch 12, batch 27000, loss[loss=0.1652, simple_loss=0.2153, pruned_loss=0.05757, over 4978.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03184, over 971526.92 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:40:25,467 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 13:40:37,911 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
2022-05-07 13:41:17,233 INFO [train.py:715] (5/8) Epoch 12, batch 27050, loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02976, over 4823.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03201, over 971689.91 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:41:55,463 INFO [train.py:715] (5/8) Epoch 12, batch 27100, loss[loss=0.119, simple_loss=0.1946, pruned_loss=0.02166, over 4931.00 frames.], tot_loss[loss=0.1381, simple_loss=0.212, pruned_loss=0.03214, over 971948.33 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:42:33,821 INFO [train.py:715] (5/8) Epoch 12, batch 27150, loss[loss=0.1373, simple_loss=0.2048, pruned_loss=0.03489, over 4837.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03175, over 971274.09 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:43:12,676 INFO [train.py:715] (5/8) Epoch 12, batch 27200, loss[loss=0.1457, simple_loss=0.2297, pruned_loss=0.03085, over 4891.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03196, over 972190.82 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 13:43:50,976 INFO [train.py:715] (5/8) Epoch 12, batch 27250, loss[loss=0.1247, simple_loss=0.193, pruned_loss=0.02817, over 4839.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03268, over 972259.32 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:44:29,601 INFO [train.py:715] (5/8) Epoch 12, batch 27300, loss[loss=0.1108, simple_loss=0.19, pruned_loss=0.01583, over 4755.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03252, over 971987.52 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:45:08,185 INFO [train.py:715] (5/8) Epoch 12, batch 27350, loss[loss=0.1529, simple_loss=0.2277, pruned_loss=0.03903, over 4890.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03272, over 971773.83 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:45:47,172 INFO [train.py:715] (5/8) Epoch 12, batch 27400, loss[loss=0.1094, simple_loss=0.1838, pruned_loss=0.01751, over 4727.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03232, over 972279.41 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 13:46:25,847 INFO [train.py:715] (5/8) Epoch 12, batch 27450, loss[loss=0.1194, simple_loss=0.206, pruned_loss=0.01635, over 4800.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03195, over 971922.48 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:47:04,345 INFO [train.py:715] (5/8) Epoch 12, batch 27500, loss[loss=0.1345, simple_loss=0.2046, pruned_loss=0.03219, over 4930.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03206, over 971362.09 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:47:43,118 INFO [train.py:715] (5/8) Epoch 12, batch 27550, loss[loss=0.1261, simple_loss=0.2047, pruned_loss=0.02375, over 4774.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03205, over 971478.14 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:48:21,799 INFO [train.py:715] (5/8) Epoch 12, batch 27600, loss[loss=0.1585, simple_loss=0.2298, pruned_loss=0.04355, over 4921.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.0322, over 972145.63 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:49:00,949 INFO [train.py:715] (5/8) Epoch 12, batch 27650, loss[loss=0.1334, simple_loss=0.2107, pruned_loss=0.02807, over 4803.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03251, over 972830.51 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:49:39,560 INFO [train.py:715] (5/8) Epoch 12, batch 27700, loss[loss=0.1102, simple_loss=0.1732, pruned_loss=0.02364, over 4818.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03269, over 972928.39 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:50:18,423 INFO [train.py:715] (5/8) Epoch 12, batch 27750, loss[loss=0.1537, simple_loss=0.2264, pruned_loss=0.04048, over 4810.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03299, over 973150.45 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 13:50:56,329 INFO [train.py:715] (5/8) Epoch 12, batch 27800, loss[loss=0.1391, simple_loss=0.2157, pruned_loss=0.03122, over 4992.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03258, over 972332.67 frames.], batch size: 31, lr: 1.79e-04
2022-05-07 13:51:34,004 INFO [train.py:715] (5/8) Epoch 12, batch 27850, loss[loss=0.1412, simple_loss=0.2119, pruned_loss=0.03523, over 4850.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03201, over 972502.32 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:52:12,421 INFO [train.py:715] (5/8) Epoch 12, batch 27900, loss[loss=0.1442, simple_loss=0.2068, pruned_loss=0.04082, over 4833.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03181, over 972803.65 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:52:50,386 INFO [train.py:715] (5/8) Epoch 12, batch 27950, loss[loss=0.1419, simple_loss=0.2118, pruned_loss=0.03603, over 4977.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03171, over 972211.63 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:53:28,679 INFO [train.py:715] (5/8) Epoch 12, batch 28000, loss[loss=0.1202, simple_loss=0.189, pruned_loss=0.0257, over 4805.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03143, over 971716.96 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 13:54:06,332 INFO [train.py:715] (5/8) Epoch 12, batch 28050, loss[loss=0.1275, simple_loss=0.2009, pruned_loss=0.02709, over 4985.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03131, over 973365.66 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:54:44,516 INFO [train.py:715] (5/8) Epoch 12, batch 28100, loss[loss=0.1335, simple_loss=0.2037, pruned_loss=0.03162, over 4793.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03133, over 972424.41 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:55:22,258 INFO [train.py:715] (5/8) Epoch 12, batch 28150, loss[loss=0.1328, simple_loss=0.2037, pruned_loss=0.03098, over 4841.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03146, over 972155.03 frames.], batch size: 26, lr: 1.79e-04
2022-05-07 13:56:00,658 INFO [train.py:715] (5/8) Epoch 12, batch 28200, loss[loss=0.135, simple_loss=0.2107, pruned_loss=0.02968, over 4849.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03202, over 972353.55 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:56:39,077 INFO [train.py:715] (5/8) Epoch 12, batch 28250, loss[loss=0.1477, simple_loss=0.226, pruned_loss=0.03463, over 4994.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03207, over 972314.21 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:57:17,044 INFO [train.py:715] (5/8) Epoch 12, batch 28300, loss[loss=0.1262, simple_loss=0.2027, pruned_loss=0.02487, over 4808.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.0319, over 972742.06 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:57:55,848 INFO [train.py:715] (5/8) Epoch 12, batch 28350, loss[loss=0.1245, simple_loss=0.213, pruned_loss=0.01801, over 4851.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2111, pruned_loss=0.03136, over 971906.77 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:58:33,887 INFO [train.py:715] (5/8) Epoch 12, batch 28400, loss[loss=0.126, simple_loss=0.1888, pruned_loss=0.03164, over 4907.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03186, over 972281.23 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:59:12,072 INFO [train.py:715] (5/8) Epoch 12, batch 28450, loss[loss=0.155, simple_loss=0.2301, pruned_loss=0.03996, over 4783.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03175, over 972132.90 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:59:49,932 INFO [train.py:715] (5/8) Epoch 12, batch 28500, loss[loss=0.1203, simple_loss=0.1907, pruned_loss=0.0249, over 4761.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 971771.26 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 14:00:27,901 INFO [train.py:715] (5/8) Epoch 12, batch 28550, loss[loss=0.1255, simple_loss=0.2, pruned_loss=0.0255, over 4740.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03188, over 972432.37 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 14:01:06,320 INFO [train.py:715] (5/8) Epoch 12, batch 28600, loss[loss=0.124, simple_loss=0.1954, pruned_loss=0.02633, over 4797.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03195, over 970614.41 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 14:01:44,215 INFO [train.py:715] (5/8) Epoch 12, batch 28650, loss[loss=0.1074, simple_loss=0.1894, pruned_loss=0.01272, over 4828.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03211, over 970272.17 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 14:02:23,314 INFO [train.py:715] (5/8) Epoch 12, batch 28700, loss[loss=0.1293, simple_loss=0.2113, pruned_loss=0.0236, over 4878.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03209, over 971003.18 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 14:03:01,819 INFO [train.py:715] (5/8) Epoch 12, batch 28750, loss[loss=0.152, simple_loss=0.2269, pruned_loss=0.03855, over 4836.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03173, over 971730.37 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 14:03:40,787 INFO [train.py:715] (5/8) Epoch 12, batch 28800, loss[loss=0.1381, simple_loss=0.207, pruned_loss=0.03464, over 4905.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03214, over 971868.45 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 14:04:18,677 INFO [train.py:715] (5/8) Epoch 12, batch 28850, loss[loss=0.108, simple_loss=0.185, pruned_loss=0.01553, over 4909.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.032, over 972230.45 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 14:04:57,034 INFO [train.py:715] (5/8) Epoch 12, batch 28900, loss[loss=0.1236, simple_loss=0.2037, pruned_loss=0.02173, over 4800.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 972396.74 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:05:35,792 INFO [train.py:715] (5/8) Epoch 12, batch 28950, loss[loss=0.1107, simple_loss=0.1853, pruned_loss=0.01806, over 4777.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03128, over 972458.98 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:06:14,145 INFO [train.py:715] (5/8) Epoch 12, batch 29000, loss[loss=0.1313, simple_loss=0.2048, pruned_loss=0.02884, over 4837.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03185, over 972490.39 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:06:53,418 INFO [train.py:715] (5/8) Epoch 12, batch 29050, loss[loss=0.1457, simple_loss=0.2196, pruned_loss=0.03588, over 4799.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03227, over 972280.01 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:07:31,884 INFO [train.py:715] (5/8) Epoch 12, batch 29100, loss[loss=0.153, simple_loss=0.2268, pruned_loss=0.03963, over 4921.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 971930.91 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:08:10,555 INFO [train.py:715] (5/8) Epoch 12, batch 29150, loss[loss=0.1456, simple_loss=0.2069, pruned_loss=0.04215, over 4834.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03164, over 971751.16 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:08:48,982 INFO [train.py:715] (5/8) Epoch 12, batch 29200, loss[loss=0.1482, simple_loss=0.2214, pruned_loss=0.03753, over 4961.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.0311, over 971801.62 frames.], batch size: 35, lr: 1.78e-04
2022-05-07 14:09:27,676 INFO [train.py:715] (5/8) Epoch 12, batch 29250, loss[loss=0.1362, simple_loss=0.2201, pruned_loss=0.02614, over 4731.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03125, over 971202.18 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:10:05,809 INFO [train.py:715] (5/8) Epoch 12, batch 29300, loss[loss=0.1245, simple_loss=0.2028, pruned_loss=0.02312, over 4787.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03173, over 971563.32 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:10:43,233 INFO [train.py:715] (5/8) Epoch 12, batch 29350, loss[loss=0.1378, simple_loss=0.2123, pruned_loss=0.03164, over 4899.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03213, over 972119.10 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:11:22,339 INFO [train.py:715] (5/8) Epoch 12, batch 29400, loss[loss=0.1377, simple_loss=0.2093, pruned_loss=0.03302, over 4844.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2098, pruned_loss=0.03186, over 971822.21 frames.], batch size: 34, lr: 1.78e-04
2022-05-07 14:12:00,594 INFO [train.py:715] (5/8) Epoch 12, batch 29450, loss[loss=0.1457, simple_loss=0.2249, pruned_loss=0.03328, over 4988.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2096, pruned_loss=0.0321, over 972034.25 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 14:12:38,752 INFO [train.py:715] (5/8) Epoch 12, batch 29500, loss[loss=0.1359, simple_loss=0.2132, pruned_loss=0.02928, over 4855.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03238, over 972490.62 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:13:16,879 INFO [train.py:715] (5/8) Epoch 12, batch 29550, loss[loss=0.1213, simple_loss=0.1897, pruned_loss=0.02638, over 4727.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03211, over 972756.92 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:13:55,807 INFO [train.py:715] (5/8) Epoch 12, batch 29600, loss[loss=0.1619, simple_loss=0.2384, pruned_loss=0.0427, over 4895.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03232, over 972872.20 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:14:34,033 INFO [train.py:715] (5/8) Epoch 12, batch 29650, loss[loss=0.101, simple_loss=0.1748, pruned_loss=0.01361, over 4803.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03169, over 972654.74 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:15:11,743 INFO [train.py:715] (5/8) Epoch 12, batch 29700, loss[loss=0.1346, simple_loss=0.2165, pruned_loss=0.02635, over 4910.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03123, over 972718.90 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:15:51,274 INFO [train.py:715] (5/8) Epoch 12, batch 29750, loss[loss=0.1303, simple_loss=0.2042, pruned_loss=0.02825, over 4771.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03122, over 972409.34 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:16:30,394 INFO [train.py:715] (5/8) Epoch 12, batch 29800, loss[loss=0.1242, simple_loss=0.1944, pruned_loss=0.02705, over 4822.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03123, over 972448.79 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 14:17:09,204 INFO [train.py:715] (5/8) Epoch 12, batch 29850, loss[loss=0.1574, simple_loss=0.2329, pruned_loss=0.04094, over 4751.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03173, over 971940.91 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:17:47,534 INFO [train.py:715] (5/8) Epoch 12, batch 29900, loss[loss=0.1234, simple_loss=0.1948, pruned_loss=0.02601, over 4906.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.0313, over 972437.93 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:18:26,387 INFO [train.py:715] (5/8) Epoch 12, batch 29950, loss[loss=0.126, simple_loss=0.2027, pruned_loss=0.02464, over 4869.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03175, over 971421.96 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:19:04,509 INFO [train.py:715] (5/8) Epoch 12, batch 30000, loss[loss=0.1302, simple_loss=0.1944, pruned_loss=0.03301, over 4860.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03149, over 971371.52 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:19:04,510 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 14:19:14,011 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
2022-05-07 14:19:52,926 INFO [train.py:715] (5/8) Epoch 12, batch 30050, loss[loss=0.1494, simple_loss=0.2212, pruned_loss=0.03882, over 4921.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03159, over 971563.10 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:20:31,330 INFO [train.py:715] (5/8) Epoch 12, batch 30100, loss[loss=0.1446, simple_loss=0.2201, pruned_loss=0.03448, over 4923.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03176, over 972161.79 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:21:10,496 INFO [train.py:715] (5/8) Epoch 12, batch 30150, loss[loss=0.148, simple_loss=0.2281, pruned_loss=0.03394, over 4904.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03189, over 972299.62 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:21:48,960 INFO [train.py:715] (5/8) Epoch 12, batch 30200, loss[loss=0.1247, simple_loss=0.2005, pruned_loss=0.02443, over 4976.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03199, over 972265.06 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:22:28,440 INFO [train.py:715] (5/8) Epoch 12, batch 30250, loss[loss=0.1195, simple_loss=0.1926, pruned_loss=0.02323, over 4944.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03206, over 972363.25 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:23:07,604 INFO [train.py:715] (5/8) Epoch 12, batch 30300, loss[loss=0.1151, simple_loss=0.1812, pruned_loss=0.02447, over 4839.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.0321, over 973588.97 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:23:45,573 INFO [train.py:715] (5/8) Epoch 12, batch 30350, loss[loss=0.1591, simple_loss=0.2291, pruned_loss=0.04452, over 4981.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03245, over 973348.28 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:24:23,562 INFO [train.py:715] (5/8) Epoch 12, batch 30400, loss[loss=0.1703, simple_loss=0.2436, pruned_loss=0.04855, over 4942.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03242, over 973381.74 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:25:01,296 INFO [train.py:715] (5/8) Epoch 12, batch 30450, loss[loss=0.1238, simple_loss=0.1959, pruned_loss=0.02587, over 4687.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03261, over 972780.83 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:25:39,285 INFO [train.py:715] (5/8) Epoch 12, batch 30500, loss[loss=0.1277, simple_loss=0.2003, pruned_loss=0.02761, over 4969.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03299, over 973544.20 frames.], batch size: 35, lr: 1.78e-04
2022-05-07 14:26:17,290 INFO [train.py:715] (5/8) Epoch 12, batch 30550, loss[loss=0.1292, simple_loss=0.188, pruned_loss=0.03518, over 4811.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03232, over 973370.38 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:26:55,237 INFO [train.py:715] (5/8) Epoch 12, batch 30600, loss[loss=0.1393, simple_loss=0.2036, pruned_loss=0.03755, over 4875.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03196, over 973603.44 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:27:32,190 INFO [train.py:715] (5/8) Epoch 12, batch 30650, loss[loss=0.1219, simple_loss=0.1951, pruned_loss=0.02437, over 4753.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03205, over 973941.16 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:28:10,733 INFO [train.py:715] (5/8) Epoch 12, batch 30700, loss[loss=0.1098, simple_loss=0.1875, pruned_loss=0.01609, over 4981.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03208, over 973886.71 frames.], batch size: 28, lr: 1.78e-04
2022-05-07 14:28:48,655 INFO [train.py:715] (5/8) Epoch 12, batch 30750, loss[loss=0.1312, simple_loss=0.2066, pruned_loss=0.02794, over 4837.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.0321, over 973135.70 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:29:27,168 INFO [train.py:715] (5/8) Epoch 12, batch 30800, loss[loss=0.1337, simple_loss=0.2084, pruned_loss=0.02956, over 4785.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03205, over 973503.78 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:30:05,817 INFO [train.py:715] (5/8) Epoch 12, batch 30850, loss[loss=0.1263, simple_loss=0.2026, pruned_loss=0.02498, over 4834.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03187, over 973512.43 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:30:45,021 INFO [train.py:715] (5/8) Epoch 12, batch 30900, loss[loss=0.137, simple_loss=0.2153, pruned_loss=0.0293, over 4829.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03143, over 972514.70 frames.], batch size: 27, lr: 1.78e-04
2022-05-07 14:31:23,359 INFO [train.py:715] (5/8) Epoch 12, batch 30950, loss[loss=0.1497, simple_loss=0.2172, pruned_loss=0.04112, over 4973.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03182, over 972633.92 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:32:02,066 INFO [train.py:715] (5/8) Epoch 12, batch 31000, loss[loss=0.1512, simple_loss=0.2275, pruned_loss=0.03743, over 4941.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03204, over 972755.65 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:32:41,213 INFO [train.py:715] (5/8) Epoch 12, batch 31050, loss[loss=0.1191, simple_loss=0.2015, pruned_loss=0.01833, over 4888.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03142, over 972850.09 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:33:19,691 INFO [train.py:715] (5/8) Epoch 12, batch 31100, loss[loss=0.1308, simple_loss=0.2131, pruned_loss=0.02424, over 4872.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.0311, over 972548.04 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:33:57,506 INFO [train.py:715] (5/8) Epoch 12, batch 31150, loss[loss=0.1484, simple_loss=0.2087, pruned_loss=0.04408, over 4945.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03156, over 972420.23 frames.], batch size: 35, lr: 1.78e-04
2022-05-07 14:34:36,503 INFO [train.py:715] (5/8) Epoch 12, batch 31200, loss[loss=0.1321, simple_loss=0.2096, pruned_loss=0.02728, over 4810.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2114, pruned_loss=0.03156, over 971332.94 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:35:15,345 INFO [train.py:715] (5/8) Epoch 12, batch 31250, loss[loss=0.1475, simple_loss=0.2137, pruned_loss=0.04065, over 4847.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2118, pruned_loss=0.03178, over 971908.68 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:35:54,049 INFO [train.py:715] (5/8) Epoch 12, batch 31300, loss[loss=0.1346, simple_loss=0.2205, pruned_loss=0.02439, over 4937.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03168, over 972391.65 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:36:32,570 INFO [train.py:715] (5/8) Epoch 12, batch 31350, loss[loss=0.1257, simple_loss=0.1963, pruned_loss=0.02749, over 4923.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2113, pruned_loss=0.03181, over 973144.69 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:37:11,735 INFO [train.py:715] (5/8) Epoch 12, batch 31400, loss[loss=0.1212, simple_loss=0.2015, pruned_loss=0.02046, over 4761.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2114, pruned_loss=0.03148, over 973010.57 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:37:50,139 INFO [train.py:715] (5/8) Epoch 12, batch 31450, loss[loss=0.1889, simple_loss=0.2526, pruned_loss=0.0626, over 4869.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03209, over 973536.46 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:38:28,380 INFO [train.py:715] (5/8) Epoch 12, batch 31500, loss[loss=0.184, simple_loss=0.2518, pruned_loss=0.05813, over 4944.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03197, over 973230.92 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:39:06,657 INFO [train.py:715] (5/8) Epoch 12, batch 31550, loss[loss=0.1173, simple_loss=0.1864, pruned_loss=0.02416, over 4655.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03197, over 972803.66 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:39:45,223 INFO [train.py:715] (5/8) Epoch 12, batch 31600, loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02841, over 4910.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03207, over 972362.51 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:40:22,890 INFO [train.py:715] (5/8) Epoch 12, batch 31650, loss[loss=0.1332, simple_loss=0.2065, pruned_loss=0.02995, over 4846.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03199, over 972761.52 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:41:00,519 INFO [train.py:715] (5/8) Epoch 12, batch 31700, loss[loss=0.1386, simple_loss=0.2219, pruned_loss=0.02763, over 4890.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.0317, over 972330.87 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:41:38,634 INFO [train.py:715] (5/8) Epoch 12, batch 31750, loss[loss=0.1343, simple_loss=0.1979, pruned_loss=0.03534, over 4850.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03178, over 972880.99 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:42:16,747 INFO [train.py:715] (5/8) Epoch 12, batch 31800, loss[loss=0.1183, simple_loss=0.1871, pruned_loss=0.02474, over 4923.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.0309, over 972803.64 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:42:54,699 INFO [train.py:715] (5/8) Epoch 12, batch 31850, loss[loss=0.1329, simple_loss=0.2135, pruned_loss=0.02618, over 4811.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03142, over 971796.90 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 14:43:32,405 INFO [train.py:715] (5/8) Epoch 12, batch 31900, loss[loss=0.1177, simple_loss=0.187, pruned_loss=0.02418, over 4929.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.0315, over 971556.19 frames.], batch size: 29, lr: 1.78e-04
2022-05-07 14:44:10,698 INFO [train.py:715] (5/8) Epoch 12, batch 31950, loss[loss=0.1334, simple_loss=0.2118, pruned_loss=0.02755, over 4844.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03143, over 970783.42 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:44:48,297 INFO [train.py:715] (5/8) Epoch 12, batch 32000, loss[loss=0.1166, simple_loss=0.1942, pruned_loss=0.01954, over 4778.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03133, over 971335.62 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:45:26,162 INFO [train.py:715] (5/8) Epoch 12, batch 32050, loss[loss=0.136, simple_loss=0.2058, pruned_loss=0.03306, over 4989.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2097, pruned_loss=0.03185, over 971726.49 frames.], batch size: 31, lr: 1.78e-04
2022-05-07 14:46:04,020 INFO [train.py:715] (5/8) Epoch 12, batch 32100, loss[loss=0.1416, simple_loss=0.2043, pruned_loss=0.03942, over 4804.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03165, over 971678.26 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 14:46:42,428 INFO [train.py:715] (5/8) Epoch 12, batch 32150, loss[loss=0.1404, simple_loss=0.2149, pruned_loss=0.03295, over 4972.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03163, over 972513.70 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:47:20,024 INFO [train.py:715] (5/8) Epoch 12, batch 32200, loss[loss=0.1524, simple_loss=0.2305, pruned_loss=0.0372, over 4931.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03196, over 973398.92 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:47:58,174 INFO [train.py:715] (5/8) Epoch 12, batch 32250, loss[loss=0.1294, simple_loss=0.1978, pruned_loss=0.03055, over 4867.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03172, over 972913.45 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:48:36,824 INFO [train.py:715] (5/8) Epoch 12, batch 32300, loss[loss=0.1316, simple_loss=0.2106, pruned_loss=0.02627, over 4845.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03189, over 972575.63 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 14:49:14,386 INFO [train.py:715] (5/8) Epoch 12, batch 32350, loss[loss=0.1534, simple_loss=0.2319, pruned_loss=0.03744, over 4924.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03197, over 972198.66 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:49:52,728 INFO [train.py:715] (5/8) Epoch 12, batch 32400, loss[loss=0.1375, simple_loss=0.2195, pruned_loss=0.02769, over 4792.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03202, over 972685.97 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:50:30,827 INFO [train.py:715] (5/8) Epoch 12, batch 32450, loss[loss=0.1353, simple_loss=0.2062, pruned_loss=0.03222, over 4913.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03202, over 972306.62 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:51:09,334 INFO [train.py:715] (5/8) Epoch 12, batch 32500, loss[loss=0.1378, simple_loss=0.2064, pruned_loss=0.03462, over 4913.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03213, over 972468.48 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:51:46,830 INFO [train.py:715] (5/8) Epoch 12, batch 32550, loss[loss=0.1604, simple_loss=0.2271, pruned_loss=0.04688, over 4850.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03228, over 972602.96 frames.], batch size: 34, lr: 1.78e-04
2022-05-07 14:52:25,070 INFO [train.py:715] (5/8) Epoch 12, batch 32600, loss[loss=0.1472, simple_loss=0.2202, pruned_loss=0.03714, over 4776.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03191, over 972460.06 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:53:03,208 INFO [train.py:715] (5/8) Epoch 12, batch 32650, loss[loss=0.1559, simple_loss=0.2203, pruned_loss=0.04574, over 4698.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.0319, over 971918.07 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:53:40,738 INFO [train.py:715] (5/8) Epoch 12, batch 32700, loss[loss=0.1355, simple_loss=0.2215, pruned_loss=0.02479, over 4873.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03159, over 972636.41 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:54:18,462 INFO [train.py:715] (5/8) Epoch 12, batch 32750, loss[loss=0.1618, simple_loss=0.2386, pruned_loss=0.04255, over 4892.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03132, over 972695.54 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:54:56,867 INFO [train.py:715] (5/8) Epoch 12, batch 32800, loss[loss=0.1387, simple_loss=0.2186, pruned_loss=0.02944, over 4879.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03146, over 973297.98 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:55:35,235 INFO [train.py:715] (5/8) Epoch 12, batch 32850, loss[loss=0.1553, simple_loss=0.2311, pruned_loss=0.03982, over 4905.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03134, over 973260.18 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:56:12,924 INFO [train.py:715] (5/8) Epoch 12, batch 32900, loss[loss=0.1369, simple_loss=0.2147, pruned_loss=0.02954, over 4690.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 973063.23 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:56:51,022 INFO [train.py:715] (5/8) Epoch 12, batch 32950, loss[loss=0.1139, simple_loss=0.189, pruned_loss=0.01938, over 4813.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03163, over 972955.23 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 14:57:29,168 INFO [train.py:715] (5/8) Epoch 12, batch 33000, loss[loss=0.1353, simple_loss=0.2175, pruned_loss=0.02658, over 4755.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03197, over 972270.09 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:57:29,168 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 14:57:38,690 INFO [train.py:742] (5/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1896, pruned_loss=0.01085, over 914524.00 frames.
2022-05-07 14:58:18,192 INFO [train.py:715] (5/8) Epoch 12, batch 33050, loss[loss=0.1082, simple_loss=0.1863, pruned_loss=0.01502, over 4831.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03217, over 972493.77 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:58:56,559 INFO [train.py:715] (5/8) Epoch 12, batch 33100, loss[loss=0.1582, simple_loss=0.2326, pruned_loss=0.04188, over 4711.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03156, over 972911.09 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:59:34,843 INFO [train.py:715] (5/8) Epoch 12, batch 33150, loss[loss=0.1194, simple_loss=0.1915, pruned_loss=0.0236, over 4964.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03177, over 972093.03 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 15:00:12,868 INFO [train.py:715] (5/8) Epoch 12, batch 33200, loss[loss=0.1347, simple_loss=0.2097, pruned_loss=0.02991, over 4800.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03137, over 972957.54 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 15:00:51,450 INFO [train.py:715] (5/8) Epoch 12, batch 33250, loss[loss=0.1411, simple_loss=0.2079, pruned_loss=0.03717, over 4752.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 972040.27 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 15:01:29,592 INFO [train.py:715] (5/8) Epoch 12, batch 33300, loss[loss=0.1382, simple_loss=0.2157, pruned_loss=0.03038, over 4846.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03165, over 972418.17 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 15:02:07,722 INFO [train.py:715] (5/8) Epoch 12, batch 33350, loss[loss=0.1299, simple_loss=0.2068, pruned_loss=0.02646, over 4946.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03215, over 971799.00 frames.], batch size: 29, lr: 1.78e-04
2022-05-07 15:02:46,383 INFO [train.py:715] (5/8) Epoch 12, batch 33400, loss[loss=0.1416, simple_loss=0.2174, pruned_loss=0.03293, over 4802.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03256, over 971769.00 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 15:03:25,037 INFO [train.py:715] (5/8) Epoch 12, batch 33450, loss[loss=0.106, simple_loss=0.1818, pruned_loss=0.0151, over 4888.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03256, over 972053.74 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 15:04:03,393 INFO [train.py:715] (5/8) Epoch 12, batch 33500, loss[loss=0.1282, simple_loss=0.2105, pruned_loss=0.02297, over 4813.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03248, over 971890.49 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 15:04:42,494 INFO [train.py:715] (5/8) Epoch 12, batch 33550, loss[loss=0.1274, simple_loss=0.1998, pruned_loss=0.02744, over 4824.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03206, over 971894.84 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 15:05:21,128 INFO [train.py:715] (5/8) Epoch 12, batch 33600, loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03216, over 4935.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03209, over 972415.25 frames.], batch size: 29, lr: 1.78e-04
2022-05-07 15:05:59,983 INFO [train.py:715] (5/8) Epoch 12, batch 33650, loss[loss=0.1302, simple_loss=0.2081, pruned_loss=0.02612, over 4750.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03249, over 972136.23 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 15:06:38,062 INFO [train.py:715] (5/8) Epoch 12, batch 33700, loss[loss=0.1218, simple_loss=0.1942, pruned_loss=0.02476, over 4962.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03229, over 972980.62 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 15:07:16,844 INFO [train.py:715] (5/8) Epoch 12, batch 33750, loss[loss=0.1239, simple_loss=0.1964, pruned_loss=0.0257, over 4985.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03141, over 973140.15 frames.], batch size: 28, lr: 1.78e-04
2022-05-07 15:07:55,113 INFO [train.py:715] (5/8) Epoch 12, batch 33800, loss[loss=0.1567, simple_loss=0.2251, pruned_loss=0.0441, over 4881.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03152, over 972136.27 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 15:08:32,476 INFO [train.py:715] (5/8) Epoch 12, batch 33850, loss[loss=0.1134, simple_loss=0.1932, pruned_loss=0.01682, over 4845.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03119, over 972543.11 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 15:09:10,656 INFO [train.py:715] (5/8) Epoch 12, batch 33900, loss[loss=0.1259, simple_loss=0.1838, pruned_loss=0.03404, over 4836.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03092, over 972226.88 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 15:09:47,910 INFO [train.py:715] (5/8) Epoch 12, batch 33950, loss[loss=0.1238, simple_loss=0.198, pruned_loss=0.02481, over 4758.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03089, over 971543.08 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:10:26,070 INFO [train.py:715] (5/8) Epoch 12, batch 34000, loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03517, over 4846.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03127, over 971182.55 frames.], batch size: 30, lr: 1.77e-04
2022-05-07 15:11:03,703 INFO [train.py:715] (5/8) Epoch 12, batch 34050, loss[loss=0.1161, simple_loss=0.189, pruned_loss=0.02158, over 4955.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03145, over 971415.26 frames.], batch size: 15, lr: 1.77e-04
2022-05-07 15:11:41,637 INFO [train.py:715] (5/8) Epoch 12, batch 34100, loss[loss=0.1462, simple_loss=0.2219, pruned_loss=0.03528, over 4772.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2119, pruned_loss=0.03189, over 971464.55 frames.], batch size: 14, lr: 1.77e-04
2022-05-07 15:12:19,670 INFO [train.py:715] (5/8) Epoch 12, batch 34150, loss[loss=0.1303, simple_loss=0.1948, pruned_loss=0.03289, over 4935.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2121, pruned_loss=0.03232, over 972276.88 frames.], batch size: 29, lr: 1.77e-04
2022-05-07 15:12:57,179 INFO [train.py:715] (5/8) Epoch 12, batch 34200, loss[loss=0.134, simple_loss=0.2091, pruned_loss=0.02942, over 4885.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03187, over 972351.18 frames.], batch size: 32, lr: 1.77e-04
2022-05-07 15:13:35,448 INFO [train.py:715] (5/8) Epoch 12, batch 34250, loss[loss=0.1242, simple_loss=0.2078, pruned_loss=0.02033, over 4750.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03194, over 971738.83 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:14:12,817 INFO [train.py:715] (5/8) Epoch 12, batch 34300, loss[loss=0.1462, simple_loss=0.2259, pruned_loss=0.03321, over 4866.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03165, over 971628.15 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:14:51,106 INFO [train.py:715] (5/8) Epoch 12, batch 34350, loss[loss=0.1092, simple_loss=0.1791, pruned_loss=0.01963, over 4688.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03138, over 971470.89 frames.], batch size: 15, lr: 1.77e-04
2022-05-07 15:15:28,882 INFO [train.py:715] (5/8) Epoch 12, batch 34400, loss[loss=0.1283, simple_loss=0.1978, pruned_loss=0.0294, over 4794.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03153, over 971400.25 frames.], batch size: 24, lr: 1.77e-04
2022-05-07 15:16:07,251 INFO [train.py:715] (5/8) Epoch 12, batch 34450, loss[loss=0.1268, simple_loss=0.2011, pruned_loss=0.02624, over 4754.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 971491.40 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:16:45,349 INFO [train.py:715] (5/8) Epoch 12, batch 34500, loss[loss=0.1512, simple_loss=0.2245, pruned_loss=0.03895, over 4871.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03167, over 972347.75 frames.], batch size: 22, lr: 1.77e-04
2022-05-07 15:17:23,596 INFO [train.py:715] (5/8) Epoch 12, batch 34550, loss[loss=0.1262, simple_loss=0.1954, pruned_loss=0.02848, over 4917.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03154, over 973178.39 frames.], batch size: 17, lr: 1.77e-04
2022-05-07 15:18:02,261 INFO [train.py:715] (5/8) Epoch 12, batch 34600, loss[loss=0.1384, simple_loss=0.2177, pruned_loss=0.02957, over 4761.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03136, over 972044.57 frames.], batch size: 19, lr: 1.77e-04
2022-05-07 15:18:41,657 INFO [train.py:715] (5/8) Epoch 12, batch 34650, loss[loss=0.1528, simple_loss=0.2208, pruned_loss=0.04237, over 4922.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03192, over 972593.31 frames.], batch size: 23, lr: 1.77e-04
2022-05-07 15:19:21,041 INFO [train.py:715] (5/8) Epoch 12, batch 34700, loss[loss=0.1303, simple_loss=0.1978, pruned_loss=0.03135, over 4920.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2095, pruned_loss=0.03185, over 971494.87 frames.], batch size: 18, lr: 1.77e-04
2022-05-07 15:19:58,681 INFO [train.py:715] (5/8) Epoch 12, batch 34750, loss[loss=0.1462, simple_loss=0.2202, pruned_loss=0.03606, over 4794.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2105, pruned_loss=0.03243, over 971543.87 frames.], batch size: 21, lr: 1.77e-04
2022-05-07 15:20:34,680 INFO [train.py:715] (5/8) Epoch 12, batch 34800, loss[loss=0.09669, simple_loss=0.1693, pruned_loss=0.01204, over 4824.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2097, pruned_loss=0.03203, over 971015.32 frames.], batch size: 12, lr: 1.77e-04
2022-05-07 15:21:23,124 INFO [train.py:715] (5/8) Epoch 13, batch 0, loss[loss=0.117, simple_loss=0.1813, pruned_loss=0.02634, over 4964.00 frames.], tot_loss[loss=0.117, simple_loss=0.1813, pruned_loss=0.02634, over 4964.00 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:22:01,154 INFO [train.py:715] (5/8) Epoch 13, batch 50, loss[loss=0.1234, simple_loss=0.2034, pruned_loss=0.0217, over 4762.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2083, pruned_loss=0.03172, over 219757.16 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:22:39,461 INFO [train.py:715] (5/8) Epoch 13, batch 100, loss[loss=0.1178, simple_loss=0.1983, pruned_loss=0.01865, over 4773.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2088, pruned_loss=0.03179, over 386911.11 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:23:17,857 INFO [train.py:715] (5/8) Epoch 13, batch 150, loss[loss=0.1713, simple_loss=0.2318, pruned_loss=0.05539, over 4840.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2081, pruned_loss=0.03158, over 517889.81 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:23:57,325 INFO [train.py:715] (5/8) Epoch 13, batch 200, loss[loss=0.1149, simple_loss=0.1813, pruned_loss=0.02422, over 4741.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2069, pruned_loss=0.03183, over 618749.19 frames.], batch size: 16, lr: 1.71e-04
2022-05-07 15:24:35,734 INFO [train.py:715] (5/8) Epoch 13, batch 250, loss[loss=0.1394, simple_loss=0.2074, pruned_loss=0.03573, over 4959.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2085, pruned_loss=0.03218, over 697673.47 frames.], batch size: 39, lr: 1.71e-04
2022-05-07 15:25:15,231 INFO [train.py:715] (5/8) Epoch 13, batch 300, loss[loss=0.1352, simple_loss=0.2171, pruned_loss=0.02664, over 4707.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2094, pruned_loss=0.03197, over 758910.37 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:25:53,992 INFO [train.py:715] (5/8) Epoch 13, batch 350, loss[loss=0.138, simple_loss=0.2071, pruned_loss=0.03447, over 4838.00 frames.], tot_loss[loss=0.136, simple_loss=0.2092, pruned_loss=0.03144, over 805607.83 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:26:33,532 INFO [train.py:715] (5/8) Epoch 13, batch 400, loss[loss=0.1356, simple_loss=0.2081, pruned_loss=0.03155, over 4871.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03131, over 842731.86 frames.], batch size: 22, lr: 1.71e-04
2022-05-07 15:27:13,029 INFO [train.py:715] (5/8) Epoch 13, batch 450, loss[loss=0.12, simple_loss=0.1978, pruned_loss=0.02109, over 4925.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03135, over 871506.74 frames.], batch size: 23, lr: 1.71e-04
2022-05-07 15:27:53,172 INFO [train.py:715] (5/8) Epoch 13, batch 500, loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04057, over 4938.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03147, over 893760.36 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:28:33,643 INFO [train.py:715] (5/8) Epoch 13, batch 550, loss[loss=0.1328, simple_loss=0.2051, pruned_loss=0.03026, over 4763.00 frames.], tot_loss[loss=0.1362, simple_loss=0.209, pruned_loss=0.03167, over 910249.48 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:29:12,912 INFO [train.py:715] (5/8) Epoch 13, batch 600, loss[loss=0.1308, simple_loss=0.195, pruned_loss=0.03323, over 4757.00 frames.], tot_loss[loss=0.137, simple_loss=0.2099, pruned_loss=0.03207, over 923759.13 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:29:53,386 INFO [train.py:715] (5/8) Epoch 13, batch 650, loss[loss=0.1275, simple_loss=0.2073, pruned_loss=0.02384, over 4969.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03214, over 934342.57 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:30:33,368 INFO [train.py:715] (5/8) Epoch 13, batch 700, loss[loss=0.1669, simple_loss=0.2158, pruned_loss=0.05904, over 4800.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03216, over 943450.89 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:31:13,983 INFO [train.py:715] (5/8) Epoch 13, batch 750, loss[loss=0.1204, simple_loss=0.1999, pruned_loss=0.02043, over 4920.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03148, over 948597.28 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:31:53,295 INFO [train.py:715] (5/8) Epoch 13, batch 800, loss[loss=0.1662, simple_loss=0.2268, pruned_loss=0.05283, over 4787.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03253, over 953361.81 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:32:32,563 INFO [train.py:715] (5/8) Epoch 13, batch 850, loss[loss=0.142, simple_loss=0.2136, pruned_loss=0.03522, over 4876.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2096, pruned_loss=0.03191, over 956948.44 frames.], batch size: 16, lr: 1.71e-04
2022-05-07 15:33:12,804 INFO [train.py:715] (5/8) Epoch 13, batch 900, loss[loss=0.1736, simple_loss=0.2564, pruned_loss=0.0454, over 4780.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.0317, over 960999.78 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:33:52,204 INFO [train.py:715] (5/8) Epoch 13, batch 950, loss[loss=0.1235, simple_loss=0.2006, pruned_loss=0.0232, over 4970.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03143, over 962885.25 frames.], batch size: 28, lr: 1.71e-04
2022-05-07 15:34:32,780 INFO [train.py:715] (5/8) Epoch 13, batch 1000, loss[loss=0.1669, simple_loss=0.2466, pruned_loss=0.0436, over 4943.00 frames.], tot_loss[loss=0.136, simple_loss=0.2091, pruned_loss=0.03142, over 965586.47 frames.], batch size: 21, lr: 1.71e-04
2022-05-07 15:35:12,237 INFO [train.py:715] (5/8) Epoch 13, batch 1050, loss[loss=0.1447, simple_loss=0.2083, pruned_loss=0.04051, over 4917.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03197, over 967184.43 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:35:52,553 INFO [train.py:715] (5/8) Epoch 13, batch 1100, loss[loss=0.1311, simple_loss=0.2112, pruned_loss=0.02549, over 4822.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03161, over 968727.52 frames.], batch size: 26, lr: 1.71e-04
2022-05-07 15:36:32,013 INFO [train.py:715] (5/8) Epoch 13, batch 1150, loss[loss=0.1186, simple_loss=0.1941, pruned_loss=0.02152, over 4820.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.0317, over 969650.30 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:37:11,796 INFO [train.py:715] (5/8) Epoch 13, batch 1200, loss[loss=0.1494, simple_loss=0.2174, pruned_loss=0.04069, over 4858.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03192, over 970784.93 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:37:52,136 INFO [train.py:715] (5/8) Epoch 13, batch 1250, loss[loss=0.1353, simple_loss=0.2082, pruned_loss=0.03123, over 4791.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03183, over 969796.18 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:38:31,094 INFO [train.py:715] (5/8) Epoch 13, batch 1300, loss[loss=0.1222, simple_loss=0.202, pruned_loss=0.02119, over 4801.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03219, over 970627.35 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:39:11,008 INFO [train.py:715] (5/8) Epoch 13, batch 1350, loss[loss=0.1228, simple_loss=0.2058, pruned_loss=0.01986, over 4953.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03254, over 970589.62 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:39:49,772 INFO [train.py:715] (5/8) Epoch 13, batch 1400, loss[loss=0.1165, simple_loss=0.1986, pruned_loss=0.01724, over 4890.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03185, over 970815.07 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:40:28,860 INFO [train.py:715] (5/8) Epoch 13, batch 1450, loss[loss=0.1196, simple_loss=0.195, pruned_loss=0.02212, over 4834.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03161, over 971689.70 frames.], batch size: 26, lr: 1.71e-04
2022-05-07 15:41:06,533 INFO [train.py:715] (5/8) Epoch 13, batch 1500, loss[loss=0.1384, simple_loss=0.2262, pruned_loss=0.02533, over 4929.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03216, over 972045.19 frames.], batch size: 29, lr: 1.71e-04
2022-05-07 15:41:44,152 INFO [train.py:715] (5/8) Epoch 13, batch 1550, loss[loss=0.1489, simple_loss=0.2249, pruned_loss=0.03647, over 4987.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03186, over 972263.05 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:42:22,722 INFO [train.py:715] (5/8) Epoch 13, batch 1600, loss[loss=0.1529, simple_loss=0.2102, pruned_loss=0.04786, over 4984.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03208, over 971596.79 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:43:00,640 INFO [train.py:715] (5/8) Epoch 13, batch 1650, loss[loss=0.1271, simple_loss=0.1948, pruned_loss=0.02968, over 4985.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03158, over 972072.52 frames.], batch size: 35, lr: 1.71e-04
2022-05-07 15:43:39,378 INFO [train.py:715] (5/8) Epoch 13, batch 1700, loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03457, over 4981.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03166, over 972271.48 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:44:17,661 INFO [train.py:715] (5/8) Epoch 13, batch 1750, loss[loss=0.1479, simple_loss=0.224, pruned_loss=0.03592, over 4982.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03117, over 972759.55 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:44:57,089 INFO [train.py:715] (5/8) Epoch 13, batch 1800, loss[loss=0.1631, simple_loss=0.2239, pruned_loss=0.05111, over 4942.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03138, over 971948.43 frames.], batch size: 39, lr: 1.71e-04
2022-05-07 15:45:35,169 INFO [train.py:715] (5/8) Epoch 13, batch 1850, loss[loss=0.1273, simple_loss=0.2045, pruned_loss=0.02498, over 4789.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03139, over 971856.05 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:46:13,430 INFO [train.py:715] (5/8) Epoch 13, batch 1900, loss[loss=0.1225, simple_loss=0.2065, pruned_loss=0.0193, over 4817.00 frames.], tot_loss[loss=0.1369, simple_loss=0.211, pruned_loss=0.03136, over 971592.42 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:46:52,088 INFO [train.py:715] (5/8) Epoch 13, batch 1950, loss[loss=0.1218, simple_loss=0.1929, pruned_loss=0.02536, over 4799.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2111, pruned_loss=0.0314, over 971867.74 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:47:30,463 INFO [train.py:715] (5/8) Epoch 13, batch 2000, loss[loss=0.1656, simple_loss=0.2305, pruned_loss=0.05036, over 4975.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2111, pruned_loss=0.03173, over 972469.76 frames.], batch size: 39, lr: 1.71e-04
2022-05-07 15:48:09,017 INFO [train.py:715] (5/8) Epoch 13, batch 2050, loss[loss=0.1593, simple_loss=0.2292, pruned_loss=0.04472, over 4805.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03139, over 972025.07 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:48:47,022 INFO [train.py:715] (5/8) Epoch 13, batch 2100, loss[loss=0.1045, simple_loss=0.1798, pruned_loss=0.01457, over 4867.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03143, over 972529.82 frames.], batch size: 34, lr: 1.71e-04
2022-05-07 15:49:26,187 INFO [train.py:715] (5/8) Epoch 13, batch 2150, loss[loss=0.1162, simple_loss=0.1888, pruned_loss=0.02175, over 4710.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03175, over 972130.18 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:50:04,031 INFO [train.py:715] (5/8) Epoch 13, batch 2200, loss[loss=0.1145, simple_loss=0.1857, pruned_loss=0.02162, over 4774.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2112, pruned_loss=0.03182, over 972182.86 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:50:42,241 INFO [train.py:715] (5/8) Epoch 13, batch 2250, loss[loss=0.1504, simple_loss=0.2293, pruned_loss=0.03572, over 4871.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03179, over 972108.54 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:51:20,491 INFO [train.py:715] (5/8) Epoch 13, batch 2300, loss[loss=0.1524, simple_loss=0.2256, pruned_loss=0.03954, over 4753.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03162, over 972030.88 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:51:59,644 INFO [train.py:715] (5/8) Epoch 13, batch 2350, loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03318, over 4878.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03186, over 972413.60 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:52:38,008 INFO [train.py:715] (5/8) Epoch 13, batch 2400, loss[loss=0.1345, simple_loss=0.2173, pruned_loss=0.02578, over 4826.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03106, over 972540.18 frames.], batch size: 30, lr: 1.71e-04
2022-05-07 15:53:16,744 INFO [train.py:715] (5/8) Epoch 13, batch 2450, loss[loss=0.1138, simple_loss=0.1786, pruned_loss=0.02443, over 4641.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03135, over 972328.12 frames.], batch size: 13, lr: 1.71e-04
2022-05-07 15:53:55,651 INFO [train.py:715] (5/8) Epoch 13, batch 2500, loss[loss=0.1167, simple_loss=0.2074, pruned_loss=0.01297, over 4816.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03144, over 972208.88 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:54:34,061 INFO [train.py:715] (5/8) Epoch 13, batch 2550, loss[loss=0.1282, simple_loss=0.1924, pruned_loss=0.03203, over 4763.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03156, over 972490.67 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:55:12,161 INFO [train.py:715] (5/8) Epoch 13, batch 2600, loss[loss=0.1349, simple_loss=0.2067, pruned_loss=0.03153, over 4860.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03131, over 972502.50 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:55:50,582 INFO [train.py:715] (5/8) Epoch 13, batch 2650, loss[loss=0.1521, simple_loss=0.2158, pruned_loss=0.04421, over 4952.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03118, over 973244.06 frames.], batch size: 35, lr: 1.71e-04
2022-05-07 15:56:28,665 INFO [train.py:715] (5/8) Epoch 13, batch 2700, loss[loss=0.1482, simple_loss=0.2273, pruned_loss=0.03454, over 4759.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03187, over 972910.53 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 15:57:06,440 INFO [train.py:715] (5/8) Epoch 13, batch 2750, loss[loss=0.1225, simple_loss=0.2013, pruned_loss=0.02185, over 4795.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03177, over 973736.74 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 15:57:43,968 INFO [train.py:715] (5/8) Epoch 13, batch 2800, loss[loss=0.1351, simple_loss=0.2105, pruned_loss=0.02981, over 4974.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.0323, over 973123.39 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 15:58:22,562 INFO [train.py:715] (5/8) Epoch 13, batch 2850, loss[loss=0.1115, simple_loss=0.1859, pruned_loss=0.01858, over 4816.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03184, over 973363.28 frames.], batch size: 27, lr: 1.70e-04
2022-05-07 15:59:00,070 INFO [train.py:715] (5/8) Epoch 13, batch 2900, loss[loss=0.1624, simple_loss=0.2386, pruned_loss=0.04306, over 4939.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03137, over 973504.18 frames.], batch size: 35, lr: 1.70e-04
2022-05-07 15:59:37,966 INFO [train.py:715] (5/8) Epoch 13, batch 2950, loss[loss=0.1491, simple_loss=0.2197, pruned_loss=0.03922, over 4930.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03152, over 973150.72 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:00:15,988 INFO [train.py:715] (5/8) Epoch 13, batch 3000, loss[loss=0.1474, simple_loss=0.2211, pruned_loss=0.03686, over 4849.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03199, over 972828.55 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:00:15,988 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 16:00:25,445 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1052, simple_loss=0.1893, pruned_loss=0.01058, over 914524.00 frames.
2022-05-07 16:01:03,672 INFO [train.py:715] (5/8) Epoch 13, batch 3050, loss[loss=0.1355, simple_loss=0.2132, pruned_loss=0.02896, over 4797.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03235, over 973124.97 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:01:42,202 INFO [train.py:715] (5/8) Epoch 13, batch 3100, loss[loss=0.1303, simple_loss=0.2177, pruned_loss=0.02146, over 4974.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.0319, over 973275.51 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:02:19,746 INFO [train.py:715] (5/8) Epoch 13, batch 3150, loss[loss=0.113, simple_loss=0.1837, pruned_loss=0.02117, over 4922.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03163, over 973268.86 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:02:57,075 INFO [train.py:715] (5/8) Epoch 13, batch 3200, loss[loss=0.1368, simple_loss=0.2327, pruned_loss=0.02051, over 4821.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03176, over 973307.82 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 16:03:35,543 INFO [train.py:715] (5/8) Epoch 13, batch 3250, loss[loss=0.1281, simple_loss=0.2009, pruned_loss=0.02761, over 4801.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03149, over 972495.14 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:04:13,564 INFO [train.py:715] (5/8) Epoch 13, batch 3300, loss[loss=0.1349, simple_loss=0.2044, pruned_loss=0.03269, over 4808.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03165, over 972372.69 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:04:51,386 INFO [train.py:715] (5/8) Epoch 13, batch 3350, loss[loss=0.123, simple_loss=0.195, pruned_loss=0.02547, over 4918.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03159, over 972861.99 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:05:29,076 INFO [train.py:715] (5/8) Epoch 13, batch 3400, loss[loss=0.116, simple_loss=0.1792, pruned_loss=0.02639, over 4835.00 frames.], tot_loss[loss=0.136, simple_loss=0.209, pruned_loss=0.03149, over 973214.68 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 16:06:07,371 INFO [train.py:715] (5/8) Epoch 13, batch 3450, loss[loss=0.1053, simple_loss=0.1734, pruned_loss=0.01861, over 4699.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03144, over 973660.96 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:06:47,671 INFO [train.py:715] (5/8) Epoch 13, batch 3500, loss[loss=0.1466, simple_loss=0.2129, pruned_loss=0.04016, over 4860.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03146, over 973469.28 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:07:25,031 INFO [train.py:715] (5/8) Epoch 13, batch 3550, loss[loss=0.1536, simple_loss=0.2307, pruned_loss=0.03829, over 4919.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 973253.79 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:08:03,489 INFO [train.py:715] (5/8) Epoch 13, batch 3600, loss[loss=0.1308, simple_loss=0.2117, pruned_loss=0.02492, over 4759.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03143, over 973713.44 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:08:41,278 INFO [train.py:715] (5/8) Epoch 13, batch 3650, loss[loss=0.1482, simple_loss=0.2283, pruned_loss=0.03408, over 4915.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03115, over 973637.87 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:09:18,851 INFO [train.py:715] (5/8) Epoch 13, batch 3700, loss[loss=0.1276, simple_loss=0.2019, pruned_loss=0.02665, over 4928.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03114, over 973288.64 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:09:56,568 INFO [train.py:715] (5/8) Epoch 13, batch 3750, loss[loss=0.1135, simple_loss=0.1868, pruned_loss=0.02012, over 4964.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03059, over 973298.69 frames.], batch size: 35, lr: 1.70e-04
2022-05-07 16:10:34,803 INFO [train.py:715] (5/8) Epoch 13, batch 3800, loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03219, over 4912.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03084, over 973138.20 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:11:11,947 INFO [train.py:715] (5/8) Epoch 13, batch 3850, loss[loss=0.1235, simple_loss=0.1999, pruned_loss=0.0235, over 4844.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03081, over 972975.37 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 16:11:49,243 INFO [train.py:715] (5/8) Epoch 13, batch 3900, loss[loss=0.125, simple_loss=0.1984, pruned_loss=0.02579, over 4776.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03072, over 972819.89 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:12:27,130 INFO [train.py:715] (5/8) Epoch 13, batch 3950, loss[loss=0.1357, simple_loss=0.2028, pruned_loss=0.03428, over 4862.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2099, pruned_loss=0.03053, over 973924.16 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:13:05,300 INFO [train.py:715] (5/8) Epoch 13, batch 4000, loss[loss=0.1571, simple_loss=0.2409, pruned_loss=0.03665, over 4897.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03036, over 973280.16 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:13:42,997 INFO [train.py:715] (5/8) Epoch 13, batch 4050, loss[loss=0.1439, simple_loss=0.2105, pruned_loss=0.03864, over 4971.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.0305, over 973522.11 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:14:20,643 INFO [train.py:715] (5/8) Epoch 13, batch 4100, loss[loss=0.1664, simple_loss=0.2275, pruned_loss=0.05263, over 4845.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03073, over 972724.49 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 16:14:59,185 INFO [train.py:715] (5/8) Epoch 13, batch 4150, loss[loss=0.1162, simple_loss=0.188, pruned_loss=0.02223, over 4989.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.0302, over 971916.62 frames.], batch size: 27, lr: 1.70e-04
2022-05-07 16:15:36,528 INFO [train.py:715] (5/8) Epoch 13, batch 4200, loss[loss=0.1007, simple_loss=0.1799, pruned_loss=0.01075, over 4809.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03035, over 972423.60 frames.], batch size: 12, lr: 1.70e-04
2022-05-07 16:16:14,502 INFO [train.py:715] (5/8) Epoch 13, batch 4250, loss[loss=0.1254, simple_loss=0.2049, pruned_loss=0.02298, over 4912.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03049, over 972951.91 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:16:52,598 INFO [train.py:715] (5/8) Epoch 13, batch 4300, loss[loss=0.1521, simple_loss=0.2254, pruned_loss=0.03946, over 4765.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03055, over 972963.85 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:17:30,605 INFO [train.py:715] (5/8) Epoch 13, batch 4350, loss[loss=0.1417, simple_loss=0.2127, pruned_loss=0.03533, over 4856.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 972688.09 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 16:18:08,277 INFO [train.py:715] (5/8) Epoch 13, batch 4400, loss[loss=0.1133, simple_loss=0.1912, pruned_loss=0.01774, over 4944.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02957, over 973561.12 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:18:46,445 INFO [train.py:715] (5/8) Epoch 13, batch 4450, loss[loss=0.1271, simple_loss=0.2128, pruned_loss=0.0207, over 4815.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.02998, over 972593.76 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:19:25,667 INFO [train.py:715] (5/8) Epoch 13, batch 4500, loss[loss=0.1118, simple_loss=0.1856, pruned_loss=0.01896, over 4818.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03045, over 972718.28 frames.], batch size: 27, lr: 1.70e-04
2022-05-07 16:20:03,831 INFO [train.py:715] (5/8) Epoch 13, batch 4550, loss[loss=0.1794, simple_loss=0.2407, pruned_loss=0.05906, over 4964.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03065, over 971815.07 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:20:40,815 INFO [train.py:715] (5/8) Epoch 13, batch 4600, loss[loss=0.15, simple_loss=0.2075, pruned_loss=0.04619, over 4759.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03082, over 972364.35 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:21:19,532 INFO [train.py:715] (5/8) Epoch 13, batch 4650, loss[loss=0.1318, simple_loss=0.2116, pruned_loss=0.02605, over 4766.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03112, over 972763.42 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:21:57,440 INFO [train.py:715] (5/8) Epoch 13, batch 4700, loss[loss=0.1698, simple_loss=0.2407, pruned_loss=0.04947, over 4944.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03074, over 972345.17 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:22:35,612 INFO [train.py:715] (5/8) Epoch 13, batch 4750, loss[loss=0.1315, simple_loss=0.2074, pruned_loss=0.02775, over 4935.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03095, over 971701.94 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:23:13,890 INFO [train.py:715] (5/8) Epoch 13, batch 4800, loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04305, over 4873.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 972277.49 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:23:53,166 INFO [train.py:715] (5/8) Epoch 13, batch 4850, loss[loss=0.1969, simple_loss=0.255, pruned_loss=0.06942, over 4981.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03116, over 972302.38 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:24:31,290 INFO [train.py:715] (5/8) Epoch 13, batch 4900, loss[loss=0.1532, simple_loss=0.2277, pruned_loss=0.0393, over 4764.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03158, over 972676.73 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:25:10,148 INFO [train.py:715] (5/8) Epoch 13, batch 4950, loss[loss=0.1303, simple_loss=0.1967, pruned_loss=0.03202, over 4934.00 frames.], tot_loss[loss=0.136, simple_loss=0.2091, pruned_loss=0.03146, over 972089.96 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:25:49,563 INFO [train.py:715] (5/8) Epoch 13, batch 5000, loss[loss=0.139, simple_loss=0.2055, pruned_loss=0.03626, over 4975.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2081, pruned_loss=0.03107, over 973178.02 frames.], batch size: 28, lr: 1.70e-04
2022-05-07 16:26:28,899 INFO [train.py:715] (5/8) Epoch 13, batch 5050, loss[loss=0.1406, simple_loss=0.2034, pruned_loss=0.0389, over 4966.00 frames.], tot_loss[loss=0.1362, simple_loss=0.209, pruned_loss=0.03168, over 973570.07 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:27:07,532 INFO [train.py:715] (5/8) Epoch 13, batch 5100, loss[loss=0.1167, simple_loss=0.1935, pruned_loss=0.01997, over 4793.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2093, pruned_loss=0.03162, over 973254.54 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:27:46,966 INFO [train.py:715] (5/8) Epoch 13, batch 5150, loss[loss=0.1367, simple_loss=0.2028, pruned_loss=0.03527, over 4785.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03169, over 974302.69 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:28:26,705 INFO [train.py:715] (5/8) Epoch 13, batch 5200, loss[loss=0.1521, simple_loss=0.2281, pruned_loss=0.03803, over 4958.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03064, over 974277.63 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:29:06,550 INFO [train.py:715] (5/8) Epoch 13, batch 5250, loss[loss=0.1649, simple_loss=0.2358, pruned_loss=0.04706, over 4938.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03096, over 974185.01 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:29:45,231 INFO [train.py:715] (5/8) Epoch 13, batch 5300, loss[loss=0.1191, simple_loss=0.1891, pruned_loss=0.02459, over 4927.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2084, pruned_loss=0.03118, over 973289.54 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:30:25,372 INFO [train.py:715] (5/8) Epoch 13, batch 5350, loss[loss=0.1391, simple_loss=0.205, pruned_loss=0.03662, over 4747.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03063, over 972898.05 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:31:05,473 INFO [train.py:715] (5/8) Epoch 13, batch 5400, loss[loss=0.1228, simple_loss=0.1992, pruned_loss=0.02317, over 4789.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03077, over 973004.03 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 16:31:45,404 INFO [train.py:715] (5/8) Epoch 13, batch 5450, loss[loss=0.1278, simple_loss=0.2046, pruned_loss=0.02555, over 4886.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03135, over 972759.75 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:32:24,988 INFO [train.py:715] (5/8) Epoch 13, batch 5500, loss[loss=0.118, simple_loss=0.2033, pruned_loss=0.01635, over 4844.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03125, over 972752.64 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:33:04,813 INFO [train.py:715] (5/8) Epoch 13, batch 5550, loss[loss=0.1525, simple_loss=0.2327, pruned_loss=0.03617, over 4757.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03113, over 972232.32 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:33:44,068 INFO [train.py:715] (5/8) Epoch 13, batch 5600, loss[loss=0.1345, simple_loss=0.1972, pruned_loss=0.03586, over 4986.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03128, over 971589.56 frames.], batch size: 33, lr: 1.70e-04
2022-05-07 16:34:23,512 INFO [train.py:715] (5/8) Epoch 13, batch 5650, loss[loss=0.1025, simple_loss=0.1775, pruned_loss=0.01377, over 4883.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03111, over 971844.82 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:35:03,786 INFO [train.py:715] (5/8) Epoch 13, batch 5700, loss[loss=0.136, simple_loss=0.2038, pruned_loss=0.03409, over 4948.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03118, over 972614.99 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:35:43,896 INFO [train.py:715] (5/8) Epoch 13, batch 5750, loss[loss=0.1254, simple_loss=0.2054, pruned_loss=0.02274, over 4948.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03111, over 973734.94 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:36:22,747 INFO [train.py:715] (5/8) Epoch 13, batch 5800, loss[loss=0.1491, simple_loss=0.2256, pruned_loss=0.03631, over 4789.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03078, over 972835.84 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:37:02,234 INFO [train.py:715] (5/8) Epoch 13, batch 5850, loss[loss=0.1408, simple_loss=0.2166, pruned_loss=0.03246, over 4781.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03088, over 971962.99 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:37:42,376 INFO [train.py:715] (5/8) Epoch 13, batch 5900, loss[loss=0.123, simple_loss=0.2006, pruned_loss=0.02271, over 4916.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03065, over 971813.97 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:38:21,735 INFO [train.py:715] (5/8) Epoch 13, batch 5950, loss[loss=0.1546, simple_loss=0.2279, pruned_loss=0.0407, over 4848.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03061, over 971347.54 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:39:01,214 INFO [train.py:715] (5/8) Epoch 13, batch 6000, loss[loss=0.1289, simple_loss=0.2056, pruned_loss=0.02612, over 4842.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03084, over 971563.31 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 16:39:01,215 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 16:39:10,778 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1893, pruned_loss=0.01078, over 914524.00 frames.
2022-05-07 16:39:50,260 INFO [train.py:715] (5/8) Epoch 13, batch 6050, loss[loss=0.1098, simple_loss=0.1882, pruned_loss=0.01573, over 4853.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03141, over 972077.40 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:40:29,776 INFO [train.py:715] (5/8) Epoch 13, batch 6100, loss[loss=0.1364, simple_loss=0.2144, pruned_loss=0.02918, over 4951.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03123, over 972141.65 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:41:09,342 INFO [train.py:715] (5/8) Epoch 13, batch 6150, loss[loss=0.127, simple_loss=0.1967, pruned_loss=0.02869, over 4831.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03139, over 972804.79 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 16:41:47,238 INFO [train.py:715] (5/8) Epoch 13, batch 6200, loss[loss=0.1224, simple_loss=0.1988, pruned_loss=0.02296, over 4765.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.0319, over 972547.29 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:42:26,290 INFO [train.py:715] (5/8) Epoch 13, batch 6250, loss[loss=0.1252, simple_loss=0.1894, pruned_loss=0.03053, over 4794.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03163, over 971811.99 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:43:05,823 INFO [train.py:715] (5/8) Epoch 13, batch 6300, loss[loss=0.1247, simple_loss=0.1931, pruned_loss=0.02814, over 4914.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03154, over 971866.00 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:43:44,412 INFO [train.py:715] (5/8) Epoch 13, batch 6350, loss[loss=0.1212, simple_loss=0.1879, pruned_loss=0.02727, over 4867.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03161, over 972028.43 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:44:24,227 INFO [train.py:715] (5/8) Epoch 13, batch 6400, loss[loss=0.1218, simple_loss=0.1916, pruned_loss=0.02599, over 4874.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03175, over 971775.34 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:45:04,048 INFO [train.py:715] (5/8) Epoch 13, batch 6450, loss[loss=0.1047, simple_loss=0.1781, pruned_loss=0.01565, over 4757.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03146, over 971525.92 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:45:44,140 INFO [train.py:715] (5/8) Epoch 13, batch 6500, loss[loss=0.1462, simple_loss=0.2269, pruned_loss=0.0328, over 4847.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03159, over 971571.64 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 16:46:23,312 INFO [train.py:715] (5/8) Epoch 13, batch 6550, loss[loss=0.1082, simple_loss=0.1829, pruned_loss=0.01674, over 4834.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03141, over 971667.93 frames.], batch size: 27, lr: 1.70e-04
2022-05-07 16:47:02,647 INFO [train.py:715] (5/8) Epoch 13, batch 6600, loss[loss=0.1307, simple_loss=0.2062, pruned_loss=0.02755, over 4774.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 972122.41 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:47:42,041 INFO [train.py:715] (5/8) Epoch 13, batch 6650, loss[loss=0.1201, simple_loss=0.1954, pruned_loss=0.02243, over 4896.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03148, over 971555.34 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:48:20,275 INFO [train.py:715] (5/8) Epoch 13, batch 6700, loss[loss=0.1201, simple_loss=0.191, pruned_loss=0.0246, over 4963.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03209, over 971059.60 frames.], batch size: 35, lr: 1.70e-04
2022-05-07 16:48:58,715 INFO [train.py:715] (5/8) Epoch 13, batch 6750, loss[loss=0.1232, simple_loss=0.2024, pruned_loss=0.02196, over 4768.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03147, over 970973.38 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:49:37,982 INFO [train.py:715] (5/8) Epoch 13, batch 6800, loss[loss=0.1157, simple_loss=0.189, pruned_loss=0.02117, over 4931.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03137, over 971206.10 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:50:17,431 INFO [train.py:715] (5/8) Epoch 13, batch 6850, loss[loss=0.1115, simple_loss=0.1894, pruned_loss=0.01682, over 4924.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2111, pruned_loss=0.03171, over 971806.75 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:50:55,364 INFO [train.py:715] (5/8) Epoch 13, batch 6900, loss[loss=0.129, simple_loss=0.2215, pruned_loss=0.01823, over 4888.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03165, over 972604.04 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:51:33,402 INFO [train.py:715] (5/8) Epoch 13, batch 6950, loss[loss=0.1317, simple_loss=0.2112, pruned_loss=0.02615, over 4814.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2115, pruned_loss=0.03171, over 972907.89 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:52:12,639 INFO [train.py:715] (5/8) Epoch 13, batch 7000, loss[loss=0.1306, simple_loss=0.2023, pruned_loss=0.02949, over 4780.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2114, pruned_loss=0.03174, over 972093.91 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:52:51,281 INFO [train.py:715] (5/8) Epoch 13, batch 7050, loss[loss=0.1134, simple_loss=0.1935, pruned_loss=0.01666, over 4939.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03136, over 972345.85 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:53:30,245 INFO [train.py:715] (5/8) Epoch 13, batch 7100, loss[loss=0.1353, simple_loss=0.2027, pruned_loss=0.03396, over 4858.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.0314, over 972176.31 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:54:09,705 INFO [train.py:715] (5/8) Epoch 13, batch 7150, loss[loss=0.1447, simple_loss=0.2242, pruned_loss=0.03257, over 4854.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2107, pruned_loss=0.03126, over 971655.59 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:54:49,406 INFO [train.py:715] (5/8) Epoch 13, batch 7200, loss[loss=0.1614, simple_loss=0.2273, pruned_loss=0.04771, over 4898.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03187, over 971421.29 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:55:27,554 INFO [train.py:715] (5/8) Epoch 13, batch 7250, loss[loss=0.1105, simple_loss=0.1897, pruned_loss=0.01565, over 4813.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03139, over 971759.26 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 16:56:05,824 INFO [train.py:715] (5/8) Epoch 13, batch 7300, loss[loss=0.1513, simple_loss=0.2263, pruned_loss=0.03819, over 4911.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03161, over 972619.19 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:56:45,076 INFO [train.py:715] (5/8) Epoch 13, batch 7350, loss[loss=0.1287, simple_loss=0.1961, pruned_loss=0.03068, over 4804.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.0317, over 972286.18 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 16:57:23,717 INFO [train.py:715] (5/8) Epoch 13, batch 7400, loss[loss=0.1283, simple_loss=0.194, pruned_loss=0.0313, over 4936.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.032, over 972848.96 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:58:01,540 INFO [train.py:715] (5/8) Epoch 13, batch 7450, loss[loss=0.1315, simple_loss=0.2037, pruned_loss=0.02969, over 4766.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03186, over 971944.70 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:58:40,994 INFO [train.py:715] (5/8) Epoch 13, batch 7500, loss[loss=0.1537, simple_loss=0.2234, pruned_loss=0.04198, over 4738.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03197, over 971954.56 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:59:20,235 INFO [train.py:715] (5/8) Epoch 13, batch 7550, loss[loss=0.1341, simple_loss=0.2124, pruned_loss=0.02787, over 4948.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03146, over 972464.13 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:59:57,837 INFO [train.py:715] (5/8) Epoch 13, batch 7600, loss[loss=0.1198, simple_loss=0.1949, pruned_loss=0.02237, over 4694.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03123, over 970963.86 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 17:00:36,714 INFO [train.py:715] (5/8) Epoch 13, batch 7650, loss[loss=0.1524, simple_loss=0.2209, pruned_loss=0.04196, over 4796.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03083, over 971860.79 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 17:01:15,684 INFO [train.py:715] (5/8) Epoch 13, batch 7700, loss[loss=0.1396, simple_loss=0.1987, pruned_loss=0.04019, over 4787.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03072, over 971741.44 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 17:01:54,650 INFO [train.py:715] (5/8) Epoch 13, batch 7750, loss[loss=0.1146, simple_loss=0.1942, pruned_loss=0.01748, over 4972.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03104, over 972460.23 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 17:02:32,576 INFO [train.py:715] (5/8) Epoch 13, batch 7800, loss[loss=0.1356, simple_loss=0.2178, pruned_loss=0.02665, over 4907.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03096, over 972170.14 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 17:03:11,061 INFO [train.py:715] (5/8) Epoch 13, batch 7850, loss[loss=0.1355, simple_loss=0.1967, pruned_loss=0.03712, over 4642.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03109, over 972147.77 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 17:03:50,704 INFO [train.py:715] (5/8) Epoch 13, batch 7900, loss[loss=0.1361, simple_loss=0.2039, pruned_loss=0.03415, over 4869.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.0314, over 972305.34 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 17:04:28,752 INFO [train.py:715] (5/8) Epoch 13, batch 7950, loss[loss=0.1436, simple_loss=0.229, pruned_loss=0.02904, over 4940.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03137, over 972082.30 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 17:05:07,214 INFO [train.py:715] (5/8) Epoch 13, batch 8000, loss[loss=0.1589, simple_loss=0.2221, pruned_loss=0.04782, over 4951.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03141, over 971760.84 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 17:05:45,982 INFO [train.py:715] (5/8) Epoch 13, batch 8050, loss[loss=0.1225, simple_loss=0.2013, pruned_loss=0.02181, over 4821.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03135, over 971517.31 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 17:06:24,532 INFO [train.py:715] (5/8) Epoch 13, batch 8100, loss[loss=0.1471, simple_loss=0.218, pruned_loss=0.03812, over 4852.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.0308, over 970468.08 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:07:02,516 INFO [train.py:715] (5/8) Epoch 13, batch 8150, loss[loss=0.1443, simple_loss=0.2126, pruned_loss=0.03806, over 4894.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03096, over 970847.72 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:07:40,993 INFO [train.py:715] (5/8) Epoch 13, batch 8200, loss[loss=0.1417, simple_loss=0.2121, pruned_loss=0.03568, over 4790.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03135, over 971192.42 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:08:20,202 INFO [train.py:715] (5/8) Epoch 13, batch 8250, loss[loss=0.1183, simple_loss=0.1873, pruned_loss=0.02465, over 4883.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03103, over 971620.66 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:08:58,109 INFO [train.py:715] (5/8) Epoch 13, batch 8300, loss[loss=0.1398, simple_loss=0.217, pruned_loss=0.0313, over 4779.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03148, over 970505.15 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:09:36,541 INFO [train.py:715] (5/8) Epoch 13, batch 8350, loss[loss=0.131, simple_loss=0.1978, pruned_loss=0.03207, over 4772.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.0313, over 970691.23 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:10:15,702 INFO [train.py:715] (5/8) Epoch 13, batch 8400, loss[loss=0.1195, simple_loss=0.1902, pruned_loss=0.02443, over 4855.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03173, over 971378.88 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:10:54,562 INFO [train.py:715] (5/8) Epoch 13, batch 8450, loss[loss=0.132, simple_loss=0.2124, pruned_loss=0.02583, over 4823.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03144, over 971703.04 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:11:32,554 INFO [train.py:715] (5/8) Epoch 13, batch 8500, loss[loss=0.1476, simple_loss=0.218, pruned_loss=0.0386, over 4899.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03121, over 972528.81 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:12:11,696 INFO [train.py:715] (5/8) Epoch 13, batch 8550, loss[loss=0.1382, simple_loss=0.2123, pruned_loss=0.03204, over 4932.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03165, over 972637.26 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:12:50,647 INFO [train.py:715] (5/8) Epoch 13, batch 8600, loss[loss=0.1322, simple_loss=0.2128, pruned_loss=0.02584, over 4907.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03112, over 972103.31 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:13:28,882 INFO [train.py:715] (5/8) Epoch 13, batch 8650, loss[loss=0.145, simple_loss=0.2135, pruned_loss=0.0383, over 4870.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.03099, over 972688.73 frames.], batch size: 32, lr: 1.69e-04
2022-05-07 17:14:07,225 INFO [train.py:715] (5/8) Epoch 13, batch 8700, loss[loss=0.1299, simple_loss=0.1907, pruned_loss=0.03451, over 4971.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.0313, over 973574.84 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:14:45,867 INFO [train.py:715] (5/8) Epoch 13, batch 8750, loss[loss=0.1383, simple_loss=0.2109, pruned_loss=0.03288, over 4889.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03103, over 973605.92 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:15:24,586 INFO [train.py:715] (5/8) Epoch 13, batch 8800, loss[loss=0.1204, simple_loss=0.1917, pruned_loss=0.02457, over 4975.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03135, over 973735.46 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:16:02,885 INFO [train.py:715] (5/8) Epoch 13, batch 8850, loss[loss=0.1491, simple_loss=0.2195, pruned_loss=0.03941, over 4886.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03091, over 973514.26 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:16:40,973 INFO [train.py:715] (5/8) Epoch 13, batch 8900, loss[loss=0.1557, simple_loss=0.2338, pruned_loss=0.03882, over 4914.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03077, over 972482.39 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:17:19,698 INFO [train.py:715] (5/8) Epoch 13, batch 8950, loss[loss=0.1345, simple_loss=0.2206, pruned_loss=0.02423, over 4774.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2104, pruned_loss=0.03123, over 972386.57 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:17:57,826 INFO [train.py:715] (5/8) Epoch 13, batch 9000, loss[loss=0.1324, simple_loss=0.1983, pruned_loss=0.03319, over 4791.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03087, over 972440.25 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 17:17:57,826 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 17:18:07,452 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 17:18:45,500 INFO [train.py:715] (5/8) Epoch 13, batch 9050, loss[loss=0.1421, simple_loss=0.224, pruned_loss=0.03011, over 4710.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03082, over 972455.84 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:19:23,909 INFO [train.py:715] (5/8) Epoch 13, batch 9100, loss[loss=0.1438, simple_loss=0.2179, pruned_loss=0.03487, over 4873.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03063, over 972861.86 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:20:03,098 INFO [train.py:715] (5/8) Epoch 13, batch 9150, loss[loss=0.155, simple_loss=0.2283, pruned_loss=0.04082, over 4936.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03069, over 972241.16 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:20:42,095 INFO [train.py:715] (5/8) Epoch 13, batch 9200, loss[loss=0.1392, simple_loss=0.2058, pruned_loss=0.03635, over 4869.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03076, over 972691.83 frames.], batch size: 32, lr: 1.69e-04
2022-05-07 17:21:20,011 INFO [train.py:715] (5/8) Epoch 13, batch 9250, loss[loss=0.1432, simple_loss=0.2192, pruned_loss=0.0336, over 4763.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03105, over 972394.52 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:21:58,913 INFO [train.py:715] (5/8) Epoch 13, batch 9300, loss[loss=0.1215, simple_loss=0.1921, pruned_loss=0.02543, over 4814.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03106, over 971750.80 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:22:37,766 INFO [train.py:715] (5/8) Epoch 13, batch 9350, loss[loss=0.1523, simple_loss=0.239, pruned_loss=0.03277, over 4943.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03131, over 971540.65 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:23:15,580 INFO [train.py:715] (5/8) Epoch 13, batch 9400, loss[loss=0.1147, simple_loss=0.1879, pruned_loss=0.02077, over 4769.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03093, over 972193.92 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:23:54,032 INFO [train.py:715] (5/8) Epoch 13, batch 9450, loss[loss=0.1576, simple_loss=0.2324, pruned_loss=0.04137, over 4988.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03093, over 972928.99 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:24:32,854 INFO [train.py:715] (5/8) Epoch 13, batch 9500, loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03408, over 4939.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03147, over 972939.31 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:25:11,108 INFO [train.py:715] (5/8) Epoch 13, batch 9550, loss[loss=0.1392, simple_loss=0.2236, pruned_loss=0.02742, over 4759.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03148, over 973082.44 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:25:49,079 INFO [train.py:715] (5/8) Epoch 13, batch 9600, loss[loss=0.1139, simple_loss=0.1949, pruned_loss=0.01643, over 4824.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.03111, over 972800.08 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:26:28,021 INFO [train.py:715] (5/8) Epoch 13, batch 9650, loss[loss=0.1302, simple_loss=0.1998, pruned_loss=0.03028, over 4929.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2083, pruned_loss=0.03125, over 972436.83 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:27:06,437 INFO [train.py:715] (5/8) Epoch 13, batch 9700, loss[loss=0.1329, simple_loss=0.2115, pruned_loss=0.02717, over 4847.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2085, pruned_loss=0.03147, over 972381.44 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:27:44,979 INFO [train.py:715] (5/8) Epoch 13, batch 9750, loss[loss=0.1275, simple_loss=0.205, pruned_loss=0.02504, over 4785.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03176, over 973084.74 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:28:23,842 INFO [train.py:715] (5/8) Epoch 13, batch 9800, loss[loss=0.1254, simple_loss=0.2036, pruned_loss=0.0236, over 4824.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2097, pruned_loss=0.03188, over 972846.92 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:29:03,033 INFO [train.py:715] (5/8) Epoch 13, batch 9850, loss[loss=0.1276, simple_loss=0.1953, pruned_loss=0.02998, over 4829.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03174, over 973437.78 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:29:41,581 INFO [train.py:715] (5/8) Epoch 13, batch 9900, loss[loss=0.132, simple_loss=0.214, pruned_loss=0.02498, over 4810.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03137, over 973696.43 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:30:19,822 INFO [train.py:715] (5/8) Epoch 13, batch 9950, loss[loss=0.1387, simple_loss=0.2184, pruned_loss=0.02948, over 4801.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03139, over 972765.42 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:30:58,615 INFO [train.py:715] (5/8) Epoch 13, batch 10000, loss[loss=0.1795, simple_loss=0.2344, pruned_loss=0.06228, over 4840.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03156, over 972611.39 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:31:37,785 INFO [train.py:715] (5/8) Epoch 13, batch 10050, loss[loss=0.1277, simple_loss=0.2051, pruned_loss=0.02517, over 4966.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03201, over 973199.08 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:32:16,721 INFO [train.py:715] (5/8) Epoch 13, batch 10100, loss[loss=0.154, simple_loss=0.2342, pruned_loss=0.03694, over 4771.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03229, over 973472.43 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:32:54,965 INFO [train.py:715] (5/8) Epoch 13, batch 10150, loss[loss=0.09831, simple_loss=0.1666, pruned_loss=0.015, over 4801.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03222, over 973012.97 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:33:33,998 INFO [train.py:715] (5/8) Epoch 13, batch 10200, loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03436, over 4934.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03182, over 973201.94 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:34:13,393 INFO [train.py:715] (5/8) Epoch 13, batch 10250, loss[loss=0.1095, simple_loss=0.1887, pruned_loss=0.01514, over 4947.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.032, over 972953.93 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:34:52,082 INFO [train.py:715] (5/8) Epoch 13, batch 10300, loss[loss=0.13, simple_loss=0.2065, pruned_loss=0.02677, over 4962.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03214, over 973539.76 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:35:31,127 INFO [train.py:715] (5/8) Epoch 13, batch 10350, loss[loss=0.1281, simple_loss=0.1978, pruned_loss=0.02915, over 4960.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.0321, over 974304.07 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:36:10,304 INFO [train.py:715] (5/8) Epoch 13, batch 10400, loss[loss=0.1214, simple_loss=0.2047, pruned_loss=0.01908, over 4937.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03226, over 974196.60 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:36:49,250 INFO [train.py:715] (5/8) Epoch 13, batch 10450, loss[loss=0.1273, simple_loss=0.2097, pruned_loss=0.0225, over 4914.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03182, over 974661.68 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:37:26,678 INFO [train.py:715] (5/8) Epoch 13, batch 10500, loss[loss=0.1645, simple_loss=0.2298, pruned_loss=0.04959, over 4871.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03152, over 973780.12 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:38:05,567 INFO [train.py:715] (5/8) Epoch 13, batch 10550, loss[loss=0.113, simple_loss=0.1883, pruned_loss=0.01884, over 4763.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03165, over 973691.30 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:38:44,487 INFO [train.py:715] (5/8) Epoch 13, batch 10600, loss[loss=0.1352, simple_loss=0.2132, pruned_loss=0.02867, over 4948.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03192, over 973512.30 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:39:22,592 INFO [train.py:715] (5/8) Epoch 13, batch 10650, loss[loss=0.1272, simple_loss=0.2014, pruned_loss=0.02655, over 4929.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03169, over 973852.23 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:40:01,765 INFO [train.py:715] (5/8) Epoch 13, batch 10700, loss[loss=0.1363, simple_loss=0.2049, pruned_loss=0.03384, over 4912.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03125, over 972703.08 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:40:41,061 INFO [train.py:715] (5/8) Epoch 13, batch 10750, loss[loss=0.1384, simple_loss=0.2068, pruned_loss=0.03495, over 4856.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03163, over 972484.74 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:41:19,858 INFO [train.py:715] (5/8) Epoch 13, batch 10800, loss[loss=0.1666, simple_loss=0.2248, pruned_loss=0.05415, over 4966.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 972495.91 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:41:57,880 INFO [train.py:715] (5/8) Epoch 13, batch 10850, loss[loss=0.1142, simple_loss=0.178, pruned_loss=0.02521, over 4937.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03123, over 972735.57 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:42:37,032 INFO [train.py:715] (5/8) Epoch 13, batch 10900, loss[loss=0.1447, simple_loss=0.2217, pruned_loss=0.03379, over 4797.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03146, over 971517.79 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:43:16,893 INFO [train.py:715] (5/8) Epoch 13, batch 10950, loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02855, over 4991.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2115, pruned_loss=0.03165, over 970939.44 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:43:56,321 INFO [train.py:715] (5/8) Epoch 13, batch 11000, loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02835, over 4958.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2108, pruned_loss=0.03109, over 971605.15 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:44:34,953 INFO [train.py:715] (5/8) Epoch 13, batch 11050, loss[loss=0.1205, simple_loss=0.1939, pruned_loss=0.02354, over 4889.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03097, over 971439.38 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:45:14,251 INFO [train.py:715] (5/8) Epoch 13, batch 11100, loss[loss=0.138, simple_loss=0.208, pruned_loss=0.03398, over 4862.00 frames.], tot_loss[loss=0.136, simple_loss=0.2104, pruned_loss=0.03079, over 971724.95 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:45:53,235 INFO [train.py:715] (5/8) Epoch 13, batch 11150, loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03751, over 4961.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2103, pruned_loss=0.03053, over 971803.04 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:46:30,990 INFO [train.py:715] (5/8) Epoch 13, batch 11200, loss[loss=0.139, simple_loss=0.2163, pruned_loss=0.0308, over 4918.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2108, pruned_loss=0.03095, over 971313.54 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:47:09,193 INFO [train.py:715] (5/8) Epoch 13, batch 11250, loss[loss=0.1182, simple_loss=0.1894, pruned_loss=0.02349, over 4814.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03075, over 971903.98 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:47:48,138 INFO [train.py:715] (5/8) Epoch 13, batch 11300, loss[loss=0.1365, simple_loss=0.2261, pruned_loss=0.02351, over 4946.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03076, over 972274.74 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:48:27,086 INFO [train.py:715] (5/8) Epoch 13, batch 11350, loss[loss=0.1422, simple_loss=0.2186, pruned_loss=0.03289, over 4816.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03112, over 972343.69 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:49:05,291 INFO [train.py:715] (5/8) Epoch 13, batch 11400, loss[loss=0.1257, simple_loss=0.2008, pruned_loss=0.02528, over 4800.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.031, over 971309.93 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:49:44,156 INFO [train.py:715] (5/8) Epoch 13, batch 11450, loss[loss=0.1139, simple_loss=0.1856, pruned_loss=0.02108, over 4807.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.031, over 971569.13 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:50:25,717 INFO [train.py:715] (5/8) Epoch 13, batch 11500, loss[loss=0.1193, simple_loss=0.1932, pruned_loss=0.02269, over 4919.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03138, over 971767.60 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:51:03,651 INFO [train.py:715] (5/8) Epoch 13, batch 11550, loss[loss=0.1743, simple_loss=0.2328, pruned_loss=0.05795, over 4704.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03155, over 971789.56 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:51:42,315 INFO [train.py:715] (5/8) Epoch 13, batch 11600, loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02989, over 4786.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03166, over 971624.16 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:52:21,602 INFO [train.py:715] (5/8) Epoch 13, batch 11650, loss[loss=0.1353, simple_loss=0.2017, pruned_loss=0.03445, over 4796.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03161, over 971931.58 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:53:00,308 INFO [train.py:715] (5/8) Epoch 13, batch 11700, loss[loss=0.1233, simple_loss=0.192, pruned_loss=0.02733, over 4708.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 971869.05 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:53:38,276 INFO [train.py:715] (5/8) Epoch 13, batch 11750, loss[loss=0.1246, simple_loss=0.205, pruned_loss=0.02212, over 4961.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03134, over 972282.57 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:54:16,754 INFO [train.py:715] (5/8) Epoch 13, batch 11800, loss[loss=0.141, simple_loss=0.2164, pruned_loss=0.03279, over 4820.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03151, over 971308.92 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:54:55,479 INFO [train.py:715] (5/8) Epoch 13, batch 11850, loss[loss=0.1522, simple_loss=0.2292, pruned_loss=0.03758, over 4958.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03183, over 972090.90 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:55:32,888 INFO [train.py:715] (5/8) Epoch 13, batch 11900, loss[loss=0.1685, simple_loss=0.2439, pruned_loss=0.04656, over 4811.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03218, over 972068.45 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:56:11,544 INFO [train.py:715] (5/8) Epoch 13, batch 11950, loss[loss=0.1642, simple_loss=0.2413, pruned_loss=0.04358, over 4840.00 frames.], tot_loss[loss=0.1382, simple_loss=0.212, pruned_loss=0.03222, over 971624.30 frames.], batch size: 34, lr: 1.69e-04
2022-05-07 17:56:50,610 INFO [train.py:715] (5/8) Epoch 13, batch 12000, loss[loss=0.132, simple_loss=0.1955, pruned_loss=0.03426, over 4958.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03174, over 971349.91 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:56:50,610 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 17:57:00,357 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 17:57:40,026 INFO [train.py:715] (5/8) Epoch 13, batch 12050, loss[loss=0.1115, simple_loss=0.1835, pruned_loss=0.01969, over 4902.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03157, over 971725.97 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:58:18,319 INFO [train.py:715] (5/8) Epoch 13, batch 12100, loss[loss=0.1333, simple_loss=0.199, pruned_loss=0.03383, over 4857.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.0313, over 971336.35 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:58:56,073 INFO [train.py:715] (5/8) Epoch 13, batch 12150, loss[loss=0.1191, simple_loss=0.1946, pruned_loss=0.02175, over 4781.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 970660.19 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:59:34,972 INFO [train.py:715] (5/8) Epoch 13, batch 12200, loss[loss=0.1449, simple_loss=0.2202, pruned_loss=0.03478, over 4937.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03185, over 971247.63 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 18:00:13,889 INFO [train.py:715] (5/8) Epoch 13, batch 12250, loss[loss=0.1513, simple_loss=0.2238, pruned_loss=0.03942, over 4868.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03211, over 971361.79 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 18:00:52,458 INFO [train.py:715] (5/8) Epoch 13, batch 12300, loss[loss=0.1397, simple_loss=0.2254, pruned_loss=0.027, over 4946.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.0319, over 971089.81 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 18:01:30,136 INFO [train.py:715] (5/8) Epoch 13, batch 12350, loss[loss=0.1365, simple_loss=0.2133, pruned_loss=0.0298, over 4947.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03191, over 972015.03 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 18:02:09,069 INFO [train.py:715] (5/8) Epoch 13, batch 12400, loss[loss=0.1582, simple_loss=0.2399, pruned_loss=0.03819, over 4919.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.0318, over 972480.15 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 18:02:47,460 INFO [train.py:715] (5/8) Epoch 13, batch 12450, loss[loss=0.1128, simple_loss=0.1917, pruned_loss=0.01692, over 4965.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03119, over 972987.62 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 18:03:24,474 INFO [train.py:715] (5/8) Epoch 13, batch 12500, loss[loss=0.1308, simple_loss=0.2076, pruned_loss=0.02703, over 4823.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03122, over 972451.98 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 18:04:03,261 INFO [train.py:715] (5/8) Epoch 13, batch 12550, loss[loss=0.1171, simple_loss=0.1932, pruned_loss=0.02051, over 4976.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.0311, over 973030.18 frames.], batch size: 28, lr: 1.69e-04
2022-05-07 18:04:41,881 INFO [train.py:715] (5/8) Epoch 13, batch 12600, loss[loss=0.1104, simple_loss=0.1812, pruned_loss=0.01977, over 4822.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03134, over 973353.74 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 18:05:20,412 INFO [train.py:715] (5/8) Epoch 13, batch 12650, loss[loss=0.1738, simple_loss=0.2336, pruned_loss=0.05701, over 4704.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03135, over 973025.86 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 18:05:58,208 INFO [train.py:715] (5/8) Epoch 13, batch 12700, loss[loss=0.1353, simple_loss=0.2106, pruned_loss=0.03002, over 4878.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03178, over 972986.37 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 18:06:37,493 INFO [train.py:715] (5/8) Epoch 13, batch 12750, loss[loss=0.1143, simple_loss=0.1971, pruned_loss=0.01574, over 4919.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03137, over 972772.19 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 18:07:16,116 INFO [train.py:715] (5/8) Epoch 13, batch 12800, loss[loss=0.1326, simple_loss=0.1958, pruned_loss=0.03469, over 4841.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03138, over 972779.01 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 18:07:53,802 INFO [train.py:715] (5/8) Epoch 13, batch 12850, loss[loss=0.1261, simple_loss=0.1993, pruned_loss=0.0264, over 4987.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03079, over 972456.40 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 18:08:32,301 INFO [train.py:715] (5/8) Epoch 13, batch 12900, loss[loss=0.1399, simple_loss=0.2064, pruned_loss=0.03674, over 4695.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03097, over 971950.64 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 18:09:10,902 INFO [train.py:715] (5/8) Epoch 13, batch 12950, loss[loss=0.1538, simple_loss=0.2314, pruned_loss=0.03811, over 4812.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03156, over 971616.11 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 18:09:48,857 INFO [train.py:715] (5/8) Epoch 13, batch 13000, loss[loss=0.1079, simple_loss=0.1794, pruned_loss=0.01821, over 4822.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03131, over 971108.13 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 18:10:26,256 INFO [train.py:715] (5/8) Epoch 13, batch 13050, loss[loss=0.1428, simple_loss=0.21, pruned_loss=0.03783, over 4816.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03163, over 970413.10 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 18:11:05,301 INFO [train.py:715] (5/8) Epoch 13, batch 13100, loss[loss=0.101, simple_loss=0.1718, pruned_loss=0.01515, over 4932.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03125, over 970819.20 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 18:11:43,995 INFO [train.py:715] (5/8) Epoch 13, batch 13150, loss[loss=0.1534, simple_loss=0.2254, pruned_loss=0.04069, over 4781.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03061, over 971404.82 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 18:12:21,745 INFO [train.py:715] (5/8) Epoch 13, batch 13200, loss[loss=0.1328, simple_loss=0.2028, pruned_loss=0.03139, over 4840.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03049, over 971811.31 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 18:13:00,176 INFO [train.py:715] (5/8) Epoch 13, batch 13250, loss[loss=0.1242, simple_loss=0.1984, pruned_loss=0.02502, over 4970.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03074, over 972146.51 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 18:13:38,868 INFO [train.py:715] (5/8) Epoch 13, batch 13300, loss[loss=0.1301, simple_loss=0.2124, pruned_loss=0.02385, over 4798.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03129, over 972445.32 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 18:14:17,604 INFO [train.py:715] (5/8) Epoch 13, batch 13350, loss[loss=0.1489, simple_loss=0.2234, pruned_loss=0.03722, over 4796.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03146, over 971379.93 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 18:14:55,893 INFO [train.py:715] (5/8) Epoch 13, batch 13400, loss[loss=0.137, simple_loss=0.2185, pruned_loss=0.02773, over 4935.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03179, over 972030.99 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 18:15:35,680 INFO [train.py:715] (5/8) Epoch 13, batch 13450, loss[loss=0.1283, simple_loss=0.2, pruned_loss=0.02829, over 4797.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03171, over 972545.57 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 18:16:14,408 INFO [train.py:715] (5/8) Epoch 13, batch 13500, loss[loss=0.1808, simple_loss=0.2474, pruned_loss=0.05709, over 4804.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03154, over 972536.55 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 18:16:52,059 INFO [train.py:715] (5/8) Epoch 13, batch 13550, loss[loss=0.133, simple_loss=0.2053, pruned_loss=0.03033, over 4762.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2109, pruned_loss=0.03107, over 972223.90 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 18:17:29,850 INFO [train.py:715] (5/8) Epoch 13, batch 13600, loss[loss=0.1462, simple_loss=0.2224, pruned_loss=0.03505, over 4934.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03142, over 972090.49 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:18:08,970 INFO [train.py:715] (5/8) Epoch 13, batch 13650, loss[loss=0.1441, simple_loss=0.2207, pruned_loss=0.03371, over 4885.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03144, over 971454.04 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:18:47,086 INFO [train.py:715] (5/8) Epoch 13, batch 13700, loss[loss=0.1278, simple_loss=0.2063, pruned_loss=0.02465, over 4787.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03147, over 971500.04 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:19:24,725 INFO [train.py:715] (5/8) Epoch 13, batch 13750, loss[loss=0.1202, simple_loss=0.1924, pruned_loss=0.02396, over 4912.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03162, over 972180.48 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:20:03,321 INFO [train.py:715] (5/8) Epoch 13, batch 13800, loss[loss=0.1205, simple_loss=0.1995, pruned_loss=0.0208, over 4906.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.0321, over 973264.55 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:20:41,460 INFO [train.py:715] (5/8) Epoch 13, batch 13850, loss[loss=0.1259, simple_loss=0.1929, pruned_loss=0.02944, over 4946.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03173, over 972359.57 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 18:21:19,872 INFO [train.py:715] (5/8) Epoch 13, batch 13900, loss[loss=0.1537, simple_loss=0.23, pruned_loss=0.03869, over 4848.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03161, over 972194.08 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:21:58,636 INFO [train.py:715] (5/8) Epoch 13, batch 13950, loss[loss=0.1163, simple_loss=0.1958, pruned_loss=0.01838, over 4907.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03159, over 971433.27 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:22:37,441 INFO [train.py:715] (5/8) Epoch 13, batch 14000, loss[loss=0.1294, simple_loss=0.192, pruned_loss=0.03343, over 4960.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03202, over 972049.03 frames.], batch size: 35, lr: 1.68e-04
2022-05-07 18:23:15,662 INFO [train.py:715] (5/8) Epoch 13, batch 14050, loss[loss=0.126, simple_loss=0.1982, pruned_loss=0.0269, over 4818.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03178, over 971534.11 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 18:23:53,254 INFO [train.py:715] (5/8) Epoch 13, batch 14100, loss[loss=0.1048, simple_loss=0.1754, pruned_loss=0.01713, over 4883.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03183, over 971096.93 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:24:32,482 INFO [train.py:715] (5/8) Epoch 13, batch 14150, loss[loss=0.108, simple_loss=0.1829, pruned_loss=0.01654, over 4776.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03177, over 971325.73 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:25:10,630 INFO [train.py:715] (5/8) Epoch 13, batch 14200, loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03122, over 4889.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03164, over 972007.81 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:25:48,510 INFO [train.py:715] (5/8) Epoch 13, batch 14250, loss[loss=0.09978, simple_loss=0.1682, pruned_loss=0.01569, over 4788.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03173, over 971661.77 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 18:26:26,774 INFO [train.py:715] (5/8) Epoch 13, batch 14300, loss[loss=0.1396, simple_loss=0.2076, pruned_loss=0.03581, over 4850.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2091, pruned_loss=0.03159, over 971271.55 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:27:06,171 INFO [train.py:715] (5/8) Epoch 13, batch 14350, loss[loss=0.1399, simple_loss=0.225, pruned_loss=0.02737, over 4792.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03167, over 971084.87 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 18:27:44,510 INFO [train.py:715] (5/8) Epoch 13, batch 14400, loss[loss=0.1673, simple_loss=0.234, pruned_loss=0.05028, over 4896.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03174, over 970451.68 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:28:22,435 INFO [train.py:715] (5/8) Epoch 13, batch 14450, loss[loss=0.1817, simple_loss=0.2547, pruned_loss=0.05434, over 4958.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03184, over 970615.08 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:29:01,543 INFO [train.py:715] (5/8) Epoch 13, batch 14500, loss[loss=0.1603, simple_loss=0.224, pruned_loss=0.04831, over 4689.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03192, over 971291.38 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:29:40,346 INFO [train.py:715] (5/8) Epoch 13, batch 14550, loss[loss=0.1506, simple_loss=0.2102, pruned_loss=0.04547, over 4845.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03188, over 971467.07 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:30:18,695 INFO [train.py:715] (5/8) Epoch 13, batch 14600, loss[loss=0.1161, simple_loss=0.1888, pruned_loss=0.02168, over 4936.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.0322, over 971907.50 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 18:30:57,059 INFO [train.py:715] (5/8) Epoch 13, batch 14650, loss[loss=0.1363, simple_loss=0.2176, pruned_loss=0.02746, over 4829.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03195, over 971955.81 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:31:35,710 INFO [train.py:715] (5/8) Epoch 13, batch 14700, loss[loss=0.1315, simple_loss=0.2041, pruned_loss=0.02945, over 4936.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03187, over 971283.71 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 18:32:13,647 INFO [train.py:715] (5/8) Epoch 13, batch 14750, loss[loss=0.141, simple_loss=0.2275, pruned_loss=0.02727, over 4780.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2115, pruned_loss=0.03139, over 971033.41 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:32:50,801 INFO [train.py:715] (5/8) Epoch 13, batch 14800, loss[loss=0.1646, simple_loss=0.2236, pruned_loss=0.0528, over 4882.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2115, pruned_loss=0.03155, over 971350.25 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:33:29,890 INFO [train.py:715] (5/8) Epoch 13, batch 14850, loss[loss=0.1159, simple_loss=0.1886, pruned_loss=0.02157, over 4888.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2107, pruned_loss=0.03118, over 970866.91 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 18:34:08,570 INFO [train.py:715] (5/8) Epoch 13, batch 14900, loss[loss=0.1395, simple_loss=0.2128, pruned_loss=0.03306, over 4786.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03136, over 971527.54 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:34:46,492 INFO [train.py:715] (5/8) Epoch 13, batch 14950, loss[loss=0.1377, simple_loss=0.2145, pruned_loss=0.0305, over 4898.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03101, over 971973.92 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 18:35:24,995 INFO [train.py:715] (5/8) Epoch 13, batch 15000, loss[loss=0.1337, simple_loss=0.205, pruned_loss=0.03117, over 4769.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03116, over 971797.61 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:35:24,995 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 18:35:34,567 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
2022-05-07 18:36:13,158 INFO [train.py:715] (5/8) Epoch 13, batch 15050, loss[loss=0.1093, simple_loss=0.1795, pruned_loss=0.01959, over 4788.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03109, over 972120.73 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:36:52,715 INFO [train.py:715] (5/8) Epoch 13, batch 15100, loss[loss=0.1222, simple_loss=0.1909, pruned_loss=0.02679, over 4925.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03099, over 971490.04 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:37:31,195 INFO [train.py:715] (5/8) Epoch 13, batch 15150, loss[loss=0.138, simple_loss=0.2155, pruned_loss=0.03021, over 4869.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03093, over 971659.87 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:38:09,446 INFO [train.py:715] (5/8) Epoch 13, batch 15200, loss[loss=0.1371, simple_loss=0.2166, pruned_loss=0.02879, over 4863.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03118, over 971759.95 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:38:49,229 INFO [train.py:715] (5/8) Epoch 13, batch 15250, loss[loss=0.1412, simple_loss=0.2148, pruned_loss=0.03378, over 4835.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03093, over 972062.52 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:39:27,975 INFO [train.py:715] (5/8) Epoch 13, batch 15300, loss[loss=0.1404, simple_loss=0.2259, pruned_loss=0.02745, over 4840.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03105, over 971855.06 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:40:06,014 INFO [train.py:715] (5/8) Epoch 13, batch 15350, loss[loss=0.1243, simple_loss=0.192, pruned_loss=0.02834, over 4875.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 971823.05 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:40:45,015 INFO [train.py:715] (5/8) Epoch 13, batch 15400, loss[loss=0.1451, simple_loss=0.2198, pruned_loss=0.03522, over 4761.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03142, over 971394.31 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:41:23,903 INFO [train.py:715] (5/8) Epoch 13, batch 15450, loss[loss=0.1406, simple_loss=0.2178, pruned_loss=0.03172, over 4930.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03077, over 970937.86 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:42:03,714 INFO [train.py:715] (5/8) Epoch 13, batch 15500, loss[loss=0.1331, simple_loss=0.2128, pruned_loss=0.02667, over 4945.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03023, over 971344.86 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 18:42:41,962 INFO [train.py:715] (5/8) Epoch 13, batch 15550, loss[loss=0.1785, simple_loss=0.2528, pruned_loss=0.05209, over 4912.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03063, over 971949.94 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:43:21,698 INFO [train.py:715] (5/8) Epoch 13, batch 15600, loss[loss=0.1518, simple_loss=0.2333, pruned_loss=0.03517, over 4909.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03072, over 972399.45 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:44:01,140 INFO [train.py:715] (5/8) Epoch 13, batch 15650, loss[loss=0.1525, simple_loss=0.2241, pruned_loss=0.04042, over 4751.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03071, over 972361.87 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:44:39,625 INFO [train.py:715] (5/8) Epoch 13, batch 15700, loss[loss=0.1181, simple_loss=0.1957, pruned_loss=0.02018, over 4941.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03089, over 972120.61 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:45:18,633 INFO [train.py:715] (5/8) Epoch 13, batch 15750, loss[loss=0.1115, simple_loss=0.1764, pruned_loss=0.0233, over 4981.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03077, over 972234.89 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:45:57,411 INFO [train.py:715] (5/8) Epoch 13, batch 15800, loss[loss=0.141, simple_loss=0.2105, pruned_loss=0.03568, over 4838.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03053, over 972557.34 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:46:35,695 INFO [train.py:715] (5/8) Epoch 13, batch 15850, loss[loss=0.1534, simple_loss=0.2292, pruned_loss=0.03885, over 4789.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.0305, over 972418.35 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:47:13,600 INFO [train.py:715] (5/8) Epoch 13, batch 15900, loss[loss=0.1297, simple_loss=0.1931, pruned_loss=0.03314, over 4872.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03049, over 972013.00 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:47:52,836 INFO [train.py:715] (5/8) Epoch 13, batch 15950, loss[loss=0.1788, simple_loss=0.2493, pruned_loss=0.05419, over 4990.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03028, over 971631.58 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 18:48:31,349 INFO [train.py:715] (5/8) Epoch 13, batch 16000, loss[loss=0.09994, simple_loss=0.1729, pruned_loss=0.01348, over 4814.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 972321.71 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 18:49:09,601 INFO [train.py:715] (5/8) Epoch 13, batch 16050, loss[loss=0.1246, simple_loss=0.2088, pruned_loss=0.02022, over 4822.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02985, over 972382.93 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 18:49:48,080 INFO [train.py:715] (5/8) Epoch 13, batch 16100, loss[loss=0.1598, simple_loss=0.2301, pruned_loss=0.04469, over 4913.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02998, over 972389.78 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:50:27,334 INFO [train.py:715] (5/8) Epoch 13, batch 16150, loss[loss=0.1408, simple_loss=0.2108, pruned_loss=0.03541, over 4743.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2096, pruned_loss=0.0305, over 972619.22 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:51:05,993 INFO [train.py:715] (5/8) Epoch 13, batch 16200, loss[loss=0.1497, simple_loss=0.2233, pruned_loss=0.03806, over 4896.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03014, over 972993.90 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:51:42,923 INFO [train.py:715] (5/8) Epoch 13, batch 16250, loss[loss=0.1439, simple_loss=0.2092, pruned_loss=0.03928, over 4857.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03064, over 973070.09 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:52:22,101 INFO [train.py:715] (5/8) Epoch 13, batch 16300, loss[loss=0.1317, simple_loss=0.2105, pruned_loss=0.02648, over 4967.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03102, over 973346.13 frames.], batch size: 35, lr: 1.68e-04
2022-05-07 18:53:00,700 INFO [train.py:715] (5/8) Epoch 13, batch 16350, loss[loss=0.1018, simple_loss=0.1821, pruned_loss=0.01071, over 4800.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2106, pruned_loss=0.03093, over 972970.28 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:53:39,044 INFO [train.py:715] (5/8) Epoch 13, batch 16400, loss[loss=0.1434, simple_loss=0.2169, pruned_loss=0.03497, over 4908.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03161, over 973459.43 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:54:18,190 INFO [train.py:715] (5/8) Epoch 13, batch 16450, loss[loss=0.1202, simple_loss=0.1963, pruned_loss=0.02207, over 4816.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2113, pruned_loss=0.03143, over 972937.06 frames.], batch size: 27, lr: 1.68e-04
2022-05-07 18:54:57,401 INFO [train.py:715] (5/8) Epoch 13, batch 16500, loss[loss=0.124, simple_loss=0.2006, pruned_loss=0.02376, over 4970.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2112, pruned_loss=0.03151, over 973117.72 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:55:36,542 INFO [train.py:715] (5/8) Epoch 13, batch 16550, loss[loss=0.1225, simple_loss=0.1948, pruned_loss=0.0251, over 4795.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2108, pruned_loss=0.03088, over 972932.19 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:56:13,925 INFO [train.py:715] (5/8) Epoch 13, batch 16600, loss[loss=0.1542, simple_loss=0.2234, pruned_loss=0.0425, over 4759.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03136, over 973360.62 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:56:53,166 INFO [train.py:715] (5/8) Epoch 13, batch 16650, loss[loss=0.1639, simple_loss=0.2407, pruned_loss=0.0435, over 4886.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.03164, over 973921.86 frames.], batch size: 38, lr: 1.68e-04
2022-05-07 18:57:31,700 INFO [train.py:715] (5/8) Epoch 13, batch 16700, loss[loss=0.1305, simple_loss=0.214, pruned_loss=0.02353, over 4783.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03223, over 973796.36 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:58:09,691 INFO [train.py:715] (5/8) Epoch 13, batch 16750, loss[loss=0.1372, simple_loss=0.2074, pruned_loss=0.0335, over 4986.00 frames.], tot_loss[loss=0.1382, simple_loss=0.212, pruned_loss=0.03219, over 973207.67 frames.], batch size: 28, lr: 1.68e-04
2022-05-07 18:58:48,290 INFO [train.py:715] (5/8) Epoch 13, batch 16800, loss[loss=0.1463, simple_loss=0.2132, pruned_loss=0.03972, over 4913.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03217, over 973168.02 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:59:27,923 INFO [train.py:715] (5/8) Epoch 13, batch 16850, loss[loss=0.1227, simple_loss=0.1982, pruned_loss=0.02356, over 4809.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03164, over 972578.91 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 19:00:06,299 INFO [train.py:715] (5/8) Epoch 13, batch 16900, loss[loss=0.1516, simple_loss=0.2077, pruned_loss=0.04771, over 4846.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 972736.83 frames.], batch size: 13, lr: 1.68e-04
2022-05-07 19:00:44,804 INFO [train.py:715] (5/8) Epoch 13, batch 16950, loss[loss=0.1602, simple_loss=0.2453, pruned_loss=0.0375, over 4912.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03171, over 972586.33 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 19:01:23,719 INFO [train.py:715] (5/8) Epoch 13, batch 17000, loss[loss=0.1522, simple_loss=0.2329, pruned_loss=0.03573, over 4778.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03198, over 972574.01 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 19:02:02,413 INFO [train.py:715] (5/8) Epoch 13, batch 17050, loss[loss=0.1298, simple_loss=0.2046, pruned_loss=0.02753, over 4918.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03216, over 973090.87 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 19:02:40,528 INFO [train.py:715] (5/8) Epoch 13, batch 17100, loss[loss=0.137, simple_loss=0.2056, pruned_loss=0.03421, over 4846.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03211, over 973627.55 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 19:03:19,261 INFO [train.py:715] (5/8) Epoch 13, batch 17150, loss[loss=0.1339, simple_loss=0.215, pruned_loss=0.02637, over 4916.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03161, over 973348.58 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:03:58,099 INFO [train.py:715] (5/8) Epoch 13, batch 17200, loss[loss=0.1576, simple_loss=0.2338, pruned_loss=0.04073, over 4926.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03185, over 973287.64 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 19:04:36,807 INFO [train.py:715] (5/8) Epoch 13, batch 17250, loss[loss=0.1364, simple_loss=0.2022, pruned_loss=0.03528, over 4914.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03189, over 972459.82 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:05:14,779 INFO [train.py:715] (5/8) Epoch 13, batch 17300, loss[loss=0.123, simple_loss=0.2042, pruned_loss=0.02093, over 4745.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03155, over 972214.52 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:05:53,538 INFO [train.py:715] (5/8) Epoch 13, batch 17350, loss[loss=0.1299, simple_loss=0.2122, pruned_loss=0.02385, over 4879.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03207, over 971538.40 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:06:32,454 INFO [train.py:715] (5/8) Epoch 13, batch 17400, loss[loss=0.1361, simple_loss=0.2125, pruned_loss=0.02989, over 4969.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.0321, over 970941.76 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 19:07:10,068 INFO [train.py:715] (5/8) Epoch 13, batch 17450, loss[loss=0.1398, simple_loss=0.2192, pruned_loss=0.03022, over 4747.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03179, over 971024.01 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:07:48,568 INFO [train.py:715] (5/8) Epoch 13, batch 17500, loss[loss=0.1077, simple_loss=0.1808, pruned_loss=0.01727, over 4808.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 971885.79 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 19:08:27,655 INFO [train.py:715] (5/8) Epoch 13, batch 17550, loss[loss=0.1198, simple_loss=0.1846, pruned_loss=0.0275, over 4986.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03129, over 971358.97 frames.], batch size: 28, lr: 1.68e-04
2022-05-07 19:09:06,326 INFO [train.py:715] (5/8) Epoch 13, batch 17600, loss[loss=0.1114, simple_loss=0.1837, pruned_loss=0.01951, over 4773.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03078, over 971087.03 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 19:09:43,948 INFO [train.py:715] (5/8) Epoch 13, batch 17650, loss[loss=0.139, simple_loss=0.2152, pruned_loss=0.03135, over 4816.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2072, pruned_loss=0.03033, over 971110.58 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:10:23,207 INFO [train.py:715] (5/8) Epoch 13, batch 17700, loss[loss=0.1375, simple_loss=0.2073, pruned_loss=0.03382, over 4989.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2077, pruned_loss=0.03053, over 971231.85 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 19:11:02,061 INFO [train.py:715] (5/8) Epoch 13, batch 17750, loss[loss=0.1438, simple_loss=0.2104, pruned_loss=0.03857, over 4911.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.0306, over 972007.63 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 19:11:39,679 INFO [train.py:715] (5/8) Epoch 13, batch 17800, loss[loss=0.1119, simple_loss=0.1827, pruned_loss=0.02057, over 4984.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2073, pruned_loss=0.03021, over 971617.36 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 19:12:18,453 INFO [train.py:715] (5/8) Epoch 13, batch 17850, loss[loss=0.1236, simple_loss=0.2041, pruned_loss=0.02155, over 4946.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03059, over 972045.89 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:12:57,285 INFO [train.py:715] (5/8) Epoch 13, batch 17900, loss[loss=0.1159, simple_loss=0.1814, pruned_loss=0.02521, over 4807.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03106, over 971247.94 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 19:13:35,477 INFO [train.py:715] (5/8) Epoch 13, batch 17950, loss[loss=0.1143, simple_loss=0.1952, pruned_loss=0.01669, over 4884.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03148, over 971663.34 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:14:13,538 INFO [train.py:715] (5/8) Epoch 13, batch 18000, loss[loss=0.1239, simple_loss=0.2038, pruned_loss=0.02199, over 4839.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.0315, over 971947.93 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 19:14:13,539 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 19:14:23,028 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1892, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 19:15:00,695 INFO [train.py:715] (5/8) Epoch 13, batch 18050, loss[loss=0.1346, simple_loss=0.2183, pruned_loss=0.02541, over 4906.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03188, over 973059.97 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:15:39,772 INFO [train.py:715] (5/8) Epoch 13, batch 18100, loss[loss=0.1315, simple_loss=0.2001, pruned_loss=0.03142, over 4913.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03135, over 973484.44 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:16:18,123 INFO [train.py:715] (5/8) Epoch 13, batch 18150, loss[loss=0.1563, simple_loss=0.2242, pruned_loss=0.04427, over 4839.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03201, over 972867.71 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:16:55,372 INFO [train.py:715] (5/8) Epoch 13, batch 18200, loss[loss=0.1236, simple_loss=0.19, pruned_loss=0.02858, over 4643.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03203, over 972183.37 frames.], batch size: 13, lr: 1.68e-04
2022-05-07 19:17:33,691 INFO [train.py:715] (5/8) Epoch 13, batch 18250, loss[loss=0.1392, simple_loss=0.2169, pruned_loss=0.03077, over 4909.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03256, over 971888.71 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 19:18:12,483 INFO [train.py:715] (5/8) Epoch 13, batch 18300, loss[loss=0.1352, simple_loss=0.2054, pruned_loss=0.03247, over 4888.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03245, over 971949.33 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:18:51,122 INFO [train.py:715] (5/8) Epoch 13, batch 18350, loss[loss=0.1685, simple_loss=0.2397, pruned_loss=0.04871, over 4853.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03213, over 972493.74 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:19:29,022 INFO [train.py:715] (5/8) Epoch 13, batch 18400, loss[loss=0.1358, simple_loss=0.2084, pruned_loss=0.03163, over 4874.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03201, over 972538.58 frames.], batch size: 13, lr: 1.68e-04
2022-05-07 19:20:07,826 INFO [train.py:715] (5/8) Epoch 13, batch 18450, loss[loss=0.1561, simple_loss=0.2297, pruned_loss=0.04127, over 4912.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03189, over 972933.82 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 19:20:46,497 INFO [train.py:715] (5/8) Epoch 13, batch 18500, loss[loss=0.1161, simple_loss=0.1857, pruned_loss=0.02321, over 4988.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03141, over 973526.68 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:21:23,939 INFO [train.py:715] (5/8) Epoch 13, batch 18550, loss[loss=0.1244, simple_loss=0.2033, pruned_loss=0.02274, over 4753.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03072, over 972872.93 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 19:22:01,960 INFO [train.py:715] (5/8) Epoch 13, batch 18600, loss[loss=0.1324, simple_loss=0.2094, pruned_loss=0.02767, over 4735.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.0305, over 972279.22 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 19:22:40,555 INFO [train.py:715] (5/8) Epoch 13, batch 18650, loss[loss=0.1597, simple_loss=0.2346, pruned_loss=0.0424, over 4826.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03093, over 972548.26 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:23:18,503 INFO [train.py:715] (5/8) Epoch 13, batch 18700, loss[loss=0.1145, simple_loss=0.1905, pruned_loss=0.01922, over 4845.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03086, over 973046.79 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 19:23:56,289 INFO [train.py:715] (5/8) Epoch 13, batch 18750, loss[loss=0.1229, simple_loss=0.1986, pruned_loss=0.0236, over 4845.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03061, over 972716.97 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 19:24:35,596 INFO [train.py:715] (5/8) Epoch 13, batch 18800, loss[loss=0.134, simple_loss=0.2087, pruned_loss=0.02969, over 4891.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03095, over 972937.82 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:25:14,015 INFO [train.py:715] (5/8) Epoch 13, batch 18850, loss[loss=0.1432, simple_loss=0.2186, pruned_loss=0.03384, over 4869.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03135, over 972413.60 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:25:52,019 INFO [train.py:715] (5/8) Epoch 13, batch 18900, loss[loss=0.1508, simple_loss=0.2341, pruned_loss=0.03377, over 4837.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03095, over 972608.04 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 19:26:30,883 INFO [train.py:715] (5/8) Epoch 13, batch 18950, loss[loss=0.1415, simple_loss=0.2135, pruned_loss=0.03475, over 4850.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03099, over 972041.65 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 19:27:09,767 INFO [train.py:715] (5/8) Epoch 13, batch 19000, loss[loss=0.1216, simple_loss=0.197, pruned_loss=0.02311, over 4792.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03086, over 972815.71 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:27:48,114 INFO [train.py:715] (5/8) Epoch 13, batch 19050, loss[loss=0.173, simple_loss=0.2599, pruned_loss=0.04301, over 4855.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03106, over 973098.86 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 19:28:26,437 INFO [train.py:715] (5/8) Epoch 13, batch 19100, loss[loss=0.1388, simple_loss=0.2055, pruned_loss=0.03606, over 4990.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03109, over 972678.31 frames.], batch size: 31, lr: 1.68e-04
2022-05-07 19:29:05,442 INFO [train.py:715] (5/8) Epoch 13, batch 19150, loss[loss=0.1313, simple_loss=0.1996, pruned_loss=0.03146, over 4868.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03127, over 972691.26 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 19:29:44,104 INFO [train.py:715] (5/8) Epoch 13, batch 19200, loss[loss=0.1285, simple_loss=0.204, pruned_loss=0.0265, over 4932.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03115, over 973046.37 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:30:21,502 INFO [train.py:715] (5/8) Epoch 13, batch 19250, loss[loss=0.1156, simple_loss=0.1919, pruned_loss=0.01966, over 4939.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 972284.16 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 19:31:00,078 INFO [train.py:715] (5/8) Epoch 13, batch 19300, loss[loss=0.1779, simple_loss=0.2459, pruned_loss=0.05492, over 4972.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03084, over 971975.68 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:31:39,542 INFO [train.py:715] (5/8) Epoch 13, batch 19350, loss[loss=0.1536, simple_loss=0.2311, pruned_loss=0.03809, over 4759.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03094, over 971629.30 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:32:18,081 INFO [train.py:715] (5/8) Epoch 13, batch 19400, loss[loss=0.1379, simple_loss=0.209, pruned_loss=0.03342, over 4977.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03086, over 971492.70 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 19:32:56,516 INFO [train.py:715] (5/8) Epoch 13, batch 19450, loss[loss=0.1299, simple_loss=0.2029, pruned_loss=0.02848, over 4815.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03151, over 971338.66 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 19:33:37,808 INFO [train.py:715] (5/8) Epoch 13, batch 19500, loss[loss=0.1394, simple_loss=0.2103, pruned_loss=0.03425, over 4963.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 970992.10 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 19:34:16,750 INFO [train.py:715] (5/8) Epoch 13, batch 19550, loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03252, over 4763.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03082, over 970562.27 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:34:54,319 INFO [train.py:715] (5/8) Epoch 13, batch 19600, loss[loss=0.1277, simple_loss=0.2027, pruned_loss=0.02634, over 4864.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03109, over 971079.93 frames.], batch size: 30, lr: 1.67e-04
2022-05-07 19:35:32,448 INFO [train.py:715] (5/8) Epoch 13, batch 19650, loss[loss=0.1305, simple_loss=0.204, pruned_loss=0.02848, over 4919.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03106, over 971772.26 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:36:11,254 INFO [train.py:715] (5/8) Epoch 13, batch 19700, loss[loss=0.1749, simple_loss=0.2442, pruned_loss=0.05282, over 4897.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03156, over 971804.36 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 19:36:49,085 INFO [train.py:715] (5/8) Epoch 13, batch 19750, loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.0322, over 4876.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03222, over 972251.22 frames.], batch size: 38, lr: 1.67e-04
2022-05-07 19:37:26,938 INFO [train.py:715] (5/8) Epoch 13, batch 19800, loss[loss=0.1429, simple_loss=0.2224, pruned_loss=0.03172, over 4770.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03227, over 972753.46 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 19:38:05,611 INFO [train.py:715] (5/8) Epoch 13, batch 19850, loss[loss=0.1556, simple_loss=0.2314, pruned_loss=0.03989, over 4811.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03178, over 972023.32 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:38:44,227 INFO [train.py:715] (5/8) Epoch 13, batch 19900, loss[loss=0.1553, simple_loss=0.2146, pruned_loss=0.04801, over 4800.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03173, over 972057.01 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 19:39:22,426 INFO [train.py:715] (5/8) Epoch 13, batch 19950, loss[loss=0.1217, simple_loss=0.1983, pruned_loss=0.02257, over 4926.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03135, over 971881.54 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:40:01,317 INFO [train.py:715] (5/8) Epoch 13, batch 20000, loss[loss=0.1137, simple_loss=0.192, pruned_loss=0.01775, over 4809.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03148, over 970997.44 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 19:40:39,758 INFO [train.py:715] (5/8) Epoch 13, batch 20050, loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04083, over 4828.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03099, over 971225.52 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 19:41:16,931 INFO [train.py:715] (5/8) Epoch 13, batch 20100, loss[loss=0.1408, simple_loss=0.2203, pruned_loss=0.03061, over 4886.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03105, over 971397.39 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 19:41:54,382 INFO [train.py:715] (5/8) Epoch 13, batch 20150, loss[loss=0.1227, simple_loss=0.1915, pruned_loss=0.02691, over 4968.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03077, over 971366.91 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:42:33,107 INFO [train.py:715] (5/8) Epoch 13, batch 20200, loss[loss=0.1193, simple_loss=0.1898, pruned_loss=0.02435, over 4866.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03047, over 971009.24 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 19:43:11,187 INFO [train.py:715] (5/8) Epoch 13, batch 20250, loss[loss=0.1317, simple_loss=0.201, pruned_loss=0.03122, over 4781.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03066, over 971501.47 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 19:43:48,891 INFO [train.py:715] (5/8) Epoch 13, batch 20300, loss[loss=0.1254, simple_loss=0.2045, pruned_loss=0.02321, over 4918.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03054, over 971451.54 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 19:44:26,993 INFO [train.py:715] (5/8) Epoch 13, batch 20350, loss[loss=0.1136, simple_loss=0.1883, pruned_loss=0.01947, over 4820.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.0307, over 971249.24 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 19:45:05,762 INFO [train.py:715] (5/8) Epoch 13, batch 20400, loss[loss=0.1362, simple_loss=0.2154, pruned_loss=0.02852, over 4773.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03107, over 971611.53 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:45:43,493 INFO [train.py:715] (5/8) Epoch 13, batch 20450, loss[loss=0.1315, simple_loss=0.2045, pruned_loss=0.02928, over 4704.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.0308, over 971638.72 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:46:21,265 INFO [train.py:715] (5/8) Epoch 13, batch 20500, loss[loss=0.124, simple_loss=0.2078, pruned_loss=0.02015, over 4791.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.0309, over 971951.37 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:46:59,824 INFO [train.py:715] (5/8) Epoch 13, batch 20550, loss[loss=0.1478, simple_loss=0.2163, pruned_loss=0.03966, over 4830.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.0316, over 971567.63 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:47:37,480 INFO [train.py:715] (5/8) Epoch 13, batch 20600, loss[loss=0.1688, simple_loss=0.2437, pruned_loss=0.04697, over 4929.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03164, over 972841.83 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:48:15,107 INFO [train.py:715] (5/8) Epoch 13, batch 20650, loss[loss=0.1315, simple_loss=0.2113, pruned_loss=0.0258, over 4967.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03168, over 972743.65 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:48:52,913 INFO [train.py:715] (5/8) Epoch 13, batch 20700, loss[loss=0.1262, simple_loss=0.2034, pruned_loss=0.02449, over 4697.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03161, over 972907.75 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:49:31,350 INFO [train.py:715] (5/8) Epoch 13, batch 20750, loss[loss=0.1313, simple_loss=0.2048, pruned_loss=0.02895, over 4962.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.0313, over 973022.24 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:50:08,696 INFO [train.py:715] (5/8) Epoch 13, batch 20800, loss[loss=0.1656, simple_loss=0.2326, pruned_loss=0.04934, over 4933.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03088, over 972008.16 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:50:46,282 INFO [train.py:715] (5/8) Epoch 13, batch 20850, loss[loss=0.1427, simple_loss=0.2278, pruned_loss=0.02878, over 4778.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03096, over 972092.55 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:51:24,967 INFO [train.py:715] (5/8) Epoch 13, batch 20900, loss[loss=0.1353, simple_loss=0.2099, pruned_loss=0.03036, over 4946.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03085, over 971196.49 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 19:52:03,240 INFO [train.py:715] (5/8) Epoch 13, batch 20950, loss[loss=0.1286, simple_loss=0.1972, pruned_loss=0.02994, over 4689.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03072, over 971749.11 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:52:40,746 INFO [train.py:715] (5/8) Epoch 13, batch 21000, loss[loss=0.1457, simple_loss=0.2216, pruned_loss=0.0349, over 4943.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03127, over 972928.39 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:52:40,747 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 19:52:50,263 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 19:53:28,434 INFO [train.py:715] (5/8) Epoch 13, batch 21050, loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03474, over 4824.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03101, over 973135.26 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:54:06,967 INFO [train.py:715] (5/8) Epoch 13, batch 21100, loss[loss=0.1924, simple_loss=0.2271, pruned_loss=0.07891, over 4766.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03132, over 973911.92 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 19:54:46,056 INFO [train.py:715] (5/8) Epoch 13, batch 21150, loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03674, over 4855.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03109, over 973314.00 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 19:55:23,879 INFO [train.py:715] (5/8) Epoch 13, batch 21200, loss[loss=0.1338, simple_loss=0.2121, pruned_loss=0.02772, over 4947.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.0313, over 972576.09 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:56:02,465 INFO [train.py:715] (5/8) Epoch 13, batch 21250, loss[loss=0.1431, simple_loss=0.2109, pruned_loss=0.03768, over 4968.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03169, over 972895.01 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:56:41,277 INFO [train.py:715] (5/8) Epoch 13, batch 21300, loss[loss=0.174, simple_loss=0.2333, pruned_loss=0.05736, over 4865.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03184, over 973338.18 frames.], batch size: 30, lr: 1.67e-04
2022-05-07 19:57:19,154 INFO [train.py:715] (5/8) Epoch 13, batch 21350, loss[loss=0.1133, simple_loss=0.1897, pruned_loss=0.01839, over 4982.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03137, over 972888.90 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:57:57,082 INFO [train.py:715] (5/8) Epoch 13, batch 21400, loss[loss=0.1502, simple_loss=0.2337, pruned_loss=0.03334, over 4760.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03129, over 972288.62 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 19:58:35,345 INFO [train.py:715] (5/8) Epoch 13, batch 21450, loss[loss=0.1623, simple_loss=0.2301, pruned_loss=0.04721, over 4950.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03096, over 972117.16 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:59:14,501 INFO [train.py:715] (5/8) Epoch 13, batch 21500, loss[loss=0.1406, simple_loss=0.2248, pruned_loss=0.02816, over 4776.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.0311, over 971935.70 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:59:52,265 INFO [train.py:715] (5/8) Epoch 13, batch 21550, loss[loss=0.1532, simple_loss=0.2299, pruned_loss=0.03825, over 4988.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03139, over 972079.34 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:00:30,897 INFO [train.py:715] (5/8) Epoch 13, batch 21600, loss[loss=0.1184, simple_loss=0.1934, pruned_loss=0.02164, over 4948.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03131, over 971468.18 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:01:09,863 INFO [train.py:715] (5/8) Epoch 13, batch 21650, loss[loss=0.1504, simple_loss=0.2181, pruned_loss=0.04134, over 4990.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03132, over 971935.22 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 20:01:48,623 INFO [train.py:715] (5/8) Epoch 13, batch 21700, loss[loss=0.1647, simple_loss=0.2357, pruned_loss=0.04685, over 4915.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03148, over 971593.18 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:02:27,466 INFO [train.py:715] (5/8) Epoch 13, batch 21750, loss[loss=0.1485, simple_loss=0.2204, pruned_loss=0.03829, over 4782.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.0313, over 971990.14 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:03:06,113 INFO [train.py:715] (5/8) Epoch 13, batch 21800, loss[loss=0.1157, simple_loss=0.1934, pruned_loss=0.01898, over 4773.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03163, over 972336.31 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:03:45,411 INFO [train.py:715] (5/8) Epoch 13, batch 21850, loss[loss=0.1816, simple_loss=0.2475, pruned_loss=0.05787, over 4980.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03153, over 971535.64 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:04:23,520 INFO [train.py:715] (5/8) Epoch 13, batch 21900, loss[loss=0.1551, simple_loss=0.2279, pruned_loss=0.04112, over 4978.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03153, over 971595.09 frames.], batch size: 28, lr: 1.67e-04
2022-05-07 20:05:01,701 INFO [train.py:715] (5/8) Epoch 13, batch 21950, loss[loss=0.1498, simple_loss=0.2341, pruned_loss=0.03275, over 4908.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 971542.44 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 20:05:40,175 INFO [train.py:715] (5/8) Epoch 13, batch 22000, loss[loss=0.1168, simple_loss=0.1894, pruned_loss=0.02206, over 4988.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03117, over 972691.46 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:06:17,896 INFO [train.py:715] (5/8) Epoch 13, batch 22050, loss[loss=0.1515, simple_loss=0.2311, pruned_loss=0.03597, over 4759.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.0316, over 972079.76 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:06:55,941 INFO [train.py:715] (5/8) Epoch 13, batch 22100, loss[loss=0.147, simple_loss=0.2208, pruned_loss=0.0366, over 4902.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03213, over 972256.21 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 20:07:33,694 INFO [train.py:715] (5/8) Epoch 13, batch 22150, loss[loss=0.1133, simple_loss=0.1913, pruned_loss=0.01764, over 4833.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03199, over 972572.57 frames.], batch size: 27, lr: 1.67e-04
2022-05-07 20:08:12,647 INFO [train.py:715] (5/8) Epoch 13, batch 22200, loss[loss=0.1315, simple_loss=0.2121, pruned_loss=0.02543, over 4986.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.0312, over 972830.98 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:08:50,193 INFO [train.py:715] (5/8) Epoch 13, batch 22250, loss[loss=0.1314, simple_loss=0.2018, pruned_loss=0.03056, over 4815.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03097, over 972104.40 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 20:09:28,955 INFO [train.py:715] (5/8) Epoch 13, batch 22300, loss[loss=0.1638, simple_loss=0.2467, pruned_loss=0.04049, over 4854.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03042, over 971907.63 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:10:07,702 INFO [train.py:715] (5/8) Epoch 13, batch 22350, loss[loss=0.1407, simple_loss=0.2115, pruned_loss=0.03498, over 4771.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.0303, over 972398.88 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:10:45,729 INFO [train.py:715] (5/8) Epoch 13, batch 22400, loss[loss=0.1175, simple_loss=0.1883, pruned_loss=0.02337, over 4794.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03034, over 971649.21 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 20:11:23,412 INFO [train.py:715] (5/8) Epoch 13, batch 22450, loss[loss=0.1476, simple_loss=0.2152, pruned_loss=0.04004, over 4873.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03072, over 972802.61 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:12:01,255 INFO [train.py:715] (5/8) Epoch 13, batch 22500, loss[loss=0.124, simple_loss=0.2014, pruned_loss=0.02323, over 4761.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03081, over 973360.31 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 20:12:39,612 INFO [train.py:715] (5/8) Epoch 13, batch 22550, loss[loss=0.1138, simple_loss=0.1874, pruned_loss=0.02008, over 4818.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.031, over 972063.13 frames.], batch size: 27, lr: 1.67e-04
2022-05-07 20:13:16,803 INFO [train.py:715] (5/8) Epoch 13, batch 22600, loss[loss=0.138, simple_loss=0.2092, pruned_loss=0.03342, over 4805.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 973099.56 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:13:54,711 INFO [train.py:715] (5/8) Epoch 13, batch 22650, loss[loss=0.133, simple_loss=0.2089, pruned_loss=0.02858, over 4988.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03058, over 973317.06 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:14:32,802 INFO [train.py:715] (5/8) Epoch 13, batch 22700, loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03158, over 4978.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03043, over 973088.24 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 20:15:11,033 INFO [train.py:715] (5/8) Epoch 13, batch 22750, loss[loss=0.1471, simple_loss=0.2169, pruned_loss=0.03863, over 4926.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2099, pruned_loss=0.03054, over 973864.10 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:15:49,013 INFO [train.py:715] (5/8) Epoch 13, batch 22800, loss[loss=0.1367, simple_loss=0.2141, pruned_loss=0.02967, over 4842.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2106, pruned_loss=0.03105, over 973060.03 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:16:27,580 INFO [train.py:715] (5/8) Epoch 13, batch 22850, loss[loss=0.1456, simple_loss=0.2086, pruned_loss=0.04131, over 4853.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03195, over 973521.88 frames.], batch size: 30, lr: 1.67e-04
2022-05-07 20:17:06,831 INFO [train.py:715] (5/8) Epoch 13, batch 22900, loss[loss=0.1288, simple_loss=0.2068, pruned_loss=0.02544, over 4864.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03183, over 972549.73 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:17:44,514 INFO [train.py:715] (5/8) Epoch 13, batch 22950, loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.0341, over 4955.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03207, over 972383.96 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:18:23,096 INFO [train.py:715] (5/8) Epoch 13, batch 23000, loss[loss=0.1422, simple_loss=0.2086, pruned_loss=0.03783, over 4883.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03193, over 972601.17 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 20:19:01,742 INFO [train.py:715] (5/8) Epoch 13, batch 23050, loss[loss=0.1187, simple_loss=0.1918, pruned_loss=0.0228, over 4974.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03165, over 972836.57 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:19:40,070 INFO [train.py:715] (5/8) Epoch 13, batch 23100, loss[loss=0.1403, simple_loss=0.2098, pruned_loss=0.03537, over 4861.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03123, over 973183.90 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:20:17,986 INFO [train.py:715] (5/8) Epoch 13, batch 23150, loss[loss=0.1463, simple_loss=0.2213, pruned_loss=0.03561, over 4877.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03112, over 972385.38 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:20:56,165 INFO [train.py:715] (5/8) Epoch 13, batch 23200, loss[loss=0.1534, simple_loss=0.2277, pruned_loss=0.03955, over 4810.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03134, over 973025.12 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:21:34,316 INFO [train.py:715] (5/8) Epoch 13, batch 23250, loss[loss=0.1256, simple_loss=0.197, pruned_loss=0.0271, over 4917.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 973218.71 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:22:11,786 INFO [train.py:715] (5/8) Epoch 13, batch 23300, loss[loss=0.1355, simple_loss=0.2115, pruned_loss=0.02974, over 4890.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03157, over 973482.96 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 20:22:50,106 INFO [train.py:715] (5/8) Epoch 13, batch 23350, loss[loss=0.1564, simple_loss=0.2271, pruned_loss=0.0429, over 4835.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03158, over 972943.83 frames.], batch size: 30, lr: 1.67e-04
2022-05-07 20:23:28,677 INFO [train.py:715] (5/8) Epoch 13, batch 23400, loss[loss=0.1577, simple_loss=0.2297, pruned_loss=0.04284, over 4889.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03122, over 971968.39 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:24:06,994 INFO [train.py:715] (5/8) Epoch 13, batch 23450, loss[loss=0.1546, simple_loss=0.2391, pruned_loss=0.03505, over 4757.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03086, over 972378.09 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 20:24:45,014 INFO [train.py:715] (5/8) Epoch 13, batch 23500, loss[loss=0.145, simple_loss=0.224, pruned_loss=0.03307, over 4786.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03111, over 972462.92 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:25:23,768 INFO [train.py:715] (5/8) Epoch 13, batch 23550, loss[loss=0.1318, simple_loss=0.1979, pruned_loss=0.03279, over 4778.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03061, over 972561.49 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:26:02,268 INFO [train.py:715] (5/8) Epoch 13, batch 23600, loss[loss=0.1509, simple_loss=0.2182, pruned_loss=0.0418, over 4930.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03096, over 973228.53 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:26:39,840 INFO [train.py:715] (5/8) Epoch 13, batch 23650, loss[loss=0.1327, simple_loss=0.2103, pruned_loss=0.02755, over 4870.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.0314, over 972340.86 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:27:18,104 INFO [train.py:715] (5/8) Epoch 13, batch 23700, loss[loss=0.1479, simple_loss=0.2223, pruned_loss=0.0367, over 4802.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03153, over 972646.24 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:27:56,587 INFO [train.py:715] (5/8) Epoch 13, batch 23750, loss[loss=0.1447, simple_loss=0.2141, pruned_loss=0.03761, over 4965.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03163, over 972803.93 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:28:34,760 INFO [train.py:715] (5/8) Epoch 13, batch 23800, loss[loss=0.1193, simple_loss=0.1912, pruned_loss=0.02371, over 4893.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.0317, over 972856.11 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:29:12,134 INFO [train.py:715] (5/8) Epoch 13, batch 23850, loss[loss=0.1436, simple_loss=0.2214, pruned_loss=0.03288, over 4640.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03171, over 973575.02 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 20:29:51,251 INFO [train.py:715] (5/8) Epoch 13, batch 23900, loss[loss=0.1682, simple_loss=0.2541, pruned_loss=0.04115, over 4886.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03165, over 973181.25 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:30:29,199 INFO [train.py:715] (5/8) Epoch 13, batch 23950, loss[loss=0.1289, simple_loss=0.1933, pruned_loss=0.03226, over 4866.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03174, over 972641.09 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 20:31:06,577 INFO [train.py:715] (5/8) Epoch 13, batch 24000, loss[loss=0.1309, simple_loss=0.1838, pruned_loss=0.03896, over 4832.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03166, over 971814.51 frames.], batch size: 30, lr: 1.67e-04
2022-05-07 20:31:06,578 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 20:31:16,109 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01069, over 914524.00 frames.
2022-05-07 20:31:53,722 INFO [train.py:715] (5/8) Epoch 13, batch 24050, loss[loss=0.1731, simple_loss=0.2434, pruned_loss=0.05134, over 4884.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03179, over 971762.18 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:32:31,541 INFO [train.py:715] (5/8) Epoch 13, batch 24100, loss[loss=0.1402, simple_loss=0.2082, pruned_loss=0.03615, over 4839.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03142, over 972336.45 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:33:10,918 INFO [train.py:715] (5/8) Epoch 13, batch 24150, loss[loss=0.1604, simple_loss=0.2298, pruned_loss=0.04552, over 4906.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03151, over 971510.44 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:33:49,885 INFO [train.py:715] (5/8) Epoch 13, batch 24200, loss[loss=0.1099, simple_loss=0.1778, pruned_loss=0.02099, over 4773.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.0309, over 972077.74 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:34:28,087 INFO [train.py:715] (5/8) Epoch 13, batch 24250, loss[loss=0.1311, simple_loss=0.205, pruned_loss=0.02857, over 4837.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03077, over 972438.08 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:35:06,951 INFO [train.py:715] (5/8) Epoch 13, batch 24300, loss[loss=0.1421, simple_loss=0.2109, pruned_loss=0.03668, over 4838.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03087, over 972328.10 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:35:45,649 INFO [train.py:715] (5/8) Epoch 13, batch 24350, loss[loss=0.1456, simple_loss=0.2201, pruned_loss=0.03554, over 4959.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03053, over 972857.90 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:36:23,174 INFO [train.py:715] (5/8) Epoch 13, batch 24400, loss[loss=0.1022, simple_loss=0.1803, pruned_loss=0.01206, over 4983.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03055, over 972900.94 frames.], batch size: 28, lr: 1.67e-04
2022-05-07 20:37:01,583 INFO [train.py:715] (5/8) Epoch 13, batch 24450, loss[loss=0.131, simple_loss=0.2012, pruned_loss=0.03039, over 4898.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 972747.20 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 20:37:40,235 INFO [train.py:715] (5/8) Epoch 13, batch 24500, loss[loss=0.1621, simple_loss=0.2247, pruned_loss=0.0497, over 4697.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03075, over 972387.69 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:38:18,535 INFO [train.py:715] (5/8) Epoch 13, batch 24550, loss[loss=0.1236, simple_loss=0.2004, pruned_loss=0.02345, over 4930.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03108, over 972605.28 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:38:56,898 INFO [train.py:715] (5/8) Epoch 13, batch 24600, loss[loss=0.1182, simple_loss=0.209, pruned_loss=0.01365, over 4777.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03132, over 972833.91 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:39:36,088 INFO [train.py:715] (5/8) Epoch 13, batch 24650, loss[loss=0.1164, simple_loss=0.1876, pruned_loss=0.0226, over 4692.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03157, over 972684.68 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:40:14,987 INFO [train.py:715] (5/8) Epoch 13, batch 24700, loss[loss=0.1186, simple_loss=0.191, pruned_loss=0.02309, over 4684.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03165, over 971953.07 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:40:52,893 INFO [train.py:715] (5/8) Epoch 13, batch 24750, loss[loss=0.1381, simple_loss=0.2143, pruned_loss=0.031, over 4772.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.0311, over 971982.82 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:41:31,284 INFO [train.py:715] (5/8) Epoch 13, batch 24800, loss[loss=0.1486, simple_loss=0.2223, pruned_loss=0.03742, over 4937.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03154, over 972537.92 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 20:42:10,093 INFO [train.py:715] (5/8) Epoch 13, batch 24850, loss[loss=0.1421, simple_loss=0.2241, pruned_loss=0.03006, over 4814.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03137, over 971825.03 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 20:42:48,216 INFO [train.py:715] (5/8) Epoch 13, batch 24900, loss[loss=0.1658, simple_loss=0.2478, pruned_loss=0.04192, over 4898.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03073, over 971869.10 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 20:43:26,336 INFO [train.py:715] (5/8) Epoch 13, batch 24950, loss[loss=0.1498, simple_loss=0.2052, pruned_loss=0.04723, over 4969.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 972148.87 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:44:04,943 INFO [train.py:715] (5/8) Epoch 13, batch 25000, loss[loss=0.1236, simple_loss=0.1885, pruned_loss=0.02937, over 4826.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03142, over 971787.24 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 20:44:43,237 INFO [train.py:715] (5/8) Epoch 13, batch 25050, loss[loss=0.1409, simple_loss=0.2199, pruned_loss=0.031, over 4936.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03151, over 972490.13 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 20:45:20,925 INFO [train.py:715] (5/8) Epoch 13, batch 25100, loss[loss=0.1349, simple_loss=0.2101, pruned_loss=0.02987, over 4953.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.0311, over 972730.41 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 20:46:00,040 INFO [train.py:715] (5/8) Epoch 13, batch 25150, loss[loss=0.1551, simple_loss=0.2187, pruned_loss=0.04581, over 4840.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.031, over 972193.81 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 20:46:38,587 INFO [train.py:715] (5/8) Epoch 13, batch 25200, loss[loss=0.1275, simple_loss=0.1946, pruned_loss=0.03014, over 4836.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03092, over 972240.86 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 20:47:17,718 INFO [train.py:715] (5/8) Epoch 13, batch 25250, loss[loss=0.1572, simple_loss=0.2201, pruned_loss=0.04712, over 4971.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03132, over 972696.78 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:47:55,927 INFO [train.py:715] (5/8) Epoch 13, batch 25300, loss[loss=0.1137, simple_loss=0.1879, pruned_loss=0.01969, over 4756.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03182, over 971875.19 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 20:48:34,492 INFO [train.py:715] (5/8) Epoch 13, batch 25350, loss[loss=0.1347, simple_loss=0.2061, pruned_loss=0.03164, over 4917.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03152, over 972255.13 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 20:49:13,702 INFO [train.py:715] (5/8) Epoch 13, batch 25400, loss[loss=0.1183, simple_loss=0.1885, pruned_loss=0.02402, over 4811.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.0314, over 972349.01 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 20:49:51,566 INFO [train.py:715] (5/8) Epoch 13, batch 25450, loss[loss=0.1198, simple_loss=0.1982, pruned_loss=0.02067, over 4880.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03183, over 972176.85 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 20:50:30,629 INFO [train.py:715] (5/8) Epoch 13, batch 25500, loss[loss=0.1382, simple_loss=0.2102, pruned_loss=0.0331, over 4916.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03202, over 972523.90 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 20:51:09,202 INFO [train.py:715] (5/8) Epoch 13, batch 25550, loss[loss=0.1221, simple_loss=0.2002, pruned_loss=0.02199, over 4858.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03183, over 973051.95 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 20:51:47,746 INFO [train.py:715] (5/8) Epoch 13, batch 25600, loss[loss=0.1068, simple_loss=0.1753, pruned_loss=0.01917, over 4823.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03155, over 972819.51 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 20:52:25,799 INFO [train.py:715] (5/8) Epoch 13, batch 25650, loss[loss=0.1304, simple_loss=0.2014, pruned_loss=0.02972, over 4877.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.0314, over 973165.95 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 20:53:05,134 INFO [train.py:715] (5/8) Epoch 13, batch 25700, loss[loss=0.1288, simple_loss=0.2053, pruned_loss=0.02609, over 4971.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03151, over 973471.65 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 20:53:43,487 INFO [train.py:715] (5/8) Epoch 13, batch 25750, loss[loss=0.1547, simple_loss=0.2375, pruned_loss=0.03595, over 4885.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03181, over 973617.93 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 20:54:21,672 INFO [train.py:715] (5/8) Epoch 13, batch 25800, loss[loss=0.1259, simple_loss=0.2074, pruned_loss=0.02218, over 4848.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03178, over 973727.92 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 20:55:00,564 INFO [train.py:715] (5/8) Epoch 13, batch 25850, loss[loss=0.1361, simple_loss=0.2166, pruned_loss=0.02783, over 4994.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03141, over 973049.22 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 20:55:39,356 INFO [train.py:715] (5/8) Epoch 13, batch 25900, loss[loss=0.1174, simple_loss=0.1905, pruned_loss=0.02218, over 4858.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03097, over 973250.88 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 20:56:18,177 INFO [train.py:715] (5/8) Epoch 13, batch 25950, loss[loss=0.1288, simple_loss=0.199, pruned_loss=0.02935, over 4772.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03079, over 973089.69 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 20:56:57,181 INFO [train.py:715] (5/8) Epoch 13, batch 26000, loss[loss=0.1437, simple_loss=0.2172, pruned_loss=0.03516, over 4976.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.0308, over 972509.18 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 20:57:36,541 INFO [train.py:715] (5/8) Epoch 13, batch 26050, loss[loss=0.149, simple_loss=0.2212, pruned_loss=0.03834, over 4780.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03092, over 971505.25 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:58:15,737 INFO [train.py:715] (5/8) Epoch 13, batch 26100, loss[loss=0.1167, simple_loss=0.1857, pruned_loss=0.0238, over 4804.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03048, over 972074.47 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 20:58:54,121 INFO [train.py:715] (5/8) Epoch 13, batch 26150, loss[loss=0.119, simple_loss=0.1907, pruned_loss=0.02366, over 4905.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03081, over 971877.31 frames.], batch size: 22, lr: 1.66e-04
2022-05-07 20:59:33,345 INFO [train.py:715] (5/8) Epoch 13, batch 26200, loss[loss=0.1453, simple_loss=0.2144, pruned_loss=0.03814, over 4917.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.0314, over 971888.40 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:00:12,169 INFO [train.py:715] (5/8) Epoch 13, batch 26250, loss[loss=0.1334, simple_loss=0.2088, pruned_loss=0.02904, over 4771.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03047, over 971998.02 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:00:50,343 INFO [train.py:715] (5/8) Epoch 13, batch 26300, loss[loss=0.1344, simple_loss=0.2136, pruned_loss=0.02765, over 4981.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03109, over 972230.53 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:01:28,297 INFO [train.py:715] (5/8) Epoch 13, batch 26350, loss[loss=0.1361, simple_loss=0.2015, pruned_loss=0.03534, over 4842.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03135, over 972301.59 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 21:02:07,165 INFO [train.py:715] (5/8) Epoch 13, batch 26400, loss[loss=0.1397, simple_loss=0.2229, pruned_loss=0.02822, over 4816.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03091, over 972270.80 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:02:46,105 INFO [train.py:715] (5/8) Epoch 13, batch 26450, loss[loss=0.1232, simple_loss=0.1965, pruned_loss=0.02496, over 4796.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.0309, over 971823.06 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:03:24,276 INFO [train.py:715] (5/8) Epoch 13, batch 26500, loss[loss=0.1245, simple_loss=0.1947, pruned_loss=0.02712, over 4927.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03111, over 971685.58 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:04:03,397 INFO [train.py:715] (5/8) Epoch 13, batch 26550, loss[loss=0.1206, simple_loss=0.1952, pruned_loss=0.02304, over 4798.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03089, over 972242.49 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:04:41,837 INFO [train.py:715] (5/8) Epoch 13, batch 26600, loss[loss=0.1387, simple_loss=0.2131, pruned_loss=0.03217, over 4924.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03059, over 972725.76 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:05:20,065 INFO [train.py:715] (5/8) Epoch 13, batch 26650, loss[loss=0.1089, simple_loss=0.1793, pruned_loss=0.01921, over 4978.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.0304, over 972727.94 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:05:58,316 INFO [train.py:715] (5/8) Epoch 13, batch 26700, loss[loss=0.1079, simple_loss=0.1826, pruned_loss=0.01663, over 4762.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03007, over 972034.54 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:06:37,481 INFO [train.py:715] (5/8) Epoch 13, batch 26750, loss[loss=0.1328, simple_loss=0.2207, pruned_loss=0.02244, over 4968.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03035, over 973395.97 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:07:15,989 INFO [train.py:715] (5/8) Epoch 13, batch 26800, loss[loss=0.1318, simple_loss=0.2052, pruned_loss=0.02915, over 4922.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03033, over 973366.82 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:07:54,602 INFO [train.py:715] (5/8) Epoch 13, batch 26850, loss[loss=0.1335, simple_loss=0.2113, pruned_loss=0.02788, over 4762.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.0302, over 973157.27 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:08:33,347 INFO [train.py:715] (5/8) Epoch 13, batch 26900, loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03099, over 4867.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03029, over 973493.80 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 21:09:11,794 INFO [train.py:715] (5/8) Epoch 13, batch 26950, loss[loss=0.105, simple_loss=0.1795, pruned_loss=0.01529, over 4801.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 974272.75 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:09:50,377 INFO [train.py:715] (5/8) Epoch 13, batch 27000, loss[loss=0.124, simple_loss=0.1991, pruned_loss=0.0245, over 4749.00 frames.], tot_loss[loss=0.1354, simple_loss=0.21, pruned_loss=0.03035, over 973965.77 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:09:50,377 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 21:09:59,936 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01077, over 914524.00 frames.
2022-05-07 21:10:39,028 INFO [train.py:715] (5/8) Epoch 13, batch 27050, loss[loss=0.1408, simple_loss=0.2183, pruned_loss=0.03163, over 4921.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2101, pruned_loss=0.0306, over 973701.17 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:11:17,913 INFO [train.py:715] (5/8) Epoch 13, batch 27100, loss[loss=0.114, simple_loss=0.1843, pruned_loss=0.02184, over 4787.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03036, over 973233.85 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:11:57,149 INFO [train.py:715] (5/8) Epoch 13, batch 27150, loss[loss=0.1166, simple_loss=0.1858, pruned_loss=0.02369, over 4761.00 frames.], tot_loss[loss=0.135, simple_loss=0.2096, pruned_loss=0.03026, over 973988.99 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:12:36,110 INFO [train.py:715] (5/8) Epoch 13, batch 27200, loss[loss=0.148, simple_loss=0.2274, pruned_loss=0.03429, over 4994.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.0306, over 973274.09 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:13:14,911 INFO [train.py:715] (5/8) Epoch 13, batch 27250, loss[loss=0.1181, simple_loss=0.1933, pruned_loss=0.02146, over 4987.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.0306, over 973586.41 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 21:13:54,908 INFO [train.py:715] (5/8) Epoch 13, batch 27300, loss[loss=0.1675, simple_loss=0.235, pruned_loss=0.05002, over 4940.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2098, pruned_loss=0.03065, over 972591.07 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:14:33,864 INFO [train.py:715] (5/8) Epoch 13, batch 27350, loss[loss=0.1183, simple_loss=0.1855, pruned_loss=0.02557, over 4855.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2105, pruned_loss=0.03095, over 972490.42 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:15:11,632 INFO [train.py:715] (5/8) Epoch 13, batch 27400, loss[loss=0.1171, simple_loss=0.1943, pruned_loss=0.01989, over 4820.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03055, over 972746.52 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:15:49,743 INFO [train.py:715] (5/8) Epoch 13, batch 27450, loss[loss=0.162, simple_loss=0.2251, pruned_loss=0.04945, over 4863.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03093, over 972777.19 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 21:16:30,589 INFO [train.py:715] (5/8) Epoch 13, batch 27500, loss[loss=0.1395, simple_loss=0.2259, pruned_loss=0.0265, over 4862.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03152, over 972592.00 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 21:17:08,828 INFO [train.py:715] (5/8) Epoch 13, batch 27550, loss[loss=0.1512, simple_loss=0.2232, pruned_loss=0.03959, over 4782.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.0315, over 971255.09 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:17:46,777 INFO [train.py:715] (5/8) Epoch 13, batch 27600, loss[loss=0.1818, simple_loss=0.2407, pruned_loss=0.0614, over 4941.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.0316, over 971702.85 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:18:25,956 INFO [train.py:715] (5/8) Epoch 13, batch 27650, loss[loss=0.1607, simple_loss=0.2317, pruned_loss=0.0448, over 4987.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03201, over 972693.07 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:19:03,876 INFO [train.py:715] (5/8) Epoch 13, batch 27700, loss[loss=0.1269, simple_loss=0.1899, pruned_loss=0.03193, over 4793.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03182, over 972409.51 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:19:42,880 INFO [train.py:715] (5/8) Epoch 13, batch 27750, loss[loss=0.1375, simple_loss=0.2185, pruned_loss=0.02822, over 4819.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03114, over 973072.04 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:20:21,393 INFO [train.py:715] (5/8) Epoch 13, batch 27800, loss[loss=0.115, simple_loss=0.1786, pruned_loss=0.02568, over 4766.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03127, over 972927.72 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:21:00,119 INFO [train.py:715] (5/8) Epoch 13, batch 27850, loss[loss=0.1231, simple_loss=0.2065, pruned_loss=0.0199, over 4765.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03119, over 972508.72 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:21:38,313 INFO [train.py:715] (5/8) Epoch 13, batch 27900, loss[loss=0.1538, simple_loss=0.2146, pruned_loss=0.0465, over 4740.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03076, over 971729.47 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:22:16,097 INFO [train.py:715] (5/8) Epoch 13, batch 27950, loss[loss=0.1337, simple_loss=0.2229, pruned_loss=0.02226, over 4957.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03078, over 972110.74 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:22:55,052 INFO [train.py:715] (5/8) Epoch 13, batch 28000, loss[loss=0.1248, simple_loss=0.2018, pruned_loss=0.02393, over 4802.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02998, over 972430.00 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:23:33,524 INFO [train.py:715] (5/8) Epoch 13, batch 28050, loss[loss=0.1319, simple_loss=0.2075, pruned_loss=0.02819, over 4789.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03021, over 971930.88 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:24:11,553 INFO [train.py:715] (5/8) Epoch 13, batch 28100, loss[loss=0.1539, simple_loss=0.23, pruned_loss=0.03889, over 4971.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03053, over 971748.88 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:24:49,598 INFO [train.py:715] (5/8) Epoch 13, batch 28150, loss[loss=0.1397, simple_loss=0.2101, pruned_loss=0.03467, over 4940.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.0304, over 972037.92 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:25:28,816 INFO [train.py:715] (5/8) Epoch 13, batch 28200, loss[loss=0.1416, simple_loss=0.2105, pruned_loss=0.03637, over 4963.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03047, over 972123.02 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:26:06,611 INFO [train.py:715] (5/8) Epoch 13, batch 28250, loss[loss=0.1417, simple_loss=0.2219, pruned_loss=0.03074, over 4821.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03089, over 970932.17 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:26:44,753 INFO [train.py:715] (5/8) Epoch 13, batch 28300, loss[loss=0.1535, simple_loss=0.228, pruned_loss=0.03948, over 4745.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03094, over 971532.80 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:27:23,461 INFO [train.py:715] (5/8) Epoch 13, batch 28350, loss[loss=0.157, simple_loss=0.2241, pruned_loss=0.04494, over 4845.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03091, over 972484.30 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:28:01,608 INFO [train.py:715] (5/8) Epoch 13, batch 28400, loss[loss=0.1086, simple_loss=0.1755, pruned_loss=0.02086, over 4693.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03056, over 971650.23 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:28:40,046 INFO [train.py:715] (5/8) Epoch 13, batch 28450, loss[loss=0.106, simple_loss=0.1776, pruned_loss=0.0172, over 4801.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03007, over 972769.71 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:29:18,385 INFO [train.py:715] (5/8) Epoch 13, batch 28500, loss[loss=0.165, simple_loss=0.2399, pruned_loss=0.04508, over 4875.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03062, over 972107.67 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:29:57,060 INFO [train.py:715] (5/8) Epoch 13, batch 28550, loss[loss=0.1291, simple_loss=0.1983, pruned_loss=0.03, over 4849.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03104, over 972680.44 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:30:35,260 INFO [train.py:715] (5/8) Epoch 13, batch 28600, loss[loss=0.1471, simple_loss=0.22, pruned_loss=0.03711, over 4786.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03092, over 972562.02 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:31:13,616 INFO [train.py:715] (5/8) Epoch 13, batch 28650, loss[loss=0.1286, simple_loss=0.2098, pruned_loss=0.0237, over 4987.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03091, over 972379.47 frames.], batch size: 28, lr: 1.66e-04
2022-05-07 21:31:52,262 INFO [train.py:715] (5/8) Epoch 13, batch 28700, loss[loss=0.1198, simple_loss=0.1915, pruned_loss=0.02405, over 4883.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.0309, over 973063.30 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:32:30,333 INFO [train.py:715] (5/8) Epoch 13, batch 28750, loss[loss=0.1668, simple_loss=0.2343, pruned_loss=0.04968, over 4945.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03138, over 973263.15 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:33:08,636 INFO [train.py:715] (5/8) Epoch 13, batch 28800, loss[loss=0.1545, simple_loss=0.2257, pruned_loss=0.04167, over 4777.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03072, over 973179.64 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:33:47,846 INFO [train.py:715] (5/8) Epoch 13, batch 28850, loss[loss=0.147, simple_loss=0.2157, pruned_loss=0.03916, over 4908.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03054, over 973216.57 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:34:26,365 INFO [train.py:715] (5/8) Epoch 13, batch 28900, loss[loss=0.134, simple_loss=0.2068, pruned_loss=0.0306, over 4977.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03102, over 972400.11 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:35:04,279 INFO [train.py:715] (5/8) Epoch 13, batch 28950, loss[loss=0.1183, simple_loss=0.1949, pruned_loss=0.02091, over 4860.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03115, over 971769.88 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 21:35:42,444 INFO [train.py:715] (5/8) Epoch 13, batch 29000, loss[loss=0.157, simple_loss=0.2339, pruned_loss=0.04009, over 4864.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03137, over 971928.88 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 21:36:21,625 INFO [train.py:715] (5/8) Epoch 13, batch 29050, loss[loss=0.1338, simple_loss=0.2151, pruned_loss=0.02627, over 4817.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03141, over 972691.24 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 21:37:00,158 INFO [train.py:715] (5/8) Epoch 13, batch 29100, loss[loss=0.1337, simple_loss=0.2018, pruned_loss=0.03277, over 4965.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03069, over 972304.42 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:37:38,204 INFO [train.py:715] (5/8) Epoch 13, batch 29150, loss[loss=0.1507, simple_loss=0.2202, pruned_loss=0.04055, over 4852.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03112, over 971865.51 frames.], batch size: 34, lr: 1.66e-04
2022-05-07 21:38:16,963 INFO [train.py:715] (5/8) Epoch 13, batch 29200, loss[loss=0.152, simple_loss=0.2104, pruned_loss=0.04683, over 4762.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03141, over 972087.34 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:38:55,210 INFO [train.py:715] (5/8) Epoch 13, batch 29250, loss[loss=0.1084, simple_loss=0.1789, pruned_loss=0.01893, over 4903.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03133, over 972414.89 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:39:34,054 INFO [train.py:715] (5/8) Epoch 13, batch 29300, loss[loss=0.12, simple_loss=0.1918, pruned_loss=0.02408, over 4932.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.0316, over 973154.94 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:40:12,800 INFO [train.py:715] (5/8) Epoch 13, batch 29350, loss[loss=0.1331, simple_loss=0.2087, pruned_loss=0.02871, over 4940.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03161, over 973277.97 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:40:51,675 INFO [train.py:715] (5/8) Epoch 13, batch 29400, loss[loss=0.1251, simple_loss=0.1884, pruned_loss=0.03085, over 4849.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03215, over 973985.24 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:41:29,698 INFO [train.py:715] (5/8) Epoch 13, batch 29450, loss[loss=0.133, simple_loss=0.211, pruned_loss=0.02752, over 4819.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03181, over 972629.54 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:42:08,738 INFO [train.py:715] (5/8) Epoch 13, batch 29500, loss[loss=0.121, simple_loss=0.1962, pruned_loss=0.02288, over 4767.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03144, over 973122.26 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:42:47,372 INFO [train.py:715] (5/8) Epoch 13, batch 29550, loss[loss=0.1218, simple_loss=0.1985, pruned_loss=0.02254, over 4880.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03102, over 973064.95 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:43:25,735 INFO [train.py:715] (5/8) Epoch 13, batch 29600, loss[loss=0.1458, simple_loss=0.228, pruned_loss=0.03179, over 4790.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03091, over 972340.06 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:44:03,482 INFO [train.py:715] (5/8) Epoch 13, batch 29650, loss[loss=0.1457, simple_loss=0.2151, pruned_loss=0.03817, over 4837.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03145, over 972500.40 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:44:41,767 INFO [train.py:715] (5/8) Epoch 13, batch 29700, loss[loss=0.1548, simple_loss=0.2306, pruned_loss=0.03953, over 4850.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03163, over 972612.54 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 21:45:20,123 INFO [train.py:715] (5/8) Epoch 13, batch 29750, loss[loss=0.1255, simple_loss=0.2055, pruned_loss=0.0227, over 4894.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 972349.12 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:45:59,496 INFO [train.py:715] (5/8) Epoch 13, batch 29800, loss[loss=0.1239, simple_loss=0.1913, pruned_loss=0.02821, over 4825.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03132, over 972321.91 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 21:46:38,729 INFO [train.py:715] (5/8) Epoch 13, batch 29850, loss[loss=0.1458, simple_loss=0.2118, pruned_loss=0.03989, over 4767.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03129, over 972355.29 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:47:18,338 INFO [train.py:715] (5/8) Epoch 13, batch 29900, loss[loss=0.1264, simple_loss=0.2062, pruned_loss=0.02332, over 4914.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2087, pruned_loss=0.03123, over 972022.18 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:47:57,734 INFO [train.py:715] (5/8) Epoch 13, batch 29950, loss[loss=0.115, simple_loss=0.1857, pruned_loss=0.02213, over 4906.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03091, over 971448.57 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:48:36,364 INFO [train.py:715] (5/8) Epoch 13, batch 30000, loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02874, over 4770.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03075, over 971503.33 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 21:48:36,365 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 21:48:45,862 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 21:49:25,287 INFO [train.py:715] (5/8) Epoch 13, batch 30050, loss[loss=0.1101, simple_loss=0.1823, pruned_loss=0.01896, over 4784.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03065, over 972278.17 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:50:05,095 INFO [train.py:715] (5/8) Epoch 13, batch 30100, loss[loss=0.1419, simple_loss=0.213, pruned_loss=0.03534, over 4922.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03085, over 971870.46 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:50:44,563 INFO [train.py:715] (5/8) Epoch 13, batch 30150, loss[loss=0.1414, simple_loss=0.2229, pruned_loss=0.02995, over 4812.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03052, over 971532.77 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 21:51:23,145 INFO [train.py:715] (5/8) Epoch 13, batch 30200, loss[loss=0.1356, simple_loss=0.215, pruned_loss=0.02807, over 4833.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03129, over 972063.70 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:52:02,984 INFO [train.py:715] (5/8) Epoch 13, batch 30250, loss[loss=0.1465, simple_loss=0.2159, pruned_loss=0.03854, over 4968.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03095, over 972503.52 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:52:42,784 INFO [train.py:715] (5/8) Epoch 13, batch 30300, loss[loss=0.1748, simple_loss=0.2493, pruned_loss=0.05015, over 4975.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.0311, over 973520.67 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:53:22,304 INFO [train.py:715] (5/8) Epoch 13, batch 30350, loss[loss=0.1262, simple_loss=0.1945, pruned_loss=0.02893, over 4837.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.0314, over 973085.15 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 21:54:01,877 INFO [train.py:715] (5/8) Epoch 13, batch 30400, loss[loss=0.1068, simple_loss=0.1907, pruned_loss=0.01146, over 4758.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03062, over 973961.59 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:54:42,498 INFO [train.py:715] (5/8) Epoch 13, batch 30450, loss[loss=0.1545, simple_loss=0.2063, pruned_loss=0.05138, over 4950.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.0306, over 973556.71 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:55:22,612 INFO [train.py:715] (5/8) Epoch 13, batch 30500, loss[loss=0.1369, simple_loss=0.2064, pruned_loss=0.0337, over 4830.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03079, over 973215.52 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:56:02,391 INFO [train.py:715] (5/8) Epoch 13, batch 30550, loss[loss=0.1409, simple_loss=0.2198, pruned_loss=0.03103, over 4883.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03095, over 973674.63 frames.], batch size: 22, lr: 1.66e-04
2022-05-07 21:56:43,836 INFO [train.py:715] (5/8) Epoch 13, batch 30600, loss[loss=0.1337, simple_loss=0.2103, pruned_loss=0.02859, over 4934.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03115, over 972430.05 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:57:24,953 INFO [train.py:715] (5/8) Epoch 13, batch 30650, loss[loss=0.102, simple_loss=0.1731, pruned_loss=0.01544, over 4640.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03105, over 973054.69 frames.], batch size: 13, lr: 1.65e-04
2022-05-07 21:58:05,361 INFO [train.py:715] (5/8) Epoch 13, batch 30700, loss[loss=0.1403, simple_loss=0.2205, pruned_loss=0.03004, over 4987.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03065, over 973525.72 frames.], batch size: 20, lr: 1.65e-04
2022-05-07 21:58:45,826 INFO [train.py:715] (5/8) Epoch 13, batch 30750, loss[loss=0.1368, simple_loss=0.2074, pruned_loss=0.03313, over 4860.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 973106.91 frames.], batch size: 20, lr: 1.65e-04
2022-05-07 21:59:26,818 INFO [train.py:715] (5/8) Epoch 13, batch 30800, loss[loss=0.134, simple_loss=0.2109, pruned_loss=0.02857, over 4851.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03078, over 973016.60 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:00:07,577 INFO [train.py:715] (5/8) Epoch 13, batch 30850, loss[loss=0.1397, simple_loss=0.1998, pruned_loss=0.03974, over 4771.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03077, over 972601.27 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:00:48,210 INFO [train.py:715] (5/8) Epoch 13, batch 30900, loss[loss=0.1459, simple_loss=0.2334, pruned_loss=0.02919, over 4845.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.0311, over 972526.50 frames.], batch size: 20, lr: 1.65e-04
2022-05-07 22:01:29,255 INFO [train.py:715] (5/8) Epoch 13, batch 30950, loss[loss=0.1508, simple_loss=0.232, pruned_loss=0.03473, over 4797.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03104, over 971967.65 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:02:09,962 INFO [train.py:715] (5/8) Epoch 13, batch 31000, loss[loss=0.1557, simple_loss=0.2358, pruned_loss=0.03783, over 4905.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03117, over 972142.21 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:02:50,144 INFO [train.py:715] (5/8) Epoch 13, batch 31050, loss[loss=0.1459, simple_loss=0.2358, pruned_loss=0.02799, over 4988.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03114, over 972434.65 frames.], batch size: 28, lr: 1.65e-04
2022-05-07 22:03:30,713 INFO [train.py:715] (5/8) Epoch 13, batch 31100, loss[loss=0.1725, simple_loss=0.244, pruned_loss=0.05051, over 4973.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03137, over 972998.71 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:04:11,682 INFO [train.py:715] (5/8) Epoch 13, batch 31150, loss[loss=0.1312, simple_loss=0.2232, pruned_loss=0.01962, over 4780.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03103, over 972401.46 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:04:52,785 INFO [train.py:715] (5/8) Epoch 13, batch 31200, loss[loss=0.1349, simple_loss=0.2059, pruned_loss=0.03197, over 4818.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03083, over 972245.40 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:05:32,914 INFO [train.py:715] (5/8) Epoch 13, batch 31250, loss[loss=0.121, simple_loss=0.1981, pruned_loss=0.02197, over 4809.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03111, over 971521.79 frames.], batch size: 13, lr: 1.65e-04
2022-05-07 22:06:13,245 INFO [train.py:715] (5/8) Epoch 13, batch 31300, loss[loss=0.09957, simple_loss=0.1636, pruned_loss=0.01777, over 4788.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03135, over 971735.07 frames.], batch size: 12, lr: 1.65e-04
2022-05-07 22:06:53,513 INFO [train.py:715] (5/8) Epoch 13, batch 31350, loss[loss=0.1294, simple_loss=0.2053, pruned_loss=0.02671, over 4983.00 frames.], tot_loss[loss=0.137, simple_loss=0.2098, pruned_loss=0.03207, over 972728.33 frames.], batch size: 31, lr: 1.65e-04
2022-05-07 22:07:33,261 INFO [train.py:715] (5/8) Epoch 13, batch 31400, loss[loss=0.1545, simple_loss=0.2273, pruned_loss=0.04088, over 4927.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03204, over 972901.81 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:08:13,738 INFO [train.py:715] (5/8) Epoch 13, batch 31450, loss[loss=0.1406, simple_loss=0.2163, pruned_loss=0.0324, over 4830.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03198, over 973315.45 frames.], batch size: 26, lr: 1.65e-04
2022-05-07 22:08:54,100 INFO [train.py:715] (5/8) Epoch 13, batch 31500, loss[loss=0.1316, simple_loss=0.198, pruned_loss=0.03264, over 4830.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03181, over 972653.44 frames.], batch size: 30, lr: 1.65e-04
2022-05-07 22:09:33,924 INFO [train.py:715] (5/8) Epoch 13, batch 31550, loss[loss=0.1395, simple_loss=0.2109, pruned_loss=0.03406, over 4893.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03158, over 972493.92 frames.], batch size: 22, lr: 1.65e-04
2022-05-07 22:10:14,441 INFO [train.py:715] (5/8) Epoch 13, batch 31600, loss[loss=0.1364, simple_loss=0.2152, pruned_loss=0.02881, over 4941.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 972245.38 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:10:55,014 INFO [train.py:715] (5/8) Epoch 13, batch 31650, loss[loss=0.1314, simple_loss=0.2103, pruned_loss=0.02625, over 4755.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03121, over 971923.71 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:11:35,404 INFO [train.py:715] (5/8) Epoch 13, batch 31700, loss[loss=0.1188, simple_loss=0.1941, pruned_loss=0.02172, over 4822.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 972175.50 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:12:15,837 INFO [train.py:715] (5/8) Epoch 13, batch 31750, loss[loss=0.1634, simple_loss=0.238, pruned_loss=0.04438, over 4917.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03092, over 972629.60 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:12:56,364 INFO [train.py:715] (5/8) Epoch 13, batch 31800, loss[loss=0.1079, simple_loss=0.1847, pruned_loss=0.01559, over 4769.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03082, over 972077.83 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:13:37,272 INFO [train.py:715] (5/8) Epoch 13, batch 31850, loss[loss=0.122, simple_loss=0.2026, pruned_loss=0.02068, over 4693.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03055, over 971541.58 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:14:18,121 INFO [train.py:715] (5/8) Epoch 13, batch 31900, loss[loss=0.1385, simple_loss=0.2192, pruned_loss=0.0289, over 4905.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03088, over 971976.53 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:14:59,145 INFO [train.py:715] (5/8) Epoch 13, batch 31950, loss[loss=0.09986, simple_loss=0.1738, pruned_loss=0.01295, over 4876.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 971959.26 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:15:39,539 INFO [train.py:715] (5/8) Epoch 13, batch 32000, loss[loss=0.09422, simple_loss=0.1701, pruned_loss=0.009188, over 4927.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03034, over 971474.58 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:16:20,151 INFO [train.py:715] (5/8) Epoch 13, batch 32050, loss[loss=0.1376, simple_loss=0.2063, pruned_loss=0.03443, over 4905.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03029, over 971895.90 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:17:00,690 INFO [train.py:715] (5/8) Epoch 13, batch 32100, loss[loss=0.1353, simple_loss=0.1983, pruned_loss=0.03609, over 4861.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03023, over 971332.20 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:17:41,703 INFO [train.py:715] (5/8) Epoch 13, batch 32150, loss[loss=0.1359, simple_loss=0.2089, pruned_loss=0.03141, over 4690.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03079, over 972086.71 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:18:22,394 INFO [train.py:715] (5/8) Epoch 13, batch 32200, loss[loss=0.1148, simple_loss=0.1855, pruned_loss=0.02205, over 4757.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03069, over 971980.37 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:19:03,050 INFO [train.py:715] (5/8) Epoch 13, batch 32250, loss[loss=0.1165, simple_loss=0.1976, pruned_loss=0.01772, over 4758.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03099, over 971285.22 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:19:43,879 INFO [train.py:715] (5/8) Epoch 13, batch 32300, loss[loss=0.1201, simple_loss=0.1942, pruned_loss=0.02302, over 4776.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03078, over 971708.19 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:20:24,947 INFO [train.py:715] (5/8) Epoch 13, batch 32350, loss[loss=0.1218, simple_loss=0.1953, pruned_loss=0.02412, over 4756.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03091, over 972800.89 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:21:06,368 INFO [train.py:715] (5/8) Epoch 13, batch 32400, loss[loss=0.1205, simple_loss=0.1934, pruned_loss=0.02379, over 4792.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03093, over 972637.02 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:21:47,424 INFO [train.py:715] (5/8) Epoch 13, batch 32450, loss[loss=0.1407, simple_loss=0.208, pruned_loss=0.03674, over 4896.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.0308, over 972661.80 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:22:28,211 INFO [train.py:715] (5/8) Epoch 13, batch 32500, loss[loss=0.1238, simple_loss=0.204, pruned_loss=0.02177, over 4797.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03031, over 972482.98 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:23:09,251 INFO [train.py:715] (5/8) Epoch 13, batch 32550, loss[loss=0.1659, simple_loss=0.2404, pruned_loss=0.04565, over 4689.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03052, over 972241.50 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:23:49,649 INFO [train.py:715] (5/8) Epoch 13, batch 32600, loss[loss=0.1491, simple_loss=0.2192, pruned_loss=0.03943, over 4817.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.0308, over 971863.63 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:24:29,999 INFO [train.py:715] (5/8) Epoch 13, batch 32650, loss[loss=0.1299, simple_loss=0.2104, pruned_loss=0.0247, over 4950.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 972938.46 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:25:10,588 INFO [train.py:715] (5/8) Epoch 13, batch 32700, loss[loss=0.1391, simple_loss=0.2138, pruned_loss=0.03221, over 4803.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03171, over 973276.21 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:25:50,910 INFO [train.py:715] (5/8) Epoch 13, batch 32750, loss[loss=0.1382, simple_loss=0.2215, pruned_loss=0.02747, over 4803.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03118, over 972457.84 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:26:31,935 INFO [train.py:715] (5/8) Epoch 13, batch 32800, loss[loss=0.1682, simple_loss=0.2275, pruned_loss=0.05446, over 4949.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03109, over 972428.69 frames.], batch size: 35, lr: 1.65e-04
2022-05-07 22:27:12,668 INFO [train.py:715] (5/8) Epoch 13, batch 32850, loss[loss=0.1508, simple_loss=0.2178, pruned_loss=0.04191, over 4838.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03123, over 972176.12 frames.], batch size: 30, lr: 1.65e-04
2022-05-07 22:27:53,751 INFO [train.py:715] (5/8) Epoch 13, batch 32900, loss[loss=0.1378, simple_loss=0.2183, pruned_loss=0.02867, over 4961.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03154, over 972025.99 frames.], batch size: 40, lr: 1.65e-04
2022-05-07 22:28:33,954 INFO [train.py:715] (5/8) Epoch 13, batch 32950, loss[loss=0.1466, simple_loss=0.2273, pruned_loss=0.033, over 4971.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03182, over 972172.56 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:29:14,629 INFO [train.py:715] (5/8) Epoch 13, batch 33000, loss[loss=0.1208, simple_loss=0.1929, pruned_loss=0.02439, over 4948.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03188, over 971955.46 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:29:14,629 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 22:29:24,503 INFO [train.py:742] (5/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1892, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 22:30:05,557 INFO [train.py:715] (5/8) Epoch 13, batch 33050, loss[loss=0.138, simple_loss=0.2141, pruned_loss=0.03097, over 4782.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2111, pruned_loss=0.03162, over 971881.06 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:30:45,210 INFO [train.py:715] (5/8) Epoch 13, batch 33100, loss[loss=0.1421, simple_loss=0.2235, pruned_loss=0.03038, over 4936.00 frames.], tot_loss[loss=0.1368, simple_loss=0.211, pruned_loss=0.03132, over 973315.99 frames.], batch size: 29, lr: 1.65e-04
2022-05-07 22:31:25,146 INFO [train.py:715] (5/8) Epoch 13, batch 33150, loss[loss=0.1454, simple_loss=0.2341, pruned_loss=0.02839, over 4896.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2114, pruned_loss=0.03161, over 972578.20 frames.], batch size: 22, lr: 1.65e-04
2022-05-07 22:32:05,572 INFO [train.py:715] (5/8) Epoch 13, batch 33200, loss[loss=0.1407, simple_loss=0.2146, pruned_loss=0.03334, over 4741.00 frames.], tot_loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03151, over 972533.93 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:32:46,036 INFO [train.py:715] (5/8) Epoch 13, batch 33250, loss[loss=0.1252, simple_loss=0.1936, pruned_loss=0.02846, over 4987.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03179, over 972797.39 frames.], batch size: 28, lr: 1.65e-04
2022-05-07 22:33:26,588 INFO [train.py:715] (5/8) Epoch 13, batch 33300, loss[loss=0.1213, simple_loss=0.1918, pruned_loss=0.02537, over 4826.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2112, pruned_loss=0.03173, over 972133.42 frames.], batch size: 27, lr: 1.65e-04
2022-05-07 22:34:07,015 INFO [train.py:715] (5/8) Epoch 13, batch 33350, loss[loss=0.1266, simple_loss=0.2105, pruned_loss=0.02135, over 4939.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03131, over 972451.15 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:34:47,633 INFO [train.py:715] (5/8) Epoch 13, batch 33400, loss[loss=0.1124, simple_loss=0.1964, pruned_loss=0.01422, over 4759.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03081, over 972135.15 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:35:28,236 INFO [train.py:715] (5/8) Epoch 13, batch 33450, loss[loss=0.121, simple_loss=0.1997, pruned_loss=0.0211, over 4895.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03085, over 971607.96 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:36:08,957 INFO [train.py:715] (5/8) Epoch 13, batch 33500, loss[loss=0.129, simple_loss=0.1973, pruned_loss=0.03033, over 4863.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.0305, over 971328.20 frames.], batch size: 30, lr: 1.65e-04
2022-05-07 22:36:49,608 INFO [train.py:715] (5/8) Epoch 13, batch 33550, loss[loss=0.1259, simple_loss=0.2032, pruned_loss=0.02435, over 4785.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03028, over 971861.19 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:37:30,304 INFO [train.py:715] (5/8) Epoch 13, batch 33600, loss[loss=0.1446, simple_loss=0.2076, pruned_loss=0.04081, over 4966.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 972064.23 frames.], batch size: 35, lr: 1.65e-04
2022-05-07 22:38:10,829 INFO [train.py:715] (5/8) Epoch 13, batch 33650, loss[loss=0.1414, simple_loss=0.219, pruned_loss=0.03195, over 4756.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03064, over 972295.75 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:38:51,062 INFO [train.py:715] (5/8) Epoch 13, batch 33700, loss[loss=0.1196, simple_loss=0.1894, pruned_loss=0.0249, over 4926.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03015, over 972623.56 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:39:32,033 INFO [train.py:715] (5/8) Epoch 13, batch 33750, loss[loss=0.1433, simple_loss=0.2073, pruned_loss=0.03962, over 4854.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03062, over 973106.51 frames.], batch size: 30, lr: 1.65e-04
2022-05-07 22:40:12,827 INFO [train.py:715] (5/8) Epoch 13, batch 33800, loss[loss=0.1652, simple_loss=0.2297, pruned_loss=0.05036, over 4873.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03075, over 972804.47 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:40:53,572 INFO [train.py:715] (5/8) Epoch 13, batch 33850, loss[loss=0.171, simple_loss=0.2376, pruned_loss=0.05217, over 4773.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03085, over 971940.05 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:41:34,020 INFO [train.py:715] (5/8) Epoch 13, batch 33900, loss[loss=0.1153, simple_loss=0.1845, pruned_loss=0.02306, over 4774.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03065, over 971270.74 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:42:15,282 INFO [train.py:715] (5/8) Epoch 13, batch 33950, loss[loss=0.1174, simple_loss=0.1954, pruned_loss=0.01971, over 4935.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03072, over 970556.48 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:42:56,291 INFO [train.py:715] (5/8) Epoch 13, batch 34000, loss[loss=0.1428, simple_loss=0.2112, pruned_loss=0.03717, over 4816.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03086, over 970898.08 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:43:36,859 INFO [train.py:715] (5/8) Epoch 13, batch 34050, loss[loss=0.1114, simple_loss=0.1954, pruned_loss=0.01374, over 4806.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03093, over 970295.75 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:44:17,681 INFO [train.py:715] (5/8) Epoch 13, batch 34100, loss[loss=0.121, simple_loss=0.1922, pruned_loss=0.02486, over 4876.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03117, over 970091.49 frames.], batch size: 22, lr: 1.65e-04
2022-05-07 22:44:57,554 INFO [train.py:715] (5/8) Epoch 13, batch 34150, loss[loss=0.1355, simple_loss=0.205, pruned_loss=0.03304, over 4926.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03114, over 971092.63 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:45:38,244 INFO [train.py:715] (5/8) Epoch 13, batch 34200, loss[loss=0.1442, simple_loss=0.2149, pruned_loss=0.03677, over 4952.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03078, over 972006.62 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:46:18,603 INFO [train.py:715] (5/8) Epoch 13, batch 34250, loss[loss=0.1253, simple_loss=0.2006, pruned_loss=0.02506, over 4912.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 972236.22 frames.], batch size: 29, lr: 1.65e-04
2022-05-07 22:46:59,525 INFO [train.py:715] (5/8) Epoch 13, batch 34300, loss[loss=0.1762, simple_loss=0.2401, pruned_loss=0.05614, over 4875.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.0307, over 972918.63 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:47:39,593 INFO [train.py:715] (5/8) Epoch 13, batch 34350, loss[loss=0.1411, simple_loss=0.2155, pruned_loss=0.03333, over 4838.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02983, over 972563.99 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:48:20,188 INFO [train.py:715] (5/8) Epoch 13, batch 34400, loss[loss=0.1305, simple_loss=0.2154, pruned_loss=0.02276, over 4943.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03009, over 973068.63 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:49:01,283 INFO [train.py:715] (5/8) Epoch 13, batch 34450, loss[loss=0.1305, simple_loss=0.2105, pruned_loss=0.02521, over 4971.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.0301, over 972920.27 frames.], batch size: 28, lr: 1.65e-04
2022-05-07 22:49:41,686 INFO [train.py:715] (5/8) Epoch 13, batch 34500, loss[loss=0.1623, simple_loss=0.2255, pruned_loss=0.04951, over 4749.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03092, over 972943.86 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:50:21,496 INFO [train.py:715] (5/8) Epoch 13, batch 34550, loss[loss=0.1264, simple_loss=0.1994, pruned_loss=0.02675, over 4778.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03086, over 972347.34 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:51:01,502 INFO [train.py:715] (5/8) Epoch 13, batch 34600, loss[loss=0.1219, simple_loss=0.1902, pruned_loss=0.02682, over 4973.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03092, over 971887.66 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:51:40,868 INFO [train.py:715] (5/8) Epoch 13, batch 34650, loss[loss=0.1263, simple_loss=0.2059, pruned_loss=0.02331, over 4856.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.0313, over 971806.27 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:52:20,404 INFO [train.py:715] (5/8) Epoch 13, batch 34700, loss[loss=0.1108, simple_loss=0.1782, pruned_loss=0.02173, over 4988.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03107, over 972378.49 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:52:59,360 INFO [train.py:715] (5/8) Epoch 13, batch 34750, loss[loss=0.1381, simple_loss=0.2052, pruned_loss=0.03554, over 4828.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03113, over 972747.36 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:53:36,106 INFO [train.py:715] (5/8) Epoch 13, batch 34800, loss[loss=0.1229, simple_loss=0.1927, pruned_loss=0.02657, over 4929.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03128, over 972608.04 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:54:25,047 INFO [train.py:715] (5/8) Epoch 14, batch 0, loss[loss=0.1307, simple_loss=0.1985, pruned_loss=0.03144, over 4901.00 frames.], tot_loss[loss=0.1307, simple_loss=0.1985, pruned_loss=0.03144, over 4901.00 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 22:55:04,014 INFO [train.py:715] (5/8) Epoch 14, batch 50, loss[loss=0.1439, simple_loss=0.2119, pruned_loss=0.03798, over 4834.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.0301, over 218761.00 frames.], batch size: 30, lr: 1.59e-04
2022-05-07 22:55:42,421 INFO [train.py:715] (5/8) Epoch 14, batch 100, loss[loss=0.1398, simple_loss=0.2181, pruned_loss=0.03073, over 4747.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03117, over 385434.16 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 22:56:21,302 INFO [train.py:715] (5/8) Epoch 14, batch 150, loss[loss=0.167, simple_loss=0.2254, pruned_loss=0.05427, over 4759.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03134, over 515183.55 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 22:56:59,875 INFO [train.py:715] (5/8) Epoch 14, batch 200, loss[loss=0.1446, simple_loss=0.2174, pruned_loss=0.03594, over 4788.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03052, over 616814.19 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 22:57:38,468 INFO [train.py:715] (5/8) Epoch 14, batch 250, loss[loss=0.1766, simple_loss=0.2473, pruned_loss=0.05295, over 4961.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 694909.63 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 22:58:17,249 INFO [train.py:715] (5/8) Epoch 14, batch 300, loss[loss=0.1844, simple_loss=0.27, pruned_loss=0.04937, over 4901.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03141, over 757044.41 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 22:58:56,806 INFO [train.py:715] (5/8) Epoch 14, batch 350, loss[loss=0.1238, simple_loss=0.1986, pruned_loss=0.02444, over 4908.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03058, over 805209.68 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 22:59:35,349 INFO [train.py:715] (5/8) Epoch 14, batch 400, loss[loss=0.1648, simple_loss=0.2375, pruned_loss=0.04602, over 4784.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03166, over 841523.99 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:00:14,780 INFO [train.py:715] (5/8) Epoch 14, batch 450, loss[loss=0.1253, simple_loss=0.1999, pruned_loss=0.02538, over 4902.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03085, over 870374.02 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:00:54,066 INFO [train.py:715] (5/8) Epoch 14, batch 500, loss[loss=0.1132, simple_loss=0.1775, pruned_loss=0.02448, over 4783.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.0309, over 893518.37 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:01:33,692 INFO [train.py:715] (5/8) Epoch 14, batch 550, loss[loss=0.1394, simple_loss=0.2072, pruned_loss=0.03576, over 4860.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.0312, over 910711.77 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:02:12,466 INFO [train.py:715] (5/8) Epoch 14, batch 600, loss[loss=0.1265, simple_loss=0.2059, pruned_loss=0.02362, over 4862.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03173, over 924194.08 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:02:51,129 INFO [train.py:715] (5/8) Epoch 14, batch 650, loss[loss=0.1354, simple_loss=0.2268, pruned_loss=0.02199, over 4923.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03157, over 935504.45 frames.], batch size: 29, lr: 1.59e-04
2022-05-07 23:03:32,629 INFO [train.py:715] (5/8) Epoch 14, batch 700, loss[loss=0.1343, simple_loss=0.2134, pruned_loss=0.0276, over 4910.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03105, over 943825.59 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:04:11,048 INFO [train.py:715] (5/8) Epoch 14, batch 750, loss[loss=0.1594, simple_loss=0.23, pruned_loss=0.04443, over 4975.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03099, over 949217.14 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:04:51,156 INFO [train.py:715] (5/8) Epoch 14, batch 800, loss[loss=0.1454, simple_loss=0.2198, pruned_loss=0.03549, over 4740.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03078, over 953843.02 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:05:30,245 INFO [train.py:715] (5/8) Epoch 14, batch 850, loss[loss=0.139, simple_loss=0.2093, pruned_loss=0.03436, over 4892.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03084, over 957614.88 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:06:09,705 INFO [train.py:715] (5/8) Epoch 14, batch 900, loss[loss=0.1406, simple_loss=0.2161, pruned_loss=0.03257, over 4786.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03059, over 960387.32 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:06:48,330 INFO [train.py:715] (5/8) Epoch 14, batch 950, loss[loss=0.1276, simple_loss=0.2034, pruned_loss=0.02589, over 4794.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03046, over 961728.82 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 23:07:27,881 INFO [train.py:715] (5/8) Epoch 14, batch 1000, loss[loss=0.1537, simple_loss=0.2247, pruned_loss=0.04132, over 4795.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03083, over 964470.46 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:08:07,943 INFO [train.py:715] (5/8) Epoch 14, batch 1050, loss[loss=0.1301, simple_loss=0.2024, pruned_loss=0.02896, over 4953.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03102, over 966278.46 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 23:08:47,253 INFO [train.py:715] (5/8) Epoch 14, batch 1100, loss[loss=0.139, simple_loss=0.2082, pruned_loss=0.03486, over 4987.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03089, over 968059.49 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:09:26,968 INFO [train.py:715] (5/8) Epoch 14, batch 1150, loss[loss=0.1646, simple_loss=0.2391, pruned_loss=0.04498, over 4903.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03104, over 968617.86 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:10:07,014 INFO [train.py:715] (5/8) Epoch 14, batch 1200, loss[loss=0.1585, simple_loss=0.2344, pruned_loss=0.04131, over 4773.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03106, over 969507.38 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:10:47,175 INFO [train.py:715] (5/8) Epoch 14, batch 1250, loss[loss=0.1381, simple_loss=0.2077, pruned_loss=0.03419, over 4786.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.0308, over 970103.01 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:11:26,192 INFO [train.py:715] (5/8) Epoch 14, batch 1300, loss[loss=0.1223, simple_loss=0.1985, pruned_loss=0.02299, over 4954.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03074, over 970149.39 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:12:05,713 INFO [train.py:715] (5/8) Epoch 14, batch 1350, loss[loss=0.1245, simple_loss=0.2049, pruned_loss=0.02208, over 4947.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.0306, over 970644.60 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 23:12:45,083 INFO [train.py:715] (5/8) Epoch 14, batch 1400, loss[loss=0.1671, simple_loss=0.2452, pruned_loss=0.0445, over 4924.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03086, over 970468.56 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:13:24,653 INFO [train.py:715] (5/8) Epoch 14, batch 1450, loss[loss=0.1553, simple_loss=0.2211, pruned_loss=0.04476, over 4813.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03076, over 969950.89 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:14:04,620 INFO [train.py:715] (5/8) Epoch 14, batch 1500, loss[loss=0.1358, simple_loss=0.2103, pruned_loss=0.03068, over 4950.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03074, over 971339.53 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 23:14:44,299 INFO [train.py:715] (5/8) Epoch 14, batch 1550, loss[loss=0.1283, simple_loss=0.2067, pruned_loss=0.02491, over 4897.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2104, pruned_loss=0.03097, over 970973.36 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:15:24,190 INFO [train.py:715] (5/8) Epoch 14, batch 1600, loss[loss=0.1229, simple_loss=0.2, pruned_loss=0.02286, over 4763.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03085, over 970915.30 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:16:03,424 INFO [train.py:715] (5/8) Epoch 14, batch 1650, loss[loss=0.1547, simple_loss=0.237, pruned_loss=0.0362, over 4982.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03112, over 971196.22 frames.], batch size: 28, lr: 1.59e-04
2022-05-07 23:16:43,079 INFO [train.py:715] (5/8) Epoch 14, batch 1700, loss[loss=0.1478, simple_loss=0.222, pruned_loss=0.03682, over 4978.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03135, over 970951.82 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:17:22,558 INFO [train.py:715] (5/8) Epoch 14, batch 1750, loss[loss=0.1133, simple_loss=0.1884, pruned_loss=0.01913, over 4896.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03115, over 972057.19 frames.], batch size: 22, lr: 1.59e-04
2022-05-07 23:18:02,285 INFO [train.py:715] (5/8) Epoch 14, batch 1800, loss[loss=0.1272, simple_loss=0.2053, pruned_loss=0.02456, over 4881.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03111, over 971509.23 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:18:40,626 INFO [train.py:715] (5/8) Epoch 14, batch 1850, loss[loss=0.1195, simple_loss=0.1932, pruned_loss=0.02289, over 4980.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03078, over 970911.48 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:19:19,859 INFO [train.py:715] (5/8) Epoch 14, batch 1900, loss[loss=0.1442, simple_loss=0.2236, pruned_loss=0.03238, over 4907.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03073, over 971404.90 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:19:59,663 INFO [train.py:715] (5/8) Epoch 14, batch 1950, loss[loss=0.129, simple_loss=0.2087, pruned_loss=0.02464, over 4978.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03023, over 972110.02 frames.], batch size: 28, lr: 1.59e-04
2022-05-07 23:20:39,805 INFO [train.py:715] (5/8) Epoch 14, batch 2000, loss[loss=0.128, simple_loss=0.2138, pruned_loss=0.02109, over 4806.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03057, over 972072.82 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:21:19,092 INFO [train.py:715] (5/8) Epoch 14, batch 2050, loss[loss=0.1521, simple_loss=0.2245, pruned_loss=0.03988, over 4914.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03045, over 972128.11 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:21:58,530 INFO [train.py:715] (5/8) Epoch 14, batch 2100, loss[loss=0.1479, simple_loss=0.2105, pruned_loss=0.04266, over 4882.00 frames.], tot_loss[loss=0.1337, simple_loss=0.207, pruned_loss=0.0302, over 971419.59 frames.], batch size: 22, lr: 1.59e-04
2022-05-07 23:22:38,245 INFO [train.py:715] (5/8) Epoch 14, batch 2150, loss[loss=0.1382, simple_loss=0.2185, pruned_loss=0.02896, over 4967.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02985, over 972160.63 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:23:16,937 INFO [train.py:715] (5/8) Epoch 14, batch 2200, loss[loss=0.1348, simple_loss=0.2173, pruned_loss=0.0262, over 4797.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02971, over 972693.21 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:23:55,887 INFO [train.py:715] (5/8) Epoch 14, batch 2250, loss[loss=0.1558, simple_loss=0.2222, pruned_loss=0.04465, over 4697.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.0299, over 971978.59 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:24:34,961 INFO [train.py:715] (5/8) Epoch 14, batch 2300, loss[loss=0.1241, simple_loss=0.2018, pruned_loss=0.02322, over 4902.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02989, over 972417.33 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:25:14,125 INFO [train.py:715] (5/8) Epoch 14, batch 2350, loss[loss=0.1257, simple_loss=0.2016, pruned_loss=0.02487, over 4913.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02971, over 973195.68 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:25:53,240 INFO [train.py:715] (5/8) Epoch 14, batch 2400, loss[loss=0.1528, simple_loss=0.2174, pruned_loss=0.0441, over 4959.00 frames.], tot_loss[loss=0.1324, simple_loss=0.206, pruned_loss=0.0294, over 973812.16 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:26:32,284 INFO [train.py:715] (5/8) Epoch 14, batch 2450, loss[loss=0.1403, simple_loss=0.2167, pruned_loss=0.03199, over 4780.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02973, over 973417.97 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:27:11,604 INFO [train.py:715] (5/8) Epoch 14, batch 2500, loss[loss=0.1109, simple_loss=0.1802, pruned_loss=0.02076, over 4757.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02987, over 972803.59 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:27:50,105 INFO [train.py:715] (5/8) Epoch 14, batch 2550, loss[loss=0.146, simple_loss=0.2085, pruned_loss=0.04175, over 4897.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02995, over 973065.27 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:28:29,682 INFO [train.py:715] (5/8) Epoch 14, batch 2600, loss[loss=0.1365, simple_loss=0.2148, pruned_loss=0.02907, over 4694.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03053, over 972665.30 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:29:09,140 INFO [train.py:715] (5/8) Epoch 14, batch 2650, loss[loss=0.1301, simple_loss=0.2119, pruned_loss=0.0241, over 4984.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03046, over 972742.89 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:29:48,492 INFO [train.py:715] (5/8) Epoch 14, batch 2700, loss[loss=0.1327, simple_loss=0.2174, pruned_loss=0.02403, over 4842.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02994, over 972287.88 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:30:27,052 INFO [train.py:715] (5/8) Epoch 14, batch 2750, loss[loss=0.1321, simple_loss=0.1943, pruned_loss=0.03495, over 4922.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03045, over 971169.08 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:31:06,229 INFO [train.py:715] (5/8) Epoch 14, batch 2800, loss[loss=0.121, simple_loss=0.1976, pruned_loss=0.02218, over 4936.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03089, over 971389.47 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 23:31:45,880 INFO [train.py:715] (5/8) Epoch 14, batch 2850, loss[loss=0.1261, simple_loss=0.1981, pruned_loss=0.02705, over 4756.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2078, pruned_loss=0.03043, over 971087.99 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:32:24,323 INFO [train.py:715] (5/8) Epoch 14, batch 2900, loss[loss=0.143, simple_loss=0.206, pruned_loss=0.03994, over 4781.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03008, over 970836.54 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:33:06,132 INFO [train.py:715] (5/8) Epoch 14, batch 2950, loss[loss=0.1684, simple_loss=0.2367, pruned_loss=0.05007, over 4785.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03023, over 970972.19 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:33:45,666 INFO [train.py:715] (5/8) Epoch 14, batch 3000, loss[loss=0.1582, simple_loss=0.2418, pruned_loss=0.03731, over 4925.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03126, over 972301.83 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:33:45,667 INFO [train.py:733] (5/8) Computing validation loss
2022-05-07 23:33:55,239 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1891, pruned_loss=0.01067, over 914524.00 frames.
2022-05-07 23:34:34,251 INFO [train.py:715] (5/8) Epoch 14, batch 3050, loss[loss=0.1365, simple_loss=0.2156, pruned_loss=0.02875, over 4703.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.0307, over 972223.66 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:35:14,212 INFO [train.py:715] (5/8) Epoch 14, batch 3100, loss[loss=0.1573, simple_loss=0.2342, pruned_loss=0.04022, over 4943.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.0313, over 972712.14 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:35:53,765 INFO [train.py:715] (5/8) Epoch 14, batch 3150, loss[loss=0.1484, simple_loss=0.2161, pruned_loss=0.04032, over 4983.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03175, over 972714.12 frames.], batch size: 33, lr: 1.59e-04
2022-05-07 23:36:33,459 INFO [train.py:715] (5/8) Epoch 14, batch 3200, loss[loss=0.1497, simple_loss=0.2194, pruned_loss=0.04003, over 4831.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03168, over 971701.11 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:37:14,481 INFO [train.py:715] (5/8) Epoch 14, batch 3250, loss[loss=0.1646, simple_loss=0.2288, pruned_loss=0.05015, over 4842.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03199, over 971613.20 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:37:54,306 INFO [train.py:715] (5/8) Epoch 14, batch 3300, loss[loss=0.1495, simple_loss=0.231, pruned_loss=0.034, over 4885.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03172, over 971398.83 frames.], batch size: 22, lr: 1.59e-04
2022-05-07 23:38:34,434 INFO [train.py:715] (5/8) Epoch 14, batch 3350, loss[loss=0.127, simple_loss=0.2042, pruned_loss=0.02488, over 4646.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03184, over 971382.41 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:39:15,376 INFO [train.py:715] (5/8) Epoch 14, batch 3400, loss[loss=0.1811, simple_loss=0.2491, pruned_loss=0.05651, over 4778.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03196, over 971442.89 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:39:56,022 INFO [train.py:715] (5/8) Epoch 14, batch 3450, loss[loss=0.1416, simple_loss=0.222, pruned_loss=0.03066, over 4986.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03187, over 970944.32 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 23:40:35,904 INFO [train.py:715] (5/8) Epoch 14, batch 3500, loss[loss=0.1464, simple_loss=0.2151, pruned_loss=0.03888, over 4815.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03116, over 971376.03 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:41:15,979 INFO [train.py:715] (5/8) Epoch 14, batch 3550, loss[loss=0.1696, simple_loss=0.2413, pruned_loss=0.04889, over 4899.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.0309, over 972064.02 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:41:56,123 INFO [train.py:715] (5/8) Epoch 14, batch 3600, loss[loss=0.1255, simple_loss=0.1951, pruned_loss=0.02793, over 4977.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03082, over 972451.71 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:42:36,127 INFO [train.py:715] (5/8) Epoch 14, batch 3650, loss[loss=0.1436, simple_loss=0.2204, pruned_loss=0.0334, over 4810.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2081, pruned_loss=0.03101, over 971667.42 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:43:16,030 INFO [train.py:715] (5/8) Epoch 14, batch 3700, loss[loss=0.1275, simple_loss=0.2044, pruned_loss=0.02527, over 4751.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03108, over 971059.84 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:43:56,761 INFO [train.py:715] (5/8) Epoch 14, batch 3750, loss[loss=0.117, simple_loss=0.1904, pruned_loss=0.02182, over 4856.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2087, pruned_loss=0.03113, over 970409.49 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:44:36,924 INFO [train.py:715] (5/8) Epoch 14, batch 3800, loss[loss=0.1341, simple_loss=0.2168, pruned_loss=0.02575, over 4933.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03092, over 971488.04 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:45:16,168 INFO [train.py:715] (5/8) Epoch 14, batch 3850, loss[loss=0.1753, simple_loss=0.2419, pruned_loss=0.05437, over 4756.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03063, over 971917.42 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:45:56,642 INFO [train.py:715] (5/8) Epoch 14, batch 3900, loss[loss=0.1418, simple_loss=0.2193, pruned_loss=0.03212, over 4935.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03051, over 972308.79 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 23:46:37,883 INFO [train.py:715] (5/8) Epoch 14, batch 3950, loss[loss=0.1314, simple_loss=0.202, pruned_loss=0.03041, over 4990.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03047, over 971975.75 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:47:18,822 INFO [train.py:715] (5/8) Epoch 14, batch 4000, loss[loss=0.1456, simple_loss=0.2154, pruned_loss=0.03794, over 4948.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03006, over 971774.59 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:47:59,308 INFO [train.py:715] (5/8) Epoch 14, batch 4050, loss[loss=0.1579, simple_loss=0.2353, pruned_loss=0.04025, over 4869.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.0303, over 971692.15 frames.], batch size: 38, lr: 1.59e-04
2022-05-07 23:48:40,124 INFO [train.py:715] (5/8) Epoch 14, batch 4100, loss[loss=0.1436, simple_loss=0.2193, pruned_loss=0.03398, over 4749.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03082, over 971939.91 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:49:21,558 INFO [train.py:715] (5/8) Epoch 14, batch 4150, loss[loss=0.1203, simple_loss=0.1917, pruned_loss=0.02446, over 4780.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03045, over 972125.34 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:50:02,217 INFO [train.py:715] (5/8) Epoch 14, batch 4200, loss[loss=0.1653, simple_loss=0.233, pruned_loss=0.04884, over 4869.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03059, over 972304.89 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:50:43,285 INFO [train.py:715] (5/8) Epoch 14, batch 4250, loss[loss=0.123, simple_loss=0.1891, pruned_loss=0.02843, over 4819.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03065, over 972144.14 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:51:25,171 INFO [train.py:715] (5/8) Epoch 14, batch 4300, loss[loss=0.1117, simple_loss=0.1884, pruned_loss=0.0175, over 4802.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03145, over 971990.72 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:52:06,420 INFO [train.py:715] (5/8) Epoch 14, batch 4350, loss[loss=0.1273, simple_loss=0.2007, pruned_loss=0.02695, over 4882.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03159, over 972292.96 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:52:46,951 INFO [train.py:715] (5/8) Epoch 14, batch 4400, loss[loss=0.1369, simple_loss=0.2158, pruned_loss=0.02894, over 4748.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03141, over 971524.34 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:53:27,638 INFO [train.py:715] (5/8) Epoch 14, batch 4450, loss[loss=0.1289, simple_loss=0.2052, pruned_loss=0.02629, over 4961.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03144, over 971025.92 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:54:08,629 INFO [train.py:715] (5/8) Epoch 14, batch 4500, loss[loss=0.1576, simple_loss=0.2263, pruned_loss=0.04448, over 4774.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03085, over 970435.43 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:54:48,677 INFO [train.py:715] (5/8) Epoch 14, batch 4550, loss[loss=0.1591, simple_loss=0.2248, pruned_loss=0.04664, over 4979.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03051, over 970788.87 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:55:27,629 INFO [train.py:715] (5/8) Epoch 14, batch 4600, loss[loss=0.134, simple_loss=0.2061, pruned_loss=0.03102, over 4820.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03097, over 971162.89 frames.], batch size: 27, lr: 1.59e-04
2022-05-07 23:56:08,466 INFO [train.py:715] (5/8) Epoch 14, batch 4650, loss[loss=0.1129, simple_loss=0.1959, pruned_loss=0.01497, over 4857.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03047, over 971308.98 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:56:48,194 INFO [train.py:715] (5/8) Epoch 14, batch 4700, loss[loss=0.1216, simple_loss=0.1934, pruned_loss=0.02492, over 4847.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03049, over 971202.85 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:57:26,877 INFO [train.py:715] (5/8) Epoch 14, batch 4750, loss[loss=0.1235, simple_loss=0.2014, pruned_loss=0.02279, over 4756.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03015, over 971771.13 frames.], batch size: 19, lr: 1.58e-04
2022-05-07 23:58:06,245 INFO [train.py:715] (5/8) Epoch 14, batch 4800, loss[loss=0.1301, simple_loss=0.1957, pruned_loss=0.03219, over 4874.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03051, over 973212.73 frames.], batch size: 30, lr: 1.58e-04
2022-05-07 23:58:46,077 INFO [train.py:715] (5/8) Epoch 14, batch 4850, loss[loss=0.1362, simple_loss=0.2079, pruned_loss=0.03226, over 4959.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03009, over 973771.94 frames.], batch size: 35, lr: 1.58e-04
2022-05-07 23:59:25,003 INFO [train.py:715] (5/8) Epoch 14, batch 4900, loss[loss=0.1246, simple_loss=0.2064, pruned_loss=0.02137, over 4886.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.031, over 973674.81 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:00:04,152 INFO [train.py:715] (5/8) Epoch 14, batch 4950, loss[loss=0.1246, simple_loss=0.199, pruned_loss=0.02511, over 4766.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03119, over 973578.45 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:00:44,229 INFO [train.py:715] (5/8) Epoch 14, batch 5000, loss[loss=0.1512, simple_loss=0.2171, pruned_loss=0.04258, over 4694.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03052, over 972541.60 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:01:23,508 INFO [train.py:715] (5/8) Epoch 14, batch 5050, loss[loss=0.1323, simple_loss=0.2058, pruned_loss=0.02938, over 4990.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03135, over 973022.26 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:02:02,196 INFO [train.py:715] (5/8) Epoch 14, batch 5100, loss[loss=0.1537, simple_loss=0.2282, pruned_loss=0.03955, over 4845.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03171, over 973328.29 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:02:41,794 INFO [train.py:715] (5/8) Epoch 14, batch 5150, loss[loss=0.1241, simple_loss=0.1936, pruned_loss=0.02736, over 4768.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03174, over 973350.67 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:03:21,425 INFO [train.py:715] (5/8) Epoch 14, batch 5200, loss[loss=0.1174, simple_loss=0.1928, pruned_loss=0.02098, over 4926.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03137, over 973126.68 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:03:59,950 INFO [train.py:715] (5/8) Epoch 14, batch 5250, loss[loss=0.161, simple_loss=0.2243, pruned_loss=0.04887, over 4688.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03164, over 972631.81 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:04:38,442 INFO [train.py:715] (5/8) Epoch 14, batch 5300, loss[loss=0.1139, simple_loss=0.1884, pruned_loss=0.01971, over 4979.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03224, over 972762.58 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:05:17,624 INFO [train.py:715] (5/8) Epoch 14, batch 5350, loss[loss=0.1418, simple_loss=0.224, pruned_loss=0.02977, over 4724.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03153, over 972434.51 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:05:56,197 INFO [train.py:715] (5/8) Epoch 14, batch 5400, loss[loss=0.127, simple_loss=0.197, pruned_loss=0.02844, over 4970.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03156, over 972052.80 frames.], batch size: 35, lr: 1.58e-04
2022-05-08 00:06:34,702 INFO [train.py:715] (5/8) Epoch 14, batch 5450, loss[loss=0.1492, simple_loss=0.2208, pruned_loss=0.03879, over 4992.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2085, pruned_loss=0.03122, over 972487.01 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:07:13,536 INFO [train.py:715] (5/8) Epoch 14, batch 5500, loss[loss=0.1074, simple_loss=0.175, pruned_loss=0.01994, over 4885.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03126, over 972347.55 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 00:07:53,213 INFO [train.py:715] (5/8) Epoch 14, batch 5550, loss[loss=0.1101, simple_loss=0.1777, pruned_loss=0.02125, over 4821.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2087, pruned_loss=0.03109, over 973307.21 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 00:08:31,527 INFO [train.py:715] (5/8) Epoch 14, batch 5600, loss[loss=0.1213, simple_loss=0.1935, pruned_loss=0.02453, over 4894.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2083, pruned_loss=0.031, over 973110.47 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:09:10,032 INFO [train.py:715] (5/8) Epoch 14, batch 5650, loss[loss=0.1463, simple_loss=0.2209, pruned_loss=0.03582, over 4840.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03097, over 972330.04 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 00:09:49,144 INFO [train.py:715] (5/8) Epoch 14, batch 5700, loss[loss=0.1284, simple_loss=0.2063, pruned_loss=0.02522, over 4824.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.03073, over 972635.62 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:10:27,414 INFO [train.py:715] (5/8) Epoch 14, batch 5750, loss[loss=0.1242, simple_loss=0.2009, pruned_loss=0.02377, over 4819.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.0302, over 972214.77 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:11:05,796 INFO [train.py:715] (5/8) Epoch 14, batch 5800, loss[loss=0.1274, simple_loss=0.2065, pruned_loss=0.02417, over 4937.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03015, over 973078.79 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:11:44,416 INFO [train.py:715] (5/8) Epoch 14, batch 5850, loss[loss=0.1355, simple_loss=0.2191, pruned_loss=0.02598, over 4812.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03008, over 973724.30 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:12:23,193 INFO [train.py:715] (5/8) Epoch 14, batch 5900, loss[loss=0.1227, simple_loss=0.2049, pruned_loss=0.02019, over 4820.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 973553.80 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:13:02,953 INFO [train.py:715] (5/8) Epoch 14, batch 5950, loss[loss=0.1129, simple_loss=0.1937, pruned_loss=0.01605, over 4799.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03036, over 974309.44 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:13:42,647 INFO [train.py:715] (5/8) Epoch 14, batch 6000, loss[loss=0.1355, simple_loss=0.2073, pruned_loss=0.03184, over 4967.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03065, over 973981.65 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:13:42,647 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 00:13:52,503 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.105, simple_loss=0.1888, pruned_loss=0.01057, over 914524.00 frames.
2022-05-08 00:14:31,606 INFO [train.py:715] (5/8) Epoch 14, batch 6050, loss[loss=0.1395, simple_loss=0.2154, pruned_loss=0.03183, over 4979.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03005, over 973699.70 frames.], batch size: 28, lr: 1.58e-04
2022-05-08 00:15:10,781 INFO [train.py:715] (5/8) Epoch 14, batch 6100, loss[loss=0.1212, simple_loss=0.1955, pruned_loss=0.02343, over 4988.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03019, over 973363.87 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:15:50,782 INFO [train.py:715] (5/8) Epoch 14, batch 6150, loss[loss=0.166, simple_loss=0.2272, pruned_loss=0.05242, over 4758.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03039, over 973619.94 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:16:30,391 INFO [train.py:715] (5/8) Epoch 14, batch 6200, loss[loss=0.1403, simple_loss=0.219, pruned_loss=0.03079, over 4740.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03039, over 973659.90 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:17:10,277 INFO [train.py:715] (5/8) Epoch 14, batch 6250, loss[loss=0.1052, simple_loss=0.1782, pruned_loss=0.01606, over 4881.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.0306, over 973784.77 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:17:49,632 INFO [train.py:715] (5/8) Epoch 14, batch 6300, loss[loss=0.1439, simple_loss=0.2064, pruned_loss=0.04068, over 4842.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03048, over 974493.54 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:18:29,661 INFO [train.py:715] (5/8) Epoch 14, batch 6350, loss[loss=0.1596, simple_loss=0.2353, pruned_loss=0.04197, over 4813.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03085, over 973421.20 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:19:09,437 INFO [train.py:715] (5/8) Epoch 14, batch 6400, loss[loss=0.1405, simple_loss=0.2188, pruned_loss=0.03108, over 4977.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03132, over 973076.49 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:19:49,527 INFO [train.py:715] (5/8) Epoch 14, batch 6450, loss[loss=0.1335, simple_loss=0.1804, pruned_loss=0.04331, over 4801.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03106, over 972697.16 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:20:29,516 INFO [train.py:715] (5/8) Epoch 14, batch 6500, loss[loss=0.1334, simple_loss=0.2053, pruned_loss=0.0307, over 4719.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03053, over 972328.80 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:21:09,170 INFO [train.py:715] (5/8) Epoch 14, batch 6550, loss[loss=0.1538, simple_loss=0.2274, pruned_loss=0.04016, over 4905.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.0304, over 972273.41 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:21:49,052 INFO [train.py:715] (5/8) Epoch 14, batch 6600, loss[loss=0.1372, simple_loss=0.2076, pruned_loss=0.03337, over 4858.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03071, over 972555.83 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:22:29,229 INFO [train.py:715] (5/8) Epoch 14, batch 6650, loss[loss=0.1522, simple_loss=0.2267, pruned_loss=0.0389, over 4748.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03033, over 971685.88 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:23:08,961 INFO [train.py:715] (5/8) Epoch 14, batch 6700, loss[loss=0.1515, simple_loss=0.2167, pruned_loss=0.04321, over 4984.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03047, over 971677.79 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:23:48,843 INFO [train.py:715] (5/8) Epoch 14, batch 6750, loss[loss=0.1192, simple_loss=0.1971, pruned_loss=0.02068, over 4793.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 971905.79 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:24:28,836 INFO [train.py:715] (5/8) Epoch 14, batch 6800, loss[loss=0.1447, simple_loss=0.2192, pruned_loss=0.03515, over 4654.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 972630.78 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 00:25:08,848 INFO [train.py:715] (5/8) Epoch 14, batch 6850, loss[loss=0.1401, simple_loss=0.2229, pruned_loss=0.02863, over 4877.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03098, over 972737.98 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:25:48,265 INFO [train.py:715] (5/8) Epoch 14, batch 6900, loss[loss=0.1556, simple_loss=0.2218, pruned_loss=0.04475, over 4975.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03076, over 972269.11 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 00:26:28,459 INFO [train.py:715] (5/8) Epoch 14, batch 6950, loss[loss=0.1181, simple_loss=0.1962, pruned_loss=0.02003, over 4787.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 972331.87 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:27:08,563 INFO [train.py:715] (5/8) Epoch 14, batch 7000, loss[loss=0.1296, simple_loss=0.2034, pruned_loss=0.02794, over 4895.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03094, over 972378.76 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:27:48,547 INFO [train.py:715] (5/8) Epoch 14, batch 7050, loss[loss=0.1277, simple_loss=0.2064, pruned_loss=0.02454, over 4830.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03057, over 972249.98 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:28:27,874 INFO [train.py:715] (5/8) Epoch 14, batch 7100, loss[loss=0.1496, simple_loss=0.2163, pruned_loss=0.0414, over 4833.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03056, over 971333.37 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:29:07,964 INFO [train.py:715] (5/8) Epoch 14, batch 7150, loss[loss=0.1529, simple_loss=0.2259, pruned_loss=0.04, over 4875.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03057, over 971664.81 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:29:48,166 INFO [train.py:715] (5/8) Epoch 14, batch 7200, loss[loss=0.1558, simple_loss=0.2203, pruned_loss=0.04567, over 4749.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03042, over 971835.20 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:30:28,012 INFO [train.py:715] (5/8) Epoch 14, batch 7250, loss[loss=0.1226, simple_loss=0.2055, pruned_loss=0.01986, over 4896.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03047, over 971522.13 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:31:08,140 INFO [train.py:715] (5/8) Epoch 14, batch 7300, loss[loss=0.1285, simple_loss=0.1928, pruned_loss=0.03213, over 4835.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03042, over 970245.34 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:31:48,262 INFO [train.py:715] (5/8) Epoch 14, batch 7350, loss[loss=0.1233, simple_loss=0.1953, pruned_loss=0.02567, over 4786.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03134, over 970312.14 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:32:28,616 INFO [train.py:715] (5/8) Epoch 14, batch 7400, loss[loss=0.1457, simple_loss=0.2252, pruned_loss=0.03307, over 4894.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03163, over 971617.80 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:33:08,078 INFO [train.py:715] (5/8) Epoch 14, batch 7450, loss[loss=0.1199, simple_loss=0.193, pruned_loss=0.02341, over 4832.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2107, pruned_loss=0.03123, over 973336.13 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 00:33:47,755 INFO [train.py:715] (5/8) Epoch 14, batch 7500, loss[loss=0.1271, simple_loss=0.1978, pruned_loss=0.02823, over 4697.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03129, over 972715.57 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:34:27,409 INFO [train.py:715] (5/8) Epoch 14, batch 7550, loss[loss=0.123, simple_loss=0.1954, pruned_loss=0.02527, over 4975.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03136, over 973185.23 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:35:06,409 INFO [train.py:715] (5/8) Epoch 14, batch 7600, loss[loss=0.1151, simple_loss=0.1844, pruned_loss=0.02291, over 4807.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03097, over 972295.78 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:35:46,364 INFO [train.py:715] (5/8) Epoch 14, batch 7650, loss[loss=0.1119, simple_loss=0.1882, pruned_loss=0.01777, over 4754.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03087, over 972061.53 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:36:25,267 INFO [train.py:715] (5/8) Epoch 14, batch 7700, loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03584, over 4892.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03075, over 971850.92 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:37:05,576 INFO [train.py:715] (5/8) Epoch 14, batch 7750, loss[loss=0.1419, simple_loss=0.2329, pruned_loss=0.02546, over 4846.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03092, over 971266.29 frames.], batch size: 34, lr: 1.58e-04
2022-05-08 00:37:44,379 INFO [train.py:715] (5/8) Epoch 14, batch 7800, loss[loss=0.1326, simple_loss=0.2086, pruned_loss=0.02834, over 4977.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03095, over 972263.02 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:38:23,469 INFO [train.py:715] (5/8) Epoch 14, batch 7850, loss[loss=0.1194, simple_loss=0.201, pruned_loss=0.01892, over 4902.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03096, over 972645.75 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:39:03,273 INFO [train.py:715] (5/8) Epoch 14, batch 7900, loss[loss=0.1174, simple_loss=0.1843, pruned_loss=0.02528, over 4939.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03123, over 973243.03 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:39:42,078 INFO [train.py:715] (5/8) Epoch 14, batch 7950, loss[loss=0.1367, simple_loss=0.2129, pruned_loss=0.03023, over 4816.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.03097, over 973181.54 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 00:40:21,689 INFO [train.py:715] (5/8) Epoch 14, batch 8000, loss[loss=0.1465, simple_loss=0.2099, pruned_loss=0.04149, over 4929.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03084, over 972659.12 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:41:00,526 INFO [train.py:715] (5/8) Epoch 14, batch 8050, loss[loss=0.1186, simple_loss=0.1939, pruned_loss=0.02167, over 4879.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03127, over 972018.53 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:41:40,051 INFO [train.py:715] (5/8) Epoch 14, batch 8100, loss[loss=0.1616, simple_loss=0.229, pruned_loss=0.04706, over 4860.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03151, over 971349.15 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:42:18,790 INFO [train.py:715] (5/8) Epoch 14, batch 8150, loss[loss=0.1224, simple_loss=0.2005, pruned_loss=0.02211, over 4782.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03224, over 971467.26 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:42:58,274 INFO [train.py:715] (5/8) Epoch 14, batch 8200, loss[loss=0.1307, simple_loss=0.2005, pruned_loss=0.03048, over 4840.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03154, over 971534.05 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:43:37,712 INFO [train.py:715] (5/8) Epoch 14, batch 8250, loss[loss=0.1576, simple_loss=0.2338, pruned_loss=0.04067, over 4890.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03163, over 971579.52 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:44:17,183 INFO [train.py:715] (5/8) Epoch 14, batch 8300, loss[loss=0.1284, simple_loss=0.2104, pruned_loss=0.02322, over 4766.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03208, over 972491.19 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:44:56,125 INFO [train.py:715] (5/8) Epoch 14, batch 8350, loss[loss=0.1574, simple_loss=0.2199, pruned_loss=0.04751, over 4646.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03187, over 971555.99 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 00:45:35,322 INFO [train.py:715] (5/8) Epoch 14, batch 8400, loss[loss=0.1246, simple_loss=0.1888, pruned_loss=0.03021, over 4983.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2096, pruned_loss=0.03186, over 970959.85 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:46:14,805 INFO [train.py:715] (5/8) Epoch 14, batch 8450, loss[loss=0.1499, simple_loss=0.2243, pruned_loss=0.03777, over 4875.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03153, over 971204.64 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:46:53,355 INFO [train.py:715] (5/8) Epoch 14, batch 8500, loss[loss=0.1408, simple_loss=0.2179, pruned_loss=0.03184, over 4905.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2088, pruned_loss=0.03138, over 971530.66 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:47:32,484 INFO [train.py:715] (5/8) Epoch 14, batch 8550, loss[loss=0.1321, simple_loss=0.2132, pruned_loss=0.02551, over 4930.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03118, over 971900.07 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:48:13,439 INFO [train.py:715] (5/8) Epoch 14, batch 8600, loss[loss=0.1469, simple_loss=0.2321, pruned_loss=0.03087, over 4810.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.0314, over 972306.25 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:48:52,731 INFO [train.py:715] (5/8) Epoch 14, batch 8650, loss[loss=0.1648, simple_loss=0.2175, pruned_loss=0.05605, over 4829.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03132, over 971926.35 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:49:34,156 INFO [train.py:715] (5/8) Epoch 14, batch 8700, loss[loss=0.1333, simple_loss=0.2138, pruned_loss=0.02642, over 4960.00 frames.], tot_loss[loss=0.1347, simple_loss=0.208, pruned_loss=0.03073, over 971804.34 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:50:13,525 INFO [train.py:715] (5/8) Epoch 14, batch 8750, loss[loss=0.1255, simple_loss=0.2017, pruned_loss=0.02467, over 4914.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2074, pruned_loss=0.03082, over 971762.90 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:50:53,243 INFO [train.py:715] (5/8) Epoch 14, batch 8800, loss[loss=0.1456, simple_loss=0.2189, pruned_loss=0.03617, over 4858.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03109, over 971605.16 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 00:51:32,823 INFO [train.py:715] (5/8) Epoch 14, batch 8850, loss[loss=0.149, simple_loss=0.234, pruned_loss=0.03194, over 4859.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03055, over 972316.74 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:52:13,342 INFO [train.py:715] (5/8) Epoch 14, batch 8900, loss[loss=0.09187, simple_loss=0.1684, pruned_loss=0.007683, over 4790.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03069, over 972472.37 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:52:53,210 INFO [train.py:715] (5/8) Epoch 14, batch 8950, loss[loss=0.1364, simple_loss=0.2113, pruned_loss=0.03075, over 4951.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03087, over 972469.57 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:53:33,014 INFO [train.py:715] (5/8) Epoch 14, batch 9000, loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03453, over 4685.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03115, over 972544.14 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:53:33,015 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 00:53:47,940 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 00:54:27,481 INFO [train.py:715] (5/8) Epoch 14, batch 9050, loss[loss=0.1077, simple_loss=0.1846, pruned_loss=0.01539, over 4787.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03078, over 972849.24 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:55:07,803 INFO [train.py:715] (5/8) Epoch 14, batch 9100, loss[loss=0.1502, simple_loss=0.239, pruned_loss=0.03064, over 4822.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03055, over 973765.92 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 00:55:47,310 INFO [train.py:715] (5/8) Epoch 14, batch 9150, loss[loss=0.1177, simple_loss=0.1885, pruned_loss=0.02344, over 4816.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03096, over 973889.94 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:56:27,170 INFO [train.py:715] (5/8) Epoch 14, batch 9200, loss[loss=0.1169, simple_loss=0.1887, pruned_loss=0.02257, over 4972.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03079, over 974033.96 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:57:06,889 INFO [train.py:715] (5/8) Epoch 14, batch 9250, loss[loss=0.1192, simple_loss=0.2053, pruned_loss=0.01658, over 4935.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 973706.60 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:57:46,603 INFO [train.py:715] (5/8) Epoch 14, batch 9300, loss[loss=0.1313, simple_loss=0.2113, pruned_loss=0.02568, over 4695.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 973015.42 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:58:26,525 INFO [train.py:715] (5/8) Epoch 14, batch 9350, loss[loss=0.1335, simple_loss=0.2062, pruned_loss=0.0304, over 4825.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.0314, over 973320.98 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 00:59:06,670 INFO [train.py:715] (5/8) Epoch 14, batch 9400, loss[loss=0.1497, simple_loss=0.2269, pruned_loss=0.03619, over 4880.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03065, over 972902.38 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:59:46,291 INFO [train.py:715] (5/8) Epoch 14, batch 9450, loss[loss=0.1067, simple_loss=0.1814, pruned_loss=0.01594, over 4741.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03048, over 972112.12 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 01:00:26,049 INFO [train.py:715] (5/8) Epoch 14, batch 9500, loss[loss=0.1509, simple_loss=0.2173, pruned_loss=0.04223, over 4899.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03051, over 971482.38 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 01:01:05,838 INFO [train.py:715] (5/8) Epoch 14, batch 9550, loss[loss=0.127, simple_loss=0.198, pruned_loss=0.02802, over 4881.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03053, over 970809.57 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 01:01:46,001 INFO [train.py:715] (5/8) Epoch 14, batch 9600, loss[loss=0.1188, simple_loss=0.1949, pruned_loss=0.02135, over 4873.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.0307, over 971192.14 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 01:02:25,427 INFO [train.py:715] (5/8) Epoch 14, batch 9650, loss[loss=0.153, simple_loss=0.218, pruned_loss=0.04397, over 4940.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03134, over 972382.85 frames.], batch size: 35, lr: 1.58e-04
2022-05-08 01:03:05,451 INFO [train.py:715] (5/8) Epoch 14, batch 9700, loss[loss=0.1028, simple_loss=0.1724, pruned_loss=0.01663, over 4933.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03121, over 971906.96 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 01:03:45,037 INFO [train.py:715] (5/8) Epoch 14, batch 9750, loss[loss=0.1379, simple_loss=0.2195, pruned_loss=0.02811, over 4818.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03081, over 971732.19 frames.], batch size: 27, lr: 1.58e-04
2022-05-08 01:04:25,339 INFO [train.py:715] (5/8) Epoch 14, batch 9800, loss[loss=0.1086, simple_loss=0.1773, pruned_loss=0.02, over 4817.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03061, over 971576.95 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 01:05:04,565 INFO [train.py:715] (5/8) Epoch 14, batch 9850, loss[loss=0.1299, simple_loss=0.1996, pruned_loss=0.03009, over 4975.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03073, over 972475.71 frames.], batch size: 35, lr: 1.58e-04
2022-05-08 01:05:44,638 INFO [train.py:715] (5/8) Epoch 14, batch 9900, loss[loss=0.1386, simple_loss=0.206, pruned_loss=0.03563, over 4976.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03104, over 972587.38 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 01:06:24,619 INFO [train.py:715] (5/8) Epoch 14, batch 9950, loss[loss=0.1143, simple_loss=0.1899, pruned_loss=0.01933, over 4984.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03101, over 972637.14 frames.], batch size: 28, lr: 1.58e-04
2022-05-08 01:07:03,942 INFO [train.py:715] (5/8) Epoch 14, batch 10000, loss[loss=0.1198, simple_loss=0.1894, pruned_loss=0.02513, over 4774.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03123, over 972042.84 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 01:07:43,992 INFO [train.py:715] (5/8) Epoch 14, batch 10050, loss[loss=0.1274, simple_loss=0.2049, pruned_loss=0.02497, over 4904.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03122, over 972571.56 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 01:08:23,513 INFO [train.py:715] (5/8) Epoch 14, batch 10100, loss[loss=0.1616, simple_loss=0.2279, pruned_loss=0.04762, over 4690.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03087, over 973074.00 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 01:09:03,291 INFO [train.py:715] (5/8) Epoch 14, batch 10150, loss[loss=0.1483, simple_loss=0.2228, pruned_loss=0.03693, over 4985.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.0305, over 972634.92 frames.], batch size: 35, lr: 1.58e-04
2022-05-08 01:09:42,484 INFO [train.py:715] (5/8) Epoch 14, batch 10200, loss[loss=0.1323, simple_loss=0.2122, pruned_loss=0.0262, over 4944.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03064, over 972247.95 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:10:22,730 INFO [train.py:715] (5/8) Epoch 14, batch 10250, loss[loss=0.1302, simple_loss=0.2017, pruned_loss=0.02936, over 4978.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03062, over 972089.22 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 01:11:02,456 INFO [train.py:715] (5/8) Epoch 14, batch 10300, loss[loss=0.1356, simple_loss=0.2139, pruned_loss=0.02865, over 4984.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.0308, over 972747.96 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 01:11:41,905 INFO [train.py:715] (5/8) Epoch 14, batch 10350, loss[loss=0.1059, simple_loss=0.1897, pruned_loss=0.01106, over 4938.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03107, over 972901.80 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 01:12:22,108 INFO [train.py:715] (5/8) Epoch 14, batch 10400, loss[loss=0.1474, simple_loss=0.2126, pruned_loss=0.04108, over 4878.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03101, over 973410.02 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 01:13:01,497 INFO [train.py:715] (5/8) Epoch 14, batch 10450, loss[loss=0.1435, simple_loss=0.2038, pruned_loss=0.04165, over 4863.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03105, over 973153.66 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 01:13:41,728 INFO [train.py:715] (5/8) Epoch 14, batch 10500, loss[loss=0.1307, simple_loss=0.2103, pruned_loss=0.02555, over 4971.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03091, over 973327.24 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 01:14:21,001 INFO [train.py:715] (5/8) Epoch 14, batch 10550, loss[loss=0.1235, simple_loss=0.205, pruned_loss=0.02101, over 4938.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03101, over 973001.65 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 01:15:01,259 INFO [train.py:715] (5/8) Epoch 14, batch 10600, loss[loss=0.1372, simple_loss=0.209, pruned_loss=0.03271, over 4861.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03138, over 972885.68 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 01:15:40,587 INFO [train.py:715] (5/8) Epoch 14, batch 10650, loss[loss=0.137, simple_loss=0.2155, pruned_loss=0.02927, over 4950.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03081, over 972876.11 frames.], batch size: 40, lr: 1.58e-04
2022-05-08 01:16:19,715 INFO [train.py:715] (5/8) Epoch 14, batch 10700, loss[loss=0.1261, simple_loss=0.2064, pruned_loss=0.02291, over 4759.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03017, over 972503.71 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 01:16:58,895 INFO [train.py:715] (5/8) Epoch 14, batch 10750, loss[loss=0.1641, simple_loss=0.2338, pruned_loss=0.04718, over 4858.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03048, over 972583.09 frames.], batch size: 38, lr: 1.58e-04
2022-05-08 01:17:38,323 INFO [train.py:715] (5/8) Epoch 14, batch 10800, loss[loss=0.1376, simple_loss=0.2098, pruned_loss=0.03269, over 4949.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03047, over 972090.14 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:18:17,861 INFO [train.py:715] (5/8) Epoch 14, batch 10850, loss[loss=0.1445, simple_loss=0.2142, pruned_loss=0.03743, over 4913.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03026, over 971851.69 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 01:18:56,527 INFO [train.py:715] (5/8) Epoch 14, batch 10900, loss[loss=0.121, simple_loss=0.1978, pruned_loss=0.02208, over 4802.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03003, over 972577.58 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 01:19:36,717 INFO [train.py:715] (5/8) Epoch 14, batch 10950, loss[loss=0.1343, simple_loss=0.2093, pruned_loss=0.02968, over 4846.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02955, over 972878.11 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 01:20:17,493 INFO [train.py:715] (5/8) Epoch 14, batch 11000, loss[loss=0.1168, simple_loss=0.1823, pruned_loss=0.02565, over 4821.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02968, over 972452.84 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 01:20:56,618 INFO [train.py:715] (5/8) Epoch 14, batch 11050, loss[loss=0.1194, simple_loss=0.2013, pruned_loss=0.01873, over 4821.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02979, over 972645.66 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:21:37,658 INFO [train.py:715] (5/8) Epoch 14, batch 11100, loss[loss=0.1445, simple_loss=0.2181, pruned_loss=0.03544, over 4971.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02964, over 972605.45 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:22:18,216 INFO [train.py:715] (5/8) Epoch 14, batch 11150, loss[loss=0.1541, simple_loss=0.2217, pruned_loss=0.04322, over 4865.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03024, over 971650.53 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 01:22:58,446 INFO [train.py:715] (5/8) Epoch 14, batch 11200, loss[loss=0.1117, simple_loss=0.1816, pruned_loss=0.02085, over 4941.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03037, over 972470.55 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 01:23:37,882 INFO [train.py:715] (5/8) Epoch 14, batch 11250, loss[loss=0.1612, simple_loss=0.239, pruned_loss=0.04177, over 4955.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03049, over 972608.72 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 01:24:18,309 INFO [train.py:715] (5/8) Epoch 14, batch 11300, loss[loss=0.1196, simple_loss=0.1941, pruned_loss=0.02259, over 4685.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03023, over 972664.11 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:24:58,573 INFO [train.py:715] (5/8) Epoch 14, batch 11350, loss[loss=0.1165, simple_loss=0.1929, pruned_loss=0.02008, over 4768.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03059, over 972185.91 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:25:37,725 INFO [train.py:715] (5/8) Epoch 14, batch 11400, loss[loss=0.09904, simple_loss=0.1737, pruned_loss=0.01219, over 4803.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03043, over 971909.06 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:26:18,731 INFO [train.py:715] (5/8) Epoch 14, batch 11450, loss[loss=0.1344, simple_loss=0.2008, pruned_loss=0.03403, over 4965.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03028, over 971975.24 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:26:59,106 INFO [train.py:715] (5/8) Epoch 14, batch 11500, loss[loss=0.1045, simple_loss=0.1754, pruned_loss=0.01684, over 4908.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03062, over 972236.24 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:27:39,023 INFO [train.py:715] (5/8) Epoch 14, batch 11550, loss[loss=0.1538, simple_loss=0.2288, pruned_loss=0.0394, over 4701.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.03047, over 972949.07 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:28:18,474 INFO [train.py:715] (5/8) Epoch 14, batch 11600, loss[loss=0.148, simple_loss=0.2209, pruned_loss=0.03755, over 4863.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2073, pruned_loss=0.0302, over 973515.23 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:28:58,176 INFO [train.py:715] (5/8) Epoch 14, batch 11650, loss[loss=0.1182, simple_loss=0.1967, pruned_loss=0.01983, over 4819.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03033, over 973007.50 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:29:37,885 INFO [train.py:715] (5/8) Epoch 14, batch 11700, loss[loss=0.1265, simple_loss=0.2139, pruned_loss=0.01957, over 4900.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03026, over 972577.58 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:30:17,152 INFO [train.py:715] (5/8) Epoch 14, batch 11750, loss[loss=0.1704, simple_loss=0.2485, pruned_loss=0.04611, over 4851.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03028, over 972552.05 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 01:30:56,856 INFO [train.py:715] (5/8) Epoch 14, batch 11800, loss[loss=0.1204, simple_loss=0.1995, pruned_loss=0.0207, over 4805.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03071, over 972604.99 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:31:35,982 INFO [train.py:715] (5/8) Epoch 14, batch 11850, loss[loss=0.1047, simple_loss=0.1816, pruned_loss=0.01392, over 4787.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03055, over 971319.56 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 01:32:14,890 INFO [train.py:715] (5/8) Epoch 14, batch 11900, loss[loss=0.1433, simple_loss=0.2049, pruned_loss=0.0408, over 4725.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03074, over 971489.76 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:32:54,214 INFO [train.py:715] (5/8) Epoch 14, batch 11950, loss[loss=0.1325, simple_loss=0.1989, pruned_loss=0.03305, over 4944.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2083, pruned_loss=0.03096, over 972361.72 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 01:33:33,585 INFO [train.py:715] (5/8) Epoch 14, batch 12000, loss[loss=0.1113, simple_loss=0.1859, pruned_loss=0.0184, over 4822.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03022, over 971488.97 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:33:33,586 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 01:33:43,198 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01067, over 914524.00 frames.
2022-05-08 01:34:22,501 INFO [train.py:715] (5/8) Epoch 14, batch 12050, loss[loss=0.1391, simple_loss=0.2159, pruned_loss=0.03117, over 4692.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03065, over 971942.54 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:35:01,859 INFO [train.py:715] (5/8) Epoch 14, batch 12100, loss[loss=0.1468, simple_loss=0.2232, pruned_loss=0.03513, over 4794.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03079, over 971715.21 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:35:41,277 INFO [train.py:715] (5/8) Epoch 14, batch 12150, loss[loss=0.1279, simple_loss=0.2098, pruned_loss=0.02297, over 4764.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03018, over 971284.26 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 01:36:20,618 INFO [train.py:715] (5/8) Epoch 14, batch 12200, loss[loss=0.1534, simple_loss=0.2328, pruned_loss=0.03696, over 4883.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03063, over 971619.32 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:37:00,487 INFO [train.py:715] (5/8) Epoch 14, batch 12250, loss[loss=0.1589, simple_loss=0.2254, pruned_loss=0.04618, over 4983.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 972699.06 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:37:39,675 INFO [train.py:715] (5/8) Epoch 14, batch 12300, loss[loss=0.1391, simple_loss=0.2037, pruned_loss=0.03724, over 4825.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03118, over 972468.63 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:38:19,197 INFO [train.py:715] (5/8) Epoch 14, batch 12350, loss[loss=0.1294, simple_loss=0.2085, pruned_loss=0.0252, over 4943.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.0315, over 972552.20 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:38:58,798 INFO [train.py:715] (5/8) Epoch 14, batch 12400, loss[loss=0.1154, simple_loss=0.1802, pruned_loss=0.02531, over 4862.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03145, over 972900.25 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 01:39:37,832 INFO [train.py:715] (5/8) Epoch 14, batch 12450, loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02839, over 4814.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03127, over 973828.31 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:40:17,256 INFO [train.py:715] (5/8) Epoch 14, batch 12500, loss[loss=0.1367, simple_loss=0.2057, pruned_loss=0.03384, over 4887.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03102, over 973370.54 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 01:40:57,007 INFO [train.py:715] (5/8) Epoch 14, batch 12550, loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02988, over 4803.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03077, over 973431.30 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 01:41:36,647 INFO [train.py:715] (5/8) Epoch 14, batch 12600, loss[loss=0.152, simple_loss=0.2218, pruned_loss=0.04111, over 4787.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03063, over 972629.63 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:42:15,594 INFO [train.py:715] (5/8) Epoch 14, batch 12650, loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02992, over 4829.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03053, over 972470.89 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 01:42:55,480 INFO [train.py:715] (5/8) Epoch 14, batch 12700, loss[loss=0.128, simple_loss=0.1957, pruned_loss=0.03012, over 4874.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03067, over 971681.49 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:43:35,535 INFO [train.py:715] (5/8) Epoch 14, batch 12750, loss[loss=0.1377, simple_loss=0.2197, pruned_loss=0.0278, over 4916.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03044, over 971870.46 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:44:15,513 INFO [train.py:715] (5/8) Epoch 14, batch 12800, loss[loss=0.1405, simple_loss=0.2187, pruned_loss=0.03119, over 4771.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03053, over 971571.81 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:44:55,315 INFO [train.py:715] (5/8) Epoch 14, batch 12850, loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03095, over 4861.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03055, over 971437.29 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 01:45:35,522 INFO [train.py:715] (5/8) Epoch 14, batch 12900, loss[loss=0.1534, simple_loss=0.2222, pruned_loss=0.04232, over 4906.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03052, over 971269.85 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:46:15,877 INFO [train.py:715] (5/8) Epoch 14, batch 12950, loss[loss=0.1752, simple_loss=0.2552, pruned_loss=0.04763, over 4782.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03123, over 971700.09 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:46:55,835 INFO [train.py:715] (5/8) Epoch 14, batch 13000, loss[loss=0.1199, simple_loss=0.1954, pruned_loss=0.02216, over 4823.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03074, over 972371.95 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:47:36,082 INFO [train.py:715] (5/8) Epoch 14, batch 13050, loss[loss=0.1497, simple_loss=0.2301, pruned_loss=0.03468, over 4915.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03112, over 971309.07 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:48:16,098 INFO [train.py:715] (5/8) Epoch 14, batch 13100, loss[loss=0.1276, simple_loss=0.2017, pruned_loss=0.0268, over 4809.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03113, over 971160.28 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 01:48:56,289 INFO [train.py:715] (5/8) Epoch 14, batch 13150, loss[loss=0.1534, simple_loss=0.2218, pruned_loss=0.04256, over 4890.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.0312, over 971423.16 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 01:49:36,385 INFO [train.py:715] (5/8) Epoch 14, batch 13200, loss[loss=0.1244, simple_loss=0.2023, pruned_loss=0.0233, over 4784.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.03107, over 972372.70 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:50:16,587 INFO [train.py:715] (5/8) Epoch 14, batch 13250, loss[loss=0.1396, simple_loss=0.2087, pruned_loss=0.03527, over 4926.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03108, over 972633.11 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:50:56,840 INFO [train.py:715] (5/8) Epoch 14, batch 13300, loss[loss=0.1249, simple_loss=0.2022, pruned_loss=0.02374, over 4983.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03126, over 972536.14 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 01:51:36,426 INFO [train.py:715] (5/8) Epoch 14, batch 13350, loss[loss=0.1537, simple_loss=0.2163, pruned_loss=0.04559, over 4884.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03113, over 972761.05 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 01:52:15,920 INFO [train.py:715] (5/8) Epoch 14, batch 13400, loss[loss=0.1109, simple_loss=0.185, pruned_loss=0.01841, over 4798.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03089, over 972724.75 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:52:55,516 INFO [train.py:715] (5/8) Epoch 14, batch 13450, loss[loss=0.1293, simple_loss=0.2045, pruned_loss=0.02702, over 4915.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.0309, over 972996.98 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:53:35,075 INFO [train.py:715] (5/8) Epoch 14, batch 13500, loss[loss=0.1418, simple_loss=0.2209, pruned_loss=0.03135, over 4793.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03085, over 973109.76 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:54:14,282 INFO [train.py:715] (5/8) Epoch 14, batch 13550, loss[loss=0.1398, simple_loss=0.2107, pruned_loss=0.0344, over 4803.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 973285.17 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:54:53,676 INFO [train.py:715] (5/8) Epoch 14, batch 13600, loss[loss=0.1077, simple_loss=0.1859, pruned_loss=0.0148, over 4985.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.0303, over 973068.45 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:55:32,970 INFO [train.py:715] (5/8) Epoch 14, batch 13650, loss[loss=0.1306, simple_loss=0.2027, pruned_loss=0.02929, over 4690.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.0304, over 973017.82 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:56:12,538 INFO [train.py:715] (5/8) Epoch 14, batch 13700, loss[loss=0.138, simple_loss=0.2121, pruned_loss=0.03195, over 4935.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03048, over 973785.24 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 01:56:51,589 INFO [train.py:715] (5/8) Epoch 14, batch 13750, loss[loss=0.1344, simple_loss=0.2127, pruned_loss=0.02798, over 4979.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.0303, over 973816.63 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:57:30,924 INFO [train.py:715] (5/8) Epoch 14, batch 13800, loss[loss=0.122, simple_loss=0.1967, pruned_loss=0.0237, over 4932.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02992, over 973604.36 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:58:12,513 INFO [train.py:715] (5/8) Epoch 14, batch 13850, loss[loss=0.1399, simple_loss=0.2244, pruned_loss=0.02772, over 4982.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.0299, over 973175.03 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 01:58:51,819 INFO [train.py:715] (5/8) Epoch 14, batch 13900, loss[loss=0.1184, simple_loss=0.1812, pruned_loss=0.02774, over 4876.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.0306, over 973500.66 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:59:31,446 INFO [train.py:715] (5/8) Epoch 14, batch 13950, loss[loss=0.1375, simple_loss=0.2057, pruned_loss=0.03464, over 4783.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03123, over 973605.90 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:00:10,941 INFO [train.py:715] (5/8) Epoch 14, batch 14000, loss[loss=0.1316, simple_loss=0.208, pruned_loss=0.02757, over 4909.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03071, over 973227.40 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:00:50,380 INFO [train.py:715] (5/8) Epoch 14, batch 14050, loss[loss=0.1163, simple_loss=0.1946, pruned_loss=0.01897, over 4916.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 973143.83 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 02:01:30,044 INFO [train.py:715] (5/8) Epoch 14, batch 14100, loss[loss=0.1251, simple_loss=0.1891, pruned_loss=0.03051, over 4883.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.031, over 973394.80 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:02:09,596 INFO [train.py:715] (5/8) Epoch 14, batch 14150, loss[loss=0.1234, simple_loss=0.194, pruned_loss=0.02637, over 4847.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03105, over 973165.52 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:02:49,094 INFO [train.py:715] (5/8) Epoch 14, batch 14200, loss[loss=0.1404, simple_loss=0.215, pruned_loss=0.03293, over 4695.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03102, over 973217.98 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:03:28,353 INFO [train.py:715] (5/8) Epoch 14, batch 14250, loss[loss=0.1543, simple_loss=0.2186, pruned_loss=0.04498, over 4960.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03101, over 972775.78 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 02:04:08,205 INFO [train.py:715] (5/8) Epoch 14, batch 14300, loss[loss=0.1226, simple_loss=0.1899, pruned_loss=0.0277, over 4810.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03056, over 972140.88 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:04:47,397 INFO [train.py:715] (5/8) Epoch 14, batch 14350, loss[loss=0.1248, simple_loss=0.2121, pruned_loss=0.0187, over 4809.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03054, over 971912.67 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 02:05:26,851 INFO [train.py:715] (5/8) Epoch 14, batch 14400, loss[loss=0.1433, simple_loss=0.2098, pruned_loss=0.03845, over 4939.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.0305, over 972207.17 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:06:06,344 INFO [train.py:715] (5/8) Epoch 14, batch 14450, loss[loss=0.1389, simple_loss=0.2221, pruned_loss=0.02783, over 4960.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03024, over 972100.72 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 02:06:45,901 INFO [train.py:715] (5/8) Epoch 14, batch 14500, loss[loss=0.1146, simple_loss=0.1935, pruned_loss=0.01782, over 4799.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03036, over 972319.79 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:07:25,175 INFO [train.py:715] (5/8) Epoch 14, batch 14550, loss[loss=0.141, simple_loss=0.213, pruned_loss=0.03451, over 4876.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03026, over 972098.52 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:08:04,456 INFO [train.py:715] (5/8) Epoch 14, batch 14600, loss[loss=0.1488, simple_loss=0.2205, pruned_loss=0.03855, over 4819.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03054, over 973242.19 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 02:08:44,677 INFO [train.py:715] (5/8) Epoch 14, batch 14650, loss[loss=0.1496, simple_loss=0.2275, pruned_loss=0.03581, over 4790.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03097, over 973314.90 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 02:09:24,104 INFO [train.py:715] (5/8) Epoch 14, batch 14700, loss[loss=0.1366, simple_loss=0.2081, pruned_loss=0.03256, over 4884.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02999, over 972643.72 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:10:03,915 INFO [train.py:715] (5/8) Epoch 14, batch 14750, loss[loss=0.1302, simple_loss=0.206, pruned_loss=0.02723, over 4829.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.0306, over 972933.21 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:10:43,092 INFO [train.py:715] (5/8) Epoch 14, batch 14800, loss[loss=0.1512, simple_loss=0.2282, pruned_loss=0.03711, over 4909.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03095, over 972591.14 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:11:23,009 INFO [train.py:715] (5/8) Epoch 14, batch 14850, loss[loss=0.1759, simple_loss=0.2524, pruned_loss=0.04973, over 4751.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03087, over 972337.68 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:12:02,551 INFO [train.py:715] (5/8) Epoch 14, batch 14900, loss[loss=0.1069, simple_loss=0.1808, pruned_loss=0.01656, over 4754.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03056, over 971933.51 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:12:41,997 INFO [train.py:715] (5/8) Epoch 14, batch 14950, loss[loss=0.1391, simple_loss=0.2166, pruned_loss=0.03079, over 4984.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03065, over 971108.17 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:13:22,058 INFO [train.py:715] (5/8) Epoch 14, batch 15000, loss[loss=0.1521, simple_loss=0.2322, pruned_loss=0.03594, over 4761.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03115, over 971795.24 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:13:22,058 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 02:13:31,707 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01079, over 914524.00 frames.
2022-05-08 02:14:12,556 INFO [train.py:715] (5/8) Epoch 14, batch 15050, loss[loss=0.1475, simple_loss=0.226, pruned_loss=0.03456, over 4940.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03123, over 972522.07 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:14:52,640 INFO [train.py:715] (5/8) Epoch 14, batch 15100, loss[loss=0.1158, simple_loss=0.193, pruned_loss=0.01929, over 4974.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03108, over 973351.98 frames.], batch size: 28, lr: 1.57e-04
2022-05-08 02:15:33,283 INFO [train.py:715] (5/8) Epoch 14, batch 15150, loss[loss=0.1325, simple_loss=0.2046, pruned_loss=0.03019, over 4967.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03094, over 973407.55 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:16:13,412 INFO [train.py:715] (5/8) Epoch 14, batch 15200, loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03121, over 4951.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03092, over 973707.59 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:16:54,055 INFO [train.py:715] (5/8) Epoch 14, batch 15250, loss[loss=0.1516, simple_loss=0.2185, pruned_loss=0.04229, over 4683.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03085, over 972676.04 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:17:33,930 INFO [train.py:715] (5/8) Epoch 14, batch 15300, loss[loss=0.1524, simple_loss=0.2132, pruned_loss=0.04581, over 4861.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03128, over 973236.49 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:18:13,474 INFO [train.py:715] (5/8) Epoch 14, batch 15350, loss[loss=0.1143, simple_loss=0.1927, pruned_loss=0.01791, over 4915.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03034, over 972993.87 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:18:53,583 INFO [train.py:715] (5/8) Epoch 14, batch 15400, loss[loss=0.1333, simple_loss=0.2066, pruned_loss=0.03001, over 4748.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 973120.53 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:19:32,975 INFO [train.py:715] (5/8) Epoch 14, batch 15450, loss[loss=0.126, simple_loss=0.1883, pruned_loss=0.03187, over 4863.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03023, over 973233.35 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:20:12,213 INFO [train.py:715] (5/8) Epoch 14, batch 15500, loss[loss=0.1273, simple_loss=0.1976, pruned_loss=0.02849, over 4803.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03051, over 973722.78 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:20:51,548 INFO [train.py:715] (5/8) Epoch 14, batch 15550, loss[loss=0.1073, simple_loss=0.1774, pruned_loss=0.01855, over 4919.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03142, over 973552.49 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:21:31,492 INFO [train.py:715] (5/8) Epoch 14, batch 15600, loss[loss=0.1479, simple_loss=0.2263, pruned_loss=0.03468, over 4800.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03071, over 973016.43 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 02:22:10,935 INFO [train.py:715] (5/8) Epoch 14, batch 15650, loss[loss=0.1174, simple_loss=0.1896, pruned_loss=0.02259, over 4793.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03034, over 972860.98 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:22:49,321 INFO [train.py:715] (5/8) Epoch 14, batch 15700, loss[loss=0.1359, simple_loss=0.1947, pruned_loss=0.03851, over 4810.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03038, over 973146.82 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:23:29,530 INFO [train.py:715] (5/8) Epoch 14, batch 15750, loss[loss=0.1249, simple_loss=0.2017, pruned_loss=0.02409, over 4920.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03013, over 973482.73 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:24:09,056 INFO [train.py:715] (5/8) Epoch 14, batch 15800, loss[loss=0.1856, simple_loss=0.2611, pruned_loss=0.05507, over 4847.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03033, over 973842.33 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 02:24:48,295 INFO [train.py:715] (5/8) Epoch 14, batch 15850, loss[loss=0.1484, simple_loss=0.2329, pruned_loss=0.03191, over 4770.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03022, over 973787.08 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 02:25:27,576 INFO [train.py:715] (5/8) Epoch 14, batch 15900, loss[loss=0.123, simple_loss=0.1871, pruned_loss=0.02945, over 4821.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.0299, over 973472.29 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:26:07,617 INFO [train.py:715] (5/8) Epoch 14, batch 15950, loss[loss=0.1496, simple_loss=0.2152, pruned_loss=0.04194, over 4946.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03002, over 973323.66 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:26:47,030 INFO [train.py:715] (5/8) Epoch 14, batch 16000, loss[loss=0.1328, simple_loss=0.1906, pruned_loss=0.03745, over 4829.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03009, over 972955.13 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:27:25,748 INFO [train.py:715] (5/8) Epoch 14, batch 16050, loss[loss=0.1298, simple_loss=0.217, pruned_loss=0.02131, over 4797.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 972942.42 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:28:04,469 INFO [train.py:715] (5/8) Epoch 14, batch 16100, loss[loss=0.1547, simple_loss=0.2277, pruned_loss=0.04083, over 4858.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03038, over 973135.92 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 02:28:42,594 INFO [train.py:715] (5/8) Epoch 14, batch 16150, loss[loss=0.1532, simple_loss=0.2335, pruned_loss=0.03644, over 4952.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03065, over 972592.01 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:29:20,836 INFO [train.py:715] (5/8) Epoch 14, batch 16200, loss[loss=0.1355, simple_loss=0.2085, pruned_loss=0.0313, over 4744.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03079, over 971508.55 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:29:59,439 INFO [train.py:715] (5/8) Epoch 14, batch 16250, loss[loss=0.1324, simple_loss=0.198, pruned_loss=0.03338, over 4865.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03071, over 971530.24 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:30:38,581 INFO [train.py:715] (5/8) Epoch 14, batch 16300, loss[loss=0.1002, simple_loss=0.1677, pruned_loss=0.01632, over 4821.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.0309, over 971453.22 frames.], batch size: 27, lr: 1.57e-04
2022-05-08 02:31:16,532 INFO [train.py:715] (5/8) Epoch 14, batch 16350, loss[loss=0.1476, simple_loss=0.2181, pruned_loss=0.0385, over 4826.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03129, over 971850.20 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 02:31:55,708 INFO [train.py:715] (5/8) Epoch 14, batch 16400, loss[loss=0.13, simple_loss=0.1957, pruned_loss=0.03217, over 4755.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2105, pruned_loss=0.03108, over 971367.85 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:32:35,421 INFO [train.py:715] (5/8) Epoch 14, batch 16450, loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03079, over 4779.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03094, over 971909.96 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:33:14,858 INFO [train.py:715] (5/8) Epoch 14, batch 16500, loss[loss=0.1212, simple_loss=0.1978, pruned_loss=0.02227, over 4878.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03035, over 971795.08 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:33:53,745 INFO [train.py:715] (5/8) Epoch 14, batch 16550, loss[loss=0.1622, simple_loss=0.2302, pruned_loss=0.0471, over 4894.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03057, over 972383.72 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:34:34,123 INFO [train.py:715] (5/8) Epoch 14, batch 16600, loss[loss=0.136, simple_loss=0.2068, pruned_loss=0.03258, over 4769.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03067, over 972471.33 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:35:13,400 INFO [train.py:715] (5/8) Epoch 14, batch 16650, loss[loss=0.1487, simple_loss=0.2211, pruned_loss=0.03818, over 4940.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.0304, over 972443.59 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:35:55,023 INFO [train.py:715] (5/8) Epoch 14, batch 16700, loss[loss=0.1296, simple_loss=0.2071, pruned_loss=0.02604, over 4787.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03027, over 972493.83 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 02:36:34,908 INFO [train.py:715] (5/8) Epoch 14, batch 16750, loss[loss=0.1651, simple_loss=0.228, pruned_loss=0.05107, over 4756.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.0308, over 972701.73 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:37:15,257 INFO [train.py:715] (5/8) Epoch 14, batch 16800, loss[loss=0.1303, simple_loss=0.2103, pruned_loss=0.02517, over 4860.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2101, pruned_loss=0.03086, over 971538.35 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:37:54,768 INFO [train.py:715] (5/8) Epoch 14, batch 16850, loss[loss=0.1499, simple_loss=0.2303, pruned_loss=0.03471, over 4913.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03083, over 972002.61 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:38:34,397 INFO [train.py:715] (5/8) Epoch 14, batch 16900, loss[loss=0.1428, simple_loss=0.2038, pruned_loss=0.04094, over 4965.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03101, over 971904.49 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 02:39:15,370 INFO [train.py:715] (5/8) Epoch 14, batch 16950, loss[loss=0.1309, simple_loss=0.2043, pruned_loss=0.02876, over 4803.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03077, over 972187.28 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:39:56,919 INFO [train.py:715] (5/8) Epoch 14, batch 17000, loss[loss=0.1498, simple_loss=0.2256, pruned_loss=0.03702, over 4854.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03123, over 972798.05 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:40:37,816 INFO [train.py:715] (5/8) Epoch 14, batch 17050, loss[loss=0.1746, simple_loss=0.2475, pruned_loss=0.05083, over 4989.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0308, over 973228.74 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:41:18,911 INFO [train.py:715] (5/8) Epoch 14, batch 17100, loss[loss=0.1503, simple_loss=0.23, pruned_loss=0.03531, over 4884.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03047, over 973090.44 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:42:01,001 INFO [train.py:715] (5/8) Epoch 14, batch 17150, loss[loss=0.13, simple_loss=0.2027, pruned_loss=0.0287, over 4792.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03051, over 973202.23 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:42:41,747 INFO [train.py:715] (5/8) Epoch 14, batch 17200, loss[loss=0.138, simple_loss=0.2257, pruned_loss=0.02519, over 4906.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03013, over 973860.50 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:43:22,726 INFO [train.py:715] (5/8) Epoch 14, batch 17250, loss[loss=0.1259, simple_loss=0.1932, pruned_loss=0.02927, over 4953.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02982, over 972856.17 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:44:04,206 INFO [train.py:715] (5/8) Epoch 14, batch 17300, loss[loss=0.1204, simple_loss=0.1934, pruned_loss=0.02375, over 4885.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03, over 971884.94 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:44:45,866 INFO [train.py:715] (5/8) Epoch 14, batch 17350, loss[loss=0.1243, simple_loss=0.2037, pruned_loss=0.02245, over 4873.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.0304, over 971561.65 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:45:26,237 INFO [train.py:715] (5/8) Epoch 14, batch 17400, loss[loss=0.1186, simple_loss=0.1995, pruned_loss=0.01885, over 4836.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02984, over 972339.89 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 02:46:07,488 INFO [train.py:715] (5/8) Epoch 14, batch 17450, loss[loss=0.1355, simple_loss=0.2173, pruned_loss=0.02679, over 4800.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03015, over 972625.58 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 02:46:49,064 INFO [train.py:715] (5/8) Epoch 14, batch 17500, loss[loss=0.1227, simple_loss=0.1917, pruned_loss=0.02687, over 4975.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 972730.41 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 02:47:29,777 INFO [train.py:715] (5/8) Epoch 14, batch 17550, loss[loss=0.1119, simple_loss=0.1895, pruned_loss=0.01716, over 4810.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03005, over 973100.46 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 02:48:10,327 INFO [train.py:715] (5/8) Epoch 14, batch 17600, loss[loss=0.1189, simple_loss=0.1973, pruned_loss=0.0203, over 4975.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02997, over 972930.42 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:48:52,042 INFO [train.py:715] (5/8) Epoch 14, batch 17650, loss[loss=0.1524, simple_loss=0.2264, pruned_loss=0.03919, over 4973.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03001, over 973021.75 frames.], batch size: 39, lr: 1.56e-04
2022-05-08 02:49:33,166 INFO [train.py:715] (5/8) Epoch 14, batch 17700, loss[loss=0.1255, simple_loss=0.1996, pruned_loss=0.02566, over 4874.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.0298, over 973429.97 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 02:50:13,658 INFO [train.py:715] (5/8) Epoch 14, batch 17750, loss[loss=0.1359, simple_loss=0.2071, pruned_loss=0.03234, over 4976.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03014, over 972579.38 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 02:50:55,018 INFO [train.py:715] (5/8) Epoch 14, batch 17800, loss[loss=0.1337, simple_loss=0.2109, pruned_loss=0.02829, over 4828.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02976, over 972454.48 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:51:35,999 INFO [train.py:715] (5/8) Epoch 14, batch 17850, loss[loss=0.1343, simple_loss=0.2057, pruned_loss=0.03143, over 4900.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03041, over 971899.43 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 02:52:16,749 INFO [train.py:715] (5/8) Epoch 14, batch 17900, loss[loss=0.1554, simple_loss=0.2288, pruned_loss=0.04103, over 4877.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02991, over 972549.24 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 02:52:57,209 INFO [train.py:715] (5/8) Epoch 14, batch 17950, loss[loss=0.1248, simple_loss=0.2077, pruned_loss=0.02098, over 4821.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02979, over 971994.66 frames.], batch size: 27, lr: 1.56e-04
2022-05-08 02:53:38,599 INFO [train.py:715] (5/8) Epoch 14, batch 18000, loss[loss=0.1217, simple_loss=0.1902, pruned_loss=0.02661, over 4890.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03017, over 972294.52 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 02:53:38,600 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 02:53:48,447 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 02:54:29,841 INFO [train.py:715] (5/8) Epoch 14, batch 18050, loss[loss=0.1681, simple_loss=0.2447, pruned_loss=0.04573, over 4800.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03063, over 972608.88 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 02:55:10,986 INFO [train.py:715] (5/8) Epoch 14, batch 18100, loss[loss=0.1819, simple_loss=0.251, pruned_loss=0.05641, over 4889.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03091, over 972888.15 frames.], batch size: 38, lr: 1.56e-04
2022-05-08 02:55:52,584 INFO [train.py:715] (5/8) Epoch 14, batch 18150, loss[loss=0.1242, simple_loss=0.1742, pruned_loss=0.03705, over 4868.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03069, over 972898.46 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 02:56:33,502 INFO [train.py:715] (5/8) Epoch 14, batch 18200, loss[loss=0.1422, simple_loss=0.2095, pruned_loss=0.03741, over 4792.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03047, over 972175.45 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 02:57:15,444 INFO [train.py:715] (5/8) Epoch 14, batch 18250, loss[loss=0.1396, simple_loss=0.216, pruned_loss=0.03156, over 4952.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.0302, over 972780.66 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 02:57:56,894 INFO [train.py:715] (5/8) Epoch 14, batch 18300, loss[loss=0.1417, simple_loss=0.2192, pruned_loss=0.03209, over 4977.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 972661.66 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:58:36,496 INFO [train.py:715] (5/8) Epoch 14, batch 18350, loss[loss=0.1278, simple_loss=0.2083, pruned_loss=0.02368, over 4847.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03075, over 973228.77 frames.], batch size: 20, lr: 1.56e-04
2022-05-08 02:59:17,362 INFO [train.py:715] (5/8) Epoch 14, batch 18400, loss[loss=0.1242, simple_loss=0.191, pruned_loss=0.02869, over 4854.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03131, over 972521.64 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 02:59:57,994 INFO [train.py:715] (5/8) Epoch 14, batch 18450, loss[loss=0.1149, simple_loss=0.1908, pruned_loss=0.01943, over 4939.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03111, over 972497.29 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 03:00:38,225 INFO [train.py:715] (5/8) Epoch 14, batch 18500, loss[loss=0.1336, simple_loss=0.2003, pruned_loss=0.03342, over 4934.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03088, over 972900.42 frames.], batch size: 35, lr: 1.56e-04
2022-05-08 03:01:18,698 INFO [train.py:715] (5/8) Epoch 14, batch 18550, loss[loss=0.131, simple_loss=0.2145, pruned_loss=0.02377, over 4921.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.031, over 972215.31 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:01:59,558 INFO [train.py:715] (5/8) Epoch 14, batch 18600, loss[loss=0.1218, simple_loss=0.2022, pruned_loss=0.02073, over 4982.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03074, over 971937.42 frames.], batch size: 28, lr: 1.56e-04
2022-05-08 03:02:39,865 INFO [train.py:715] (5/8) Epoch 14, batch 18650, loss[loss=0.1242, simple_loss=0.1946, pruned_loss=0.02689, over 4939.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03104, over 972140.41 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:03:20,562 INFO [train.py:715] (5/8) Epoch 14, batch 18700, loss[loss=0.1258, simple_loss=0.2089, pruned_loss=0.02132, over 4951.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03062, over 972175.75 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:04:01,157 INFO [train.py:715] (5/8) Epoch 14, batch 18750, loss[loss=0.1459, simple_loss=0.2315, pruned_loss=0.03014, over 4900.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03046, over 971342.80 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:04:41,115 INFO [train.py:715] (5/8) Epoch 14, batch 18800, loss[loss=0.1623, simple_loss=0.237, pruned_loss=0.04385, over 4741.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03058, over 972570.60 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:05:21,092 INFO [train.py:715] (5/8) Epoch 14, batch 18850, loss[loss=0.1054, simple_loss=0.1894, pruned_loss=0.01067, over 4821.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03066, over 972220.27 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:06:01,851 INFO [train.py:715] (5/8) Epoch 14, batch 18900, loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03691, over 4901.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03076, over 972440.96 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:06:42,899 INFO [train.py:715] (5/8) Epoch 14, batch 18950, loss[loss=0.1297, simple_loss=0.2051, pruned_loss=0.02712, over 4839.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03059, over 973109.92 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:07:23,140 INFO [train.py:715] (5/8) Epoch 14, batch 19000, loss[loss=0.1264, simple_loss=0.2022, pruned_loss=0.02535, over 4780.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03081, over 972318.01 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:08:04,084 INFO [train.py:715] (5/8) Epoch 14, batch 19050, loss[loss=0.1587, simple_loss=0.2388, pruned_loss=0.03924, over 4864.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03077, over 971930.79 frames.], batch size: 20, lr: 1.56e-04
2022-05-08 03:08:45,082 INFO [train.py:715] (5/8) Epoch 14, batch 19100, loss[loss=0.118, simple_loss=0.18, pruned_loss=0.02795, over 4809.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03044, over 971452.66 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 03:09:25,466 INFO [train.py:715] (5/8) Epoch 14, batch 19150, loss[loss=0.1957, simple_loss=0.2436, pruned_loss=0.07388, over 4699.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.0306, over 972251.85 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:10:04,871 INFO [train.py:715] (5/8) Epoch 14, batch 19200, loss[loss=0.1056, simple_loss=0.1742, pruned_loss=0.01853, over 4708.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.03074, over 972350.04 frames.], batch size: 12, lr: 1.56e-04
2022-05-08 03:10:45,992 INFO [train.py:715] (5/8) Epoch 14, batch 19250, loss[loss=0.1201, simple_loss=0.1919, pruned_loss=0.02416, over 4777.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.0308, over 973661.23 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:11:26,904 INFO [train.py:715] (5/8) Epoch 14, batch 19300, loss[loss=0.1155, simple_loss=0.1957, pruned_loss=0.01763, over 4799.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03089, over 973311.19 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:12:06,950 INFO [train.py:715] (5/8) Epoch 14, batch 19350, loss[loss=0.151, simple_loss=0.2192, pruned_loss=0.04136, over 4898.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.0312, over 973311.27 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:12:47,194 INFO [train.py:715] (5/8) Epoch 14, batch 19400, loss[loss=0.1393, simple_loss=0.2174, pruned_loss=0.03062, over 4930.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03118, over 973220.84 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 03:13:28,658 INFO [train.py:715] (5/8) Epoch 14, batch 19450, loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04266, over 4750.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03075, over 972674.20 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:14:08,960 INFO [train.py:715] (5/8) Epoch 14, batch 19500, loss[loss=0.1157, simple_loss=0.1977, pruned_loss=0.01684, over 4921.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03012, over 972032.79 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 03:14:49,607 INFO [train.py:715] (5/8) Epoch 14, batch 19550, loss[loss=0.1228, simple_loss=0.1963, pruned_loss=0.02463, over 4796.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02985, over 971554.09 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:15:30,061 INFO [train.py:715] (5/8) Epoch 14, batch 19600, loss[loss=0.14, simple_loss=0.2118, pruned_loss=0.03416, over 4981.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03007, over 972421.22 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:16:10,998 INFO [train.py:715] (5/8) Epoch 14, batch 19650, loss[loss=0.124, simple_loss=0.2067, pruned_loss=0.02068, over 4825.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.0302, over 972843.70 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:16:51,971 INFO [train.py:715] (5/8) Epoch 14, batch 19700, loss[loss=0.1484, simple_loss=0.2087, pruned_loss=0.04409, over 4949.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03053, over 972920.71 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:17:32,729 INFO [train.py:715] (5/8) Epoch 14, batch 19750, loss[loss=0.142, simple_loss=0.2174, pruned_loss=0.03329, over 4906.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03057, over 972244.63 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:18:13,652 INFO [train.py:715] (5/8) Epoch 14, batch 19800, loss[loss=0.1165, simple_loss=0.1981, pruned_loss=0.01742, over 4817.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03074, over 971616.51 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:18:54,281 INFO [train.py:715] (5/8) Epoch 14, batch 19850, loss[loss=0.1355, simple_loss=0.2067, pruned_loss=0.03216, over 4874.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03039, over 972309.38 frames.], batch size: 38, lr: 1.56e-04
2022-05-08 03:19:35,279 INFO [train.py:715] (5/8) Epoch 14, batch 19900, loss[loss=0.1223, simple_loss=0.1862, pruned_loss=0.02922, over 4953.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02982, over 972845.74 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:20:15,390 INFO [train.py:715] (5/8) Epoch 14, batch 19950, loss[loss=0.1334, simple_loss=0.2015, pruned_loss=0.03269, over 4818.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.0298, over 971995.93 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:20:55,689 INFO [train.py:715] (5/8) Epoch 14, batch 20000, loss[loss=0.1468, simple_loss=0.2125, pruned_loss=0.04056, over 4968.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02983, over 972270.97 frames.], batch size: 39, lr: 1.56e-04
2022-05-08 03:21:35,498 INFO [train.py:715] (5/8) Epoch 14, batch 20050, loss[loss=0.1421, simple_loss=0.2257, pruned_loss=0.02931, over 4964.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02972, over 972126.73 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:22:15,343 INFO [train.py:715] (5/8) Epoch 14, batch 20100, loss[loss=0.1528, simple_loss=0.2286, pruned_loss=0.03848, over 4898.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02966, over 972460.15 frames.], batch size: 39, lr: 1.56e-04
2022-05-08 03:22:55,785 INFO [train.py:715] (5/8) Epoch 14, batch 20150, loss[loss=0.1021, simple_loss=0.1722, pruned_loss=0.01601, over 4791.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02982, over 973497.04 frames.], batch size: 12, lr: 1.56e-04
2022-05-08 03:23:35,885 INFO [train.py:715] (5/8) Epoch 14, batch 20200, loss[loss=0.123, simple_loss=0.2125, pruned_loss=0.01678, over 4957.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.0299, over 973438.01 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:24:16,357 INFO [train.py:715] (5/8) Epoch 14, batch 20250, loss[loss=0.1493, simple_loss=0.2253, pruned_loss=0.03667, over 4980.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.0298, over 973101.89 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:24:56,502 INFO [train.py:715] (5/8) Epoch 14, batch 20300, loss[loss=0.1187, simple_loss=0.1925, pruned_loss=0.02246, over 4911.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02993, over 973286.91 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 03:25:37,279 INFO [train.py:715] (5/8) Epoch 14, batch 20350, loss[loss=0.1232, simple_loss=0.19, pruned_loss=0.02823, over 4900.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02997, over 973310.53 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:26:17,609 INFO [train.py:715] (5/8) Epoch 14, batch 20400, loss[loss=0.1273, simple_loss=0.1988, pruned_loss=0.02788, over 4960.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.0296, over 972565.77 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:26:58,058 INFO [train.py:715] (5/8) Epoch 14, batch 20450, loss[loss=0.1135, simple_loss=0.1772, pruned_loss=0.02488, over 4880.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02938, over 972355.55 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:27:39,215 INFO [train.py:715] (5/8) Epoch 14, batch 20500, loss[loss=0.1258, simple_loss=0.2079, pruned_loss=0.02188, over 4933.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02962, over 972763.65 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:28:19,572 INFO [train.py:715] (5/8) Epoch 14, batch 20550, loss[loss=0.1367, simple_loss=0.2206, pruned_loss=0.02642, over 4908.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02995, over 972116.92 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:29:00,472 INFO [train.py:715] (5/8) Epoch 14, batch 20600, loss[loss=0.1117, simple_loss=0.1881, pruned_loss=0.01765, over 4983.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 972178.17 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:29:41,268 INFO [train.py:715] (5/8) Epoch 14, batch 20650, loss[loss=0.12, simple_loss=0.1975, pruned_loss=0.02127, over 4777.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02964, over 972180.41 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:30:22,920 INFO [train.py:715] (5/8) Epoch 14, batch 20700, loss[loss=0.125, simple_loss=0.2014, pruned_loss=0.02428, over 4985.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02991, over 971715.48 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:31:03,258 INFO [train.py:715] (5/8) Epoch 14, batch 20750, loss[loss=0.1265, simple_loss=0.2055, pruned_loss=0.02377, over 4938.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 971826.51 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 03:31:43,457 INFO [train.py:715] (5/8) Epoch 14, batch 20800, loss[loss=0.1161, simple_loss=0.1953, pruned_loss=0.01847, over 4818.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03028, over 971958.43 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:32:24,157 INFO [train.py:715] (5/8) Epoch 14, batch 20850, loss[loss=0.1423, simple_loss=0.2195, pruned_loss=0.03254, over 4980.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03041, over 973331.95 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:33:04,700 INFO [train.py:715] (5/8) Epoch 14, batch 20900, loss[loss=0.1238, simple_loss=0.1945, pruned_loss=0.02658, over 4797.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03063, over 973256.32 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:33:45,367 INFO [train.py:715] (5/8) Epoch 14, batch 20950, loss[loss=0.133, simple_loss=0.2018, pruned_loss=0.03207, over 4842.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03063, over 973385.30 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 03:34:25,916 INFO [train.py:715] (5/8) Epoch 14, batch 21000, loss[loss=0.1566, simple_loss=0.2129, pruned_loss=0.05017, over 4722.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03074, over 973220.02 frames.], batch size: 12, lr: 1.56e-04
2022-05-08 03:34:25,916 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 03:34:37,000 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.0107, over 914524.00 frames.
2022-05-08 03:35:17,901 INFO [train.py:715] (5/8) Epoch 14, batch 21050, loss[loss=0.1549, simple_loss=0.235, pruned_loss=0.03735, over 4910.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03103, over 972595.46 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:35:58,606 INFO [train.py:715] (5/8) Epoch 14, batch 21100, loss[loss=0.1566, simple_loss=0.2306, pruned_loss=0.04129, over 4909.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03111, over 971956.15 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:36:39,417 INFO [train.py:715] (5/8) Epoch 14, batch 21150, loss[loss=0.1272, simple_loss=0.2073, pruned_loss=0.02358, over 4965.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03088, over 972582.72 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:37:18,913 INFO [train.py:715] (5/8) Epoch 14, batch 21200, loss[loss=0.1104, simple_loss=0.186, pruned_loss=0.0174, over 4893.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 971941.48 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:37:59,327 INFO [train.py:715] (5/8) Epoch 14, batch 21250, loss[loss=0.1262, simple_loss=0.1948, pruned_loss=0.02879, over 4820.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03094, over 972174.06 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:38:39,034 INFO [train.py:715] (5/8) Epoch 14, batch 21300, loss[loss=0.1276, simple_loss=0.2011, pruned_loss=0.02701, over 4763.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03109, over 972619.68 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:39:17,956 INFO [train.py:715] (5/8) Epoch 14, batch 21350, loss[loss=0.1751, simple_loss=0.2406, pruned_loss=0.05481, over 4844.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 972905.30 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:39:58,397 INFO [train.py:715] (5/8) Epoch 14, batch 21400, loss[loss=0.1304, simple_loss=0.1954, pruned_loss=0.03264, over 4936.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03012, over 973041.89 frames.], batch size: 35, lr: 1.56e-04
2022-05-08 03:40:38,643 INFO [train.py:715] (5/8) Epoch 14, batch 21450, loss[loss=0.1435, simple_loss=0.2201, pruned_loss=0.03345, over 4754.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03038, over 972678.19 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:41:18,060 INFO [train.py:715] (5/8) Epoch 14, batch 21500, loss[loss=0.135, simple_loss=0.2234, pruned_loss=0.02334, over 4810.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03009, over 972026.48 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:41:57,079 INFO [train.py:715] (5/8) Epoch 14, batch 21550, loss[loss=0.1298, simple_loss=0.2102, pruned_loss=0.02466, over 4794.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02979, over 972046.16 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:42:37,070 INFO [train.py:715] (5/8) Epoch 14, batch 21600, loss[loss=0.1308, simple_loss=0.198, pruned_loss=0.03177, over 4746.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03024, over 972399.82 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:43:16,844 INFO [train.py:715] (5/8) Epoch 14, batch 21650, loss[loss=0.1158, simple_loss=0.1862, pruned_loss=0.02266, over 4714.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02954, over 972166.82 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:43:55,946 INFO [train.py:715] (5/8) Epoch 14, batch 21700, loss[loss=0.1541, simple_loss=0.2268, pruned_loss=0.04069, over 4689.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02974, over 972339.43 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:44:36,357 INFO [train.py:715] (5/8) Epoch 14, batch 21750, loss[loss=0.1526, simple_loss=0.2157, pruned_loss=0.04475, over 4858.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03017, over 972708.87 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:45:16,752 INFO [train.py:715] (5/8) Epoch 14, batch 21800, loss[loss=0.133, simple_loss=0.2043, pruned_loss=0.03082, over 4960.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03045, over 972677.66 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:45:56,146 INFO [train.py:715] (5/8) Epoch 14, batch 21850, loss[loss=0.1505, simple_loss=0.2237, pruned_loss=0.03872, over 4871.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03013, over 971822.33 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:46:35,751 INFO [train.py:715] (5/8) Epoch 14, batch 21900, loss[loss=0.144, simple_loss=0.2111, pruned_loss=0.03845, over 4704.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03033, over 971942.54 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:47:16,023 INFO [train.py:715] (5/8) Epoch 14, batch 21950, loss[loss=0.1408, simple_loss=0.2145, pruned_loss=0.03358, over 4793.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.0304, over 972536.47 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:47:55,285 INFO [train.py:715] (5/8) Epoch 14, batch 22000, loss[loss=0.1442, simple_loss=0.2256, pruned_loss=0.03138, over 4945.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03011, over 972645.51 frames.], batch size: 35, lr: 1.56e-04
2022-05-08 03:48:34,005 INFO [train.py:715] (5/8) Epoch 14, batch 22050, loss[loss=0.134, simple_loss=0.2158, pruned_loss=0.02609, over 4828.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.0301, over 972303.03 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:49:14,106 INFO [train.py:715] (5/8) Epoch 14, batch 22100, loss[loss=0.1502, simple_loss=0.2215, pruned_loss=0.03948, over 4914.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02999, over 972510.69 frames.], batch size: 39, lr: 1.56e-04
2022-05-08 03:49:53,816 INFO [train.py:715] (5/8) Epoch 14, batch 22150, loss[loss=0.1115, simple_loss=0.1869, pruned_loss=0.01803, over 4982.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.029, over 971919.68 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:50:32,843 INFO [train.py:715] (5/8) Epoch 14, batch 22200, loss[loss=0.1309, simple_loss=0.2021, pruned_loss=0.02989, over 4695.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.029, over 971868.26 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:51:12,587 INFO [train.py:715] (5/8) Epoch 14, batch 22250, loss[loss=0.164, simple_loss=0.2387, pruned_loss=0.04465, over 4918.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02957, over 972448.74 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:51:52,762 INFO [train.py:715] (5/8) Epoch 14, batch 22300, loss[loss=0.1528, simple_loss=0.2272, pruned_loss=0.03919, over 4901.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03017, over 972385.56 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:52:32,250 INFO [train.py:715] (5/8) Epoch 14, batch 22350, loss[loss=0.1462, simple_loss=0.2198, pruned_loss=0.0363, over 4833.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03005, over 972254.74 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:53:11,401 INFO [train.py:715] (5/8) Epoch 14, batch 22400, loss[loss=0.1336, simple_loss=0.1984, pruned_loss=0.03441, over 4849.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 972340.11 frames.], batch size: 34, lr: 1.56e-04
2022-05-08 03:53:51,748 INFO [train.py:715] (5/8) Epoch 14, batch 22450, loss[loss=0.1613, simple_loss=0.224, pruned_loss=0.04927, over 4747.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02988, over 971843.11 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:54:31,159 INFO [train.py:715] (5/8) Epoch 14, batch 22500, loss[loss=0.1729, simple_loss=0.2552, pruned_loss=0.04526, over 4921.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03041, over 971465.83 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:55:10,455 INFO [train.py:715] (5/8) Epoch 14, batch 22550, loss[loss=0.1168, simple_loss=0.1907, pruned_loss=0.02139, over 4825.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 971374.37 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:55:50,811 INFO [train.py:715] (5/8) Epoch 14, batch 22600, loss[loss=0.1623, simple_loss=0.2296, pruned_loss=0.04744, over 4945.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03097, over 971014.14 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:56:31,695 INFO [train.py:715] (5/8) Epoch 14, batch 22650, loss[loss=0.1304, simple_loss=0.19, pruned_loss=0.03543, over 4764.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03094, over 972191.63 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:57:11,531 INFO [train.py:715] (5/8) Epoch 14, batch 22700, loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03836, over 4864.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03116, over 972610.27 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:57:50,665 INFO [train.py:715] (5/8) Epoch 14, batch 22750, loss[loss=0.1435, simple_loss=0.2166, pruned_loss=0.03515, over 4953.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03105, over 973199.15 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:58:31,998 INFO [train.py:715] (5/8) Epoch 14, batch 22800, loss[loss=0.1371, simple_loss=0.2202, pruned_loss=0.02705, over 4779.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.0309, over 972849.07 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:59:12,915 INFO [train.py:715] (5/8) Epoch 14, batch 22850, loss[loss=0.1371, simple_loss=0.215, pruned_loss=0.02961, over 4832.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03131, over 972536.94 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:59:53,204 INFO [train.py:715] (5/8) Epoch 14, batch 22900, loss[loss=0.1386, simple_loss=0.2147, pruned_loss=0.03127, over 4942.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03107, over 972181.35 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 04:00:33,077 INFO [train.py:715] (5/8) Epoch 14, batch 22950, loss[loss=0.1433, simple_loss=0.2137, pruned_loss=0.03643, over 4792.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03145, over 971880.68 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 04:01:13,582 INFO [train.py:715] (5/8) Epoch 14, batch 23000, loss[loss=0.1143, simple_loss=0.183, pruned_loss=0.02285, over 4793.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.0317, over 971400.86 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 04:01:53,098 INFO [train.py:715] (5/8) Epoch 14, batch 23050, loss[loss=0.1436, simple_loss=0.2214, pruned_loss=0.03295, over 4856.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03152, over 971190.64 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 04:02:32,412 INFO [train.py:715] (5/8) Epoch 14, batch 23100, loss[loss=0.1238, simple_loss=0.1969, pruned_loss=0.02533, over 4792.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03129, over 970433.63 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 04:03:13,067 INFO [train.py:715] (5/8) Epoch 14, batch 23150, loss[loss=0.1089, simple_loss=0.187, pruned_loss=0.01534, over 4955.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03092, over 970625.64 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 04:03:54,319 INFO [train.py:715] (5/8) Epoch 14, batch 23200, loss[loss=0.1395, simple_loss=0.2081, pruned_loss=0.03542, over 4798.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03075, over 971433.15 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 04:04:33,064 INFO [train.py:715] (5/8) Epoch 14, batch 23250, loss[loss=0.1331, simple_loss=0.2037, pruned_loss=0.03126, over 4971.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03091, over 971668.78 frames.], batch size: 35, lr: 1.56e-04
2022-05-08 04:05:13,475 INFO [train.py:715] (5/8) Epoch 14, batch 23300, loss[loss=0.1346, simple_loss=0.2121, pruned_loss=0.02856, over 4959.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03053, over 972098.13 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 04:05:54,159 INFO [train.py:715] (5/8) Epoch 14, batch 23350, loss[loss=0.1205, simple_loss=0.1928, pruned_loss=0.02405, over 4979.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03021, over 972367.68 frames.], batch size: 28, lr: 1.56e-04
2022-05-08 04:06:33,754 INFO [train.py:715] (5/8) Epoch 14, batch 23400, loss[loss=0.1444, simple_loss=0.211, pruned_loss=0.03894, over 4793.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03066, over 972152.66 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 04:07:12,801 INFO [train.py:715] (5/8) Epoch 14, batch 23450, loss[loss=0.1422, simple_loss=0.2225, pruned_loss=0.03093, over 4964.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03094, over 972992.66 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 04:07:53,395 INFO [train.py:715] (5/8) Epoch 14, batch 23500, loss[loss=0.1326, simple_loss=0.212, pruned_loss=0.02664, over 4816.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03083, over 973308.84 frames.], batch size: 27, lr: 1.56e-04
2022-05-08 04:08:34,057 INFO [train.py:715] (5/8) Epoch 14, batch 23550, loss[loss=0.1554, simple_loss=0.2337, pruned_loss=0.0385, over 4896.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03072, over 973458.37 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 04:09:13,317 INFO [train.py:715] (5/8) Epoch 14, batch 23600, loss[loss=0.161, simple_loss=0.2221, pruned_loss=0.04992, over 4986.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03065, over 973235.31 frames.], batch size: 31, lr: 1.56e-04
2022-05-08 04:09:52,598 INFO [train.py:715] (5/8) Epoch 14, batch 23650, loss[loss=0.1495, simple_loss=0.223, pruned_loss=0.03802, over 4944.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03065, over 972616.61 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 04:10:32,136 INFO [train.py:715] (5/8) Epoch 14, batch 23700, loss[loss=0.1498, simple_loss=0.227, pruned_loss=0.03626, over 4949.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03075, over 972813.66 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 04:11:11,199 INFO [train.py:715] (5/8) Epoch 14, batch 23750, loss[loss=0.1185, simple_loss=0.1928, pruned_loss=0.0221, over 4880.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03089, over 973120.24 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 04:11:50,481 INFO [train.py:715] (5/8) Epoch 14, batch 23800, loss[loss=0.1767, simple_loss=0.2406, pruned_loss=0.0564, over 4782.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03173, over 973059.44 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 04:12:30,655 INFO [train.py:715] (5/8) Epoch 14, batch 23850, loss[loss=0.1317, simple_loss=0.2038, pruned_loss=0.02976, over 4898.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03167, over 972881.49 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 04:13:10,487 INFO [train.py:715] (5/8) Epoch 14, batch 23900, loss[loss=0.1425, simple_loss=0.2199, pruned_loss=0.03258, over 4770.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.0314, over 972922.77 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 04:13:49,736 INFO [train.py:715] (5/8) Epoch 14, batch 23950, loss[loss=0.1689, simple_loss=0.2342, pruned_loss=0.05184, over 4847.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03176, over 972957.29 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:14:30,059 INFO [train.py:715] (5/8) Epoch 14, batch 24000, loss[loss=0.133, simple_loss=0.2054, pruned_loss=0.03032, over 4776.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03172, over 972508.86 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:14:30,060 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 04:14:41,438 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 04:15:21,380 INFO [train.py:715] (5/8) Epoch 14, batch 24050, loss[loss=0.1273, simple_loss=0.2069, pruned_loss=0.02382, over 4793.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03133, over 973459.13 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 04:16:02,432 INFO [train.py:715] (5/8) Epoch 14, batch 24100, loss[loss=0.1516, simple_loss=0.2184, pruned_loss=0.04236, over 4802.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03141, over 973261.01 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:16:41,512 INFO [train.py:715] (5/8) Epoch 14, batch 24150, loss[loss=0.133, simple_loss=0.2109, pruned_loss=0.0275, over 4943.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03146, over 973204.18 frames.], batch size: 23, lr: 1.55e-04
2022-05-08 04:17:21,101 INFO [train.py:715] (5/8) Epoch 14, batch 24200, loss[loss=0.1178, simple_loss=0.1944, pruned_loss=0.0206, over 4833.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03139, over 973288.52 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:18:01,395 INFO [train.py:715] (5/8) Epoch 14, batch 24250, loss[loss=0.132, simple_loss=0.2121, pruned_loss=0.02593, over 4854.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03058, over 971988.27 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 04:18:41,642 INFO [train.py:715] (5/8) Epoch 14, batch 24300, loss[loss=0.1143, simple_loss=0.1968, pruned_loss=0.01592, over 4960.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03076, over 972053.54 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:19:20,604 INFO [train.py:715] (5/8) Epoch 14, batch 24350, loss[loss=0.13, simple_loss=0.2089, pruned_loss=0.02556, over 4865.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2101, pruned_loss=0.03068, over 972067.52 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 04:20:01,378 INFO [train.py:715] (5/8) Epoch 14, batch 24400, loss[loss=0.1409, simple_loss=0.2198, pruned_loss=0.03102, over 4923.00 frames.], tot_loss[loss=0.1354, simple_loss=0.21, pruned_loss=0.03043, over 972784.12 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:20:43,004 INFO [train.py:715] (5/8) Epoch 14, batch 24450, loss[loss=0.133, simple_loss=0.2039, pruned_loss=0.03101, over 4767.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2095, pruned_loss=0.03012, over 972936.40 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:21:22,337 INFO [train.py:715] (5/8) Epoch 14, batch 24500, loss[loss=0.1367, simple_loss=0.2119, pruned_loss=0.03076, over 4905.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03007, over 972621.98 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:22:02,598 INFO [train.py:715] (5/8) Epoch 14, batch 24550, loss[loss=0.1447, simple_loss=0.2222, pruned_loss=0.03365, over 4921.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03027, over 972292.94 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:22:43,757 INFO [train.py:715] (5/8) Epoch 14, batch 24600, loss[loss=0.1329, simple_loss=0.2112, pruned_loss=0.02732, over 4861.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03015, over 972676.35 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 04:23:25,374 INFO [train.py:715] (5/8) Epoch 14, batch 24650, loss[loss=0.1382, simple_loss=0.206, pruned_loss=0.03522, over 4866.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03072, over 971998.62 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:24:07,555 INFO [train.py:715] (5/8) Epoch 14, batch 24700, loss[loss=0.1493, simple_loss=0.2101, pruned_loss=0.04423, over 4914.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03078, over 972021.52 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:24:48,462 INFO [train.py:715] (5/8) Epoch 14, batch 24750, loss[loss=0.1321, simple_loss=0.202, pruned_loss=0.03113, over 4828.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.0308, over 971267.48 frames.], batch size: 26, lr: 1.55e-04
2022-05-08 04:25:30,060 INFO [train.py:715] (5/8) Epoch 14, batch 24800, loss[loss=0.1368, simple_loss=0.2136, pruned_loss=0.02996, over 4911.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03052, over 971775.74 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:26:10,635 INFO [train.py:715] (5/8) Epoch 14, batch 24850, loss[loss=0.121, simple_loss=0.2056, pruned_loss=0.0182, over 4884.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03061, over 972414.55 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:26:50,219 INFO [train.py:715] (5/8) Epoch 14, batch 24900, loss[loss=0.1352, simple_loss=0.2049, pruned_loss=0.03274, over 4887.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03031, over 973686.63 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 04:27:31,158 INFO [train.py:715] (5/8) Epoch 14, batch 24950, loss[loss=0.1735, simple_loss=0.2516, pruned_loss=0.04766, over 4918.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03004, over 973462.56 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:28:12,055 INFO [train.py:715] (5/8) Epoch 14, batch 25000, loss[loss=0.1289, simple_loss=0.2016, pruned_loss=0.02811, over 4969.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03026, over 972974.90 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:28:51,323 INFO [train.py:715] (5/8) Epoch 14, batch 25050, loss[loss=0.1385, simple_loss=0.2108, pruned_loss=0.03312, over 4978.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03021, over 972683.87 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:29:32,179 INFO [train.py:715] (5/8) Epoch 14, batch 25100, loss[loss=0.119, simple_loss=0.1997, pruned_loss=0.01909, over 4870.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02998, over 971908.87 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:30:13,134 INFO [train.py:715] (5/8) Epoch 14, batch 25150, loss[loss=0.1069, simple_loss=0.1798, pruned_loss=0.017, over 4868.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02957, over 971959.14 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 04:30:53,336 INFO [train.py:715] (5/8) Epoch 14, batch 25200, loss[loss=0.1211, simple_loss=0.1954, pruned_loss=0.0234, over 4780.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02968, over 971359.22 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:31:31,961 INFO [train.py:715] (5/8) Epoch 14, batch 25250, loss[loss=0.173, simple_loss=0.2394, pruned_loss=0.05326, over 4792.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03003, over 970974.99 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:32:12,613 INFO [train.py:715] (5/8) Epoch 14, batch 25300, loss[loss=0.1574, simple_loss=0.2252, pruned_loss=0.04484, over 4753.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03015, over 970780.51 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:32:53,032 INFO [train.py:715] (5/8) Epoch 14, batch 25350, loss[loss=0.1325, simple_loss=0.2039, pruned_loss=0.03053, over 4879.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2068, pruned_loss=0.03003, over 971725.98 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:33:31,586 INFO [train.py:715] (5/8) Epoch 14, batch 25400, loss[loss=0.1369, simple_loss=0.2074, pruned_loss=0.03316, over 4854.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.0306, over 971557.29 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:34:11,984 INFO [train.py:715] (5/8) Epoch 14, batch 25450, loss[loss=0.1447, simple_loss=0.2149, pruned_loss=0.03728, over 4689.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03031, over 972291.28 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:34:52,385 INFO [train.py:715] (5/8) Epoch 14, batch 25500, loss[loss=0.1248, simple_loss=0.2078, pruned_loss=0.02089, over 4789.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02989, over 972098.01 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 04:35:31,817 INFO [train.py:715] (5/8) Epoch 14, batch 25550, loss[loss=0.1479, simple_loss=0.2252, pruned_loss=0.03525, over 4747.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02988, over 971478.53 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:36:10,559 INFO [train.py:715] (5/8) Epoch 14, batch 25600, loss[loss=0.1553, simple_loss=0.2198, pruned_loss=0.04538, over 4985.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03002, over 971631.36 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:36:50,632 INFO [train.py:715] (5/8) Epoch 14, batch 25650, loss[loss=0.1368, simple_loss=0.2132, pruned_loss=0.03013, over 4804.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03014, over 971504.53 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 04:37:30,745 INFO [train.py:715] (5/8) Epoch 14, batch 25700, loss[loss=0.1044, simple_loss=0.1674, pruned_loss=0.02075, over 4878.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03017, over 970698.89 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 04:38:09,213 INFO [train.py:715] (5/8) Epoch 14, batch 25750, loss[loss=0.1216, simple_loss=0.2051, pruned_loss=0.01908, over 4908.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 970700.44 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:38:48,530 INFO [train.py:715] (5/8) Epoch 14, batch 25800, loss[loss=0.1463, simple_loss=0.2221, pruned_loss=0.03524, over 4904.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03056, over 971583.79 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 04:39:28,743 INFO [train.py:715] (5/8) Epoch 14, batch 25850, loss[loss=0.1046, simple_loss=0.1788, pruned_loss=0.01517, over 4905.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03011, over 971115.47 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:40:07,961 INFO [train.py:715] (5/8) Epoch 14, batch 25900, loss[loss=0.1336, simple_loss=0.2096, pruned_loss=0.02876, over 4848.00 frames.], tot_loss[loss=0.1336, simple_loss=0.207, pruned_loss=0.03004, over 970814.86 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:40:46,739 INFO [train.py:715] (5/8) Epoch 14, batch 25950, loss[loss=0.1427, simple_loss=0.2183, pruned_loss=0.03357, over 4973.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03024, over 971392.84 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:41:26,884 INFO [train.py:715] (5/8) Epoch 14, batch 26000, loss[loss=0.1114, simple_loss=0.1779, pruned_loss=0.02246, over 4690.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03053, over 970669.31 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:42:06,870 INFO [train.py:715] (5/8) Epoch 14, batch 26050, loss[loss=0.161, simple_loss=0.2325, pruned_loss=0.04478, over 4969.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.0304, over 971040.57 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:42:44,780 INFO [train.py:715] (5/8) Epoch 14, batch 26100, loss[loss=0.1422, simple_loss=0.2138, pruned_loss=0.03531, over 4815.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03035, over 970897.08 frames.], batch size: 27, lr: 1.55e-04
2022-05-08 04:43:24,714 INFO [train.py:715] (5/8) Epoch 14, batch 26150, loss[loss=0.1393, simple_loss=0.207, pruned_loss=0.03581, over 4813.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03024, over 971075.46 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:44:05,197 INFO [train.py:715] (5/8) Epoch 14, batch 26200, loss[loss=0.1057, simple_loss=0.1785, pruned_loss=0.01638, over 4831.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02987, over 971126.64 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:44:44,004 INFO [train.py:715] (5/8) Epoch 14, batch 26250, loss[loss=0.1518, simple_loss=0.221, pruned_loss=0.0413, over 4857.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.0296, over 971069.64 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 04:45:23,184 INFO [train.py:715] (5/8) Epoch 14, batch 26300, loss[loss=0.1704, simple_loss=0.2364, pruned_loss=0.05221, over 4734.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.0304, over 971225.35 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:46:03,661 INFO [train.py:715] (5/8) Epoch 14, batch 26350, loss[loss=0.1403, simple_loss=0.2203, pruned_loss=0.0302, over 4979.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03024, over 971442.05 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:46:43,191 INFO [train.py:715] (5/8) Epoch 14, batch 26400, loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02811, over 4808.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 971291.44 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:47:21,823 INFO [train.py:715] (5/8) Epoch 14, batch 26450, loss[loss=0.1387, simple_loss=0.2022, pruned_loss=0.03762, over 4754.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02986, over 971560.36 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:48:02,183 INFO [train.py:715] (5/8) Epoch 14, batch 26500, loss[loss=0.1071, simple_loss=0.1791, pruned_loss=0.01753, over 4953.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02975, over 971489.84 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:48:42,600 INFO [train.py:715] (5/8) Epoch 14, batch 26550, loss[loss=0.1175, simple_loss=0.198, pruned_loss=0.01847, over 4842.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 971833.30 frames.], batch size: 26, lr: 1.55e-04
2022-05-08 04:49:21,894 INFO [train.py:715] (5/8) Epoch 14, batch 26600, loss[loss=0.1272, simple_loss=0.2055, pruned_loss=0.02447, over 4988.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02956, over 971718.00 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 04:50:00,866 INFO [train.py:715] (5/8) Epoch 14, batch 26650, loss[loss=0.1344, simple_loss=0.215, pruned_loss=0.02685, over 4901.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 972819.16 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 04:50:41,181 INFO [train.py:715] (5/8) Epoch 14, batch 26700, loss[loss=0.1448, simple_loss=0.2174, pruned_loss=0.03608, over 4695.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.0294, over 972431.65 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:51:21,681 INFO [train.py:715] (5/8) Epoch 14, batch 26750, loss[loss=0.1228, simple_loss=0.204, pruned_loss=0.02082, over 4834.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02929, over 972123.91 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:52:00,698 INFO [train.py:715] (5/8) Epoch 14, batch 26800, loss[loss=0.1177, simple_loss=0.197, pruned_loss=0.01924, over 4746.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02965, over 971703.02 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:52:40,480 INFO [train.py:715] (5/8) Epoch 14, batch 26850, loss[loss=0.1277, simple_loss=0.2018, pruned_loss=0.02678, over 4853.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02961, over 971932.84 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:53:20,915 INFO [train.py:715] (5/8) Epoch 14, batch 26900, loss[loss=0.141, simple_loss=0.2069, pruned_loss=0.03757, over 4746.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02985, over 971791.90 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:54:00,758 INFO [train.py:715] (5/8) Epoch 14, batch 26950, loss[loss=0.1199, simple_loss=0.1926, pruned_loss=0.0236, over 4931.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02997, over 971998.83 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 04:54:39,964 INFO [train.py:715] (5/8) Epoch 14, batch 27000, loss[loss=0.159, simple_loss=0.23, pruned_loss=0.04396, over 4781.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03107, over 972222.41 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:54:39,965 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 04:54:49,613 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1049, simple_loss=0.1886, pruned_loss=0.01053, over 914524.00 frames.
2022-05-08 04:55:29,145 INFO [train.py:715] (5/8) Epoch 14, batch 27050, loss[loss=0.1623, simple_loss=0.239, pruned_loss=0.04276, over 4919.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 972400.05 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:56:09,800 INFO [train.py:715] (5/8) Epoch 14, batch 27100, loss[loss=0.1441, simple_loss=0.2171, pruned_loss=0.03548, over 4946.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03074, over 972833.96 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:56:50,327 INFO [train.py:715] (5/8) Epoch 14, batch 27150, loss[loss=0.1283, simple_loss=0.2026, pruned_loss=0.02699, over 4788.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03111, over 973124.22 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:57:29,047 INFO [train.py:715] (5/8) Epoch 14, batch 27200, loss[loss=0.1171, simple_loss=0.1936, pruned_loss=0.02037, over 4920.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03092, over 972355.61 frames.], batch size: 23, lr: 1.55e-04
2022-05-08 04:58:08,435 INFO [train.py:715] (5/8) Epoch 14, batch 27250, loss[loss=0.1372, simple_loss=0.216, pruned_loss=0.02915, over 4764.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03112, over 971619.04 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:58:48,575 INFO [train.py:715] (5/8) Epoch 14, batch 27300, loss[loss=0.1282, simple_loss=0.2103, pruned_loss=0.02304, over 4963.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03137, over 972006.35 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:59:28,191 INFO [train.py:715] (5/8) Epoch 14, batch 27350, loss[loss=0.1377, simple_loss=0.2123, pruned_loss=0.0315, over 4883.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03093, over 972847.54 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:00:06,588 INFO [train.py:715] (5/8) Epoch 14, batch 27400, loss[loss=0.121, simple_loss=0.1945, pruned_loss=0.02373, over 4768.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2096, pruned_loss=0.03055, over 972894.10 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:00:46,867 INFO [train.py:715] (5/8) Epoch 14, batch 27450, loss[loss=0.1355, simple_loss=0.2032, pruned_loss=0.03392, over 4845.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03068, over 973117.84 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:01:26,695 INFO [train.py:715] (5/8) Epoch 14, batch 27500, loss[loss=0.1569, simple_loss=0.2344, pruned_loss=0.03976, over 4982.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2098, pruned_loss=0.03045, over 973004.01 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:02:05,455 INFO [train.py:715] (5/8) Epoch 14, batch 27550, loss[loss=0.2476, simple_loss=0.2854, pruned_loss=0.1049, over 4913.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 973514.49 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 05:02:45,161 INFO [train.py:715] (5/8) Epoch 14, batch 27600, loss[loss=0.1107, simple_loss=0.1897, pruned_loss=0.01583, over 4950.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 972939.92 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 05:03:25,490 INFO [train.py:715] (5/8) Epoch 14, batch 27650, loss[loss=0.1392, simple_loss=0.2162, pruned_loss=0.03109, over 4731.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03112, over 972353.10 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:04:04,753 INFO [train.py:715] (5/8) Epoch 14, batch 27700, loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03807, over 4842.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 972474.70 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:04:43,281 INFO [train.py:715] (5/8) Epoch 14, batch 27750, loss[loss=0.1226, simple_loss=0.198, pruned_loss=0.02366, over 4936.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.031, over 972843.53 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 05:05:23,450 INFO [train.py:715] (5/8) Epoch 14, batch 27800, loss[loss=0.123, simple_loss=0.199, pruned_loss=0.02349, over 4944.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 973298.91 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 05:06:03,187 INFO [train.py:715] (5/8) Epoch 14, batch 27850, loss[loss=0.1475, simple_loss=0.2108, pruned_loss=0.04207, over 4808.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03082, over 973185.83 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 05:06:41,701 INFO [train.py:715] (5/8) Epoch 14, batch 27900, loss[loss=0.1359, simple_loss=0.1963, pruned_loss=0.03777, over 4862.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03056, over 973537.40 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 05:07:21,725 INFO [train.py:715] (5/8) Epoch 14, batch 27950, loss[loss=0.1199, simple_loss=0.1959, pruned_loss=0.022, over 4978.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2073, pruned_loss=0.03022, over 974158.35 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 05:08:01,576 INFO [train.py:715] (5/8) Epoch 14, batch 28000, loss[loss=0.1385, simple_loss=0.2137, pruned_loss=0.03166, over 4952.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03019, over 974219.89 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 05:08:40,621 INFO [train.py:715] (5/8) Epoch 14, batch 28050, loss[loss=0.1371, simple_loss=0.2097, pruned_loss=0.03228, over 4877.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02996, over 973170.36 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 05:09:19,677 INFO [train.py:715] (5/8) Epoch 14, batch 28100, loss[loss=0.1735, simple_loss=0.2389, pruned_loss=0.05407, over 4817.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.0301, over 972579.34 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:10:00,233 INFO [train.py:715] (5/8) Epoch 14, batch 28150, loss[loss=0.1413, simple_loss=0.2115, pruned_loss=0.03559, over 4835.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03022, over 973358.27 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:10:39,940 INFO [train.py:715] (5/8) Epoch 14, batch 28200, loss[loss=0.1078, simple_loss=0.1881, pruned_loss=0.01372, over 4815.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.02999, over 974170.79 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:11:17,981 INFO [train.py:715] (5/8) Epoch 14, batch 28250, loss[loss=0.1342, simple_loss=0.2052, pruned_loss=0.03161, over 4756.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03017, over 973578.69 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:11:58,123 INFO [train.py:715] (5/8) Epoch 14, batch 28300, loss[loss=0.131, simple_loss=0.2069, pruned_loss=0.02759, over 4872.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03013, over 974282.97 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 05:12:38,001 INFO [train.py:715] (5/8) Epoch 14, batch 28350, loss[loss=0.1242, simple_loss=0.2082, pruned_loss=0.02008, over 4909.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03022, over 974180.88 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 05:13:16,549 INFO [train.py:715] (5/8) Epoch 14, batch 28400, loss[loss=0.1441, simple_loss=0.2252, pruned_loss=0.03155, over 4806.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03018, over 974445.87 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:13:56,136 INFO [train.py:715] (5/8) Epoch 14, batch 28450, loss[loss=0.1333, simple_loss=0.204, pruned_loss=0.03135, over 4864.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02981, over 974646.02 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 05:14:36,399 INFO [train.py:715] (5/8) Epoch 14, batch 28500, loss[loss=0.1104, simple_loss=0.1898, pruned_loss=0.01554, over 4855.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02963, over 972972.83 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 05:15:15,661 INFO [train.py:715] (5/8) Epoch 14, batch 28550, loss[loss=0.1489, simple_loss=0.2224, pruned_loss=0.03772, over 4822.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02969, over 972984.84 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:15:54,180 INFO [train.py:715] (5/8) Epoch 14, batch 28600, loss[loss=0.1259, simple_loss=0.2077, pruned_loss=0.02206, over 4808.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02993, over 972997.57 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:16:34,515 INFO [train.py:715] (5/8) Epoch 14, batch 28650, loss[loss=0.1248, simple_loss=0.1916, pruned_loss=0.02903, over 4808.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 972941.57 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:17:14,554 INFO [train.py:715] (5/8) Epoch 14, batch 28700, loss[loss=0.1187, simple_loss=0.1998, pruned_loss=0.01877, over 4869.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02975, over 972729.04 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 05:17:52,650 INFO [train.py:715] (5/8) Epoch 14, batch 28750, loss[loss=0.1123, simple_loss=0.1704, pruned_loss=0.02708, over 4783.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02948, over 971617.93 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:18:32,374 INFO [train.py:715] (5/8) Epoch 14, batch 28800, loss[loss=0.1064, simple_loss=0.1863, pruned_loss=0.01321, over 4924.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02946, over 972210.31 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 05:19:12,480 INFO [train.py:715] (5/8) Epoch 14, batch 28850, loss[loss=0.09998, simple_loss=0.1734, pruned_loss=0.01328, over 4976.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02976, over 972920.71 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:19:52,376 INFO [train.py:715] (5/8) Epoch 14, batch 28900, loss[loss=0.1246, simple_loss=0.2027, pruned_loss=0.02328, over 4908.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03032, over 973556.93 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:20:30,224 INFO [train.py:715] (5/8) Epoch 14, batch 28950, loss[loss=0.1152, simple_loss=0.1832, pruned_loss=0.02355, over 4826.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02994, over 972097.72 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:21:10,701 INFO [train.py:715] (5/8) Epoch 14, batch 29000, loss[loss=0.1375, simple_loss=0.2177, pruned_loss=0.02867, over 4811.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03003, over 972002.51 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:21:50,334 INFO [train.py:715] (5/8) Epoch 14, batch 29050, loss[loss=0.1267, simple_loss=0.1953, pruned_loss=0.02904, over 4832.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02959, over 971009.36 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:22:29,103 INFO [train.py:715] (5/8) Epoch 14, batch 29100, loss[loss=0.1209, simple_loss=0.2001, pruned_loss=0.02087, over 4898.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02945, over 971385.39 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:23:08,496 INFO [train.py:715] (5/8) Epoch 14, batch 29150, loss[loss=0.1228, simple_loss=0.192, pruned_loss=0.02675, over 4822.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02922, over 972440.27 frames.], batch size: 26, lr: 1.55e-04
2022-05-08 05:23:48,530 INFO [train.py:715] (5/8) Epoch 14, batch 29200, loss[loss=0.133, simple_loss=0.2087, pruned_loss=0.02869, over 4841.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 972526.37 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:24:28,392 INFO [train.py:715] (5/8) Epoch 14, batch 29250, loss[loss=0.1453, simple_loss=0.2198, pruned_loss=0.03536, over 4969.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02977, over 972958.59 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:25:06,487 INFO [train.py:715] (5/8) Epoch 14, batch 29300, loss[loss=0.125, simple_loss=0.194, pruned_loss=0.02805, over 4776.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02974, over 971603.43 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:25:46,606 INFO [train.py:715] (5/8) Epoch 14, batch 29350, loss[loss=0.1475, simple_loss=0.2166, pruned_loss=0.03917, over 4831.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02974, over 971258.15 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:26:26,515 INFO [train.py:715] (5/8) Epoch 14, batch 29400, loss[loss=0.1418, simple_loss=0.2241, pruned_loss=0.02972, over 4979.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03025, over 971540.69 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:27:05,390 INFO [train.py:715] (5/8) Epoch 14, batch 29450, loss[loss=0.1256, simple_loss=0.1944, pruned_loss=0.02838, over 4984.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03006, over 971806.97 frames.], batch size: 31, lr: 1.55e-04
2022-05-08 05:27:45,240 INFO [train.py:715] (5/8) Epoch 14, batch 29500, loss[loss=0.1329, simple_loss=0.2151, pruned_loss=0.02536, over 4760.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03005, over 971695.78 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:28:25,577 INFO [train.py:715] (5/8) Epoch 14, batch 29550, loss[loss=0.1215, simple_loss=0.1906, pruned_loss=0.02619, over 4753.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03031, over 971310.64 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:29:05,387 INFO [train.py:715] (5/8) Epoch 14, batch 29600, loss[loss=0.1288, simple_loss=0.2178, pruned_loss=0.01987, over 4959.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03064, over 972334.31 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:29:44,395 INFO [train.py:715] (5/8) Epoch 14, batch 29650, loss[loss=0.1207, simple_loss=0.2066, pruned_loss=0.01737, over 4794.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03079, over 972064.62 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 05:30:25,190 INFO [train.py:715] (5/8) Epoch 14, batch 29700, loss[loss=0.1128, simple_loss=0.1892, pruned_loss=0.01823, over 4796.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03078, over 971730.94 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 05:31:06,284 INFO [train.py:715] (5/8) Epoch 14, batch 29750, loss[loss=0.132, simple_loss=0.2081, pruned_loss=0.02794, over 4942.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03085, over 972009.24 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 05:31:45,875 INFO [train.py:715] (5/8) Epoch 14, batch 29800, loss[loss=0.1112, simple_loss=0.1814, pruned_loss=0.02051, over 4977.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03085, over 971836.96 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:32:26,696 INFO [train.py:715] (5/8) Epoch 14, batch 29850, loss[loss=0.1404, simple_loss=0.2119, pruned_loss=0.03448, over 4951.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2076, pruned_loss=0.03052, over 972384.36 frames.], batch size: 23, lr: 1.55e-04
2022-05-08 05:33:06,680 INFO [train.py:715] (5/8) Epoch 14, batch 29900, loss[loss=0.1474, simple_loss=0.2114, pruned_loss=0.04169, over 4701.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03087, over 972008.49 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:33:46,336 INFO [train.py:715] (5/8) Epoch 14, batch 29950, loss[loss=0.1325, simple_loss=0.2031, pruned_loss=0.0309, over 4931.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2076, pruned_loss=0.03045, over 972138.63 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 05:34:25,101 INFO [train.py:715] (5/8) Epoch 14, batch 30000, loss[loss=0.163, simple_loss=0.2259, pruned_loss=0.05009, over 4965.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03041, over 972517.98 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 05:34:25,102 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 05:34:42,241 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 05:35:21,213 INFO [train.py:715] (5/8) Epoch 14, batch 30050, loss[loss=0.1304, simple_loss=0.2007, pruned_loss=0.03002, over 4984.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03093, over 972068.54 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 05:36:01,186 INFO [train.py:715] (5/8) Epoch 14, batch 30100, loss[loss=0.1291, simple_loss=0.2087, pruned_loss=0.02475, over 4847.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03107, over 971826.63 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 05:36:42,312 INFO [train.py:715] (5/8) Epoch 14, batch 30150, loss[loss=0.1416, simple_loss=0.2162, pruned_loss=0.03352, over 4828.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03076, over 971619.11 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:37:21,245 INFO [train.py:715] (5/8) Epoch 14, batch 30200, loss[loss=0.118, simple_loss=0.1819, pruned_loss=0.02706, over 4783.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03075, over 971725.88 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 05:38:01,177 INFO [train.py:715] (5/8) Epoch 14, batch 30250, loss[loss=0.1157, simple_loss=0.186, pruned_loss=0.0227, over 4755.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03025, over 971178.00 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:38:41,857 INFO [train.py:715] (5/8) Epoch 14, batch 30300, loss[loss=0.1438, simple_loss=0.2123, pruned_loss=0.03762, over 4961.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.0307, over 971817.34 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 05:39:21,374 INFO [train.py:715] (5/8) Epoch 14, batch 30350, loss[loss=0.1193, simple_loss=0.191, pruned_loss=0.02384, over 4837.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.0303, over 971368.04 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:40:00,595 INFO [train.py:715] (5/8) Epoch 14, batch 30400, loss[loss=0.1151, simple_loss=0.1899, pruned_loss=0.02015, over 4774.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03042, over 971661.23 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:40:40,498 INFO [train.py:715] (5/8) Epoch 14, batch 30450, loss[loss=0.1377, simple_loss=0.2087, pruned_loss=0.03329, over 4986.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 972458.28 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:41:20,821 INFO [train.py:715] (5/8) Epoch 14, batch 30500, loss[loss=0.1522, simple_loss=0.2201, pruned_loss=0.04211, over 4975.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.0303, over 971629.92 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:41:59,763 INFO [train.py:715] (5/8) Epoch 14, batch 30550, loss[loss=0.1304, simple_loss=0.1872, pruned_loss=0.03678, over 4793.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03009, over 971899.95 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 05:42:39,647 INFO [train.py:715] (5/8) Epoch 14, batch 30600, loss[loss=0.1603, simple_loss=0.232, pruned_loss=0.04424, over 4796.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03063, over 971640.68 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 05:43:20,419 INFO [train.py:715] (5/8) Epoch 14, batch 30650, loss[loss=0.1138, simple_loss=0.187, pruned_loss=0.0203, over 4841.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03074, over 971747.08 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 05:43:59,993 INFO [train.py:715] (5/8) Epoch 14, batch 30700, loss[loss=0.1313, simple_loss=0.1943, pruned_loss=0.03418, over 4783.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03063, over 971465.25 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 05:44:39,757 INFO [train.py:715] (5/8) Epoch 14, batch 30750, loss[loss=0.1526, simple_loss=0.2245, pruned_loss=0.04037, over 4868.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03071, over 971723.80 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 05:45:19,656 INFO [train.py:715] (5/8) Epoch 14, batch 30800, loss[loss=0.1502, simple_loss=0.2169, pruned_loss=0.04175, over 4767.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03041, over 970992.98 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 05:46:00,445 INFO [train.py:715] (5/8) Epoch 14, batch 30850, loss[loss=0.1432, simple_loss=0.223, pruned_loss=0.03171, over 4918.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03033, over 971235.91 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:46:39,513 INFO [train.py:715] (5/8) Epoch 14, batch 30900, loss[loss=0.1387, simple_loss=0.2128, pruned_loss=0.03229, over 4712.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03085, over 971623.30 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:47:18,044 INFO [train.py:715] (5/8) Epoch 14, batch 30950, loss[loss=0.1433, simple_loss=0.2137, pruned_loss=0.03644, over 4872.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03119, over 971440.98 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 05:47:57,805 INFO [train.py:715] (5/8) Epoch 14, batch 31000, loss[loss=0.1273, simple_loss=0.2037, pruned_loss=0.02547, over 4867.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03123, over 971786.01 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 05:48:37,485 INFO [train.py:715] (5/8) Epoch 14, batch 31050, loss[loss=0.1172, simple_loss=0.1924, pruned_loss=0.02097, over 4771.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03101, over 970742.21 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:49:17,852 INFO [train.py:715] (5/8) Epoch 14, batch 31100, loss[loss=0.1242, simple_loss=0.201, pruned_loss=0.02371, over 4902.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03143, over 971520.25 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:49:58,977 INFO [train.py:715] (5/8) Epoch 14, batch 31150, loss[loss=0.106, simple_loss=0.1796, pruned_loss=0.01624, over 4756.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03124, over 972100.97 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:50:40,132 INFO [train.py:715] (5/8) Epoch 14, batch 31200, loss[loss=0.1257, simple_loss=0.1946, pruned_loss=0.02842, over 4959.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03089, over 972519.82 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 05:51:19,911 INFO [train.py:715] (5/8) Epoch 14, batch 31250, loss[loss=0.1453, simple_loss=0.2131, pruned_loss=0.03868, over 4762.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03079, over 972373.28 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:52:00,313 INFO [train.py:715] (5/8) Epoch 14, batch 31300, loss[loss=0.1334, simple_loss=0.1986, pruned_loss=0.03415, over 4816.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03133, over 973050.84 frames.], batch size: 26, lr: 1.54e-04
2022-05-08 05:52:41,154 INFO [train.py:715] (5/8) Epoch 14, batch 31350, loss[loss=0.1221, simple_loss=0.1955, pruned_loss=0.02437, over 4849.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03111, over 972889.61 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 05:53:21,044 INFO [train.py:715] (5/8) Epoch 14, batch 31400, loss[loss=0.1228, simple_loss=0.1924, pruned_loss=0.02663, over 4981.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03101, over 973434.03 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 05:54:00,720 INFO [train.py:715] (5/8) Epoch 14, batch 31450, loss[loss=0.1325, simple_loss=0.2005, pruned_loss=0.03227, over 4694.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03104, over 973499.86 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:54:40,751 INFO [train.py:715] (5/8) Epoch 14, batch 31500, loss[loss=0.1357, simple_loss=0.2217, pruned_loss=0.02487, over 4802.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03065, over 972608.00 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 05:55:21,335 INFO [train.py:715] (5/8) Epoch 14, batch 31550, loss[loss=0.1677, simple_loss=0.2324, pruned_loss=0.05151, over 4830.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03043, over 972865.85 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:56:01,191 INFO [train.py:715] (5/8) Epoch 14, batch 31600, loss[loss=0.1428, simple_loss=0.2232, pruned_loss=0.03123, over 4776.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2099, pruned_loss=0.03067, over 972070.12 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:56:40,697 INFO [train.py:715] (5/8) Epoch 14, batch 31650, loss[loss=0.1259, simple_loss=0.2059, pruned_loss=0.02296, over 4980.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03062, over 972982.20 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 05:57:21,073 INFO [train.py:715] (5/8) Epoch 14, batch 31700, loss[loss=0.1434, simple_loss=0.2128, pruned_loss=0.03705, over 4750.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03041, over 972300.91 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:58:00,668 INFO [train.py:715] (5/8) Epoch 14, batch 31750, loss[loss=0.1496, simple_loss=0.2241, pruned_loss=0.03756, over 4854.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03036, over 970775.40 frames.], batch size: 30, lr: 1.54e-04
2022-05-08 05:58:40,576 INFO [train.py:715] (5/8) Epoch 14, batch 31800, loss[loss=0.1096, simple_loss=0.1772, pruned_loss=0.02106, over 4833.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.0307, over 970944.75 frames.], batch size: 30, lr: 1.54e-04
2022-05-08 05:59:20,882 INFO [train.py:715] (5/8) Epoch 14, batch 31850, loss[loss=0.1071, simple_loss=0.1869, pruned_loss=0.01358, over 4805.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03006, over 971128.59 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:00:01,591 INFO [train.py:715] (5/8) Epoch 14, batch 31900, loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03135, over 4837.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02983, over 970228.06 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:00:40,982 INFO [train.py:715] (5/8) Epoch 14, batch 31950, loss[loss=0.1261, simple_loss=0.2012, pruned_loss=0.02548, over 4981.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02981, over 971701.49 frames.], batch size: 27, lr: 1.54e-04
2022-05-08 06:01:20,564 INFO [train.py:715] (5/8) Epoch 14, batch 32000, loss[loss=0.131, simple_loss=0.2141, pruned_loss=0.02393, over 4894.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02958, over 972566.63 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:02:01,143 INFO [train.py:715] (5/8) Epoch 14, batch 32050, loss[loss=0.09464, simple_loss=0.1695, pruned_loss=0.009886, over 4736.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02934, over 972717.32 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:02:40,616 INFO [train.py:715] (5/8) Epoch 14, batch 32100, loss[loss=0.1489, simple_loss=0.2189, pruned_loss=0.03948, over 4938.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02937, over 972477.96 frames.], batch size: 39, lr: 1.54e-04
2022-05-08 06:03:20,379 INFO [train.py:715] (5/8) Epoch 14, batch 32150, loss[loss=0.1543, simple_loss=0.215, pruned_loss=0.04679, over 4639.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02997, over 971641.15 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:04:00,809 INFO [train.py:715] (5/8) Epoch 14, batch 32200, loss[loss=0.1322, simple_loss=0.2169, pruned_loss=0.02373, over 4896.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03018, over 971241.75 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:04:41,245 INFO [train.py:715] (5/8) Epoch 14, batch 32250, loss[loss=0.1239, simple_loss=0.1976, pruned_loss=0.02507, over 4962.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2067, pruned_loss=0.02987, over 970572.27 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:05:20,520 INFO [train.py:715] (5/8) Epoch 14, batch 32300, loss[loss=0.1289, simple_loss=0.202, pruned_loss=0.02788, over 4840.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03014, over 971111.16 frames.], batch size: 30, lr: 1.54e-04
2022-05-08 06:06:00,147 INFO [train.py:715] (5/8) Epoch 14, batch 32350, loss[loss=0.1222, simple_loss=0.1923, pruned_loss=0.02607, over 4840.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 971256.42 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:06:40,262 INFO [train.py:715] (5/8) Epoch 14, batch 32400, loss[loss=0.1652, simple_loss=0.2276, pruned_loss=0.05141, over 4871.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03027, over 971592.07 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:07:19,950 INFO [train.py:715] (5/8) Epoch 14, batch 32450, loss[loss=0.1663, simple_loss=0.2419, pruned_loss=0.04533, over 4776.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03051, over 971636.09 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:07:59,618 INFO [train.py:715] (5/8) Epoch 14, batch 32500, loss[loss=0.1697, simple_loss=0.2427, pruned_loss=0.04841, over 4884.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03038, over 971009.30 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:08:39,987 INFO [train.py:715] (5/8) Epoch 14, batch 32550, loss[loss=0.1135, simple_loss=0.1925, pruned_loss=0.01723, over 4914.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 971263.77 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:09:20,732 INFO [train.py:715] (5/8) Epoch 14, batch 32600, loss[loss=0.1111, simple_loss=0.1754, pruned_loss=0.02334, over 4730.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02985, over 970457.47 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:10:00,315 INFO [train.py:715] (5/8) Epoch 14, batch 32650, loss[loss=0.1274, simple_loss=0.213, pruned_loss=0.02094, over 4908.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.0302, over 970914.75 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:10:43,611 INFO [train.py:715] (5/8) Epoch 14, batch 32700, loss[loss=0.1185, simple_loss=0.1844, pruned_loss=0.02624, over 4824.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02998, over 970764.78 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:11:24,768 INFO [train.py:715] (5/8) Epoch 14, batch 32750, loss[loss=0.1185, simple_loss=0.1879, pruned_loss=0.02459, over 4844.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 971688.91 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 06:12:05,087 INFO [train.py:715] (5/8) Epoch 14, batch 32800, loss[loss=0.1242, simple_loss=0.1968, pruned_loss=0.02583, over 4848.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 971499.52 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:12:45,512 INFO [train.py:715] (5/8) Epoch 14, batch 32850, loss[loss=0.1099, simple_loss=0.1867, pruned_loss=0.01652, over 4826.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 971708.57 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:13:26,807 INFO [train.py:715] (5/8) Epoch 14, batch 32900, loss[loss=0.1256, simple_loss=0.2034, pruned_loss=0.02391, over 4800.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02976, over 971189.35 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:14:07,968 INFO [train.py:715] (5/8) Epoch 14, batch 32950, loss[loss=0.1497, simple_loss=0.224, pruned_loss=0.03765, over 4754.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02995, over 971710.57 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:14:47,668 INFO [train.py:715] (5/8) Epoch 14, batch 33000, loss[loss=0.1208, simple_loss=0.1956, pruned_loss=0.02303, over 4833.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.0295, over 970815.36 frames.], batch size: 26, lr: 1.54e-04
2022-05-08 06:14:47,668 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 06:15:25,559 INFO [train.py:742] (5/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01071, over 914524.00 frames.
2022-05-08 06:16:05,296 INFO [train.py:715] (5/8) Epoch 14, batch 33050, loss[loss=0.1283, simple_loss=0.199, pruned_loss=0.02879, over 4929.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02949, over 970893.06 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 06:16:46,143 INFO [train.py:715] (5/8) Epoch 14, batch 33100, loss[loss=0.1275, simple_loss=0.1904, pruned_loss=0.03228, over 4805.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 971191.97 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:17:27,374 INFO [train.py:715] (5/8) Epoch 14, batch 33150, loss[loss=0.1218, simple_loss=0.2041, pruned_loss=0.01974, over 4802.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02996, over 971400.46 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:18:07,431 INFO [train.py:715] (5/8) Epoch 14, batch 33200, loss[loss=0.1343, simple_loss=0.2038, pruned_loss=0.0324, over 4769.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03004, over 971018.60 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:18:47,775 INFO [train.py:715] (5/8) Epoch 14, batch 33250, loss[loss=0.1441, simple_loss=0.2052, pruned_loss=0.04146, over 4833.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03069, over 970728.44 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:19:28,526 INFO [train.py:715] (5/8) Epoch 14, batch 33300, loss[loss=0.1419, simple_loss=0.2092, pruned_loss=0.03731, over 4965.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03052, over 972152.59 frames.], batch size: 35, lr: 1.54e-04
2022-05-08 06:20:09,728 INFO [train.py:715] (5/8) Epoch 14, batch 33350, loss[loss=0.1203, simple_loss=0.1911, pruned_loss=0.0248, over 4942.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03065, over 972908.44 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:20:49,899 INFO [train.py:715] (5/8) Epoch 14, batch 33400, loss[loss=0.1168, simple_loss=0.1951, pruned_loss=0.01922, over 4798.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03068, over 972591.89 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:21:30,273 INFO [train.py:715] (5/8) Epoch 14, batch 33450, loss[loss=0.131, simple_loss=0.2021, pruned_loss=0.03001, over 4944.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03067, over 972663.57 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:22:11,509 INFO [train.py:715] (5/8) Epoch 14, batch 33500, loss[loss=0.1261, simple_loss=0.2094, pruned_loss=0.0214, over 4860.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2096, pruned_loss=0.03064, over 972495.90 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 06:22:51,810 INFO [train.py:715] (5/8) Epoch 14, batch 33550, loss[loss=0.1305, simple_loss=0.2082, pruned_loss=0.02645, over 4819.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02991, over 972702.89 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:23:33,008 INFO [train.py:715] (5/8) Epoch 14, batch 33600, loss[loss=0.1459, simple_loss=0.2256, pruned_loss=0.03314, over 4782.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03021, over 972356.87 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:24:14,050 INFO [train.py:715] (5/8) Epoch 14, batch 33650, loss[loss=0.1276, simple_loss=0.1976, pruned_loss=0.02875, over 4891.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03041, over 972303.45 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:24:54,970 INFO [train.py:715] (5/8) Epoch 14, batch 33700, loss[loss=0.1374, simple_loss=0.21, pruned_loss=0.03247, over 4912.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02997, over 971806.89 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 06:25:35,116 INFO [train.py:715] (5/8) Epoch 14, batch 33750, loss[loss=0.1357, simple_loss=0.2116, pruned_loss=0.02992, over 4981.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03009, over 970913.22 frames.], batch size: 39, lr: 1.54e-04
2022-05-08 06:26:15,686 INFO [train.py:715] (5/8) Epoch 14, batch 33800, loss[loss=0.1296, simple_loss=0.2044, pruned_loss=0.02734, over 4960.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03011, over 971040.03 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:26:56,936 INFO [train.py:715] (5/8) Epoch 14, batch 33850, loss[loss=0.1266, simple_loss=0.193, pruned_loss=0.03006, over 4973.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02949, over 971391.67 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:27:37,014 INFO [train.py:715] (5/8) Epoch 14, batch 33900, loss[loss=0.1151, simple_loss=0.1852, pruned_loss=0.02248, over 4905.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02928, over 971991.01 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:28:17,550 INFO [train.py:715] (5/8) Epoch 14, batch 33950, loss[loss=0.1435, simple_loss=0.2182, pruned_loss=0.03442, over 4883.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02989, over 971655.71 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:28:58,277 INFO [train.py:715] (5/8) Epoch 14, batch 34000, loss[loss=0.1536, simple_loss=0.2231, pruned_loss=0.04211, over 4701.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03033, over 971794.38 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:29:39,262 INFO [train.py:715] (5/8) Epoch 14, batch 34050, loss[loss=0.1273, simple_loss=0.205, pruned_loss=0.02479, over 4932.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03053, over 972116.71 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:30:19,208 INFO [train.py:715] (5/8) Epoch 14, batch 34100, loss[loss=0.1392, simple_loss=0.2094, pruned_loss=0.03453, over 4880.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03088, over 971682.78 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:30:59,701 INFO [train.py:715] (5/8) Epoch 14, batch 34150, loss[loss=0.1068, simple_loss=0.18, pruned_loss=0.01683, over 4834.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03073, over 972051.17 frames.], batch size: 32, lr: 1.54e-04
2022-05-08 06:31:40,132 INFO [train.py:715] (5/8) Epoch 14, batch 34200, loss[loss=0.1554, simple_loss=0.2217, pruned_loss=0.04452, over 4907.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03078, over 972743.75 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 06:32:20,303 INFO [train.py:715] (5/8) Epoch 14, batch 34250, loss[loss=0.1287, simple_loss=0.2033, pruned_loss=0.02705, over 4806.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03061, over 971788.05 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 06:33:00,835 INFO [train.py:715] (5/8) Epoch 14, batch 34300, loss[loss=0.1303, simple_loss=0.2018, pruned_loss=0.02946, over 4828.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03026, over 971468.69 frames.], batch size: 30, lr: 1.54e-04
2022-05-08 06:33:41,487 INFO [train.py:715] (5/8) Epoch 14, batch 34350, loss[loss=0.1423, simple_loss=0.2231, pruned_loss=0.03074, over 4852.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03039, over 971563.67 frames.], batch size: 38, lr: 1.54e-04
2022-05-08 06:34:22,183 INFO [train.py:715] (5/8) Epoch 14, batch 34400, loss[loss=0.1249, simple_loss=0.1966, pruned_loss=0.02663, over 4987.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03026, over 971220.31 frames.], batch size: 28, lr: 1.54e-04
2022-05-08 06:35:01,770 INFO [train.py:715] (5/8) Epoch 14, batch 34450, loss[loss=0.1389, simple_loss=0.2231, pruned_loss=0.02733, over 4974.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03012, over 971302.73 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 06:35:42,627 INFO [train.py:715] (5/8) Epoch 14, batch 34500, loss[loss=0.1314, simple_loss=0.2072, pruned_loss=0.02775, over 4893.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03032, over 970794.85 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:36:23,323 INFO [train.py:715] (5/8) Epoch 14, batch 34550, loss[loss=0.1153, simple_loss=0.1955, pruned_loss=0.01755, over 4985.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03038, over 970683.24 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:37:03,435 INFO [train.py:715] (5/8) Epoch 14, batch 34600, loss[loss=0.113, simple_loss=0.1832, pruned_loss=0.02136, over 4758.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.0306, over 970871.18 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:37:43,655 INFO [train.py:715] (5/8) Epoch 14, batch 34650, loss[loss=0.1022, simple_loss=0.1798, pruned_loss=0.01226, over 4907.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03016, over 971726.85 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 06:38:24,406 INFO [train.py:715] (5/8) Epoch 14, batch 34700, loss[loss=0.1185, simple_loss=0.1977, pruned_loss=0.01963, over 4920.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03001, over 972167.95 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:39:03,271 INFO [train.py:715] (5/8) Epoch 14, batch 34750, loss[loss=0.1138, simple_loss=0.1869, pruned_loss=0.02032, over 4888.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02976, over 972644.34 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:39:40,045 INFO [train.py:715] (5/8) Epoch 14, batch 34800, loss[loss=0.1522, simple_loss=0.2307, pruned_loss=0.03682, over 4938.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.0301, over 971588.97 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:40:33,612 INFO [train.py:715] (5/8) Epoch 15, batch 0, loss[loss=0.1384, simple_loss=0.2173, pruned_loss=0.02974, over 4814.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2173, pruned_loss=0.02974, over 4814.00 frames.], batch size: 27, lr: 1.49e-04
2022-05-08 06:41:12,925 INFO [train.py:715] (5/8) Epoch 15, batch 50, loss[loss=0.1358, simple_loss=0.2078, pruned_loss=0.0319, over 4746.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2091, pruned_loss=0.03235, over 219170.14 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 06:41:54,168 INFO [train.py:715] (5/8) Epoch 15, batch 100, loss[loss=0.1466, simple_loss=0.2187, pruned_loss=0.03727, over 4977.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2086, pruned_loss=0.03155, over 386564.66 frames.], batch size: 33, lr: 1.49e-04
2022-05-08 06:42:35,662 INFO [train.py:715] (5/8) Epoch 15, batch 150, loss[loss=0.1443, simple_loss=0.2254, pruned_loss=0.03154, over 4989.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2076, pruned_loss=0.03109, over 516650.60 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:43:15,919 INFO [train.py:715] (5/8) Epoch 15, batch 200, loss[loss=0.1522, simple_loss=0.2266, pruned_loss=0.03895, over 4793.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2083, pruned_loss=0.03143, over 617240.51 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 06:43:56,385 INFO [train.py:715] (5/8) Epoch 15, batch 250, loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02955, over 4976.00 frames.], tot_loss[loss=0.1353, simple_loss=0.208, pruned_loss=0.03124, over 696875.60 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 06:44:37,768 INFO [train.py:715] (5/8) Epoch 15, batch 300, loss[loss=0.1449, simple_loss=0.222, pruned_loss=0.03396, over 4851.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2074, pruned_loss=0.03065, over 757888.53 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 06:45:18,788 INFO [train.py:715] (5/8) Epoch 15, batch 350, loss[loss=0.1297, simple_loss=0.1946, pruned_loss=0.0324, over 4777.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03019, over 806172.74 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:45:58,476 INFO [train.py:715] (5/8) Epoch 15, batch 400, loss[loss=0.1154, simple_loss=0.1897, pruned_loss=0.02053, over 4887.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02986, over 843108.13 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 06:46:39,368 INFO [train.py:715] (5/8) Epoch 15, batch 450, loss[loss=0.1266, simple_loss=0.2041, pruned_loss=0.02461, over 4803.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03017, over 871873.29 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:47:20,101 INFO [train.py:715] (5/8) Epoch 15, batch 500, loss[loss=0.1591, simple_loss=0.2293, pruned_loss=0.04449, over 4877.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03046, over 894318.02 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 06:48:00,515 INFO [train.py:715] (5/8) Epoch 15, batch 550, loss[loss=0.1504, simple_loss=0.2308, pruned_loss=0.03495, over 4821.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03037, over 911569.88 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 06:48:40,065 INFO [train.py:715] (5/8) Epoch 15, batch 600, loss[loss=0.1268, simple_loss=0.1984, pruned_loss=0.02758, over 4933.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03025, over 924993.31 frames.], batch size: 23, lr: 1.49e-04
2022-05-08 06:49:21,142 INFO [train.py:715] (5/8) Epoch 15, batch 650, loss[loss=0.1323, simple_loss=0.2047, pruned_loss=0.02996, over 4940.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2097, pruned_loss=0.03025, over 935839.20 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:50:01,507 INFO [train.py:715] (5/8) Epoch 15, batch 700, loss[loss=0.13, simple_loss=0.1962, pruned_loss=0.03192, over 4821.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02942, over 943785.24 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 06:50:41,530 INFO [train.py:715] (5/8) Epoch 15, batch 750, loss[loss=0.1657, simple_loss=0.2324, pruned_loss=0.04944, over 4657.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02979, over 949857.68 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 06:51:22,003 INFO [train.py:715] (5/8) Epoch 15, batch 800, loss[loss=0.155, simple_loss=0.2312, pruned_loss=0.03941, over 4954.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02988, over 955092.35 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 06:52:02,786 INFO [train.py:715] (5/8) Epoch 15, batch 850, loss[loss=0.1253, simple_loss=0.2079, pruned_loss=0.02132, over 4823.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02979, over 958865.99 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:52:43,865 INFO [train.py:715] (5/8) Epoch 15, batch 900, loss[loss=0.1569, simple_loss=0.2332, pruned_loss=0.04036, over 4785.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02992, over 961921.68 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:53:23,526 INFO [train.py:715] (5/8) Epoch 15, batch 950, loss[loss=0.1292, simple_loss=0.2101, pruned_loss=0.0241, over 4772.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03005, over 963027.77 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 06:54:04,076 INFO [train.py:715] (5/8) Epoch 15, batch 1000, loss[loss=0.1307, simple_loss=0.211, pruned_loss=0.02521, over 4821.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03033, over 964335.45 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 06:54:44,300 INFO [train.py:715] (5/8) Epoch 15, batch 1050, loss[loss=0.1133, simple_loss=0.1894, pruned_loss=0.01857, over 4806.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03066, over 965522.55 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:55:23,585 INFO [train.py:715] (5/8) Epoch 15, batch 1100, loss[loss=0.1409, simple_loss=0.2049, pruned_loss=0.03843, over 4916.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03044, over 967440.39 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:56:04,685 INFO [train.py:715] (5/8) Epoch 15, batch 1150, loss[loss=0.1256, simple_loss=0.2012, pruned_loss=0.02502, over 4856.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03027, over 968566.69 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 06:56:45,827 INFO [train.py:715] (5/8) Epoch 15, batch 1200, loss[loss=0.1159, simple_loss=0.183, pruned_loss=0.02436, over 4748.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03026, over 969635.62 frames.], batch size: 12, lr: 1.49e-04
2022-05-08 06:57:26,537 INFO [train.py:715] (5/8) Epoch 15, batch 1250, loss[loss=0.1289, simple_loss=0.1987, pruned_loss=0.02956, over 4787.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03048, over 969858.99 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:58:06,004 INFO [train.py:715] (5/8) Epoch 15, batch 1300, loss[loss=0.1387, simple_loss=0.2085, pruned_loss=0.03444, over 4685.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03032, over 969254.65 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 06:58:46,697 INFO [train.py:715] (5/8) Epoch 15, batch 1350, loss[loss=0.1479, simple_loss=0.2129, pruned_loss=0.04142, over 4862.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03079, over 968989.00 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 06:59:27,344 INFO [train.py:715] (5/8) Epoch 15, batch 1400, loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02937, over 4810.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03061, over 969447.76 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:00:07,535 INFO [train.py:715] (5/8) Epoch 15, batch 1450, loss[loss=0.1355, simple_loss=0.1957, pruned_loss=0.03761, over 4839.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03117, over 970725.02 frames.], batch size: 30, lr: 1.49e-04
2022-05-08 07:00:47,341 INFO [train.py:715] (5/8) Epoch 15, batch 1500, loss[loss=0.1227, simple_loss=0.2021, pruned_loss=0.02163, over 4939.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03128, over 970678.43 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:01:28,515 INFO [train.py:715] (5/8) Epoch 15, batch 1550, loss[loss=0.1642, simple_loss=0.2299, pruned_loss=0.04928, over 4812.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03154, over 970902.14 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:02:08,734 INFO [train.py:715] (5/8) Epoch 15, batch 1600, loss[loss=0.1334, simple_loss=0.1982, pruned_loss=0.03432, over 4793.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.0318, over 971200.82 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 07:02:47,773 INFO [train.py:715] (5/8) Epoch 15, batch 1650, loss[loss=0.1212, simple_loss=0.2019, pruned_loss=0.02024, over 4901.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03166, over 971910.66 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:03:28,304 INFO [train.py:715] (5/8) Epoch 15, batch 1700, loss[loss=0.1475, simple_loss=0.2222, pruned_loss=0.03635, over 4981.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03142, over 972862.94 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:04:08,886 INFO [train.py:715] (5/8) Epoch 15, batch 1750, loss[loss=0.1177, simple_loss=0.1958, pruned_loss=0.01982, over 4872.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03083, over 971784.02 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:04:48,965 INFO [train.py:715] (5/8) Epoch 15, batch 1800, loss[loss=0.1089, simple_loss=0.192, pruned_loss=0.0129, over 4871.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03087, over 971023.56 frames.], batch size: 22, lr: 1.49e-04
2022-05-08 07:05:28,951 INFO [train.py:715] (5/8) Epoch 15, batch 1850, loss[loss=0.1211, simple_loss=0.1997, pruned_loss=0.02131, over 4825.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03047, over 971592.90 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:06:09,785 INFO [train.py:715] (5/8) Epoch 15, batch 1900, loss[loss=0.1163, simple_loss=0.1832, pruned_loss=0.02471, over 4965.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03001, over 971649.01 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:06:50,234 INFO [train.py:715] (5/8) Epoch 15, batch 1950, loss[loss=0.1028, simple_loss=0.1778, pruned_loss=0.01387, over 4826.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02965, over 971831.48 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 07:07:29,412 INFO [train.py:715] (5/8) Epoch 15, batch 2000, loss[loss=0.135, simple_loss=0.1973, pruned_loss=0.03638, over 4796.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02964, over 972002.17 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 07:08:10,502 INFO [train.py:715] (5/8) Epoch 15, batch 2050, loss[loss=0.1275, simple_loss=0.2024, pruned_loss=0.02626, over 4897.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02997, over 971994.02 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:08:50,817 INFO [train.py:715] (5/8) Epoch 15, batch 2100, loss[loss=0.109, simple_loss=0.1791, pruned_loss=0.01942, over 4746.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02989, over 971606.14 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:09:30,724 INFO [train.py:715] (5/8) Epoch 15, batch 2150, loss[loss=0.1345, simple_loss=0.2094, pruned_loss=0.02981, over 4875.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02984, over 971030.07 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 07:10:10,978 INFO [train.py:715] (5/8) Epoch 15, batch 2200, loss[loss=0.1584, simple_loss=0.241, pruned_loss=0.03785, over 4896.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02982, over 971093.04 frames.], batch size: 39, lr: 1.49e-04
2022-05-08 07:10:51,404 INFO [train.py:715] (5/8) Epoch 15, batch 2250, loss[loss=0.1288, simple_loss=0.2035, pruned_loss=0.027, over 4781.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 971420.28 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 07:11:31,549 INFO [train.py:715] (5/8) Epoch 15, batch 2300, loss[loss=0.1301, simple_loss=0.2174, pruned_loss=0.0214, over 4856.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 971826.72 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:12:11,044 INFO [train.py:715] (5/8) Epoch 15, batch 2350, loss[loss=0.1131, simple_loss=0.1768, pruned_loss=0.02472, over 4733.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03014, over 972101.52 frames.], batch size: 12, lr: 1.49e-04
2022-05-08 07:12:51,318 INFO [train.py:715] (5/8) Epoch 15, batch 2400, loss[loss=0.1155, simple_loss=0.1985, pruned_loss=0.01624, over 4977.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03043, over 972627.30 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 07:13:31,564 INFO [train.py:715] (5/8) Epoch 15, batch 2450, loss[loss=0.161, simple_loss=0.243, pruned_loss=0.03951, over 4969.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03076, over 972286.90 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:14:11,489 INFO [train.py:715] (5/8) Epoch 15, batch 2500, loss[loss=0.1376, simple_loss=0.2206, pruned_loss=0.02725, over 4761.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03084, over 972240.95 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 07:14:50,607 INFO [train.py:715] (5/8) Epoch 15, batch 2550, loss[loss=0.1209, simple_loss=0.1913, pruned_loss=0.02528, over 4844.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03017, over 972213.22 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 07:15:31,419 INFO [train.py:715] (5/8) Epoch 15, batch 2600, loss[loss=0.1479, simple_loss=0.216, pruned_loss=0.03989, over 4904.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03013, over 972617.09 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:16:12,104 INFO [train.py:715] (5/8) Epoch 15, batch 2650, loss[loss=0.1232, simple_loss=0.1979, pruned_loss=0.02431, over 4769.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03022, over 972796.98 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:16:51,595 INFO [train.py:715] (5/8) Epoch 15, batch 2700, loss[loss=0.106, simple_loss=0.1809, pruned_loss=0.01557, over 4754.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2094, pruned_loss=0.03018, over 972764.07 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:17:33,119 INFO [train.py:715] (5/8) Epoch 15, batch 2750, loss[loss=0.1675, simple_loss=0.2288, pruned_loss=0.05312, over 4770.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03079, over 972016.54 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 07:18:14,187 INFO [train.py:715] (5/8) Epoch 15, batch 2800, loss[loss=0.1145, simple_loss=0.1889, pruned_loss=0.02006, over 4856.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03024, over 971725.90 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:18:54,887 INFO [train.py:715] (5/8) Epoch 15, batch 2850, loss[loss=0.1554, simple_loss=0.227, pruned_loss=0.04186, over 4851.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03059, over 972273.89 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:19:34,220 INFO [train.py:715] (5/8) Epoch 15, batch 2900, loss[loss=0.1334, simple_loss=0.2059, pruned_loss=0.03045, over 4898.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03073, over 972416.48 frames.], batch size: 22, lr: 1.49e-04
2022-05-08 07:20:14,829 INFO [train.py:715] (5/8) Epoch 15, batch 2950, loss[loss=0.1728, simple_loss=0.2428, pruned_loss=0.05139, over 4857.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03059, over 972394.35 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:20:55,617 INFO [train.py:715] (5/8) Epoch 15, batch 3000, loss[loss=0.1139, simple_loss=0.1882, pruned_loss=0.01983, over 4820.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03072, over 971449.46 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:20:55,618 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 07:21:13,096 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1887, pruned_loss=0.01057, over 914524.00 frames.
2022-05-08 07:21:54,024 INFO [train.py:715] (5/8) Epoch 15, batch 3050, loss[loss=0.1584, simple_loss=0.2432, pruned_loss=0.03677, over 4862.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03097, over 971835.75 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:22:33,939 INFO [train.py:715] (5/8) Epoch 15, batch 3100, loss[loss=0.1187, simple_loss=0.2024, pruned_loss=0.0175, over 4821.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03075, over 972146.17 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:23:14,657 INFO [train.py:715] (5/8) Epoch 15, batch 3150, loss[loss=0.1429, simple_loss=0.2189, pruned_loss=0.03345, over 4828.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03156, over 972430.49 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 07:23:55,203 INFO [train.py:715] (5/8) Epoch 15, batch 3200, loss[loss=0.1447, simple_loss=0.2214, pruned_loss=0.03397, over 4759.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03064, over 973043.12 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:24:35,382 INFO [train.py:715] (5/8) Epoch 15, batch 3250, loss[loss=0.1763, simple_loss=0.2454, pruned_loss=0.0536, over 4986.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03108, over 971813.30 frames.], batch size: 33, lr: 1.49e-04
2022-05-08 07:25:15,331 INFO [train.py:715] (5/8) Epoch 15, batch 3300, loss[loss=0.1464, simple_loss=0.2133, pruned_loss=0.03977, over 4967.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03058, over 972135.15 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 07:25:56,108 INFO [train.py:715] (5/8) Epoch 15, batch 3350, loss[loss=0.1402, simple_loss=0.2201, pruned_loss=0.03019, over 4880.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03037, over 972323.01 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:26:36,436 INFO [train.py:715] (5/8) Epoch 15, batch 3400, loss[loss=0.1134, simple_loss=0.1894, pruned_loss=0.01872, over 4829.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02995, over 972367.59 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 07:27:16,663 INFO [train.py:715] (5/8) Epoch 15, batch 3450, loss[loss=0.1152, simple_loss=0.1873, pruned_loss=0.02154, over 4737.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03016, over 972194.89 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 07:27:56,932 INFO [train.py:715] (5/8) Epoch 15, batch 3500, loss[loss=0.1424, simple_loss=0.2101, pruned_loss=0.03739, over 4846.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 972395.61 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:28:37,338 INFO [train.py:715] (5/8) Epoch 15, batch 3550, loss[loss=0.115, simple_loss=0.19, pruned_loss=0.02003, over 4981.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03065, over 972797.67 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 07:29:17,844 INFO [train.py:715] (5/8) Epoch 15, batch 3600, loss[loss=0.1376, simple_loss=0.2187, pruned_loss=0.02825, over 4952.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 973726.69 frames.], batch size: 24, lr: 1.49e-04
2022-05-08 07:29:57,636 INFO [train.py:715] (5/8) Epoch 15, batch 3650, loss[loss=0.1116, simple_loss=0.1832, pruned_loss=0.01994, over 4767.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 972705.03 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 07:30:38,281 INFO [train.py:715] (5/8) Epoch 15, batch 3700, loss[loss=0.1597, simple_loss=0.2276, pruned_loss=0.04592, over 4977.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 973117.73 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 07:31:19,135 INFO [train.py:715] (5/8) Epoch 15, batch 3750, loss[loss=0.1659, simple_loss=0.2323, pruned_loss=0.04978, over 4828.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02943, over 971730.31 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 07:31:58,796 INFO [train.py:715] (5/8) Epoch 15, batch 3800, loss[loss=0.1246, simple_loss=0.1981, pruned_loss=0.0255, over 4968.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2068, pruned_loss=0.02981, over 972143.16 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:32:38,800 INFO [train.py:715] (5/8) Epoch 15, batch 3850, loss[loss=0.1646, simple_loss=0.2337, pruned_loss=0.04775, over 4851.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2067, pruned_loss=0.02972, over 972341.97 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 07:33:19,085 INFO [train.py:715] (5/8) Epoch 15, batch 3900, loss[loss=0.1173, simple_loss=0.1964, pruned_loss=0.0191, over 4975.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02935, over 972291.77 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:33:58,252 INFO [train.py:715] (5/8) Epoch 15, batch 3950, loss[loss=0.1549, simple_loss=0.228, pruned_loss=0.0409, over 4831.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 972825.71 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:34:37,990 INFO [train.py:715] (5/8) Epoch 15, batch 4000, loss[loss=0.1405, simple_loss=0.2084, pruned_loss=0.0363, over 4831.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02983, over 973133.29 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 07:35:17,770 INFO [train.py:715] (5/8) Epoch 15, batch 4050, loss[loss=0.1305, simple_loss=0.2029, pruned_loss=0.02903, over 4698.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02966, over 972416.64 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:35:58,783 INFO [train.py:715] (5/8) Epoch 15, batch 4100, loss[loss=0.1486, simple_loss=0.2115, pruned_loss=0.04288, over 4822.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03012, over 972090.29 frames.], batch size: 13, lr: 1.48e-04
2022-05-08 07:36:37,610 INFO [train.py:715] (5/8) Epoch 15, batch 4150, loss[loss=0.1312, simple_loss=0.2018, pruned_loss=0.03033, over 4821.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03006, over 972498.09 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 07:37:17,775 INFO [train.py:715] (5/8) Epoch 15, batch 4200, loss[loss=0.1091, simple_loss=0.179, pruned_loss=0.01965, over 4722.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02972, over 972131.62 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 07:37:58,203 INFO [train.py:715] (5/8) Epoch 15, batch 4250, loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03949, over 4859.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02977, over 972313.33 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 07:38:38,202 INFO [train.py:715] (5/8) Epoch 15, batch 4300, loss[loss=0.1459, simple_loss=0.2276, pruned_loss=0.03211, over 4970.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02993, over 973064.67 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:39:18,224 INFO [train.py:715] (5/8) Epoch 15, batch 4350, loss[loss=0.1423, simple_loss=0.2032, pruned_loss=0.04071, over 4726.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02982, over 972863.99 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:39:58,269 INFO [train.py:715] (5/8) Epoch 15, batch 4400, loss[loss=0.127, simple_loss=0.1911, pruned_loss=0.03139, over 4980.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03003, over 972615.06 frames.], batch size: 33, lr: 1.48e-04
2022-05-08 07:40:38,801 INFO [train.py:715] (5/8) Epoch 15, batch 4450, loss[loss=0.1314, simple_loss=0.2075, pruned_loss=0.02769, over 4989.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.0299, over 971851.70 frames.], batch size: 31, lr: 1.48e-04
2022-05-08 07:41:18,469 INFO [train.py:715] (5/8) Epoch 15, batch 4500, loss[loss=0.1162, simple_loss=0.1891, pruned_loss=0.02169, over 4915.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03026, over 971761.47 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:41:58,881 INFO [train.py:715] (5/8) Epoch 15, batch 4550, loss[loss=0.1368, simple_loss=0.2087, pruned_loss=0.03243, over 4849.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03047, over 971627.05 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 07:42:39,500 INFO [train.py:715] (5/8) Epoch 15, batch 4600, loss[loss=0.1279, simple_loss=0.2032, pruned_loss=0.02628, over 4770.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.0303, over 971305.35 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 07:43:19,668 INFO [train.py:715] (5/8) Epoch 15, batch 4650, loss[loss=0.1527, simple_loss=0.2179, pruned_loss=0.04374, over 4752.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03081, over 971901.18 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:43:59,060 INFO [train.py:715] (5/8) Epoch 15, batch 4700, loss[loss=0.1279, simple_loss=0.1962, pruned_loss=0.02981, over 4762.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2098, pruned_loss=0.03044, over 972450.31 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 07:44:39,327 INFO [train.py:715] (5/8) Epoch 15, batch 4750, loss[loss=0.138, simple_loss=0.2273, pruned_loss=0.02439, over 4948.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2093, pruned_loss=0.03023, over 972663.99 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:45:20,586 INFO [train.py:715] (5/8) Epoch 15, batch 4800, loss[loss=0.1202, simple_loss=0.1939, pruned_loss=0.02324, over 4855.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 973316.30 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 07:46:00,533 INFO [train.py:715] (5/8) Epoch 15, batch 4850, loss[loss=0.1165, simple_loss=0.2006, pruned_loss=0.01624, over 4779.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03022, over 972726.62 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 07:46:41,240 INFO [train.py:715] (5/8) Epoch 15, batch 4900, loss[loss=0.1499, simple_loss=0.2135, pruned_loss=0.04314, over 4799.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03046, over 973168.00 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 07:47:21,681 INFO [train.py:715] (5/8) Epoch 15, batch 4950, loss[loss=0.1327, simple_loss=0.2149, pruned_loss=0.02523, over 4901.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02998, over 973611.05 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 07:48:02,265 INFO [train.py:715] (5/8) Epoch 15, batch 5000, loss[loss=0.1251, simple_loss=0.201, pruned_loss=0.02457, over 4988.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02942, over 973045.26 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:48:41,751 INFO [train.py:715] (5/8) Epoch 15, batch 5050, loss[loss=0.1593, simple_loss=0.2341, pruned_loss=0.04222, over 4992.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02963, over 973460.26 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 07:49:21,837 INFO [train.py:715] (5/8) Epoch 15, batch 5100, loss[loss=0.1636, simple_loss=0.2513, pruned_loss=0.03795, over 4877.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03032, over 973527.94 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:50:02,142 INFO [train.py:715] (5/8) Epoch 15, batch 5150, loss[loss=0.1813, simple_loss=0.2484, pruned_loss=0.05712, over 4843.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03043, over 973260.75 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:50:42,065 INFO [train.py:715] (5/8) Epoch 15, batch 5200, loss[loss=0.132, simple_loss=0.2094, pruned_loss=0.02731, over 4832.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03016, over 973678.95 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:51:22,084 INFO [train.py:715] (5/8) Epoch 15, batch 5250, loss[loss=0.1299, simple_loss=0.2067, pruned_loss=0.0266, over 4684.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03015, over 973099.27 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:52:03,630 INFO [train.py:715] (5/8) Epoch 15, batch 5300, loss[loss=0.1299, simple_loss=0.2113, pruned_loss=0.02425, over 4979.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02978, over 972993.76 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 07:52:45,863 INFO [train.py:715] (5/8) Epoch 15, batch 5350, loss[loss=0.1321, simple_loss=0.2005, pruned_loss=0.03189, over 4961.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02932, over 972732.10 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:53:26,855 INFO [train.py:715] (5/8) Epoch 15, batch 5400, loss[loss=0.161, simple_loss=0.2338, pruned_loss=0.04405, over 4816.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02932, over 972697.74 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 07:54:08,829 INFO [train.py:715] (5/8) Epoch 15, batch 5450, loss[loss=0.1555, simple_loss=0.2156, pruned_loss=0.0477, over 4731.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02943, over 972759.83 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:54:50,466 INFO [train.py:715] (5/8) Epoch 15, batch 5500, loss[loss=0.1278, simple_loss=0.1975, pruned_loss=0.02911, over 4963.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02964, over 973748.70 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:55:32,153 INFO [train.py:715] (5/8) Epoch 15, batch 5550, loss[loss=0.1248, simple_loss=0.2008, pruned_loss=0.0244, over 4941.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02961, over 972806.43 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 07:56:12,916 INFO [train.py:715] (5/8) Epoch 15, batch 5600, loss[loss=0.1388, simple_loss=0.2179, pruned_loss=0.02982, over 4952.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03026, over 972980.87 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 07:56:54,777 INFO [train.py:715] (5/8) Epoch 15, batch 5650, loss[loss=0.1236, simple_loss=0.1954, pruned_loss=0.0259, over 4799.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03052, over 972444.96 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:57:37,296 INFO [train.py:715] (5/8) Epoch 15, batch 5700, loss[loss=0.1533, simple_loss=0.2361, pruned_loss=0.03523, over 4819.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 972809.31 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:58:18,522 INFO [train.py:715] (5/8) Epoch 15, batch 5750, loss[loss=0.1942, simple_loss=0.2745, pruned_loss=0.05694, over 4840.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03061, over 973175.75 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:58:59,988 INFO [train.py:715] (5/8) Epoch 15, batch 5800, loss[loss=0.1463, simple_loss=0.2351, pruned_loss=0.02874, over 4832.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03107, over 972069.87 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:59:41,226 INFO [train.py:715] (5/8) Epoch 15, batch 5850, loss[loss=0.135, simple_loss=0.2065, pruned_loss=0.03179, over 4781.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03063, over 971342.09 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:00:25,528 INFO [train.py:715] (5/8) Epoch 15, batch 5900, loss[loss=0.1153, simple_loss=0.1949, pruned_loss=0.01781, over 4938.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03056, over 971447.12 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 08:01:06,121 INFO [train.py:715] (5/8) Epoch 15, batch 5950, loss[loss=0.1213, simple_loss=0.1968, pruned_loss=0.02293, over 4801.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03053, over 971541.77 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 08:01:47,585 INFO [train.py:715] (5/8) Epoch 15, batch 6000, loss[loss=0.123, simple_loss=0.1961, pruned_loss=0.02496, over 4764.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03083, over 971994.41 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:01:47,586 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 08:01:57,159 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
2022-05-08 08:02:38,326 INFO [train.py:715] (5/8) Epoch 15, batch 6050, loss[loss=0.135, simple_loss=0.2121, pruned_loss=0.02899, over 4801.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03028, over 972330.48 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:03:20,375 INFO [train.py:715] (5/8) Epoch 15, batch 6100, loss[loss=0.1161, simple_loss=0.189, pruned_loss=0.02163, over 4771.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03072, over 972154.22 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:04:00,129 INFO [train.py:715] (5/8) Epoch 15, batch 6150, loss[loss=0.1336, simple_loss=0.2195, pruned_loss=0.02384, over 4783.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03073, over 973211.31 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:04:41,013 INFO [train.py:715] (5/8) Epoch 15, batch 6200, loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03, over 4966.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03049, over 973700.21 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:05:20,642 INFO [train.py:715] (5/8) Epoch 15, batch 6250, loss[loss=0.1298, simple_loss=0.1978, pruned_loss=0.0309, over 4739.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03073, over 972972.09 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:06:01,396 INFO [train.py:715] (5/8) Epoch 15, batch 6300, loss[loss=0.1359, simple_loss=0.2195, pruned_loss=0.02609, over 4801.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03036, over 972131.25 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:06:41,234 INFO [train.py:715] (5/8) Epoch 15, batch 6350, loss[loss=0.11, simple_loss=0.1842, pruned_loss=0.01785, over 4867.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03027, over 972325.03 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:07:21,275 INFO [train.py:715] (5/8) Epoch 15, batch 6400, loss[loss=0.1401, simple_loss=0.1927, pruned_loss=0.04376, over 4981.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03071, over 972484.28 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:08:01,848 INFO [train.py:715] (5/8) Epoch 15, batch 6450, loss[loss=0.1327, simple_loss=0.2109, pruned_loss=0.02725, over 4967.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03029, over 972618.26 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:08:41,388 INFO [train.py:715] (5/8) Epoch 15, batch 6500, loss[loss=0.1439, simple_loss=0.2271, pruned_loss=0.03038, over 4966.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03035, over 972153.90 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:09:21,822 INFO [train.py:715] (5/8) Epoch 15, batch 6550, loss[loss=0.1566, simple_loss=0.2306, pruned_loss=0.04134, over 4976.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03054, over 973271.05 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:10:02,130 INFO [train.py:715] (5/8) Epoch 15, batch 6600, loss[loss=0.1336, simple_loss=0.2108, pruned_loss=0.02826, over 4868.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03064, over 973705.03 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:10:42,817 INFO [train.py:715] (5/8) Epoch 15, batch 6650, loss[loss=0.1424, simple_loss=0.2174, pruned_loss=0.03367, over 4749.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03019, over 972956.49 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:11:22,254 INFO [train.py:715] (5/8) Epoch 15, batch 6700, loss[loss=0.1057, simple_loss=0.1768, pruned_loss=0.01734, over 4735.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2069, pruned_loss=0.02999, over 972163.23 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:12:02,761 INFO [train.py:715] (5/8) Epoch 15, batch 6750, loss[loss=0.1476, simple_loss=0.2132, pruned_loss=0.04103, over 4774.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03033, over 971892.06 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:12:44,118 INFO [train.py:715] (5/8) Epoch 15, batch 6800, loss[loss=0.1398, simple_loss=0.2138, pruned_loss=0.03297, over 4936.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03055, over 972996.15 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:13:23,952 INFO [train.py:715] (5/8) Epoch 15, batch 6850, loss[loss=0.1441, simple_loss=0.2225, pruned_loss=0.03281, over 4696.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03066, over 973560.71 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:14:03,536 INFO [train.py:715] (5/8) Epoch 15, batch 6900, loss[loss=0.1579, simple_loss=0.2287, pruned_loss=0.04358, over 4932.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03004, over 973255.22 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:14:44,364 INFO [train.py:715] (5/8) Epoch 15, batch 6950, loss[loss=0.1216, simple_loss=0.1944, pruned_loss=0.02433, over 4867.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02974, over 972834.76 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:15:24,999 INFO [train.py:715] (5/8) Epoch 15, batch 7000, loss[loss=0.1363, simple_loss=0.2125, pruned_loss=0.03005, over 4778.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03027, over 972723.45 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:16:03,961 INFO [train.py:715] (5/8) Epoch 15, batch 7050, loss[loss=0.127, simple_loss=0.2022, pruned_loss=0.02594, over 4916.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02999, over 973063.31 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:16:44,708 INFO [train.py:715] (5/8) Epoch 15, batch 7100, loss[loss=0.1557, simple_loss=0.2314, pruned_loss=0.03996, over 4889.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03001, over 973035.42 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:17:25,231 INFO [train.py:715] (5/8) Epoch 15, batch 7150, loss[loss=0.1395, simple_loss=0.215, pruned_loss=0.03206, over 4980.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02998, over 972755.48 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:18:05,135 INFO [train.py:715] (5/8) Epoch 15, batch 7200, loss[loss=0.121, simple_loss=0.1946, pruned_loss=0.02363, over 4873.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03064, over 972072.89 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:18:44,343 INFO [train.py:715] (5/8) Epoch 15, batch 7250, loss[loss=0.1597, simple_loss=0.2288, pruned_loss=0.04526, over 4985.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03035, over 972486.40 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:19:25,091 INFO [train.py:715] (5/8) Epoch 15, batch 7300, loss[loss=0.1344, simple_loss=0.2089, pruned_loss=0.02993, over 4810.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03059, over 972310.07 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 08:20:06,079 INFO [train.py:715] (5/8) Epoch 15, batch 7350, loss[loss=0.1385, simple_loss=0.2242, pruned_loss=0.02643, over 4911.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2098, pruned_loss=0.03062, over 972415.99 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:20:45,518 INFO [train.py:715] (5/8) Epoch 15, batch 7400, loss[loss=0.1376, simple_loss=0.2079, pruned_loss=0.03367, over 4931.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03065, over 973085.88 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:21:25,989 INFO [train.py:715] (5/8) Epoch 15, batch 7450, loss[loss=0.1301, simple_loss=0.2143, pruned_loss=0.02295, over 4856.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03056, over 972801.54 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 08:22:06,377 INFO [train.py:715] (5/8) Epoch 15, batch 7500, loss[loss=0.1027, simple_loss=0.1713, pruned_loss=0.01708, over 4811.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.0313, over 972596.57 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:22:46,667 INFO [train.py:715] (5/8) Epoch 15, batch 7550, loss[loss=0.1218, simple_loss=0.1932, pruned_loss=0.0252, over 4823.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03067, over 972720.13 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:23:25,907 INFO [train.py:715] (5/8) Epoch 15, batch 7600, loss[loss=0.1351, simple_loss=0.2064, pruned_loss=0.03192, over 4898.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03014, over 973196.29 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:24:05,911 INFO [train.py:715] (5/8) Epoch 15, batch 7650, loss[loss=0.1395, simple_loss=0.2193, pruned_loss=0.02982, over 4943.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03049, over 973316.73 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:24:45,959 INFO [train.py:715] (5/8) Epoch 15, batch 7700, loss[loss=0.1351, simple_loss=0.2038, pruned_loss=0.03321, over 4983.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03095, over 972994.42 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 08:25:24,894 INFO [train.py:715] (5/8) Epoch 15, batch 7750, loss[loss=0.1258, simple_loss=0.201, pruned_loss=0.02531, over 4932.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03099, over 972716.17 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:26:04,530 INFO [train.py:715] (5/8) Epoch 15, batch 7800, loss[loss=0.111, simple_loss=0.1867, pruned_loss=0.0176, over 4793.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03043, over 972036.29 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:26:43,771 INFO [train.py:715] (5/8) Epoch 15, batch 7850, loss[loss=0.1326, simple_loss=0.2148, pruned_loss=0.02522, over 4967.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03043, over 971871.08 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 08:27:23,764 INFO [train.py:715] (5/8) Epoch 15, batch 7900, loss[loss=0.1179, simple_loss=0.1974, pruned_loss=0.01915, over 4775.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03051, over 973114.57 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:28:01,920 INFO [train.py:715] (5/8) Epoch 15, batch 7950, loss[loss=0.1083, simple_loss=0.1847, pruned_loss=0.01592, over 4990.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03043, over 973507.89 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:28:41,236 INFO [train.py:715] (5/8) Epoch 15, batch 8000, loss[loss=0.1345, simple_loss=0.2034, pruned_loss=0.03277, over 4741.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02982, over 972695.93 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:29:20,796 INFO [train.py:715] (5/8) Epoch 15, batch 8050, loss[loss=0.1532, simple_loss=0.2312, pruned_loss=0.03761, over 4868.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02979, over 972279.05 frames.], batch size: 38, lr: 1.48e-04
2022-05-08 08:29:59,764 INFO [train.py:715] (5/8) Epoch 15, batch 8100, loss[loss=0.1245, simple_loss=0.1956, pruned_loss=0.02675, over 4781.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 972098.22 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:30:38,765 INFO [train.py:715] (5/8) Epoch 15, batch 8150, loss[loss=0.1654, simple_loss=0.2331, pruned_loss=0.0488, over 4843.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02989, over 971005.24 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 08:31:18,842 INFO [train.py:715] (5/8) Epoch 15, batch 8200, loss[loss=0.1738, simple_loss=0.2385, pruned_loss=0.05457, over 4977.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03025, over 971401.26 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:31:57,572 INFO [train.py:715] (5/8) Epoch 15, batch 8250, loss[loss=0.1179, simple_loss=0.1994, pruned_loss=0.01824, over 4838.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03018, over 972079.39 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:32:36,548 INFO [train.py:715] (5/8) Epoch 15, batch 8300, loss[loss=0.1312, simple_loss=0.2095, pruned_loss=0.02648, over 4778.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02999, over 972637.52 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:33:15,771 INFO [train.py:715] (5/8) Epoch 15, batch 8350, loss[loss=0.1375, simple_loss=0.208, pruned_loss=0.03351, over 4702.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03066, over 971933.33 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:33:55,972 INFO [train.py:715] (5/8) Epoch 15, batch 8400, loss[loss=0.1445, simple_loss=0.2152, pruned_loss=0.03689, over 4988.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 971623.09 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:34:35,512 INFO [train.py:715] (5/8) Epoch 15, batch 8450, loss[loss=0.1464, simple_loss=0.2281, pruned_loss=0.03232, over 4779.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03022, over 970104.94 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:35:14,650 INFO [train.py:715] (5/8) Epoch 15, batch 8500, loss[loss=0.1642, simple_loss=0.2281, pruned_loss=0.05012, over 4876.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02995, over 970006.86 frames.], batch size: 22, lr: 1.48e-04
2022-05-08 08:35:54,834 INFO [train.py:715] (5/8) Epoch 15, batch 8550, loss[loss=0.1306, simple_loss=0.2032, pruned_loss=0.02907, over 4748.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03023, over 970696.64 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:36:33,509 INFO [train.py:715] (5/8) Epoch 15, batch 8600, loss[loss=0.1238, simple_loss=0.1971, pruned_loss=0.02529, over 4942.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02991, over 971962.99 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:37:12,322 INFO [train.py:715] (5/8) Epoch 15, batch 8650, loss[loss=0.1257, simple_loss=0.2, pruned_loss=0.02567, over 4774.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02987, over 971357.35 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:37:51,174 INFO [train.py:715] (5/8) Epoch 15, batch 8700, loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.04142, over 4968.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 971157.50 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:38:30,425 INFO [train.py:715] (5/8) Epoch 15, batch 8750, loss[loss=0.1596, simple_loss=0.235, pruned_loss=0.04208, over 4754.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03018, over 971623.13 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:39:08,911 INFO [train.py:715] (5/8) Epoch 15, batch 8800, loss[loss=0.1696, simple_loss=0.2387, pruned_loss=0.05027, over 4875.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03027, over 972112.78 frames.], batch size: 38, lr: 1.48e-04
2022-05-08 08:39:47,404 INFO [train.py:715] (5/8) Epoch 15, batch 8850, loss[loss=0.111, simple_loss=0.1872, pruned_loss=0.01744, over 4940.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03024, over 971531.24 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 08:40:26,831 INFO [train.py:715] (5/8) Epoch 15, batch 8900, loss[loss=0.1585, simple_loss=0.2233, pruned_loss=0.04687, over 4984.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03034, over 971314.63 frames.], batch size: 31, lr: 1.48e-04
2022-05-08 08:41:06,367 INFO [train.py:715] (5/8) Epoch 15, batch 8950, loss[loss=0.1298, simple_loss=0.1992, pruned_loss=0.03022, over 4781.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02983, over 971900.61 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:41:45,472 INFO [train.py:715] (5/8) Epoch 15, batch 9000, loss[loss=0.1648, simple_loss=0.2286, pruned_loss=0.05047, over 4877.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03036, over 971727.54 frames.], batch size: 22, lr: 1.48e-04
2022-05-08 08:41:45,472 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 08:42:05,028 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 08:42:44,050 INFO [train.py:715] (5/8) Epoch 15, batch 9050, loss[loss=0.1366, simple_loss=0.2062, pruned_loss=0.03356, over 4754.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2078, pruned_loss=0.03043, over 971598.18 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:43:23,566 INFO [train.py:715] (5/8) Epoch 15, batch 9100, loss[loss=0.1383, simple_loss=0.2142, pruned_loss=0.03115, over 4989.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03036, over 972023.87 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:44:03,264 INFO [train.py:715] (5/8) Epoch 15, batch 9150, loss[loss=0.143, simple_loss=0.2117, pruned_loss=0.03711, over 4954.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03048, over 971879.61 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:44:42,060 INFO [train.py:715] (5/8) Epoch 15, batch 9200, loss[loss=0.1446, simple_loss=0.2224, pruned_loss=0.03344, over 4902.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03061, over 972588.88 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:45:21,342 INFO [train.py:715] (5/8) Epoch 15, batch 9250, loss[loss=0.1506, simple_loss=0.2224, pruned_loss=0.03943, over 4915.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03036, over 972512.37 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:46:01,213 INFO [train.py:715] (5/8) Epoch 15, batch 9300, loss[loss=0.1386, simple_loss=0.2092, pruned_loss=0.03406, over 4916.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03023, over 972923.09 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:46:41,140 INFO [train.py:715] (5/8) Epoch 15, batch 9350, loss[loss=0.1612, simple_loss=0.2327, pruned_loss=0.04482, over 4950.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02998, over 972527.36 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:47:19,982 INFO [train.py:715] (5/8) Epoch 15, batch 9400, loss[loss=0.1275, simple_loss=0.2036, pruned_loss=0.02574, over 4827.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 972551.60 frames.], batch size: 27, lr: 1.48e-04
2022-05-08 08:47:59,297 INFO [train.py:715] (5/8) Epoch 15, batch 9450, loss[loss=0.133, simple_loss=0.2105, pruned_loss=0.0278, over 4985.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2095, pruned_loss=0.03018, over 972913.77 frames.], batch size: 27, lr: 1.48e-04
2022-05-08 08:48:38,582 INFO [train.py:715] (5/8) Epoch 15, batch 9500, loss[loss=0.1451, simple_loss=0.2136, pruned_loss=0.0383, over 4847.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.0302, over 972172.08 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 08:49:16,969 INFO [train.py:715] (5/8) Epoch 15, batch 9550, loss[loss=0.105, simple_loss=0.1744, pruned_loss=0.0178, over 4821.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02978, over 971284.78 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:49:56,304 INFO [train.py:715] (5/8) Epoch 15, batch 9600, loss[loss=0.1446, simple_loss=0.2194, pruned_loss=0.03494, over 4762.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.0298, over 971512.10 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:50:35,894 INFO [train.py:715] (5/8) Epoch 15, batch 9650, loss[loss=0.1444, simple_loss=0.2183, pruned_loss=0.03532, over 4982.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02984, over 970972.06 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:51:15,446 INFO [train.py:715] (5/8) Epoch 15, batch 9700, loss[loss=0.1203, simple_loss=0.1879, pruned_loss=0.02635, over 4790.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02993, over 971558.78 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:51:53,982 INFO [train.py:715] (5/8) Epoch 15, batch 9750, loss[loss=0.1576, simple_loss=0.2311, pruned_loss=0.04203, over 4786.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03044, over 971020.22 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:52:33,223 INFO [train.py:715] (5/8) Epoch 15, batch 9800, loss[loss=0.1431, simple_loss=0.2172, pruned_loss=0.03453, over 4890.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03038, over 970741.72 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:53:12,410 INFO [train.py:715] (5/8) Epoch 15, batch 9850, loss[loss=0.145, simple_loss=0.2192, pruned_loss=0.03539, over 4780.00 frames.], tot_loss[loss=0.136, simple_loss=0.2105, pruned_loss=0.03081, over 970078.50 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:53:50,990 INFO [train.py:715] (5/8) Epoch 15, batch 9900, loss[loss=0.1317, simple_loss=0.2191, pruned_loss=0.02212, over 4937.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03075, over 971015.38 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:54:30,416 INFO [train.py:715] (5/8) Epoch 15, batch 9950, loss[loss=0.1223, simple_loss=0.1975, pruned_loss=0.02358, over 4796.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03074, over 971648.77 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:55:09,387 INFO [train.py:715] (5/8) Epoch 15, batch 10000, loss[loss=0.1271, simple_loss=0.2023, pruned_loss=0.02596, over 4782.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03105, over 971384.08 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:55:48,601 INFO [train.py:715] (5/8) Epoch 15, batch 10050, loss[loss=0.1218, simple_loss=0.1979, pruned_loss=0.02283, over 4756.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03065, over 972183.74 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:56:26,958 INFO [train.py:715] (5/8) Epoch 15, batch 10100, loss[loss=0.1359, simple_loss=0.2064, pruned_loss=0.03272, over 4863.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03087, over 973101.01 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 08:57:05,757 INFO [train.py:715] (5/8) Epoch 15, batch 10150, loss[loss=0.1475, simple_loss=0.2213, pruned_loss=0.03683, over 4968.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03055, over 972609.42 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:57:45,602 INFO [train.py:715] (5/8) Epoch 15, batch 10200, loss[loss=0.1276, simple_loss=0.2029, pruned_loss=0.02613, over 4809.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03015, over 972132.95 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:58:23,923 INFO [train.py:715] (5/8) Epoch 15, batch 10250, loss[loss=0.1404, simple_loss=0.2247, pruned_loss=0.02804, over 4918.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03053, over 972154.70 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:59:03,219 INFO [train.py:715] (5/8) Epoch 15, batch 10300, loss[loss=0.1308, simple_loss=0.2068, pruned_loss=0.02737, over 4953.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03039, over 972453.06 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:59:42,681 INFO [train.py:715] (5/8) Epoch 15, batch 10350, loss[loss=0.1299, simple_loss=0.2029, pruned_loss=0.02849, over 4994.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03019, over 972317.77 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 09:00:21,805 INFO [train.py:715] (5/8) Epoch 15, batch 10400, loss[loss=0.1291, simple_loss=0.2051, pruned_loss=0.0266, over 4925.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03003, over 972650.91 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 09:00:59,820 INFO [train.py:715] (5/8) Epoch 15, batch 10450, loss[loss=0.1228, simple_loss=0.1981, pruned_loss=0.02378, over 4819.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02992, over 971783.45 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 09:01:38,803 INFO [train.py:715] (5/8) Epoch 15, batch 10500, loss[loss=0.128, simple_loss=0.1974, pruned_loss=0.02935, over 4953.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03068, over 972564.83 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 09:02:18,519 INFO [train.py:715] (5/8) Epoch 15, batch 10550, loss[loss=0.126, simple_loss=0.2098, pruned_loss=0.02109, over 4820.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03033, over 972857.97 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 09:02:56,678 INFO [train.py:715] (5/8) Epoch 15, batch 10600, loss[loss=0.137, simple_loss=0.2061, pruned_loss=0.03396, over 4765.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03016, over 971864.04 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 09:03:35,332 INFO [train.py:715] (5/8) Epoch 15, batch 10650, loss[loss=0.1126, simple_loss=0.1889, pruned_loss=0.01815, over 4814.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03011, over 971638.81 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 09:04:14,417 INFO [train.py:715] (5/8) Epoch 15, batch 10700, loss[loss=0.1328, simple_loss=0.2104, pruned_loss=0.02758, over 4915.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02987, over 971074.49 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 09:04:53,625 INFO [train.py:715] (5/8) Epoch 15, batch 10750, loss[loss=0.1315, simple_loss=0.2009, pruned_loss=0.03101, over 4790.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03024, over 971488.01 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 09:05:31,575 INFO [train.py:715] (5/8) Epoch 15, batch 10800, loss[loss=0.1483, simple_loss=0.2275, pruned_loss=0.03456, over 4908.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03017, over 972454.78 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:06:11,097 INFO [train.py:715] (5/8) Epoch 15, batch 10850, loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03155, over 4962.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03012, over 971842.68 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:06:50,390 INFO [train.py:715] (5/8) Epoch 15, batch 10900, loss[loss=0.1253, simple_loss=0.2034, pruned_loss=0.02358, over 4749.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02954, over 971829.85 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:07:28,756 INFO [train.py:715] (5/8) Epoch 15, batch 10950, loss[loss=0.1178, simple_loss=0.2043, pruned_loss=0.01569, over 4954.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02937, over 972992.84 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 09:08:06,754 INFO [train.py:715] (5/8) Epoch 15, batch 11000, loss[loss=0.1247, simple_loss=0.1989, pruned_loss=0.02528, over 4977.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02969, over 973157.06 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:08:45,833 INFO [train.py:715] (5/8) Epoch 15, batch 11050, loss[loss=0.1137, simple_loss=0.1871, pruned_loss=0.02017, over 4979.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02987, over 973431.55 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:09:25,315 INFO [train.py:715] (5/8) Epoch 15, batch 11100, loss[loss=0.138, simple_loss=0.2087, pruned_loss=0.03361, over 4927.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03025, over 972840.81 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:10:03,226 INFO [train.py:715] (5/8) Epoch 15, batch 11150, loss[loss=0.1112, simple_loss=0.1861, pruned_loss=0.01821, over 4798.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03021, over 972584.60 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:10:41,861 INFO [train.py:715] (5/8) Epoch 15, batch 11200, loss[loss=0.1389, simple_loss=0.2085, pruned_loss=0.03466, over 4820.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02959, over 972316.83 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:11:20,811 INFO [train.py:715] (5/8) Epoch 15, batch 11250, loss[loss=0.1251, simple_loss=0.2017, pruned_loss=0.02421, over 4808.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02899, over 971682.48 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:11:59,332 INFO [train.py:715] (5/8) Epoch 15, batch 11300, loss[loss=0.1347, simple_loss=0.2003, pruned_loss=0.03453, over 4898.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02907, over 971438.25 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 09:12:37,835 INFO [train.py:715] (5/8) Epoch 15, batch 11350, loss[loss=0.1281, simple_loss=0.2075, pruned_loss=0.02434, over 4924.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02916, over 972252.29 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 09:13:17,187 INFO [train.py:715] (5/8) Epoch 15, batch 11400, loss[loss=0.1382, simple_loss=0.2158, pruned_loss=0.03024, over 4739.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02872, over 971794.08 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:13:55,484 INFO [train.py:715] (5/8) Epoch 15, batch 11450, loss[loss=0.1194, simple_loss=0.1949, pruned_loss=0.02194, over 4750.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02912, over 971650.94 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:14:34,170 INFO [train.py:715] (5/8) Epoch 15, batch 11500, loss[loss=0.1177, simple_loss=0.194, pruned_loss=0.02067, over 4891.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02931, over 971681.90 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 09:15:13,131 INFO [train.py:715] (5/8) Epoch 15, batch 11550, loss[loss=0.1469, simple_loss=0.2287, pruned_loss=0.03249, over 4931.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02967, over 972399.28 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:15:52,415 INFO [train.py:715] (5/8) Epoch 15, batch 11600, loss[loss=0.1361, simple_loss=0.201, pruned_loss=0.03556, over 4790.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02956, over 973043.71 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:16:30,744 INFO [train.py:715] (5/8) Epoch 15, batch 11650, loss[loss=0.1214, simple_loss=0.1921, pruned_loss=0.02538, over 4754.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02983, over 972911.81 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:17:09,221 INFO [train.py:715] (5/8) Epoch 15, batch 11700, loss[loss=0.1078, simple_loss=0.1852, pruned_loss=0.01523, over 4760.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03012, over 973489.49 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:17:48,442 INFO [train.py:715] (5/8) Epoch 15, batch 11750, loss[loss=0.1139, simple_loss=0.1888, pruned_loss=0.01951, over 4796.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03004, over 973758.71 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:18:27,446 INFO [train.py:715] (5/8) Epoch 15, batch 11800, loss[loss=0.1344, simple_loss=0.2198, pruned_loss=0.02454, over 4932.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03041, over 973938.21 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:19:05,512 INFO [train.py:715] (5/8) Epoch 15, batch 11850, loss[loss=0.1577, simple_loss=0.2243, pruned_loss=0.04556, over 4847.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03006, over 972771.73 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:19:45,040 INFO [train.py:715] (5/8) Epoch 15, batch 11900, loss[loss=0.1534, simple_loss=0.2184, pruned_loss=0.04425, over 4774.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02957, over 972357.89 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:20:25,121 INFO [train.py:715] (5/8) Epoch 15, batch 11950, loss[loss=0.1814, simple_loss=0.2497, pruned_loss=0.05655, over 4909.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.02958, over 972753.74 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 09:21:03,708 INFO [train.py:715] (5/8) Epoch 15, batch 12000, loss[loss=0.1382, simple_loss=0.2025, pruned_loss=0.03696, over 4950.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0298, over 973088.40 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:21:03,708 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 09:21:20,396 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.105, simple_loss=0.1887, pruned_loss=0.01066, over 914524.00 frames.
2022-05-08 09:21:59,114 INFO [train.py:715] (5/8) Epoch 15, batch 12050, loss[loss=0.1258, simple_loss=0.2022, pruned_loss=0.02469, over 4989.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 973139.75 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:22:38,254 INFO [train.py:715] (5/8) Epoch 15, batch 12100, loss[loss=0.1791, simple_loss=0.2358, pruned_loss=0.06119, over 4890.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02986, over 973532.10 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:23:17,964 INFO [train.py:715] (5/8) Epoch 15, batch 12150, loss[loss=0.1535, simple_loss=0.2417, pruned_loss=0.03264, over 4963.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02988, over 972538.41 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:23:56,409 INFO [train.py:715] (5/8) Epoch 15, batch 12200, loss[loss=0.1134, simple_loss=0.1975, pruned_loss=0.01463, over 4803.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02946, over 971969.61 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:24:35,177 INFO [train.py:715] (5/8) Epoch 15, batch 12250, loss[loss=0.1415, simple_loss=0.2231, pruned_loss=0.02997, over 4925.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03016, over 972122.97 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:25:14,195 INFO [train.py:715] (5/8) Epoch 15, batch 12300, loss[loss=0.1052, simple_loss=0.1781, pruned_loss=0.01618, over 4808.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03037, over 971782.10 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:25:54,058 INFO [train.py:715] (5/8) Epoch 15, batch 12350, loss[loss=0.1389, simple_loss=0.2018, pruned_loss=0.03799, over 4816.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03023, over 971868.43 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:26:32,325 INFO [train.py:715] (5/8) Epoch 15, batch 12400, loss[loss=0.1388, simple_loss=0.2055, pruned_loss=0.03604, over 4977.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03046, over 972285.95 frames.], batch size: 28, lr: 1.47e-04
2022-05-08 09:27:11,074 INFO [train.py:715] (5/8) Epoch 15, batch 12450, loss[loss=0.1277, simple_loss=0.2115, pruned_loss=0.02197, over 4830.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03025, over 972526.43 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:27:51,092 INFO [train.py:715] (5/8) Epoch 15, batch 12500, loss[loss=0.1174, simple_loss=0.1965, pruned_loss=0.01919, over 4972.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03063, over 971691.13 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:28:29,287 INFO [train.py:715] (5/8) Epoch 15, batch 12550, loss[loss=0.1423, simple_loss=0.2117, pruned_loss=0.03643, over 4776.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03068, over 971870.21 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:29:08,353 INFO [train.py:715] (5/8) Epoch 15, batch 12600, loss[loss=0.1346, simple_loss=0.2182, pruned_loss=0.02543, over 4968.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02997, over 972605.13 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:29:46,866 INFO [train.py:715] (5/8) Epoch 15, batch 12650, loss[loss=0.1203, simple_loss=0.1956, pruned_loss=0.02249, over 4699.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02951, over 971767.76 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:30:26,459 INFO [train.py:715] (5/8) Epoch 15, batch 12700, loss[loss=0.12, simple_loss=0.2001, pruned_loss=0.01998, over 4809.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 971502.19 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:31:04,801 INFO [train.py:715] (5/8) Epoch 15, batch 12750, loss[loss=0.1514, simple_loss=0.2146, pruned_loss=0.04416, over 4850.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03039, over 971995.26 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:31:43,633 INFO [train.py:715] (5/8) Epoch 15, batch 12800, loss[loss=0.1104, simple_loss=0.1833, pruned_loss=0.01878, over 4824.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03008, over 971805.31 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:32:23,164 INFO [train.py:715] (5/8) Epoch 15, batch 12850, loss[loss=0.1288, simple_loss=0.2128, pruned_loss=0.02239, over 4792.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02953, over 972644.80 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:33:01,777 INFO [train.py:715] (5/8) Epoch 15, batch 12900, loss[loss=0.1126, simple_loss=0.1923, pruned_loss=0.01649, over 4723.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02933, over 973648.17 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:33:40,808 INFO [train.py:715] (5/8) Epoch 15, batch 12950, loss[loss=0.1395, simple_loss=0.2133, pruned_loss=0.03285, over 4844.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02978, over 973507.49 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 09:34:20,125 INFO [train.py:715] (5/8) Epoch 15, batch 13000, loss[loss=0.1314, simple_loss=0.2096, pruned_loss=0.02655, over 4784.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 973436.84 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:34:59,663 INFO [train.py:715] (5/8) Epoch 15, batch 13050, loss[loss=0.1197, simple_loss=0.1967, pruned_loss=0.02132, over 4797.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03055, over 973363.73 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:35:38,148 INFO [train.py:715] (5/8) Epoch 15, batch 13100, loss[loss=0.1266, simple_loss=0.1922, pruned_loss=0.03046, over 4807.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03037, over 973678.25 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:36:17,622 INFO [train.py:715] (5/8) Epoch 15, batch 13150, loss[loss=0.1341, simple_loss=0.2118, pruned_loss=0.0282, over 4938.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03066, over 972542.77 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:36:57,404 INFO [train.py:715] (5/8) Epoch 15, batch 13200, loss[loss=0.1217, simple_loss=0.1975, pruned_loss=0.02296, over 4762.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03113, over 971991.30 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:37:35,198 INFO [train.py:715] (5/8) Epoch 15, batch 13250, loss[loss=0.139, simple_loss=0.2178, pruned_loss=0.03011, over 4885.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03122, over 972631.20 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 09:38:14,331 INFO [train.py:715] (5/8) Epoch 15, batch 13300, loss[loss=0.1231, simple_loss=0.1974, pruned_loss=0.02444, over 4861.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03123, over 972312.38 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:38:53,946 INFO [train.py:715] (5/8) Epoch 15, batch 13350, loss[loss=0.1128, simple_loss=0.1862, pruned_loss=0.01969, over 4965.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03085, over 972505.03 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:39:34,556 INFO [train.py:715] (5/8) Epoch 15, batch 13400, loss[loss=0.1328, simple_loss=0.2052, pruned_loss=0.03015, over 4780.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.0305, over 973291.90 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:40:13,183 INFO [train.py:715] (5/8) Epoch 15, batch 13450, loss[loss=0.1401, simple_loss=0.2146, pruned_loss=0.03282, over 4979.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03027, over 973174.29 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:40:51,764 INFO [train.py:715] (5/8) Epoch 15, batch 13500, loss[loss=0.1398, simple_loss=0.21, pruned_loss=0.03483, over 4848.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.0303, over 972591.56 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:41:31,304 INFO [train.py:715] (5/8) Epoch 15, batch 13550, loss[loss=0.1183, simple_loss=0.2041, pruned_loss=0.01622, over 4820.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03021, over 972836.93 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:42:09,583 INFO [train.py:715] (5/8) Epoch 15, batch 13600, loss[loss=0.1448, simple_loss=0.2276, pruned_loss=0.03103, over 4963.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02993, over 973257.67 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:42:48,565 INFO [train.py:715] (5/8) Epoch 15, batch 13650, loss[loss=0.1106, simple_loss=0.1899, pruned_loss=0.01564, over 4874.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02956, over 973014.30 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:43:27,813 INFO [train.py:715] (5/8) Epoch 15, batch 13700, loss[loss=0.1451, simple_loss=0.2164, pruned_loss=0.03693, over 4971.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02977, over 972629.34 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:44:06,259 INFO [train.py:715] (5/8) Epoch 15, batch 13750, loss[loss=0.1247, simple_loss=0.2024, pruned_loss=0.02352, over 4758.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03041, over 972189.77 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:44:44,979 INFO [train.py:715] (5/8) Epoch 15, batch 13800, loss[loss=0.1295, simple_loss=0.2079, pruned_loss=0.02554, over 4940.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03022, over 972603.64 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:45:23,199 INFO [train.py:715] (5/8) Epoch 15, batch 13850, loss[loss=0.1368, simple_loss=0.2036, pruned_loss=0.03498, over 4924.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03045, over 973328.29 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:46:05,203 INFO [train.py:715] (5/8) Epoch 15, batch 13900, loss[loss=0.1224, simple_loss=0.1949, pruned_loss=0.02498, over 4989.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03025, over 973411.65 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:46:43,312 INFO [train.py:715] (5/8) Epoch 15, batch 13950, loss[loss=0.1279, simple_loss=0.198, pruned_loss=0.02886, over 4826.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03042, over 973082.30 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 09:47:21,601 INFO [train.py:715] (5/8) Epoch 15, batch 14000, loss[loss=0.1181, simple_loss=0.1959, pruned_loss=0.02011, over 4955.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02997, over 973983.68 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:48:00,897 INFO [train.py:715] (5/8) Epoch 15, batch 14050, loss[loss=0.1287, simple_loss=0.2097, pruned_loss=0.0238, over 4877.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03008, over 972711.97 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 09:48:38,845 INFO [train.py:715] (5/8) Epoch 15, batch 14100, loss[loss=0.1415, simple_loss=0.2162, pruned_loss=0.03345, over 4797.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03011, over 972676.15 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:49:17,894 INFO [train.py:715] (5/8) Epoch 15, batch 14150, loss[loss=0.1139, simple_loss=0.19, pruned_loss=0.01891, over 4943.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.02999, over 972843.34 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:49:56,535 INFO [train.py:715] (5/8) Epoch 15, batch 14200, loss[loss=0.1483, simple_loss=0.2138, pruned_loss=0.0414, over 4984.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03068, over 972747.54 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:50:35,492 INFO [train.py:715] (5/8) Epoch 15, batch 14250, loss[loss=0.1263, simple_loss=0.1998, pruned_loss=0.02645, over 4979.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03027, over 972826.42 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:51:13,330 INFO [train.py:715] (5/8) Epoch 15, batch 14300, loss[loss=0.1435, simple_loss=0.2128, pruned_loss=0.03711, over 4902.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 972560.64 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:51:51,767 INFO [train.py:715] (5/8) Epoch 15, batch 14350, loss[loss=0.1558, simple_loss=0.2391, pruned_loss=0.0363, over 4818.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03012, over 971470.41 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:52:30,860 INFO [train.py:715] (5/8) Epoch 15, batch 14400, loss[loss=0.1258, simple_loss=0.203, pruned_loss=0.02432, over 4687.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02989, over 972010.85 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:53:08,607 INFO [train.py:715] (5/8) Epoch 15, batch 14450, loss[loss=0.1348, simple_loss=0.2212, pruned_loss=0.02422, over 4854.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03002, over 971544.36 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 09:53:47,593 INFO [train.py:715] (5/8) Epoch 15, batch 14500, loss[loss=0.1191, simple_loss=0.1942, pruned_loss=0.02197, over 4803.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02984, over 972804.55 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:54:25,856 INFO [train.py:715] (5/8) Epoch 15, batch 14550, loss[loss=0.1101, simple_loss=0.1911, pruned_loss=0.01459, over 4921.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 972848.90 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:55:04,849 INFO [train.py:715] (5/8) Epoch 15, batch 14600, loss[loss=0.1371, simple_loss=0.204, pruned_loss=0.03506, over 4769.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03006, over 972817.64 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:55:42,672 INFO [train.py:715] (5/8) Epoch 15, batch 14650, loss[loss=0.1325, simple_loss=0.2044, pruned_loss=0.03026, over 4823.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03032, over 971845.52 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:56:20,651 INFO [train.py:715] (5/8) Epoch 15, batch 14700, loss[loss=0.1129, simple_loss=0.1978, pruned_loss=0.01398, over 4829.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03063, over 971759.87 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:56:59,721 INFO [train.py:715] (5/8) Epoch 15, batch 14750, loss[loss=0.1184, simple_loss=0.2029, pruned_loss=0.01699, over 4814.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03026, over 971379.59 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:57:37,352 INFO [train.py:715] (5/8) Epoch 15, batch 14800, loss[loss=0.1197, simple_loss=0.1927, pruned_loss=0.0234, over 4862.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03034, over 970705.51 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:58:16,192 INFO [train.py:715] (5/8) Epoch 15, batch 14850, loss[loss=0.1448, simple_loss=0.2118, pruned_loss=0.03894, over 4951.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02998, over 971252.83 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:58:55,098 INFO [train.py:715] (5/8) Epoch 15, batch 14900, loss[loss=0.1436, simple_loss=0.2212, pruned_loss=0.03299, over 4889.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.0302, over 971850.62 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 09:59:33,271 INFO [train.py:715] (5/8) Epoch 15, batch 14950, loss[loss=0.1509, simple_loss=0.2306, pruned_loss=0.0356, over 4894.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03001, over 972331.41 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:00:11,564 INFO [train.py:715] (5/8) Epoch 15, batch 15000, loss[loss=0.1388, simple_loss=0.2087, pruned_loss=0.03451, over 4853.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2078, pruned_loss=0.03055, over 971629.18 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 10:00:11,564 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 10:00:26,344 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
2022-05-08 10:01:05,812 INFO [train.py:715] (5/8) Epoch 15, batch 15050, loss[loss=0.1302, simple_loss=0.2035, pruned_loss=0.02846, over 4836.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03004, over 972354.52 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:01:43,978 INFO [train.py:715] (5/8) Epoch 15, batch 15100, loss[loss=0.1326, simple_loss=0.2177, pruned_loss=0.0237, over 4800.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03035, over 972004.33 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:02:23,331 INFO [train.py:715] (5/8) Epoch 15, batch 15150, loss[loss=0.1373, simple_loss=0.2233, pruned_loss=0.02563, over 4717.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03036, over 971035.68 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:03:01,053 INFO [train.py:715] (5/8) Epoch 15, batch 15200, loss[loss=0.1401, simple_loss=0.2112, pruned_loss=0.03446, over 4849.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.0305, over 971070.08 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:03:39,351 INFO [train.py:715] (5/8) Epoch 15, batch 15250, loss[loss=0.1231, simple_loss=0.1967, pruned_loss=0.02479, over 4866.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03037, over 971378.55 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:04:18,903 INFO [train.py:715] (5/8) Epoch 15, batch 15300, loss[loss=0.1354, simple_loss=0.2156, pruned_loss=0.02756, over 4930.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02936, over 971845.48 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:04:56,984 INFO [train.py:715] (5/8) Epoch 15, batch 15350, loss[loss=0.1378, simple_loss=0.2098, pruned_loss=0.03292, over 4823.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02986, over 971733.69 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:05:35,891 INFO [train.py:715] (5/8) Epoch 15, batch 15400, loss[loss=0.1342, simple_loss=0.2012, pruned_loss=0.03356, over 4785.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02986, over 971223.14 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:06:13,986 INFO [train.py:715] (5/8) Epoch 15, batch 15450, loss[loss=0.1381, simple_loss=0.2245, pruned_loss=0.02584, over 4984.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02989, over 972124.26 frames.], batch size: 28, lr: 1.47e-04
2022-05-08 10:06:52,879 INFO [train.py:715] (5/8) Epoch 15, batch 15500, loss[loss=0.1233, simple_loss=0.2048, pruned_loss=0.02086, over 4975.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02975, over 972726.90 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:07:31,444 INFO [train.py:715] (5/8) Epoch 15, batch 15550, loss[loss=0.1346, simple_loss=0.2171, pruned_loss=0.02603, over 4767.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02939, over 972604.51 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:08:10,326 INFO [train.py:715] (5/8) Epoch 15, batch 15600, loss[loss=0.1369, simple_loss=0.2086, pruned_loss=0.03263, over 4880.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 972536.98 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 10:08:49,133 INFO [train.py:715] (5/8) Epoch 15, batch 15650, loss[loss=0.1522, simple_loss=0.2179, pruned_loss=0.04329, over 4851.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02993, over 972327.95 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 10:09:27,216 INFO [train.py:715] (5/8) Epoch 15, batch 15700, loss[loss=0.1405, simple_loss=0.2191, pruned_loss=0.03092, over 4936.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02979, over 972424.34 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:10:05,787 INFO [train.py:715] (5/8) Epoch 15, batch 15750, loss[loss=0.115, simple_loss=0.1856, pruned_loss=0.02218, over 4863.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03008, over 971957.54 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 10:10:44,347 INFO [train.py:715] (5/8) Epoch 15, batch 15800, loss[loss=0.1342, simple_loss=0.2115, pruned_loss=0.02848, over 4767.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02995, over 972018.38 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:11:23,020 INFO [train.py:715] (5/8) Epoch 15, batch 15850, loss[loss=0.1309, simple_loss=0.197, pruned_loss=0.03237, over 4844.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 972926.39 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:12:01,146 INFO [train.py:715] (5/8) Epoch 15, batch 15900, loss[loss=0.1057, simple_loss=0.1833, pruned_loss=0.01404, over 4821.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02999, over 972700.11 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 10:12:39,306 INFO [train.py:715] (5/8) Epoch 15, batch 15950, loss[loss=0.1522, simple_loss=0.2425, pruned_loss=0.03094, over 4815.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02991, over 972722.09 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:13:18,369 INFO [train.py:715] (5/8) Epoch 15, batch 16000, loss[loss=0.1424, simple_loss=0.2181, pruned_loss=0.0333, over 4952.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2088, pruned_loss=0.02968, over 972547.62 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 10:13:56,003 INFO [train.py:715] (5/8) Epoch 15, batch 16050, loss[loss=0.1441, simple_loss=0.2278, pruned_loss=0.03023, over 4904.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2091, pruned_loss=0.02978, over 973015.83 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:14:34,593 INFO [train.py:715] (5/8) Epoch 15, batch 16100, loss[loss=0.1009, simple_loss=0.1718, pruned_loss=0.015, over 4800.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2092, pruned_loss=0.02978, over 973283.86 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:15:13,038 INFO [train.py:715] (5/8) Epoch 15, batch 16150, loss[loss=0.1105, simple_loss=0.186, pruned_loss=0.01752, over 4908.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2091, pruned_loss=0.02977, over 973322.21 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:15:51,555 INFO [train.py:715] (5/8) Epoch 15, batch 16200, loss[loss=0.1002, simple_loss=0.1744, pruned_loss=0.01294, over 4800.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02968, over 973256.59 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:16:29,837 INFO [train.py:715] (5/8) Epoch 15, batch 16250, loss[loss=0.1455, simple_loss=0.2185, pruned_loss=0.03628, over 4925.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02984, over 973271.16 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:17:08,215 INFO [train.py:715] (5/8) Epoch 15, batch 16300, loss[loss=0.1402, simple_loss=0.2172, pruned_loss=0.03161, over 4695.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02978, over 971693.48 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:17:46,752 INFO [train.py:715] (5/8) Epoch 15, batch 16350, loss[loss=0.1207, simple_loss=0.1953, pruned_loss=0.02305, over 4962.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03008, over 972502.84 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 10:18:24,621 INFO [train.py:715] (5/8) Epoch 15, batch 16400, loss[loss=0.1347, simple_loss=0.2033, pruned_loss=0.0331, over 4845.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 972103.96 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:19:03,503 INFO [train.py:715] (5/8) Epoch 15, batch 16450, loss[loss=0.136, simple_loss=0.2058, pruned_loss=0.03311, over 4820.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03057, over 971874.28 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:19:41,759 INFO [train.py:715] (5/8) Epoch 15, batch 16500, loss[loss=0.1003, simple_loss=0.1805, pruned_loss=0.01005, over 4890.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03039, over 972525.66 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 10:20:20,131 INFO [train.py:715] (5/8) Epoch 15, batch 16550, loss[loss=0.1477, simple_loss=0.216, pruned_loss=0.03969, over 4784.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03039, over 972564.34 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:20:58,277 INFO [train.py:715] (5/8) Epoch 15, batch 16600, loss[loss=0.1245, simple_loss=0.2031, pruned_loss=0.02295, over 4789.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03029, over 972501.17 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 10:21:37,034 INFO [train.py:715] (5/8) Epoch 15, batch 16650, loss[loss=0.1385, simple_loss=0.2207, pruned_loss=0.02814, over 4942.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03065, over 972575.39 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:22:16,798 INFO [train.py:715] (5/8) Epoch 15, batch 16700, loss[loss=0.1187, simple_loss=0.1919, pruned_loss=0.0227, over 4762.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03046, over 973087.77 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:22:55,521 INFO [train.py:715] (5/8) Epoch 15, batch 16750, loss[loss=0.1139, simple_loss=0.1796, pruned_loss=0.02403, over 4788.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03036, over 972470.37 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:23:34,512 INFO [train.py:715] (5/8) Epoch 15, batch 16800, loss[loss=0.144, simple_loss=0.213, pruned_loss=0.03748, over 4850.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02998, over 972036.72 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 10:24:13,668 INFO [train.py:715] (5/8) Epoch 15, batch 16850, loss[loss=0.1398, simple_loss=0.2145, pruned_loss=0.03252, over 4783.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03011, over 971953.59 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:24:52,753 INFO [train.py:715] (5/8) Epoch 15, batch 16900, loss[loss=0.1456, simple_loss=0.2181, pruned_loss=0.03653, over 4965.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03037, over 971874.66 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 10:25:31,720 INFO [train.py:715] (5/8) Epoch 15, batch 16950, loss[loss=0.1567, simple_loss=0.2234, pruned_loss=0.04497, over 4920.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03048, over 972608.05 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 10:26:10,073 INFO [train.py:715] (5/8) Epoch 15, batch 17000, loss[loss=0.1391, simple_loss=0.2089, pruned_loss=0.03464, over 4874.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03065, over 972593.73 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 10:26:49,335 INFO [train.py:715] (5/8) Epoch 15, batch 17050, loss[loss=0.1185, simple_loss=0.1874, pruned_loss=0.02481, over 4912.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03038, over 973506.30 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:27:27,263 INFO [train.py:715] (5/8) Epoch 15, batch 17100, loss[loss=0.1143, simple_loss=0.1837, pruned_loss=0.02251, over 4793.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03039, over 972105.19 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:28:06,076 INFO [train.py:715] (5/8) Epoch 15, batch 17150, loss[loss=0.1761, simple_loss=0.2424, pruned_loss=0.05493, over 4969.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.0301, over 972408.82 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 10:28:44,478 INFO [train.py:715] (5/8) Epoch 15, batch 17200, loss[loss=0.1134, simple_loss=0.1888, pruned_loss=0.01893, over 4647.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03041, over 971876.81 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:29:23,147 INFO [train.py:715] (5/8) Epoch 15, batch 17250, loss[loss=0.1199, simple_loss=0.2002, pruned_loss=0.0198, over 4764.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.03002, over 972227.72 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:30:01,723 INFO [train.py:715] (5/8) Epoch 15, batch 17300, loss[loss=0.1363, simple_loss=0.2025, pruned_loss=0.03501, over 4885.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03033, over 971691.35 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 10:30:40,362 INFO [train.py:715] (5/8) Epoch 15, batch 17350, loss[loss=0.1125, simple_loss=0.1928, pruned_loss=0.01611, over 4818.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03034, over 971337.44 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 10:31:19,952 INFO [train.py:715] (5/8) Epoch 15, batch 17400, loss[loss=0.1489, simple_loss=0.2261, pruned_loss=0.03582, over 4979.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02996, over 972008.66 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:31:57,891 INFO [train.py:715] (5/8) Epoch 15, batch 17450, loss[loss=0.1229, simple_loss=0.206, pruned_loss=0.01991, over 4789.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02971, over 972868.53 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:32:36,870 INFO [train.py:715] (5/8) Epoch 15, batch 17500, loss[loss=0.1362, simple_loss=0.214, pruned_loss=0.02922, over 4914.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02907, over 973098.08 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:33:15,843 INFO [train.py:715] (5/8) Epoch 15, batch 17550, loss[loss=0.1281, simple_loss=0.2048, pruned_loss=0.02577, over 4861.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02932, over 972948.53 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 10:33:54,432 INFO [train.py:715] (5/8) Epoch 15, batch 17600, loss[loss=0.1148, simple_loss=0.1874, pruned_loss=0.02106, over 4838.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02973, over 972386.91 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 10:34:32,813 INFO [train.py:715] (5/8) Epoch 15, batch 17650, loss[loss=0.1117, simple_loss=0.1817, pruned_loss=0.02086, over 4942.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02979, over 972616.90 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:35:11,435 INFO [train.py:715] (5/8) Epoch 15, batch 17700, loss[loss=0.1473, simple_loss=0.2193, pruned_loss=0.0377, over 4950.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03046, over 972960.54 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:35:50,324 INFO [train.py:715] (5/8) Epoch 15, batch 17750, loss[loss=0.1225, simple_loss=0.1958, pruned_loss=0.02459, over 4936.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03066, over 973803.11 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:36:28,684 INFO [train.py:715] (5/8) Epoch 15, batch 17800, loss[loss=0.1695, simple_loss=0.2308, pruned_loss=0.0541, over 4957.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03027, over 973215.07 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 10:37:07,667 INFO [train.py:715] (5/8) Epoch 15, batch 17850, loss[loss=0.1415, simple_loss=0.2181, pruned_loss=0.03244, over 4866.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03013, over 973087.05 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 10:37:46,657 INFO [train.py:715] (5/8) Epoch 15, batch 17900, loss[loss=0.1253, simple_loss=0.2045, pruned_loss=0.02303, over 4748.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02966, over 972253.18 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:38:25,488 INFO [train.py:715] (5/8) Epoch 15, batch 17950, loss[loss=0.1353, simple_loss=0.1936, pruned_loss=0.03847, over 4769.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03001, over 972366.47 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:39:03,819 INFO [train.py:715] (5/8) Epoch 15, batch 18000, loss[loss=0.1601, simple_loss=0.2475, pruned_loss=0.03634, over 4799.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02967, over 972643.28 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:39:03,819 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 10:39:13,328 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1048, simple_loss=0.1885, pruned_loss=0.01059, over 914524.00 frames.
2022-05-08 10:39:51,810 INFO [train.py:715] (5/8) Epoch 15, batch 18050, loss[loss=0.1236, simple_loss=0.1872, pruned_loss=0.03001, over 4976.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.0297, over 972205.93 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:40:30,478 INFO [train.py:715] (5/8) Epoch 15, batch 18100, loss[loss=0.1442, simple_loss=0.2147, pruned_loss=0.03688, over 4875.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02996, over 972298.12 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 10:41:09,234 INFO [train.py:715] (5/8) Epoch 15, batch 18150, loss[loss=0.1098, simple_loss=0.1845, pruned_loss=0.01762, over 4971.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2072, pruned_loss=0.03012, over 971941.97 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 10:41:47,121 INFO [train.py:715] (5/8) Epoch 15, batch 18200, loss[loss=0.1413, simple_loss=0.2062, pruned_loss=0.03823, over 4867.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03028, over 972390.18 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 10:42:25,783 INFO [train.py:715] (5/8) Epoch 15, batch 18250, loss[loss=0.1227, simple_loss=0.1999, pruned_loss=0.02274, over 4788.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.0302, over 972936.35 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 10:43:04,445 INFO [train.py:715] (5/8) Epoch 15, batch 18300, loss[loss=0.1228, simple_loss=0.1954, pruned_loss=0.02507, over 4976.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03027, over 972793.14 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 10:43:42,533 INFO [train.py:715] (5/8) Epoch 15, batch 18350, loss[loss=0.1294, simple_loss=0.1985, pruned_loss=0.03015, over 4776.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03043, over 972839.60 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 10:44:21,121 INFO [train.py:715] (5/8) Epoch 15, batch 18400, loss[loss=0.1297, simple_loss=0.1946, pruned_loss=0.0324, over 4950.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 973717.19 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 10:44:59,619 INFO [train.py:715] (5/8) Epoch 15, batch 18450, loss[loss=0.1302, simple_loss=0.2069, pruned_loss=0.02676, over 4916.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03019, over 972856.93 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 10:45:38,880 INFO [train.py:715] (5/8) Epoch 15, batch 18500, loss[loss=0.1346, simple_loss=0.2161, pruned_loss=0.02654, over 4792.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03046, over 972866.96 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 10:46:17,375 INFO [train.py:715] (5/8) Epoch 15, batch 18550, loss[loss=0.103, simple_loss=0.1747, pruned_loss=0.01563, over 4690.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03094, over 972247.14 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:46:55,965 INFO [train.py:715] (5/8) Epoch 15, batch 18600, loss[loss=0.1301, simple_loss=0.2005, pruned_loss=0.02985, over 4837.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 972907.50 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 10:47:34,881 INFO [train.py:715] (5/8) Epoch 15, batch 18650, loss[loss=0.1626, simple_loss=0.2185, pruned_loss=0.05334, over 4980.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03093, over 973128.63 frames.], batch size: 31, lr: 1.46e-04
2022-05-08 10:48:13,536 INFO [train.py:715] (5/8) Epoch 15, batch 18700, loss[loss=0.131, simple_loss=0.1943, pruned_loss=0.03385, over 4814.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03111, over 972866.69 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 10:48:52,386 INFO [train.py:715] (5/8) Epoch 15, batch 18750, loss[loss=0.1526, simple_loss=0.227, pruned_loss=0.03913, over 4791.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03113, over 972852.53 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 10:49:31,674 INFO [train.py:715] (5/8) Epoch 15, batch 18800, loss[loss=0.1263, simple_loss=0.1981, pruned_loss=0.02725, over 4761.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03085, over 972793.82 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:50:10,918 INFO [train.py:715] (5/8) Epoch 15, batch 18850, loss[loss=0.11, simple_loss=0.1841, pruned_loss=0.01802, over 4799.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.0304, over 971706.92 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 10:50:49,338 INFO [train.py:715] (5/8) Epoch 15, batch 18900, loss[loss=0.155, simple_loss=0.2231, pruned_loss=0.04343, over 4792.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03034, over 972590.47 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 10:51:28,550 INFO [train.py:715] (5/8) Epoch 15, batch 18950, loss[loss=0.1484, simple_loss=0.2163, pruned_loss=0.04026, over 4822.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03046, over 972288.25 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:52:07,868 INFO [train.py:715] (5/8) Epoch 15, batch 19000, loss[loss=0.1279, simple_loss=0.2089, pruned_loss=0.02348, over 4954.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03021, over 972391.85 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 10:52:46,222 INFO [train.py:715] (5/8) Epoch 15, batch 19050, loss[loss=0.1123, simple_loss=0.1925, pruned_loss=0.01608, over 4956.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03027, over 971756.00 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 10:53:25,396 INFO [train.py:715] (5/8) Epoch 15, batch 19100, loss[loss=0.1222, simple_loss=0.196, pruned_loss=0.02414, over 4744.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03011, over 972438.26 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 10:54:03,698 INFO [train.py:715] (5/8) Epoch 15, batch 19150, loss[loss=0.1285, simple_loss=0.1982, pruned_loss=0.02945, over 4977.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.0302, over 972905.18 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:54:41,931 INFO [train.py:715] (5/8) Epoch 15, batch 19200, loss[loss=0.1187, simple_loss=0.1997, pruned_loss=0.01885, over 4898.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03055, over 973468.03 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:55:19,947 INFO [train.py:715] (5/8) Epoch 15, batch 19250, loss[loss=0.134, simple_loss=0.2014, pruned_loss=0.03325, over 4778.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03039, over 973358.74 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 10:55:58,064 INFO [train.py:715] (5/8) Epoch 15, batch 19300, loss[loss=0.121, simple_loss=0.196, pruned_loss=0.02299, over 4793.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02995, over 972557.93 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 10:56:36,951 INFO [train.py:715] (5/8) Epoch 15, batch 19350, loss[loss=0.1359, simple_loss=0.2084, pruned_loss=0.03167, over 4897.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02996, over 971955.14 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:57:14,728 INFO [train.py:715] (5/8) Epoch 15, batch 19400, loss[loss=0.1116, simple_loss=0.1826, pruned_loss=0.02035, over 4965.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03013, over 972601.02 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 10:57:53,614 INFO [train.py:715] (5/8) Epoch 15, batch 19450, loss[loss=0.1369, simple_loss=0.212, pruned_loss=0.03085, over 4878.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03024, over 972644.15 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 10:58:31,637 INFO [train.py:715] (5/8) Epoch 15, batch 19500, loss[loss=0.1228, simple_loss=0.1992, pruned_loss=0.02322, over 4944.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03013, over 972770.16 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 10:59:09,771 INFO [train.py:715] (5/8) Epoch 15, batch 19550, loss[loss=0.1354, simple_loss=0.1998, pruned_loss=0.03551, over 4641.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02998, over 972524.58 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 10:59:48,219 INFO [train.py:715] (5/8) Epoch 15, batch 19600, loss[loss=0.158, simple_loss=0.2192, pruned_loss=0.04842, over 4978.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.0301, over 973416.98 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:00:26,255 INFO [train.py:715] (5/8) Epoch 15, batch 19650, loss[loss=0.1661, simple_loss=0.2471, pruned_loss=0.04256, over 4784.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.03, over 972734.95 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:01:05,292 INFO [train.py:715] (5/8) Epoch 15, batch 19700, loss[loss=0.1576, simple_loss=0.235, pruned_loss=0.04012, over 4863.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03016, over 972806.41 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:01:42,989 INFO [train.py:715] (5/8) Epoch 15, batch 19750, loss[loss=0.1663, simple_loss=0.2407, pruned_loss=0.04599, over 4732.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02978, over 971893.84 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:02:21,391 INFO [train.py:715] (5/8) Epoch 15, batch 19800, loss[loss=0.1032, simple_loss=0.1825, pruned_loss=0.01195, over 4840.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03056, over 972587.79 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:02:59,698 INFO [train.py:715] (5/8) Epoch 15, batch 19850, loss[loss=0.1303, simple_loss=0.2025, pruned_loss=0.02909, over 4967.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03003, over 972667.74 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:03:37,786 INFO [train.py:715] (5/8) Epoch 15, batch 19900, loss[loss=0.125, simple_loss=0.2017, pruned_loss=0.02419, over 4805.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02995, over 972401.99 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:04:16,957 INFO [train.py:715] (5/8) Epoch 15, batch 19950, loss[loss=0.13, simple_loss=0.2098, pruned_loss=0.02509, over 4876.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03, over 972791.21 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:04:55,169 INFO [train.py:715] (5/8) Epoch 15, batch 20000, loss[loss=0.1504, simple_loss=0.2279, pruned_loss=0.03649, over 4852.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03013, over 972707.62 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:05:33,568 INFO [train.py:715] (5/8) Epoch 15, batch 20050, loss[loss=0.1291, simple_loss=0.2077, pruned_loss=0.02524, over 4871.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 972934.90 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:06:11,839 INFO [train.py:715] (5/8) Epoch 15, batch 20100, loss[loss=0.1332, simple_loss=0.2105, pruned_loss=0.02792, over 4969.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 972473.89 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:06:50,119 INFO [train.py:715] (5/8) Epoch 15, batch 20150, loss[loss=0.1176, simple_loss=0.2021, pruned_loss=0.01658, over 4907.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02975, over 971667.12 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:07:28,124 INFO [train.py:715] (5/8) Epoch 15, batch 20200, loss[loss=0.1299, simple_loss=0.2035, pruned_loss=0.02817, over 4831.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02927, over 972152.65 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:08:05,820 INFO [train.py:715] (5/8) Epoch 15, batch 20250, loss[loss=0.1218, simple_loss=0.1969, pruned_loss=0.02334, over 4984.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 971884.46 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:08:44,518 INFO [train.py:715] (5/8) Epoch 15, batch 20300, loss[loss=0.1569, simple_loss=0.2279, pruned_loss=0.04298, over 4764.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03, over 972333.76 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:09:22,705 INFO [train.py:715] (5/8) Epoch 15, batch 20350, loss[loss=0.12, simple_loss=0.1937, pruned_loss=0.02315, over 4935.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03009, over 972206.56 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:10:01,091 INFO [train.py:715] (5/8) Epoch 15, batch 20400, loss[loss=0.1258, simple_loss=0.2073, pruned_loss=0.02218, over 4759.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03049, over 971071.88 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:10:38,947 INFO [train.py:715] (5/8) Epoch 15, batch 20450, loss[loss=0.1118, simple_loss=0.1879, pruned_loss=0.01787, over 4818.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03003, over 971203.41 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:11:17,698 INFO [train.py:715] (5/8) Epoch 15, batch 20500, loss[loss=0.1265, simple_loss=0.2041, pruned_loss=0.0245, over 4886.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03021, over 971694.24 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:11:55,871 INFO [train.py:715] (5/8) Epoch 15, batch 20550, loss[loss=0.1044, simple_loss=0.176, pruned_loss=0.01643, over 4844.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03029, over 971714.90 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:12:33,920 INFO [train.py:715] (5/8) Epoch 15, batch 20600, loss[loss=0.1283, simple_loss=0.2126, pruned_loss=0.02203, over 4887.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03014, over 971083.34 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:13:12,980 INFO [train.py:715] (5/8) Epoch 15, batch 20650, loss[loss=0.12, simple_loss=0.1914, pruned_loss=0.02429, over 4818.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03017, over 971126.17 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:13:51,738 INFO [train.py:715] (5/8) Epoch 15, batch 20700, loss[loss=0.1542, simple_loss=0.2122, pruned_loss=0.04807, over 4850.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03033, over 971372.53 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:14:31,083 INFO [train.py:715] (5/8) Epoch 15, batch 20750, loss[loss=0.1246, simple_loss=0.2004, pruned_loss=0.0244, over 4898.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03047, over 971439.52 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:15:09,387 INFO [train.py:715] (5/8) Epoch 15, batch 20800, loss[loss=0.1312, simple_loss=0.1926, pruned_loss=0.03489, over 4887.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03005, over 971640.04 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:15:48,763 INFO [train.py:715] (5/8) Epoch 15, batch 20850, loss[loss=0.1623, simple_loss=0.2398, pruned_loss=0.04242, over 4915.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03036, over 971563.36 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:16:27,991 INFO [train.py:715] (5/8) Epoch 15, batch 20900, loss[loss=0.1343, simple_loss=0.2114, pruned_loss=0.02864, over 4890.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2094, pruned_loss=0.03008, over 972896.29 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:17:06,243 INFO [train.py:715] (5/8) Epoch 15, batch 20950, loss[loss=0.1478, simple_loss=0.2183, pruned_loss=0.03864, over 4798.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03068, over 972541.20 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:17:45,526 INFO [train.py:715] (5/8) Epoch 15, batch 21000, loss[loss=0.1197, simple_loss=0.1931, pruned_loss=0.02312, over 4923.00 frames.], tot_loss[loss=0.1354, simple_loss=0.21, pruned_loss=0.03043, over 971530.81 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 11:17:45,527 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 11:17:56,038 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 11:18:35,286 INFO [train.py:715] (5/8) Epoch 15, batch 21050, loss[loss=0.1453, simple_loss=0.2099, pruned_loss=0.04034, over 4762.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03, over 972287.79 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:19:14,770 INFO [train.py:715] (5/8) Epoch 15, batch 21100, loss[loss=0.1307, simple_loss=0.1992, pruned_loss=0.03108, over 4907.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02973, over 972870.07 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:19:53,786 INFO [train.py:715] (5/8) Epoch 15, batch 21150, loss[loss=0.1688, simple_loss=0.2305, pruned_loss=0.05353, over 4935.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02998, over 973342.10 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:20:32,266 INFO [train.py:715] (5/8) Epoch 15, batch 21200, loss[loss=0.1436, simple_loss=0.2209, pruned_loss=0.03319, over 4952.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03066, over 973434.23 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:21:11,105 INFO [train.py:715] (5/8) Epoch 15, batch 21250, loss[loss=0.1386, simple_loss=0.2131, pruned_loss=0.03204, over 4931.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03003, over 973201.43 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 11:21:49,146 INFO [train.py:715] (5/8) Epoch 15, batch 21300, loss[loss=0.1114, simple_loss=0.1863, pruned_loss=0.01823, over 4932.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02975, over 973756.62 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 11:22:26,788 INFO [train.py:715] (5/8) Epoch 15, batch 21350, loss[loss=0.1342, simple_loss=0.2157, pruned_loss=0.02639, over 4882.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 973837.52 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:23:05,095 INFO [train.py:715] (5/8) Epoch 15, batch 21400, loss[loss=0.1446, simple_loss=0.2088, pruned_loss=0.04021, over 4898.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02941, over 973779.45 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:23:43,353 INFO [train.py:715] (5/8) Epoch 15, batch 21450, loss[loss=0.1741, simple_loss=0.248, pruned_loss=0.05016, over 4851.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 973672.13 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:24:21,357 INFO [train.py:715] (5/8) Epoch 15, batch 21500, loss[loss=0.167, simple_loss=0.2335, pruned_loss=0.05022, over 4833.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 973714.51 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:24:59,647 INFO [train.py:715] (5/8) Epoch 15, batch 21550, loss[loss=0.1456, simple_loss=0.2229, pruned_loss=0.03416, over 4844.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02955, over 972617.19 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:25:38,152 INFO [train.py:715] (5/8) Epoch 15, batch 21600, loss[loss=0.1272, simple_loss=0.197, pruned_loss=0.02873, over 4809.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 973091.83 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:26:16,020 INFO [train.py:715] (5/8) Epoch 15, batch 21650, loss[loss=0.1205, simple_loss=0.2014, pruned_loss=0.0198, over 4891.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02975, over 974115.86 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:26:54,239 INFO [train.py:715] (5/8) Epoch 15, batch 21700, loss[loss=0.1464, simple_loss=0.2242, pruned_loss=0.0343, over 4851.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03023, over 973807.73 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:27:32,377 INFO [train.py:715] (5/8) Epoch 15, batch 21750, loss[loss=0.1172, simple_loss=0.1973, pruned_loss=0.01857, over 4979.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03028, over 973645.31 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:28:10,477 INFO [train.py:715] (5/8) Epoch 15, batch 21800, loss[loss=0.1293, simple_loss=0.1963, pruned_loss=0.03111, over 4904.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02971, over 972696.45 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:28:48,403 INFO [train.py:715] (5/8) Epoch 15, batch 21850, loss[loss=0.126, simple_loss=0.2009, pruned_loss=0.02558, over 4765.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02972, over 973001.17 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:29:29,584 INFO [train.py:715] (5/8) Epoch 15, batch 21900, loss[loss=0.1371, simple_loss=0.198, pruned_loss=0.03816, over 4752.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03022, over 973240.01 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:30:08,735 INFO [train.py:715] (5/8) Epoch 15, batch 21950, loss[loss=0.1297, simple_loss=0.1997, pruned_loss=0.02987, over 4955.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02986, over 973099.83 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:30:47,269 INFO [train.py:715] (5/8) Epoch 15, batch 22000, loss[loss=0.1243, simple_loss=0.1938, pruned_loss=0.02742, over 4984.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02934, over 973023.20 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 11:31:25,790 INFO [train.py:715] (5/8) Epoch 15, batch 22050, loss[loss=0.1123, simple_loss=0.1912, pruned_loss=0.01675, over 4775.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02918, over 972493.99 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:32:05,113 INFO [train.py:715] (5/8) Epoch 15, batch 22100, loss[loss=0.1153, simple_loss=0.191, pruned_loss=0.01983, over 4872.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03005, over 972745.04 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:32:43,915 INFO [train.py:715] (5/8) Epoch 15, batch 22150, loss[loss=0.1413, simple_loss=0.2097, pruned_loss=0.03644, over 4842.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.03001, over 972502.29 frames.], batch size: 34, lr: 1.46e-04
2022-05-08 11:33:22,285 INFO [train.py:715] (5/8) Epoch 15, batch 22200, loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02857, over 4786.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03001, over 972001.23 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:34:01,326 INFO [train.py:715] (5/8) Epoch 15, batch 22250, loss[loss=0.1308, simple_loss=0.207, pruned_loss=0.02734, over 4885.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03013, over 972499.46 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:34:40,257 INFO [train.py:715] (5/8) Epoch 15, batch 22300, loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03153, over 4750.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03012, over 971239.46 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:35:18,795 INFO [train.py:715] (5/8) Epoch 15, batch 22350, loss[loss=0.1268, simple_loss=0.205, pruned_loss=0.02427, over 4924.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.0299, over 970948.47 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:35:57,366 INFO [train.py:715] (5/8) Epoch 15, batch 22400, loss[loss=0.1339, simple_loss=0.1994, pruned_loss=0.0342, over 4859.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02981, over 971490.61 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:36:36,629 INFO [train.py:715] (5/8) Epoch 15, batch 22450, loss[loss=0.1669, simple_loss=0.2309, pruned_loss=0.05149, over 4903.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02997, over 971681.47 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:37:15,518 INFO [train.py:715] (5/8) Epoch 15, batch 22500, loss[loss=0.1407, simple_loss=0.2097, pruned_loss=0.03584, over 4966.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 972318.69 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:37:54,242 INFO [train.py:715] (5/8) Epoch 15, batch 22550, loss[loss=0.1141, simple_loss=0.1883, pruned_loss=0.01992, over 4655.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.0298, over 971960.78 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:38:32,798 INFO [train.py:715] (5/8) Epoch 15, batch 22600, loss[loss=0.1393, simple_loss=0.2082, pruned_loss=0.03519, over 4924.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02997, over 972154.96 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:39:11,718 INFO [train.py:715] (5/8) Epoch 15, batch 22650, loss[loss=0.1269, simple_loss=0.2051, pruned_loss=0.02436, over 4868.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02984, over 972331.41 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:39:50,375 INFO [train.py:715] (5/8) Epoch 15, batch 22700, loss[loss=0.1114, simple_loss=0.1886, pruned_loss=0.01705, over 4766.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03005, over 972765.76 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:40:29,112 INFO [train.py:715] (5/8) Epoch 15, batch 22750, loss[loss=0.1347, simple_loss=0.2152, pruned_loss=0.0271, over 4644.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03033, over 972303.30 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:41:08,456 INFO [train.py:715] (5/8) Epoch 15, batch 22800, loss[loss=0.1511, simple_loss=0.2298, pruned_loss=0.03616, over 4695.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02994, over 972148.52 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:41:47,280 INFO [train.py:715] (5/8) Epoch 15, batch 22850, loss[loss=0.1046, simple_loss=0.1739, pruned_loss=0.01769, over 4976.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2099, pruned_loss=0.03026, over 972306.17 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:42:26,024 INFO [train.py:715] (5/8) Epoch 15, batch 22900, loss[loss=0.1466, simple_loss=0.2152, pruned_loss=0.03901, over 4870.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03027, over 971769.29 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:43:05,208 INFO [train.py:715] (5/8) Epoch 15, batch 22950, loss[loss=0.1441, simple_loss=0.2149, pruned_loss=0.03668, over 4703.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03022, over 971397.04 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:43:43,827 INFO [train.py:715] (5/8) Epoch 15, batch 23000, loss[loss=0.1379, simple_loss=0.2124, pruned_loss=0.03172, over 4853.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03051, over 972364.49 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:44:22,237 INFO [train.py:715] (5/8) Epoch 15, batch 23050, loss[loss=0.1351, simple_loss=0.1955, pruned_loss=0.03732, over 4818.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03039, over 972589.41 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:45:00,627 INFO [train.py:715] (5/8) Epoch 15, batch 23100, loss[loss=0.1255, simple_loss=0.2033, pruned_loss=0.02382, over 4780.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02976, over 972741.91 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:45:39,480 INFO [train.py:715] (5/8) Epoch 15, batch 23150, loss[loss=0.1418, simple_loss=0.2202, pruned_loss=0.03166, over 4892.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03008, over 972468.66 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:46:17,452 INFO [train.py:715] (5/8) Epoch 15, batch 23200, loss[loss=0.1537, simple_loss=0.2266, pruned_loss=0.04034, over 4764.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 972678.47 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:46:55,709 INFO [train.py:715] (5/8) Epoch 15, batch 23250, loss[loss=0.1254, simple_loss=0.1995, pruned_loss=0.02565, over 4960.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03025, over 971579.74 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:47:34,387 INFO [train.py:715] (5/8) Epoch 15, batch 23300, loss[loss=0.1305, simple_loss=0.2091, pruned_loss=0.02594, over 4807.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03019, over 972270.40 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:48:12,429 INFO [train.py:715] (5/8) Epoch 15, batch 23350, loss[loss=0.1035, simple_loss=0.1799, pruned_loss=0.01355, over 4974.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03011, over 972397.23 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 11:48:50,738 INFO [train.py:715] (5/8) Epoch 15, batch 23400, loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.0437, over 4756.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03028, over 971057.51 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:49:28,562 INFO [train.py:715] (5/8) Epoch 15, batch 23450, loss[loss=0.1243, simple_loss=0.1999, pruned_loss=0.02437, over 4904.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2069, pruned_loss=0.02994, over 970792.43 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:50:07,085 INFO [train.py:715] (5/8) Epoch 15, batch 23500, loss[loss=0.137, simple_loss=0.2211, pruned_loss=0.02644, over 4789.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2075, pruned_loss=0.03043, over 970715.50 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:50:44,858 INFO [train.py:715] (5/8) Epoch 15, batch 23550, loss[loss=0.1091, simple_loss=0.1882, pruned_loss=0.01502, over 4922.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03091, over 969843.00 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 11:51:22,854 INFO [train.py:715] (5/8) Epoch 15, batch 23600, loss[loss=0.1402, simple_loss=0.214, pruned_loss=0.03321, over 4927.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2074, pruned_loss=0.03049, over 970386.39 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:52:01,279 INFO [train.py:715] (5/8) Epoch 15, batch 23650, loss[loss=0.1281, simple_loss=0.2098, pruned_loss=0.02319, over 4889.00 frames.], tot_loss[loss=0.1347, simple_loss=0.208, pruned_loss=0.03074, over 969997.82 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:52:39,167 INFO [train.py:715] (5/8) Epoch 15, batch 23700, loss[loss=0.1222, simple_loss=0.1938, pruned_loss=0.02526, over 4985.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03055, over 970468.32 frames.], batch size: 33, lr: 1.46e-04
2022-05-08 11:53:17,231 INFO [train.py:715] (5/8) Epoch 15, batch 23750, loss[loss=0.1233, simple_loss=0.1995, pruned_loss=0.02353, over 4969.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 971345.97 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:53:55,058 INFO [train.py:715] (5/8) Epoch 15, batch 23800, loss[loss=0.141, simple_loss=0.2145, pruned_loss=0.03378, over 4897.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03043, over 971103.02 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:54:33,045 INFO [train.py:715] (5/8) Epoch 15, batch 23850, loss[loss=0.1486, simple_loss=0.2292, pruned_loss=0.03401, over 4896.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03054, over 971302.53 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:55:11,363 INFO [train.py:715] (5/8) Epoch 15, batch 23900, loss[loss=0.1131, simple_loss=0.1881, pruned_loss=0.01907, over 4810.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03044, over 971365.27 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 11:55:48,900 INFO [train.py:715] (5/8) Epoch 15, batch 23950, loss[loss=0.1347, simple_loss=0.2179, pruned_loss=0.02579, over 4957.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03055, over 971499.02 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:56:27,442 INFO [train.py:715] (5/8) Epoch 15, batch 24000, loss[loss=0.1019, simple_loss=0.1705, pruned_loss=0.01663, over 4803.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03062, over 971600.08 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:56:27,442 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 11:56:37,033 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.105, simple_loss=0.1886, pruned_loss=0.01071, over 914524.00 frames.
2022-05-08 11:57:15,621 INFO [train.py:715] (5/8) Epoch 15, batch 24050, loss[loss=0.1395, simple_loss=0.2116, pruned_loss=0.03371, over 4950.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03052, over 972025.36 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:57:54,187 INFO [train.py:715] (5/8) Epoch 15, batch 24100, loss[loss=0.1286, simple_loss=0.2138, pruned_loss=0.02172, over 4953.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03015, over 972620.44 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:58:32,192 INFO [train.py:715] (5/8) Epoch 15, batch 24150, loss[loss=0.1764, simple_loss=0.2405, pruned_loss=0.05615, over 4912.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.0298, over 972664.89 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:59:10,406 INFO [train.py:715] (5/8) Epoch 15, batch 24200, loss[loss=0.1467, simple_loss=0.2212, pruned_loss=0.03608, over 4912.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 972492.74 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:59:48,422 INFO [train.py:715] (5/8) Epoch 15, batch 24250, loss[loss=0.1185, simple_loss=0.1934, pruned_loss=0.02181, over 4827.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03034, over 971818.35 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 12:00:26,748 INFO [train.py:715] (5/8) Epoch 15, batch 24300, loss[loss=0.1374, simple_loss=0.22, pruned_loss=0.02741, over 4799.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02995, over 972269.44 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 12:01:03,898 INFO [train.py:715] (5/8) Epoch 15, batch 24350, loss[loss=0.1257, simple_loss=0.1996, pruned_loss=0.0259, over 4893.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03031, over 972574.72 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 12:01:42,322 INFO [train.py:715] (5/8) Epoch 15, batch 24400, loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.03101, over 4979.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02988, over 972993.24 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 12:02:20,846 INFO [train.py:715] (5/8) Epoch 15, batch 24450, loss[loss=0.1543, simple_loss=0.2254, pruned_loss=0.04162, over 4980.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2092, pruned_loss=0.02993, over 973227.63 frames.], batch size: 31, lr: 1.46e-04
2022-05-08 12:02:58,825 INFO [train.py:715] (5/8) Epoch 15, batch 24500, loss[loss=0.1514, simple_loss=0.2164, pruned_loss=0.04317, over 4872.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03044, over 972384.69 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 12:03:36,484 INFO [train.py:715] (5/8) Epoch 15, batch 24550, loss[loss=0.1712, simple_loss=0.2393, pruned_loss=0.05154, over 4745.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.0303, over 972311.26 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 12:04:14,727 INFO [train.py:715] (5/8) Epoch 15, batch 24600, loss[loss=0.1163, simple_loss=0.1912, pruned_loss=0.02069, over 4645.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03017, over 972021.07 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 12:04:53,494 INFO [train.py:715] (5/8) Epoch 15, batch 24650, loss[loss=0.1287, simple_loss=0.2064, pruned_loss=0.02553, over 4976.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.0301, over 971906.92 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 12:05:31,178 INFO [train.py:715] (5/8) Epoch 15, batch 24700, loss[loss=0.1348, simple_loss=0.2159, pruned_loss=0.02686, over 4934.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03052, over 971785.19 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 12:06:09,581 INFO [train.py:715] (5/8) Epoch 15, batch 24750, loss[loss=0.1329, simple_loss=0.2148, pruned_loss=0.02552, over 4818.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.03061, over 970980.91 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 12:06:47,909 INFO [train.py:715] (5/8) Epoch 15, batch 24800, loss[loss=0.1227, simple_loss=0.1927, pruned_loss=0.02636, over 4863.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03069, over 970125.44 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 12:07:25,661 INFO [train.py:715] (5/8) Epoch 15, batch 24850, loss[loss=0.1095, simple_loss=0.1848, pruned_loss=0.01713, over 4813.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2081, pruned_loss=0.03072, over 969547.61 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 12:08:03,592 INFO [train.py:715] (5/8) Epoch 15, batch 24900, loss[loss=0.1341, simple_loss=0.2048, pruned_loss=0.03168, over 4938.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02979, over 969836.06 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 12:08:41,838 INFO [train.py:715] (5/8) Epoch 15, batch 24950, loss[loss=0.108, simple_loss=0.1877, pruned_loss=0.01418, over 4934.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02955, over 970075.51 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 12:09:20,948 INFO [train.py:715] (5/8) Epoch 15, batch 25000, loss[loss=0.1471, simple_loss=0.2281, pruned_loss=0.03304, over 4905.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02916, over 971234.67 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 12:09:58,499 INFO [train.py:715] (5/8) Epoch 15, batch 25050, loss[loss=0.1582, simple_loss=0.2282, pruned_loss=0.04413, over 4805.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02938, over 971831.91 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:10:36,536 INFO [train.py:715] (5/8) Epoch 15, batch 25100, loss[loss=0.1441, simple_loss=0.2126, pruned_loss=0.03785, over 4933.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02972, over 972068.06 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 12:11:14,987 INFO [train.py:715] (5/8) Epoch 15, batch 25150, loss[loss=0.1542, simple_loss=0.2066, pruned_loss=0.05089, over 4869.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02951, over 972492.09 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 12:11:53,005 INFO [train.py:715] (5/8) Epoch 15, batch 25200, loss[loss=0.1268, simple_loss=0.1989, pruned_loss=0.02735, over 4761.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.0294, over 971896.27 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 12:12:30,795 INFO [train.py:715] (5/8) Epoch 15, batch 25250, loss[loss=0.1541, simple_loss=0.2298, pruned_loss=0.03919, over 4814.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.0296, over 971630.30 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 12:13:09,120 INFO [train.py:715] (5/8) Epoch 15, batch 25300, loss[loss=0.1293, simple_loss=0.204, pruned_loss=0.02729, over 4988.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02968, over 971593.81 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 12:13:47,203 INFO [train.py:715] (5/8) Epoch 15, batch 25350, loss[loss=0.1212, simple_loss=0.1966, pruned_loss=0.02294, over 4820.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02969, over 971786.28 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 12:14:24,744 INFO [train.py:715] (5/8) Epoch 15, batch 25400, loss[loss=0.1284, simple_loss=0.1981, pruned_loss=0.02935, over 4791.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 971816.02 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 12:15:02,819 INFO [train.py:715] (5/8) Epoch 15, batch 25450, loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02975, over 4936.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03007, over 970798.04 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 12:15:41,207 INFO [train.py:715] (5/8) Epoch 15, batch 25500, loss[loss=0.1373, simple_loss=0.2066, pruned_loss=0.03394, over 4953.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.0296, over 971441.41 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 12:16:18,764 INFO [train.py:715] (5/8) Epoch 15, batch 25550, loss[loss=0.1157, simple_loss=0.1875, pruned_loss=0.0219, over 4781.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02999, over 971660.22 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:16:56,914 INFO [train.py:715] (5/8) Epoch 15, batch 25600, loss[loss=0.1417, simple_loss=0.1996, pruned_loss=0.04193, over 4846.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03006, over 971747.62 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:17:35,538 INFO [train.py:715] (5/8) Epoch 15, batch 25650, loss[loss=0.1387, simple_loss=0.2068, pruned_loss=0.03524, over 4783.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03009, over 971412.68 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:18:13,815 INFO [train.py:715] (5/8) Epoch 15, batch 25700, loss[loss=0.1362, simple_loss=0.2078, pruned_loss=0.0323, over 4902.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03, over 971379.42 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:18:51,202 INFO [train.py:715] (5/8) Epoch 15, batch 25750, loss[loss=0.1311, simple_loss=0.2162, pruned_loss=0.02304, over 4947.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03004, over 971683.03 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 12:19:29,351 INFO [train.py:715] (5/8) Epoch 15, batch 25800, loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03254, over 4749.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02974, over 971999.35 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:20:07,975 INFO [train.py:715] (5/8) Epoch 15, batch 25850, loss[loss=0.1657, simple_loss=0.2285, pruned_loss=0.05139, over 4990.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03, over 972384.23 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:20:45,417 INFO [train.py:715] (5/8) Epoch 15, batch 25900, loss[loss=0.2072, simple_loss=0.2866, pruned_loss=0.06394, over 4887.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02998, over 972010.45 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:21:24,013 INFO [train.py:715] (5/8) Epoch 15, batch 25950, loss[loss=0.1443, simple_loss=0.211, pruned_loss=0.03886, over 4834.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03041, over 971069.57 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:22:02,167 INFO [train.py:715] (5/8) Epoch 15, batch 26000, loss[loss=0.127, simple_loss=0.199, pruned_loss=0.02743, over 4687.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03049, over 971122.55 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:22:39,853 INFO [train.py:715] (5/8) Epoch 15, batch 26050, loss[loss=0.1405, simple_loss=0.2237, pruned_loss=0.02867, over 4763.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03024, over 971425.45 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:23:17,644 INFO [train.py:715] (5/8) Epoch 15, batch 26100, loss[loss=0.1435, simple_loss=0.218, pruned_loss=0.03448, over 4784.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03017, over 971602.04 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:23:56,076 INFO [train.py:715] (5/8) Epoch 15, batch 26150, loss[loss=0.161, simple_loss=0.2295, pruned_loss=0.04625, over 4956.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03027, over 972778.20 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:24:33,868 INFO [train.py:715] (5/8) Epoch 15, batch 26200, loss[loss=0.1119, simple_loss=0.1737, pruned_loss=0.02504, over 4804.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03048, over 973038.67 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:25:11,686 INFO [train.py:715] (5/8) Epoch 15, batch 26250, loss[loss=0.123, simple_loss=0.2022, pruned_loss=0.02189, over 4897.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03005, over 973174.72 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:25:50,004 INFO [train.py:715] (5/8) Epoch 15, batch 26300, loss[loss=0.1496, simple_loss=0.2242, pruned_loss=0.03748, over 4776.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03036, over 972859.27 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:26:28,460 INFO [train.py:715] (5/8) Epoch 15, batch 26350, loss[loss=0.121, simple_loss=0.1915, pruned_loss=0.02528, over 4792.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 973428.17 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:27:06,220 INFO [train.py:715] (5/8) Epoch 15, batch 26400, loss[loss=0.1254, simple_loss=0.1912, pruned_loss=0.02986, over 4848.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03026, over 973483.54 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:27:44,352 INFO [train.py:715] (5/8) Epoch 15, batch 26450, loss[loss=0.1287, simple_loss=0.2003, pruned_loss=0.02853, over 4867.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03035, over 972842.87 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:28:22,637 INFO [train.py:715] (5/8) Epoch 15, batch 26500, loss[loss=0.1408, simple_loss=0.2191, pruned_loss=0.03123, over 4764.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02965, over 972992.65 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:29:00,418 INFO [train.py:715] (5/8) Epoch 15, batch 26550, loss[loss=0.1263, simple_loss=0.2063, pruned_loss=0.02316, over 4928.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 971986.98 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 12:29:38,155 INFO [train.py:715] (5/8) Epoch 15, batch 26600, loss[loss=0.1333, simple_loss=0.2201, pruned_loss=0.02327, over 4859.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.0297, over 972871.40 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:30:16,188 INFO [train.py:715] (5/8) Epoch 15, batch 26650, loss[loss=0.1237, simple_loss=0.1973, pruned_loss=0.02507, over 4650.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02955, over 973477.04 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:30:54,319 INFO [train.py:715] (5/8) Epoch 15, batch 26700, loss[loss=0.1043, simple_loss=0.1704, pruned_loss=0.01914, over 4871.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02958, over 973496.74 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:31:31,945 INFO [train.py:715] (5/8) Epoch 15, batch 26750, loss[loss=0.1353, simple_loss=0.2229, pruned_loss=0.02388, over 4895.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03019, over 973263.04 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:32:10,363 INFO [train.py:715] (5/8) Epoch 15, batch 26800, loss[loss=0.1445, simple_loss=0.2108, pruned_loss=0.03912, over 4791.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03085, over 973271.74 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:32:48,680 INFO [train.py:715] (5/8) Epoch 15, batch 26850, loss[loss=0.1413, simple_loss=0.2146, pruned_loss=0.03399, over 4777.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.0309, over 973115.57 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:33:26,762 INFO [train.py:715] (5/8) Epoch 15, batch 26900, loss[loss=0.153, simple_loss=0.2295, pruned_loss=0.03828, over 4887.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03089, over 972730.78 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:34:04,502 INFO [train.py:715] (5/8) Epoch 15, batch 26950, loss[loss=0.1143, simple_loss=0.1962, pruned_loss=0.01618, over 4814.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03051, over 972294.41 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 12:34:42,585 INFO [train.py:715] (5/8) Epoch 15, batch 27000, loss[loss=0.1504, simple_loss=0.234, pruned_loss=0.03345, over 4773.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03116, over 971781.09 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:34:42,585 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 12:34:52,203 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01064, over 914524.00 frames.
2022-05-08 12:35:31,297 INFO [train.py:715] (5/8) Epoch 15, batch 27050, loss[loss=0.1262, simple_loss=0.1906, pruned_loss=0.03084, over 4835.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03116, over 972646.58 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:36:10,020 INFO [train.py:715] (5/8) Epoch 15, batch 27100, loss[loss=0.1437, simple_loss=0.212, pruned_loss=0.03766, over 4880.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2084, pruned_loss=0.03106, over 972443.40 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:36:48,677 INFO [train.py:715] (5/8) Epoch 15, batch 27150, loss[loss=0.1303, simple_loss=0.2092, pruned_loss=0.02568, over 4961.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03096, over 972553.02 frames.], batch size: 35, lr: 1.45e-04
2022-05-08 12:37:26,866 INFO [train.py:715] (5/8) Epoch 15, batch 27200, loss[loss=0.1205, simple_loss=0.196, pruned_loss=0.02252, over 4852.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03089, over 972647.44 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:38:05,903 INFO [train.py:715] (5/8) Epoch 15, batch 27250, loss[loss=0.12, simple_loss=0.2027, pruned_loss=0.01866, over 4851.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03025, over 973014.89 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:38:43,693 INFO [train.py:715] (5/8) Epoch 15, batch 27300, loss[loss=0.1386, simple_loss=0.2281, pruned_loss=0.02451, over 4768.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03006, over 972390.12 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:39:21,922 INFO [train.py:715] (5/8) Epoch 15, batch 27350, loss[loss=0.124, simple_loss=0.2021, pruned_loss=0.02297, over 4743.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03032, over 972405.70 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:40:00,097 INFO [train.py:715] (5/8) Epoch 15, batch 27400, loss[loss=0.1406, simple_loss=0.2155, pruned_loss=0.03279, over 4923.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 972583.26 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:40:38,395 INFO [train.py:715] (5/8) Epoch 15, batch 27450, loss[loss=0.1324, simple_loss=0.1911, pruned_loss=0.03681, over 4799.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03035, over 972107.49 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:41:16,659 INFO [train.py:715] (5/8) Epoch 15, batch 27500, loss[loss=0.1209, simple_loss=0.1894, pruned_loss=0.02621, over 4836.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02995, over 972757.61 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:41:54,849 INFO [train.py:715] (5/8) Epoch 15, batch 27550, loss[loss=0.1363, simple_loss=0.2115, pruned_loss=0.03052, over 4762.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02995, over 972303.75 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:42:33,402 INFO [train.py:715] (5/8) Epoch 15, batch 27600, loss[loss=0.1156, simple_loss=0.1948, pruned_loss=0.0182, over 4924.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 972125.70 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 12:43:10,759 INFO [train.py:715] (5/8) Epoch 15, batch 27650, loss[loss=0.1243, simple_loss=0.1995, pruned_loss=0.02452, over 4768.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03018, over 971925.11 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:43:49,456 INFO [train.py:715] (5/8) Epoch 15, batch 27700, loss[loss=0.1405, simple_loss=0.2059, pruned_loss=0.03757, over 4838.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03029, over 972040.31 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:44:27,756 INFO [train.py:715] (5/8) Epoch 15, batch 27750, loss[loss=0.1134, simple_loss=0.189, pruned_loss=0.01894, over 4939.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03023, over 971887.13 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 12:45:06,222 INFO [train.py:715] (5/8) Epoch 15, batch 27800, loss[loss=0.1191, simple_loss=0.1974, pruned_loss=0.02035, over 4800.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 972062.60 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 12:45:44,233 INFO [train.py:715] (5/8) Epoch 15, batch 27850, loss[loss=0.1365, simple_loss=0.2109, pruned_loss=0.03111, over 4923.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03002, over 972341.77 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 12:46:21,974 INFO [train.py:715] (5/8) Epoch 15, batch 27900, loss[loss=0.1174, simple_loss=0.1886, pruned_loss=0.02309, over 4640.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02977, over 972106.86 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:47:00,799 INFO [train.py:715] (5/8) Epoch 15, batch 27950, loss[loss=0.1142, simple_loss=0.1843, pruned_loss=0.02206, over 4786.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02993, over 971958.49 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:47:38,668 INFO [train.py:715] (5/8) Epoch 15, batch 28000, loss[loss=0.1455, simple_loss=0.2291, pruned_loss=0.03091, over 4981.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02984, over 972035.63 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:48:16,881 INFO [train.py:715] (5/8) Epoch 15, batch 28050, loss[loss=0.1188, simple_loss=0.1941, pruned_loss=0.02172, over 4878.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03011, over 972146.54 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:48:55,112 INFO [train.py:715] (5/8) Epoch 15, batch 28100, loss[loss=0.1382, simple_loss=0.2059, pruned_loss=0.03523, over 4869.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.0297, over 972145.82 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:49:33,363 INFO [train.py:715] (5/8) Epoch 15, batch 28150, loss[loss=0.1353, simple_loss=0.2195, pruned_loss=0.0256, over 4850.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.0297, over 972011.88 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:50:11,124 INFO [train.py:715] (5/8) Epoch 15, batch 28200, loss[loss=0.1344, simple_loss=0.217, pruned_loss=0.02593, over 4777.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03002, over 971790.15 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:50:49,027 INFO [train.py:715] (5/8) Epoch 15, batch 28250, loss[loss=0.1295, simple_loss=0.2075, pruned_loss=0.02574, over 4835.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2092, pruned_loss=0.03005, over 972523.43 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:51:28,180 INFO [train.py:715] (5/8) Epoch 15, batch 28300, loss[loss=0.1613, simple_loss=0.2359, pruned_loss=0.04337, over 4802.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2098, pruned_loss=0.03019, over 972161.71 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:52:05,677 INFO [train.py:715] (5/8) Epoch 15, batch 28350, loss[loss=0.13, simple_loss=0.2039, pruned_loss=0.02804, over 4872.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2093, pruned_loss=0.02978, over 971892.11 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:52:43,906 INFO [train.py:715] (5/8) Epoch 15, batch 28400, loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03404, over 4783.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02957, over 971661.15 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:53:22,225 INFO [train.py:715] (5/8) Epoch 15, batch 28450, loss[loss=0.1564, simple_loss=0.2273, pruned_loss=0.04277, over 4833.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03038, over 972157.31 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:54:00,375 INFO [train.py:715] (5/8) Epoch 15, batch 28500, loss[loss=0.1524, simple_loss=0.2244, pruned_loss=0.04023, over 4864.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03035, over 972463.54 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:54:38,503 INFO [train.py:715] (5/8) Epoch 15, batch 28550, loss[loss=0.1299, simple_loss=0.2133, pruned_loss=0.02321, over 4943.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2093, pruned_loss=0.0299, over 972247.22 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:55:16,670 INFO [train.py:715] (5/8) Epoch 15, batch 28600, loss[loss=0.1266, simple_loss=0.1961, pruned_loss=0.02859, over 4883.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02987, over 971753.44 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:55:55,087 INFO [train.py:715] (5/8) Epoch 15, batch 28650, loss[loss=0.1254, simple_loss=0.2057, pruned_loss=0.02253, over 4978.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02954, over 971422.28 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:56:32,942 INFO [train.py:715] (5/8) Epoch 15, batch 28700, loss[loss=0.1138, simple_loss=0.1824, pruned_loss=0.02262, over 4821.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 972285.80 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:57:11,383 INFO [train.py:715] (5/8) Epoch 15, batch 28750, loss[loss=0.1159, simple_loss=0.1884, pruned_loss=0.02174, over 4927.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02935, over 972586.73 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 12:57:50,114 INFO [train.py:715] (5/8) Epoch 15, batch 28800, loss[loss=0.1297, simple_loss=0.2061, pruned_loss=0.02668, over 4885.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02931, over 972216.63 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:58:28,472 INFO [train.py:715] (5/8) Epoch 15, batch 28850, loss[loss=0.1545, simple_loss=0.2214, pruned_loss=0.04377, over 4840.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02943, over 972846.82 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:59:06,966 INFO [train.py:715] (5/8) Epoch 15, batch 28900, loss[loss=0.1417, simple_loss=0.2045, pruned_loss=0.03946, over 4831.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 972321.50 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:59:45,682 INFO [train.py:715] (5/8) Epoch 15, batch 28950, loss[loss=0.1298, simple_loss=0.204, pruned_loss=0.0278, over 4914.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02917, over 972607.01 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:00:24,854 INFO [train.py:715] (5/8) Epoch 15, batch 29000, loss[loss=0.1346, simple_loss=0.2036, pruned_loss=0.0328, over 4775.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02957, over 972073.20 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:01:03,427 INFO [train.py:715] (5/8) Epoch 15, batch 29050, loss[loss=0.1231, simple_loss=0.1962, pruned_loss=0.02504, over 4918.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02955, over 971498.03 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:01:42,350 INFO [train.py:715] (5/8) Epoch 15, batch 29100, loss[loss=0.1416, simple_loss=0.2263, pruned_loss=0.0285, over 4792.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02948, over 971064.88 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:02:21,518 INFO [train.py:715] (5/8) Epoch 15, batch 29150, loss[loss=0.106, simple_loss=0.1806, pruned_loss=0.0157, over 4924.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 971028.89 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:03:00,530 INFO [train.py:715] (5/8) Epoch 15, batch 29200, loss[loss=0.1314, simple_loss=0.2018, pruned_loss=0.03049, over 4929.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0297, over 970392.35 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:03:38,942 INFO [train.py:715] (5/8) Epoch 15, batch 29250, loss[loss=0.1293, simple_loss=0.1956, pruned_loss=0.03148, over 4875.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02992, over 970930.09 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:04:18,000 INFO [train.py:715] (5/8) Epoch 15, batch 29300, loss[loss=0.1599, simple_loss=0.2248, pruned_loss=0.04752, over 4747.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02989, over 970980.27 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:04:56,889 INFO [train.py:715] (5/8) Epoch 15, batch 29350, loss[loss=0.126, simple_loss=0.2047, pruned_loss=0.02367, over 4952.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03008, over 971696.93 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 13:05:35,476 INFO [train.py:715] (5/8) Epoch 15, batch 29400, loss[loss=0.1613, simple_loss=0.2404, pruned_loss=0.04112, over 4978.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03018, over 971324.87 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:06:14,534 INFO [train.py:715] (5/8) Epoch 15, batch 29450, loss[loss=0.1434, simple_loss=0.2183, pruned_loss=0.03428, over 4913.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03021, over 970945.58 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:06:53,809 INFO [train.py:715] (5/8) Epoch 15, batch 29500, loss[loss=0.1466, simple_loss=0.2146, pruned_loss=0.03925, over 4899.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02966, over 971577.66 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:07:31,956 INFO [train.py:715] (5/8) Epoch 15, batch 29550, loss[loss=0.1491, simple_loss=0.2231, pruned_loss=0.03758, over 4921.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02984, over 971263.72 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:08:09,734 INFO [train.py:715] (5/8) Epoch 15, batch 29600, loss[loss=0.1288, simple_loss=0.1977, pruned_loss=0.02991, over 4968.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02961, over 971852.37 frames.], batch size: 35, lr: 1.45e-04
2022-05-08 13:08:48,779 INFO [train.py:715] (5/8) Epoch 15, batch 29650, loss[loss=0.1243, simple_loss=0.1907, pruned_loss=0.02897, over 4896.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03013, over 971481.83 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:09:27,544 INFO [train.py:715] (5/8) Epoch 15, batch 29700, loss[loss=0.1451, simple_loss=0.2052, pruned_loss=0.04249, over 4931.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03028, over 972485.75 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:10:05,828 INFO [train.py:715] (5/8) Epoch 15, batch 29750, loss[loss=0.123, simple_loss=0.1942, pruned_loss=0.02589, over 4924.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03014, over 972098.08 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:10:43,494 INFO [train.py:715] (5/8) Epoch 15, batch 29800, loss[loss=0.1135, simple_loss=0.1918, pruned_loss=0.01756, over 4768.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02991, over 972186.87 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:11:22,787 INFO [train.py:715] (5/8) Epoch 15, batch 29850, loss[loss=0.1237, simple_loss=0.1954, pruned_loss=0.02596, over 4819.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 971656.35 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:12:04,497 INFO [train.py:715] (5/8) Epoch 15, batch 29900, loss[loss=0.1299, simple_loss=0.2039, pruned_loss=0.02791, over 4854.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02959, over 971779.19 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:12:43,058 INFO [train.py:715] (5/8) Epoch 15, batch 29950, loss[loss=0.1526, simple_loss=0.2362, pruned_loss=0.0345, over 4795.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02955, over 972589.36 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:13:21,388 INFO [train.py:715] (5/8) Epoch 15, batch 30000, loss[loss=0.1236, simple_loss=0.1997, pruned_loss=0.02374, over 4693.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02957, over 972027.54 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:13:21,389 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 13:13:30,915 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1885, pruned_loss=0.01066, over 914524.00 frames.
2022-05-08 13:14:09,969 INFO [train.py:715] (5/8) Epoch 15, batch 30050, loss[loss=0.1279, simple_loss=0.2011, pruned_loss=0.02739, over 4900.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02946, over 972738.90 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:14:49,058 INFO [train.py:715] (5/8) Epoch 15, batch 30100, loss[loss=0.1323, simple_loss=0.2076, pruned_loss=0.02852, over 4772.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03, over 972998.45 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:15:28,216 INFO [train.py:715] (5/8) Epoch 15, batch 30150, loss[loss=0.1396, simple_loss=0.2192, pruned_loss=0.03005, over 4835.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03008, over 972349.95 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:16:07,080 INFO [train.py:715] (5/8) Epoch 15, batch 30200, loss[loss=0.1278, simple_loss=0.2012, pruned_loss=0.02722, over 4825.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02979, over 973420.58 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 13:16:46,375 INFO [train.py:715] (5/8) Epoch 15, batch 30250, loss[loss=0.1675, simple_loss=0.2412, pruned_loss=0.04691, over 4831.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03003, over 972388.14 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:17:25,197 INFO [train.py:715] (5/8) Epoch 15, batch 30300, loss[loss=0.1247, simple_loss=0.2098, pruned_loss=0.01975, over 4774.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03014, over 972378.52 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:18:03,168 INFO [train.py:715] (5/8) Epoch 15, batch 30350, loss[loss=0.1522, simple_loss=0.2176, pruned_loss=0.04338, over 4896.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03027, over 972313.29 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:18:42,390 INFO [train.py:715] (5/8) Epoch 15, batch 30400, loss[loss=0.1113, simple_loss=0.1776, pruned_loss=0.02249, over 4646.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02999, over 971709.64 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:19:21,254 INFO [train.py:715] (5/8) Epoch 15, batch 30450, loss[loss=0.1166, simple_loss=0.1983, pruned_loss=0.01752, over 4939.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02961, over 972664.72 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:20:00,134 INFO [train.py:715] (5/8) Epoch 15, batch 30500, loss[loss=0.1133, simple_loss=0.1975, pruned_loss=0.01457, over 4921.00 frames.], tot_loss[loss=0.1345, simple_loss=0.209, pruned_loss=0.03003, over 972425.55 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:20:38,344 INFO [train.py:715] (5/8) Epoch 15, batch 30550, loss[loss=0.1476, simple_loss=0.2241, pruned_loss=0.03552, over 4790.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03017, over 972429.94 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:21:17,388 INFO [train.py:715] (5/8) Epoch 15, batch 30600, loss[loss=0.1456, simple_loss=0.2076, pruned_loss=0.04178, over 4888.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02967, over 972515.71 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:21:56,194 INFO [train.py:715] (5/8) Epoch 15, batch 30650, loss[loss=0.1143, simple_loss=0.1889, pruned_loss=0.0199, over 4775.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 973023.44 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:22:34,337 INFO [train.py:715] (5/8) Epoch 15, batch 30700, loss[loss=0.1681, simple_loss=0.2436, pruned_loss=0.04631, over 4905.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03009, over 973409.16 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:23:13,404 INFO [train.py:715] (5/8) Epoch 15, batch 30750, loss[loss=0.1296, simple_loss=0.2082, pruned_loss=0.02555, over 4918.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02988, over 972867.32 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:23:52,076 INFO [train.py:715] (5/8) Epoch 15, batch 30800, loss[loss=0.09955, simple_loss=0.1738, pruned_loss=0.01265, over 4774.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03007, over 972549.57 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:24:30,181 INFO [train.py:715] (5/8) Epoch 15, batch 30850, loss[loss=0.1137, simple_loss=0.1906, pruned_loss=0.01841, over 4739.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03016, over 973196.63 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:25:08,417 INFO [train.py:715] (5/8) Epoch 15, batch 30900, loss[loss=0.1495, simple_loss=0.2256, pruned_loss=0.03673, over 4793.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02991, over 973706.38 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:25:46,857 INFO [train.py:715] (5/8) Epoch 15, batch 30950, loss[loss=0.1247, simple_loss=0.1999, pruned_loss=0.02475, over 4821.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02991, over 973660.09 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:26:25,011 INFO [train.py:715] (5/8) Epoch 15, batch 31000, loss[loss=0.1485, simple_loss=0.2265, pruned_loss=0.03524, over 4698.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02975, over 971951.48 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:27:02,424 INFO [train.py:715] (5/8) Epoch 15, batch 31050, loss[loss=0.1513, simple_loss=0.226, pruned_loss=0.03834, over 4951.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02965, over 972740.69 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 13:27:40,734 INFO [train.py:715] (5/8) Epoch 15, batch 31100, loss[loss=0.1143, simple_loss=0.1886, pruned_loss=0.02004, over 4774.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02987, over 972215.31 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:28:18,886 INFO [train.py:715] (5/8) Epoch 15, batch 31150, loss[loss=0.1162, simple_loss=0.1899, pruned_loss=0.02125, over 4770.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02982, over 972464.12 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:28:57,278 INFO [train.py:715] (5/8) Epoch 15, batch 31200, loss[loss=0.1229, simple_loss=0.1965, pruned_loss=0.02467, over 4902.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03003, over 972582.57 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:29:34,876 INFO [train.py:715] (5/8) Epoch 15, batch 31250, loss[loss=0.1339, simple_loss=0.2154, pruned_loss=0.02616, over 4869.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03011, over 972577.79 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:30:13,198 INFO [train.py:715] (5/8) Epoch 15, batch 31300, loss[loss=0.1342, simple_loss=0.2093, pruned_loss=0.02955, over 4791.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02992, over 972395.72 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:30:51,248 INFO [train.py:715] (5/8) Epoch 15, batch 31350, loss[loss=0.1465, simple_loss=0.2149, pruned_loss=0.03902, over 4989.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03015, over 972197.58 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:31:28,513 INFO [train.py:715] (5/8) Epoch 15, batch 31400, loss[loss=0.1177, simple_loss=0.1839, pruned_loss=0.02577, over 4779.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.0302, over 972384.68 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:32:06,856 INFO [train.py:715] (5/8) Epoch 15, batch 31450, loss[loss=0.1168, simple_loss=0.1894, pruned_loss=0.02207, over 4900.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03026, over 973787.30 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:32:45,118 INFO [train.py:715] (5/8) Epoch 15, batch 31500, loss[loss=0.1403, simple_loss=0.22, pruned_loss=0.03028, over 4924.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02977, over 973878.25 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:33:23,446 INFO [train.py:715] (5/8) Epoch 15, batch 31550, loss[loss=0.1251, simple_loss=0.1999, pruned_loss=0.02518, over 4988.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02931, over 974194.13 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:34:01,214 INFO [train.py:715] (5/8) Epoch 15, batch 31600, loss[loss=0.1315, simple_loss=0.2135, pruned_loss=0.02475, over 4986.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02969, over 973155.78 frames.], batch size: 28, lr: 1.45e-04
2022-05-08 13:34:39,669 INFO [train.py:715] (5/8) Epoch 15, batch 31650, loss[loss=0.1533, simple_loss=0.2321, pruned_loss=0.03724, over 4977.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03016, over 972737.69 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:35:18,000 INFO [train.py:715] (5/8) Epoch 15, batch 31700, loss[loss=0.1515, simple_loss=0.2258, pruned_loss=0.03859, over 4976.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02992, over 973160.49 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:35:55,495 INFO [train.py:715] (5/8) Epoch 15, batch 31750, loss[loss=0.135, simple_loss=0.2043, pruned_loss=0.03281, over 4774.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02948, over 972498.67 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:36:34,377 INFO [train.py:715] (5/8) Epoch 15, batch 31800, loss[loss=0.1344, simple_loss=0.2124, pruned_loss=0.02825, over 4929.00 frames.], tot_loss[loss=0.133, simple_loss=0.208, pruned_loss=0.02899, over 971537.48 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:37:12,850 INFO [train.py:715] (5/8) Epoch 15, batch 31850, loss[loss=0.1743, simple_loss=0.231, pruned_loss=0.05885, over 4711.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02944, over 971526.30 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:37:52,389 INFO [train.py:715] (5/8) Epoch 15, batch 31900, loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02845, over 4949.00 frames.], tot_loss[loss=0.134, simple_loss=0.2088, pruned_loss=0.02958, over 972033.01 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:38:29,679 INFO [train.py:715] (5/8) Epoch 15, batch 31950, loss[loss=0.1377, simple_loss=0.2149, pruned_loss=0.03026, over 4929.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2089, pruned_loss=0.02943, over 971691.97 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:39:08,342 INFO [train.py:715] (5/8) Epoch 15, batch 32000, loss[loss=0.1284, simple_loss=0.2001, pruned_loss=0.0283, over 4929.00 frames.], tot_loss[loss=0.1339, simple_loss=0.209, pruned_loss=0.02946, over 971109.01 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:39:46,519 INFO [train.py:715] (5/8) Epoch 15, batch 32050, loss[loss=0.1336, simple_loss=0.2023, pruned_loss=0.0324, over 4849.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02996, over 971425.43 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:40:23,950 INFO [train.py:715] (5/8) Epoch 15, batch 32100, loss[loss=0.1363, simple_loss=0.2089, pruned_loss=0.0319, over 4755.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03006, over 970625.11 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:41:02,343 INFO [train.py:715] (5/8) Epoch 15, batch 32150, loss[loss=0.1348, simple_loss=0.205, pruned_loss=0.03236, over 4752.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03034, over 970219.11 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:41:40,505 INFO [train.py:715] (5/8) Epoch 15, batch 32200, loss[loss=0.132, simple_loss=0.2076, pruned_loss=0.02819, over 4821.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03051, over 970643.58 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 13:42:19,023 INFO [train.py:715] (5/8) Epoch 15, batch 32250, loss[loss=0.1731, simple_loss=0.2567, pruned_loss=0.04472, over 4823.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03096, over 971318.38 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 13:42:56,890 INFO [train.py:715] (5/8) Epoch 15, batch 32300, loss[loss=0.1508, simple_loss=0.2411, pruned_loss=0.03025, over 4942.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03077, over 971758.97 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:43:35,758 INFO [train.py:715] (5/8) Epoch 15, batch 32350, loss[loss=0.1308, simple_loss=0.2121, pruned_loss=0.02472, over 4923.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03044, over 971738.49 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:44:14,154 INFO [train.py:715] (5/8) Epoch 15, batch 32400, loss[loss=0.1091, simple_loss=0.1828, pruned_loss=0.01771, over 4807.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03087, over 971644.33 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 13:44:51,908 INFO [train.py:715] (5/8) Epoch 15, batch 32450, loss[loss=0.1457, simple_loss=0.2252, pruned_loss=0.03308, over 4884.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 971739.37 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:45:30,472 INFO [train.py:715] (5/8) Epoch 15, batch 32500, loss[loss=0.1426, simple_loss=0.2209, pruned_loss=0.03214, over 4983.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03115, over 972133.70 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 13:46:08,935 INFO [train.py:715] (5/8) Epoch 15, batch 32550, loss[loss=0.1125, simple_loss=0.1785, pruned_loss=0.02327, over 4768.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03078, over 971115.79 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:46:47,815 INFO [train.py:715] (5/8) Epoch 15, batch 32600, loss[loss=0.1195, simple_loss=0.1981, pruned_loss=0.02046, over 4928.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03042, over 972404.12 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:47:26,417 INFO [train.py:715] (5/8) Epoch 15, batch 32650, loss[loss=0.1529, simple_loss=0.2164, pruned_loss=0.04473, over 4989.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03014, over 972038.88 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:48:05,086 INFO [train.py:715] (5/8) Epoch 15, batch 32700, loss[loss=0.1293, simple_loss=0.2037, pruned_loss=0.02746, over 4907.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 972569.94 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:48:43,313 INFO [train.py:715] (5/8) Epoch 15, batch 32750, loss[loss=0.1202, simple_loss=0.1915, pruned_loss=0.02449, over 4782.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03028, over 972728.79 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:49:21,521 INFO [train.py:715] (5/8) Epoch 15, batch 32800, loss[loss=0.1473, simple_loss=0.2175, pruned_loss=0.0385, over 4892.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 972049.35 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:49:59,268 INFO [train.py:715] (5/8) Epoch 15, batch 32850, loss[loss=0.1349, simple_loss=0.206, pruned_loss=0.03191, over 4979.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03021, over 972623.81 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:50:37,486 INFO [train.py:715] (5/8) Epoch 15, batch 32900, loss[loss=0.1262, simple_loss=0.201, pruned_loss=0.02564, over 4885.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02986, over 972534.89 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:51:16,078 INFO [train.py:715] (5/8) Epoch 15, batch 32950, loss[loss=0.1283, simple_loss=0.2178, pruned_loss=0.01939, over 4685.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02971, over 972732.28 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:51:54,466 INFO [train.py:715] (5/8) Epoch 15, batch 33000, loss[loss=0.1367, simple_loss=0.2093, pruned_loss=0.03205, over 4825.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02973, over 971523.90 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 13:51:54,467 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 13:52:03,985 INFO [train.py:742] (5/8) Epoch 15, validation: loss=0.1052, simple_loss=0.1886, pruned_loss=0.01088, over 914524.00 frames.
2022-05-08 13:52:42,025 INFO [train.py:715] (5/8) Epoch 15, batch 33050, loss[loss=0.1254, simple_loss=0.2029, pruned_loss=0.02397, over 4923.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02998, over 970821.58 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:53:20,376 INFO [train.py:715] (5/8) Epoch 15, batch 33100, loss[loss=0.1178, simple_loss=0.189, pruned_loss=0.02328, over 4841.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02997, over 970820.50 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:53:58,082 INFO [train.py:715] (5/8) Epoch 15, batch 33150, loss[loss=0.1177, simple_loss=0.1971, pruned_loss=0.01913, over 4873.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02989, over 970214.85 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 13:54:37,162 INFO [train.py:715] (5/8) Epoch 15, batch 33200, loss[loss=0.1355, simple_loss=0.2078, pruned_loss=0.03156, over 4981.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.0298, over 970952.60 frames.], batch size: 14, lr: 1.44e-04
2022-05-08 13:55:15,596 INFO [train.py:715] (5/8) Epoch 15, batch 33250, loss[loss=0.159, simple_loss=0.2303, pruned_loss=0.04385, over 4844.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02989, over 971053.77 frames.], batch size: 15, lr: 1.44e-04
2022-05-08 13:55:53,707 INFO [train.py:715] (5/8) Epoch 15, batch 33300, loss[loss=0.1255, simple_loss=0.1996, pruned_loss=0.02566, over 4937.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03045, over 971806.33 frames.], batch size: 29, lr: 1.44e-04
2022-05-08 13:56:31,676 INFO [train.py:715] (5/8) Epoch 15, batch 33350, loss[loss=0.1642, simple_loss=0.2258, pruned_loss=0.05129, over 4872.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03001, over 972338.61 frames.], batch size: 22, lr: 1.44e-04
2022-05-08 13:57:09,333 INFO [train.py:715] (5/8) Epoch 15, batch 33400, loss[loss=0.1098, simple_loss=0.1775, pruned_loss=0.021, over 4940.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02968, over 972595.10 frames.], batch size: 29, lr: 1.44e-04
2022-05-08 13:57:47,385 INFO [train.py:715] (5/8) Epoch 15, batch 33450, loss[loss=0.1211, simple_loss=0.1937, pruned_loss=0.02424, over 4737.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2089, pruned_loss=0.02947, over 972515.58 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 13:58:25,100 INFO [train.py:715] (5/8) Epoch 15, batch 33500, loss[loss=0.1187, simple_loss=0.2037, pruned_loss=0.01683, over 4973.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2084, pruned_loss=0.02949, over 971466.06 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 13:59:02,925 INFO [train.py:715] (5/8) Epoch 15, batch 33550, loss[loss=0.1224, simple_loss=0.2007, pruned_loss=0.02208, over 4892.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02975, over 971549.83 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 13:59:40,602 INFO [train.py:715] (5/8) Epoch 15, batch 33600, loss[loss=0.1397, simple_loss=0.217, pruned_loss=0.03122, over 4812.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02966, over 971793.36 frames.], batch size: 21, lr: 1.44e-04
2022-05-08 14:00:18,653 INFO [train.py:715] (5/8) Epoch 15, batch 33650, loss[loss=0.1456, simple_loss=0.2034, pruned_loss=0.04387, over 4788.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 971635.10 frames.], batch size: 14, lr: 1.44e-04
2022-05-08 14:00:56,120 INFO [train.py:715] (5/8) Epoch 15, batch 33700, loss[loss=0.1355, simple_loss=0.2074, pruned_loss=0.03186, over 4787.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02985, over 972497.17 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:01:33,646 INFO [train.py:715] (5/8) Epoch 15, batch 33750, loss[loss=0.1191, simple_loss=0.2004, pruned_loss=0.01889, over 4815.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03, over 971966.50 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:02:11,484 INFO [train.py:715] (5/8) Epoch 15, batch 33800, loss[loss=0.1314, simple_loss=0.2079, pruned_loss=0.02744, over 4746.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02989, over 972128.88 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 14:02:48,675 INFO [train.py:715] (5/8) Epoch 15, batch 33850, loss[loss=0.1283, simple_loss=0.1913, pruned_loss=0.03271, over 4820.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02958, over 972237.90 frames.], batch size: 13, lr: 1.44e-04
2022-05-08 14:03:26,485 INFO [train.py:715] (5/8) Epoch 15, batch 33900, loss[loss=0.1745, simple_loss=0.232, pruned_loss=0.05855, over 4820.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03022, over 971518.37 frames.], batch size: 13, lr: 1.44e-04
2022-05-08 14:04:04,823 INFO [train.py:715] (5/8) Epoch 15, batch 33950, loss[loss=0.1422, simple_loss=0.2121, pruned_loss=0.03617, over 4780.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03089, over 972207.43 frames.], batch size: 14, lr: 1.44e-04
2022-05-08 14:04:42,874 INFO [train.py:715] (5/8) Epoch 15, batch 34000, loss[loss=0.1247, simple_loss=0.2046, pruned_loss=0.02235, over 4957.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03077, over 971699.05 frames.], batch size: 21, lr: 1.44e-04
2022-05-08 14:05:20,769 INFO [train.py:715] (5/8) Epoch 15, batch 34050, loss[loss=0.1436, simple_loss=0.2077, pruned_loss=0.03978, over 4891.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03057, over 972094.52 frames.], batch size: 19, lr: 1.44e-04
2022-05-08 14:05:58,931 INFO [train.py:715] (5/8) Epoch 15, batch 34100, loss[loss=0.123, simple_loss=0.1937, pruned_loss=0.02614, over 4938.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03064, over 972361.02 frames.], batch size: 35, lr: 1.44e-04
2022-05-08 14:06:37,188 INFO [train.py:715] (5/8) Epoch 15, batch 34150, loss[loss=0.1374, simple_loss=0.1974, pruned_loss=0.0387, over 4957.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03046, over 971568.62 frames.], batch size: 35, lr: 1.44e-04
2022-05-08 14:07:14,888 INFO [train.py:715] (5/8) Epoch 15, batch 34200, loss[loss=0.1358, simple_loss=0.2075, pruned_loss=0.03209, over 4755.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02981, over 971793.54 frames.], batch size: 19, lr: 1.44e-04
2022-05-08 14:07:52,719 INFO [train.py:715] (5/8) Epoch 15, batch 34250, loss[loss=0.1219, simple_loss=0.2048, pruned_loss=0.01948, over 4948.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02989, over 971495.85 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:08:30,685 INFO [train.py:715] (5/8) Epoch 15, batch 34300, loss[loss=0.1231, simple_loss=0.2007, pruned_loss=0.02278, over 4929.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03026, over 971174.17 frames.], batch size: 29, lr: 1.44e-04
2022-05-08 14:09:08,612 INFO [train.py:715] (5/8) Epoch 15, batch 34350, loss[loss=0.1449, simple_loss=0.2147, pruned_loss=0.03755, over 4839.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03034, over 972250.74 frames.], batch size: 30, lr: 1.44e-04
2022-05-08 14:09:45,972 INFO [train.py:715] (5/8) Epoch 15, batch 34400, loss[loss=0.1245, simple_loss=0.1967, pruned_loss=0.02613, over 4984.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03027, over 972721.22 frames.], batch size: 35, lr: 1.44e-04
2022-05-08 14:10:24,174 INFO [train.py:715] (5/8) Epoch 15, batch 34450, loss[loss=0.1179, simple_loss=0.2061, pruned_loss=0.01487, over 4959.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03005, over 971441.41 frames.], batch size: 28, lr: 1.44e-04
2022-05-08 14:11:02,055 INFO [train.py:715] (5/8) Epoch 15, batch 34500, loss[loss=0.1289, simple_loss=0.2007, pruned_loss=0.02856, over 4953.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03002, over 971694.38 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:11:39,391 INFO [train.py:715] (5/8) Epoch 15, batch 34550, loss[loss=0.1193, simple_loss=0.203, pruned_loss=0.01784, over 4825.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03019, over 972465.09 frames.], batch size: 25, lr: 1.44e-04
2022-05-08 14:12:17,005 INFO [train.py:715] (5/8) Epoch 15, batch 34600, loss[loss=0.1407, simple_loss=0.2174, pruned_loss=0.03197, over 4920.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03001, over 971993.59 frames.], batch size: 17, lr: 1.44e-04
2022-05-08 14:12:54,930 INFO [train.py:715] (5/8) Epoch 15, batch 34650, loss[loss=0.1529, simple_loss=0.2425, pruned_loss=0.03164, over 4861.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02991, over 972202.10 frames.], batch size: 20, lr: 1.44e-04
2022-05-08 14:13:32,475 INFO [train.py:715] (5/8) Epoch 15, batch 34700, loss[loss=0.1037, simple_loss=0.1832, pruned_loss=0.01211, over 4988.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03003, over 972076.68 frames.], batch size: 28, lr: 1.44e-04
2022-05-08 14:14:09,603 INFO [train.py:715] (5/8) Epoch 15, batch 34750, loss[loss=0.121, simple_loss=0.2015, pruned_loss=0.02021, over 4877.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03039, over 972046.78 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 14:14:44,840 INFO [train.py:715] (5/8) Epoch 15, batch 34800, loss[loss=0.156, simple_loss=0.2197, pruned_loss=0.04612, over 4926.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03021, over 972818.48 frames.], batch size: 18, lr: 1.44e-04
2022-05-08 14:15:33,454 INFO [train.py:715] (5/8) Epoch 16, batch 0, loss[loss=0.1239, simple_loss=0.2044, pruned_loss=0.02168, over 4819.00 frames.], tot_loss[loss=0.1239, simple_loss=0.2044, pruned_loss=0.02168, over 4819.00 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:16:11,643 INFO [train.py:715] (5/8) Epoch 16, batch 50, loss[loss=0.1205, simple_loss=0.193, pruned_loss=0.02398, over 4821.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2078, pruned_loss=0.02846, over 218633.64 frames.], batch size: 26, lr: 1.40e-04
2022-05-08 14:16:50,212 INFO [train.py:715] (5/8) Epoch 16, batch 100, loss[loss=0.1398, simple_loss=0.2238, pruned_loss=0.0279, over 4815.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03022, over 385861.09 frames.], batch size: 26, lr: 1.40e-04
2022-05-08 14:17:27,945 INFO [train.py:715] (5/8) Epoch 16, batch 150, loss[loss=0.122, simple_loss=0.181, pruned_loss=0.03147, over 4987.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03065, over 516131.59 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:18:06,152 INFO [train.py:715] (5/8) Epoch 16, batch 200, loss[loss=0.1059, simple_loss=0.181, pruned_loss=0.01543, over 4981.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03028, over 617772.17 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:18:44,279 INFO [train.py:715] (5/8) Epoch 16, batch 250, loss[loss=0.1073, simple_loss=0.185, pruned_loss=0.01483, over 4785.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02942, over 696217.15 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:19:22,600 INFO [train.py:715] (5/8) Epoch 16, batch 300, loss[loss=0.1211, simple_loss=0.1984, pruned_loss=0.0219, over 4900.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02964, over 758107.55 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:20:01,027 INFO [train.py:715] (5/8) Epoch 16, batch 350, loss[loss=0.1502, simple_loss=0.2201, pruned_loss=0.04013, over 4933.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03061, over 805520.56 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:20:38,707 INFO [train.py:715] (5/8) Epoch 16, batch 400, loss[loss=0.1449, simple_loss=0.2145, pruned_loss=0.03762, over 4834.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03096, over 842651.95 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:21:17,413 INFO [train.py:715] (5/8) Epoch 16, batch 450, loss[loss=0.144, simple_loss=0.2074, pruned_loss=0.04032, over 4862.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03067, over 871147.89 frames.], batch size: 32, lr: 1.40e-04
2022-05-08 14:21:55,826 INFO [train.py:715] (5/8) Epoch 16, batch 500, loss[loss=0.1229, simple_loss=0.195, pruned_loss=0.02543, over 4806.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03031, over 894275.81 frames.], batch size: 26, lr: 1.40e-04
2022-05-08 14:22:33,536 INFO [train.py:715] (5/8) Epoch 16, batch 550, loss[loss=0.1259, simple_loss=0.2091, pruned_loss=0.02135, over 4987.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03036, over 911729.16 frames.], batch size: 28, lr: 1.40e-04
2022-05-08 14:23:12,212 INFO [train.py:715] (5/8) Epoch 16, batch 600, loss[loss=0.123, simple_loss=0.1962, pruned_loss=0.02489, over 4791.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03018, over 924780.68 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:23:50,876 INFO [train.py:715] (5/8) Epoch 16, batch 650, loss[loss=0.1505, simple_loss=0.2272, pruned_loss=0.03686, over 4771.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02971, over 935767.04 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:24:28,546 INFO [train.py:715] (5/8) Epoch 16, batch 700, loss[loss=0.1302, simple_loss=0.2091, pruned_loss=0.02569, over 4839.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.0298, over 944066.30 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:25:06,445 INFO [train.py:715] (5/8) Epoch 16, batch 750, loss[loss=0.1209, simple_loss=0.1976, pruned_loss=0.0221, over 4897.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03022, over 949885.49 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:25:45,233 INFO [train.py:715] (5/8) Epoch 16, batch 800, loss[loss=0.1134, simple_loss=0.1772, pruned_loss=0.02485, over 4781.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03067, over 954363.46 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:26:23,532 INFO [train.py:715] (5/8) Epoch 16, batch 850, loss[loss=0.1131, simple_loss=0.1916, pruned_loss=0.01727, over 4804.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02978, over 958381.42 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:27:01,575 INFO [train.py:715] (5/8) Epoch 16, batch 900, loss[loss=0.1417, simple_loss=0.2181, pruned_loss=0.03264, over 4825.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03035, over 961510.75 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:27:39,692 INFO [train.py:715] (5/8) Epoch 16, batch 950, loss[loss=0.1088, simple_loss=0.1836, pruned_loss=0.01702, over 4893.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2069, pruned_loss=0.03029, over 964484.54 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:28:18,128 INFO [train.py:715] (5/8) Epoch 16, batch 1000, loss[loss=0.1136, simple_loss=0.1821, pruned_loss=0.02257, over 4982.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02989, over 966184.21 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:28:55,786 INFO [train.py:715] (5/8) Epoch 16, batch 1050, loss[loss=0.1372, simple_loss=0.212, pruned_loss=0.03119, over 4762.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.03036, over 967314.71 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:29:33,186 INFO [train.py:715] (5/8) Epoch 16, batch 1100, loss[loss=0.1256, simple_loss=0.2167, pruned_loss=0.01722, over 4948.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03061, over 967887.41 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:30:11,812 INFO [train.py:715] (5/8) Epoch 16, batch 1150, loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03622, over 4751.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03035, over 968281.59 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:30:49,880 INFO [train.py:715] (5/8) Epoch 16, batch 1200, loss[loss=0.1229, simple_loss=0.2057, pruned_loss=0.02009, over 4863.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03034, over 969363.40 frames.], batch size: 22, lr: 1.40e-04
2022-05-08 14:31:27,246 INFO [train.py:715] (5/8) Epoch 16, batch 1250, loss[loss=0.1402, simple_loss=0.2097, pruned_loss=0.03531, over 4944.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03039, over 969878.10 frames.], batch size: 29, lr: 1.40e-04
2022-05-08 14:32:05,203 INFO [train.py:715] (5/8) Epoch 16, batch 1300, loss[loss=0.1236, simple_loss=0.1993, pruned_loss=0.02396, over 4822.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02986, over 970668.36 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:32:43,364 INFO [train.py:715] (5/8) Epoch 16, batch 1350, loss[loss=0.1475, simple_loss=0.225, pruned_loss=0.03504, over 4865.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02985, over 971562.13 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:33:21,096 INFO [train.py:715] (5/8) Epoch 16, batch 1400, loss[loss=0.1216, simple_loss=0.1989, pruned_loss=0.02217, over 4785.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02983, over 972463.87 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:33:59,219 INFO [train.py:715] (5/8) Epoch 16, batch 1450, loss[loss=0.142, simple_loss=0.2163, pruned_loss=0.03386, over 4751.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03013, over 972264.59 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:34:37,200 INFO [train.py:715] (5/8) Epoch 16, batch 1500, loss[loss=0.1255, simple_loss=0.198, pruned_loss=0.02647, over 4941.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03003, over 972055.99 frames.], batch size: 29, lr: 1.40e-04
2022-05-08 14:35:14,922 INFO [train.py:715] (5/8) Epoch 16, batch 1550, loss[loss=0.1552, simple_loss=0.2204, pruned_loss=0.04502, over 4757.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03031, over 972132.50 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:35:52,770 INFO [train.py:715] (5/8) Epoch 16, batch 1600, loss[loss=0.1471, simple_loss=0.2174, pruned_loss=0.03836, over 4881.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03008, over 971636.97 frames.], batch size: 39, lr: 1.40e-04
2022-05-08 14:36:30,169 INFO [train.py:715] (5/8) Epoch 16, batch 1650, loss[loss=0.1243, simple_loss=0.2008, pruned_loss=0.02392, over 4775.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.0301, over 972253.24 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:37:07,993 INFO [train.py:715] (5/8) Epoch 16, batch 1700, loss[loss=0.1494, simple_loss=0.2134, pruned_loss=0.0427, over 4692.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02941, over 972859.73 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:37:46,152 INFO [train.py:715] (5/8) Epoch 16, batch 1750, loss[loss=0.127, simple_loss=0.2134, pruned_loss=0.02029, over 4985.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02891, over 972368.30 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:38:24,068 INFO [train.py:715] (5/8) Epoch 16, batch 1800, loss[loss=0.1426, simple_loss=0.2167, pruned_loss=0.03421, over 4795.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02916, over 971891.77 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:39:02,376 INFO [train.py:715] (5/8) Epoch 16, batch 1850, loss[loss=0.1273, simple_loss=0.2044, pruned_loss=0.02506, over 4776.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02936, over 971625.32 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:39:41,009 INFO [train.py:715] (5/8) Epoch 16, batch 1900, loss[loss=0.1227, simple_loss=0.2028, pruned_loss=0.02126, over 4813.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2057, pruned_loss=0.02924, over 971847.39 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:40:18,871 INFO [train.py:715] (5/8) Epoch 16, batch 1950, loss[loss=0.1344, simple_loss=0.2046, pruned_loss=0.03208, over 4882.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2061, pruned_loss=0.02943, over 973142.05 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:40:57,049 INFO [train.py:715] (5/8) Epoch 16, batch 2000, loss[loss=0.1544, simple_loss=0.2184, pruned_loss=0.04521, over 4943.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02961, over 972485.56 frames.], batch size: 35, lr: 1.40e-04
2022-05-08 14:41:35,847 INFO [train.py:715] (5/8) Epoch 16, batch 2050, loss[loss=0.1336, simple_loss=0.2095, pruned_loss=0.02882, over 4935.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02989, over 972512.43 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:42:14,574 INFO [train.py:715] (5/8) Epoch 16, batch 2100, loss[loss=0.1529, simple_loss=0.2293, pruned_loss=0.03828, over 4916.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02984, over 972348.01 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:42:52,429 INFO [train.py:715] (5/8) Epoch 16, batch 2150, loss[loss=0.1446, simple_loss=0.2263, pruned_loss=0.03144, over 4966.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.02961, over 972087.71 frames.], batch size: 39, lr: 1.40e-04
2022-05-08 14:43:31,556 INFO [train.py:715] (5/8) Epoch 16, batch 2200, loss[loss=0.1119, simple_loss=0.1843, pruned_loss=0.01971, over 4859.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.0293, over 972418.34 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:44:09,851 INFO [train.py:715] (5/8) Epoch 16, batch 2250, loss[loss=0.1454, simple_loss=0.2145, pruned_loss=0.03819, over 4773.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02939, over 971804.25 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:44:47,484 INFO [train.py:715] (5/8) Epoch 16, batch 2300, loss[loss=0.1236, simple_loss=0.1932, pruned_loss=0.02702, over 4817.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02927, over 971939.15 frames.], batch size: 12, lr: 1.40e-04
2022-05-08 14:45:25,052 INFO [train.py:715] (5/8) Epoch 16, batch 2350, loss[loss=0.1194, simple_loss=0.1991, pruned_loss=0.0198, over 4904.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02913, over 972952.10 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:46:03,344 INFO [train.py:715] (5/8) Epoch 16, batch 2400, loss[loss=0.1191, simple_loss=0.1949, pruned_loss=0.02164, over 4989.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02886, over 972766.66 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:46:41,419 INFO [train.py:715] (5/8) Epoch 16, batch 2450, loss[loss=0.1666, simple_loss=0.229, pruned_loss=0.05214, over 4918.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02922, over 974044.70 frames.], batch size: 39, lr: 1.40e-04
2022-05-08 14:47:18,880 INFO [train.py:715] (5/8) Epoch 16, batch 2500, loss[loss=0.121, simple_loss=0.1995, pruned_loss=0.02128, over 4822.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02889, over 973640.39 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:47:57,274 INFO [train.py:715] (5/8) Epoch 16, batch 2550, loss[loss=0.1315, simple_loss=0.2143, pruned_loss=0.02428, over 4836.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02925, over 973134.17 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:48:35,428 INFO [train.py:715] (5/8) Epoch 16, batch 2600, loss[loss=0.1628, simple_loss=0.2317, pruned_loss=0.04695, over 4789.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.0296, over 972611.46 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:49:13,159 INFO [train.py:715] (5/8) Epoch 16, batch 2650, loss[loss=0.1264, simple_loss=0.2043, pruned_loss=0.02421, over 4702.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02929, over 972368.33 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:49:51,048 INFO [train.py:715] (5/8) Epoch 16, batch 2700, loss[loss=0.1161, simple_loss=0.1871, pruned_loss=0.02254, over 4795.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02873, over 972137.80 frames.], batch size: 12, lr: 1.40e-04
2022-05-08 14:50:29,658 INFO [train.py:715] (5/8) Epoch 16, batch 2750, loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02835, over 4768.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02915, over 971809.13 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:51:08,571 INFO [train.py:715] (5/8) Epoch 16, batch 2800, loss[loss=0.1406, simple_loss=0.2191, pruned_loss=0.03108, over 4894.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 972245.43 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:51:46,949 INFO [train.py:715] (5/8) Epoch 16, batch 2850, loss[loss=0.1022, simple_loss=0.1689, pruned_loss=0.01775, over 4808.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02951, over 972437.85 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:52:24,998 INFO [train.py:715] (5/8) Epoch 16, batch 2900, loss[loss=0.1224, simple_loss=0.1916, pruned_loss=0.02663, over 4822.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.0295, over 972425.23 frames.], batch size: 27, lr: 1.40e-04
2022-05-08 14:53:03,773 INFO [train.py:715] (5/8) Epoch 16, batch 2950, loss[loss=0.1207, simple_loss=0.1944, pruned_loss=0.02347, over 4784.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 972712.75 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 14:53:41,757 INFO [train.py:715] (5/8) Epoch 16, batch 3000, loss[loss=0.1302, simple_loss=0.2087, pruned_loss=0.02582, over 4962.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02954, over 973122.90 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:53:41,758 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 14:53:51,190 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 14:54:29,007 INFO [train.py:715] (5/8) Epoch 16, batch 3050, loss[loss=0.1502, simple_loss=0.2314, pruned_loss=0.03451, over 4991.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.0293, over 972889.33 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:55:09,458 INFO [train.py:715] (5/8) Epoch 16, batch 3100, loss[loss=0.1368, simple_loss=0.2078, pruned_loss=0.03294, over 4940.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02933, over 973130.88 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:55:47,850 INFO [train.py:715] (5/8) Epoch 16, batch 3150, loss[loss=0.1509, simple_loss=0.2325, pruned_loss=0.03463, over 4780.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02942, over 972788.75 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:56:26,003 INFO [train.py:715] (5/8) Epoch 16, batch 3200, loss[loss=0.1391, simple_loss=0.2142, pruned_loss=0.03201, over 4831.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02951, over 971855.75 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:57:04,239 INFO [train.py:715] (5/8) Epoch 16, batch 3250, loss[loss=0.1516, simple_loss=0.2195, pruned_loss=0.04182, over 4834.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02978, over 971841.16 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:57:42,064 INFO [train.py:715] (5/8) Epoch 16, batch 3300, loss[loss=0.1246, simple_loss=0.2024, pruned_loss=0.02337, over 4884.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.0297, over 971472.11 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:58:20,053 INFO [train.py:715] (5/8) Epoch 16, batch 3350, loss[loss=0.1389, simple_loss=0.1997, pruned_loss=0.03904, over 4817.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03041, over 970794.11 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:58:57,929 INFO [train.py:715] (5/8) Epoch 16, batch 3400, loss[loss=0.1271, simple_loss=0.2141, pruned_loss=0.02009, over 4796.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03039, over 971423.40 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:59:35,864 INFO [train.py:715] (5/8) Epoch 16, batch 3450, loss[loss=0.1216, simple_loss=0.1962, pruned_loss=0.02351, over 4858.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03043, over 971325.47 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 15:00:13,953 INFO [train.py:715] (5/8) Epoch 16, batch 3500, loss[loss=0.156, simple_loss=0.2092, pruned_loss=0.0514, over 4824.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03017, over 971743.46 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 15:00:51,754 INFO [train.py:715] (5/8) Epoch 16, batch 3550, loss[loss=0.1151, simple_loss=0.1904, pruned_loss=0.01988, over 4943.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03057, over 972190.96 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 15:01:30,177 INFO [train.py:715] (5/8) Epoch 16, batch 3600, loss[loss=0.148, simple_loss=0.2274, pruned_loss=0.0343, over 4986.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03053, over 971429.84 frames.], batch size: 35, lr: 1.40e-04
2022-05-08 15:02:07,897 INFO [train.py:715] (5/8) Epoch 16, batch 3650, loss[loss=0.1404, simple_loss=0.2064, pruned_loss=0.03719, over 4850.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03067, over 971120.47 frames.], batch size: 32, lr: 1.40e-04
2022-05-08 15:02:46,542 INFO [train.py:715] (5/8) Epoch 16, batch 3700, loss[loss=0.1257, simple_loss=0.2108, pruned_loss=0.02029, over 4770.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03055, over 971606.66 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 15:03:25,026 INFO [train.py:715] (5/8) Epoch 16, batch 3750, loss[loss=0.1218, simple_loss=0.1978, pruned_loss=0.02287, over 4922.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03053, over 971849.02 frames.], batch size: 23, lr: 1.40e-04
2022-05-08 15:04:03,390 INFO [train.py:715] (5/8) Epoch 16, batch 3800, loss[loss=0.1348, simple_loss=0.2143, pruned_loss=0.02769, over 4969.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2079, pruned_loss=0.03086, over 972075.48 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 15:04:42,255 INFO [train.py:715] (5/8) Epoch 16, batch 3850, loss[loss=0.1041, simple_loss=0.175, pruned_loss=0.01664, over 4882.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03041, over 972465.57 frames.], batch size: 22, lr: 1.40e-04
2022-05-08 15:05:21,012 INFO [train.py:715] (5/8) Epoch 16, batch 3900, loss[loss=0.1491, simple_loss=0.2165, pruned_loss=0.04085, over 4898.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03058, over 972753.86 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:05:58,859 INFO [train.py:715] (5/8) Epoch 16, batch 3950, loss[loss=0.1225, simple_loss=0.2013, pruned_loss=0.02184, over 4975.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2076, pruned_loss=0.03036, over 971949.97 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:06:36,784 INFO [train.py:715] (5/8) Epoch 16, batch 4000, loss[loss=0.136, simple_loss=0.211, pruned_loss=0.03045, over 4919.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2075, pruned_loss=0.03041, over 971815.07 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:07:14,744 INFO [train.py:715] (5/8) Epoch 16, batch 4050, loss[loss=0.1354, simple_loss=0.2105, pruned_loss=0.03016, over 4971.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03004, over 972312.04 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:07:52,146 INFO [train.py:715] (5/8) Epoch 16, batch 4100, loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03578, over 4686.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02995, over 971891.95 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:08:29,797 INFO [train.py:715] (5/8) Epoch 16, batch 4150, loss[loss=0.1574, simple_loss=0.2391, pruned_loss=0.03782, over 4754.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02997, over 971740.56 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:09:07,464 INFO [train.py:715] (5/8) Epoch 16, batch 4200, loss[loss=0.1518, simple_loss=0.2283, pruned_loss=0.03771, over 4905.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02969, over 972720.16 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:09:45,632 INFO [train.py:715] (5/8) Epoch 16, batch 4250, loss[loss=0.126, simple_loss=0.2028, pruned_loss=0.02466, over 4983.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03014, over 972958.91 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:10:23,340 INFO [train.py:715] (5/8) Epoch 16, batch 4300, loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02937, over 4826.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 972779.04 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:11:01,195 INFO [train.py:715] (5/8) Epoch 16, batch 4350, loss[loss=0.1401, simple_loss=0.2109, pruned_loss=0.03461, over 4967.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.0302, over 972795.75 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:11:39,304 INFO [train.py:715] (5/8) Epoch 16, batch 4400, loss[loss=0.1436, simple_loss=0.2272, pruned_loss=0.03002, over 4808.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03001, over 972723.03 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:12:17,134 INFO [train.py:715] (5/8) Epoch 16, batch 4450, loss[loss=0.1408, simple_loss=0.2172, pruned_loss=0.03217, over 4863.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02995, over 972362.82 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:12:54,751 INFO [train.py:715] (5/8) Epoch 16, batch 4500, loss[loss=0.12, simple_loss=0.1971, pruned_loss=0.0214, over 4816.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03003, over 972364.32 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 15:13:32,859 INFO [train.py:715] (5/8) Epoch 16, batch 4550, loss[loss=0.1333, simple_loss=0.2134, pruned_loss=0.02666, over 4797.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03009, over 971949.35 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:14:11,254 INFO [train.py:715] (5/8) Epoch 16, batch 4600, loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03577, over 4910.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02976, over 971903.16 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:14:49,229 INFO [train.py:715] (5/8) Epoch 16, batch 4650, loss[loss=0.1377, simple_loss=0.2255, pruned_loss=0.02497, over 4903.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 972309.98 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:15:27,630 INFO [train.py:715] (5/8) Epoch 16, batch 4700, loss[loss=0.1636, simple_loss=0.233, pruned_loss=0.04713, over 4695.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 972006.71 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:16:06,226 INFO [train.py:715] (5/8) Epoch 16, batch 4750, loss[loss=0.1464, simple_loss=0.2154, pruned_loss=0.03867, over 4826.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02988, over 971928.51 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:16:44,828 INFO [train.py:715] (5/8) Epoch 16, batch 4800, loss[loss=0.1323, simple_loss=0.2187, pruned_loss=0.0229, over 4881.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02939, over 972248.14 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:17:23,109 INFO [train.py:715] (5/8) Epoch 16, batch 4850, loss[loss=0.1388, simple_loss=0.2184, pruned_loss=0.02959, over 4895.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02924, over 972874.21 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 15:18:01,808 INFO [train.py:715] (5/8) Epoch 16, batch 4900, loss[loss=0.1351, simple_loss=0.2143, pruned_loss=0.02793, over 4779.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02939, over 973171.06 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:18:40,682 INFO [train.py:715] (5/8) Epoch 16, batch 4950, loss[loss=0.151, simple_loss=0.2163, pruned_loss=0.04288, over 4946.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2082, pruned_loss=0.02921, over 972802.77 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 15:19:18,924 INFO [train.py:715] (5/8) Epoch 16, batch 5000, loss[loss=0.1358, simple_loss=0.2029, pruned_loss=0.03434, over 4964.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02955, over 972375.89 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:19:57,138 INFO [train.py:715] (5/8) Epoch 16, batch 5050, loss[loss=0.1321, simple_loss=0.2036, pruned_loss=0.03028, over 4937.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02965, over 972259.57 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:20:35,446 INFO [train.py:715] (5/8) Epoch 16, batch 5100, loss[loss=0.1288, simple_loss=0.2078, pruned_loss=0.02485, over 4834.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02992, over 973232.58 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:21:13,348 INFO [train.py:715] (5/8) Epoch 16, batch 5150, loss[loss=0.1234, simple_loss=0.2079, pruned_loss=0.01946, over 4849.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02928, over 973102.24 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 15:21:50,906 INFO [train.py:715] (5/8) Epoch 16, batch 5200, loss[loss=0.1247, simple_loss=0.1915, pruned_loss=0.02894, over 4922.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 973104.35 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:22:28,865 INFO [train.py:715] (5/8) Epoch 16, batch 5250, loss[loss=0.1354, simple_loss=0.207, pruned_loss=0.03191, over 4764.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02912, over 973378.77 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:23:07,102 INFO [train.py:715] (5/8) Epoch 16, batch 5300, loss[loss=0.1215, simple_loss=0.1824, pruned_loss=0.03026, over 4837.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02951, over 973204.89 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:23:45,225 INFO [train.py:715] (5/8) Epoch 16, batch 5350, loss[loss=0.1533, simple_loss=0.2123, pruned_loss=0.04713, over 4780.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.0296, over 972939.45 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:24:23,037 INFO [train.py:715] (5/8) Epoch 16, batch 5400, loss[loss=0.1249, simple_loss=0.204, pruned_loss=0.02286, over 4903.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02981, over 973202.58 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:25:00,888 INFO [train.py:715] (5/8) Epoch 16, batch 5450, loss[loss=0.1753, simple_loss=0.2481, pruned_loss=0.05126, over 4891.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03031, over 973404.56 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:25:38,706 INFO [train.py:715] (5/8) Epoch 16, batch 5500, loss[loss=0.1291, simple_loss=0.1982, pruned_loss=0.03, over 4960.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03007, over 973325.30 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:26:16,324 INFO [train.py:715] (5/8) Epoch 16, batch 5550, loss[loss=0.151, simple_loss=0.2241, pruned_loss=0.0389, over 4924.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03008, over 972813.16 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:26:54,074 INFO [train.py:715] (5/8) Epoch 16, batch 5600, loss[loss=0.1229, simple_loss=0.1947, pruned_loss=0.02557, over 4845.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02978, over 972170.33 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:27:32,728 INFO [train.py:715] (5/8) Epoch 16, batch 5650, loss[loss=0.1216, simple_loss=0.1911, pruned_loss=0.02606, over 4817.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03003, over 971176.78 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:28:10,545 INFO [train.py:715] (5/8) Epoch 16, batch 5700, loss[loss=0.1455, simple_loss=0.2243, pruned_loss=0.03331, over 4817.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02969, over 971566.20 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:28:48,367 INFO [train.py:715] (5/8) Epoch 16, batch 5750, loss[loss=0.1126, simple_loss=0.1889, pruned_loss=0.01822, over 4982.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02992, over 971827.16 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:29:26,212 INFO [train.py:715] (5/8) Epoch 16, batch 5800, loss[loss=0.1307, simple_loss=0.2073, pruned_loss=0.02709, over 4982.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02934, over 972700.83 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 15:30:04,475 INFO [train.py:715] (5/8) Epoch 16, batch 5850, loss[loss=0.1183, simple_loss=0.2044, pruned_loss=0.01614, over 4988.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02888, over 973438.12 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:30:42,017 INFO [train.py:715] (5/8) Epoch 16, batch 5900, loss[loss=0.1303, simple_loss=0.2084, pruned_loss=0.02605, over 4917.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02897, over 973416.35 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:31:19,660 INFO [train.py:715] (5/8) Epoch 16, batch 5950, loss[loss=0.1348, simple_loss=0.2198, pruned_loss=0.02487, over 4762.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02923, over 972041.25 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:31:58,427 INFO [train.py:715] (5/8) Epoch 16, batch 6000, loss[loss=0.1185, simple_loss=0.1981, pruned_loss=0.01949, over 4931.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02968, over 971851.80 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 15:31:58,427 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 15:32:07,944 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01082, over 914524.00 frames.
2022-05-08 15:32:46,980 INFO [train.py:715] (5/8) Epoch 16, batch 6050, loss[loss=0.1575, simple_loss=0.2313, pruned_loss=0.04189, over 4852.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 972675.20 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 15:33:25,023 INFO [train.py:715] (5/8) Epoch 16, batch 6100, loss[loss=0.1372, simple_loss=0.22, pruned_loss=0.02718, over 4848.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 973293.41 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 15:34:02,794 INFO [train.py:715] (5/8) Epoch 16, batch 6150, loss[loss=0.1396, simple_loss=0.2214, pruned_loss=0.02886, over 4960.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02913, over 973269.45 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:34:40,935 INFO [train.py:715] (5/8) Epoch 16, batch 6200, loss[loss=0.1262, simple_loss=0.2006, pruned_loss=0.02589, over 4783.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02922, over 972357.46 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:35:19,472 INFO [train.py:715] (5/8) Epoch 16, batch 6250, loss[loss=0.1042, simple_loss=0.1815, pruned_loss=0.01348, over 4985.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02904, over 972131.08 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:35:57,115 INFO [train.py:715] (5/8) Epoch 16, batch 6300, loss[loss=0.1287, simple_loss=0.2061, pruned_loss=0.02561, over 4983.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02931, over 972035.06 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:36:34,885 INFO [train.py:715] (5/8) Epoch 16, batch 6350, loss[loss=0.1513, simple_loss=0.2237, pruned_loss=0.03944, over 4977.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02893, over 973055.38 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:37:13,402 INFO [train.py:715] (5/8) Epoch 16, batch 6400, loss[loss=0.1251, simple_loss=0.2028, pruned_loss=0.02373, over 4908.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02865, over 973063.98 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:37:51,669 INFO [train.py:715] (5/8) Epoch 16, batch 6450, loss[loss=0.1288, simple_loss=0.2074, pruned_loss=0.02507, over 4838.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02877, over 972809.39 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:38:29,441 INFO [train.py:715] (5/8) Epoch 16, batch 6500, loss[loss=0.1294, simple_loss=0.2042, pruned_loss=0.02735, over 4942.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 973221.89 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:39:07,582 INFO [train.py:715] (5/8) Epoch 16, batch 6550, loss[loss=0.1075, simple_loss=0.1795, pruned_loss=0.01777, over 4797.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02936, over 972508.22 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:39:46,029 INFO [train.py:715] (5/8) Epoch 16, batch 6600, loss[loss=0.1531, simple_loss=0.2397, pruned_loss=0.03327, over 4987.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02967, over 971936.90 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:40:23,829 INFO [train.py:715] (5/8) Epoch 16, batch 6650, loss[loss=0.1245, simple_loss=0.2108, pruned_loss=0.01905, over 4754.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02944, over 971169.31 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:41:01,687 INFO [train.py:715] (5/8) Epoch 16, batch 6700, loss[loss=0.1283, simple_loss=0.2039, pruned_loss=0.02632, over 4822.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.0296, over 971377.84 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 15:41:39,713 INFO [train.py:715] (5/8) Epoch 16, batch 6750, loss[loss=0.1313, simple_loss=0.2101, pruned_loss=0.0262, over 4936.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02978, over 971960.04 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:42:17,831 INFO [train.py:715] (5/8) Epoch 16, batch 6800, loss[loss=0.1298, simple_loss=0.1961, pruned_loss=0.03181, over 4796.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02992, over 971699.38 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:42:54,812 INFO [train.py:715] (5/8) Epoch 16, batch 6850, loss[loss=0.1359, simple_loss=0.2211, pruned_loss=0.02536, over 4799.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02948, over 971553.17 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:43:32,596 INFO [train.py:715] (5/8) Epoch 16, batch 6900, loss[loss=0.1094, simple_loss=0.1831, pruned_loss=0.01786, over 4965.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02923, over 972389.30 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:44:10,714 INFO [train.py:715] (5/8) Epoch 16, batch 6950, loss[loss=0.1424, simple_loss=0.2117, pruned_loss=0.03655, over 4749.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.0292, over 972278.14 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:44:48,420 INFO [train.py:715] (5/8) Epoch 16, batch 7000, loss[loss=0.1431, simple_loss=0.2137, pruned_loss=0.03627, over 4831.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02962, over 972657.28 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:45:26,358 INFO [train.py:715] (5/8) Epoch 16, batch 7050, loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04051, over 4927.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 972681.66 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:46:04,189 INFO [train.py:715] (5/8) Epoch 16, batch 7100, loss[loss=0.1364, simple_loss=0.2182, pruned_loss=0.02735, over 4934.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02958, over 973339.46 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:46:42,646 INFO [train.py:715] (5/8) Epoch 16, batch 7150, loss[loss=0.1263, simple_loss=0.1962, pruned_loss=0.02818, over 4831.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02988, over 973846.18 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:47:19,959 INFO [train.py:715] (5/8) Epoch 16, batch 7200, loss[loss=0.1136, simple_loss=0.1977, pruned_loss=0.0147, over 4753.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02988, over 974350.53 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:47:57,928 INFO [train.py:715] (5/8) Epoch 16, batch 7250, loss[loss=0.1383, simple_loss=0.221, pruned_loss=0.02784, over 4749.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02996, over 973584.31 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:48:36,996 INFO [train.py:715] (5/8) Epoch 16, batch 7300, loss[loss=0.1458, simple_loss=0.2193, pruned_loss=0.03619, over 4836.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03009, over 973667.11 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:49:15,801 INFO [train.py:715] (5/8) Epoch 16, batch 7350, loss[loss=0.1636, simple_loss=0.2423, pruned_loss=0.04248, over 4821.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 973528.85 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:49:55,266 INFO [train.py:715] (5/8) Epoch 16, batch 7400, loss[loss=0.1187, simple_loss=0.1985, pruned_loss=0.01939, over 4796.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.0296, over 973274.55 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:50:34,948 INFO [train.py:715] (5/8) Epoch 16, batch 7450, loss[loss=0.1388, simple_loss=0.214, pruned_loss=0.03179, over 4985.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02975, over 973553.83 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:51:14,629 INFO [train.py:715] (5/8) Epoch 16, batch 7500, loss[loss=0.1395, simple_loss=0.202, pruned_loss=0.03851, over 4793.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03013, over 973287.82 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:51:53,688 INFO [train.py:715] (5/8) Epoch 16, batch 7550, loss[loss=0.1398, simple_loss=0.2083, pruned_loss=0.03568, over 4931.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02957, over 973310.87 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:52:33,701 INFO [train.py:715] (5/8) Epoch 16, batch 7600, loss[loss=0.1515, simple_loss=0.2259, pruned_loss=0.03851, over 4797.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 972846.80 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:53:14,084 INFO [train.py:715] (5/8) Epoch 16, batch 7650, loss[loss=0.1692, simple_loss=0.2414, pruned_loss=0.0485, over 4841.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03024, over 973523.88 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:53:54,222 INFO [train.py:715] (5/8) Epoch 16, batch 7700, loss[loss=0.1138, simple_loss=0.1901, pruned_loss=0.01875, over 4763.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02966, over 972809.88 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:54:33,736 INFO [train.py:715] (5/8) Epoch 16, batch 7750, loss[loss=0.1625, simple_loss=0.2405, pruned_loss=0.04221, over 4855.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 972896.73 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 15:55:13,927 INFO [train.py:715] (5/8) Epoch 16, batch 7800, loss[loss=0.1291, simple_loss=0.2015, pruned_loss=0.02836, over 4834.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02953, over 972780.34 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:55:54,770 INFO [train.py:715] (5/8) Epoch 16, batch 7850, loss[loss=0.1625, simple_loss=0.2405, pruned_loss=0.04222, over 4846.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02958, over 972745.82 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:56:34,177 INFO [train.py:715] (5/8) Epoch 16, batch 7900, loss[loss=0.1591, simple_loss=0.2328, pruned_loss=0.04274, over 4700.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02954, over 971335.04 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:57:14,069 INFO [train.py:715] (5/8) Epoch 16, batch 7950, loss[loss=0.118, simple_loss=0.1972, pruned_loss=0.01938, over 4813.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02983, over 971138.76 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:57:54,573 INFO [train.py:715] (5/8) Epoch 16, batch 8000, loss[loss=0.119, simple_loss=0.1939, pruned_loss=0.02205, over 4891.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02958, over 971107.94 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 15:58:34,607 INFO [train.py:715] (5/8) Epoch 16, batch 8050, loss[loss=0.1157, simple_loss=0.1847, pruned_loss=0.0233, over 4828.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.0299, over 971245.63 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:59:14,260 INFO [train.py:715] (5/8) Epoch 16, batch 8100, loss[loss=0.1473, simple_loss=0.2222, pruned_loss=0.03619, over 4808.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03012, over 971189.42 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 15:59:54,690 INFO [train.py:715] (5/8) Epoch 16, batch 8150, loss[loss=0.103, simple_loss=0.1792, pruned_loss=0.01338, over 4793.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03031, over 971270.24 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:00:35,765 INFO [train.py:715] (5/8) Epoch 16, batch 8200, loss[loss=0.1239, simple_loss=0.2067, pruned_loss=0.02057, over 4813.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03054, over 971376.06 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:01:15,839 INFO [train.py:715] (5/8) Epoch 16, batch 8250, loss[loss=0.1446, simple_loss=0.222, pruned_loss=0.03361, over 4974.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03103, over 972501.20 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:01:55,603 INFO [train.py:715] (5/8) Epoch 16, batch 8300, loss[loss=0.1188, simple_loss=0.1971, pruned_loss=0.02025, over 4976.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03024, over 972563.64 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:02:36,304 INFO [train.py:715] (5/8) Epoch 16, batch 8350, loss[loss=0.1343, simple_loss=0.2168, pruned_loss=0.02588, over 4977.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03041, over 971932.82 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 16:03:16,602 INFO [train.py:715] (5/8) Epoch 16, batch 8400, loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03723, over 4828.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03033, over 971622.80 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:03:55,139 INFO [train.py:715] (5/8) Epoch 16, batch 8450, loss[loss=0.116, simple_loss=0.1906, pruned_loss=0.02072, over 4883.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.03042, over 971766.26 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:04:34,541 INFO [train.py:715] (5/8) Epoch 16, batch 8500, loss[loss=0.1541, simple_loss=0.2405, pruned_loss=0.03385, over 4859.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03104, over 971889.02 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:05:13,261 INFO [train.py:715] (5/8) Epoch 16, batch 8550, loss[loss=0.1144, simple_loss=0.1845, pruned_loss=0.02211, over 4991.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03063, over 971946.46 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:05:51,580 INFO [train.py:715] (5/8) Epoch 16, batch 8600, loss[loss=0.1343, simple_loss=0.2141, pruned_loss=0.02724, over 4972.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03027, over 972235.23 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:06:29,596 INFO [train.py:715] (5/8) Epoch 16, batch 8650, loss[loss=0.1279, simple_loss=0.2013, pruned_loss=0.02729, over 4849.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02966, over 971212.84 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:07:08,670 INFO [train.py:715] (5/8) Epoch 16, batch 8700, loss[loss=0.1398, simple_loss=0.2176, pruned_loss=0.03094, over 4883.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 970909.30 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 16:07:47,715 INFO [train.py:715] (5/8) Epoch 16, batch 8750, loss[loss=0.1522, simple_loss=0.2267, pruned_loss=0.03884, over 4952.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.02958, over 972099.15 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 16:08:26,279 INFO [train.py:715] (5/8) Epoch 16, batch 8800, loss[loss=0.1178, simple_loss=0.1912, pruned_loss=0.02216, over 4979.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02997, over 972069.56 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:09:04,975 INFO [train.py:715] (5/8) Epoch 16, batch 8850, loss[loss=0.1332, simple_loss=0.2101, pruned_loss=0.0282, over 4985.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03016, over 971862.68 frames.], batch size: 31, lr: 1.39e-04
2022-05-08 16:09:44,465 INFO [train.py:715] (5/8) Epoch 16, batch 8900, loss[loss=0.1096, simple_loss=0.1853, pruned_loss=0.01694, over 4816.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.03, over 971636.96 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:10:22,906 INFO [train.py:715] (5/8) Epoch 16, batch 8950, loss[loss=0.1844, simple_loss=0.2439, pruned_loss=0.06241, over 4894.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03001, over 971462.35 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:11:01,136 INFO [train.py:715] (5/8) Epoch 16, batch 9000, loss[loss=0.09022, simple_loss=0.162, pruned_loss=0.009248, over 4831.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 972585.44 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:11:01,137 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 16:11:23,893 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01076, over 914524.00 frames.
2022-05-08 16:12:02,818 INFO [train.py:715] (5/8) Epoch 16, batch 9050, loss[loss=0.1159, simple_loss=0.2011, pruned_loss=0.01529, over 4972.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02969, over 972936.80 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:12:41,945 INFO [train.py:715] (5/8) Epoch 16, batch 9100, loss[loss=0.1215, simple_loss=0.1974, pruned_loss=0.02282, over 4856.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02937, over 972457.33 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:13:20,955 INFO [train.py:715] (5/8) Epoch 16, batch 9150, loss[loss=0.1285, simple_loss=0.1966, pruned_loss=0.03022, over 4962.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02949, over 973287.97 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:13:58,479 INFO [train.py:715] (5/8) Epoch 16, batch 9200, loss[loss=0.1427, simple_loss=0.2168, pruned_loss=0.03432, over 4924.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02996, over 972438.15 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 16:14:37,128 INFO [train.py:715] (5/8) Epoch 16, batch 9250, loss[loss=0.1532, simple_loss=0.2248, pruned_loss=0.04082, over 4847.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02986, over 972410.43 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:15:16,085 INFO [train.py:715] (5/8) Epoch 16, batch 9300, loss[loss=0.1362, simple_loss=0.2093, pruned_loss=0.03159, over 4903.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03024, over 972507.82 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 16:15:54,779 INFO [train.py:715] (5/8) Epoch 16, batch 9350, loss[loss=0.1288, simple_loss=0.1918, pruned_loss=0.03292, over 4985.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02987, over 973782.14 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:16:33,104 INFO [train.py:715] (5/8) Epoch 16, batch 9400, loss[loss=0.1368, simple_loss=0.2226, pruned_loss=0.02547, over 4931.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.0296, over 973128.12 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:17:11,620 INFO [train.py:715] (5/8) Epoch 16, batch 9450, loss[loss=0.1046, simple_loss=0.1863, pruned_loss=0.01141, over 4982.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02941, over 972805.32 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:17:50,526 INFO [train.py:715] (5/8) Epoch 16, batch 9500, loss[loss=0.1565, simple_loss=0.2315, pruned_loss=0.0407, over 4959.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02924, over 973588.80 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:18:28,785 INFO [train.py:715] (5/8) Epoch 16, batch 9550, loss[loss=0.1261, simple_loss=0.1909, pruned_loss=0.03064, over 4886.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02959, over 972928.05 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:19:08,106 INFO [train.py:715] (5/8) Epoch 16, batch 9600, loss[loss=0.1329, simple_loss=0.212, pruned_loss=0.02687, over 4755.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02961, over 972835.32 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:19:47,953 INFO [train.py:715] (5/8) Epoch 16, batch 9650, loss[loss=0.1173, simple_loss=0.1881, pruned_loss=0.02331, over 4800.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02953, over 973537.96 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:20:27,627 INFO [train.py:715] (5/8) Epoch 16, batch 9700, loss[loss=0.1262, simple_loss=0.1981, pruned_loss=0.02719, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.0295, over 973315.28 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:21:08,023 INFO [train.py:715] (5/8) Epoch 16, batch 9750, loss[loss=0.1361, simple_loss=0.2204, pruned_loss=0.0259, over 4770.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.0298, over 972623.88 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:21:49,085 INFO [train.py:715] (5/8) Epoch 16, batch 9800, loss[loss=0.148, simple_loss=0.2231, pruned_loss=0.03645, over 4968.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03001, over 972460.10 frames.], batch size: 31, lr: 1.39e-04
2022-05-08 16:22:29,518 INFO [train.py:715] (5/8) Epoch 16, batch 9850, loss[loss=0.1625, simple_loss=0.2296, pruned_loss=0.04773, over 4817.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03009, over 972116.52 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:23:09,308 INFO [train.py:715] (5/8) Epoch 16, batch 9900, loss[loss=0.1545, simple_loss=0.2167, pruned_loss=0.04618, over 4981.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.0302, over 971797.35 frames.], batch size: 31, lr: 1.39e-04
2022-05-08 16:23:49,494 INFO [train.py:715] (5/8) Epoch 16, batch 9950, loss[loss=0.16, simple_loss=0.2307, pruned_loss=0.04469, over 4855.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03019, over 972485.54 frames.], batch size: 34, lr: 1.39e-04
2022-05-08 16:24:30,464 INFO [train.py:715] (5/8) Epoch 16, batch 10000, loss[loss=0.1175, simple_loss=0.2006, pruned_loss=0.01724, over 4734.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02965, over 971899.56 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:25:09,396 INFO [train.py:715] (5/8) Epoch 16, batch 10050, loss[loss=0.1249, simple_loss=0.2002, pruned_loss=0.02475, over 4932.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02956, over 972691.60 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:25:49,624 INFO [train.py:715] (5/8) Epoch 16, batch 10100, loss[loss=0.1221, simple_loss=0.199, pruned_loss=0.02258, over 4973.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02974, over 972721.75 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:26:30,396 INFO [train.py:715] (5/8) Epoch 16, batch 10150, loss[loss=0.1434, simple_loss=0.2208, pruned_loss=0.03293, over 4811.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02978, over 972233.74 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:27:10,599 INFO [train.py:715] (5/8) Epoch 16, batch 10200, loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04764, over 4981.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02994, over 971980.03 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 16:27:49,590 INFO [train.py:715] (5/8) Epoch 16, batch 10250, loss[loss=0.124, simple_loss=0.1978, pruned_loss=0.02515, over 4805.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 972459.97 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:28:29,501 INFO [train.py:715] (5/8) Epoch 16, batch 10300, loss[loss=0.132, simple_loss=0.2123, pruned_loss=0.0259, over 4974.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02994, over 972993.59 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:29:09,156 INFO [train.py:715] (5/8) Epoch 16, batch 10350, loss[loss=0.1371, simple_loss=0.2075, pruned_loss=0.03339, over 4825.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.0302, over 973080.12 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 16:29:47,475 INFO [train.py:715] (5/8) Epoch 16, batch 10400, loss[loss=0.1757, simple_loss=0.2373, pruned_loss=0.05701, over 4871.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03043, over 974232.43 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:30:26,269 INFO [train.py:715] (5/8) Epoch 16, batch 10450, loss[loss=0.1382, simple_loss=0.2087, pruned_loss=0.03387, over 4834.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03005, over 973640.81 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:31:05,205 INFO [train.py:715] (5/8) Epoch 16, batch 10500, loss[loss=0.09331, simple_loss=0.1662, pruned_loss=0.01022, over 4839.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02989, over 972742.14 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:31:44,637 INFO [train.py:715] (5/8) Epoch 16, batch 10550, loss[loss=0.1595, simple_loss=0.2273, pruned_loss=0.04583, over 4697.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03022, over 972843.30 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:32:22,615 INFO [train.py:715] (5/8) Epoch 16, batch 10600, loss[loss=0.1372, simple_loss=0.2149, pruned_loss=0.02977, over 4821.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03024, over 972138.77 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 16:33:01,320 INFO [train.py:715] (5/8) Epoch 16, batch 10650, loss[loss=0.09514, simple_loss=0.1665, pruned_loss=0.01188, over 4768.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02973, over 973098.59 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:33:40,770 INFO [train.py:715] (5/8) Epoch 16, batch 10700, loss[loss=0.1194, simple_loss=0.1935, pruned_loss=0.02269, over 4814.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02992, over 972321.71 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 16:34:19,615 INFO [train.py:715] (5/8) Epoch 16, batch 10750, loss[loss=0.1459, simple_loss=0.2195, pruned_loss=0.03613, over 4768.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.0303, over 972018.00 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:34:58,503 INFO [train.py:715] (5/8) Epoch 16, batch 10800, loss[loss=0.1094, simple_loss=0.1848, pruned_loss=0.01697, over 4913.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03028, over 971738.72 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:35:37,667 INFO [train.py:715] (5/8) Epoch 16, batch 10850, loss[loss=0.1183, simple_loss=0.2038, pruned_loss=0.01635, over 4820.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2068, pruned_loss=0.03005, over 972011.04 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:36:17,326 INFO [train.py:715] (5/8) Epoch 16, batch 10900, loss[loss=0.1042, simple_loss=0.1814, pruned_loss=0.0135, over 4764.00 frames.], tot_loss[loss=0.134, simple_loss=0.2073, pruned_loss=0.03032, over 971955.47 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:36:55,551 INFO [train.py:715] (5/8) Epoch 16, batch 10950, loss[loss=0.1292, simple_loss=0.1948, pruned_loss=0.03178, over 4809.00 frames.], tot_loss[loss=0.1348, simple_loss=0.208, pruned_loss=0.0308, over 972293.79 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:37:34,521 INFO [train.py:715] (5/8) Epoch 16, batch 11000, loss[loss=0.1526, simple_loss=0.2278, pruned_loss=0.03874, over 4922.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03108, over 972648.96 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 16:38:13,975 INFO [train.py:715] (5/8) Epoch 16, batch 11050, loss[loss=0.1387, simple_loss=0.2174, pruned_loss=0.03004, over 4869.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03052, over 972704.74 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:38:55,220 INFO [train.py:715] (5/8) Epoch 16, batch 11100, loss[loss=0.125, simple_loss=0.1952, pruned_loss=0.02744, over 4843.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03034, over 972447.36 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:39:33,649 INFO [train.py:715] (5/8) Epoch 16, batch 11150, loss[loss=0.1296, simple_loss=0.2096, pruned_loss=0.02481, over 4816.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02997, over 972251.43 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 16:40:12,898 INFO [train.py:715] (5/8) Epoch 16, batch 11200, loss[loss=0.1172, simple_loss=0.1972, pruned_loss=0.01862, over 4931.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.0295, over 971984.96 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 16:40:51,683 INFO [train.py:715] (5/8) Epoch 16, batch 11250, loss[loss=0.1121, simple_loss=0.186, pruned_loss=0.01912, over 4941.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02944, over 971845.24 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 16:41:29,875 INFO [train.py:715] (5/8) Epoch 16, batch 11300, loss[loss=0.1022, simple_loss=0.1819, pruned_loss=0.01128, over 4773.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02954, over 971691.48 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:42:08,149 INFO [train.py:715] (5/8) Epoch 16, batch 11350, loss[loss=0.1223, simple_loss=0.1929, pruned_loss=0.02581, over 4841.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02989, over 972122.08 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:42:47,129 INFO [train.py:715] (5/8) Epoch 16, batch 11400, loss[loss=0.1284, simple_loss=0.2082, pruned_loss=0.02431, over 4885.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02975, over 972532.10 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:43:25,154 INFO [train.py:715] (5/8) Epoch 16, batch 11450, loss[loss=0.1304, simple_loss=0.2092, pruned_loss=0.02583, over 4825.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03037, over 973612.99 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:44:03,095 INFO [train.py:715] (5/8) Epoch 16, batch 11500, loss[loss=0.128, simple_loss=0.2102, pruned_loss=0.02288, over 4968.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03031, over 972868.21 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:44:41,776 INFO [train.py:715] (5/8) Epoch 16, batch 11550, loss[loss=0.1197, simple_loss=0.1954, pruned_loss=0.02204, over 4839.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.0298, over 972589.12 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:45:20,367 INFO [train.py:715] (5/8) Epoch 16, batch 11600, loss[loss=0.1329, simple_loss=0.2095, pruned_loss=0.02818, over 4776.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02958, over 972323.95 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:45:57,962 INFO [train.py:715] (5/8) Epoch 16, batch 11650, loss[loss=0.1423, simple_loss=0.2113, pruned_loss=0.03667, over 4975.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02947, over 972601.92 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:46:36,441 INFO [train.py:715] (5/8) Epoch 16, batch 11700, loss[loss=0.1083, simple_loss=0.1843, pruned_loss=0.01618, over 4815.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 972529.15 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:47:15,523 INFO [train.py:715] (5/8) Epoch 16, batch 11750, loss[loss=0.147, simple_loss=0.2223, pruned_loss=0.03591, over 4983.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02967, over 973334.44 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 16:47:53,673 INFO [train.py:715] (5/8) Epoch 16, batch 11800, loss[loss=0.141, simple_loss=0.2097, pruned_loss=0.03613, over 4852.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03001, over 972982.49 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:48:31,492 INFO [train.py:715] (5/8) Epoch 16, batch 11850, loss[loss=0.1168, simple_loss=0.1906, pruned_loss=0.02151, over 4810.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03035, over 973196.94 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:49:10,176 INFO [train.py:715] (5/8) Epoch 16, batch 11900, loss[loss=0.1629, simple_loss=0.2334, pruned_loss=0.04618, over 4948.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.0306, over 972537.23 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:49:48,597 INFO [train.py:715] (5/8) Epoch 16, batch 11950, loss[loss=0.1471, simple_loss=0.2249, pruned_loss=0.03462, over 4973.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03034, over 973372.71 frames.], batch size: 40, lr: 1.39e-04
2022-05-08 16:50:26,416 INFO [train.py:715] (5/8) Epoch 16, batch 12000, loss[loss=0.1325, simple_loss=0.2014, pruned_loss=0.03175, over 4808.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03035, over 972672.62 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 16:50:26,417 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 16:50:37,200 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01072, over 914524.00 frames.
2022-05-08 16:51:16,048 INFO [train.py:715] (5/8) Epoch 16, batch 12050, loss[loss=0.14, simple_loss=0.2087, pruned_loss=0.03563, over 4973.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03004, over 972841.46 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 16:51:55,270 INFO [train.py:715] (5/8) Epoch 16, batch 12100, loss[loss=0.1749, simple_loss=0.2517, pruned_loss=0.04908, over 4781.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.0301, over 972851.24 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 16:52:34,708 INFO [train.py:715] (5/8) Epoch 16, batch 12150, loss[loss=0.1326, simple_loss=0.196, pruned_loss=0.03459, over 4710.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02969, over 972287.70 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 16:53:12,373 INFO [train.py:715] (5/8) Epoch 16, batch 12200, loss[loss=0.1239, simple_loss=0.2025, pruned_loss=0.02266, over 4914.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02988, over 972557.76 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 16:53:50,654 INFO [train.py:715] (5/8) Epoch 16, batch 12250, loss[loss=0.1453, simple_loss=0.199, pruned_loss=0.04575, over 4864.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02985, over 972649.08 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 16:54:29,691 INFO [train.py:715] (5/8) Epoch 16, batch 12300, loss[loss=0.1312, simple_loss=0.212, pruned_loss=0.02523, over 4939.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02916, over 973015.00 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 16:55:08,772 INFO [train.py:715] (5/8) Epoch 16, batch 12350, loss[loss=0.1302, simple_loss=0.2035, pruned_loss=0.02846, over 4859.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02911, over 973011.50 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 16:55:47,032 INFO [train.py:715] (5/8) Epoch 16, batch 12400, loss[loss=0.1291, simple_loss=0.2072, pruned_loss=0.02547, over 4950.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02896, over 973387.38 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 16:56:26,128 INFO [train.py:715] (5/8) Epoch 16, batch 12450, loss[loss=0.1252, simple_loss=0.2072, pruned_loss=0.02154, over 4837.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02876, over 973387.67 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 16:57:05,989 INFO [train.py:715] (5/8) Epoch 16, batch 12500, loss[loss=0.1422, simple_loss=0.2082, pruned_loss=0.03804, over 4869.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02886, over 974280.34 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 16:57:44,598 INFO [train.py:715] (5/8) Epoch 16, batch 12550, loss[loss=0.1098, simple_loss=0.1822, pruned_loss=0.01865, over 4931.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 974042.36 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 16:58:23,183 INFO [train.py:715] (5/8) Epoch 16, batch 12600, loss[loss=0.1504, simple_loss=0.2259, pruned_loss=0.03747, over 4897.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02934, over 973226.67 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 16:59:01,906 INFO [train.py:715] (5/8) Epoch 16, batch 12650, loss[loss=0.1766, simple_loss=0.244, pruned_loss=0.05455, over 4963.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.03, over 972767.33 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 16:59:40,539 INFO [train.py:715] (5/8) Epoch 16, batch 12700, loss[loss=0.09688, simple_loss=0.1703, pruned_loss=0.01171, over 4782.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02939, over 973129.32 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:00:18,083 INFO [train.py:715] (5/8) Epoch 16, batch 12750, loss[loss=0.1505, simple_loss=0.2271, pruned_loss=0.03696, over 4810.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02966, over 973167.80 frames.], batch size: 26, lr: 1.38e-04
2022-05-08 17:00:57,706 INFO [train.py:715] (5/8) Epoch 16, batch 12800, loss[loss=0.1261, simple_loss=0.1994, pruned_loss=0.02638, over 4988.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02942, over 972908.55 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:01:36,687 INFO [train.py:715] (5/8) Epoch 16, batch 12850, loss[loss=0.1146, simple_loss=0.1906, pruned_loss=0.01925, over 4796.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02994, over 972766.39 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:02:15,046 INFO [train.py:715] (5/8) Epoch 16, batch 12900, loss[loss=0.1351, simple_loss=0.2115, pruned_loss=0.02939, over 4883.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 973104.91 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:02:53,759 INFO [train.py:715] (5/8) Epoch 16, batch 12950, loss[loss=0.1588, simple_loss=0.2331, pruned_loss=0.04224, over 4923.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03013, over 973035.60 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 17:03:32,778 INFO [train.py:715] (5/8) Epoch 16, batch 13000, loss[loss=0.1316, simple_loss=0.2193, pruned_loss=0.02193, over 4855.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02989, over 972824.50 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:04:11,282 INFO [train.py:715] (5/8) Epoch 16, batch 13050, loss[loss=0.1342, simple_loss=0.2002, pruned_loss=0.03405, over 4874.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02968, over 973423.06 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:04:49,802 INFO [train.py:715] (5/8) Epoch 16, batch 13100, loss[loss=0.1316, simple_loss=0.2105, pruned_loss=0.02633, over 4986.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02981, over 973018.02 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:05:28,954 INFO [train.py:715] (5/8) Epoch 16, batch 13150, loss[loss=0.1379, simple_loss=0.198, pruned_loss=0.03887, over 4982.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02961, over 972985.97 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:06:08,077 INFO [train.py:715] (5/8) Epoch 16, batch 13200, loss[loss=0.1273, simple_loss=0.2071, pruned_loss=0.02376, over 4798.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 973329.50 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:06:46,154 INFO [train.py:715] (5/8) Epoch 16, batch 13250, loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04088, over 4865.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02938, over 972871.70 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:07:25,007 INFO [train.py:715] (5/8) Epoch 16, batch 13300, loss[loss=0.1612, simple_loss=0.2268, pruned_loss=0.04778, over 4879.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.0292, over 973266.45 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:08:04,361 INFO [train.py:715] (5/8) Epoch 16, batch 13350, loss[loss=0.1385, simple_loss=0.2213, pruned_loss=0.02785, over 4893.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02927, over 973019.97 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 17:08:42,684 INFO [train.py:715] (5/8) Epoch 16, batch 13400, loss[loss=0.1389, simple_loss=0.2186, pruned_loss=0.0296, over 4817.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02955, over 972543.24 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:09:21,147 INFO [train.py:715] (5/8) Epoch 16, batch 13450, loss[loss=0.1284, simple_loss=0.2072, pruned_loss=0.02479, over 4806.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02944, over 973034.93 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:10:00,909 INFO [train.py:715] (5/8) Epoch 16, batch 13500, loss[loss=0.1557, simple_loss=0.2325, pruned_loss=0.03945, over 4947.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02941, over 973615.47 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:10:39,240 INFO [train.py:715] (5/8) Epoch 16, batch 13550, loss[loss=0.1174, simple_loss=0.1975, pruned_loss=0.01862, over 4906.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02906, over 973395.63 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:11:17,353 INFO [train.py:715] (5/8) Epoch 16, batch 13600, loss[loss=0.1259, simple_loss=0.2037, pruned_loss=0.02402, over 4971.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02908, over 973538.75 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:11:56,187 INFO [train.py:715] (5/8) Epoch 16, batch 13650, loss[loss=0.1476, simple_loss=0.2214, pruned_loss=0.0369, over 4784.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02905, over 972403.10 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:12:35,111 INFO [train.py:715] (5/8) Epoch 16, batch 13700, loss[loss=0.162, simple_loss=0.235, pruned_loss=0.04449, over 4766.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02924, over 971703.20 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:13:13,502 INFO [train.py:715] (5/8) Epoch 16, batch 13750, loss[loss=0.1254, simple_loss=0.2099, pruned_loss=0.02043, over 4913.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02874, over 971792.22 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 17:13:52,014 INFO [train.py:715] (5/8) Epoch 16, batch 13800, loss[loss=0.1354, simple_loss=0.2076, pruned_loss=0.03164, over 4907.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02849, over 971133.89 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:14:30,651 INFO [train.py:715] (5/8) Epoch 16, batch 13850, loss[loss=0.1379, simple_loss=0.2033, pruned_loss=0.03625, over 4872.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02895, over 971362.59 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:15:08,623 INFO [train.py:715] (5/8) Epoch 16, batch 13900, loss[loss=0.1314, simple_loss=0.2199, pruned_loss=0.02151, over 4980.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02844, over 972001.19 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:15:46,310 INFO [train.py:715] (5/8) Epoch 16, batch 13950, loss[loss=0.1507, simple_loss=0.2309, pruned_loss=0.03522, over 4981.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02885, over 971125.64 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:16:24,662 INFO [train.py:715] (5/8) Epoch 16, batch 14000, loss[loss=0.1565, simple_loss=0.2287, pruned_loss=0.04214, over 4933.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 970761.42 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 17:17:03,283 INFO [train.py:715] (5/8) Epoch 16, batch 14050, loss[loss=0.1612, simple_loss=0.2284, pruned_loss=0.04699, over 4912.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 970286.26 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:17:41,057 INFO [train.py:715] (5/8) Epoch 16, batch 14100, loss[loss=0.1239, simple_loss=0.2047, pruned_loss=0.02162, over 4860.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02974, over 969990.63 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:18:18,777 INFO [train.py:715] (5/8) Epoch 16, batch 14150, loss[loss=0.1282, simple_loss=0.2038, pruned_loss=0.02626, over 4979.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02974, over 970871.61 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:18:57,315 INFO [train.py:715] (5/8) Epoch 16, batch 14200, loss[loss=0.1206, simple_loss=0.1997, pruned_loss=0.02073, over 4641.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02952, over 970628.90 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:19:36,008 INFO [train.py:715] (5/8) Epoch 16, batch 14250, loss[loss=0.1374, simple_loss=0.2276, pruned_loss=0.02365, over 4938.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02919, over 971530.12 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:20:14,629 INFO [train.py:715] (5/8) Epoch 16, batch 14300, loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03682, over 4817.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.0292, over 972410.64 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:20:53,332 INFO [train.py:715] (5/8) Epoch 16, batch 14350, loss[loss=0.1295, simple_loss=0.1986, pruned_loss=0.03019, over 4693.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02933, over 972053.88 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:21:32,525 INFO [train.py:715] (5/8) Epoch 16, batch 14400, loss[loss=0.1207, simple_loss=0.1887, pruned_loss=0.02634, over 4781.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.0291, over 971934.10 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:22:10,261 INFO [train.py:715] (5/8) Epoch 16, batch 14450, loss[loss=0.1248, simple_loss=0.2015, pruned_loss=0.02402, over 4976.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02886, over 971304.26 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 17:22:49,090 INFO [train.py:715] (5/8) Epoch 16, batch 14500, loss[loss=0.1282, simple_loss=0.2118, pruned_loss=0.02235, over 4799.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02949, over 971953.09 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:23:28,026 INFO [train.py:715] (5/8) Epoch 16, batch 14550, loss[loss=0.1317, simple_loss=0.2035, pruned_loss=0.02992, over 4916.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02927, over 971894.68 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 17:24:06,693 INFO [train.py:715] (5/8) Epoch 16, batch 14600, loss[loss=0.1035, simple_loss=0.1713, pruned_loss=0.01786, over 4795.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.0293, over 971932.00 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:24:44,964 INFO [train.py:715] (5/8) Epoch 16, batch 14650, loss[loss=0.1501, simple_loss=0.2187, pruned_loss=0.04069, over 4801.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03001, over 972380.34 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:25:23,541 INFO [train.py:715] (5/8) Epoch 16, batch 14700, loss[loss=0.1277, simple_loss=0.2019, pruned_loss=0.02674, over 4812.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03014, over 972349.62 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:26:02,839 INFO [train.py:715] (5/8) Epoch 16, batch 14750, loss[loss=0.1019, simple_loss=0.1799, pruned_loss=0.012, over 4772.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02997, over 971436.85 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:26:40,633 INFO [train.py:715] (5/8) Epoch 16, batch 14800, loss[loss=0.1292, simple_loss=0.1991, pruned_loss=0.02962, over 4860.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03017, over 971766.89 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:27:19,708 INFO [train.py:715] (5/8) Epoch 16, batch 14850, loss[loss=0.1275, simple_loss=0.1992, pruned_loss=0.02787, over 4871.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03016, over 972106.02 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:27:58,605 INFO [train.py:715] (5/8) Epoch 16, batch 14900, loss[loss=0.1602, simple_loss=0.2288, pruned_loss=0.04583, over 4741.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 972104.20 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:28:37,058 INFO [train.py:715] (5/8) Epoch 16, batch 14950, loss[loss=0.1388, simple_loss=0.2091, pruned_loss=0.03423, over 4905.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02998, over 972238.48 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:29:16,116 INFO [train.py:715] (5/8) Epoch 16, batch 15000, loss[loss=0.2005, simple_loss=0.2616, pruned_loss=0.06972, over 4976.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03025, over 972167.26 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:29:16,117 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 17:29:25,725 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01069, over 914524.00 frames.
2022-05-08 17:30:03,999 INFO [train.py:715] (5/8) Epoch 16, batch 15050, loss[loss=0.1328, simple_loss=0.2254, pruned_loss=0.02009, over 4982.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03018, over 972508.44 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:30:42,064 INFO [train.py:715] (5/8) Epoch 16, batch 15100, loss[loss=0.1574, simple_loss=0.2294, pruned_loss=0.04264, over 4784.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03016, over 972582.54 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:31:20,869 INFO [train.py:715] (5/8) Epoch 16, batch 15150, loss[loss=0.1292, simple_loss=0.1997, pruned_loss=0.02939, over 4836.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03011, over 971986.14 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:31:58,565 INFO [train.py:715] (5/8) Epoch 16, batch 15200, loss[loss=0.1476, simple_loss=0.2388, pruned_loss=0.02818, over 4749.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03009, over 971675.79 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:32:36,118 INFO [train.py:715] (5/8) Epoch 16, batch 15250, loss[loss=0.1427, simple_loss=0.2047, pruned_loss=0.0404, over 4782.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02978, over 970766.70 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:33:14,310 INFO [train.py:715] (5/8) Epoch 16, batch 15300, loss[loss=0.1298, simple_loss=0.1957, pruned_loss=0.03197, over 4790.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03032, over 970616.98 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:33:52,456 INFO [train.py:715] (5/8) Epoch 16, batch 15350, loss[loss=0.1227, simple_loss=0.198, pruned_loss=0.02368, over 4688.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 970527.16 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:34:30,725 INFO [train.py:715] (5/8) Epoch 16, batch 15400, loss[loss=0.1333, simple_loss=0.2038, pruned_loss=0.03143, over 4983.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03067, over 971330.39 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:35:08,739 INFO [train.py:715] (5/8) Epoch 16, batch 15450, loss[loss=0.1254, simple_loss=0.2015, pruned_loss=0.02461, over 4758.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02991, over 971099.72 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:35:47,170 INFO [train.py:715] (5/8) Epoch 16, batch 15500, loss[loss=0.1437, simple_loss=0.2202, pruned_loss=0.03357, over 4812.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02937, over 971426.03 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:36:24,800 INFO [train.py:715] (5/8) Epoch 16, batch 15550, loss[loss=0.1404, simple_loss=0.2157, pruned_loss=0.03253, over 4932.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02929, over 971814.38 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:37:02,467 INFO [train.py:715] (5/8) Epoch 16, batch 15600, loss[loss=0.1108, simple_loss=0.1901, pruned_loss=0.01573, over 4989.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02902, over 971227.02 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:37:41,084 INFO [train.py:715] (5/8) Epoch 16, batch 15650, loss[loss=0.1268, simple_loss=0.2012, pruned_loss=0.0262, over 4980.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02901, over 970724.54 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:38:19,117 INFO [train.py:715] (5/8) Epoch 16, batch 15700, loss[loss=0.1603, simple_loss=0.2279, pruned_loss=0.04635, over 4875.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02926, over 970669.92 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:38:56,852 INFO [train.py:715] (5/8) Epoch 16, batch 15750, loss[loss=0.1415, simple_loss=0.2032, pruned_loss=0.03993, over 4846.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.0294, over 971500.50 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:39:34,742 INFO [train.py:715] (5/8) Epoch 16, batch 15800, loss[loss=0.1371, simple_loss=0.2094, pruned_loss=0.03242, over 4688.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02982, over 971670.72 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:40:13,085 INFO [train.py:715] (5/8) Epoch 16, batch 15850, loss[loss=0.1291, simple_loss=0.2087, pruned_loss=0.02468, over 4938.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02989, over 971760.39 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:40:50,712 INFO [train.py:715] (5/8) Epoch 16, batch 15900, loss[loss=0.1528, simple_loss=0.2281, pruned_loss=0.03873, over 4968.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02945, over 971890.15 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:41:28,316 INFO [train.py:715] (5/8) Epoch 16, batch 15950, loss[loss=0.1727, simple_loss=0.2419, pruned_loss=0.05174, over 4923.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02976, over 972013.25 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:42:06,730 INFO [train.py:715] (5/8) Epoch 16, batch 16000, loss[loss=0.1448, simple_loss=0.213, pruned_loss=0.0383, over 4775.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02963, over 972242.26 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:42:44,835 INFO [train.py:715] (5/8) Epoch 16, batch 16050, loss[loss=0.123, simple_loss=0.1986, pruned_loss=0.02366, over 4976.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02953, over 972710.06 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:43:22,461 INFO [train.py:715] (5/8) Epoch 16, batch 16100, loss[loss=0.1413, simple_loss=0.2129, pruned_loss=0.03487, over 4790.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02966, over 972766.41 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:43:59,972 INFO [train.py:715] (5/8) Epoch 16, batch 16150, loss[loss=0.1301, simple_loss=0.2126, pruned_loss=0.02383, over 4693.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02953, over 972091.69 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:44:38,351 INFO [train.py:715] (5/8) Epoch 16, batch 16200, loss[loss=0.1036, simple_loss=0.1762, pruned_loss=0.01554, over 4811.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02938, over 971108.04 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:45:15,917 INFO [train.py:715] (5/8) Epoch 16, batch 16250, loss[loss=0.1307, simple_loss=0.2097, pruned_loss=0.02585, over 4825.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02972, over 971029.95 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:45:53,547 INFO [train.py:715] (5/8) Epoch 16, batch 16300, loss[loss=0.1439, simple_loss=0.2171, pruned_loss=0.03531, over 4847.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02948, over 971144.43 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:46:31,874 INFO [train.py:715] (5/8) Epoch 16, batch 16350, loss[loss=0.1515, simple_loss=0.2315, pruned_loss=0.03576, over 4834.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02964, over 971819.02 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:47:10,532 INFO [train.py:715] (5/8) Epoch 16, batch 16400, loss[loss=0.1682, simple_loss=0.2432, pruned_loss=0.0466, over 4799.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03036, over 970973.17 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:47:47,571 INFO [train.py:715] (5/8) Epoch 16, batch 16450, loss[loss=0.1282, simple_loss=0.2027, pruned_loss=0.02683, over 4794.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.0304, over 971377.29 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:48:25,521 INFO [train.py:715] (5/8) Epoch 16, batch 16500, loss[loss=0.1151, simple_loss=0.1965, pruned_loss=0.01691, over 4864.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.0302, over 971735.83 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:49:04,093 INFO [train.py:715] (5/8) Epoch 16, batch 16550, loss[loss=0.1376, simple_loss=0.2158, pruned_loss=0.02971, over 4694.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03027, over 971871.92 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:49:41,516 INFO [train.py:715] (5/8) Epoch 16, batch 16600, loss[loss=0.1255, simple_loss=0.2077, pruned_loss=0.02166, over 4926.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02995, over 972396.84 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:50:19,533 INFO [train.py:715] (5/8) Epoch 16, batch 16650, loss[loss=0.1589, simple_loss=0.2436, pruned_loss=0.03712, over 4899.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02994, over 972076.05 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:50:57,796 INFO [train.py:715] (5/8) Epoch 16, batch 16700, loss[loss=0.1611, simple_loss=0.2364, pruned_loss=0.04288, over 4695.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02989, over 972292.98 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:51:35,938 INFO [train.py:715] (5/8) Epoch 16, batch 16750, loss[loss=0.1494, simple_loss=0.229, pruned_loss=0.03488, over 4905.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02994, over 972100.87 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:52:13,454 INFO [train.py:715] (5/8) Epoch 16, batch 16800, loss[loss=0.1416, simple_loss=0.2061, pruned_loss=0.03855, over 4782.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02986, over 972342.03 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:52:51,537 INFO [train.py:715] (5/8) Epoch 16, batch 16850, loss[loss=0.1326, simple_loss=0.203, pruned_loss=0.0311, over 4855.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03017, over 972579.03 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:53:30,000 INFO [train.py:715] (5/8) Epoch 16, batch 16900, loss[loss=0.1555, simple_loss=0.2262, pruned_loss=0.04238, over 4848.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03104, over 972583.11 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:54:07,591 INFO [train.py:715] (5/8) Epoch 16, batch 16950, loss[loss=0.1758, simple_loss=0.2538, pruned_loss=0.04887, over 4828.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03117, over 972337.48 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:54:45,477 INFO [train.py:715] (5/8) Epoch 16, batch 17000, loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03306, over 4771.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03082, over 972749.00 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:55:23,674 INFO [train.py:715] (5/8) Epoch 16, batch 17050, loss[loss=0.1202, simple_loss=0.1967, pruned_loss=0.0218, over 4987.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.0303, over 972864.27 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:56:02,257 INFO [train.py:715] (5/8) Epoch 16, batch 17100, loss[loss=0.134, simple_loss=0.2072, pruned_loss=0.03045, over 4837.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03006, over 973288.82 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:56:39,333 INFO [train.py:715] (5/8) Epoch 16, batch 17150, loss[loss=0.152, simple_loss=0.2322, pruned_loss=0.03589, over 4969.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02992, over 973074.22 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 17:57:17,464 INFO [train.py:715] (5/8) Epoch 16, batch 17200, loss[loss=0.1489, simple_loss=0.2053, pruned_loss=0.04623, over 4849.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02977, over 972454.46 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:57:56,362 INFO [train.py:715] (5/8) Epoch 16, batch 17250, loss[loss=0.1099, simple_loss=0.1833, pruned_loss=0.01827, over 4792.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 972371.96 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:58:33,738 INFO [train.py:715] (5/8) Epoch 16, batch 17300, loss[loss=0.1073, simple_loss=0.1812, pruned_loss=0.0167, over 4773.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02948, over 972572.63 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:59:11,267 INFO [train.py:715] (5/8) Epoch 16, batch 17350, loss[loss=0.154, simple_loss=0.23, pruned_loss=0.03904, over 4853.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02979, over 972496.81 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 17:59:49,077 INFO [train.py:715] (5/8) Epoch 16, batch 17400, loss[loss=0.1267, simple_loss=0.1987, pruned_loss=0.02738, over 4957.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02944, over 972416.57 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:00:27,744 INFO [train.py:715] (5/8) Epoch 16, batch 17450, loss[loss=0.1273, simple_loss=0.1981, pruned_loss=0.02827, over 4965.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02954, over 972836.05 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:01:04,507 INFO [train.py:715] (5/8) Epoch 16, batch 17500, loss[loss=0.1131, simple_loss=0.187, pruned_loss=0.01956, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02986, over 972957.53 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:01:42,654 INFO [train.py:715] (5/8) Epoch 16, batch 17550, loss[loss=0.1197, simple_loss=0.1978, pruned_loss=0.02078, over 4852.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03016, over 971930.46 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 18:02:21,341 INFO [train.py:715] (5/8) Epoch 16, batch 17600, loss[loss=0.1078, simple_loss=0.1739, pruned_loss=0.02088, over 4799.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.0302, over 972186.91 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:02:58,693 INFO [train.py:715] (5/8) Epoch 16, batch 17650, loss[loss=0.1336, simple_loss=0.2064, pruned_loss=0.03039, over 4976.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03035, over 972445.67 frames.], batch size: 31, lr: 1.38e-04
2022-05-08 18:03:36,637 INFO [train.py:715] (5/8) Epoch 16, batch 17700, loss[loss=0.1153, simple_loss=0.196, pruned_loss=0.01737, over 4935.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03007, over 972407.31 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 18:04:15,005 INFO [train.py:715] (5/8) Epoch 16, batch 17750, loss[loss=0.134, simple_loss=0.2066, pruned_loss=0.03071, over 4914.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02948, over 971952.10 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:04:53,068 INFO [train.py:715] (5/8) Epoch 16, batch 17800, loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.03331, over 4753.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02944, over 971604.19 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:05:30,279 INFO [train.py:715] (5/8) Epoch 16, batch 17850, loss[loss=0.1083, simple_loss=0.1834, pruned_loss=0.01659, over 4889.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02939, over 972413.20 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:06:08,450 INFO [train.py:715] (5/8) Epoch 16, batch 17900, loss[loss=0.1289, simple_loss=0.1941, pruned_loss=0.03181, over 4985.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02968, over 972606.49 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:06:46,891 INFO [train.py:715] (5/8) Epoch 16, batch 17950, loss[loss=0.1255, simple_loss=0.2017, pruned_loss=0.02461, over 4908.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02938, over 973173.88 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:07:24,274 INFO [train.py:715] (5/8) Epoch 16, batch 18000, loss[loss=0.1243, simple_loss=0.2105, pruned_loss=0.0191, over 4692.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02976, over 972343.59 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:07:24,275 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 18:07:33,811 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01082, over 914524.00 frames.
2022-05-08 18:08:11,767 INFO [train.py:715] (5/8) Epoch 16, batch 18050, loss[loss=0.1387, simple_loss=0.2194, pruned_loss=0.02903, over 4872.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02963, over 972157.47 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:08:50,178 INFO [train.py:715] (5/8) Epoch 16, batch 18100, loss[loss=0.132, simple_loss=0.2056, pruned_loss=0.02917, over 4862.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03003, over 972141.02 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 18:09:28,824 INFO [train.py:715] (5/8) Epoch 16, batch 18150, loss[loss=0.1297, simple_loss=0.2091, pruned_loss=0.02514, over 4976.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 972039.12 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:10:07,472 INFO [train.py:715] (5/8) Epoch 16, batch 18200, loss[loss=0.1326, simple_loss=0.2051, pruned_loss=0.03002, over 4777.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02953, over 972397.12 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:10:45,083 INFO [train.py:715] (5/8) Epoch 16, batch 18250, loss[loss=0.1236, simple_loss=0.1932, pruned_loss=0.02697, over 4977.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02957, over 971720.50 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:11:23,845 INFO [train.py:715] (5/8) Epoch 16, batch 18300, loss[loss=0.165, simple_loss=0.2331, pruned_loss=0.0484, over 4903.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02979, over 971402.68 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:12:02,947 INFO [train.py:715] (5/8) Epoch 16, batch 18350, loss[loss=0.1433, simple_loss=0.2122, pruned_loss=0.0372, over 4870.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02976, over 971467.93 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:12:40,719 INFO [train.py:715] (5/8) Epoch 16, batch 18400, loss[loss=0.162, simple_loss=0.2431, pruned_loss=0.04043, over 4758.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 971841.79 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:13:19,244 INFO [train.py:715] (5/8) Epoch 16, batch 18450, loss[loss=0.1168, simple_loss=0.1894, pruned_loss=0.02214, over 4969.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03027, over 971502.56 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 18:13:57,851 INFO [train.py:715] (5/8) Epoch 16, batch 18500, loss[loss=0.1278, simple_loss=0.2027, pruned_loss=0.02645, over 4682.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03003, over 971889.91 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:14:36,372 INFO [train.py:715] (5/8) Epoch 16, batch 18550, loss[loss=0.1204, simple_loss=0.1938, pruned_loss=0.0235, over 4924.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03038, over 972088.71 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:15:13,856 INFO [train.py:715] (5/8) Epoch 16, batch 18600, loss[loss=0.1093, simple_loss=0.1853, pruned_loss=0.01664, over 4783.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03036, over 971648.37 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:15:52,139 INFO [train.py:715] (5/8) Epoch 16, batch 18650, loss[loss=0.1254, simple_loss=0.1964, pruned_loss=0.0272, over 4975.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03004, over 971425.61 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:16:30,642 INFO [train.py:715] (5/8) Epoch 16, batch 18700, loss[loss=0.1062, simple_loss=0.1774, pruned_loss=0.01747, over 4826.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02983, over 972720.48 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 18:17:08,139 INFO [train.py:715] (5/8) Epoch 16, batch 18750, loss[loss=0.1081, simple_loss=0.195, pruned_loss=0.01054, over 4823.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02936, over 972437.45 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:17:45,513 INFO [train.py:715] (5/8) Epoch 16, batch 18800, loss[loss=0.147, simple_loss=0.2165, pruned_loss=0.03876, over 4985.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.0295, over 973366.50 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 18:18:23,822 INFO [train.py:715] (5/8) Epoch 16, batch 18850, loss[loss=0.1256, simple_loss=0.2049, pruned_loss=0.0232, over 4741.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02972, over 973439.16 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:19:02,092 INFO [train.py:715] (5/8) Epoch 16, batch 18900, loss[loss=0.1194, simple_loss=0.1981, pruned_loss=0.02035, over 4804.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02971, over 973118.32 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 18:19:39,524 INFO [train.py:715] (5/8) Epoch 16, batch 18950, loss[loss=0.154, simple_loss=0.2231, pruned_loss=0.04243, over 4762.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02921, over 973631.32 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:20:17,360 INFO [train.py:715] (5/8) Epoch 16, batch 19000, loss[loss=0.1482, simple_loss=0.223, pruned_loss=0.03668, over 4944.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.0295, over 972750.25 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:20:55,965 INFO [train.py:715] (5/8) Epoch 16, batch 19050, loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.0415, over 4974.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02988, over 973098.57 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:21:36,428 INFO [train.py:715] (5/8) Epoch 16, batch 19100, loss[loss=0.1068, simple_loss=0.1843, pruned_loss=0.01462, over 4970.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02953, over 972180.48 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 18:22:14,090 INFO [train.py:715] (5/8) Epoch 16, batch 19150, loss[loss=0.1367, simple_loss=0.2226, pruned_loss=0.0254, over 4882.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02982, over 971723.78 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 18:22:52,369 INFO [train.py:715] (5/8) Epoch 16, batch 19200, loss[loss=0.1426, simple_loss=0.2093, pruned_loss=0.03797, over 4768.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02958, over 970831.32 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:23:31,020 INFO [train.py:715] (5/8) Epoch 16, batch 19250, loss[loss=0.1309, simple_loss=0.21, pruned_loss=0.02593, over 4949.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.0296, over 970082.99 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:24:08,555 INFO [train.py:715] (5/8) Epoch 16, batch 19300, loss[loss=0.1068, simple_loss=0.1787, pruned_loss=0.01742, over 4772.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.0297, over 971033.19 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:24:46,583 INFO [train.py:715] (5/8) Epoch 16, batch 19350, loss[loss=0.1189, simple_loss=0.202, pruned_loss=0.01783, over 4957.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 971285.35 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 18:25:25,228 INFO [train.py:715] (5/8) Epoch 16, batch 19400, loss[loss=0.1325, simple_loss=0.2102, pruned_loss=0.02737, over 4775.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03036, over 970957.59 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:26:03,260 INFO [train.py:715] (5/8) Epoch 16, batch 19450, loss[loss=0.1379, simple_loss=0.2026, pruned_loss=0.0366, over 4974.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03001, over 971916.27 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:26:40,799 INFO [train.py:715] (5/8) Epoch 16, batch 19500, loss[loss=0.1635, simple_loss=0.2407, pruned_loss=0.04317, over 4932.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03054, over 972148.60 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 18:27:18,959 INFO [train.py:715] (5/8) Epoch 16, batch 19550, loss[loss=0.1412, simple_loss=0.2149, pruned_loss=0.03374, over 4779.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03022, over 971661.74 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:27:57,192 INFO [train.py:715] (5/8) Epoch 16, batch 19600, loss[loss=0.1541, simple_loss=0.2293, pruned_loss=0.03941, over 4941.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03022, over 972677.28 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 18:28:34,601 INFO [train.py:715] (5/8) Epoch 16, batch 19650, loss[loss=0.1495, simple_loss=0.218, pruned_loss=0.04051, over 4919.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03004, over 972416.68 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:29:12,876 INFO [train.py:715] (5/8) Epoch 16, batch 19700, loss[loss=0.1134, simple_loss=0.1842, pruned_loss=0.02126, over 4961.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02964, over 972915.40 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:29:51,092 INFO [train.py:715] (5/8) Epoch 16, batch 19750, loss[loss=0.1271, simple_loss=0.2019, pruned_loss=0.02618, over 4788.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02974, over 973240.15 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:30:28,918 INFO [train.py:715] (5/8) Epoch 16, batch 19800, loss[loss=0.1175, simple_loss=0.1957, pruned_loss=0.01966, over 4967.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02989, over 972796.49 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 18:31:06,637 INFO [train.py:715] (5/8) Epoch 16, batch 19850, loss[loss=0.1314, simple_loss=0.2028, pruned_loss=0.03003, over 4843.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03019, over 971427.59 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 18:31:44,946 INFO [train.py:715] (5/8) Epoch 16, batch 19900, loss[loss=0.1589, simple_loss=0.2285, pruned_loss=0.0447, over 4884.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03003, over 971836.36 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 18:32:22,972 INFO [train.py:715] (5/8) Epoch 16, batch 19950, loss[loss=0.1122, simple_loss=0.1794, pruned_loss=0.0225, over 4865.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2078, pruned_loss=0.03057, over 972450.75 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 18:33:00,614 INFO [train.py:715] (5/8) Epoch 16, batch 20000, loss[loss=0.1209, simple_loss=0.2045, pruned_loss=0.01867, over 4923.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03047, over 973355.89 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 18:33:38,892 INFO [train.py:715] (5/8) Epoch 16, batch 20050, loss[loss=0.1069, simple_loss=0.1838, pruned_loss=0.01501, over 4777.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03012, over 973212.28 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:34:17,307 INFO [train.py:715] (5/8) Epoch 16, batch 20100, loss[loss=0.1335, simple_loss=0.216, pruned_loss=0.02551, over 4882.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 974047.64 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 18:34:54,669 INFO [train.py:715] (5/8) Epoch 16, batch 20150, loss[loss=0.1384, simple_loss=0.2239, pruned_loss=0.02648, over 4708.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 972638.21 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:35:32,577 INFO [train.py:715] (5/8) Epoch 16, batch 20200, loss[loss=0.156, simple_loss=0.2302, pruned_loss=0.04092, over 4913.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03021, over 972749.76 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:36:10,897 INFO [train.py:715] (5/8) Epoch 16, batch 20250, loss[loss=0.1367, simple_loss=0.2119, pruned_loss=0.03077, over 4812.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02992, over 972507.34 frames.], batch size: 27, lr: 1.38e-04
2022-05-08 18:36:49,192 INFO [train.py:715] (5/8) Epoch 16, batch 20300, loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03464, over 4912.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02959, over 972397.34 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:37:27,016 INFO [train.py:715] (5/8) Epoch 16, batch 20350, loss[loss=0.1158, simple_loss=0.1945, pruned_loss=0.01855, over 4781.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02954, over 972194.86 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:38:05,174 INFO [train.py:715] (5/8) Epoch 16, batch 20400, loss[loss=0.1622, simple_loss=0.2389, pruned_loss=0.04274, over 4784.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2078, pruned_loss=0.03037, over 972487.82 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 18:38:43,165 INFO [train.py:715] (5/8) Epoch 16, batch 20450, loss[loss=0.128, simple_loss=0.21, pruned_loss=0.02302, over 4769.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02994, over 971720.88 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 18:39:21,071 INFO [train.py:715] (5/8) Epoch 16, batch 20500, loss[loss=0.1072, simple_loss=0.183, pruned_loss=0.01573, over 4888.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.0297, over 971239.10 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 18:39:58,716 INFO [train.py:715] (5/8) Epoch 16, batch 20550, loss[loss=0.1316, simple_loss=0.2088, pruned_loss=0.02724, over 4956.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03015, over 971784.10 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 18:40:37,507 INFO [train.py:715] (5/8) Epoch 16, batch 20600, loss[loss=0.1476, simple_loss=0.2299, pruned_loss=0.03266, over 4763.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03057, over 972411.53 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 18:41:15,474 INFO [train.py:715] (5/8) Epoch 16, batch 20650, loss[loss=0.1143, simple_loss=0.1867, pruned_loss=0.02094, over 4880.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03043, over 972432.68 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 18:41:52,934 INFO [train.py:715] (5/8) Epoch 16, batch 20700, loss[loss=0.1195, simple_loss=0.1869, pruned_loss=0.0261, over 4800.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03005, over 972314.58 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 18:42:31,440 INFO [train.py:715] (5/8) Epoch 16, batch 20750, loss[loss=0.1226, simple_loss=0.1933, pruned_loss=0.02596, over 4943.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02988, over 972588.11 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 18:43:09,457 INFO [train.py:715] (5/8) Epoch 16, batch 20800, loss[loss=0.116, simple_loss=0.1926, pruned_loss=0.01966, over 4849.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 972536.38 frames.], batch size: 34, lr: 1.37e-04
2022-05-08 18:43:47,990 INFO [train.py:715] (5/8) Epoch 16, batch 20850, loss[loss=0.1318, simple_loss=0.2075, pruned_loss=0.02802, over 4918.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03068, over 972285.94 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 18:44:25,953 INFO [train.py:715] (5/8) Epoch 16, batch 20900, loss[loss=0.1252, simple_loss=0.1964, pruned_loss=0.02704, over 4856.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03027, over 972614.26 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 18:45:05,225 INFO [train.py:715] (5/8) Epoch 16, batch 20950, loss[loss=0.138, simple_loss=0.2254, pruned_loss=0.02531, over 4830.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03039, over 972761.66 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:45:43,430 INFO [train.py:715] (5/8) Epoch 16, batch 21000, loss[loss=0.1263, simple_loss=0.2025, pruned_loss=0.02508, over 4911.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03021, over 972128.57 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 18:45:43,431 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 18:45:53,027 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.0106, over 914524.00 frames.
2022-05-08 18:46:31,913 INFO [train.py:715] (5/8) Epoch 16, batch 21050, loss[loss=0.145, simple_loss=0.221, pruned_loss=0.03454, over 4754.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03037, over 972359.46 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 18:47:10,474 INFO [train.py:715] (5/8) Epoch 16, batch 21100, loss[loss=0.1418, simple_loss=0.221, pruned_loss=0.03132, over 4810.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.0304, over 972265.60 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 18:47:49,071 INFO [train.py:715] (5/8) Epoch 16, batch 21150, loss[loss=0.1293, simple_loss=0.1973, pruned_loss=0.03061, over 4903.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03025, over 972756.35 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 18:48:27,790 INFO [train.py:715] (5/8) Epoch 16, batch 21200, loss[loss=0.135, simple_loss=0.2187, pruned_loss=0.02564, over 4775.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03041, over 972940.35 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:49:06,847 INFO [train.py:715] (5/8) Epoch 16, batch 21250, loss[loss=0.1289, simple_loss=0.2122, pruned_loss=0.02277, over 4918.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03027, over 972272.11 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 18:49:44,920 INFO [train.py:715] (5/8) Epoch 16, batch 21300, loss[loss=0.1301, simple_loss=0.2071, pruned_loss=0.02651, over 4752.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03013, over 972753.74 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 18:50:23,523 INFO [train.py:715] (5/8) Epoch 16, batch 21350, loss[loss=0.1345, simple_loss=0.2138, pruned_loss=0.02759, over 4882.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.0298, over 972614.90 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 18:51:01,536 INFO [train.py:715] (5/8) Epoch 16, batch 21400, loss[loss=0.1233, simple_loss=0.1979, pruned_loss=0.02442, over 4786.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 971958.00 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 18:51:39,055 INFO [train.py:715] (5/8) Epoch 16, batch 21450, loss[loss=0.1234, simple_loss=0.1891, pruned_loss=0.02881, over 4938.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02934, over 971809.95 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 18:52:17,450 INFO [train.py:715] (5/8) Epoch 16, batch 21500, loss[loss=0.1524, simple_loss=0.2237, pruned_loss=0.04055, over 4861.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02899, over 971608.42 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 18:52:55,413 INFO [train.py:715] (5/8) Epoch 16, batch 21550, loss[loss=0.1171, simple_loss=0.1935, pruned_loss=0.02032, over 4690.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02872, over 971053.86 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:53:33,004 INFO [train.py:715] (5/8) Epoch 16, batch 21600, loss[loss=0.1301, simple_loss=0.2198, pruned_loss=0.02022, over 4843.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02875, over 971819.50 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 18:54:11,337 INFO [train.py:715] (5/8) Epoch 16, batch 21650, loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03373, over 4989.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 972258.54 frames.], batch size: 31, lr: 1.37e-04
2022-05-08 18:54:49,122 INFO [train.py:715] (5/8) Epoch 16, batch 21700, loss[loss=0.1511, simple_loss=0.2128, pruned_loss=0.04474, over 4974.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 972445.77 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:55:27,323 INFO [train.py:715] (5/8) Epoch 16, batch 21750, loss[loss=0.1341, simple_loss=0.2057, pruned_loss=0.03126, over 4791.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02989, over 972327.95 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:56:04,819 INFO [train.py:715] (5/8) Epoch 16, batch 21800, loss[loss=0.1261, simple_loss=0.2104, pruned_loss=0.0209, over 4966.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03034, over 972839.85 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:56:42,923 INFO [train.py:715] (5/8) Epoch 16, batch 21850, loss[loss=0.1385, simple_loss=0.2105, pruned_loss=0.03325, over 4857.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 972243.10 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 18:57:20,564 INFO [train.py:715] (5/8) Epoch 16, batch 21900, loss[loss=0.1343, simple_loss=0.224, pruned_loss=0.02229, over 4954.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03056, over 973118.52 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:57:57,980 INFO [train.py:715] (5/8) Epoch 16, batch 21950, loss[loss=0.1317, simple_loss=0.1969, pruned_loss=0.03321, over 4839.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02979, over 972903.00 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 18:58:36,387 INFO [train.py:715] (5/8) Epoch 16, batch 22000, loss[loss=0.1473, simple_loss=0.2323, pruned_loss=0.03111, over 4754.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02962, over 972501.74 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 18:59:14,000 INFO [train.py:715] (5/8) Epoch 16, batch 22050, loss[loss=0.1266, simple_loss=0.2075, pruned_loss=0.02282, over 4822.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02942, over 972616.92 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 18:59:52,238 INFO [train.py:715] (5/8) Epoch 16, batch 22100, loss[loss=0.1448, simple_loss=0.2092, pruned_loss=0.0402, over 4948.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02926, over 972682.16 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:00:29,954 INFO [train.py:715] (5/8) Epoch 16, batch 22150, loss[loss=0.1212, simple_loss=0.2017, pruned_loss=0.02036, over 4829.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02919, over 972278.29 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:01:08,389 INFO [train.py:715] (5/8) Epoch 16, batch 22200, loss[loss=0.1246, simple_loss=0.2037, pruned_loss=0.02272, over 4832.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02945, over 972414.18 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:01:46,152 INFO [train.py:715] (5/8) Epoch 16, batch 22250, loss[loss=0.1411, simple_loss=0.212, pruned_loss=0.03507, over 4771.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02966, over 972755.31 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:02:24,240 INFO [train.py:715] (5/8) Epoch 16, batch 22300, loss[loss=0.1095, simple_loss=0.181, pruned_loss=0.01899, over 4639.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02953, over 972007.20 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:03:02,795 INFO [train.py:715] (5/8) Epoch 16, batch 22350, loss[loss=0.1227, simple_loss=0.2085, pruned_loss=0.01848, over 4850.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02962, over 972810.51 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:03:40,845 INFO [train.py:715] (5/8) Epoch 16, batch 22400, loss[loss=0.1232, simple_loss=0.193, pruned_loss=0.02668, over 4818.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02973, over 972169.02 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:04:19,199 INFO [train.py:715] (5/8) Epoch 16, batch 22450, loss[loss=0.1399, simple_loss=0.2165, pruned_loss=0.0317, over 4837.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02995, over 971965.45 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:04:57,329 INFO [train.py:715] (5/8) Epoch 16, batch 22500, loss[loss=0.1096, simple_loss=0.1828, pruned_loss=0.01818, over 4820.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 971879.92 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:05:35,514 INFO [train.py:715] (5/8) Epoch 16, batch 22550, loss[loss=0.1548, simple_loss=0.2272, pruned_loss=0.04122, over 4862.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02985, over 972679.02 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:06:13,253 INFO [train.py:715] (5/8) Epoch 16, batch 22600, loss[loss=0.1161, simple_loss=0.1911, pruned_loss=0.02057, over 4869.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02961, over 972326.02 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:06:50,943 INFO [train.py:715] (5/8) Epoch 16, batch 22650, loss[loss=0.1159, simple_loss=0.1901, pruned_loss=0.02088, over 4811.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02954, over 972671.99 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:07:29,635 INFO [train.py:715] (5/8) Epoch 16, batch 22700, loss[loss=0.1278, simple_loss=0.2053, pruned_loss=0.02513, over 4886.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02968, over 972798.03 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 19:08:07,678 INFO [train.py:715] (5/8) Epoch 16, batch 22750, loss[loss=0.1185, simple_loss=0.195, pruned_loss=0.02102, over 4935.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02942, over 973012.19 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:08:45,791 INFO [train.py:715] (5/8) Epoch 16, batch 22800, loss[loss=0.1191, simple_loss=0.2, pruned_loss=0.01912, over 4971.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02941, over 973130.36 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:09:23,700 INFO [train.py:715] (5/8) Epoch 16, batch 22850, loss[loss=0.1081, simple_loss=0.1855, pruned_loss=0.01538, over 4817.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.0296, over 972371.85 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:10:01,846 INFO [train.py:715] (5/8) Epoch 16, batch 22900, loss[loss=0.1149, simple_loss=0.1901, pruned_loss=0.0199, over 4940.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02989, over 972187.20 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:10:39,883 INFO [train.py:715] (5/8) Epoch 16, batch 22950, loss[loss=0.1301, simple_loss=0.2003, pruned_loss=0.02991, over 4799.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2092, pruned_loss=0.03005, over 971926.73 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:11:17,830 INFO [train.py:715] (5/8) Epoch 16, batch 23000, loss[loss=0.1383, simple_loss=0.2133, pruned_loss=0.03171, over 4770.00 frames.], tot_loss[loss=0.134, simple_loss=0.2088, pruned_loss=0.0296, over 972198.89 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:11:56,368 INFO [train.py:715] (5/8) Epoch 16, batch 23050, loss[loss=0.1318, simple_loss=0.2069, pruned_loss=0.02837, over 4820.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2087, pruned_loss=0.0295, over 972637.50 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:12:34,516 INFO [train.py:715] (5/8) Epoch 16, batch 23100, loss[loss=0.1624, simple_loss=0.2238, pruned_loss=0.0505, over 4786.00 frames.], tot_loss[loss=0.133, simple_loss=0.208, pruned_loss=0.02901, over 972457.66 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:13:12,453 INFO [train.py:715] (5/8) Epoch 16, batch 23150, loss[loss=0.1585, simple_loss=0.2428, pruned_loss=0.03714, over 4769.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02881, over 972646.25 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:13:50,198 INFO [train.py:715] (5/8) Epoch 16, batch 23200, loss[loss=0.1225, simple_loss=0.204, pruned_loss=0.0205, over 4773.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02887, over 972146.52 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:14:28,511 INFO [train.py:715] (5/8) Epoch 16, batch 23250, loss[loss=0.1204, simple_loss=0.1959, pruned_loss=0.02242, over 4746.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02895, over 973153.49 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:15:06,178 INFO [train.py:715] (5/8) Epoch 16, batch 23300, loss[loss=0.1249, simple_loss=0.1949, pruned_loss=0.02749, over 4859.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2086, pruned_loss=0.02951, over 973591.05 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:15:44,248 INFO [train.py:715] (5/8) Epoch 16, batch 23350, loss[loss=0.1648, simple_loss=0.2323, pruned_loss=0.04862, over 4846.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.03007, over 974283.80 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:16:21,896 INFO [train.py:715] (5/8) Epoch 16, batch 23400, loss[loss=0.1606, simple_loss=0.2371, pruned_loss=0.04206, over 4882.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03005, over 974605.95 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 19:16:59,785 INFO [train.py:715] (5/8) Epoch 16, batch 23450, loss[loss=0.1124, simple_loss=0.1853, pruned_loss=0.01975, over 4916.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02935, over 974714.42 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:17:37,691 INFO [train.py:715] (5/8) Epoch 16, batch 23500, loss[loss=0.1301, simple_loss=0.2007, pruned_loss=0.02971, over 4821.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02908, over 974540.04 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:18:15,673 INFO [train.py:715] (5/8) Epoch 16, batch 23550, loss[loss=0.1467, simple_loss=0.1989, pruned_loss=0.04723, over 4702.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02906, over 973792.15 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:18:54,223 INFO [train.py:715] (5/8) Epoch 16, batch 23600, loss[loss=0.1212, simple_loss=0.2057, pruned_loss=0.01837, over 4982.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02896, over 974393.42 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:19:31,590 INFO [train.py:715] (5/8) Epoch 16, batch 23650, loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02866, over 4815.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02869, over 973865.08 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:20:09,503 INFO [train.py:715] (5/8) Epoch 16, batch 23700, loss[loss=0.1163, simple_loss=0.1879, pruned_loss=0.02232, over 4920.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02882, over 974093.45 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:20:47,876 INFO [train.py:715] (5/8) Epoch 16, batch 23750, loss[loss=0.1287, simple_loss=0.2142, pruned_loss=0.02155, over 4825.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02852, over 973139.53 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:21:25,950 INFO [train.py:715] (5/8) Epoch 16, batch 23800, loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.0283, over 4769.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02877, over 973241.74 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:22:04,206 INFO [train.py:715] (5/8) Epoch 16, batch 23850, loss[loss=0.1681, simple_loss=0.2275, pruned_loss=0.05439, over 4832.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02943, over 972465.88 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 19:22:42,142 INFO [train.py:715] (5/8) Epoch 16, batch 23900, loss[loss=0.1541, simple_loss=0.2236, pruned_loss=0.04228, over 4944.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02935, over 972165.14 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:23:20,419 INFO [train.py:715] (5/8) Epoch 16, batch 23950, loss[loss=0.1287, simple_loss=0.2058, pruned_loss=0.02587, over 4805.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02968, over 972400.97 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:23:57,819 INFO [train.py:715] (5/8) Epoch 16, batch 24000, loss[loss=0.1168, simple_loss=0.2027, pruned_loss=0.01547, over 4986.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02974, over 971844.86 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:23:57,820 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 19:24:07,634 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1883, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 19:24:46,403 INFO [train.py:715] (5/8) Epoch 16, batch 24050, loss[loss=0.1345, simple_loss=0.2096, pruned_loss=0.02974, over 4842.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02939, over 972610.53 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:25:24,730 INFO [train.py:715] (5/8) Epoch 16, batch 24100, loss[loss=0.1361, simple_loss=0.2109, pruned_loss=0.03063, over 4974.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02953, over 972138.92 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 19:26:03,115 INFO [train.py:715] (5/8) Epoch 16, batch 24150, loss[loss=0.1467, simple_loss=0.2138, pruned_loss=0.03979, over 4964.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02926, over 971943.60 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:26:40,870 INFO [train.py:715] (5/8) Epoch 16, batch 24200, loss[loss=0.1113, simple_loss=0.1825, pruned_loss=0.02007, over 4846.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02868, over 972292.07 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:27:19,230 INFO [train.py:715] (5/8) Epoch 16, batch 24250, loss[loss=0.1343, simple_loss=0.2105, pruned_loss=0.02905, over 4868.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02887, over 971863.22 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:27:57,173 INFO [train.py:715] (5/8) Epoch 16, batch 24300, loss[loss=0.128, simple_loss=0.2137, pruned_loss=0.02111, over 4780.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02863, over 971598.91 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:28:35,672 INFO [train.py:715] (5/8) Epoch 16, batch 24350, loss[loss=0.1769, simple_loss=0.2557, pruned_loss=0.04906, over 4819.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02834, over 971620.65 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:29:13,224 INFO [train.py:715] (5/8) Epoch 16, batch 24400, loss[loss=0.1066, simple_loss=0.1832, pruned_loss=0.01499, over 4777.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02869, over 971630.80 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:29:50,781 INFO [train.py:715] (5/8) Epoch 16, batch 24450, loss[loss=0.1554, simple_loss=0.2413, pruned_loss=0.03478, over 4749.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.0289, over 971996.56 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:30:28,697 INFO [train.py:715] (5/8) Epoch 16, batch 24500, loss[loss=0.1681, simple_loss=0.2267, pruned_loss=0.05479, over 4872.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02845, over 971919.68 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:31:06,547 INFO [train.py:715] (5/8) Epoch 16, batch 24550, loss[loss=0.1326, simple_loss=0.1987, pruned_loss=0.03328, over 4702.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02925, over 972408.20 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:31:43,993 INFO [train.py:715] (5/8) Epoch 16, batch 24600, loss[loss=0.1189, simple_loss=0.1972, pruned_loss=0.02027, over 4926.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.0298, over 972889.90 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:32:21,347 INFO [train.py:715] (5/8) Epoch 16, batch 24650, loss[loss=0.1048, simple_loss=0.1867, pruned_loss=0.01139, over 4913.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02964, over 972303.23 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:32:59,496 INFO [train.py:715] (5/8) Epoch 16, batch 24700, loss[loss=0.1752, simple_loss=0.2333, pruned_loss=0.05855, over 4811.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2061, pruned_loss=0.02954, over 972370.09 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:33:37,067 INFO [train.py:715] (5/8) Epoch 16, batch 24750, loss[loss=0.1292, simple_loss=0.2016, pruned_loss=0.02843, over 4757.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02991, over 972701.30 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:34:14,867 INFO [train.py:715] (5/8) Epoch 16, batch 24800, loss[loss=0.112, simple_loss=0.1931, pruned_loss=0.01546, over 4940.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2062, pruned_loss=0.0297, over 972486.23 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:34:52,613 INFO [train.py:715] (5/8) Epoch 16, batch 24850, loss[loss=0.1193, simple_loss=0.1991, pruned_loss=0.01978, over 4981.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2068, pruned_loss=0.03002, over 972545.94 frames.], batch size: 31, lr: 1.37e-04
2022-05-08 19:35:30,369 INFO [train.py:715] (5/8) Epoch 16, batch 24900, loss[loss=0.1021, simple_loss=0.1751, pruned_loss=0.01457, over 4818.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02957, over 971702.74 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:36:08,067 INFO [train.py:715] (5/8) Epoch 16, batch 24950, loss[loss=0.115, simple_loss=0.1895, pruned_loss=0.02026, over 4976.00 frames.], tot_loss[loss=0.133, simple_loss=0.2065, pruned_loss=0.02974, over 971431.18 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:36:45,486 INFO [train.py:715] (5/8) Epoch 16, batch 25000, loss[loss=0.1123, simple_loss=0.1879, pruned_loss=0.01836, over 4786.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02962, over 971437.18 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:37:23,737 INFO [train.py:715] (5/8) Epoch 16, batch 25050, loss[loss=0.1284, simple_loss=0.2018, pruned_loss=0.02747, over 4978.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02946, over 971895.59 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:38:02,501 INFO [train.py:715] (5/8) Epoch 16, batch 25100, loss[loss=0.1316, simple_loss=0.2091, pruned_loss=0.02703, over 4931.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02889, over 972951.29 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:38:40,228 INFO [train.py:715] (5/8) Epoch 16, batch 25150, loss[loss=0.1442, simple_loss=0.2266, pruned_loss=0.03088, over 4918.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02913, over 973115.76 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:39:18,063 INFO [train.py:715] (5/8) Epoch 16, batch 25200, loss[loss=0.1359, simple_loss=0.2007, pruned_loss=0.03557, over 4975.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02899, over 973254.57 frames.], batch size: 33, lr: 1.37e-04
2022-05-08 19:39:56,033 INFO [train.py:715] (5/8) Epoch 16, batch 25250, loss[loss=0.1108, simple_loss=0.1806, pruned_loss=0.02048, over 4707.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02951, over 972757.59 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:40:33,644 INFO [train.py:715] (5/8) Epoch 16, batch 25300, loss[loss=0.1047, simple_loss=0.1808, pruned_loss=0.0143, over 4770.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02961, over 971979.56 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:41:10,910 INFO [train.py:715] (5/8) Epoch 16, batch 25350, loss[loss=0.1433, simple_loss=0.2139, pruned_loss=0.03631, over 4805.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02951, over 972402.61 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:41:49,014 INFO [train.py:715] (5/8) Epoch 16, batch 25400, loss[loss=0.118, simple_loss=0.1918, pruned_loss=0.02211, over 4921.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02979, over 973111.13 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:42:27,348 INFO [train.py:715] (5/8) Epoch 16, batch 25450, loss[loss=0.1108, simple_loss=0.1813, pruned_loss=0.02021, over 4850.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.0295, over 973508.68 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:43:04,844 INFO [train.py:715] (5/8) Epoch 16, batch 25500, loss[loss=0.1287, simple_loss=0.2035, pruned_loss=0.02694, over 4694.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02912, over 973300.75 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:43:42,833 INFO [train.py:715] (5/8) Epoch 16, batch 25550, loss[loss=0.1252, simple_loss=0.1949, pruned_loss=0.02777, over 4772.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 972599.42 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:44:21,343 INFO [train.py:715] (5/8) Epoch 16, batch 25600, loss[loss=0.1223, simple_loss=0.1983, pruned_loss=0.02314, over 4817.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02913, over 972262.35 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 19:45:00,128 INFO [train.py:715] (5/8) Epoch 16, batch 25650, loss[loss=0.1387, simple_loss=0.2112, pruned_loss=0.03311, over 4970.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02988, over 973257.84 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:45:38,354 INFO [train.py:715] (5/8) Epoch 16, batch 25700, loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03729, over 4907.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03003, over 973232.22 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:46:16,987 INFO [train.py:715] (5/8) Epoch 16, batch 25750, loss[loss=0.138, simple_loss=0.2134, pruned_loss=0.03126, over 4746.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03001, over 972553.50 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:46:55,625 INFO [train.py:715] (5/8) Epoch 16, batch 25800, loss[loss=0.1059, simple_loss=0.1843, pruned_loss=0.01378, over 4976.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02954, over 972634.03 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:47:34,229 INFO [train.py:715] (5/8) Epoch 16, batch 25850, loss[loss=0.1174, simple_loss=0.1927, pruned_loss=0.02106, over 4914.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02966, over 972242.65 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:48:13,051 INFO [train.py:715] (5/8) Epoch 16, batch 25900, loss[loss=0.1278, simple_loss=0.2062, pruned_loss=0.02469, over 4813.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02925, over 972946.36 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:48:52,469 INFO [train.py:715] (5/8) Epoch 16, batch 25950, loss[loss=0.1377, simple_loss=0.2066, pruned_loss=0.03438, over 4916.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02926, over 972053.00 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:49:32,203 INFO [train.py:715] (5/8) Epoch 16, batch 26000, loss[loss=0.1336, simple_loss=0.2038, pruned_loss=0.03172, over 4976.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02981, over 972503.27 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:50:11,554 INFO [train.py:715] (5/8) Epoch 16, batch 26050, loss[loss=0.1526, simple_loss=0.2296, pruned_loss=0.03786, over 4814.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02964, over 972882.71 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:50:50,795 INFO [train.py:715] (5/8) Epoch 16, batch 26100, loss[loss=0.1262, simple_loss=0.1981, pruned_loss=0.02714, over 4833.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 973265.56 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:51:30,061 INFO [train.py:715] (5/8) Epoch 16, batch 26150, loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02929, over 4947.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02925, over 973633.85 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:52:08,701 INFO [train.py:715] (5/8) Epoch 16, batch 26200, loss[loss=0.1268, simple_loss=0.2062, pruned_loss=0.0237, over 4829.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02931, over 972470.85 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 19:52:48,175 INFO [train.py:715] (5/8) Epoch 16, batch 26250, loss[loss=0.1287, simple_loss=0.1912, pruned_loss=0.03314, over 4845.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02947, over 972581.65 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:53:27,330 INFO [train.py:715] (5/8) Epoch 16, batch 26300, loss[loss=0.1152, simple_loss=0.1886, pruned_loss=0.02093, over 4952.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02959, over 972605.80 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:54:06,988 INFO [train.py:715] (5/8) Epoch 16, batch 26350, loss[loss=0.1395, simple_loss=0.2118, pruned_loss=0.03354, over 4971.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02938, over 973131.61 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:54:46,283 INFO [train.py:715] (5/8) Epoch 16, batch 26400, loss[loss=0.1395, simple_loss=0.2106, pruned_loss=0.03424, over 4928.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 972296.39 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:55:26,167 INFO [train.py:715] (5/8) Epoch 16, batch 26450, loss[loss=0.1382, simple_loss=0.2141, pruned_loss=0.03121, over 4770.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02898, over 971852.55 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:56:05,125 INFO [train.py:715] (5/8) Epoch 16, batch 26500, loss[loss=0.09984, simple_loss=0.1717, pruned_loss=0.01397, over 4943.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02896, over 971943.96 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:56:44,034 INFO [train.py:715] (5/8) Epoch 16, batch 26550, loss[loss=0.1305, simple_loss=0.2085, pruned_loss=0.02625, over 4924.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02895, over 971990.20 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:57:23,105 INFO [train.py:715] (5/8) Epoch 16, batch 26600, loss[loss=0.1269, simple_loss=0.2001, pruned_loss=0.02684, over 4833.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02938, over 971809.19 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:58:02,094 INFO [train.py:715] (5/8) Epoch 16, batch 26650, loss[loss=0.1504, simple_loss=0.2289, pruned_loss=0.03596, over 4691.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02894, over 971280.02 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:58:41,426 INFO [train.py:715] (5/8) Epoch 16, batch 26700, loss[loss=0.1146, simple_loss=0.1907, pruned_loss=0.01921, over 4922.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02918, over 971479.97 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:59:20,661 INFO [train.py:715] (5/8) Epoch 16, batch 26750, loss[loss=0.1143, simple_loss=0.1967, pruned_loss=0.01591, over 4923.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02917, over 971459.10 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 20:00:00,474 INFO [train.py:715] (5/8) Epoch 16, batch 26800, loss[loss=0.1267, simple_loss=0.1974, pruned_loss=0.02802, over 4901.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02873, over 971147.99 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:00:39,346 INFO [train.py:715] (5/8) Epoch 16, batch 26850, loss[loss=0.1451, simple_loss=0.2217, pruned_loss=0.03426, over 4694.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02915, over 971823.57 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:01:18,827 INFO [train.py:715] (5/8) Epoch 16, batch 26900, loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 4790.00 frames.], tot_loss[loss=0.134, simple_loss=0.2089, pruned_loss=0.02959, over 971298.72 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 20:01:58,324 INFO [train.py:715] (5/8) Epoch 16, batch 26950, loss[loss=0.1402, simple_loss=0.2147, pruned_loss=0.03286, over 4869.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2099, pruned_loss=0.02992, over 971860.16 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:02:37,504 INFO [train.py:715] (5/8) Epoch 16, batch 27000, loss[loss=0.1348, simple_loss=0.1913, pruned_loss=0.03914, over 4760.00 frames.], tot_loss[loss=0.135, simple_loss=0.2096, pruned_loss=0.03022, over 971014.49 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 20:02:37,505 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 20:02:47,199 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1048, simple_loss=0.1883, pruned_loss=0.01067, over 914524.00 frames.
2022-05-08 20:03:26,296 INFO [train.py:715] (5/8) Epoch 16, batch 27050, loss[loss=0.144, simple_loss=0.2156, pruned_loss=0.03627, over 4878.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02975, over 971311.06 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:04:08,234 INFO [train.py:715] (5/8) Epoch 16, batch 27100, loss[loss=0.1268, simple_loss=0.2082, pruned_loss=0.02268, over 4917.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02991, over 971977.81 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 20:04:47,172 INFO [train.py:715] (5/8) Epoch 16, batch 27150, loss[loss=0.1349, simple_loss=0.2026, pruned_loss=0.0336, over 4935.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02943, over 972470.08 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:05:26,606 INFO [train.py:715] (5/8) Epoch 16, batch 27200, loss[loss=0.1494, simple_loss=0.22, pruned_loss=0.03936, over 4952.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02957, over 972162.94 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:06:05,792 INFO [train.py:715] (5/8) Epoch 16, batch 27250, loss[loss=0.1466, simple_loss=0.2157, pruned_loss=0.03876, over 4824.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02966, over 972506.13 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 20:06:45,175 INFO [train.py:715] (5/8) Epoch 16, batch 27300, loss[loss=0.1071, simple_loss=0.1811, pruned_loss=0.01656, over 4801.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.0292, over 972549.93 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 20:07:24,246 INFO [train.py:715] (5/8) Epoch 16, batch 27350, loss[loss=0.1404, simple_loss=0.2139, pruned_loss=0.03347, over 4825.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02911, over 973561.93 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 20:08:03,612 INFO [train.py:715] (5/8) Epoch 16, batch 27400, loss[loss=0.1523, simple_loss=0.2334, pruned_loss=0.03558, over 4942.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02951, over 973294.60 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:08:42,904 INFO [train.py:715] (5/8) Epoch 16, batch 27450, loss[loss=0.1613, simple_loss=0.2377, pruned_loss=0.0424, over 4889.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02967, over 973317.43 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:09:21,909 INFO [train.py:715] (5/8) Epoch 16, batch 27500, loss[loss=0.1695, simple_loss=0.2454, pruned_loss=0.04676, over 4949.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 973272.00 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:10:01,269 INFO [train.py:715] (5/8) Epoch 16, batch 27550, loss[loss=0.1149, simple_loss=0.1838, pruned_loss=0.02303, over 4806.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02919, over 972934.10 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 20:10:41,122 INFO [train.py:715] (5/8) Epoch 16, batch 27600, loss[loss=0.1419, simple_loss=0.2128, pruned_loss=0.03553, over 4847.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.0293, over 971639.06 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:11:20,147 INFO [train.py:715] (5/8) Epoch 16, batch 27650, loss[loss=0.1448, simple_loss=0.2178, pruned_loss=0.03588, over 4756.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02958, over 971171.21 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:11:59,673 INFO [train.py:715] (5/8) Epoch 16, batch 27700, loss[loss=0.1197, simple_loss=0.1911, pruned_loss=0.02418, over 4873.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.0295, over 971683.32 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 20:12:38,977 INFO [train.py:715] (5/8) Epoch 16, batch 27750, loss[loss=0.1116, simple_loss=0.1916, pruned_loss=0.0158, over 4829.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02943, over 971147.57 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:13:18,197 INFO [train.py:715] (5/8) Epoch 16, batch 27800, loss[loss=0.1507, simple_loss=0.2284, pruned_loss=0.03649, over 4901.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02933, over 971287.10 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:13:57,554 INFO [train.py:715] (5/8) Epoch 16, batch 27850, loss[loss=0.1356, simple_loss=0.2048, pruned_loss=0.03317, over 4852.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02936, over 970866.49 frames.], batch size: 34, lr: 1.37e-04
2022-05-08 20:14:36,983 INFO [train.py:715] (5/8) Epoch 16, batch 27900, loss[loss=0.1125, simple_loss=0.1816, pruned_loss=0.02171, over 4826.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02993, over 971172.62 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 20:15:16,663 INFO [train.py:715] (5/8) Epoch 16, batch 27950, loss[loss=0.1091, simple_loss=0.1877, pruned_loss=0.01524, over 4816.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02959, over 971301.37 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 20:15:55,974 INFO [train.py:715] (5/8) Epoch 16, batch 28000, loss[loss=0.1019, simple_loss=0.1825, pruned_loss=0.01068, over 4894.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02969, over 972107.23 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 20:16:35,539 INFO [train.py:715] (5/8) Epoch 16, batch 28050, loss[loss=0.13, simple_loss=0.2071, pruned_loss=0.02647, over 4815.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02935, over 972740.75 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 20:17:15,208 INFO [train.py:715] (5/8) Epoch 16, batch 28100, loss[loss=0.1339, simple_loss=0.2046, pruned_loss=0.03155, over 4741.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 972137.54 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:17:54,190 INFO [train.py:715] (5/8) Epoch 16, batch 28150, loss[loss=0.1841, simple_loss=0.2512, pruned_loss=0.05852, over 4803.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02967, over 972115.30 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 20:18:33,941 INFO [train.py:715] (5/8) Epoch 16, batch 28200, loss[loss=0.1121, simple_loss=0.1892, pruned_loss=0.01748, over 4896.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03022, over 971522.11 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 20:19:13,273 INFO [train.py:715] (5/8) Epoch 16, batch 28250, loss[loss=0.132, simple_loss=0.212, pruned_loss=0.02597, over 4940.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02994, over 972301.99 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 20:19:51,891 INFO [train.py:715] (5/8) Epoch 16, batch 28300, loss[loss=0.09938, simple_loss=0.173, pruned_loss=0.01287, over 4861.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02979, over 972377.11 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 20:20:31,607 INFO [train.py:715] (5/8) Epoch 16, batch 28350, loss[loss=0.1409, simple_loss=0.2154, pruned_loss=0.03316, over 4884.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03004, over 973445.64 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:21:11,561 INFO [train.py:715] (5/8) Epoch 16, batch 28400, loss[loss=0.1444, simple_loss=0.2138, pruned_loss=0.03753, over 4942.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 973013.58 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 20:21:51,019 INFO [train.py:715] (5/8) Epoch 16, batch 28450, loss[loss=0.1299, simple_loss=0.2118, pruned_loss=0.02397, over 4899.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02932, over 972205.42 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 20:22:29,721 INFO [train.py:715] (5/8) Epoch 16, batch 28500, loss[loss=0.1238, simple_loss=0.2017, pruned_loss=0.023, over 4820.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02948, over 971360.58 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 20:23:09,887 INFO [train.py:715] (5/8) Epoch 16, batch 28550, loss[loss=0.1272, simple_loss=0.1962, pruned_loss=0.02913, over 4773.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02951, over 972063.65 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:23:49,360 INFO [train.py:715] (5/8) Epoch 16, batch 28600, loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03232, over 4774.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02972, over 971552.99 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:24:28,945 INFO [train.py:715] (5/8) Epoch 16, batch 28650, loss[loss=0.136, simple_loss=0.211, pruned_loss=0.03051, over 4926.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02964, over 972203.63 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:25:08,100 INFO [train.py:715] (5/8) Epoch 16, batch 28700, loss[loss=0.1314, simple_loss=0.2015, pruned_loss=0.03065, over 4823.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 971751.16 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 20:25:47,666 INFO [train.py:715] (5/8) Epoch 16, batch 28750, loss[loss=0.1245, simple_loss=0.1981, pruned_loss=0.02541, over 4872.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02965, over 971805.69 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 20:26:27,377 INFO [train.py:715] (5/8) Epoch 16, batch 28800, loss[loss=0.1479, simple_loss=0.2311, pruned_loss=0.03236, over 4883.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02933, over 971935.85 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:27:06,537 INFO [train.py:715] (5/8) Epoch 16, batch 28850, loss[loss=0.1104, simple_loss=0.1847, pruned_loss=0.0181, over 4769.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 971263.88 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:27:46,355 INFO [train.py:715] (5/8) Epoch 16, batch 28900, loss[loss=0.1303, simple_loss=0.2058, pruned_loss=0.02738, over 4790.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02959, over 970786.60 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:28:25,933 INFO [train.py:715] (5/8) Epoch 16, batch 28950, loss[loss=0.1911, simple_loss=0.2528, pruned_loss=0.0647, over 4703.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 970551.64 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:29:05,871 INFO [train.py:715] (5/8) Epoch 16, batch 29000, loss[loss=0.1344, simple_loss=0.2183, pruned_loss=0.02521, over 4746.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02926, over 971018.94 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:29:45,338 INFO [train.py:715] (5/8) Epoch 16, batch 29050, loss[loss=0.115, simple_loss=0.1914, pruned_loss=0.01932, over 4909.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02962, over 971651.10 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:30:25,180 INFO [train.py:715] (5/8) Epoch 16, batch 29100, loss[loss=0.1565, simple_loss=0.2268, pruned_loss=0.04312, over 4900.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02945, over 971201.02 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:31:06,238 INFO [train.py:715] (5/8) Epoch 16, batch 29150, loss[loss=0.152, simple_loss=0.2382, pruned_loss=0.03293, over 4977.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02946, over 971957.46 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:31:46,266 INFO [train.py:715] (5/8) Epoch 16, batch 29200, loss[loss=0.1193, simple_loss=0.1977, pruned_loss=0.0205, over 4887.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 972586.69 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:32:27,442 INFO [train.py:715] (5/8) Epoch 16, batch 29250, loss[loss=0.1285, simple_loss=0.1988, pruned_loss=0.02913, over 4960.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02943, over 972760.68 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 20:33:08,441 INFO [train.py:715] (5/8) Epoch 16, batch 29300, loss[loss=0.1308, simple_loss=0.2094, pruned_loss=0.02612, over 4904.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02956, over 972840.78 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:33:49,836 INFO [train.py:715] (5/8) Epoch 16, batch 29350, loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03651, over 4751.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02975, over 973244.28 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:34:30,965 INFO [train.py:715] (5/8) Epoch 16, batch 29400, loss[loss=0.1015, simple_loss=0.175, pruned_loss=0.01399, over 4727.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 971592.62 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:35:12,717 INFO [train.py:715] (5/8) Epoch 16, batch 29450, loss[loss=0.1447, simple_loss=0.2173, pruned_loss=0.03604, over 4898.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02989, over 971437.63 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:35:54,215 INFO [train.py:715] (5/8) Epoch 16, batch 29500, loss[loss=0.1366, simple_loss=0.215, pruned_loss=0.02908, over 4979.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 971919.88 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 20:36:36,035 INFO [train.py:715] (5/8) Epoch 16, batch 29550, loss[loss=0.1255, simple_loss=0.2016, pruned_loss=0.02474, over 4944.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02978, over 972500.88 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:37:17,258 INFO [train.py:715] (5/8) Epoch 16, batch 29600, loss[loss=0.111, simple_loss=0.1847, pruned_loss=0.01861, over 4966.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02971, over 972195.44 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:37:59,052 INFO [train.py:715] (5/8) Epoch 16, batch 29650, loss[loss=0.1195, simple_loss=0.19, pruned_loss=0.02447, over 4755.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03002, over 972166.12 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:38:40,540 INFO [train.py:715] (5/8) Epoch 16, batch 29700, loss[loss=0.1331, simple_loss=0.2114, pruned_loss=0.02738, over 4870.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02981, over 972781.56 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 20:39:21,788 INFO [train.py:715] (5/8) Epoch 16, batch 29750, loss[loss=0.1344, simple_loss=0.2063, pruned_loss=0.0312, over 4699.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02993, over 972459.13 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:40:02,894 INFO [train.py:715] (5/8) Epoch 16, batch 29800, loss[loss=0.1463, simple_loss=0.2217, pruned_loss=0.03547, over 4981.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02958, over 972442.20 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:40:44,775 INFO [train.py:715] (5/8) Epoch 16, batch 29850, loss[loss=0.1623, simple_loss=0.2269, pruned_loss=0.0488, over 4959.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02925, over 972607.65 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 20:41:26,318 INFO [train.py:715] (5/8) Epoch 16, batch 29900, loss[loss=0.1433, simple_loss=0.2198, pruned_loss=0.03343, over 4895.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02929, over 973321.35 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:42:07,627 INFO [train.py:715] (5/8) Epoch 16, batch 29950, loss[loss=0.1498, simple_loss=0.2095, pruned_loss=0.04501, over 4915.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02874, over 972979.51 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:42:50,227 INFO [train.py:715] (5/8) Epoch 16, batch 30000, loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03326, over 4893.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02868, over 973315.63 frames.], batch size: 39, lr: 1.36e-04
2022-05-08 20:42:50,228 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 20:43:01,792 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1883, pruned_loss=0.01058, over 914524.00 frames.
2022-05-08 20:43:44,296 INFO [train.py:715] (5/8) Epoch 16, batch 30050, loss[loss=0.1225, simple_loss=0.1987, pruned_loss=0.02317, over 4880.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 973974.56 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 20:44:26,133 INFO [train.py:715] (5/8) Epoch 16, batch 30100, loss[loss=0.135, simple_loss=0.2167, pruned_loss=0.02661, over 4750.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02878, over 974392.89 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:45:06,930 INFO [train.py:715] (5/8) Epoch 16, batch 30150, loss[loss=0.1278, simple_loss=0.2113, pruned_loss=0.02219, over 4965.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02937, over 973600.72 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:45:48,622 INFO [train.py:715] (5/8) Epoch 16, batch 30200, loss[loss=0.1566, simple_loss=0.2373, pruned_loss=0.03796, over 4777.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02909, over 973367.80 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:46:29,889 INFO [train.py:715] (5/8) Epoch 16, batch 30250, loss[loss=0.1789, simple_loss=0.2484, pruned_loss=0.05475, over 4784.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02929, over 973159.20 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:47:09,988 INFO [train.py:715] (5/8) Epoch 16, batch 30300, loss[loss=0.1348, simple_loss=0.1968, pruned_loss=0.03636, over 4903.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02918, over 972486.09 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:47:50,184 INFO [train.py:715] (5/8) Epoch 16, batch 30350, loss[loss=0.1161, simple_loss=0.198, pruned_loss=0.01704, over 4806.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02922, over 972516.35 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:48:30,609 INFO [train.py:715] (5/8) Epoch 16, batch 30400, loss[loss=0.1338, simple_loss=0.2008, pruned_loss=0.03333, over 4959.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02942, over 972930.28 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:49:10,257 INFO [train.py:715] (5/8) Epoch 16, batch 30450, loss[loss=0.1437, simple_loss=0.2214, pruned_loss=0.033, over 4901.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.0296, over 974139.18 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:49:49,412 INFO [train.py:715] (5/8) Epoch 16, batch 30500, loss[loss=0.142, simple_loss=0.2082, pruned_loss=0.03792, over 4900.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02963, over 974176.71 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:50:29,336 INFO [train.py:715] (5/8) Epoch 16, batch 30550, loss[loss=0.1388, simple_loss=0.2161, pruned_loss=0.03074, over 4925.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02992, over 973772.67 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 20:51:09,800 INFO [train.py:715] (5/8) Epoch 16, batch 30600, loss[loss=0.1477, simple_loss=0.2234, pruned_loss=0.03603, over 4842.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 974451.12 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:51:49,047 INFO [train.py:715] (5/8) Epoch 16, batch 30650, loss[loss=0.1138, simple_loss=0.1991, pruned_loss=0.01423, over 4819.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02916, over 974243.03 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 20:52:28,801 INFO [train.py:715] (5/8) Epoch 16, batch 30700, loss[loss=0.1324, simple_loss=0.2088, pruned_loss=0.02802, over 4771.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02907, over 974198.17 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:53:10,030 INFO [train.py:715] (5/8) Epoch 16, batch 30750, loss[loss=0.1376, simple_loss=0.2132, pruned_loss=0.03099, over 4890.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02936, over 973817.61 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:53:49,621 INFO [train.py:715] (5/8) Epoch 16, batch 30800, loss[loss=0.1523, simple_loss=0.2343, pruned_loss=0.03517, over 4792.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02913, over 973091.52 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:54:28,447 INFO [train.py:715] (5/8) Epoch 16, batch 30850, loss[loss=0.1199, simple_loss=0.1992, pruned_loss=0.02024, over 4798.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02919, over 972798.97 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:55:08,443 INFO [train.py:715] (5/8) Epoch 16, batch 30900, loss[loss=0.2499, simple_loss=0.3167, pruned_loss=0.0915, over 4772.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02967, over 972055.93 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:55:47,875 INFO [train.py:715] (5/8) Epoch 16, batch 30950, loss[loss=0.132, simple_loss=0.208, pruned_loss=0.02799, over 4753.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02946, over 972081.33 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:56:26,902 INFO [train.py:715] (5/8) Epoch 16, batch 31000, loss[loss=0.1222, simple_loss=0.1887, pruned_loss=0.02783, over 4691.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02958, over 972686.13 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:57:06,082 INFO [train.py:715] (5/8) Epoch 16, batch 31050, loss[loss=0.1429, simple_loss=0.2088, pruned_loss=0.03843, over 4876.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.0298, over 973030.48 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 20:57:45,840 INFO [train.py:715] (5/8) Epoch 16, batch 31100, loss[loss=0.1686, simple_loss=0.2411, pruned_loss=0.04806, over 4775.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02994, over 973159.37 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:58:25,689 INFO [train.py:715] (5/8) Epoch 16, batch 31150, loss[loss=0.1845, simple_loss=0.2601, pruned_loss=0.05446, over 4979.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03002, over 973378.34 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 20:59:04,401 INFO [train.py:715] (5/8) Epoch 16, batch 31200, loss[loss=0.1305, simple_loss=0.2079, pruned_loss=0.02658, over 4942.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02994, over 973818.40 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:59:44,074 INFO [train.py:715] (5/8) Epoch 16, batch 31250, loss[loss=0.1331, simple_loss=0.2124, pruned_loss=0.02685, over 4931.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02934, over 973805.29 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 21:00:23,614 INFO [train.py:715] (5/8) Epoch 16, batch 31300, loss[loss=0.113, simple_loss=0.1943, pruned_loss=0.01585, over 4868.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02895, over 973962.47 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 21:01:03,209 INFO [train.py:715] (5/8) Epoch 16, batch 31350, loss[loss=0.1236, simple_loss=0.1981, pruned_loss=0.02461, over 4821.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02936, over 974347.06 frames.], batch size: 27, lr: 1.36e-04
2022-05-08 21:01:42,657 INFO [train.py:715] (5/8) Epoch 16, batch 31400, loss[loss=0.1226, simple_loss=0.1952, pruned_loss=0.02495, over 4960.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02952, over 973085.26 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:02:22,718 INFO [train.py:715] (5/8) Epoch 16, batch 31450, loss[loss=0.1376, simple_loss=0.2042, pruned_loss=0.03545, over 4787.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.0294, over 972324.55 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:03:01,697 INFO [train.py:715] (5/8) Epoch 16, batch 31500, loss[loss=0.1283, simple_loss=0.2033, pruned_loss=0.02664, over 4685.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02949, over 973290.68 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:03:40,540 INFO [train.py:715] (5/8) Epoch 16, batch 31550, loss[loss=0.1277, simple_loss=0.2062, pruned_loss=0.02456, over 4817.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 973586.82 frames.], batch size: 27, lr: 1.36e-04
2022-05-08 21:04:19,803 INFO [train.py:715] (5/8) Epoch 16, batch 31600, loss[loss=0.1363, simple_loss=0.2065, pruned_loss=0.03305, over 4780.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02985, over 971961.09 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:04:58,917 INFO [train.py:715] (5/8) Epoch 16, batch 31650, loss[loss=0.1564, simple_loss=0.232, pruned_loss=0.04041, over 4870.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02958, over 973030.33 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:05:37,855 INFO [train.py:715] (5/8) Epoch 16, batch 31700, loss[loss=0.1854, simple_loss=0.2591, pruned_loss=0.05583, over 4883.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 973518.04 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:06:17,108 INFO [train.py:715] (5/8) Epoch 16, batch 31750, loss[loss=0.1295, simple_loss=0.1992, pruned_loss=0.02989, over 4832.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.0292, over 974070.12 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:06:56,938 INFO [train.py:715] (5/8) Epoch 16, batch 31800, loss[loss=0.1185, simple_loss=0.1969, pruned_loss=0.02003, over 4778.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02907, over 972934.67 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:07:36,868 INFO [train.py:715] (5/8) Epoch 16, batch 31850, loss[loss=0.1527, simple_loss=0.2279, pruned_loss=0.0388, over 4790.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 972351.69 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:08:15,873 INFO [train.py:715] (5/8) Epoch 16, batch 31900, loss[loss=0.1666, simple_loss=0.2277, pruned_loss=0.05271, over 4711.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02896, over 973037.20 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:08:55,064 INFO [train.py:715] (5/8) Epoch 16, batch 31950, loss[loss=0.1235, simple_loss=0.1967, pruned_loss=0.02518, over 4929.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02884, over 973483.52 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 21:09:34,439 INFO [train.py:715] (5/8) Epoch 16, batch 32000, loss[loss=0.1264, simple_loss=0.2064, pruned_loss=0.0232, over 4939.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02915, over 974099.11 frames.], batch size: 39, lr: 1.36e-04
2022-05-08 21:10:13,550 INFO [train.py:715] (5/8) Epoch 16, batch 32050, loss[loss=0.1397, simple_loss=0.2121, pruned_loss=0.03365, over 4812.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02892, over 974011.55 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 21:10:53,100 INFO [train.py:715] (5/8) Epoch 16, batch 32100, loss[loss=0.1251, simple_loss=0.1902, pruned_loss=0.02999, over 4958.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02935, over 973155.55 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 21:11:32,624 INFO [train.py:715] (5/8) Epoch 16, batch 32150, loss[loss=0.1539, simple_loss=0.2291, pruned_loss=0.03932, over 4980.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.029, over 972968.82 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 21:12:12,708 INFO [train.py:715] (5/8) Epoch 16, batch 32200, loss[loss=0.1131, simple_loss=0.1921, pruned_loss=0.01701, over 4879.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02868, over 972694.92 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 21:12:51,831 INFO [train.py:715] (5/8) Epoch 16, batch 32250, loss[loss=0.1231, simple_loss=0.2034, pruned_loss=0.02142, over 4867.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02861, over 972584.90 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:13:31,326 INFO [train.py:715] (5/8) Epoch 16, batch 32300, loss[loss=0.1184, simple_loss=0.1912, pruned_loss=0.02279, over 4804.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02936, over 971948.75 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:14:11,342 INFO [train.py:715] (5/8) Epoch 16, batch 32350, loss[loss=0.1104, simple_loss=0.1863, pruned_loss=0.01725, over 4795.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02901, over 970950.42 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:14:50,974 INFO [train.py:715] (5/8) Epoch 16, batch 32400, loss[loss=0.1237, simple_loss=0.1943, pruned_loss=0.02655, over 4872.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02883, over 971054.65 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 21:15:30,003 INFO [train.py:715] (5/8) Epoch 16, batch 32450, loss[loss=0.129, simple_loss=0.2072, pruned_loss=0.02542, over 4742.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02915, over 971484.42 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:16:10,032 INFO [train.py:715] (5/8) Epoch 16, batch 32500, loss[loss=0.1446, simple_loss=0.224, pruned_loss=0.0326, over 4819.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02937, over 971796.10 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:16:49,323 INFO [train.py:715] (5/8) Epoch 16, batch 32550, loss[loss=0.1332, simple_loss=0.2174, pruned_loss=0.02448, over 4874.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02944, over 971847.10 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 21:17:28,286 INFO [train.py:715] (5/8) Epoch 16, batch 32600, loss[loss=0.1319, simple_loss=0.1985, pruned_loss=0.03263, over 4788.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 971738.48 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:18:07,199 INFO [train.py:715] (5/8) Epoch 16, batch 32650, loss[loss=0.1111, simple_loss=0.1901, pruned_loss=0.01602, over 4816.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02996, over 971825.01 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:18:46,394 INFO [train.py:715] (5/8) Epoch 16, batch 32700, loss[loss=0.1397, simple_loss=0.2156, pruned_loss=0.03196, over 4888.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02984, over 972287.09 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:19:25,735 INFO [train.py:715] (5/8) Epoch 16, batch 32750, loss[loss=0.1246, simple_loss=0.2069, pruned_loss=0.02117, over 4912.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02978, over 973039.88 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:20:05,460 INFO [train.py:715] (5/8) Epoch 16, batch 32800, loss[loss=0.1279, simple_loss=0.1984, pruned_loss=0.02873, over 4842.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 971893.15 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 21:20:44,827 INFO [train.py:715] (5/8) Epoch 16, batch 32850, loss[loss=0.1423, simple_loss=0.2195, pruned_loss=0.03253, over 4961.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02933, over 971518.16 frames.], batch size: 40, lr: 1.36e-04
2022-05-08 21:21:24,457 INFO [train.py:715] (5/8) Epoch 16, batch 32900, loss[loss=0.1337, simple_loss=0.2049, pruned_loss=0.03124, over 4814.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02948, over 971388.68 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:22:03,427 INFO [train.py:715] (5/8) Epoch 16, batch 32950, loss[loss=0.1549, simple_loss=0.2249, pruned_loss=0.04245, over 4772.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02931, over 971665.17 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:22:42,574 INFO [train.py:715] (5/8) Epoch 16, batch 33000, loss[loss=0.1387, simple_loss=0.2029, pruned_loss=0.03724, over 4792.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02955, over 972080.01 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:22:42,575 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 21:22:55,770 INFO [train.py:742] (5/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01078, over 914524.00 frames.
2022-05-08 21:23:35,555 INFO [train.py:715] (5/8) Epoch 16, batch 33050, loss[loss=0.1193, simple_loss=0.1906, pruned_loss=0.02398, over 4857.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.0292, over 972677.84 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 21:24:14,880 INFO [train.py:715] (5/8) Epoch 16, batch 33100, loss[loss=0.1183, simple_loss=0.1856, pruned_loss=0.02554, over 4951.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02943, over 973385.09 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 21:24:54,241 INFO [train.py:715] (5/8) Epoch 16, batch 33150, loss[loss=0.1392, simple_loss=0.2163, pruned_loss=0.03099, over 4811.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02895, over 973273.41 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:25:34,102 INFO [train.py:715] (5/8) Epoch 16, batch 33200, loss[loss=0.1411, simple_loss=0.2206, pruned_loss=0.03079, over 4813.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02916, over 973061.83 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 21:26:13,843 INFO [train.py:715] (5/8) Epoch 16, batch 33250, loss[loss=0.1527, simple_loss=0.2193, pruned_loss=0.04301, over 4699.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02961, over 972640.98 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:26:53,435 INFO [train.py:715] (5/8) Epoch 16, batch 33300, loss[loss=0.1425, simple_loss=0.2318, pruned_loss=0.02655, over 4880.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02965, over 972990.84 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 21:27:32,747 INFO [train.py:715] (5/8) Epoch 16, batch 33350, loss[loss=0.1154, simple_loss=0.1889, pruned_loss=0.02097, over 4799.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02931, over 973029.92 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:28:12,218 INFO [train.py:715] (5/8) Epoch 16, batch 33400, loss[loss=0.1447, simple_loss=0.2251, pruned_loss=0.03214, over 4901.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.0295, over 973030.64 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:28:51,453 INFO [train.py:715] (5/8) Epoch 16, batch 33450, loss[loss=0.1238, simple_loss=0.193, pruned_loss=0.02733, over 4837.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02943, over 972793.24 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:29:30,509 INFO [train.py:715] (5/8) Epoch 16, batch 33500, loss[loss=0.1253, simple_loss=0.1962, pruned_loss=0.02722, over 4866.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02936, over 972106.29 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:30:09,462 INFO [train.py:715] (5/8) Epoch 16, batch 33550, loss[loss=0.1377, simple_loss=0.2192, pruned_loss=0.02814, over 4762.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02918, over 972017.93 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:30:49,227 INFO [train.py:715] (5/8) Epoch 16, batch 33600, loss[loss=0.1371, simple_loss=0.216, pruned_loss=0.02912, over 4688.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02943, over 972263.80 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:31:28,204 INFO [train.py:715] (5/8) Epoch 16, batch 33650, loss[loss=0.1201, simple_loss=0.1948, pruned_loss=0.02274, over 4930.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02917, over 971921.69 frames.], batch size: 29, lr: 1.36e-04
2022-05-08 21:32:07,846 INFO [train.py:715] (5/8) Epoch 16, batch 33700, loss[loss=0.153, simple_loss=0.2201, pruned_loss=0.04292, over 4975.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 971534.98 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:32:46,797 INFO [train.py:715] (5/8) Epoch 16, batch 33750, loss[loss=0.1398, simple_loss=0.2025, pruned_loss=0.03853, over 4694.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02906, over 971749.75 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:33:25,786 INFO [train.py:715] (5/8) Epoch 16, batch 33800, loss[loss=0.1124, simple_loss=0.1864, pruned_loss=0.01919, over 4828.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02873, over 971670.17 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:34:05,044 INFO [train.py:715] (5/8) Epoch 16, batch 33850, loss[loss=0.1353, simple_loss=0.21, pruned_loss=0.03031, over 4822.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02888, over 972298.45 frames.], batch size: 27, lr: 1.36e-04
2022-05-08 21:34:44,269 INFO [train.py:715] (5/8) Epoch 16, batch 33900, loss[loss=0.1214, simple_loss=0.2005, pruned_loss=0.02115, over 4914.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02881, over 972185.58 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:35:24,623 INFO [train.py:715] (5/8) Epoch 16, batch 33950, loss[loss=0.16, simple_loss=0.241, pruned_loss=0.03951, over 4963.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 972136.95 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:36:03,122 INFO [train.py:715] (5/8) Epoch 16, batch 34000, loss[loss=0.1215, simple_loss=0.195, pruned_loss=0.02397, over 4917.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02913, over 972158.41 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:36:43,151 INFO [train.py:715] (5/8) Epoch 16, batch 34050, loss[loss=0.113, simple_loss=0.1841, pruned_loss=0.02097, over 4938.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 973244.57 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:37:22,557 INFO [train.py:715] (5/8) Epoch 16, batch 34100, loss[loss=0.1631, simple_loss=0.2459, pruned_loss=0.0401, over 4706.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.02939, over 972988.37 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:38:01,718 INFO [train.py:715] (5/8) Epoch 16, batch 34150, loss[loss=0.1563, simple_loss=0.2351, pruned_loss=0.03875, over 4956.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02895, over 972709.75 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:38:41,100 INFO [train.py:715] (5/8) Epoch 16, batch 34200, loss[loss=0.1102, simple_loss=0.1822, pruned_loss=0.01911, over 4907.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02871, over 973264.02 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:39:20,449 INFO [train.py:715] (5/8) Epoch 16, batch 34250, loss[loss=0.1332, simple_loss=0.2065, pruned_loss=0.02996, over 4706.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02905, over 973499.54 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:40:00,529 INFO [train.py:715] (5/8) Epoch 16, batch 34300, loss[loss=0.1259, simple_loss=0.2017, pruned_loss=0.02503, over 4899.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02899, over 972912.42 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:40:39,497 INFO [train.py:715] (5/8) Epoch 16, batch 34350, loss[loss=0.1274, simple_loss=0.205, pruned_loss=0.02485, over 4799.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02967, over 973627.34 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:41:18,851 INFO [train.py:715] (5/8) Epoch 16, batch 34400, loss[loss=0.1249, simple_loss=0.2032, pruned_loss=0.02331, over 4847.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 973103.58 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 21:41:58,452 INFO [train.py:715] (5/8) Epoch 16, batch 34450, loss[loss=0.09544, simple_loss=0.166, pruned_loss=0.01244, over 4807.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02965, over 972791.51 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:42:37,728 INFO [train.py:715] (5/8) Epoch 16, batch 34500, loss[loss=0.1237, simple_loss=0.2023, pruned_loss=0.02252, over 4918.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02969, over 972702.99 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:43:17,126 INFO [train.py:715] (5/8) Epoch 16, batch 34550, loss[loss=0.1191, simple_loss=0.1988, pruned_loss=0.01968, over 4976.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 972874.29 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 21:43:56,245 INFO [train.py:715] (5/8) Epoch 16, batch 34600, loss[loss=0.1657, simple_loss=0.2229, pruned_loss=0.05422, over 4795.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.0298, over 972206.37 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 21:44:36,199 INFO [train.py:715] (5/8) Epoch 16, batch 34650, loss[loss=0.1307, simple_loss=0.1964, pruned_loss=0.03243, over 4990.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02998, over 972184.66 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 21:45:15,693 INFO [train.py:715] (5/8) Epoch 16, batch 34700, loss[loss=0.1304, simple_loss=0.215, pruned_loss=0.02297, over 4977.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02978, over 971643.38 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 21:45:54,802 INFO [train.py:715] (5/8) Epoch 16, batch 34750, loss[loss=0.1345, simple_loss=0.2078, pruned_loss=0.03059, over 4780.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02936, over 971272.88 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:46:32,020 INFO [train.py:715] (5/8) Epoch 16, batch 34800, loss[loss=0.1397, simple_loss=0.2207, pruned_loss=0.02933, over 4931.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02916, over 971443.34 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:47:23,863 INFO [train.py:715] (5/8) Epoch 17, batch 0, loss[loss=0.1232, simple_loss=0.1928, pruned_loss=0.02682, over 4960.00 frames.], tot_loss[loss=0.1232, simple_loss=0.1928, pruned_loss=0.02682, over 4960.00 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 21:48:03,329 INFO [train.py:715] (5/8) Epoch 17, batch 50, loss[loss=0.1032, simple_loss=0.186, pruned_loss=0.01021, over 4839.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2085, pruned_loss=0.02916, over 218896.79 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 21:48:44,385 INFO [train.py:715] (5/8) Epoch 17, batch 100, loss[loss=0.1079, simple_loss=0.1832, pruned_loss=0.01634, over 4808.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03023, over 386085.66 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 21:49:25,331 INFO [train.py:715] (5/8) Epoch 17, batch 150, loss[loss=0.1477, simple_loss=0.2201, pruned_loss=0.03762, over 4802.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03044, over 515370.90 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 21:50:06,393 INFO [train.py:715] (5/8) Epoch 17, batch 200, loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02942, over 4963.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03033, over 617412.78 frames.], batch size: 35, lr: 1.32e-04
2022-05-08 21:50:49,386 INFO [train.py:715] (5/8) Epoch 17, batch 250, loss[loss=0.1035, simple_loss=0.166, pruned_loss=0.02054, over 4750.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02997, over 695873.91 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 21:51:30,986 INFO [train.py:715] (5/8) Epoch 17, batch 300, loss[loss=0.1287, simple_loss=0.207, pruned_loss=0.02515, over 4949.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03026, over 758201.91 frames.], batch size: 23, lr: 1.32e-04
2022-05-08 21:52:11,854 INFO [train.py:715] (5/8) Epoch 17, batch 350, loss[loss=0.1083, simple_loss=0.1808, pruned_loss=0.01792, over 4943.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02982, over 805836.89 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 21:52:52,792 INFO [train.py:715] (5/8) Epoch 17, batch 400, loss[loss=0.1089, simple_loss=0.1801, pruned_loss=0.01891, over 4827.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 842541.62 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 21:53:33,713 INFO [train.py:715] (5/8) Epoch 17, batch 450, loss[loss=0.1658, simple_loss=0.231, pruned_loss=0.0503, over 4898.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02921, over 871228.33 frames.], batch size: 39, lr: 1.32e-04
2022-05-08 21:54:14,771 INFO [train.py:715] (5/8) Epoch 17, batch 500, loss[loss=0.1534, simple_loss=0.2294, pruned_loss=0.03871, over 4971.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 893909.71 frames.], batch size: 35, lr: 1.32e-04
2022-05-08 21:54:56,771 INFO [train.py:715] (5/8) Epoch 17, batch 550, loss[loss=0.1145, simple_loss=0.1933, pruned_loss=0.01783, over 4827.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02931, over 911156.99 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 21:55:37,896 INFO [train.py:715] (5/8) Epoch 17, batch 600, loss[loss=0.1425, simple_loss=0.2178, pruned_loss=0.03361, over 4762.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02916, over 923730.14 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 21:56:20,091 INFO [train.py:715] (5/8) Epoch 17, batch 650, loss[loss=0.1285, simple_loss=0.2122, pruned_loss=0.02236, over 4950.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02896, over 934316.19 frames.], batch size: 29, lr: 1.32e-04
2022-05-08 21:57:01,709 INFO [train.py:715] (5/8) Epoch 17, batch 700, loss[loss=0.1299, simple_loss=0.2005, pruned_loss=0.02969, over 4837.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.0294, over 942765.60 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 21:57:42,595 INFO [train.py:715] (5/8) Epoch 17, batch 750, loss[loss=0.139, simple_loss=0.2235, pruned_loss=0.02727, over 4694.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02935, over 949173.89 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 21:58:23,377 INFO [train.py:715] (5/8) Epoch 17, batch 800, loss[loss=0.1359, simple_loss=0.1975, pruned_loss=0.03709, over 4872.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02903, over 954606.22 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 21:59:03,981 INFO [train.py:715] (5/8) Epoch 17, batch 850, loss[loss=0.1326, simple_loss=0.2145, pruned_loss=0.02533, over 4917.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.0285, over 959440.49 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 21:59:45,396 INFO [train.py:715] (5/8) Epoch 17, batch 900, loss[loss=0.1124, simple_loss=0.1902, pruned_loss=0.01733, over 4913.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02905, over 962091.57 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:00:26,270 INFO [train.py:715] (5/8) Epoch 17, batch 950, loss[loss=0.1142, simple_loss=0.1974, pruned_loss=0.01555, over 4926.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02949, over 964630.31 frames.], batch size: 29, lr: 1.32e-04
2022-05-08 22:01:07,641 INFO [train.py:715] (5/8) Epoch 17, batch 1000, loss[loss=0.101, simple_loss=0.18, pruned_loss=0.01103, over 4878.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02916, over 966461.01 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:01:48,889 INFO [train.py:715] (5/8) Epoch 17, batch 1050, loss[loss=0.1442, simple_loss=0.2125, pruned_loss=0.03796, over 4641.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02921, over 967278.35 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:02:29,881 INFO [train.py:715] (5/8) Epoch 17, batch 1100, loss[loss=0.1225, simple_loss=0.2012, pruned_loss=0.0219, over 4988.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02972, over 968449.18 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:03:10,392 INFO [train.py:715] (5/8) Epoch 17, batch 1150, loss[loss=0.1357, simple_loss=0.221, pruned_loss=0.02525, over 4825.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03005, over 969788.16 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:03:51,861 INFO [train.py:715] (5/8) Epoch 17, batch 1200, loss[loss=0.1232, simple_loss=0.1956, pruned_loss=0.02537, over 4762.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03034, over 970228.92 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:04:32,826 INFO [train.py:715] (5/8) Epoch 17, batch 1250, loss[loss=0.1199, simple_loss=0.1973, pruned_loss=0.02121, over 4759.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03021, over 970685.32 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:05:13,883 INFO [train.py:715] (5/8) Epoch 17, batch 1300, loss[loss=0.1342, simple_loss=0.1996, pruned_loss=0.03434, over 4817.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03028, over 971518.30 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 22:05:55,244 INFO [train.py:715] (5/8) Epoch 17, batch 1350, loss[loss=0.1097, simple_loss=0.1854, pruned_loss=0.01698, over 4698.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03011, over 972167.68 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:06:36,199 INFO [train.py:715] (5/8) Epoch 17, batch 1400, loss[loss=0.1504, simple_loss=0.2192, pruned_loss=0.04084, over 4861.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03084, over 971044.15 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:07:16,800 INFO [train.py:715] (5/8) Epoch 17, batch 1450, loss[loss=0.137, simple_loss=0.2068, pruned_loss=0.03361, over 4871.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03083, over 971561.33 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:07:57,515 INFO [train.py:715] (5/8) Epoch 17, batch 1500, loss[loss=0.1453, simple_loss=0.2163, pruned_loss=0.03719, over 4986.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03052, over 971961.36 frames.], batch size: 39, lr: 1.32e-04
2022-05-08 22:08:39,011 INFO [train.py:715] (5/8) Epoch 17, batch 1550, loss[loss=0.1263, simple_loss=0.2033, pruned_loss=0.02463, over 4853.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03051, over 972080.65 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 22:09:20,353 INFO [train.py:715] (5/8) Epoch 17, batch 1600, loss[loss=0.1302, simple_loss=0.201, pruned_loss=0.02968, over 4987.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03002, over 972606.49 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:10:01,027 INFO [train.py:715] (5/8) Epoch 17, batch 1650, loss[loss=0.1492, simple_loss=0.2227, pruned_loss=0.03783, over 4788.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.0296, over 972092.94 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:10:42,367 INFO [train.py:715] (5/8) Epoch 17, batch 1700, loss[loss=0.1503, simple_loss=0.2182, pruned_loss=0.04117, over 4771.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02941, over 971771.79 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:11:23,610 INFO [train.py:715] (5/8) Epoch 17, batch 1750, loss[loss=0.1537, simple_loss=0.213, pruned_loss=0.04723, over 4860.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02954, over 971955.33 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:12:04,539 INFO [train.py:715] (5/8) Epoch 17, batch 1800, loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03265, over 4839.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02938, over 971821.66 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:12:45,638 INFO [train.py:715] (5/8) Epoch 17, batch 1850, loss[loss=0.1497, simple_loss=0.2112, pruned_loss=0.04409, over 4951.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02964, over 971556.17 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:13:27,331 INFO [train.py:715] (5/8) Epoch 17, batch 1900, loss[loss=0.1305, simple_loss=0.1965, pruned_loss=0.0322, over 4698.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02974, over 971401.08 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:14:08,484 INFO [train.py:715] (5/8) Epoch 17, batch 1950, loss[loss=0.1296, simple_loss=0.2128, pruned_loss=0.02323, over 4754.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02928, over 970693.58 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:14:49,372 INFO [train.py:715] (5/8) Epoch 17, batch 2000, loss[loss=0.1543, simple_loss=0.2203, pruned_loss=0.04416, over 4758.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02915, over 971183.90 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:15:30,343 INFO [train.py:715] (5/8) Epoch 17, batch 2050, loss[loss=0.1317, simple_loss=0.2136, pruned_loss=0.0249, over 4940.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 971956.63 frames.], batch size: 23, lr: 1.32e-04
2022-05-08 22:16:11,452 INFO [train.py:715] (5/8) Epoch 17, batch 2100, loss[loss=0.1303, simple_loss=0.1972, pruned_loss=0.03176, over 4970.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.0284, over 972909.13 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:16:52,788 INFO [train.py:715] (5/8) Epoch 17, batch 2150, loss[loss=0.1117, simple_loss=0.1854, pruned_loss=0.01895, over 4845.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02815, over 971609.97 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:17:34,183 INFO [train.py:715] (5/8) Epoch 17, batch 2200, loss[loss=0.1235, simple_loss=0.2014, pruned_loss=0.02278, over 4841.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.0284, over 971708.00 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 22:18:15,307 INFO [train.py:715] (5/8) Epoch 17, batch 2250, loss[loss=0.1199, simple_loss=0.1979, pruned_loss=0.02101, over 4799.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02891, over 971612.52 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:18:56,041 INFO [train.py:715] (5/8) Epoch 17, batch 2300, loss[loss=0.1288, simple_loss=0.1946, pruned_loss=0.03151, over 4821.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02895, over 972199.94 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:19:36,478 INFO [train.py:715] (5/8) Epoch 17, batch 2350, loss[loss=0.155, simple_loss=0.2193, pruned_loss=0.04537, over 4868.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02915, over 971802.15 frames.], batch size: 32, lr: 1.32e-04
2022-05-08 22:20:17,318 INFO [train.py:715] (5/8) Epoch 17, batch 2400, loss[loss=0.1364, simple_loss=0.2153, pruned_loss=0.02877, over 4773.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02853, over 972296.80 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:20:58,226 INFO [train.py:715] (5/8) Epoch 17, batch 2450, loss[loss=0.1219, simple_loss=0.1919, pruned_loss=0.02593, over 4755.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02893, over 972713.97 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 22:21:39,040 INFO [train.py:715] (5/8) Epoch 17, batch 2500, loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02925, over 4831.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02941, over 971722.53 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:22:20,005 INFO [train.py:715] (5/8) Epoch 17, batch 2550, loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03411, over 4960.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 972157.46 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:23:00,960 INFO [train.py:715] (5/8) Epoch 17, batch 2600, loss[loss=0.1241, simple_loss=0.1953, pruned_loss=0.02643, over 4807.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02871, over 972331.42 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:23:42,201 INFO [train.py:715] (5/8) Epoch 17, batch 2650, loss[loss=0.09855, simple_loss=0.1719, pruned_loss=0.01261, over 4739.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02871, over 972704.98 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:24:22,845 INFO [train.py:715] (5/8) Epoch 17, batch 2700, loss[loss=0.1257, simple_loss=0.2127, pruned_loss=0.01931, over 4842.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02909, over 972814.15 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 22:25:04,064 INFO [train.py:715] (5/8) Epoch 17, batch 2750, loss[loss=0.111, simple_loss=0.1848, pruned_loss=0.01864, over 4967.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02875, over 974291.72 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:25:44,577 INFO [train.py:715] (5/8) Epoch 17, batch 2800, loss[loss=0.1169, simple_loss=0.2064, pruned_loss=0.01365, over 4779.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02904, over 973817.41 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:26:25,557 INFO [train.py:715] (5/8) Epoch 17, batch 2850, loss[loss=0.1109, simple_loss=0.189, pruned_loss=0.01635, over 4834.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02914, over 972934.33 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:27:06,299 INFO [train.py:715] (5/8) Epoch 17, batch 2900, loss[loss=0.1135, simple_loss=0.195, pruned_loss=0.01596, over 4936.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02901, over 972339.34 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:27:47,264 INFO [train.py:715] (5/8) Epoch 17, batch 2950, loss[loss=0.135, simple_loss=0.2196, pruned_loss=0.0252, over 4745.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02914, over 972062.52 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:28:28,419 INFO [train.py:715] (5/8) Epoch 17, batch 3000, loss[loss=0.115, simple_loss=0.1867, pruned_loss=0.02167, over 4906.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.0289, over 972176.39 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:28:28,420 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 22:28:43,492 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.01063, over 914524.00 frames.
2022-05-08 22:29:24,680 INFO [train.py:715] (5/8) Epoch 17, batch 3050, loss[loss=0.1048, simple_loss=0.1817, pruned_loss=0.01399, over 4917.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02906, over 973059.59 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:30:05,287 INFO [train.py:715] (5/8) Epoch 17, batch 3100, loss[loss=0.1257, simple_loss=0.2077, pruned_loss=0.0219, over 4982.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02929, over 972963.69 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:30:46,409 INFO [train.py:715] (5/8) Epoch 17, batch 3150, loss[loss=0.1317, simple_loss=0.2084, pruned_loss=0.0275, over 4920.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 972151.43 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:31:26,339 INFO [train.py:715] (5/8) Epoch 17, batch 3200, loss[loss=0.1236, simple_loss=0.1928, pruned_loss=0.02723, over 4974.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.02999, over 972782.87 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:32:07,676 INFO [train.py:715] (5/8) Epoch 17, batch 3250, loss[loss=0.1397, simple_loss=0.2166, pruned_loss=0.03138, over 4802.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2072, pruned_loss=0.03011, over 973344.08 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:32:47,740 INFO [train.py:715] (5/8) Epoch 17, batch 3300, loss[loss=0.1443, simple_loss=0.2203, pruned_loss=0.03417, over 4949.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03019, over 974097.79 frames.], batch size: 40, lr: 1.32e-04
2022-05-08 22:33:28,434 INFO [train.py:715] (5/8) Epoch 17, batch 3350, loss[loss=0.11, simple_loss=0.1847, pruned_loss=0.01763, over 4910.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03001, over 974025.68 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:34:09,185 INFO [train.py:715] (5/8) Epoch 17, batch 3400, loss[loss=0.1612, simple_loss=0.2374, pruned_loss=0.04246, over 4875.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03039, over 974184.18 frames.], batch size: 39, lr: 1.32e-04
2022-05-08 22:34:50,597 INFO [train.py:715] (5/8) Epoch 17, batch 3450, loss[loss=0.1221, simple_loss=0.1976, pruned_loss=0.02331, over 4861.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02985, over 973540.30 frames.], batch size: 34, lr: 1.32e-04
2022-05-08 22:35:30,944 INFO [train.py:715] (5/8) Epoch 17, batch 3500, loss[loss=0.1245, simple_loss=0.2107, pruned_loss=0.01918, over 4941.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02971, over 973208.07 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:36:11,164 INFO [train.py:715] (5/8) Epoch 17, batch 3550, loss[loss=0.1177, simple_loss=0.1936, pruned_loss=0.02093, over 4939.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02997, over 973219.42 frames.], batch size: 29, lr: 1.32e-04
2022-05-08 22:36:52,128 INFO [train.py:715] (5/8) Epoch 17, batch 3600, loss[loss=0.1272, simple_loss=0.2081, pruned_loss=0.02309, over 4823.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.0296, over 972433.96 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 22:37:31,756 INFO [train.py:715] (5/8) Epoch 17, batch 3650, loss[loss=0.1547, simple_loss=0.2218, pruned_loss=0.04381, over 4829.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2063, pruned_loss=0.02958, over 971989.76 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:38:11,927 INFO [train.py:715] (5/8) Epoch 17, batch 3700, loss[loss=0.1316, simple_loss=0.2126, pruned_loss=0.02527, over 4691.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02969, over 971669.08 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:38:52,845 INFO [train.py:715] (5/8) Epoch 17, batch 3750, loss[loss=0.1138, simple_loss=0.1857, pruned_loss=0.02095, over 4946.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.0294, over 972955.68 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:39:33,615 INFO [train.py:715] (5/8) Epoch 17, batch 3800, loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03575, over 4912.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02947, over 974108.28 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:40:14,220 INFO [train.py:715] (5/8) Epoch 17, batch 3850, loss[loss=0.1002, simple_loss=0.1734, pruned_loss=0.01345, over 4891.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02936, over 973949.09 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:40:54,280 INFO [train.py:715] (5/8) Epoch 17, batch 3900, loss[loss=0.144, simple_loss=0.2271, pruned_loss=0.03047, over 4770.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02956, over 973347.99 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:41:35,758 INFO [train.py:715] (5/8) Epoch 17, batch 3950, loss[loss=0.1, simple_loss=0.1668, pruned_loss=0.01663, over 4970.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02946, over 973595.81 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:42:15,633 INFO [train.py:715] (5/8) Epoch 17, batch 4000, loss[loss=0.1225, simple_loss=0.1897, pruned_loss=0.02761, over 4851.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02934, over 973122.95 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:42:56,133 INFO [train.py:715] (5/8) Epoch 17, batch 4050, loss[loss=0.1167, simple_loss=0.1917, pruned_loss=0.02092, over 4880.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02917, over 972747.99 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:43:36,613 INFO [train.py:715] (5/8) Epoch 17, batch 4100, loss[loss=0.1355, simple_loss=0.1982, pruned_loss=0.03638, over 4847.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02887, over 972355.42 frames.], batch size: 34, lr: 1.32e-04
2022-05-08 22:44:17,667 INFO [train.py:715] (5/8) Epoch 17, batch 4150, loss[loss=0.1235, simple_loss=0.1932, pruned_loss=0.0269, over 4911.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.0288, over 973224.19 frames.], batch size: 29, lr: 1.32e-04
2022-05-08 22:44:56,902 INFO [train.py:715] (5/8) Epoch 17, batch 4200, loss[loss=0.118, simple_loss=0.2052, pruned_loss=0.01544, over 4800.00 frames.], tot_loss[loss=0.1322, simple_loss=0.206, pruned_loss=0.02919, over 972373.68 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:45:36,944 INFO [train.py:715] (5/8) Epoch 17, batch 4250, loss[loss=0.1545, simple_loss=0.2276, pruned_loss=0.0407, over 4750.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0299, over 971631.87 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:46:18,118 INFO [train.py:715] (5/8) Epoch 17, batch 4300, loss[loss=0.145, simple_loss=0.2161, pruned_loss=0.03692, over 4810.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 971224.62 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 22:46:58,167 INFO [train.py:715] (5/8) Epoch 17, batch 4350, loss[loss=0.1198, simple_loss=0.1968, pruned_loss=0.02136, over 4757.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02979, over 970912.52 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 22:47:38,038 INFO [train.py:715] (5/8) Epoch 17, batch 4400, loss[loss=0.1637, simple_loss=0.2231, pruned_loss=0.05214, over 4965.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.0299, over 971336.55 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 22:48:18,895 INFO [train.py:715] (5/8) Epoch 17, batch 4450, loss[loss=0.1131, simple_loss=0.1969, pruned_loss=0.01464, over 4803.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02965, over 971088.42 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 22:48:59,883 INFO [train.py:715] (5/8) Epoch 17, batch 4500, loss[loss=0.1227, simple_loss=0.1963, pruned_loss=0.02456, over 4804.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02981, over 971321.70 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 22:49:39,759 INFO [train.py:715] (5/8) Epoch 17, batch 4550, loss[loss=0.123, simple_loss=0.1951, pruned_loss=0.02539, over 4768.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02928, over 971232.64 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:50:20,190 INFO [train.py:715] (5/8) Epoch 17, batch 4600, loss[loss=0.1538, simple_loss=0.2242, pruned_loss=0.04172, over 4830.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02949, over 971525.75 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 22:51:01,212 INFO [train.py:715] (5/8) Epoch 17, batch 4650, loss[loss=0.1288, simple_loss=0.2026, pruned_loss=0.0275, over 4944.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02964, over 972068.59 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 22:51:41,118 INFO [train.py:715] (5/8) Epoch 17, batch 4700, loss[loss=0.1226, simple_loss=0.1856, pruned_loss=0.02974, over 4798.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.0296, over 973053.21 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 22:52:21,064 INFO [train.py:715] (5/8) Epoch 17, batch 4750, loss[loss=0.1519, simple_loss=0.2258, pruned_loss=0.03901, over 4884.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03014, over 972930.13 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 22:53:02,043 INFO [train.py:715] (5/8) Epoch 17, batch 4800, loss[loss=0.1235, simple_loss=0.204, pruned_loss=0.02146, over 4924.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02997, over 973627.29 frames.], batch size: 29, lr: 1.31e-04
2022-05-08 22:53:42,825 INFO [train.py:715] (5/8) Epoch 17, batch 4850, loss[loss=0.1195, simple_loss=0.1893, pruned_loss=0.02484, over 4812.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02974, over 973592.31 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 22:54:22,664 INFO [train.py:715] (5/8) Epoch 17, batch 4900, loss[loss=0.1488, simple_loss=0.2237, pruned_loss=0.03693, over 4977.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02954, over 973295.13 frames.], batch size: 31, lr: 1.31e-04
2022-05-08 22:55:03,095 INFO [train.py:715] (5/8) Epoch 17, batch 4950, loss[loss=0.175, simple_loss=0.2468, pruned_loss=0.05162, over 4833.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02968, over 972941.11 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 22:55:44,138 INFO [train.py:715] (5/8) Epoch 17, batch 5000, loss[loss=0.1271, simple_loss=0.2088, pruned_loss=0.0227, over 4773.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 973021.43 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:56:24,632 INFO [train.py:715] (5/8) Epoch 17, batch 5050, loss[loss=0.136, simple_loss=0.2085, pruned_loss=0.0317, over 4852.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02928, over 973458.85 frames.], batch size: 20, lr: 1.31e-04
2022-05-08 22:57:04,162 INFO [train.py:715] (5/8) Epoch 17, batch 5100, loss[loss=0.1526, simple_loss=0.2279, pruned_loss=0.03861, over 4772.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.0287, over 973999.61 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:57:44,981 INFO [train.py:715] (5/8) Epoch 17, batch 5150, loss[loss=0.1374, simple_loss=0.208, pruned_loss=0.03337, over 4982.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02843, over 973973.76 frames.], batch size: 28, lr: 1.31e-04
2022-05-08 22:58:26,125 INFO [train.py:715] (5/8) Epoch 17, batch 5200, loss[loss=0.1279, simple_loss=0.2108, pruned_loss=0.02253, over 4955.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02845, over 974026.77 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 22:59:05,339 INFO [train.py:715] (5/8) Epoch 17, batch 5250, loss[loss=0.1349, simple_loss=0.2137, pruned_loss=0.0281, over 4791.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02867, over 974345.57 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:59:44,887 INFO [train.py:715] (5/8) Epoch 17, batch 5300, loss[loss=0.1374, simple_loss=0.2194, pruned_loss=0.02773, over 4835.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02886, over 974420.06 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:00:25,451 INFO [train.py:715] (5/8) Epoch 17, batch 5350, loss[loss=0.1376, simple_loss=0.2134, pruned_loss=0.03093, over 4934.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02894, over 973850.71 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:01:06,238 INFO [train.py:715] (5/8) Epoch 17, batch 5400, loss[loss=0.1532, simple_loss=0.2326, pruned_loss=0.03689, over 4840.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02918, over 973876.99 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:01:45,348 INFO [train.py:715] (5/8) Epoch 17, batch 5450, loss[loss=0.1629, simple_loss=0.2253, pruned_loss=0.05027, over 4700.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02964, over 973040.84 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:02:26,548 INFO [train.py:715] (5/8) Epoch 17, batch 5500, loss[loss=0.1281, simple_loss=0.2, pruned_loss=0.02808, over 4846.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03003, over 973691.26 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:03:07,878 INFO [train.py:715] (5/8) Epoch 17, batch 5550, loss[loss=0.1596, simple_loss=0.2346, pruned_loss=0.04226, over 4772.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02997, over 973652.53 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:03:46,989 INFO [train.py:715] (5/8) Epoch 17, batch 5600, loss[loss=0.1351, simple_loss=0.2109, pruned_loss=0.02964, over 4781.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02969, over 973191.31 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:04:27,248 INFO [train.py:715] (5/8) Epoch 17, batch 5650, loss[loss=0.1333, simple_loss=0.2016, pruned_loss=0.03246, over 4810.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02948, over 972539.75 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:05:08,283 INFO [train.py:715] (5/8) Epoch 17, batch 5700, loss[loss=0.1334, simple_loss=0.2057, pruned_loss=0.03059, over 4984.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.0292, over 972678.59 frames.], batch size: 35, lr: 1.31e-04
2022-05-08 23:05:48,475 INFO [train.py:715] (5/8) Epoch 17, batch 5750, loss[loss=0.1493, simple_loss=0.216, pruned_loss=0.04132, over 4770.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02953, over 972076.29 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:06:27,752 INFO [train.py:715] (5/8) Epoch 17, batch 5800, loss[loss=0.1223, simple_loss=0.1922, pruned_loss=0.02615, over 4821.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 972933.51 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:07:08,773 INFO [train.py:715] (5/8) Epoch 17, batch 5850, loss[loss=0.1285, simple_loss=0.205, pruned_loss=0.02595, over 4949.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02901, over 973149.84 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:07:49,080 INFO [train.py:715] (5/8) Epoch 17, batch 5900, loss[loss=0.1263, simple_loss=0.1994, pruned_loss=0.02664, over 4744.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02883, over 972756.45 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:08:29,706 INFO [train.py:715] (5/8) Epoch 17, batch 5950, loss[loss=0.1419, simple_loss=0.2072, pruned_loss=0.03824, over 4857.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 971616.96 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:09:09,142 INFO [train.py:715] (5/8) Epoch 17, batch 6000, loss[loss=0.1082, simple_loss=0.1798, pruned_loss=0.0183, over 4897.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 971905.34 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:09:09,143 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 23:09:23,454 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01069, over 914524.00 frames.
2022-05-08 23:10:02,838 INFO [train.py:715] (5/8) Epoch 17, batch 6050, loss[loss=0.1448, simple_loss=0.218, pruned_loss=0.03579, over 4954.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02924, over 972128.75 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:10:43,310 INFO [train.py:715] (5/8) Epoch 17, batch 6100, loss[loss=0.1237, simple_loss=0.1958, pruned_loss=0.02579, over 4904.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02955, over 972128.42 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:11:22,422 INFO [train.py:715] (5/8) Epoch 17, batch 6150, loss[loss=0.1277, simple_loss=0.2065, pruned_loss=0.02441, over 4969.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.0289, over 972618.48 frames.], batch size: 35, lr: 1.31e-04
2022-05-08 23:12:02,005 INFO [train.py:715] (5/8) Epoch 17, batch 6200, loss[loss=0.148, simple_loss=0.2247, pruned_loss=0.03564, over 4760.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02872, over 972992.93 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:12:42,482 INFO [train.py:715] (5/8) Epoch 17, batch 6250, loss[loss=0.1324, simple_loss=0.2022, pruned_loss=0.03125, over 4939.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02901, over 971899.80 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:13:22,264 INFO [train.py:715] (5/8) Epoch 17, batch 6300, loss[loss=0.1279, simple_loss=0.2083, pruned_loss=0.02378, over 4708.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02864, over 971525.52 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:14:01,677 INFO [train.py:715] (5/8) Epoch 17, batch 6350, loss[loss=0.1328, simple_loss=0.21, pruned_loss=0.02775, over 4968.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02875, over 971567.47 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:14:41,495 INFO [train.py:715] (5/8) Epoch 17, batch 6400, loss[loss=0.1443, simple_loss=0.2053, pruned_loss=0.04169, over 4857.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 971400.15 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:15:21,777 INFO [train.py:715] (5/8) Epoch 17, batch 6450, loss[loss=0.09452, simple_loss=0.1696, pruned_loss=0.00972, over 4865.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02895, over 972063.93 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:16:01,144 INFO [train.py:715] (5/8) Epoch 17, batch 6500, loss[loss=0.1454, simple_loss=0.2223, pruned_loss=0.03423, over 4944.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.029, over 972328.73 frames.], batch size: 35, lr: 1.31e-04
2022-05-08 23:16:40,475 INFO [train.py:715] (5/8) Epoch 17, batch 6550, loss[loss=0.134, simple_loss=0.207, pruned_loss=0.03053, over 4905.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02966, over 972836.11 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:17:20,843 INFO [train.py:715] (5/8) Epoch 17, batch 6600, loss[loss=0.1367, simple_loss=0.2076, pruned_loss=0.03291, over 4746.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03032, over 971892.75 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:18:01,036 INFO [train.py:715] (5/8) Epoch 17, batch 6650, loss[loss=0.1473, simple_loss=0.2231, pruned_loss=0.03575, over 4756.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02997, over 972258.52 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:18:40,480 INFO [train.py:715] (5/8) Epoch 17, batch 6700, loss[loss=0.1173, simple_loss=0.1888, pruned_loss=0.02295, over 4840.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02988, over 972358.90 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:19:20,726 INFO [train.py:715] (5/8) Epoch 17, batch 6750, loss[loss=0.1094, simple_loss=0.1853, pruned_loss=0.01674, over 4812.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02991, over 971577.61 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:20:00,495 INFO [train.py:715] (5/8) Epoch 17, batch 6800, loss[loss=0.1166, simple_loss=0.1967, pruned_loss=0.01828, over 4936.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03012, over 972781.80 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:20:41,161 INFO [train.py:715] (5/8) Epoch 17, batch 6850, loss[loss=0.1373, simple_loss=0.2187, pruned_loss=0.02797, over 4960.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03005, over 972545.31 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:21:20,240 INFO [train.py:715] (5/8) Epoch 17, batch 6900, loss[loss=0.1234, simple_loss=0.1967, pruned_loss=0.02506, over 4986.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03028, over 972996.58 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:22:00,929 INFO [train.py:715] (5/8) Epoch 17, batch 6950, loss[loss=0.1252, simple_loss=0.201, pruned_loss=0.02475, over 4857.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.0306, over 972638.69 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:22:40,662 INFO [train.py:715] (5/8) Epoch 17, batch 7000, loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.0423, over 4766.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.0302, over 972153.86 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:23:20,236 INFO [train.py:715] (5/8) Epoch 17, batch 7050, loss[loss=0.16, simple_loss=0.2247, pruned_loss=0.04767, over 4847.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03035, over 973277.36 frames.], batch size: 34, lr: 1.31e-04
2022-05-08 23:24:00,497 INFO [train.py:715] (5/8) Epoch 17, batch 7100, loss[loss=0.1376, simple_loss=0.2103, pruned_loss=0.03246, over 4975.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03002, over 973562.34 frames.], batch size: 33, lr: 1.31e-04
2022-05-08 23:24:40,019 INFO [train.py:715] (5/8) Epoch 17, batch 7150, loss[loss=0.1085, simple_loss=0.1846, pruned_loss=0.01616, over 4933.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0299, over 974208.44 frames.], batch size: 29, lr: 1.31e-04
2022-05-08 23:25:19,631 INFO [train.py:715] (5/8) Epoch 17, batch 7200, loss[loss=0.1512, simple_loss=0.22, pruned_loss=0.0412, over 4855.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 973639.09 frames.], batch size: 34, lr: 1.31e-04
2022-05-08 23:25:58,581 INFO [train.py:715] (5/8) Epoch 17, batch 7250, loss[loss=0.1597, simple_loss=0.2199, pruned_loss=0.04978, over 4854.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 973819.16 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:26:39,072 INFO [train.py:715] (5/8) Epoch 17, batch 7300, loss[loss=0.1237, simple_loss=0.1824, pruned_loss=0.03247, over 4828.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02882, over 973771.22 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:27:18,025 INFO [train.py:715] (5/8) Epoch 17, batch 7350, loss[loss=0.1203, simple_loss=0.1996, pruned_loss=0.02055, over 4714.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.0283, over 973407.39 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:27:56,386 INFO [train.py:715] (5/8) Epoch 17, batch 7400, loss[loss=0.1328, simple_loss=0.2036, pruned_loss=0.03096, over 4987.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02843, over 972951.28 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:28:36,429 INFO [train.py:715] (5/8) Epoch 17, batch 7450, loss[loss=0.1241, simple_loss=0.2038, pruned_loss=0.02217, over 4972.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02837, over 973503.04 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:29:15,432 INFO [train.py:715] (5/8) Epoch 17, batch 7500, loss[loss=0.1434, simple_loss=0.2195, pruned_loss=0.03364, over 4838.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02869, over 973589.65 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:29:55,163 INFO [train.py:715] (5/8) Epoch 17, batch 7550, loss[loss=0.1387, simple_loss=0.2152, pruned_loss=0.03108, over 4895.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.0288, over 973585.93 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:30:34,487 INFO [train.py:715] (5/8) Epoch 17, batch 7600, loss[loss=0.131, simple_loss=0.2045, pruned_loss=0.02872, over 4848.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02902, over 974090.57 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:31:14,609 INFO [train.py:715] (5/8) Epoch 17, batch 7650, loss[loss=0.1519, simple_loss=0.2381, pruned_loss=0.03287, over 4833.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 973667.31 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:31:54,496 INFO [train.py:715] (5/8) Epoch 17, batch 7700, loss[loss=0.1255, simple_loss=0.2006, pruned_loss=0.02521, over 4950.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02885, over 973796.88 frames.], batch size: 29, lr: 1.31e-04
2022-05-08 23:32:33,789 INFO [train.py:715] (5/8) Epoch 17, batch 7750, loss[loss=0.1447, simple_loss=0.2208, pruned_loss=0.03431, over 4807.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02825, over 972975.07 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:33:14,387 INFO [train.py:715] (5/8) Epoch 17, batch 7800, loss[loss=0.1351, simple_loss=0.2102, pruned_loss=0.02996, over 4796.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02854, over 972391.47 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:33:54,604 INFO [train.py:715] (5/8) Epoch 17, batch 7850, loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03436, over 4968.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02899, over 972157.03 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:34:34,851 INFO [train.py:715] (5/8) Epoch 17, batch 7900, loss[loss=0.1451, simple_loss=0.2272, pruned_loss=0.0315, over 4715.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02889, over 972253.94 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:35:13,814 INFO [train.py:715] (5/8) Epoch 17, batch 7950, loss[loss=0.1134, simple_loss=0.1808, pruned_loss=0.02298, over 4854.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02833, over 972071.48 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:35:53,564 INFO [train.py:715] (5/8) Epoch 17, batch 8000, loss[loss=0.1712, simple_loss=0.2423, pruned_loss=0.05003, over 4784.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02876, over 971664.82 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:36:33,459 INFO [train.py:715] (5/8) Epoch 17, batch 8050, loss[loss=0.1286, simple_loss=0.2106, pruned_loss=0.02325, over 4885.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02946, over 972156.02 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:37:12,795 INFO [train.py:715] (5/8) Epoch 17, batch 8100, loss[loss=0.1275, simple_loss=0.1957, pruned_loss=0.02962, over 4646.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02943, over 971561.97 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:37:52,688 INFO [train.py:715] (5/8) Epoch 17, batch 8150, loss[loss=0.1082, simple_loss=0.1825, pruned_loss=0.01694, over 4976.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 971893.59 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:38:32,362 INFO [train.py:715] (5/8) Epoch 17, batch 8200, loss[loss=0.1309, simple_loss=0.2026, pruned_loss=0.02962, over 4939.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02957, over 972199.36 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:39:14,691 INFO [train.py:715] (5/8) Epoch 17, batch 8250, loss[loss=0.1398, simple_loss=0.2136, pruned_loss=0.03299, over 4903.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.0292, over 973030.04 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:39:53,903 INFO [train.py:715] (5/8) Epoch 17, batch 8300, loss[loss=0.1418, simple_loss=0.2236, pruned_loss=0.03004, over 4772.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02958, over 973027.99 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:40:33,622 INFO [train.py:715] (5/8) Epoch 17, batch 8350, loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03249, over 4776.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.0292, over 972575.28 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:41:13,213 INFO [train.py:715] (5/8) Epoch 17, batch 8400, loss[loss=0.1166, simple_loss=0.1931, pruned_loss=0.02007, over 4978.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02945, over 973467.35 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:41:52,764 INFO [train.py:715] (5/8) Epoch 17, batch 8450, loss[loss=0.09887, simple_loss=0.177, pruned_loss=0.01034, over 4982.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02949, over 973355.40 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:42:32,330 INFO [train.py:715] (5/8) Epoch 17, batch 8500, loss[loss=0.1189, simple_loss=0.2031, pruned_loss=0.01737, over 4812.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02943, over 973247.78 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:43:12,144 INFO [train.py:715] (5/8) Epoch 17, batch 8550, loss[loss=0.1443, simple_loss=0.2178, pruned_loss=0.0354, over 4838.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02957, over 972849.00 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:43:52,009 INFO [train.py:715] (5/8) Epoch 17, batch 8600, loss[loss=0.1439, simple_loss=0.2129, pruned_loss=0.03743, over 4733.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02934, over 972654.97 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:44:31,014 INFO [train.py:715] (5/8) Epoch 17, batch 8650, loss[loss=0.1163, simple_loss=0.1847, pruned_loss=0.02397, over 4752.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02913, over 971720.52 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:45:10,884 INFO [train.py:715] (5/8) Epoch 17, batch 8700, loss[loss=0.1438, simple_loss=0.2232, pruned_loss=0.03214, over 4962.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02968, over 971984.07 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:45:50,294 INFO [train.py:715] (5/8) Epoch 17, batch 8750, loss[loss=0.1313, simple_loss=0.2027, pruned_loss=0.02991, over 4961.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02984, over 971735.89 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:46:29,857 INFO [train.py:715] (5/8) Epoch 17, batch 8800, loss[loss=0.1187, simple_loss=0.1938, pruned_loss=0.02183, over 4786.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02995, over 972081.40 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:47:09,590 INFO [train.py:715] (5/8) Epoch 17, batch 8850, loss[loss=0.1301, simple_loss=0.2107, pruned_loss=0.02478, over 4683.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02945, over 972064.65 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:47:48,800 INFO [train.py:715] (5/8) Epoch 17, batch 8900, loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02819, over 4823.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02918, over 972288.91 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:48:28,446 INFO [train.py:715] (5/8) Epoch 17, batch 8950, loss[loss=0.1177, simple_loss=0.1913, pruned_loss=0.02208, over 4864.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02924, over 972509.46 frames.], batch size: 20, lr: 1.31e-04
2022-05-08 23:49:07,470 INFO [train.py:715] (5/8) Epoch 17, batch 9000, loss[loss=0.1487, simple_loss=0.2143, pruned_loss=0.04152, over 4832.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.0292, over 973169.78 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:49:07,471 INFO [train.py:733] (5/8) Computing validation loss
2022-05-08 23:49:17,246 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.01072, over 914524.00 frames.
2022-05-08 23:49:56,410 INFO [train.py:715] (5/8) Epoch 17, batch 9050, loss[loss=0.138, simple_loss=0.2205, pruned_loss=0.02775, over 4919.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02928, over 973208.00 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:50:36,246 INFO [train.py:715] (5/8) Epoch 17, batch 9100, loss[loss=0.1161, simple_loss=0.1964, pruned_loss=0.01787, over 4932.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02907, over 973056.78 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:51:15,866 INFO [train.py:715] (5/8) Epoch 17, batch 9150, loss[loss=0.1155, simple_loss=0.1933, pruned_loss=0.0189, over 4864.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02868, over 972522.98 frames.], batch size: 20, lr: 1.31e-04
2022-05-08 23:51:54,747 INFO [train.py:715] (5/8) Epoch 17, batch 9200, loss[loss=0.1892, simple_loss=0.2596, pruned_loss=0.05947, over 4795.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02866, over 973251.37 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:52:34,931 INFO [train.py:715] (5/8) Epoch 17, batch 9250, loss[loss=0.1081, simple_loss=0.1852, pruned_loss=0.01545, over 4929.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02877, over 972890.60 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:53:14,616 INFO [train.py:715] (5/8) Epoch 17, batch 9300, loss[loss=0.1476, simple_loss=0.2208, pruned_loss=0.03718, over 4775.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02945, over 972083.36 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:53:53,951 INFO [train.py:715] (5/8) Epoch 17, batch 9350, loss[loss=0.1291, simple_loss=0.1838, pruned_loss=0.03717, over 4790.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02959, over 971792.66 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:54:33,279 INFO [train.py:715] (5/8) Epoch 17, batch 9400, loss[loss=0.1049, simple_loss=0.1814, pruned_loss=0.0142, over 4750.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02967, over 971947.66 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:55:13,704 INFO [train.py:715] (5/8) Epoch 17, batch 9450, loss[loss=0.1506, simple_loss=0.2249, pruned_loss=0.03814, over 4918.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02937, over 972145.38 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 23:55:53,692 INFO [train.py:715] (5/8) Epoch 17, batch 9500, loss[loss=0.1385, simple_loss=0.2172, pruned_loss=0.02991, over 4974.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 972450.46 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:56:32,926 INFO [train.py:715] (5/8) Epoch 17, batch 9550, loss[loss=0.1118, simple_loss=0.1837, pruned_loss=0.01995, over 4769.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02915, over 972728.56 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:57:12,480 INFO [train.py:715] (5/8) Epoch 17, batch 9600, loss[loss=0.128, simple_loss=0.196, pruned_loss=0.03, over 4791.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02886, over 972227.50 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:57:52,758 INFO [train.py:715] (5/8) Epoch 17, batch 9650, loss[loss=0.1198, simple_loss=0.201, pruned_loss=0.01929, over 4810.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02834, over 972588.68 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:58:31,950 INFO [train.py:715] (5/8) Epoch 17, batch 9700, loss[loss=0.1117, simple_loss=0.1864, pruned_loss=0.01856, over 4927.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02833, over 971907.72 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:59:11,716 INFO [train.py:715] (5/8) Epoch 17, batch 9750, loss[loss=0.1365, simple_loss=0.2046, pruned_loss=0.03417, over 4899.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.0284, over 972347.68 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:59:51,460 INFO [train.py:715] (5/8) Epoch 17, batch 9800, loss[loss=0.1239, simple_loss=0.1985, pruned_loss=0.02465, over 4953.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02869, over 972437.82 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:00:31,042 INFO [train.py:715] (5/8) Epoch 17, batch 9850, loss[loss=0.1225, simple_loss=0.1959, pruned_loss=0.02457, over 4784.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02908, over 971614.14 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:01:10,444 INFO [train.py:715] (5/8) Epoch 17, batch 9900, loss[loss=0.1191, simple_loss=0.1964, pruned_loss=0.0209, over 4922.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02911, over 972317.05 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:01:49,848 INFO [train.py:715] (5/8) Epoch 17, batch 9950, loss[loss=0.1319, simple_loss=0.2081, pruned_loss=0.02786, over 4948.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.0293, over 972251.09 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:02:30,138 INFO [train.py:715] (5/8) Epoch 17, batch 10000, loss[loss=0.139, simple_loss=0.2159, pruned_loss=0.03106, over 4915.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02914, over 972121.57 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:03:09,389 INFO [train.py:715] (5/8) Epoch 17, batch 10050, loss[loss=0.1129, simple_loss=0.1906, pruned_loss=0.01757, over 4815.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02907, over 972431.04 frames.], batch size: 25, lr: 1.31e-04
2022-05-09 00:03:48,275 INFO [train.py:715] (5/8) Epoch 17, batch 10100, loss[loss=0.1344, simple_loss=0.2039, pruned_loss=0.03242, over 4895.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.0293, over 971834.17 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:04:27,594 INFO [train.py:715] (5/8) Epoch 17, batch 10150, loss[loss=0.1221, simple_loss=0.1865, pruned_loss=0.02886, over 4973.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02918, over 971635.40 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:05:06,928 INFO [train.py:715] (5/8) Epoch 17, batch 10200, loss[loss=0.1372, simple_loss=0.2101, pruned_loss=0.03221, over 4860.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02933, over 972184.00 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:05:44,872 INFO [train.py:715] (5/8) Epoch 17, batch 10250, loss[loss=0.118, simple_loss=0.1965, pruned_loss=0.01978, over 4911.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02884, over 973336.05 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:06:24,647 INFO [train.py:715] (5/8) Epoch 17, batch 10300, loss[loss=0.1372, simple_loss=0.2188, pruned_loss=0.02778, over 4906.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 973453.76 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:07:04,573 INFO [train.py:715] (5/8) Epoch 17, batch 10350, loss[loss=0.1497, simple_loss=0.2231, pruned_loss=0.03811, over 4801.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02929, over 972642.38 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:07:43,243 INFO [train.py:715] (5/8) Epoch 17, batch 10400, loss[loss=0.1352, simple_loss=0.2118, pruned_loss=0.02926, over 4743.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02953, over 973235.10 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:08:22,344 INFO [train.py:715] (5/8) Epoch 17, batch 10450, loss[loss=0.1031, simple_loss=0.1773, pruned_loss=0.01447, over 4754.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 973098.73 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:09:02,376 INFO [train.py:715] (5/8) Epoch 17, batch 10500, loss[loss=0.1369, simple_loss=0.2021, pruned_loss=0.03587, over 4752.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02964, over 972146.60 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:09:41,414 INFO [train.py:715] (5/8) Epoch 17, batch 10550, loss[loss=0.1696, simple_loss=0.2361, pruned_loss=0.05156, over 4746.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02995, over 971326.57 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:10:19,760 INFO [train.py:715] (5/8) Epoch 17, batch 10600, loss[loss=0.1369, simple_loss=0.2139, pruned_loss=0.02997, over 4898.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02958, over 971827.97 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:10:59,064 INFO [train.py:715] (5/8) Epoch 17, batch 10650, loss[loss=0.1186, simple_loss=0.1982, pruned_loss=0.01948, over 4932.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02928, over 971720.42 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:11:38,576 INFO [train.py:715] (5/8) Epoch 17, batch 10700, loss[loss=0.1428, simple_loss=0.2259, pruned_loss=0.02984, over 4813.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02897, over 972244.20 frames.], batch size: 26, lr: 1.31e-04
2022-05-09 00:12:17,256 INFO [train.py:715] (5/8) Epoch 17, batch 10750, loss[loss=0.1195, simple_loss=0.1907, pruned_loss=0.02418, over 4988.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.0287, over 971732.40 frames.], batch size: 31, lr: 1.31e-04
2022-05-09 00:12:56,254 INFO [train.py:715] (5/8) Epoch 17, batch 10800, loss[loss=0.1392, simple_loss=0.2069, pruned_loss=0.03573, over 4784.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02912, over 972256.04 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:13:36,022 INFO [train.py:715] (5/8) Epoch 17, batch 10850, loss[loss=0.1442, simple_loss=0.2179, pruned_loss=0.03521, over 4831.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02893, over 972132.67 frames.], batch size: 30, lr: 1.31e-04
2022-05-09 00:14:15,588 INFO [train.py:715] (5/8) Epoch 17, batch 10900, loss[loss=0.1208, simple_loss=0.1984, pruned_loss=0.0216, over 4939.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02853, over 972196.12 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:14:53,759 INFO [train.py:715] (5/8) Epoch 17, batch 10950, loss[loss=0.1619, simple_loss=0.2397, pruned_loss=0.04201, over 4875.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02881, over 972201.50 frames.], batch size: 39, lr: 1.31e-04
2022-05-09 00:15:33,874 INFO [train.py:715] (5/8) Epoch 17, batch 11000, loss[loss=0.1568, simple_loss=0.229, pruned_loss=0.04228, over 4773.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02917, over 973225.31 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:16:13,746 INFO [train.py:715] (5/8) Epoch 17, batch 11050, loss[loss=0.1337, simple_loss=0.2146, pruned_loss=0.02642, over 4863.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02873, over 973425.55 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:16:52,423 INFO [train.py:715] (5/8) Epoch 17, batch 11100, loss[loss=0.1174, simple_loss=0.1943, pruned_loss=0.02026, over 4862.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02907, over 972937.88 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:17:31,480 INFO [train.py:715] (5/8) Epoch 17, batch 11150, loss[loss=0.1157, simple_loss=0.1935, pruned_loss=0.01892, over 4854.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02847, over 973044.41 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:18:11,486 INFO [train.py:715] (5/8) Epoch 17, batch 11200, loss[loss=0.1286, simple_loss=0.2061, pruned_loss=0.02556, over 4816.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02878, over 972758.78 frames.], batch size: 27, lr: 1.31e-04
2022-05-09 00:18:51,600 INFO [train.py:715] (5/8) Epoch 17, batch 11250, loss[loss=0.1218, simple_loss=0.1987, pruned_loss=0.02241, over 4796.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02886, over 972612.34 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:19:29,830 INFO [train.py:715] (5/8) Epoch 17, batch 11300, loss[loss=0.1043, simple_loss=0.1727, pruned_loss=0.01792, over 4790.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02905, over 972508.56 frames.], batch size: 12, lr: 1.31e-04
2022-05-09 00:20:09,300 INFO [train.py:715] (5/8) Epoch 17, batch 11350, loss[loss=0.1232, simple_loss=0.203, pruned_loss=0.02167, over 4911.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.0287, over 972731.69 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:20:49,487 INFO [train.py:715] (5/8) Epoch 17, batch 11400, loss[loss=0.1351, simple_loss=0.2098, pruned_loss=0.03024, over 4957.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02837, over 972466.12 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:21:28,496 INFO [train.py:715] (5/8) Epoch 17, batch 11450, loss[loss=0.09861, simple_loss=0.1667, pruned_loss=0.01524, over 4832.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02835, over 971526.67 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:22:07,510 INFO [train.py:715] (5/8) Epoch 17, batch 11500, loss[loss=0.1233, simple_loss=0.2025, pruned_loss=0.02208, over 4781.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02889, over 972035.46 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:22:47,220 INFO [train.py:715] (5/8) Epoch 17, batch 11550, loss[loss=0.1216, simple_loss=0.1942, pruned_loss=0.02452, over 4938.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02858, over 971840.13 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:23:27,161 INFO [train.py:715] (5/8) Epoch 17, batch 11600, loss[loss=0.1658, simple_loss=0.2251, pruned_loss=0.05323, over 4986.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2053, pruned_loss=0.02865, over 971657.75 frames.], batch size: 31, lr: 1.31e-04
2022-05-09 00:24:05,128 INFO [train.py:715] (5/8) Epoch 17, batch 11650, loss[loss=0.1435, simple_loss=0.218, pruned_loss=0.03447, over 4930.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02818, over 971834.62 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:24:44,952 INFO [train.py:715] (5/8) Epoch 17, batch 11700, loss[loss=0.1311, simple_loss=0.1984, pruned_loss=0.03189, over 4950.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02869, over 972355.19 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:25:24,935 INFO [train.py:715] (5/8) Epoch 17, batch 11750, loss[loss=0.1276, simple_loss=0.1983, pruned_loss=0.02842, over 4819.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2055, pruned_loss=0.02884, over 972024.84 frames.], batch size: 27, lr: 1.31e-04
2022-05-09 00:26:03,879 INFO [train.py:715] (5/8) Epoch 17, batch 11800, loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.02992, over 4837.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.029, over 972254.09 frames.], batch size: 26, lr: 1.31e-04
2022-05-09 00:26:42,874 INFO [train.py:715] (5/8) Epoch 17, batch 11850, loss[loss=0.1349, simple_loss=0.1977, pruned_loss=0.03603, over 4756.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02906, over 971888.57 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:27:22,145 INFO [train.py:715] (5/8) Epoch 17, batch 11900, loss[loss=0.1092, simple_loss=0.1805, pruned_loss=0.01898, over 4780.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02937, over 971187.79 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:28:01,948 INFO [train.py:715] (5/8) Epoch 17, batch 11950, loss[loss=0.1372, simple_loss=0.209, pruned_loss=0.03275, over 4804.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02875, over 971367.57 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:28:40,961 INFO [train.py:715] (5/8) Epoch 17, batch 12000, loss[loss=0.1087, simple_loss=0.1704, pruned_loss=0.0235, over 4965.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02902, over 971912.73 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:28:40,962 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 00:28:52,718 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.0107, over 914524.00 frames.
2022-05-09 00:29:31,826 INFO [train.py:715] (5/8) Epoch 17, batch 12050, loss[loss=0.1192, simple_loss=0.1994, pruned_loss=0.01949, over 4977.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02913, over 972597.18 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:30:10,918 INFO [train.py:715] (5/8) Epoch 17, batch 12100, loss[loss=0.1416, simple_loss=0.2115, pruned_loss=0.03585, over 4951.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02945, over 972423.10 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:30:50,930 INFO [train.py:715] (5/8) Epoch 17, batch 12150, loss[loss=0.1513, simple_loss=0.2234, pruned_loss=0.03961, over 4850.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02922, over 972146.03 frames.], batch size: 30, lr: 1.31e-04
2022-05-09 00:31:29,659 INFO [train.py:715] (5/8) Epoch 17, batch 12200, loss[loss=0.1369, simple_loss=0.2197, pruned_loss=0.02704, over 4888.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02922, over 971698.29 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:32:08,192 INFO [train.py:715] (5/8) Epoch 17, batch 12250, loss[loss=0.116, simple_loss=0.1826, pruned_loss=0.02473, over 4968.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 972183.49 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:32:47,683 INFO [train.py:715] (5/8) Epoch 17, batch 12300, loss[loss=0.1351, simple_loss=0.2026, pruned_loss=0.03383, over 4982.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 972280.56 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:33:26,859 INFO [train.py:715] (5/8) Epoch 17, batch 12350, loss[loss=0.1218, simple_loss=0.1909, pruned_loss=0.02635, over 4828.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972447.98 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:34:05,563 INFO [train.py:715] (5/8) Epoch 17, batch 12400, loss[loss=0.1216, simple_loss=0.2017, pruned_loss=0.02075, over 4902.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02852, over 972644.59 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:34:44,615 INFO [train.py:715] (5/8) Epoch 17, batch 12450, loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03, over 4929.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.0287, over 973695.95 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:35:24,994 INFO [train.py:715] (5/8) Epoch 17, batch 12500, loss[loss=0.1272, simple_loss=0.2036, pruned_loss=0.02544, over 4789.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02867, over 973104.82 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:36:03,578 INFO [train.py:715] (5/8) Epoch 17, batch 12550, loss[loss=0.1364, simple_loss=0.2153, pruned_loss=0.02876, over 4851.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02869, over 973621.64 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:36:42,923 INFO [train.py:715] (5/8) Epoch 17, batch 12600, loss[loss=0.1423, simple_loss=0.2179, pruned_loss=0.03338, over 4709.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 973200.80 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:37:22,857 INFO [train.py:715] (5/8) Epoch 17, batch 12650, loss[loss=0.1235, simple_loss=0.2027, pruned_loss=0.02217, over 4977.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02847, over 972973.19 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:38:02,852 INFO [train.py:715] (5/8) Epoch 17, batch 12700, loss[loss=0.1464, simple_loss=0.215, pruned_loss=0.03892, over 4928.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02884, over 972936.85 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:38:42,159 INFO [train.py:715] (5/8) Epoch 17, batch 12750, loss[loss=0.1508, simple_loss=0.2246, pruned_loss=0.03855, over 4743.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 973345.05 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:39:20,961 INFO [train.py:715] (5/8) Epoch 17, batch 12800, loss[loss=0.1356, simple_loss=0.2019, pruned_loss=0.03468, over 4991.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02927, over 973232.79 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:40:00,596 INFO [train.py:715] (5/8) Epoch 17, batch 12850, loss[loss=0.1381, simple_loss=0.2284, pruned_loss=0.02392, over 4699.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 972740.29 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:40:39,039 INFO [train.py:715] (5/8) Epoch 17, batch 12900, loss[loss=0.151, simple_loss=0.2322, pruned_loss=0.03487, over 4782.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02968, over 972725.04 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:41:18,425 INFO [train.py:715] (5/8) Epoch 17, batch 12950, loss[loss=0.1524, simple_loss=0.2131, pruned_loss=0.04586, over 4763.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02971, over 972938.91 frames.], batch size: 12, lr: 1.31e-04
2022-05-09 00:41:57,021 INFO [train.py:715] (5/8) Epoch 17, batch 13000, loss[loss=0.1354, simple_loss=0.2028, pruned_loss=0.03403, over 4969.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02979, over 972818.05 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:42:36,102 INFO [train.py:715] (5/8) Epoch 17, batch 13050, loss[loss=0.1136, simple_loss=0.1888, pruned_loss=0.01921, over 4842.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02975, over 972198.15 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:43:15,222 INFO [train.py:715] (5/8) Epoch 17, batch 13100, loss[loss=0.132, simple_loss=0.2007, pruned_loss=0.03162, over 4987.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0296, over 972262.40 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:43:54,020 INFO [train.py:715] (5/8) Epoch 17, batch 13150, loss[loss=0.1431, simple_loss=0.2188, pruned_loss=0.03374, over 4954.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03004, over 972100.31 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:44:33,794 INFO [train.py:715] (5/8) Epoch 17, batch 13200, loss[loss=0.1258, simple_loss=0.1968, pruned_loss=0.02738, over 4780.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2088, pruned_loss=0.02973, over 972047.30 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:45:12,321 INFO [train.py:715] (5/8) Epoch 17, batch 13250, loss[loss=0.09096, simple_loss=0.1665, pruned_loss=0.007731, over 4963.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02931, over 971730.56 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:45:51,622 INFO [train.py:715] (5/8) Epoch 17, batch 13300, loss[loss=0.1713, simple_loss=0.2353, pruned_loss=0.05362, over 4869.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02961, over 971931.02 frames.], batch size: 32, lr: 1.31e-04
2022-05-09 00:46:30,709 INFO [train.py:715] (5/8) Epoch 17, batch 13350, loss[loss=0.1097, simple_loss=0.1822, pruned_loss=0.01859, over 4819.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02944, over 971877.89 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:47:09,938 INFO [train.py:715] (5/8) Epoch 17, batch 13400, loss[loss=0.1277, simple_loss=0.1967, pruned_loss=0.02929, over 4785.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 971623.23 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:47:49,247 INFO [train.py:715] (5/8) Epoch 17, batch 13450, loss[loss=0.1353, simple_loss=0.2103, pruned_loss=0.03017, over 4843.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02937, over 971524.63 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 00:48:27,713 INFO [train.py:715] (5/8) Epoch 17, batch 13500, loss[loss=0.1127, simple_loss=0.1957, pruned_loss=0.01488, over 4941.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.0294, over 972661.62 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 00:49:07,419 INFO [train.py:715] (5/8) Epoch 17, batch 13550, loss[loss=0.1167, simple_loss=0.1964, pruned_loss=0.01852, over 4778.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02932, over 973068.27 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 00:49:45,773 INFO [train.py:715] (5/8) Epoch 17, batch 13600, loss[loss=0.1376, simple_loss=0.2147, pruned_loss=0.03027, over 4849.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02914, over 972804.09 frames.], batch size: 34, lr: 1.30e-04
2022-05-09 00:50:24,815 INFO [train.py:715] (5/8) Epoch 17, batch 13650, loss[loss=0.1352, simple_loss=0.2048, pruned_loss=0.03281, over 4884.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02907, over 973005.27 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 00:51:04,635 INFO [train.py:715] (5/8) Epoch 17, batch 13700, loss[loss=0.126, simple_loss=0.2053, pruned_loss=0.02337, over 4858.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02855, over 973231.85 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 00:51:43,955 INFO [train.py:715] (5/8) Epoch 17, batch 13750, loss[loss=0.1338, simple_loss=0.2142, pruned_loss=0.02665, over 4768.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02837, over 973319.46 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 00:52:24,096 INFO [train.py:715] (5/8) Epoch 17, batch 13800, loss[loss=0.1058, simple_loss=0.1782, pruned_loss=0.01666, over 4894.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02877, over 972034.34 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 00:53:03,508 INFO [train.py:715] (5/8) Epoch 17, batch 13850, loss[loss=0.1553, simple_loss=0.2357, pruned_loss=0.03744, over 4831.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.0288, over 973224.27 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 00:53:43,317 INFO [train.py:715] (5/8) Epoch 17, batch 13900, loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03358, over 4812.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02895, over 972766.19 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 00:54:22,805 INFO [train.py:715] (5/8) Epoch 17, batch 13950, loss[loss=0.1154, simple_loss=0.1901, pruned_loss=0.02034, over 4841.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.0288, over 972702.86 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 00:55:02,838 INFO [train.py:715] (5/8) Epoch 17, batch 14000, loss[loss=0.1468, simple_loss=0.2234, pruned_loss=0.03511, over 4889.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02923, over 972014.25 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 00:55:42,002 INFO [train.py:715] (5/8) Epoch 17, batch 14050, loss[loss=0.1242, simple_loss=0.1901, pruned_loss=0.02915, over 4973.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.0293, over 972381.53 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 00:56:21,073 INFO [train.py:715] (5/8) Epoch 17, batch 14100, loss[loss=0.1241, simple_loss=0.2049, pruned_loss=0.02165, over 4911.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02898, over 972688.30 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 00:57:01,246 INFO [train.py:715] (5/8) Epoch 17, batch 14150, loss[loss=0.1377, simple_loss=0.2214, pruned_loss=0.02697, over 4767.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.029, over 972856.07 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 00:57:40,316 INFO [train.py:715] (5/8) Epoch 17, batch 14200, loss[loss=0.1523, simple_loss=0.2261, pruned_loss=0.03927, over 4978.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02935, over 972074.94 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 00:58:19,829 INFO [train.py:715] (5/8) Epoch 17, batch 14250, loss[loss=0.1139, simple_loss=0.1924, pruned_loss=0.01772, over 4852.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02917, over 972055.80 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 00:58:58,996 INFO [train.py:715] (5/8) Epoch 17, batch 14300, loss[loss=0.154, simple_loss=0.2305, pruned_loss=0.03879, over 4906.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02913, over 972535.01 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 00:59:38,851 INFO [train.py:715] (5/8) Epoch 17, batch 14350, loss[loss=0.1055, simple_loss=0.189, pruned_loss=0.01096, over 4820.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.029, over 972647.54 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:00:17,886 INFO [train.py:715] (5/8) Epoch 17, batch 14400, loss[loss=0.1268, simple_loss=0.2067, pruned_loss=0.02351, over 4786.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.0293, over 971629.73 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:00:56,575 INFO [train.py:715] (5/8) Epoch 17, batch 14450, loss[loss=0.1333, simple_loss=0.2132, pruned_loss=0.02672, over 4767.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02902, over 971984.52 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:01:36,310 INFO [train.py:715] (5/8) Epoch 17, batch 14500, loss[loss=0.1492, simple_loss=0.2185, pruned_loss=0.03994, over 4981.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02938, over 972757.13 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:02:15,668 INFO [train.py:715] (5/8) Epoch 17, batch 14550, loss[loss=0.1183, simple_loss=0.184, pruned_loss=0.02628, over 4925.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02919, over 973613.25 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:02:54,145 INFO [train.py:715] (5/8) Epoch 17, batch 14600, loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02838, over 4848.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02872, over 973038.07 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:03:33,786 INFO [train.py:715] (5/8) Epoch 17, batch 14650, loss[loss=0.112, simple_loss=0.1917, pruned_loss=0.0162, over 4940.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02894, over 972392.39 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:04:13,437 INFO [train.py:715] (5/8) Epoch 17, batch 14700, loss[loss=0.1247, simple_loss=0.1989, pruned_loss=0.02525, over 4941.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02882, over 971939.87 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 01:04:52,650 INFO [train.py:715] (5/8) Epoch 17, batch 14750, loss[loss=0.1497, simple_loss=0.2216, pruned_loss=0.03892, over 4913.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02941, over 972318.63 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:05:31,535 INFO [train.py:715] (5/8) Epoch 17, batch 14800, loss[loss=0.1325, simple_loss=0.2006, pruned_loss=0.03224, over 4850.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02962, over 971842.62 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:06:11,600 INFO [train.py:715] (5/8) Epoch 17, batch 14850, loss[loss=0.1213, simple_loss=0.1932, pruned_loss=0.0247, over 4961.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 973193.34 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:06:50,382 INFO [train.py:715] (5/8) Epoch 17, batch 14900, loss[loss=0.1218, simple_loss=0.1966, pruned_loss=0.02348, over 4638.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02878, over 971899.21 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:07:29,328 INFO [train.py:715] (5/8) Epoch 17, batch 14950, loss[loss=0.1156, simple_loss=0.1877, pruned_loss=0.02176, over 4962.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02892, over 972006.39 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:08:09,014 INFO [train.py:715] (5/8) Epoch 17, batch 15000, loss[loss=0.1221, simple_loss=0.1938, pruned_loss=0.02523, over 4781.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 972875.35 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:08:09,014 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 01:08:19,081 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1046, simple_loss=0.1881, pruned_loss=0.01059, over 914524.00 frames.
2022-05-09 01:08:59,144 INFO [train.py:715] (5/8) Epoch 17, batch 15050, loss[loss=0.1483, simple_loss=0.2147, pruned_loss=0.041, over 4940.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02932, over 972891.87 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:09:38,651 INFO [train.py:715] (5/8) Epoch 17, batch 15100, loss[loss=0.1706, simple_loss=0.2445, pruned_loss=0.0483, over 4823.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02952, over 972159.88 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:10:17,572 INFO [train.py:715] (5/8) Epoch 17, batch 15150, loss[loss=0.1401, simple_loss=0.2166, pruned_loss=0.03177, over 4889.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02974, over 972500.62 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:10:56,608 INFO [train.py:715] (5/8) Epoch 17, batch 15200, loss[loss=0.102, simple_loss=0.1826, pruned_loss=0.01074, over 4972.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.0296, over 972583.43 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:11:36,235 INFO [train.py:715] (5/8) Epoch 17, batch 15250, loss[loss=0.1167, simple_loss=0.1894, pruned_loss=0.02199, over 4811.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02931, over 972752.79 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:12:15,600 INFO [train.py:715] (5/8) Epoch 17, batch 15300, loss[loss=0.1457, simple_loss=0.2184, pruned_loss=0.03649, over 4855.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02935, over 972806.62 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:12:53,856 INFO [train.py:715] (5/8) Epoch 17, batch 15350, loss[loss=0.1249, simple_loss=0.1955, pruned_loss=0.02716, over 4776.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02901, over 973452.18 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:13:33,400 INFO [train.py:715] (5/8) Epoch 17, batch 15400, loss[loss=0.152, simple_loss=0.2179, pruned_loss=0.04302, over 4822.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02911, over 973216.49 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:14:12,474 INFO [train.py:715] (5/8) Epoch 17, batch 15450, loss[loss=0.1345, simple_loss=0.2094, pruned_loss=0.02974, over 4799.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02896, over 973116.69 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:14:51,818 INFO [train.py:715] (5/8) Epoch 17, batch 15500, loss[loss=0.1383, simple_loss=0.2091, pruned_loss=0.0337, over 4844.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02921, over 972979.68 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:15:30,647 INFO [train.py:715] (5/8) Epoch 17, batch 15550, loss[loss=0.1345, simple_loss=0.2057, pruned_loss=0.03169, over 4956.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02936, over 972170.73 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:16:10,369 INFO [train.py:715] (5/8) Epoch 17, batch 15600, loss[loss=0.1428, simple_loss=0.2225, pruned_loss=0.03158, over 4979.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02922, over 971724.74 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:16:49,789 INFO [train.py:715] (5/8) Epoch 17, batch 15650, loss[loss=0.1383, simple_loss=0.2051, pruned_loss=0.03572, over 4954.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 972189.84 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:17:27,920 INFO [train.py:715] (5/8) Epoch 17, batch 15700, loss[loss=0.1426, simple_loss=0.202, pruned_loss=0.04157, over 4843.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02931, over 973050.17 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:18:07,730 INFO [train.py:715] (5/8) Epoch 17, batch 15750, loss[loss=0.1499, simple_loss=0.2142, pruned_loss=0.04281, over 4903.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02954, over 972741.74 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:18:47,134 INFO [train.py:715] (5/8) Epoch 17, batch 15800, loss[loss=0.1221, simple_loss=0.1969, pruned_loss=0.0237, over 4943.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02907, over 971978.14 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:19:26,080 INFO [train.py:715] (5/8) Epoch 17, batch 15850, loss[loss=0.1321, simple_loss=0.2199, pruned_loss=0.0221, over 4811.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 973467.30 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:20:04,718 INFO [train.py:715] (5/8) Epoch 17, batch 15900, loss[loss=0.1404, simple_loss=0.2164, pruned_loss=0.0322, over 4933.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02898, over 974552.09 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:20:44,127 INFO [train.py:715] (5/8) Epoch 17, batch 15950, loss[loss=0.1045, simple_loss=0.1684, pruned_loss=0.0203, over 4830.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02931, over 973537.37 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:21:23,629 INFO [train.py:715] (5/8) Epoch 17, batch 16000, loss[loss=0.1396, simple_loss=0.2136, pruned_loss=0.03276, over 4961.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03011, over 972983.18 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 01:22:02,017 INFO [train.py:715] (5/8) Epoch 17, batch 16050, loss[loss=0.115, simple_loss=0.1985, pruned_loss=0.01575, over 4789.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2089, pruned_loss=0.02999, over 973290.59 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 01:22:42,057 INFO [train.py:715] (5/8) Epoch 17, batch 16100, loss[loss=0.1297, simple_loss=0.1993, pruned_loss=0.0301, over 4955.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02915, over 972561.27 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:23:21,958 INFO [train.py:715] (5/8) Epoch 17, batch 16150, loss[loss=0.134, simple_loss=0.2, pruned_loss=0.03396, over 4757.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02856, over 972121.07 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:24:01,718 INFO [train.py:715] (5/8) Epoch 17, batch 16200, loss[loss=0.1738, simple_loss=0.261, pruned_loss=0.0433, over 4970.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02876, over 971556.86 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 01:24:43,129 INFO [train.py:715] (5/8) Epoch 17, batch 16250, loss[loss=0.1321, simple_loss=0.1977, pruned_loss=0.03325, over 4743.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02904, over 971198.52 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:25:23,140 INFO [train.py:715] (5/8) Epoch 17, batch 16300, loss[loss=0.1119, simple_loss=0.1787, pruned_loss=0.02254, over 4814.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02903, over 971620.09 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:26:02,216 INFO [train.py:715] (5/8) Epoch 17, batch 16350, loss[loss=0.123, simple_loss=0.2007, pruned_loss=0.02271, over 4972.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02942, over 972147.11 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 01:26:40,871 INFO [train.py:715] (5/8) Epoch 17, batch 16400, loss[loss=0.1109, simple_loss=0.1856, pruned_loss=0.01807, over 4825.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02885, over 971171.75 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 01:27:20,588 INFO [train.py:715] (5/8) Epoch 17, batch 16450, loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02845, over 4778.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02895, over 971527.64 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:28:00,550 INFO [train.py:715] (5/8) Epoch 17, batch 16500, loss[loss=0.1439, simple_loss=0.214, pruned_loss=0.03689, over 4752.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.029, over 971721.97 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:28:39,572 INFO [train.py:715] (5/8) Epoch 17, batch 16550, loss[loss=0.1362, simple_loss=0.2093, pruned_loss=0.03155, over 4699.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02912, over 971666.15 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:29:18,071 INFO [train.py:715] (5/8) Epoch 17, batch 16600, loss[loss=0.1137, simple_loss=0.1988, pruned_loss=0.01433, over 4824.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02883, over 971917.40 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:29:58,263 INFO [train.py:715] (5/8) Epoch 17, batch 16650, loss[loss=0.1303, simple_loss=0.2092, pruned_loss=0.0257, over 4801.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02907, over 972277.31 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:30:38,043 INFO [train.py:715] (5/8) Epoch 17, batch 16700, loss[loss=0.1231, simple_loss=0.2022, pruned_loss=0.02199, over 4814.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02882, over 972811.74 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:31:16,489 INFO [train.py:715] (5/8) Epoch 17, batch 16750, loss[loss=0.1518, simple_loss=0.2245, pruned_loss=0.03957, over 4978.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02888, over 972468.91 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:31:56,309 INFO [train.py:715] (5/8) Epoch 17, batch 16800, loss[loss=0.1218, simple_loss=0.2016, pruned_loss=0.021, over 4894.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02886, over 972646.33 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:32:35,733 INFO [train.py:715] (5/8) Epoch 17, batch 16850, loss[loss=0.1319, simple_loss=0.2057, pruned_loss=0.02902, over 4931.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02881, over 972313.85 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 01:33:15,640 INFO [train.py:715] (5/8) Epoch 17, batch 16900, loss[loss=0.1272, simple_loss=0.197, pruned_loss=0.02873, over 4758.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 972010.81 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 01:33:53,866 INFO [train.py:715] (5/8) Epoch 17, batch 16950, loss[loss=0.1213, simple_loss=0.1985, pruned_loss=0.02205, over 4893.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02904, over 971510.56 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:34:33,424 INFO [train.py:715] (5/8) Epoch 17, batch 17000, loss[loss=0.1261, simple_loss=0.2074, pruned_loss=0.02246, over 4941.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02865, over 971543.78 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:35:12,910 INFO [train.py:715] (5/8) Epoch 17, batch 17050, loss[loss=0.1293, simple_loss=0.1966, pruned_loss=0.03097, over 4980.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02834, over 972544.29 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:35:51,175 INFO [train.py:715] (5/8) Epoch 17, batch 17100, loss[loss=0.1711, simple_loss=0.2442, pruned_loss=0.04898, over 4928.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02829, over 973111.68 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:36:30,679 INFO [train.py:715] (5/8) Epoch 17, batch 17150, loss[loss=0.1378, simple_loss=0.2158, pruned_loss=0.02992, over 4967.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02877, over 972726.66 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:37:10,049 INFO [train.py:715] (5/8) Epoch 17, batch 17200, loss[loss=0.1287, simple_loss=0.2006, pruned_loss=0.02841, over 4956.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 973267.17 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:37:48,553 INFO [train.py:715] (5/8) Epoch 17, batch 17250, loss[loss=0.1313, simple_loss=0.2045, pruned_loss=0.02904, over 4939.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02888, over 973314.85 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:38:26,820 INFO [train.py:715] (5/8) Epoch 17, batch 17300, loss[loss=0.1151, simple_loss=0.1873, pruned_loss=0.02141, over 4851.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02877, over 973562.34 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:39:06,135 INFO [train.py:715] (5/8) Epoch 17, batch 17350, loss[loss=0.1256, simple_loss=0.193, pruned_loss=0.0291, over 4774.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 972618.20 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:39:45,335 INFO [train.py:715] (5/8) Epoch 17, batch 17400, loss[loss=0.1095, simple_loss=0.1807, pruned_loss=0.01915, over 4982.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.0284, over 972754.09 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:40:23,321 INFO [train.py:715] (5/8) Epoch 17, batch 17450, loss[loss=0.1588, simple_loss=0.2366, pruned_loss=0.04055, over 4897.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02809, over 973008.86 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:41:03,008 INFO [train.py:715] (5/8) Epoch 17, batch 17500, loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03571, over 4943.00 frames.], tot_loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.02791, over 972600.47 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:41:42,131 INFO [train.py:715] (5/8) Epoch 17, batch 17550, loss[loss=0.1259, simple_loss=0.2024, pruned_loss=0.0247, over 4874.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02836, over 972665.17 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:42:20,890 INFO [train.py:715] (5/8) Epoch 17, batch 17600, loss[loss=0.1583, simple_loss=0.2421, pruned_loss=0.03724, over 4990.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02881, over 972907.72 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:42:59,399 INFO [train.py:715] (5/8) Epoch 17, batch 17650, loss[loss=0.1041, simple_loss=0.1783, pruned_loss=0.01496, over 4874.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02921, over 972463.93 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:43:38,884 INFO [train.py:715] (5/8) Epoch 17, batch 17700, loss[loss=0.1206, simple_loss=0.1981, pruned_loss=0.02154, over 4994.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 973150.10 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:44:17,596 INFO [train.py:715] (5/8) Epoch 17, batch 17750, loss[loss=0.1349, simple_loss=0.2102, pruned_loss=0.02979, over 4913.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02927, over 972808.23 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:44:56,091 INFO [train.py:715] (5/8) Epoch 17, batch 17800, loss[loss=0.129, simple_loss=0.2083, pruned_loss=0.0249, over 4890.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02914, over 973312.54 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:45:35,676 INFO [train.py:715] (5/8) Epoch 17, batch 17850, loss[loss=0.1369, simple_loss=0.2115, pruned_loss=0.03117, over 4840.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02914, over 972476.69 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:46:14,668 INFO [train.py:715] (5/8) Epoch 17, batch 17900, loss[loss=0.1227, simple_loss=0.1982, pruned_loss=0.02363, over 4966.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.029, over 972403.70 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:46:54,013 INFO [train.py:715] (5/8) Epoch 17, batch 17950, loss[loss=0.1294, simple_loss=0.2171, pruned_loss=0.02083, over 4954.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02923, over 972926.24 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 01:47:32,275 INFO [train.py:715] (5/8) Epoch 17, batch 18000, loss[loss=0.1063, simple_loss=0.1709, pruned_loss=0.02078, over 4846.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02909, over 972594.96 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:47:32,275 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 01:47:42,061 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01066, over 914524.00 frames.
2022-05-09 01:48:20,782 INFO [train.py:715] (5/8) Epoch 17, batch 18050, loss[loss=0.1039, simple_loss=0.1838, pruned_loss=0.01205, over 4808.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02932, over 972257.86 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:49:00,409 INFO [train.py:715] (5/8) Epoch 17, batch 18100, loss[loss=0.1227, simple_loss=0.2007, pruned_loss=0.02232, over 4979.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02944, over 972705.42 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:49:39,795 INFO [train.py:715] (5/8) Epoch 17, batch 18150, loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.04276, over 4864.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 972835.19 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:50:17,779 INFO [train.py:715] (5/8) Epoch 17, batch 18200, loss[loss=0.1183, simple_loss=0.1926, pruned_loss=0.02202, over 4797.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02948, over 972700.31 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:50:57,530 INFO [train.py:715] (5/8) Epoch 17, batch 18250, loss[loss=0.1312, simple_loss=0.2096, pruned_loss=0.02644, over 4932.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02972, over 972425.19 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:51:37,060 INFO [train.py:715] (5/8) Epoch 17, batch 18300, loss[loss=0.1514, simple_loss=0.2234, pruned_loss=0.03966, over 4964.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02979, over 972969.29 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 01:52:15,572 INFO [train.py:715] (5/8) Epoch 17, batch 18350, loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03885, over 4871.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02945, over 972758.55 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:52:55,004 INFO [train.py:715] (5/8) Epoch 17, batch 18400, loss[loss=0.1154, simple_loss=0.1832, pruned_loss=0.0238, over 4973.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02919, over 972967.20 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:53:33,897 INFO [train.py:715] (5/8) Epoch 17, batch 18450, loss[loss=0.1215, simple_loss=0.1907, pruned_loss=0.02617, over 4956.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02961, over 973057.71 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:54:13,085 INFO [train.py:715] (5/8) Epoch 17, batch 18500, loss[loss=0.1538, simple_loss=0.2271, pruned_loss=0.04028, over 4819.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0296, over 972619.55 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 01:54:51,414 INFO [train.py:715] (5/8) Epoch 17, batch 18550, loss[loss=0.1582, simple_loss=0.2368, pruned_loss=0.03978, over 4953.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.0294, over 972013.87 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:55:30,371 INFO [train.py:715] (5/8) Epoch 17, batch 18600, loss[loss=0.133, simple_loss=0.2024, pruned_loss=0.03178, over 4907.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 972200.05 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:56:09,529 INFO [train.py:715] (5/8) Epoch 17, batch 18650, loss[loss=0.1316, simple_loss=0.2109, pruned_loss=0.0262, over 4897.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02957, over 972384.60 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:56:47,375 INFO [train.py:715] (5/8) Epoch 17, batch 18700, loss[loss=0.1319, simple_loss=0.2035, pruned_loss=0.03012, over 4928.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02974, over 971911.45 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 01:57:27,053 INFO [train.py:715] (5/8) Epoch 17, batch 18750, loss[loss=0.1256, simple_loss=0.2029, pruned_loss=0.02415, over 4965.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02934, over 972856.89 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:58:06,642 INFO [train.py:715] (5/8) Epoch 17, batch 18800, loss[loss=0.1551, simple_loss=0.2352, pruned_loss=0.03748, over 4984.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 972787.60 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:58:45,348 INFO [train.py:715] (5/8) Epoch 17, batch 18850, loss[loss=0.1377, simple_loss=0.208, pruned_loss=0.03373, over 4985.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02947, over 972109.43 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:59:23,453 INFO [train.py:715] (5/8) Epoch 17, batch 18900, loss[loss=0.1183, simple_loss=0.2029, pruned_loss=0.01679, over 4852.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02929, over 971960.85 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 02:00:02,550 INFO [train.py:715] (5/8) Epoch 17, batch 18950, loss[loss=0.1114, simple_loss=0.1898, pruned_loss=0.01643, over 4909.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02938, over 972549.01 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:00:41,833 INFO [train.py:715] (5/8) Epoch 17, batch 19000, loss[loss=0.1335, simple_loss=0.2092, pruned_loss=0.02891, over 4766.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.0293, over 972026.78 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:01:20,326 INFO [train.py:715] (5/8) Epoch 17, batch 19050, loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03243, over 4917.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.0292, over 972578.98 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:01:59,754 INFO [train.py:715] (5/8) Epoch 17, batch 19100, loss[loss=0.124, simple_loss=0.1981, pruned_loss=0.02491, over 4796.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02952, over 973702.96 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:02:38,884 INFO [train.py:715] (5/8) Epoch 17, batch 19150, loss[loss=0.1392, simple_loss=0.2225, pruned_loss=0.02799, over 4938.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02959, over 973359.85 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:03:17,327 INFO [train.py:715] (5/8) Epoch 17, batch 19200, loss[loss=0.1456, simple_loss=0.214, pruned_loss=0.03862, over 4928.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02955, over 972895.42 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 02:03:56,163 INFO [train.py:715] (5/8) Epoch 17, batch 19250, loss[loss=0.1397, simple_loss=0.2059, pruned_loss=0.03671, over 4763.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 974215.28 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:04:35,739 INFO [train.py:715] (5/8) Epoch 17, batch 19300, loss[loss=0.1576, simple_loss=0.2378, pruned_loss=0.03868, over 4952.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02918, over 974376.19 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:05:15,461 INFO [train.py:715] (5/8) Epoch 17, batch 19350, loss[loss=0.1112, simple_loss=0.1781, pruned_loss=0.02212, over 4906.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02889, over 973931.08 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:05:54,626 INFO [train.py:715] (5/8) Epoch 17, batch 19400, loss[loss=0.1479, simple_loss=0.2282, pruned_loss=0.03382, over 4901.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02895, over 973178.55 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:06:34,192 INFO [train.py:715] (5/8) Epoch 17, batch 19450, loss[loss=0.1354, simple_loss=0.2019, pruned_loss=0.03451, over 4899.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02859, over 972828.36 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:07:13,756 INFO [train.py:715] (5/8) Epoch 17, batch 19500, loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03563, over 4960.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02874, over 972996.78 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:07:53,344 INFO [train.py:715] (5/8) Epoch 17, batch 19550, loss[loss=0.1161, simple_loss=0.1827, pruned_loss=0.02475, over 4966.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02915, over 972937.19 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:08:31,621 INFO [train.py:715] (5/8) Epoch 17, batch 19600, loss[loss=0.1446, simple_loss=0.2051, pruned_loss=0.04207, over 4762.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02933, over 971932.48 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:09:11,585 INFO [train.py:715] (5/8) Epoch 17, batch 19650, loss[loss=0.1141, simple_loss=0.1865, pruned_loss=0.0208, over 4832.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02893, over 971759.11 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:09:51,451 INFO [train.py:715] (5/8) Epoch 17, batch 19700, loss[loss=0.1204, simple_loss=0.1948, pruned_loss=0.02296, over 4797.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02929, over 972337.59 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:10:30,058 INFO [train.py:715] (5/8) Epoch 17, batch 19750, loss[loss=0.129, simple_loss=0.194, pruned_loss=0.03201, over 4767.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02956, over 972237.30 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:11:09,367 INFO [train.py:715] (5/8) Epoch 17, batch 19800, loss[loss=0.116, simple_loss=0.1805, pruned_loss=0.02575, over 4785.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02955, over 971458.38 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:11:47,959 INFO [train.py:715] (5/8) Epoch 17, batch 19850, loss[loss=0.1287, simple_loss=0.2037, pruned_loss=0.02682, over 4896.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02985, over 971219.90 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:12:26,930 INFO [train.py:715] (5/8) Epoch 17, batch 19900, loss[loss=0.09711, simple_loss=0.1728, pruned_loss=0.01072, over 4816.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02957, over 972152.26 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:13:05,187 INFO [train.py:715] (5/8) Epoch 17, batch 19950, loss[loss=0.1291, simple_loss=0.2039, pruned_loss=0.02714, over 4915.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02968, over 971660.86 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:13:44,430 INFO [train.py:715] (5/8) Epoch 17, batch 20000, loss[loss=0.1087, simple_loss=0.1849, pruned_loss=0.0162, over 4771.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2065, pruned_loss=0.02957, over 972404.53 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:14:24,054 INFO [train.py:715] (5/8) Epoch 17, batch 20050, loss[loss=0.1134, simple_loss=0.197, pruned_loss=0.01486, over 4758.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02916, over 972384.45 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:15:03,199 INFO [train.py:715] (5/8) Epoch 17, batch 20100, loss[loss=0.1443, simple_loss=0.2051, pruned_loss=0.04176, over 4700.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02919, over 972558.33 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:15:42,009 INFO [train.py:715] (5/8) Epoch 17, batch 20150, loss[loss=0.1233, simple_loss=0.1882, pruned_loss=0.02917, over 4822.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02858, over 972383.06 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:16:22,283 INFO [train.py:715] (5/8) Epoch 17, batch 20200, loss[loss=0.1285, simple_loss=0.2038, pruned_loss=0.0266, over 4968.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02849, over 972653.45 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:17:02,699 INFO [train.py:715] (5/8) Epoch 17, batch 20250, loss[loss=0.1421, simple_loss=0.202, pruned_loss=0.04113, over 4811.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.0286, over 973017.48 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:17:40,774 INFO [train.py:715] (5/8) Epoch 17, batch 20300, loss[loss=0.09609, simple_loss=0.1702, pruned_loss=0.01099, over 4810.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02933, over 972991.37 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:18:20,507 INFO [train.py:715] (5/8) Epoch 17, batch 20350, loss[loss=0.1254, simple_loss=0.2008, pruned_loss=0.02497, over 4969.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02921, over 972655.76 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:19:00,632 INFO [train.py:715] (5/8) Epoch 17, batch 20400, loss[loss=0.1263, simple_loss=0.2072, pruned_loss=0.02275, over 4817.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 973264.49 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:19:39,221 INFO [train.py:715] (5/8) Epoch 17, batch 20450, loss[loss=0.1406, simple_loss=0.2144, pruned_loss=0.03337, over 4992.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02918, over 973007.76 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:20:17,923 INFO [train.py:715] (5/8) Epoch 17, batch 20500, loss[loss=0.165, simple_loss=0.2306, pruned_loss=0.04968, over 4735.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02937, over 973472.07 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:20:57,775 INFO [train.py:715] (5/8) Epoch 17, batch 20550, loss[loss=0.1684, simple_loss=0.2317, pruned_loss=0.05256, over 4846.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02943, over 972975.61 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 02:21:36,909 INFO [train.py:715] (5/8) Epoch 17, batch 20600, loss[loss=0.1229, simple_loss=0.1937, pruned_loss=0.02601, over 4855.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02948, over 973568.21 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 02:22:15,098 INFO [train.py:715] (5/8) Epoch 17, batch 20650, loss[loss=0.1432, simple_loss=0.2208, pruned_loss=0.03284, over 4789.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02951, over 973115.04 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:22:54,070 INFO [train.py:715] (5/8) Epoch 17, batch 20700, loss[loss=0.1474, simple_loss=0.2152, pruned_loss=0.03974, over 4975.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03, over 972544.20 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:23:33,732 INFO [train.py:715] (5/8) Epoch 17, batch 20750, loss[loss=0.1361, simple_loss=0.2123, pruned_loss=0.02994, over 4952.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03005, over 972478.79 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:24:12,680 INFO [train.py:715] (5/8) Epoch 17, batch 20800, loss[loss=0.1285, simple_loss=0.2143, pruned_loss=0.02135, over 4818.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02942, over 972694.19 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:24:51,254 INFO [train.py:715] (5/8) Epoch 17, batch 20850, loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03281, over 4988.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02884, over 971529.30 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:25:30,263 INFO [train.py:715] (5/8) Epoch 17, batch 20900, loss[loss=0.1051, simple_loss=0.179, pruned_loss=0.01567, over 4825.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02877, over 972141.14 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:26:10,246 INFO [train.py:715] (5/8) Epoch 17, batch 20950, loss[loss=0.1241, simple_loss=0.2031, pruned_loss=0.02255, over 4976.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02853, over 972126.84 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:26:48,268 INFO [train.py:715] (5/8) Epoch 17, batch 21000, loss[loss=0.1351, simple_loss=0.2052, pruned_loss=0.03247, over 4954.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02857, over 972207.41 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:26:48,269 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 02:27:00,911 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1882, pruned_loss=0.01077, over 914524.00 frames.
2022-05-09 02:27:38,928 INFO [train.py:715] (5/8) Epoch 17, batch 21050, loss[loss=0.1196, simple_loss=0.1907, pruned_loss=0.02424, over 4986.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.0285, over 971914.34 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:28:18,320 INFO [train.py:715] (5/8) Epoch 17, batch 21100, loss[loss=0.1356, simple_loss=0.2161, pruned_loss=0.0276, over 4981.00 frames.], tot_loss[loss=0.1309, simple_loss=0.205, pruned_loss=0.02836, over 971679.07 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:28:58,365 INFO [train.py:715] (5/8) Epoch 17, batch 21150, loss[loss=0.124, simple_loss=0.212, pruned_loss=0.01796, over 4816.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02865, over 971105.25 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:29:37,028 INFO [train.py:715] (5/8) Epoch 17, batch 21200, loss[loss=0.1222, simple_loss=0.1919, pruned_loss=0.02628, over 4701.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02911, over 971220.14 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:30:15,710 INFO [train.py:715] (5/8) Epoch 17, batch 21250, loss[loss=0.1322, simple_loss=0.2001, pruned_loss=0.03216, over 4727.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02972, over 971220.26 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:30:55,575 INFO [train.py:715] (5/8) Epoch 17, batch 21300, loss[loss=0.1359, simple_loss=0.2116, pruned_loss=0.03011, over 4810.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02926, over 970978.70 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:31:35,364 INFO [train.py:715] (5/8) Epoch 17, batch 21350, loss[loss=0.1289, simple_loss=0.2123, pruned_loss=0.02277, over 4804.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02934, over 971886.37 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:32:13,589 INFO [train.py:715] (5/8) Epoch 17, batch 21400, loss[loss=0.1277, simple_loss=0.2039, pruned_loss=0.02574, over 4810.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0293, over 971391.87 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:32:53,761 INFO [train.py:715] (5/8) Epoch 17, batch 21450, loss[loss=0.1373, simple_loss=0.2117, pruned_loss=0.03149, over 4662.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02901, over 971967.60 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:33:33,550 INFO [train.py:715] (5/8) Epoch 17, batch 21500, loss[loss=0.1424, simple_loss=0.2187, pruned_loss=0.03307, over 4839.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02882, over 971781.39 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:34:12,045 INFO [train.py:715] (5/8) Epoch 17, batch 21550, loss[loss=0.1263, simple_loss=0.2111, pruned_loss=0.02075, over 4867.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02906, over 971575.05 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 02:34:51,492 INFO [train.py:715] (5/8) Epoch 17, batch 21600, loss[loss=0.1272, simple_loss=0.2015, pruned_loss=0.02647, over 4852.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02927, over 971785.69 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:35:31,959 INFO [train.py:715] (5/8) Epoch 17, batch 21650, loss[loss=0.1399, simple_loss=0.2153, pruned_loss=0.03226, over 4848.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02885, over 971953.12 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:36:11,046 INFO [train.py:715] (5/8) Epoch 17, batch 21700, loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03147, over 4947.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 972945.33 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 02:36:49,697 INFO [train.py:715] (5/8) Epoch 17, batch 21750, loss[loss=0.1465, simple_loss=0.2148, pruned_loss=0.03911, over 4867.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03003, over 973296.32 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:37:29,249 INFO [train.py:715] (5/8) Epoch 17, batch 21800, loss[loss=0.137, simple_loss=0.2097, pruned_loss=0.03212, over 4820.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.03001, over 973390.23 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:38:08,211 INFO [train.py:715] (5/8) Epoch 17, batch 21850, loss[loss=0.1264, simple_loss=0.2, pruned_loss=0.02639, over 4884.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0297, over 973252.01 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:38:47,460 INFO [train.py:715] (5/8) Epoch 17, batch 21900, loss[loss=0.1181, simple_loss=0.1831, pruned_loss=0.02654, over 4780.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02971, over 973101.75 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:39:25,952 INFO [train.py:715] (5/8) Epoch 17, batch 21950, loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04266, over 4839.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02962, over 973172.64 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 02:40:05,669 INFO [train.py:715] (5/8) Epoch 17, batch 22000, loss[loss=0.1458, simple_loss=0.2238, pruned_loss=0.03389, over 4776.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02969, over 973858.13 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:40:45,436 INFO [train.py:715] (5/8) Epoch 17, batch 22050, loss[loss=0.1228, simple_loss=0.1898, pruned_loss=0.0279, over 4797.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.0299, over 973450.38 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:41:23,861 INFO [train.py:715] (5/8) Epoch 17, batch 22100, loss[loss=0.1426, simple_loss=0.2139, pruned_loss=0.03562, over 4974.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02968, over 972924.63 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:42:03,597 INFO [train.py:715] (5/8) Epoch 17, batch 22150, loss[loss=0.1195, simple_loss=0.1969, pruned_loss=0.02107, over 4848.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.0292, over 973363.29 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:42:43,493 INFO [train.py:715] (5/8) Epoch 17, batch 22200, loss[loss=0.1302, simple_loss=0.2067, pruned_loss=0.02685, over 4761.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02938, over 973014.10 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:43:22,388 INFO [train.py:715] (5/8) Epoch 17, batch 22250, loss[loss=0.1341, simple_loss=0.2138, pruned_loss=0.02724, over 4813.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02915, over 973555.24 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:44:01,342 INFO [train.py:715] (5/8) Epoch 17, batch 22300, loss[loss=0.1206, simple_loss=0.1993, pruned_loss=0.02101, over 4818.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 972206.04 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:44:41,264 INFO [train.py:715] (5/8) Epoch 17, batch 22350, loss[loss=0.1241, simple_loss=0.2009, pruned_loss=0.02366, over 4817.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02915, over 971818.53 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 02:45:20,839 INFO [train.py:715] (5/8) Epoch 17, batch 22400, loss[loss=0.1535, simple_loss=0.2263, pruned_loss=0.04033, over 4962.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02883, over 971852.60 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 02:45:59,648 INFO [train.py:715] (5/8) Epoch 17, batch 22450, loss[loss=0.1407, simple_loss=0.2098, pruned_loss=0.03586, over 4770.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 970992.34 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:46:38,622 INFO [train.py:715] (5/8) Epoch 17, batch 22500, loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03674, over 4861.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02903, over 970729.94 frames.], batch size: 34, lr: 1.30e-04
2022-05-09 02:47:18,396 INFO [train.py:715] (5/8) Epoch 17, batch 22550, loss[loss=0.128, simple_loss=0.2061, pruned_loss=0.02492, over 4932.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02862, over 971014.15 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:47:56,725 INFO [train.py:715] (5/8) Epoch 17, batch 22600, loss[loss=0.1294, simple_loss=0.2083, pruned_loss=0.02525, over 4859.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02929, over 971072.40 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 02:48:36,264 INFO [train.py:715] (5/8) Epoch 17, batch 22650, loss[loss=0.1317, simple_loss=0.2096, pruned_loss=0.02693, over 4921.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02937, over 971320.71 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:49:15,729 INFO [train.py:715] (5/8) Epoch 17, batch 22700, loss[loss=0.1256, simple_loss=0.2071, pruned_loss=0.02209, over 4787.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03004, over 971492.85 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:49:54,662 INFO [train.py:715] (5/8) Epoch 17, batch 22750, loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.04467, over 4876.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02959, over 971339.55 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 02:50:33,046 INFO [train.py:715] (5/8) Epoch 17, batch 22800, loss[loss=0.1325, simple_loss=0.1942, pruned_loss=0.03534, over 4754.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2078, pruned_loss=0.02899, over 971676.61 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:51:12,437 INFO [train.py:715] (5/8) Epoch 17, batch 22850, loss[loss=0.1184, simple_loss=0.195, pruned_loss=0.02088, over 4888.00 frames.], tot_loss[loss=0.1329, simple_loss=0.208, pruned_loss=0.02888, over 972513.73 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 02:51:52,338 INFO [train.py:715] (5/8) Epoch 17, batch 22900, loss[loss=0.1223, simple_loss=0.194, pruned_loss=0.02527, over 4942.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02912, over 972882.95 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 02:52:30,190 INFO [train.py:715] (5/8) Epoch 17, batch 22950, loss[loss=0.1423, simple_loss=0.2267, pruned_loss=0.02898, over 4946.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02945, over 972941.84 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 02:53:10,086 INFO [train.py:715] (5/8) Epoch 17, batch 23000, loss[loss=0.1354, simple_loss=0.208, pruned_loss=0.03137, over 4776.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02969, over 973571.52 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:53:50,345 INFO [train.py:715] (5/8) Epoch 17, batch 23050, loss[loss=0.1505, simple_loss=0.2141, pruned_loss=0.04341, over 4834.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02979, over 973879.87 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 02:54:29,511 INFO [train.py:715] (5/8) Epoch 17, batch 23100, loss[loss=0.1402, simple_loss=0.2064, pruned_loss=0.03699, over 4889.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02944, over 973648.90 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 02:55:07,924 INFO [train.py:715] (5/8) Epoch 17, batch 23150, loss[loss=0.131, simple_loss=0.2095, pruned_loss=0.02625, over 4890.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02937, over 973364.88 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 02:55:47,704 INFO [train.py:715] (5/8) Epoch 17, batch 23200, loss[loss=0.1373, simple_loss=0.2052, pruned_loss=0.03471, over 4926.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02936, over 973525.44 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:56:27,703 INFO [train.py:715] (5/8) Epoch 17, batch 23250, loss[loss=0.166, simple_loss=0.2373, pruned_loss=0.04742, over 4772.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02955, over 972735.36 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 02:57:05,639 INFO [train.py:715] (5/8) Epoch 17, batch 23300, loss[loss=0.113, simple_loss=0.1913, pruned_loss=0.01736, over 4832.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02981, over 971453.10 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 02:57:44,993 INFO [train.py:715] (5/8) Epoch 17, batch 23350, loss[loss=0.1486, simple_loss=0.2045, pruned_loss=0.0463, over 4991.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03067, over 971767.27 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 02:58:25,086 INFO [train.py:715] (5/8) Epoch 17, batch 23400, loss[loss=0.1489, simple_loss=0.2143, pruned_loss=0.04181, over 4851.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2072, pruned_loss=0.03017, over 971495.05 frames.], batch size: 34, lr: 1.29e-04
2022-05-09 02:59:03,868 INFO [train.py:715] (5/8) Epoch 17, batch 23450, loss[loss=0.1327, simple_loss=0.2111, pruned_loss=0.02715, over 4903.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02953, over 971603.10 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:59:42,962 INFO [train.py:715] (5/8) Epoch 17, batch 23500, loss[loss=0.1286, simple_loss=0.1916, pruned_loss=0.03282, over 4780.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02983, over 971650.43 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:00:22,278 INFO [train.py:715] (5/8) Epoch 17, batch 23550, loss[loss=0.138, simple_loss=0.2089, pruned_loss=0.03351, over 4899.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02975, over 971259.10 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:01:01,965 INFO [train.py:715] (5/8) Epoch 17, batch 23600, loss[loss=0.1209, simple_loss=0.1795, pruned_loss=0.0311, over 4642.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02931, over 971686.68 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:01:40,304 INFO [train.py:715] (5/8) Epoch 17, batch 23650, loss[loss=0.1341, simple_loss=0.2032, pruned_loss=0.03251, over 4835.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02895, over 971460.72 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:02:19,917 INFO [train.py:715] (5/8) Epoch 17, batch 23700, loss[loss=0.1469, simple_loss=0.2292, pruned_loss=0.03232, over 4892.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02916, over 971523.93 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:02:59,506 INFO [train.py:715] (5/8) Epoch 17, batch 23750, loss[loss=0.1501, simple_loss=0.2221, pruned_loss=0.03906, over 4791.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02929, over 971863.26 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:03:38,381 INFO [train.py:715] (5/8) Epoch 17, batch 23800, loss[loss=0.1151, simple_loss=0.1872, pruned_loss=0.02149, over 4980.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02949, over 971935.25 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:04:16,664 INFO [train.py:715] (5/8) Epoch 17, batch 23850, loss[loss=0.1507, simple_loss=0.2264, pruned_loss=0.03756, over 4953.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02955, over 972873.12 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:04:56,705 INFO [train.py:715] (5/8) Epoch 17, batch 23900, loss[loss=0.1332, simple_loss=0.2111, pruned_loss=0.0277, over 4800.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02957, over 972750.59 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:05:35,868 INFO [train.py:715] (5/8) Epoch 17, batch 23950, loss[loss=0.1387, simple_loss=0.2239, pruned_loss=0.02673, over 4792.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02942, over 972666.11 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:06:14,198 INFO [train.py:715] (5/8) Epoch 17, batch 24000, loss[loss=0.1234, simple_loss=0.1929, pruned_loss=0.02693, over 4969.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02938, over 973260.49 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:06:14,199 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 03:06:24,067 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 03:07:02,580 INFO [train.py:715] (5/8) Epoch 17, batch 24050, loss[loss=0.1139, simple_loss=0.1892, pruned_loss=0.01927, over 4804.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 973437.16 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:07:41,973 INFO [train.py:715] (5/8) Epoch 17, batch 24100, loss[loss=0.1161, simple_loss=0.2049, pruned_loss=0.01362, over 4806.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02914, over 972307.34 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:08:22,152 INFO [train.py:715] (5/8) Epoch 17, batch 24150, loss[loss=0.1324, simple_loss=0.2155, pruned_loss=0.02465, over 4808.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.0292, over 971610.00 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:09:00,901 INFO [train.py:715] (5/8) Epoch 17, batch 24200, loss[loss=0.1448, simple_loss=0.2121, pruned_loss=0.03871, over 4985.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02925, over 971309.46 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:09:42,453 INFO [train.py:715] (5/8) Epoch 17, batch 24250, loss[loss=0.1186, simple_loss=0.1863, pruned_loss=0.02546, over 4836.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02919, over 971253.97 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:10:23,059 INFO [train.py:715] (5/8) Epoch 17, batch 24300, loss[loss=0.1556, simple_loss=0.2321, pruned_loss=0.03956, over 4810.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02942, over 971727.96 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:11:02,611 INFO [train.py:715] (5/8) Epoch 17, batch 24350, loss[loss=0.1056, simple_loss=0.1799, pruned_loss=0.01563, over 4895.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02882, over 971629.44 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:11:41,990 INFO [train.py:715] (5/8) Epoch 17, batch 24400, loss[loss=0.1531, simple_loss=0.2282, pruned_loss=0.03894, over 4640.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02864, over 970572.95 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:12:21,139 INFO [train.py:715] (5/8) Epoch 17, batch 24450, loss[loss=0.1501, simple_loss=0.2269, pruned_loss=0.03662, over 4753.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02851, over 971054.32 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:13:01,329 INFO [train.py:715] (5/8) Epoch 17, batch 24500, loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02894, over 4932.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02848, over 971554.10 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 03:13:40,455 INFO [train.py:715] (5/8) Epoch 17, batch 24550, loss[loss=0.137, simple_loss=0.214, pruned_loss=0.02996, over 4963.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02887, over 971661.78 frames.], batch size: 28, lr: 1.29e-04
2022-05-09 03:14:19,285 INFO [train.py:715] (5/8) Epoch 17, batch 24600, loss[loss=0.1293, simple_loss=0.2182, pruned_loss=0.02021, over 4905.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02914, over 971256.03 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:14:59,436 INFO [train.py:715] (5/8) Epoch 17, batch 24650, loss[loss=0.1401, simple_loss=0.2187, pruned_loss=0.03072, over 4753.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02971, over 971173.86 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:15:39,737 INFO [train.py:715] (5/8) Epoch 17, batch 24700, loss[loss=0.1426, simple_loss=0.2224, pruned_loss=0.0314, over 4748.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03005, over 971083.18 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:16:18,260 INFO [train.py:715] (5/8) Epoch 17, batch 24750, loss[loss=0.1286, simple_loss=0.206, pruned_loss=0.02558, over 4985.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02961, over 971734.42 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:16:58,093 INFO [train.py:715] (5/8) Epoch 17, batch 24800, loss[loss=0.1073, simple_loss=0.1846, pruned_loss=0.01503, over 4784.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02918, over 970872.21 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:17:37,934 INFO [train.py:715] (5/8) Epoch 17, batch 24850, loss[loss=0.1401, simple_loss=0.2136, pruned_loss=0.03332, over 4917.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02928, over 970251.41 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:18:17,563 INFO [train.py:715] (5/8) Epoch 17, batch 24900, loss[loss=0.1108, simple_loss=0.1846, pruned_loss=0.0185, over 4791.00 frames.], tot_loss[loss=0.1325, simple_loss=0.206, pruned_loss=0.02954, over 968599.80 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 03:18:56,114 INFO [train.py:715] (5/8) Epoch 17, batch 24950, loss[loss=0.1198, simple_loss=0.2038, pruned_loss=0.01791, over 4780.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02899, over 969579.53 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:19:35,618 INFO [train.py:715] (5/8) Epoch 17, batch 25000, loss[loss=0.1177, simple_loss=0.2018, pruned_loss=0.01685, over 4852.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02901, over 970620.26 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:20:14,000 INFO [train.py:715] (5/8) Epoch 17, batch 25050, loss[loss=0.1389, simple_loss=0.2065, pruned_loss=0.03568, over 4926.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02897, over 970621.50 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:20:52,999 INFO [train.py:715] (5/8) Epoch 17, batch 25100, loss[loss=0.1204, simple_loss=0.1829, pruned_loss=0.02892, over 4852.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02867, over 971116.99 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 03:21:32,978 INFO [train.py:715] (5/8) Epoch 17, batch 25150, loss[loss=0.1261, simple_loss=0.1908, pruned_loss=0.0307, over 4920.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02905, over 972499.08 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:22:12,872 INFO [train.py:715] (5/8) Epoch 17, batch 25200, loss[loss=0.1267, simple_loss=0.1972, pruned_loss=0.02809, over 4919.00 frames.], tot_loss[loss=0.1322, simple_loss=0.206, pruned_loss=0.02921, over 972413.20 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:22:51,915 INFO [train.py:715] (5/8) Epoch 17, batch 25250, loss[loss=0.1168, simple_loss=0.1985, pruned_loss=0.01756, over 4951.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02885, over 972720.89 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:23:31,034 INFO [train.py:715] (5/8) Epoch 17, batch 25300, loss[loss=0.1344, simple_loss=0.2104, pruned_loss=0.02922, over 4774.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02899, over 972408.62 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:24:11,042 INFO [train.py:715] (5/8) Epoch 17, batch 25350, loss[loss=0.1515, simple_loss=0.2338, pruned_loss=0.03459, over 4890.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2055, pruned_loss=0.02887, over 971584.92 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:24:49,786 INFO [train.py:715] (5/8) Epoch 17, batch 25400, loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.0338, over 4826.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02855, over 971958.46 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:25:28,939 INFO [train.py:715] (5/8) Epoch 17, batch 25450, loss[loss=0.1474, simple_loss=0.2235, pruned_loss=0.03562, over 4879.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02903, over 972121.69 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 03:26:08,064 INFO [train.py:715] (5/8) Epoch 17, batch 25500, loss[loss=0.1396, simple_loss=0.2032, pruned_loss=0.038, over 4936.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02899, over 972597.54 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 03:26:47,842 INFO [train.py:715] (5/8) Epoch 17, batch 25550, loss[loss=0.1431, simple_loss=0.2211, pruned_loss=0.03256, over 4954.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.02917, over 972271.16 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:27:26,922 INFO [train.py:715] (5/8) Epoch 17, batch 25600, loss[loss=0.1179, simple_loss=0.199, pruned_loss=0.01839, over 4804.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02876, over 972429.71 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:28:05,427 INFO [train.py:715] (5/8) Epoch 17, batch 25650, loss[loss=0.121, simple_loss=0.1959, pruned_loss=0.02301, over 4729.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02824, over 972446.26 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:28:45,199 INFO [train.py:715] (5/8) Epoch 17, batch 25700, loss[loss=0.1063, simple_loss=0.1774, pruned_loss=0.01754, over 4961.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02864, over 972890.67 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:29:24,287 INFO [train.py:715] (5/8) Epoch 17, batch 25750, loss[loss=0.1387, simple_loss=0.229, pruned_loss=0.02425, over 4865.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02863, over 972121.68 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:30:03,680 INFO [train.py:715] (5/8) Epoch 17, batch 25800, loss[loss=0.1449, simple_loss=0.2218, pruned_loss=0.03393, over 4932.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02904, over 972656.12 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:30:43,161 INFO [train.py:715] (5/8) Epoch 17, batch 25850, loss[loss=0.1444, simple_loss=0.2181, pruned_loss=0.03533, over 4860.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 972029.22 frames.], batch size: 38, lr: 1.29e-04
2022-05-09 03:31:22,523 INFO [train.py:715] (5/8) Epoch 17, batch 25900, loss[loss=0.1236, simple_loss=0.199, pruned_loss=0.02409, over 4819.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 972524.76 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:32:01,050 INFO [train.py:715] (5/8) Epoch 17, batch 25950, loss[loss=0.1493, simple_loss=0.221, pruned_loss=0.0388, over 4920.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02924, over 971955.06 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:32:39,479 INFO [train.py:715] (5/8) Epoch 17, batch 26000, loss[loss=0.1233, simple_loss=0.1982, pruned_loss=0.02426, over 4972.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02881, over 971816.03 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:33:19,119 INFO [train.py:715] (5/8) Epoch 17, batch 26050, loss[loss=0.1535, simple_loss=0.233, pruned_loss=0.03698, over 4757.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02899, over 971086.11 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:33:57,727 INFO [train.py:715] (5/8) Epoch 17, batch 26100, loss[loss=0.1061, simple_loss=0.1864, pruned_loss=0.01295, over 4930.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02907, over 971460.73 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:34:37,124 INFO [train.py:715] (5/8) Epoch 17, batch 26150, loss[loss=0.1159, simple_loss=0.1873, pruned_loss=0.02226, over 4947.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02905, over 971996.95 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:35:16,509 INFO [train.py:715] (5/8) Epoch 17, batch 26200, loss[loss=0.1182, simple_loss=0.197, pruned_loss=0.01972, over 4972.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 972532.20 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:35:56,476 INFO [train.py:715] (5/8) Epoch 17, batch 26250, loss[loss=0.1379, simple_loss=0.1987, pruned_loss=0.03852, over 4893.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02931, over 973241.79 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:36:35,144 INFO [train.py:715] (5/8) Epoch 17, batch 26300, loss[loss=0.1451, simple_loss=0.2271, pruned_loss=0.03154, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02937, over 972687.88 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:37:13,922 INFO [train.py:715] (5/8) Epoch 17, batch 26350, loss[loss=0.1191, simple_loss=0.1919, pruned_loss=0.02311, over 4827.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2051, pruned_loss=0.02873, over 972442.48 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:37:53,864 INFO [train.py:715] (5/8) Epoch 17, batch 26400, loss[loss=0.1155, simple_loss=0.1984, pruned_loss=0.01632, over 4983.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2056, pruned_loss=0.02907, over 971667.47 frames.], batch size: 28, lr: 1.29e-04
2022-05-09 03:38:32,577 INFO [train.py:715] (5/8) Epoch 17, batch 26450, loss[loss=0.1367, simple_loss=0.2163, pruned_loss=0.02858, over 4917.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02895, over 972363.93 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:39:11,786 INFO [train.py:715] (5/8) Epoch 17, batch 26500, loss[loss=0.1438, simple_loss=0.2177, pruned_loss=0.03495, over 4941.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 971975.56 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:39:51,009 INFO [train.py:715] (5/8) Epoch 17, batch 26550, loss[loss=0.1193, simple_loss=0.1953, pruned_loss=0.02167, over 4747.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02897, over 972611.11 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 03:40:29,941 INFO [train.py:715] (5/8) Epoch 17, batch 26600, loss[loss=0.1318, simple_loss=0.2095, pruned_loss=0.02707, over 4660.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 972154.61 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:41:08,350 INFO [train.py:715] (5/8) Epoch 17, batch 26650, loss[loss=0.1289, simple_loss=0.1871, pruned_loss=0.03534, over 4826.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02901, over 972746.33 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:41:47,383 INFO [train.py:715] (5/8) Epoch 17, batch 26700, loss[loss=0.126, simple_loss=0.2024, pruned_loss=0.02481, over 4755.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02896, over 971656.84 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:42:26,787 INFO [train.py:715] (5/8) Epoch 17, batch 26750, loss[loss=0.1344, simple_loss=0.2028, pruned_loss=0.033, over 4955.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02901, over 971885.01 frames.], batch size: 35, lr: 1.29e-04
2022-05-09 03:43:05,134 INFO [train.py:715] (5/8) Epoch 17, batch 26800, loss[loss=0.1139, simple_loss=0.1905, pruned_loss=0.01868, over 4780.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02856, over 970986.32 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:43:43,936 INFO [train.py:715] (5/8) Epoch 17, batch 26850, loss[loss=0.1252, simple_loss=0.2004, pruned_loss=0.02498, over 4910.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02844, over 970757.48 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:44:23,811 INFO [train.py:715] (5/8) Epoch 17, batch 26900, loss[loss=0.1273, simple_loss=0.1974, pruned_loss=0.02861, over 4989.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02838, over 971369.93 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:45:02,978 INFO [train.py:715] (5/8) Epoch 17, batch 26950, loss[loss=0.1396, simple_loss=0.2272, pruned_loss=0.02599, over 4926.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02808, over 972532.89 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:45:41,692 INFO [train.py:715] (5/8) Epoch 17, batch 27000, loss[loss=0.134, simple_loss=0.2056, pruned_loss=0.03117, over 4958.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02839, over 972809.39 frames.], batch size: 35, lr: 1.29e-04
2022-05-09 03:45:41,693 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 03:45:51,479 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.0107, over 914524.00 frames.
2022-05-09 03:46:30,447 INFO [train.py:715] (5/8) Epoch 17, batch 27050, loss[loss=0.135, simple_loss=0.2076, pruned_loss=0.03122, over 4866.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02883, over 972132.77 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:47:09,964 INFO [train.py:715] (5/8) Epoch 17, batch 27100, loss[loss=0.1284, simple_loss=0.2043, pruned_loss=0.02621, over 4812.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02897, over 971669.49 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:47:49,459 INFO [train.py:715] (5/8) Epoch 17, batch 27150, loss[loss=0.1235, simple_loss=0.1936, pruned_loss=0.02676, over 4704.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02902, over 971353.34 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:48:27,666 INFO [train.py:715] (5/8) Epoch 17, batch 27200, loss[loss=0.12, simple_loss=0.1942, pruned_loss=0.02291, over 4972.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02861, over 971140.29 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:49:06,448 INFO [train.py:715] (5/8) Epoch 17, batch 27250, loss[loss=0.1386, simple_loss=0.223, pruned_loss=0.02708, over 4979.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 971342.13 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:49:46,074 INFO [train.py:715] (5/8) Epoch 17, batch 27300, loss[loss=0.09803, simple_loss=0.1737, pruned_loss=0.01117, over 4746.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.0286, over 971980.50 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:50:25,157 INFO [train.py:715] (5/8) Epoch 17, batch 27350, loss[loss=0.1178, simple_loss=0.2005, pruned_loss=0.01756, over 4946.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02876, over 972712.73 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:51:04,593 INFO [train.py:715] (5/8) Epoch 17, batch 27400, loss[loss=0.1228, simple_loss=0.2103, pruned_loss=0.01765, over 4817.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02906, over 972011.23 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:51:43,495 INFO [train.py:715] (5/8) Epoch 17, batch 27450, loss[loss=0.1291, simple_loss=0.2054, pruned_loss=0.02636, over 4698.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02902, over 972824.17 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:52:23,142 INFO [train.py:715] (5/8) Epoch 17, batch 27500, loss[loss=0.1173, simple_loss=0.1925, pruned_loss=0.02107, over 4964.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02906, over 972891.88 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:53:01,811 INFO [train.py:715] (5/8) Epoch 17, batch 27550, loss[loss=0.118, simple_loss=0.1962, pruned_loss=0.01985, over 4931.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 972765.22 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:53:40,304 INFO [train.py:715] (5/8) Epoch 17, batch 27600, loss[loss=0.1434, simple_loss=0.2141, pruned_loss=0.03636, over 4921.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02955, over 971941.09 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:54:19,257 INFO [train.py:715] (5/8) Epoch 17, batch 27650, loss[loss=0.1357, simple_loss=0.2166, pruned_loss=0.02739, over 4962.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.0293, over 972761.78 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:54:57,850 INFO [train.py:715] (5/8) Epoch 17, batch 27700, loss[loss=0.1217, simple_loss=0.1966, pruned_loss=0.0234, over 4841.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02884, over 972616.48 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:55:37,177 INFO [train.py:715] (5/8) Epoch 17, batch 27750, loss[loss=0.1265, simple_loss=0.1927, pruned_loss=0.03015, over 4972.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02862, over 973271.86 frames.], batch size: 33, lr: 1.29e-04
2022-05-09 03:56:16,912 INFO [train.py:715] (5/8) Epoch 17, batch 27800, loss[loss=0.1412, simple_loss=0.2169, pruned_loss=0.03273, over 4985.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 974438.66 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:56:57,479 INFO [train.py:715] (5/8) Epoch 17, batch 27850, loss[loss=0.1501, simple_loss=0.2235, pruned_loss=0.03834, over 4888.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02882, over 973726.98 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:57:37,276 INFO [train.py:715] (5/8) Epoch 17, batch 27900, loss[loss=0.1226, simple_loss=0.1938, pruned_loss=0.02572, over 4834.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02913, over 972886.41 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:58:16,552 INFO [train.py:715] (5/8) Epoch 17, batch 27950, loss[loss=0.128, simple_loss=0.1979, pruned_loss=0.02902, over 4933.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02881, over 972371.75 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 03:58:56,515 INFO [train.py:715] (5/8) Epoch 17, batch 28000, loss[loss=0.1267, simple_loss=0.2047, pruned_loss=0.0243, over 4828.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 971757.26 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:59:36,521 INFO [train.py:715] (5/8) Epoch 17, batch 28050, loss[loss=0.1265, simple_loss=0.2015, pruned_loss=0.02571, over 4942.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02921, over 972511.12 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:00:15,250 INFO [train.py:715] (5/8) Epoch 17, batch 28100, loss[loss=0.1391, simple_loss=0.2104, pruned_loss=0.0339, over 4779.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02924, over 972592.44 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:00:54,612 INFO [train.py:715] (5/8) Epoch 17, batch 28150, loss[loss=0.1283, simple_loss=0.195, pruned_loss=0.03076, over 4773.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02919, over 972296.79 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:01:33,612 INFO [train.py:715] (5/8) Epoch 17, batch 28200, loss[loss=0.1185, simple_loss=0.2003, pruned_loss=0.0184, over 4804.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02897, over 971977.32 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:02:12,000 INFO [train.py:715] (5/8) Epoch 17, batch 28250, loss[loss=0.1331, simple_loss=0.202, pruned_loss=0.03212, over 4812.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02873, over 972087.36 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:02:50,449 INFO [train.py:715] (5/8) Epoch 17, batch 28300, loss[loss=0.1163, simple_loss=0.1998, pruned_loss=0.01642, over 4937.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02833, over 972003.56 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:03:29,616 INFO [train.py:715] (5/8) Epoch 17, batch 28350, loss[loss=0.147, simple_loss=0.2243, pruned_loss=0.0349, over 4860.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02856, over 973017.93 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:04:09,193 INFO [train.py:715] (5/8) Epoch 17, batch 28400, loss[loss=0.1166, simple_loss=0.19, pruned_loss=0.02162, over 4875.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02912, over 972677.42 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:04:48,214 INFO [train.py:715] (5/8) Epoch 17, batch 28450, loss[loss=0.1372, simple_loss=0.2071, pruned_loss=0.03365, over 4844.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02927, over 972929.00 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:05:26,442 INFO [train.py:715] (5/8) Epoch 17, batch 28500, loss[loss=0.1394, simple_loss=0.2159, pruned_loss=0.03142, over 4794.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02889, over 973518.19 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:06:06,461 INFO [train.py:715] (5/8) Epoch 17, batch 28550, loss[loss=0.1353, simple_loss=0.2124, pruned_loss=0.02911, over 4785.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02913, over 971981.43 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 04:06:45,100 INFO [train.py:715] (5/8) Epoch 17, batch 28600, loss[loss=0.1193, simple_loss=0.2012, pruned_loss=0.0187, over 4941.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02948, over 972655.00 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:07:23,871 INFO [train.py:715] (5/8) Epoch 17, batch 28650, loss[loss=0.1032, simple_loss=0.1838, pruned_loss=0.0113, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02915, over 972445.81 frames.], batch size: 28, lr: 1.29e-04
2022-05-09 04:08:02,257 INFO [train.py:715] (5/8) Epoch 17, batch 28700, loss[loss=0.1506, simple_loss=0.2256, pruned_loss=0.03775, over 4987.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02912, over 972755.24 frames.], batch size: 31, lr: 1.29e-04
2022-05-09 04:08:41,574 INFO [train.py:715] (5/8) Epoch 17, batch 28750, loss[loss=0.135, simple_loss=0.2108, pruned_loss=0.02962, over 4776.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02898, over 972189.31 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:09:20,208 INFO [train.py:715] (5/8) Epoch 17, batch 28800, loss[loss=0.1419, simple_loss=0.2198, pruned_loss=0.03202, over 4896.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02895, over 972505.81 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 04:09:58,903 INFO [train.py:715] (5/8) Epoch 17, batch 28850, loss[loss=0.1514, simple_loss=0.2287, pruned_loss=0.03707, over 4980.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02922, over 972730.60 frames.], batch size: 31, lr: 1.29e-04
2022-05-09 04:10:37,991 INFO [train.py:715] (5/8) Epoch 17, batch 28900, loss[loss=0.1191, simple_loss=0.1891, pruned_loss=0.02455, over 4779.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.0296, over 971961.46 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:11:16,520 INFO [train.py:715] (5/8) Epoch 17, batch 28950, loss[loss=0.1366, simple_loss=0.2197, pruned_loss=0.02671, over 4840.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02963, over 972032.61 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:11:54,923 INFO [train.py:715] (5/8) Epoch 17, batch 29000, loss[loss=0.1128, simple_loss=0.1881, pruned_loss=0.01874, over 4756.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 971747.11 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:12:33,658 INFO [train.py:715] (5/8) Epoch 17, batch 29050, loss[loss=0.1284, simple_loss=0.21, pruned_loss=0.0234, over 4919.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02912, over 972053.95 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:13:13,013 INFO [train.py:715] (5/8) Epoch 17, batch 29100, loss[loss=0.1191, simple_loss=0.1892, pruned_loss=0.02445, over 4831.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02867, over 972461.82 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:13:51,907 INFO [train.py:715] (5/8) Epoch 17, batch 29150, loss[loss=0.1202, simple_loss=0.1954, pruned_loss=0.02255, over 4755.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02914, over 971051.56 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:14:30,015 INFO [train.py:715] (5/8) Epoch 17, batch 29200, loss[loss=0.1181, simple_loss=0.1905, pruned_loss=0.0229, over 4823.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02925, over 971117.90 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:15:09,518 INFO [train.py:715] (5/8) Epoch 17, batch 29250, loss[loss=0.1544, simple_loss=0.2153, pruned_loss=0.04674, over 4835.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02943, over 972075.23 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:15:49,144 INFO [train.py:715] (5/8) Epoch 17, batch 29300, loss[loss=0.1298, simple_loss=0.2087, pruned_loss=0.02545, over 4680.00 frames.], tot_loss[loss=0.132, simple_loss=0.2057, pruned_loss=0.02909, over 972324.37 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:16:27,569 INFO [train.py:715] (5/8) Epoch 17, batch 29350, loss[loss=0.1077, simple_loss=0.1802, pruned_loss=0.0176, over 4737.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02915, over 972749.54 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:17:06,157 INFO [train.py:715] (5/8) Epoch 17, batch 29400, loss[loss=0.1343, simple_loss=0.2114, pruned_loss=0.02856, over 4740.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.0293, over 971469.77 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:17:45,840 INFO [train.py:715] (5/8) Epoch 17, batch 29450, loss[loss=0.1091, simple_loss=0.1895, pruned_loss=0.01435, over 4761.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02919, over 972329.52 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:18:24,964 INFO [train.py:715] (5/8) Epoch 17, batch 29500, loss[loss=0.1243, simple_loss=0.1949, pruned_loss=0.02685, over 4944.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02926, over 972066.96 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:19:03,883 INFO [train.py:715] (5/8) Epoch 17, batch 29550, loss[loss=0.1253, simple_loss=0.1917, pruned_loss=0.02946, over 4699.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02924, over 972473.39 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:19:43,164 INFO [train.py:715] (5/8) Epoch 17, batch 29600, loss[loss=0.1201, simple_loss=0.1903, pruned_loss=0.025, over 4835.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 972876.06 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:20:22,739 INFO [train.py:715] (5/8) Epoch 17, batch 29650, loss[loss=0.1105, simple_loss=0.1794, pruned_loss=0.02082, over 4760.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 973074.18 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:21:01,516 INFO [train.py:715] (5/8) Epoch 17, batch 29700, loss[loss=0.1309, simple_loss=0.2126, pruned_loss=0.02459, over 4864.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02868, over 972653.50 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 04:21:40,464 INFO [train.py:715] (5/8) Epoch 17, batch 29750, loss[loss=0.1054, simple_loss=0.1914, pruned_loss=0.009665, over 4906.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02883, over 972979.55 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:22:20,621 INFO [train.py:715] (5/8) Epoch 17, batch 29800, loss[loss=0.1658, simple_loss=0.2362, pruned_loss=0.0477, over 4800.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02896, over 972741.65 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:22:59,615 INFO [train.py:715] (5/8) Epoch 17, batch 29850, loss[loss=0.1314, simple_loss=0.2039, pruned_loss=0.02947, over 4898.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02877, over 972146.18 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 04:23:38,910 INFO [train.py:715] (5/8) Epoch 17, batch 29900, loss[loss=0.131, simple_loss=0.2043, pruned_loss=0.02887, over 4857.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02908, over 972715.97 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:24:18,620 INFO [train.py:715] (5/8) Epoch 17, batch 29950, loss[loss=0.1183, simple_loss=0.1815, pruned_loss=0.02756, over 4866.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02918, over 973196.98 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:24:58,024 INFO [train.py:715] (5/8) Epoch 17, batch 30000, loss[loss=0.1164, simple_loss=0.1845, pruned_loss=0.02413, over 4854.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02885, over 973650.40 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:24:58,025 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 04:25:08,261 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01065, over 914524.00 frames.
2022-05-09 04:25:48,092 INFO [train.py:715] (5/8) Epoch 17, batch 30050, loss[loss=0.1387, simple_loss=0.2067, pruned_loss=0.03534, over 4973.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02914, over 973933.92 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:26:27,727 INFO [train.py:715] (5/8) Epoch 17, batch 30100, loss[loss=0.1593, simple_loss=0.2283, pruned_loss=0.04513, over 4791.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 973130.11 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:27:06,815 INFO [train.py:715] (5/8) Epoch 17, batch 30150, loss[loss=0.1207, simple_loss=0.1914, pruned_loss=0.02498, over 4961.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 973433.09 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:27:46,310 INFO [train.py:715] (5/8) Epoch 17, batch 30200, loss[loss=0.1607, simple_loss=0.2335, pruned_loss=0.04395, over 4759.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2086, pruned_loss=0.02957, over 972339.98 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:28:25,426 INFO [train.py:715] (5/8) Epoch 17, batch 30250, loss[loss=0.1073, simple_loss=0.1753, pruned_loss=0.01962, over 4974.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2088, pruned_loss=0.02971, over 972594.28 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:29:04,418 INFO [train.py:715] (5/8) Epoch 17, batch 30300, loss[loss=0.1225, simple_loss=0.2051, pruned_loss=0.02002, over 4827.00 frames.], tot_loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.02989, over 972720.90 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:29:44,186 INFO [train.py:715] (5/8) Epoch 17, batch 30350, loss[loss=0.1225, simple_loss=0.1982, pruned_loss=0.02338, over 4744.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02948, over 973201.32 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:30:23,369 INFO [train.py:715] (5/8) Epoch 17, batch 30400, loss[loss=0.2004, simple_loss=0.2715, pruned_loss=0.06461, over 4857.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02973, over 973230.07 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:31:02,092 INFO [train.py:715] (5/8) Epoch 17, batch 30450, loss[loss=0.1303, simple_loss=0.2036, pruned_loss=0.02845, over 4853.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02954, over 973100.46 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:31:41,826 INFO [train.py:715] (5/8) Epoch 17, batch 30500, loss[loss=0.1257, simple_loss=0.2019, pruned_loss=0.02473, over 4813.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.0292, over 972889.71 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:32:21,634 INFO [train.py:715] (5/8) Epoch 17, batch 30550, loss[loss=0.1184, simple_loss=0.1948, pruned_loss=0.02098, over 4827.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02946, over 971930.22 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:33:01,422 INFO [train.py:715] (5/8) Epoch 17, batch 30600, loss[loss=0.1593, simple_loss=0.2286, pruned_loss=0.04498, over 4920.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 972285.85 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:33:40,318 INFO [train.py:715] (5/8) Epoch 17, batch 30650, loss[loss=0.1434, simple_loss=0.211, pruned_loss=0.03794, over 4838.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02955, over 972905.77 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:34:20,060 INFO [train.py:715] (5/8) Epoch 17, batch 30700, loss[loss=0.1277, simple_loss=0.2039, pruned_loss=0.02575, over 4903.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02864, over 971893.57 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:34:59,085 INFO [train.py:715] (5/8) Epoch 17, batch 30750, loss[loss=0.1359, simple_loss=0.2053, pruned_loss=0.03324, over 4970.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02847, over 971893.66 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:35:38,912 INFO [train.py:715] (5/8) Epoch 17, batch 30800, loss[loss=0.1415, simple_loss=0.2207, pruned_loss=0.03116, over 4983.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02814, over 972242.85 frames.], batch size: 35, lr: 1.29e-04
2022-05-09 04:36:18,141 INFO [train.py:715] (5/8) Epoch 17, batch 30850, loss[loss=0.1291, simple_loss=0.2071, pruned_loss=0.02551, over 4954.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02865, over 971959.36 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:36:58,357 INFO [train.py:715] (5/8) Epoch 17, batch 30900, loss[loss=0.127, simple_loss=0.2071, pruned_loss=0.02339, over 4763.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02863, over 972451.91 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:37:38,028 INFO [train.py:715] (5/8) Epoch 17, batch 30950, loss[loss=0.1609, simple_loss=0.2381, pruned_loss=0.04183, over 4843.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02889, over 972089.79 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:38:17,299 INFO [train.py:715] (5/8) Epoch 17, batch 31000, loss[loss=0.1219, simple_loss=0.2052, pruned_loss=0.01931, over 4826.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02872, over 971315.76 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:38:57,009 INFO [train.py:715] (5/8) Epoch 17, batch 31050, loss[loss=0.1239, simple_loss=0.1963, pruned_loss=0.02574, over 4840.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02853, over 971633.10 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:39:36,076 INFO [train.py:715] (5/8) Epoch 17, batch 31100, loss[loss=0.1079, simple_loss=0.1824, pruned_loss=0.0167, over 4783.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02871, over 971688.07 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:40:15,211 INFO [train.py:715] (5/8) Epoch 17, batch 31150, loss[loss=0.1238, simple_loss=0.1948, pruned_loss=0.02646, over 4939.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02862, over 971465.02 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:40:54,496 INFO [train.py:715] (5/8) Epoch 17, batch 31200, loss[loss=0.1148, simple_loss=0.1857, pruned_loss=0.0219, over 4959.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02881, over 972420.06 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:41:34,595 INFO [train.py:715] (5/8) Epoch 17, batch 31250, loss[loss=0.1619, simple_loss=0.2377, pruned_loss=0.04307, over 4754.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.0291, over 972267.54 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:42:13,892 INFO [train.py:715] (5/8) Epoch 17, batch 31300, loss[loss=0.1277, simple_loss=0.2065, pruned_loss=0.02447, over 4929.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02954, over 972058.28 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:42:53,279 INFO [train.py:715] (5/8) Epoch 17, batch 31350, loss[loss=0.1367, simple_loss=0.203, pruned_loss=0.03519, over 4831.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 971895.28 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:43:32,644 INFO [train.py:715] (5/8) Epoch 17, batch 31400, loss[loss=0.1658, simple_loss=0.2276, pruned_loss=0.052, over 4993.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 972313.13 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:44:11,254 INFO [train.py:715] (5/8) Epoch 17, batch 31450, loss[loss=0.1162, simple_loss=0.1946, pruned_loss=0.01892, over 4933.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.0292, over 971994.02 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:44:51,214 INFO [train.py:715] (5/8) Epoch 17, batch 31500, loss[loss=0.115, simple_loss=0.1872, pruned_loss=0.02146, over 4814.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.0292, over 972100.35 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:45:29,939 INFO [train.py:715] (5/8) Epoch 17, batch 31550, loss[loss=0.1291, simple_loss=0.207, pruned_loss=0.02556, over 4909.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02852, over 971632.29 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:46:09,496 INFO [train.py:715] (5/8) Epoch 17, batch 31600, loss[loss=0.1534, simple_loss=0.2177, pruned_loss=0.0445, over 4834.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02836, over 972509.07 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:46:48,901 INFO [train.py:715] (5/8) Epoch 17, batch 31650, loss[loss=0.1192, simple_loss=0.1926, pruned_loss=0.02294, over 4779.00 frames.], tot_loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.02795, over 972499.54 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:47:28,181 INFO [train.py:715] (5/8) Epoch 17, batch 31700, loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.0284, over 4985.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02814, over 971825.31 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:48:07,938 INFO [train.py:715] (5/8) Epoch 17, batch 31750, loss[loss=0.1671, simple_loss=0.2577, pruned_loss=0.03823, over 4974.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02848, over 972895.62 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:48:47,176 INFO [train.py:715] (5/8) Epoch 17, batch 31800, loss[loss=0.1472, simple_loss=0.2225, pruned_loss=0.03592, over 4742.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 972432.03 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:49:27,377 INFO [train.py:715] (5/8) Epoch 17, batch 31850, loss[loss=0.1331, simple_loss=0.2063, pruned_loss=0.0299, over 4799.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02867, over 973392.20 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:50:06,508 INFO [train.py:715] (5/8) Epoch 17, batch 31900, loss[loss=0.154, simple_loss=0.2133, pruned_loss=0.0474, over 4961.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02861, over 973019.69 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 04:50:45,987 INFO [train.py:715] (5/8) Epoch 17, batch 31950, loss[loss=0.1236, simple_loss=0.1954, pruned_loss=0.02595, over 4847.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02867, over 973677.10 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:51:25,761 INFO [train.py:715] (5/8) Epoch 17, batch 32000, loss[loss=0.1335, simple_loss=0.1986, pruned_loss=0.03419, over 4814.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02849, over 972718.76 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:52:04,647 INFO [train.py:715] (5/8) Epoch 17, batch 32050, loss[loss=0.1617, simple_loss=0.2233, pruned_loss=0.05008, over 4909.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02865, over 973415.14 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 04:52:44,368 INFO [train.py:715] (5/8) Epoch 17, batch 32100, loss[loss=0.1413, simple_loss=0.2231, pruned_loss=0.02971, over 4911.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 973362.88 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:53:23,404 INFO [train.py:715] (5/8) Epoch 17, batch 32150, loss[loss=0.1292, simple_loss=0.2004, pruned_loss=0.02896, over 4990.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02882, over 973504.68 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:54:02,757 INFO [train.py:715] (5/8) Epoch 17, batch 32200, loss[loss=0.1553, simple_loss=0.2434, pruned_loss=0.03354, over 4889.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 972635.64 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 04:54:45,063 INFO [train.py:715] (5/8) Epoch 17, batch 32250, loss[loss=0.1088, simple_loss=0.1859, pruned_loss=0.01585, over 4760.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02811, over 972520.92 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:55:24,424 INFO [train.py:715] (5/8) Epoch 17, batch 32300, loss[loss=0.1355, simple_loss=0.2204, pruned_loss=0.0253, over 4982.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02897, over 972964.95 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:56:04,325 INFO [train.py:715] (5/8) Epoch 17, batch 32350, loss[loss=0.1412, simple_loss=0.2199, pruned_loss=0.0313, over 4889.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02891, over 973242.51 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 04:56:43,382 INFO [train.py:715] (5/8) Epoch 17, batch 32400, loss[loss=0.1201, simple_loss=0.1934, pruned_loss=0.02337, over 4783.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02875, over 972622.90 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:57:22,532 INFO [train.py:715] (5/8) Epoch 17, batch 32450, loss[loss=0.1584, simple_loss=0.2277, pruned_loss=0.04454, over 4963.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02854, over 972364.96 frames.], batch size: 39, lr: 1.28e-04
2022-05-09 04:58:02,555 INFO [train.py:715] (5/8) Epoch 17, batch 32500, loss[loss=0.1281, simple_loss=0.1999, pruned_loss=0.02819, over 4764.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02831, over 970890.53 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 04:58:41,968 INFO [train.py:715] (5/8) Epoch 17, batch 32550, loss[loss=0.1533, simple_loss=0.2378, pruned_loss=0.03437, over 4863.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02842, over 970286.47 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 04:59:21,560 INFO [train.py:715] (5/8) Epoch 17, batch 32600, loss[loss=0.1213, simple_loss=0.1874, pruned_loss=0.02764, over 4795.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02907, over 971123.76 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:00:01,071 INFO [train.py:715] (5/8) Epoch 17, batch 32650, loss[loss=0.1587, simple_loss=0.229, pruned_loss=0.04421, over 4986.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02964, over 972270.72 frames.], batch size: 31, lr: 1.28e-04
2022-05-09 05:00:39,805 INFO [train.py:715] (5/8) Epoch 17, batch 32700, loss[loss=0.1645, simple_loss=0.2351, pruned_loss=0.04696, over 4952.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02949, over 972557.96 frames.], batch size: 39, lr: 1.28e-04
2022-05-09 05:01:19,987 INFO [train.py:715] (5/8) Epoch 17, batch 32750, loss[loss=0.1324, simple_loss=0.2151, pruned_loss=0.0249, over 4901.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02903, over 972562.23 frames.], batch size: 22, lr: 1.28e-04
2022-05-09 05:01:59,335 INFO [train.py:715] (5/8) Epoch 17, batch 32800, loss[loss=0.108, simple_loss=0.1814, pruned_loss=0.01728, over 4795.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 971484.96 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:02:38,971 INFO [train.py:715] (5/8) Epoch 17, batch 32850, loss[loss=0.1405, simple_loss=0.2115, pruned_loss=0.0348, over 4934.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.0293, over 971332.76 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:03:18,520 INFO [train.py:715] (5/8) Epoch 17, batch 32900, loss[loss=0.1405, simple_loss=0.221, pruned_loss=0.03001, over 4777.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.02922, over 972386.17 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:03:58,025 INFO [train.py:715] (5/8) Epoch 17, batch 32950, loss[loss=0.1409, simple_loss=0.2262, pruned_loss=0.0278, over 4817.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02858, over 971459.20 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 05:04:36,960 INFO [train.py:715] (5/8) Epoch 17, batch 33000, loss[loss=0.1605, simple_loss=0.2347, pruned_loss=0.04316, over 4816.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02857, over 971146.53 frames.], batch size: 26, lr: 1.28e-04
2022-05-09 05:04:36,961 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 05:04:49,645 INFO [train.py:742] (5/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1881, pruned_loss=0.0108, over 914524.00 frames.
2022-05-09 05:05:28,990 INFO [train.py:715] (5/8) Epoch 17, batch 33050, loss[loss=0.1211, simple_loss=0.1994, pruned_loss=0.02141, over 4789.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02925, over 970890.95 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:06:08,146 INFO [train.py:715] (5/8) Epoch 17, batch 33100, loss[loss=0.1364, simple_loss=0.209, pruned_loss=0.03187, over 4961.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02946, over 971521.70 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:06:47,450 INFO [train.py:715] (5/8) Epoch 17, batch 33150, loss[loss=0.1281, simple_loss=0.2019, pruned_loss=0.02719, over 4828.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02948, over 971560.31 frames.], batch size: 30, lr: 1.28e-04
2022-05-09 05:07:27,183 INFO [train.py:715] (5/8) Epoch 17, batch 33200, loss[loss=0.1211, simple_loss=0.1961, pruned_loss=0.02304, over 4900.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02923, over 972181.53 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 05:08:06,797 INFO [train.py:715] (5/8) Epoch 17, batch 33250, loss[loss=0.158, simple_loss=0.2429, pruned_loss=0.03653, over 4947.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02887, over 972746.08 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:08:46,105 INFO [train.py:715] (5/8) Epoch 17, batch 33300, loss[loss=0.1073, simple_loss=0.1765, pruned_loss=0.01907, over 4772.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02906, over 973517.34 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:09:25,687 INFO [train.py:715] (5/8) Epoch 17, batch 33350, loss[loss=0.1339, simple_loss=0.2005, pruned_loss=0.0337, over 4839.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02896, over 973327.98 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:10:05,486 INFO [train.py:715] (5/8) Epoch 17, batch 33400, loss[loss=0.1498, simple_loss=0.216, pruned_loss=0.04187, over 4759.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02942, over 972675.52 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:10:44,825 INFO [train.py:715] (5/8) Epoch 17, batch 33450, loss[loss=0.1131, simple_loss=0.1913, pruned_loss=0.01751, over 4961.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02937, over 972130.81 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:11:24,374 INFO [train.py:715] (5/8) Epoch 17, batch 33500, loss[loss=0.1398, simple_loss=0.2167, pruned_loss=0.0315, over 4857.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02922, over 971793.51 frames.], batch size: 20, lr: 1.28e-04
2022-05-09 05:12:04,586 INFO [train.py:715] (5/8) Epoch 17, batch 33550, loss[loss=0.1267, simple_loss=0.2007, pruned_loss=0.02633, over 4930.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 972228.23 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:12:44,743 INFO [train.py:715] (5/8) Epoch 17, batch 33600, loss[loss=0.1373, simple_loss=0.2206, pruned_loss=0.02704, over 4738.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02835, over 972639.79 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:13:23,720 INFO [train.py:715] (5/8) Epoch 17, batch 33650, loss[loss=0.1459, simple_loss=0.228, pruned_loss=0.03187, over 4884.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02806, over 973081.74 frames.], batch size: 22, lr: 1.28e-04
2022-05-09 05:14:03,357 INFO [train.py:715] (5/8) Epoch 17, batch 33700, loss[loss=0.1428, simple_loss=0.2213, pruned_loss=0.03215, over 4844.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02801, over 972371.46 frames.], batch size: 32, lr: 1.28e-04
2022-05-09 05:14:42,577 INFO [train.py:715] (5/8) Epoch 17, batch 33750, loss[loss=0.1079, simple_loss=0.1848, pruned_loss=0.01545, over 4778.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.0281, over 972074.19 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:15:21,394 INFO [train.py:715] (5/8) Epoch 17, batch 33800, loss[loss=0.1271, simple_loss=0.2033, pruned_loss=0.02543, over 4914.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971706.74 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:16:01,527 INFO [train.py:715] (5/8) Epoch 17, batch 33850, loss[loss=0.1253, simple_loss=0.1988, pruned_loss=0.02596, over 4799.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02839, over 971308.35 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:16:41,836 INFO [train.py:715] (5/8) Epoch 17, batch 33900, loss[loss=0.1189, simple_loss=0.1908, pruned_loss=0.02345, over 4918.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02864, over 971626.64 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:17:21,089 INFO [train.py:715] (5/8) Epoch 17, batch 33950, loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.02774, over 4870.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.0288, over 971524.32 frames.], batch size: 32, lr: 1.28e-04
2022-05-09 05:18:00,096 INFO [train.py:715] (5/8) Epoch 17, batch 34000, loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03072, over 4950.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.029, over 972109.06 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:18:39,507 INFO [train.py:715] (5/8) Epoch 17, batch 34050, loss[loss=0.1477, simple_loss=0.2208, pruned_loss=0.03729, over 4968.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02848, over 970850.89 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:19:19,505 INFO [train.py:715] (5/8) Epoch 17, batch 34100, loss[loss=0.1507, simple_loss=0.2174, pruned_loss=0.042, over 4914.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.0287, over 971008.65 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:19:58,308 INFO [train.py:715] (5/8) Epoch 17, batch 34150, loss[loss=0.1248, simple_loss=0.2019, pruned_loss=0.02384, over 4822.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02919, over 971066.89 frames.], batch size: 26, lr: 1.28e-04
2022-05-09 05:20:37,450 INFO [train.py:715] (5/8) Epoch 17, batch 34200, loss[loss=0.117, simple_loss=0.1992, pruned_loss=0.01735, over 4974.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 972890.07 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 05:21:16,560 INFO [train.py:715] (5/8) Epoch 17, batch 34250, loss[loss=0.1182, simple_loss=0.1923, pruned_loss=0.02201, over 4924.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.0289, over 972669.01 frames.], batch size: 23, lr: 1.28e-04
2022-05-09 05:21:55,280 INFO [train.py:715] (5/8) Epoch 17, batch 34300, loss[loss=0.1158, simple_loss=0.1852, pruned_loss=0.02322, over 4902.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.02843, over 972667.23 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:22:34,165 INFO [train.py:715] (5/8) Epoch 17, batch 34350, loss[loss=0.1152, simple_loss=0.1947, pruned_loss=0.01781, over 4933.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.02842, over 973294.30 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:23:13,526 INFO [train.py:715] (5/8) Epoch 17, batch 34400, loss[loss=0.1061, simple_loss=0.1856, pruned_loss=0.01328, over 4926.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02823, over 973530.99 frames.], batch size: 29, lr: 1.28e-04
2022-05-09 05:23:52,516 INFO [train.py:715] (5/8) Epoch 17, batch 34450, loss[loss=0.1197, simple_loss=0.2084, pruned_loss=0.01552, over 4961.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.0284, over 974071.26 frames.], batch size: 24, lr: 1.28e-04
2022-05-09 05:24:30,968 INFO [train.py:715] (5/8) Epoch 17, batch 34500, loss[loss=0.1251, simple_loss=0.1919, pruned_loss=0.02914, over 4919.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02904, over 973465.51 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 05:25:09,845 INFO [train.py:715] (5/8) Epoch 17, batch 34550, loss[loss=0.1067, simple_loss=0.1885, pruned_loss=0.01249, over 4960.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02873, over 972902.58 frames.], batch size: 24, lr: 1.28e-04
2022-05-09 05:25:48,993 INFO [train.py:715] (5/8) Epoch 17, batch 34600, loss[loss=0.1611, simple_loss=0.2276, pruned_loss=0.04731, over 4753.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02876, over 972166.32 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:26:27,693 INFO [train.py:715] (5/8) Epoch 17, batch 34650, loss[loss=0.1163, simple_loss=0.1957, pruned_loss=0.01843, over 4801.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02851, over 972100.84 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:27:06,960 INFO [train.py:715] (5/8) Epoch 17, batch 34700, loss[loss=0.1443, simple_loss=0.206, pruned_loss=0.04136, over 4815.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02882, over 972816.52 frames.], batch size: 13, lr: 1.28e-04
2022-05-09 05:27:45,506 INFO [train.py:715] (5/8) Epoch 17, batch 34750, loss[loss=0.1456, simple_loss=0.2224, pruned_loss=0.03438, over 4699.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.0286, over 972874.55 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:28:22,196 INFO [train.py:715] (5/8) Epoch 17, batch 34800, loss[loss=0.1509, simple_loss=0.2104, pruned_loss=0.0457, over 4837.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02883, over 973231.73 frames.], batch size: 12, lr: 1.28e-04
2022-05-09 05:29:12,356 INFO [train.py:715] (5/8) Epoch 18, batch 0, loss[loss=0.1248, simple_loss=0.2062, pruned_loss=0.0217, over 4819.00 frames.], tot_loss[loss=0.1248, simple_loss=0.2062, pruned_loss=0.0217, over 4819.00 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 05:29:51,055 INFO [train.py:715] (5/8) Epoch 18, batch 50, loss[loss=0.1338, simple_loss=0.2132, pruned_loss=0.02714, over 4753.00 frames.], tot_loss[loss=0.1285, simple_loss=0.2025, pruned_loss=0.02723, over 219372.31 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:30:31,043 INFO [train.py:715] (5/8) Epoch 18, batch 100, loss[loss=0.1166, simple_loss=0.1894, pruned_loss=0.02188, over 4957.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2041, pruned_loss=0.02783, over 387317.87 frames.], batch size: 23, lr: 1.25e-04
2022-05-09 05:31:10,961 INFO [train.py:715] (5/8) Epoch 18, batch 150, loss[loss=0.1361, simple_loss=0.2141, pruned_loss=0.02902, over 4747.00 frames.], tot_loss[loss=0.13, simple_loss=0.205, pruned_loss=0.02744, over 516950.90 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:31:50,258 INFO [train.py:715] (5/8) Epoch 18, batch 200, loss[loss=0.1325, simple_loss=0.2138, pruned_loss=0.02562, over 4701.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.028, over 618497.32 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:32:29,108 INFO [train.py:715] (5/8) Epoch 18, batch 250, loss[loss=0.1261, simple_loss=0.1941, pruned_loss=0.02902, over 4884.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02866, over 696644.02 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:33:08,563 INFO [train.py:715] (5/8) Epoch 18, batch 300, loss[loss=0.1167, simple_loss=0.1871, pruned_loss=0.02311, over 4825.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.02837, over 758100.46 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:33:48,414 INFO [train.py:715] (5/8) Epoch 18, batch 350, loss[loss=0.2346, simple_loss=0.2998, pruned_loss=0.08474, over 4835.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02825, over 805963.59 frames.], batch size: 30, lr: 1.25e-04
2022-05-09 05:34:27,355 INFO [train.py:715] (5/8) Epoch 18, batch 400, loss[loss=0.1141, simple_loss=0.1914, pruned_loss=0.01839, over 4956.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02917, over 843658.97 frames.], batch size: 35, lr: 1.25e-04
2022-05-09 05:35:07,143 INFO [train.py:715] (5/8) Epoch 18, batch 450, loss[loss=0.1498, simple_loss=0.2259, pruned_loss=0.03686, over 4890.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 872514.01 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 05:35:47,324 INFO [train.py:715] (5/8) Epoch 18, batch 500, loss[loss=0.115, simple_loss=0.1993, pruned_loss=0.01532, over 4991.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02919, over 895330.83 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:36:27,093 INFO [train.py:715] (5/8) Epoch 18, batch 550, loss[loss=0.1332, simple_loss=0.197, pruned_loss=0.03467, over 4972.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02907, over 912660.76 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:37:06,105 INFO [train.py:715] (5/8) Epoch 18, batch 600, loss[loss=0.1341, simple_loss=0.2097, pruned_loss=0.0293, over 4973.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02874, over 926096.33 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:37:45,637 INFO [train.py:715] (5/8) Epoch 18, batch 650, loss[loss=0.1234, simple_loss=0.2037, pruned_loss=0.02154, over 4940.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 936664.97 frames.], batch size: 23, lr: 1.25e-04
2022-05-09 05:38:25,475 INFO [train.py:715] (5/8) Epoch 18, batch 700, loss[loss=0.1419, simple_loss=0.2105, pruned_loss=0.03671, over 4860.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02875, over 943908.68 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 05:39:04,427 INFO [train.py:715] (5/8) Epoch 18, batch 750, loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.0278, over 4890.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02864, over 950071.39 frames.], batch size: 22, lr: 1.25e-04
2022-05-09 05:39:43,256 INFO [train.py:715] (5/8) Epoch 18, batch 800, loss[loss=0.1266, simple_loss=0.2064, pruned_loss=0.02341, over 4915.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02903, over 954431.24 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:40:22,748 INFO [train.py:715] (5/8) Epoch 18, batch 850, loss[loss=0.1382, simple_loss=0.2088, pruned_loss=0.03378, over 4903.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02978, over 958356.89 frames.], batch size: 39, lr: 1.25e-04
2022-05-09 05:41:02,300 INFO [train.py:715] (5/8) Epoch 18, batch 900, loss[loss=0.1326, simple_loss=0.1991, pruned_loss=0.03304, over 4869.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02934, over 961738.60 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 05:41:41,274 INFO [train.py:715] (5/8) Epoch 18, batch 950, loss[loss=0.1261, simple_loss=0.2051, pruned_loss=0.02358, over 4800.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02949, over 963629.24 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:42:20,890 INFO [train.py:715] (5/8) Epoch 18, batch 1000, loss[loss=0.1366, simple_loss=0.2001, pruned_loss=0.03658, over 4974.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02947, over 965902.17 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:43:00,528 INFO [train.py:715] (5/8) Epoch 18, batch 1050, loss[loss=0.1568, simple_loss=0.2422, pruned_loss=0.03576, over 4909.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03009, over 967481.03 frames.], batch size: 39, lr: 1.25e-04
2022-05-09 05:43:39,931 INFO [train.py:715] (5/8) Epoch 18, batch 1100, loss[loss=0.1378, simple_loss=0.2123, pruned_loss=0.03159, over 4958.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02999, over 968639.86 frames.], batch size: 24, lr: 1.25e-04
2022-05-09 05:44:18,725 INFO [train.py:715] (5/8) Epoch 18, batch 1150, loss[loss=0.133, simple_loss=0.209, pruned_loss=0.02844, over 4769.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03003, over 969418.28 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:44:58,551 INFO [train.py:715] (5/8) Epoch 18, batch 1200, loss[loss=0.1215, simple_loss=0.1964, pruned_loss=0.02332, over 4789.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02979, over 969144.42 frames.], batch size: 24, lr: 1.25e-04
2022-05-09 05:45:38,520 INFO [train.py:715] (5/8) Epoch 18, batch 1250, loss[loss=0.1297, simple_loss=0.2039, pruned_loss=0.02771, over 4822.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02983, over 969582.81 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 05:46:17,550 INFO [train.py:715] (5/8) Epoch 18, batch 1300, loss[loss=0.1142, simple_loss=0.1905, pruned_loss=0.01895, over 4907.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02998, over 969880.41 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 05:46:56,373 INFO [train.py:715] (5/8) Epoch 18, batch 1350, loss[loss=0.1739, simple_loss=0.2527, pruned_loss=0.04759, over 4852.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02988, over 970060.30 frames.], batch size: 20, lr: 1.25e-04
2022-05-09 05:47:35,781 INFO [train.py:715] (5/8) Epoch 18, batch 1400, loss[loss=0.1139, simple_loss=0.1832, pruned_loss=0.02229, over 4851.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02968, over 971145.06 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 05:48:15,008 INFO [train.py:715] (5/8) Epoch 18, batch 1450, loss[loss=0.1638, simple_loss=0.2349, pruned_loss=0.0464, over 4824.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02998, over 971313.72 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:48:53,404 INFO [train.py:715] (5/8) Epoch 18, batch 1500, loss[loss=0.1316, simple_loss=0.2116, pruned_loss=0.02575, over 4812.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2091, pruned_loss=0.02977, over 970916.01 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 05:49:32,909 INFO [train.py:715] (5/8) Epoch 18, batch 1550, loss[loss=0.1074, simple_loss=0.1796, pruned_loss=0.01761, over 4772.00 frames.], tot_loss[loss=0.134, simple_loss=0.2087, pruned_loss=0.02962, over 971475.88 frames.], batch size: 12, lr: 1.25e-04
2022-05-09 05:50:12,321 INFO [train.py:715] (5/8) Epoch 18, batch 1600, loss[loss=0.1104, simple_loss=0.1842, pruned_loss=0.01832, over 4964.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2087, pruned_loss=0.02951, over 971109.72 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:50:51,521 INFO [train.py:715] (5/8) Epoch 18, batch 1650, loss[loss=0.1326, simple_loss=0.2058, pruned_loss=0.02966, over 4934.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2086, pruned_loss=0.02949, over 971610.71 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:51:30,467 INFO [train.py:715] (5/8) Epoch 18, batch 1700, loss[loss=0.1316, simple_loss=0.2106, pruned_loss=0.02633, over 4697.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02966, over 971442.30 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:52:09,885 INFO [train.py:715] (5/8) Epoch 18, batch 1750, loss[loss=0.1215, simple_loss=0.1948, pruned_loss=0.02406, over 4834.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2082, pruned_loss=0.0293, over 971321.33 frames.], batch size: 30, lr: 1.25e-04
2022-05-09 05:52:49,168 INFO [train.py:715] (5/8) Epoch 18, batch 1800, loss[loss=0.1433, simple_loss=0.2203, pruned_loss=0.03312, over 4947.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02883, over 971711.89 frames.], batch size: 29, lr: 1.25e-04
2022-05-09 05:53:27,452 INFO [train.py:715] (5/8) Epoch 18, batch 1850, loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03539, over 4757.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02875, over 972503.28 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:54:06,242 INFO [train.py:715] (5/8) Epoch 18, batch 1900, loss[loss=0.1171, simple_loss=0.1803, pruned_loss=0.02695, over 4833.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02873, over 971804.98 frames.], batch size: 13, lr: 1.25e-04
2022-05-09 05:54:45,620 INFO [train.py:715] (5/8) Epoch 18, batch 1950, loss[loss=0.178, simple_loss=0.2354, pruned_loss=0.06035, over 4872.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02929, over 971144.08 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:55:24,352 INFO [train.py:715] (5/8) Epoch 18, batch 2000, loss[loss=0.1067, simple_loss=0.1778, pruned_loss=0.01785, over 4829.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02965, over 971315.26 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 05:56:02,839 INFO [train.py:715] (5/8) Epoch 18, batch 2050, loss[loss=0.123, simple_loss=0.1977, pruned_loss=0.02409, over 4800.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02986, over 972424.67 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:56:42,076 INFO [train.py:715] (5/8) Epoch 18, batch 2100, loss[loss=0.1369, simple_loss=0.2232, pruned_loss=0.02525, over 4816.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02957, over 972053.98 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 05:57:21,523 INFO [train.py:715] (5/8) Epoch 18, batch 2150, loss[loss=0.1401, simple_loss=0.2126, pruned_loss=0.03377, over 4948.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.0296, over 971464.20 frames.], batch size: 35, lr: 1.25e-04
2022-05-09 05:57:59,831 INFO [train.py:715] (5/8) Epoch 18, batch 2200, loss[loss=0.124, simple_loss=0.2032, pruned_loss=0.02238, over 4747.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02912, over 971623.02 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:58:39,479 INFO [train.py:715] (5/8) Epoch 18, batch 2250, loss[loss=0.1033, simple_loss=0.1777, pruned_loss=0.01445, over 4985.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02881, over 972109.92 frames.], batch size: 24, lr: 1.25e-04
2022-05-09 05:59:18,829 INFO [train.py:715] (5/8) Epoch 18, batch 2300, loss[loss=0.1618, simple_loss=0.2354, pruned_loss=0.04412, over 4932.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 973502.80 frames.], batch size: 23, lr: 1.25e-04
2022-05-09 05:59:57,619 INFO [train.py:715] (5/8) Epoch 18, batch 2350, loss[loss=0.1199, simple_loss=0.1939, pruned_loss=0.02299, over 4987.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02864, over 972906.44 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 06:00:36,231 INFO [train.py:715] (5/8) Epoch 18, batch 2400, loss[loss=0.1458, simple_loss=0.2185, pruned_loss=0.03656, over 4918.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02888, over 973205.47 frames.], batch size: 39, lr: 1.25e-04
2022-05-09 06:01:15,693 INFO [train.py:715] (5/8) Epoch 18, batch 2450, loss[loss=0.1326, simple_loss=0.2085, pruned_loss=0.02841, over 4752.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02956, over 973367.52 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 06:01:55,086 INFO [train.py:715] (5/8) Epoch 18, batch 2500, loss[loss=0.1412, simple_loss=0.2108, pruned_loss=0.03577, over 4829.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02892, over 972386.70 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 06:02:33,096 INFO [train.py:715] (5/8) Epoch 18, batch 2550, loss[loss=0.1257, simple_loss=0.2046, pruned_loss=0.02341, over 4968.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02915, over 971469.25 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 06:03:11,864 INFO [train.py:715] (5/8) Epoch 18, batch 2600, loss[loss=0.1253, simple_loss=0.2078, pruned_loss=0.02144, over 4814.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02941, over 971635.81 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 06:03:51,787 INFO [train.py:715] (5/8) Epoch 18, batch 2650, loss[loss=0.1112, simple_loss=0.1928, pruned_loss=0.0148, over 4745.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02898, over 972073.66 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 06:04:30,525 INFO [train.py:715] (5/8) Epoch 18, batch 2700, loss[loss=0.1469, simple_loss=0.2132, pruned_loss=0.04027, over 4908.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02888, over 971855.78 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 06:05:08,887 INFO [train.py:715] (5/8) Epoch 18, batch 2750, loss[loss=0.1169, simple_loss=0.1941, pruned_loss=0.01983, over 4951.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02876, over 972545.52 frames.], batch size: 29, lr: 1.25e-04
2022-05-09 06:05:47,974 INFO [train.py:715] (5/8) Epoch 18, batch 2800, loss[loss=0.1563, simple_loss=0.2286, pruned_loss=0.04203, over 4757.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.02913, over 972124.80 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 06:06:27,517 INFO [train.py:715] (5/8) Epoch 18, batch 2850, loss[loss=0.1367, simple_loss=0.2146, pruned_loss=0.02941, over 4980.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02887, over 971773.35 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 06:07:06,090 INFO [train.py:715] (5/8) Epoch 18, batch 2900, loss[loss=0.1589, simple_loss=0.2332, pruned_loss=0.04233, over 4921.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02912, over 971466.32 frames.], batch size: 29, lr: 1.25e-04
2022-05-09 06:07:44,916 INFO [train.py:715] (5/8) Epoch 18, batch 2950, loss[loss=0.1364, simple_loss=0.202, pruned_loss=0.03544, over 4788.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02925, over 971311.29 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 06:08:24,280 INFO [train.py:715] (5/8) Epoch 18, batch 3000, loss[loss=0.1466, simple_loss=0.2194, pruned_loss=0.03693, over 4852.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02942, over 972019.49 frames.], batch size: 20, lr: 1.25e-04
2022-05-09 06:08:24,281 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 06:08:34,097 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01065, over 914524.00 frames.
2022-05-09 06:09:14,111 INFO [train.py:715] (5/8) Epoch 18, batch 3050, loss[loss=0.1423, simple_loss=0.2235, pruned_loss=0.03058, over 4761.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02924, over 971130.45 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 06:09:52,622 INFO [train.py:715] (5/8) Epoch 18, batch 3100, loss[loss=0.1486, simple_loss=0.2127, pruned_loss=0.04223, over 4977.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02941, over 971156.71 frames.], batch size: 35, lr: 1.25e-04
2022-05-09 06:10:31,509 INFO [train.py:715] (5/8) Epoch 18, batch 3150, loss[loss=0.1238, simple_loss=0.2007, pruned_loss=0.02348, over 4836.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02889, over 972007.42 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 06:11:10,547 INFO [train.py:715] (5/8) Epoch 18, batch 3200, loss[loss=0.1508, simple_loss=0.2146, pruned_loss=0.04352, over 4936.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02852, over 972102.55 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:11:50,028 INFO [train.py:715] (5/8) Epoch 18, batch 3250, loss[loss=0.1359, simple_loss=0.2177, pruned_loss=0.02699, over 4991.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02852, over 972054.69 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 06:12:28,190 INFO [train.py:715] (5/8) Epoch 18, batch 3300, loss[loss=0.1424, simple_loss=0.2089, pruned_loss=0.03799, over 4985.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 971933.68 frames.], batch size: 31, lr: 1.24e-04
2022-05-09 06:13:07,648 INFO [train.py:715] (5/8) Epoch 18, batch 3350, loss[loss=0.1539, simple_loss=0.2151, pruned_loss=0.04638, over 4839.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 971451.41 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:13:47,789 INFO [train.py:715] (5/8) Epoch 18, batch 3400, loss[loss=0.1457, simple_loss=0.2263, pruned_loss=0.03251, over 4906.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02871, over 971873.88 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:14:26,392 INFO [train.py:715] (5/8) Epoch 18, batch 3450, loss[loss=0.1302, simple_loss=0.2099, pruned_loss=0.0253, over 4926.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02895, over 972081.79 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 06:15:05,248 INFO [train.py:715] (5/8) Epoch 18, batch 3500, loss[loss=0.1266, simple_loss=0.1909, pruned_loss=0.0311, over 4988.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02896, over 973004.01 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:15:45,334 INFO [train.py:715] (5/8) Epoch 18, batch 3550, loss[loss=0.1173, simple_loss=0.1946, pruned_loss=0.02001, over 4920.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.0287, over 972162.69 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 06:16:24,509 INFO [train.py:715] (5/8) Epoch 18, batch 3600, loss[loss=0.1526, simple_loss=0.2436, pruned_loss=0.03085, over 4842.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.0286, over 972446.02 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:17:03,258 INFO [train.py:715] (5/8) Epoch 18, batch 3650, loss[loss=0.1351, simple_loss=0.2158, pruned_loss=0.02722, over 4966.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02884, over 973395.64 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:17:42,727 INFO [train.py:715] (5/8) Epoch 18, batch 3700, loss[loss=0.1743, simple_loss=0.2353, pruned_loss=0.05669, over 4815.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 973635.55 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:18:22,000 INFO [train.py:715] (5/8) Epoch 18, batch 3750, loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.033, over 4955.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02931, over 973118.38 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 06:18:59,953 INFO [train.py:715] (5/8) Epoch 18, batch 3800, loss[loss=0.1411, simple_loss=0.2102, pruned_loss=0.036, over 4855.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02899, over 972633.58 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:19:39,326 INFO [train.py:715] (5/8) Epoch 18, batch 3850, loss[loss=0.1869, simple_loss=0.2471, pruned_loss=0.06337, over 4976.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.029, over 971929.33 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:20:19,353 INFO [train.py:715] (5/8) Epoch 18, batch 3900, loss[loss=0.1236, simple_loss=0.2039, pruned_loss=0.02162, over 4779.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02932, over 971447.81 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:20:57,826 INFO [train.py:715] (5/8) Epoch 18, batch 3950, loss[loss=0.1262, simple_loss=0.2017, pruned_loss=0.0253, over 4882.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02906, over 970794.83 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:21:37,236 INFO [train.py:715] (5/8) Epoch 18, batch 4000, loss[loss=0.1126, simple_loss=0.1924, pruned_loss=0.01644, over 4916.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02907, over 971309.28 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 06:22:16,734 INFO [train.py:715] (5/8) Epoch 18, batch 4050, loss[loss=0.1566, simple_loss=0.2204, pruned_loss=0.04633, over 4849.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02944, over 971399.05 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 06:22:56,010 INFO [train.py:715] (5/8) Epoch 18, batch 4100, loss[loss=0.1265, simple_loss=0.2014, pruned_loss=0.02582, over 4903.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02943, over 971250.47 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:23:34,760 INFO [train.py:715] (5/8) Epoch 18, batch 4150, loss[loss=0.1147, simple_loss=0.189, pruned_loss=0.02016, over 4772.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.0293, over 971213.19 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:24:14,198 INFO [train.py:715] (5/8) Epoch 18, batch 4200, loss[loss=0.1247, simple_loss=0.1983, pruned_loss=0.02559, over 4984.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.0289, over 971818.65 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:24:53,579 INFO [train.py:715] (5/8) Epoch 18, batch 4250, loss[loss=0.1275, simple_loss=0.2076, pruned_loss=0.02371, over 4845.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02882, over 971766.23 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:25:32,490 INFO [train.py:715] (5/8) Epoch 18, batch 4300, loss[loss=0.1262, simple_loss=0.1977, pruned_loss=0.02742, over 4749.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02888, over 971914.67 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:26:12,599 INFO [train.py:715] (5/8) Epoch 18, batch 4350, loss[loss=0.1315, simple_loss=0.2128, pruned_loss=0.02512, over 4967.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02924, over 971506.04 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:26:52,060 INFO [train.py:715] (5/8) Epoch 18, batch 4400, loss[loss=0.1309, simple_loss=0.2064, pruned_loss=0.02775, over 4976.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02886, over 971104.52 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 06:27:31,548 INFO [train.py:715] (5/8) Epoch 18, batch 4450, loss[loss=0.1151, simple_loss=0.1911, pruned_loss=0.01953, over 4796.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02888, over 971740.69 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:28:09,901 INFO [train.py:715] (5/8) Epoch 18, batch 4500, loss[loss=0.1741, simple_loss=0.2494, pruned_loss=0.04947, over 4839.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.0291, over 972301.78 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:28:49,167 INFO [train.py:715] (5/8) Epoch 18, batch 4550, loss[loss=0.1441, simple_loss=0.2185, pruned_loss=0.03482, over 4879.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02906, over 971654.12 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:29:29,014 INFO [train.py:715] (5/8) Epoch 18, batch 4600, loss[loss=0.1136, simple_loss=0.1928, pruned_loss=0.01713, over 4764.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.029, over 971463.53 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:30:07,895 INFO [train.py:715] (5/8) Epoch 18, batch 4650, loss[loss=0.1187, simple_loss=0.1963, pruned_loss=0.02057, over 4810.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02906, over 970977.03 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:30:47,009 INFO [train.py:715] (5/8) Epoch 18, batch 4700, loss[loss=0.1227, simple_loss=0.1989, pruned_loss=0.0232, over 4780.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02932, over 970752.08 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:31:26,063 INFO [train.py:715] (5/8) Epoch 18, batch 4750, loss[loss=0.1402, simple_loss=0.2189, pruned_loss=0.0307, over 4969.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02911, over 971293.46 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:32:06,181 INFO [train.py:715] (5/8) Epoch 18, batch 4800, loss[loss=0.1222, simple_loss=0.1937, pruned_loss=0.02538, over 4847.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02894, over 971857.22 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 06:32:44,915 INFO [train.py:715] (5/8) Epoch 18, batch 4850, loss[loss=0.1887, simple_loss=0.2713, pruned_loss=0.05304, over 4856.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02878, over 971788.90 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:33:24,372 INFO [train.py:715] (5/8) Epoch 18, batch 4900, loss[loss=0.1419, simple_loss=0.2169, pruned_loss=0.03345, over 4873.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.0288, over 971636.42 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:34:04,560 INFO [train.py:715] (5/8) Epoch 18, batch 4950, loss[loss=0.1259, simple_loss=0.1872, pruned_loss=0.03236, over 4835.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02848, over 972004.07 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 06:34:43,673 INFO [train.py:715] (5/8) Epoch 18, batch 5000, loss[loss=0.1264, simple_loss=0.1998, pruned_loss=0.02648, over 4944.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02875, over 971698.63 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 06:35:22,355 INFO [train.py:715] (5/8) Epoch 18, batch 5050, loss[loss=0.1068, simple_loss=0.1745, pruned_loss=0.01955, over 4877.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02898, over 972564.49 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:36:01,523 INFO [train.py:715] (5/8) Epoch 18, batch 5100, loss[loss=0.1163, simple_loss=0.1875, pruned_loss=0.02261, over 4905.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02879, over 974376.12 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:36:41,088 INFO [train.py:715] (5/8) Epoch 18, batch 5150, loss[loss=0.1186, simple_loss=0.1892, pruned_loss=0.02402, over 4976.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.0286, over 973966.08 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:37:19,647 INFO [train.py:715] (5/8) Epoch 18, batch 5200, loss[loss=0.1545, simple_loss=0.2271, pruned_loss=0.04095, over 4951.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02879, over 973514.88 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 06:37:59,017 INFO [train.py:715] (5/8) Epoch 18, batch 5250, loss[loss=0.1186, simple_loss=0.1998, pruned_loss=0.0187, over 4905.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02882, over 974330.12 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:38:38,938 INFO [train.py:715] (5/8) Epoch 18, batch 5300, loss[loss=0.1224, simple_loss=0.2049, pruned_loss=0.01995, over 4965.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02914, over 975049.01 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:39:18,964 INFO [train.py:715] (5/8) Epoch 18, batch 5350, loss[loss=0.118, simple_loss=0.1851, pruned_loss=0.0255, over 4860.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02901, over 974259.23 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:39:57,062 INFO [train.py:715] (5/8) Epoch 18, batch 5400, loss[loss=0.124, simple_loss=0.1993, pruned_loss=0.02435, over 4847.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02922, over 974416.06 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:40:38,717 INFO [train.py:715] (5/8) Epoch 18, batch 5450, loss[loss=0.1169, simple_loss=0.1855, pruned_loss=0.02416, over 4779.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.0294, over 974074.58 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:41:19,095 INFO [train.py:715] (5/8) Epoch 18, batch 5500, loss[loss=0.1166, simple_loss=0.1825, pruned_loss=0.02539, over 4993.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 973772.30 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:41:58,078 INFO [train.py:715] (5/8) Epoch 18, batch 5550, loss[loss=0.1234, simple_loss=0.2024, pruned_loss=0.02218, over 4905.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02956, over 974615.09 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 06:42:36,882 INFO [train.py:715] (5/8) Epoch 18, batch 5600, loss[loss=0.1349, simple_loss=0.2113, pruned_loss=0.02926, over 4843.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02919, over 973759.21 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 06:43:15,921 INFO [train.py:715] (5/8) Epoch 18, batch 5650, loss[loss=0.1396, simple_loss=0.203, pruned_loss=0.03804, over 4834.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02925, over 973194.49 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 06:43:55,545 INFO [train.py:715] (5/8) Epoch 18, batch 5700, loss[loss=0.1201, simple_loss=0.1932, pruned_loss=0.0235, over 4794.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02858, over 973240.02 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:44:33,665 INFO [train.py:715] (5/8) Epoch 18, batch 5750, loss[loss=0.1145, simple_loss=0.1955, pruned_loss=0.01669, over 4967.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02905, over 973498.07 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:45:12,595 INFO [train.py:715] (5/8) Epoch 18, batch 5800, loss[loss=0.1235, simple_loss=0.1959, pruned_loss=0.0256, over 4769.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02896, over 973600.72 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:45:52,339 INFO [train.py:715] (5/8) Epoch 18, batch 5850, loss[loss=0.1347, simple_loss=0.2105, pruned_loss=0.02948, over 4963.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02878, over 973604.94 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 06:46:31,448 INFO [train.py:715] (5/8) Epoch 18, batch 5900, loss[loss=0.1228, simple_loss=0.2038, pruned_loss=0.02088, over 4950.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02872, over 973015.93 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:47:10,143 INFO [train.py:715] (5/8) Epoch 18, batch 5950, loss[loss=0.1179, simple_loss=0.1973, pruned_loss=0.01926, over 4840.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02878, over 973781.01 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:47:49,550 INFO [train.py:715] (5/8) Epoch 18, batch 6000, loss[loss=0.1327, simple_loss=0.2086, pruned_loss=0.02838, over 4920.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02838, over 974184.36 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:47:49,550 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 06:47:59,475 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01075, over 914524.00 frames.
2022-05-09 06:48:39,111 INFO [train.py:715] (5/8) Epoch 18, batch 6050, loss[loss=0.1357, simple_loss=0.2101, pruned_loss=0.03069, over 4819.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02846, over 973566.79 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:49:18,283 INFO [train.py:715] (5/8) Epoch 18, batch 6100, loss[loss=0.1045, simple_loss=0.1836, pruned_loss=0.01267, over 4875.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02843, over 973602.96 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:49:56,627 INFO [train.py:715] (5/8) Epoch 18, batch 6150, loss[loss=0.1176, simple_loss=0.1941, pruned_loss=0.02053, over 4898.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02843, over 974336.60 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:50:35,919 INFO [train.py:715] (5/8) Epoch 18, batch 6200, loss[loss=0.1081, simple_loss=0.1769, pruned_loss=0.01967, over 4965.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02877, over 973905.19 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:51:15,500 INFO [train.py:715] (5/8) Epoch 18, batch 6250, loss[loss=0.1581, simple_loss=0.2206, pruned_loss=0.04777, over 4751.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02896, over 974012.39 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:51:54,531 INFO [train.py:715] (5/8) Epoch 18, batch 6300, loss[loss=0.1299, simple_loss=0.2192, pruned_loss=0.02031, over 4745.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02893, over 973665.32 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:52:33,700 INFO [train.py:715] (5/8) Epoch 18, batch 6350, loss[loss=0.1557, simple_loss=0.238, pruned_loss=0.03668, over 4859.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02924, over 972889.63 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:53:12,894 INFO [train.py:715] (5/8) Epoch 18, batch 6400, loss[loss=0.1235, simple_loss=0.1987, pruned_loss=0.02418, over 4891.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02865, over 972620.58 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:53:52,076 INFO [train.py:715] (5/8) Epoch 18, batch 6450, loss[loss=0.142, simple_loss=0.2188, pruned_loss=0.03261, over 4931.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02898, over 972065.15 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 06:54:30,357 INFO [train.py:715] (5/8) Epoch 18, batch 6500, loss[loss=0.149, simple_loss=0.2255, pruned_loss=0.03628, over 4966.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02901, over 971730.84 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:55:08,638 INFO [train.py:715] (5/8) Epoch 18, batch 6550, loss[loss=0.1375, simple_loss=0.2059, pruned_loss=0.03459, over 4944.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02923, over 972560.00 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 06:55:48,100 INFO [train.py:715] (5/8) Epoch 18, batch 6600, loss[loss=0.1293, simple_loss=0.2, pruned_loss=0.02925, over 4974.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02877, over 973295.74 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:56:27,457 INFO [train.py:715] (5/8) Epoch 18, batch 6650, loss[loss=0.1217, simple_loss=0.2013, pruned_loss=0.02103, over 4859.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02863, over 972957.56 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 06:57:05,503 INFO [train.py:715] (5/8) Epoch 18, batch 6700, loss[loss=0.1421, simple_loss=0.2162, pruned_loss=0.03398, over 4741.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02892, over 972354.17 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:57:44,485 INFO [train.py:715] (5/8) Epoch 18, batch 6750, loss[loss=0.1377, simple_loss=0.2099, pruned_loss=0.03276, over 4882.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.0294, over 971910.71 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:58:23,843 INFO [train.py:715] (5/8) Epoch 18, batch 6800, loss[loss=0.1206, simple_loss=0.2012, pruned_loss=0.01997, over 4896.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02883, over 972073.50 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:59:02,551 INFO [train.py:715] (5/8) Epoch 18, batch 6850, loss[loss=0.1377, simple_loss=0.2103, pruned_loss=0.03256, over 4947.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02874, over 972051.29 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:59:40,720 INFO [train.py:715] (5/8) Epoch 18, batch 6900, loss[loss=0.1382, simple_loss=0.2143, pruned_loss=0.03104, over 4934.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02874, over 972355.90 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 07:00:20,315 INFO [train.py:715] (5/8) Epoch 18, batch 6950, loss[loss=0.1214, simple_loss=0.2035, pruned_loss=0.01965, over 4798.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02801, over 971818.37 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:00:59,040 INFO [train.py:715] (5/8) Epoch 18, batch 7000, loss[loss=0.1509, simple_loss=0.2256, pruned_loss=0.03809, over 4787.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02824, over 972030.26 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:01:37,418 INFO [train.py:715] (5/8) Epoch 18, batch 7050, loss[loss=0.1227, simple_loss=0.1911, pruned_loss=0.02714, over 4844.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.029, over 972020.73 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:02:16,624 INFO [train.py:715] (5/8) Epoch 18, batch 7100, loss[loss=0.1279, simple_loss=0.2025, pruned_loss=0.02663, over 4801.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 972365.90 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:02:56,203 INFO [train.py:715] (5/8) Epoch 18, batch 7150, loss[loss=0.1549, simple_loss=0.2292, pruned_loss=0.04027, over 4763.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02897, over 972407.23 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:03:34,828 INFO [train.py:715] (5/8) Epoch 18, batch 7200, loss[loss=0.1066, simple_loss=0.1746, pruned_loss=0.01932, over 4830.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02901, over 971937.31 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 07:04:13,060 INFO [train.py:715] (5/8) Epoch 18, batch 7250, loss[loss=0.1208, simple_loss=0.2024, pruned_loss=0.01959, over 4821.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02935, over 971969.54 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 07:04:52,160 INFO [train.py:715] (5/8) Epoch 18, batch 7300, loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03842, over 4774.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02949, over 971622.64 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:05:31,285 INFO [train.py:715] (5/8) Epoch 18, batch 7350, loss[loss=0.09771, simple_loss=0.1718, pruned_loss=0.01181, over 4766.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02936, over 972215.04 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:06:09,357 INFO [train.py:715] (5/8) Epoch 18, batch 7400, loss[loss=0.1611, simple_loss=0.2331, pruned_loss=0.04457, over 4798.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.0293, over 971698.16 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:06:48,511 INFO [train.py:715] (5/8) Epoch 18, batch 7450, loss[loss=0.1283, simple_loss=0.2077, pruned_loss=0.02443, over 4958.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02924, over 971068.44 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:07:27,762 INFO [train.py:715] (5/8) Epoch 18, batch 7500, loss[loss=0.1014, simple_loss=0.174, pruned_loss=0.01444, over 4939.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02925, over 971845.22 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:08:05,376 INFO [train.py:715] (5/8) Epoch 18, batch 7550, loss[loss=0.1289, simple_loss=0.2094, pruned_loss=0.02422, over 4817.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 970779.77 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:08:43,906 INFO [train.py:715] (5/8) Epoch 18, batch 7600, loss[loss=0.1301, simple_loss=0.201, pruned_loss=0.02964, over 4857.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02863, over 970585.46 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 07:09:23,638 INFO [train.py:715] (5/8) Epoch 18, batch 7650, loss[loss=0.1272, simple_loss=0.1898, pruned_loss=0.03228, over 4873.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02876, over 971452.00 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 07:10:02,903 INFO [train.py:715] (5/8) Epoch 18, batch 7700, loss[loss=0.1399, simple_loss=0.2106, pruned_loss=0.0346, over 4863.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02843, over 971771.26 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 07:10:41,610 INFO [train.py:715] (5/8) Epoch 18, batch 7750, loss[loss=0.1293, simple_loss=0.2094, pruned_loss=0.02459, over 4988.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02843, over 972181.92 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 07:11:21,215 INFO [train.py:715] (5/8) Epoch 18, batch 7800, loss[loss=0.1286, simple_loss=0.2114, pruned_loss=0.02287, over 4914.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02867, over 972355.07 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:12:01,094 INFO [train.py:715] (5/8) Epoch 18, batch 7850, loss[loss=0.1224, simple_loss=0.1843, pruned_loss=0.03028, over 4980.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02859, over 972187.29 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:12:40,478 INFO [train.py:715] (5/8) Epoch 18, batch 7900, loss[loss=0.1273, simple_loss=0.1963, pruned_loss=0.02919, over 4794.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02918, over 972465.73 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:13:19,677 INFO [train.py:715] (5/8) Epoch 18, batch 7950, loss[loss=0.143, simple_loss=0.2131, pruned_loss=0.03649, over 4830.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02919, over 972547.66 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:13:59,117 INFO [train.py:715] (5/8) Epoch 18, batch 8000, loss[loss=0.1284, simple_loss=0.2149, pruned_loss=0.02096, over 4912.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02884, over 972899.11 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:14:38,128 INFO [train.py:715] (5/8) Epoch 18, batch 8050, loss[loss=0.1144, simple_loss=0.19, pruned_loss=0.01937, over 4958.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02899, over 972749.96 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:15:16,607 INFO [train.py:715] (5/8) Epoch 18, batch 8100, loss[loss=0.1177, simple_loss=0.191, pruned_loss=0.02222, over 4849.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02907, over 972155.46 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 07:15:55,248 INFO [train.py:715] (5/8) Epoch 18, batch 8150, loss[loss=0.1451, simple_loss=0.2211, pruned_loss=0.03451, over 4838.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.0293, over 972004.24 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 07:16:34,308 INFO [train.py:715] (5/8) Epoch 18, batch 8200, loss[loss=0.1243, simple_loss=0.2088, pruned_loss=0.01996, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.0291, over 971982.29 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:17:12,927 INFO [train.py:715] (5/8) Epoch 18, batch 8250, loss[loss=0.1316, simple_loss=0.2003, pruned_loss=0.03143, over 4962.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02924, over 972424.91 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 07:17:51,221 INFO [train.py:715] (5/8) Epoch 18, batch 8300, loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03571, over 4972.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02911, over 972536.16 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:18:31,281 INFO [train.py:715] (5/8) Epoch 18, batch 8350, loss[loss=0.1047, simple_loss=0.1844, pruned_loss=0.01252, over 4844.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02965, over 972253.16 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:19:10,479 INFO [train.py:715] (5/8) Epoch 18, batch 8400, loss[loss=0.1279, simple_loss=0.1984, pruned_loss=0.02876, over 4774.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.029, over 972244.88 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:19:48,919 INFO [train.py:715] (5/8) Epoch 18, batch 8450, loss[loss=0.1207, simple_loss=0.1878, pruned_loss=0.02681, over 4806.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02868, over 972337.98 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:20:28,154 INFO [train.py:715] (5/8) Epoch 18, batch 8500, loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02996, over 4899.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02824, over 971521.07 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:21:07,333 INFO [train.py:715] (5/8) Epoch 18, batch 8550, loss[loss=0.1369, simple_loss=0.2114, pruned_loss=0.0312, over 4931.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02903, over 971729.13 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:21:46,035 INFO [train.py:715] (5/8) Epoch 18, batch 8600, loss[loss=0.1442, simple_loss=0.2214, pruned_loss=0.03349, over 4874.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02917, over 972014.37 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 07:22:24,239 INFO [train.py:715] (5/8) Epoch 18, batch 8650, loss[loss=0.1358, simple_loss=0.2132, pruned_loss=0.02918, over 4839.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02905, over 971771.64 frames.], batch size: 27, lr: 1.24e-04
2022-05-09 07:23:03,807 INFO [train.py:715] (5/8) Epoch 18, batch 8700, loss[loss=0.1351, simple_loss=0.2157, pruned_loss=0.02725, over 4856.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02911, over 972247.37 frames.], batch size: 38, lr: 1.24e-04
2022-05-09 07:23:43,633 INFO [train.py:715] (5/8) Epoch 18, batch 8750, loss[loss=0.1271, simple_loss=0.2011, pruned_loss=0.02652, over 4994.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02918, over 971844.54 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:24:23,136 INFO [train.py:715] (5/8) Epoch 18, batch 8800, loss[loss=0.1515, simple_loss=0.2054, pruned_loss=0.04878, over 4701.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02907, over 972755.64 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:25:01,504 INFO [train.py:715] (5/8) Epoch 18, batch 8850, loss[loss=0.1194, simple_loss=0.1898, pruned_loss=0.02446, over 4773.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02949, over 972842.85 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:25:41,122 INFO [train.py:715] (5/8) Epoch 18, batch 8900, loss[loss=0.1289, simple_loss=0.1999, pruned_loss=0.02891, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02925, over 973322.79 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:26:19,638 INFO [train.py:715] (5/8) Epoch 18, batch 8950, loss[loss=0.1273, simple_loss=0.2017, pruned_loss=0.02639, over 4976.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02876, over 973110.94 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:26:58,102 INFO [train.py:715] (5/8) Epoch 18, batch 9000, loss[loss=0.1404, simple_loss=0.2162, pruned_loss=0.03228, over 4974.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02903, over 973250.94 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:26:58,102 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 07:27:08,039 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1879, pruned_loss=0.01057, over 914524.00 frames.
2022-05-09 07:27:46,931 INFO [train.py:715] (5/8) Epoch 18, batch 9050, loss[loss=0.1072, simple_loss=0.1891, pruned_loss=0.01272, over 4819.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02882, over 973705.74 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:28:26,537 INFO [train.py:715] (5/8) Epoch 18, batch 9100, loss[loss=0.147, simple_loss=0.2275, pruned_loss=0.03328, over 4925.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02903, over 973689.86 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:29:05,673 INFO [train.py:715] (5/8) Epoch 18, batch 9150, loss[loss=0.1118, simple_loss=0.1903, pruned_loss=0.01663, over 4754.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02934, over 973600.53 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:29:43,361 INFO [train.py:715] (5/8) Epoch 18, batch 9200, loss[loss=0.1298, simple_loss=0.1973, pruned_loss=0.03119, over 4787.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2078, pruned_loss=0.029, over 973739.88 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:30:22,560 INFO [train.py:715] (5/8) Epoch 18, batch 9250, loss[loss=0.131, simple_loss=0.2142, pruned_loss=0.02386, over 4820.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2087, pruned_loss=0.02935, over 973842.18 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:31:01,721 INFO [train.py:715] (5/8) Epoch 18, batch 9300, loss[loss=0.1539, simple_loss=0.2263, pruned_loss=0.04073, over 4984.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2091, pruned_loss=0.02959, over 973182.63 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:31:39,924 INFO [train.py:715] (5/8) Epoch 18, batch 9350, loss[loss=0.1305, simple_loss=0.1947, pruned_loss=0.0331, over 4903.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02942, over 972996.71 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:32:18,512 INFO [train.py:715] (5/8) Epoch 18, batch 9400, loss[loss=0.1605, simple_loss=0.2407, pruned_loss=0.04017, over 4942.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.02917, over 972587.50 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:32:58,075 INFO [train.py:715] (5/8) Epoch 18, batch 9450, loss[loss=0.1391, simple_loss=0.2254, pruned_loss=0.02644, over 4849.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02863, over 972329.35 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:33:36,480 INFO [train.py:715] (5/8) Epoch 18, batch 9500, loss[loss=0.1233, simple_loss=0.1993, pruned_loss=0.02369, over 4845.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02876, over 972242.35 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 07:34:14,734 INFO [train.py:715] (5/8) Epoch 18, batch 9550, loss[loss=0.1344, simple_loss=0.202, pruned_loss=0.03337, over 4798.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02848, over 971677.30 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:34:53,870 INFO [train.py:715] (5/8) Epoch 18, batch 9600, loss[loss=0.1287, simple_loss=0.2004, pruned_loss=0.0285, over 4868.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02838, over 972237.35 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 07:35:33,427 INFO [train.py:715] (5/8) Epoch 18, batch 9650, loss[loss=0.1184, simple_loss=0.1973, pruned_loss=0.01972, over 4957.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.02841, over 973420.34 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:36:12,256 INFO [train.py:715] (5/8) Epoch 18, batch 9700, loss[loss=0.1385, simple_loss=0.2064, pruned_loss=0.03534, over 4830.00 frames.], tot_loss[loss=0.132, simple_loss=0.2069, pruned_loss=0.02861, over 972706.25 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:36:50,931 INFO [train.py:715] (5/8) Epoch 18, batch 9750, loss[loss=0.1324, simple_loss=0.2131, pruned_loss=0.02586, over 4757.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.028, over 972479.00 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:37:31,032 INFO [train.py:715] (5/8) Epoch 18, batch 9800, loss[loss=0.1276, simple_loss=0.2006, pruned_loss=0.02734, over 4835.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2051, pruned_loss=0.0276, over 972064.58 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 07:38:09,633 INFO [train.py:715] (5/8) Epoch 18, batch 9850, loss[loss=0.1164, simple_loss=0.1893, pruned_loss=0.02176, over 4965.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.02784, over 971900.20 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 07:38:47,993 INFO [train.py:715] (5/8) Epoch 18, batch 9900, loss[loss=0.1229, simple_loss=0.206, pruned_loss=0.01984, over 4804.00 frames.], tot_loss[loss=0.132, simple_loss=0.2071, pruned_loss=0.02846, over 972517.44 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:39:27,318 INFO [train.py:715] (5/8) Epoch 18, batch 9950, loss[loss=0.1508, simple_loss=0.2224, pruned_loss=0.0396, over 4773.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2072, pruned_loss=0.02852, over 973317.87 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:40:06,405 INFO [train.py:715] (5/8) Epoch 18, batch 10000, loss[loss=0.1355, simple_loss=0.2073, pruned_loss=0.03182, over 4984.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02857, over 972910.27 frames.], batch size: 31, lr: 1.24e-04
2022-05-09 07:40:45,255 INFO [train.py:715] (5/8) Epoch 18, batch 10050, loss[loss=0.1231, simple_loss=0.2061, pruned_loss=0.01998, over 4940.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02868, over 972932.37 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:41:23,497 INFO [train.py:715] (5/8) Epoch 18, batch 10100, loss[loss=0.1172, simple_loss=0.2049, pruned_loss=0.01477, over 4861.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02876, over 972608.30 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:42:02,486 INFO [train.py:715] (5/8) Epoch 18, batch 10150, loss[loss=0.1485, simple_loss=0.2221, pruned_loss=0.03749, over 4924.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.0288, over 972355.10 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 07:42:41,661 INFO [train.py:715] (5/8) Epoch 18, batch 10200, loss[loss=0.136, simple_loss=0.218, pruned_loss=0.02701, over 4839.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02872, over 972123.90 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 07:43:20,196 INFO [train.py:715] (5/8) Epoch 18, batch 10250, loss[loss=0.1298, simple_loss=0.2081, pruned_loss=0.0258, over 4764.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.0287, over 972938.25 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:43:59,315 INFO [train.py:715] (5/8) Epoch 18, batch 10300, loss[loss=0.1319, simple_loss=0.2092, pruned_loss=0.02727, over 4847.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02829, over 973177.83 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 07:44:39,641 INFO [train.py:715] (5/8) Epoch 18, batch 10350, loss[loss=0.1085, simple_loss=0.1845, pruned_loss=0.01624, over 4960.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02841, over 971957.10 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:45:18,122 INFO [train.py:715] (5/8) Epoch 18, batch 10400, loss[loss=0.1117, simple_loss=0.1862, pruned_loss=0.01861, over 4899.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02861, over 972024.89 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:45:56,569 INFO [train.py:715] (5/8) Epoch 18, batch 10450, loss[loss=0.1194, simple_loss=0.2066, pruned_loss=0.01614, over 4939.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02894, over 971071.56 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 07:46:36,303 INFO [train.py:715] (5/8) Epoch 18, batch 10500, loss[loss=0.1058, simple_loss=0.1773, pruned_loss=0.01715, over 4835.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02914, over 971281.86 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:47:15,167 INFO [train.py:715] (5/8) Epoch 18, batch 10550, loss[loss=0.1382, simple_loss=0.206, pruned_loss=0.03523, over 4923.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 972600.31 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:47:53,900 INFO [train.py:715] (5/8) Epoch 18, batch 10600, loss[loss=0.1801, simple_loss=0.2411, pruned_loss=0.05955, over 4829.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.029, over 972420.63 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:48:33,501 INFO [train.py:715] (5/8) Epoch 18, batch 10650, loss[loss=0.1161, simple_loss=0.1847, pruned_loss=0.02372, over 4946.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 973765.96 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:49:13,191 INFO [train.py:715] (5/8) Epoch 18, batch 10700, loss[loss=0.1672, simple_loss=0.2309, pruned_loss=0.05177, over 4714.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02942, over 973336.44 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:49:52,115 INFO [train.py:715] (5/8) Epoch 18, batch 10750, loss[loss=0.1154, simple_loss=0.1893, pruned_loss=0.02079, over 4988.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.0292, over 973838.94 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:50:31,124 INFO [train.py:715] (5/8) Epoch 18, batch 10800, loss[loss=0.1249, simple_loss=0.1966, pruned_loss=0.02656, over 4951.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02845, over 973940.81 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:51:10,556 INFO [train.py:715] (5/8) Epoch 18, batch 10850, loss[loss=0.1178, simple_loss=0.1805, pruned_loss=0.02754, over 4760.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02832, over 973675.26 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:51:49,056 INFO [train.py:715] (5/8) Epoch 18, batch 10900, loss[loss=0.1336, simple_loss=0.2052, pruned_loss=0.031, over 4752.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02823, over 972752.40 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:52:27,639 INFO [train.py:715] (5/8) Epoch 18, batch 10950, loss[loss=0.1139, simple_loss=0.1907, pruned_loss=0.01858, over 4913.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02802, over 972502.36 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:53:07,687 INFO [train.py:715] (5/8) Epoch 18, batch 11000, loss[loss=0.1412, simple_loss=0.21, pruned_loss=0.03614, over 4827.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02792, over 972702.10 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:53:46,745 INFO [train.py:715] (5/8) Epoch 18, batch 11050, loss[loss=0.1363, simple_loss=0.2118, pruned_loss=0.03041, over 4826.00 frames.], tot_loss[loss=0.1309, simple_loss=0.206, pruned_loss=0.02792, over 973836.49 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:54:26,305 INFO [train.py:715] (5/8) Epoch 18, batch 11100, loss[loss=0.1528, simple_loss=0.2334, pruned_loss=0.03606, over 4849.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02785, over 973237.56 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:55:05,196 INFO [train.py:715] (5/8) Epoch 18, batch 11150, loss[loss=0.1574, simple_loss=0.2229, pruned_loss=0.04598, over 4845.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02825, over 973240.92 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:55:44,747 INFO [train.py:715] (5/8) Epoch 18, batch 11200, loss[loss=0.1347, simple_loss=0.2115, pruned_loss=0.02893, over 4770.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02826, over 973031.48 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:56:23,191 INFO [train.py:715] (5/8) Epoch 18, batch 11250, loss[loss=0.114, simple_loss=0.1913, pruned_loss=0.01835, over 4750.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02855, over 972883.39 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:57:01,930 INFO [train.py:715] (5/8) Epoch 18, batch 11300, loss[loss=0.1533, simple_loss=0.2228, pruned_loss=0.04187, over 4886.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02845, over 973583.96 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:57:41,019 INFO [train.py:715] (5/8) Epoch 18, batch 11350, loss[loss=0.1153, simple_loss=0.1931, pruned_loss=0.01869, over 4833.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.0281, over 973067.12 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:58:20,186 INFO [train.py:715] (5/8) Epoch 18, batch 11400, loss[loss=0.1113, simple_loss=0.1883, pruned_loss=0.01714, over 4980.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.02776, over 973624.42 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 07:58:59,553 INFO [train.py:715] (5/8) Epoch 18, batch 11450, loss[loss=0.1312, simple_loss=0.21, pruned_loss=0.02621, over 4876.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02817, over 973941.32 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:59:38,058 INFO [train.py:715] (5/8) Epoch 18, batch 11500, loss[loss=0.1301, simple_loss=0.2159, pruned_loss=0.02219, over 4983.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02858, over 973922.43 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:00:17,723 INFO [train.py:715] (5/8) Epoch 18, batch 11550, loss[loss=0.1428, simple_loss=0.2214, pruned_loss=0.03211, over 4757.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02828, over 973238.79 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:00:57,123 INFO [train.py:715] (5/8) Epoch 18, batch 11600, loss[loss=0.1329, simple_loss=0.2119, pruned_loss=0.02697, over 4892.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02812, over 972569.25 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:01:35,948 INFO [train.py:715] (5/8) Epoch 18, batch 11650, loss[loss=0.1193, simple_loss=0.1894, pruned_loss=0.02457, over 4738.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02832, over 972719.72 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:02:15,655 INFO [train.py:715] (5/8) Epoch 18, batch 11700, loss[loss=0.121, simple_loss=0.2015, pruned_loss=0.02023, over 4921.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02771, over 972667.53 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 08:02:54,932 INFO [train.py:715] (5/8) Epoch 18, batch 11750, loss[loss=0.1249, simple_loss=0.2053, pruned_loss=0.02224, over 4950.00 frames.], tot_loss[loss=0.13, simple_loss=0.2047, pruned_loss=0.02766, over 973281.85 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 08:03:34,976 INFO [train.py:715] (5/8) Epoch 18, batch 11800, loss[loss=0.1219, simple_loss=0.1957, pruned_loss=0.02405, over 4780.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02788, over 973209.69 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 08:04:13,541 INFO [train.py:715] (5/8) Epoch 18, batch 11850, loss[loss=0.1401, simple_loss=0.2104, pruned_loss=0.03485, over 4921.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.0283, over 973148.46 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 08:04:53,376 INFO [train.py:715] (5/8) Epoch 18, batch 11900, loss[loss=0.1575, simple_loss=0.2139, pruned_loss=0.05061, over 4963.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02854, over 972263.40 frames.], batch size: 31, lr: 1.24e-04
2022-05-09 08:05:32,232 INFO [train.py:715] (5/8) Epoch 18, batch 11950, loss[loss=0.1355, simple_loss=0.1999, pruned_loss=0.03557, over 4861.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 972389.88 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 08:06:10,822 INFO [train.py:715] (5/8) Epoch 18, batch 12000, loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02806, over 4815.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02818, over 973227.08 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 08:06:10,823 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 08:06:20,736 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1046, simple_loss=0.188, pruned_loss=0.01063, over 914524.00 frames.
2022-05-09 08:07:00,011 INFO [train.py:715] (5/8) Epoch 18, batch 12050, loss[loss=0.1391, simple_loss=0.2154, pruned_loss=0.03142, over 4930.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 974291.86 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 08:07:39,523 INFO [train.py:715] (5/8) Epoch 18, batch 12100, loss[loss=0.1129, simple_loss=0.1913, pruned_loss=0.01728, over 4937.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02851, over 973203.75 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 08:08:19,049 INFO [train.py:715] (5/8) Epoch 18, batch 12150, loss[loss=0.1282, simple_loss=0.2036, pruned_loss=0.02635, over 4905.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02837, over 973133.94 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 08:08:59,345 INFO [train.py:715] (5/8) Epoch 18, batch 12200, loss[loss=0.1622, simple_loss=0.2341, pruned_loss=0.04512, over 4981.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 973454.40 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 08:09:38,280 INFO [train.py:715] (5/8) Epoch 18, batch 12250, loss[loss=0.1115, simple_loss=0.1907, pruned_loss=0.01618, over 4794.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02903, over 973104.40 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 08:10:18,805 INFO [train.py:715] (5/8) Epoch 18, batch 12300, loss[loss=0.1232, simple_loss=0.1912, pruned_loss=0.02764, over 4779.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02887, over 972887.46 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 08:10:58,225 INFO [train.py:715] (5/8) Epoch 18, batch 12350, loss[loss=0.131, simple_loss=0.2086, pruned_loss=0.02677, over 4947.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02874, over 972626.51 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 08:11:37,141 INFO [train.py:715] (5/8) Epoch 18, batch 12400, loss[loss=0.1582, simple_loss=0.2359, pruned_loss=0.04026, over 4780.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02892, over 972125.14 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 08:12:16,681 INFO [train.py:715] (5/8) Epoch 18, batch 12450, loss[loss=0.1558, simple_loss=0.223, pruned_loss=0.04433, over 4864.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02862, over 972582.28 frames.], batch size: 38, lr: 1.24e-04
2022-05-09 08:12:55,936 INFO [train.py:715] (5/8) Epoch 18, batch 12500, loss[loss=0.1351, simple_loss=0.1914, pruned_loss=0.03936, over 4757.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02903, over 971812.96 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:13:36,318 INFO [train.py:715] (5/8) Epoch 18, batch 12550, loss[loss=0.1598, simple_loss=0.2265, pruned_loss=0.04658, over 4798.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02895, over 971696.19 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 08:14:14,820 INFO [train.py:715] (5/8) Epoch 18, batch 12600, loss[loss=0.1541, simple_loss=0.2185, pruned_loss=0.04478, over 4981.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02917, over 970838.83 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 08:14:54,512 INFO [train.py:715] (5/8) Epoch 18, batch 12650, loss[loss=0.1459, simple_loss=0.2248, pruned_loss=0.03345, over 4763.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02906, over 971539.98 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:15:33,310 INFO [train.py:715] (5/8) Epoch 18, batch 12700, loss[loss=0.1377, simple_loss=0.2143, pruned_loss=0.03055, over 4961.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02865, over 971395.87 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:16:12,930 INFO [train.py:715] (5/8) Epoch 18, batch 12750, loss[loss=0.1142, simple_loss=0.1923, pruned_loss=0.01801, over 4813.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02855, over 970963.13 frames.], batch size: 27, lr: 1.24e-04
2022-05-09 08:16:52,481 INFO [train.py:715] (5/8) Epoch 18, batch 12800, loss[loss=0.1109, simple_loss=0.1912, pruned_loss=0.01533, over 4796.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02847, over 971665.18 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 08:17:31,837 INFO [train.py:715] (5/8) Epoch 18, batch 12850, loss[loss=0.1314, simple_loss=0.1967, pruned_loss=0.03306, over 4812.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02873, over 971128.17 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 08:18:11,706 INFO [train.py:715] (5/8) Epoch 18, batch 12900, loss[loss=0.1673, simple_loss=0.2428, pruned_loss=0.04592, over 4943.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.0292, over 970862.14 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 08:18:50,194 INFO [train.py:715] (5/8) Epoch 18, batch 12950, loss[loss=0.1351, simple_loss=0.2191, pruned_loss=0.02556, over 4758.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02897, over 971853.09 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:19:30,193 INFO [train.py:715] (5/8) Epoch 18, batch 13000, loss[loss=0.131, simple_loss=0.2036, pruned_loss=0.02917, over 4976.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02876, over 972191.85 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 08:20:09,525 INFO [train.py:715] (5/8) Epoch 18, batch 13050, loss[loss=0.1186, simple_loss=0.2025, pruned_loss=0.01734, over 4777.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02863, over 972196.67 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 08:20:48,611 INFO [train.py:715] (5/8) Epoch 18, batch 13100, loss[loss=0.1327, simple_loss=0.2128, pruned_loss=0.02626, over 4936.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02927, over 971884.28 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 08:21:28,135 INFO [train.py:715] (5/8) Epoch 18, batch 13150, loss[loss=0.1556, simple_loss=0.2299, pruned_loss=0.04059, over 4961.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02916, over 971384.05 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:22:07,408 INFO [train.py:715] (5/8) Epoch 18, batch 13200, loss[loss=0.1243, simple_loss=0.2066, pruned_loss=0.02096, over 4887.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02903, over 970999.11 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 08:22:47,220 INFO [train.py:715] (5/8) Epoch 18, batch 13250, loss[loss=0.1248, simple_loss=0.2065, pruned_loss=0.02153, over 4918.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02925, over 971954.47 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 08:23:25,809 INFO [train.py:715] (5/8) Epoch 18, batch 13300, loss[loss=0.1293, simple_loss=0.1977, pruned_loss=0.03043, over 4793.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02937, over 972625.99 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 08:24:05,549 INFO [train.py:715] (5/8) Epoch 18, batch 13350, loss[loss=0.1639, simple_loss=0.2359, pruned_loss=0.04589, over 4880.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02952, over 972525.21 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 08:24:44,552 INFO [train.py:715] (5/8) Epoch 18, batch 13400, loss[loss=0.1428, simple_loss=0.2204, pruned_loss=0.03262, over 4870.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02919, over 972434.17 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 08:25:25,444 INFO [train.py:715] (5/8) Epoch 18, batch 13450, loss[loss=0.1283, simple_loss=0.1907, pruned_loss=0.03296, over 4922.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02926, over 971927.02 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 08:26:05,135 INFO [train.py:715] (5/8) Epoch 18, batch 13500, loss[loss=0.1183, simple_loss=0.1894, pruned_loss=0.02357, over 4978.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 972441.26 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:26:44,081 INFO [train.py:715] (5/8) Epoch 18, batch 13550, loss[loss=0.1295, simple_loss=0.2067, pruned_loss=0.02615, over 4749.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02938, over 971619.80 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:27:23,341 INFO [train.py:715] (5/8) Epoch 18, batch 13600, loss[loss=0.1341, simple_loss=0.1881, pruned_loss=0.03999, over 4907.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.0295, over 972191.71 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:28:02,155 INFO [train.py:715] (5/8) Epoch 18, batch 13650, loss[loss=0.1231, simple_loss=0.1923, pruned_loss=0.02693, over 4860.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02923, over 972025.84 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 08:28:41,561 INFO [train.py:715] (5/8) Epoch 18, batch 13700, loss[loss=0.1246, simple_loss=0.2052, pruned_loss=0.02195, over 4989.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02901, over 972669.70 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:29:20,648 INFO [train.py:715] (5/8) Epoch 18, batch 13750, loss[loss=0.1264, simple_loss=0.2049, pruned_loss=0.02397, over 4755.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02909, over 972162.92 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 08:29:59,712 INFO [train.py:715] (5/8) Epoch 18, batch 13800, loss[loss=0.1299, simple_loss=0.2032, pruned_loss=0.02824, over 4804.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02891, over 971413.42 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:30:39,483 INFO [train.py:715] (5/8) Epoch 18, batch 13850, loss[loss=0.1353, simple_loss=0.2077, pruned_loss=0.03147, over 4877.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.0287, over 970901.98 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:31:18,289 INFO [train.py:715] (5/8) Epoch 18, batch 13900, loss[loss=0.1095, simple_loss=0.1864, pruned_loss=0.01627, over 4907.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02813, over 971573.11 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:31:57,752 INFO [train.py:715] (5/8) Epoch 18, batch 13950, loss[loss=0.1096, simple_loss=0.1758, pruned_loss=0.02173, over 4770.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02812, over 972350.92 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 08:32:37,349 INFO [train.py:715] (5/8) Epoch 18, batch 14000, loss[loss=0.1123, simple_loss=0.1852, pruned_loss=0.01968, over 4762.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02784, over 972641.03 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:33:17,109 INFO [train.py:715] (5/8) Epoch 18, batch 14050, loss[loss=0.137, simple_loss=0.2036, pruned_loss=0.03523, over 4808.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.0281, over 972918.32 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:33:56,294 INFO [train.py:715] (5/8) Epoch 18, batch 14100, loss[loss=0.1156, simple_loss=0.1923, pruned_loss=0.01944, over 4782.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02844, over 973367.02 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:34:35,395 INFO [train.py:715] (5/8) Epoch 18, batch 14150, loss[loss=0.1131, simple_loss=0.1813, pruned_loss=0.02249, over 4972.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02873, over 973768.41 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:35:14,782 INFO [train.py:715] (5/8) Epoch 18, batch 14200, loss[loss=0.1414, simple_loss=0.2114, pruned_loss=0.03572, over 4986.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.0291, over 973208.28 frames.], batch size: 31, lr: 1.23e-04
2022-05-09 08:35:54,061 INFO [train.py:715] (5/8) Epoch 18, batch 14250, loss[loss=0.1302, simple_loss=0.2091, pruned_loss=0.02562, over 4977.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02855, over 972509.41 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:36:33,985 INFO [train.py:715] (5/8) Epoch 18, batch 14300, loss[loss=0.1153, simple_loss=0.1848, pruned_loss=0.02288, over 4838.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02886, over 972572.37 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 08:37:13,313 INFO [train.py:715] (5/8) Epoch 18, batch 14350, loss[loss=0.1351, simple_loss=0.2138, pruned_loss=0.0282, over 4760.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02897, over 972344.67 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:37:52,856 INFO [train.py:715] (5/8) Epoch 18, batch 14400, loss[loss=0.1168, simple_loss=0.195, pruned_loss=0.01933, over 4935.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02866, over 972312.86 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 08:38:32,505 INFO [train.py:715] (5/8) Epoch 18, batch 14450, loss[loss=0.133, simple_loss=0.2109, pruned_loss=0.02759, over 4885.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02891, over 972514.91 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 08:39:11,246 INFO [train.py:715] (5/8) Epoch 18, batch 14500, loss[loss=0.1363, simple_loss=0.2025, pruned_loss=0.03506, over 4911.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02899, over 972758.96 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:39:50,388 INFO [train.py:715] (5/8) Epoch 18, batch 14550, loss[loss=0.1472, simple_loss=0.2279, pruned_loss=0.0333, over 4820.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02885, over 972282.58 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:40:29,523 INFO [train.py:715] (5/8) Epoch 18, batch 14600, loss[loss=0.1656, simple_loss=0.2367, pruned_loss=0.04726, over 4798.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2077, pruned_loss=0.02869, over 972239.91 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:41:09,223 INFO [train.py:715] (5/8) Epoch 18, batch 14650, loss[loss=0.1285, simple_loss=0.2091, pruned_loss=0.02392, over 4839.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.0284, over 973151.18 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:41:48,678 INFO [train.py:715] (5/8) Epoch 18, batch 14700, loss[loss=0.1132, simple_loss=0.1908, pruned_loss=0.01784, over 4948.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02863, over 972687.12 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 08:42:28,034 INFO [train.py:715] (5/8) Epoch 18, batch 14750, loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03623, over 4872.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02865, over 972672.48 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 08:43:07,464 INFO [train.py:715] (5/8) Epoch 18, batch 14800, loss[loss=0.1629, simple_loss=0.2414, pruned_loss=0.0422, over 4709.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02868, over 972776.95 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:43:46,221 INFO [train.py:715] (5/8) Epoch 18, batch 14850, loss[loss=0.1265, simple_loss=0.1921, pruned_loss=0.0305, over 4744.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02894, over 972211.14 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 08:44:25,876 INFO [train.py:715] (5/8) Epoch 18, batch 14900, loss[loss=0.124, simple_loss=0.1991, pruned_loss=0.0245, over 4770.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02882, over 972304.24 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 08:45:05,547 INFO [train.py:715] (5/8) Epoch 18, batch 14950, loss[loss=0.119, simple_loss=0.2012, pruned_loss=0.01842, over 4988.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02861, over 972546.62 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:45:44,811 INFO [train.py:715] (5/8) Epoch 18, batch 15000, loss[loss=0.1168, simple_loss=0.1866, pruned_loss=0.0235, over 4852.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02839, over 972656.79 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 08:45:44,813 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 08:45:54,765 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1048, simple_loss=0.1881, pruned_loss=0.01071, over 914524.00 frames.
2022-05-09 08:46:34,347 INFO [train.py:715] (5/8) Epoch 18, batch 15050, loss[loss=0.1105, simple_loss=0.191, pruned_loss=0.01497, over 4913.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02866, over 972559.58 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:47:13,524 INFO [train.py:715] (5/8) Epoch 18, batch 15100, loss[loss=0.1455, simple_loss=0.2077, pruned_loss=0.0417, over 4963.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02839, over 972455.98 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:47:53,254 INFO [train.py:715] (5/8) Epoch 18, batch 15150, loss[loss=0.133, simple_loss=0.21, pruned_loss=0.02799, over 4761.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02854, over 972956.49 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:48:32,384 INFO [train.py:715] (5/8) Epoch 18, batch 15200, loss[loss=0.1274, simple_loss=0.2045, pruned_loss=0.02518, over 4921.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2049, pruned_loss=0.02839, over 972232.89 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 08:49:11,927 INFO [train.py:715] (5/8) Epoch 18, batch 15250, loss[loss=0.1445, simple_loss=0.2197, pruned_loss=0.03467, over 4988.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02856, over 972704.15 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:49:51,789 INFO [train.py:715] (5/8) Epoch 18, batch 15300, loss[loss=0.1348, simple_loss=0.2055, pruned_loss=0.03208, over 4952.00 frames.], tot_loss[loss=0.1309, simple_loss=0.205, pruned_loss=0.02836, over 972632.61 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:50:31,162 INFO [train.py:715] (5/8) Epoch 18, batch 15350, loss[loss=0.1263, simple_loss=0.2076, pruned_loss=0.02249, over 4814.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02849, over 972906.90 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:51:10,081 INFO [train.py:715] (5/8) Epoch 18, batch 15400, loss[loss=0.1593, simple_loss=0.2201, pruned_loss=0.04929, over 4692.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.0285, over 972456.81 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:51:49,370 INFO [train.py:715] (5/8) Epoch 18, batch 15450, loss[loss=0.1072, simple_loss=0.1866, pruned_loss=0.01387, over 4638.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02881, over 972531.96 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 08:52:28,996 INFO [train.py:715] (5/8) Epoch 18, batch 15500, loss[loss=0.1349, simple_loss=0.2121, pruned_loss=0.02885, over 4762.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02886, over 972454.93 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:53:08,161 INFO [train.py:715] (5/8) Epoch 18, batch 15550, loss[loss=0.1265, simple_loss=0.2041, pruned_loss=0.0244, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02915, over 972300.52 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:53:47,887 INFO [train.py:715] (5/8) Epoch 18, batch 15600, loss[loss=0.1318, simple_loss=0.2087, pruned_loss=0.0274, over 4903.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02899, over 972063.17 frames.], batch size: 38, lr: 1.23e-04
2022-05-09 08:54:28,012 INFO [train.py:715] (5/8) Epoch 18, batch 15650, loss[loss=0.1282, simple_loss=0.1934, pruned_loss=0.03152, over 4857.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02908, over 971860.43 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 08:55:07,611 INFO [train.py:715] (5/8) Epoch 18, batch 15700, loss[loss=0.1531, simple_loss=0.2359, pruned_loss=0.03516, over 4984.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02893, over 972785.48 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 08:55:46,517 INFO [train.py:715] (5/8) Epoch 18, batch 15750, loss[loss=0.1474, simple_loss=0.2275, pruned_loss=0.03364, over 4912.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02904, over 972539.73 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:56:25,956 INFO [train.py:715] (5/8) Epoch 18, batch 15800, loss[loss=0.1099, simple_loss=0.1864, pruned_loss=0.01673, over 4944.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02906, over 972370.07 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:57:05,867 INFO [train.py:715] (5/8) Epoch 18, batch 15850, loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03528, over 4859.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02894, over 973049.47 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 08:57:45,101 INFO [train.py:715] (5/8) Epoch 18, batch 15900, loss[loss=0.1561, simple_loss=0.2468, pruned_loss=0.03269, over 4814.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 973138.78 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:58:24,413 INFO [train.py:715] (5/8) Epoch 18, batch 15950, loss[loss=0.1525, simple_loss=0.2376, pruned_loss=0.03366, over 4830.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02785, over 973588.72 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:59:04,888 INFO [train.py:715] (5/8) Epoch 18, batch 16000, loss[loss=0.1164, simple_loss=0.1906, pruned_loss=0.0211, over 4947.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02806, over 973888.65 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:59:45,379 INFO [train.py:715] (5/8) Epoch 18, batch 16050, loss[loss=0.1234, simple_loss=0.2029, pruned_loss=0.02193, over 4646.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02809, over 972957.02 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:00:24,419 INFO [train.py:715] (5/8) Epoch 18, batch 16100, loss[loss=0.1299, simple_loss=0.2051, pruned_loss=0.02732, over 4765.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02792, over 972311.08 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:01:03,602 INFO [train.py:715] (5/8) Epoch 18, batch 16150, loss[loss=0.1254, simple_loss=0.1934, pruned_loss=0.02866, over 4781.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02814, over 972500.07 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:01:43,694 INFO [train.py:715] (5/8) Epoch 18, batch 16200, loss[loss=0.134, simple_loss=0.2034, pruned_loss=0.03227, over 4829.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02902, over 972182.93 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:02:22,640 INFO [train.py:715] (5/8) Epoch 18, batch 16250, loss[loss=0.1328, simple_loss=0.2044, pruned_loss=0.0306, over 4787.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02847, over 970761.25 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:03:01,671 INFO [train.py:715] (5/8) Epoch 18, batch 16300, loss[loss=0.1619, simple_loss=0.2437, pruned_loss=0.0401, over 4855.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02849, over 971071.33 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:03:41,211 INFO [train.py:715] (5/8) Epoch 18, batch 16350, loss[loss=0.1297, simple_loss=0.2017, pruned_loss=0.02886, over 4832.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.02784, over 972032.52 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:04:20,328 INFO [train.py:715] (5/8) Epoch 18, batch 16400, loss[loss=0.1784, simple_loss=0.2357, pruned_loss=0.06049, over 4646.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02832, over 972299.00 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:04:59,286 INFO [train.py:715] (5/8) Epoch 18, batch 16450, loss[loss=0.1577, simple_loss=0.231, pruned_loss=0.04225, over 4983.00 frames.], tot_loss[loss=0.1309, simple_loss=0.206, pruned_loss=0.02792, over 973012.26 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:05:38,804 INFO [train.py:715] (5/8) Epoch 18, batch 16500, loss[loss=0.1282, simple_loss=0.2016, pruned_loss=0.02735, over 4981.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02799, over 972351.53 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:06:18,645 INFO [train.py:715] (5/8) Epoch 18, batch 16550, loss[loss=0.1208, simple_loss=0.1919, pruned_loss=0.02482, over 4832.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02792, over 971943.63 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:06:57,074 INFO [train.py:715] (5/8) Epoch 18, batch 16600, loss[loss=0.1215, simple_loss=0.1955, pruned_loss=0.02372, over 4931.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02827, over 972437.38 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 09:07:36,513 INFO [train.py:715] (5/8) Epoch 18, batch 16650, loss[loss=0.1207, simple_loss=0.2066, pruned_loss=0.01737, over 4865.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02853, over 972178.07 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 09:08:15,858 INFO [train.py:715] (5/8) Epoch 18, batch 16700, loss[loss=0.1304, simple_loss=0.1982, pruned_loss=0.03125, over 4876.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02843, over 972955.30 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:08:55,196 INFO [train.py:715] (5/8) Epoch 18, batch 16750, loss[loss=0.1093, simple_loss=0.1869, pruned_loss=0.01579, over 4863.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02838, over 972249.86 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 09:09:34,646 INFO [train.py:715] (5/8) Epoch 18, batch 16800, loss[loss=0.1436, simple_loss=0.2176, pruned_loss=0.03476, over 4992.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02848, over 972904.63 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:10:13,849 INFO [train.py:715] (5/8) Epoch 18, batch 16850, loss[loss=0.1128, simple_loss=0.1813, pruned_loss=0.02217, over 4942.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02831, over 973210.32 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 09:10:53,309 INFO [train.py:715] (5/8) Epoch 18, batch 16900, loss[loss=0.1151, simple_loss=0.1877, pruned_loss=0.02123, over 4902.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02857, over 972424.65 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:11:32,153 INFO [train.py:715] (5/8) Epoch 18, batch 16950, loss[loss=0.1264, simple_loss=0.198, pruned_loss=0.02737, over 4901.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02839, over 971408.65 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:12:11,612 INFO [train.py:715] (5/8) Epoch 18, batch 17000, loss[loss=0.1392, simple_loss=0.207, pruned_loss=0.03565, over 4765.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02856, over 971021.59 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:12:51,061 INFO [train.py:715] (5/8) Epoch 18, batch 17050, loss[loss=0.1157, simple_loss=0.1897, pruned_loss=0.02091, over 4886.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02856, over 972100.71 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:13:30,534 INFO [train.py:715] (5/8) Epoch 18, batch 17100, loss[loss=0.132, simple_loss=0.2201, pruned_loss=0.02194, over 4926.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02831, over 972985.61 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:14:10,113 INFO [train.py:715] (5/8) Epoch 18, batch 17150, loss[loss=0.1198, simple_loss=0.1973, pruned_loss=0.02119, over 4902.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02784, over 973336.88 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:14:49,239 INFO [train.py:715] (5/8) Epoch 18, batch 17200, loss[loss=0.1288, simple_loss=0.1916, pruned_loss=0.03304, over 4985.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02856, over 973529.25 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:15:28,959 INFO [train.py:715] (5/8) Epoch 18, batch 17250, loss[loss=0.1441, simple_loss=0.2171, pruned_loss=0.03548, over 4787.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02876, over 972689.55 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:16:08,220 INFO [train.py:715] (5/8) Epoch 18, batch 17300, loss[loss=0.1188, simple_loss=0.1948, pruned_loss=0.02137, over 4762.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02859, over 972016.67 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:16:48,153 INFO [train.py:715] (5/8) Epoch 18, batch 17350, loss[loss=0.1605, simple_loss=0.2202, pruned_loss=0.0504, over 4899.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02865, over 972162.67 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:17:27,215 INFO [train.py:715] (5/8) Epoch 18, batch 17400, loss[loss=0.1183, simple_loss=0.1871, pruned_loss=0.02473, over 4789.00 frames.], tot_loss[loss=0.1309, simple_loss=0.205, pruned_loss=0.02843, over 972370.44 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:18:07,006 INFO [train.py:715] (5/8) Epoch 18, batch 17450, loss[loss=0.1323, simple_loss=0.1975, pruned_loss=0.03356, over 4804.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2054, pruned_loss=0.02877, over 972583.16 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:18:46,082 INFO [train.py:715] (5/8) Epoch 18, batch 17500, loss[loss=0.1288, simple_loss=0.2092, pruned_loss=0.02426, over 4930.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02825, over 972716.92 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:19:24,711 INFO [train.py:715] (5/8) Epoch 18, batch 17550, loss[loss=0.138, simple_loss=0.1998, pruned_loss=0.03805, over 4773.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02836, over 972443.01 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 09:20:04,280 INFO [train.py:715] (5/8) Epoch 18, batch 17600, loss[loss=0.148, simple_loss=0.226, pruned_loss=0.03497, over 4923.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2051, pruned_loss=0.02863, over 972971.71 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 09:20:43,547 INFO [train.py:715] (5/8) Epoch 18, batch 17650, loss[loss=0.1269, simple_loss=0.1996, pruned_loss=0.02711, over 4906.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2046, pruned_loss=0.02839, over 972264.39 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:21:22,850 INFO [train.py:715] (5/8) Epoch 18, batch 17700, loss[loss=0.1493, simple_loss=0.2267, pruned_loss=0.03599, over 4950.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02871, over 972378.43 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:22:01,949 INFO [train.py:715] (5/8) Epoch 18, batch 17750, loss[loss=0.1486, simple_loss=0.2247, pruned_loss=0.03628, over 4866.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02889, over 971587.21 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:22:41,549 INFO [train.py:715] (5/8) Epoch 18, batch 17800, loss[loss=0.1394, simple_loss=0.2172, pruned_loss=0.0308, over 4785.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02855, over 972346.20 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:23:20,833 INFO [train.py:715] (5/8) Epoch 18, batch 17850, loss[loss=0.1381, simple_loss=0.2123, pruned_loss=0.03199, over 4983.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02916, over 972120.00 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:23:59,345 INFO [train.py:715] (5/8) Epoch 18, batch 17900, loss[loss=0.1432, simple_loss=0.2235, pruned_loss=0.0314, over 4758.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02881, over 972547.06 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:24:39,458 INFO [train.py:715] (5/8) Epoch 18, batch 17950, loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03399, over 4957.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02889, over 971768.91 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:25:18,519 INFO [train.py:715] (5/8) Epoch 18, batch 18000, loss[loss=0.1301, simple_loss=0.1995, pruned_loss=0.03041, over 4806.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02895, over 972013.94 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:25:18,520 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 09:25:28,382 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01063, over 914524.00 frames.
2022-05-09 09:26:07,768 INFO [train.py:715] (5/8) Epoch 18, batch 18050, loss[loss=0.09872, simple_loss=0.1682, pruned_loss=0.01462, over 4775.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02902, over 971369.34 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:26:47,164 INFO [train.py:715] (5/8) Epoch 18, batch 18100, loss[loss=0.1364, simple_loss=0.2077, pruned_loss=0.03255, over 4946.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02906, over 971831.90 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:27:26,270 INFO [train.py:715] (5/8) Epoch 18, batch 18150, loss[loss=0.1159, simple_loss=0.1854, pruned_loss=0.02318, over 4898.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2055, pruned_loss=0.0289, over 971452.11 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:28:06,058 INFO [train.py:715] (5/8) Epoch 18, batch 18200, loss[loss=0.1161, simple_loss=0.1903, pruned_loss=0.02094, over 4825.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02891, over 971731.20 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 09:28:45,753 INFO [train.py:715] (5/8) Epoch 18, batch 18250, loss[loss=0.1512, simple_loss=0.2283, pruned_loss=0.03709, over 4825.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02934, over 971557.21 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:29:24,153 INFO [train.py:715] (5/8) Epoch 18, batch 18300, loss[loss=0.1227, simple_loss=0.1971, pruned_loss=0.02411, over 4839.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02942, over 971616.40 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:30:03,825 INFO [train.py:715] (5/8) Epoch 18, batch 18350, loss[loss=0.1396, simple_loss=0.2222, pruned_loss=0.02853, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02874, over 971665.63 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 09:30:43,381 INFO [train.py:715] (5/8) Epoch 18, batch 18400, loss[loss=0.1156, simple_loss=0.1898, pruned_loss=0.02071, over 4832.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02807, over 971739.13 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:31:22,381 INFO [train.py:715] (5/8) Epoch 18, batch 18450, loss[loss=0.1322, simple_loss=0.2136, pruned_loss=0.02537, over 4932.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02838, over 970556.67 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:32:01,511 INFO [train.py:715] (5/8) Epoch 18, batch 18500, loss[loss=0.1308, simple_loss=0.1988, pruned_loss=0.03139, over 4855.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02859, over 971722.91 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:32:40,864 INFO [train.py:715] (5/8) Epoch 18, batch 18550, loss[loss=0.1619, simple_loss=0.2477, pruned_loss=0.03807, over 4928.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.0285, over 971758.06 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 09:33:20,074 INFO [train.py:715] (5/8) Epoch 18, batch 18600, loss[loss=0.1581, simple_loss=0.2236, pruned_loss=0.04628, over 4873.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02847, over 972118.87 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:33:58,713 INFO [train.py:715] (5/8) Epoch 18, batch 18650, loss[loss=0.1434, simple_loss=0.2118, pruned_loss=0.0375, over 4929.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02889, over 972528.43 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:34:38,207 INFO [train.py:715] (5/8) Epoch 18, batch 18700, loss[loss=0.1208, simple_loss=0.1907, pruned_loss=0.02541, over 4851.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02846, over 971976.86 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:35:17,421 INFO [train.py:715] (5/8) Epoch 18, batch 18750, loss[loss=0.103, simple_loss=0.177, pruned_loss=0.01453, over 4879.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02851, over 972227.75 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:35:56,634 INFO [train.py:715] (5/8) Epoch 18, batch 18800, loss[loss=0.153, simple_loss=0.2369, pruned_loss=0.03452, over 4806.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.0288, over 973282.31 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:36:35,997 INFO [train.py:715] (5/8) Epoch 18, batch 18850, loss[loss=0.138, simple_loss=0.2124, pruned_loss=0.03176, over 4827.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02895, over 973745.15 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:37:15,846 INFO [train.py:715] (5/8) Epoch 18, batch 18900, loss[loss=0.1003, simple_loss=0.176, pruned_loss=0.01225, over 4783.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02825, over 974029.12 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 09:37:54,910 INFO [train.py:715] (5/8) Epoch 18, batch 18950, loss[loss=0.1272, simple_loss=0.2049, pruned_loss=0.02477, over 4806.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02867, over 973815.84 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:38:33,358 INFO [train.py:715] (5/8) Epoch 18, batch 19000, loss[loss=0.1037, simple_loss=0.1811, pruned_loss=0.01314, over 4803.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02887, over 973153.30 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:39:12,865 INFO [train.py:715] (5/8) Epoch 18, batch 19050, loss[loss=0.1303, simple_loss=0.204, pruned_loss=0.02831, over 4786.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02907, over 973581.38 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:39:51,873 INFO [train.py:715] (5/8) Epoch 18, batch 19100, loss[loss=0.1535, simple_loss=0.2196, pruned_loss=0.04371, over 4943.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02897, over 974013.85 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 09:40:31,188 INFO [train.py:715] (5/8) Epoch 18, batch 19150, loss[loss=0.1185, simple_loss=0.204, pruned_loss=0.01652, over 4873.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02861, over 973634.45 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 09:41:11,055 INFO [train.py:715] (5/8) Epoch 18, batch 19200, loss[loss=0.1492, simple_loss=0.2337, pruned_loss=0.0323, over 4899.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02814, over 974069.30 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:41:50,578 INFO [train.py:715] (5/8) Epoch 18, batch 19250, loss[loss=0.1382, simple_loss=0.217, pruned_loss=0.02971, over 4891.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02814, over 973866.05 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 09:42:29,652 INFO [train.py:715] (5/8) Epoch 18, batch 19300, loss[loss=0.1277, simple_loss=0.2179, pruned_loss=0.01877, over 4967.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02817, over 973390.31 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:43:08,116 INFO [train.py:715] (5/8) Epoch 18, batch 19350, loss[loss=0.1045, simple_loss=0.1762, pruned_loss=0.01645, over 4813.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02835, over 972022.18 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:43:47,525 INFO [train.py:715] (5/8) Epoch 18, batch 19400, loss[loss=0.1179, simple_loss=0.2015, pruned_loss=0.01721, over 4803.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02858, over 972172.66 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:44:26,733 INFO [train.py:715] (5/8) Epoch 18, batch 19450, loss[loss=0.1205, simple_loss=0.1913, pruned_loss=0.02482, over 4899.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02917, over 972786.40 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:45:05,481 INFO [train.py:715] (5/8) Epoch 18, batch 19500, loss[loss=0.1206, simple_loss=0.2029, pruned_loss=0.01915, over 4784.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 971694.47 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:45:44,652 INFO [train.py:715] (5/8) Epoch 18, batch 19550, loss[loss=0.1339, simple_loss=0.2095, pruned_loss=0.02917, over 4744.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02857, over 972041.68 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:46:24,058 INFO [train.py:715] (5/8) Epoch 18, batch 19600, loss[loss=0.1222, simple_loss=0.2018, pruned_loss=0.02131, over 4792.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02852, over 971444.77 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:47:02,885 INFO [train.py:715] (5/8) Epoch 18, batch 19650, loss[loss=0.1863, simple_loss=0.2647, pruned_loss=0.05398, over 4994.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 971947.44 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:47:41,710 INFO [train.py:715] (5/8) Epoch 18, batch 19700, loss[loss=0.1537, simple_loss=0.2349, pruned_loss=0.03627, over 4883.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02893, over 972344.08 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:48:21,728 INFO [train.py:715] (5/8) Epoch 18, batch 19750, loss[loss=0.1217, simple_loss=0.1884, pruned_loss=0.02748, over 4839.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02909, over 972752.32 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:49:01,595 INFO [train.py:715] (5/8) Epoch 18, batch 19800, loss[loss=0.1419, simple_loss=0.2124, pruned_loss=0.03569, over 4842.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02929, over 973417.44 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:49:40,676 INFO [train.py:715] (5/8) Epoch 18, batch 19850, loss[loss=0.1294, simple_loss=0.1944, pruned_loss=0.03218, over 4910.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02874, over 973041.16 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:50:20,122 INFO [train.py:715] (5/8) Epoch 18, batch 19900, loss[loss=0.1487, simple_loss=0.2258, pruned_loss=0.0358, over 4831.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02867, over 972699.44 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:50:59,799 INFO [train.py:715] (5/8) Epoch 18, batch 19950, loss[loss=0.1241, simple_loss=0.2009, pruned_loss=0.0237, over 4907.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02835, over 971348.81 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:51:39,045 INFO [train.py:715] (5/8) Epoch 18, batch 20000, loss[loss=0.1107, simple_loss=0.185, pruned_loss=0.01821, over 4914.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.0282, over 970601.58 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:52:18,799 INFO [train.py:715] (5/8) Epoch 18, batch 20050, loss[loss=0.1202, simple_loss=0.1966, pruned_loss=0.02197, over 4803.00 frames.], tot_loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.0279, over 971354.10 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:52:59,018 INFO [train.py:715] (5/8) Epoch 18, batch 20100, loss[loss=0.1285, simple_loss=0.2045, pruned_loss=0.02628, over 4973.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02818, over 973024.44 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:53:39,143 INFO [train.py:715] (5/8) Epoch 18, batch 20150, loss[loss=0.1365, simple_loss=0.2014, pruned_loss=0.03584, over 4868.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02838, over 972431.37 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:54:18,208 INFO [train.py:715] (5/8) Epoch 18, batch 20200, loss[loss=0.1164, simple_loss=0.1954, pruned_loss=0.01868, over 4803.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2065, pruned_loss=0.02827, over 973051.97 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:54:57,194 INFO [train.py:715] (5/8) Epoch 18, batch 20250, loss[loss=0.1308, simple_loss=0.2011, pruned_loss=0.03025, over 4989.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02788, over 973001.99 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:55:36,874 INFO [train.py:715] (5/8) Epoch 18, batch 20300, loss[loss=0.1617, simple_loss=0.2322, pruned_loss=0.04558, over 4905.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2054, pruned_loss=0.02784, over 972115.68 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:56:16,002 INFO [train.py:715] (5/8) Epoch 18, batch 20350, loss[loss=0.1287, simple_loss=0.204, pruned_loss=0.02671, over 4945.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2058, pruned_loss=0.02795, over 972583.08 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:56:55,260 INFO [train.py:715] (5/8) Epoch 18, batch 20400, loss[loss=0.1324, simple_loss=0.2013, pruned_loss=0.03173, over 4925.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02835, over 972693.76 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:57:34,097 INFO [train.py:715] (5/8) Epoch 18, batch 20450, loss[loss=0.1313, simple_loss=0.2014, pruned_loss=0.03059, over 4851.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02877, over 972646.24 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:58:14,209 INFO [train.py:715] (5/8) Epoch 18, batch 20500, loss[loss=0.151, simple_loss=0.236, pruned_loss=0.03297, over 4815.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02853, over 972452.25 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:58:52,923 INFO [train.py:715] (5/8) Epoch 18, batch 20550, loss[loss=0.132, simple_loss=0.2087, pruned_loss=0.02768, over 4823.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02883, over 972166.46 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:59:31,852 INFO [train.py:715] (5/8) Epoch 18, batch 20600, loss[loss=0.1301, simple_loss=0.2051, pruned_loss=0.0275, over 4993.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.0288, over 973203.03 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:00:10,870 INFO [train.py:715] (5/8) Epoch 18, batch 20650, loss[loss=0.1297, simple_loss=0.2054, pruned_loss=0.02701, over 4926.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02865, over 973165.54 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:00:50,418 INFO [train.py:715] (5/8) Epoch 18, batch 20700, loss[loss=0.1226, simple_loss=0.2032, pruned_loss=0.02101, over 4869.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02857, over 973797.87 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:01:28,860 INFO [train.py:715] (5/8) Epoch 18, batch 20750, loss[loss=0.1384, simple_loss=0.223, pruned_loss=0.02696, over 4775.00 frames.], tot_loss[loss=0.1319, simple_loss=0.207, pruned_loss=0.0284, over 973166.94 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:02:08,331 INFO [train.py:715] (5/8) Epoch 18, batch 20800, loss[loss=0.1318, simple_loss=0.2032, pruned_loss=0.03014, over 4865.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02857, over 973279.57 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:02:47,764 INFO [train.py:715] (5/8) Epoch 18, batch 20850, loss[loss=0.1324, simple_loss=0.2107, pruned_loss=0.02705, over 4779.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02839, over 973523.43 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:03:26,622 INFO [train.py:715] (5/8) Epoch 18, batch 20900, loss[loss=0.1162, simple_loss=0.1943, pruned_loss=0.01908, over 4920.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972588.13 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:04:05,320 INFO [train.py:715] (5/8) Epoch 18, batch 20950, loss[loss=0.1592, simple_loss=0.224, pruned_loss=0.04718, over 4811.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02871, over 972826.46 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 10:04:44,839 INFO [train.py:715] (5/8) Epoch 18, batch 21000, loss[loss=0.151, simple_loss=0.2241, pruned_loss=0.03893, over 4702.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.0284, over 973138.59 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:04:44,840 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 10:04:54,815 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1879, pruned_loss=0.01059, over 914524.00 frames.
2022-05-09 10:05:34,565 INFO [train.py:715] (5/8) Epoch 18, batch 21050, loss[loss=0.1491, simple_loss=0.2367, pruned_loss=0.03071, over 4798.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02884, over 972837.63 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 10:06:14,354 INFO [train.py:715] (5/8) Epoch 18, batch 21100, loss[loss=0.1367, simple_loss=0.2135, pruned_loss=0.02999, over 4912.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 973343.62 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:06:53,522 INFO [train.py:715] (5/8) Epoch 18, batch 21150, loss[loss=0.1425, simple_loss=0.2191, pruned_loss=0.03295, over 4835.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02854, over 972532.73 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:07:33,002 INFO [train.py:715] (5/8) Epoch 18, batch 21200, loss[loss=0.1251, simple_loss=0.1949, pruned_loss=0.02767, over 4859.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02818, over 972996.51 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:08:12,708 INFO [train.py:715] (5/8) Epoch 18, batch 21250, loss[loss=0.1197, simple_loss=0.1995, pruned_loss=0.02, over 4764.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02825, over 972479.77 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:08:51,642 INFO [train.py:715] (5/8) Epoch 18, batch 21300, loss[loss=0.1367, simple_loss=0.2226, pruned_loss=0.0254, over 4737.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02852, over 972126.45 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 10:09:30,192 INFO [train.py:715] (5/8) Epoch 18, batch 21350, loss[loss=0.1248, simple_loss=0.1918, pruned_loss=0.02889, over 4746.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02872, over 972113.17 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 10:10:09,582 INFO [train.py:715] (5/8) Epoch 18, batch 21400, loss[loss=0.1313, simple_loss=0.2099, pruned_loss=0.0264, over 4982.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02932, over 973056.02 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:10:51,762 INFO [train.py:715] (5/8) Epoch 18, batch 21450, loss[loss=0.134, simple_loss=0.2191, pruned_loss=0.02446, over 4838.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02952, over 973232.69 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 10:11:30,942 INFO [train.py:715] (5/8) Epoch 18, batch 21500, loss[loss=0.1427, simple_loss=0.22, pruned_loss=0.03274, over 4928.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02964, over 972837.19 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:12:09,693 INFO [train.py:715] (5/8) Epoch 18, batch 21550, loss[loss=0.109, simple_loss=0.1816, pruned_loss=0.01817, over 4790.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2063, pruned_loss=0.02949, over 972835.16 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:12:49,088 INFO [train.py:715] (5/8) Epoch 18, batch 21600, loss[loss=0.1196, simple_loss=0.2004, pruned_loss=0.01935, over 4972.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.0295, over 973697.77 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:13:28,300 INFO [train.py:715] (5/8) Epoch 18, batch 21650, loss[loss=0.1387, simple_loss=0.2156, pruned_loss=0.03085, over 4878.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 972866.77 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:14:06,693 INFO [train.py:715] (5/8) Epoch 18, batch 21700, loss[loss=0.1258, simple_loss=0.1984, pruned_loss=0.02663, over 4789.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.0291, over 972555.28 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:14:45,677 INFO [train.py:715] (5/8) Epoch 18, batch 21750, loss[loss=0.09913, simple_loss=0.1673, pruned_loss=0.01547, over 4831.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.0289, over 972314.06 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:15:24,822 INFO [train.py:715] (5/8) Epoch 18, batch 21800, loss[loss=0.127, simple_loss=0.2023, pruned_loss=0.0259, over 4841.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02904, over 971855.02 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:16:04,131 INFO [train.py:715] (5/8) Epoch 18, batch 21850, loss[loss=0.1225, simple_loss=0.1869, pruned_loss=0.02904, over 4975.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02922, over 971716.68 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:16:43,559 INFO [train.py:715] (5/8) Epoch 18, batch 21900, loss[loss=0.1194, simple_loss=0.193, pruned_loss=0.02287, over 4871.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 972117.99 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:17:23,080 INFO [train.py:715] (5/8) Epoch 18, batch 21950, loss[loss=0.1176, simple_loss=0.1908, pruned_loss=0.02218, over 4927.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.0293, over 971563.22 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:18:02,135 INFO [train.py:715] (5/8) Epoch 18, batch 22000, loss[loss=0.1607, simple_loss=0.2343, pruned_loss=0.0435, over 4971.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02959, over 972740.09 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:18:41,236 INFO [train.py:715] (5/8) Epoch 18, batch 22050, loss[loss=0.1276, simple_loss=0.2025, pruned_loss=0.02638, over 4888.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.0292, over 973169.30 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 10:19:20,731 INFO [train.py:715] (5/8) Epoch 18, batch 22100, loss[loss=0.1185, simple_loss=0.2045, pruned_loss=0.01623, over 4874.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 973500.67 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:19:59,603 INFO [train.py:715] (5/8) Epoch 18, batch 22150, loss[loss=0.1239, simple_loss=0.1957, pruned_loss=0.02609, over 4883.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02907, over 972311.61 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 10:20:39,094 INFO [train.py:715] (5/8) Epoch 18, batch 22200, loss[loss=0.1271, simple_loss=0.2058, pruned_loss=0.02423, over 4703.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02821, over 971671.59 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:21:17,770 INFO [train.py:715] (5/8) Epoch 18, batch 22250, loss[loss=0.1431, simple_loss=0.2196, pruned_loss=0.03332, over 4816.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02825, over 971986.14 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 10:21:57,019 INFO [train.py:715] (5/8) Epoch 18, batch 22300, loss[loss=0.1267, simple_loss=0.2004, pruned_loss=0.02651, over 4747.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02828, over 971852.31 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:22:35,716 INFO [train.py:715] (5/8) Epoch 18, batch 22350, loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02935, over 4978.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02832, over 971571.49 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:23:14,495 INFO [train.py:715] (5/8) Epoch 18, batch 22400, loss[loss=0.1196, simple_loss=0.2036, pruned_loss=0.01778, over 4934.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02858, over 971495.17 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:23:53,396 INFO [train.py:715] (5/8) Epoch 18, batch 22450, loss[loss=0.1178, simple_loss=0.1962, pruned_loss=0.01972, over 4949.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02846, over 971855.81 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:24:32,483 INFO [train.py:715] (5/8) Epoch 18, batch 22500, loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02832, over 4868.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02877, over 972357.60 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 10:25:11,262 INFO [train.py:715] (5/8) Epoch 18, batch 22550, loss[loss=0.1183, simple_loss=0.2008, pruned_loss=0.01788, over 4912.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02906, over 972251.89 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:25:50,057 INFO [train.py:715] (5/8) Epoch 18, batch 22600, loss[loss=0.1394, simple_loss=0.2245, pruned_loss=0.02709, over 4872.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02877, over 972350.88 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 10:26:29,078 INFO [train.py:715] (5/8) Epoch 18, batch 22650, loss[loss=0.1212, simple_loss=0.2021, pruned_loss=0.02017, over 4981.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02891, over 972490.23 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:27:07,863 INFO [train.py:715] (5/8) Epoch 18, batch 22700, loss[loss=0.1334, simple_loss=0.2119, pruned_loss=0.02748, over 4829.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.0287, over 972708.79 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 10:27:46,836 INFO [train.py:715] (5/8) Epoch 18, batch 22750, loss[loss=0.1389, simple_loss=0.2158, pruned_loss=0.03105, over 4861.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02862, over 972506.76 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:28:26,214 INFO [train.py:715] (5/8) Epoch 18, batch 22800, loss[loss=0.1408, simple_loss=0.2256, pruned_loss=0.02804, over 4941.00 frames.], tot_loss[loss=0.132, simple_loss=0.2071, pruned_loss=0.02851, over 972876.94 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:29:04,922 INFO [train.py:715] (5/8) Epoch 18, batch 22850, loss[loss=0.1456, simple_loss=0.2271, pruned_loss=0.0321, over 4638.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02861, over 972462.25 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:29:43,879 INFO [train.py:715] (5/8) Epoch 18, batch 22900, loss[loss=0.1294, simple_loss=0.2096, pruned_loss=0.02456, over 4899.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02879, over 971875.58 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:30:22,780 INFO [train.py:715] (5/8) Epoch 18, batch 22950, loss[loss=0.1459, simple_loss=0.2152, pruned_loss=0.03836, over 4966.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02908, over 971981.78 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 10:31:02,202 INFO [train.py:715] (5/8) Epoch 18, batch 23000, loss[loss=0.1369, simple_loss=0.2158, pruned_loss=0.029, over 4951.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02905, over 971939.62 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:31:40,967 INFO [train.py:715] (5/8) Epoch 18, batch 23050, loss[loss=0.1261, simple_loss=0.2045, pruned_loss=0.02386, over 4955.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02947, over 972671.10 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:32:20,092 INFO [train.py:715] (5/8) Epoch 18, batch 23100, loss[loss=0.1222, simple_loss=0.1991, pruned_loss=0.02268, over 4933.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02874, over 972356.19 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:32:59,654 INFO [train.py:715] (5/8) Epoch 18, batch 23150, loss[loss=0.1326, simple_loss=0.2029, pruned_loss=0.03117, over 4795.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02853, over 972213.74 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:33:38,765 INFO [train.py:715] (5/8) Epoch 18, batch 23200, loss[loss=0.1027, simple_loss=0.1731, pruned_loss=0.01614, over 4973.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02834, over 972632.83 frames.], batch size: 28, lr: 1.23e-04
2022-05-09 10:34:17,630 INFO [train.py:715] (5/8) Epoch 18, batch 23250, loss[loss=0.1278, simple_loss=0.204, pruned_loss=0.02576, over 4897.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02841, over 973818.20 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 10:34:56,935 INFO [train.py:715] (5/8) Epoch 18, batch 23300, loss[loss=0.1361, simple_loss=0.2124, pruned_loss=0.02995, over 4896.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 973457.79 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:35:36,582 INFO [train.py:715] (5/8) Epoch 18, batch 23350, loss[loss=0.1495, simple_loss=0.2341, pruned_loss=0.03251, over 4822.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02862, over 973515.52 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:36:15,528 INFO [train.py:715] (5/8) Epoch 18, batch 23400, loss[loss=0.1218, simple_loss=0.1919, pruned_loss=0.02581, over 4915.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02849, over 973294.97 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:36:54,046 INFO [train.py:715] (5/8) Epoch 18, batch 23450, loss[loss=0.126, simple_loss=0.1942, pruned_loss=0.02888, over 4881.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02813, over 972778.66 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:37:33,552 INFO [train.py:715] (5/8) Epoch 18, batch 23500, loss[loss=0.1295, simple_loss=0.2022, pruned_loss=0.02837, over 4904.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02808, over 972114.00 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:38:12,433 INFO [train.py:715] (5/8) Epoch 18, batch 23550, loss[loss=0.1259, simple_loss=0.1962, pruned_loss=0.02782, over 4967.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02802, over 972537.73 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:38:51,084 INFO [train.py:715] (5/8) Epoch 18, batch 23600, loss[loss=0.1386, simple_loss=0.2254, pruned_loss=0.02586, over 4808.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02803, over 972494.07 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:39:30,021 INFO [train.py:715] (5/8) Epoch 18, batch 23650, loss[loss=0.1611, simple_loss=0.2114, pruned_loss=0.05545, over 4975.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02869, over 973187.60 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:40:08,660 INFO [train.py:715] (5/8) Epoch 18, batch 23700, loss[loss=0.1377, simple_loss=0.222, pruned_loss=0.02667, over 4931.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972979.97 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:40:47,464 INFO [train.py:715] (5/8) Epoch 18, batch 23750, loss[loss=0.1251, simple_loss=0.2038, pruned_loss=0.02317, over 4931.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02889, over 973464.12 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:41:26,882 INFO [train.py:715] (5/8) Epoch 18, batch 23800, loss[loss=0.1209, simple_loss=0.1994, pruned_loss=0.02122, over 4765.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02906, over 972667.08 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:42:06,530 INFO [train.py:715] (5/8) Epoch 18, batch 23850, loss[loss=0.1017, simple_loss=0.1725, pruned_loss=0.01548, over 4770.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02943, over 972522.65 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 10:42:45,349 INFO [train.py:715] (5/8) Epoch 18, batch 23900, loss[loss=0.1655, simple_loss=0.2295, pruned_loss=0.05075, over 4975.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02959, over 972389.53 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:43:24,101 INFO [train.py:715] (5/8) Epoch 18, batch 23950, loss[loss=0.1349, simple_loss=0.2131, pruned_loss=0.0283, over 4767.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02951, over 971227.42 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 10:44:03,426 INFO [train.py:715] (5/8) Epoch 18, batch 24000, loss[loss=0.1168, simple_loss=0.1868, pruned_loss=0.02345, over 4810.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 971408.44 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 10:44:03,427 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 10:44:13,350 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01057, over 914524.00 frames.
2022-05-09 10:44:52,991 INFO [train.py:715] (5/8) Epoch 18, batch 24050, loss[loss=0.1059, simple_loss=0.1797, pruned_loss=0.01608, over 4824.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02867, over 971241.68 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:45:31,813 INFO [train.py:715] (5/8) Epoch 18, batch 24100, loss[loss=0.1192, simple_loss=0.1938, pruned_loss=0.02231, over 4936.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02841, over 971719.16 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 10:46:10,744 INFO [train.py:715] (5/8) Epoch 18, batch 24150, loss[loss=0.1104, simple_loss=0.1836, pruned_loss=0.01857, over 4747.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02853, over 971386.84 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:46:50,170 INFO [train.py:715] (5/8) Epoch 18, batch 24200, loss[loss=0.123, simple_loss=0.1894, pruned_loss=0.02833, over 4922.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02893, over 972056.20 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 10:47:29,226 INFO [train.py:715] (5/8) Epoch 18, batch 24250, loss[loss=0.1186, simple_loss=0.1985, pruned_loss=0.01933, over 4961.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02897, over 972505.25 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 10:48:08,107 INFO [train.py:715] (5/8) Epoch 18, batch 24300, loss[loss=0.1463, simple_loss=0.2241, pruned_loss=0.0342, over 4819.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 972955.91 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 10:48:46,578 INFO [train.py:715] (5/8) Epoch 18, batch 24350, loss[loss=0.1559, simple_loss=0.206, pruned_loss=0.05286, over 4834.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02892, over 972385.65 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 10:49:25,639 INFO [train.py:715] (5/8) Epoch 18, batch 24400, loss[loss=0.1349, simple_loss=0.2119, pruned_loss=0.02891, over 4829.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02873, over 972326.14 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:50:04,248 INFO [train.py:715] (5/8) Epoch 18, batch 24450, loss[loss=0.1228, simple_loss=0.2028, pruned_loss=0.02144, over 4897.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02885, over 971962.83 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 10:50:42,848 INFO [train.py:715] (5/8) Epoch 18, batch 24500, loss[loss=0.1468, simple_loss=0.2226, pruned_loss=0.03554, over 4804.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02903, over 972039.04 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 10:51:22,304 INFO [train.py:715] (5/8) Epoch 18, batch 24550, loss[loss=0.1256, simple_loss=0.2048, pruned_loss=0.02315, over 4948.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 972417.85 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 10:52:01,509 INFO [train.py:715] (5/8) Epoch 18, batch 24600, loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03209, over 4967.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 973061.37 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 10:52:40,237 INFO [train.py:715] (5/8) Epoch 18, batch 24650, loss[loss=0.1098, simple_loss=0.1936, pruned_loss=0.01301, over 4942.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02968, over 972800.73 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 10:53:18,842 INFO [train.py:715] (5/8) Epoch 18, batch 24700, loss[loss=0.1272, simple_loss=0.1946, pruned_loss=0.02988, over 4793.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02938, over 972379.19 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 10:53:58,060 INFO [train.py:715] (5/8) Epoch 18, batch 24750, loss[loss=0.1202, simple_loss=0.1877, pruned_loss=0.02638, over 4935.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2058, pruned_loss=0.02929, over 973810.98 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 10:54:37,026 INFO [train.py:715] (5/8) Epoch 18, batch 24800, loss[loss=0.1182, simple_loss=0.1945, pruned_loss=0.021, over 4861.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.0291, over 974407.59 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 10:55:16,441 INFO [train.py:715] (5/8) Epoch 18, batch 24850, loss[loss=0.1221, simple_loss=0.1974, pruned_loss=0.02337, over 4927.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02944, over 973998.38 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 10:55:55,501 INFO [train.py:715] (5/8) Epoch 18, batch 24900, loss[loss=0.1431, simple_loss=0.2222, pruned_loss=0.03193, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2062, pruned_loss=0.02921, over 973339.42 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 10:56:35,062 INFO [train.py:715] (5/8) Epoch 18, batch 24950, loss[loss=0.11, simple_loss=0.1892, pruned_loss=0.01542, over 4824.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02885, over 973208.91 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:57:14,186 INFO [train.py:715] (5/8) Epoch 18, batch 25000, loss[loss=0.1179, simple_loss=0.1913, pruned_loss=0.02227, over 4814.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02869, over 973223.36 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 10:57:52,841 INFO [train.py:715] (5/8) Epoch 18, batch 25050, loss[loss=0.1342, simple_loss=0.2108, pruned_loss=0.02877, over 4952.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02859, over 973479.83 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 10:58:32,132 INFO [train.py:715] (5/8) Epoch 18, batch 25100, loss[loss=0.1406, simple_loss=0.2028, pruned_loss=0.03925, over 4879.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.0291, over 973853.98 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:59:11,690 INFO [train.py:715] (5/8) Epoch 18, batch 25150, loss[loss=0.1416, simple_loss=0.2193, pruned_loss=0.03199, over 4836.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02918, over 973892.98 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 10:59:50,259 INFO [train.py:715] (5/8) Epoch 18, batch 25200, loss[loss=0.1349, simple_loss=0.2131, pruned_loss=0.02833, over 4756.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02897, over 972522.85 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 11:00:29,817 INFO [train.py:715] (5/8) Epoch 18, batch 25250, loss[loss=0.1493, simple_loss=0.2314, pruned_loss=0.03363, over 4817.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02882, over 972297.65 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:01:09,546 INFO [train.py:715] (5/8) Epoch 18, batch 25300, loss[loss=0.1398, simple_loss=0.2114, pruned_loss=0.03409, over 4777.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02851, over 971791.17 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:01:48,677 INFO [train.py:715] (5/8) Epoch 18, batch 25350, loss[loss=0.1156, simple_loss=0.1932, pruned_loss=0.019, over 4917.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 972245.51 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:02:27,380 INFO [train.py:715] (5/8) Epoch 18, batch 25400, loss[loss=0.1131, simple_loss=0.1926, pruned_loss=0.01686, over 4911.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.0292, over 971647.15 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:03:06,961 INFO [train.py:715] (5/8) Epoch 18, batch 25450, loss[loss=0.1187, simple_loss=0.1957, pruned_loss=0.02084, over 4984.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02884, over 971487.98 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 11:03:45,935 INFO [train.py:715] (5/8) Epoch 18, batch 25500, loss[loss=0.1371, simple_loss=0.2194, pruned_loss=0.02738, over 4779.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02907, over 971441.15 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:04:24,922 INFO [train.py:715] (5/8) Epoch 18, batch 25550, loss[loss=0.1145, simple_loss=0.1843, pruned_loss=0.02238, over 4830.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02905, over 971789.14 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:05:04,553 INFO [train.py:715] (5/8) Epoch 18, batch 25600, loss[loss=0.1201, simple_loss=0.1885, pruned_loss=0.0259, over 4926.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971661.90 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:05:44,104 INFO [train.py:715] (5/8) Epoch 18, batch 25650, loss[loss=0.1835, simple_loss=0.2552, pruned_loss=0.05586, over 4897.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02877, over 971698.86 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:06:23,311 INFO [train.py:715] (5/8) Epoch 18, batch 25700, loss[loss=0.1307, simple_loss=0.207, pruned_loss=0.02723, over 4935.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02847, over 971047.96 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:07:02,567 INFO [train.py:715] (5/8) Epoch 18, batch 25750, loss[loss=0.132, simple_loss=0.2002, pruned_loss=0.03192, over 4853.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 970059.37 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:07:41,970 INFO [train.py:715] (5/8) Epoch 18, batch 25800, loss[loss=0.1849, simple_loss=0.2577, pruned_loss=0.05606, over 4912.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02905, over 971064.79 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:08:20,794 INFO [train.py:715] (5/8) Epoch 18, batch 25850, loss[loss=0.1053, simple_loss=0.1811, pruned_loss=0.01473, over 4702.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02872, over 970950.90 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:08:59,115 INFO [train.py:715] (5/8) Epoch 18, batch 25900, loss[loss=0.1414, simple_loss=0.2146, pruned_loss=0.03411, over 4961.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.0286, over 972245.85 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:09:38,440 INFO [train.py:715] (5/8) Epoch 18, batch 25950, loss[loss=0.1193, simple_loss=0.1916, pruned_loss=0.02352, over 4966.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 971704.64 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 11:10:17,514 INFO [train.py:715] (5/8) Epoch 18, batch 26000, loss[loss=0.138, simple_loss=0.2102, pruned_loss=0.03291, over 4908.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 972659.18 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:10:56,982 INFO [train.py:715] (5/8) Epoch 18, batch 26050, loss[loss=0.1348, simple_loss=0.2165, pruned_loss=0.02657, over 4822.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02925, over 972020.34 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:11:36,113 INFO [train.py:715] (5/8) Epoch 18, batch 26100, loss[loss=0.1285, simple_loss=0.2124, pruned_loss=0.02232, over 4883.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02908, over 971691.63 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 11:12:15,690 INFO [train.py:715] (5/8) Epoch 18, batch 26150, loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.02874, over 4987.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02888, over 971213.18 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:12:54,903 INFO [train.py:715] (5/8) Epoch 18, batch 26200, loss[loss=0.126, simple_loss=0.1926, pruned_loss=0.0297, over 4748.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.029, over 971986.98 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 11:13:33,235 INFO [train.py:715] (5/8) Epoch 18, batch 26250, loss[loss=0.1698, simple_loss=0.2503, pruned_loss=0.04462, over 4936.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02904, over 971156.89 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:14:12,859 INFO [train.py:715] (5/8) Epoch 18, batch 26300, loss[loss=0.1089, simple_loss=0.1873, pruned_loss=0.01527, over 4867.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02867, over 972388.83 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:14:51,544 INFO [train.py:715] (5/8) Epoch 18, batch 26350, loss[loss=0.1214, simple_loss=0.1971, pruned_loss=0.02282, over 4791.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 972262.41 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:15:30,589 INFO [train.py:715] (5/8) Epoch 18, batch 26400, loss[loss=0.159, simple_loss=0.2224, pruned_loss=0.04773, over 4958.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02848, over 972111.99 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:16:09,486 INFO [train.py:715] (5/8) Epoch 18, batch 26450, loss[loss=0.1509, simple_loss=0.2124, pruned_loss=0.04477, over 4839.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02852, over 972784.86 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 11:16:49,037 INFO [train.py:715] (5/8) Epoch 18, batch 26500, loss[loss=0.126, simple_loss=0.1903, pruned_loss=0.03084, over 4920.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02817, over 972551.36 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:17:28,071 INFO [train.py:715] (5/8) Epoch 18, batch 26550, loss[loss=0.1681, simple_loss=0.2405, pruned_loss=0.0478, over 4917.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02834, over 972470.04 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:18:06,864 INFO [train.py:715] (5/8) Epoch 18, batch 26600, loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03175, over 4770.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02856, over 972884.43 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:18:46,126 INFO [train.py:715] (5/8) Epoch 18, batch 26650, loss[loss=0.1224, simple_loss=0.1977, pruned_loss=0.02354, over 4790.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2049, pruned_loss=0.02848, over 972372.27 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:19:25,269 INFO [train.py:715] (5/8) Epoch 18, batch 26700, loss[loss=0.1334, simple_loss=0.2094, pruned_loss=0.02875, over 4775.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2051, pruned_loss=0.02868, over 971606.89 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:20:05,260 INFO [train.py:715] (5/8) Epoch 18, batch 26750, loss[loss=0.1441, simple_loss=0.2205, pruned_loss=0.03388, over 4774.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02857, over 971806.35 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:20:43,659 INFO [train.py:715] (5/8) Epoch 18, batch 26800, loss[loss=0.1133, simple_loss=0.1842, pruned_loss=0.02125, over 4823.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 971621.35 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:21:23,698 INFO [train.py:715] (5/8) Epoch 18, batch 26850, loss[loss=0.1217, simple_loss=0.2044, pruned_loss=0.01952, over 4777.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02847, over 972371.32 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:22:03,379 INFO [train.py:715] (5/8) Epoch 18, batch 26900, loss[loss=0.1484, simple_loss=0.2225, pruned_loss=0.03716, over 4977.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02802, over 972837.30 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:22:41,419 INFO [train.py:715] (5/8) Epoch 18, batch 26950, loss[loss=0.1395, simple_loss=0.2164, pruned_loss=0.03132, over 4833.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2057, pruned_loss=0.028, over 972510.65 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 11:23:20,806 INFO [train.py:715] (5/8) Epoch 18, batch 27000, loss[loss=0.1204, simple_loss=0.1988, pruned_loss=0.02094, over 4958.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02822, over 972305.97 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:23:20,807 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 11:23:30,796 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01055, over 914524.00 frames.
2022-05-09 11:24:11,108 INFO [train.py:715] (5/8) Epoch 18, batch 27050, loss[loss=0.1276, simple_loss=0.2043, pruned_loss=0.02541, over 4869.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02806, over 972450.62 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:24:50,010 INFO [train.py:715] (5/8) Epoch 18, batch 27100, loss[loss=0.1386, simple_loss=0.2172, pruned_loss=0.02998, over 4809.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02838, over 973241.12 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:25:29,321 INFO [train.py:715] (5/8) Epoch 18, batch 27150, loss[loss=0.1264, simple_loss=0.2081, pruned_loss=0.02235, over 4908.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02853, over 972227.25 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:26:08,684 INFO [train.py:715] (5/8) Epoch 18, batch 27200, loss[loss=0.1549, simple_loss=0.2272, pruned_loss=0.0413, over 4939.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02859, over 971287.46 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:26:47,914 INFO [train.py:715] (5/8) Epoch 18, batch 27250, loss[loss=0.142, simple_loss=0.2108, pruned_loss=0.03659, over 4811.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02899, over 971876.46 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:27:26,982 INFO [train.py:715] (5/8) Epoch 18, batch 27300, loss[loss=0.1353, simple_loss=0.2166, pruned_loss=0.02698, over 4871.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02861, over 972067.00 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 11:28:05,823 INFO [train.py:715] (5/8) Epoch 18, batch 27350, loss[loss=0.1592, simple_loss=0.227, pruned_loss=0.04571, over 4919.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02912, over 972496.99 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:28:46,003 INFO [train.py:715] (5/8) Epoch 18, batch 27400, loss[loss=0.1422, simple_loss=0.2245, pruned_loss=0.02995, over 4971.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 973401.05 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:29:25,405 INFO [train.py:715] (5/8) Epoch 18, batch 27450, loss[loss=0.123, simple_loss=0.197, pruned_loss=0.02453, over 4868.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02907, over 973919.30 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:30:04,445 INFO [train.py:715] (5/8) Epoch 18, batch 27500, loss[loss=0.1441, simple_loss=0.2264, pruned_loss=0.03089, over 4915.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02889, over 973623.57 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:30:44,161 INFO [train.py:715] (5/8) Epoch 18, batch 27550, loss[loss=0.1118, simple_loss=0.1851, pruned_loss=0.01924, over 4898.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02908, over 973264.93 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 11:31:23,280 INFO [train.py:715] (5/8) Epoch 18, batch 27600, loss[loss=0.1299, simple_loss=0.1984, pruned_loss=0.03067, over 4884.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02908, over 973247.93 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 11:32:01,944 INFO [train.py:715] (5/8) Epoch 18, batch 27650, loss[loss=0.1405, simple_loss=0.2204, pruned_loss=0.03032, over 4985.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02885, over 973059.67 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:32:40,859 INFO [train.py:715] (5/8) Epoch 18, batch 27700, loss[loss=0.1129, simple_loss=0.1896, pruned_loss=0.01811, over 4819.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02884, over 972730.14 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:33:20,157 INFO [train.py:715] (5/8) Epoch 18, batch 27750, loss[loss=0.1318, simple_loss=0.2012, pruned_loss=0.03116, over 4965.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.0287, over 973097.45 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:33:59,616 INFO [train.py:715] (5/8) Epoch 18, batch 27800, loss[loss=0.1094, simple_loss=0.1819, pruned_loss=0.01846, over 4696.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02828, over 973170.75 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:34:38,868 INFO [train.py:715] (5/8) Epoch 18, batch 27850, loss[loss=0.1454, simple_loss=0.2145, pruned_loss=0.03812, over 4681.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02799, over 973708.25 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:35:18,479 INFO [train.py:715] (5/8) Epoch 18, batch 27900, loss[loss=0.1246, simple_loss=0.1983, pruned_loss=0.02542, over 4854.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.02808, over 973312.69 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 11:35:57,740 INFO [train.py:715] (5/8) Epoch 18, batch 27950, loss[loss=0.1018, simple_loss=0.1742, pruned_loss=0.01471, over 4912.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02818, over 972079.74 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:36:36,983 INFO [train.py:715] (5/8) Epoch 18, batch 28000, loss[loss=0.1023, simple_loss=0.1764, pruned_loss=0.01409, over 4781.00 frames.], tot_loss[loss=0.13, simple_loss=0.2043, pruned_loss=0.02779, over 972303.58 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:37:16,532 INFO [train.py:715] (5/8) Epoch 18, batch 28050, loss[loss=0.1456, simple_loss=0.2225, pruned_loss=0.03438, over 4983.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2045, pruned_loss=0.02759, over 972896.45 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:37:56,319 INFO [train.py:715] (5/8) Epoch 18, batch 28100, loss[loss=0.135, simple_loss=0.2014, pruned_loss=0.03427, over 4772.00 frames.], tot_loss[loss=0.13, simple_loss=0.2046, pruned_loss=0.02766, over 972830.86 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:38:35,510 INFO [train.py:715] (5/8) Epoch 18, batch 28150, loss[loss=0.1649, simple_loss=0.2303, pruned_loss=0.04977, over 4964.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02835, over 972430.69 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:39:13,845 INFO [train.py:715] (5/8) Epoch 18, batch 28200, loss[loss=0.1129, simple_loss=0.1932, pruned_loss=0.01636, over 4814.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02891, over 972305.97 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:39:53,466 INFO [train.py:715] (5/8) Epoch 18, batch 28250, loss[loss=0.1237, simple_loss=0.1995, pruned_loss=0.02396, over 4833.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.0295, over 971851.83 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:40:32,292 INFO [train.py:715] (5/8) Epoch 18, batch 28300, loss[loss=0.138, simple_loss=0.2046, pruned_loss=0.03568, over 4769.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02992, over 972119.92 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:41:11,197 INFO [train.py:715] (5/8) Epoch 18, batch 28350, loss[loss=0.1019, simple_loss=0.1657, pruned_loss=0.01904, over 4981.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02948, over 972730.41 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:41:50,493 INFO [train.py:715] (5/8) Epoch 18, batch 28400, loss[loss=0.1227, simple_loss=0.1989, pruned_loss=0.0233, over 4975.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02947, over 972380.29 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 11:42:29,770 INFO [train.py:715] (5/8) Epoch 18, batch 28450, loss[loss=0.1155, simple_loss=0.1934, pruned_loss=0.01879, over 4978.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02988, over 973070.04 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:43:08,844 INFO [train.py:715] (5/8) Epoch 18, batch 28500, loss[loss=0.1127, simple_loss=0.1851, pruned_loss=0.02012, over 4761.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03009, over 972575.47 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:43:47,952 INFO [train.py:715] (5/8) Epoch 18, batch 28550, loss[loss=0.1176, simple_loss=0.1957, pruned_loss=0.01973, over 4930.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02986, over 972855.18 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 11:44:27,959 INFO [train.py:715] (5/8) Epoch 18, batch 28600, loss[loss=0.1449, simple_loss=0.2136, pruned_loss=0.03813, over 4810.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03011, over 972957.63 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:45:06,660 INFO [train.py:715] (5/8) Epoch 18, batch 28650, loss[loss=0.1331, simple_loss=0.2143, pruned_loss=0.02597, over 4861.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03007, over 972700.05 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:45:45,608 INFO [train.py:715] (5/8) Epoch 18, batch 28700, loss[loss=0.1333, simple_loss=0.2094, pruned_loss=0.02861, over 4696.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02975, over 972642.59 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:46:25,176 INFO [train.py:715] (5/8) Epoch 18, batch 28750, loss[loss=0.1198, simple_loss=0.2, pruned_loss=0.01987, over 4833.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02971, over 972179.32 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 11:47:04,221 INFO [train.py:715] (5/8) Epoch 18, batch 28800, loss[loss=0.1223, simple_loss=0.1943, pruned_loss=0.02517, over 4969.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02971, over 972103.58 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:47:43,077 INFO [train.py:715] (5/8) Epoch 18, batch 28850, loss[loss=0.1046, simple_loss=0.1752, pruned_loss=0.01703, over 4709.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 971078.71 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:48:21,620 INFO [train.py:715] (5/8) Epoch 18, batch 28900, loss[loss=0.1266, simple_loss=0.2094, pruned_loss=0.0219, over 4926.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02901, over 971641.38 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:49:01,744 INFO [train.py:715] (5/8) Epoch 18, batch 28950, loss[loss=0.1093, simple_loss=0.1872, pruned_loss=0.01568, over 4961.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02887, over 971655.99 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:49:40,558 INFO [train.py:715] (5/8) Epoch 18, batch 29000, loss[loss=0.09691, simple_loss=0.167, pruned_loss=0.01344, over 4866.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02911, over 971831.64 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 11:50:19,733 INFO [train.py:715] (5/8) Epoch 18, batch 29050, loss[loss=0.09782, simple_loss=0.1616, pruned_loss=0.017, over 4734.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02886, over 971902.20 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:50:59,123 INFO [train.py:715] (5/8) Epoch 18, batch 29100, loss[loss=0.1341, simple_loss=0.2221, pruned_loss=0.02307, over 4780.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02856, over 971588.11 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:51:38,414 INFO [train.py:715] (5/8) Epoch 18, batch 29150, loss[loss=0.1328, simple_loss=0.2013, pruned_loss=0.03212, over 4933.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02868, over 972192.56 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:52:17,127 INFO [train.py:715] (5/8) Epoch 18, batch 29200, loss[loss=0.1381, simple_loss=0.2107, pruned_loss=0.03275, over 4812.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02837, over 971612.77 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:52:55,642 INFO [train.py:715] (5/8) Epoch 18, batch 29250, loss[loss=0.114, simple_loss=0.187, pruned_loss=0.02051, over 4803.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.0283, over 971958.96 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:53:35,209 INFO [train.py:715] (5/8) Epoch 18, batch 29300, loss[loss=0.1384, simple_loss=0.202, pruned_loss=0.0374, over 4978.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02837, over 971850.37 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:54:13,910 INFO [train.py:715] (5/8) Epoch 18, batch 29350, loss[loss=0.1133, simple_loss=0.1949, pruned_loss=0.01585, over 4917.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02827, over 972059.45 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:54:52,608 INFO [train.py:715] (5/8) Epoch 18, batch 29400, loss[loss=0.1364, simple_loss=0.2072, pruned_loss=0.0328, over 4783.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02879, over 971516.87 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:55:33,954 INFO [train.py:715] (5/8) Epoch 18, batch 29450, loss[loss=0.1413, simple_loss=0.2198, pruned_loss=0.03138, over 4787.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02915, over 971134.44 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:56:12,979 INFO [train.py:715] (5/8) Epoch 18, batch 29500, loss[loss=0.1111, simple_loss=0.1768, pruned_loss=0.02269, over 4983.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02885, over 971523.50 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:56:52,070 INFO [train.py:715] (5/8) Epoch 18, batch 29550, loss[loss=0.1398, simple_loss=0.2256, pruned_loss=0.02699, over 4758.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 972019.52 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:57:30,047 INFO [train.py:715] (5/8) Epoch 18, batch 29600, loss[loss=0.1472, simple_loss=0.2122, pruned_loss=0.04106, over 4777.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02885, over 971620.14 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:58:09,258 INFO [train.py:715] (5/8) Epoch 18, batch 29650, loss[loss=0.1335, simple_loss=0.2098, pruned_loss=0.02865, over 4975.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02888, over 971520.79 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:58:48,233 INFO [train.py:715] (5/8) Epoch 18, batch 29700, loss[loss=0.122, simple_loss=0.2115, pruned_loss=0.01624, over 4744.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02831, over 970963.02 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:59:26,598 INFO [train.py:715] (5/8) Epoch 18, batch 29750, loss[loss=0.1297, simple_loss=0.2149, pruned_loss=0.0222, over 4798.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02837, over 971534.73 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:00:05,912 INFO [train.py:715] (5/8) Epoch 18, batch 29800, loss[loss=0.1428, simple_loss=0.2277, pruned_loss=0.029, over 4927.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02853, over 971860.44 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 12:00:45,626 INFO [train.py:715] (5/8) Epoch 18, batch 29850, loss[loss=0.1152, simple_loss=0.1758, pruned_loss=0.02724, over 4799.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02853, over 972313.90 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:01:24,705 INFO [train.py:715] (5/8) Epoch 18, batch 29900, loss[loss=0.1091, simple_loss=0.1793, pruned_loss=0.01943, over 4980.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02839, over 972152.83 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:02:03,295 INFO [train.py:715] (5/8) Epoch 18, batch 29950, loss[loss=0.1246, simple_loss=0.1993, pruned_loss=0.02497, over 4831.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02788, over 972384.02 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:02:43,060 INFO [train.py:715] (5/8) Epoch 18, batch 30000, loss[loss=0.1127, simple_loss=0.1901, pruned_loss=0.01768, over 4883.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2045, pruned_loss=0.02807, over 972715.11 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:02:43,061 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 12:02:52,967 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01071, over 914524.00 frames.
2022-05-09 12:03:33,193 INFO [train.py:715] (5/8) Epoch 18, batch 30050, loss[loss=0.1512, simple_loss=0.2247, pruned_loss=0.03883, over 4753.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02834, over 971908.90 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:04:12,320 INFO [train.py:715] (5/8) Epoch 18, batch 30100, loss[loss=0.1078, simple_loss=0.1836, pruned_loss=0.016, over 4770.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02875, over 972374.28 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:04:50,502 INFO [train.py:715] (5/8) Epoch 18, batch 30150, loss[loss=0.1651, simple_loss=0.2278, pruned_loss=0.05125, over 4758.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02856, over 972458.11 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:05:29,936 INFO [train.py:715] (5/8) Epoch 18, batch 30200, loss[loss=0.132, simple_loss=0.2094, pruned_loss=0.02729, over 4940.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02862, over 972638.38 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:06:09,181 INFO [train.py:715] (5/8) Epoch 18, batch 30250, loss[loss=0.1081, simple_loss=0.1794, pruned_loss=0.01843, over 4799.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 972815.49 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:06:48,871 INFO [train.py:715] (5/8) Epoch 18, batch 30300, loss[loss=0.1381, simple_loss=0.2143, pruned_loss=0.03095, over 4680.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 972179.19 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:07:27,507 INFO [train.py:715] (5/8) Epoch 18, batch 30350, loss[loss=0.1289, simple_loss=0.2035, pruned_loss=0.02716, over 4774.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02891, over 971545.10 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:08:07,405 INFO [train.py:715] (5/8) Epoch 18, batch 30400, loss[loss=0.1409, simple_loss=0.2144, pruned_loss=0.03371, over 4844.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2058, pruned_loss=0.02939, over 971270.71 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:08:46,433 INFO [train.py:715] (5/8) Epoch 18, batch 30450, loss[loss=0.1539, simple_loss=0.235, pruned_loss=0.03639, over 4975.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02896, over 971918.39 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:09:24,921 INFO [train.py:715] (5/8) Epoch 18, batch 30500, loss[loss=0.1385, simple_loss=0.205, pruned_loss=0.03604, over 4951.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.0287, over 971773.20 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:10:04,133 INFO [train.py:715] (5/8) Epoch 18, batch 30550, loss[loss=0.1326, simple_loss=0.2157, pruned_loss=0.02474, over 4957.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02848, over 972412.11 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:10:42,815 INFO [train.py:715] (5/8) Epoch 18, batch 30600, loss[loss=0.1573, simple_loss=0.2383, pruned_loss=0.03819, over 4876.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02846, over 972792.69 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:11:21,482 INFO [train.py:715] (5/8) Epoch 18, batch 30650, loss[loss=0.147, simple_loss=0.2136, pruned_loss=0.0402, over 4820.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02835, over 972475.14 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:12:00,153 INFO [train.py:715] (5/8) Epoch 18, batch 30700, loss[loss=0.1247, simple_loss=0.1966, pruned_loss=0.02645, over 4823.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02801, over 972258.99 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:12:39,280 INFO [train.py:715] (5/8) Epoch 18, batch 30750, loss[loss=0.112, simple_loss=0.1828, pruned_loss=0.02063, over 4636.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02819, over 971662.29 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 12:13:18,035 INFO [train.py:715] (5/8) Epoch 18, batch 30800, loss[loss=0.1361, simple_loss=0.22, pruned_loss=0.02609, over 4993.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02881, over 971386.00 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:13:56,473 INFO [train.py:715] (5/8) Epoch 18, batch 30850, loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03074, over 4788.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.0288, over 971908.19 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:14:35,508 INFO [train.py:715] (5/8) Epoch 18, batch 30900, loss[loss=0.1479, simple_loss=0.2146, pruned_loss=0.04064, over 4975.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02916, over 971844.76 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:15:14,124 INFO [train.py:715] (5/8) Epoch 18, batch 30950, loss[loss=0.1106, simple_loss=0.1919, pruned_loss=0.01465, over 4953.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02895, over 972228.47 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:15:52,435 INFO [train.py:715] (5/8) Epoch 18, batch 31000, loss[loss=0.1349, simple_loss=0.2118, pruned_loss=0.02899, over 4914.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02846, over 972530.69 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 12:16:31,404 INFO [train.py:715] (5/8) Epoch 18, batch 31050, loss[loss=0.1133, simple_loss=0.1964, pruned_loss=0.01513, over 4756.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02836, over 972040.32 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:17:10,959 INFO [train.py:715] (5/8) Epoch 18, batch 31100, loss[loss=0.1565, simple_loss=0.237, pruned_loss=0.03798, over 4937.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02835, over 973037.38 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:17:49,894 INFO [train.py:715] (5/8) Epoch 18, batch 31150, loss[loss=0.1308, simple_loss=0.2042, pruned_loss=0.02867, over 4950.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02844, over 972454.40 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:18:28,836 INFO [train.py:715] (5/8) Epoch 18, batch 31200, loss[loss=0.1386, simple_loss=0.2072, pruned_loss=0.03502, over 4947.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02839, over 972186.59 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:19:08,214 INFO [train.py:715] (5/8) Epoch 18, batch 31250, loss[loss=0.1181, simple_loss=0.1953, pruned_loss=0.02043, over 4851.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02859, over 972719.85 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:19:47,257 INFO [train.py:715] (5/8) Epoch 18, batch 31300, loss[loss=0.1236, simple_loss=0.1958, pruned_loss=0.02567, over 4822.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.0285, over 972451.94 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:20:25,876 INFO [train.py:715] (5/8) Epoch 18, batch 31350, loss[loss=0.09015, simple_loss=0.1612, pruned_loss=0.009551, over 4852.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02886, over 971880.45 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:21:05,050 INFO [train.py:715] (5/8) Epoch 18, batch 31400, loss[loss=0.125, simple_loss=0.2045, pruned_loss=0.02274, over 4780.00 frames.], tot_loss[loss=0.132, simple_loss=0.2057, pruned_loss=0.02908, over 972445.82 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:21:44,553 INFO [train.py:715] (5/8) Epoch 18, batch 31450, loss[loss=0.1157, simple_loss=0.1795, pruned_loss=0.02593, over 4782.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02929, over 972964.45 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:22:23,387 INFO [train.py:715] (5/8) Epoch 18, batch 31500, loss[loss=0.1903, simple_loss=0.2515, pruned_loss=0.06452, over 4751.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02906, over 972193.45 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:23:01,621 INFO [train.py:715] (5/8) Epoch 18, batch 31550, loss[loss=0.1221, simple_loss=0.2006, pruned_loss=0.02179, over 4768.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02899, over 971840.58 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:23:41,438 INFO [train.py:715] (5/8) Epoch 18, batch 31600, loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03418, over 4799.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02882, over 972465.07 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:24:20,708 INFO [train.py:715] (5/8) Epoch 18, batch 31650, loss[loss=0.1143, simple_loss=0.1945, pruned_loss=0.01706, over 4980.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02867, over 971311.72 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 12:24:59,687 INFO [train.py:715] (5/8) Epoch 18, batch 31700, loss[loss=0.1131, simple_loss=0.1854, pruned_loss=0.02037, over 4785.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.0288, over 971580.87 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:25:38,808 INFO [train.py:715] (5/8) Epoch 18, batch 31750, loss[loss=0.132, simple_loss=0.1972, pruned_loss=0.03338, over 4790.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02846, over 971325.64 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:26:18,650 INFO [train.py:715] (5/8) Epoch 18, batch 31800, loss[loss=0.1733, simple_loss=0.2512, pruned_loss=0.04771, over 4988.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02913, over 972638.74 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 12:26:58,018 INFO [train.py:715] (5/8) Epoch 18, batch 31850, loss[loss=0.1413, simple_loss=0.217, pruned_loss=0.03275, over 4754.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02874, over 972480.15 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:27:36,975 INFO [train.py:715] (5/8) Epoch 18, batch 31900, loss[loss=0.1288, simple_loss=0.196, pruned_loss=0.03083, over 4889.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02853, over 972591.61 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:28:16,145 INFO [train.py:715] (5/8) Epoch 18, batch 31950, loss[loss=0.125, simple_loss=0.1947, pruned_loss=0.02767, over 4922.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02893, over 973042.31 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:28:54,458 INFO [train.py:715] (5/8) Epoch 18, batch 32000, loss[loss=0.1222, simple_loss=0.1974, pruned_loss=0.02353, over 4768.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02848, over 972844.40 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:29:32,617 INFO [train.py:715] (5/8) Epoch 18, batch 32050, loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03159, over 4821.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02864, over 972379.26 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 12:30:11,875 INFO [train.py:715] (5/8) Epoch 18, batch 32100, loss[loss=0.1183, simple_loss=0.1864, pruned_loss=0.02505, over 4911.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02814, over 971806.36 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:30:51,371 INFO [train.py:715] (5/8) Epoch 18, batch 32150, loss[loss=0.1028, simple_loss=0.1778, pruned_loss=0.01391, over 4803.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02817, over 972408.06 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:31:30,531 INFO [train.py:715] (5/8) Epoch 18, batch 32200, loss[loss=0.1398, simple_loss=0.2171, pruned_loss=0.03119, over 4855.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2056, pruned_loss=0.02784, over 972020.05 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 12:32:08,907 INFO [train.py:715] (5/8) Epoch 18, batch 32250, loss[loss=0.1526, simple_loss=0.2335, pruned_loss=0.03588, over 4888.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.0283, over 971269.64 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:32:48,157 INFO [train.py:715] (5/8) Epoch 18, batch 32300, loss[loss=0.109, simple_loss=0.1795, pruned_loss=0.01928, over 4779.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02869, over 971044.89 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:33:26,713 INFO [train.py:715] (5/8) Epoch 18, batch 32350, loss[loss=0.126, simple_loss=0.1935, pruned_loss=0.02927, over 4960.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02843, over 971661.80 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:34:05,358 INFO [train.py:715] (5/8) Epoch 18, batch 32400, loss[loss=0.1352, simple_loss=0.2101, pruned_loss=0.03013, over 4977.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 970406.35 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:34:44,779 INFO [train.py:715] (5/8) Epoch 18, batch 32450, loss[loss=0.1162, simple_loss=0.1906, pruned_loss=0.02086, over 4936.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 970363.67 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:35:23,648 INFO [train.py:715] (5/8) Epoch 18, batch 32500, loss[loss=0.1049, simple_loss=0.1843, pruned_loss=0.01271, over 4773.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02843, over 970745.44 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:36:02,852 INFO [train.py:715] (5/8) Epoch 18, batch 32550, loss[loss=0.1332, simple_loss=0.212, pruned_loss=0.02723, over 4927.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02853, over 971340.01 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:36:42,025 INFO [train.py:715] (5/8) Epoch 18, batch 32600, loss[loss=0.1289, simple_loss=0.1999, pruned_loss=0.02892, over 4851.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02878, over 971597.55 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:37:21,476 INFO [train.py:715] (5/8) Epoch 18, batch 32650, loss[loss=0.1333, simple_loss=0.2234, pruned_loss=0.02161, over 4712.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02852, over 971563.00 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:37:59,899 INFO [train.py:715] (5/8) Epoch 18, batch 32700, loss[loss=0.1221, simple_loss=0.1912, pruned_loss=0.02647, over 4868.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02844, over 972383.60 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 12:38:38,643 INFO [train.py:715] (5/8) Epoch 18, batch 32750, loss[loss=0.1335, simple_loss=0.2011, pruned_loss=0.03297, over 4848.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02811, over 971950.80 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 12:39:17,959 INFO [train.py:715] (5/8) Epoch 18, batch 32800, loss[loss=0.1512, simple_loss=0.2229, pruned_loss=0.03977, over 4770.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02823, over 972051.14 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:39:57,150 INFO [train.py:715] (5/8) Epoch 18, batch 32850, loss[loss=0.1315, simple_loss=0.207, pruned_loss=0.02795, over 4858.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02847, over 972111.17 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 12:40:35,663 INFO [train.py:715] (5/8) Epoch 18, batch 32900, loss[loss=0.1309, simple_loss=0.2065, pruned_loss=0.02765, over 4796.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2064, pruned_loss=0.02819, over 972101.97 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 12:41:14,762 INFO [train.py:715] (5/8) Epoch 18, batch 32950, loss[loss=0.1041, simple_loss=0.1735, pruned_loss=0.01734, over 4934.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02859, over 972343.69 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:41:53,955 INFO [train.py:715] (5/8) Epoch 18, batch 33000, loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03259, over 4746.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2073, pruned_loss=0.02827, over 972455.58 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:41:53,957 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 12:42:03,826 INFO [train.py:742] (5/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01068, over 914524.00 frames.
2022-05-09 12:42:43,655 INFO [train.py:715] (5/8) Epoch 18, batch 33050, loss[loss=0.1483, simple_loss=0.206, pruned_loss=0.04527, over 4938.00 frames.], tot_loss[loss=0.1319, simple_loss=0.207, pruned_loss=0.0284, over 973492.04 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:43:22,617 INFO [train.py:715] (5/8) Epoch 18, batch 33100, loss[loss=0.1344, simple_loss=0.2056, pruned_loss=0.03162, over 4984.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2074, pruned_loss=0.02861, over 973643.01 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 12:44:02,105 INFO [train.py:715] (5/8) Epoch 18, batch 33150, loss[loss=0.1334, simple_loss=0.203, pruned_loss=0.03189, over 4857.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02853, over 973507.49 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:44:41,944 INFO [train.py:715] (5/8) Epoch 18, batch 33200, loss[loss=0.1298, simple_loss=0.2033, pruned_loss=0.02814, over 4900.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02846, over 973343.75 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:45:20,898 INFO [train.py:715] (5/8) Epoch 18, batch 33250, loss[loss=0.1344, simple_loss=0.2108, pruned_loss=0.02899, over 4928.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02896, over 973432.22 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:45:59,529 INFO [train.py:715] (5/8) Epoch 18, batch 33300, loss[loss=0.1787, simple_loss=0.2455, pruned_loss=0.05593, over 4864.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02966, over 972907.63 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:46:38,974 INFO [train.py:715] (5/8) Epoch 18, batch 33350, loss[loss=0.1456, simple_loss=0.2142, pruned_loss=0.03846, over 4876.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02969, over 974118.97 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:47:18,352 INFO [train.py:715] (5/8) Epoch 18, batch 33400, loss[loss=0.1404, simple_loss=0.2007, pruned_loss=0.04001, over 4888.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02954, over 973969.43 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:47:57,079 INFO [train.py:715] (5/8) Epoch 18, batch 33450, loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02963, over 4957.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02948, over 974147.22 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:48:36,023 INFO [train.py:715] (5/8) Epoch 18, batch 33500, loss[loss=0.1336, simple_loss=0.2042, pruned_loss=0.03155, over 4760.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02956, over 973165.86 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:49:15,395 INFO [train.py:715] (5/8) Epoch 18, batch 33550, loss[loss=0.1106, simple_loss=0.1917, pruned_loss=0.01476, over 4977.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02945, over 974000.51 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 12:49:54,439 INFO [train.py:715] (5/8) Epoch 18, batch 33600, loss[loss=0.1561, simple_loss=0.215, pruned_loss=0.04859, over 4828.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02883, over 972962.82 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:50:32,502 INFO [train.py:715] (5/8) Epoch 18, batch 33650, loss[loss=0.1274, simple_loss=0.2141, pruned_loss=0.02032, over 4974.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02908, over 972396.65 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 12:51:11,947 INFO [train.py:715] (5/8) Epoch 18, batch 33700, loss[loss=0.1022, simple_loss=0.1818, pruned_loss=0.01131, over 4976.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02848, over 972101.63 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 12:51:51,114 INFO [train.py:715] (5/8) Epoch 18, batch 33750, loss[loss=0.1324, simple_loss=0.2023, pruned_loss=0.03121, over 4862.00 frames.], tot_loss[loss=0.1318, simple_loss=0.207, pruned_loss=0.02835, over 972310.20 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:52:30,431 INFO [train.py:715] (5/8) Epoch 18, batch 33800, loss[loss=0.1337, simple_loss=0.2256, pruned_loss=0.02087, over 4967.00 frames.], tot_loss[loss=0.1317, simple_loss=0.207, pruned_loss=0.02818, over 972742.02 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:53:09,706 INFO [train.py:715] (5/8) Epoch 18, batch 33850, loss[loss=0.1131, simple_loss=0.1819, pruned_loss=0.02211, over 4725.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2066, pruned_loss=0.0282, over 972140.02 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:53:49,534 INFO [train.py:715] (5/8) Epoch 18, batch 33900, loss[loss=0.1168, simple_loss=0.1924, pruned_loss=0.02056, over 4814.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2065, pruned_loss=0.02802, over 972415.85 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:54:28,736 INFO [train.py:715] (5/8) Epoch 18, batch 33950, loss[loss=0.1177, simple_loss=0.189, pruned_loss=0.02322, over 4975.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2067, pruned_loss=0.02814, over 973025.61 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:55:07,057 INFO [train.py:715] (5/8) Epoch 18, batch 34000, loss[loss=0.1108, simple_loss=0.1731, pruned_loss=0.02429, over 4971.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2066, pruned_loss=0.02817, over 973698.97 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:55:46,476 INFO [train.py:715] (5/8) Epoch 18, batch 34050, loss[loss=0.1539, simple_loss=0.2348, pruned_loss=0.03646, over 4881.00 frames.], tot_loss[loss=0.132, simple_loss=0.2072, pruned_loss=0.02845, over 973949.93 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:56:25,888 INFO [train.py:715] (5/8) Epoch 18, batch 34100, loss[loss=0.1585, simple_loss=0.2347, pruned_loss=0.04117, over 4699.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02845, over 973031.42 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:57:05,033 INFO [train.py:715] (5/8) Epoch 18, batch 34150, loss[loss=0.1115, simple_loss=0.1788, pruned_loss=0.02212, over 4846.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02809, over 972367.31 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:57:44,077 INFO [train.py:715] (5/8) Epoch 18, batch 34200, loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03683, over 4859.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.028, over 973015.73 frames.], batch size: 38, lr: 1.22e-04
2022-05-09 12:58:23,224 INFO [train.py:715] (5/8) Epoch 18, batch 34250, loss[loss=0.1198, simple_loss=0.198, pruned_loss=0.02082, over 4869.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02813, over 973088.25 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:59:02,032 INFO [train.py:715] (5/8) Epoch 18, batch 34300, loss[loss=0.1513, simple_loss=0.2039, pruned_loss=0.04931, over 4970.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02822, over 972287.76 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:59:40,333 INFO [train.py:715] (5/8) Epoch 18, batch 34350, loss[loss=0.1476, simple_loss=0.2214, pruned_loss=0.03688, over 4972.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 972579.42 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 13:00:19,860 INFO [train.py:715] (5/8) Epoch 18, batch 34400, loss[loss=0.1286, simple_loss=0.2043, pruned_loss=0.02649, over 4901.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 972565.80 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 13:00:59,442 INFO [train.py:715] (5/8) Epoch 18, batch 34450, loss[loss=0.1154, simple_loss=0.1866, pruned_loss=0.02214, over 4820.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02873, over 971881.52 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 13:01:39,370 INFO [train.py:715] (5/8) Epoch 18, batch 34500, loss[loss=0.1012, simple_loss=0.1763, pruned_loss=0.01308, over 4953.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 970842.00 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 13:02:18,894 INFO [train.py:715] (5/8) Epoch 18, batch 34550, loss[loss=0.1486, simple_loss=0.2182, pruned_loss=0.03946, over 4910.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02902, over 970403.02 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 13:02:58,575 INFO [train.py:715] (5/8) Epoch 18, batch 34600, loss[loss=0.1101, simple_loss=0.1907, pruned_loss=0.01473, over 4980.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02907, over 970694.61 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 13:03:37,754 INFO [train.py:715] (5/8) Epoch 18, batch 34650, loss[loss=0.1432, simple_loss=0.2124, pruned_loss=0.03706, over 4767.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02897, over 970923.03 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 13:04:17,381 INFO [train.py:715] (5/8) Epoch 18, batch 34700, loss[loss=0.1509, simple_loss=0.2195, pruned_loss=0.04113, over 4969.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02872, over 970959.13 frames.], batch size: 15, lr: 1.21e-04
2022-05-09 13:04:56,519 INFO [train.py:715] (5/8) Epoch 18, batch 34750, loss[loss=0.1162, simple_loss=0.1911, pruned_loss=0.0206, over 4828.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02872, over 970953.75 frames.], batch size: 25, lr: 1.21e-04
2022-05-09 13:05:34,142 INFO [train.py:715] (5/8) Epoch 18, batch 34800, loss[loss=0.1006, simple_loss=0.1702, pruned_loss=0.01546, over 4823.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02882, over 968888.77 frames.], batch size: 12, lr: 1.21e-04
2022-05-09 13:06:24,917 INFO [train.py:715] (5/8) Epoch 19, batch 0, loss[loss=0.1153, simple_loss=0.1802, pruned_loss=0.02513, over 4839.00 frames.], tot_loss[loss=0.1153, simple_loss=0.1802, pruned_loss=0.02513, over 4839.00 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:07:03,499 INFO [train.py:715] (5/8) Epoch 19, batch 50, loss[loss=0.1075, simple_loss=0.1849, pruned_loss=0.01509, over 4986.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02909, over 219050.53 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:07:43,525 INFO [train.py:715] (5/8) Epoch 19, batch 100, loss[loss=0.1378, simple_loss=0.2195, pruned_loss=0.028, over 4985.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02893, over 385312.31 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:08:23,943 INFO [train.py:715] (5/8) Epoch 19, batch 150, loss[loss=0.1392, simple_loss=0.2102, pruned_loss=0.03411, over 4793.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02855, over 515332.49 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:09:04,144 INFO [train.py:715] (5/8) Epoch 19, batch 200, loss[loss=0.128, simple_loss=0.2049, pruned_loss=0.02557, over 4750.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02882, over 617651.80 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:09:44,076 INFO [train.py:715] (5/8) Epoch 19, batch 250, loss[loss=0.1385, simple_loss=0.2164, pruned_loss=0.03024, over 4862.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02888, over 697032.09 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 13:10:24,215 INFO [train.py:715] (5/8) Epoch 19, batch 300, loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02992, over 4799.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.0289, over 758770.96 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:11:04,671 INFO [train.py:715] (5/8) Epoch 19, batch 350, loss[loss=0.1385, simple_loss=0.2047, pruned_loss=0.03616, over 4747.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 805475.43 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:11:43,717 INFO [train.py:715] (5/8) Epoch 19, batch 400, loss[loss=0.1439, simple_loss=0.213, pruned_loss=0.0374, over 4810.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02886, over 841599.47 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:12:24,045 INFO [train.py:715] (5/8) Epoch 19, batch 450, loss[loss=0.1061, simple_loss=0.1762, pruned_loss=0.01799, over 4800.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02859, over 870222.40 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:13:04,619 INFO [train.py:715] (5/8) Epoch 19, batch 500, loss[loss=0.1268, simple_loss=0.205, pruned_loss=0.02427, over 4913.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02886, over 892429.87 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:13:44,280 INFO [train.py:715] (5/8) Epoch 19, batch 550, loss[loss=0.111, simple_loss=0.1822, pruned_loss=0.01988, over 4799.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02899, over 910187.53 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:14:24,234 INFO [train.py:715] (5/8) Epoch 19, batch 600, loss[loss=0.1471, simple_loss=0.2025, pruned_loss=0.04586, over 4766.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02928, over 923738.73 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:15:04,545 INFO [train.py:715] (5/8) Epoch 19, batch 650, loss[loss=0.1381, simple_loss=0.2009, pruned_loss=0.03768, over 4844.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02937, over 933912.72 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:15:44,873 INFO [train.py:715] (5/8) Epoch 19, batch 700, loss[loss=0.1263, simple_loss=0.1992, pruned_loss=0.02672, over 4964.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 942414.74 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:16:24,133 INFO [train.py:715] (5/8) Epoch 19, batch 750, loss[loss=0.1302, simple_loss=0.206, pruned_loss=0.0272, over 4825.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02916, over 948609.30 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:17:03,938 INFO [train.py:715] (5/8) Epoch 19, batch 800, loss[loss=0.1194, simple_loss=0.1912, pruned_loss=0.02378, over 4835.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02906, over 953258.64 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:17:44,201 INFO [train.py:715] (5/8) Epoch 19, batch 850, loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03596, over 4833.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02925, over 957167.54 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:18:24,382 INFO [train.py:715] (5/8) Epoch 19, batch 900, loss[loss=0.1235, simple_loss=0.2045, pruned_loss=0.02122, over 4786.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.02931, over 960447.79 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:19:03,893 INFO [train.py:715] (5/8) Epoch 19, batch 950, loss[loss=0.1004, simple_loss=0.1808, pruned_loss=0.01, over 4761.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02917, over 963832.38 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:19:43,251 INFO [train.py:715] (5/8) Epoch 19, batch 1000, loss[loss=0.1208, simple_loss=0.1948, pruned_loss=0.02342, over 4801.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02898, over 965289.36 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:20:23,192 INFO [train.py:715] (5/8) Epoch 19, batch 1050, loss[loss=0.1504, simple_loss=0.2287, pruned_loss=0.03604, over 4983.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 967535.25 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:21:02,192 INFO [train.py:715] (5/8) Epoch 19, batch 1100, loss[loss=0.1519, simple_loss=0.2214, pruned_loss=0.04118, over 4880.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 969062.88 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 13:21:42,016 INFO [train.py:715] (5/8) Epoch 19, batch 1150, loss[loss=0.1138, simple_loss=0.1869, pruned_loss=0.02031, over 4982.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02936, over 970413.46 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:22:21,961 INFO [train.py:715] (5/8) Epoch 19, batch 1200, loss[loss=0.1329, simple_loss=0.2093, pruned_loss=0.02822, over 4946.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02864, over 970812.14 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:23:01,716 INFO [train.py:715] (5/8) Epoch 19, batch 1250, loss[loss=0.1257, simple_loss=0.1966, pruned_loss=0.02741, over 4838.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02888, over 971771.23 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:23:41,057 INFO [train.py:715] (5/8) Epoch 19, batch 1300, loss[loss=0.1539, simple_loss=0.2211, pruned_loss=0.04341, over 4841.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02902, over 972157.21 frames.], batch size: 34, lr: 1.18e-04
2022-05-09 13:24:20,595 INFO [train.py:715] (5/8) Epoch 19, batch 1350, loss[loss=0.1516, simple_loss=0.2181, pruned_loss=0.04255, over 4898.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.0291, over 972815.20 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:25:00,618 INFO [train.py:715] (5/8) Epoch 19, batch 1400, loss[loss=0.1106, simple_loss=0.1729, pruned_loss=0.02415, over 4742.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.029, over 973144.85 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 13:25:39,918 INFO [train.py:715] (5/8) Epoch 19, batch 1450, loss[loss=0.1285, simple_loss=0.2087, pruned_loss=0.02421, over 4817.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02877, over 973297.28 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:26:20,232 INFO [train.py:715] (5/8) Epoch 19, batch 1500, loss[loss=0.123, simple_loss=0.1991, pruned_loss=0.02349, over 4795.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02906, over 973160.42 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 13:27:00,284 INFO [train.py:715] (5/8) Epoch 19, batch 1550, loss[loss=0.1506, simple_loss=0.2331, pruned_loss=0.03401, over 4940.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 972509.29 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:27:40,369 INFO [train.py:715] (5/8) Epoch 19, batch 1600, loss[loss=0.1431, simple_loss=0.211, pruned_loss=0.03754, over 4982.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.0286, over 972835.52 frames.], batch size: 33, lr: 1.18e-04
2022-05-09 13:28:19,706 INFO [train.py:715] (5/8) Epoch 19, batch 1650, loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03558, over 4825.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02873, over 972438.35 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 13:28:59,070 INFO [train.py:715] (5/8) Epoch 19, batch 1700, loss[loss=0.133, simple_loss=0.2065, pruned_loss=0.02978, over 4817.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02906, over 973165.79 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:29:39,055 INFO [train.py:715] (5/8) Epoch 19, batch 1750, loss[loss=0.1409, simple_loss=0.2171, pruned_loss=0.03231, over 4725.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02912, over 972629.37 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:30:18,168 INFO [train.py:715] (5/8) Epoch 19, batch 1800, loss[loss=0.1444, simple_loss=0.2154, pruned_loss=0.03677, over 4927.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02908, over 972446.37 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:30:57,611 INFO [train.py:715] (5/8) Epoch 19, batch 1850, loss[loss=0.1114, simple_loss=0.1904, pruned_loss=0.01621, over 4902.00 frames.], tot_loss[loss=0.1322, simple_loss=0.206, pruned_loss=0.02915, over 972604.88 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 13:31:36,857 INFO [train.py:715] (5/8) Epoch 19, batch 1900, loss[loss=0.152, simple_loss=0.2107, pruned_loss=0.04666, over 4814.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02928, over 972907.73 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:32:16,777 INFO [train.py:715] (5/8) Epoch 19, batch 1950, loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03281, over 4788.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2061, pruned_loss=0.0294, over 973331.13 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:32:55,074 INFO [train.py:715] (5/8) Epoch 19, batch 2000, loss[loss=0.1422, simple_loss=0.2159, pruned_loss=0.03427, over 4911.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02888, over 973510.39 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:33:34,210 INFO [train.py:715] (5/8) Epoch 19, batch 2050, loss[loss=0.1242, simple_loss=0.1915, pruned_loss=0.02842, over 4841.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02956, over 973525.86 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 13:34:13,314 INFO [train.py:715] (5/8) Epoch 19, batch 2100, loss[loss=0.1273, simple_loss=0.1989, pruned_loss=0.02791, over 4974.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 973342.31 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:34:52,132 INFO [train.py:715] (5/8) Epoch 19, batch 2150, loss[loss=0.1343, simple_loss=0.2112, pruned_loss=0.0287, over 4856.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 971324.81 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 13:35:31,126 INFO [train.py:715] (5/8) Epoch 19, batch 2200, loss[loss=0.1138, simple_loss=0.1842, pruned_loss=0.02171, over 4957.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02924, over 972190.28 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:36:09,823 INFO [train.py:715] (5/8) Epoch 19, batch 2250, loss[loss=0.1692, simple_loss=0.2409, pruned_loss=0.04876, over 4897.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02909, over 972665.98 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:36:49,414 INFO [train.py:715] (5/8) Epoch 19, batch 2300, loss[loss=0.1222, simple_loss=0.2013, pruned_loss=0.0216, over 4776.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02901, over 971834.90 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:37:28,005 INFO [train.py:715] (5/8) Epoch 19, batch 2350, loss[loss=0.1229, simple_loss=0.1926, pruned_loss=0.02653, over 4827.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02869, over 971313.30 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 13:38:07,163 INFO [train.py:715] (5/8) Epoch 19, batch 2400, loss[loss=0.1251, simple_loss=0.1964, pruned_loss=0.02688, over 4935.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2054, pruned_loss=0.02875, over 971676.07 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:38:46,612 INFO [train.py:715] (5/8) Epoch 19, batch 2450, loss[loss=0.1125, simple_loss=0.1933, pruned_loss=0.01582, over 4745.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2054, pruned_loss=0.02879, over 971490.80 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:39:25,448 INFO [train.py:715] (5/8) Epoch 19, batch 2500, loss[loss=0.12, simple_loss=0.1874, pruned_loss=0.02632, over 4818.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02849, over 971576.43 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 13:40:04,475 INFO [train.py:715] (5/8) Epoch 19, batch 2550, loss[loss=0.1175, simple_loss=0.1888, pruned_loss=0.0231, over 4828.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02802, over 971214.91 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:40:44,007 INFO [train.py:715] (5/8) Epoch 19, batch 2600, loss[loss=0.13, simple_loss=0.2053, pruned_loss=0.02739, over 4834.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02828, over 970778.46 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:41:26,473 INFO [train.py:715] (5/8) Epoch 19, batch 2650, loss[loss=0.1588, simple_loss=0.2445, pruned_loss=0.03652, over 4844.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02809, over 972367.33 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:42:05,377 INFO [train.py:715] (5/8) Epoch 19, batch 2700, loss[loss=0.1212, simple_loss=0.1987, pruned_loss=0.02192, over 4879.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02845, over 972284.28 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:42:44,050 INFO [train.py:715] (5/8) Epoch 19, batch 2750, loss[loss=0.1625, simple_loss=0.2342, pruned_loss=0.0454, over 4971.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.0284, over 972672.25 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:43:23,786 INFO [train.py:715] (5/8) Epoch 19, batch 2800, loss[loss=0.1376, simple_loss=0.2181, pruned_loss=0.02856, over 4814.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.02788, over 972309.33 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 13:44:03,072 INFO [train.py:715] (5/8) Epoch 19, batch 2850, loss[loss=0.1492, simple_loss=0.2172, pruned_loss=0.04063, over 4843.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02799, over 971934.22 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:44:42,003 INFO [train.py:715] (5/8) Epoch 19, batch 2900, loss[loss=0.1448, simple_loss=0.2217, pruned_loss=0.03397, over 4924.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02795, over 972441.48 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 13:45:20,759 INFO [train.py:715] (5/8) Epoch 19, batch 2950, loss[loss=0.118, simple_loss=0.195, pruned_loss=0.0205, over 4775.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02796, over 972600.79 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:46:00,073 INFO [train.py:715] (5/8) Epoch 19, batch 3000, loss[loss=0.1265, simple_loss=0.2075, pruned_loss=0.02272, over 4801.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02838, over 971786.42 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:46:00,074 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 13:46:10,050 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01062, over 914524.00 frames.
2022-05-09 13:46:50,338 INFO [train.py:715] (5/8) Epoch 19, batch 3050, loss[loss=0.1181, simple_loss=0.1894, pruned_loss=0.02336, over 4743.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02915, over 971338.80 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:47:29,688 INFO [train.py:715] (5/8) Epoch 19, batch 3100, loss[loss=0.1578, simple_loss=0.2321, pruned_loss=0.04175, over 4754.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.0288, over 971042.98 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:48:08,829 INFO [train.py:715] (5/8) Epoch 19, batch 3150, loss[loss=0.1377, simple_loss=0.2054, pruned_loss=0.035, over 4777.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 970666.20 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:48:48,668 INFO [train.py:715] (5/8) Epoch 19, batch 3200, loss[loss=0.1317, simple_loss=0.1991, pruned_loss=0.03218, over 4911.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02944, over 970916.46 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:49:27,687 INFO [train.py:715] (5/8) Epoch 19, batch 3250, loss[loss=0.1318, simple_loss=0.2041, pruned_loss=0.02973, over 4900.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02932, over 970829.69 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:50:07,130 INFO [train.py:715] (5/8) Epoch 19, batch 3300, loss[loss=0.1518, simple_loss=0.2151, pruned_loss=0.04428, over 4746.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02949, over 971340.89 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:50:46,361 INFO [train.py:715] (5/8) Epoch 19, batch 3350, loss[loss=0.1531, simple_loss=0.2172, pruned_loss=0.04456, over 4880.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02937, over 971791.24 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 13:51:26,504 INFO [train.py:715] (5/8) Epoch 19, batch 3400, loss[loss=0.1198, simple_loss=0.1943, pruned_loss=0.02261, over 4775.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02879, over 972238.79 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:52:05,355 INFO [train.py:715] (5/8) Epoch 19, batch 3450, loss[loss=0.1389, simple_loss=0.2105, pruned_loss=0.0336, over 4744.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2047, pruned_loss=0.02849, over 971467.07 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:52:44,612 INFO [train.py:715] (5/8) Epoch 19, batch 3500, loss[loss=0.1254, simple_loss=0.1954, pruned_loss=0.02767, over 4760.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02867, over 971495.05 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:53:23,731 INFO [train.py:715] (5/8) Epoch 19, batch 3550, loss[loss=0.1378, simple_loss=0.215, pruned_loss=0.03033, over 4776.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02864, over 972362.46 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:54:02,618 INFO [train.py:715] (5/8) Epoch 19, batch 3600, loss[loss=0.1282, simple_loss=0.1971, pruned_loss=0.02964, over 4780.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02837, over 972769.23 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:54:42,248 INFO [train.py:715] (5/8) Epoch 19, batch 3650, loss[loss=0.1291, simple_loss=0.2084, pruned_loss=0.02495, over 4888.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02825, over 972753.11 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 13:55:21,393 INFO [train.py:715] (5/8) Epoch 19, batch 3700, loss[loss=0.1071, simple_loss=0.1846, pruned_loss=0.01476, over 4737.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02808, over 972824.02 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:56:01,850 INFO [train.py:715] (5/8) Epoch 19, batch 3750, loss[loss=0.1284, simple_loss=0.1998, pruned_loss=0.02853, over 4756.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02815, over 973394.79 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:56:40,834 INFO [train.py:715] (5/8) Epoch 19, batch 3800, loss[loss=0.1796, simple_loss=0.2454, pruned_loss=0.05693, over 4947.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 973557.61 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:57:19,813 INFO [train.py:715] (5/8) Epoch 19, batch 3850, loss[loss=0.1302, simple_loss=0.1982, pruned_loss=0.0311, over 4919.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02858, over 973262.49 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:57:59,510 INFO [train.py:715] (5/8) Epoch 19, batch 3900, loss[loss=0.1399, simple_loss=0.2154, pruned_loss=0.03217, over 4882.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02854, over 973453.88 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 13:58:38,559 INFO [train.py:715] (5/8) Epoch 19, batch 3950, loss[loss=0.1498, simple_loss=0.216, pruned_loss=0.04175, over 4756.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2078, pruned_loss=0.02872, over 973887.78 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:59:17,192 INFO [train.py:715] (5/8) Epoch 19, batch 4000, loss[loss=0.1117, simple_loss=0.1862, pruned_loss=0.01867, over 4785.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02857, over 973101.84 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:59:56,645 INFO [train.py:715] (5/8) Epoch 19, batch 4050, loss[loss=0.1504, simple_loss=0.2289, pruned_loss=0.03597, over 4701.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.02863, over 972909.64 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:00:36,776 INFO [train.py:715] (5/8) Epoch 19, batch 4100, loss[loss=0.1147, simple_loss=0.1993, pruned_loss=0.01506, over 4806.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02859, over 972602.35 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:01:15,964 INFO [train.py:715] (5/8) Epoch 19, batch 4150, loss[loss=0.1008, simple_loss=0.1714, pruned_loss=0.01517, over 4787.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.02828, over 972852.27 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:01:54,738 INFO [train.py:715] (5/8) Epoch 19, batch 4200, loss[loss=0.1298, simple_loss=0.2054, pruned_loss=0.0271, over 4813.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2055, pruned_loss=0.02766, over 973181.73 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 14:02:33,999 INFO [train.py:715] (5/8) Epoch 19, batch 4250, loss[loss=0.1413, simple_loss=0.2041, pruned_loss=0.03926, over 4825.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02792, over 972903.73 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 14:03:13,063 INFO [train.py:715] (5/8) Epoch 19, batch 4300, loss[loss=0.1296, simple_loss=0.2063, pruned_loss=0.0264, over 4880.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02856, over 973006.67 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:03:52,546 INFO [train.py:715] (5/8) Epoch 19, batch 4350, loss[loss=0.1367, simple_loss=0.2145, pruned_loss=0.02946, over 4930.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02835, over 973299.51 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:04:31,612 INFO [train.py:715] (5/8) Epoch 19, batch 4400, loss[loss=0.1287, simple_loss=0.2023, pruned_loss=0.02758, over 4905.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02839, over 973061.67 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:05:11,663 INFO [train.py:715] (5/8) Epoch 19, batch 4450, loss[loss=0.09447, simple_loss=0.1655, pruned_loss=0.01172, over 4818.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.0281, over 972696.43 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:05:50,508 INFO [train.py:715] (5/8) Epoch 19, batch 4500, loss[loss=0.1174, simple_loss=0.1931, pruned_loss=0.02088, over 4949.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02832, over 972348.57 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:06:29,203 INFO [train.py:715] (5/8) Epoch 19, batch 4550, loss[loss=0.1393, simple_loss=0.2248, pruned_loss=0.02689, over 4791.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02822, over 973140.75 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:07:08,890 INFO [train.py:715] (5/8) Epoch 19, batch 4600, loss[loss=0.1094, simple_loss=0.1899, pruned_loss=0.01446, over 4942.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02828, over 973208.79 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:07:48,134 INFO [train.py:715] (5/8) Epoch 19, batch 4650, loss[loss=0.1642, simple_loss=0.236, pruned_loss=0.04625, over 4794.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02856, over 972568.18 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:08:27,121 INFO [train.py:715] (5/8) Epoch 19, batch 4700, loss[loss=0.122, simple_loss=0.2015, pruned_loss=0.02127, over 4839.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02864, over 971641.59 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 14:09:06,334 INFO [train.py:715] (5/8) Epoch 19, batch 4750, loss[loss=0.1523, simple_loss=0.2268, pruned_loss=0.03887, over 4890.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02855, over 972017.61 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:09:46,295 INFO [train.py:715] (5/8) Epoch 19, batch 4800, loss[loss=0.1374, simple_loss=0.2148, pruned_loss=0.02999, over 4984.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02866, over 971963.91 frames.], batch size: 40, lr: 1.18e-04
2022-05-09 14:10:25,677 INFO [train.py:715] (5/8) Epoch 19, batch 4850, loss[loss=0.1393, simple_loss=0.2154, pruned_loss=0.03163, over 4808.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02843, over 972065.83 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:11:04,335 INFO [train.py:715] (5/8) Epoch 19, batch 4900, loss[loss=0.1416, simple_loss=0.2164, pruned_loss=0.03339, over 4900.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02806, over 972718.90 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:11:44,090 INFO [train.py:715] (5/8) Epoch 19, batch 4950, loss[loss=0.1408, simple_loss=0.2093, pruned_loss=0.03616, over 4983.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.0287, over 973681.61 frames.], batch size: 28, lr: 1.18e-04
2022-05-09 14:12:23,740 INFO [train.py:715] (5/8) Epoch 19, batch 5000, loss[loss=0.1224, simple_loss=0.199, pruned_loss=0.02296, over 4933.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.0286, over 973231.32 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 14:13:02,751 INFO [train.py:715] (5/8) Epoch 19, batch 5050, loss[loss=0.119, simple_loss=0.1919, pruned_loss=0.02309, over 4802.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02854, over 973241.15 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:13:41,115 INFO [train.py:715] (5/8) Epoch 19, batch 5100, loss[loss=0.1064, simple_loss=0.1753, pruned_loss=0.01872, over 4839.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02778, over 973677.12 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 14:14:21,159 INFO [train.py:715] (5/8) Epoch 19, batch 5150, loss[loss=0.1138, simple_loss=0.1916, pruned_loss=0.01799, over 4921.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02815, over 972957.34 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 14:15:00,186 INFO [train.py:715] (5/8) Epoch 19, batch 5200, loss[loss=0.1275, simple_loss=0.2041, pruned_loss=0.0254, over 4700.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02818, over 972003.40 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:15:38,851 INFO [train.py:715] (5/8) Epoch 19, batch 5250, loss[loss=0.1337, simple_loss=0.215, pruned_loss=0.02619, over 4835.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02808, over 971367.46 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:16:18,533 INFO [train.py:715] (5/8) Epoch 19, batch 5300, loss[loss=0.1199, simple_loss=0.1964, pruned_loss=0.02166, over 4879.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2043, pruned_loss=0.02759, over 971981.33 frames.], batch size: 38, lr: 1.18e-04
2022-05-09 14:16:58,482 INFO [train.py:715] (5/8) Epoch 19, batch 5350, loss[loss=0.1405, simple_loss=0.2152, pruned_loss=0.03286, over 4979.00 frames.], tot_loss[loss=0.13, simple_loss=0.2047, pruned_loss=0.02767, over 972938.01 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:17:38,564 INFO [train.py:715] (5/8) Epoch 19, batch 5400, loss[loss=0.1237, simple_loss=0.2077, pruned_loss=0.01988, over 4972.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2049, pruned_loss=0.02748, over 972917.51 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:18:17,823 INFO [train.py:715] (5/8) Epoch 19, batch 5450, loss[loss=0.1066, simple_loss=0.182, pruned_loss=0.01555, over 4796.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2044, pruned_loss=0.02743, over 972921.55 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:18:58,016 INFO [train.py:715] (5/8) Epoch 19, batch 5500, loss[loss=0.1466, simple_loss=0.214, pruned_loss=0.03955, over 4846.00 frames.], tot_loss[loss=0.13, simple_loss=0.2045, pruned_loss=0.0277, over 972364.98 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:19:37,204 INFO [train.py:715] (5/8) Epoch 19, batch 5550, loss[loss=0.1129, simple_loss=0.187, pruned_loss=0.01937, over 4817.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02783, over 972172.74 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 14:20:16,792 INFO [train.py:715] (5/8) Epoch 19, batch 5600, loss[loss=0.1301, simple_loss=0.2149, pruned_loss=0.02259, over 4935.00 frames.], tot_loss[loss=0.1303, simple_loss=0.205, pruned_loss=0.02779, over 972307.53 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:20:56,102 INFO [train.py:715] (5/8) Epoch 19, batch 5650, loss[loss=0.1606, simple_loss=0.2128, pruned_loss=0.05421, over 4824.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02793, over 972227.87 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 14:21:35,826 INFO [train.py:715] (5/8) Epoch 19, batch 5700, loss[loss=0.1305, simple_loss=0.2071, pruned_loss=0.02688, over 4967.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.02769, over 971895.19 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:22:15,333 INFO [train.py:715] (5/8) Epoch 19, batch 5750, loss[loss=0.1215, simple_loss=0.204, pruned_loss=0.01952, over 4779.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02821, over 972278.13 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:22:53,917 INFO [train.py:715] (5/8) Epoch 19, batch 5800, loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 4757.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02809, over 971664.71 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:23:33,192 INFO [train.py:715] (5/8) Epoch 19, batch 5850, loss[loss=0.1294, simple_loss=0.2161, pruned_loss=0.02136, over 4902.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02784, over 972027.81 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:24:11,657 INFO [train.py:715] (5/8) Epoch 19, batch 5900, loss[loss=0.1344, simple_loss=0.2134, pruned_loss=0.0277, over 4757.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02815, over 972090.05 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:24:51,079 INFO [train.py:715] (5/8) Epoch 19, batch 5950, loss[loss=0.1086, simple_loss=0.1864, pruned_loss=0.0154, over 4764.00 frames.], tot_loss[loss=0.1301, simple_loss=0.205, pruned_loss=0.02761, over 971888.34 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:25:30,281 INFO [train.py:715] (5/8) Epoch 19, batch 6000, loss[loss=0.1201, simple_loss=0.2011, pruned_loss=0.01961, over 4877.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02801, over 971658.74 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:25:30,282 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 14:25:40,196 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 14:26:19,488 INFO [train.py:715] (5/8) Epoch 19, batch 6050, loss[loss=0.1038, simple_loss=0.1764, pruned_loss=0.01565, over 4801.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2051, pruned_loss=0.02755, over 971601.91 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:26:58,345 INFO [train.py:715] (5/8) Epoch 19, batch 6100, loss[loss=0.1296, simple_loss=0.207, pruned_loss=0.02614, over 4907.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2054, pruned_loss=0.02751, over 971277.42 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:27:37,412 INFO [train.py:715] (5/8) Epoch 19, batch 6150, loss[loss=0.1471, simple_loss=0.2129, pruned_loss=0.0407, over 4782.00 frames.], tot_loss[loss=0.131, simple_loss=0.2061, pruned_loss=0.02791, over 971714.16 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:28:15,611 INFO [train.py:715] (5/8) Epoch 19, batch 6200, loss[loss=0.1159, simple_loss=0.1988, pruned_loss=0.0165, over 4943.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.02788, over 971777.11 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:28:55,857 INFO [train.py:715] (5/8) Epoch 19, batch 6250, loss[loss=0.137, simple_loss=0.2171, pruned_loss=0.0284, over 4940.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.0279, over 971976.98 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:29:35,037 INFO [train.py:715] (5/8) Epoch 19, batch 6300, loss[loss=0.1209, simple_loss=0.1792, pruned_loss=0.03124, over 4799.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 971406.12 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:30:14,721 INFO [train.py:715] (5/8) Epoch 19, batch 6350, loss[loss=0.1339, simple_loss=0.1977, pruned_loss=0.03504, over 4855.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02838, over 971628.76 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:30:54,199 INFO [train.py:715] (5/8) Epoch 19, batch 6400, loss[loss=0.132, simple_loss=0.202, pruned_loss=0.03097, over 4813.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 971916.57 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:31:33,476 INFO [train.py:715] (5/8) Epoch 19, batch 6450, loss[loss=0.1599, simple_loss=0.2233, pruned_loss=0.04827, over 4876.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02866, over 971337.52 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:32:12,981 INFO [train.py:715] (5/8) Epoch 19, batch 6500, loss[loss=0.1411, simple_loss=0.2092, pruned_loss=0.03652, over 4903.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02858, over 971591.05 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:32:51,556 INFO [train.py:715] (5/8) Epoch 19, batch 6550, loss[loss=0.1176, simple_loss=0.1879, pruned_loss=0.02369, over 4958.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.0286, over 972019.27 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:33:31,044 INFO [train.py:715] (5/8) Epoch 19, batch 6600, loss[loss=0.1142, simple_loss=0.1902, pruned_loss=0.01911, over 4840.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02896, over 971631.95 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:34:10,194 INFO [train.py:715] (5/8) Epoch 19, batch 6650, loss[loss=0.1333, simple_loss=0.2018, pruned_loss=0.03238, over 4855.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02866, over 972392.13 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:34:48,935 INFO [train.py:715] (5/8) Epoch 19, batch 6700, loss[loss=0.1202, simple_loss=0.2026, pruned_loss=0.01894, over 4859.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 972695.89 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:35:28,065 INFO [train.py:715] (5/8) Epoch 19, batch 6750, loss[loss=0.1253, simple_loss=0.1977, pruned_loss=0.0264, over 4757.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02843, over 972209.86 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:36:07,538 INFO [train.py:715] (5/8) Epoch 19, batch 6800, loss[loss=0.1237, simple_loss=0.1886, pruned_loss=0.02941, over 4735.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02876, over 971723.95 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:36:46,928 INFO [train.py:715] (5/8) Epoch 19, batch 6850, loss[loss=0.1921, simple_loss=0.2591, pruned_loss=0.06257, over 4836.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02886, over 972175.07 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:37:25,086 INFO [train.py:715] (5/8) Epoch 19, batch 6900, loss[loss=0.1156, simple_loss=0.1985, pruned_loss=0.01639, over 4947.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02885, over 972782.41 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:38:04,130 INFO [train.py:715] (5/8) Epoch 19, batch 6950, loss[loss=0.1147, simple_loss=0.1874, pruned_loss=0.02103, over 4744.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 972595.54 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:38:43,598 INFO [train.py:715] (5/8) Epoch 19, batch 7000, loss[loss=0.1618, simple_loss=0.2323, pruned_loss=0.04563, over 4877.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02911, over 972934.01 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:39:22,851 INFO [train.py:715] (5/8) Epoch 19, batch 7050, loss[loss=0.1579, simple_loss=0.2253, pruned_loss=0.04519, over 4971.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02883, over 971754.18 frames.], batch size: 31, lr: 1.18e-04
2022-05-09 14:40:02,433 INFO [train.py:715] (5/8) Epoch 19, batch 7100, loss[loss=0.1391, simple_loss=0.2159, pruned_loss=0.03112, over 4767.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02911, over 972232.93 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:40:42,072 INFO [train.py:715] (5/8) Epoch 19, batch 7150, loss[loss=0.1049, simple_loss=0.1832, pruned_loss=0.01335, over 4892.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.029, over 972199.36 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:41:20,978 INFO [train.py:715] (5/8) Epoch 19, batch 7200, loss[loss=0.1372, simple_loss=0.217, pruned_loss=0.02868, over 4946.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02872, over 972754.90 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:41:59,731 INFO [train.py:715] (5/8) Epoch 19, batch 7250, loss[loss=0.1581, simple_loss=0.2256, pruned_loss=0.04531, over 4962.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02867, over 972966.05 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:42:39,093 INFO [train.py:715] (5/8) Epoch 19, batch 7300, loss[loss=0.1098, simple_loss=0.1804, pruned_loss=0.01958, over 4739.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02841, over 972315.26 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:43:18,256 INFO [train.py:715] (5/8) Epoch 19, batch 7350, loss[loss=0.131, simple_loss=0.2107, pruned_loss=0.02571, over 4764.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2072, pruned_loss=0.0283, over 971877.67 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:43:57,160 INFO [train.py:715] (5/8) Epoch 19, batch 7400, loss[loss=0.1345, simple_loss=0.228, pruned_loss=0.02051, over 4795.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.02835, over 971240.44 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:44:37,623 INFO [train.py:715] (5/8) Epoch 19, batch 7450, loss[loss=0.1203, simple_loss=0.2032, pruned_loss=0.01875, over 4908.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2069, pruned_loss=0.02813, over 971103.55 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:45:17,477 INFO [train.py:715] (5/8) Epoch 19, batch 7500, loss[loss=0.1374, simple_loss=0.218, pruned_loss=0.02838, over 4923.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2069, pruned_loss=0.02846, over 971850.08 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:45:56,702 INFO [train.py:715] (5/8) Epoch 19, batch 7550, loss[loss=0.1232, simple_loss=0.1954, pruned_loss=0.02548, over 4827.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02837, over 971858.22 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 14:46:36,055 INFO [train.py:715] (5/8) Epoch 19, batch 7600, loss[loss=0.1245, simple_loss=0.2, pruned_loss=0.02448, over 4749.00 frames.], tot_loss[loss=0.132, simple_loss=0.2069, pruned_loss=0.0285, over 971145.39 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:47:16,833 INFO [train.py:715] (5/8) Epoch 19, batch 7650, loss[loss=0.1155, simple_loss=0.1858, pruned_loss=0.02265, over 4938.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02847, over 972434.59 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:47:56,150 INFO [train.py:715] (5/8) Epoch 19, batch 7700, loss[loss=0.1196, simple_loss=0.1995, pruned_loss=0.01988, over 4835.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.0281, over 972092.37 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 14:48:34,960 INFO [train.py:715] (5/8) Epoch 19, batch 7750, loss[loss=0.1331, simple_loss=0.2038, pruned_loss=0.03123, over 4724.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.02864, over 970581.24 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:49:14,657 INFO [train.py:715] (5/8) Epoch 19, batch 7800, loss[loss=0.1181, simple_loss=0.1947, pruned_loss=0.02076, over 4923.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2074, pruned_loss=0.02846, over 970807.56 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:49:54,091 INFO [train.py:715] (5/8) Epoch 19, batch 7850, loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02972, over 4819.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.0284, over 971062.97 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:50:33,358 INFO [train.py:715] (5/8) Epoch 19, batch 7900, loss[loss=0.1384, simple_loss=0.2126, pruned_loss=0.03207, over 4867.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.02833, over 971581.89 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:51:11,760 INFO [train.py:715] (5/8) Epoch 19, batch 7950, loss[loss=0.1437, simple_loss=0.2217, pruned_loss=0.03284, over 4824.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.02868, over 972028.00 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:51:51,086 INFO [train.py:715] (5/8) Epoch 19, batch 8000, loss[loss=0.1433, simple_loss=0.2118, pruned_loss=0.03739, over 4975.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2067, pruned_loss=0.0283, over 972024.25 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:52:30,290 INFO [train.py:715] (5/8) Epoch 19, batch 8050, loss[loss=0.1279, simple_loss=0.2103, pruned_loss=0.02278, over 4922.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2068, pruned_loss=0.02824, over 971784.43 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 14:53:08,822 INFO [train.py:715] (5/8) Epoch 19, batch 8100, loss[loss=0.09236, simple_loss=0.164, pruned_loss=0.01038, over 4965.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02836, over 971857.09 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:53:48,274 INFO [train.py:715] (5/8) Epoch 19, batch 8150, loss[loss=0.13, simple_loss=0.2153, pruned_loss=0.02235, over 4785.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2067, pruned_loss=0.02814, over 971666.33 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:54:27,921 INFO [train.py:715] (5/8) Epoch 19, batch 8200, loss[loss=0.1262, simple_loss=0.2032, pruned_loss=0.02459, over 4748.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02804, over 971440.93 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:55:06,906 INFO [train.py:715] (5/8) Epoch 19, batch 8250, loss[loss=0.1196, simple_loss=0.1917, pruned_loss=0.02378, over 4975.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02814, over 971620.41 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:55:45,534 INFO [train.py:715] (5/8) Epoch 19, batch 8300, loss[loss=0.1435, simple_loss=0.2103, pruned_loss=0.03841, over 4865.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02813, over 971565.73 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:56:25,222 INFO [train.py:715] (5/8) Epoch 19, batch 8350, loss[loss=0.136, simple_loss=0.2162, pruned_loss=0.02786, over 4785.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02805, over 971386.30 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:57:04,445 INFO [train.py:715] (5/8) Epoch 19, batch 8400, loss[loss=0.1279, simple_loss=0.2049, pruned_loss=0.02548, over 4813.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2046, pruned_loss=0.02826, over 971137.12 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:57:43,452 INFO [train.py:715] (5/8) Epoch 19, batch 8450, loss[loss=0.1191, simple_loss=0.1828, pruned_loss=0.02772, over 4798.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.0286, over 971203.23 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:58:23,230 INFO [train.py:715] (5/8) Epoch 19, batch 8500, loss[loss=0.1396, simple_loss=0.2173, pruned_loss=0.03095, over 4980.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02872, over 970856.28 frames.], batch size: 31, lr: 1.18e-04
2022-05-09 14:59:01,924 INFO [train.py:715] (5/8) Epoch 19, batch 8550, loss[loss=0.1237, simple_loss=0.1898, pruned_loss=0.02877, over 4690.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02856, over 971520.28 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:59:41,018 INFO [train.py:715] (5/8) Epoch 19, batch 8600, loss[loss=0.1437, simple_loss=0.2223, pruned_loss=0.03256, over 4954.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.0284, over 971018.57 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 15:00:20,522 INFO [train.py:715] (5/8) Epoch 19, batch 8650, loss[loss=0.1185, simple_loss=0.1961, pruned_loss=0.02049, over 4797.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02829, over 971563.96 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 15:01:00,040 INFO [train.py:715] (5/8) Epoch 19, batch 8700, loss[loss=0.1125, simple_loss=0.1826, pruned_loss=0.02117, over 4804.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2039, pruned_loss=0.02773, over 971806.91 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 15:01:39,199 INFO [train.py:715] (5/8) Epoch 19, batch 8750, loss[loss=0.131, simple_loss=0.2104, pruned_loss=0.02577, over 4828.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2045, pruned_loss=0.02779, over 971505.52 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:02:17,955 INFO [train.py:715] (5/8) Epoch 19, batch 8800, loss[loss=0.1204, simple_loss=0.1977, pruned_loss=0.02156, over 4806.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02835, over 971426.28 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 15:02:57,606 INFO [train.py:715] (5/8) Epoch 19, batch 8850, loss[loss=0.1071, simple_loss=0.1822, pruned_loss=0.01596, over 4936.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.02817, over 971826.90 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 15:03:36,661 INFO [train.py:715] (5/8) Epoch 19, batch 8900, loss[loss=0.1151, simple_loss=0.1889, pruned_loss=0.02067, over 4818.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2044, pruned_loss=0.02786, over 972528.16 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 15:04:16,005 INFO [train.py:715] (5/8) Epoch 19, batch 8950, loss[loss=0.1194, simple_loss=0.1957, pruned_loss=0.02152, over 4793.00 frames.], tot_loss[loss=0.131, simple_loss=0.2051, pruned_loss=0.02842, over 972377.03 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 15:04:54,901 INFO [train.py:715] (5/8) Epoch 19, batch 9000, loss[loss=0.1438, simple_loss=0.2252, pruned_loss=0.03122, over 4921.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02865, over 971730.79 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:04:54,901 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 15:05:04,819 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1879, pruned_loss=0.01072, over 914524.00 frames.
2022-05-09 15:05:44,267 INFO [train.py:715] (5/8) Epoch 19, batch 9050, loss[loss=0.1331, simple_loss=0.2084, pruned_loss=0.02896, over 4985.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.0288, over 972368.50 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 15:06:23,987 INFO [train.py:715] (5/8) Epoch 19, batch 9100, loss[loss=0.1311, simple_loss=0.201, pruned_loss=0.03066, over 4773.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02833, over 972764.71 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:07:03,250 INFO [train.py:715] (5/8) Epoch 19, batch 9150, loss[loss=0.1481, simple_loss=0.2164, pruned_loss=0.0399, over 4893.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02833, over 972361.11 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 15:07:42,031 INFO [train.py:715] (5/8) Epoch 19, batch 9200, loss[loss=0.1414, simple_loss=0.2106, pruned_loss=0.03608, over 4835.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.0284, over 971784.67 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:08:21,754 INFO [train.py:715] (5/8) Epoch 19, batch 9250, loss[loss=0.1102, simple_loss=0.1911, pruned_loss=0.01463, over 4829.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02837, over 971733.25 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 15:09:00,949 INFO [train.py:715] (5/8) Epoch 19, batch 9300, loss[loss=0.1474, simple_loss=0.2233, pruned_loss=0.03575, over 4866.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02873, over 971938.57 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 15:09:39,863 INFO [train.py:715] (5/8) Epoch 19, batch 9350, loss[loss=0.1547, simple_loss=0.2279, pruned_loss=0.04077, over 4915.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02915, over 972914.53 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:10:19,953 INFO [train.py:715] (5/8) Epoch 19, batch 9400, loss[loss=0.1393, simple_loss=0.2076, pruned_loss=0.03548, over 4840.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02849, over 972774.80 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 15:11:00,059 INFO [train.py:715] (5/8) Epoch 19, batch 9450, loss[loss=0.1157, simple_loss=0.2021, pruned_loss=0.01462, over 4823.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02812, over 972061.37 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:11:38,882 INFO [train.py:715] (5/8) Epoch 19, batch 9500, loss[loss=0.1236, simple_loss=0.1937, pruned_loss=0.02677, over 4829.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02794, over 972389.10 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 15:12:18,093 INFO [train.py:715] (5/8) Epoch 19, batch 9550, loss[loss=0.1402, simple_loss=0.2006, pruned_loss=0.03993, over 4783.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02841, over 971539.32 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 15:12:57,472 INFO [train.py:715] (5/8) Epoch 19, batch 9600, loss[loss=0.1285, simple_loss=0.2054, pruned_loss=0.02583, over 4751.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02864, over 971541.01 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 15:13:36,648 INFO [train.py:715] (5/8) Epoch 19, batch 9650, loss[loss=0.1132, simple_loss=0.1943, pruned_loss=0.01603, over 4986.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02861, over 971724.08 frames.], batch size: 28, lr: 1.18e-04
2022-05-09 15:14:14,973 INFO [train.py:715] (5/8) Epoch 19, batch 9700, loss[loss=0.1352, simple_loss=0.2203, pruned_loss=0.025, over 4949.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02818, over 972259.63 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 15:14:54,703 INFO [train.py:715] (5/8) Epoch 19, batch 9750, loss[loss=0.1213, simple_loss=0.2012, pruned_loss=0.02072, over 4863.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02806, over 972442.41 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 15:15:34,782 INFO [train.py:715] (5/8) Epoch 19, batch 9800, loss[loss=0.1272, simple_loss=0.2011, pruned_loss=0.02661, over 4881.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02819, over 972908.77 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 15:16:14,505 INFO [train.py:715] (5/8) Epoch 19, batch 9850, loss[loss=0.1393, simple_loss=0.2206, pruned_loss=0.02899, over 4991.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02803, over 972841.95 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 15:16:53,380 INFO [train.py:715] (5/8) Epoch 19, batch 9900, loss[loss=0.1436, simple_loss=0.2105, pruned_loss=0.03829, over 4834.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02833, over 972682.67 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 15:17:33,332 INFO [train.py:715] (5/8) Epoch 19, batch 9950, loss[loss=0.1123, simple_loss=0.1935, pruned_loss=0.01557, over 4893.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02845, over 973052.75 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 15:18:12,860 INFO [train.py:715] (5/8) Epoch 19, batch 10000, loss[loss=0.1508, simple_loss=0.211, pruned_loss=0.04535, over 4968.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02856, over 973322.12 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:18:51,542 INFO [train.py:715] (5/8) Epoch 19, batch 10050, loss[loss=0.1223, simple_loss=0.1988, pruned_loss=0.02287, over 4709.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02855, over 973549.15 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:19:31,277 INFO [train.py:715] (5/8) Epoch 19, batch 10100, loss[loss=0.1286, simple_loss=0.2025, pruned_loss=0.02739, over 4968.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02885, over 972915.14 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 15:20:10,772 INFO [train.py:715] (5/8) Epoch 19, batch 10150, loss[loss=0.1179, simple_loss=0.1921, pruned_loss=0.02189, over 4948.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02899, over 973146.68 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:20:49,757 INFO [train.py:715] (5/8) Epoch 19, batch 10200, loss[loss=0.1304, simple_loss=0.22, pruned_loss=0.02043, over 4793.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02868, over 973507.76 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:21:29,136 INFO [train.py:715] (5/8) Epoch 19, batch 10250, loss[loss=0.1151, simple_loss=0.1943, pruned_loss=0.01798, over 4802.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 973244.85 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 15:22:09,265 INFO [train.py:715] (5/8) Epoch 19, batch 10300, loss[loss=0.1306, simple_loss=0.1996, pruned_loss=0.03075, over 4966.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02911, over 972454.26 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:22:48,847 INFO [train.py:715] (5/8) Epoch 19, batch 10350, loss[loss=0.123, simple_loss=0.195, pruned_loss=0.0255, over 4802.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02853, over 972493.31 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 15:23:27,532 INFO [train.py:715] (5/8) Epoch 19, batch 10400, loss[loss=0.1287, simple_loss=0.2038, pruned_loss=0.02685, over 4866.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02891, over 972104.23 frames.], batch size: 38, lr: 1.17e-04
2022-05-09 15:24:07,292 INFO [train.py:715] (5/8) Epoch 19, batch 10450, loss[loss=0.1283, simple_loss=0.1949, pruned_loss=0.03086, over 4808.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02854, over 971161.92 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:24:47,013 INFO [train.py:715] (5/8) Epoch 19, batch 10500, loss[loss=0.1435, simple_loss=0.2129, pruned_loss=0.03701, over 4953.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02899, over 971618.82 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 15:25:25,925 INFO [train.py:715] (5/8) Epoch 19, batch 10550, loss[loss=0.1475, simple_loss=0.2247, pruned_loss=0.03514, over 4776.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02906, over 971511.38 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:26:04,897 INFO [train.py:715] (5/8) Epoch 19, batch 10600, loss[loss=0.1482, simple_loss=0.2277, pruned_loss=0.03436, over 4758.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02837, over 971559.69 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 15:26:47,169 INFO [train.py:715] (5/8) Epoch 19, batch 10650, loss[loss=0.1205, simple_loss=0.1842, pruned_loss=0.02834, over 4962.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02802, over 971256.43 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:27:26,341 INFO [train.py:715] (5/8) Epoch 19, batch 10700, loss[loss=0.1207, simple_loss=0.2102, pruned_loss=0.01561, over 4749.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02813, over 972058.01 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:28:05,701 INFO [train.py:715] (5/8) Epoch 19, batch 10750, loss[loss=0.1375, simple_loss=0.2206, pruned_loss=0.02725, over 4747.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02818, over 972012.00 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 15:28:45,280 INFO [train.py:715] (5/8) Epoch 19, batch 10800, loss[loss=0.1379, simple_loss=0.2249, pruned_loss=0.02541, over 4933.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02807, over 972388.64 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:29:25,027 INFO [train.py:715] (5/8) Epoch 19, batch 10850, loss[loss=0.1383, simple_loss=0.218, pruned_loss=0.02928, over 4925.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.0284, over 972624.08 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:30:03,631 INFO [train.py:715] (5/8) Epoch 19, batch 10900, loss[loss=0.1157, simple_loss=0.197, pruned_loss=0.01721, over 4940.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02829, over 971934.67 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:30:42,649 INFO [train.py:715] (5/8) Epoch 19, batch 10950, loss[loss=0.134, simple_loss=0.2051, pruned_loss=0.03145, over 4868.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02809, over 972121.13 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 15:31:22,351 INFO [train.py:715] (5/8) Epoch 19, batch 11000, loss[loss=0.1485, simple_loss=0.2185, pruned_loss=0.03922, over 4971.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02794, over 973077.94 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 15:32:02,207 INFO [train.py:715] (5/8) Epoch 19, batch 11050, loss[loss=0.1073, simple_loss=0.1815, pruned_loss=0.01653, over 4964.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02786, over 973813.44 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:32:40,674 INFO [train.py:715] (5/8) Epoch 19, batch 11100, loss[loss=0.1286, simple_loss=0.1968, pruned_loss=0.03023, over 4773.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2057, pruned_loss=0.02799, over 973247.01 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:33:20,041 INFO [train.py:715] (5/8) Epoch 19, batch 11150, loss[loss=0.1315, simple_loss=0.2004, pruned_loss=0.03129, over 4920.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02795, over 972966.16 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:33:59,470 INFO [train.py:715] (5/8) Epoch 19, batch 11200, loss[loss=0.1226, simple_loss=0.1937, pruned_loss=0.02575, over 4786.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2042, pruned_loss=0.02765, over 973374.85 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:34:38,836 INFO [train.py:715] (5/8) Epoch 19, batch 11250, loss[loss=0.1031, simple_loss=0.1801, pruned_loss=0.01305, over 4730.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02774, over 971979.62 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 15:35:18,202 INFO [train.py:715] (5/8) Epoch 19, batch 11300, loss[loss=0.1293, simple_loss=0.2018, pruned_loss=0.02836, over 4982.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2042, pruned_loss=0.02798, over 972023.80 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:35:56,986 INFO [train.py:715] (5/8) Epoch 19, batch 11350, loss[loss=0.1347, simple_loss=0.2123, pruned_loss=0.02852, over 4882.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02828, over 972285.18 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 15:36:36,599 INFO [train.py:715] (5/8) Epoch 19, batch 11400, loss[loss=0.1388, simple_loss=0.2215, pruned_loss=0.02802, over 4924.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02815, over 971787.91 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:37:16,205 INFO [train.py:715] (5/8) Epoch 19, batch 11450, loss[loss=0.09871, simple_loss=0.1683, pruned_loss=0.01458, over 4777.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02808, over 972061.22 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:37:56,158 INFO [train.py:715] (5/8) Epoch 19, batch 11500, loss[loss=0.1309, simple_loss=0.2069, pruned_loss=0.02741, over 4774.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02811, over 972203.05 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:38:35,580 INFO [train.py:715] (5/8) Epoch 19, batch 11550, loss[loss=0.1096, simple_loss=0.1955, pruned_loss=0.01188, over 4812.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02778, over 972793.03 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:39:14,555 INFO [train.py:715] (5/8) Epoch 19, batch 11600, loss[loss=0.1279, simple_loss=0.1884, pruned_loss=0.03368, over 4708.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02811, over 972924.70 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:39:54,373 INFO [train.py:715] (5/8) Epoch 19, batch 11650, loss[loss=0.1441, simple_loss=0.2136, pruned_loss=0.03725, over 4957.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2048, pruned_loss=0.0279, over 973138.62 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 15:40:33,464 INFO [train.py:715] (5/8) Epoch 19, batch 11700, loss[loss=0.1196, simple_loss=0.1943, pruned_loss=0.02244, over 4782.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02808, over 973569.90 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 15:41:13,003 INFO [train.py:715] (5/8) Epoch 19, batch 11750, loss[loss=0.1428, simple_loss=0.2109, pruned_loss=0.03738, over 4890.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.0282, over 973400.82 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 15:41:52,544 INFO [train.py:715] (5/8) Epoch 19, batch 11800, loss[loss=0.1356, simple_loss=0.2172, pruned_loss=0.02694, over 4792.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02846, over 972604.11 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:42:32,202 INFO [train.py:715] (5/8) Epoch 19, batch 11850, loss[loss=0.1213, simple_loss=0.1889, pruned_loss=0.02686, over 4897.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.0285, over 973076.50 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 15:43:11,791 INFO [train.py:715] (5/8) Epoch 19, batch 11900, loss[loss=0.1469, simple_loss=0.206, pruned_loss=0.04393, over 4850.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02794, over 972242.53 frames.], batch size: 34, lr: 1.17e-04
2022-05-09 15:43:51,289 INFO [train.py:715] (5/8) Epoch 19, batch 11950, loss[loss=0.1384, simple_loss=0.2185, pruned_loss=0.02919, over 4928.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02816, over 971511.82 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:44:30,453 INFO [train.py:715] (5/8) Epoch 19, batch 12000, loss[loss=0.1504, simple_loss=0.2292, pruned_loss=0.03578, over 4714.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02826, over 971209.19 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:44:30,454 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 15:44:40,311 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01054, over 914524.00 frames.
2022-05-09 15:45:20,290 INFO [train.py:715] (5/8) Epoch 19, batch 12050, loss[loss=0.1497, simple_loss=0.2142, pruned_loss=0.04261, over 4831.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.0281, over 971414.97 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 15:46:00,177 INFO [train.py:715] (5/8) Epoch 19, batch 12100, loss[loss=0.1367, simple_loss=0.2053, pruned_loss=0.03405, over 4794.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02815, over 971809.36 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 15:46:39,301 INFO [train.py:715] (5/8) Epoch 19, batch 12150, loss[loss=0.1396, simple_loss=0.211, pruned_loss=0.03413, over 4768.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02859, over 971476.96 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:47:18,769 INFO [train.py:715] (5/8) Epoch 19, batch 12200, loss[loss=0.1045, simple_loss=0.1818, pruned_loss=0.01361, over 4890.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02761, over 971401.24 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:47:58,232 INFO [train.py:715] (5/8) Epoch 19, batch 12250, loss[loss=0.12, simple_loss=0.1955, pruned_loss=0.02224, over 4871.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2044, pruned_loss=0.02743, over 971694.53 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 15:48:37,869 INFO [train.py:715] (5/8) Epoch 19, batch 12300, loss[loss=0.1573, simple_loss=0.2279, pruned_loss=0.0434, over 4906.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.0278, over 972270.70 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 15:49:17,547 INFO [train.py:715] (5/8) Epoch 19, batch 12350, loss[loss=0.1329, simple_loss=0.2062, pruned_loss=0.02974, over 4927.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2054, pruned_loss=0.02786, over 973153.79 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:49:56,104 INFO [train.py:715] (5/8) Epoch 19, batch 12400, loss[loss=0.1091, simple_loss=0.1781, pruned_loss=0.02003, over 4849.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2045, pruned_loss=0.02756, over 973476.35 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 15:50:35,578 INFO [train.py:715] (5/8) Epoch 19, batch 12450, loss[loss=0.1342, simple_loss=0.2066, pruned_loss=0.03095, over 4808.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2045, pruned_loss=0.02755, over 973270.19 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:51:14,297 INFO [train.py:715] (5/8) Epoch 19, batch 12500, loss[loss=0.118, simple_loss=0.1974, pruned_loss=0.01926, over 4915.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02793, over 973250.04 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:51:53,638 INFO [train.py:715] (5/8) Epoch 19, batch 12550, loss[loss=0.1414, simple_loss=0.2357, pruned_loss=0.02361, over 4814.00 frames.], tot_loss[loss=0.13, simple_loss=0.2047, pruned_loss=0.02765, over 972549.91 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:52:33,120 INFO [train.py:715] (5/8) Epoch 19, batch 12600, loss[loss=0.1355, simple_loss=0.199, pruned_loss=0.03602, over 4973.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2046, pruned_loss=0.02814, over 972277.45 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:53:12,606 INFO [train.py:715] (5/8) Epoch 19, batch 12650, loss[loss=0.1096, simple_loss=0.1982, pruned_loss=0.01046, over 4943.00 frames.], tot_loss[loss=0.13, simple_loss=0.2048, pruned_loss=0.02761, over 972299.86 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:53:51,569 INFO [train.py:715] (5/8) Epoch 19, batch 12700, loss[loss=0.1206, simple_loss=0.1986, pruned_loss=0.02131, over 4931.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02793, over 972231.70 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:54:30,744 INFO [train.py:715] (5/8) Epoch 19, batch 12750, loss[loss=0.1374, simple_loss=0.2136, pruned_loss=0.03064, over 4906.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02813, over 972665.90 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:55:10,387 INFO [train.py:715] (5/8) Epoch 19, batch 12800, loss[loss=0.1223, simple_loss=0.204, pruned_loss=0.02032, over 4753.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02824, over 972668.85 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:55:49,788 INFO [train.py:715] (5/8) Epoch 19, batch 12850, loss[loss=0.1344, simple_loss=0.2008, pruned_loss=0.03402, over 4715.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02809, over 973007.43 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:56:28,726 INFO [train.py:715] (5/8) Epoch 19, batch 12900, loss[loss=0.1219, simple_loss=0.198, pruned_loss=0.02288, over 4959.00 frames.], tot_loss[loss=0.1302, simple_loss=0.205, pruned_loss=0.02777, over 972878.06 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 15:57:08,291 INFO [train.py:715] (5/8) Epoch 19, batch 12950, loss[loss=0.1168, simple_loss=0.1821, pruned_loss=0.02575, over 4684.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2046, pruned_loss=0.02753, over 972803.57 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:57:47,532 INFO [train.py:715] (5/8) Epoch 19, batch 13000, loss[loss=0.137, simple_loss=0.2138, pruned_loss=0.03011, over 4759.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02782, over 972259.40 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 15:58:26,677 INFO [train.py:715] (5/8) Epoch 19, batch 13050, loss[loss=0.1371, simple_loss=0.2181, pruned_loss=0.02801, over 4836.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02785, over 971737.34 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 15:59:05,569 INFO [train.py:715] (5/8) Epoch 19, batch 13100, loss[loss=0.1363, simple_loss=0.212, pruned_loss=0.03026, over 4813.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02821, over 971776.02 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:59:44,829 INFO [train.py:715] (5/8) Epoch 19, batch 13150, loss[loss=0.1609, simple_loss=0.2451, pruned_loss=0.03837, over 4900.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02836, over 970818.70 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:00:24,452 INFO [train.py:715] (5/8) Epoch 19, batch 13200, loss[loss=0.1143, simple_loss=0.1982, pruned_loss=0.01525, over 4918.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02824, over 971682.44 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:01:03,676 INFO [train.py:715] (5/8) Epoch 19, batch 13250, loss[loss=0.1434, simple_loss=0.2104, pruned_loss=0.03822, over 4829.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02809, over 971432.15 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:01:42,977 INFO [train.py:715] (5/8) Epoch 19, batch 13300, loss[loss=0.126, simple_loss=0.2051, pruned_loss=0.02341, over 4757.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02815, over 971140.94 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:02:22,611 INFO [train.py:715] (5/8) Epoch 19, batch 13350, loss[loss=0.1119, simple_loss=0.1928, pruned_loss=0.01549, over 4885.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 971507.61 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:03:01,275 INFO [train.py:715] (5/8) Epoch 19, batch 13400, loss[loss=0.1223, simple_loss=0.202, pruned_loss=0.02129, over 4835.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 971497.95 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 16:03:40,771 INFO [train.py:715] (5/8) Epoch 19, batch 13450, loss[loss=0.1547, simple_loss=0.2273, pruned_loss=0.04101, over 4843.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2064, pruned_loss=0.0283, over 971416.76 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:04:20,046 INFO [train.py:715] (5/8) Epoch 19, batch 13500, loss[loss=0.1329, simple_loss=0.2149, pruned_loss=0.02541, over 4987.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2071, pruned_loss=0.02831, over 971847.19 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:04:59,470 INFO [train.py:715] (5/8) Epoch 19, batch 13550, loss[loss=0.1351, simple_loss=0.2073, pruned_loss=0.03145, over 4865.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02874, over 971672.43 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:05:38,405 INFO [train.py:715] (5/8) Epoch 19, batch 13600, loss[loss=0.1096, simple_loss=0.1905, pruned_loss=0.01438, over 4970.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02888, over 972121.54 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:06:17,568 INFO [train.py:715] (5/8) Epoch 19, batch 13650, loss[loss=0.1499, simple_loss=0.2299, pruned_loss=0.03493, over 4913.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02911, over 973040.23 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:06:57,011 INFO [train.py:715] (5/8) Epoch 19, batch 13700, loss[loss=0.128, simple_loss=0.2003, pruned_loss=0.02784, over 4910.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 972781.50 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:07:35,731 INFO [train.py:715] (5/8) Epoch 19, batch 13750, loss[loss=0.1315, simple_loss=0.211, pruned_loss=0.02601, over 4838.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02865, over 972275.96 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:08:14,997 INFO [train.py:715] (5/8) Epoch 19, batch 13800, loss[loss=0.1054, simple_loss=0.1804, pruned_loss=0.01517, over 4959.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02828, over 972498.46 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:08:55,059 INFO [train.py:715] (5/8) Epoch 19, batch 13850, loss[loss=0.13, simple_loss=0.199, pruned_loss=0.03051, over 4982.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02811, over 972422.15 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 16:09:34,677 INFO [train.py:715] (5/8) Epoch 19, batch 13900, loss[loss=0.1706, simple_loss=0.2347, pruned_loss=0.0533, over 4753.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02783, over 972034.51 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:10:14,442 INFO [train.py:715] (5/8) Epoch 19, batch 13950, loss[loss=0.1273, simple_loss=0.2027, pruned_loss=0.02595, over 4923.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2049, pruned_loss=0.02776, over 972453.99 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:10:53,215 INFO [train.py:715] (5/8) Epoch 19, batch 14000, loss[loss=0.1147, simple_loss=0.187, pruned_loss=0.02116, over 4947.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02796, over 971681.97 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:11:32,642 INFO [train.py:715] (5/8) Epoch 19, batch 14050, loss[loss=0.129, simple_loss=0.2094, pruned_loss=0.02424, over 4843.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02808, over 970962.09 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:12:11,843 INFO [train.py:715] (5/8) Epoch 19, batch 14100, loss[loss=0.1315, simple_loss=0.2047, pruned_loss=0.0291, over 4989.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02872, over 971288.11 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:12:51,004 INFO [train.py:715] (5/8) Epoch 19, batch 14150, loss[loss=0.1438, simple_loss=0.2233, pruned_loss=0.03219, over 4818.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02881, over 971987.04 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 16:13:30,122 INFO [train.py:715] (5/8) Epoch 19, batch 14200, loss[loss=0.1242, simple_loss=0.1905, pruned_loss=0.02898, over 4886.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02882, over 971756.58 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:14:08,938 INFO [train.py:715] (5/8) Epoch 19, batch 14250, loss[loss=0.1338, simple_loss=0.2024, pruned_loss=0.03257, over 4767.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02845, over 971393.63 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:14:48,112 INFO [train.py:715] (5/8) Epoch 19, batch 14300, loss[loss=0.1177, simple_loss=0.1783, pruned_loss=0.02851, over 4975.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02846, over 971403.51 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:15:27,231 INFO [train.py:715] (5/8) Epoch 19, batch 14350, loss[loss=0.1486, simple_loss=0.2167, pruned_loss=0.0402, over 4956.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02863, over 971816.67 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:16:06,785 INFO [train.py:715] (5/8) Epoch 19, batch 14400, loss[loss=0.1386, simple_loss=0.2184, pruned_loss=0.02937, over 4901.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.0281, over 972796.92 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:16:45,666 INFO [train.py:715] (5/8) Epoch 19, batch 14450, loss[loss=0.1653, simple_loss=0.2185, pruned_loss=0.05602, over 4844.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02869, over 973138.49 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 16:17:24,667 INFO [train.py:715] (5/8) Epoch 19, batch 14500, loss[loss=0.1568, simple_loss=0.2356, pruned_loss=0.03894, over 4832.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02867, over 972391.39 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:18:03,481 INFO [train.py:715] (5/8) Epoch 19, batch 14550, loss[loss=0.1157, simple_loss=0.1998, pruned_loss=0.01574, over 4918.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02838, over 973295.30 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:18:43,153 INFO [train.py:715] (5/8) Epoch 19, batch 14600, loss[loss=0.1231, simple_loss=0.2053, pruned_loss=0.02045, over 4782.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02845, over 973290.70 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:19:22,222 INFO [train.py:715] (5/8) Epoch 19, batch 14650, loss[loss=0.1351, simple_loss=0.2041, pruned_loss=0.03305, over 4919.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02871, over 972432.43 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:20:01,160 INFO [train.py:715] (5/8) Epoch 19, batch 14700, loss[loss=0.1277, simple_loss=0.191, pruned_loss=0.03219, over 4857.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02855, over 972860.06 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 16:20:40,518 INFO [train.py:715] (5/8) Epoch 19, batch 14750, loss[loss=0.1119, simple_loss=0.1855, pruned_loss=0.01919, over 4772.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02879, over 972255.60 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:21:19,782 INFO [train.py:715] (5/8) Epoch 19, batch 14800, loss[loss=0.1397, simple_loss=0.2048, pruned_loss=0.0373, over 4983.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02899, over 973250.75 frames.], batch size: 33, lr: 1.17e-04
2022-05-09 16:21:58,083 INFO [train.py:715] (5/8) Epoch 19, batch 14850, loss[loss=0.1313, simple_loss=0.2089, pruned_loss=0.0269, over 4797.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 972298.61 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:22:37,371 INFO [train.py:715] (5/8) Epoch 19, batch 14900, loss[loss=0.1345, simple_loss=0.2222, pruned_loss=0.02339, over 4927.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02873, over 972493.53 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:23:16,321 INFO [train.py:715] (5/8) Epoch 19, batch 14950, loss[loss=0.1311, simple_loss=0.2024, pruned_loss=0.0299, over 4915.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02873, over 972079.37 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:23:55,094 INFO [train.py:715] (5/8) Epoch 19, batch 15000, loss[loss=0.117, simple_loss=0.1953, pruned_loss=0.01938, over 4938.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02891, over 972854.00 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:23:55,095 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 16:24:07,488 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01064, over 914524.00 frames.
2022-05-09 16:24:46,702 INFO [train.py:715] (5/8) Epoch 19, batch 15050, loss[loss=0.1359, simple_loss=0.208, pruned_loss=0.03186, over 4710.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02878, over 972948.10 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:25:26,174 INFO [train.py:715] (5/8) Epoch 19, batch 15100, loss[loss=0.1535, simple_loss=0.2209, pruned_loss=0.04306, over 4839.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02907, over 973246.49 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:26:05,807 INFO [train.py:715] (5/8) Epoch 19, batch 15150, loss[loss=0.1328, simple_loss=0.2186, pruned_loss=0.02351, over 4982.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.029, over 972939.82 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:26:45,269 INFO [train.py:715] (5/8) Epoch 19, batch 15200, loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.03346, over 4842.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 972602.03 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:27:24,250 INFO [train.py:715] (5/8) Epoch 19, batch 15250, loss[loss=0.1137, simple_loss=0.1899, pruned_loss=0.01871, over 4916.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02874, over 972743.30 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:28:04,171 INFO [train.py:715] (5/8) Epoch 19, batch 15300, loss[loss=0.1346, simple_loss=0.2052, pruned_loss=0.032, over 4899.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02861, over 973029.76 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:28:43,719 INFO [train.py:715] (5/8) Epoch 19, batch 15350, loss[loss=0.1322, simple_loss=0.2111, pruned_loss=0.02667, over 4788.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02851, over 972507.45 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:29:23,529 INFO [train.py:715] (5/8) Epoch 19, batch 15400, loss[loss=0.1226, simple_loss=0.1964, pruned_loss=0.02444, over 4692.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02881, over 972732.05 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:30:03,012 INFO [train.py:715] (5/8) Epoch 19, batch 15450, loss[loss=0.1244, simple_loss=0.2035, pruned_loss=0.02264, over 4781.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02889, over 972786.68 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:30:42,449 INFO [train.py:715] (5/8) Epoch 19, batch 15500, loss[loss=0.1274, simple_loss=0.1993, pruned_loss=0.0278, over 4785.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02889, over 973581.77 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:31:21,336 INFO [train.py:715] (5/8) Epoch 19, batch 15550, loss[loss=0.1431, simple_loss=0.2149, pruned_loss=0.03563, over 4746.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02924, over 974533.39 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:32:00,418 INFO [train.py:715] (5/8) Epoch 19, batch 15600, loss[loss=0.1336, simple_loss=0.2068, pruned_loss=0.03017, over 4938.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02941, over 974532.10 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:32:40,086 INFO [train.py:715] (5/8) Epoch 19, batch 15650, loss[loss=0.1505, simple_loss=0.2252, pruned_loss=0.03788, over 4772.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02938, over 973511.40 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:33:19,037 INFO [train.py:715] (5/8) Epoch 19, batch 15700, loss[loss=0.125, simple_loss=0.2102, pruned_loss=0.01988, over 4959.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02967, over 972966.33 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:33:59,137 INFO [train.py:715] (5/8) Epoch 19, batch 15750, loss[loss=0.1222, simple_loss=0.1984, pruned_loss=0.02301, over 4877.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.0291, over 972906.94 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:34:38,393 INFO [train.py:715] (5/8) Epoch 19, batch 15800, loss[loss=0.1285, simple_loss=0.2025, pruned_loss=0.02727, over 4826.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02926, over 972273.22 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:35:17,529 INFO [train.py:715] (5/8) Epoch 19, batch 15850, loss[loss=0.127, simple_loss=0.1908, pruned_loss=0.03156, over 4835.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02874, over 972619.18 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:35:56,469 INFO [train.py:715] (5/8) Epoch 19, batch 15900, loss[loss=0.1492, simple_loss=0.2198, pruned_loss=0.03931, over 4966.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02883, over 972929.83 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:36:35,617 INFO [train.py:715] (5/8) Epoch 19, batch 15950, loss[loss=0.1274, simple_loss=0.2, pruned_loss=0.02736, over 4776.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02915, over 972421.06 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:37:15,271 INFO [train.py:715] (5/8) Epoch 19, batch 16000, loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03246, over 4844.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02893, over 972513.02 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:37:53,932 INFO [train.py:715] (5/8) Epoch 19, batch 16050, loss[loss=0.1458, simple_loss=0.2214, pruned_loss=0.03512, over 4905.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02885, over 972469.79 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:38:33,243 INFO [train.py:715] (5/8) Epoch 19, batch 16100, loss[loss=0.1643, simple_loss=0.2549, pruned_loss=0.03689, over 4972.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02884, over 971991.41 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 16:39:12,543 INFO [train.py:715] (5/8) Epoch 19, batch 16150, loss[loss=0.126, simple_loss=0.2048, pruned_loss=0.02358, over 4923.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.0291, over 971818.39 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:39:51,597 INFO [train.py:715] (5/8) Epoch 19, batch 16200, loss[loss=0.1162, simple_loss=0.1909, pruned_loss=0.02074, over 4972.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02899, over 972947.19 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 16:40:29,888 INFO [train.py:715] (5/8) Epoch 19, batch 16250, loss[loss=0.1278, simple_loss=0.2076, pruned_loss=0.02403, over 4907.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02904, over 972244.04 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:41:08,934 INFO [train.py:715] (5/8) Epoch 19, batch 16300, loss[loss=0.149, simple_loss=0.235, pruned_loss=0.03149, over 4860.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2073, pruned_loss=0.02857, over 972486.71 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:41:48,390 INFO [train.py:715] (5/8) Epoch 19, batch 16350, loss[loss=0.1317, simple_loss=0.2097, pruned_loss=0.02691, over 4933.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2078, pruned_loss=0.02861, over 972558.53 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:42:26,931 INFO [train.py:715] (5/8) Epoch 19, batch 16400, loss[loss=0.1216, simple_loss=0.1983, pruned_loss=0.02242, over 4818.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2081, pruned_loss=0.02869, over 972675.58 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 16:43:05,776 INFO [train.py:715] (5/8) Epoch 19, batch 16450, loss[loss=0.1286, simple_loss=0.2034, pruned_loss=0.02695, over 4897.00 frames.], tot_loss[loss=0.1324, simple_loss=0.208, pruned_loss=0.0284, over 972471.28 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:43:44,321 INFO [train.py:715] (5/8) Epoch 19, batch 16500, loss[loss=0.1227, simple_loss=0.1994, pruned_loss=0.02295, over 4852.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2067, pruned_loss=0.02813, over 972671.87 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:44:23,741 INFO [train.py:715] (5/8) Epoch 19, batch 16550, loss[loss=0.1199, simple_loss=0.1953, pruned_loss=0.02219, over 4782.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02783, over 972534.72 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:45:02,746 INFO [train.py:715] (5/8) Epoch 19, batch 16600, loss[loss=0.1174, simple_loss=0.1923, pruned_loss=0.02123, over 4815.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02771, over 971951.33 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 16:45:41,758 INFO [train.py:715] (5/8) Epoch 19, batch 16650, loss[loss=0.1312, simple_loss=0.211, pruned_loss=0.02576, over 4938.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02804, over 972084.42 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:46:21,731 INFO [train.py:715] (5/8) Epoch 19, batch 16700, loss[loss=0.1226, simple_loss=0.1925, pruned_loss=0.02632, over 4694.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2053, pruned_loss=0.02814, over 972267.71 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:47:00,842 INFO [train.py:715] (5/8) Epoch 19, batch 16750, loss[loss=0.1353, simple_loss=0.2085, pruned_loss=0.0311, over 4693.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.0278, over 971588.25 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:47:40,565 INFO [train.py:715] (5/8) Epoch 19, batch 16800, loss[loss=0.1069, simple_loss=0.1772, pruned_loss=0.0183, over 4715.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.0281, over 971468.77 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:48:19,963 INFO [train.py:715] (5/8) Epoch 19, batch 16850, loss[loss=0.1172, simple_loss=0.1935, pruned_loss=0.0205, over 4780.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02815, over 971188.51 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:48:59,491 INFO [train.py:715] (5/8) Epoch 19, batch 16900, loss[loss=0.1303, simple_loss=0.2097, pruned_loss=0.02549, over 4896.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2054, pruned_loss=0.02864, over 971780.59 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:49:38,107 INFO [train.py:715] (5/8) Epoch 19, batch 16950, loss[loss=0.1234, simple_loss=0.196, pruned_loss=0.02541, over 4783.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02893, over 971856.19 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:50:17,672 INFO [train.py:715] (5/8) Epoch 19, batch 17000, loss[loss=0.1915, simple_loss=0.2429, pruned_loss=0.07006, over 4753.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02943, over 971728.61 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:50:57,094 INFO [train.py:715] (5/8) Epoch 19, batch 17050, loss[loss=0.1349, simple_loss=0.1995, pruned_loss=0.03513, over 4844.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02918, over 971721.31 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:51:36,155 INFO [train.py:715] (5/8) Epoch 19, batch 17100, loss[loss=0.1754, simple_loss=0.2353, pruned_loss=0.05772, over 4970.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02947, over 971952.89 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:52:15,337 INFO [train.py:715] (5/8) Epoch 19, batch 17150, loss[loss=0.1067, simple_loss=0.1754, pruned_loss=0.01902, over 4763.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02889, over 972017.91 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:52:54,351 INFO [train.py:715] (5/8) Epoch 19, batch 17200, loss[loss=0.1325, simple_loss=0.2012, pruned_loss=0.03189, over 4768.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02876, over 972354.80 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:53:33,088 INFO [train.py:715] (5/8) Epoch 19, batch 17250, loss[loss=0.1127, simple_loss=0.192, pruned_loss=0.01674, over 4753.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02858, over 972880.81 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:54:12,077 INFO [train.py:715] (5/8) Epoch 19, batch 17300, loss[loss=0.1249, simple_loss=0.19, pruned_loss=0.02989, over 4768.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.0287, over 972506.72 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:54:51,727 INFO [train.py:715] (5/8) Epoch 19, batch 17350, loss[loss=0.1426, simple_loss=0.2107, pruned_loss=0.0373, over 4960.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02906, over 973227.95 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 16:55:31,272 INFO [train.py:715] (5/8) Epoch 19, batch 17400, loss[loss=0.1438, simple_loss=0.215, pruned_loss=0.03634, over 4988.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02907, over 972600.80 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:56:10,518 INFO [train.py:715] (5/8) Epoch 19, batch 17450, loss[loss=0.1126, simple_loss=0.181, pruned_loss=0.02208, over 4831.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 971872.26 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:56:49,865 INFO [train.py:715] (5/8) Epoch 19, batch 17500, loss[loss=0.1633, simple_loss=0.2453, pruned_loss=0.04069, over 4790.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02915, over 971257.09 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:57:29,144 INFO [train.py:715] (5/8) Epoch 19, batch 17550, loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03091, over 4894.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02932, over 970521.88 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:58:08,751 INFO [train.py:715] (5/8) Epoch 19, batch 17600, loss[loss=0.1481, simple_loss=0.2232, pruned_loss=0.03655, over 4920.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02909, over 971090.41 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:58:47,927 INFO [train.py:715] (5/8) Epoch 19, batch 17650, loss[loss=0.1339, simple_loss=0.2114, pruned_loss=0.02822, over 4906.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02905, over 971266.09 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:59:27,074 INFO [train.py:715] (5/8) Epoch 19, batch 17700, loss[loss=0.1289, simple_loss=0.2072, pruned_loss=0.02524, over 4984.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02959, over 971629.77 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 17:00:06,646 INFO [train.py:715] (5/8) Epoch 19, batch 17750, loss[loss=0.1001, simple_loss=0.1709, pruned_loss=0.01463, over 4757.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 971816.46 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:00:45,236 INFO [train.py:715] (5/8) Epoch 19, batch 17800, loss[loss=0.1491, simple_loss=0.2284, pruned_loss=0.03491, over 4870.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02908, over 971460.06 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:01:24,009 INFO [train.py:715] (5/8) Epoch 19, batch 17850, loss[loss=0.1141, simple_loss=0.1911, pruned_loss=0.01859, over 4979.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02896, over 970866.50 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 17:02:03,484 INFO [train.py:715] (5/8) Epoch 19, batch 17900, loss[loss=0.1464, simple_loss=0.2218, pruned_loss=0.03548, over 4811.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02917, over 971566.37 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 17:02:41,968 INFO [train.py:715] (5/8) Epoch 19, batch 17950, loss[loss=0.1228, simple_loss=0.1886, pruned_loss=0.02847, over 4659.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02909, over 970692.04 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 17:03:21,255 INFO [train.py:715] (5/8) Epoch 19, batch 18000, loss[loss=0.1208, simple_loss=0.2074, pruned_loss=0.01713, over 4909.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02877, over 971301.78 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:03:21,256 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 17:03:31,129 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1877, pruned_loss=0.01074, over 914524.00 frames.
2022-05-09 17:04:10,639 INFO [train.py:715] (5/8) Epoch 19, batch 18050, loss[loss=0.1194, simple_loss=0.1944, pruned_loss=0.02224, over 4903.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02865, over 971093.68 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:04:50,208 INFO [train.py:715] (5/8) Epoch 19, batch 18100, loss[loss=0.1545, simple_loss=0.2351, pruned_loss=0.03694, over 4876.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02826, over 970868.13 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:05:30,064 INFO [train.py:715] (5/8) Epoch 19, batch 18150, loss[loss=0.1401, simple_loss=0.2185, pruned_loss=0.0309, over 4932.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02826, over 971143.57 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:06:09,189 INFO [train.py:715] (5/8) Epoch 19, batch 18200, loss[loss=0.09678, simple_loss=0.1755, pruned_loss=0.009024, over 4806.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02794, over 970737.16 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 17:06:48,110 INFO [train.py:715] (5/8) Epoch 19, batch 18250, loss[loss=0.136, simple_loss=0.2087, pruned_loss=0.03161, over 4984.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2044, pruned_loss=0.02792, over 971246.03 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:07:28,072 INFO [train.py:715] (5/8) Epoch 19, batch 18300, loss[loss=0.1283, simple_loss=0.2111, pruned_loss=0.02277, over 4866.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02795, over 971759.97 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:08:07,531 INFO [train.py:715] (5/8) Epoch 19, batch 18350, loss[loss=0.1235, simple_loss=0.1971, pruned_loss=0.02499, over 4810.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02815, over 970895.62 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:08:47,417 INFO [train.py:715] (5/8) Epoch 19, batch 18400, loss[loss=0.1373, simple_loss=0.2068, pruned_loss=0.03392, over 4958.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02846, over 970770.34 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 17:09:26,676 INFO [train.py:715] (5/8) Epoch 19, batch 18450, loss[loss=0.1401, simple_loss=0.2203, pruned_loss=0.02996, over 4947.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 971715.50 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 17:10:06,108 INFO [train.py:715] (5/8) Epoch 19, batch 18500, loss[loss=0.1136, simple_loss=0.1874, pruned_loss=0.01996, over 4819.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02882, over 971061.75 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 17:10:45,346 INFO [train.py:715] (5/8) Epoch 19, batch 18550, loss[loss=0.1213, simple_loss=0.1983, pruned_loss=0.02214, over 4811.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02923, over 970183.62 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:11:24,400 INFO [train.py:715] (5/8) Epoch 19, batch 18600, loss[loss=0.1185, simple_loss=0.1952, pruned_loss=0.02091, over 4907.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02881, over 970400.06 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:12:06,302 INFO [train.py:715] (5/8) Epoch 19, batch 18650, loss[loss=0.1253, simple_loss=0.1962, pruned_loss=0.02715, over 4980.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02869, over 970789.35 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 17:12:45,147 INFO [train.py:715] (5/8) Epoch 19, batch 18700, loss[loss=0.1498, simple_loss=0.2343, pruned_loss=0.03267, over 4788.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02873, over 970331.69 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:13:24,439 INFO [train.py:715] (5/8) Epoch 19, batch 18750, loss[loss=0.1618, simple_loss=0.2376, pruned_loss=0.04299, over 4793.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 970355.86 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:14:04,380 INFO [train.py:715] (5/8) Epoch 19, batch 18800, loss[loss=0.1571, simple_loss=0.2235, pruned_loss=0.04534, over 4778.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02884, over 969885.78 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:14:44,261 INFO [train.py:715] (5/8) Epoch 19, batch 18850, loss[loss=0.1253, simple_loss=0.1983, pruned_loss=0.02612, over 4863.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02904, over 970161.11 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:15:23,447 INFO [train.py:715] (5/8) Epoch 19, batch 18900, loss[loss=0.119, simple_loss=0.1902, pruned_loss=0.02389, over 4899.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02924, over 970765.23 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:16:02,832 INFO [train.py:715] (5/8) Epoch 19, batch 18950, loss[loss=0.1443, simple_loss=0.2253, pruned_loss=0.03169, over 4810.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02873, over 970727.64 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:16:42,871 INFO [train.py:715] (5/8) Epoch 19, batch 19000, loss[loss=0.1235, simple_loss=0.2048, pruned_loss=0.02115, over 4975.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02839, over 970810.70 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:17:22,368 INFO [train.py:715] (5/8) Epoch 19, batch 19050, loss[loss=0.1206, simple_loss=0.1961, pruned_loss=0.02251, over 4956.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02813, over 970782.40 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:18:01,435 INFO [train.py:715] (5/8) Epoch 19, batch 19100, loss[loss=0.1379, simple_loss=0.2138, pruned_loss=0.03098, over 4805.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02823, over 971817.88 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:18:41,049 INFO [train.py:715] (5/8) Epoch 19, batch 19150, loss[loss=0.1267, simple_loss=0.2061, pruned_loss=0.02359, over 4886.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02855, over 972214.25 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:19:20,392 INFO [train.py:715] (5/8) Epoch 19, batch 19200, loss[loss=0.1129, simple_loss=0.1895, pruned_loss=0.01814, over 4763.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.0284, over 973090.60 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:19:59,880 INFO [train.py:715] (5/8) Epoch 19, batch 19250, loss[loss=0.1439, simple_loss=0.2144, pruned_loss=0.03668, over 4797.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.02835, over 972231.76 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:20:39,158 INFO [train.py:715] (5/8) Epoch 19, batch 19300, loss[loss=0.1006, simple_loss=0.1649, pruned_loss=0.01814, over 4789.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02854, over 972114.41 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:21:19,522 INFO [train.py:715] (5/8) Epoch 19, batch 19350, loss[loss=0.1209, simple_loss=0.1831, pruned_loss=0.02937, over 4763.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02828, over 971402.95 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:21:58,943 INFO [train.py:715] (5/8) Epoch 19, batch 19400, loss[loss=0.1293, simple_loss=0.2049, pruned_loss=0.02681, over 4848.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02813, over 970880.65 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:22:38,648 INFO [train.py:715] (5/8) Epoch 19, batch 19450, loss[loss=0.1067, simple_loss=0.1823, pruned_loss=0.01556, over 4865.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02826, over 971803.22 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:23:18,391 INFO [train.py:715] (5/8) Epoch 19, batch 19500, loss[loss=0.1599, simple_loss=0.228, pruned_loss=0.04588, over 4840.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.0281, over 971901.43 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 17:23:57,781 INFO [train.py:715] (5/8) Epoch 19, batch 19550, loss[loss=0.1322, simple_loss=0.2006, pruned_loss=0.03189, over 4759.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02809, over 971971.12 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:24:36,949 INFO [train.py:715] (5/8) Epoch 19, batch 19600, loss[loss=0.137, simple_loss=0.2191, pruned_loss=0.02741, over 4976.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2048, pruned_loss=0.02773, over 972865.41 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:25:17,642 INFO [train.py:715] (5/8) Epoch 19, batch 19650, loss[loss=0.1093, simple_loss=0.1873, pruned_loss=0.01562, over 4903.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02778, over 972845.82 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:25:56,966 INFO [train.py:715] (5/8) Epoch 19, batch 19700, loss[loss=0.1498, simple_loss=0.217, pruned_loss=0.04127, over 4891.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2039, pruned_loss=0.02782, over 972434.83 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 17:26:35,805 INFO [train.py:715] (5/8) Epoch 19, batch 19750, loss[loss=0.1376, simple_loss=0.216, pruned_loss=0.0296, over 4962.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02794, over 972133.11 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:27:16,059 INFO [train.py:715] (5/8) Epoch 19, batch 19800, loss[loss=0.1116, simple_loss=0.1906, pruned_loss=0.01627, over 4876.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02827, over 972834.54 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:27:55,916 INFO [train.py:715] (5/8) Epoch 19, batch 19850, loss[loss=0.1168, simple_loss=0.1953, pruned_loss=0.0192, over 4830.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02859, over 972025.19 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:28:35,200 INFO [train.py:715] (5/8) Epoch 19, batch 19900, loss[loss=0.1204, simple_loss=0.1896, pruned_loss=0.02559, over 4878.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02818, over 971473.09 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:29:13,882 INFO [train.py:715] (5/8) Epoch 19, batch 19950, loss[loss=0.1313, simple_loss=0.2041, pruned_loss=0.02926, over 4887.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02824, over 971809.42 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:29:53,615 INFO [train.py:715] (5/8) Epoch 19, batch 20000, loss[loss=0.1318, simple_loss=0.2051, pruned_loss=0.02926, over 4796.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02815, over 971820.05 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:30:33,007 INFO [train.py:715] (5/8) Epoch 19, batch 20050, loss[loss=0.1136, simple_loss=0.1867, pruned_loss=0.02027, over 4777.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02778, over 972356.88 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:31:12,640 INFO [train.py:715] (5/8) Epoch 19, batch 20100, loss[loss=0.1222, simple_loss=0.1943, pruned_loss=0.02509, over 4980.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02824, over 972488.56 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:31:52,171 INFO [train.py:715] (5/8) Epoch 19, batch 20150, loss[loss=0.1425, simple_loss=0.2207, pruned_loss=0.03217, over 4781.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02818, over 972664.18 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:32:31,818 INFO [train.py:715] (5/8) Epoch 19, batch 20200, loss[loss=0.127, simple_loss=0.2027, pruned_loss=0.02558, over 4957.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2064, pruned_loss=0.02824, over 973094.57 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:33:11,344 INFO [train.py:715] (5/8) Epoch 19, batch 20250, loss[loss=0.0932, simple_loss=0.1659, pruned_loss=0.01024, over 4814.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02815, over 972724.81 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:33:50,680 INFO [train.py:715] (5/8) Epoch 19, batch 20300, loss[loss=0.1291, simple_loss=0.1979, pruned_loss=0.03016, over 4691.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02805, over 971978.78 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:34:30,221 INFO [train.py:715] (5/8) Epoch 19, batch 20350, loss[loss=0.127, simple_loss=0.2011, pruned_loss=0.02645, over 4791.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02824, over 972053.47 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:35:09,431 INFO [train.py:715] (5/8) Epoch 19, batch 20400, loss[loss=0.1205, simple_loss=0.2018, pruned_loss=0.01956, over 4970.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02793, over 972845.52 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:35:48,298 INFO [train.py:715] (5/8) Epoch 19, batch 20450, loss[loss=0.1323, simple_loss=0.2142, pruned_loss=0.02516, over 4703.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2063, pruned_loss=0.02801, over 971801.78 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:36:28,040 INFO [train.py:715] (5/8) Epoch 19, batch 20500, loss[loss=0.1506, simple_loss=0.2225, pruned_loss=0.03941, over 4816.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02825, over 971725.50 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:37:07,743 INFO [train.py:715] (5/8) Epoch 19, batch 20550, loss[loss=0.1627, simple_loss=0.2395, pruned_loss=0.04297, over 4794.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.0284, over 971432.65 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:37:46,559 INFO [train.py:715] (5/8) Epoch 19, batch 20600, loss[loss=0.1293, simple_loss=0.2105, pruned_loss=0.02404, over 4941.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2084, pruned_loss=0.02903, over 972348.71 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:38:26,011 INFO [train.py:715] (5/8) Epoch 19, batch 20650, loss[loss=0.1308, simple_loss=0.2085, pruned_loss=0.02655, over 4851.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2081, pruned_loss=0.02887, over 972377.87 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:39:05,344 INFO [train.py:715] (5/8) Epoch 19, batch 20700, loss[loss=0.1421, simple_loss=0.2186, pruned_loss=0.03278, over 4750.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02922, over 972880.51 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:39:44,822 INFO [train.py:715] (5/8) Epoch 19, batch 20750, loss[loss=0.1458, simple_loss=0.2204, pruned_loss=0.03559, over 4865.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02952, over 972832.25 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 17:40:23,535 INFO [train.py:715] (5/8) Epoch 19, batch 20800, loss[loss=0.1209, simple_loss=0.1967, pruned_loss=0.02256, over 4951.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.0289, over 972214.06 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:41:02,810 INFO [train.py:715] (5/8) Epoch 19, batch 20850, loss[loss=0.1622, simple_loss=0.2416, pruned_loss=0.04144, over 4746.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02864, over 972603.28 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:41:42,480 INFO [train.py:715] (5/8) Epoch 19, batch 20900, loss[loss=0.1397, simple_loss=0.2252, pruned_loss=0.02714, over 4754.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02864, over 971616.90 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:42:21,286 INFO [train.py:715] (5/8) Epoch 19, batch 20950, loss[loss=0.1235, simple_loss=0.198, pruned_loss=0.02453, over 4843.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02863, over 971944.14 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 17:43:01,034 INFO [train.py:715] (5/8) Epoch 19, batch 21000, loss[loss=0.1626, simple_loss=0.2295, pruned_loss=0.04786, over 4859.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02896, over 970648.27 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 17:43:01,035 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 17:43:11,504 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01062, over 914524.00 frames.
2022-05-09 17:43:51,340 INFO [train.py:715] (5/8) Epoch 19, batch 21050, loss[loss=0.143, simple_loss=0.2136, pruned_loss=0.03616, over 4979.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2053, pruned_loss=0.02863, over 970536.41 frames.], batch size: 31, lr: 1.17e-04
2022-05-09 17:44:31,301 INFO [train.py:715] (5/8) Epoch 19, batch 21100, loss[loss=0.1263, simple_loss=0.2055, pruned_loss=0.02352, over 4920.00 frames.], tot_loss[loss=0.131, simple_loss=0.2048, pruned_loss=0.02857, over 970929.19 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:45:10,119 INFO [train.py:715] (5/8) Epoch 19, batch 21150, loss[loss=0.1173, simple_loss=0.1806, pruned_loss=0.02707, over 4786.00 frames.], tot_loss[loss=0.131, simple_loss=0.2046, pruned_loss=0.0287, over 971330.08 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:45:49,701 INFO [train.py:715] (5/8) Epoch 19, batch 21200, loss[loss=0.1334, simple_loss=0.2168, pruned_loss=0.02502, over 4942.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02847, over 972528.44 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 17:46:28,950 INFO [train.py:715] (5/8) Epoch 19, batch 21250, loss[loss=0.1105, simple_loss=0.1809, pruned_loss=0.02007, over 4771.00 frames.], tot_loss[loss=0.1311, simple_loss=0.205, pruned_loss=0.02865, over 971443.57 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:47:07,992 INFO [train.py:715] (5/8) Epoch 19, batch 21300, loss[loss=0.1122, simple_loss=0.1866, pruned_loss=0.01895, over 4920.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2044, pruned_loss=0.02831, over 971483.44 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:47:46,807 INFO [train.py:715] (5/8) Epoch 19, batch 21350, loss[loss=0.1443, simple_loss=0.2178, pruned_loss=0.03543, over 4771.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02825, over 971644.61 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:48:26,341 INFO [train.py:715] (5/8) Epoch 19, batch 21400, loss[loss=0.1462, simple_loss=0.224, pruned_loss=0.03419, over 4936.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2052, pruned_loss=0.02874, over 971869.07 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:49:05,853 INFO [train.py:715] (5/8) Epoch 19, batch 21450, loss[loss=0.1356, simple_loss=0.2119, pruned_loss=0.02969, over 4846.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02897, over 971675.68 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:49:44,646 INFO [train.py:715] (5/8) Epoch 19, batch 21500, loss[loss=0.1228, simple_loss=0.1999, pruned_loss=0.02287, over 4825.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02879, over 971289.41 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 17:50:24,356 INFO [train.py:715] (5/8) Epoch 19, batch 21550, loss[loss=0.1278, simple_loss=0.2005, pruned_loss=0.0276, over 4779.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02891, over 971220.91 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:51:04,079 INFO [train.py:715] (5/8) Epoch 19, batch 21600, loss[loss=0.1255, simple_loss=0.207, pruned_loss=0.02202, over 4985.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02869, over 971524.27 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:51:43,837 INFO [train.py:715] (5/8) Epoch 19, batch 21650, loss[loss=0.1293, simple_loss=0.1964, pruned_loss=0.03113, over 4869.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02847, over 972071.21 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 17:52:22,732 INFO [train.py:715] (5/8) Epoch 19, batch 21700, loss[loss=0.1381, simple_loss=0.2168, pruned_loss=0.02966, over 4768.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02829, over 972275.10 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 17:53:02,147 INFO [train.py:715] (5/8) Epoch 19, batch 21750, loss[loss=0.1203, simple_loss=0.1921, pruned_loss=0.02422, over 4986.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2042, pruned_loss=0.02817, over 972179.73 frames.], batch size: 31, lr: 1.16e-04
2022-05-09 17:53:43,113 INFO [train.py:715] (5/8) Epoch 19, batch 21800, loss[loss=0.1184, simple_loss=0.1926, pruned_loss=0.02206, over 4899.00 frames.], tot_loss[loss=0.1299, simple_loss=0.204, pruned_loss=0.02791, over 971711.35 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 17:54:22,934 INFO [train.py:715] (5/8) Epoch 19, batch 21850, loss[loss=0.118, simple_loss=0.1959, pruned_loss=0.0201, over 4968.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2041, pruned_loss=0.02828, over 971843.04 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 17:55:03,313 INFO [train.py:715] (5/8) Epoch 19, batch 21900, loss[loss=0.115, simple_loss=0.189, pruned_loss=0.02053, over 4824.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.0283, over 972142.00 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 17:55:43,305 INFO [train.py:715] (5/8) Epoch 19, batch 21950, loss[loss=0.1475, simple_loss=0.2223, pruned_loss=0.03642, over 4707.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2045, pruned_loss=0.02817, over 972176.21 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 17:56:22,524 INFO [train.py:715] (5/8) Epoch 19, batch 22000, loss[loss=0.1222, simple_loss=0.1945, pruned_loss=0.02493, over 4976.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02858, over 972134.19 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 17:57:01,817 INFO [train.py:715] (5/8) Epoch 19, batch 22050, loss[loss=0.1089, simple_loss=0.1872, pruned_loss=0.01531, over 4942.00 frames.], tot_loss[loss=0.1312, simple_loss=0.205, pruned_loss=0.02871, over 972380.63 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 17:57:41,388 INFO [train.py:715] (5/8) Epoch 19, batch 22100, loss[loss=0.1362, simple_loss=0.2171, pruned_loss=0.02764, over 4860.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2042, pruned_loss=0.02831, over 971580.66 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 17:58:21,388 INFO [train.py:715] (5/8) Epoch 19, batch 22150, loss[loss=0.1285, simple_loss=0.2, pruned_loss=0.02852, over 4750.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.02833, over 972317.32 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 17:59:00,690 INFO [train.py:715] (5/8) Epoch 19, batch 22200, loss[loss=0.1453, simple_loss=0.2189, pruned_loss=0.03583, over 4919.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02848, over 973008.31 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 17:59:40,595 INFO [train.py:715] (5/8) Epoch 19, batch 22250, loss[loss=0.1317, simple_loss=0.202, pruned_loss=0.03073, over 4983.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02861, over 972935.34 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:00:20,344 INFO [train.py:715] (5/8) Epoch 19, batch 22300, loss[loss=0.1275, simple_loss=0.2045, pruned_loss=0.02523, over 4820.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2046, pruned_loss=0.02799, over 973099.87 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:00:59,304 INFO [train.py:715] (5/8) Epoch 19, batch 22350, loss[loss=0.1112, simple_loss=0.1867, pruned_loss=0.01779, over 4878.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02784, over 972010.46 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:01:38,318 INFO [train.py:715] (5/8) Epoch 19, batch 22400, loss[loss=0.1139, simple_loss=0.1929, pruned_loss=0.01742, over 4779.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02825, over 971608.51 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:02:17,606 INFO [train.py:715] (5/8) Epoch 19, batch 22450, loss[loss=0.1276, simple_loss=0.1963, pruned_loss=0.02943, over 4875.00 frames.], tot_loss[loss=0.13, simple_loss=0.2041, pruned_loss=0.02798, over 971813.60 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:02:57,543 INFO [train.py:715] (5/8) Epoch 19, batch 22500, loss[loss=0.1038, simple_loss=0.1885, pruned_loss=0.009554, over 4819.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2043, pruned_loss=0.028, over 972828.59 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 18:03:36,397 INFO [train.py:715] (5/8) Epoch 19, batch 22550, loss[loss=0.1423, simple_loss=0.2199, pruned_loss=0.03232, over 4741.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02851, over 971826.71 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:04:16,060 INFO [train.py:715] (5/8) Epoch 19, batch 22600, loss[loss=0.1333, simple_loss=0.196, pruned_loss=0.03527, over 4910.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02845, over 971657.92 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:04:55,710 INFO [train.py:715] (5/8) Epoch 19, batch 22650, loss[loss=0.1382, simple_loss=0.214, pruned_loss=0.03118, over 4705.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02838, over 971616.81 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:05:34,682 INFO [train.py:715] (5/8) Epoch 19, batch 22700, loss[loss=0.1175, simple_loss=0.1851, pruned_loss=0.02497, over 4988.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 972670.76 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:06:13,668 INFO [train.py:715] (5/8) Epoch 19, batch 22750, loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03512, over 4902.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02816, over 973378.88 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:06:53,390 INFO [train.py:715] (5/8) Epoch 19, batch 22800, loss[loss=0.1126, simple_loss=0.1809, pruned_loss=0.02214, over 4791.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02831, over 972464.54 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:07:33,728 INFO [train.py:715] (5/8) Epoch 19, batch 22850, loss[loss=0.1487, simple_loss=0.2234, pruned_loss=0.03696, over 4842.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02877, over 971796.57 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:08:11,746 INFO [train.py:715] (5/8) Epoch 19, batch 22900, loss[loss=0.1332, simple_loss=0.2115, pruned_loss=0.02745, over 4955.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02877, over 972339.79 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:08:51,141 INFO [train.py:715] (5/8) Epoch 19, batch 22950, loss[loss=0.1254, simple_loss=0.214, pruned_loss=0.01838, over 4844.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.0283, over 972282.28 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:09:31,741 INFO [train.py:715] (5/8) Epoch 19, batch 23000, loss[loss=0.125, simple_loss=0.2041, pruned_loss=0.02299, over 4941.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02837, over 971832.97 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:10:12,244 INFO [train.py:715] (5/8) Epoch 19, batch 23050, loss[loss=0.1297, simple_loss=0.2011, pruned_loss=0.02917, over 4861.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02812, over 972803.58 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:10:52,462 INFO [train.py:715] (5/8) Epoch 19, batch 23100, loss[loss=0.1469, simple_loss=0.2172, pruned_loss=0.03832, over 4951.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02827, over 972825.48 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 18:11:33,199 INFO [train.py:715] (5/8) Epoch 19, batch 23150, loss[loss=0.1233, simple_loss=0.201, pruned_loss=0.02283, over 4804.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02828, over 972934.05 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:12:14,199 INFO [train.py:715] (5/8) Epoch 19, batch 23200, loss[loss=0.1497, simple_loss=0.2325, pruned_loss=0.03343, over 4813.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02868, over 972879.43 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:12:53,606 INFO [train.py:715] (5/8) Epoch 19, batch 23250, loss[loss=0.1558, simple_loss=0.2228, pruned_loss=0.04441, over 4913.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.0285, over 973675.93 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:13:34,361 INFO [train.py:715] (5/8) Epoch 19, batch 23300, loss[loss=0.1261, simple_loss=0.2065, pruned_loss=0.02287, over 4839.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02853, over 974403.19 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:14:16,099 INFO [train.py:715] (5/8) Epoch 19, batch 23350, loss[loss=0.1412, simple_loss=0.2245, pruned_loss=0.02894, over 4962.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02867, over 973834.57 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:14:56,711 INFO [train.py:715] (5/8) Epoch 19, batch 23400, loss[loss=0.1088, simple_loss=0.1894, pruned_loss=0.01406, over 4817.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02822, over 972509.92 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:15:37,874 INFO [train.py:715] (5/8) Epoch 19, batch 23450, loss[loss=0.1311, simple_loss=0.2104, pruned_loss=0.02591, over 4817.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02809, over 973360.67 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 18:16:19,140 INFO [train.py:715] (5/8) Epoch 19, batch 23500, loss[loss=0.1263, simple_loss=0.196, pruned_loss=0.02828, over 4982.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2052, pruned_loss=0.02762, over 973551.22 frames.], batch size: 31, lr: 1.16e-04
2022-05-09 18:17:00,518 INFO [train.py:715] (5/8) Epoch 19, batch 23550, loss[loss=0.1184, simple_loss=0.1959, pruned_loss=0.0205, over 4976.00 frames.], tot_loss[loss=0.1293, simple_loss=0.2043, pruned_loss=0.02717, over 974087.62 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:17:41,323 INFO [train.py:715] (5/8) Epoch 19, batch 23600, loss[loss=0.1165, simple_loss=0.1896, pruned_loss=0.02167, over 4813.00 frames.], tot_loss[loss=0.129, simple_loss=0.2037, pruned_loss=0.02717, over 973402.16 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:18:22,144 INFO [train.py:715] (5/8) Epoch 19, batch 23650, loss[loss=0.1285, simple_loss=0.205, pruned_loss=0.02596, over 4758.00 frames.], tot_loss[loss=0.13, simple_loss=0.2044, pruned_loss=0.02784, over 973006.77 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:19:04,121 INFO [train.py:715] (5/8) Epoch 19, batch 23700, loss[loss=0.1243, simple_loss=0.195, pruned_loss=0.02678, over 4957.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02765, over 972296.45 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:19:44,517 INFO [train.py:715] (5/8) Epoch 19, batch 23750, loss[loss=0.1309, simple_loss=0.2087, pruned_loss=0.02659, over 4837.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02758, over 971556.65 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:20:24,718 INFO [train.py:715] (5/8) Epoch 19, batch 23800, loss[loss=0.1603, simple_loss=0.2276, pruned_loss=0.04649, over 4826.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2048, pruned_loss=0.02747, over 971939.15 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:21:05,132 INFO [train.py:715] (5/8) Epoch 19, batch 23850, loss[loss=0.1452, simple_loss=0.224, pruned_loss=0.03317, over 4757.00 frames.], tot_loss[loss=0.1301, simple_loss=0.205, pruned_loss=0.02763, over 971506.24 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:21:45,587 INFO [train.py:715] (5/8) Epoch 19, batch 23900, loss[loss=0.1278, simple_loss=0.1981, pruned_loss=0.02873, over 4779.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2048, pruned_loss=0.02751, over 971799.64 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:22:24,879 INFO [train.py:715] (5/8) Epoch 19, batch 23950, loss[loss=0.1373, simple_loss=0.2095, pruned_loss=0.0326, over 4962.00 frames.], tot_loss[loss=0.1295, simple_loss=0.2044, pruned_loss=0.02734, over 972023.50 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 18:23:05,243 INFO [train.py:715] (5/8) Epoch 19, batch 24000, loss[loss=0.1186, simple_loss=0.1905, pruned_loss=0.02331, over 4822.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2048, pruned_loss=0.02729, over 972268.29 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 18:23:05,244 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 18:23:15,157 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01073, over 914524.00 frames.
2022-05-09 18:23:55,486 INFO [train.py:715] (5/8) Epoch 19, batch 24050, loss[loss=0.1123, simple_loss=0.1862, pruned_loss=0.01923, over 4926.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02771, over 972332.67 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:24:36,270 INFO [train.py:715] (5/8) Epoch 19, batch 24100, loss[loss=0.1017, simple_loss=0.1718, pruned_loss=0.01576, over 4705.00 frames.], tot_loss[loss=0.1295, simple_loss=0.2042, pruned_loss=0.02735, over 972384.66 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:25:16,110 INFO [train.py:715] (5/8) Epoch 19, batch 24150, loss[loss=0.1371, simple_loss=0.2097, pruned_loss=0.03231, over 4940.00 frames.], tot_loss[loss=0.1292, simple_loss=0.2042, pruned_loss=0.0271, over 972887.19 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:25:56,275 INFO [train.py:715] (5/8) Epoch 19, batch 24200, loss[loss=0.1298, simple_loss=0.2041, pruned_loss=0.02776, over 4867.00 frames.], tot_loss[loss=0.1293, simple_loss=0.2043, pruned_loss=0.02719, over 973473.34 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:26:36,610 INFO [train.py:715] (5/8) Epoch 19, batch 24250, loss[loss=0.1492, simple_loss=0.2233, pruned_loss=0.03754, over 4906.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2047, pruned_loss=0.02754, over 973015.44 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:27:17,345 INFO [train.py:715] (5/8) Epoch 19, batch 24300, loss[loss=0.1398, simple_loss=0.2207, pruned_loss=0.02946, over 4810.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02793, over 972814.33 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:27:56,390 INFO [train.py:715] (5/8) Epoch 19, batch 24350, loss[loss=0.1355, simple_loss=0.2066, pruned_loss=0.03217, over 4819.00 frames.], tot_loss[loss=0.1301, simple_loss=0.205, pruned_loss=0.0276, over 972887.84 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 18:28:36,033 INFO [train.py:715] (5/8) Epoch 19, batch 24400, loss[loss=0.1304, simple_loss=0.218, pruned_loss=0.02136, over 4770.00 frames.], tot_loss[loss=0.13, simple_loss=0.2049, pruned_loss=0.02751, over 973295.17 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:29:16,436 INFO [train.py:715] (5/8) Epoch 19, batch 24450, loss[loss=0.1155, simple_loss=0.1901, pruned_loss=0.02043, over 4869.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2047, pruned_loss=0.02758, over 973816.96 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:29:55,849 INFO [train.py:715] (5/8) Epoch 19, batch 24500, loss[loss=0.1059, simple_loss=0.1745, pruned_loss=0.01866, over 4841.00 frames.], tot_loss[loss=0.1293, simple_loss=0.2041, pruned_loss=0.02722, over 973680.78 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:30:34,369 INFO [train.py:715] (5/8) Epoch 19, batch 24550, loss[loss=0.112, simple_loss=0.1934, pruned_loss=0.01526, over 4765.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2045, pruned_loss=0.02731, over 973856.95 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:31:13,261 INFO [train.py:715] (5/8) Epoch 19, batch 24600, loss[loss=0.1102, simple_loss=0.1838, pruned_loss=0.01827, over 4974.00 frames.], tot_loss[loss=0.13, simple_loss=0.2048, pruned_loss=0.02755, over 973865.79 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:31:52,756 INFO [train.py:715] (5/8) Epoch 19, batch 24650, loss[loss=0.1154, simple_loss=0.1816, pruned_loss=0.02461, over 4968.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02767, over 972625.15 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:32:31,483 INFO [train.py:715] (5/8) Epoch 19, batch 24700, loss[loss=0.1197, simple_loss=0.1925, pruned_loss=0.0234, over 4792.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02808, over 972435.29 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:33:10,027 INFO [train.py:715] (5/8) Epoch 19, batch 24750, loss[loss=0.1329, simple_loss=0.2139, pruned_loss=0.02599, over 4786.00 frames.], tot_loss[loss=0.1304, simple_loss=0.205, pruned_loss=0.02788, over 971716.64 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:33:50,379 INFO [train.py:715] (5/8) Epoch 19, batch 24800, loss[loss=0.143, simple_loss=0.2128, pruned_loss=0.03667, over 4944.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2039, pruned_loss=0.02768, over 971712.10 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:34:30,018 INFO [train.py:715] (5/8) Epoch 19, batch 24850, loss[loss=0.1639, simple_loss=0.2245, pruned_loss=0.05161, over 4823.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2047, pruned_loss=0.02804, over 971513.12 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:35:09,082 INFO [train.py:715] (5/8) Epoch 19, batch 24900, loss[loss=0.1228, simple_loss=0.1966, pruned_loss=0.02457, over 4803.00 frames.], tot_loss[loss=0.13, simple_loss=0.2045, pruned_loss=0.02778, over 971498.06 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:35:48,549 INFO [train.py:715] (5/8) Epoch 19, batch 24950, loss[loss=0.1294, simple_loss=0.207, pruned_loss=0.02589, over 4759.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02826, over 971672.14 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:36:28,358 INFO [train.py:715] (5/8) Epoch 19, batch 25000, loss[loss=0.1186, simple_loss=0.1929, pruned_loss=0.02216, over 4898.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02866, over 973157.97 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 18:37:07,181 INFO [train.py:715] (5/8) Epoch 19, batch 25050, loss[loss=0.1259, simple_loss=0.2016, pruned_loss=0.02512, over 4939.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02834, over 972941.36 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 18:37:46,487 INFO [train.py:715] (5/8) Epoch 19, batch 25100, loss[loss=0.1186, simple_loss=0.1953, pruned_loss=0.02099, over 4899.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2048, pruned_loss=0.02766, over 972855.34 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:38:26,084 INFO [train.py:715] (5/8) Epoch 19, batch 25150, loss[loss=0.1561, simple_loss=0.2267, pruned_loss=0.04275, over 4824.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02798, over 972627.49 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:39:05,716 INFO [train.py:715] (5/8) Epoch 19, batch 25200, loss[loss=0.1237, simple_loss=0.1965, pruned_loss=0.02541, over 4975.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.0278, over 973340.43 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 18:39:44,329 INFO [train.py:715] (5/8) Epoch 19, batch 25250, loss[loss=0.1353, simple_loss=0.216, pruned_loss=0.02728, over 4961.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02852, over 972895.33 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:40:23,571 INFO [train.py:715] (5/8) Epoch 19, batch 25300, loss[loss=0.1317, simple_loss=0.2094, pruned_loss=0.027, over 4684.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02847, over 972760.27 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:41:03,215 INFO [train.py:715] (5/8) Epoch 19, batch 25350, loss[loss=0.2023, simple_loss=0.2603, pruned_loss=0.07213, over 4791.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.02833, over 973161.85 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:41:42,426 INFO [train.py:715] (5/8) Epoch 19, batch 25400, loss[loss=0.1471, simple_loss=0.2119, pruned_loss=0.04117, over 4738.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02851, over 972751.30 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:42:21,492 INFO [train.py:715] (5/8) Epoch 19, batch 25450, loss[loss=0.1211, simple_loss=0.1962, pruned_loss=0.02295, over 4818.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02816, over 973046.75 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:43:00,712 INFO [train.py:715] (5/8) Epoch 19, batch 25500, loss[loss=0.1298, simple_loss=0.2074, pruned_loss=0.02607, over 4706.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02824, over 971999.69 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:43:39,818 INFO [train.py:715] (5/8) Epoch 19, batch 25550, loss[loss=0.1368, simple_loss=0.2043, pruned_loss=0.03464, over 4960.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02827, over 972936.10 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:44:18,029 INFO [train.py:715] (5/8) Epoch 19, batch 25600, loss[loss=0.1329, simple_loss=0.2094, pruned_loss=0.02823, over 4777.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02817, over 972439.74 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:44:56,956 INFO [train.py:715] (5/8) Epoch 19, batch 25650, loss[loss=0.1221, simple_loss=0.1909, pruned_loss=0.02664, over 4854.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02831, over 972225.09 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:45:36,002 INFO [train.py:715] (5/8) Epoch 19, batch 25700, loss[loss=0.123, simple_loss=0.193, pruned_loss=0.02646, over 4988.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02811, over 972357.28 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:46:14,563 INFO [train.py:715] (5/8) Epoch 19, batch 25750, loss[loss=0.1369, simple_loss=0.2152, pruned_loss=0.02933, over 4951.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.02839, over 972386.91 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:46:53,571 INFO [train.py:715] (5/8) Epoch 19, batch 25800, loss[loss=0.1324, simple_loss=0.2057, pruned_loss=0.02955, over 4845.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02844, over 972732.95 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:47:32,968 INFO [train.py:715] (5/8) Epoch 19, batch 25850, loss[loss=0.1434, simple_loss=0.2152, pruned_loss=0.03574, over 4930.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02826, over 972875.78 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:48:12,297 INFO [train.py:715] (5/8) Epoch 19, batch 25900, loss[loss=0.1381, simple_loss=0.2134, pruned_loss=0.0314, over 4886.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02839, over 972761.21 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:48:50,878 INFO [train.py:715] (5/8) Epoch 19, batch 25950, loss[loss=0.1459, simple_loss=0.2263, pruned_loss=0.03272, over 4858.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.0285, over 972176.75 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:49:30,499 INFO [train.py:715] (5/8) Epoch 19, batch 26000, loss[loss=0.1343, simple_loss=0.2267, pruned_loss=0.0209, over 4951.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02854, over 972238.28 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:50:10,474 INFO [train.py:715] (5/8) Epoch 19, batch 26050, loss[loss=0.1551, simple_loss=0.2253, pruned_loss=0.04244, over 4692.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02847, over 971663.92 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:50:49,156 INFO [train.py:715] (5/8) Epoch 19, batch 26100, loss[loss=0.1333, simple_loss=0.21, pruned_loss=0.02834, over 4766.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02907, over 971596.32 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:51:28,555 INFO [train.py:715] (5/8) Epoch 19, batch 26150, loss[loss=0.1357, simple_loss=0.2057, pruned_loss=0.03281, over 4931.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02854, over 971077.72 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:52:07,551 INFO [train.py:715] (5/8) Epoch 19, batch 26200, loss[loss=0.1113, simple_loss=0.1839, pruned_loss=0.01934, over 4935.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02788, over 971826.52 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 18:52:47,074 INFO [train.py:715] (5/8) Epoch 19, batch 26250, loss[loss=0.1122, simple_loss=0.1836, pruned_loss=0.02043, over 4776.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02803, over 971953.12 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:53:25,455 INFO [train.py:715] (5/8) Epoch 19, batch 26300, loss[loss=0.1232, simple_loss=0.2151, pruned_loss=0.01571, over 4937.00 frames.], tot_loss[loss=0.1303, simple_loss=0.205, pruned_loss=0.02785, over 971787.90 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:54:04,836 INFO [train.py:715] (5/8) Epoch 19, batch 26350, loss[loss=0.1208, simple_loss=0.1872, pruned_loss=0.02724, over 4775.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02787, over 971300.12 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 18:54:44,058 INFO [train.py:715] (5/8) Epoch 19, batch 26400, loss[loss=0.1609, simple_loss=0.246, pruned_loss=0.03794, over 4788.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.0288, over 970440.87 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:55:23,155 INFO [train.py:715] (5/8) Epoch 19, batch 26450, loss[loss=0.1187, simple_loss=0.1973, pruned_loss=0.01999, over 4984.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.029, over 970748.77 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:56:02,214 INFO [train.py:715] (5/8) Epoch 19, batch 26500, loss[loss=0.1484, simple_loss=0.2339, pruned_loss=0.0315, over 4683.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 970643.64 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:56:40,880 INFO [train.py:715] (5/8) Epoch 19, batch 26550, loss[loss=0.1299, simple_loss=0.2104, pruned_loss=0.02464, over 4777.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02832, over 971652.75 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:57:21,640 INFO [train.py:715] (5/8) Epoch 19, batch 26600, loss[loss=0.1201, simple_loss=0.1909, pruned_loss=0.02471, over 4811.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02871, over 971305.80 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:58:02,781 INFO [train.py:715] (5/8) Epoch 19, batch 26650, loss[loss=0.1633, simple_loss=0.242, pruned_loss=0.04227, over 4812.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2077, pruned_loss=0.02893, over 970702.45 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:58:41,694 INFO [train.py:715] (5/8) Epoch 19, batch 26700, loss[loss=0.1286, simple_loss=0.2003, pruned_loss=0.02841, over 4896.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02886, over 971411.27 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:59:21,010 INFO [train.py:715] (5/8) Epoch 19, batch 26750, loss[loss=0.1555, simple_loss=0.2434, pruned_loss=0.03383, over 4878.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02863, over 972181.91 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:00:00,954 INFO [train.py:715] (5/8) Epoch 19, batch 26800, loss[loss=0.1236, simple_loss=0.2012, pruned_loss=0.02301, over 4824.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02826, over 972673.33 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 19:00:41,173 INFO [train.py:715] (5/8) Epoch 19, batch 26850, loss[loss=0.1477, simple_loss=0.2276, pruned_loss=0.03395, over 4888.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2062, pruned_loss=0.02806, over 972435.24 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:01:20,365 INFO [train.py:715] (5/8) Epoch 19, batch 26900, loss[loss=0.1351, simple_loss=0.1974, pruned_loss=0.03643, over 4770.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02846, over 972584.44 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:02:00,249 INFO [train.py:715] (5/8) Epoch 19, batch 26950, loss[loss=0.1183, simple_loss=0.192, pruned_loss=0.02227, over 4969.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02843, over 972859.86 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:02:39,713 INFO [train.py:715] (5/8) Epoch 19, batch 27000, loss[loss=0.1587, simple_loss=0.2135, pruned_loss=0.05197, over 4685.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02911, over 973081.93 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:02:39,714 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 19:02:49,599 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1878, pruned_loss=0.0108, over 914524.00 frames.
2022-05-09 19:03:29,467 INFO [train.py:715] (5/8) Epoch 19, batch 27050, loss[loss=0.1521, simple_loss=0.241, pruned_loss=0.03159, over 4879.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02905, over 973762.92 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:04:09,789 INFO [train.py:715] (5/8) Epoch 19, batch 27100, loss[loss=0.1154, simple_loss=0.1852, pruned_loss=0.02276, over 4758.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02858, over 973125.32 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:04:50,657 INFO [train.py:715] (5/8) Epoch 19, batch 27150, loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03374, over 4919.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02837, over 972687.13 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:05:30,588 INFO [train.py:715] (5/8) Epoch 19, batch 27200, loss[loss=0.1268, simple_loss=0.2018, pruned_loss=0.0259, over 4854.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02804, over 972222.94 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 19:06:11,126 INFO [train.py:715] (5/8) Epoch 19, batch 27250, loss[loss=0.1317, simple_loss=0.2052, pruned_loss=0.02909, over 4967.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02832, over 972801.64 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:06:52,922 INFO [train.py:715] (5/8) Epoch 19, batch 27300, loss[loss=0.1462, simple_loss=0.2246, pruned_loss=0.03396, over 4836.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02851, over 972430.69 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:07:33,646 INFO [train.py:715] (5/8) Epoch 19, batch 27350, loss[loss=0.1455, simple_loss=0.2111, pruned_loss=0.03999, over 4963.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02903, over 973272.24 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:08:14,907 INFO [train.py:715] (5/8) Epoch 19, batch 27400, loss[loss=0.1357, simple_loss=0.2168, pruned_loss=0.02735, over 4982.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 973421.33 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:08:54,851 INFO [train.py:715] (5/8) Epoch 19, batch 27450, loss[loss=0.1446, simple_loss=0.2251, pruned_loss=0.032, over 4947.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02924, over 974401.65 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:09:36,479 INFO [train.py:715] (5/8) Epoch 19, batch 27500, loss[loss=0.1195, simple_loss=0.1915, pruned_loss=0.02381, over 4950.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02915, over 973283.48 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:10:17,081 INFO [train.py:715] (5/8) Epoch 19, batch 27550, loss[loss=0.14, simple_loss=0.2139, pruned_loss=0.03304, over 4945.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.0294, over 973421.04 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:10:57,700 INFO [train.py:715] (5/8) Epoch 19, batch 27600, loss[loss=0.1194, simple_loss=0.2037, pruned_loss=0.01757, over 4870.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02951, over 973224.58 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:11:38,776 INFO [train.py:715] (5/8) Epoch 19, batch 27650, loss[loss=0.1272, simple_loss=0.2103, pruned_loss=0.02201, over 4895.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02959, over 973204.80 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:12:19,401 INFO [train.py:715] (5/8) Epoch 19, batch 27700, loss[loss=0.1111, simple_loss=0.1897, pruned_loss=0.01629, over 4803.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 973627.60 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:13:00,035 INFO [train.py:715] (5/8) Epoch 19, batch 27750, loss[loss=0.1264, simple_loss=0.1969, pruned_loss=0.02791, over 4775.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02915, over 972617.52 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:13:40,113 INFO [train.py:715] (5/8) Epoch 19, batch 27800, loss[loss=0.1232, simple_loss=0.1946, pruned_loss=0.02586, over 4768.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02939, over 972636.18 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:14:21,132 INFO [train.py:715] (5/8) Epoch 19, batch 27850, loss[loss=0.1379, simple_loss=0.2034, pruned_loss=0.03622, over 4931.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02887, over 972585.17 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:15:01,160 INFO [train.py:715] (5/8) Epoch 19, batch 27900, loss[loss=0.1363, simple_loss=0.213, pruned_loss=0.02981, over 4991.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02865, over 972766.37 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:15:41,279 INFO [train.py:715] (5/8) Epoch 19, batch 27950, loss[loss=0.1386, simple_loss=0.2132, pruned_loss=0.03201, over 4987.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02807, over 973852.77 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:16:21,257 INFO [train.py:715] (5/8) Epoch 19, batch 28000, loss[loss=0.1213, simple_loss=0.1984, pruned_loss=0.02206, over 4864.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02803, over 973435.10 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 19:17:02,090 INFO [train.py:715] (5/8) Epoch 19, batch 28050, loss[loss=0.08504, simple_loss=0.154, pruned_loss=0.008045, over 4779.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02827, over 972726.76 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:17:42,529 INFO [train.py:715] (5/8) Epoch 19, batch 28100, loss[loss=0.1275, simple_loss=0.2026, pruned_loss=0.02622, over 4986.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02821, over 972736.07 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 19:18:22,475 INFO [train.py:715] (5/8) Epoch 19, batch 28150, loss[loss=0.1434, simple_loss=0.22, pruned_loss=0.03338, over 4984.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02826, over 973022.51 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:19:02,901 INFO [train.py:715] (5/8) Epoch 19, batch 28200, loss[loss=0.1294, simple_loss=0.2127, pruned_loss=0.02304, over 4970.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02815, over 972829.06 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:19:42,610 INFO [train.py:715] (5/8) Epoch 19, batch 28250, loss[loss=0.1279, simple_loss=0.2043, pruned_loss=0.02575, over 4815.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02901, over 972894.89 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 19:20:22,517 INFO [train.py:715] (5/8) Epoch 19, batch 28300, loss[loss=0.1136, simple_loss=0.1912, pruned_loss=0.01798, over 4952.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02906, over 972500.09 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:21:02,198 INFO [train.py:715] (5/8) Epoch 19, batch 28350, loss[loss=0.1413, simple_loss=0.2215, pruned_loss=0.03061, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02895, over 972468.62 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:21:42,213 INFO [train.py:715] (5/8) Epoch 19, batch 28400, loss[loss=0.1187, simple_loss=0.2013, pruned_loss=0.01806, over 4877.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02882, over 972755.26 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:22:22,330 INFO [train.py:715] (5/8) Epoch 19, batch 28450, loss[loss=0.1374, simple_loss=0.2173, pruned_loss=0.02875, over 4976.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.0285, over 972779.33 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:23:02,154 INFO [train.py:715] (5/8) Epoch 19, batch 28500, loss[loss=0.1288, simple_loss=0.2123, pruned_loss=0.02262, over 4935.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02848, over 972952.55 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:23:42,828 INFO [train.py:715] (5/8) Epoch 19, batch 28550, loss[loss=0.1183, simple_loss=0.1957, pruned_loss=0.02039, over 4904.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02814, over 972551.35 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:24:22,312 INFO [train.py:715] (5/8) Epoch 19, batch 28600, loss[loss=0.1131, simple_loss=0.1913, pruned_loss=0.01747, over 4828.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.0284, over 972967.02 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:25:02,350 INFO [train.py:715] (5/8) Epoch 19, batch 28650, loss[loss=0.1331, simple_loss=0.2003, pruned_loss=0.03294, over 4874.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02848, over 972566.31 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:25:43,119 INFO [train.py:715] (5/8) Epoch 19, batch 28700, loss[loss=0.1247, simple_loss=0.2013, pruned_loss=0.02405, over 4775.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02865, over 972439.46 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:26:22,652 INFO [train.py:715] (5/8) Epoch 19, batch 28750, loss[loss=0.1271, simple_loss=0.1889, pruned_loss=0.03267, over 4901.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972722.78 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:27:02,561 INFO [train.py:715] (5/8) Epoch 19, batch 28800, loss[loss=0.131, simple_loss=0.2007, pruned_loss=0.03066, over 4905.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02863, over 972745.42 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:27:41,938 INFO [train.py:715] (5/8) Epoch 19, batch 28850, loss[loss=0.1291, simple_loss=0.2126, pruned_loss=0.02275, over 4888.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02858, over 972582.41 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:28:21,324 INFO [train.py:715] (5/8) Epoch 19, batch 28900, loss[loss=0.1509, simple_loss=0.2155, pruned_loss=0.0431, over 4933.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02857, over 973063.40 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:28:59,434 INFO [train.py:715] (5/8) Epoch 19, batch 28950, loss[loss=0.1468, simple_loss=0.2221, pruned_loss=0.03568, over 4850.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02862, over 972980.00 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 19:29:38,324 INFO [train.py:715] (5/8) Epoch 19, batch 29000, loss[loss=0.1369, simple_loss=0.2115, pruned_loss=0.03118, over 4745.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02852, over 972831.47 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:30:17,557 INFO [train.py:715] (5/8) Epoch 19, batch 29050, loss[loss=0.1468, simple_loss=0.2284, pruned_loss=0.03263, over 4941.00 frames.], tot_loss[loss=0.131, simple_loss=0.2061, pruned_loss=0.02792, over 974330.10 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:30:56,437 INFO [train.py:715] (5/8) Epoch 19, batch 29100, loss[loss=0.1165, simple_loss=0.2039, pruned_loss=0.01451, over 4948.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2059, pruned_loss=0.0276, over 973237.02 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:31:35,380 INFO [train.py:715] (5/8) Epoch 19, batch 29150, loss[loss=0.1179, simple_loss=0.2001, pruned_loss=0.0179, over 4956.00 frames.], tot_loss[loss=0.1308, simple_loss=0.206, pruned_loss=0.02778, over 972952.68 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:32:14,165 INFO [train.py:715] (5/8) Epoch 19, batch 29200, loss[loss=0.1407, simple_loss=0.208, pruned_loss=0.03668, over 4890.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2064, pruned_loss=0.02818, over 972324.49 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:32:53,529 INFO [train.py:715] (5/8) Epoch 19, batch 29250, loss[loss=0.1211, simple_loss=0.1994, pruned_loss=0.02142, over 4938.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02845, over 972117.05 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:33:32,154 INFO [train.py:715] (5/8) Epoch 19, batch 29300, loss[loss=0.153, simple_loss=0.2269, pruned_loss=0.03957, over 4754.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02902, over 971852.70 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:34:11,673 INFO [train.py:715] (5/8) Epoch 19, batch 29350, loss[loss=0.122, simple_loss=0.1897, pruned_loss=0.02716, over 4942.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02886, over 972526.95 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:34:50,605 INFO [train.py:715] (5/8) Epoch 19, batch 29400, loss[loss=0.1453, simple_loss=0.2254, pruned_loss=0.03261, over 4914.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02883, over 973484.19 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:35:29,741 INFO [train.py:715] (5/8) Epoch 19, batch 29450, loss[loss=0.1417, simple_loss=0.2272, pruned_loss=0.02813, over 4978.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02883, over 973328.82 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:36:09,168 INFO [train.py:715] (5/8) Epoch 19, batch 29500, loss[loss=0.1495, simple_loss=0.2216, pruned_loss=0.03871, over 4953.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 973627.36 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:36:48,558 INFO [train.py:715] (5/8) Epoch 19, batch 29550, loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02781, over 4776.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02845, over 972910.49 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:37:28,169 INFO [train.py:715] (5/8) Epoch 19, batch 29600, loss[loss=0.1294, simple_loss=0.2082, pruned_loss=0.0253, over 4808.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02885, over 972736.53 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:38:07,300 INFO [train.py:715] (5/8) Epoch 19, batch 29650, loss[loss=0.1371, simple_loss=0.2068, pruned_loss=0.03369, over 4971.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02884, over 973131.92 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:38:47,452 INFO [train.py:715] (5/8) Epoch 19, batch 29700, loss[loss=0.1254, simple_loss=0.2005, pruned_loss=0.02514, over 4795.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02833, over 973304.24 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:39:26,743 INFO [train.py:715] (5/8) Epoch 19, batch 29750, loss[loss=0.1334, simple_loss=0.2037, pruned_loss=0.03159, over 4848.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02844, over 972414.02 frames.], batch size: 34, lr: 1.16e-04
2022-05-09 19:40:06,089 INFO [train.py:715] (5/8) Epoch 19, batch 29800, loss[loss=0.1341, simple_loss=0.213, pruned_loss=0.0276, over 4885.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02852, over 972564.53 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:40:45,393 INFO [train.py:715] (5/8) Epoch 19, batch 29850, loss[loss=0.1236, simple_loss=0.1968, pruned_loss=0.02516, over 4955.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02824, over 972400.64 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:41:24,807 INFO [train.py:715] (5/8) Epoch 19, batch 29900, loss[loss=0.1364, simple_loss=0.2194, pruned_loss=0.02672, over 4865.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02843, over 972791.91 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:42:04,768 INFO [train.py:715] (5/8) Epoch 19, batch 29950, loss[loss=0.1274, simple_loss=0.196, pruned_loss=0.02942, over 4849.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02827, over 972503.55 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:42:43,615 INFO [train.py:715] (5/8) Epoch 19, batch 30000, loss[loss=0.1385, simple_loss=0.2184, pruned_loss=0.02928, over 4906.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 972577.01 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:42:43,616 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 19:42:53,507 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 19:43:32,625 INFO [train.py:715] (5/8) Epoch 19, batch 30050, loss[loss=0.1603, simple_loss=0.2304, pruned_loss=0.04508, over 4967.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02821, over 972474.79 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:44:12,190 INFO [train.py:715] (5/8) Epoch 19, batch 30100, loss[loss=0.101, simple_loss=0.1736, pruned_loss=0.01419, over 4958.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02816, over 972549.88 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:44:51,309 INFO [train.py:715] (5/8) Epoch 19, batch 30150, loss[loss=0.1287, simple_loss=0.2098, pruned_loss=0.02381, over 4970.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.0281, over 972632.09 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:45:31,083 INFO [train.py:715] (5/8) Epoch 19, batch 30200, loss[loss=0.1394, simple_loss=0.2112, pruned_loss=0.0338, over 4756.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.0283, over 971948.08 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:46:09,572 INFO [train.py:715] (5/8) Epoch 19, batch 30250, loss[loss=0.1365, simple_loss=0.2118, pruned_loss=0.03062, over 4859.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.02786, over 971820.58 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 19:46:48,892 INFO [train.py:715] (5/8) Epoch 19, batch 30300, loss[loss=0.1208, simple_loss=0.1988, pruned_loss=0.02143, over 4811.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.0278, over 971594.35 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:47:28,481 INFO [train.py:715] (5/8) Epoch 19, batch 30350, loss[loss=0.136, simple_loss=0.2129, pruned_loss=0.02956, over 4793.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02787, over 972103.90 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:48:08,087 INFO [train.py:715] (5/8) Epoch 19, batch 30400, loss[loss=0.1107, simple_loss=0.1908, pruned_loss=0.01536, over 4758.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02801, over 971954.65 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:48:47,853 INFO [train.py:715] (5/8) Epoch 19, batch 30450, loss[loss=0.1203, simple_loss=0.1972, pruned_loss=0.02169, over 4991.00 frames.], tot_loss[loss=0.13, simple_loss=0.2047, pruned_loss=0.02763, over 972510.31 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:49:26,658 INFO [train.py:715] (5/8) Epoch 19, batch 30500, loss[loss=0.14, simple_loss=0.2118, pruned_loss=0.03413, over 4848.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02809, over 972985.62 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:50:06,592 INFO [train.py:715] (5/8) Epoch 19, batch 30550, loss[loss=0.1194, simple_loss=0.2069, pruned_loss=0.01599, over 4818.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.0284, over 973369.07 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 19:50:45,746 INFO [train.py:715] (5/8) Epoch 19, batch 30600, loss[loss=0.1318, simple_loss=0.205, pruned_loss=0.02925, over 4785.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02808, over 973287.76 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:51:25,826 INFO [train.py:715] (5/8) Epoch 19, batch 30650, loss[loss=0.1548, simple_loss=0.236, pruned_loss=0.03685, over 4909.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02812, over 972767.82 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:52:05,612 INFO [train.py:715] (5/8) Epoch 19, batch 30700, loss[loss=0.1555, simple_loss=0.2327, pruned_loss=0.03912, over 4966.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02824, over 972610.74 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:52:45,192 INFO [train.py:715] (5/8) Epoch 19, batch 30750, loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03359, over 4979.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02803, over 972915.04 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:53:25,711 INFO [train.py:715] (5/8) Epoch 19, batch 30800, loss[loss=0.1243, simple_loss=0.2076, pruned_loss=0.02052, over 4761.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02756, over 973117.56 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:54:05,655 INFO [train.py:715] (5/8) Epoch 19, batch 30850, loss[loss=0.1208, simple_loss=0.1971, pruned_loss=0.02227, over 4935.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02807, over 972949.61 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:54:46,447 INFO [train.py:715] (5/8) Epoch 19, batch 30900, loss[loss=0.1371, simple_loss=0.2082, pruned_loss=0.03301, over 4849.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02785, over 973102.43 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 19:55:26,511 INFO [train.py:715] (5/8) Epoch 19, batch 30950, loss[loss=0.124, simple_loss=0.2026, pruned_loss=0.02271, over 4807.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02799, over 972109.44 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:56:07,122 INFO [train.py:715] (5/8) Epoch 19, batch 31000, loss[loss=0.1054, simple_loss=0.1722, pruned_loss=0.01931, over 4783.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02795, over 971551.20 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:56:47,788 INFO [train.py:715] (5/8) Epoch 19, batch 31050, loss[loss=0.1092, simple_loss=0.1792, pruned_loss=0.01964, over 4841.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02793, over 971893.93 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 19:57:28,117 INFO [train.py:715] (5/8) Epoch 19, batch 31100, loss[loss=0.1438, simple_loss=0.2097, pruned_loss=0.03897, over 4965.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02793, over 972032.08 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:58:08,815 INFO [train.py:715] (5/8) Epoch 19, batch 31150, loss[loss=0.1088, simple_loss=0.1886, pruned_loss=0.01446, over 4955.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02787, over 972552.10 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:58:49,193 INFO [train.py:715] (5/8) Epoch 19, batch 31200, loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.0299, over 4942.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2046, pruned_loss=0.02743, over 972396.18 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:59:30,188 INFO [train.py:715] (5/8) Epoch 19, batch 31250, loss[loss=0.1157, simple_loss=0.189, pruned_loss=0.0212, over 4973.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2049, pruned_loss=0.02733, over 972581.05 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:00:09,923 INFO [train.py:715] (5/8) Epoch 19, batch 31300, loss[loss=0.1138, simple_loss=0.1911, pruned_loss=0.01827, over 4945.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2043, pruned_loss=0.02741, over 972535.76 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 20:00:50,565 INFO [train.py:715] (5/8) Epoch 19, batch 31350, loss[loss=0.1141, simple_loss=0.1976, pruned_loss=0.01529, over 4814.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02787, over 972599.23 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:01:31,160 INFO [train.py:715] (5/8) Epoch 19, batch 31400, loss[loss=0.1322, simple_loss=0.2138, pruned_loss=0.02535, over 4849.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02852, over 972657.36 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 20:02:11,467 INFO [train.py:715] (5/8) Epoch 19, batch 31450, loss[loss=0.1391, simple_loss=0.2168, pruned_loss=0.03066, over 4941.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02878, over 973025.61 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:02:52,729 INFO [train.py:715] (5/8) Epoch 19, batch 31500, loss[loss=0.1554, simple_loss=0.2317, pruned_loss=0.03954, over 4929.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02885, over 973272.50 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:03:32,845 INFO [train.py:715] (5/8) Epoch 19, batch 31550, loss[loss=0.1088, simple_loss=0.1762, pruned_loss=0.02064, over 4980.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02858, over 973579.37 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:04:13,426 INFO [train.py:715] (5/8) Epoch 19, batch 31600, loss[loss=0.1283, simple_loss=0.2042, pruned_loss=0.02618, over 4985.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02843, over 973625.93 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 20:04:53,555 INFO [train.py:715] (5/8) Epoch 19, batch 31650, loss[loss=0.167, simple_loss=0.2382, pruned_loss=0.04795, over 4754.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02835, over 972439.37 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:05:33,937 INFO [train.py:715] (5/8) Epoch 19, batch 31700, loss[loss=0.1219, simple_loss=0.1963, pruned_loss=0.0237, over 4818.00 frames.], tot_loss[loss=0.1309, simple_loss=0.205, pruned_loss=0.02841, over 972076.39 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:06:14,404 INFO [train.py:715] (5/8) Epoch 19, batch 31750, loss[loss=0.1162, simple_loss=0.1859, pruned_loss=0.02331, over 4864.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2047, pruned_loss=0.02846, over 971551.79 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 20:06:54,585 INFO [train.py:715] (5/8) Epoch 19, batch 31800, loss[loss=0.1342, simple_loss=0.201, pruned_loss=0.0337, over 4830.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02826, over 971578.26 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 20:07:35,678 INFO [train.py:715] (5/8) Epoch 19, batch 31850, loss[loss=0.1513, simple_loss=0.2206, pruned_loss=0.04101, over 4858.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.0286, over 971502.57 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:08:15,981 INFO [train.py:715] (5/8) Epoch 19, batch 31900, loss[loss=0.1084, simple_loss=0.1836, pruned_loss=0.01657, over 4755.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02854, over 971480.83 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:08:56,573 INFO [train.py:715] (5/8) Epoch 19, batch 31950, loss[loss=0.1253, simple_loss=0.2027, pruned_loss=0.02396, over 4992.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.0285, over 971928.10 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:09:36,642 INFO [train.py:715] (5/8) Epoch 19, batch 32000, loss[loss=0.1154, simple_loss=0.1972, pruned_loss=0.01681, over 4932.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02826, over 971265.35 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:10:16,974 INFO [train.py:715] (5/8) Epoch 19, batch 32050, loss[loss=0.1245, simple_loss=0.2016, pruned_loss=0.02369, over 4827.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02808, over 971647.53 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:10:57,300 INFO [train.py:715] (5/8) Epoch 19, batch 32100, loss[loss=0.1185, simple_loss=0.1973, pruned_loss=0.01987, over 4802.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02816, over 970414.09 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 20:11:37,100 INFO [train.py:715] (5/8) Epoch 19, batch 32150, loss[loss=0.1353, simple_loss=0.2073, pruned_loss=0.03166, over 4786.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 970383.75 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 20:12:18,361 INFO [train.py:715] (5/8) Epoch 19, batch 32200, loss[loss=0.106, simple_loss=0.183, pruned_loss=0.01447, over 4753.00 frames.], tot_loss[loss=0.1305, simple_loss=0.205, pruned_loss=0.02802, over 970370.19 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:12:58,106 INFO [train.py:715] (5/8) Epoch 19, batch 32250, loss[loss=0.1062, simple_loss=0.1812, pruned_loss=0.01561, over 4758.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.0281, over 970797.58 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 20:13:38,488 INFO [train.py:715] (5/8) Epoch 19, batch 32300, loss[loss=0.09652, simple_loss=0.1637, pruned_loss=0.01469, over 4807.00 frames.], tot_loss[loss=0.1299, simple_loss=0.204, pruned_loss=0.02787, over 971275.11 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 20:14:19,665 INFO [train.py:715] (5/8) Epoch 19, batch 32350, loss[loss=0.1331, simple_loss=0.2151, pruned_loss=0.02558, over 4968.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2043, pruned_loss=0.0286, over 972223.11 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 20:15:00,203 INFO [train.py:715] (5/8) Epoch 19, batch 32400, loss[loss=0.1458, simple_loss=0.2235, pruned_loss=0.03407, over 4983.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.02858, over 973057.81 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:15:40,800 INFO [train.py:715] (5/8) Epoch 19, batch 32450, loss[loss=0.1232, simple_loss=0.1964, pruned_loss=0.02502, over 4904.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02928, over 973147.20 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:16:20,797 INFO [train.py:715] (5/8) Epoch 19, batch 32500, loss[loss=0.1298, simple_loss=0.2101, pruned_loss=0.02475, over 4859.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02889, over 973412.48 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 20:17:01,568 INFO [train.py:715] (5/8) Epoch 19, batch 32550, loss[loss=0.1241, simple_loss=0.1975, pruned_loss=0.02538, over 4890.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02921, over 972834.61 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 20:17:41,583 INFO [train.py:715] (5/8) Epoch 19, batch 32600, loss[loss=0.1205, simple_loss=0.1968, pruned_loss=0.02205, over 4894.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02854, over 972743.47 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:18:21,658 INFO [train.py:715] (5/8) Epoch 19, batch 32650, loss[loss=0.1124, simple_loss=0.1876, pruned_loss=0.01857, over 4929.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02854, over 972886.89 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:19:02,298 INFO [train.py:715] (5/8) Epoch 19, batch 32700, loss[loss=0.1669, simple_loss=0.2241, pruned_loss=0.05485, over 4785.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2052, pruned_loss=0.0289, over 973636.92 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 20:19:42,120 INFO [train.py:715] (5/8) Epoch 19, batch 32750, loss[loss=0.158, simple_loss=0.2322, pruned_loss=0.04187, over 4978.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02898, over 973694.04 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:20:21,840 INFO [train.py:715] (5/8) Epoch 19, batch 32800, loss[loss=0.1176, simple_loss=0.1967, pruned_loss=0.01921, over 4792.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02915, over 972724.38 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 20:21:00,655 INFO [train.py:715] (5/8) Epoch 19, batch 32850, loss[loss=0.1351, simple_loss=0.199, pruned_loss=0.03562, over 4970.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02938, over 972775.52 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:21:39,680 INFO [train.py:715] (5/8) Epoch 19, batch 32900, loss[loss=0.1443, simple_loss=0.2282, pruned_loss=0.03022, over 4930.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 973745.65 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:22:18,348 INFO [train.py:715] (5/8) Epoch 19, batch 32950, loss[loss=0.1091, simple_loss=0.1826, pruned_loss=0.0178, over 4656.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02867, over 972807.77 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 20:22:57,660 INFO [train.py:715] (5/8) Epoch 19, batch 33000, loss[loss=0.1327, simple_loss=0.2023, pruned_loss=0.03154, over 4963.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02867, over 972811.33 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 20:22:57,661 INFO [train.py:733] (5/8) Computing validation loss
2022-05-09 20:23:07,491 INFO [train.py:742] (5/8) Epoch 19, validation: loss=0.1048, simple_loss=0.1878, pruned_loss=0.01088, over 914524.00 frames.
2022-05-09 20:23:46,769 INFO [train.py:715] (5/8) Epoch 19, batch 33050, loss[loss=0.1145, simple_loss=0.1953, pruned_loss=0.0169, over 4926.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.0284, over 971896.34 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:24:26,211 INFO [train.py:715] (5/8) Epoch 19, batch 33100, loss[loss=0.1411, simple_loss=0.2087, pruned_loss=0.03673, over 4787.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02811, over 971776.11 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 20:25:05,027 INFO [train.py:715] (5/8) Epoch 19, batch 33150, loss[loss=0.1308, simple_loss=0.1906, pruned_loss=0.03551, over 4957.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 972021.34 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 20:25:44,208 INFO [train.py:715] (5/8) Epoch 19, batch 33200, loss[loss=0.1686, simple_loss=0.2441, pruned_loss=0.0465, over 4782.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02849, over 972232.32 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 20:26:23,765 INFO [train.py:715] (5/8) Epoch 19, batch 33250, loss[loss=0.1587, simple_loss=0.2436, pruned_loss=0.03686, over 4784.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02823, over 971499.65 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 20:27:03,191 INFO [train.py:715] (5/8) Epoch 19, batch 33300, loss[loss=0.1463, simple_loss=0.2174, pruned_loss=0.03761, over 4856.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.0284, over 971759.73 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 20:27:42,908 INFO [train.py:715] (5/8) Epoch 19, batch 33350, loss[loss=0.1193, simple_loss=0.1868, pruned_loss=0.02587, over 4851.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2074, pruned_loss=0.02841, over 972325.68 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 20:28:22,075 INFO [train.py:715] (5/8) Epoch 19, batch 33400, loss[loss=0.1193, simple_loss=0.199, pruned_loss=0.01983, over 4881.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02811, over 972275.41 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:29:01,053 INFO [train.py:715] (5/8) Epoch 19, batch 33450, loss[loss=0.1165, simple_loss=0.1848, pruned_loss=0.02411, over 4841.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2059, pruned_loss=0.02777, over 972018.01 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 20:29:40,020 INFO [train.py:715] (5/8) Epoch 19, batch 33500, loss[loss=0.1444, simple_loss=0.2259, pruned_loss=0.03146, over 4975.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2064, pruned_loss=0.02796, over 972608.96 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:30:18,904 INFO [train.py:715] (5/8) Epoch 19, batch 33550, loss[loss=0.1355, simple_loss=0.2035, pruned_loss=0.0338, over 4864.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2057, pruned_loss=0.02748, over 972747.08 frames.], batch size: 20, lr: 1.15e-04
2022-05-09 20:30:58,231 INFO [train.py:715] (5/8) Epoch 19, batch 33600, loss[loss=0.1373, simple_loss=0.2195, pruned_loss=0.02754, over 4925.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2058, pruned_loss=0.02754, over 971650.54 frames.], batch size: 29, lr: 1.15e-04
2022-05-09 20:31:37,214 INFO [train.py:715] (5/8) Epoch 19, batch 33650, loss[loss=0.1196, simple_loss=0.1958, pruned_loss=0.02173, over 4814.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2057, pruned_loss=0.02732, over 971283.19 frames.], batch size: 24, lr: 1.15e-04
2022-05-09 20:32:16,615 INFO [train.py:715] (5/8) Epoch 19, batch 33700, loss[loss=0.1043, simple_loss=0.1835, pruned_loss=0.01256, over 4956.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2059, pruned_loss=0.0277, over 971361.79 frames.], batch size: 24, lr: 1.15e-04
2022-05-09 20:32:55,329 INFO [train.py:715] (5/8) Epoch 19, batch 33750, loss[loss=0.1336, simple_loss=0.2048, pruned_loss=0.03117, over 4751.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2061, pruned_loss=0.02782, over 971893.03 frames.], batch size: 19, lr: 1.15e-04
2022-05-09 20:33:34,123 INFO [train.py:715] (5/8) Epoch 19, batch 33800, loss[loss=0.1423, simple_loss=0.2198, pruned_loss=0.0324, over 4976.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2058, pruned_loss=0.02772, over 971916.01 frames.], batch size: 14, lr: 1.15e-04
2022-05-09 20:34:12,732 INFO [train.py:715] (5/8) Epoch 19, batch 33850, loss[loss=0.1217, simple_loss=0.1953, pruned_loss=0.024, over 4965.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.028, over 971849.51 frames.], batch size: 35, lr: 1.15e-04
2022-05-09 20:34:51,527 INFO [train.py:715] (5/8) Epoch 19, batch 33900, loss[loss=0.1316, simple_loss=0.1946, pruned_loss=0.03427, over 4917.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02867, over 971501.27 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:35:31,244 INFO [train.py:715] (5/8) Epoch 19, batch 33950, loss[loss=0.137, simple_loss=0.2054, pruned_loss=0.03432, over 4688.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02877, over 971809.77 frames.], batch size: 15, lr: 1.15e-04
2022-05-09 20:36:10,889 INFO [train.py:715] (5/8) Epoch 19, batch 34000, loss[loss=0.1287, simple_loss=0.1956, pruned_loss=0.0309, over 4937.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02872, over 971641.58 frames.], batch size: 29, lr: 1.15e-04
2022-05-09 20:36:50,179 INFO [train.py:715] (5/8) Epoch 19, batch 34050, loss[loss=0.1316, simple_loss=0.2107, pruned_loss=0.02628, over 4959.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 972140.26 frames.], batch size: 39, lr: 1.15e-04
2022-05-09 20:37:28,968 INFO [train.py:715] (5/8) Epoch 19, batch 34100, loss[loss=0.1863, simple_loss=0.2634, pruned_loss=0.05457, over 4956.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02882, over 971872.02 frames.], batch size: 21, lr: 1.15e-04
2022-05-09 20:38:08,480 INFO [train.py:715] (5/8) Epoch 19, batch 34150, loss[loss=0.1418, simple_loss=0.2304, pruned_loss=0.02661, over 4959.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02838, over 972128.26 frames.], batch size: 21, lr: 1.15e-04
2022-05-09 20:38:48,055 INFO [train.py:715] (5/8) Epoch 19, batch 34200, loss[loss=0.1527, simple_loss=0.2255, pruned_loss=0.03998, over 4867.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02822, over 972925.23 frames.], batch size: 34, lr: 1.15e-04
2022-05-09 20:39:27,597 INFO [train.py:715] (5/8) Epoch 19, batch 34250, loss[loss=0.1169, simple_loss=0.1864, pruned_loss=0.02365, over 4815.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02799, over 972534.63 frames.], batch size: 25, lr: 1.15e-04
2022-05-09 20:40:06,930 INFO [train.py:715] (5/8) Epoch 19, batch 34300, loss[loss=0.1334, simple_loss=0.2109, pruned_loss=0.02796, over 4799.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02797, over 972257.47 frames.], batch size: 14, lr: 1.15e-04
2022-05-09 20:40:46,125 INFO [train.py:715] (5/8) Epoch 19, batch 34350, loss[loss=0.1449, simple_loss=0.2109, pruned_loss=0.03945, over 4776.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2046, pruned_loss=0.02802, over 972776.08 frames.], batch size: 12, lr: 1.15e-04
2022-05-09 20:41:25,881 INFO [train.py:715] (5/8) Epoch 19, batch 34400, loss[loss=0.1288, simple_loss=0.2013, pruned_loss=0.02817, over 4872.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2044, pruned_loss=0.02805, over 971185.73 frames.], batch size: 16, lr: 1.15e-04
2022-05-09 20:42:05,038 INFO [train.py:715] (5/8) Epoch 19, batch 34450, loss[loss=0.1601, simple_loss=0.2403, pruned_loss=0.03992, over 4781.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2043, pruned_loss=0.02797, over 971706.29 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:42:44,559 INFO [train.py:715] (5/8) Epoch 19, batch 34500, loss[loss=0.1311, simple_loss=0.2028, pruned_loss=0.02973, over 4985.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02775, over 972708.50 frames.], batch size: 35, lr: 1.15e-04
2022-05-09 20:43:24,264 INFO [train.py:715] (5/8) Epoch 19, batch 34550, loss[loss=0.1113, simple_loss=0.1874, pruned_loss=0.01758, over 4860.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02817, over 972275.32 frames.], batch size: 20, lr: 1.15e-04
2022-05-09 20:44:03,126 INFO [train.py:715] (5/8) Epoch 19, batch 34600, loss[loss=0.1266, simple_loss=0.2131, pruned_loss=0.02004, over 4917.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02839, over 971409.32 frames.], batch size: 23, lr: 1.15e-04
2022-05-09 20:44:45,165 INFO [train.py:715] (5/8) Epoch 19, batch 34650, loss[loss=0.1186, simple_loss=0.2021, pruned_loss=0.0176, over 4946.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.0283, over 972484.97 frames.], batch size: 21, lr: 1.15e-04
2022-05-09 20:45:24,628 INFO [train.py:715] (5/8) Epoch 19, batch 34700, loss[loss=0.1163, simple_loss=0.1929, pruned_loss=0.01983, over 4864.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02834, over 972121.50 frames.], batch size: 22, lr: 1.15e-04
2022-05-09 20:46:02,676 INFO [train.py:715] (5/8) Epoch 19, batch 34750, loss[loss=0.1098, simple_loss=0.1806, pruned_loss=0.01956, over 4770.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.0282, over 971912.62 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:46:39,962 INFO [train.py:715] (5/8) Epoch 19, batch 34800, loss[loss=0.1234, simple_loss=0.2022, pruned_loss=0.02226, over 4893.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02848, over 971862.79 frames.], batch size: 19, lr: 1.15e-04
2022-05-09 20:46:48,546 INFO [train.py:915] (5/8) Done!