2022-04-28 06:39:03,127 INFO [train.py:827] (4/8) Training started
2022-04-28 06:39:03,127 INFO [train.py:837] (4/8) Device: cuda:4
2022-04-28 06:39:03,161 INFO [train.py:846] (4/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '3b83183234d0f1d8391872630551c5af7c491ed2', 'k2-git-date': 'Tue Apr 12 08:26:41 2022', 'lhotse-version': '1.1.0.dev+missing.version.file', 'torch-version': '1.10.0+cu102', 'torch-cuda-available': True, 'torch-cuda-version': '10.2', 'python-version': '3.8', 'icefall-git-branch': 'deeper-conformer', 'icefall-git-sha1': 'd79f5fe-dirty', 'icefall-git-date': 'Mon Apr 25 17:26:43 2022', 'icefall-path': '/ceph-fj/fangjun/open-source-2/icefall-deeper-conformer', 'k2-path': '/ceph-fj/fangjun/open-source-2/k2-multi-2/k2/python/k2/__init__.py', 'lhotse-path': '/ceph-fj/fangjun/open-source-2/lhotse-multi-3/lhotse/__init__.py', 'hostname': 'de-74279-k2-train-7-0309102938-68688b4cbd-xhtcg', 'IP address': '10.48.32.137'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless4/exp-L'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 6, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 20, 'use_fp16': False, 'num_encoder_layers': 18, 'dim_feedforward': 2048, 'nhead': 8, 'encoder_dim': 512, 'decoder_dim': 512, 'joiner_dim': 512, 'full_libri': True, 'manifest_dir': PosixPath('data/fbank'), 'max_duration': 300, 'bucketing_sampler': True, 'num_buckets': 30, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'on_the_fly_feats': False, 'shuffle': True, 'return_cuts': True, 'num_workers': 2, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'enable_musan': True, 'blank_id': 0, 'vocab_size': 500}
2022-04-28 06:39:03,161 INFO [train.py:848] (4/8) About to create model
2022-04-28 06:39:03,688 INFO [train.py:852] (4/8) Number of model parameters: 118129516
2022-04-28 06:39:09,649 INFO [train.py:858] (4/8) Using DDP
2022-04-28 06:39:10,516 INFO [asr_datamodule.py:391] (4/8) About to get train-clean-100 cuts
2022-04-28 06:39:17,304 INFO [asr_datamodule.py:398] (4/8) About to get train-clean-360 cuts
2022-04-28 06:39:42,109 INFO [asr_datamodule.py:405] (4/8) About to get train-other-500 cuts
2022-04-28 06:40:23,575 INFO [asr_datamodule.py:209] (4/8) Enable MUSAN
2022-04-28 06:40:23,575 INFO [asr_datamodule.py:210] (4/8) About to get Musan cuts
2022-04-28 06:40:24,848 INFO [asr_datamodule.py:238] (4/8) Enable SpecAugment
2022-04-28 06:40:24,848 INFO [asr_datamodule.py:239] (4/8) Time warp factor: 80
2022-04-28 06:40:24,848 INFO [asr_datamodule.py:251] (4/8) Num frame mask: 10
2022-04-28 06:40:24,848 INFO [asr_datamodule.py:264] (4/8) About to create train dataset
2022-04-28 06:40:24,848 INFO [asr_datamodule.py:292] (4/8) Using BucketingSampler.
2022-04-28 06:40:29,535 INFO [asr_datamodule.py:308] (4/8) About to create train dataloader
2022-04-28 06:40:29,536 INFO [asr_datamodule.py:412] (4/8) About to get dev-clean cuts
2022-04-28 06:40:29,806 INFO [asr_datamodule.py:417] (4/8) About to get dev-other cuts
2022-04-28 06:40:29,934 INFO [asr_datamodule.py:339] (4/8) About to create dev dataset
2022-04-28 06:40:29,944 INFO [asr_datamodule.py:358] (4/8) About to create dev dataloader
2022-04-28 06:40:29,945 INFO [train.py:987] (4/8) Sanity check -- see if any of the batches in epoch 0 would cause OOM.
2022-04-28 06:40:42,725 INFO [distributed.py:874] (4/8) Reducer buckets have been rebuilt in this iteration.
2022-04-28 06:41:17,062 INFO [train.py:763] (4/8) Epoch 0, batch 0, loss[loss=0.6391, simple_loss=1.278, pruned_loss=7.02, over 7271.00 frames.], tot_loss[loss=0.6391, simple_loss=1.278, pruned_loss=7.02, over 7271.00 frames.], batch size: 17, lr: 3.00e-03
2022-04-28 06:42:23,563 INFO [train.py:763] (4/8) Epoch 0, batch 50, loss[loss=0.5067, simple_loss=1.013, pruned_loss=6.55, over 7167.00 frames.], tot_loss[loss=0.5708, simple_loss=1.142, pruned_loss=6.957, over 323781.91 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:43:30,297 INFO [train.py:763] (4/8) Epoch 0, batch 100, loss[loss=0.396, simple_loss=0.792, pruned_loss=6.665, over 7010.00 frames.], tot_loss[loss=0.5094, simple_loss=1.019, pruned_loss=6.868, over 566803.75 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:44:37,535 INFO [train.py:763] (4/8) Epoch 0, batch 150, loss[loss=0.3804, simple_loss=0.7609, pruned_loss=6.616, over 6997.00 frames.], tot_loss[loss=0.4761, simple_loss=0.9523, pruned_loss=6.854, over 758181.76 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:45:44,956 INFO [train.py:763] (4/8) Epoch 0, batch 200, loss[loss=0.446, simple_loss=0.8919, pruned_loss=6.827, over 7275.00 frames.], tot_loss[loss=0.4516, simple_loss=0.9031, pruned_loss=6.827, over 908430.83 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:46:50,978 INFO [train.py:763] (4/8) Epoch 0, batch 250, loss[loss=0.4066, simple_loss=0.8132, pruned_loss=6.653, over 7313.00 frames.], tot_loss[loss=0.4359, simple_loss=0.8717, pruned_loss=6.793, over 1017318.61 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:47:58,724 INFO [train.py:763] (4/8) Epoch 0, batch 300, loss[loss=0.4114, simple_loss=0.8229, pruned_loss=6.727, over 7334.00 frames.], tot_loss[loss=0.4234, simple_loss=0.8467, pruned_loss=6.763, over 1109518.70 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:49:06,197 INFO [train.py:763] (4/8) Epoch 0, batch 350, loss[loss=0.358, simple_loss=0.716, pruned_loss=6.497, over 7265.00 frames.], tot_loss[loss=0.4144, simple_loss=0.8288, pruned_loss=6.731, over 1179133.12 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:50:12,115 INFO [train.py:763] (4/8) Epoch 0, batch 400, loss[loss=0.3699, simple_loss=0.7399, pruned_loss=6.586, over 7416.00 frames.], tot_loss[loss=0.4042, simple_loss=0.8085, pruned_loss=6.703, over 1231336.60 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:51:17,801 INFO [train.py:763] (4/8) Epoch 0, batch 450, loss[loss=0.3633, simple_loss=0.7266, pruned_loss=6.748, over 7411.00 frames.], tot_loss[loss=0.3915, simple_loss=0.7831, pruned_loss=6.684, over 1267423.76 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:52:24,498 INFO [train.py:763] (4/8) Epoch 0, batch 500, loss[loss=0.338, simple_loss=0.6761, pruned_loss=6.705, over 7205.00 frames.], tot_loss[loss=0.3756, simple_loss=0.7511, pruned_loss=6.672, over 1303952.73 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:53:29,995 INFO [train.py:763] (4/8) Epoch 0, batch 550, loss[loss=0.2939, simple_loss=0.5879, pruned_loss=6.748, over 7353.00 frames.], tot_loss[loss=0.3609, simple_loss=0.7218, pruned_loss=6.673, over 1330893.34 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:54:36,573 INFO [train.py:763] (4/8) Epoch 0, batch 600, loss[loss=0.3051, simple_loss=0.6103, pruned_loss=6.711, over 7127.00 frames.], tot_loss[loss=0.3456, simple_loss=0.6911, pruned_loss=6.666, over 1350998.97 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:55:42,122 INFO [train.py:763] (4/8) Epoch 0, batch 650, loss[loss=0.229, simple_loss=0.4579, pruned_loss=6.453, over 7007.00 frames.], tot_loss[loss=0.3311, simple_loss=0.6621, pruned_loss=6.655, over 1369531.01 frames.], batch size: 16, lr: 2.99e-03
2022-04-28 06:56:47,772 INFO [train.py:763] (4/8) Epoch 0, batch 700, loss[loss=0.2891, simple_loss=0.5781, pruned_loss=6.723, over 7190.00 frames.], tot_loss[loss=0.3168, simple_loss=0.6336, pruned_loss=6.641, over 1380731.44 frames.], batch size: 23, lr: 2.99e-03
2022-04-28 06:57:54,483 INFO [train.py:763] (4/8) Epoch 0, batch 750, loss[loss=0.249, simple_loss=0.4981, pruned_loss=6.475, over 7282.00 frames.], tot_loss[loss=0.3034, simple_loss=0.6068, pruned_loss=6.62, over 1392316.71 frames.], batch size: 17, lr: 2.98e-03
2022-04-28 06:59:01,267 INFO [train.py:763] (4/8) Epoch 0, batch 800, loss[loss=0.2669, simple_loss=0.5338, pruned_loss=6.655, over 7109.00 frames.], tot_loss[loss=0.2939, simple_loss=0.5878, pruned_loss=6.612, over 1397298.86 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:00:07,430 INFO [train.py:763] (4/8) Epoch 0, batch 850, loss[loss=0.2383, simple_loss=0.4766, pruned_loss=6.592, over 7220.00 frames.], tot_loss[loss=0.284, simple_loss=0.568, pruned_loss=6.599, over 1402376.38 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:01:13,426 INFO [train.py:763] (4/8) Epoch 0, batch 900, loss[loss=0.24, simple_loss=0.48, pruned_loss=6.586, over 7328.00 frames.], tot_loss[loss=0.2754, simple_loss=0.5508, pruned_loss=6.587, over 1407374.77 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:02:19,009 INFO [train.py:763] (4/8) Epoch 0, batch 950, loss[loss=0.2303, simple_loss=0.4606, pruned_loss=6.494, over 7005.00 frames.], tot_loss[loss=0.2696, simple_loss=0.5391, pruned_loss=6.582, over 1405040.20 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:03:26,140 INFO [train.py:763] (4/8) Epoch 0, batch 1000, loss[loss=0.2128, simple_loss=0.4255, pruned_loss=6.45, over 7420.00 frames.], tot_loss[loss=0.2638, simple_loss=0.5276, pruned_loss=6.578, over 1405734.11 frames.], batch size: 17, lr: 2.97e-03
2022-04-28 07:04:32,976 INFO [train.py:763] (4/8) Epoch 0, batch 1050, loss[loss=0.2105, simple_loss=0.421, pruned_loss=6.543, over 7000.00 frames.], tot_loss[loss=0.2586, simple_loss=0.5171, pruned_loss=6.574, over 1407422.06 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:05:39,528 INFO [train.py:763] (4/8) Epoch 0, batch 1100, loss[loss=0.2629, simple_loss=0.5258, pruned_loss=6.741, over 7190.00 frames.], tot_loss[loss=0.2536, simple_loss=0.5072, pruned_loss=6.579, over 1410982.20 frames.], batch size: 22, lr: 2.96e-03
2022-04-28 07:06:46,910 INFO [train.py:763] (4/8) Epoch 0, batch 1150, loss[loss=0.2384, simple_loss=0.4768, pruned_loss=6.476, over 6723.00 frames.], tot_loss[loss=0.2477, simple_loss=0.4954, pruned_loss=6.573, over 1411362.96 frames.], batch size: 31, lr: 2.96e-03
2022-04-28 07:07:52,781 INFO [train.py:763] (4/8) Epoch 0, batch 1200, loss[loss=0.2251, simple_loss=0.4502, pruned_loss=6.655, over 7191.00 frames.], tot_loss[loss=0.2429, simple_loss=0.4858, pruned_loss=6.573, over 1418972.47 frames.], batch size: 26, lr: 2.96e-03
2022-04-28 07:08:58,129 INFO [train.py:763] (4/8) Epoch 0, batch 1250, loss[loss=0.2519, simple_loss=0.5038, pruned_loss=6.656, over 7374.00 frames.], tot_loss[loss=0.24, simple_loss=0.48, pruned_loss=6.577, over 1414156.32 frames.], batch size: 23, lr: 2.95e-03
2022-04-28 07:10:04,042 INFO [train.py:763] (4/8) Epoch 0, batch 1300, loss[loss=0.2196, simple_loss=0.4391, pruned_loss=6.642, over 7315.00 frames.], tot_loss[loss=0.2367, simple_loss=0.4735, pruned_loss=6.583, over 1422399.17 frames.], batch size: 24, lr: 2.95e-03
2022-04-28 07:11:09,798 INFO [train.py:763] (4/8) Epoch 0, batch 1350, loss[loss=0.1945, simple_loss=0.3891, pruned_loss=6.473, over 7147.00 frames.], tot_loss[loss=0.2321, simple_loss=0.4643, pruned_loss=6.578, over 1424095.63 frames.], batch size: 20, lr: 2.95e-03
2022-04-28 07:12:15,112 INFO [train.py:763] (4/8) Epoch 0, batch 1400, loss[loss=0.2116, simple_loss=0.4233, pruned_loss=6.571, over 7280.00 frames.], tot_loss[loss=0.2305, simple_loss=0.4609, pruned_loss=6.588, over 1419433.93 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:13:21,015 INFO [train.py:763] (4/8) Epoch 0, batch 1450, loss[loss=0.207, simple_loss=0.414, pruned_loss=6.476, over 7143.00 frames.], tot_loss[loss=0.2273, simple_loss=0.4547, pruned_loss=6.581, over 1419863.36 frames.], batch size: 17, lr: 2.94e-03
2022-04-28 07:14:26,711 INFO [train.py:763] (4/8) Epoch 0, batch 1500, loss[loss=0.2328, simple_loss=0.4656, pruned_loss=6.695, over 7302.00 frames.], tot_loss[loss=0.2256, simple_loss=0.4512, pruned_loss=6.579, over 1422598.05 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:15:32,246 INFO [train.py:763] (4/8) Epoch 0, batch 1550, loss[loss=0.2253, simple_loss=0.4507, pruned_loss=6.61, over 7115.00 frames.], tot_loss[loss=0.2234, simple_loss=0.4468, pruned_loss=6.577, over 1422816.74 frames.], batch size: 21, lr: 2.93e-03
2022-04-28 07:16:38,326 INFO [train.py:763] (4/8) Epoch 0, batch 1600, loss[loss=0.206, simple_loss=0.4121, pruned_loss=6.551, over 7319.00 frames.], tot_loss[loss=0.2211, simple_loss=0.4421, pruned_loss=6.57, over 1421076.06 frames.], batch size: 20, lr: 2.93e-03
2022-04-28 07:17:45,336 INFO [train.py:763] (4/8) Epoch 0, batch 1650, loss[loss=0.2066, simple_loss=0.4132, pruned_loss=6.56, over 7154.00 frames.], tot_loss[loss=0.2192, simple_loss=0.4384, pruned_loss=6.571, over 1422927.72 frames.], batch size: 18, lr: 2.92e-03
2022-04-28 07:18:51,994 INFO [train.py:763] (4/8) Epoch 0, batch 1700, loss[loss=0.2328, simple_loss=0.4656, pruned_loss=6.587, over 6231.00 frames.], tot_loss[loss=0.2179, simple_loss=0.4357, pruned_loss=6.571, over 1419474.82 frames.], batch size: 37, lr: 2.92e-03
2022-04-28 07:19:58,694 INFO [train.py:763] (4/8) Epoch 0, batch 1750, loss[loss=0.2208, simple_loss=0.4416, pruned_loss=6.548, over 6552.00 frames.], tot_loss[loss=0.2153, simple_loss=0.4306, pruned_loss=6.57, over 1420282.17 frames.], batch size: 38, lr: 2.91e-03
2022-04-28 07:21:06,364 INFO [train.py:763] (4/8) Epoch 0, batch 1800, loss[loss=0.1766, simple_loss=0.3531, pruned_loss=6.429, over 7129.00 frames.], tot_loss[loss=0.2142, simple_loss=0.4283, pruned_loss=6.569, over 1420107.81 frames.], batch size: 28, lr: 2.91e-03
2022-04-28 07:22:12,425 INFO [train.py:763] (4/8) Epoch 0, batch 1850, loss[loss=0.2453, simple_loss=0.4907, pruned_loss=6.439, over 5061.00 frames.], tot_loss[loss=0.2125, simple_loss=0.4251, pruned_loss=6.57, over 1420395.78 frames.], batch size: 52, lr: 2.91e-03
2022-04-28 07:23:18,917 INFO [train.py:763] (4/8) Epoch 0, batch 1900, loss[loss=0.1917, simple_loss=0.3833, pruned_loss=6.576, over 7254.00 frames.], tot_loss[loss=0.2116, simple_loss=0.4233, pruned_loss=6.574, over 1420382.01 frames.], batch size: 19, lr: 2.90e-03
2022-04-28 07:24:26,525 INFO [train.py:763] (4/8) Epoch 0, batch 1950, loss[loss=0.2123, simple_loss=0.4247, pruned_loss=6.684, over 7318.00 frames.], tot_loss[loss=0.2106, simple_loss=0.4212, pruned_loss=6.576, over 1423075.49 frames.], batch size: 21, lr: 2.90e-03
2022-04-28 07:25:34,069 INFO [train.py:763] (4/8) Epoch 0, batch 2000, loss[loss=0.2082, simple_loss=0.4163, pruned_loss=6.51, over 6791.00 frames.], tot_loss[loss=0.2096, simple_loss=0.4193, pruned_loss=6.576, over 1423492.70 frames.], batch size: 15, lr: 2.89e-03
2022-04-28 07:26:39,962 INFO [train.py:763] (4/8) Epoch 0, batch 2050, loss[loss=0.1947, simple_loss=0.3894, pruned_loss=6.568, over 7157.00 frames.], tot_loss[loss=0.2078, simple_loss=0.4157, pruned_loss=6.572, over 1421362.56 frames.], batch size: 26, lr: 2.89e-03
2022-04-28 07:27:45,820 INFO [train.py:763] (4/8) Epoch 0, batch 2100, loss[loss=0.1903, simple_loss=0.3807, pruned_loss=6.443, over 7171.00 frames.], tot_loss[loss=0.2064, simple_loss=0.4129, pruned_loss=6.573, over 1418172.26 frames.], batch size: 18, lr: 2.88e-03
2022-04-28 07:28:51,549 INFO [train.py:763] (4/8) Epoch 0, batch 2150, loss[loss=0.2124, simple_loss=0.4248, pruned_loss=6.738, over 7340.00 frames.], tot_loss[loss=0.2049, simple_loss=0.4098, pruned_loss=6.574, over 1421893.87 frames.], batch size: 22, lr: 2.88e-03
2022-04-28 07:29:57,476 INFO [train.py:763] (4/8) Epoch 0, batch 2200, loss[loss=0.2081, simple_loss=0.4162, pruned_loss=6.683, over 7305.00 frames.], tot_loss[loss=0.2039, simple_loss=0.4078, pruned_loss=6.578, over 1420907.64 frames.], batch size: 25, lr: 2.87e-03
2022-04-28 07:31:03,288 INFO [train.py:763] (4/8) Epoch 0, batch 2250, loss[loss=0.2132, simple_loss=0.4264, pruned_loss=6.711, over 7221.00 frames.], tot_loss[loss=0.2027, simple_loss=0.4054, pruned_loss=6.576, over 1419265.77 frames.], batch size: 21, lr: 2.86e-03
2022-04-28 07:32:08,988 INFO [train.py:763] (4/8) Epoch 0, batch 2300, loss[loss=0.1647, simple_loss=0.3295, pruned_loss=6.446, over 7258.00 frames.], tot_loss[loss=0.2019, simple_loss=0.4039, pruned_loss=6.574, over 1414780.78 frames.], batch size: 19, lr: 2.86e-03
2022-04-28 07:33:14,406 INFO [train.py:763] (4/8) Epoch 0, batch 2350, loss[loss=0.2327, simple_loss=0.4655, pruned_loss=6.57, over 5293.00 frames.], tot_loss[loss=0.2016, simple_loss=0.4033, pruned_loss=6.58, over 1414466.39 frames.], batch size: 52, lr: 2.85e-03
2022-04-28 07:34:20,287 INFO [train.py:763] (4/8) Epoch 0, batch 2400, loss[loss=0.1857, simple_loss=0.3714, pruned_loss=6.545, over 7434.00 frames.], tot_loss[loss=0.2007, simple_loss=0.4014, pruned_loss=6.577, over 1412034.61 frames.], batch size: 20, lr: 2.85e-03
2022-04-28 07:35:25,714 INFO [train.py:763] (4/8) Epoch 0, batch 2450, loss[loss=0.2385, simple_loss=0.4769, pruned_loss=6.667, over 5232.00 frames.], tot_loss[loss=0.2004, simple_loss=0.4007, pruned_loss=6.579, over 1413151.61 frames.], batch size: 52, lr: 2.84e-03
2022-04-28 07:36:32,806 INFO [train.py:763] (4/8) Epoch 0, batch 2500, loss[loss=0.1853, simple_loss=0.3706, pruned_loss=6.668, over 7324.00 frames.], tot_loss[loss=0.1994, simple_loss=0.3987, pruned_loss=6.581, over 1418599.98 frames.], batch size: 20, lr: 2.84e-03
2022-04-28 07:37:40,458 INFO [train.py:763] (4/8) Epoch 0, batch 2550, loss[loss=0.1691, simple_loss=0.3382, pruned_loss=6.443, over 7422.00 frames.], tot_loss[loss=0.1991, simple_loss=0.3982, pruned_loss=6.59, over 1419112.42 frames.], batch size: 18, lr: 2.83e-03
2022-04-28 07:38:46,543 INFO [train.py:763] (4/8) Epoch 0, batch 2600, loss[loss=0.2166, simple_loss=0.4332, pruned_loss=6.717, over 7234.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3966, pruned_loss=6.594, over 1421936.53 frames.], batch size: 20, lr: 2.83e-03
2022-04-28 07:39:52,334 INFO [train.py:763] (4/8) Epoch 0, batch 2650, loss[loss=0.1828, simple_loss=0.3656, pruned_loss=6.527, over 7231.00 frames.], tot_loss[loss=0.197, simple_loss=0.394, pruned_loss=6.592, over 1424001.17 frames.], batch size: 20, lr: 2.82e-03
2022-04-28 07:40:58,203 INFO [train.py:763] (4/8) Epoch 0, batch 2700, loss[loss=0.1985, simple_loss=0.3971, pruned_loss=6.702, over 7138.00 frames.], tot_loss[loss=0.1964, simple_loss=0.3927, pruned_loss=6.59, over 1422995.13 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:42:03,315 INFO [train.py:763] (4/8) Epoch 0, batch 2750, loss[loss=0.1862, simple_loss=0.3723, pruned_loss=6.559, over 7315.00 frames.], tot_loss[loss=0.1962, simple_loss=0.3924, pruned_loss=6.597, over 1422885.98 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:43:09,946 INFO [train.py:763] (4/8) Epoch 0, batch 2800, loss[loss=0.2027, simple_loss=0.4054, pruned_loss=6.624, over 7146.00 frames.], tot_loss[loss=0.1961, simple_loss=0.3921, pruned_loss=6.601, over 1421752.14 frames.], batch size: 20, lr: 2.80e-03
2022-04-28 07:44:16,827 INFO [train.py:763] (4/8) Epoch 0, batch 2850, loss[loss=0.1722, simple_loss=0.3444, pruned_loss=6.465, over 7357.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3898, pruned_loss=6.599, over 1425293.06 frames.], batch size: 19, lr: 2.80e-03
2022-04-28 07:45:22,335 INFO [train.py:763] (4/8) Epoch 0, batch 2900, loss[loss=0.2213, simple_loss=0.4426, pruned_loss=6.697, over 7327.00 frames.], tot_loss[loss=0.1952, simple_loss=0.3904, pruned_loss=6.602, over 1421106.53 frames.], batch size: 20, lr: 2.79e-03
2022-04-28 07:46:27,653 INFO [train.py:763] (4/8) Epoch 0, batch 2950, loss[loss=0.2078, simple_loss=0.4155, pruned_loss=6.635, over 7170.00 frames.], tot_loss[loss=0.1945, simple_loss=0.389, pruned_loss=6.601, over 1416900.75 frames.], batch size: 26, lr: 2.78e-03
2022-04-28 07:47:32,887 INFO [train.py:763] (4/8) Epoch 0, batch 3000, loss[loss=0.3612, simple_loss=0.4123, pruned_loss=1.551, over 7272.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3877, pruned_loss=6.577, over 1421117.19 frames.], batch size: 17, lr: 2.78e-03
2022-04-28 07:47:32,888 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 07:47:50,998 INFO [train.py:792] (4/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
2022-04-28 07:48:57,673 INFO [train.py:763] (4/8) Epoch 0, batch 3050, loss[loss=0.2946, simple_loss=0.4062, pruned_loss=0.9147, over 6579.00 frames.], tot_loss[loss=0.251, simple_loss=0.3965, pruned_loss=5.392, over 1420754.87 frames.], batch size: 38, lr: 2.77e-03
2022-04-28 07:50:04,083 INFO [train.py:763] (4/8) Epoch 0, batch 3100, loss[loss=0.2606, simple_loss=0.4128, pruned_loss=0.5422, over 7418.00 frames.], tot_loss[loss=0.2522, simple_loss=0.3922, pruned_loss=4.332, over 1426452.31 frames.], batch size: 21, lr: 2.77e-03
2022-04-28 07:51:10,053 INFO [train.py:763] (4/8) Epoch 0, batch 3150, loss[loss=0.2357, simple_loss=0.4009, pruned_loss=0.3527, over 7409.00 frames.], tot_loss[loss=0.247, simple_loss=0.3884, pruned_loss=3.461, over 1427561.10 frames.], batch size: 21, lr: 2.76e-03
2022-04-28 07:52:16,816 INFO [train.py:763] (4/8) Epoch 0, batch 3200, loss[loss=0.2287, simple_loss=0.4021, pruned_loss=0.2766, over 7300.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3876, pruned_loss=2.769, over 1423982.13 frames.], batch size: 24, lr: 2.75e-03
2022-04-28 07:53:24,320 INFO [train.py:763] (4/8) Epoch 0, batch 3250, loss[loss=0.1915, simple_loss=0.3465, pruned_loss=0.1825, over 7143.00 frames.], tot_loss[loss=0.236, simple_loss=0.3857, pruned_loss=2.214, over 1423367.96 frames.], batch size: 20, lr: 2.75e-03
2022-04-28 07:54:30,945 INFO [train.py:763] (4/8) Epoch 0, batch 3300, loss[loss=0.2231, simple_loss=0.3976, pruned_loss=0.2428, over 7384.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3861, pruned_loss=1.783, over 1418667.99 frames.], batch size: 23, lr: 2.74e-03
2022-04-28 07:55:37,617 INFO [train.py:763] (4/8) Epoch 0, batch 3350, loss[loss=0.2481, simple_loss=0.4383, pruned_loss=0.2895, over 7307.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3858, pruned_loss=1.434, over 1423304.99 frames.], batch size: 24, lr: 2.73e-03
2022-04-28 07:56:43,234 INFO [train.py:763] (4/8) Epoch 0, batch 3400, loss[loss=0.1815, simple_loss=0.3312, pruned_loss=0.1587, over 7249.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3858, pruned_loss=1.164, over 1423616.78 frames.], batch size: 19, lr: 2.73e-03
2022-04-28 07:57:49,070 INFO [train.py:763] (4/8) Epoch 0, batch 3450, loss[loss=0.2239, simple_loss=0.4058, pruned_loss=0.2107, over 7263.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3857, pruned_loss=0.9532, over 1422546.83 frames.], batch size: 25, lr: 2.72e-03
2022-04-28 07:58:54,326 INFO [train.py:763] (4/8) Epoch 0, batch 3500, loss[loss=0.2249, simple_loss=0.4063, pruned_loss=0.2177, over 7189.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3845, pruned_loss=0.7858, over 1420601.60 frames.], batch size: 26, lr: 2.72e-03
2022-04-28 08:00:00,007 INFO [train.py:763] (4/8) Epoch 0, batch 3550, loss[loss=0.1905, simple_loss=0.3518, pruned_loss=0.1459, over 7216.00 frames.], tot_loss[loss=0.217, simple_loss=0.3826, pruned_loss=0.6532, over 1422577.06 frames.], batch size: 21, lr: 2.71e-03
2022-04-28 08:01:06,047 INFO [train.py:763] (4/8) Epoch 0, batch 3600, loss[loss=0.1857, simple_loss=0.3403, pruned_loss=0.1557, over 7005.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3807, pruned_loss=0.5498, over 1421566.41 frames.], batch size: 16, lr: 2.70e-03
2022-04-28 08:02:21,059 INFO [train.py:763] (4/8) Epoch 0, batch 3650, loss[loss=0.2056, simple_loss=0.3751, pruned_loss=0.1805, over 7232.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3783, pruned_loss=0.4663, over 1422393.96 frames.], batch size: 21, lr: 2.70e-03
2022-04-28 08:04:03,464 INFO [train.py:763] (4/8) Epoch 0, batch 3700, loss[loss=0.2089, simple_loss=0.3834, pruned_loss=0.1726, over 6652.00 frames.], tot_loss[loss=0.21, simple_loss=0.377, pruned_loss=0.4016, over 1425816.73 frames.], batch size: 31, lr: 2.69e-03
2022-04-28 08:05:34,887 INFO [train.py:763] (4/8) Epoch 0, batch 3750, loss[loss=0.1933, simple_loss=0.3532, pruned_loss=0.1671, over 7284.00 frames.], tot_loss[loss=0.2084, simple_loss=0.3755, pruned_loss=0.3521, over 1417383.62 frames.], batch size: 18, lr: 2.68e-03
2022-04-28 08:06:40,594 INFO [train.py:763] (4/8) Epoch 0, batch 3800, loss[loss=0.1771, simple_loss=0.3256, pruned_loss=0.1435, over 7120.00 frames.], tot_loss[loss=0.207, simple_loss=0.3743, pruned_loss=0.3119, over 1417193.68 frames.], batch size: 17, lr: 2.68e-03
2022-04-28 08:07:46,189 INFO [train.py:763] (4/8) Epoch 0, batch 3850, loss[loss=0.1736, simple_loss=0.3223, pruned_loss=0.1246, over 7131.00 frames.], tot_loss[loss=0.2055, simple_loss=0.3727, pruned_loss=0.2791, over 1422609.68 frames.], batch size: 17, lr: 2.67e-03
2022-04-28 08:08:52,444 INFO [train.py:763] (4/8) Epoch 0, batch 3900, loss[loss=0.1936, simple_loss=0.3537, pruned_loss=0.1679, over 7226.00 frames.], tot_loss[loss=0.2049, simple_loss=0.3725, pruned_loss=0.255, over 1419714.16 frames.], batch size: 16, lr: 2.66e-03
2022-04-28 08:09:58,857 INFO [train.py:763] (4/8) Epoch 0, batch 3950, loss[loss=0.1794, simple_loss=0.33, pruned_loss=0.1441, over 6821.00 frames.], tot_loss[loss=0.203, simple_loss=0.37, pruned_loss=0.2342, over 1417516.29 frames.], batch size: 15, lr: 2.66e-03
2022-04-28 08:11:04,203 INFO [train.py:763] (4/8) Epoch 0, batch 4000, loss[loss=0.2106, simple_loss=0.3895, pruned_loss=0.1591, over 7322.00 frames.], tot_loss[loss=0.2034, simple_loss=0.3712, pruned_loss=0.2191, over 1419856.17 frames.], batch size: 21, lr: 2.65e-03
2022-04-28 08:12:09,507 INFO [train.py:763] (4/8) Epoch 0, batch 4050, loss[loss=0.1912, simple_loss=0.3551, pruned_loss=0.1368, over 7080.00 frames.], tot_loss[loss=0.2026, simple_loss=0.3705, pruned_loss=0.2063, over 1421785.01 frames.], batch size: 28, lr: 2.64e-03
2022-04-28 08:13:15,838 INFO [train.py:763] (4/8) Epoch 0, batch 4100, loss[loss=0.1798, simple_loss=0.3332, pruned_loss=0.1314, over 7254.00 frames.], tot_loss[loss=0.2004, simple_loss=0.367, pruned_loss=0.1938, over 1421579.95 frames.], batch size: 19, lr: 2.64e-03
2022-04-28 08:14:22,418 INFO [train.py:763] (4/8) Epoch 0, batch 4150, loss[loss=0.167, simple_loss=0.3108, pruned_loss=0.1161, over 7060.00 frames.], tot_loss[loss=0.2005, simple_loss=0.3676, pruned_loss=0.186, over 1425944.08 frames.], batch size: 18, lr: 2.63e-03
2022-04-28 08:15:27,427 INFO [train.py:763] (4/8) Epoch 0, batch 4200, loss[loss=0.1978, simple_loss=0.3662, pruned_loss=0.1475, over 7199.00 frames.], tot_loss[loss=0.2005, simple_loss=0.368, pruned_loss=0.18, over 1425058.67 frames.], batch size: 22, lr: 2.63e-03
2022-04-28 08:16:32,481 INFO [train.py:763] (4/8) Epoch 0, batch 4250, loss[loss=0.1766, simple_loss=0.3309, pruned_loss=0.112, over 7439.00 frames.], tot_loss[loss=0.2008, simple_loss=0.3689, pruned_loss=0.1756, over 1423638.07 frames.], batch size: 20, lr: 2.62e-03
2022-04-28 08:17:38,263 INFO [train.py:763] (4/8) Epoch 0, batch 4300, loss[loss=0.1929, simple_loss=0.356, pruned_loss=0.1486, over 7056.00 frames.], tot_loss[loss=0.2003, simple_loss=0.3681, pruned_loss=0.1717, over 1422735.60 frames.], batch size: 28, lr: 2.61e-03
2022-04-28 08:18:43,769 INFO [train.py:763] (4/8) Epoch 0, batch 4350, loss[loss=0.1959, simple_loss=0.36, pruned_loss=0.1597, over 7432.00 frames.], tot_loss[loss=0.2007, simple_loss=0.3691, pruned_loss=0.1689, over 1426742.24 frames.], batch size: 20, lr: 2.61e-03
2022-04-28 08:19:48,915 INFO [train.py:763] (4/8) Epoch 0, batch 4400, loss[loss=0.1955, simple_loss=0.3563, pruned_loss=0.1731, over 7265.00 frames.], tot_loss[loss=0.2007, simple_loss=0.3692, pruned_loss=0.1661, over 1424218.74 frames.], batch size: 18, lr: 2.60e-03
2022-04-28 08:20:54,080 INFO [train.py:763] (4/8) Epoch 0, batch 4450, loss[loss=0.1844, simple_loss=0.343, pruned_loss=0.129, over 7431.00 frames.], tot_loss[loss=0.2012, simple_loss=0.3704, pruned_loss=0.1642, over 1423641.74 frames.], batch size: 20, lr: 2.59e-03
2022-04-28 08:21:59,569 INFO [train.py:763] (4/8) Epoch 0, batch 4500, loss[loss=0.2344, simple_loss=0.4292, pruned_loss=0.1977, over 6773.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3702, pruned_loss=0.1615, over 1413795.13 frames.], batch size: 38, lr: 2.59e-03
2022-04-28 08:23:05,614 INFO [train.py:763] (4/8) Epoch 0, batch 4550, loss[loss=0.1967, simple_loss=0.3648, pruned_loss=0.1432, over 5137.00 frames.], tot_loss[loss=0.2018, simple_loss=0.3718, pruned_loss=0.1616, over 1395368.92 frames.], batch size: 52, lr: 2.58e-03
2022-04-28 08:24:44,868 INFO [train.py:763] (4/8) Epoch 1, batch 0, loss[loss=0.1974, simple_loss=0.3647, pruned_loss=0.1507, over 7139.00 frames.], tot_loss[loss=0.1974, simple_loss=0.3647, pruned_loss=0.1507, over 7139.00 frames.], batch size: 26, lr: 2.56e-03
2022-04-28 08:25:50,517 INFO [train.py:763] (4/8) Epoch 1, batch 50, loss[loss=0.1881, simple_loss=0.351, pruned_loss=0.1262, over 7228.00 frames.], tot_loss[loss=0.1994, simple_loss=0.3676, pruned_loss=0.156, over 311111.01 frames.], batch size: 20, lr: 2.55e-03
2022-04-28 08:26:56,236 INFO [train.py:763] (4/8) Epoch 1, batch 100, loss[loss=0.1898, simple_loss=0.3508, pruned_loss=0.1441, over 7433.00 frames.], tot_loss[loss=0.1966, simple_loss=0.3632, pruned_loss=0.1496, over 558745.00 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:28:01,395 INFO [train.py:763] (4/8) Epoch 1, batch 150, loss[loss=0.197, simple_loss=0.3641, pruned_loss=0.1489, over 7330.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3603, pruned_loss=0.1468, over 749423.20 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:29:06,943 INFO [train.py:763] (4/8) Epoch 1, batch 200, loss[loss=0.1685, simple_loss=0.3177, pruned_loss=0.09587, over 7161.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3586, pruned_loss=0.1445, over 899402.64 frames.], batch size: 19, lr: 2.53e-03
2022-04-28 08:30:12,403 INFO [train.py:763] (4/8) Epoch 1, batch 250, loss[loss=0.2031, simple_loss=0.3782, pruned_loss=0.1398, over 7377.00 frames.], tot_loss[loss=0.194, simple_loss=0.3592, pruned_loss=0.1441, over 1014649.31 frames.], batch size: 23, lr: 2.53e-03
2022-04-28 08:31:17,598 INFO [train.py:763] (4/8) Epoch 1, batch 300, loss[loss=0.2015, simple_loss=0.3729, pruned_loss=0.151, over 7251.00 frames.], tot_loss[loss=0.1949, simple_loss=0.3609, pruned_loss=0.1444, over 1104050.87 frames.], batch size: 19, lr: 2.52e-03
2022-04-28 08:32:23,177 INFO [train.py:763] (4/8) Epoch 1, batch 350, loss[loss=0.1826, simple_loss=0.3408, pruned_loss=0.1216, over 7218.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3604, pruned_loss=0.1444, over 1173207.63 frames.], batch size: 21, lr: 2.51e-03
2022-04-28 08:33:29,295 INFO [train.py:763] (4/8) Epoch 1, batch 400, loss[loss=0.2032, simple_loss=0.3757, pruned_loss=0.153, over 7145.00 frames.], tot_loss[loss=0.1944, simple_loss=0.3601, pruned_loss=0.1437, over 1229849.51 frames.], batch size: 20, lr: 2.51e-03
2022-04-28 08:34:36,146 INFO [train.py:763] (4/8) Epoch 1, batch 450, loss[loss=0.183, simple_loss=0.3389, pruned_loss=0.1353, over 7169.00 frames.], tot_loss[loss=0.1936, simple_loss=0.359, pruned_loss=0.1416, over 1275148.48 frames.], batch size: 19, lr: 2.50e-03
2022-04-28 08:35:42,354 INFO [train.py:763] (4/8) Epoch 1, batch 500, loss[loss=0.1698, simple_loss=0.3159, pruned_loss=0.118, over 7160.00 frames.], tot_loss[loss=0.1929, simple_loss=0.3577, pruned_loss=0.1402, over 1307416.14 frames.], batch size: 18, lr: 2.49e-03
2022-04-28 08:36:48,842 INFO [train.py:763] (4/8) Epoch 1, batch 550, loss[loss=0.1876, simple_loss=0.3467, pruned_loss=0.1427, over 7355.00 frames.], tot_loss[loss=0.1927, simple_loss=0.3574, pruned_loss=0.1401, over 1332158.96 frames.], batch size: 19, lr: 2.49e-03
2022-04-28 08:37:55,691 INFO [train.py:763] (4/8) Epoch 1, batch 600, loss[loss=0.2094, simple_loss=0.3853, pruned_loss=0.1681, over 7379.00 frames.], tot_loss[loss=0.1934, simple_loss=0.3588, pruned_loss=0.1406, over 1352902.84 frames.], batch size: 23, lr: 2.48e-03
2022-04-28 08:39:01,282 INFO [train.py:763] (4/8) Epoch 1, batch 650, loss[loss=0.182, simple_loss=0.3384, pruned_loss=0.128, over 7283.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3592, pruned_loss=0.1411, over 1367414.22 frames.], batch size: 18, lr: 2.48e-03
2022-04-28 08:40:06,980 INFO [train.py:763] (4/8) Epoch 1, batch 700, loss[loss=0.2338, simple_loss=0.425, pruned_loss=0.2132, over 4987.00 frames.], tot_loss[loss=0.1931, simple_loss=0.3583, pruned_loss=0.14, over 1379554.33 frames.], batch size: 52, lr: 2.47e-03
2022-04-28 08:41:12,395 INFO [train.py:763] (4/8) Epoch 1, batch 750, loss[loss=0.198, simple_loss=0.3664, pruned_loss=0.148, over 7251.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3594, pruned_loss=0.1405, over 1391192.98 frames.], batch size: 19, lr: 2.46e-03
2022-04-28 08:42:18,199 INFO [train.py:763] (4/8) Epoch 1, batch 800, loss[loss=0.1849, simple_loss=0.3439, pruned_loss=0.1289, over 7453.00 frames.], tot_loss[loss=0.1926, simple_loss=0.3574, pruned_loss=0.1387, over 1401124.59 frames.], batch size: 19, lr: 2.46e-03
2022-04-28 08:43:24,113 INFO [train.py:763] (4/8) Epoch 1, batch 850, loss[loss=0.1867, simple_loss=0.3499, pruned_loss=0.1168, over 7323.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3556, pruned_loss=0.1376, over 1408349.72 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:44:29,822 INFO [train.py:763] (4/8) Epoch 1, batch 900, loss[loss=0.164, simple_loss=0.3103, pruned_loss=0.0887, over 7436.00 frames.], tot_loss[loss=0.1916, simple_loss=0.3557, pruned_loss=0.1377, over 1412655.65 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:45:35,247 INFO [train.py:763] (4/8) Epoch 1, batch 950, loss[loss=0.1713, simple_loss=0.3201, pruned_loss=0.1119, over 7260.00 frames.], tot_loss[loss=0.1917, simple_loss=0.3558, pruned_loss=0.1375, over 1415146.16 frames.], batch size: 19, lr: 2.44e-03
2022-04-28 08:46:40,815 INFO [train.py:763] (4/8) Epoch 1, batch 1000, loss[loss=0.1861, simple_loss=0.3463, pruned_loss=0.1299, over 6752.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3541, pruned_loss=0.1356, over 1416392.47 frames.], batch size: 31, lr: 2.43e-03
2022-04-28 08:47:46,477 INFO [train.py:763] (4/8) Epoch 1, batch 1050, loss[loss=0.1837, simple_loss=0.3431, pruned_loss=0.1213, over 7424.00 frames.], tot_loss[loss=0.1904, simple_loss=0.3538, pruned_loss=0.1354, over 1418256.37 frames.], batch size: 20, lr: 2.43e-03
2022-04-28 08:48:51,691 INFO [train.py:763] (4/8) Epoch 1, batch 1100, loss[loss=0.1846, simple_loss=0.3427, pruned_loss=0.1329, over 7161.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3542, pruned_loss=0.1348, over 1420120.83 frames.], batch size: 18, lr: 2.42e-03
2022-04-28 08:49:57,303 INFO [train.py:763] (4/8) Epoch 1, batch 1150, loss[loss=0.1877, simple_loss=0.3491, pruned_loss=0.1312, over 7229.00 frames.], tot_loss[loss=0.19, simple_loss=0.3532, pruned_loss=0.1338, over 1423776.37 frames.], batch size: 20, lr: 2.41e-03
2022-04-28 08:51:02,488 INFO [train.py:763] (4/8) Epoch 1, batch 1200, loss[loss=0.2125, simple_loss=0.3952, pruned_loss=0.1486, over 7037.00 frames.], tot_loss[loss=0.1901, simple_loss=0.3534, pruned_loss=0.1336, over 1423052.42 frames.], batch size: 28, lr: 2.41e-03
2022-04-28 08:52:07,803 INFO [train.py:763] (4/8) Epoch 1, batch 1250, loss[loss=0.1724, simple_loss=0.3233, pruned_loss=0.1079, over 7283.00 frames.], tot_loss[loss=0.1899, simple_loss=0.3533, pruned_loss=0.133, over 1424088.22 frames.], batch size: 18, lr: 2.40e-03
2022-04-28 08:53:12,957 INFO [train.py:763] (4/8) Epoch 1, batch 1300, loss[loss=0.2082, simple_loss=0.3838, pruned_loss=0.163, over 7219.00 frames.], tot_loss[loss=0.19, simple_loss=0.3534, pruned_loss=0.1332, over 1417768.83 frames.], batch size: 21, lr: 2.40e-03
2022-04-28 08:54:18,348 INFO [train.py:763] (4/8) Epoch 1, batch 1350, loss[loss=0.1576, simple_loss=0.298, pruned_loss=0.08668, over 7286.00 frames.], tot_loss[loss=0.189, simple_loss=0.3518, pruned_loss=0.1314, over 1420656.68 frames.], batch size: 17, lr: 2.39e-03
2022-04-28 08:55:23,445 INFO [train.py:763] (4/8) Epoch 1, batch 1400, loss[loss=0.1972, simple_loss=0.3671, pruned_loss=0.137, over 7230.00 frames.], tot_loss[loss=0.1896, simple_loss=0.3528, pruned_loss=0.1325, over 1419279.77 frames.], batch size: 21, lr: 2.39e-03
2022-04-28 08:56:28,946 INFO [train.py:763] (4/8) Epoch 1, batch 1450, loss[loss=0.3307, simple_loss=0.374, pruned_loss=0.1437, over 7176.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3547, pruned_loss=0.1352, over 1422972.88 frames.], batch size: 26, lr: 2.38e-03
2022-04-28 08:57:34,411 INFO [train.py:763] (4/8) Epoch 1, batch 1500, loss[loss=0.3788, simple_loss=0.4134, pruned_loss=0.1721, over 6397.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3572, pruned_loss=0.1363, over 1422008.46 frames.], batch size: 38, lr: 2.37e-03
2022-04-28 08:58:40,146 INFO [train.py:763] (4/8) Epoch 1, batch 1550, loss[loss=0.263, simple_loss=0.3203, pruned_loss=0.1028, over 7419.00 frames.], tot_loss[loss=0.2545, simple_loss=0.357, pruned_loss=0.1347, over 1425357.12 frames.], batch size: 20, lr: 2.37e-03
2022-04-28 08:59:47,366 INFO [train.py:763] (4/8) Epoch 1, batch 1600, loss[loss=0.2847, simple_loss=0.3315, pruned_loss=0.119, over 7161.00 frames.], tot_loss[loss=0.2641, simple_loss=0.3548, pruned_loss=0.1325, over 1424094.76 frames.], batch size: 18, lr: 2.36e-03
2022-04-28 09:00:52,891 INFO [train.py:763] (4/8) Epoch 1, batch 1650, loss[loss=0.308, simple_loss=0.3635, pruned_loss=0.1263, over 7441.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3559, pruned_loss=0.1322, over 1424806.70 frames.], batch size: 20, lr: 2.36e-03
2022-04-28 09:01:59,213 INFO [train.py:763] (4/8) Epoch 1, batch 1700, loss[loss=0.3662, simple_loss=0.4018, pruned_loss=0.1653, over 7415.00 frames.], tot_loss[loss=0.281, simple_loss=0.3555, pruned_loss=0.131, over 1424348.15 frames.], batch size: 21, lr: 2.35e-03
2022-04-28 09:03:06,111 INFO [train.py:763] (4/8) Epoch 1, batch 1750, loss[loss=0.2425, simple_loss=0.3054, pruned_loss=0.08977, over 7277.00 frames.], tot_loss[loss=0.2873, simple_loss=0.3564, pruned_loss=0.1307, over 1424277.23 frames.], batch size: 18, lr: 2.34e-03
2022-04-28 09:04:13,392 INFO [train.py:763] (4/8) Epoch 1, batch 1800, loss[loss=0.2908, simple_loss=0.3516, pruned_loss=0.115, over 7354.00 frames.], tot_loss[loss=0.2902, simple_loss=0.3555, pruned_loss=0.1292, over 1425199.88 frames.], batch size: 19, lr: 2.34e-03
2022-04-28 09:05:20,641 INFO [train.py:763] (4/8) Epoch 1, batch 1850, loss[loss=0.2983, simple_loss=0.3555, pruned_loss=0.1205, over 7325.00 frames.], tot_loss[loss=0.2907, simple_loss=0.3535, pruned_loss=0.127, over 1425571.85 frames.], batch size: 20, lr: 2.33e-03
2022-04-28 09:06:26,263 INFO [train.py:763] (4/8) Epoch 1, batch 1900, loss[loss=0.227, simple_loss=0.2961, pruned_loss=0.07893, over 6992.00 frames.], tot_loss[loss=0.2941, simple_loss=0.3551, pruned_loss=0.1267, over 1429679.74 frames.], batch size: 16, lr: 2.33e-03
2022-04-28 09:07:32,760 INFO [train.py:763] (4/8) Epoch 1, batch 1950, loss[loss=0.214, simple_loss=0.2908, pruned_loss=0.06855, over 7295.00 frames.], tot_loss[loss=0.2971, simple_loss=0.3565, pruned_loss=0.1268, over 1430151.98 frames.], batch size: 18, lr: 2.32e-03
2022-04-28 09:08:38,159 INFO [train.py:763] (4/8) Epoch 1, batch 2000, loss[loss=0.3327, simple_loss=0.3857, pruned_loss=0.1398, over 7122.00 frames.], tot_loss[loss=0.3002, simple_loss=0.3581, pruned_loss=0.1272, over 1424222.39 frames.], batch size: 21, lr: 2.32e-03
2022-04-28 09:09:44,442 INFO [train.py:763] (4/8) Epoch 1, batch 2050, loss[loss=0.317, simple_loss=0.3695, pruned_loss=0.1322, over 7061.00 frames.], tot_loss[loss=0.3, simple_loss=0.3568, pruned_loss=0.1264, over 1424530.07 frames.], batch size: 28, lr: 2.31e-03
2022-04-28 09:10:49,767 INFO [train.py:763] (4/8) Epoch 1, batch 2100, loss[loss=0.294, simple_loss=0.349, pruned_loss=0.1195, over 7427.00 frames.], tot_loss[loss=0.3005, simple_loss=0.357, pruned_loss=0.1258, over 1424928.42 frames.], batch size: 18, lr: 2.31e-03
2022-04-28 09:11:55,362 INFO [train.py:763] (4/8) Epoch 1, batch 2150, loss[loss=0.3369, simple_loss=0.3926, pruned_loss=0.1406, over 7411.00 frames.], tot_loss[loss=0.3022, simple_loss=0.3575, pruned_loss=0.1264, over 1423461.21 frames.], batch size: 21, lr: 2.30e-03
2022-04-28 09:13:01,254 INFO [train.py:763] (4/8) Epoch 1, batch 2200, loss[loss=0.3282, simple_loss=0.3774, pruned_loss=0.1395, over 7110.00 frames.], tot_loss[loss=0.3008, simple_loss=0.3565, pruned_loss=0.1248, over 1423141.72 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:14:06,867 INFO [train.py:763] (4/8) Epoch 1, batch 2250, loss[loss=0.3245, simple_loss=0.3715, pruned_loss=0.1387, over 7225.00 frames.], tot_loss[loss=0.2995, simple_loss=0.3557, pruned_loss=0.1234, over 1424382.65 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:15:14,109 INFO [train.py:763] (4/8) Epoch 1, batch 2300, loss[loss=0.338, simple_loss=0.3697, pruned_loss=0.1532, over 7197.00 frames.], tot_loss[loss=0.3009, simple_loss=0.3563, pruned_loss=0.1241, over 1424844.15 frames.], batch size: 22, lr: 2.28e-03
2022-04-28 09:16:21,354 INFO [train.py:763] (4/8) Epoch 1, batch 2350, loss[loss=0.3339, simple_loss=0.3918, pruned_loss=0.138, over 7232.00 frames.], tot_loss[loss=0.3019, simple_loss=0.3573, pruned_loss=0.1243, over 1422951.37 frames.], batch size: 20, lr: 2.28e-03
2022-04-28 09:17:26,497 INFO [train.py:763] (4/8) Epoch 1, batch 2400, loss[loss=0.3202, simple_loss=0.3831, pruned_loss=0.1286, over 7313.00 frames.], tot_loss[loss=0.3001, simple_loss=0.3561, pruned_loss=0.1228, over 1423566.94 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:18:31,928 INFO [train.py:763] (4/8) Epoch 1, batch 2450, loss[loss=0.2943, simple_loss=0.3537, pruned_loss=0.1174, over 7319.00 frames.], tot_loss[loss=0.2997, simple_loss=0.3559, pruned_loss=0.1224, over 1426930.59 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:19:37,096 INFO [train.py:763] (4/8) Epoch 1, batch 2500, loss[loss=0.3625, simple_loss=0.4106, pruned_loss=0.1572, over 7167.00 frames.], tot_loss[loss=0.3007, simple_loss=0.3569, pruned_loss=0.1227, over 1427277.04 frames.], batch size: 26, lr: 2.26e-03
2022-04-28 09:20:43,298 INFO [train.py:763] (4/8) Epoch 1, batch 2550, loss[loss=0.343, simple_loss=0.3627, pruned_loss=0.1616, over 7414.00 frames.], tot_loss[loss=0.3025, simple_loss=0.358, pruned_loss=0.1238, over 1427792.39 frames.], batch size: 17, lr: 2.26e-03
2022-04-28 09:21:48,825 INFO [train.py:763] (4/8) Epoch 1, batch 2600, loss[loss=0.3453, simple_loss=0.3882, pruned_loss=0.1512, over 7187.00 frames.], tot_loss[loss=0.2989, simple_loss=0.3552, pruned_loss=0.1216, over 1429148.76 frames.], batch size: 26, lr: 2.25e-03
2022-04-28 09:22:54,014 INFO [train.py:763] (4/8) Epoch 1, batch 2650, loss[loss=0.3452, simple_loss=0.3865, pruned_loss=0.1519, over 6349.00 frames.], tot_loss[loss=0.297, simple_loss=0.3536, pruned_loss=0.1205, over 1427897.57 frames.], batch size: 38, lr: 2.25e-03
2022-04-28 09:24:00,440 INFO [train.py:763] (4/8) Epoch 1, batch 2700, loss[loss=0.3982, simple_loss=0.428, pruned_loss=0.1842, over 6952.00 frames.], tot_loss[loss=0.2956, simple_loss=0.3528, pruned_loss=0.1194, over 1427360.67 frames.], batch size: 32, lr: 2.24e-03
2022-04-28 09:25:06,553 INFO [train.py:763] (4/8) Epoch 1, batch 2750, loss[loss=0.3005, simple_loss=0.3592, pruned_loss=0.121, over 7279.00 frames.], tot_loss[loss=0.2964, simple_loss=0.3531, pruned_loss=0.12, over 1423427.14 frames.], batch size: 24, lr: 2.24e-03
2022-04-28 09:26:12,249 INFO [train.py:763] (4/8) Epoch 1, batch 2800, loss[loss=0.3043, simple_loss=0.3587, pruned_loss=0.125, over 7191.00 frames.], tot_loss[loss=0.2954, simple_loss=0.3529, pruned_loss=0.119, over 1426955.57 frames.], batch size: 23, lr: 2.23e-03
2022-04-28 09:27:17,543 INFO [train.py:763] (4/8) Epoch 1, batch 2850, loss[loss=0.2932, simple_loss=0.3525, pruned_loss=0.117, over 7284.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3517, pruned_loss=0.1176, over 1426058.91 frames.], batch size: 24, lr: 2.23e-03
2022-04-28 09:28:22,520 INFO [train.py:763] (4/8) Epoch 1, batch 2900, loss[loss=0.2911, simple_loss=0.3634, pruned_loss=0.1094, over 7232.00 frames.], tot_loss[loss=0.2946, simple_loss=0.3527, pruned_loss=0.1183, over 1420994.45 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:29:27,934 INFO [train.py:763] (4/8) Epoch 1, batch 2950, loss[loss=0.3293, simple_loss=0.3781, pruned_loss=0.1402, over 7244.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3521, pruned_loss=0.1174, over 1421978.42 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:30:33,551 INFO [train.py:763] (4/8) Epoch 1, batch 3000, loss[loss=0.2259, simple_loss=0.2888, pruned_loss=0.08146, over 7263.00 frames.], tot_loss[loss=0.2923, simple_loss=0.351, pruned_loss=0.1168, over 1426515.54 frames.], batch size: 17, lr: 2.21e-03
2022-04-28 09:30:33,552 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 09:30:49,513 INFO [train.py:792] (4/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
2022-04-28 09:31:55,881 INFO [train.py:763] (4/8) Epoch 1, batch 3050, loss[loss=0.2873, simple_loss=0.3267, pruned_loss=0.1239, over 7279.00 frames.], tot_loss[loss=0.2936, simple_loss=0.3518, pruned_loss=0.1178, over 1421789.58 frames.], batch size: 18, lr: 2.20e-03
2022-04-28 09:33:01,967 INFO [train.py:763] (4/8) Epoch 1, batch 3100, loss[loss=0.4126, simple_loss=0.4194, pruned_loss=0.2029, over 4842.00 frames.], tot_loss[loss=0.2942, simple_loss=0.3521, pruned_loss=0.1182, over 1420939.33 frames.], batch size: 53, lr: 2.20e-03
2022-04-28 09:34:07,382 INFO [train.py:763] (4/8) Epoch 1, batch 3150, loss[loss=0.2352, simple_loss=0.2932, pruned_loss=0.08865, over 6790.00 frames.], tot_loss[loss=0.2923, simple_loss=0.351, pruned_loss=0.1168, over 1423338.22 frames.], batch size: 15, lr: 2.19e-03
2022-04-28 09:35:13,545 INFO [train.py:763] (4/8) Epoch 1, batch 3200, loss[loss=0.4082, simple_loss=0.4357, pruned_loss=0.1904, over 4915.00 frames.], tot_loss[loss=0.2942, simple_loss=0.3526, pruned_loss=0.1179, over 1412818.79 frames.], batch size: 52, lr: 2.19e-03
2022-04-28 09:36:19,395 INFO [train.py:763] (4/8) Epoch 1, batch 3250, loss[loss=0.31, simple_loss=0.3606, pruned_loss=0.1297, over 7199.00 frames.], tot_loss[loss=0.2929, simple_loss=0.3524, pruned_loss=0.1167, over 1415692.45 frames.], batch size: 23, lr: 2.18e-03
2022-04-28 09:37:26,020 INFO [train.py:763] (4/8) Epoch 1, batch 3300, loss[loss=0.2944, simple_loss=0.3575, pruned_loss=0.1157, over 7205.00 frames.], tot_loss[loss=0.2893, simple_loss=0.3498, pruned_loss=0.1144, over 1420431.52 frames.], batch size: 22, lr: 2.18e-03
2022-04-28 09:38:31,144 INFO [train.py:763] (4/8) Epoch 1, batch 3350, loss[loss=0.2859, simple_loss=0.351, pruned_loss=0.1104, over 7196.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3511, pruned_loss=0.1149, over 1422867.90 frames.], batch size: 26, lr: 2.18e-03
2022-04-28 09:39:36,457 INFO [train.py:763] (4/8) Epoch 1, batch 3400, loss[loss=0.2236, simple_loss=0.2956, pruned_loss=0.07582, over 7148.00 frames.], tot_loss[loss=0.2894, simple_loss=0.3498, pruned_loss=0.1145, over 1424706.44 frames.], batch size: 17, lr: 2.17e-03
2022-04-28 09:40:52,291 INFO [train.py:763] (4/8) Epoch 1, batch 3450, loss[loss=0.332, simple_loss=0.4081, pruned_loss=0.128, over 7262.00 frames.], tot_loss[loss=0.2895, simple_loss=0.3501, pruned_loss=0.1144, over 1426583.63 frames.], batch size: 24, lr: 2.17e-03
2022-04-28 09:41:59,069 INFO [train.py:763] (4/8) Epoch 1, batch 3500, loss[loss=0.3456, simple_loss=0.3914, pruned_loss=0.1499, over 6356.00 frames.], tot_loss[loss=0.2898, simple_loss=0.3506, pruned_loss=0.1145, over 1423495.59 frames.], batch size: 37, lr: 2.16e-03
2022-04-28 09:43:05,801 INFO [train.py:763] (4/8) Epoch 1, batch 3550, loss[loss=0.3147, simple_loss=0.383, pruned_loss=0.1232, over 7264.00 frames.], tot_loss[loss=0.2906, simple_loss=0.3515, pruned_loss=0.1148, over 1423600.87 frames.], batch size: 25, lr: 2.16e-03
2022-04-28 09:44:12,972 INFO [train.py:763] (4/8) Epoch 1, batch 3600, loss[loss=0.2959, simple_loss=0.3517, pruned_loss=0.1201, over 7223.00 frames.], tot_loss[loss=0.2904, simple_loss=0.3516, pruned_loss=0.1146, over 1425019.05 frames.], batch size: 20, lr: 2.15e-03
2022-04-28 09:45:20,591 INFO [train.py:763] (4/8) Epoch 1, batch 3650, loss[loss=0.3503, simple_loss=0.3853, pruned_loss=0.1577, over 6813.00 frames.], tot_loss[loss=0.2894, simple_loss=0.3508, pruned_loss=0.114, over 1427057.33 frames.], batch size: 15, lr: 2.15e-03
2022-04-28 09:46:27,938 INFO [train.py:763] (4/8) Epoch 1, batch 3700, loss[loss=0.2972, simple_loss=0.3452, pruned_loss=0.1246, over 7172.00 frames.], tot_loss[loss=0.2902, simple_loss=0.3517, pruned_loss=0.1144, over 1429562.97 frames.], batch size: 19, lr: 2.14e-03
2022-04-28 09:47:33,410 INFO [train.py:763] (4/8) Epoch 1, batch 3750, loss[loss=0.3437, simple_loss=0.3938, pruned_loss=0.1468, over 7260.00 frames.], tot_loss[loss=0.289, simple_loss=0.3511, pruned_loss=0.1135, over 1430086.75 frames.], batch size: 24, lr: 2.14e-03
2022-04-28 09:48:38,885 INFO [train.py:763] (4/8) Epoch 1, batch 3800, loss[loss=0.2512, simple_loss=0.3213, pruned_loss=0.09057, over 6777.00 frames.], tot_loss[loss=0.2873, simple_loss=0.35, pruned_loss=0.1123, over 1428719.39 frames.], batch size: 15, lr: 2.13e-03
2022-04-28 09:49:44,145 INFO [train.py:763] (4/8) Epoch 1, batch 3850, loss[loss=0.3142, simple_loss=0.3762, pruned_loss=0.1261, over 7173.00 frames.], tot_loss[loss=0.2896, simple_loss=0.3518, pruned_loss=0.1137, over 1430853.67 frames.], batch size: 26, lr: 2.13e-03
2022-04-28 09:50:49,543 INFO [train.py:763] (4/8) Epoch 1, batch 3900, loss[loss=0.277, simple_loss=0.3515, pruned_loss=0.1013, over 7268.00 frames.], tot_loss[loss=0.286, simple_loss=0.3494, pruned_loss=0.1113, over 1430735.33 frames.], batch size: 24, lr: 2.12e-03
2022-04-28 09:51:55,497 INFO [train.py:763] (4/8) Epoch 1, batch 3950, loss[loss=0.3121, simple_loss=0.3794, pruned_loss=0.1224, over 7110.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3484, pruned_loss=0.1105, over 1428397.34 frames.], batch size: 21, lr: 2.12e-03
2022-04-28 09:53:01,241 INFO [train.py:763] (4/8) Epoch 1, batch 4000, loss[loss=0.3118, simple_loss=0.3671, pruned_loss=0.1282, over 7201.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3476, pruned_loss=0.11, over 1428410.95 frames.], batch size: 22, lr: 2.11e-03
2022-04-28 09:54:07,049 INFO [train.py:763] (4/8) Epoch 1, batch 4050, loss[loss=0.369, simple_loss=0.4232, pruned_loss=0.1574, over 6868.00 frames.], tot_loss[loss=0.2852, simple_loss=0.3486, pruned_loss=0.1109, over 1426767.59 frames.], batch size: 31, lr: 2.11e-03
2022-04-28 09:55:12,315 INFO [train.py:763] (4/8) Epoch 1, batch 4100, loss[loss=0.2676, simple_loss=0.3365, pruned_loss=0.09933, over 7218.00 frames.], tot_loss[loss=0.2852, simple_loss=0.3484, pruned_loss=0.111, over 1421436.87 frames.], batch size: 21, lr: 2.10e-03
2022-04-28 09:56:17,392 INFO [train.py:763] (4/8) Epoch 1, batch 4150, loss[loss=0.316, simple_loss=0.3646, pruned_loss=0.1337, over 6834.00 frames.], tot_loss[loss=0.2848, simple_loss=0.3479, pruned_loss=0.1108, over 1420593.59 frames.], batch size: 31, lr: 2.10e-03
2022-04-28 09:57:22,844 INFO [train.py:763] (4/8) Epoch 1, batch 4200, loss[loss=0.2263, simple_loss=0.2995, pruned_loss=0.07656, over 7267.00 frames.], tot_loss[loss=0.2841, simple_loss=0.3471, pruned_loss=0.1106, over 1419004.71 frames.], batch size: 18, lr: 2.10e-03
2022-04-28 09:58:27,890 INFO [train.py:763] (4/8) Epoch 1, batch 4250, loss[loss=0.2553, simple_loss=0.3252, pruned_loss=0.09273, over 7270.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3472, pruned_loss=0.111, over 1414640.92 frames.], batch size: 18, lr: 2.09e-03
2022-04-28 09:59:34,312 INFO [train.py:763] (4/8) Epoch 1, batch 4300, loss[loss=0.2918, simple_loss=0.3629, pruned_loss=0.1104, over 7305.00 frames.], tot_loss[loss=0.2853, simple_loss=0.3479, pruned_loss=0.1114, over 1414213.04 frames.], batch size: 25, lr: 2.09e-03
2022-04-28 10:00:39,970 INFO [train.py:763] (4/8) Epoch 1, batch 4350, loss[loss=0.2369, simple_loss=0.3029, pruned_loss=0.08538, over 6981.00 frames.], tot_loss[loss=0.2862, simple_loss=0.3492, pruned_loss=0.1116, over 1414456.37 frames.], batch size: 16, lr: 2.08e-03
2022-04-28 10:01:45,335 INFO [train.py:763] (4/8) Epoch 1, batch 4400, loss[loss=0.2857, simple_loss=0.3595, pruned_loss=0.106, over 7317.00 frames.], tot_loss[loss=0.286, simple_loss=0.3492, pruned_loss=0.1114, over 1408764.18 frames.], batch size: 21, lr: 2.08e-03
2022-04-28 10:02:50,265 INFO [train.py:763] (4/8) Epoch 1, batch 4450, loss[loss=0.3108, simple_loss=0.3736, pruned_loss=0.1241, over 6527.00 frames.], tot_loss[loss=0.2868, simple_loss=0.3499, pruned_loss=0.1119, over 1401013.63 frames.], batch size: 38, lr: 2.07e-03
2022-04-28 10:03:55,334 INFO [train.py:763] (4/8) Epoch 1, batch 4500, loss[loss=0.2827, simple_loss=0.343, pruned_loss=0.1112, over 6478.00 frames.], tot_loss[loss=0.2877, simple_loss=0.3497, pruned_loss=0.1128, over 1387501.74 frames.], batch size: 38, lr: 2.07e-03
2022-04-28 10:04:59,433 INFO [train.py:763] (4/8) Epoch 1, batch 4550, loss[loss=0.3572, simple_loss=0.3899, pruned_loss=0.1622, over 4915.00 frames.], tot_loss[loss=0.2911, simple_loss=0.3524, pruned_loss=0.1149, over 1356133.70 frames.], batch size: 52, lr: 2.06e-03
2022-04-28 10:06:27,050 INFO [train.py:763] (4/8) Epoch 2, batch 0, loss[loss=0.3061, simple_loss=0.3364, pruned_loss=0.1379, over 7287.00 frames.], tot_loss[loss=0.3061, simple_loss=0.3364, pruned_loss=0.1379, over 7287.00 frames.], batch size: 17, lr: 2.02e-03
2022-04-28 10:07:33,518 INFO [train.py:763] (4/8) Epoch 2, batch 50, loss[loss=0.2732, simple_loss=0.35, pruned_loss=0.09822, over 7296.00 frames.], tot_loss[loss=0.2822, simple_loss=0.3459, pruned_loss=0.1092, over 322271.71 frames.], batch size: 25, lr: 2.02e-03
2022-04-28 10:08:39,164 INFO [train.py:763] (4/8) Epoch 2, batch 100, loss[loss=0.3191, simple_loss=0.3501, pruned_loss=0.1441, over 6994.00 frames.], tot_loss[loss=0.2801, simple_loss=0.3456, pruned_loss=0.1073, over 569489.37 frames.], batch size: 16, lr: 2.01e-03
2022-04-28 10:09:45,122 INFO [train.py:763] (4/8) Epoch 2, batch 150, loss[loss=0.3039, simple_loss=0.3675, pruned_loss=0.1202, over 6790.00 frames.], tot_loss[loss=0.2779, simple_loss=0.3439, pruned_loss=0.1059, over 761811.99 frames.], batch size: 31, lr: 2.01e-03
2022-04-28 10:10:50,698 INFO [train.py:763] (4/8) Epoch 2, batch 200, loss[loss=0.2449, simple_loss=0.3, pruned_loss=0.09486, over 6859.00 frames.], tot_loss[loss=0.2759, simple_loss=0.3425, pruned_loss=0.1047, over 901325.86 frames.], batch size: 15, lr: 2.00e-03
2022-04-28 10:11:56,041 INFO [train.py:763] (4/8) Epoch 2, batch 250, loss[loss=0.2958, simple_loss=0.3576, pruned_loss=0.117, over 7353.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3446, pruned_loss=0.106, over 1011702.63 frames.], batch size: 19, lr: 2.00e-03
2022-04-28 10:13:01,576 INFO [train.py:763] (4/8) Epoch 2, batch 300, loss[loss=0.3168, simple_loss=0.3703, pruned_loss=0.1317, over 6803.00 frames.], tot_loss[loss=0.2801, simple_loss=0.3464, pruned_loss=0.1068, over 1101894.40 frames.], batch size: 32, lr: 2.00e-03
2022-04-28 10:14:07,025 INFO [train.py:763] (4/8) Epoch 2, batch 350, loss[loss=0.2486, simple_loss=0.3349, pruned_loss=0.08117, over 7323.00 frames.], tot_loss[loss=0.2796, simple_loss=0.3461, pruned_loss=0.1066, over 1171638.02 frames.], batch size: 21, lr: 1.99e-03
2022-04-28 10:15:12,736 INFO [train.py:763] (4/8) Epoch 2, batch 400, loss[loss=0.2775, simple_loss=0.3541, pruned_loss=0.1005, over 7295.00 frames.], tot_loss[loss=0.2816, simple_loss=0.3473, pruned_loss=0.108, over 1222395.41 frames.], batch size: 24, lr: 1.99e-03
2022-04-28 10:16:17,702 INFO [train.py:763] (4/8) Epoch 2, batch 450, loss[loss=0.3099, simple_loss=0.3691, pruned_loss=0.1254, over 7219.00 frames.], tot_loss[loss=0.2797, simple_loss=0.3461, pruned_loss=0.1066, over 1262931.41 frames.], batch size: 22, lr: 1.98e-03
2022-04-28 10:17:41,016 INFO [train.py:763] (4/8) Epoch 2, batch 500, loss[loss=0.2229, simple_loss=0.2878, pruned_loss=0.07897, over 6987.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3449, pruned_loss=0.1057, over 1301305.72 frames.], batch size: 16, lr: 1.98e-03
2022-04-28 10:19:24,489 INFO [train.py:763] (4/8) Epoch 2, batch 550, loss[loss=0.2301, simple_loss=0.3118, pruned_loss=0.07416, over 7224.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3446, pruned_loss=0.105, over 1331443.09 frames.], batch size: 21, lr: 1.98e-03
2022-04-28 10:20:31,146 INFO [train.py:763] (4/8) Epoch 2, batch 600, loss[loss=0.357, simple_loss=0.4198, pruned_loss=0.1471, over 7283.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3442, pruned_loss=0.1044, over 1351839.68 frames.], batch size: 25, lr: 1.97e-03
2022-04-28 10:21:56,818 INFO [train.py:763] (4/8) Epoch 2, batch 650, loss[loss=0.2716, simple_loss=0.3402, pruned_loss=0.1015, over 7362.00 frames.], tot_loss[loss=0.2762, simple_loss=0.3437, pruned_loss=0.1044, over 1367254.58 frames.], batch size: 19, lr: 1.97e-03
2022-04-28 10:23:03,990 INFO [train.py:763] (4/8) Epoch 2, batch 700, loss[loss=0.2733, simple_loss=0.351, pruned_loss=0.09785, over 7221.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3429, pruned_loss=0.104, over 1378036.25 frames.], batch size: 21, lr: 1.96e-03
2022-04-28 10:24:09,347 INFO [train.py:763] (4/8) Epoch 2, batch 750, loss[loss=0.2638, simple_loss=0.3486, pruned_loss=0.08945, over 7187.00 frames.], tot_loss[loss=0.275, simple_loss=0.3426, pruned_loss=0.1037, over 1391086.31 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:25:14,622 INFO [train.py:763] (4/8) Epoch 2, batch 800, loss[loss=0.2829, simple_loss=0.3551, pruned_loss=0.1053, over 7197.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3425, pruned_loss=0.1037, over 1402244.57 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:26:20,183 INFO [train.py:763] (4/8) Epoch 2, batch 850, loss[loss=0.2537, simple_loss=0.3321, pruned_loss=0.08763, over 7321.00 frames.], tot_loss[loss=0.274, simple_loss=0.3417, pruned_loss=0.1032, over 1410370.80 frames.], batch size: 25, lr: 1.95e-03
2022-04-28 10:27:26,275 INFO [train.py:763] (4/8) Epoch 2, batch 900, loss[loss=0.2308, simple_loss=0.3064, pruned_loss=0.07763, over 7058.00 frames.], tot_loss[loss=0.2761, simple_loss=0.3436, pruned_loss=0.1043, over 1412196.48 frames.], batch size: 18, lr: 1.95e-03
2022-04-28 10:28:31,599 INFO [train.py:763] (4/8) Epoch 2, batch 950, loss[loss=0.2429, simple_loss=0.3262, pruned_loss=0.07976, over 7149.00 frames.], tot_loss[loss=0.2745, simple_loss=0.3423, pruned_loss=0.1033, over 1417068.20 frames.], batch size: 20, lr: 1.94e-03
2022-04-28 10:29:36,675 INFO [train.py:763] (4/8) Epoch 2, batch 1000, loss[loss=0.2939, simple_loss=0.3607, pruned_loss=0.1136, over 6813.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3431, pruned_loss=0.1041, over 1416396.16 frames.], batch size: 31, lr: 1.94e-03
2022-04-28 10:30:41,951 INFO [train.py:763] (4/8) Epoch 2, batch 1050, loss[loss=0.2283, simple_loss=0.2946, pruned_loss=0.08099, over 7268.00 frames.], tot_loss[loss=0.2743, simple_loss=0.342, pruned_loss=0.1033, over 1414550.47 frames.], batch size: 18, lr: 1.94e-03
2022-04-28 10:31:48,320 INFO [train.py:763] (4/8) Epoch 2, batch 1100, loss[loss=0.3102, simple_loss=0.3788, pruned_loss=0.1208, over 7221.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3442, pruned_loss=0.1042, over 1419594.69 frames.], batch size: 21, lr: 1.93e-03
2022-04-28 10:32:55,818 INFO [train.py:763] (4/8) Epoch 2, batch 1150, loss[loss=0.3089, simple_loss=0.3735, pruned_loss=0.1221, over 7239.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3426, pruned_loss=0.1036, over 1420812.64 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:34:03,563 INFO [train.py:763] (4/8) Epoch 2, batch 1200, loss[loss=0.2523, simple_loss=0.3245, pruned_loss=0.09002, over 7442.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3423, pruned_loss=0.1029, over 1424117.38 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:35:11,224 INFO [train.py:763] (4/8) Epoch 2, batch 1250, loss[loss=0.3143, simple_loss=0.3746, pruned_loss=0.127, over 7423.00 frames.], tot_loss[loss=0.2729, simple_loss=0.341, pruned_loss=0.1024, over 1424367.59 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:36:17,276 INFO [train.py:763] (4/8) Epoch 2, batch 1300, loss[loss=0.3379, simple_loss=0.3925, pruned_loss=0.1417, over 7323.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3401, pruned_loss=0.1015, over 1425938.31 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:37:22,331 INFO [train.py:763] (4/8) Epoch 2, batch 1350, loss[loss=0.2967, simple_loss=0.3607, pruned_loss=0.1163, over 7440.00 frames.], tot_loss[loss=0.2733, simple_loss=0.3418, pruned_loss=0.1024, over 1425723.94 frames.], batch size: 20, lr: 1.91e-03
2022-04-28 10:38:27,402 INFO [train.py:763] (4/8) Epoch 2, batch 1400, loss[loss=0.2381, simple_loss=0.3117, pruned_loss=0.08231, over 7172.00 frames.], tot_loss[loss=0.2736, simple_loss=0.342, pruned_loss=0.1026, over 1422936.23 frames.], batch size: 19, lr: 1.91e-03
2022-04-28 10:39:32,821 INFO [train.py:763] (4/8) Epoch 2, batch 1450, loss[loss=0.2415, simple_loss=0.2998, pruned_loss=0.09158, over 7135.00 frames.], tot_loss[loss=0.2729, simple_loss=0.3415, pruned_loss=0.1021, over 1419927.88 frames.], batch size: 17, lr: 1.91e-03
2022-04-28 10:40:38,389 INFO [train.py:763] (4/8) Epoch 2, batch 1500, loss[loss=0.2627, simple_loss=0.3424, pruned_loss=0.09146, over 7308.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3412, pruned_loss=0.1022, over 1418146.42 frames.], batch size: 21, lr: 1.90e-03
2022-04-28 10:41:43,972 INFO [train.py:763] (4/8) Epoch 2, batch 1550, loss[loss=0.3243, simple_loss=0.3794, pruned_loss=0.1346, over 7175.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3412, pruned_loss=0.1015, over 1422297.69 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:42:49,541 INFO [train.py:763] (4/8) Epoch 2, batch 1600, loss[loss=0.2444, simple_loss=0.3132, pruned_loss=0.08784, over 7153.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3405, pruned_loss=0.1011, over 1425333.48 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:43:56,342 INFO [train.py:763] (4/8) Epoch 2, batch 1650, loss[loss=0.2704, simple_loss=0.3386, pruned_loss=0.1011, over 7430.00 frames.], tot_loss[loss=0.2707, simple_loss=0.3401, pruned_loss=0.1006, over 1427155.09 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:45:02,820 INFO [train.py:763] (4/8) Epoch 2, batch 1700, loss[loss=0.2416, simple_loss=0.3281, pruned_loss=0.07751, over 7135.00 frames.], tot_loss[loss=0.2719, simple_loss=0.3408, pruned_loss=0.1015, over 1418425.68 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:46:08,588 INFO [train.py:763] (4/8) Epoch 2, batch 1750, loss[loss=0.2273, simple_loss=0.311, pruned_loss=0.07181, over 7229.00 frames.], tot_loss[loss=0.27, simple_loss=0.3397, pruned_loss=0.1001, over 1425192.55 frames.], batch size: 20, lr: 1.88e-03
2022-04-28 10:47:13,947 INFO [train.py:763] (4/8) Epoch 2, batch 1800, loss[loss=0.3313, simple_loss=0.3839, pruned_loss=0.1394, over 7110.00 frames.], tot_loss[loss=0.2701, simple_loss=0.3396, pruned_loss=0.1003, over 1417331.21 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:48:20,967 INFO [train.py:763] (4/8) Epoch 2, batch 1850, loss[loss=0.2758, simple_loss=0.3538, pruned_loss=0.09884, over 7407.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3393, pruned_loss=0.1, over 1418292.14 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:49:26,582 INFO [train.py:763] (4/8) Epoch 2, batch 1900, loss[loss=0.246, simple_loss=0.3121, pruned_loss=0.08995, over 7166.00 frames.], tot_loss[loss=0.2705, simple_loss=0.3397, pruned_loss=0.1006, over 1415680.08 frames.], batch size: 18, lr: 1.87e-03
2022-04-28 10:50:31,921 INFO [train.py:763] (4/8) Epoch 2, batch 1950, loss[loss=0.301, simple_loss=0.3703, pruned_loss=0.1159, over 6698.00 frames.], tot_loss[loss=0.269, simple_loss=0.3381, pruned_loss=0.09998, over 1416831.13 frames.], batch size: 31, lr: 1.87e-03
2022-04-28 10:51:37,332 INFO [train.py:763] (4/8) Epoch 2, batch 2000, loss[loss=0.2734, simple_loss=0.3391, pruned_loss=0.1038, over 7138.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3365, pruned_loss=0.09863, over 1421513.37 frames.], batch size: 19, lr: 1.87e-03
2022-04-28 10:52:43,638 INFO [train.py:763] (4/8) Epoch 2, batch 2050, loss[loss=0.3426, simple_loss=0.387, pruned_loss=0.1491, over 5221.00 frames.], tot_loss[loss=0.268, simple_loss=0.338, pruned_loss=0.09903, over 1421850.31 frames.], batch size: 52, lr: 1.86e-03
2022-04-28 10:53:49,749 INFO [train.py:763] (4/8) Epoch 2, batch 2100, loss[loss=0.2824, simple_loss=0.3607, pruned_loss=0.1021, over 7324.00 frames.], tot_loss[loss=0.2689, simple_loss=0.3389, pruned_loss=0.09944, over 1424981.66 frames.], batch size: 21, lr: 1.86e-03
2022-04-28 10:54:55,189 INFO [train.py:763] (4/8) Epoch 2, batch 2150, loss[loss=0.2891, simple_loss=0.3587, pruned_loss=0.1098, over 7242.00 frames.], tot_loss[loss=0.2664, simple_loss=0.3372, pruned_loss=0.09783, over 1426702.05 frames.], batch size: 20, lr: 1.86e-03
2022-04-28 10:56:00,715 INFO [train.py:763] (4/8) Epoch 2, batch 2200, loss[loss=0.2659, simple_loss=0.3407, pruned_loss=0.09553, over 7138.00 frames.], tot_loss[loss=0.2667, simple_loss=0.3372, pruned_loss=0.09808, over 1426044.83 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:57:05,938 INFO [train.py:763] (4/8) Epoch 2, batch 2250, loss[loss=0.2584, simple_loss=0.3306, pruned_loss=0.09306, over 7330.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3376, pruned_loss=0.0977, over 1426402.31 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:58:11,383 INFO [train.py:763] (4/8) Epoch 2, batch 2300, loss[loss=0.2398, simple_loss=0.3134, pruned_loss=0.08303, over 7356.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3375, pruned_loss=0.09842, over 1413372.43 frames.], batch size: 19, lr: 1.85e-03
2022-04-28 10:59:16,565 INFO [train.py:763] (4/8) Epoch 2, batch 2350, loss[loss=0.2466, simple_loss=0.3213, pruned_loss=0.08591, over 7252.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3368, pruned_loss=0.09721, over 1414539.01 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:00:21,739 INFO [train.py:763] (4/8) Epoch 2, batch 2400, loss[loss=0.2356, simple_loss=0.3208, pruned_loss=0.0752, over 7260.00 frames.], tot_loss[loss=0.2669, simple_loss=0.3381, pruned_loss=0.09785, over 1417752.62 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:01:26,802 INFO [train.py:763] (4/8) Epoch 2, batch 2450, loss[loss=0.33, simple_loss=0.3943, pruned_loss=0.1328, over 7241.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3391, pruned_loss=0.09819, over 1415744.92 frames.], batch size: 20, lr: 1.84e-03
2022-04-28 11:02:32,496 INFO [train.py:763] (4/8) Epoch 2, batch 2500, loss[loss=0.2741, simple_loss=0.3465, pruned_loss=0.1009, over 7159.00 frames.], tot_loss[loss=0.2685, simple_loss=0.3395, pruned_loss=0.09879, over 1414307.28 frames.], batch size: 19, lr: 1.83e-03
2022-04-28 11:03:38,313 INFO [train.py:763] (4/8) Epoch 2, batch 2550, loss[loss=0.2748, simple_loss=0.3554, pruned_loss=0.09715, over 7214.00 frames.], tot_loss[loss=0.2679, simple_loss=0.3386, pruned_loss=0.09857, over 1413024.01 frames.], batch size: 21, lr: 1.83e-03
2022-04-28 11:04:44,221 INFO [train.py:763] (4/8) Epoch 2, batch 2600, loss[loss=0.2292, simple_loss=0.3035, pruned_loss=0.07751, over 7279.00 frames.], tot_loss[loss=0.2673, simple_loss=0.3379, pruned_loss=0.09832, over 1419475.15 frames.], batch size: 18, lr: 1.83e-03
2022-04-28 11:05:50,132 INFO [train.py:763] (4/8) Epoch 2, batch 2650, loss[loss=0.2412, simple_loss=0.3233, pruned_loss=0.07959, over 7334.00 frames.], tot_loss[loss=0.266, simple_loss=0.3368, pruned_loss=0.09756, over 1418837.91 frames.], batch size: 20, lr: 1.82e-03
2022-04-28 11:06:55,491 INFO [train.py:763] (4/8) Epoch 2, batch 2700, loss[loss=0.2023, simple_loss=0.2825, pruned_loss=0.0611, over 7067.00 frames.], tot_loss[loss=0.2658, simple_loss=0.3369, pruned_loss=0.09737, over 1419339.95 frames.], batch size: 18, lr: 1.82e-03
2022-04-28 11:08:01,948 INFO [train.py:763] (4/8) Epoch 2, batch 2750, loss[loss=0.3264, simple_loss=0.3959, pruned_loss=0.1285, over 7151.00 frames.], tot_loss[loss=0.2653, simple_loss=0.3366, pruned_loss=0.09697, over 1418224.19 frames.], batch size: 26, lr: 1.82e-03
2022-04-28 11:09:07,550 INFO [train.py:763] (4/8) Epoch 2, batch 2800, loss[loss=0.3897, simple_loss=0.4095, pruned_loss=0.185, over 5100.00 frames.], tot_loss[loss=0.2655, simple_loss=0.3367, pruned_loss=0.09716, over 1418475.11 frames.], batch size: 52, lr: 1.81e-03
2022-04-28 11:10:13,389 INFO [train.py:763] (4/8) Epoch 2, batch 2850, loss[loss=0.3014, simple_loss=0.3696, pruned_loss=0.1166, over 7219.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3365, pruned_loss=0.09666, over 1420332.18 frames.], batch size: 21, lr: 1.81e-03
2022-04-28 11:11:19,190 INFO [train.py:763] (4/8) Epoch 2, batch 2900, loss[loss=0.324, simple_loss=0.3867, pruned_loss=0.1306, over 6412.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3364, pruned_loss=0.09666, over 1417376.13 frames.], batch size: 38, lr: 1.81e-03
2022-04-28 11:12:24,868 INFO [train.py:763] (4/8) Epoch 2, batch 2950, loss[loss=0.2717, simple_loss=0.3423, pruned_loss=0.1006, over 7153.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3357, pruned_loss=0.09579, over 1416682.73 frames.], batch size: 26, lr: 1.80e-03
2022-04-28 11:13:30,377 INFO [train.py:763] (4/8) Epoch 2, batch 3000, loss[loss=0.2967, simple_loss=0.3551, pruned_loss=0.1191, over 7339.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3352, pruned_loss=0.09558, over 1420110.18 frames.], batch size: 22, lr: 1.80e-03
2022-04-28 11:13:30,378 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 11:13:45,774 INFO [train.py:792] (4/8) Epoch 2, validation: loss=0.2017, simple_loss=0.3052, pruned_loss=0.04915, over 698248.00 frames.
2022-04-28 11:14:51,524 INFO [train.py:763] (4/8) Epoch 2, batch 3050, loss[loss=0.3011, simple_loss=0.3583, pruned_loss=0.1219, over 7409.00 frames.], tot_loss[loss=0.2642, simple_loss=0.336, pruned_loss=0.09619, over 1425365.23 frames.], batch size: 21, lr: 1.80e-03
2022-04-28 11:15:57,113 INFO [train.py:763] (4/8) Epoch 2, batch 3100, loss[loss=0.2373, simple_loss=0.3094, pruned_loss=0.08263, over 7290.00 frames.], tot_loss[loss=0.2629, simple_loss=0.3347, pruned_loss=0.09553, over 1428166.20 frames.], batch size: 18, lr: 1.79e-03
2022-04-28 11:17:02,757 INFO [train.py:763] (4/8) Epoch 2, batch 3150, loss[loss=0.242, simple_loss=0.3295, pruned_loss=0.07724, over 7228.00 frames.], tot_loss[loss=0.2612, simple_loss=0.333, pruned_loss=0.09467, over 1421926.22 frames.], batch size: 21, lr: 1.79e-03
2022-04-28 11:18:08,968 INFO [train.py:763] (4/8) Epoch 2, batch 3200, loss[loss=0.2791, simple_loss=0.3555, pruned_loss=0.1013, over 7379.00 frames.], tot_loss[loss=0.2604, simple_loss=0.333, pruned_loss=0.09389, over 1424506.85 frames.], batch size: 23, lr: 1.79e-03
2022-04-28 11:19:14,934 INFO [train.py:763] (4/8) Epoch 2, batch 3250, loss[loss=0.2267, simple_loss=0.3059, pruned_loss=0.0737, over 7153.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3329, pruned_loss=0.09317, over 1425250.91 frames.], batch size: 19, lr: 1.79e-03
2022-04-28 11:20:20,951 INFO [train.py:763] (4/8) Epoch 2, batch 3300, loss[loss=0.2768, simple_loss=0.3519, pruned_loss=0.1009, over 7211.00 frames.], tot_loss[loss=0.2586, simple_loss=0.3323, pruned_loss=0.09242, over 1427936.72 frames.], batch size: 26, lr: 1.78e-03
2022-04-28 11:21:25,808 INFO [train.py:763] (4/8) Epoch 2, batch 3350, loss[loss=0.2225, simple_loss=0.299, pruned_loss=0.07301, over 7288.00 frames.], tot_loss[loss=0.2606, simple_loss=0.3337, pruned_loss=0.09377, over 1425090.46 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:22:30,851 INFO [train.py:763] (4/8) Epoch 2, batch 3400, loss[loss=0.2294, simple_loss=0.2949, pruned_loss=0.08199, over 7414.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3351, pruned_loss=0.09471, over 1422623.80 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:23:36,216 INFO [train.py:763] (4/8) Epoch 2, batch 3450, loss[loss=0.2749, simple_loss=0.3332, pruned_loss=0.1083, over 7274.00 frames.], tot_loss[loss=0.2628, simple_loss=0.3353, pruned_loss=0.09514, over 1420320.33 frames.], batch size: 19, lr: 1.77e-03
2022-04-28 11:24:41,578 INFO [train.py:763] (4/8) Epoch 2, batch 3500, loss[loss=0.2905, simple_loss=0.357, pruned_loss=0.112, over 7333.00 frames.], tot_loss[loss=0.2622, simple_loss=0.3345, pruned_loss=0.09494, over 1421091.69 frames.], batch size: 25, lr: 1.77e-03
2022-04-28 11:25:47,025 INFO [train.py:763] (4/8) Epoch 2, batch 3550, loss[loss=0.2371, simple_loss=0.322, pruned_loss=0.07609, over 7223.00 frames.], tot_loss[loss=0.2637, simple_loss=0.336, pruned_loss=0.09571, over 1420294.93 frames.], batch size: 21, lr: 1.77e-03
2022-04-28 11:26:52,369 INFO [train.py:763] (4/8) Epoch 2, batch 3600, loss[loss=0.2414, simple_loss=0.3282, pruned_loss=0.07733, over 7290.00 frames.], tot_loss[loss=0.2608, simple_loss=0.3334, pruned_loss=0.09412, over 1421192.52 frames.], batch size: 24, lr: 1.76e-03
2022-04-28 11:27:57,953 INFO [train.py:763] (4/8) Epoch 2, batch 3650, loss[loss=0.2958, simple_loss=0.3599, pruned_loss=0.1158, over 7383.00 frames.], tot_loss[loss=0.2584, simple_loss=0.3313, pruned_loss=0.09271, over 1421748.94 frames.], batch size: 23, lr: 1.76e-03
2022-04-28 11:29:03,178 INFO [train.py:763] (4/8) Epoch 2, batch 3700, loss[loss=0.2075, simple_loss=0.2825, pruned_loss=0.06628, over 7411.00 frames.], tot_loss[loss=0.2586, simple_loss=0.3317, pruned_loss=0.09278, over 1416893.43 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:30:08,698 INFO [train.py:763] (4/8) Epoch 2, batch 3750, loss[loss=0.2364, simple_loss=0.3055, pruned_loss=0.08362, over 7277.00 frames.], tot_loss[loss=0.2578, simple_loss=0.3312, pruned_loss=0.09223, over 1422807.04 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:31:14,664 INFO [train.py:763] (4/8) Epoch 2, batch 3800, loss[loss=0.2563, simple_loss=0.3186, pruned_loss=0.09699, over 7167.00 frames.], tot_loss[loss=0.2576, simple_loss=0.3308, pruned_loss=0.09217, over 1423535.64 frames.], batch size: 18, lr: 1.75e-03
2022-04-28 11:32:20,647 INFO [train.py:763] (4/8) Epoch 2, batch 3850, loss[loss=0.246, simple_loss=0.3288, pruned_loss=0.08159, over 7339.00 frames.], tot_loss[loss=0.2583, simple_loss=0.3312, pruned_loss=0.09271, over 1422411.99 frames.], batch size: 22, lr: 1.75e-03
2022-04-28 11:33:26,575 INFO [train.py:763] (4/8) Epoch 2, batch 3900, loss[loss=0.2414, simple_loss=0.3223, pruned_loss=0.08027, over 7338.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3299, pruned_loss=0.09127, over 1423957.48 frames.], batch size: 20, lr: 1.75e-03
2022-04-28 11:34:31,997 INFO [train.py:763] (4/8) Epoch 2, batch 3950, loss[loss=0.2964, simple_loss=0.3654, pruned_loss=0.1137, over 7318.00 frames.], tot_loss[loss=0.2568, simple_loss=0.3303, pruned_loss=0.09163, over 1421121.46 frames.], batch size: 21, lr: 1.74e-03
2022-04-28 11:35:37,600 INFO [train.py:763] (4/8) Epoch 2, batch 4000, loss[loss=0.2841, simple_loss=0.3464, pruned_loss=0.1109, over 7348.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3313, pruned_loss=0.09224, over 1425432.80 frames.], batch size: 22, lr: 1.74e-03
2022-04-28 11:36:44,078 INFO [train.py:763] (4/8) Epoch 2, batch 4050, loss[loss=0.309, simple_loss=0.3916, pruned_loss=0.1132, over 7439.00 frames.], tot_loss[loss=0.2573, simple_loss=0.3309, pruned_loss=0.09178, over 1426310.74 frames.], batch size: 20, lr: 1.74e-03
2022-04-28 11:37:49,241 INFO [train.py:763] (4/8) Epoch 2, batch 4100, loss[loss=0.2566, simple_loss=0.3285, pruned_loss=0.09238, over 7059.00 frames.], tot_loss[loss=0.2586, simple_loss=0.3321, pruned_loss=0.09252, over 1416153.05 frames.], batch size: 18, lr: 1.73e-03
2022-04-28 11:38:54,190 INFO [train.py:763] (4/8) Epoch 2, batch 4150, loss[loss=0.2695, simple_loss=0.3431, pruned_loss=0.0979, over 7123.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3319, pruned_loss=0.09222, over 1420980.54 frames.], batch size: 21, lr: 1.73e-03
2022-04-28 11:40:00,863 INFO [train.py:763] (4/8) Epoch 2, batch 4200, loss[loss=0.2709, simple_loss=0.3436, pruned_loss=0.09904, over 7123.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3329, pruned_loss=0.09266, over 1420607.40 frames.], batch size: 28, lr: 1.73e-03
2022-04-28 11:41:07,989 INFO [train.py:763] (4/8) Epoch 2, batch 4250, loss[loss=0.2708, simple_loss=0.3549, pruned_loss=0.09334, over 7199.00 frames.], tot_loss[loss=0.2584, simple_loss=0.3321, pruned_loss=0.09238, over 1422150.42 frames.], batch size: 22, lr: 1.73e-03
2022-04-28 11:42:14,752 INFO [train.py:763] (4/8) Epoch 2, batch 4300, loss[loss=0.2063, simple_loss=0.2888, pruned_loss=0.06188, over 7069.00 frames.], tot_loss[loss=0.2593, simple_loss=0.3327, pruned_loss=0.09296, over 1423876.15 frames.], batch size: 18, lr: 1.72e-03
2022-04-28 11:43:21,899 INFO [train.py:763] (4/8) Epoch 2, batch 4350, loss[loss=0.2575, simple_loss=0.3356, pruned_loss=0.08972, over 7161.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3331, pruned_loss=0.09304, over 1425744.31 frames.], batch size: 20, lr: 1.72e-03
2022-04-28 11:44:27,743 INFO [train.py:763] (4/8) Epoch 2, batch 4400, loss[loss=0.3053, simple_loss=0.371, pruned_loss=0.1198, over 7290.00 frames.], tot_loss[loss=0.2607, simple_loss=0.3335, pruned_loss=0.09392, over 1419623.94 frames.], batch size: 25, lr: 1.72e-03
2022-04-28 11:45:33,249 INFO [train.py:763] (4/8) Epoch 2, batch 4450, loss[loss=0.2534, simple_loss=0.3277, pruned_loss=0.08955, over 7332.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3354, pruned_loss=0.09488, over 1411830.42 frames.], batch size: 22, lr: 1.71e-03
2022-04-28 11:46:38,402 INFO [train.py:763] (4/8) Epoch 2, batch 4500, loss[loss=0.2862, simple_loss=0.3462, pruned_loss=0.1131, over 7104.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3355, pruned_loss=0.09472, over 1406736.17 frames.], batch size: 21, lr: 1.71e-03
2022-04-28 11:47:42,632 INFO [train.py:763] (4/8) Epoch 2, batch 4550, loss[loss=0.2345, simple_loss=0.3175, pruned_loss=0.07576, over 6438.00 frames.], tot_loss[loss=0.2659, simple_loss=0.3385, pruned_loss=0.09665, over 1378432.97 frames.], batch size: 38, lr: 1.71e-03
2022-04-28 11:49:10,866 INFO [train.py:763] (4/8) Epoch 3, batch 0, loss[loss=0.2922, simple_loss=0.3659, pruned_loss=0.1092, over 7200.00 frames.], tot_loss[loss=0.2922, simple_loss=0.3659, pruned_loss=0.1092, over 7200.00 frames.], batch size: 23, lr: 1.66e-03
2022-04-28 11:50:17,403 INFO [train.py:763] (4/8) Epoch 3, batch 50, loss[loss=0.2098, simple_loss=0.2911, pruned_loss=0.06428, over 7283.00 frames.], tot_loss[loss=0.252, simple_loss=0.3267, pruned_loss=0.08865, over 318688.55 frames.], batch size: 17, lr: 1.66e-03
2022-04-28 11:51:23,920 INFO [train.py:763] (4/8) Epoch 3, batch 100, loss[loss=0.2221, simple_loss=0.3014, pruned_loss=0.07144, over 7277.00 frames.], tot_loss[loss=0.249, simple_loss=0.3243, pruned_loss=0.08688, over 566218.81 frames.], batch size: 17, lr: 1.65e-03
2022-04-28 11:52:29,494 INFO [train.py:763] (4/8) Epoch 3, batch 150, loss[loss=0.2705, simple_loss=0.3581, pruned_loss=0.09144, over 7333.00 frames.], tot_loss[loss=0.2519, simple_loss=0.3266, pruned_loss=0.08857, over 756783.10 frames.], batch size: 22, lr: 1.65e-03
2022-04-28 11:53:34,974 INFO [train.py:763] (4/8) Epoch 3, batch 200, loss[loss=0.2739, simple_loss=0.3482, pruned_loss=0.09978, over 7192.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3261, pruned_loss=0.08681, over 905723.39 frames.], batch size: 23, lr: 1.65e-03
2022-04-28 11:54:40,981 INFO [train.py:763] (4/8) Epoch 3, batch 250, loss[loss=0.2238, simple_loss=0.3112, pruned_loss=0.06816, over 7329.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3279, pruned_loss=0.08734, over 1017513.99 frames.], batch size: 22, lr: 1.64e-03
2022-04-28 11:55:46,608 INFO [train.py:763] (4/8) Epoch 3, batch 300, loss[loss=0.2473, simple_loss=0.3467, pruned_loss=0.07399, over 7384.00 frames.], tot_loss[loss=0.251, simple_loss=0.3276, pruned_loss=0.08714, over 1111429.99 frames.], batch size: 23, lr: 1.64e-03
2022-04-28 11:56:52,027 INFO [train.py:763] (4/8) Epoch 3, batch 350, loss[loss=0.2599, simple_loss=0.348, pruned_loss=0.08588, over 7321.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3272, pruned_loss=0.08722, over 1182706.96 frames.], batch size: 21, lr: 1.64e-03
2022-04-28 11:57:57,844 INFO [train.py:763] (4/8) Epoch 3, batch 400, loss[loss=0.2891, simple_loss=0.3634, pruned_loss=0.1074, over 7229.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3263, pruned_loss=0.08702, over 1233162.08 frames.], batch size: 20, lr: 1.64e-03
2022-04-28 11:59:03,269 INFO [train.py:763] (4/8) Epoch 3, batch 450, loss[loss=0.2759, simple_loss=0.3535, pruned_loss=0.09915, over 7145.00 frames.], tot_loss[loss=0.25, simple_loss=0.3263, pruned_loss=0.08683, over 1275117.20 frames.], batch size: 20, lr: 1.63e-03
2022-04-28 12:00:09,020 INFO [train.py:763] (4/8) Epoch 3, batch 500, loss[loss=0.216, simple_loss=0.2994, pruned_loss=0.06629, over 7159.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3281, pruned_loss=0.08713, over 1304003.90 frames.], batch size: 19, lr: 1.63e-03
2022-04-28 12:01:14,925 INFO [train.py:763] (4/8) Epoch 3, batch 550, loss[loss=0.2128, simple_loss=0.2957, pruned_loss=0.06497, over 7152.00 frames.], tot_loss[loss=0.2513, simple_loss=0.3281, pruned_loss=0.08726, over 1329808.86 frames.], batch size: 18, lr: 1.63e-03
2022-04-28 12:02:20,854 INFO [train.py:763] (4/8) Epoch 3, batch 600, loss[loss=0.3162, simple_loss=0.3711, pruned_loss=0.1307, over 6468.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3279, pruned_loss=0.08729, over 1347853.90 frames.], batch size: 38, lr: 1.63e-03
2022-04-28 12:03:27,784 INFO [train.py:763] (4/8) Epoch 3, batch 650, loss[loss=0.25, simple_loss=0.3283, pruned_loss=0.08586, over 7435.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3274, pruned_loss=0.08669, over 1368200.43 frames.], batch size: 20, lr: 1.62e-03
2022-04-28 12:04:35,116 INFO [train.py:763] (4/8) Epoch 3, batch 700, loss[loss=0.2522, simple_loss=0.3356, pruned_loss=0.08435, over 7304.00 frames.], tot_loss[loss=0.2487, simple_loss=0.3259, pruned_loss=0.08577, over 1385978.34 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:05:41,309 INFO [train.py:763] (4/8) Epoch 3, batch 750, loss[loss=0.2575, simple_loss=0.3365, pruned_loss=0.08928, over 7282.00 frames.], tot_loss[loss=0.2499, simple_loss=0.3263, pruned_loss=0.08676, over 1393675.05 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:06:46,991 INFO [train.py:763] (4/8) Epoch 3, batch 800, loss[loss=0.232, simple_loss=0.3321, pruned_loss=0.06591, over 7259.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3274, pruned_loss=0.08751, over 1397567.33 frames.], batch size: 19, lr: 1.62e-03
2022-04-28 12:07:53,458 INFO [train.py:763] (4/8) Epoch 3, batch 850, loss[loss=0.2274, simple_loss=0.3066, pruned_loss=0.07407, over 7062.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3281, pruned_loss=0.08733, over 1407199.60 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:09:00,226 INFO [train.py:763] (4/8) Epoch 3, batch 900, loss[loss=0.2755, simple_loss=0.3653, pruned_loss=0.09279, over 7121.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3275, pruned_loss=0.08689, over 1414777.67 frames.], batch size: 21, lr: 1.61e-03
2022-04-28 12:10:06,503 INFO [train.py:763] (4/8) Epoch 3, batch 950, loss[loss=0.2582, simple_loss=0.345, pruned_loss=0.08567, over 7155.00 frames.], tot_loss[loss=0.2502, simple_loss=0.327, pruned_loss=0.08668, over 1419640.19 frames.], batch size: 26, lr: 1.61e-03
2022-04-28 12:11:12,746 INFO [train.py:763] (4/8) Epoch 3, batch 1000, loss[loss=0.2522, simple_loss=0.329, pruned_loss=0.08771, over 7274.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3265, pruned_loss=0.08652, over 1420243.53 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:12:18,771 INFO [train.py:763] (4/8) Epoch 3, batch 1050, loss[loss=0.3497, simple_loss=0.3959, pruned_loss=0.1518, over 6607.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3265, pruned_loss=0.08644, over 1419238.54 frames.], batch size: 31, lr: 1.60e-03
2022-04-28 12:13:24,396 INFO [train.py:763] (4/8) Epoch 3, batch 1100, loss[loss=0.2385, simple_loss=0.3261, pruned_loss=0.07541, over 7418.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3266, pruned_loss=0.08647, over 1420434.53 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:14:28,835 INFO [train.py:763] (4/8) Epoch 3, batch 1150, loss[loss=0.2701, simple_loss=0.3536, pruned_loss=0.09331, over 7310.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3286, pruned_loss=0.08749, over 1417029.03 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:15:35,086 INFO [train.py:763] (4/8) Epoch 3, batch 1200, loss[loss=0.2487, simple_loss=0.3337, pruned_loss=0.08183, over 7325.00 frames.], tot_loss[loss=0.252, simple_loss=0.3292, pruned_loss=0.08745, over 1414464.29 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:16:40,630 INFO [train.py:763] (4/8) Epoch 3, batch 1250, loss[loss=0.1888, simple_loss=0.2669, pruned_loss=0.05534, over 6835.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3286, pruned_loss=0.08704, over 1412181.30 frames.], batch size: 15, lr: 1.59e-03
2022-04-28 12:17:46,144 INFO [train.py:763] (4/8) Epoch 3, batch 1300, loss[loss=0.3106, simple_loss=0.3762, pruned_loss=0.1225, over 7204.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3276, pruned_loss=0.08636, over 1416385.34 frames.], batch size: 23, lr: 1.59e-03
2022-04-28 12:18:51,889 INFO [train.py:763] (4/8) Epoch 3, batch 1350, loss[loss=0.2882, simple_loss=0.3654, pruned_loss=0.1055, over 7241.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3279, pruned_loss=0.08679, over 1416518.23 frames.], batch size: 20, lr: 1.59e-03
2022-04-28 12:19:57,900 INFO [train.py:763] (4/8) Epoch 3, batch 1400, loss[loss=0.244, simple_loss=0.317, pruned_loss=0.08543, over 7191.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3277, pruned_loss=0.08707, over 1419924.22 frames.], batch size: 22, lr: 1.59e-03
2022-04-28 12:21:03,059 INFO [train.py:763] (4/8) Epoch 3, batch 1450, loss[loss=0.2292, simple_loss=0.31, pruned_loss=0.07423, over 7299.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3283, pruned_loss=0.08726, over 1421963.47 frames.], batch size: 24, lr: 1.59e-03
2022-04-28 12:22:08,500 INFO [train.py:763] (4/8) Epoch 3, batch 1500, loss[loss=0.2692, simple_loss=0.3567, pruned_loss=0.09081, over 7302.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3285, pruned_loss=0.08713, over 1418887.98 frames.], batch size: 24, lr: 1.58e-03
2022-04-28 12:23:13,998 INFO [train.py:763] (4/8) Epoch 3, batch 1550, loss[loss=0.3213, simple_loss=0.3826, pruned_loss=0.13, over 5299.00 frames.], tot_loss[loss=0.2508, simple_loss=0.3278, pruned_loss=0.08694, over 1417982.03 frames.], batch size: 53, lr: 1.58e-03
2022-04-28 12:24:20,149 INFO [train.py:763] (4/8) Epoch 3, batch 1600, loss[loss=0.2636, simple_loss=0.3483, pruned_loss=0.08945, over 7302.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3282, pruned_loss=0.08702, over 1414400.58 frames.], batch size: 25, lr: 1.58e-03
2022-04-28 12:25:26,867 INFO [train.py:763] (4/8) Epoch 3, batch 1650, loss[loss=0.2429, simple_loss=0.3153, pruned_loss=0.08522, over 7325.00 frames.], tot_loss[loss=0.2498, simple_loss=0.3266, pruned_loss=0.08653, over 1416350.31 frames.], batch size: 20, lr: 1.58e-03
2022-04-28 12:26:34,037 INFO [train.py:763] (4/8) Epoch 3, batch 1700, loss[loss=0.2767, simple_loss=0.3527, pruned_loss=0.1004, over 7143.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3267, pruned_loss=0.08629, over 1420245.66 frames.], batch size: 20, lr: 1.57e-03
2022-04-28 12:27:40,150 INFO [train.py:763] (4/8) Epoch 3, batch 1750, loss[loss=0.2496, simple_loss=0.3331, pruned_loss=0.08307, over 7199.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3263, pruned_loss=0.08627, over 1419894.86 frames.], batch size: 22, lr: 1.57e-03
2022-04-28 12:28:45,188 INFO [train.py:763] (4/8) Epoch 3, batch 1800, loss[loss=0.2653, simple_loss=0.3467, pruned_loss=0.0919, over 7218.00 frames.], tot_loss[loss=0.2514, simple_loss=0.3282, pruned_loss=0.08729, over 1421728.24 frames.], batch size: 21, lr: 1.57e-03
2022-04-28 12:29:50,458 INFO [train.py:763] (4/8) Epoch 3, batch 1850, loss[loss=0.2415, simple_loss=0.319, pruned_loss=0.08194, over 7144.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3284, pruned_loss=0.08695, over 1420371.27 frames.], batch size: 17, lr: 1.57e-03
2022-04-28 12:30:57,294 INFO [train.py:763] (4/8) Epoch 3, batch 1900, loss[loss=0.2947, simple_loss=0.3527, pruned_loss=0.1183, over 7156.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3282, pruned_loss=0.0875, over 1423432.46 frames.], batch size: 19, lr: 1.56e-03
2022-04-28 12:32:03,218 INFO [train.py:763] (4/8) Epoch 3, batch 1950, loss[loss=0.2857, simple_loss=0.3553, pruned_loss=0.1081, over 6634.00 frames.], tot_loss[loss=0.251, simple_loss=0.3282, pruned_loss=0.08691, over 1428870.61 frames.], batch size: 38, lr: 1.56e-03
2022-04-28 12:33:17,823 INFO [train.py:763] (4/8) Epoch 3, batch 2000, loss[loss=0.2384, simple_loss=0.3308, pruned_loss=0.07302, over 7124.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3287, pruned_loss=0.08686, over 1425757.32 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:35:10,050 INFO [train.py:763] (4/8) Epoch 3, batch 2050, loss[loss=0.2511, simple_loss=0.3396, pruned_loss=0.08126, over 6599.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3284, pruned_loss=0.08703, over 1422859.34 frames.], batch size: 31, lr: 1.56e-03
2022-04-28 12:36:15,498 INFO [train.py:763] (4/8) Epoch 3, batch 2100, loss[loss=0.2406, simple_loss=0.3216, pruned_loss=0.07975, over 7322.00 frames.], tot_loss[loss=0.2492, simple_loss=0.327, pruned_loss=0.08574, over 1421661.25 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:37:29,640 INFO [train.py:763] (4/8) Epoch 3, batch 2150, loss[loss=0.244, simple_loss=0.3343, pruned_loss=0.07687, over 7326.00 frames.], tot_loss[loss=0.248, simple_loss=0.3259, pruned_loss=0.085, over 1423438.28 frames.], batch size: 22, lr: 1.55e-03
2022-04-28 12:38:44,718 INFO [train.py:763] (4/8) Epoch 3, batch 2200, loss[loss=0.2842, simple_loss=0.3684, pruned_loss=0.1, over 7226.00 frames.], tot_loss[loss=0.2467, simple_loss=0.325, pruned_loss=0.08421, over 1425741.44 frames.], batch size: 21, lr: 1.55e-03
2022-04-28 12:40:02,462 INFO [train.py:763] (4/8) Epoch 3, batch 2250, loss[loss=0.3518, simple_loss=0.4011, pruned_loss=0.1512, over 5158.00 frames.], tot_loss[loss=0.248, simple_loss=0.3263, pruned_loss=0.08484, over 1427483.37 frames.], batch size: 52, lr: 1.55e-03
2022-04-28 12:41:07,752 INFO [train.py:763] (4/8) Epoch 3, batch 2300, loss[loss=0.2336, simple_loss=0.3179, pruned_loss=0.07472, over 7168.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3266, pruned_loss=0.08496, over 1430531.33 frames.], batch size: 19, lr: 1.55e-03
2022-04-28 12:42:14,639 INFO [train.py:763] (4/8) Epoch 3, batch 2350, loss[loss=0.248, simple_loss=0.3286, pruned_loss=0.08364, over 7328.00 frames.], tot_loss[loss=0.2474, simple_loss=0.3259, pruned_loss=0.08448, over 1431665.90 frames.], batch size: 20, lr: 1.54e-03
2022-04-28 12:43:19,978 INFO [train.py:763] (4/8) Epoch 3, batch 2400, loss[loss=0.2417, simple_loss=0.3203, pruned_loss=0.08156, over 7266.00 frames.], tot_loss[loss=0.2475, simple_loss=0.3267, pruned_loss=0.0842, over 1433353.66 frames.], batch size: 25, lr: 1.54e-03
2022-04-28 12:44:25,914 INFO [train.py:763] (4/8) Epoch 3, batch 2450, loss[loss=0.2823, simple_loss=0.3483, pruned_loss=0.1081, over 7375.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3268, pruned_loss=0.08469, over 1436341.09 frames.], batch size: 23, lr: 1.54e-03
2022-04-28 12:45:31,560 INFO [train.py:763] (4/8) Epoch 3, batch 2500, loss[loss=0.2109, simple_loss=0.2973, pruned_loss=0.06223, over 7161.00 frames.], tot_loss[loss=0.2488, simple_loss=0.327, pruned_loss=0.08534, over 1434009.12 frames.], batch size: 19, lr: 1.54e-03
2022-04-28 12:46:36,891 INFO [train.py:763] (4/8) Epoch 3, batch 2550, loss[loss=0.2197, simple_loss=0.293, pruned_loss=0.07324, over 7394.00 frames.], tot_loss[loss=0.2492, simple_loss=0.3271, pruned_loss=0.08566, over 1425842.75 frames.], batch size: 18, lr: 1.54e-03
2022-04-28 12:47:42,414 INFO [train.py:763] (4/8) Epoch 3, batch 2600, loss[loss=0.2455, simple_loss=0.3299, pruned_loss=0.08055, over 7237.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3289, pruned_loss=0.08739, over 1426014.50 frames.], batch size: 20, lr: 1.53e-03
2022-04-28 12:48:47,821 INFO [train.py:763] (4/8) Epoch 3, batch 2650, loss[loss=0.2364, simple_loss=0.3, pruned_loss=0.08639, over 7002.00 frames.], tot_loss[loss=0.2523, simple_loss=0.3295, pruned_loss=0.08753, over 1419485.82 frames.], batch size: 16, lr: 1.53e-03
2022-04-28 12:49:52,899 INFO [train.py:763] (4/8) Epoch 3, batch 2700, loss[loss=0.2026, simple_loss=0.2821, pruned_loss=0.06159, over 6803.00 frames.], tot_loss[loss=0.251, simple_loss=0.3286, pruned_loss=0.08671, over 1417804.91 frames.], batch size: 15, lr: 1.53e-03
2022-04-28 12:50:58,279 INFO [train.py:763] (4/8) Epoch 3, batch 2750, loss[loss=0.2207, simple_loss=0.3101, pruned_loss=0.06568, over 7249.00 frames.], tot_loss[loss=0.2493, simple_loss=0.328, pruned_loss=0.08533, over 1421424.92 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:52:03,625 INFO [train.py:763] (4/8) Epoch 3, batch 2800, loss[loss=0.2176, simple_loss=0.3017, pruned_loss=0.06679, over 7162.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3258, pruned_loss=0.08385, over 1423781.51 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:53:09,246 INFO [train.py:763] (4/8) Epoch 3, batch 2850, loss[loss=0.2599, simple_loss=0.3405, pruned_loss=0.08968, over 5257.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3248, pruned_loss=0.08321, over 1423527.08 frames.], batch size: 53, lr: 1.52e-03
2022-04-28 12:54:14,534 INFO [train.py:763] (4/8) Epoch 3, batch 2900, loss[loss=0.3028, simple_loss=0.369, pruned_loss=0.1183, over 6747.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3251, pruned_loss=0.08378, over 1423895.95 frames.], batch size: 31, lr: 1.52e-03
2022-04-28 12:55:20,286 INFO [train.py:763] (4/8) Epoch 3, batch 2950, loss[loss=0.2499, simple_loss=0.3319, pruned_loss=0.08394, over 7076.00 frames.], tot_loss[loss=0.2461, simple_loss=0.325, pruned_loss=0.08358, over 1428140.90 frames.], batch size: 28, lr: 1.52e-03
2022-04-28 12:56:25,609 INFO [train.py:763] (4/8) Epoch 3, batch 3000, loss[loss=0.2497, simple_loss=0.3387, pruned_loss=0.08039, over 7138.00 frames.], tot_loss[loss=0.2461, simple_loss=0.3249, pruned_loss=0.08367, over 1426342.09 frames.], batch size: 20, lr: 1.52e-03
2022-04-28 12:56:25,610 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 12:56:40,878 INFO [train.py:792] (4/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
2022-04-28 12:57:46,579 INFO [train.py:763] (4/8) Epoch 3, batch 3050, loss[loss=0.2349, simple_loss=0.3222, pruned_loss=0.07375, over 7104.00 frames.], tot_loss[loss=0.2472, simple_loss=0.326, pruned_loss=0.08422, over 1420504.96 frames.], batch size: 21, lr: 1.51e-03
2022-04-28 12:58:52,512 INFO [train.py:763] (4/8) Epoch 3, batch 3100, loss[loss=0.2721, simple_loss=0.3438, pruned_loss=0.1002, over 7287.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3252, pruned_loss=0.08399, over 1417377.13 frames.], batch size: 24, lr: 1.51e-03
2022-04-28 12:59:58,114 INFO [train.py:763] (4/8) Epoch 3, batch 3150, loss[loss=0.2561, simple_loss=0.3312, pruned_loss=0.09052, over 7275.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3242, pruned_loss=0.08351, over 1421695.56 frames.], batch size: 25, lr: 1.51e-03
2022-04-28 13:01:03,461 INFO [train.py:763] (4/8) Epoch 3, batch 3200, loss[loss=0.1997, simple_loss=0.2912, pruned_loss=0.0541, over 7061.00 frames.], tot_loss[loss=0.2445, simple_loss=0.323, pruned_loss=0.08297, over 1422956.19 frames.], batch size: 18, lr: 1.51e-03
2022-04-28 13:02:09,451 INFO [train.py:763] (4/8) Epoch 3, batch 3250, loss[loss=0.2225, simple_loss=0.298, pruned_loss=0.07353, over 7254.00 frames.], tot_loss[loss=0.245, simple_loss=0.3234, pruned_loss=0.08329, over 1423424.84 frames.], batch size: 19, lr: 1.51e-03
2022-04-28 13:03:16,230 INFO [train.py:763] (4/8) Epoch 3, batch 3300, loss[loss=0.2371, simple_loss=0.3163, pruned_loss=0.0789, over 7201.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3223, pruned_loss=0.08268, over 1422783.02 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:04:22,925 INFO [train.py:763] (4/8) Epoch 3, batch 3350, loss[loss=0.2837, simple_loss=0.3533, pruned_loss=0.107, over 6528.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3217, pruned_loss=0.08235, over 1421118.25 frames.], batch size: 38, lr: 1.50e-03
2022-04-28 13:05:28,640 INFO [train.py:763] (4/8) Epoch 3, batch 3400, loss[loss=0.2492, simple_loss=0.3184, pruned_loss=0.09003, over 6986.00 frames.], tot_loss[loss=0.2441, simple_loss=0.3221, pruned_loss=0.08309, over 1422195.38 frames.], batch size: 16, lr: 1.50e-03
2022-04-28 13:06:35,005 INFO [train.py:763] (4/8) Epoch 3, batch 3450, loss[loss=0.2255, simple_loss=0.3033, pruned_loss=0.07383, over 7160.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3208, pruned_loss=0.08201, over 1426888.44 frames.], batch size: 18, lr: 1.50e-03
2022-04-28 13:07:42,191 INFO [train.py:763] (4/8) Epoch 3, batch 3500, loss[loss=0.2615, simple_loss=0.3394, pruned_loss=0.09185, over 7373.00 frames.], tot_loss[loss=0.2432, simple_loss=0.3215, pruned_loss=0.08248, over 1428340.21 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:08:48,563 INFO [train.py:763] (4/8) Epoch 3, batch 3550, loss[loss=0.291, simple_loss=0.3645, pruned_loss=0.1088, over 7322.00 frames.], tot_loss[loss=0.242, simple_loss=0.3206, pruned_loss=0.08168, over 1429851.79 frames.], batch size: 24, lr: 1.49e-03
2022-04-28 13:09:55,525 INFO [train.py:763] (4/8) Epoch 3, batch 3600, loss[loss=0.226, simple_loss=0.3057, pruned_loss=0.07318, over 7414.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3217, pruned_loss=0.08258, over 1428677.52 frames.], batch size: 17, lr: 1.49e-03
2022-04-28 13:11:02,049 INFO [train.py:763] (4/8) Epoch 3, batch 3650, loss[loss=0.2608, simple_loss=0.3258, pruned_loss=0.09789, over 7130.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3212, pruned_loss=0.08212, over 1428716.53 frames.], batch size: 17, lr: 1.49e-03
2022-04-28 13:12:07,902 INFO [train.py:763] (4/8) Epoch 3, batch 3700, loss[loss=0.194, simple_loss=0.2778, pruned_loss=0.05508, over 6989.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3209, pruned_loss=0.08177, over 1427641.02 frames.], batch size: 16, lr: 1.49e-03
2022-04-28 13:13:15,358 INFO [train.py:763] (4/8) Epoch 3, batch 3750, loss[loss=0.2302, simple_loss=0.3076, pruned_loss=0.07634, over 7435.00 frames.], tot_loss[loss=0.2415, simple_loss=0.3202, pruned_loss=0.08142, over 1424696.34 frames.], batch size: 20, lr: 1.49e-03
2022-04-28 13:14:22,355 INFO [train.py:763] (4/8) Epoch 3, batch 3800, loss[loss=0.2193, simple_loss=0.3007, pruned_loss=0.06897, over 7067.00 frames.], tot_loss[loss=0.2429, simple_loss=0.3216, pruned_loss=0.08217, over 1420374.86 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:15:29,711 INFO [train.py:763] (4/8) Epoch 3, batch 3850, loss[loss=0.1952, simple_loss=0.2766, pruned_loss=0.0569, over 7412.00 frames.], tot_loss[loss=0.2422, simple_loss=0.321, pruned_loss=0.0817, over 1424706.64 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:16:35,235 INFO [train.py:763] (4/8) Epoch 3, batch 3900, loss[loss=0.2918, simple_loss=0.357, pruned_loss=0.1133, over 4808.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3203, pruned_loss=0.0805, over 1426052.97 frames.], batch size: 53, lr: 1.48e-03
2022-04-28 13:17:41,251 INFO [train.py:763] (4/8) Epoch 3, batch 3950, loss[loss=0.22, simple_loss=0.2944, pruned_loss=0.07278, over 6778.00 frames.], tot_loss[loss=0.2396, simple_loss=0.319, pruned_loss=0.08006, over 1424614.61 frames.], batch size: 15, lr: 1.48e-03
2022-04-28 13:18:46,785 INFO [train.py:763] (4/8) Epoch 3, batch 4000, loss[loss=0.273, simple_loss=0.3483, pruned_loss=0.0988, over 7211.00 frames.], tot_loss[loss=0.2406, simple_loss=0.3197, pruned_loss=0.08077, over 1415951.72 frames.], batch size: 21, lr: 1.48e-03
2022-04-28 13:19:52,128 INFO [train.py:763] (4/8) Epoch 3, batch 4050, loss[loss=0.2507, simple_loss=0.3352, pruned_loss=0.08307, over 7410.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3208, pruned_loss=0.08154, over 1418699.73 frames.], batch size: 21, lr: 1.47e-03
2022-04-28 13:20:58,241 INFO [train.py:763] (4/8) Epoch 3, batch 4100, loss[loss=0.2388, simple_loss=0.3174, pruned_loss=0.08007, over 6342.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3223, pruned_loss=0.08277, over 1421215.92 frames.], batch size: 37, lr: 1.47e-03
2022-04-28 13:22:04,071 INFO [train.py:763] (4/8) Epoch 3, batch 4150, loss[loss=0.1983, simple_loss=0.2711, pruned_loss=0.06277, over 6988.00 frames.], tot_loss[loss=0.2423, simple_loss=0.3209, pruned_loss=0.08185, over 1423543.65 frames.], batch size: 16, lr: 1.47e-03
2022-04-28 13:23:11,043 INFO [train.py:763] (4/8) Epoch 3, batch 4200, loss[loss=0.2209, simple_loss=0.3124, pruned_loss=0.06471, over 7156.00 frames.], tot_loss[loss=0.2424, simple_loss=0.3211, pruned_loss=0.08183, over 1421784.08 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:24:18,325 INFO [train.py:763] (4/8) Epoch 3, batch 4250, loss[loss=0.2319, simple_loss=0.3058, pruned_loss=0.07897, over 7360.00 frames.], tot_loss[loss=0.243, simple_loss=0.3209, pruned_loss=0.08251, over 1413996.98 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:25:24,086 INFO [train.py:763] (4/8) Epoch 3, batch 4300, loss[loss=0.2291, simple_loss=0.3108, pruned_loss=0.07376, over 7357.00 frames.], tot_loss[loss=0.2407, simple_loss=0.3185, pruned_loss=0.08144, over 1412486.75 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:26:29,893 INFO [train.py:763] (4/8) Epoch 3, batch 4350, loss[loss=0.2623, simple_loss=0.3365, pruned_loss=0.09403, over 6317.00 frames.], tot_loss[loss=0.2385, simple_loss=0.3163, pruned_loss=0.08035, over 1410841.43 frames.], batch size: 37, lr: 1.46e-03
2022-04-28 13:27:35,677 INFO [train.py:763] (4/8) Epoch 3, batch 4400, loss[loss=0.2262, simple_loss=0.2987, pruned_loss=0.07681, over 7066.00 frames.], tot_loss[loss=0.2391, simple_loss=0.3164, pruned_loss=0.08085, over 1409174.60 frames.], batch size: 18, lr: 1.46e-03
2022-04-28 13:28:41,561 INFO [train.py:763] (4/8) Epoch 3, batch 4450, loss[loss=0.2641, simple_loss=0.3358, pruned_loss=0.09623, over 7373.00 frames.], tot_loss[loss=0.2403, simple_loss=0.317, pruned_loss=0.08176, over 1400880.26 frames.], batch size: 23, lr: 1.46e-03
2022-04-28 13:29:46,949 INFO [train.py:763] (4/8) Epoch 3, batch 4500, loss[loss=0.2699, simple_loss=0.3376, pruned_loss=0.1011, over 6483.00 frames.], tot_loss[loss=0.2411, simple_loss=0.3176, pruned_loss=0.08229, over 1396244.29 frames.], batch size: 38, lr: 1.46e-03
2022-04-28 13:30:51,038 INFO [train.py:763] (4/8) Epoch 3, batch 4550, loss[loss=0.2928, simple_loss=0.3507, pruned_loss=0.1175, over 5262.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3213, pruned_loss=0.08471, over 1361505.34 frames.], batch size: 52, lr: 1.46e-03
2022-04-28 13:32:20,223 INFO [train.py:763] (4/8) Epoch 4, batch 0, loss[loss=0.2556, simple_loss=0.3492, pruned_loss=0.08104, over 7201.00 frames.], tot_loss[loss=0.2556, simple_loss=0.3492, pruned_loss=0.08104, over 7201.00 frames.], batch size: 23, lr: 1.40e-03
2022-04-28 13:33:26,502 INFO [train.py:763] (4/8) Epoch 4, batch 50, loss[loss=0.2544, simple_loss=0.3443, pruned_loss=0.08221, over 7332.00 frames.], tot_loss[loss=0.2427, simple_loss=0.3233, pruned_loss=0.08108, over 320830.00 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:34:31,939 INFO [train.py:763] (4/8) Epoch 4, batch 100, loss[loss=0.2491, simple_loss=0.3395, pruned_loss=0.07937, over 7343.00 frames.], tot_loss[loss=0.2387, simple_loss=0.3209, pruned_loss=0.07828, over 566370.58 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:35:37,379 INFO [train.py:763] (4/8) Epoch 4, batch 150, loss[loss=0.2677, simple_loss=0.3304, pruned_loss=0.1025, over 4895.00 frames.], tot_loss[loss=0.2398, simple_loss=0.3203, pruned_loss=0.07965, over 754890.60 frames.], batch size: 52, lr: 1.40e-03
2022-04-28 13:36:43,012 INFO [train.py:763] (4/8) Epoch 4, batch 200, loss[loss=0.2029, simple_loss=0.2953, pruned_loss=0.05523, over 7155.00 frames.], tot_loss[loss=0.2414, simple_loss=0.3218, pruned_loss=0.08047, over 903987.76 frames.], batch size: 19, lr: 1.40e-03
2022-04-28 13:37:48,978 INFO [train.py:763] (4/8) Epoch 4, batch 250, loss[loss=0.2455, simple_loss=0.3372, pruned_loss=0.07692, over 7344.00 frames.], tot_loss[loss=0.2434, simple_loss=0.324, pruned_loss=0.08145, over 1021357.41 frames.], batch size: 22, lr: 1.39e-03
2022-04-28 13:38:55,651 INFO [train.py:763] (4/8) Epoch 4, batch 300, loss[loss=0.2325, simple_loss=0.2922, pruned_loss=0.08634, over 7264.00 frames.], tot_loss[loss=0.2401, simple_loss=0.3206, pruned_loss=0.0798, over 1113916.01 frames.], batch size: 17, lr: 1.39e-03
2022-04-28 13:40:02,792 INFO [train.py:763] (4/8) Epoch 4, batch 350, loss[loss=0.2112, simple_loss=0.3035, pruned_loss=0.05949, over 7160.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3179, pruned_loss=0.07776, over 1182247.92 frames.], batch size: 19, lr: 1.39e-03
2022-04-28 13:41:09,480 INFO [train.py:763] (4/8) Epoch 4, batch 400, loss[loss=0.2251, simple_loss=0.3162, pruned_loss=0.06695, over 7081.00 frames.], tot_loss[loss=0.2379, simple_loss=0.3185, pruned_loss=0.07865, over 1233833.45 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:42:15,464 INFO [train.py:763] (4/8) Epoch 4, batch 450, loss[loss=0.2548, simple_loss=0.3344, pruned_loss=0.08765, over 7061.00 frames.], tot_loss[loss=0.2384, simple_loss=0.3187, pruned_loss=0.07902, over 1275394.13 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:43:21,270 INFO [train.py:763] (4/8) Epoch 4, batch 500, loss[loss=0.2195, simple_loss=0.3095, pruned_loss=0.06474, over 7321.00 frames.], tot_loss[loss=0.2356, simple_loss=0.3166, pruned_loss=0.07726, over 1309761.35 frames.], batch size: 21, lr: 1.39e-03
2022-04-28 13:44:28,334 INFO [train.py:763] (4/8) Epoch 4, batch 550, loss[loss=0.233, simple_loss=0.3151, pruned_loss=0.0754, over 6749.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3165, pruned_loss=0.07732, over 1333773.05 frames.], batch size: 31, lr: 1.38e-03
2022-04-28 13:45:33,790 INFO [train.py:763] (4/8) Epoch 4, batch 600, loss[loss=0.2309, simple_loss=0.2898, pruned_loss=0.08597, over 6997.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3153, pruned_loss=0.07671, over 1355429.84 frames.], batch size: 16, lr: 1.38e-03
2022-04-28 13:46:39,056 INFO [train.py:763] (4/8) Epoch 4, batch 650, loss[loss=0.2077, simple_loss=0.2932, pruned_loss=0.06113, over 7319.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3152, pruned_loss=0.07657, over 1369976.10 frames.], batch size: 20, lr: 1.38e-03
2022-04-28 13:47:44,002 INFO [train.py:763] (4/8) Epoch 4, batch 700, loss[loss=0.2751, simple_loss=0.3712, pruned_loss=0.08951, over 7294.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3174, pruned_loss=0.07761, over 1379691.24 frames.], batch size: 25, lr: 1.38e-03
2022-04-28 13:48:49,477 INFO [train.py:763] (4/8) Epoch 4, batch 750, loss[loss=0.2185, simple_loss=0.2987, pruned_loss=0.06916, over 7063.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3172, pruned_loss=0.07763, over 1385046.31 frames.], batch size: 18, lr: 1.38e-03
2022-04-28 13:49:55,001 INFO [train.py:763] (4/8) Epoch 4, batch 800, loss[loss=0.2213, simple_loss=0.2994, pruned_loss=0.07161, over 7070.00 frames.], tot_loss[loss=0.2341, simple_loss=0.315, pruned_loss=0.07656, over 1396693.25 frames.], batch size: 18, lr: 1.38e-03
2022-04-28 13:50:59,965 INFO [train.py:763] (4/8) Epoch 4, batch 850, loss[loss=0.2293, simple_loss=0.3042, pruned_loss=0.0772, over 7063.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3149, pruned_loss=0.07638, over 1396164.36 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:52:05,755 INFO [train.py:763] (4/8) Epoch 4, batch 900, loss[loss=0.2577, simple_loss=0.3388, pruned_loss=0.08833, over 7317.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3152, pruned_loss=0.07658, over 1402777.82 frames.], batch size: 21, lr: 1.37e-03
2022-04-28 13:53:12,230 INFO [train.py:763] (4/8) Epoch 4, batch 950, loss[loss=0.2678, simple_loss=0.3498, pruned_loss=0.09291, over 7063.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3155, pruned_loss=0.07676, over 1406760.91 frames.], batch size: 28, lr: 1.37e-03
2022-04-28 13:54:19,381 INFO [train.py:763] (4/8) Epoch 4, batch 1000, loss[loss=0.2097, simple_loss=0.291, pruned_loss=0.06423, over 7067.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3152, pruned_loss=0.07687, over 1410255.73 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:55:24,900 INFO [train.py:763] (4/8) Epoch 4, batch 1050, loss[loss=0.2717, simple_loss=0.3505, pruned_loss=0.0964, over 7296.00 frames.], tot_loss[loss=0.2349, simple_loss=0.316, pruned_loss=0.07693, over 1415956.34 frames.], batch size: 24, lr: 1.37e-03
2022-04-28 13:56:29,979 INFO [train.py:763] (4/8) Epoch 4, batch 1100, loss[loss=0.2577, simple_loss=0.3332, pruned_loss=0.09114, over 6354.00 frames.], tot_loss[loss=0.237, simple_loss=0.3177, pruned_loss=0.07818, over 1412688.53 frames.], batch size: 37, lr: 1.37e-03
2022-04-28 13:57:36,085 INFO [train.py:763] (4/8) Epoch 4, batch 1150, loss[loss=0.2156, simple_loss=0.2983, pruned_loss=0.06649, over 7421.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3177, pruned_loss=0.07798, over 1415522.21 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 13:58:41,142 INFO [train.py:763] (4/8) Epoch 4, batch 1200, loss[loss=0.2793, simple_loss=0.3501, pruned_loss=0.1043, over 6281.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3165, pruned_loss=0.07712, over 1416955.98 frames.], batch size: 37, lr: 1.36e-03
2022-04-28 13:59:46,357 INFO [train.py:763] (4/8) Epoch 4, batch 1250, loss[loss=0.2194, simple_loss=0.307, pruned_loss=0.06588, over 7252.00 frames.], tot_loss[loss=0.2365, simple_loss=0.3166, pruned_loss=0.07817, over 1413205.73 frames.], batch size: 19, lr: 1.36e-03
2022-04-28 14:00:51,529 INFO [train.py:763] (4/8) Epoch 4, batch 1300, loss[loss=0.2378, simple_loss=0.3148, pruned_loss=0.08036, over 7328.00 frames.], tot_loss[loss=0.2367, simple_loss=0.3175, pruned_loss=0.07795, over 1417147.97 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:01:57,421 INFO [train.py:763] (4/8) Epoch 4, batch 1350, loss[loss=0.2106, simple_loss=0.2798, pruned_loss=0.07075, over 7125.00 frames.], tot_loss[loss=0.2378, simple_loss=0.3185, pruned_loss=0.0785, over 1423617.81 frames.], batch size: 17, lr: 1.36e-03
2022-04-28 14:03:02,787 INFO [train.py:763] (4/8) Epoch 4, batch 1400, loss[loss=0.2488, simple_loss=0.3252, pruned_loss=0.08617, over 7239.00 frames.], tot_loss[loss=0.239, simple_loss=0.3199, pruned_loss=0.07906, over 1419240.78 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:04:07,963 INFO [train.py:763] (4/8) Epoch 4, batch 1450, loss[loss=0.1962, simple_loss=0.272, pruned_loss=0.06026, over 6999.00 frames.], tot_loss[loss=0.2386, simple_loss=0.3195, pruned_loss=0.07882, over 1419643.10 frames.], batch size: 16, lr: 1.35e-03
2022-04-28 14:05:14,092 INFO [train.py:763] (4/8) Epoch 4, batch 1500, loss[loss=0.2037, simple_loss=0.2881, pruned_loss=0.0597, over 7336.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3171, pruned_loss=0.07696, over 1422805.60 frames.], batch size: 20, lr: 1.35e-03
2022-04-28 14:06:19,705 INFO [train.py:763] (4/8) Epoch 4, batch 1550, loss[loss=0.2331, simple_loss=0.3291, pruned_loss=0.06858, over 7368.00 frames.], tot_loss[loss=0.2338, simple_loss=0.3153, pruned_loss=0.07617, over 1424723.97 frames.], batch size: 23, lr: 1.35e-03
2022-04-28 14:07:24,977 INFO [train.py:763] (4/8) Epoch 4, batch 1600, loss[loss=0.2632, simple_loss=0.3439, pruned_loss=0.09121, over 7278.00 frames.], tot_loss[loss=0.234, simple_loss=0.3154, pruned_loss=0.07632, over 1423891.03 frames.], batch size: 25, lr: 1.35e-03
2022-04-28 14:08:30,206 INFO [train.py:763] (4/8) Epoch 4, batch 1650, loss[loss=0.2626, simple_loss=0.3385, pruned_loss=0.09338, over 7111.00 frames.], tot_loss[loss=0.2345, simple_loss=0.316, pruned_loss=0.07652, over 1421116.32 frames.], batch size: 21, lr: 1.35e-03
2022-04-28 14:09:35,798 INFO [train.py:763] (4/8) Epoch 4, batch 1700, loss[loss=0.2488, simple_loss=0.337, pruned_loss=0.0803, over 7340.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3145, pruned_loss=0.07534, over 1423904.71 frames.], batch size: 22, lr: 1.35e-03
2022-04-28 14:10:42,768 INFO [train.py:763] (4/8) Epoch 4, batch 1750, loss[loss=0.2182, simple_loss=0.3039, pruned_loss=0.06627, over 7307.00 frames.], tot_loss[loss=0.2334, simple_loss=0.315, pruned_loss=0.07585, over 1424202.95 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:11:49,091 INFO [train.py:763] (4/8) Epoch 4, batch 1800, loss[loss=0.2256, simple_loss=0.3229, pruned_loss=0.06414, over 7324.00 frames.], tot_loss[loss=0.2335, simple_loss=0.3153, pruned_loss=0.07581, over 1426433.78 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:12:54,648 INFO [train.py:763] (4/8) Epoch 4, batch 1850, loss[loss=0.2477, simple_loss=0.3339, pruned_loss=0.08078, over 6276.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3161, pruned_loss=0.07605, over 1427104.96 frames.], batch size: 37, lr: 1.34e-03
2022-04-28 14:13:59,949 INFO [train.py:763] (4/8) Epoch 4, batch 1900, loss[loss=0.2715, simple_loss=0.3531, pruned_loss=0.09494, over 7121.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3156, pruned_loss=0.07539, over 1428740.89 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:15:05,360 INFO [train.py:763] (4/8) Epoch 4, batch 1950, loss[loss=0.217, simple_loss=0.2958, pruned_loss=0.06907, over 7154.00 frames.], tot_loss[loss=0.2326, simple_loss=0.315, pruned_loss=0.07509, over 1429190.65 frames.], batch size: 18, lr: 1.34e-03
2022-04-28 14:16:10,981 INFO [train.py:763] (4/8) Epoch 4, batch 2000, loss[loss=0.2319, simple_loss=0.3131, pruned_loss=0.07531, over 7270.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3146, pruned_loss=0.07549, over 1426871.14 frames.], batch size: 25, lr: 1.34e-03
2022-04-28 14:17:16,769 INFO [train.py:763] (4/8) Epoch 4, batch 2050, loss[loss=0.2339, simple_loss=0.3231, pruned_loss=0.0724, over 7269.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3148, pruned_loss=0.07555, over 1431753.04 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:18:22,257 INFO [train.py:763] (4/8) Epoch 4, batch 2100, loss[loss=0.1877, simple_loss=0.2649, pruned_loss=0.05522, over 7398.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3138, pruned_loss=0.07485, over 1434504.70 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:19:27,835 INFO [train.py:763] (4/8) Epoch 4, batch 2150, loss[loss=0.2242, simple_loss=0.3008, pruned_loss=0.07384, over 7061.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3148, pruned_loss=0.07492, over 1432755.91 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:20:34,205 INFO [train.py:763] (4/8) Epoch 4, batch 2200, loss[loss=0.2534, simple_loss=0.3405, pruned_loss=0.08318, over 7353.00 frames.], tot_loss[loss=0.2328, simple_loss=0.315, pruned_loss=0.07531, over 1433899.96 frames.], batch size: 22, lr: 1.33e-03
2022-04-28 14:21:39,758 INFO [train.py:763] (4/8) Epoch 4, batch 2250, loss[loss=0.2604, simple_loss=0.3466, pruned_loss=0.08714, over 7373.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3162, pruned_loss=0.07617, over 1431477.66 frames.], batch size: 23, lr: 1.33e-03
2022-04-28 14:22:45,296 INFO [train.py:763] (4/8) Epoch 4, batch 2300, loss[loss=0.2119, simple_loss=0.2805, pruned_loss=0.07162, over 7265.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3165, pruned_loss=0.07687, over 1429189.75 frames.], batch size: 17, lr: 1.33e-03
2022-04-28 14:23:50,800 INFO [train.py:763] (4/8) Epoch 4, batch 2350, loss[loss=0.1912, simple_loss=0.2778, pruned_loss=0.05231, over 7415.00 frames.], tot_loss[loss=0.2357, simple_loss=0.3171, pruned_loss=0.07712, over 1432487.74 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:24:56,453 INFO [train.py:763] (4/8) Epoch 4, batch 2400, loss[loss=0.2356, simple_loss=0.3403, pruned_loss=0.06538, over 7223.00 frames.], tot_loss[loss=0.2352, simple_loss=0.3167, pruned_loss=0.07688, over 1434064.81 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:26:01,946 INFO [train.py:763] (4/8) Epoch 4, batch 2450, loss[loss=0.2251, simple_loss=0.2999, pruned_loss=0.07509, over 7272.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3166, pruned_loss=0.07656, over 1434222.20 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:27:09,067 INFO [train.py:763] (4/8) Epoch 4, batch 2500, loss[loss=0.2341, simple_loss=0.3245, pruned_loss=0.07186, over 7209.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3156, pruned_loss=0.07608, over 1431825.16 frames.], batch size: 22, lr: 1.32e-03
2022-04-28 14:28:14,995 INFO [train.py:763] (4/8) Epoch 4, batch 2550, loss[loss=0.2525, simple_loss=0.3429, pruned_loss=0.081, over 7140.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3153, pruned_loss=0.07553, over 1432284.19 frames.], batch size: 20, lr: 1.32e-03
2022-04-28 14:29:20,317 INFO [train.py:763] (4/8) Epoch 4, batch 2600, loss[loss=0.259, simple_loss=0.3382, pruned_loss=0.08995, over 7317.00 frames.], tot_loss[loss=0.2339, simple_loss=0.316, pruned_loss=0.07594, over 1430940.46 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:30:26,095 INFO [train.py:763] (4/8) Epoch 4, batch 2650, loss[loss=0.1951, simple_loss=0.2758, pruned_loss=0.05715, over 6995.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3152, pruned_loss=0.07568, over 1429438.98 frames.], batch size: 16, lr: 1.32e-03
2022-04-28 14:31:31,705 INFO [train.py:763] (4/8) Epoch 4, batch 2700, loss[loss=0.1811, simple_loss=0.2656, pruned_loss=0.04827, over 7269.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3148, pruned_loss=0.07537, over 1431631.80 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:32:38,235 INFO [train.py:763] (4/8) Epoch 4, batch 2750, loss[loss=0.1985, simple_loss=0.2884, pruned_loss=0.0543, over 7348.00 frames.], tot_loss[loss=0.232, simple_loss=0.3141, pruned_loss=0.07489, over 1432601.19 frames.], batch size: 19, lr: 1.31e-03
2022-04-28 14:33:43,920 INFO [train.py:763] (4/8) Epoch 4, batch 2800, loss[loss=0.2375, simple_loss=0.307, pruned_loss=0.08404, over 7148.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3131, pruned_loss=0.07449, over 1433243.77 frames.], batch size: 17, lr: 1.31e-03
2022-04-28 14:34:49,325 INFO [train.py:763] (4/8) Epoch 4, batch 2850, loss[loss=0.2893, simple_loss=0.3752, pruned_loss=0.1016, over 6740.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3133, pruned_loss=0.0744, over 1430839.58 frames.], batch size: 31, lr: 1.31e-03
2022-04-28 14:35:55,985 INFO [train.py:763] (4/8) Epoch 4, batch 2900, loss[loss=0.2635, simple_loss=0.3381, pruned_loss=0.09441, over 7281.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3147, pruned_loss=0.0753, over 1428840.24 frames.], batch size: 24, lr: 1.31e-03
2022-04-28 14:37:01,944 INFO [train.py:763] (4/8) Epoch 4, batch 2950, loss[loss=0.2243, simple_loss=0.3127, pruned_loss=0.06793, over 7345.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3131, pruned_loss=0.07425, over 1428320.14 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:38:07,792 INFO [train.py:763] (4/8) Epoch 4, batch 3000, loss[loss=0.2518, simple_loss=0.3251, pruned_loss=0.08931, over 7180.00 frames.], tot_loss[loss=0.232, simple_loss=0.3136, pruned_loss=0.07515, over 1423930.76 frames.], batch size: 26, lr: 1.31e-03
2022-04-28 14:38:07,793 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 14:38:23,246 INFO [train.py:792] (4/8) Epoch 4, validation: loss=0.1809, simple_loss=0.2865, pruned_loss=0.03766, over 698248.00 frames.
2022-04-28 14:39:28,675 INFO [train.py:763] (4/8) Epoch 4, batch 3050, loss[loss=0.2331, simple_loss=0.317, pruned_loss=0.07461, over 7200.00 frames.], tot_loss[loss=0.2323, simple_loss=0.3141, pruned_loss=0.0753, over 1428194.86 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:40:34,109 INFO [train.py:763] (4/8) Epoch 4, batch 3100, loss[loss=0.1978, simple_loss=0.2824, pruned_loss=0.05664, over 7232.00 frames.], tot_loss[loss=0.2313, simple_loss=0.3136, pruned_loss=0.07449, over 1427409.44 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:41:39,917 INFO [train.py:763] (4/8) Epoch 4, batch 3150, loss[loss=0.2598, simple_loss=0.3372, pruned_loss=0.09117, over 7307.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3135, pruned_loss=0.07391, over 1428055.28 frames.], batch size: 25, lr: 1.30e-03
2022-04-28 14:42:46,504 INFO [train.py:763] (4/8) Epoch 4, batch 3200, loss[loss=0.2496, simple_loss=0.3226, pruned_loss=0.08834, over 7368.00 frames.], tot_loss[loss=0.2308, simple_loss=0.3137, pruned_loss=0.07398, over 1429641.71 frames.], batch size: 19, lr: 1.30e-03
2022-04-28 14:43:52,376 INFO [train.py:763] (4/8) Epoch 4, batch 3250, loss[loss=0.2141, simple_loss=0.2887, pruned_loss=0.06975, over 7173.00 frames.], tot_loss[loss=0.231, simple_loss=0.3139, pruned_loss=0.07406, over 1428187.39 frames.], batch size: 18, lr: 1.30e-03
2022-04-28 14:44:57,964 INFO [train.py:763] (4/8) Epoch 4, batch 3300, loss[loss=0.2395, simple_loss=0.3188, pruned_loss=0.08007, over 7181.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3143, pruned_loss=0.07453, over 1423664.56 frames.], batch size: 26, lr: 1.30e-03
2022-04-28 14:46:03,552 INFO [train.py:763] (4/8) Epoch 4, batch 3350, loss[loss=0.2873, simple_loss=0.3606, pruned_loss=0.107, over 7109.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3148, pruned_loss=0.07444, over 1426393.96 frames.], batch size: 21, lr: 1.30e-03
2022-04-28 14:47:08,813 INFO [train.py:763] (4/8) Epoch 4, batch 3400, loss[loss=0.2706, simple_loss=0.3518, pruned_loss=0.09469, over 7239.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3157, pruned_loss=0.07529, over 1428046.65 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:48:14,156 INFO [train.py:763] (4/8) Epoch 4, batch 3450, loss[loss=0.2496, simple_loss=0.3382, pruned_loss=0.08049, over 7200.00 frames.], tot_loss[loss=0.233, simple_loss=0.3155, pruned_loss=0.07527, over 1428103.43 frames.], batch size: 23, lr: 1.29e-03
2022-04-28 14:49:37,445 INFO [train.py:763] (4/8) Epoch 4, batch 3500, loss[loss=0.216, simple_loss=0.2993, pruned_loss=0.06633, over 7320.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3155, pruned_loss=0.075, over 1430828.05 frames.], batch size: 20, lr: 1.29e-03
2022-04-28 14:50:52,144 INFO [train.py:763] (4/8) Epoch 4, batch 3550, loss[loss=0.234, simple_loss=0.3261, pruned_loss=0.07092, over 7409.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3162, pruned_loss=0.07499, over 1425583.39 frames.], batch size: 21, lr: 1.29e-03
2022-04-28 14:51:57,840 INFO [train.py:763] (4/8) Epoch 4, batch 3600, loss[loss=0.2335, simple_loss=0.3099, pruned_loss=0.07855, over 7263.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3143, pruned_loss=0.07451, over 1421779.82 frames.], batch size: 19, lr: 1.29e-03
2022-04-28 14:53:23,229 INFO [train.py:763] (4/8) Epoch 4, batch 3650, loss[loss=0.2299, simple_loss=0.3184, pruned_loss=0.07068, over 6710.00 frames.], tot_loss[loss=0.2331, simple_loss=0.3153, pruned_loss=0.07542, over 1416336.76 frames.], batch size: 31, lr: 1.29e-03
2022-04-28 14:54:39,012 INFO [train.py:763] (4/8) Epoch 4, batch 3700, loss[loss=0.2112, simple_loss=0.2984, pruned_loss=0.06195, over 7169.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3127, pruned_loss=0.07417, over 1419822.50 frames.], batch size: 18, lr: 1.29e-03
2022-04-28 14:55:53,480 INFO [train.py:763] (4/8) Epoch 4, batch 3750, loss[loss=0.2428, simple_loss=0.3108, pruned_loss=0.08739, over 6815.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3146, pruned_loss=0.07522, over 1419563.21 frames.], batch size: 15, lr: 1.29e-03
2022-04-28 14:56:59,176 INFO [train.py:763] (4/8) Epoch 4, batch 3800, loss[loss=0.2041, simple_loss=0.2759, pruned_loss=0.06616, over 7279.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3141, pruned_loss=0.07463, over 1421309.97 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 14:58:05,505 INFO [train.py:763] (4/8) Epoch 4, batch 3850, loss[loss=0.2285, simple_loss=0.3118, pruned_loss=0.07259, over 7416.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3131, pruned_loss=0.0742, over 1421031.02 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 14:59:11,122 INFO [train.py:763] (4/8) Epoch 4, batch 3900, loss[loss=0.2045, simple_loss=0.294, pruned_loss=0.05756, over 7175.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3117, pruned_loss=0.07382, over 1417708.70 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:00:16,491 INFO [train.py:763] (4/8) Epoch 4, batch 3950, loss[loss=0.219, simple_loss=0.2999, pruned_loss=0.06907, over 7413.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3118, pruned_loss=0.07366, over 1414634.65 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:01:21,847 INFO [train.py:763] (4/8) Epoch 4, batch 4000, loss[loss=0.2252, simple_loss=0.3085, pruned_loss=0.07099, over 7427.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3117, pruned_loss=0.07291, over 1418753.13 frames.], batch size: 20, lr: 1.28e-03
2022-04-28 15:02:27,494 INFO [train.py:763] (4/8) Epoch 4, batch 4050, loss[loss=0.2407, simple_loss=0.3216, pruned_loss=0.0799, over 7217.00 frames.], tot_loss[loss=0.2282, simple_loss=0.3109, pruned_loss=0.07279, over 1422132.33 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:03:34,095 INFO [train.py:763] (4/8) Epoch 4, batch 4100, loss[loss=0.2125, simple_loss=0.291, pruned_loss=0.06695, over 7284.00 frames.], tot_loss[loss=0.2314, simple_loss=0.3142, pruned_loss=0.07432, over 1419153.67 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:04:40,945 INFO [train.py:763] (4/8) Epoch 4, batch 4150, loss[loss=0.2375, simple_loss=0.3239, pruned_loss=0.07557, over 7213.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3148, pruned_loss=0.07496, over 1417319.11 frames.], batch size: 22, lr: 1.27e-03
2022-04-28 15:05:47,253 INFO [train.py:763] (4/8) Epoch 4, batch 4200, loss[loss=0.2712, simple_loss=0.3413, pruned_loss=0.1005, over 7146.00 frames.], tot_loss[loss=0.2321, simple_loss=0.315, pruned_loss=0.07463, over 1415269.14 frames.], batch size: 17, lr: 1.27e-03
2022-04-28 15:06:53,140 INFO [train.py:763] (4/8) Epoch 4, batch 4250, loss[loss=0.2216, simple_loss=0.3046, pruned_loss=0.06928, over 7067.00 frames.], tot_loss[loss=0.2313, simple_loss=0.314, pruned_loss=0.07428, over 1416583.55 frames.], batch size: 18, lr: 1.27e-03
2022-04-28 15:07:59,468 INFO [train.py:763] (4/8) Epoch 4, batch 4300, loss[loss=0.2255, simple_loss=0.3149, pruned_loss=0.06807, over 7150.00 frames.], tot_loss[loss=0.231, simple_loss=0.3141, pruned_loss=0.07401, over 1416911.10 frames.], batch size: 20, lr: 1.27e-03
2022-04-28 15:09:04,572 INFO [train.py:763] (4/8) Epoch 4, batch 4350, loss[loss=0.2146, simple_loss=0.3093, pruned_loss=0.05994, over 7417.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3139, pruned_loss=0.0732, over 1415349.57 frames.], batch size: 21, lr: 1.27e-03
2022-04-28 15:10:09,733 INFO [train.py:763] (4/8) Epoch 4, batch 4400, loss[loss=0.192, simple_loss=0.2821, pruned_loss=0.05093, over 7258.00 frames.], tot_loss[loss=0.23, simple_loss=0.3138, pruned_loss=0.07315, over 1411869.12 frames.], batch size: 19, lr: 1.27e-03
2022-04-28 15:11:14,749 INFO [train.py:763] (4/8) Epoch 4, batch 4450, loss[loss=0.22, simple_loss=0.3078, pruned_loss=0.06614, over 6882.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3145, pruned_loss=0.07343, over 1405570.56 frames.], batch size: 31, lr: 1.27e-03
2022-04-28 15:12:19,723 INFO [train.py:763] (4/8) Epoch 4, batch 4500, loss[loss=0.2471, simple_loss=0.3303, pruned_loss=0.08189, over 4816.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3172, pruned_loss=0.07533, over 1394741.34 frames.], batch size: 52, lr: 1.27e-03
2022-04-28 15:13:25,331 INFO [train.py:763] (4/8) Epoch 4, batch 4550, loss[loss=0.2863, simple_loss=0.3488, pruned_loss=0.1119, over 4860.00 frames.], tot_loss[loss=0.2404, simple_loss=0.3211, pruned_loss=0.07982, over 1337079.29 frames.], batch size: 52, lr: 1.26e-03
2022-04-28 15:14:53,613 INFO [train.py:763] (4/8) Epoch 5, batch 0, loss[loss=0.2526, simple_loss=0.3245, pruned_loss=0.09032, over 7159.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3245, pruned_loss=0.09032, over 7159.00 frames.], batch size: 19, lr: 1.21e-03
2022-04-28 15:15:59,876 INFO [train.py:763] (4/8) Epoch 5, batch 50, loss[loss=0.254, simple_loss=0.3228, pruned_loss=0.09256, over 5237.00 frames.], tot_loss[loss=0.2307, simple_loss=0.3128, pruned_loss=0.07428, over 319467.42 frames.], batch size: 52, lr: 1.21e-03
2022-04-28 15:17:05,482 INFO [train.py:763] (4/8) Epoch 5, batch 100, loss[loss=0.2162, simple_loss=0.3211, pruned_loss=0.05565, over 7142.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3129, pruned_loss=0.07129, over 562339.50 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:18:11,202 INFO [train.py:763] (4/8) Epoch 5, batch 150, loss[loss=0.2413, simple_loss=0.3346, pruned_loss=0.07407, over 6768.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3118, pruned_loss=0.07053, over 749292.44 frames.], batch size: 31, lr: 1.21e-03
2022-04-28 15:19:17,536 INFO [train.py:763] (4/8) Epoch 5, batch 200, loss[loss=0.1984, simple_loss=0.2885, pruned_loss=0.05419, over 7418.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3104, pruned_loss=0.06948, over 899603.21 frames.], batch size: 18, lr: 1.21e-03
2022-04-28 15:20:23,012 INFO [train.py:763] (4/8) Epoch 5, batch 250, loss[loss=0.2476, simple_loss=0.3384, pruned_loss=0.07835, over 7331.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3103, pruned_loss=0.06914, over 1019739.57 frames.], batch size: 22, lr: 1.21e-03
2022-04-28 15:21:29,011 INFO [train.py:763] (4/8) Epoch 5, batch 300, loss[loss=0.1964, simple_loss=0.2963, pruned_loss=0.04827, over 7223.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3101, pruned_loss=0.06975, over 1111878.57 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:22:35,195 INFO [train.py:763] (4/8) Epoch 5, batch 350, loss[loss=0.2554, simple_loss=0.336, pruned_loss=0.08736, over 7339.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3076, pruned_loss=0.06871, over 1185296.72 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:23:40,933 INFO [train.py:763] (4/8) Epoch 5, batch 400, loss[loss=0.2533, simple_loss=0.3366, pruned_loss=0.08499, over 7380.00 frames.], tot_loss[loss=0.2246, simple_loss=0.3092, pruned_loss=0.06999, over 1236774.51 frames.], batch size: 23, lr: 1.20e-03
2022-04-28 15:24:46,895 INFO [train.py:763] (4/8) Epoch 5, batch 450, loss[loss=0.23, simple_loss=0.3005, pruned_loss=0.0797, over 6794.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3084, pruned_loss=0.06925, over 1279220.68 frames.], batch size: 15, lr: 1.20e-03
2022-04-28 15:25:52,437 INFO [train.py:763] (4/8) Epoch 5, batch 500, loss[loss=0.2743, simple_loss=0.3452, pruned_loss=0.1017, over 5100.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3097, pruned_loss=0.06991, over 1308458.15 frames.], batch size: 52, lr: 1.20e-03
2022-04-28 15:26:57,642 INFO [train.py:763] (4/8) Epoch 5, batch 550, loss[loss=0.2005, simple_loss=0.2985, pruned_loss=0.05129, over 6321.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3087, pruned_loss=0.06905, over 1332810.29 frames.], batch size: 37, lr: 1.20e-03
2022-04-28 15:28:04,518 INFO [train.py:763] (4/8) Epoch 5, batch 600, loss[loss=0.2045, simple_loss=0.2945, pruned_loss=0.05725, over 7158.00 frames.], tot_loss[loss=0.224, simple_loss=0.3087, pruned_loss=0.06969, over 1352121.42 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:29:09,666 INFO [train.py:763] (4/8) Epoch 5, batch 650, loss[loss=0.2327, simple_loss=0.3223, pruned_loss=0.07151, over 7409.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3086, pruned_loss=0.06924, over 1366449.56 frames.], batch size: 21, lr: 1.20e-03
2022-04-28 15:30:15,009 INFO [train.py:763] (4/8) Epoch 5, batch 700, loss[loss=0.2212, simple_loss=0.3028, pruned_loss=0.06982, over 7248.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3092, pruned_loss=0.06924, over 1379354.74 frames.], batch size: 16, lr: 1.20e-03
2022-04-28 15:31:20,298 INFO [train.py:763] (4/8) Epoch 5, batch 750, loss[loss=0.2557, simple_loss=0.3426, pruned_loss=0.08441, over 7216.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3107, pruned_loss=0.06972, over 1388565.02 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:32:25,890 INFO [train.py:763] (4/8) Epoch 5, batch 800, loss[loss=0.2237, simple_loss=0.3245, pruned_loss=0.06146, over 7226.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3092, pruned_loss=0.06902, over 1399070.07 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:33:31,212 INFO [train.py:763] (4/8) Epoch 5, batch 850, loss[loss=0.2312, simple_loss=0.3185, pruned_loss=0.07196, over 7193.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3094, pruned_loss=0.06921, over 1404419.71 frames.], batch size: 23, lr: 1.19e-03
2022-04-28 15:34:36,541 INFO [train.py:763] (4/8) Epoch 5, batch 900, loss[loss=0.2411, simple_loss=0.3293, pruned_loss=0.07641, over 7411.00 frames.], tot_loss[loss=0.224, simple_loss=0.3096, pruned_loss=0.06924, over 1405715.01 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:35:42,332 INFO [train.py:763] (4/8) Epoch 5, batch 950, loss[loss=0.1972, simple_loss=0.2774, pruned_loss=0.05852, over 7134.00 frames.], tot_loss[loss=0.225, simple_loss=0.3101, pruned_loss=0.06996, over 1406853.07 frames.], batch size: 17, lr: 1.19e-03
2022-04-28 15:36:47,761 INFO [train.py:763] (4/8) Epoch 5, batch 1000, loss[loss=0.2019, simple_loss=0.3005, pruned_loss=0.05165, over 7414.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3107, pruned_loss=0.07024, over 1409292.35 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:37:53,890 INFO [train.py:763] (4/8) Epoch 5, batch 1050, loss[loss=0.2038, simple_loss=0.2944, pruned_loss=0.05662, over 7327.00 frames.], tot_loss[loss=0.2259, simple_loss=0.311, pruned_loss=0.07043, over 1414213.23 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:39:10,230 INFO [train.py:763] (4/8) Epoch 5, batch 1100, loss[loss=0.1972, simple_loss=0.2853, pruned_loss=0.05455, over 7322.00 frames.], tot_loss[loss=0.2272, simple_loss=0.3118, pruned_loss=0.07131, over 1409767.71 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:40:16,761 INFO [train.py:763] (4/8) Epoch 5, batch 1150, loss[loss=0.2404, simple_loss=0.3239, pruned_loss=0.07846, over 7151.00 frames.], tot_loss[loss=0.2277, simple_loss=0.3128, pruned_loss=0.07131, over 1413715.86 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:41:22,500 INFO [train.py:763] (4/8) Epoch 5, batch 1200, loss[loss=0.2019, simple_loss=0.3003, pruned_loss=0.05171, over 7156.00 frames.], tot_loss[loss=0.2265, simple_loss=0.3114, pruned_loss=0.07079, over 1414448.11 frames.], batch size: 26, lr: 1.18e-03
2022-04-28 15:42:28,992 INFO [train.py:763] (4/8) Epoch 5, batch 1250, loss[loss=0.2183, simple_loss=0.3019, pruned_loss=0.06729, over 7149.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3105, pruned_loss=0.0702, over 1413524.51 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:43:35,964 INFO [train.py:763] (4/8) Epoch 5, batch 1300, loss[loss=0.2359, simple_loss=0.3015, pruned_loss=0.08516, over 7346.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3101, pruned_loss=0.07076, over 1410940.97 frames.], batch size: 19, lr: 1.18e-03
2022-04-28 15:44:42,293 INFO [train.py:763] (4/8) Epoch 5, batch 1350, loss[loss=0.234, simple_loss=0.3278, pruned_loss=0.07008, over 6990.00 frames.], tot_loss[loss=0.224, simple_loss=0.308, pruned_loss=0.06999, over 1414567.01 frames.], batch size: 28, lr: 1.18e-03
2022-04-28 15:45:48,503 INFO [train.py:763] (4/8) Epoch 5, batch 1400, loss[loss=0.2009, simple_loss=0.2935, pruned_loss=0.05415, over 7336.00 frames.], tot_loss[loss=0.224, simple_loss=0.3085, pruned_loss=0.06974, over 1418406.25 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:46:53,763 INFO [train.py:763] (4/8) Epoch 5, batch 1450, loss[loss=0.2431, simple_loss=0.3208, pruned_loss=0.08274, over 7430.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3074, pruned_loss=0.0689, over 1420257.65 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:47:59,047 INFO [train.py:763] (4/8) Epoch 5, batch 1500, loss[loss=0.2476, simple_loss=0.3309, pruned_loss=0.08211, over 7142.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3076, pruned_loss=0.0693, over 1420774.70 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:49:04,606 INFO [train.py:763] (4/8) Epoch 5, batch 1550, loss[loss=0.1851, simple_loss=0.2639, pruned_loss=0.05314, over 7253.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3079, pruned_loss=0.06931, over 1423608.99 frames.], batch size: 17, lr: 1.18e-03
2022-04-28 15:50:09,898 INFO [train.py:763] (4/8) Epoch 5, batch 1600, loss[loss=0.2259, simple_loss=0.3124, pruned_loss=0.0697, over 7423.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3081, pruned_loss=0.06948, over 1417032.90 frames.], batch size: 20, lr: 1.17e-03
2022-04-28 15:51:15,386 INFO [train.py:763] (4/8) Epoch 5, batch 1650, loss[loss=0.2423, simple_loss=0.3256, pruned_loss=0.0795, over 7328.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3077, pruned_loss=0.06926, over 1416863.31 frames.], batch size: 25, lr: 1.17e-03
2022-04-28 15:52:21,474 INFO [train.py:763] (4/8) Epoch 5, batch 1700, loss[loss=0.2434, simple_loss=0.3256, pruned_loss=0.08064, over 7215.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3091, pruned_loss=0.07015, over 1414662.51 frames.], batch size: 22, lr: 1.17e-03
2022-04-28 15:53:26,972 INFO [train.py:763] (4/8) Epoch 5, batch 1750, loss[loss=0.1803, simple_loss=0.2639, pruned_loss=0.04835, over 7278.00 frames.], tot_loss[loss=0.2248, simple_loss=0.3095, pruned_loss=0.07006, over 1411847.24 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:54:32,245 INFO [train.py:763] (4/8) Epoch 5, batch 1800, loss[loss=0.2751, simple_loss=0.3393, pruned_loss=0.1054, over 5164.00 frames.], tot_loss[loss=0.2253, simple_loss=0.31, pruned_loss=0.07034, over 1413665.72 frames.], batch size: 52, lr: 1.17e-03
2022-04-28 15:55:37,878 INFO [train.py:763] (4/8) Epoch 5, batch 1850, loss[loss=0.2569, simple_loss=0.3269, pruned_loss=0.09351, over 7171.00 frames.], tot_loss[loss=0.2256, simple_loss=0.31, pruned_loss=0.07056, over 1416448.38 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:56:43,237 INFO [train.py:763] (4/8) Epoch 5, batch 1900, loss[loss=0.1892, simple_loss=0.2715, pruned_loss=0.05343, over 7135.00 frames.], tot_loss[loss=0.2264, simple_loss=0.3105, pruned_loss=0.07114, over 1415497.53 frames.], batch size: 17, lr: 1.17e-03
2022-04-28 15:57:48,603 INFO [train.py:763] (4/8) Epoch 5, batch 1950, loss[loss=0.2602, simple_loss=0.3547, pruned_loss=0.08286, over 7108.00 frames.], tot_loss[loss=0.2274, simple_loss=0.3115, pruned_loss=0.07162, over 1420669.10 frames.], batch size: 21, lr: 1.17e-03
2022-04-28 15:58:54,741 INFO [train.py:763] (4/8) Epoch 5, batch 2000, loss[loss=0.211, simple_loss=0.2949, pruned_loss=0.06352, over 7274.00 frames.], tot_loss[loss=0.2268, simple_loss=0.3114, pruned_loss=0.0711, over 1424128.25 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:59:59,952 INFO [train.py:763] (4/8) Epoch 5, batch 2050, loss[loss=0.2383, simple_loss=0.3221, pruned_loss=0.07727, over 7033.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3113, pruned_loss=0.07028, over 1424689.82 frames.], batch size: 28, lr: 1.16e-03
2022-04-28 16:01:06,583 INFO [train.py:763] (4/8) Epoch 5, batch 2100, loss[loss=0.265, simple_loss=0.3473, pruned_loss=0.09129, over 6498.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3113, pruned_loss=0.07024, over 1426003.91 frames.], batch size: 38, lr: 1.16e-03
2022-04-28 16:02:12,116 INFO [train.py:763] (4/8) Epoch 5, batch 2150, loss[loss=0.246, simple_loss=0.326, pruned_loss=0.08302, over 7149.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3093, pruned_loss=0.069, over 1430771.34 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:03:17,456 INFO [train.py:763] (4/8) Epoch 5, batch 2200, loss[loss=0.2369, simple_loss=0.3318, pruned_loss=0.071, over 7144.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3091, pruned_loss=0.06903, over 1427223.91 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:04:22,912 INFO [train.py:763] (4/8) Epoch 5, batch 2250, loss[loss=0.2037, simple_loss=0.2847, pruned_loss=0.06137, over 7360.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3082, pruned_loss=0.06886, over 1425512.34 frames.], batch size: 19, lr: 1.16e-03
2022-04-28 16:05:29,057 INFO [train.py:763] (4/8) Epoch 5, batch 2300, loss[loss=0.2308, simple_loss=0.3129, pruned_loss=0.07436, over 7308.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3079, pruned_loss=0.06883, over 1422197.33 frames.], batch size: 24, lr: 1.16e-03
2022-04-28 16:06:35,242 INFO [train.py:763] (4/8) Epoch 5, batch 2350, loss[loss=0.2064, simple_loss=0.3046, pruned_loss=0.05416, over 7227.00 frames.], tot_loss[loss=0.223, simple_loss=0.3078, pruned_loss=0.06905, over 1421733.61 frames.], batch size: 21, lr: 1.16e-03
2022-04-28 16:07:41,476 INFO [train.py:763] (4/8) Epoch 5, batch 2400, loss[loss=0.2375, simple_loss=0.3226, pruned_loss=0.07616, over 7324.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3061, pruned_loss=0.06835, over 1421730.08 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:08:47,664 INFO [train.py:763] (4/8) Epoch 5, batch 2450, loss[loss=0.2077, simple_loss=0.2874, pruned_loss=0.06405, over 6774.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3046, pruned_loss=0.06727, over 1420993.44 frames.], batch size: 15, lr: 1.16e-03
2022-04-28 16:09:52,912 INFO [train.py:763] (4/8) Epoch 5, batch 2500, loss[loss=0.2251, simple_loss=0.3192, pruned_loss=0.06551, over 7326.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3051, pruned_loss=0.06713, over 1419934.83 frames.], batch size: 22, lr: 1.15e-03
2022-04-28 16:10:59,308 INFO [train.py:763] (4/8) Epoch 5, batch 2550, loss[loss=0.2073, simple_loss=0.2778, pruned_loss=0.06845, over 6818.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3054, pruned_loss=0.06762, over 1422242.57 frames.], batch size: 15, lr: 1.15e-03
2022-04-28 16:12:05,354 INFO [train.py:763] (4/8) Epoch 5, batch 2600, loss[loss=0.2142, simple_loss=0.3192, pruned_loss=0.05464, over 7298.00 frames.], tot_loss[loss=0.2218, simple_loss=0.307, pruned_loss=0.06826, over 1425389.28 frames.], batch size: 21, lr: 1.15e-03
2022-04-28 16:13:10,876 INFO [train.py:763] (4/8) Epoch 5, batch 2650, loss[loss=0.2493, simple_loss=0.339, pruned_loss=0.07977, over 7273.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3081, pruned_loss=0.06854, over 1423917.15 frames.], batch size: 25, lr: 1.15e-03
2022-04-28 16:14:16,437 INFO [train.py:763] (4/8) Epoch 5, batch 2700, loss[loss=0.2582, simple_loss=0.322, pruned_loss=0.09726, over 6774.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3079, pruned_loss=0.06825, over 1425865.29 frames.], batch size: 15, lr: 1.15e-03
2022-04-28 16:15:15,066 INFO [train.py:763] (4/8) Epoch 5, batch 2750, loss[loss=0.2254, simple_loss=0.314, pruned_loss=0.06843, over 7225.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3089, pruned_loss=0.06843, over 1423859.55 frames.], batch size: 20, lr: 1.15e-03
2022-04-28 16:16:11,914 INFO [train.py:763] (4/8) Epoch 5, batch 2800, loss[loss=0.2202, simple_loss=0.2983, pruned_loss=0.07106, over 7275.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3088, pruned_loss=0.06849, over 1421986.38 frames.], batch size: 18, lr: 1.15e-03
2022-04-28 16:17:08,597 INFO [train.py:763] (4/8) Epoch 5, batch 2850, loss[loss=0.2132, simple_loss=0.2871, pruned_loss=0.06966, over 7282.00 frames.], tot_loss[loss=0.2229, simple_loss=0.3086, pruned_loss=0.06864, over 1419200.25 frames.], batch size: 17, lr: 1.15e-03
2022-04-28 16:18:06,396 INFO [train.py:763] (4/8) Epoch 5, batch 2900, loss[loss=0.2093, simple_loss=0.2982, pruned_loss=0.06021, over 6666.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3083, pruned_loss=0.06811, over 1421013.49 frames.], batch size: 31, lr: 1.15e-03
2022-04-28 16:19:04,267 INFO [train.py:763] (4/8) Epoch 5, batch 2950, loss[loss=0.2247, simple_loss=0.3136, pruned_loss=0.06792, over 7154.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3076, pruned_loss=0.06815, over 1420902.20 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,109 INFO [train.py:763] (4/8) Epoch 5, batch 3000, loss[loss=0.1935, simple_loss=0.2885, pruned_loss=0.04926, over 7224.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3067, pruned_loss=0.0671, over 1420311.56 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,111 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 16:20:13,356 INFO [train.py:792] (4/8) Epoch 5, validation: loss=0.1791, simple_loss=0.2847, pruned_loss=0.03677, over 698248.00 frames.
2022-04-28 16:21:19,339 INFO [train.py:763] (4/8) Epoch 5, batch 3050, loss[loss=0.2751, simple_loss=0.349, pruned_loss=0.1006, over 7193.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3061, pruned_loss=0.06725, over 1426050.29 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:22:24,937 INFO [train.py:763] (4/8) Epoch 5, batch 3100, loss[loss=0.2197, simple_loss=0.31, pruned_loss=0.0647, over 7327.00 frames.], tot_loss[loss=0.2211, simple_loss=0.3066, pruned_loss=0.06783, over 1423629.20 frames.], batch size: 22, lr: 1.14e-03
2022-04-28 16:23:30,169 INFO [train.py:763] (4/8) Epoch 5, batch 3150, loss[loss=0.2386, simple_loss=0.3261, pruned_loss=0.07559, over 7219.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3078, pruned_loss=0.06833, over 1423698.24 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:24:36,687 INFO [train.py:763] (4/8) Epoch 5, batch 3200, loss[loss=0.2231, simple_loss=0.3184, pruned_loss=0.06392, over 7213.00 frames.], tot_loss[loss=0.2224, simple_loss=0.3082, pruned_loss=0.06832, over 1424578.69 frames.], batch size: 21, lr: 1.14e-03
2022-04-28 16:25:42,632 INFO [train.py:763] (4/8) Epoch 5, batch 3250, loss[loss=0.194, simple_loss=0.2838, pruned_loss=0.05215, over 7359.00 frames.], tot_loss[loss=0.2231, simple_loss=0.309, pruned_loss=0.06859, over 1424411.10 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:26:48,951 INFO [train.py:763] (4/8) Epoch 5, batch 3300, loss[loss=0.2859, simple_loss=0.3522, pruned_loss=0.1099, over 7203.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3097, pruned_loss=0.06905, over 1420752.57 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:27:54,258 INFO [train.py:763] (4/8) Epoch 5, batch 3350, loss[loss=0.2584, simple_loss=0.3156, pruned_loss=0.1006, over 7259.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3081, pruned_loss=0.06869, over 1424842.68 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:28:59,512 INFO [train.py:763] (4/8) Epoch 5, batch 3400, loss[loss=0.2065, simple_loss=0.3008, pruned_loss=0.05607, over 7273.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3076, pruned_loss=0.06872, over 1425039.69 frames.], batch size: 24, lr: 1.14e-03
2022-04-28 16:30:05,193 INFO [train.py:763] (4/8) Epoch 5, batch 3450, loss[loss=0.2493, simple_loss=0.3207, pruned_loss=0.0889, over 7421.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3096, pruned_loss=0.06966, over 1426984.18 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:31:11,003 INFO [train.py:763] (4/8) Epoch 5, batch 3500, loss[loss=0.2312, simple_loss=0.3165, pruned_loss=0.07294, over 7195.00 frames.], tot_loss[loss=0.2228, simple_loss=0.308, pruned_loss=0.06876, over 1424493.06 frames.], batch size: 22, lr: 1.13e-03
2022-04-28 16:32:16,130 INFO [train.py:763] (4/8) Epoch 5, batch 3550, loss[loss=0.2222, simple_loss=0.3238, pruned_loss=0.06028, over 7323.00 frames.], tot_loss[loss=0.2217, simple_loss=0.3072, pruned_loss=0.06807, over 1427289.89 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:33:21,406 INFO [train.py:763] (4/8) Epoch 5, batch 3600, loss[loss=0.1924, simple_loss=0.2684, pruned_loss=0.05823, over 7172.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3067, pruned_loss=0.06798, over 1428829.62 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:34:27,110 INFO [train.py:763] (4/8) Epoch 5, batch 3650, loss[loss=0.2387, simple_loss=0.3251, pruned_loss=0.0762, over 7414.00 frames.], tot_loss[loss=0.2212, simple_loss=0.3067, pruned_loss=0.06782, over 1428144.24 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:35:34,071 INFO [train.py:763] (4/8) Epoch 5, batch 3700, loss[loss=0.2245, simple_loss=0.3114, pruned_loss=0.06876, over 7231.00 frames.], tot_loss[loss=0.2215, simple_loss=0.307, pruned_loss=0.068, over 1426043.62 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:36:39,370 INFO [train.py:763] (4/8) Epoch 5, batch 3750, loss[loss=0.2489, simple_loss=0.3348, pruned_loss=0.08154, over 7366.00 frames.], tot_loss[loss=0.2214, simple_loss=0.3068, pruned_loss=0.06799, over 1424388.13 frames.], batch size: 23, lr: 1.13e-03
2022-04-28 16:37:46,337 INFO [train.py:763] (4/8) Epoch 5, batch 3800, loss[loss=0.2675, simple_loss=0.3503, pruned_loss=0.09233, over 7244.00 frames.], tot_loss[loss=0.2207, simple_loss=0.306, pruned_loss=0.06772, over 1419937.16 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:38:51,769 INFO [train.py:763] (4/8) Epoch 5, batch 3850, loss[loss=0.1947, simple_loss=0.2842, pruned_loss=0.05265, over 7437.00 frames.], tot_loss[loss=0.2215, simple_loss=0.3069, pruned_loss=0.06804, over 1420826.26 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:39:57,099 INFO [train.py:763] (4/8) Epoch 5, batch 3900, loss[loss=0.2166, simple_loss=0.2864, pruned_loss=0.07344, over 7405.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3065, pruned_loss=0.06811, over 1424997.32 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:41:04,042 INFO [train.py:763] (4/8) Epoch 5, batch 3950, loss[loss=0.2582, simple_loss=0.342, pruned_loss=0.08722, over 7287.00 frames.], tot_loss[loss=0.2203, simple_loss=0.3053, pruned_loss=0.06769, over 1423640.25 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:42:10,955 INFO [train.py:763] (4/8) Epoch 5, batch 4000, loss[loss=0.2465, simple_loss=0.3369, pruned_loss=0.078, over 7211.00 frames.], tot_loss[loss=0.2199, simple_loss=0.3058, pruned_loss=0.06699, over 1426161.92 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:43:18,247 INFO [train.py:763] (4/8) Epoch 5, batch 4050, loss[loss=0.2573, simple_loss=0.3374, pruned_loss=0.08855, over 7289.00 frames.], tot_loss[loss=0.2209, simple_loss=0.3068, pruned_loss=0.06747, over 1426874.67 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:44:25,533 INFO [train.py:763] (4/8) Epoch 5, batch 4100, loss[loss=0.2173, simple_loss=0.2886, pruned_loss=0.07301, over 7415.00 frames.], tot_loss[loss=0.2205, simple_loss=0.3058, pruned_loss=0.06759, over 1427440.23 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:45:32,376 INFO [train.py:763] (4/8) Epoch 5, batch 4150, loss[loss=0.2157, simple_loss=0.3166, pruned_loss=0.05735, over 6797.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3049, pruned_loss=0.06714, over 1427605.93 frames.], batch size: 31, lr: 1.12e-03
2022-04-28 16:46:39,132 INFO [train.py:763] (4/8) Epoch 5, batch 4200, loss[loss=0.2556, simple_loss=0.3369, pruned_loss=0.08714, over 7107.00 frames.], tot_loss[loss=0.2192, simple_loss=0.3046, pruned_loss=0.06694, over 1428929.27 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:47:45,470 INFO [train.py:763] (4/8) Epoch 5, batch 4250, loss[loss=0.2306, simple_loss=0.3189, pruned_loss=0.07115, over 7376.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3049, pruned_loss=0.06686, over 1429487.60 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:48:52,194 INFO [train.py:763] (4/8) Epoch 5, batch 4300, loss[loss=0.2253, simple_loss=0.3127, pruned_loss=0.069, over 7067.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3052, pruned_loss=0.06701, over 1424142.11 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:49:59,887 INFO [train.py:763] (4/8) Epoch 5, batch 4350, loss[loss=0.2207, simple_loss=0.3174, pruned_loss=0.06193, over 7229.00 frames.], tot_loss[loss=0.2195, simple_loss=0.3052, pruned_loss=0.06695, over 1424201.69 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:51:07,554 INFO [train.py:763] (4/8) Epoch 5, batch 4400, loss[loss=0.2062, simple_loss=0.2983, pruned_loss=0.05705, over 7443.00 frames.], tot_loss[loss=0.2197, simple_loss=0.3045, pruned_loss=0.06744, over 1422567.45 frames.], batch size: 20, lr: 1.12e-03
2022-04-28 16:52:13,248 INFO [train.py:763] (4/8) Epoch 5, batch 4450, loss[loss=0.1823, simple_loss=0.27, pruned_loss=0.04733, over 7274.00 frames.], tot_loss[loss=0.2202, simple_loss=0.3046, pruned_loss=0.06785, over 1408900.50 frames.], batch size: 17, lr: 1.11e-03
2022-04-28 16:53:19,248 INFO [train.py:763] (4/8) Epoch 5, batch 4500, loss[loss=0.2024, simple_loss=0.2916, pruned_loss=0.05665, over 7232.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3024, pruned_loss=0.0675, over 1408245.29 frames.], batch size: 20, lr: 1.11e-03
2022-04-28 16:54:23,898 INFO [train.py:763] (4/8) Epoch 5, batch 4550, loss[loss=0.2673, simple_loss=0.3576, pruned_loss=0.08848, over 5127.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3054, pruned_loss=0.07012, over 1359299.34 frames.], batch size: 52, lr: 1.11e-03
2022-04-28 16:55:51,897 INFO [train.py:763] (4/8) Epoch 6, batch 0, loss[loss=0.2137, simple_loss=0.2942, pruned_loss=0.06662, over 7412.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2942, pruned_loss=0.06662, over 7412.00 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:56:58,098 INFO [train.py:763] (4/8) Epoch 6, batch 50, loss[loss=0.1957, simple_loss=0.2756, pruned_loss=0.05793, over 7409.00 frames.], tot_loss[loss=0.2121, simple_loss=0.2979, pruned_loss=0.06315, over 323101.49 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:58:04,028 INFO [train.py:763] (4/8) Epoch 6, batch 100, loss[loss=0.2015, simple_loss=0.289, pruned_loss=0.05705, over 7144.00 frames.], tot_loss[loss=0.2134, simple_loss=0.2997, pruned_loss=0.06354, over 567543.02 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 16:59:09,767 INFO [train.py:763] (4/8) Epoch 6, batch 150, loss[loss=0.1776, simple_loss=0.2782, pruned_loss=0.03855, over 7162.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3016, pruned_loss=0.06428, over 757775.76 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:00:15,501 INFO [train.py:763] (4/8) Epoch 6, batch 200, loss[loss=0.2483, simple_loss=0.3351, pruned_loss=0.08078, over 7379.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3028, pruned_loss=0.065, over 907154.22 frames.], batch size: 23, lr: 1.06e-03
2022-04-28 17:01:29,826 INFO [train.py:763] (4/8) Epoch 6, batch 250, loss[loss=0.2138, simple_loss=0.309, pruned_loss=0.05935, over 7139.00 frames.], tot_loss[loss=0.2165, simple_loss=0.303, pruned_loss=0.06502, over 1021371.12 frames.], batch size: 20, lr: 1.06e-03
2022-04-28 17:02:45,512 INFO [train.py:763] (4/8) Epoch 6, batch 300, loss[loss=0.1688, simple_loss=0.2533, pruned_loss=0.04218, over 7273.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3044, pruned_loss=0.06591, over 1107525.18 frames.], batch size: 16, lr: 1.06e-03
2022-04-28 17:03:59,809 INFO [train.py:763] (4/8) Epoch 6, batch 350, loss[loss=0.209, simple_loss=0.2934, pruned_loss=0.06226, over 7119.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3039, pruned_loss=0.06522, over 1178837.73 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:05:05,096 INFO [train.py:763] (4/8) Epoch 6, batch 400, loss[loss=0.1823, simple_loss=0.2918, pruned_loss=0.03639, over 7160.00 frames.], tot_loss[loss=0.218, simple_loss=0.3049, pruned_loss=0.06557, over 1231005.05 frames.], batch size: 18, lr: 1.06e-03
2022-04-28 17:06:20,537 INFO [train.py:763] (4/8) Epoch 6, batch 450, loss[loss=0.2087, simple_loss=0.2991, pruned_loss=0.05921, over 7360.00 frames.], tot_loss[loss=0.217, simple_loss=0.3039, pruned_loss=0.06501, over 1276390.72 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:07:44,114 INFO [train.py:763] (4/8) Epoch 6, batch 500, loss[loss=0.2147, simple_loss=0.3068, pruned_loss=0.06133, over 6333.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3039, pruned_loss=0.06477, over 1305001.76 frames.], batch size: 37, lr: 1.06e-03
2022-04-28 17:08:59,112 INFO [train.py:763] (4/8) Epoch 6, batch 550, loss[loss=0.2045, simple_loss=0.2919, pruned_loss=0.05853, over 7116.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3022, pruned_loss=0.06442, over 1329644.85 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:10:13,641 INFO [train.py:763] (4/8) Epoch 6, batch 600, loss[loss=0.2152, simple_loss=0.3083, pruned_loss=0.06102, over 7002.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3032, pruned_loss=0.06483, over 1348457.85 frames.], batch size: 28, lr: 1.06e-03
2022-04-28 17:11:19,489 INFO [train.py:763] (4/8) Epoch 6, batch 650, loss[loss=0.2615, simple_loss=0.3389, pruned_loss=0.09205, over 5007.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3017, pruned_loss=0.06446, over 1364712.67 frames.], batch size: 53, lr: 1.05e-03
2022-04-28 17:12:25,177 INFO [train.py:763] (4/8) Epoch 6, batch 700, loss[loss=0.1985, simple_loss=0.2751, pruned_loss=0.06092, over 7168.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3011, pruned_loss=0.0637, over 1379187.80 frames.], batch size: 18, lr: 1.05e-03
2022-04-28 17:13:31,497 INFO [train.py:763] (4/8) Epoch 6, batch 750, loss[loss=0.1923, simple_loss=0.2832, pruned_loss=0.0507, over 6733.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3013, pruned_loss=0.06377, over 1392202.57 frames.], batch size: 31, lr: 1.05e-03
2022-04-28 17:14:37,092 INFO [train.py:763] (4/8) Epoch 6, batch 800, loss[loss=0.2386, simple_loss=0.3182, pruned_loss=0.07955, over 7328.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3012, pruned_loss=0.06365, over 1391587.33 frames.], batch size: 20, lr: 1.05e-03
2022-04-28 17:15:43,492 INFO [train.py:763] (4/8) Epoch 6, batch 850, loss[loss=0.2142, simple_loss=0.3105, pruned_loss=0.05891, over 7284.00 frames.], tot_loss[loss=0.214, simple_loss=0.3013, pruned_loss=0.06331, over 1397652.68 frames.], batch size: 24, lr: 1.05e-03
2022-04-28 17:16:48,951 INFO [train.py:763] (4/8) Epoch 6, batch 900, loss[loss=0.2261, simple_loss=0.3157, pruned_loss=0.06821, over 7380.00 frames.], tot_loss[loss=0.215, simple_loss=0.3021, pruned_loss=0.06391, over 1403539.80 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:17:54,043 INFO [train.py:763] (4/8) Epoch 6, batch 950, loss[loss=0.2501, simple_loss=0.3357, pruned_loss=0.08225, over 7369.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3023, pruned_loss=0.0642, over 1408115.70 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:18:59,562 INFO [train.py:763] (4/8) Epoch 6, batch 1000, loss[loss=0.2204, simple_loss=0.3225, pruned_loss=0.05913, over 7391.00 frames.], tot_loss[loss=0.215, simple_loss=0.3017, pruned_loss=0.06415, over 1408154.67 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:20:06,058 INFO [train.py:763] (4/8) Epoch 6, batch 1050, loss[loss=0.1837, simple_loss=0.2788, pruned_loss=0.04429, over 7165.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3022, pruned_loss=0.06432, over 1414783.27 frames.], batch size: 19, lr: 1.05e-03
2022-04-28 17:21:12,153 INFO [train.py:763] (4/8) Epoch 6, batch 1100, loss[loss=0.2331, simple_loss=0.3306, pruned_loss=0.06774, over 7234.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3019, pruned_loss=0.06411, over 1418353.30 frames.], batch size: 25, lr: 1.05e-03
2022-04-28 17:22:18,726 INFO [train.py:763] (4/8) Epoch 6, batch 1150, loss[loss=0.2145, simple_loss=0.2874, pruned_loss=0.07083, over 7135.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3025, pruned_loss=0.06418, over 1416768.76 frames.], batch size: 17, lr: 1.05e-03
2022-04-28 17:23:26,111 INFO [train.py:763] (4/8) Epoch 6, batch 1200, loss[loss=0.2461, simple_loss=0.3144, pruned_loss=0.08891, over 7268.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3023, pruned_loss=0.06443, over 1412338.06 frames.], batch size: 16, lr: 1.04e-03
2022-04-28 17:24:33,316 INFO [train.py:763] (4/8) Epoch 6, batch 1250, loss[loss=0.2171, simple_loss=0.3048, pruned_loss=0.06469, over 7241.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3018, pruned_loss=0.06456, over 1413767.41 frames.], batch size: 20, lr: 1.04e-03
2022-04-28 17:25:39,226 INFO [train.py:763] (4/8) Epoch 6, batch 1300, loss[loss=0.1927, simple_loss=0.2843, pruned_loss=0.05056, over 7277.00 frames.], tot_loss[loss=0.2159, simple_loss=0.3024, pruned_loss=0.06467, over 1415418.06 frames.], batch size: 17, lr: 1.04e-03
2022-04-28 17:26:44,442 INFO [train.py:763] (4/8) Epoch 6, batch 1350, loss[loss=0.2305, simple_loss=0.3147, pruned_loss=0.07318, over 7402.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3033, pruned_loss=0.06481, over 1420500.95 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:27:49,617 INFO [train.py:763] (4/8) Epoch 6, batch 1400, loss[loss=0.2182, simple_loss=0.3044, pruned_loss=0.06599, over 7150.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3048, pruned_loss=0.06571, over 1418384.78 frames.], batch size: 19, lr: 1.04e-03
2022-04-28 17:28:55,363 INFO [train.py:763] (4/8) Epoch 6, batch 1450, loss[loss=0.2437, simple_loss=0.3366, pruned_loss=0.07536, over 6805.00 frames.], tot_loss[loss=0.2177, simple_loss=0.305, pruned_loss=0.06518, over 1418679.79 frames.], batch size: 31, lr: 1.04e-03
2022-04-28 17:30:00,747 INFO [train.py:763] (4/8) Epoch 6, batch 1500, loss[loss=0.2093, simple_loss=0.2935, pruned_loss=0.06252, over 7408.00 frames.], tot_loss[loss=0.217, simple_loss=0.3043, pruned_loss=0.06487, over 1422710.42 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:31:05,968 INFO [train.py:763] (4/8) Epoch 6, batch 1550, loss[loss=0.2253, simple_loss=0.3105, pruned_loss=0.07007, over 7113.00 frames.], tot_loss[loss=0.216, simple_loss=0.3033, pruned_loss=0.0643, over 1417487.62 frames.], batch size: 26, lr: 1.04e-03
2022-04-28 17:32:11,537 INFO [train.py:763] (4/8) Epoch 6, batch 1600, loss[loss=0.2095, simple_loss=0.3077, pruned_loss=0.05566, over 7106.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3026, pruned_loss=0.06356, over 1424425.56 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:33:16,936 INFO [train.py:763] (4/8) Epoch 6, batch 1650, loss[loss=0.1675, simple_loss=0.2558, pruned_loss=0.03958, over 7069.00 frames.], tot_loss[loss=0.2151, simple_loss=0.3023, pruned_loss=0.06399, over 1418076.04 frames.], batch size: 18, lr: 1.04e-03
2022-04-28 17:34:24,083 INFO [train.py:763] (4/8) Epoch 6, batch 1700, loss[loss=0.2303, simple_loss=0.3246, pruned_loss=0.06804, over 7201.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3017, pruned_loss=0.06348, over 1417583.14 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:35:30,121 INFO [train.py:763] (4/8) Epoch 6, batch 1750, loss[loss=0.2519, simple_loss=0.34, pruned_loss=0.08195, over 7329.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3023, pruned_loss=0.06425, over 1412403.64 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:36:35,223 INFO [train.py:763] (4/8) Epoch 6, batch 1800, loss[loss=0.2619, simple_loss=0.3468, pruned_loss=0.08847, over 7341.00 frames.], tot_loss[loss=0.2167, simple_loss=0.304, pruned_loss=0.06469, over 1415309.93 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:37:41,010 INFO [train.py:763] (4/8) Epoch 6, batch 1850, loss[loss=0.1736, simple_loss=0.2619, pruned_loss=0.04268, over 6995.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3038, pruned_loss=0.06438, over 1417540.86 frames.], batch size: 16, lr: 1.03e-03
2022-04-28 17:38:46,200 INFO [train.py:763] (4/8) Epoch 6, batch 1900, loss[loss=0.1863, simple_loss=0.2821, pruned_loss=0.04527, over 7055.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3047, pruned_loss=0.06496, over 1414411.76 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:39:52,667 INFO [train.py:763] (4/8) Epoch 6, batch 1950, loss[loss=0.2199, simple_loss=0.2986, pruned_loss=0.07058, over 7273.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3042, pruned_loss=0.06483, over 1418032.02 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:40:59,180 INFO [train.py:763] (4/8) Epoch 6, batch 2000, loss[loss=0.2038, simple_loss=0.3032, pruned_loss=0.05221, over 7294.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3043, pruned_loss=0.06503, over 1418428.23 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:42:06,055 INFO [train.py:763] (4/8) Epoch 6, batch 2050, loss[loss=0.2309, simple_loss=0.3168, pruned_loss=0.07249, over 7284.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3046, pruned_loss=0.06534, over 1414939.55 frames.], batch size: 24, lr: 1.03e-03
2022-04-28 17:43:12,552 INFO [train.py:763] (4/8) Epoch 6, batch 2100, loss[loss=0.1615, simple_loss=0.2521, pruned_loss=0.03549, over 7441.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3033, pruned_loss=0.06449, over 1418421.71 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:44:19,358 INFO [train.py:763] (4/8) Epoch 6, batch 2150, loss[loss=0.2312, simple_loss=0.3152, pruned_loss=0.07359, over 7408.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3039, pruned_loss=0.0644, over 1423866.85 frames.], batch size: 21, lr: 1.03e-03
2022-04-28 17:45:25,693 INFO [train.py:763] (4/8) Epoch 6, batch 2200, loss[loss=0.2057, simple_loss=0.2798, pruned_loss=0.06579, over 7146.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3039, pruned_loss=0.06456, over 1422286.76 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:46:32,097 INFO [train.py:763] (4/8) Epoch 6, batch 2250, loss[loss=0.1926, simple_loss=0.2669, pruned_loss=0.05917, over 7270.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3051, pruned_loss=0.06592, over 1417028.64 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:47:38,685 INFO [train.py:763] (4/8) Epoch 6, batch 2300, loss[loss=0.2286, simple_loss=0.3139, pruned_loss=0.07166, over 7203.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3043, pruned_loss=0.06534, over 1419826.51 frames.], batch size: 23, lr: 1.03e-03
2022-04-28 17:48:44,943 INFO [train.py:763] (4/8) Epoch 6, batch 2350, loss[loss=0.235, simple_loss=0.3184, pruned_loss=0.07582, over 7412.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3044, pruned_loss=0.06572, over 1417629.63 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:49:50,848 INFO [train.py:763] (4/8) Epoch 6, batch 2400, loss[loss=0.1839, simple_loss=0.2739, pruned_loss=0.04696, over 7270.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3032, pruned_loss=0.06513, over 1421123.84 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:50:56,967 INFO [train.py:763] (4/8) Epoch 6, batch 2450, loss[loss=0.2213, simple_loss=0.3143, pruned_loss=0.06415, over 7412.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3033, pruned_loss=0.06506, over 1417068.38 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:52:02,800 INFO [train.py:763] (4/8) Epoch 6, batch 2500, loss[loss=0.2895, simple_loss=0.3429, pruned_loss=0.1181, over 7318.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3042, pruned_loss=0.06573, over 1416858.41 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:53:08,640 INFO [train.py:763] (4/8) Epoch 6, batch 2550, loss[loss=0.2323, simple_loss=0.3162, pruned_loss=0.07422, over 7424.00 frames.], tot_loss[loss=0.2163, simple_loss=0.303, pruned_loss=0.06485, over 1423275.10 frames.], batch size: 20, lr: 1.02e-03
2022-04-28 17:54:14,769 INFO [train.py:763] (4/8) Epoch 6, batch 2600, loss[loss=0.1759, simple_loss=0.2641, pruned_loss=0.04384, over 7171.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3034, pruned_loss=0.06541, over 1417171.60 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:55:21,044 INFO [train.py:763] (4/8) Epoch 6, batch 2650, loss[loss=0.228, simple_loss=0.3057, pruned_loss=0.07518, over 7160.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3035, pruned_loss=0.06535, over 1416866.11 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:56:26,530 INFO [train.py:763] (4/8) Epoch 6, batch 2700, loss[loss=0.1837, simple_loss=0.2712, pruned_loss=0.04806, over 6846.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3024, pruned_loss=0.06412, over 1418841.80 frames.], batch size: 15, lr: 1.02e-03
2022-04-28 17:57:32,629 INFO [train.py:763] (4/8) Epoch 6, batch 2750, loss[loss=0.169, simple_loss=0.2553, pruned_loss=0.04139, over 7402.00 frames.], tot_loss[loss=0.215, simple_loss=0.3025, pruned_loss=0.06377, over 1419009.47 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:58:39,119 INFO [train.py:763] (4/8) Epoch 6, batch 2800, loss[loss=0.1563, simple_loss=0.2471, pruned_loss=0.03276, over 6983.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3016, pruned_loss=0.06363, over 1417504.90 frames.], batch size: 16, lr: 1.02e-03
2022-04-28 17:59:46,047 INFO [train.py:763] (4/8) Epoch 6, batch 2850, loss[loss=0.1856, simple_loss=0.2737, pruned_loss=0.04872, over 7323.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3002, pruned_loss=0.06309, over 1422708.15 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 18:00:52,207 INFO [train.py:763] (4/8) Epoch 6, batch 2900, loss[loss=0.2477, simple_loss=0.3202, pruned_loss=0.08762, over 4987.00 frames.], tot_loss[loss=0.2128, simple_loss=0.2999, pruned_loss=0.06285, over 1425244.48 frames.], batch size: 53, lr: 1.02e-03
2022-04-28 18:01:57,561 INFO [train.py:763] (4/8) Epoch 6, batch 2950, loss[loss=0.24, simple_loss=0.3299, pruned_loss=0.07501, over 7328.00 frames.], tot_loss[loss=0.2124, simple_loss=0.3002, pruned_loss=0.0623, over 1425302.40 frames.], batch size: 25, lr: 1.01e-03
2022-04-28 18:03:03,518 INFO [train.py:763] (4/8) Epoch 6, batch 3000, loss[loss=0.2465, simple_loss=0.3361, pruned_loss=0.07846, over 7171.00 frames.], tot_loss[loss=0.2128, simple_loss=0.3008, pruned_loss=0.06238, over 1427166.92 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:03:03,519 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 18:03:18,818 INFO [train.py:792] (4/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
2022-04-28 18:04:24,347 INFO [train.py:763] (4/8) Epoch 6, batch 3050, loss[loss=0.2383, simple_loss=0.3335, pruned_loss=0.07151, over 7144.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3003, pruned_loss=0.06207, over 1427648.63 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:05:30,257 INFO [train.py:763] (4/8) Epoch 6, batch 3100, loss[loss=0.2375, simple_loss=0.3257, pruned_loss=0.07465, over 7196.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3014, pruned_loss=0.0628, over 1424916.08 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:06:36,926 INFO [train.py:763] (4/8) Epoch 6, batch 3150, loss[loss=0.2435, simple_loss=0.3287, pruned_loss=0.07919, over 7034.00 frames.], tot_loss[loss=0.2127, simple_loss=0.3009, pruned_loss=0.0622, over 1428176.11 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:07:42,731 INFO [train.py:763] (4/8) Epoch 6, batch 3200, loss[loss=0.2184, simple_loss=0.3205, pruned_loss=0.05816, over 7341.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3025, pruned_loss=0.06316, over 1424343.97 frames.], batch size: 22, lr: 1.01e-03
2022-04-28 18:08:48,607 INFO [train.py:763] (4/8) Epoch 6, batch 3250, loss[loss=0.2292, simple_loss=0.3282, pruned_loss=0.06515, over 7081.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3018, pruned_loss=0.06294, over 1422884.18 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:09:54,854 INFO [train.py:763] (4/8) Epoch 6, batch 3300, loss[loss=0.2099, simple_loss=0.3128, pruned_loss=0.05354, over 7140.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3023, pruned_loss=0.06306, over 1417776.60 frames.], batch size: 20, lr: 1.01e-03
2022-04-28 18:11:00,640 INFO [train.py:763] (4/8) Epoch 6, batch 3350, loss[loss=0.178, simple_loss=0.2677, pruned_loss=0.04409, over 7149.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3025, pruned_loss=0.06296, over 1419271.81 frames.], batch size: 19, lr: 1.01e-03
2022-04-28 18:12:05,975 INFO [train.py:763] (4/8) Epoch 6, batch 3400, loss[loss=0.2144, simple_loss=0.3234, pruned_loss=0.05269, over 7436.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3027, pruned_loss=0.06324, over 1422825.39 frames.], batch size: 22, lr: 1.01e-03
2022-04-28 18:13:11,469 INFO [train.py:763] (4/8) Epoch 6, batch 3450, loss[loss=0.2151, simple_loss=0.3082, pruned_loss=0.061, over 7276.00 frames.], tot_loss[loss=0.2152, simple_loss=0.3033, pruned_loss=0.06355, over 1420612.71 frames.], batch size: 24, lr: 1.01e-03
2022-04-28 18:14:16,739 INFO [train.py:763] (4/8) Epoch 6, batch 3500, loss[loss=0.2093, simple_loss=0.3002, pruned_loss=0.05916, over 7220.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3031, pruned_loss=0.06312, over 1423156.11 frames.], batch size: 21, lr: 1.01e-03
2022-04-28 18:15:22,306 INFO [train.py:763] (4/8) Epoch 6, batch 3550, loss[loss=0.2291, simple_loss=0.3051, pruned_loss=0.07655, over 7370.00 frames.], tot_loss[loss=0.215, simple_loss=0.3029, pruned_loss=0.06355, over 1424191.64 frames.], batch size: 23, lr: 1.01e-03
2022-04-28 18:16:27,534 INFO [train.py:763] (4/8) Epoch 6, batch 3600, loss[loss=0.2401, simple_loss=0.3305, pruned_loss=0.07485, over 7222.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3023, pruned_loss=0.06327, over 1425510.49 frames.], batch size: 21, lr: 1.00e-03
2022-04-28 18:17:32,791 INFO [train.py:763] (4/8) Epoch 6, batch 3650, loss[loss=0.227, simple_loss=0.3133, pruned_loss=0.07038, over 7048.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3011, pruned_loss=0.06284, over 1422370.78 frames.], batch size: 28, lr: 1.00e-03
2022-04-28 18:18:39,442 INFO [train.py:763] (4/8) Epoch 6, batch 3700, loss[loss=0.1814, simple_loss=0.2805, pruned_loss=0.04119, over 7434.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3007, pruned_loss=0.06299, over 1423751.30 frames.], batch size: 20, lr: 1.00e-03
2022-04-28 18:19:44,868 INFO [train.py:763] (4/8) Epoch 6, batch 3750, loss[loss=0.2855, simple_loss=0.3543, pruned_loss=0.1083, over 4856.00 frames.], tot_loss[loss=0.2138, simple_loss=0.301, pruned_loss=0.06334, over 1424186.68 frames.], batch size: 53, lr: 1.00e-03
2022-04-28 18:20:50,220 INFO [train.py:763] (4/8) Epoch 6, batch 3800, loss[loss=0.2099, simple_loss=0.302, pruned_loss=0.05894, over 7362.00 frames.], tot_loss[loss=0.2137, simple_loss=0.3015, pruned_loss=0.063, over 1422436.24 frames.], batch size: 19, lr: 1.00e-03
2022-04-28 18:21:56,429 INFO [train.py:763] (4/8) Epoch 6, batch 3850, loss[loss=0.2422, simple_loss=0.3149, pruned_loss=0.08473, over 7144.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3008, pruned_loss=0.06321, over 1425496.70 frames.], batch size: 17, lr: 1.00e-03
2022-04-28 18:23:02,741 INFO [train.py:763] (4/8) Epoch 6, batch 3900, loss[loss=0.1954, simple_loss=0.284, pruned_loss=0.05343, over 7160.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3009, pruned_loss=0.06312, over 1425643.18 frames.], batch size: 18, lr: 1.00e-03
2022-04-28 18:24:08,624 INFO [train.py:763] (4/8) Epoch 6, batch 3950, loss[loss=0.2334, simple_loss=0.3138, pruned_loss=0.07646, over 7337.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2997, pruned_loss=0.06242, over 1427435.64 frames.], batch size: 22, lr: 9.99e-04
2022-04-28 18:25:14,069 INFO [train.py:763] (4/8) Epoch 6, batch 4000, loss[loss=0.2414, simple_loss=0.32, pruned_loss=0.08139, over 6883.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2999, pruned_loss=0.06243, over 1431716.93 frames.], batch size: 32, lr: 9.98e-04
2022-04-28 18:26:19,660 INFO [train.py:763] (4/8) Epoch 6, batch 4050, loss[loss=0.2197, simple_loss=0.3063, pruned_loss=0.06649, over 7163.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3003, pruned_loss=0.06294, over 1428964.96 frames.], batch size: 18, lr: 9.98e-04
2022-04-28 18:27:25,497 INFO [train.py:763] (4/8) Epoch 6, batch 4100, loss[loss=0.2162, simple_loss=0.2998, pruned_loss=0.06632, over 7129.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3018, pruned_loss=0.06364, over 1424847.98 frames.], batch size: 21, lr: 9.97e-04
2022-04-28 18:28:32,062 INFO [train.py:763] (4/8) Epoch 6, batch 4150, loss[loss=0.2405, simple_loss=0.3275, pruned_loss=0.07674, over 7201.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3019, pruned_loss=0.06346, over 1425907.91 frames.], batch size: 23, lr: 9.96e-04
2022-04-28 18:29:37,829 INFO [train.py:763] (4/8) Epoch 6, batch 4200, loss[loss=0.1602, simple_loss=0.2445, pruned_loss=0.03795, over 7285.00 frames.], tot_loss[loss=0.2129, simple_loss=0.3009, pruned_loss=0.06247, over 1427805.35 frames.], batch size: 17, lr: 9.95e-04
2022-04-28 18:30:43,248 INFO [train.py:763] (4/8) Epoch 6, batch 4250, loss[loss=0.1949, simple_loss=0.2885, pruned_loss=0.05063, over 7424.00 frames.], tot_loss[loss=0.2131, simple_loss=0.301, pruned_loss=0.06261, over 1422372.91 frames.], batch size: 20, lr: 9.95e-04
2022-04-28 18:31:48,726 INFO [train.py:763] (4/8) Epoch 6, batch 4300, loss[loss=0.2337, simple_loss=0.3217, pruned_loss=0.0728, over 7235.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3029, pruned_loss=0.06343, over 1416641.61 frames.], batch size: 20, lr: 9.94e-04
2022-04-28 18:32:54,884 INFO [train.py:763] (4/8) Epoch 6, batch 4350, loss[loss=0.205, simple_loss=0.2984, pruned_loss=0.05577, over 6448.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3035, pruned_loss=0.06353, over 1411202.60 frames.], batch size: 37, lr: 9.93e-04
2022-04-28 18:34:00,596 INFO [train.py:763] (4/8) Epoch 6, batch 4400, loss[loss=0.2389, simple_loss=0.3256, pruned_loss=0.07608, over 6837.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3023, pruned_loss=0.06308, over 1412103.23 frames.], batch size: 32, lr: 9.92e-04
2022-04-28 18:35:07,311 INFO [train.py:763] (4/8) Epoch 6, batch 4450, loss[loss=0.2113, simple_loss=0.2962, pruned_loss=0.06327, over 7207.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3026, pruned_loss=0.06318, over 1405814.34 frames.], batch size: 22, lr: 9.92e-04
2022-04-28 18:36:23,318 INFO [train.py:763] (4/8) Epoch 6, batch 4500, loss[loss=0.2204, simple_loss=0.3168, pruned_loss=0.06196, over 7224.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3026, pruned_loss=0.06308, over 1403185.10 frames.], batch size: 22, lr: 9.91e-04
2022-04-28 18:37:28,288 INFO [train.py:763] (4/8) Epoch 6, batch 4550, loss[loss=0.2798, simple_loss=0.3465, pruned_loss=0.1066, over 4940.00 frames.], tot_loss[loss=0.2171, simple_loss=0.305, pruned_loss=0.06464, over 1389195.18 frames.], batch size: 52, lr: 9.90e-04
2022-04-28 18:38:57,443 INFO [train.py:763] (4/8) Epoch 7, batch 0, loss[loss=0.2306, simple_loss=0.3303, pruned_loss=0.06545, over 7325.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3303, pruned_loss=0.06545, over 7325.00 frames.], batch size: 22, lr: 9.49e-04
2022-04-28 18:40:02,640 INFO [train.py:763] (4/8) Epoch 7, batch 50, loss[loss=0.2412, simple_loss=0.3066, pruned_loss=0.08791, over 7138.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3047, pruned_loss=0.06313, over 320061.46 frames.], batch size: 17, lr: 9.48e-04
2022-04-28 18:41:07,849 INFO [train.py:763] (4/8) Epoch 7, batch 100, loss[loss=0.2214, simple_loss=0.3208, pruned_loss=0.06099, over 7327.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3035, pruned_loss=0.06141, over 568506.55 frames.], batch size: 25, lr: 9.48e-04
2022-04-28 18:42:13,272 INFO [train.py:763] (4/8) Epoch 7, batch 150, loss[loss=0.2356, simple_loss=0.3251, pruned_loss=0.07308, over 7113.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2998, pruned_loss=0.06003, over 758889.95 frames.], batch size: 21, lr: 9.47e-04
2022-04-28 18:43:19,109 INFO [train.py:763] (4/8) Epoch 7, batch 200, loss[loss=0.2167, simple_loss=0.3095, pruned_loss=0.06191, over 7208.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3019, pruned_loss=0.06165, over 907584.26 frames.], batch size: 22, lr: 9.46e-04
2022-04-28 18:44:24,612 INFO [train.py:763] (4/8) Epoch 7, batch 250, loss[loss=0.2135, simple_loss=0.3098, pruned_loss=0.05861, over 7129.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3031, pruned_loss=0.06223, over 1020676.67 frames.], batch size: 21, lr: 9.46e-04
2022-04-28 18:45:29,825 INFO [train.py:763] (4/8) Epoch 7, batch 300, loss[loss=0.2031, simple_loss=0.2946, pruned_loss=0.05575, over 7071.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3029, pruned_loss=0.06201, over 1107145.39 frames.], batch size: 18, lr: 9.45e-04
2022-04-28 18:46:35,548 INFO [train.py:763] (4/8) Epoch 7, batch 350, loss[loss=0.2135, simple_loss=0.316, pruned_loss=0.05549, over 7106.00 frames.], tot_loss[loss=0.212, simple_loss=0.3011, pruned_loss=0.06143, over 1178226.30 frames.], batch size: 21, lr: 9.44e-04
2022-04-28 18:47:40,823 INFO [train.py:763] (4/8) Epoch 7, batch 400, loss[loss=0.2894, simple_loss=0.355, pruned_loss=0.1119, over 5076.00 frames.], tot_loss[loss=0.2117, simple_loss=0.3009, pruned_loss=0.06127, over 1231442.35 frames.], batch size: 52, lr: 9.43e-04
2022-04-28 18:48:46,396 INFO [train.py:763] (4/8) Epoch 7, batch 450, loss[loss=0.2086, simple_loss=0.2907, pruned_loss=0.06326, over 6893.00 frames.], tot_loss[loss=0.2119, simple_loss=0.3008, pruned_loss=0.06153, over 1272173.52 frames.], batch size: 15, lr: 9.43e-04
2022-04-28 18:49:51,763 INFO [train.py:763] (4/8) Epoch 7, batch 500, loss[loss=0.2334, simple_loss=0.3179, pruned_loss=0.07442, over 7189.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2994, pruned_loss=0.06074, over 1305699.30 frames.], batch size: 23, lr: 9.42e-04
2022-04-28 18:50:57,359 INFO [train.py:763] (4/8) Epoch 7, batch 550, loss[loss=0.2234, simple_loss=0.3163, pruned_loss=0.06523, over 7205.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2997, pruned_loss=0.06087, over 1333435.26 frames.], batch size: 23, lr: 9.41e-04
2022-04-28 18:52:02,631 INFO [train.py:763] (4/8) Epoch 7, batch 600, loss[loss=0.2367, simple_loss=0.32, pruned_loss=0.07667, over 7228.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3004, pruned_loss=0.06092, over 1353419.00 frames.], batch size: 21, lr: 9.41e-04
2022-04-28 18:53:08,460 INFO [train.py:763] (4/8) Epoch 7, batch 650, loss[loss=0.1833, simple_loss=0.2761, pruned_loss=0.04527, over 7265.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2997, pruned_loss=0.0603, over 1367782.37 frames.], batch size: 19, lr: 9.40e-04
2022-04-28 18:54:13,816 INFO [train.py:763] (4/8) Epoch 7, batch 700, loss[loss=0.2284, simple_loss=0.3067, pruned_loss=0.07503, over 5052.00 frames.], tot_loss[loss=0.2112, simple_loss=0.3006, pruned_loss=0.06091, over 1376250.56 frames.], batch size: 52, lr: 9.39e-04
2022-04-28 18:55:19,473 INFO [train.py:763] (4/8) Epoch 7, batch 750, loss[loss=0.2499, simple_loss=0.3206, pruned_loss=0.08961, over 7363.00 frames.], tot_loss[loss=0.2111, simple_loss=0.3004, pruned_loss=0.06089, over 1384991.31 frames.], batch size: 19, lr: 9.39e-04
2022-04-28 18:56:26,108 INFO [train.py:763] (4/8) Epoch 7, batch 800, loss[loss=0.2209, simple_loss=0.3012, pruned_loss=0.07026, over 6471.00 frames.], tot_loss[loss=0.2126, simple_loss=0.302, pruned_loss=0.0616, over 1390596.56 frames.], batch size: 38, lr: 9.38e-04
2022-04-28 18:57:33,276 INFO [train.py:763] (4/8) Epoch 7, batch 850, loss[loss=0.2022, simple_loss=0.2789, pruned_loss=0.06272, over 7398.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2993, pruned_loss=0.0606, over 1399292.02 frames.], batch size: 18, lr: 9.37e-04
2022-04-28 18:58:40,225 INFO [train.py:763] (4/8) Epoch 7, batch 900, loss[loss=0.2256, simple_loss=0.32, pruned_loss=0.06563, over 6799.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2994, pruned_loss=0.06115, over 1398565.54 frames.], batch size: 31, lr: 9.36e-04
2022-04-28 18:59:46,945 INFO [train.py:763] (4/8) Epoch 7, batch 950, loss[loss=0.1959, simple_loss=0.2966, pruned_loss=0.04763, over 7237.00 frames.], tot_loss[loss=0.2118, simple_loss=0.3005, pruned_loss=0.06149, over 1404578.65 frames.], batch size: 20, lr: 9.36e-04
2022-04-28 19:00:52,051 INFO [train.py:763] (4/8) Epoch 7, batch 1000, loss[loss=0.2388, simple_loss=0.3219, pruned_loss=0.0778, over 7228.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2996, pruned_loss=0.06098, over 1409546.55 frames.], batch size: 21, lr: 9.35e-04
2022-04-28 19:01:58,577 INFO [train.py:763] (4/8) Epoch 7, batch 1050, loss[loss=0.1892, simple_loss=0.2861, pruned_loss=0.04619, over 7145.00 frames.], tot_loss[loss=0.2114, simple_loss=0.3004, pruned_loss=0.06121, over 1407324.48 frames.], batch size: 17, lr: 9.34e-04
2022-04-28 19:03:05,226 INFO [train.py:763] (4/8) Epoch 7, batch 1100, loss[loss=0.2032, simple_loss=0.2948, pruned_loss=0.05578, over 7203.00 frames.], tot_loss[loss=0.2104, simple_loss=0.299, pruned_loss=0.06092, over 1412226.74 frames.], batch size: 22, lr: 9.34e-04
2022-04-28 19:04:11,928 INFO [train.py:763] (4/8) Epoch 7, batch 1150, loss[loss=0.3073, simple_loss=0.3707, pruned_loss=0.1219, over 4848.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2997, pruned_loss=0.0606, over 1417137.63 frames.], batch size: 52, lr: 9.33e-04
2022-04-28 19:05:18,438 INFO [train.py:763] (4/8) Epoch 7, batch 1200, loss[loss=0.2452, simple_loss=0.342, pruned_loss=0.07421, over 7144.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2998, pruned_loss=0.06029, over 1420388.94 frames.], batch size: 20, lr: 9.32e-04
2022-04-28 19:06:24,030 INFO [train.py:763] (4/8) Epoch 7, batch 1250, loss[loss=0.1767, simple_loss=0.2689, pruned_loss=0.04227, over 7278.00 frames.], tot_loss[loss=0.2091, simple_loss=0.2987, pruned_loss=0.05972, over 1419624.55 frames.], batch size: 18, lr: 9.32e-04
2022-04-28 19:07:30,156 INFO [train.py:763] (4/8) Epoch 7, batch 1300, loss[loss=0.1939, simple_loss=0.2799, pruned_loss=0.05394, over 7150.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3001, pruned_loss=0.0608, over 1415892.75 frames.], batch size: 20, lr: 9.31e-04
2022-04-28 19:08:35,479 INFO [train.py:763] (4/8) Epoch 7, batch 1350, loss[loss=0.2105, simple_loss=0.3028, pruned_loss=0.05913, over 7165.00 frames.], tot_loss[loss=0.2115, simple_loss=0.3004, pruned_loss=0.0613, over 1415044.13 frames.], batch size: 19, lr: 9.30e-04
2022-04-28 19:09:41,317 INFO [train.py:763] (4/8) Epoch 7, batch 1400, loss[loss=0.1803, simple_loss=0.2664, pruned_loss=0.04708, over 7288.00 frames.], tot_loss[loss=0.2116, simple_loss=0.3007, pruned_loss=0.06123, over 1415621.81 frames.], batch size: 18, lr: 9.30e-04
2022-04-28 19:10:48,151 INFO [train.py:763] (4/8) Epoch 7, batch 1450, loss[loss=0.2147, simple_loss=0.2947, pruned_loss=0.06733, over 7160.00 frames.], tot_loss[loss=0.21, simple_loss=0.2997, pruned_loss=0.06016, over 1414962.37 frames.], batch size: 18, lr: 9.29e-04
2022-04-28 19:11:54,398 INFO [train.py:763] (4/8) Epoch 7, batch 1500, loss[loss=0.1458, simple_loss=0.2403, pruned_loss=0.02558, over 7400.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2982, pruned_loss=0.05972, over 1415083.22 frames.], batch size: 18, lr: 9.28e-04
2022-04-28 19:12:59,476 INFO [train.py:763] (4/8) Epoch 7, batch 1550, loss[loss=0.1856, simple_loss=0.2826, pruned_loss=0.04427, over 7193.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2982, pruned_loss=0.0594, over 1420223.70 frames.], batch size: 22, lr: 9.28e-04
2022-04-28 19:14:04,512 INFO [train.py:763] (4/8) Epoch 7, batch 1600, loss[loss=0.2161, simple_loss=0.3037, pruned_loss=0.06425, over 6520.00 frames.], tot_loss[loss=0.21, simple_loss=0.2996, pruned_loss=0.06022, over 1420388.13 frames.], batch size: 38, lr: 9.27e-04
2022-04-28 19:15:09,642 INFO [train.py:763] (4/8) Epoch 7, batch 1650, loss[loss=0.2239, simple_loss=0.3015, pruned_loss=0.07319, over 7308.00 frames.], tot_loss[loss=0.2096, simple_loss=0.299, pruned_loss=0.06011, over 1418521.17 frames.], batch size: 24, lr: 9.26e-04
2022-04-28 19:16:15,821 INFO [train.py:763] (4/8) Epoch 7, batch 1700, loss[loss=0.207, simple_loss=0.3064, pruned_loss=0.05382, over 7316.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3002, pruned_loss=0.06081, over 1419028.66 frames.], batch size: 21, lr: 9.26e-04
2022-04-28 19:17:22,177 INFO [train.py:763] (4/8) Epoch 7, batch 1750, loss[loss=0.2118, simple_loss=0.2994, pruned_loss=0.06212, over 7344.00 frames.], tot_loss[loss=0.2101, simple_loss=0.299, pruned_loss=0.0606, over 1419603.35 frames.], batch size: 22, lr: 9.25e-04
2022-04-28 19:18:45,816 INFO [train.py:763] (4/8) Epoch 7, batch 1800, loss[loss=0.2485, simple_loss=0.3383, pruned_loss=0.07937, over 7335.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2972, pruned_loss=0.05974, over 1420505.62 frames.], batch size: 22, lr: 9.24e-04
2022-04-28 19:19:59,991 INFO [train.py:763] (4/8) Epoch 7, batch 1850, loss[loss=0.2385, simple_loss=0.3171, pruned_loss=0.07998, over 7236.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2985, pruned_loss=0.06001, over 1422521.81 frames.], batch size: 20, lr: 9.24e-04
2022-04-28 19:21:23,366 INFO [train.py:763] (4/8) Epoch 7, batch 1900, loss[loss=0.2319, simple_loss=0.3156, pruned_loss=0.07408, over 7295.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2979, pruned_loss=0.05992, over 1421792.63 frames.], batch size: 25, lr: 9.23e-04
2022-04-28 19:22:40,070 INFO [train.py:763] (4/8) Epoch 7, batch 1950, loss[loss=0.2045, simple_loss=0.2829, pruned_loss=0.06303, over 7001.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2974, pruned_loss=0.0598, over 1426420.14 frames.], batch size: 16, lr: 9.22e-04
2022-04-28 19:23:47,451 INFO [train.py:763] (4/8) Epoch 7, batch 2000, loss[loss=0.2091, simple_loss=0.3147, pruned_loss=0.05176, over 7106.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2975, pruned_loss=0.05962, over 1426618.76 frames.], batch size: 21, lr: 9.22e-04
2022-04-28 19:25:02,868 INFO [train.py:763] (4/8) Epoch 7, batch 2050, loss[loss=0.2833, simple_loss=0.355, pruned_loss=0.1058, over 5371.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2986, pruned_loss=0.0603, over 1420577.73 frames.], batch size: 52, lr: 9.21e-04
2022-04-28 19:26:07,936 INFO [train.py:763] (4/8) Epoch 7, batch 2100, loss[loss=0.2042, simple_loss=0.2935, pruned_loss=0.05749, over 7241.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2996, pruned_loss=0.06061, over 1416690.46 frames.], batch size: 20, lr: 9.20e-04
2022-04-28 19:27:22,247 INFO [train.py:763] (4/8) Epoch 7, batch 2150, loss[loss=0.2129, simple_loss=0.3145, pruned_loss=0.05566, over 7194.00 frames.], tot_loss[loss=0.2098, simple_loss=0.299, pruned_loss=0.06028, over 1418399.23 frames.], batch size: 22, lr: 9.20e-04
2022-04-28 19:28:27,687 INFO [train.py:763] (4/8) Epoch 7, batch 2200, loss[loss=0.2297, simple_loss=0.3094, pruned_loss=0.07503, over 7278.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2974, pruned_loss=0.05992, over 1417292.73 frames.], batch size: 24, lr: 9.19e-04
2022-04-28 19:29:32,842 INFO [train.py:763] (4/8) Epoch 7, batch 2250, loss[loss=0.2321, simple_loss=0.3164, pruned_loss=0.07391, over 7219.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2968, pruned_loss=0.05986, over 1412873.66 frames.], batch size: 23, lr: 9.18e-04
2022-04-28 19:30:38,170 INFO [train.py:763] (4/8) Epoch 7, batch 2300, loss[loss=0.1934, simple_loss=0.2761, pruned_loss=0.05532, over 7403.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2964, pruned_loss=0.05963, over 1412787.63 frames.], batch size: 18, lr: 9.18e-04
2022-04-28 19:31:43,911 INFO [train.py:763] (4/8) Epoch 7, batch 2350, loss[loss=0.1986, simple_loss=0.2791, pruned_loss=0.05901, over 7459.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2975, pruned_loss=0.05986, over 1413285.41 frames.], batch size: 19, lr: 9.17e-04
2022-04-28 19:32:50,591 INFO [train.py:763] (4/8) Epoch 7, batch 2400, loss[loss=0.2134, simple_loss=0.2996, pruned_loss=0.06361, over 7255.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2979, pruned_loss=0.06035, over 1416879.73 frames.], batch size: 19, lr: 9.16e-04
2022-04-28 19:33:55,901 INFO [train.py:763] (4/8) Epoch 7, batch 2450, loss[loss=0.1992, simple_loss=0.288, pruned_loss=0.05516, over 7277.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2976, pruned_loss=0.0598, over 1423192.18 frames.], batch size: 24, lr: 9.16e-04
2022-04-28 19:35:01,300 INFO [train.py:763] (4/8) Epoch 7, batch 2500, loss[loss=0.2093, simple_loss=0.3096, pruned_loss=0.05448, over 7320.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2984, pruned_loss=0.06026, over 1421035.39 frames.], batch size: 21, lr: 9.15e-04
2022-04-28 19:36:06,925 INFO [train.py:763] (4/8) Epoch 7, batch 2550, loss[loss=0.1986, simple_loss=0.2895, pruned_loss=0.05381, over 7370.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2973, pruned_loss=0.05989, over 1425900.80 frames.], batch size: 19, lr: 9.14e-04
2022-04-28 19:37:12,482 INFO [train.py:763] (4/8) Epoch 7, batch 2600, loss[loss=0.1692, simple_loss=0.2489, pruned_loss=0.04478, over 6815.00 frames.], tot_loss[loss=0.2093, simple_loss=0.298, pruned_loss=0.06027, over 1426695.62 frames.], batch size: 15, lr: 9.14e-04
2022-04-28 19:38:17,712 INFO [train.py:763] (4/8) Epoch 7, batch 2650, loss[loss=0.2445, simple_loss=0.3301, pruned_loss=0.07945, over 7115.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2981, pruned_loss=0.0602, over 1427212.33 frames.], batch size: 21, lr: 9.13e-04
2022-04-28 19:39:23,652 INFO [train.py:763] (4/8) Epoch 7, batch 2700, loss[loss=0.1893, simple_loss=0.2654, pruned_loss=0.05654, over 6835.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2978, pruned_loss=0.06033, over 1429411.59 frames.], batch size: 15, lr: 9.12e-04
2022-04-28 19:40:30,717 INFO [train.py:763] (4/8) Epoch 7, batch 2750, loss[loss=0.1656, simple_loss=0.2523, pruned_loss=0.03941, over 7009.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2977, pruned_loss=0.06043, over 1428570.71 frames.], batch size: 16, lr: 9.12e-04
2022-04-28 19:41:36,687 INFO [train.py:763] (4/8) Epoch 7, batch 2800, loss[loss=0.2152, simple_loss=0.3062, pruned_loss=0.0621, over 7143.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2975, pruned_loss=0.05981, over 1428594.74 frames.], batch size: 20, lr: 9.11e-04
2022-04-28 19:42:43,484 INFO [train.py:763] (4/8) Epoch 7, batch 2850, loss[loss=0.2156, simple_loss=0.309, pruned_loss=0.0611, over 7197.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2983, pruned_loss=0.06028, over 1426592.93 frames.], batch size: 22, lr: 9.11e-04
2022-04-28 19:43:49,293 INFO [train.py:763] (4/8) Epoch 7, batch 2900, loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03239, over 7126.00 frames.], tot_loss[loss=0.209, simple_loss=0.2983, pruned_loss=0.05983, over 1425688.84 frames.], batch size: 17, lr: 9.10e-04
2022-04-28 19:44:55,754 INFO [train.py:763] (4/8) Epoch 7, batch 2950, loss[loss=0.1789, simple_loss=0.2708, pruned_loss=0.0435, over 7048.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2963, pruned_loss=0.05904, over 1425082.08 frames.], batch size: 18, lr: 9.09e-04
2022-04-28 19:46:01,158 INFO [train.py:763] (4/8) Epoch 7, batch 3000, loss[loss=0.2726, simple_loss=0.3485, pruned_loss=0.09838, over 4925.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2967, pruned_loss=0.05945, over 1421854.19 frames.], batch size: 53, lr: 9.09e-04
2022-04-28 19:46:01,159 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 19:46:16,423 INFO [train.py:792] (4/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
2022-04-28 19:47:23,037 INFO [train.py:763] (4/8) Epoch 7, batch 3050, loss[loss=0.2373, simple_loss=0.325, pruned_loss=0.07477, over 6344.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2961, pruned_loss=0.05958, over 1414956.96 frames.], batch size: 37, lr: 9.08e-04
2022-04-28 19:48:28,733 INFO [train.py:763] (4/8) Epoch 7, batch 3100, loss[loss=0.183, simple_loss=0.2833, pruned_loss=0.0414, over 7256.00 frames.], tot_loss[loss=0.2071, simple_loss=0.296, pruned_loss=0.05912, over 1420015.24 frames.], batch size: 19, lr: 9.07e-04
2022-04-28 19:49:34,313 INFO [train.py:763] (4/8) Epoch 7, batch 3150, loss[loss=0.2129, simple_loss=0.312, pruned_loss=0.05689, over 7440.00 frames.], tot_loss[loss=0.206, simple_loss=0.2947, pruned_loss=0.05862, over 1421471.92 frames.], batch size: 20, lr: 9.07e-04
2022-04-28 19:50:39,917 INFO [train.py:763] (4/8) Epoch 7, batch 3200, loss[loss=0.1647, simple_loss=0.2571, pruned_loss=0.03613, over 7437.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2942, pruned_loss=0.05808, over 1424452.57 frames.], batch size: 20, lr: 9.06e-04
2022-04-28 19:51:45,167 INFO [train.py:763] (4/8) Epoch 7, batch 3250, loss[loss=0.2069, simple_loss=0.2952, pruned_loss=0.05925, over 7046.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2958, pruned_loss=0.05865, over 1423089.89 frames.], batch size: 28, lr: 9.05e-04
2022-04-28 19:52:50,674 INFO [train.py:763] (4/8) Epoch 7, batch 3300, loss[loss=0.225, simple_loss=0.311, pruned_loss=0.06947, over 6709.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2955, pruned_loss=0.05897, over 1422351.61 frames.], batch size: 31, lr: 9.05e-04
2022-04-28 19:53:56,155 INFO [train.py:763] (4/8) Epoch 7, batch 3350, loss[loss=0.1901, simple_loss=0.2778, pruned_loss=0.05122, over 7441.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2954, pruned_loss=0.05898, over 1419958.94 frames.], batch size: 20, lr: 9.04e-04
2022-04-28 19:55:01,740 INFO [train.py:763] (4/8) Epoch 7, batch 3400, loss[loss=0.2225, simple_loss=0.3139, pruned_loss=0.06558, over 6744.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2954, pruned_loss=0.05909, over 1418416.87 frames.], batch size: 31, lr: 9.04e-04
2022-04-28 19:56:08,384 INFO [train.py:763] (4/8) Epoch 7, batch 3450, loss[loss=0.1999, simple_loss=0.2756, pruned_loss=0.06208, over 7418.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2974, pruned_loss=0.05987, over 1421757.78 frames.], batch size: 18, lr: 9.03e-04
2022-04-28 19:57:15,787 INFO [train.py:763] (4/8) Epoch 7, batch 3500, loss[loss=0.1962, simple_loss=0.2921, pruned_loss=0.05018, over 7363.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2979, pruned_loss=0.05976, over 1420799.46 frames.], batch size: 23, lr: 9.02e-04
2022-04-28 19:58:22,784 INFO [train.py:763] (4/8) Epoch 7, batch 3550, loss[loss=0.2136, simple_loss=0.3072, pruned_loss=0.06002, over 7254.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2983, pruned_loss=0.06034, over 1422515.81 frames.], batch size: 19, lr: 9.02e-04
2022-04-28 19:59:29,955 INFO [train.py:763] (4/8) Epoch 7, batch 3600, loss[loss=0.1676, simple_loss=0.2443, pruned_loss=0.0454, over 7288.00 frames.], tot_loss[loss=0.2081, simple_loss=0.297, pruned_loss=0.05961, over 1421253.67 frames.], batch size: 17, lr: 9.01e-04
2022-04-28 20:00:37,036 INFO [train.py:763] (4/8) Epoch 7, batch 3650, loss[loss=0.1988, simple_loss=0.292, pruned_loss=0.05282, over 7414.00 frames.], tot_loss[loss=0.21, simple_loss=0.2991, pruned_loss=0.06047, over 1416006.25 frames.], batch size: 21, lr: 9.01e-04
2022-04-28 20:01:42,539 INFO [train.py:763] (4/8) Epoch 7, batch 3700, loss[loss=0.2371, simple_loss=0.32, pruned_loss=0.07706, over 7219.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2984, pruned_loss=0.0601, over 1420042.70 frames.], batch size: 21, lr: 9.00e-04
2022-04-28 20:02:49,190 INFO [train.py:763] (4/8) Epoch 7, batch 3750, loss[loss=0.1944, simple_loss=0.2959, pruned_loss=0.04644, over 7155.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2977, pruned_loss=0.05945, over 1418007.42 frames.], batch size: 19, lr: 8.99e-04
2022-04-28 20:03:54,760 INFO [train.py:763] (4/8) Epoch 7, batch 3800, loss[loss=0.2263, simple_loss=0.3042, pruned_loss=0.0742, over 7283.00 frames.], tot_loss[loss=0.2094, simple_loss=0.299, pruned_loss=0.05992, over 1420667.38 frames.], batch size: 24, lr: 8.99e-04
2022-04-28 20:05:00,506 INFO [train.py:763] (4/8) Epoch 7, batch 3850, loss[loss=0.1928, simple_loss=0.2905, pruned_loss=0.04748, over 7224.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2994, pruned_loss=0.05989, over 1418165.95 frames.], batch size: 21, lr: 8.98e-04
2022-04-28 20:06:06,735 INFO [train.py:763] (4/8) Epoch 7, batch 3900, loss[loss=0.1852, simple_loss=0.2821, pruned_loss=0.04418, over 7436.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2973, pruned_loss=0.05887, over 1421764.62 frames.], batch size: 20, lr: 8.97e-04
2022-04-28 20:07:13,247 INFO [train.py:763] (4/8) Epoch 7, batch 3950, loss[loss=0.2078, simple_loss=0.2784, pruned_loss=0.06856, over 6998.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2962, pruned_loss=0.05844, over 1424118.11 frames.], batch size: 16, lr: 8.97e-04
2022-04-28 20:08:18,735 INFO [train.py:763] (4/8) Epoch 7, batch 4000, loss[loss=0.2195, simple_loss=0.3103, pruned_loss=0.06436, over 7148.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2969, pruned_loss=0.05863, over 1422377.58 frames.], batch size: 20, lr: 8.96e-04
2022-04-28 20:09:23,869 INFO [train.py:763] (4/8) Epoch 7, batch 4050, loss[loss=0.1848, simple_loss=0.2839, pruned_loss=0.04284, over 7411.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2964, pruned_loss=0.05802, over 1424940.39 frames.], batch size: 21, lr: 8.96e-04
2022-04-28 20:10:29,411 INFO [train.py:763] (4/8) Epoch 7, batch 4100, loss[loss=0.177, simple_loss=0.2514, pruned_loss=0.0513, over 7280.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2965, pruned_loss=0.05833, over 1418238.31 frames.], batch size: 17, lr: 8.95e-04
2022-04-28 20:11:34,139 INFO [train.py:763] (4/8) Epoch 7, batch 4150, loss[loss=0.2096, simple_loss=0.2987, pruned_loss=0.06024, over 7324.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2973, pruned_loss=0.05892, over 1412738.31 frames.], batch size: 22, lr: 8.94e-04
2022-04-28 20:12:39,364 INFO [train.py:763] (4/8) Epoch 7, batch 4200, loss[loss=0.2111, simple_loss=0.3059, pruned_loss=0.05813, over 7149.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2984, pruned_loss=0.05924, over 1415264.87 frames.], batch size: 20, lr: 8.94e-04
2022-04-28 20:13:44,888 INFO [train.py:763] (4/8) Epoch 7, batch 4250, loss[loss=0.2679, simple_loss=0.336, pruned_loss=0.09993, over 7195.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2985, pruned_loss=0.05967, over 1420028.94 frames.], batch size: 22, lr: 8.93e-04
2022-04-28 20:14:50,388 INFO [train.py:763] (4/8) Epoch 7, batch 4300, loss[loss=0.2132, simple_loss=0.3076, pruned_loss=0.05938, over 7310.00 frames.], tot_loss[loss=0.2074, simple_loss=0.297, pruned_loss=0.05893, over 1418368.14 frames.], batch size: 21, lr: 8.93e-04
2022-04-28 20:15:55,683 INFO [train.py:763] (4/8) Epoch 7, batch 4350, loss[loss=0.2426, simple_loss=0.3267, pruned_loss=0.07922, over 7120.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2956, pruned_loss=0.0584, over 1414902.94 frames.], batch size: 21, lr: 8.92e-04
2022-04-28 20:17:01,779 INFO [train.py:763] (4/8) Epoch 7, batch 4400, loss[loss=0.2092, simple_loss=0.2982, pruned_loss=0.06008, over 7077.00 frames.], tot_loss[loss=0.2046, simple_loss=0.294, pruned_loss=0.05766, over 1417174.04 frames.], batch size: 28, lr: 8.91e-04
2022-04-28 20:18:08,978 INFO [train.py:763] (4/8) Epoch 7, batch 4450, loss[loss=0.2274, simple_loss=0.3266, pruned_loss=0.06409, over 7319.00 frames.], tot_loss[loss=0.205, simple_loss=0.2942, pruned_loss=0.05787, over 1417450.34 frames.], batch size: 20, lr: 8.91e-04
2022-04-28 20:19:16,354 INFO [train.py:763] (4/8) Epoch 7, batch 4500, loss[loss=0.196, simple_loss=0.2833, pruned_loss=0.05435, over 7171.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2942, pruned_loss=0.05786, over 1414651.55 frames.], batch size: 18, lr: 8.90e-04
2022-04-28 20:20:24,250 INFO [train.py:763] (4/8) Epoch 7, batch 4550, loss[loss=0.1719, simple_loss=0.2495, pruned_loss=0.04718, over 7270.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2937, pruned_loss=0.05865, over 1398847.91 frames.], batch size: 17, lr: 8.90e-04
2022-04-28 20:21:52,805 INFO [train.py:763] (4/8) Epoch 8, batch 0, loss[loss=0.2239, simple_loss=0.3172, pruned_loss=0.06526, over 7209.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3172, pruned_loss=0.06526, over 7209.00 frames.], batch size: 23, lr: 8.54e-04
2022-04-28 20:22:58,560 INFO [train.py:763] (4/8) Epoch 8, batch 50, loss[loss=0.1853, simple_loss=0.2869, pruned_loss=0.04183, over 7088.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2984, pruned_loss=0.05817, over 319503.66 frames.], batch size: 28, lr: 8.53e-04
2022-04-28 20:24:03,943 INFO [train.py:763] (4/8) Epoch 8, batch 100, loss[loss=0.2143, simple_loss=0.3116, pruned_loss=0.05848, over 7242.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2926, pruned_loss=0.05486, over 566498.67 frames.], batch size: 20, lr: 8.53e-04
2022-04-28 20:25:10,089 INFO [train.py:763] (4/8) Epoch 8, batch 150, loss[loss=0.2336, simple_loss=0.3115, pruned_loss=0.07789, over 4875.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2931, pruned_loss=0.05561, over 753680.19 frames.], batch size: 52, lr: 8.52e-04
2022-04-28 20:26:16,004 INFO [train.py:763] (4/8) Epoch 8, batch 200, loss[loss=0.2079, simple_loss=0.3045, pruned_loss=0.05568, over 7193.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2936, pruned_loss=0.05606, over 902536.99 frames.], batch size: 22, lr: 8.51e-04
2022-04-28 20:27:21,273 INFO [train.py:763] (4/8) Epoch 8, batch 250, loss[loss=0.211, simple_loss=0.3003, pruned_loss=0.06085, over 7435.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2921, pruned_loss=0.05489, over 1018854.74 frames.], batch size: 20, lr: 8.51e-04
2022-04-28 20:28:27,033 INFO [train.py:763] (4/8) Epoch 8, batch 300, loss[loss=0.219, simple_loss=0.3102, pruned_loss=0.06392, over 7326.00 frames.], tot_loss[loss=0.2023, simple_loss=0.293, pruned_loss=0.05578, over 1104015.94 frames.], batch size: 22, lr: 8.50e-04
2022-04-28 20:29:32,796 INFO [train.py:763] (4/8) Epoch 8, batch 350, loss[loss=0.1738, simple_loss=0.2654, pruned_loss=0.04106, over 7171.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2904, pruned_loss=0.05464, over 1178275.22 frames.], batch size: 19, lr: 8.50e-04
2022-04-28 20:30:38,284 INFO [train.py:763] (4/8) Epoch 8, batch 400, loss[loss=0.1585, simple_loss=0.246, pruned_loss=0.03544, over 7140.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2915, pruned_loss=0.055, over 1237260.86 frames.], batch size: 17, lr: 8.49e-04
2022-04-28 20:31:43,710 INFO [train.py:763] (4/8) Epoch 8, batch 450, loss[loss=0.1767, simple_loss=0.2685, pruned_loss=0.04242, over 7258.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2913, pruned_loss=0.05513, over 1277908.68 frames.], batch size: 19, lr: 8.49e-04
2022-04-28 20:32:50,560 INFO [train.py:763] (4/8) Epoch 8, batch 500, loss[loss=0.1728, simple_loss=0.2605, pruned_loss=0.04261, over 7404.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2924, pruned_loss=0.05559, over 1310726.06 frames.], batch size: 18, lr: 8.48e-04
2022-04-28 20:33:57,711 INFO [train.py:763] (4/8) Epoch 8, batch 550, loss[loss=0.1587, simple_loss=0.2429, pruned_loss=0.03723, over 7075.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2914, pruned_loss=0.05471, over 1338199.21 frames.], batch size: 18, lr: 8.48e-04
2022-04-28 20:35:03,798 INFO [train.py:763] (4/8) Epoch 8, batch 600, loss[loss=0.2253, simple_loss=0.3049, pruned_loss=0.07289, over 7062.00 frames.], tot_loss[loss=0.201, simple_loss=0.2918, pruned_loss=0.05507, over 1359898.63 frames.], batch size: 18, lr: 8.47e-04
2022-04-28 20:36:09,107 INFO [train.py:763] (4/8) Epoch 8, batch 650, loss[loss=0.2046, simple_loss=0.2934, pruned_loss=0.05789, over 7357.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2918, pruned_loss=0.05489, over 1373248.08 frames.], batch size: 19, lr: 8.46e-04
2022-04-28 20:37:14,551 INFO [train.py:763] (4/8) Epoch 8, batch 700, loss[loss=0.1668, simple_loss=0.2586, pruned_loss=0.03751, over 7427.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2926, pruned_loss=0.05538, over 1386039.80 frames.], batch size: 20, lr: 8.46e-04
2022-04-28 20:38:20,312 INFO [train.py:763] (4/8) Epoch 8, batch 750, loss[loss=0.1853, simple_loss=0.2803, pruned_loss=0.04518, over 7160.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2933, pruned_loss=0.05581, over 1388710.88 frames.], batch size: 18, lr: 8.45e-04
2022-04-28 20:39:25,912 INFO [train.py:763] (4/8) Epoch 8, batch 800, loss[loss=0.2306, simple_loss=0.3171, pruned_loss=0.07212, over 7366.00 frames.], tot_loss[loss=0.203, simple_loss=0.2936, pruned_loss=0.05618, over 1395996.88 frames.], batch size: 23, lr: 8.45e-04
2022-04-28 20:40:32,527 INFO [train.py:763] (4/8) Epoch 8, batch 850, loss[loss=0.2024, simple_loss=0.2889, pruned_loss=0.05792, over 7323.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05591, over 1401173.37 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:41:39,525 INFO [train.py:763] (4/8) Epoch 8, batch 900, loss[loss=0.2366, simple_loss=0.3233, pruned_loss=0.07499, over 7221.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2925, pruned_loss=0.05529, over 1410498.16 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:42:46,672 INFO [train.py:763] (4/8) Epoch 8, batch 950, loss[loss=0.1487, simple_loss=0.2514, pruned_loss=0.02297, over 7324.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05588, over 1408076.32 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:43:53,790 INFO [train.py:763] (4/8) Epoch 8, batch 1000, loss[loss=0.1952, simple_loss=0.283, pruned_loss=0.05372, over 7427.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2931, pruned_loss=0.05603, over 1412734.72 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:45:00,936 INFO [train.py:763] (4/8) Epoch 8, batch 1050, loss[loss=0.1961, simple_loss=0.2819, pruned_loss=0.05517, over 7273.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05581, over 1417217.51 frames.], batch size: 19, lr: 8.42e-04
2022-04-28 20:46:07,159 INFO [train.py:763] (4/8) Epoch 8, batch 1100, loss[loss=0.1678, simple_loss=0.2623, pruned_loss=0.0367, over 7282.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2944, pruned_loss=0.05602, over 1420031.54 frames.], batch size: 17, lr: 8.41e-04
2022-04-28 20:47:12,899 INFO [train.py:763] (4/8) Epoch 8, batch 1150, loss[loss=0.2259, simple_loss=0.3102, pruned_loss=0.07074, over 7323.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2929, pruned_loss=0.0555, over 1420954.15 frames.], batch size: 25, lr: 8.41e-04
2022-04-28 20:48:18,240 INFO [train.py:763] (4/8) Epoch 8, batch 1200, loss[loss=0.1897, simple_loss=0.2793, pruned_loss=0.05009, over 7433.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2925, pruned_loss=0.05538, over 1420767.17 frames.], batch size: 20, lr: 8.40e-04
2022-04-28 20:49:23,426 INFO [train.py:763] (4/8) Epoch 8, batch 1250, loss[loss=0.1989, simple_loss=0.2766, pruned_loss=0.06055, over 6760.00 frames.], tot_loss[loss=0.202, simple_loss=0.2925, pruned_loss=0.05581, over 1417325.97 frames.], batch size: 15, lr: 8.40e-04
2022-04-28 20:50:29,919 INFO [train.py:763] (4/8) Epoch 8, batch 1300, loss[loss=0.2244, simple_loss=0.3086, pruned_loss=0.07013, over 7168.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2941, pruned_loss=0.05662, over 1414602.29 frames.], batch size: 19, lr: 8.39e-04
2022-04-28 20:51:37,148 INFO [train.py:763] (4/8) Epoch 8, batch 1350, loss[loss=0.2069, simple_loss=0.2975, pruned_loss=0.05813, over 7414.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2936, pruned_loss=0.05665, over 1419019.50 frames.], batch size: 20, lr: 8.39e-04
2022-04-28 20:52:43,210 INFO [train.py:763] (4/8) Epoch 8, batch 1400, loss[loss=0.2022, simple_loss=0.292, pruned_loss=0.05624, over 7221.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2931, pruned_loss=0.0565, over 1416109.59 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:53:48,891 INFO [train.py:763] (4/8) Epoch 8, batch 1450, loss[loss=0.2018, simple_loss=0.3016, pruned_loss=0.05099, over 7317.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2917, pruned_loss=0.05538, over 1420762.93 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:54:55,523 INFO [train.py:763] (4/8) Epoch 8, batch 1500, loss[loss=0.1837, simple_loss=0.2937, pruned_loss=0.03689, over 7233.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2924, pruned_loss=0.05563, over 1423310.82 frames.], batch size: 20, lr: 8.37e-04
2022-04-28 20:56:02,359 INFO [train.py:763] (4/8) Epoch 8, batch 1550, loss[loss=0.1928, simple_loss=0.2805, pruned_loss=0.05252, over 7206.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2925, pruned_loss=0.05604, over 1422091.80 frames.], batch size: 22, lr: 8.37e-04
2022-04-28 20:57:08,582 INFO [train.py:763] (4/8) Epoch 8, batch 1600, loss[loss=0.1498, simple_loss=0.24, pruned_loss=0.02975, over 7069.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2933, pruned_loss=0.05599, over 1420292.23 frames.], batch size: 18, lr: 8.36e-04
2022-04-28 20:58:15,578 INFO [train.py:763] (4/8) Epoch 8, batch 1650, loss[loss=0.209, simple_loss=0.3068, pruned_loss=0.05563, over 7110.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2949, pruned_loss=0.0567, over 1420763.86 frames.], batch size: 21, lr: 8.35e-04
2022-04-28 20:59:22,334 INFO [train.py:763] (4/8) Epoch 8, batch 1700, loss[loss=0.1929, simple_loss=0.2915, pruned_loss=0.04715, over 7142.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2945, pruned_loss=0.05636, over 1419180.57 frames.], batch size: 20, lr: 8.35e-04
2022-04-28 21:00:28,777 INFO [train.py:763] (4/8) Epoch 8, batch 1750, loss[loss=0.2261, simple_loss=0.3316, pruned_loss=0.06031, over 7314.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2933, pruned_loss=0.05588, over 1421181.83 frames.], batch size: 21, lr: 8.34e-04
2022-04-28 21:01:33,978 INFO [train.py:763] (4/8) Epoch 8, batch 1800, loss[loss=0.2014, simple_loss=0.3022, pruned_loss=0.05029, over 7236.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2931, pruned_loss=0.05597, over 1417835.11 frames.], batch size: 20, lr: 8.34e-04
2022-04-28 21:02:39,281 INFO [train.py:763] (4/8) Epoch 8, batch 1850, loss[loss=0.2086, simple_loss=0.3031, pruned_loss=0.05706, over 7241.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2938, pruned_loss=0.05597, over 1420988.59 frames.], batch size: 20, lr: 8.33e-04
2022-04-28 21:03:44,673 INFO [train.py:763] (4/8) Epoch 8, batch 1900, loss[loss=0.2061, simple_loss=0.2909, pruned_loss=0.06059, over 7155.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05623, over 1419586.82 frames.], batch size: 19, lr: 8.33e-04
2022-04-28 21:04:50,204 INFO [train.py:763] (4/8) Epoch 8, batch 1950, loss[loss=0.2257, simple_loss=0.3171, pruned_loss=0.06712, over 7114.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2948, pruned_loss=0.05624, over 1420473.83 frames.], batch size: 21, lr: 8.32e-04
2022-04-28 21:05:55,497 INFO [train.py:763] (4/8) Epoch 8, batch 2000, loss[loss=0.2093, simple_loss=0.307, pruned_loss=0.05577, over 7260.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2931, pruned_loss=0.05533, over 1421350.82 frames.], batch size: 24, lr: 8.32e-04
2022-04-28 21:07:00,729 INFO [train.py:763] (4/8) Epoch 8, batch 2050, loss[loss=0.1654, simple_loss=0.2423, pruned_loss=0.04425, over 7285.00 frames.], tot_loss[loss=0.202, simple_loss=0.293, pruned_loss=0.05548, over 1420552.36 frames.], batch size: 17, lr: 8.31e-04
2022-04-28 21:08:05,935 INFO [train.py:763] (4/8) Epoch 8, batch 2100, loss[loss=0.2006, simple_loss=0.2962, pruned_loss=0.05254, over 7248.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2933, pruned_loss=0.05579, over 1422249.18 frames.], batch size: 19, lr: 8.31e-04
2022-04-28 21:09:08,023 INFO [train.py:763] (4/8) Epoch 8, batch 2150, loss[loss=0.1927, simple_loss=0.2743, pruned_loss=0.05562, over 7077.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2931, pruned_loss=0.056, over 1425070.96 frames.], batch size: 18, lr: 8.30e-04
2022-04-28 21:10:14,556 INFO [train.py:763] (4/8) Epoch 8, batch 2200, loss[loss=0.1796, simple_loss=0.2681, pruned_loss=0.0455, over 7270.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2932, pruned_loss=0.05598, over 1422836.36 frames.], batch size: 17, lr: 8.30e-04
2022-04-28 21:11:21,395 INFO [train.py:763] (4/8) Epoch 8, batch 2250, loss[loss=0.1853, simple_loss=0.2731, pruned_loss=0.04879, over 7153.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2928, pruned_loss=0.05607, over 1423861.70 frames.], batch size: 18, lr: 8.29e-04
2022-04-28 21:12:26,807 INFO [train.py:763] (4/8) Epoch 8, batch 2300, loss[loss=0.1645, simple_loss=0.2712, pruned_loss=0.02896, over 7131.00 frames.], tot_loss[loss=0.2036, simple_loss=0.294, pruned_loss=0.05657, over 1425365.78 frames.], batch size: 20, lr: 8.29e-04
2022-04-28 21:13:32,124 INFO [train.py:763] (4/8) Epoch 8, batch 2350, loss[loss=0.1986, simple_loss=0.3023, pruned_loss=0.0474, over 6856.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2947, pruned_loss=0.05673, over 1423786.93 frames.], batch size: 31, lr: 8.28e-04
2022-04-28 21:14:37,449 INFO [train.py:763] (4/8) Epoch 8, batch 2400, loss[loss=0.188, simple_loss=0.2759, pruned_loss=0.05002, over 7270.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2947, pruned_loss=0.05658, over 1423792.73 frames.], batch size: 18, lr: 8.28e-04
2022-04-28 21:15:42,876 INFO [train.py:763] (4/8) Epoch 8, batch 2450, loss[loss=0.1932, simple_loss=0.2758, pruned_loss=0.05531, over 7403.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2955, pruned_loss=0.05733, over 1425115.99 frames.], batch size: 18, lr: 8.27e-04
2022-04-28 21:16:48,162 INFO [train.py:763] (4/8) Epoch 8, batch 2500, loss[loss=0.2175, simple_loss=0.3227, pruned_loss=0.05615, over 7203.00 frames.], tot_loss[loss=0.2056, simple_loss=0.296, pruned_loss=0.05756, over 1424312.73 frames.], batch size: 22, lr: 8.27e-04
2022-04-28 21:17:53,461 INFO [train.py:763] (4/8) Epoch 8, batch 2550, loss[loss=0.1729, simple_loss=0.2614, pruned_loss=0.04219, over 7134.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2953, pruned_loss=0.05764, over 1421559.76 frames.], batch size: 17, lr: 8.26e-04
2022-04-28 21:18:58,782 INFO [train.py:763] (4/8) Epoch 8, batch 2600, loss[loss=0.244, simple_loss=0.3372, pruned_loss=0.07539, over 7390.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2961, pruned_loss=0.05786, over 1418956.20 frames.], batch size: 23, lr: 8.25e-04
2022-04-28 21:20:03,877 INFO [train.py:763] (4/8) Epoch 8, batch 2650, loss[loss=0.2341, simple_loss=0.319, pruned_loss=0.07457, over 4959.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2944, pruned_loss=0.05698, over 1417647.44 frames.], batch size: 52, lr: 8.25e-04
2022-04-28 21:21:09,312 INFO [train.py:763] (4/8) Epoch 8, batch 2700, loss[loss=0.183, simple_loss=0.2817, pruned_loss=0.04215, over 7333.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2945, pruned_loss=0.05666, over 1418929.63 frames.], batch size: 22, lr: 8.24e-04
2022-04-28 21:22:14,617 INFO [train.py:763] (4/8) Epoch 8, batch 2750, loss[loss=0.1936, simple_loss=0.2858, pruned_loss=0.05074, over 7337.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2934, pruned_loss=0.05579, over 1423252.43 frames.], batch size: 20, lr: 8.24e-04
2022-04-28 21:23:20,615 INFO [train.py:763] (4/8) Epoch 8, batch 2800, loss[loss=0.188, simple_loss=0.2872, pruned_loss=0.04439, over 7211.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2932, pruned_loss=0.05558, over 1425993.14 frames.], batch size: 22, lr: 8.23e-04
2022-04-28 21:24:26,771 INFO [train.py:763] (4/8) Epoch 8, batch 2850, loss[loss=0.2204, simple_loss=0.3076, pruned_loss=0.06655, over 7158.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2926, pruned_loss=0.05541, over 1428370.71 frames.], batch size: 19, lr: 8.23e-04
2022-04-28 21:25:32,042 INFO [train.py:763] (4/8) Epoch 8, batch 2900, loss[loss=0.2306, simple_loss=0.3137, pruned_loss=0.0737, over 7318.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2935, pruned_loss=0.05594, over 1426827.50 frames.], batch size: 21, lr: 8.22e-04
2022-04-28 21:26:37,469 INFO [train.py:763] (4/8) Epoch 8, batch 2950, loss[loss=0.1965, simple_loss=0.2776, pruned_loss=0.05769, over 7273.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2945, pruned_loss=0.05638, over 1423540.58 frames.], batch size: 18, lr: 8.22e-04
2022-04-28 21:27:43,084 INFO [train.py:763] (4/8) Epoch 8, batch 3000, loss[loss=0.2346, simple_loss=0.3115, pruned_loss=0.07885, over 7265.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2947, pruned_loss=0.05682, over 1421820.93 frames.], batch size: 24, lr: 8.21e-04
2022-04-28 21:27:43,085 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 21:27:58,489 INFO [train.py:792] (4/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 21:29:04,150 INFO [train.py:763] (4/8) Epoch 8, batch 3050, loss[loss=0.2074, simple_loss=0.2871, pruned_loss=0.06389, over 7321.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2944, pruned_loss=0.05694, over 1418993.44 frames.], batch size: 20, lr: 8.21e-04
2022-04-28 21:30:09,329 INFO [train.py:763] (4/8) Epoch 8, batch 3100, loss[loss=0.2154, simple_loss=0.3036, pruned_loss=0.06359, over 6817.00 frames.], tot_loss[loss=0.2051, simple_loss=0.2959, pruned_loss=0.05714, over 1413892.92 frames.], batch size: 31, lr: 8.20e-04
2022-04-28 21:31:14,877 INFO [train.py:763] (4/8) Epoch 8, batch 3150, loss[loss=0.207, simple_loss=0.3135, pruned_loss=0.05024, over 7156.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2947, pruned_loss=0.05634, over 1417621.76 frames.], batch size: 19, lr: 8.20e-04
2022-04-28 21:32:20,532 INFO [train.py:763] (4/8) Epoch 8, batch 3200, loss[loss=0.2117, simple_loss=0.3178, pruned_loss=0.05277, over 7143.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2942, pruned_loss=0.05581, over 1421462.82 frames.], batch size: 20, lr: 8.19e-04
2022-04-28 21:33:34,630 INFO [train.py:763] (4/8) Epoch 8, batch 3250, loss[loss=0.2619, simple_loss=0.3387, pruned_loss=0.09252, over 5277.00 frames.], tot_loss[loss=0.204, simple_loss=0.2951, pruned_loss=0.05647, over 1420119.28 frames.], batch size: 53, lr: 8.19e-04
2022-04-28 21:34:51,670 INFO [train.py:763] (4/8) Epoch 8, batch 3300, loss[loss=0.2084, simple_loss=0.2971, pruned_loss=0.05985, over 7197.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2938, pruned_loss=0.05601, over 1419923.28 frames.], batch size: 22, lr: 8.18e-04
2022-04-28 21:36:05,887 INFO [train.py:763] (4/8) Epoch 8, batch 3350, loss[loss=0.1561, simple_loss=0.2573, pruned_loss=0.02747, over 7249.00 frames.], tot_loss[loss=0.202, simple_loss=0.2931, pruned_loss=0.0554, over 1423640.10 frames.], batch size: 19, lr: 8.18e-04
2022-04-28 21:37:39,077 INFO [train.py:763] (4/8) Epoch 8, batch 3400, loss[loss=0.1993, simple_loss=0.2988, pruned_loss=0.04993, over 6866.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2927, pruned_loss=0.05486, over 1422450.78 frames.], batch size: 31, lr: 8.17e-04
2022-04-28 21:38:45,184 INFO [train.py:763] (4/8) Epoch 8, batch 3450, loss[loss=0.1747, simple_loss=0.2617, pruned_loss=0.04389, over 7408.00 frames.], tot_loss[loss=0.2017, simple_loss=0.293, pruned_loss=0.05517, over 1424936.70 frames.], batch size: 18, lr: 8.17e-04
2022-04-28 21:40:00,473 INFO [train.py:763] (4/8) Epoch 8, batch 3500, loss[loss=0.1973, simple_loss=0.2789, pruned_loss=0.05786, over 7165.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2928, pruned_loss=0.05512, over 1425238.30 frames.], batch size: 19, lr: 8.16e-04
2022-04-28 21:41:15,116 INFO [train.py:763] (4/8) Epoch 8, batch 3550, loss[loss=0.2164, simple_loss=0.2938, pruned_loss=0.0695, over 7171.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2923, pruned_loss=0.05506, over 1427241.98 frames.], batch size: 18, lr: 8.16e-04
2022-04-28 21:42:20,505 INFO [train.py:763] (4/8) Epoch 8, batch 3600, loss[loss=0.2058, simple_loss=0.2974, pruned_loss=0.05709, over 7277.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05589, over 1424235.00 frames.], batch size: 18, lr: 8.15e-04
2022-04-28 21:43:26,011 INFO [train.py:763] (4/8) Epoch 8, batch 3650, loss[loss=0.1976, simple_loss=0.2765, pruned_loss=0.0594, over 7123.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2928, pruned_loss=0.05583, over 1426195.78 frames.], batch size: 17, lr: 8.15e-04
2022-04-28 21:44:39,929 INFO [train.py:763] (4/8) Epoch 8, batch 3700, loss[loss=0.2257, simple_loss=0.3107, pruned_loss=0.0704, over 7308.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05589, over 1427011.20 frames.], batch size: 25, lr: 8.14e-04
2022-04-28 21:45:45,257 INFO [train.py:763] (4/8) Epoch 8, batch 3750, loss[loss=0.1902, simple_loss=0.2891, pruned_loss=0.04566, over 7429.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2937, pruned_loss=0.05577, over 1426120.58 frames.], batch size: 20, lr: 8.14e-04
2022-04-28 21:46:51,548 INFO [train.py:763] (4/8) Epoch 8, batch 3800, loss[loss=0.1669, simple_loss=0.2498, pruned_loss=0.04205, over 7401.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2942, pruned_loss=0.05607, over 1427658.77 frames.], batch size: 18, lr: 8.13e-04
2022-04-28 21:47:57,460 INFO [train.py:763] (4/8) Epoch 8, batch 3850, loss[loss=0.1945, simple_loss=0.2763, pruned_loss=0.05635, over 7284.00 frames.], tot_loss[loss=0.203, simple_loss=0.2938, pruned_loss=0.05605, over 1429720.97 frames.], batch size: 17, lr: 8.13e-04
2022-04-28 21:49:03,314 INFO [train.py:763] (4/8) Epoch 8, batch 3900, loss[loss=0.2319, simple_loss=0.3071, pruned_loss=0.07837, over 5051.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2946, pruned_loss=0.05636, over 1427297.21 frames.], batch size: 52, lr: 8.12e-04
2022-04-28 21:50:08,719 INFO [train.py:763] (4/8) Epoch 8, batch 3950, loss[loss=0.2078, simple_loss=0.3068, pruned_loss=0.05445, over 6796.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2928, pruned_loss=0.05522, over 1428821.58 frames.], batch size: 31, lr: 8.12e-04
2022-04-28 21:51:14,795 INFO [train.py:763] (4/8) Epoch 8, batch 4000, loss[loss=0.1969, simple_loss=0.3009, pruned_loss=0.04646, over 7225.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2944, pruned_loss=0.05636, over 1428289.55 frames.], batch size: 21, lr: 8.11e-04
2022-04-28 21:52:21,950 INFO [train.py:763] (4/8) Epoch 8, batch 4050, loss[loss=0.1845, simple_loss=0.2814, pruned_loss=0.04377, over 7410.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2932, pruned_loss=0.05603, over 1426841.28 frames.], batch size: 18, lr: 8.11e-04
2022-04-28 21:53:28,734 INFO [train.py:763] (4/8) Epoch 8, batch 4100, loss[loss=0.2151, simple_loss=0.2977, pruned_loss=0.06622, over 7125.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2931, pruned_loss=0.05563, over 1427601.99 frames.], batch size: 17, lr: 8.10e-04
2022-04-28 21:54:34,088 INFO [train.py:763] (4/8) Epoch 8, batch 4150, loss[loss=0.1881, simple_loss=0.2898, pruned_loss=0.0432, over 7125.00 frames.], tot_loss[loss=0.202, simple_loss=0.2927, pruned_loss=0.05568, over 1422521.92 frames.], batch size: 28, lr: 8.10e-04
2022-04-28 21:55:39,787 INFO [train.py:763] (4/8) Epoch 8, batch 4200, loss[loss=0.1745, simple_loss=0.2665, pruned_loss=0.04123, over 7324.00 frames.], tot_loss[loss=0.2011, simple_loss=0.2915, pruned_loss=0.05537, over 1423453.32 frames.], batch size: 20, lr: 8.09e-04
2022-04-28 21:56:45,194 INFO [train.py:763] (4/8) Epoch 8, batch 4250, loss[loss=0.1727, simple_loss=0.2681, pruned_loss=0.0386, over 7130.00 frames.], tot_loss[loss=0.2, simple_loss=0.2905, pruned_loss=0.05477, over 1419315.97 frames.], batch size: 17, lr: 8.09e-04
2022-04-28 21:57:50,930 INFO [train.py:763] (4/8) Epoch 8, batch 4300, loss[loss=0.2226, simple_loss=0.3198, pruned_loss=0.06275, over 7417.00 frames.], tot_loss[loss=0.2006, simple_loss=0.291, pruned_loss=0.0551, over 1414487.22 frames.], batch size: 21, lr: 8.08e-04
2022-04-28 21:58:56,620 INFO [train.py:763] (4/8) Epoch 8, batch 4350, loss[loss=0.1762, simple_loss=0.254, pruned_loss=0.04921, over 7287.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2902, pruned_loss=0.0543, over 1420358.19 frames.], batch size: 17, lr: 8.08e-04
2022-04-28 22:00:02,320 INFO [train.py:763] (4/8) Epoch 8, batch 4400, loss[loss=0.2035, simple_loss=0.301, pruned_loss=0.053, over 7042.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2902, pruned_loss=0.05429, over 1417097.00 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:01:09,618 INFO [train.py:763] (4/8) Epoch 8, batch 4450, loss[loss=0.2222, simple_loss=0.3203, pruned_loss=0.06208, over 7072.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2883, pruned_loss=0.05411, over 1412154.46 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:02:15,952 INFO [train.py:763] (4/8) Epoch 8, batch 4500, loss[loss=0.2069, simple_loss=0.3015, pruned_loss=0.05613, over 7092.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2901, pruned_loss=0.05589, over 1394504.40 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:03:19,877 INFO [train.py:763] (4/8) Epoch 8, batch 4550, loss[loss=0.1898, simple_loss=0.2947, pruned_loss=0.04248, over 6440.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2951, pruned_loss=0.05896, over 1353476.33 frames.], batch size: 38, lr: 8.06e-04
2022-04-28 22:04:39,796 INFO [train.py:763] (4/8) Epoch 9, batch 0, loss[loss=0.2213, simple_loss=0.3132, pruned_loss=0.06467, over 7410.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3132, pruned_loss=0.06467, over 7410.00 frames.], batch size: 21, lr: 7.75e-04
2022-04-28 22:05:45,910 INFO [train.py:763] (4/8) Epoch 9, batch 50, loss[loss=0.2361, simple_loss=0.3146, pruned_loss=0.07877, over 7214.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05622, over 321619.37 frames.], batch size: 23, lr: 7.74e-04
2022-04-28 22:06:51,596 INFO [train.py:763] (4/8) Epoch 9, batch 100, loss[loss=0.2494, simple_loss=0.3197, pruned_loss=0.0895, over 5232.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2925, pruned_loss=0.05622, over 557011.48 frames.], batch size: 52, lr: 7.74e-04
2022-04-28 22:07:57,278 INFO [train.py:763] (4/8) Epoch 9, batch 150, loss[loss=0.188, simple_loss=0.2867, pruned_loss=0.04463, over 7431.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2917, pruned_loss=0.05467, over 750390.68 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:09:03,713 INFO [train.py:763] (4/8) Epoch 9, batch 200, loss[loss=0.1968, simple_loss=0.2862, pruned_loss=0.05364, over 7427.00 frames.], tot_loss[loss=0.201, simple_loss=0.2921, pruned_loss=0.05489, over 897735.32 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:10:10,397 INFO [train.py:763] (4/8) Epoch 9, batch 250, loss[loss=0.2218, simple_loss=0.308, pruned_loss=0.06783, over 7168.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2925, pruned_loss=0.05448, over 1009451.69 frames.], batch size: 18, lr: 7.72e-04
2022-04-28 22:11:16,227 INFO [train.py:763] (4/8) Epoch 9, batch 300, loss[loss=0.2019, simple_loss=0.2923, pruned_loss=0.05575, over 7331.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2909, pruned_loss=0.05432, over 1103084.20 frames.], batch size: 20, lr: 7.72e-04
2022-04-28 22:12:21,601 INFO [train.py:763] (4/8) Epoch 9, batch 350, loss[loss=0.2468, simple_loss=0.3191, pruned_loss=0.08722, over 7188.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2912, pruned_loss=0.05397, over 1170886.42 frames.], batch size: 23, lr: 7.71e-04
2022-04-28 22:13:26,943 INFO [train.py:763] (4/8) Epoch 9, batch 400, loss[loss=0.2382, simple_loss=0.3224, pruned_loss=0.07705, over 7138.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2924, pruned_loss=0.05449, over 1221929.79 frames.], batch size: 26, lr: 7.71e-04
2022-04-28 22:14:32,124 INFO [train.py:763] (4/8) Epoch 9, batch 450, loss[loss=0.1809, simple_loss=0.2769, pruned_loss=0.0425, over 6372.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2926, pruned_loss=0.05412, over 1260742.65 frames.], batch size: 37, lr: 7.71e-04
2022-04-28 22:15:37,755 INFO [train.py:763] (4/8) Epoch 9, batch 500, loss[loss=0.2056, simple_loss=0.2822, pruned_loss=0.06446, over 7159.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2927, pruned_loss=0.05439, over 1296029.20 frames.], batch size: 19, lr: 7.70e-04
2022-04-28 22:16:43,391 INFO [train.py:763] (4/8) Epoch 9, batch 550, loss[loss=0.1656, simple_loss=0.2527, pruned_loss=0.03929, over 7133.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2914, pruned_loss=0.05385, over 1323470.23 frames.], batch size: 17, lr: 7.70e-04
2022-04-28 22:17:49,457 INFO [train.py:763] (4/8) Epoch 9, batch 600, loss[loss=0.1634, simple_loss=0.2619, pruned_loss=0.03244, over 7281.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2912, pruned_loss=0.05379, over 1344828.58 frames.], batch size: 18, lr: 7.69e-04
2022-04-28 22:18:54,912 INFO [train.py:763] (4/8) Epoch 9, batch 650, loss[loss=0.2195, simple_loss=0.3117, pruned_loss=0.06363, over 7123.00 frames.], tot_loss[loss=0.1994, simple_loss=0.291, pruned_loss=0.05389, over 1361178.42 frames.], batch size: 26, lr: 7.69e-04
2022-04-28 22:20:00,484 INFO [train.py:763] (4/8) Epoch 9, batch 700, loss[loss=0.2314, simple_loss=0.3182, pruned_loss=0.07234, over 7291.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2904, pruned_loss=0.05353, over 1375986.98 frames.], batch size: 25, lr: 7.68e-04
2022-04-28 22:21:06,840 INFO [train.py:763] (4/8) Epoch 9, batch 750, loss[loss=0.1843, simple_loss=0.2851, pruned_loss=0.04176, over 7432.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2911, pruned_loss=0.05412, over 1385986.28 frames.], batch size: 20, lr: 7.68e-04
2022-04-28 22:22:12,197 INFO [train.py:763] (4/8) Epoch 9, batch 800, loss[loss=0.2144, simple_loss=0.3115, pruned_loss=0.05862, over 7288.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2902, pruned_loss=0.05344, over 1393604.51 frames.], batch size: 24, lr: 7.67e-04
2022-04-28 22:23:17,412 INFO [train.py:763] (4/8) Epoch 9, batch 850, loss[loss=0.2146, simple_loss=0.3059, pruned_loss=0.06165, over 6353.00 frames.], tot_loss[loss=0.2, simple_loss=0.2921, pruned_loss=0.05399, over 1396472.64 frames.], batch size: 38, lr: 7.67e-04
2022-04-28 22:24:22,755 INFO [train.py:763] (4/8) Epoch 9, batch 900, loss[loss=0.194, simple_loss=0.2899, pruned_loss=0.04903, over 7311.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2921, pruned_loss=0.054, over 1406044.25 frames.], batch size: 21, lr: 7.66e-04
2022-04-28 22:25:27,953 INFO [train.py:763] (4/8) Epoch 9, batch 950, loss[loss=0.1894, simple_loss=0.2821, pruned_loss=0.04838, over 7187.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2924, pruned_loss=0.05425, over 1405984.03 frames.], batch size: 26, lr: 7.66e-04
2022-04-28 22:26:33,997 INFO [train.py:763] (4/8) Epoch 9, batch 1000, loss[loss=0.1838, simple_loss=0.2945, pruned_loss=0.03655, over 7319.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2913, pruned_loss=0.05328, over 1414320.56 frames.], batch size: 20, lr: 7.66e-04
2022-04-28 22:27:40,362 INFO [train.py:763] (4/8) Epoch 9, batch 1050, loss[loss=0.1961, simple_loss=0.2971, pruned_loss=0.04749, over 7053.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2907, pruned_loss=0.05321, over 1416606.26 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:28:46,000 INFO [train.py:763] (4/8) Epoch 9, batch 1100, loss[loss=0.2058, simple_loss=0.3001, pruned_loss=0.05578, over 7032.00 frames.], tot_loss[loss=0.2001, simple_loss=0.292, pruned_loss=0.05406, over 1416913.24 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:29:52,328 INFO [train.py:763] (4/8) Epoch 9, batch 1150, loss[loss=0.1971, simple_loss=0.2883, pruned_loss=0.05291, over 7334.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2916, pruned_loss=0.05375, over 1421597.30 frames.], batch size: 20, lr: 7.64e-04
2022-04-28 22:30:57,645 INFO [train.py:763] (4/8) Epoch 9, batch 1200, loss[loss=0.2232, simple_loss=0.3138, pruned_loss=0.06629, over 7203.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2923, pruned_loss=0.05433, over 1420051.97 frames.], batch size: 23, lr: 7.64e-04
2022-04-28 22:32:04,403 INFO [train.py:763] (4/8) Epoch 9, batch 1250, loss[loss=0.1672, simple_loss=0.2566, pruned_loss=0.03886, over 7274.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2917, pruned_loss=0.05402, over 1418712.76 frames.], batch size: 17, lr: 7.63e-04
2022-04-28 22:33:11,154 INFO [train.py:763] (4/8) Epoch 9, batch 1300, loss[loss=0.166, simple_loss=0.2513, pruned_loss=0.04033, over 7010.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2911, pruned_loss=0.05416, over 1416504.70 frames.], batch size: 16, lr: 7.63e-04
2022-04-28 22:34:16,570 INFO [train.py:763] (4/8) Epoch 9, batch 1350, loss[loss=0.2055, simple_loss=0.2983, pruned_loss=0.05633, over 7323.00 frames.], tot_loss[loss=0.201, simple_loss=0.2921, pruned_loss=0.05496, over 1414087.28 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:35:21,674 INFO [train.py:763] (4/8) Epoch 9, batch 1400, loss[loss=0.2341, simple_loss=0.3256, pruned_loss=0.07132, over 7130.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2923, pruned_loss=0.05471, over 1417469.89 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:36:27,458 INFO [train.py:763] (4/8) Epoch 9, batch 1450, loss[loss=0.236, simple_loss=0.3228, pruned_loss=0.07459, over 7316.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2914, pruned_loss=0.05396, over 1418729.52 frames.], batch size: 25, lr: 7.62e-04
2022-04-28 22:37:33,359 INFO [train.py:763] (4/8) Epoch 9, batch 1500, loss[loss=0.2299, simple_loss=0.3196, pruned_loss=0.0701, over 5001.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2922, pruned_loss=0.05431, over 1414753.01 frames.], batch size: 52, lr: 7.61e-04
2022-04-28 22:38:38,708 INFO [train.py:763] (4/8) Epoch 9, batch 1550, loss[loss=0.1902, simple_loss=0.2761, pruned_loss=0.05211, over 7354.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2915, pruned_loss=0.05396, over 1417882.27 frames.], batch size: 19, lr: 7.61e-04
2022-04-28 22:39:43,987 INFO [train.py:763] (4/8) Epoch 9, batch 1600, loss[loss=0.1847, simple_loss=0.2769, pruned_loss=0.04623, over 7249.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2901, pruned_loss=0.05337, over 1417310.94 frames.], batch size: 19, lr: 7.60e-04
2022-04-28 22:40:50,096 INFO [train.py:763] (4/8) Epoch 9, batch 1650, loss[loss=0.2219, simple_loss=0.3191, pruned_loss=0.06232, over 7403.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2901, pruned_loss=0.05376, over 1415805.28 frames.], batch size: 21, lr: 7.60e-04
2022-04-28 22:41:56,340 INFO [train.py:763] (4/8) Epoch 9, batch 1700, loss[loss=0.2111, simple_loss=0.302, pruned_loss=0.06008, over 7276.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2897, pruned_loss=0.05348, over 1414423.48 frames.], batch size: 24, lr: 7.59e-04
2022-04-28 22:43:01,518 INFO [train.py:763] (4/8) Epoch 9, batch 1750, loss[loss=0.1988, simple_loss=0.2724, pruned_loss=0.06258, over 7242.00 frames.], tot_loss[loss=0.2003, simple_loss=0.2914, pruned_loss=0.05465, over 1406717.54 frames.], batch size: 16, lr: 7.59e-04
2022-04-28 22:44:07,085 INFO [train.py:763] (4/8) Epoch 9, batch 1800, loss[loss=0.1859, simple_loss=0.2872, pruned_loss=0.04235, over 7354.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2911, pruned_loss=0.05435, over 1411207.10 frames.], batch size: 19, lr: 7.59e-04
2022-04-28 22:45:14,102 INFO [train.py:763] (4/8) Epoch 9, batch 1850, loss[loss=0.2048, simple_loss=0.2871, pruned_loss=0.0612, over 7362.00 frames.], tot_loss[loss=0.201, simple_loss=0.2923, pruned_loss=0.05483, over 1411991.15 frames.], batch size: 19, lr: 7.58e-04
2022-04-28 22:46:21,652 INFO [train.py:763] (4/8) Epoch 9, batch 1900, loss[loss=0.174, simple_loss=0.2605, pruned_loss=0.04378, over 7283.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2916, pruned_loss=0.05433, over 1416630.29 frames.], batch size: 18, lr: 7.58e-04
2022-04-28 22:47:28,652 INFO [train.py:763] (4/8) Epoch 9, batch 1950, loss[loss=0.2182, simple_loss=0.3158, pruned_loss=0.06029, over 7210.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2901, pruned_loss=0.05352, over 1415959.84 frames.], batch size: 23, lr: 7.57e-04
2022-04-28 22:48:34,054 INFO [train.py:763] (4/8) Epoch 9, batch 2000, loss[loss=0.1891, simple_loss=0.2875, pruned_loss=0.04533, over 7242.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2895, pruned_loss=0.05287, over 1418629.09 frames.], batch size: 20, lr: 7.57e-04
2022-04-28 22:49:39,698 INFO [train.py:763] (4/8) Epoch 9, batch 2050, loss[loss=0.179, simple_loss=0.2812, pruned_loss=0.03838, over 7198.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2887, pruned_loss=0.0524, over 1420473.05 frames.], batch size: 23, lr: 7.56e-04
2022-04-28 22:50:45,162 INFO [train.py:763] (4/8) Epoch 9, batch 2100, loss[loss=0.2071, simple_loss=0.3083, pruned_loss=0.05294, over 7143.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2888, pruned_loss=0.05218, over 1424912.94 frames.], batch size: 20, lr: 7.56e-04
2022-04-28 22:51:50,834 INFO [train.py:763] (4/8) Epoch 9, batch 2150, loss[loss=0.1557, simple_loss=0.2463, pruned_loss=0.03256, over 7419.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2886, pruned_loss=0.05206, over 1427242.57 frames.], batch size: 18, lr: 7.56e-04
2022-04-28 22:52:56,056 INFO [train.py:763] (4/8) Epoch 9, batch 2200, loss[loss=0.1957, simple_loss=0.2849, pruned_loss=0.05323, over 6527.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2891, pruned_loss=0.05202, over 1426952.54 frames.], batch size: 38, lr: 7.55e-04
2022-04-28 22:54:01,585 INFO [train.py:763] (4/8) Epoch 9, batch 2250, loss[loss=0.2099, simple_loss=0.3057, pruned_loss=0.05708, over 7319.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2887, pruned_loss=0.05208, over 1428531.78 frames.], batch size: 21, lr: 7.55e-04
2022-04-28 22:55:07,217 INFO [train.py:763] (4/8) Epoch 9, batch 2300, loss[loss=0.1933, simple_loss=0.2972, pruned_loss=0.04466, over 7146.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2895, pruned_loss=0.0526, over 1426467.59 frames.], batch size: 20, lr: 7.54e-04
2022-04-28 22:56:13,145 INFO [train.py:763] (4/8) Epoch 9, batch 2350, loss[loss=0.2129, simple_loss=0.308, pruned_loss=0.05885, over 7199.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2889, pruned_loss=0.05262, over 1424686.36 frames.], batch size: 22, lr: 7.54e-04
2022-04-28 22:57:18,360 INFO [train.py:763] (4/8) Epoch 9, batch 2400, loss[loss=0.1817, simple_loss=0.2802, pruned_loss=0.04156, over 7277.00 frames.], tot_loss[loss=0.1973, simple_loss=0.289, pruned_loss=0.05273, over 1426506.83 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:58:24,893 INFO [train.py:763] (4/8) Epoch 9, batch 2450, loss[loss=0.1553, simple_loss=0.2464, pruned_loss=0.0321, over 7062.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2887, pruned_loss=0.05291, over 1430241.26 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:59:30,586 INFO [train.py:763] (4/8) Epoch 9, batch 2500, loss[loss=0.2132, simple_loss=0.3117, pruned_loss=0.05732, over 7323.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2884, pruned_loss=0.05248, over 1428515.23 frames.], batch size: 21, lr: 7.53e-04
2022-04-28 23:00:35,847 INFO [train.py:763] (4/8) Epoch 9, batch 2550, loss[loss=0.2136, simple_loss=0.3099, pruned_loss=0.05871, over 7227.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2889, pruned_loss=0.05275, over 1426040.63 frames.], batch size: 21, lr: 7.52e-04
2022-04-28 23:01:42,060 INFO [train.py:763] (4/8) Epoch 9, batch 2600, loss[loss=0.2016, simple_loss=0.3, pruned_loss=0.05163, over 7159.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2884, pruned_loss=0.05253, over 1429133.80 frames.], batch size: 26, lr: 7.52e-04
2022-04-28 23:02:47,158 INFO [train.py:763] (4/8) Epoch 9, batch 2650, loss[loss=0.1841, simple_loss=0.2912, pruned_loss=0.03853, over 7333.00 frames.], tot_loss[loss=0.197, simple_loss=0.289, pruned_loss=0.05248, over 1425088.28 frames.], batch size: 22, lr: 7.51e-04
2022-04-28 23:03:53,443 INFO [train.py:763] (4/8) Epoch 9, batch 2700, loss[loss=0.2023, simple_loss=0.3085, pruned_loss=0.04807, over 6773.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2881, pruned_loss=0.05202, over 1425021.62 frames.], batch size: 31, lr: 7.51e-04
2022-04-28 23:04:58,882 INFO [train.py:763] (4/8) Epoch 9, batch 2750, loss[loss=0.1679, simple_loss=0.2679, pruned_loss=0.03399, over 6744.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2875, pruned_loss=0.05206, over 1422450.12 frames.], batch size: 31, lr: 7.50e-04
2022-04-28 23:06:04,503 INFO [train.py:763] (4/8) Epoch 9, batch 2800, loss[loss=0.1948, simple_loss=0.282, pruned_loss=0.05379, over 7379.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2876, pruned_loss=0.05169, over 1427779.21 frames.], batch size: 23, lr: 7.50e-04
2022-04-28 23:07:09,869 INFO [train.py:763] (4/8) Epoch 9, batch 2850, loss[loss=0.2413, simple_loss=0.3316, pruned_loss=0.0755, over 7325.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2875, pruned_loss=0.05176, over 1425753.02 frames.], batch size: 22, lr: 7.50e-04
2022-04-28 23:08:15,553 INFO [train.py:763] (4/8) Epoch 9, batch 2900, loss[loss=0.2072, simple_loss=0.2983, pruned_loss=0.05801, over 7109.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2883, pruned_loss=0.05252, over 1425356.92 frames.], batch size: 21, lr: 7.49e-04
2022-04-28 23:09:22,016 INFO [train.py:763] (4/8) Epoch 9, batch 2950, loss[loss=0.1968, simple_loss=0.2759, pruned_loss=0.0589, over 7279.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2888, pruned_loss=0.05292, over 1425781.90 frames.], batch size: 18, lr: 7.49e-04
2022-04-28 23:10:28,989 INFO [train.py:763] (4/8) Epoch 9, batch 3000, loss[loss=0.1788, simple_loss=0.2608, pruned_loss=0.04842, over 7277.00 frames.], tot_loss[loss=0.197, simple_loss=0.2883, pruned_loss=0.05286, over 1425435.48 frames.], batch size: 17, lr: 7.48e-04
2022-04-28 23:10:28,990 INFO [train.py:783] (4/8) Computing validation loss
2022-04-28 23:10:44,551 INFO [train.py:792] (4/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 23:11:50,374 INFO [train.py:763] (4/8) Epoch 9, batch 3050, loss[loss=0.172, simple_loss=0.2719, pruned_loss=0.03605, over 7161.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2885, pruned_loss=0.05271, over 1425302.85 frames.], batch size: 19, lr: 7.48e-04
2022-04-28 23:12:55,854 INFO [train.py:763] (4/8) Epoch 9, batch 3100, loss[loss=0.2048, simple_loss=0.3093, pruned_loss=0.0502, over 7122.00 frames.], tot_loss[loss=0.197, simple_loss=0.2888, pruned_loss=0.05264, over 1428461.20 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:14:01,343 INFO [train.py:763] (4/8) Epoch 9, batch 3150, loss[loss=0.2104, simple_loss=0.3048, pruned_loss=0.058, over 7314.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2875, pruned_loss=0.05187, over 1424559.92 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:15:07,615 INFO [train.py:763] (4/8) Epoch 9, batch 3200, loss[loss=0.1901, simple_loss=0.2892, pruned_loss=0.04548, over 7232.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2861, pruned_loss=0.05101, over 1424387.77 frames.], batch size: 20, lr: 7.47e-04
2022-04-28 23:16:13,884 INFO [train.py:763] (4/8) Epoch 9, batch 3250, loss[loss=0.2173, simple_loss=0.3091, pruned_loss=0.0627, over 7405.00 frames.], tot_loss[loss=0.195, simple_loss=0.2871, pruned_loss=0.05144, over 1424704.51 frames.], batch size: 21, lr: 7.46e-04
2022-04-28 23:17:19,390 INFO [train.py:763] (4/8) Epoch 9, batch 3300, loss[loss=0.2151, simple_loss=0.3079, pruned_loss=0.0612, over 7202.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2871, pruned_loss=0.05187, over 1425534.36 frames.], batch size: 22, lr: 7.46e-04
2022-04-28 23:18:25,152 INFO [train.py:763] (4/8) Epoch 9, batch 3350, loss[loss=0.2094, simple_loss=0.2972, pruned_loss=0.06079, over 7186.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2875, pruned_loss=0.05191, over 1426989.32 frames.], batch size: 23, lr: 7.45e-04
2022-04-28 23:19:31,232 INFO [train.py:763] (4/8) Epoch 9, batch 3400, loss[loss=0.1381, simple_loss=0.2336, pruned_loss=0.02131, over 7286.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2878, pruned_loss=0.0519, over 1423012.60 frames.], batch size: 17, lr: 7.45e-04
2022-04-28 23:20:36,536 INFO [train.py:763] (4/8) Epoch 9, batch 3450, loss[loss=0.2089, simple_loss=0.3041, pruned_loss=0.05684, over 7300.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2882, pruned_loss=0.05228, over 1422126.72 frames.], batch size: 24, lr: 7.45e-04
2022-04-28 23:21:42,129 INFO [train.py:763] (4/8) Epoch 9, batch 3500, loss[loss=0.1817, simple_loss=0.2777, pruned_loss=0.04284, over 7418.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2887, pruned_loss=0.05226, over 1422139.48 frames.], batch size: 21, lr: 7.44e-04
2022-04-28 23:22:49,851 INFO [train.py:763] (4/8) Epoch 9, batch 3550, loss[loss=0.2157, simple_loss=0.3038, pruned_loss=0.06375, over 7072.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2869, pruned_loss=0.05142, over 1425469.34 frames.], batch size: 28, lr: 7.44e-04
2022-04-28 23:23:55,515 INFO [train.py:763] (4/8) Epoch 9, batch 3600, loss[loss=0.2156, simple_loss=0.3173, pruned_loss=0.05698, over 7071.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2874, pruned_loss=0.05153, over 1425913.84 frames.], batch size: 28, lr: 7.43e-04
2022-04-28 23:25:02,070 INFO [train.py:763] (4/8) Epoch 9, batch 3650, loss[loss=0.2032, simple_loss=0.2988, pruned_loss=0.0538, over 7063.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2884, pruned_loss=0.05212, over 1422697.81 frames.], batch size: 18, lr: 7.43e-04
2022-04-28 23:26:07,305 INFO [train.py:763] (4/8) Epoch 9, batch 3700, loss[loss=0.1507, simple_loss=0.2411, pruned_loss=0.0302, over 7268.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2883, pruned_loss=0.05168, over 1425652.83 frames.], batch size: 17, lr: 7.43e-04
2022-04-28 23:27:12,603 INFO [train.py:763] (4/8) Epoch 9, batch 3750, loss[loss=0.2916, simple_loss=0.3273, pruned_loss=0.1279, over 7162.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2903, pruned_loss=0.05276, over 1427676.42 frames.], batch size: 19, lr: 7.42e-04
2022-04-28 23:28:17,822 INFO [train.py:763] (4/8) Epoch 9, batch 3800, loss[loss=0.2006, simple_loss=0.2862, pruned_loss=0.05749, over 7420.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2901, pruned_loss=0.05277, over 1426289.31 frames.], batch size: 20, lr: 7.42e-04
2022-04-28 23:29:23,008 INFO [train.py:763] (4/8) Epoch 9, batch 3850, loss[loss=0.167, simple_loss=0.2515, pruned_loss=0.04131, over 7064.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2904, pruned_loss=0.05256, over 1425233.95 frames.], batch size: 18, lr: 7.41e-04
2022-04-28 23:30:28,552 INFO [train.py:763] (4/8) Epoch 9, batch 3900, loss[loss=0.2234, simple_loss=0.3104, pruned_loss=0.06823, over 7161.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2903, pruned_loss=0.05292, over 1426863.77 frames.], batch size: 19, lr: 7.41e-04
2022-04-28 23:31:35,175 INFO [train.py:763] (4/8) Epoch 9, batch 3950, loss[loss=0.2188, simple_loss=0.2962, pruned_loss=0.07072, over 5355.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2906, pruned_loss=0.053, over 1421246.08 frames.], batch size: 52, lr: 7.41e-04
2022-04-28 23:32:42,032 INFO [train.py:763] (4/8) Epoch 9, batch 4000, loss[loss=0.1994, simple_loss=0.2885, pruned_loss=0.0551, over 7270.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2903, pruned_loss=0.05311, over 1422443.64 frames.], batch size: 19, lr: 7.40e-04
2022-04-28 23:33:47,286 INFO [train.py:763] (4/8) Epoch 9, batch 4050, loss[loss=0.1986, simple_loss=0.2904, pruned_loss=0.05337, over 7134.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2897, pruned_loss=0.05268, over 1422797.34 frames.], batch size: 17, lr: 7.40e-04
2022-04-28 23:34:53,525 INFO [train.py:763] (4/8) Epoch 9, batch 4100, loss[loss=0.1776, simple_loss=0.2832, pruned_loss=0.03599, over 7317.00 frames.], tot_loss[loss=0.1967, simple_loss=0.289, pruned_loss=0.05218, over 1425517.15 frames.], batch size: 21, lr: 7.39e-04
2022-04-28 23:35:59,480 INFO [train.py:763] (4/8) Epoch 9, batch 4150, loss[loss=0.1721, simple_loss=0.2636, pruned_loss=0.04027, over 7409.00 frames.], tot_loss[loss=0.197, simple_loss=0.2891, pruned_loss=0.05247, over 1425898.91 frames.], batch size: 18, lr: 7.39e-04
2022-04-28 23:37:04,697 INFO [train.py:763] (4/8) Epoch 9, batch 4200, loss[loss=0.1889, simple_loss=0.2778, pruned_loss=0.04998, over 7280.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2894, pruned_loss=0.05239, over 1427851.91 frames.], batch size: 24, lr: 7.39e-04
2022-04-28 23:38:10,554 INFO [train.py:763] (4/8) Epoch 9, batch 4250, loss[loss=0.1746, simple_loss=0.2742, pruned_loss=0.03751, over 7268.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2898, pruned_loss=0.0527, over 1423059.33 frames.], batch size: 17, lr: 7.38e-04
2022-04-28 23:39:16,463 INFO [train.py:763] (4/8) Epoch 9, batch 4300, loss[loss=0.1792, simple_loss=0.2829, pruned_loss=0.03778, over 7290.00 frames.], tot_loss[loss=0.1977, simple_loss=0.29, pruned_loss=0.05265, over 1418228.50 frames.], batch size: 24, lr: 7.38e-04
2022-04-28 23:40:22,451 INFO [train.py:763] (4/8) Epoch 9, batch 4350, loss[loss=0.2165, simple_loss=0.3027, pruned_loss=0.06513, over 4965.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2912, pruned_loss=0.05314, over 1408601.36 frames.], batch size: 52, lr: 7.37e-04
2022-04-28 23:41:28,472 INFO [train.py:763] (4/8) Epoch 9, batch 4400, loss[loss=0.2002, simple_loss=0.3014, pruned_loss=0.04948, over 7197.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2922, pruned_loss=0.05365, over 1410682.66 frames.], batch size: 22, lr: 7.37e-04
2022-04-28 23:42:35,220 INFO [train.py:763] (4/8) Epoch 9, batch 4450, loss[loss=0.2557, simple_loss=0.3344, pruned_loss=0.08856, over 5227.00 frames.], tot_loss[loss=0.2004, simple_loss=0.2924, pruned_loss=0.0542, over 1396824.56 frames.], batch size: 52, lr: 7.37e-04
2022-04-28 23:43:41,391 INFO [train.py:763] (4/8) Epoch 9, batch 4500, loss[loss=0.2126, simple_loss=0.3092, pruned_loss=0.05802, over 7134.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2916, pruned_loss=0.05391, over 1393975.07 frames.], batch size: 20, lr: 7.36e-04
2022-04-28 23:44:47,990 INFO [train.py:763] (4/8) Epoch 9, batch 4550, loss[loss=0.1871, simple_loss=0.2878, pruned_loss=0.0432, over 7144.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2919, pruned_loss=0.05493, over 1374738.67 frames.], batch size: 26, lr: 7.36e-04
2022-04-28 23:46:26,278 INFO [train.py:763] (4/8) Epoch 10, batch 0, loss[loss=0.2175, simple_loss=0.303, pruned_loss=0.06599, over 7420.00 frames.], tot_loss[loss=0.2175, simple_loss=0.303, pruned_loss=0.06599, over 7420.00 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:47:32,323 INFO [train.py:763] (4/8) Epoch 10, batch 50, loss[loss=0.1962, simple_loss=0.286, pruned_loss=0.05324, over 7420.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2895, pruned_loss=0.04875, over 322854.97 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:48:38,907 INFO [train.py:763] (4/8) Epoch 10, batch 100, loss[loss=0.1684, simple_loss=0.2522, pruned_loss=0.04233, over 7280.00 frames.], tot_loss[loss=0.1947, simple_loss=0.289, pruned_loss=0.05024, over 567328.36 frames.], batch size: 18, lr: 7.08e-04
2022-04-28 23:49:55,132 INFO [train.py:763] (4/8) Epoch 10, batch 150, loss[loss=0.1982, simple_loss=0.2792, pruned_loss=0.05862, over 7188.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2905, pruned_loss=0.05047, over 760584.06 frames.], batch size: 16, lr: 7.07e-04
2022-04-28 23:51:18,545 INFO [train.py:763] (4/8) Epoch 10, batch 200, loss[loss=0.177, simple_loss=0.2637, pruned_loss=0.04515, over 7389.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2899, pruned_loss=0.0505, over 907834.61 frames.], batch size: 18, lr: 7.07e-04
2022-04-28 23:52:32,862 INFO [train.py:763] (4/8) Epoch 10, batch 250, loss[loss=0.2197, simple_loss=0.3112, pruned_loss=0.06406, over 6429.00 frames.], tot_loss[loss=0.1948, simple_loss=0.289, pruned_loss=0.0503, over 1023487.97 frames.], batch size: 38, lr: 7.06e-04
2022-04-28 23:53:48,224 INFO [train.py:763] (4/8) Epoch 10, batch 300, loss[loss=0.2272, simple_loss=0.3082, pruned_loss=0.07304, over 4995.00 frames.], tot_loss[loss=0.194, simple_loss=0.2876, pruned_loss=0.0502, over 1114558.63 frames.], batch size: 53, lr: 7.06e-04
2022-04-28 23:54:53,615 INFO [train.py:763] (4/8) Epoch 10, batch 350, loss[loss=0.2268, simple_loss=0.3133, pruned_loss=0.07011, over 6771.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2872, pruned_loss=0.05019, over 1187063.60 frames.], batch size: 31, lr: 7.06e-04
2022-04-28 23:56:17,499 INFO [train.py:763] (4/8) Epoch 10, batch 400, loss[loss=0.2031, simple_loss=0.2927, pruned_loss=0.05673, over 7429.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2882, pruned_loss=0.05082, over 1240532.39 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:57:23,251 INFO [train.py:763] (4/8) Epoch 10, batch 450, loss[loss=0.1995, simple_loss=0.302, pruned_loss=0.04854, over 7230.00 frames.], tot_loss[loss=0.194, simple_loss=0.2871, pruned_loss=0.05043, over 1280448.46 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:58:37,637 INFO [train.py:763] (4/8) Epoch 10, batch 500, loss[loss=0.2186, simple_loss=0.3043, pruned_loss=0.06651, over 7320.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2864, pruned_loss=0.05015, over 1315082.22 frames.], batch size: 20, lr: 7.04e-04
2022-04-28 23:59:42,723 INFO [train.py:763] (4/8) Epoch 10, batch 550, loss[loss=0.1762, simple_loss=0.2729, pruned_loss=0.03978, over 7447.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2875, pruned_loss=0.05045, over 1340256.00 frames.], batch size: 19, lr: 7.04e-04
2022-04-29 00:00:47,810 INFO [train.py:763] (4/8) Epoch 10, batch 600, loss[loss=0.1787, simple_loss=0.261, pruned_loss=0.04827, over 6998.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2873, pruned_loss=0.05072, over 1359435.82 frames.], batch size: 16, lr: 7.04e-04
2022-04-29 00:01:53,005 INFO [train.py:763] (4/8) Epoch 10, batch 650, loss[loss=0.1545, simple_loss=0.2431, pruned_loss=0.03295, over 7137.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2876, pruned_loss=0.0513, over 1364748.46 frames.], batch size: 17, lr: 7.03e-04
2022-04-29 00:02:58,035 INFO [train.py:763] (4/8) Epoch 10, batch 700, loss[loss=0.1604, simple_loss=0.2464, pruned_loss=0.0372, over 6755.00 frames.], tot_loss[loss=0.1963, simple_loss=0.2893, pruned_loss=0.05168, over 1374732.15 frames.], batch size: 15, lr: 7.03e-04
2022-04-29 00:04:03,193 INFO [train.py:763] (4/8) Epoch 10, batch 750, loss[loss=0.1828, simple_loss=0.2813, pruned_loss=0.0422, over 7150.00 frames.], tot_loss[loss=0.1947, simple_loss=0.288, pruned_loss=0.05075, over 1382012.62 frames.], batch size: 20, lr: 7.03e-04
2022-04-29 00:05:08,475 INFO [train.py:763] (4/8) Epoch 10, batch 800, loss[loss=0.199, simple_loss=0.2954, pruned_loss=0.05134, over 7189.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2873, pruned_loss=0.05059, over 1393662.39 frames.], batch size: 26, lr: 7.02e-04
2022-04-29 00:06:13,823 INFO [train.py:763] (4/8) Epoch 10, batch 850, loss[loss=0.1758, simple_loss=0.2741, pruned_loss=0.03872, over 7324.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2873, pruned_loss=0.05075, over 1398369.58 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:07:19,241 INFO [train.py:763] (4/8) Epoch 10, batch 900, loss[loss=0.1631, simple_loss=0.2584, pruned_loss=0.03384, over 7418.00 frames.], tot_loss[loss=0.194, simple_loss=0.2868, pruned_loss=0.05055, over 1406957.99 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:08:24,539 INFO [train.py:763] (4/8) Epoch 10, batch 950, loss[loss=0.1862, simple_loss=0.2644, pruned_loss=0.05403, over 7007.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2875, pruned_loss=0.05107, over 1409752.48 frames.], batch size: 16, lr: 7.01e-04
2022-04-29 00:09:29,918 INFO [train.py:763] (4/8) Epoch 10, batch 1000, loss[loss=0.2071, simple_loss=0.3059, pruned_loss=0.05411, over 7277.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2882, pruned_loss=0.05141, over 1413522.54 frames.], batch size: 25, lr: 7.01e-04
2022-04-29 00:10:35,516 INFO [train.py:763] (4/8) Epoch 10, batch 1050, loss[loss=0.1909, simple_loss=0.2811, pruned_loss=0.05034, over 7274.00 frames.], tot_loss[loss=0.1962, simple_loss=0.289, pruned_loss=0.05165, over 1408893.27 frames.], batch size: 19, lr: 7.00e-04
2022-04-29 00:11:41,109 INFO [train.py:763] (4/8) Epoch 10, batch 1100, loss[loss=0.191, simple_loss=0.2825, pruned_loss=0.04979, over 7160.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2872, pruned_loss=0.05051, over 1413898.72 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:12:46,584 INFO [train.py:763] (4/8) Epoch 10, batch 1150, loss[loss=0.2026, simple_loss=0.2887, pruned_loss=0.05831, over 7067.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2864, pruned_loss=0.05039, over 1417853.18 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:13:53,258 INFO [train.py:763] (4/8) Epoch 10, batch 1200, loss[loss=0.1693, simple_loss=0.2627, pruned_loss=0.03792, over 7212.00 frames.], tot_loss[loss=0.192, simple_loss=0.2844, pruned_loss=0.04974, over 1420461.92 frames.], batch size: 16, lr: 6.99e-04
2022-04-29 00:14:58,978 INFO [train.py:763] (4/8) Epoch 10, batch 1250, loss[loss=0.1667, simple_loss=0.2567, pruned_loss=0.03831, over 7138.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2854, pruned_loss=0.05044, over 1424410.17 frames.], batch size: 17, lr: 6.99e-04
2022-04-29 00:16:04,761 INFO [train.py:763] (4/8) Epoch 10, batch 1300, loss[loss=0.1994, simple_loss=0.3053, pruned_loss=0.0468, over 7307.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2856, pruned_loss=0.0504, over 1421551.33 frames.], batch size: 21, lr: 6.99e-04
2022-04-29 00:17:11,804 INFO [train.py:763] (4/8) Epoch 10, batch 1350, loss[loss=0.1716, simple_loss=0.2692, pruned_loss=0.03703, over 7322.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2861, pruned_loss=0.05055, over 1425315.61 frames.], batch size: 21, lr: 6.98e-04
2022-04-29 00:18:18,354 INFO [train.py:763] (4/8) Epoch 10, batch 1400, loss[loss=0.1837, simple_loss=0.2756, pruned_loss=0.04592, over 7153.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2861, pruned_loss=0.05024, over 1427686.52 frames.], batch size: 19, lr: 6.98e-04
2022-04-29 00:19:25,279 INFO [train.py:763] (4/8) Epoch 10, batch 1450, loss[loss=0.1628, simple_loss=0.2546, pruned_loss=0.0355, over 7267.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2863, pruned_loss=0.05027, over 1428020.44 frames.], batch size: 17, lr: 6.97e-04
2022-04-29 00:20:30,749 INFO [train.py:763] (4/8) Epoch 10, batch 1500, loss[loss=0.1907, simple_loss=0.2884, pruned_loss=0.04646, over 7035.00 frames.], tot_loss[loss=0.1942, simple_loss=0.287, pruned_loss=0.05068, over 1426403.36 frames.], batch size: 28, lr: 6.97e-04
2022-04-29 00:21:36,428 INFO [train.py:763] (4/8) Epoch 10, batch 1550, loss[loss=0.2031, simple_loss=0.2938, pruned_loss=0.05621, over 7435.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2867, pruned_loss=0.05056, over 1424732.86 frames.], batch size: 20, lr: 6.97e-04
2022-04-29 00:22:41,606 INFO [train.py:763] (4/8) Epoch 10, batch 1600, loss[loss=0.2107, simple_loss=0.307, pruned_loss=0.05727, over 6740.00 frames.], tot_loss[loss=0.195, simple_loss=0.2874, pruned_loss=0.05123, over 1418989.59 frames.], batch size: 31, lr: 6.96e-04
2022-04-29 00:23:47,727 INFO [train.py:763] (4/8) Epoch 10, batch 1650, loss[loss=0.1697, simple_loss=0.2617, pruned_loss=0.03884, over 6789.00 frames.], tot_loss[loss=0.1946, simple_loss=0.287, pruned_loss=0.05107, over 1418580.16 frames.], batch size: 15, lr: 6.96e-04
2022-04-29 00:24:52,734 INFO [train.py:763] (4/8) Epoch 10, batch 1700, loss[loss=0.1627, simple_loss=0.2656, pruned_loss=0.02986, over 6782.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2873, pruned_loss=0.05064, over 1417886.62 frames.], batch size: 15, lr: 6.96e-04
2022-04-29 00:25:58,395 INFO [train.py:763] (4/8) Epoch 10, batch 1750, loss[loss=0.1845, simple_loss=0.2863, pruned_loss=0.04128, over 7126.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2871, pruned_loss=0.05106, over 1413774.59 frames.], batch size: 21, lr: 6.95e-04
2022-04-29 00:27:03,848 INFO [train.py:763] (4/8) Epoch 10, batch 1800, loss[loss=0.2592, simple_loss=0.3314, pruned_loss=0.09351, over 5128.00 frames.], tot_loss[loss=0.1952, simple_loss=0.2878, pruned_loss=0.05125, over 1413418.75 frames.], batch size: 52, lr: 6.95e-04
2022-04-29 00:28:10,765 INFO [train.py:763] (4/8) Epoch 10, batch 1850, loss[loss=0.2043, simple_loss=0.3001, pruned_loss=0.05422, over 6404.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2879, pruned_loss=0.05151, over 1417403.35 frames.], batch size: 37, lr: 6.95e-04
2022-04-29 00:29:17,820 INFO [train.py:763] (4/8) Epoch 10, batch 1900, loss[loss=0.2069, simple_loss=0.312, pruned_loss=0.05096, over 7317.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2875, pruned_loss=0.0511, over 1421985.67 frames.], batch size: 21, lr: 6.94e-04
2022-04-29 00:30:24,811 INFO [train.py:763] (4/8) Epoch 10, batch 1950, loss[loss=0.1992, simple_loss=0.2943, pruned_loss=0.05207, over 7368.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2871, pruned_loss=0.05089, over 1420938.91 frames.], batch size: 19, lr: 6.94e-04
2022-04-29 00:31:31,793 INFO [train.py:763] (4/8) Epoch 10, batch 2000, loss[loss=0.1877, simple_loss=0.2845, pruned_loss=0.04541, over 7157.00 frames.], tot_loss[loss=0.194, simple_loss=0.2869, pruned_loss=0.05061, over 1422730.09 frames.], batch size: 18, lr: 6.93e-04
2022-04-29 00:32:38,659 INFO [train.py:763] (4/8) Epoch 10, batch 2050, loss[loss=0.176, simple_loss=0.2618, pruned_loss=0.04512, over 7306.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2868, pruned_loss=0.05025, over 1424969.33 frames.], batch size: 17, lr: 6.93e-04
2022-04-29 00:33:45,454 INFO [train.py:763] (4/8) Epoch 10, batch 2100, loss[loss=0.2056, simple_loss=0.2977, pruned_loss=0.05677, over 7391.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2872, pruned_loss=0.05065, over 1425345.16 frames.], batch size: 23, lr: 6.93e-04
2022-04-29 00:35:01,069 INFO [train.py:763] (4/8) Epoch 10, batch 2150, loss[loss=0.1923, simple_loss=0.2726, pruned_loss=0.05604, over 7162.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2866, pruned_loss=0.05052, over 1425410.40 frames.], batch size: 18, lr: 6.92e-04
2022-04-29 00:36:06,564 INFO [train.py:763] (4/8) Epoch 10, batch 2200, loss[loss=0.2381, simple_loss=0.3193, pruned_loss=0.0784, over 7233.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2869, pruned_loss=0.05097, over 1423744.09 frames.], batch size: 20, lr: 6.92e-04
2022-04-29 00:37:11,925 INFO [train.py:763] (4/8) Epoch 10, batch 2250, loss[loss=0.1776, simple_loss=0.2769, pruned_loss=0.03915, over 7350.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2876, pruned_loss=0.05107, over 1427035.28 frames.], batch size: 22, lr: 6.92e-04
2022-04-29 00:38:17,409 INFO [train.py:763] (4/8) Epoch 10, batch 2300, loss[loss=0.2155, simple_loss=0.3059, pruned_loss=0.06254, over 7162.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2872, pruned_loss=0.05106, over 1427042.03 frames.], batch size: 26, lr: 6.91e-04
2022-04-29 00:39:22,702 INFO [train.py:763] (4/8) Epoch 10, batch 2350, loss[loss=0.2263, simple_loss=0.3095, pruned_loss=0.0715, over 6790.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2861, pruned_loss=0.05056, over 1429645.96 frames.], batch size: 31, lr: 6.91e-04
2022-04-29 00:40:27,864 INFO [train.py:763] (4/8) Epoch 10, batch 2400, loss[loss=0.2004, simple_loss=0.2891, pruned_loss=0.05584, over 7321.00 frames.], tot_loss[loss=0.194, simple_loss=0.2864, pruned_loss=0.05079, over 1423899.60 frames.], batch size: 21, lr: 6.91e-04
2022-04-29 00:41:33,297 INFO [train.py:763] (4/8) Epoch 10, batch 2450, loss[loss=0.2059, simple_loss=0.2908, pruned_loss=0.06045, over 7018.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2862, pruned_loss=0.05082, over 1424033.99 frames.], batch size: 16, lr: 6.90e-04
2022-04-29 00:42:38,512 INFO [train.py:763] (4/8) Epoch 10, batch 2500, loss[loss=0.1674, simple_loss=0.267, pruned_loss=0.03393, over 7159.00 frames.], tot_loss[loss=0.1936, simple_loss=0.286, pruned_loss=0.05057, over 1422947.80 frames.], batch size: 19, lr: 6.90e-04
2022-04-29 00:43:44,249 INFO [train.py:763] (4/8) Epoch 10, batch 2550, loss[loss=0.2238, simple_loss=0.3, pruned_loss=0.07381, over 6768.00 frames.], tot_loss[loss=0.1935, simple_loss=0.286, pruned_loss=0.05055, over 1427008.02 frames.], batch size: 15, lr: 6.90e-04
2022-04-29 00:44:51,065 INFO [train.py:763] (4/8) Epoch 10, batch 2600, loss[loss=0.1908, simple_loss=0.2995, pruned_loss=0.04103, over 7367.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2859, pruned_loss=0.0502, over 1428314.52 frames.], batch size: 23, lr: 6.89e-04
2022-04-29 00:45:56,180 INFO [train.py:763] (4/8) Epoch 10, batch 2650, loss[loss=0.1744, simple_loss=0.254, pruned_loss=0.04743, over 6992.00 frames.], tot_loss[loss=0.194, simple_loss=0.2872, pruned_loss=0.05044, over 1423677.40 frames.], batch size: 16, lr: 6.89e-04
2022-04-29 00:47:01,610 INFO [train.py:763] (4/8) Epoch 10, batch 2700, loss[loss=0.2108, simple_loss=0.3112, pruned_loss=0.05517, over 7417.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2873, pruned_loss=0.05019, over 1426578.47 frames.], batch size: 21, lr: 6.89e-04
2022-04-29 00:48:08,163 INFO [train.py:763] (4/8) Epoch 10, batch 2750, loss[loss=0.1977, simple_loss=0.2786, pruned_loss=0.05837, over 7275.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2864, pruned_loss=0.05014, over 1425877.50 frames.], batch size: 18, lr: 6.88e-04
2022-04-29 00:49:13,511 INFO [train.py:763] (4/8) Epoch 10, batch 2800, loss[loss=0.1992, simple_loss=0.2936, pruned_loss=0.05242, over 7161.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2865, pruned_loss=0.05024, over 1424845.81 frames.], batch size: 19, lr: 6.88e-04
2022-04-29 00:50:19,051 INFO [train.py:763] (4/8) Epoch 10, batch 2850, loss[loss=0.2054, simple_loss=0.3031, pruned_loss=0.05382, over 7313.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2869, pruned_loss=0.05015, over 1425083.79 frames.], batch size: 21, lr: 6.87e-04
2022-04-29 00:51:24,554 INFO [train.py:763] (4/8) Epoch 10, batch 2900, loss[loss=0.2014, simple_loss=0.3028, pruned_loss=0.05003, over 7189.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2865, pruned_loss=0.04989, over 1427103.25 frames.], batch size: 23, lr: 6.87e-04
2022-04-29 00:52:30,305 INFO [train.py:763] (4/8) Epoch 10, batch 2950, loss[loss=0.2298, simple_loss=0.3281, pruned_loss=0.06574, over 7201.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2869, pruned_loss=0.05007, over 1424978.33 frames.], batch size: 22, lr: 6.87e-04
2022-04-29 00:53:36,006 INFO [train.py:763] (4/8) Epoch 10, batch 3000, loss[loss=0.1729, simple_loss=0.2702, pruned_loss=0.03777, over 7165.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2878, pruned_loss=0.05006, over 1424282.58 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:53:36,007 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 00:53:51,272 INFO [train.py:792] (4/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
2022-04-29 00:54:57,773 INFO [train.py:763] (4/8) Epoch 10, batch 3050, loss[loss=0.2098, simple_loss=0.3021, pruned_loss=0.05871, over 7223.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2868, pruned_loss=0.04984, over 1428239.41 frames.], batch size: 26, lr: 6.86e-04
2022-04-29 00:56:03,585 INFO [train.py:763] (4/8) Epoch 10, batch 3100, loss[loss=0.1666, simple_loss=0.2543, pruned_loss=0.03944, over 7420.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2879, pruned_loss=0.05096, over 1426145.86 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:57:10,794 INFO [train.py:763] (4/8) Epoch 10, batch 3150, loss[loss=0.1921, simple_loss=0.2677, pruned_loss=0.05822, over 7266.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2857, pruned_loss=0.0497, over 1428697.72 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:58:16,971 INFO [train.py:763] (4/8) Epoch 10, batch 3200, loss[loss=0.1604, simple_loss=0.2427, pruned_loss=0.03902, over 7170.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2847, pruned_loss=0.04978, over 1430480.66 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:59:22,560 INFO [train.py:763] (4/8) Epoch 10, batch 3250, loss[loss=0.1984, simple_loss=0.2848, pruned_loss=0.05594, over 7059.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2855, pruned_loss=0.04971, over 1431175.85 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 01:00:29,375 INFO [train.py:763] (4/8) Epoch 10, batch 3300, loss[loss=0.1857, simple_loss=0.2837, pruned_loss=0.04379, over 6497.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2857, pruned_loss=0.04968, over 1430049.70 frames.], batch size: 38, lr: 6.84e-04
2022-04-29 01:01:36,446 INFO [train.py:763] (4/8) Epoch 10, batch 3350, loss[loss=0.232, simple_loss=0.3273, pruned_loss=0.06829, over 7119.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2858, pruned_loss=0.04982, over 1424258.27 frames.], batch size: 21, lr: 6.84e-04
2022-04-29 01:02:41,921 INFO [train.py:763] (4/8) Epoch 10, batch 3400, loss[loss=0.2034, simple_loss=0.2916, pruned_loss=0.05758, over 6996.00 frames.], tot_loss[loss=0.193, simple_loss=0.286, pruned_loss=0.05003, over 1420926.12 frames.], batch size: 16, lr: 6.84e-04
2022-04-29 01:03:47,410 INFO [train.py:763] (4/8) Epoch 10, batch 3450, loss[loss=0.2067, simple_loss=0.3083, pruned_loss=0.05256, over 7115.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2867, pruned_loss=0.05027, over 1423966.56 frames.], batch size: 21, lr: 6.83e-04
2022-04-29 01:04:52,721 INFO [train.py:763] (4/8) Epoch 10, batch 3500, loss[loss=0.1532, simple_loss=0.2534, pruned_loss=0.02653, over 7413.00 frames.], tot_loss[loss=0.1929, simple_loss=0.286, pruned_loss=0.04987, over 1425438.86 frames.], batch size: 18, lr: 6.83e-04
2022-04-29 01:05:58,210 INFO [train.py:763] (4/8) Epoch 10, batch 3550, loss[loss=0.2009, simple_loss=0.2963, pruned_loss=0.05274, over 6175.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2862, pruned_loss=0.05008, over 1423896.43 frames.], batch size: 37, lr: 6.83e-04
2022-04-29 01:07:03,430 INFO [train.py:763] (4/8) Epoch 10, batch 3600, loss[loss=0.191, simple_loss=0.2855, pruned_loss=0.04822, over 6397.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2866, pruned_loss=0.05035, over 1419889.82 frames.], batch size: 38, lr: 6.82e-04
2022-04-29 01:08:09,033 INFO [train.py:763] (4/8) Epoch 10, batch 3650, loss[loss=0.2035, simple_loss=0.3014, pruned_loss=0.05278, over 7117.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2873, pruned_loss=0.05017, over 1422296.02 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:09:14,316 INFO [train.py:763] (4/8) Epoch 10, batch 3700, loss[loss=0.241, simple_loss=0.3293, pruned_loss=0.07635, over 7123.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2876, pruned_loss=0.05027, over 1417976.98 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:10:20,242 INFO [train.py:763] (4/8) Epoch 10, batch 3750, loss[loss=0.1937, simple_loss=0.2833, pruned_loss=0.05205, over 7431.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2878, pruned_loss=0.05037, over 1424355.31 frames.], batch size: 20, lr: 6.81e-04
2022-04-29 01:11:26,039 INFO [train.py:763] (4/8) Epoch 10, batch 3800, loss[loss=0.2038, simple_loss=0.2975, pruned_loss=0.055, over 7289.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2879, pruned_loss=0.05072, over 1422960.34 frames.], batch size: 24, lr: 6.81e-04
2022-04-29 01:12:32,916 INFO [train.py:763] (4/8) Epoch 10, batch 3850, loss[loss=0.2135, simple_loss=0.3207, pruned_loss=0.05316, over 7203.00 frames.], tot_loss[loss=0.1937, simple_loss=0.287, pruned_loss=0.0502, over 1428101.34 frames.], batch size: 22, lr: 6.81e-04
2022-04-29 01:13:40,342 INFO [train.py:763] (4/8) Epoch 10, batch 3900, loss[loss=0.2105, simple_loss=0.2919, pruned_loss=0.06461, over 7384.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2859, pruned_loss=0.04967, over 1428486.61 frames.], batch size: 23, lr: 6.80e-04
2022-04-29 01:14:47,716 INFO [train.py:763] (4/8) Epoch 10, batch 3950, loss[loss=0.1836, simple_loss=0.283, pruned_loss=0.04217, over 7437.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2854, pruned_loss=0.0494, over 1427116.88 frames.], batch size: 20, lr: 6.80e-04
2022-04-29 01:15:53,612 INFO [train.py:763] (4/8) Epoch 10, batch 4000, loss[loss=0.2082, simple_loss=0.2984, pruned_loss=0.05906, over 7226.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2856, pruned_loss=0.05016, over 1418157.49 frames.], batch size: 21, lr: 6.80e-04
2022-04-29 01:17:00,540 INFO [train.py:763] (4/8) Epoch 10, batch 4050, loss[loss=0.2127, simple_loss=0.2955, pruned_loss=0.06492, over 7198.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2865, pruned_loss=0.05057, over 1417991.80 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:18:07,362 INFO [train.py:763] (4/8) Epoch 10, batch 4100, loss[loss=0.2099, simple_loss=0.3084, pruned_loss=0.05568, over 7193.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2863, pruned_loss=0.05042, over 1418048.32 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:19:14,028 INFO [train.py:763] (4/8) Epoch 10, batch 4150, loss[loss=0.2167, simple_loss=0.3099, pruned_loss=0.06172, over 6802.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2869, pruned_loss=0.0502, over 1414882.55 frames.], batch size: 31, lr: 6.79e-04
2022-04-29 01:20:19,800 INFO [train.py:763] (4/8) Epoch 10, batch 4200, loss[loss=0.1998, simple_loss=0.308, pruned_loss=0.04577, over 7008.00 frames.], tot_loss[loss=0.194, simple_loss=0.2873, pruned_loss=0.05037, over 1416052.81 frames.], batch size: 28, lr: 6.78e-04
2022-04-29 01:21:26,027 INFO [train.py:763] (4/8) Epoch 10, batch 4250, loss[loss=0.219, simple_loss=0.3042, pruned_loss=0.06688, over 5223.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2877, pruned_loss=0.05059, over 1415676.77 frames.], batch size: 52, lr: 6.78e-04
2022-04-29 01:22:31,074 INFO [train.py:763] (4/8) Epoch 10, batch 4300, loss[loss=0.2435, simple_loss=0.3298, pruned_loss=0.07859, over 5152.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2877, pruned_loss=0.05081, over 1412060.19 frames.], batch size: 54, lr: 6.78e-04
2022-04-29 01:23:36,202 INFO [train.py:763] (4/8) Epoch 10, batch 4350, loss[loss=0.2219, simple_loss=0.3123, pruned_loss=0.06579, over 7224.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2891, pruned_loss=0.05118, over 1409643.37 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:24:41,258 INFO [train.py:763] (4/8) Epoch 10, batch 4400, loss[loss=0.1892, simple_loss=0.2912, pruned_loss=0.04357, over 7211.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2897, pruned_loss=0.05105, over 1415240.48 frames.], batch size: 22, lr: 6.77e-04
2022-04-29 01:25:46,575 INFO [train.py:763] (4/8) Epoch 10, batch 4450, loss[loss=0.19, simple_loss=0.2695, pruned_loss=0.05525, over 7232.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2908, pruned_loss=0.05149, over 1417759.90 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:26:52,300 INFO [train.py:763] (4/8) Epoch 10, batch 4500, loss[loss=0.247, simple_loss=0.3337, pruned_loss=0.08016, over 4890.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2913, pruned_loss=0.05197, over 1409255.25 frames.], batch size: 52, lr: 6.76e-04
2022-04-29 01:27:57,100 INFO [train.py:763] (4/8) Epoch 10, batch 4550, loss[loss=0.2175, simple_loss=0.3083, pruned_loss=0.06335, over 5192.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2941, pruned_loss=0.05474, over 1346333.44 frames.], batch size: 53, lr: 6.76e-04
2022-04-29 01:29:26,058 INFO [train.py:763] (4/8) Epoch 11, batch 0, loss[loss=0.2007, simple_loss=0.3065, pruned_loss=0.04749, over 7417.00 frames.], tot_loss[loss=0.2007, simple_loss=0.3065, pruned_loss=0.04749, over 7417.00 frames.], batch size: 21, lr: 6.52e-04
2022-04-29 01:30:32,264 INFO [train.py:763] (4/8) Epoch 11, batch 50, loss[loss=0.2408, simple_loss=0.3194, pruned_loss=0.08108, over 5239.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2848, pruned_loss=0.04914, over 319163.02 frames.], batch size: 52, lr: 6.52e-04
2022-04-29 01:31:38,377 INFO [train.py:763] (4/8) Epoch 11, batch 100, loss[loss=0.1824, simple_loss=0.2774, pruned_loss=0.04373, over 6491.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2863, pruned_loss=0.04964, over 559018.96 frames.], batch size: 38, lr: 6.51e-04
2022-04-29 01:32:44,336 INFO [train.py:763] (4/8) Epoch 11, batch 150, loss[loss=0.1899, simple_loss=0.2721, pruned_loss=0.05388, over 7276.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2866, pruned_loss=0.04879, over 748978.02 frames.], batch size: 17, lr: 6.51e-04
2022-04-29 01:33:50,247 INFO [train.py:763] (4/8) Epoch 11, batch 200, loss[loss=0.1905, simple_loss=0.2956, pruned_loss=0.04271, over 7204.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2879, pruned_loss=0.04971, over 896949.82 frames.], batch size: 22, lr: 6.51e-04
2022-04-29 01:34:55,807 INFO [train.py:763] (4/8) Epoch 11, batch 250, loss[loss=0.2047, simple_loss=0.3002, pruned_loss=0.05461, over 6806.00 frames.], tot_loss[loss=0.192, simple_loss=0.2864, pruned_loss=0.04882, over 1014109.60 frames.], batch size: 31, lr: 6.50e-04
2022-04-29 01:36:01,201 INFO [train.py:763] (4/8) Epoch 11, batch 300, loss[loss=0.1991, simple_loss=0.3015, pruned_loss=0.04835, over 7209.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2867, pruned_loss=0.04876, over 1098657.86 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:37:06,904 INFO [train.py:763] (4/8) Epoch 11, batch 350, loss[loss=0.2042, simple_loss=0.2997, pruned_loss=0.05434, over 7335.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2865, pruned_loss=0.04889, over 1165782.92 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:38:12,674 INFO [train.py:763] (4/8) Epoch 11, batch 400, loss[loss=0.1833, simple_loss=0.29, pruned_loss=0.03834, over 7332.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2854, pruned_loss=0.04808, over 1220738.93 frames.], batch size: 22, lr: 6.49e-04
2022-04-29 01:39:18,301 INFO [train.py:763] (4/8) Epoch 11, batch 450, loss[loss=0.1717, simple_loss=0.2635, pruned_loss=0.03996, over 7157.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2847, pruned_loss=0.04785, over 1269032.45 frames.], batch size: 19, lr: 6.49e-04
2022-04-29 01:40:24,053 INFO [train.py:763] (4/8) Epoch 11, batch 500, loss[loss=0.2263, simple_loss=0.3149, pruned_loss=0.06886, over 7376.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2846, pruned_loss=0.04811, over 1303321.18 frames.], batch size: 23, lr: 6.49e-04
2022-04-29 01:41:30,079 INFO [train.py:763] (4/8) Epoch 11, batch 550, loss[loss=0.1787, simple_loss=0.2815, pruned_loss=0.03794, over 7408.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2834, pruned_loss=0.04746, over 1329923.59 frames.], batch size: 21, lr: 6.48e-04
2022-04-29 01:42:36,718 INFO [train.py:763] (4/8) Epoch 11, batch 600, loss[loss=0.1935, simple_loss=0.297, pruned_loss=0.045, over 7329.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2826, pruned_loss=0.047, over 1350418.18 frames.], batch size: 22, lr: 6.48e-04
2022-04-29 01:43:44,063 INFO [train.py:763] (4/8) Epoch 11, batch 650, loss[loss=0.1978, simple_loss=0.2974, pruned_loss=0.0491, over 7387.00 frames.], tot_loss[loss=0.187, simple_loss=0.2811, pruned_loss=0.04644, over 1371489.47 frames.], batch size: 23, lr: 6.48e-04
2022-04-29 01:44:51,066 INFO [train.py:763] (4/8) Epoch 11, batch 700, loss[loss=0.1811, simple_loss=0.2777, pruned_loss=0.04228, over 7294.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2816, pruned_loss=0.04682, over 1382417.97 frames.], batch size: 24, lr: 6.47e-04
2022-04-29 01:45:57,535 INFO [train.py:763] (4/8) Epoch 11, batch 750, loss[loss=0.1789, simple_loss=0.2707, pruned_loss=0.04358, over 7330.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2829, pruned_loss=0.04763, over 1388049.89 frames.], batch size: 20, lr: 6.47e-04
2022-04-29 01:47:03,477 INFO [train.py:763] (4/8) Epoch 11, batch 800, loss[loss=0.1812, simple_loss=0.2734, pruned_loss=0.04452, over 7411.00 frames.], tot_loss[loss=0.1888, simple_loss=0.283, pruned_loss=0.04732, over 1400817.23 frames.], batch size: 18, lr: 6.47e-04
2022-04-29 01:48:08,962 INFO [train.py:763] (4/8) Epoch 11, batch 850, loss[loss=0.2222, simple_loss=0.3189, pruned_loss=0.06275, over 6838.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2837, pruned_loss=0.04749, over 1404852.80 frames.], batch size: 31, lr: 6.46e-04
2022-04-29 01:49:14,788 INFO [train.py:763] (4/8) Epoch 11, batch 900, loss[loss=0.1752, simple_loss=0.2709, pruned_loss=0.03978, over 7331.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2836, pruned_loss=0.04757, over 1408352.71 frames.], batch size: 22, lr: 6.46e-04
2022-04-29 01:50:20,603 INFO [train.py:763] (4/8) Epoch 11, batch 950, loss[loss=0.1628, simple_loss=0.2646, pruned_loss=0.03053, over 7427.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2831, pruned_loss=0.04761, over 1413548.42 frames.], batch size: 20, lr: 6.46e-04
2022-04-29 01:51:27,135 INFO [train.py:763] (4/8) Epoch 11, batch 1000, loss[loss=0.2129, simple_loss=0.3037, pruned_loss=0.06108, over 7166.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2842, pruned_loss=0.0481, over 1416233.86 frames.], batch size: 19, lr: 6.46e-04
2022-04-29 01:52:32,487 INFO [train.py:763] (4/8) Epoch 11, batch 1050, loss[loss=0.1417, simple_loss=0.2233, pruned_loss=0.03, over 6980.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2844, pruned_loss=0.0482, over 1415412.14 frames.], batch size: 16, lr: 6.45e-04
2022-04-29 01:53:38,687 INFO [train.py:763] (4/8) Epoch 11, batch 1100, loss[loss=0.2037, simple_loss=0.2969, pruned_loss=0.05521, over 7163.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2853, pruned_loss=0.04845, over 1418221.13 frames.], batch size: 19, lr: 6.45e-04
2022-04-29 01:54:45,796 INFO [train.py:763] (4/8) Epoch 11, batch 1150, loss[loss=0.2176, simple_loss=0.3056, pruned_loss=0.06481, over 4715.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2845, pruned_loss=0.04815, over 1421022.75 frames.], batch size: 54, lr: 6.45e-04
2022-04-29 01:55:51,956 INFO [train.py:763] (4/8) Epoch 11, batch 1200, loss[loss=0.1846, simple_loss=0.2834, pruned_loss=0.04289, over 7113.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2839, pruned_loss=0.04776, over 1423682.19 frames.], batch size: 21, lr: 6.44e-04
2022-04-29 01:56:57,796 INFO [train.py:763] (4/8) Epoch 11, batch 1250, loss[loss=0.1679, simple_loss=0.2576, pruned_loss=0.03912, over 6995.00 frames.], tot_loss[loss=0.189, simple_loss=0.283, pruned_loss=0.04751, over 1424990.26 frames.], batch size: 16, lr: 6.44e-04
2022-04-29 01:58:03,702 INFO [train.py:763] (4/8) Epoch 11, batch 1300, loss[loss=0.1872, simple_loss=0.286, pruned_loss=0.0442, over 7319.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2834, pruned_loss=0.04765, over 1427206.23 frames.], batch size: 20, lr: 6.44e-04
2022-04-29 01:59:10,163 INFO [train.py:763] (4/8) Epoch 11, batch 1350, loss[loss=0.1954, simple_loss=0.2949, pruned_loss=0.04795, over 7317.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2833, pruned_loss=0.04764, over 1424826.01 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:00:15,526 INFO [train.py:763] (4/8) Epoch 11, batch 1400, loss[loss=0.1873, simple_loss=0.287, pruned_loss=0.04381, over 7319.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2833, pruned_loss=0.0476, over 1421821.64 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:01:21,165 INFO [train.py:763] (4/8) Epoch 11, batch 1450, loss[loss=0.1666, simple_loss=0.2596, pruned_loss=0.03677, over 7056.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2834, pruned_loss=0.04763, over 1421594.07 frames.], batch size: 18, lr: 6.43e-04
2022-04-29 02:02:28,453 INFO [train.py:763] (4/8) Epoch 11, batch 1500, loss[loss=0.1964, simple_loss=0.2941, pruned_loss=0.04937, over 7205.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2829, pruned_loss=0.04733, over 1425448.95 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:03:33,957 INFO [train.py:763] (4/8) Epoch 11, batch 1550, loss[loss=0.2447, simple_loss=0.3312, pruned_loss=0.07912, over 7231.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2832, pruned_loss=0.04796, over 1424895.51 frames.], batch size: 20, lr: 6.42e-04
2022-04-29 02:04:39,634 INFO [train.py:763] (4/8) Epoch 11, batch 1600, loss[loss=0.1936, simple_loss=0.2852, pruned_loss=0.05103, over 7357.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2839, pruned_loss=0.04849, over 1426090.05 frames.], batch size: 19, lr: 6.42e-04
2022-04-29 02:06:04,015 INFO [train.py:763] (4/8) Epoch 11, batch 1650, loss[loss=0.1793, simple_loss=0.2776, pruned_loss=0.0405, over 7375.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2843, pruned_loss=0.04867, over 1426911.83 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:07:17,965 INFO [train.py:763] (4/8) Epoch 11, batch 1700, loss[loss=0.2087, simple_loss=0.2993, pruned_loss=0.05909, over 7228.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2844, pruned_loss=0.04853, over 1427678.06 frames.], batch size: 21, lr: 6.41e-04
2022-04-29 02:08:33,273 INFO [train.py:763] (4/8) Epoch 11, batch 1750, loss[loss=0.2025, simple_loss=0.2941, pruned_loss=0.05543, over 7170.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2843, pruned_loss=0.04873, over 1428376.86 frames.], batch size: 26, lr: 6.41e-04
2022-04-29 02:09:47,984 INFO [train.py:763] (4/8) Epoch 11, batch 1800, loss[loss=0.152, simple_loss=0.245, pruned_loss=0.02948, over 6974.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2835, pruned_loss=0.04847, over 1427747.72 frames.], batch size: 16, lr: 6.41e-04
2022-04-29 02:11:03,169 INFO [train.py:763] (4/8) Epoch 11, batch 1850, loss[loss=0.2079, simple_loss=0.3004, pruned_loss=0.05775, over 7139.00 frames.], tot_loss[loss=0.1899, simple_loss=0.283, pruned_loss=0.04842, over 1426454.59 frames.], batch size: 26, lr: 6.40e-04
2022-04-29 02:12:18,079 INFO [train.py:763] (4/8) Epoch 11, batch 1900, loss[loss=0.1858, simple_loss=0.2766, pruned_loss=0.04754, over 7429.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2823, pruned_loss=0.04772, over 1428739.53 frames.], batch size: 20, lr: 6.40e-04
2022-04-29 02:13:32,347 INFO [train.py:763] (4/8) Epoch 11, batch 1950, loss[loss=0.1874, simple_loss=0.2675, pruned_loss=0.05361, over 7019.00 frames.], tot_loss[loss=0.189, simple_loss=0.2823, pruned_loss=0.04782, over 1427584.22 frames.], batch size: 16, lr: 6.40e-04
2022-04-29 02:14:38,123 INFO [train.py:763] (4/8) Epoch 11, batch 2000, loss[loss=0.2047, simple_loss=0.298, pruned_loss=0.05571, over 6493.00 frames.], tot_loss[loss=0.19, simple_loss=0.2835, pruned_loss=0.04825, over 1426861.00 frames.], batch size: 38, lr: 6.39e-04
2022-04-29 02:15:44,445 INFO [train.py:763] (4/8) Epoch 11, batch 2050, loss[loss=0.2064, simple_loss=0.3027, pruned_loss=0.05501, over 7385.00 frames.], tot_loss[loss=0.1895, simple_loss=0.283, pruned_loss=0.048, over 1425078.73 frames.], batch size: 23, lr: 6.39e-04
2022-04-29 02:16:50,750 INFO [train.py:763] (4/8) Epoch 11, batch 2100, loss[loss=0.2237, simple_loss=0.3202, pruned_loss=0.06365, over 6743.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2832, pruned_loss=0.04792, over 1428585.96 frames.], batch size: 31, lr: 6.39e-04
2022-04-29 02:17:57,122 INFO [train.py:763] (4/8) Epoch 11, batch 2150, loss[loss=0.2038, simple_loss=0.2764, pruned_loss=0.06561, over 6826.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2835, pruned_loss=0.0485, over 1423244.58 frames.], batch size: 15, lr: 6.38e-04
2022-04-29 02:19:03,273 INFO [train.py:763] (4/8) Epoch 11, batch 2200, loss[loss=0.1847, simple_loss=0.2766, pruned_loss=0.04642, over 7421.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2835, pruned_loss=0.04858, over 1427366.39 frames.], batch size: 20, lr: 6.38e-04
2022-04-29 02:20:09,533 INFO [train.py:763] (4/8) Epoch 11, batch 2250, loss[loss=0.1906, simple_loss=0.2795, pruned_loss=0.05085, over 7135.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2832, pruned_loss=0.04849, over 1425691.72 frames.], batch size: 17, lr: 6.38e-04
2022-04-29 02:21:16,306 INFO [train.py:763] (4/8) Epoch 11, batch 2300, loss[loss=0.1759, simple_loss=0.2703, pruned_loss=0.04075, over 7359.00 frames.], tot_loss[loss=0.1907, simple_loss=0.284, pruned_loss=0.04873, over 1424979.10 frames.], batch size: 19, lr: 6.38e-04
2022-04-29 02:22:22,088 INFO [train.py:763] (4/8) Epoch 11, batch 2350, loss[loss=0.215, simple_loss=0.3183, pruned_loss=0.05584, over 7297.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2836, pruned_loss=0.04857, over 1426907.56 frames.], batch size: 24, lr: 6.37e-04
2022-04-29 02:23:28,142 INFO [train.py:763] (4/8) Epoch 11, batch 2400, loss[loss=0.1756, simple_loss=0.2736, pruned_loss=0.03881, over 7126.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2836, pruned_loss=0.04848, over 1428296.22 frames.], batch size: 21, lr: 6.37e-04
2022-04-29 02:24:33,620 INFO [train.py:763] (4/8) Epoch 11, batch 2450, loss[loss=0.192, simple_loss=0.2997, pruned_loss=0.04217, over 7240.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2836, pruned_loss=0.04839, over 1426317.57 frames.], batch size: 20, lr: 6.37e-04
2022-04-29 02:25:39,225 INFO [train.py:763] (4/8) Epoch 11, batch 2500, loss[loss=0.2015, simple_loss=0.2824, pruned_loss=0.06024, over 7072.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2837, pruned_loss=0.04877, over 1424865.08 frames.], batch size: 18, lr: 6.36e-04
2022-04-29 02:26:45,644 INFO [train.py:763] (4/8) Epoch 11, batch 2550, loss[loss=0.19, simple_loss=0.2717, pruned_loss=0.05408, over 7279.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2842, pruned_loss=0.04875, over 1427432.51 frames.], batch size: 17, lr: 6.36e-04
2022-04-29 02:27:50,865 INFO [train.py:763] (4/8) Epoch 11, batch 2600, loss[loss=0.2475, simple_loss=0.3294, pruned_loss=0.08283, over 7283.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2837, pruned_loss=0.04865, over 1421740.27 frames.], batch size: 24, lr: 6.36e-04
2022-04-29 02:28:56,394 INFO [train.py:763] (4/8) Epoch 11, batch 2650, loss[loss=0.1767, simple_loss=0.2723, pruned_loss=0.04058, over 7262.00 frames.], tot_loss[loss=0.191, simple_loss=0.2844, pruned_loss=0.04883, over 1418257.65 frames.], batch size: 19, lr: 6.36e-04
2022-04-29 02:30:03,347 INFO [train.py:763] (4/8) Epoch 11, batch 2700, loss[loss=0.1956, simple_loss=0.2895, pruned_loss=0.0508, over 7294.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2846, pruned_loss=0.04836, over 1422625.13 frames.], batch size: 25, lr: 6.35e-04
2022-04-29 02:31:08,819 INFO [train.py:763] (4/8) Epoch 11, batch 2750, loss[loss=0.1878, simple_loss=0.2818, pruned_loss=0.04691, over 7446.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2844, pruned_loss=0.04791, over 1425636.20 frames.], batch size: 20, lr: 6.35e-04
2022-04-29 02:32:14,646 INFO [train.py:763] (4/8) Epoch 11, batch 2800, loss[loss=0.2629, simple_loss=0.3498, pruned_loss=0.08798, over 7110.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2851, pruned_loss=0.04858, over 1426642.61 frames.], batch size: 21, lr: 6.35e-04
2022-04-29 02:33:21,112 INFO [train.py:763] (4/8) Epoch 11, batch 2850, loss[loss=0.19, simple_loss=0.278, pruned_loss=0.05097, over 7319.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2841, pruned_loss=0.04822, over 1429007.71 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:34:28,402 INFO [train.py:763] (4/8) Epoch 11, batch 2900, loss[loss=0.1775, simple_loss=0.2739, pruned_loss=0.04053, over 7313.00 frames.], tot_loss[loss=0.192, simple_loss=0.2857, pruned_loss=0.04918, over 1425018.26 frames.], batch size: 24, lr: 6.34e-04
2022-04-29 02:35:35,069 INFO [train.py:763] (4/8) Epoch 11, batch 2950, loss[loss=0.2368, simple_loss=0.3303, pruned_loss=0.0716, over 7235.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2853, pruned_loss=0.04909, over 1420917.40 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:36:40,643 INFO [train.py:763] (4/8) Epoch 11, batch 3000, loss[loss=0.1988, simple_loss=0.2891, pruned_loss=0.05427, over 7311.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2843, pruned_loss=0.04855, over 1421413.49 frames.], batch size: 25, lr: 6.33e-04
2022-04-29 02:36:40,644 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 02:36:55,964 INFO [train.py:792] (4/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
2022-04-29 02:38:01,323 INFO [train.py:763] (4/8) Epoch 11, batch 3050, loss[loss=0.1757, simple_loss=0.2803, pruned_loss=0.03551, over 7364.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2851, pruned_loss=0.04873, over 1420018.72 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:39:06,997 INFO [train.py:763] (4/8) Epoch 11, batch 3100, loss[loss=0.1835, simple_loss=0.2796, pruned_loss=0.04375, over 7324.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2838, pruned_loss=0.04826, over 1421483.19 frames.], batch size: 20, lr: 6.33e-04
2022-04-29 02:40:14,522 INFO [train.py:763] (4/8) Epoch 11, batch 3150, loss[loss=0.215, simple_loss=0.3123, pruned_loss=0.05891, over 7379.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2844, pruned_loss=0.04845, over 1424072.86 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:41:19,854 INFO [train.py:763] (4/8) Epoch 11, batch 3200, loss[loss=0.1865, simple_loss=0.2978, pruned_loss=0.03758, over 7112.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2844, pruned_loss=0.04808, over 1424276.30 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:42:26,202 INFO [train.py:763] (4/8) Epoch 11, batch 3250, loss[loss=0.1995, simple_loss=0.2857, pruned_loss=0.05669, over 7420.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2847, pruned_loss=0.04839, over 1425319.81 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:43:31,316 INFO [train.py:763] (4/8) Epoch 11, batch 3300, loss[loss=0.1667, simple_loss=0.2396, pruned_loss=0.04692, over 6996.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2854, pruned_loss=0.04878, over 1426148.92 frames.], batch size: 16, lr: 6.32e-04
2022-04-29 02:44:36,747 INFO [train.py:763] (4/8) Epoch 11, batch 3350, loss[loss=0.1561, simple_loss=0.2427, pruned_loss=0.03471, over 7282.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2843, pruned_loss=0.04849, over 1426690.60 frames.], batch size: 18, lr: 6.31e-04
2022-04-29 02:45:42,396 INFO [train.py:763] (4/8) Epoch 11, batch 3400, loss[loss=0.1978, simple_loss=0.3003, pruned_loss=0.04766, over 6415.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2841, pruned_loss=0.04823, over 1421294.19 frames.], batch size: 37, lr: 6.31e-04
2022-04-29 02:46:49,526 INFO [train.py:763] (4/8) Epoch 11, batch 3450, loss[loss=0.1928, simple_loss=0.2978, pruned_loss=0.04387, over 7121.00 frames.], tot_loss[loss=0.19, simple_loss=0.2835, pruned_loss=0.04821, over 1419245.44 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:47:56,121 INFO [train.py:763] (4/8) Epoch 11, batch 3500, loss[loss=0.2259, simple_loss=0.32, pruned_loss=0.06587, over 7307.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2849, pruned_loss=0.04847, over 1424998.93 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:49:02,210 INFO [train.py:763] (4/8) Epoch 11, batch 3550, loss[loss=0.1685, simple_loss=0.2506, pruned_loss=0.04319, over 6999.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2849, pruned_loss=0.04871, over 1423787.06 frames.], batch size: 16, lr: 6.30e-04
2022-04-29 02:50:08,006 INFO [train.py:763] (4/8) Epoch 11, batch 3600, loss[loss=0.1895, simple_loss=0.2987, pruned_loss=0.04015, over 7244.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2861, pruned_loss=0.04903, over 1425518.85 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:51:13,359 INFO [train.py:763] (4/8) Epoch 11, batch 3650, loss[loss=0.1927, simple_loss=0.2937, pruned_loss=0.04585, over 7428.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2855, pruned_loss=0.0486, over 1424843.63 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:52:20,067 INFO [train.py:763] (4/8) Epoch 11, batch 3700, loss[loss=0.1917, simple_loss=0.2877, pruned_loss=0.0479, over 6744.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2855, pruned_loss=0.04881, over 1421558.77 frames.], batch size: 31, lr: 6.29e-04
2022-04-29 02:53:25,480 INFO [train.py:763] (4/8) Epoch 11, batch 3750, loss[loss=0.1779, simple_loss=0.2812, pruned_loss=0.03731, over 7371.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2845, pruned_loss=0.04847, over 1425324.46 frames.], batch size: 23, lr: 6.29e-04
2022-04-29 02:54:30,949 INFO [train.py:763] (4/8) Epoch 11, batch 3800, loss[loss=0.2045, simple_loss=0.3, pruned_loss=0.05445, over 7158.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2837, pruned_loss=0.048, over 1428420.28 frames.], batch size: 26, lr: 6.29e-04
2022-04-29 02:55:36,104 INFO [train.py:763] (4/8) Epoch 11, batch 3850, loss[loss=0.1901, simple_loss=0.2943, pruned_loss=0.04298, over 7118.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2834, pruned_loss=0.04745, over 1429050.57 frames.], batch size: 21, lr: 6.29e-04
2022-04-29 02:56:41,382 INFO [train.py:763] (4/8) Epoch 11, batch 3900, loss[loss=0.1986, simple_loss=0.3039, pruned_loss=0.04665, over 7426.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2835, pruned_loss=0.04755, over 1429890.72 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:57:46,957 INFO [train.py:763] (4/8) Epoch 11, batch 3950, loss[loss=0.227, simple_loss=0.3161, pruned_loss=0.06901, over 7243.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2832, pruned_loss=0.0477, over 1431257.82 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:58:52,090 INFO [train.py:763] (4/8) Epoch 11, batch 4000, loss[loss=0.18, simple_loss=0.2885, pruned_loss=0.03582, over 7419.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2838, pruned_loss=0.04777, over 1426872.89 frames.], batch size: 21, lr: 6.28e-04
2022-04-29 02:59:57,355 INFO [train.py:763] (4/8) Epoch 11, batch 4050, loss[loss=0.2121, simple_loss=0.3072, pruned_loss=0.05851, over 7427.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2832, pruned_loss=0.04775, over 1425252.87 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:01:03,190 INFO [train.py:763] (4/8) Epoch 11, batch 4100, loss[loss=0.1567, simple_loss=0.2547, pruned_loss=0.02932, over 7334.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2821, pruned_loss=0.04714, over 1422177.86 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:02:08,241 INFO [train.py:763] (4/8) Epoch 11, batch 4150, loss[loss=0.1796, simple_loss=0.2758, pruned_loss=0.04169, over 7232.00 frames.], tot_loss[loss=0.188, simple_loss=0.2822, pruned_loss=0.04694, over 1422723.50 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:03:14,694 INFO [train.py:763] (4/8) Epoch 11, batch 4200, loss[loss=0.1746, simple_loss=0.2835, pruned_loss=0.03284, over 7342.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2838, pruned_loss=0.04766, over 1421994.18 frames.], batch size: 22, lr: 6.27e-04
2022-04-29 03:04:21,491 INFO [train.py:763] (4/8) Epoch 11, batch 4250, loss[loss=0.1832, simple_loss=0.2642, pruned_loss=0.05113, over 7423.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2821, pruned_loss=0.04733, over 1426008.18 frames.], batch size: 18, lr: 6.26e-04
2022-04-29 03:05:27,591 INFO [train.py:763] (4/8) Epoch 11, batch 4300, loss[loss=0.1972, simple_loss=0.2927, pruned_loss=0.05088, over 7230.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2819, pruned_loss=0.04746, over 1419500.50 frames.], batch size: 20, lr: 6.26e-04
2022-04-29 03:06:35,253 INFO [train.py:763] (4/8) Epoch 11, batch 4350, loss[loss=0.2042, simple_loss=0.308, pruned_loss=0.05024, over 7208.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2807, pruned_loss=0.04701, over 1421210.39 frames.], batch size: 22, lr: 6.26e-04
2022-04-29 03:07:41,463 INFO [train.py:763] (4/8) Epoch 11, batch 4400, loss[loss=0.194, simple_loss=0.2923, pruned_loss=0.04789, over 7315.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2811, pruned_loss=0.04722, over 1420068.56 frames.], batch size: 21, lr: 6.25e-04
2022-04-29 03:08:47,763 INFO [train.py:763] (4/8) Epoch 11, batch 4450, loss[loss=0.2004, simple_loss=0.2934, pruned_loss=0.05373, over 6428.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2806, pruned_loss=0.04795, over 1408360.40 frames.], batch size: 38, lr: 6.25e-04
2022-04-29 03:09:54,260 INFO [train.py:763] (4/8) Epoch 11, batch 4500, loss[loss=0.178, simple_loss=0.2719, pruned_loss=0.042, over 6391.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2815, pruned_loss=0.04906, over 1391397.22 frames.], batch size: 37, lr: 6.25e-04
2022-04-29 03:10:59,840 INFO [train.py:763] (4/8) Epoch 11, batch 4550, loss[loss=0.2515, simple_loss=0.3317, pruned_loss=0.08562, over 4947.00 frames.], tot_loss[loss=0.1925, simple_loss=0.2836, pruned_loss=0.05074, over 1350803.42 frames.], batch size: 55, lr: 6.25e-04
2022-04-29 03:12:38,229 INFO [train.py:763] (4/8) Epoch 12, batch 0, loss[loss=0.1681, simple_loss=0.2676, pruned_loss=0.03432, over 7139.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2676, pruned_loss=0.03432, over 7139.00 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:13:44,616 INFO [train.py:763] (4/8) Epoch 12, batch 50, loss[loss=0.1786, simple_loss=0.2809, pruned_loss=0.03814, over 7233.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2819, pruned_loss=0.04656, over 318612.94 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:14:50,355 INFO [train.py:763] (4/8) Epoch 12, batch 100, loss[loss=0.2038, simple_loss=0.2963, pruned_loss=0.05562, over 7203.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2848, pruned_loss=0.04703, over 565214.66 frames.], batch size: 23, lr: 6.03e-04
2022-04-29 03:15:56,439 INFO [train.py:763] (4/8) Epoch 12, batch 150, loss[loss=0.2079, simple_loss=0.3055, pruned_loss=0.05513, over 7145.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2866, pruned_loss=0.04723, over 753959.76 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:17:02,800 INFO [train.py:763] (4/8) Epoch 12, batch 200, loss[loss=0.172, simple_loss=0.2775, pruned_loss=0.03327, over 7160.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2853, pruned_loss=0.04788, over 900288.98 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:18:09,053 INFO [train.py:763] (4/8) Epoch 12, batch 250, loss[loss=0.1822, simple_loss=0.268, pruned_loss=0.04823, over 6770.00 frames.], tot_loss[loss=0.19, simple_loss=0.2846, pruned_loss=0.04772, over 1013087.43 frames.], batch size: 15, lr: 6.02e-04
2022-04-29 03:19:15,280 INFO [train.py:763] (4/8) Epoch 12, batch 300, loss[loss=0.185, simple_loss=0.2882, pruned_loss=0.04088, over 7139.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2848, pruned_loss=0.04775, over 1102883.79 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:20:20,569 INFO [train.py:763] (4/8) Epoch 12, batch 350, loss[loss=0.2078, simple_loss=0.3007, pruned_loss=0.05741, over 7059.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2837, pruned_loss=0.04696, over 1175348.77 frames.], batch size: 28, lr: 6.01e-04
2022-04-29 03:21:26,171 INFO [train.py:763] (4/8) Epoch 12, batch 400, loss[loss=0.1835, simple_loss=0.2811, pruned_loss=0.04295, over 7368.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2834, pruned_loss=0.04683, over 1232871.02 frames.], batch size: 19, lr: 6.01e-04
2022-04-29 03:22:31,835 INFO [train.py:763] (4/8) Epoch 12, batch 450, loss[loss=0.1725, simple_loss=0.2733, pruned_loss=0.03584, over 7315.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2825, pruned_loss=0.04659, over 1277090.39 frames.], batch size: 21, lr: 6.01e-04
2022-04-29 03:23:38,034 INFO [train.py:763] (4/8) Epoch 12, batch 500, loss[loss=0.1972, simple_loss=0.3061, pruned_loss=0.04414, over 6293.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2808, pruned_loss=0.04595, over 1310770.57 frames.], batch size: 37, lr: 6.01e-04
2022-04-29 03:24:43,943 INFO [train.py:763] (4/8) Epoch 12, batch 550, loss[loss=0.1906, simple_loss=0.2912, pruned_loss=0.04506, over 7362.00 frames.], tot_loss[loss=0.1868, simple_loss=0.281, pruned_loss=0.04625, over 1333350.72 frames.], batch size: 23, lr: 6.00e-04
2022-04-29 03:25:49,962 INFO [train.py:763] (4/8) Epoch 12, batch 600, loss[loss=0.1819, simple_loss=0.2687, pruned_loss=0.04752, over 7235.00 frames.], tot_loss[loss=0.1869, simple_loss=0.281, pruned_loss=0.04643, over 1347309.17 frames.], batch size: 16, lr: 6.00e-04
2022-04-29 03:26:55,891 INFO [train.py:763] (4/8) Epoch 12, batch 650, loss[loss=0.1611, simple_loss=0.2574, pruned_loss=0.03235, over 7271.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2804, pruned_loss=0.04564, over 1366134.50 frames.], batch size: 18, lr: 6.00e-04
2022-04-29 03:28:02,296 INFO [train.py:763] (4/8) Epoch 12, batch 700, loss[loss=0.17, simple_loss=0.2588, pruned_loss=0.04058, over 6809.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2807, pruned_loss=0.04551, over 1383318.27 frames.], batch size: 15, lr: 6.00e-04
2022-04-29 03:29:07,991 INFO [train.py:763] (4/8) Epoch 12, batch 750, loss[loss=0.1925, simple_loss=0.2822, pruned_loss=0.05141, over 7201.00 frames.], tot_loss[loss=0.1861, simple_loss=0.281, pruned_loss=0.04562, over 1395483.27 frames.], batch size: 23, lr: 5.99e-04
2022-04-29 03:30:14,230 INFO [train.py:763] (4/8) Epoch 12, batch 800, loss[loss=0.2139, simple_loss=0.3043, pruned_loss=0.06174, over 7201.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2816, pruned_loss=0.04585, over 1403911.20 frames.], batch size: 22, lr: 5.99e-04
2022-04-29 03:31:20,650 INFO [train.py:763] (4/8) Epoch 12, batch 850, loss[loss=0.1753, simple_loss=0.2702, pruned_loss=0.04019, over 7148.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2824, pruned_loss=0.04613, over 1410362.27 frames.], batch size: 17, lr: 5.99e-04
2022-04-29 03:32:27,842 INFO [train.py:763] (4/8) Epoch 12, batch 900, loss[loss=0.1546, simple_loss=0.2521, pruned_loss=0.02861, over 7333.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2817, pruned_loss=0.04581, over 1413965.36 frames.], batch size: 20, lr: 5.99e-04
2022-04-29 03:33:44,134 INFO [train.py:763] (4/8) Epoch 12, batch 950, loss[loss=0.1739, simple_loss=0.2799, pruned_loss=0.03394, over 7161.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2814, pruned_loss=0.04557, over 1414068.94 frames.], batch size: 26, lr: 5.98e-04
2022-04-29 03:34:49,708 INFO [train.py:763] (4/8) Epoch 12, batch 1000, loss[loss=0.1872, simple_loss=0.2781, pruned_loss=0.04816, over 6434.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2827, pruned_loss=0.04613, over 1414458.93 frames.], batch size: 37, lr: 5.98e-04
2022-04-29 03:35:56,174 INFO [train.py:763] (4/8) Epoch 12, batch 1050, loss[loss=0.2112, simple_loss=0.2914, pruned_loss=0.06548, over 7251.00 frames.], tot_loss[loss=0.187, simple_loss=0.2816, pruned_loss=0.04623, over 1415962.84 frames.], batch size: 19, lr: 5.98e-04
2022-04-29 03:37:02,295 INFO [train.py:763] (4/8) Epoch 12, batch 1100, loss[loss=0.1949, simple_loss=0.2896, pruned_loss=0.05014, over 7376.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2827, pruned_loss=0.04704, over 1422603.46 frames.], batch size: 23, lr: 5.97e-04
2022-04-29 03:38:08,854 INFO [train.py:763] (4/8) Epoch 12, batch 1150, loss[loss=0.1745, simple_loss=0.272, pruned_loss=0.03851, over 7337.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2819, pruned_loss=0.0465, over 1424484.10 frames.], batch size: 20, lr: 5.97e-04
2022-04-29 03:39:15,118 INFO [train.py:763] (4/8) Epoch 12, batch 1200, loss[loss=0.2388, simple_loss=0.3237, pruned_loss=0.07691, over 5085.00 frames.], tot_loss[loss=0.1882, simple_loss=0.282, pruned_loss=0.04723, over 1422042.26 frames.], batch size: 52, lr: 5.97e-04
2022-04-29 03:40:21,631 INFO [train.py:763] (4/8) Epoch 12, batch 1250, loss[loss=0.1882, simple_loss=0.2823, pruned_loss=0.04706, over 7156.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2824, pruned_loss=0.04734, over 1419158.78 frames.], batch size: 19, lr: 5.97e-04
2022-04-29 03:41:28,264 INFO [train.py:763] (4/8) Epoch 12, batch 1300, loss[loss=0.1979, simple_loss=0.2812, pruned_loss=0.05732, over 7075.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2819, pruned_loss=0.04727, over 1419749.84 frames.], batch size: 18, lr: 5.96e-04
2022-04-29 03:42:33,924 INFO [train.py:763] (4/8) Epoch 12, batch 1350, loss[loss=0.2396, simple_loss=0.3164, pruned_loss=0.08143, over 4959.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2832, pruned_loss=0.04785, over 1417503.10 frames.], batch size: 52, lr: 5.96e-04
2022-04-29 03:43:39,825 INFO [train.py:763] (4/8) Epoch 12, batch 1400, loss[loss=0.2106, simple_loss=0.308, pruned_loss=0.05663, over 7302.00 frames.], tot_loss[loss=0.189, simple_loss=0.2832, pruned_loss=0.04742, over 1416263.02 frames.], batch size: 25, lr: 5.96e-04
2022-04-29 03:44:45,259 INFO [train.py:763] (4/8) Epoch 12, batch 1450, loss[loss=0.1873, simple_loss=0.2925, pruned_loss=0.04103, over 7314.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2834, pruned_loss=0.0472, over 1414281.53 frames.], batch size: 21, lr: 5.96e-04
2022-04-29 03:45:51,846 INFO [train.py:763] (4/8) Epoch 12, batch 1500, loss[loss=0.1902, simple_loss=0.2957, pruned_loss=0.04233, over 7212.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2828, pruned_loss=0.04668, over 1417554.33 frames.], batch size: 23, lr: 5.95e-04
2022-04-29 03:46:59,220 INFO [train.py:763] (4/8) Epoch 12, batch 1550, loss[loss=0.2103, simple_loss=0.3074, pruned_loss=0.05654, over 7073.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2823, pruned_loss=0.04649, over 1420186.74 frames.], batch size: 28, lr: 5.95e-04
2022-04-29 03:48:05,681 INFO [train.py:763] (4/8) Epoch 12, batch 1600, loss[loss=0.2083, simple_loss=0.3054, pruned_loss=0.05561, over 7282.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2834, pruned_loss=0.04715, over 1419171.04 frames.], batch size: 25, lr: 5.95e-04
2022-04-29 03:49:11,827 INFO [train.py:763] (4/8) Epoch 12, batch 1650, loss[loss=0.1838, simple_loss=0.2863, pruned_loss=0.04066, over 7306.00 frames.], tot_loss[loss=0.189, simple_loss=0.2833, pruned_loss=0.04732, over 1421722.29 frames.], batch size: 24, lr: 5.95e-04
2022-04-29 03:50:17,592 INFO [train.py:763] (4/8) Epoch 12, batch 1700, loss[loss=0.1746, simple_loss=0.2625, pruned_loss=0.04332, over 7145.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2826, pruned_loss=0.04732, over 1417630.74 frames.], batch size: 17, lr: 5.94e-04
2022-04-29 03:51:23,274 INFO [train.py:763] (4/8) Epoch 12, batch 1750, loss[loss=0.2027, simple_loss=0.2958, pruned_loss=0.05476, over 7184.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2817, pruned_loss=0.04694, over 1420868.89 frames.], batch size: 26, lr: 5.94e-04
2022-04-29 03:52:29,187 INFO [train.py:763] (4/8) Epoch 12, batch 1800, loss[loss=0.16, simple_loss=0.2487, pruned_loss=0.03566, over 6997.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2813, pruned_loss=0.0469, over 1426329.91 frames.], batch size: 16, lr: 5.94e-04
2022-04-29 03:53:35,386 INFO [train.py:763] (4/8) Epoch 12, batch 1850, loss[loss=0.21, simple_loss=0.3173, pruned_loss=0.05136, over 7324.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2808, pruned_loss=0.04623, over 1426799.03 frames.], batch size: 22, lr: 5.94e-04
2022-04-29 03:54:41,515 INFO [train.py:763] (4/8) Epoch 12, batch 1900, loss[loss=0.1773, simple_loss=0.2731, pruned_loss=0.04079, over 7234.00 frames.], tot_loss[loss=0.187, simple_loss=0.2813, pruned_loss=0.04632, over 1427499.98 frames.], batch size: 20, lr: 5.93e-04
2022-04-29 03:55:47,350 INFO [train.py:763] (4/8) Epoch 12, batch 1950, loss[loss=0.1472, simple_loss=0.233, pruned_loss=0.03065, over 7276.00 frames.], tot_loss[loss=0.186, simple_loss=0.2804, pruned_loss=0.04583, over 1427545.10 frames.], batch size: 17, lr: 5.93e-04
2022-04-29 03:56:53,845 INFO [train.py:763] (4/8) Epoch 12, batch 2000, loss[loss=0.1788, simple_loss=0.2681, pruned_loss=0.04471, over 6989.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2801, pruned_loss=0.04609, over 1427254.07 frames.], batch size: 16, lr: 5.93e-04
2022-04-29 03:57:59,760 INFO [train.py:763] (4/8) Epoch 12, batch 2050, loss[loss=0.1746, simple_loss=0.2767, pruned_loss=0.03625, over 7154.00 frames.], tot_loss[loss=0.185, simple_loss=0.279, pruned_loss=0.04544, over 1421213.34 frames.], batch size: 19, lr: 5.93e-04
2022-04-29 03:59:05,458 INFO [train.py:763] (4/8) Epoch 12, batch 2100, loss[loss=0.1863, simple_loss=0.2915, pruned_loss=0.04059, over 7165.00 frames.], tot_loss[loss=0.1859, simple_loss=0.28, pruned_loss=0.04587, over 1421486.69 frames.], batch size: 19, lr: 5.92e-04
2022-04-29 04:00:11,329 INFO [train.py:763] (4/8) Epoch 12, batch 2150, loss[loss=0.1834, simple_loss=0.2812, pruned_loss=0.04283, over 7287.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2809, pruned_loss=0.04638, over 1422129.69 frames.], batch size: 18, lr: 5.92e-04
2022-04-29 04:01:17,159 INFO [train.py:763] (4/8) Epoch 12, batch 2200, loss[loss=0.1715, simple_loss=0.2723, pruned_loss=0.03541, over 7327.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2799, pruned_loss=0.04577, over 1422657.09 frames.], batch size: 20, lr: 5.92e-04
2022-04-29 04:02:23,225 INFO [train.py:763] (4/8) Epoch 12, batch 2250, loss[loss=0.2103, simple_loss=0.3084, pruned_loss=0.05615, over 7090.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2792, pruned_loss=0.04531, over 1420395.28 frames.], batch size: 28, lr: 5.91e-04
2022-04-29 04:03:29,733 INFO [train.py:763] (4/8) Epoch 12, batch 2300, loss[loss=0.1774, simple_loss=0.2831, pruned_loss=0.0359, over 7117.00 frames.], tot_loss[loss=0.1861, simple_loss=0.281, pruned_loss=0.04561, over 1424684.47 frames.], batch size: 21, lr: 5.91e-04
2022-04-29 04:04:36,289 INFO [train.py:763] (4/8) Epoch 12, batch 2350, loss[loss=0.1812, simple_loss=0.2749, pruned_loss=0.04376, over 7157.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2815, pruned_loss=0.04575, over 1426330.58 frames.], batch size: 19, lr: 5.91e-04
2022-04-29 04:05:42,053 INFO [train.py:763] (4/8) Epoch 12, batch 2400, loss[loss=0.1807, simple_loss=0.2651, pruned_loss=0.0482, over 7139.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2811, pruned_loss=0.04559, over 1426350.97 frames.], batch size: 17, lr: 5.91e-04
2022-04-29 04:06:47,899 INFO [train.py:763] (4/8) Epoch 12, batch 2450, loss[loss=0.1824, simple_loss=0.2872, pruned_loss=0.0388, over 7215.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2814, pruned_loss=0.04573, over 1426275.25 frames.], batch size: 21, lr: 5.90e-04
2022-04-29 04:07:54,985 INFO [train.py:763] (4/8) Epoch 12, batch 2500, loss[loss=0.1714, simple_loss=0.262, pruned_loss=0.04044, over 7281.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2819, pruned_loss=0.04639, over 1427320.99 frames.], batch size: 18, lr: 5.90e-04
2022-04-29 04:09:01,285 INFO [train.py:763] (4/8) Epoch 12, batch 2550, loss[loss=0.1909, simple_loss=0.2756, pruned_loss=0.05313, over 7219.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2825, pruned_loss=0.04709, over 1429153.79 frames.], batch size: 16, lr: 5.90e-04
2022-04-29 04:10:08,000 INFO [train.py:763] (4/8) Epoch 12, batch 2600, loss[loss=0.1734, simple_loss=0.2631, pruned_loss=0.0419, over 6793.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2819, pruned_loss=0.04696, over 1425733.25 frames.], batch size: 15, lr: 5.90e-04
2022-04-29 04:11:13,658 INFO [train.py:763] (4/8) Epoch 12, batch 2650, loss[loss=0.1772, simple_loss=0.252, pruned_loss=0.05123, over 6984.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2821, pruned_loss=0.04702, over 1423235.79 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:12:19,556 INFO [train.py:763] (4/8) Epoch 12, batch 2700, loss[loss=0.1455, simple_loss=0.2452, pruned_loss=0.02294, over 7012.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2816, pruned_loss=0.04653, over 1424665.85 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:13:25,129 INFO [train.py:763] (4/8) Epoch 12, batch 2750, loss[loss=0.1862, simple_loss=0.2837, pruned_loss=0.04437, over 7108.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2812, pruned_loss=0.04668, over 1422349.65 frames.], batch size: 21, lr: 5.89e-04
2022-04-29 04:14:30,844 INFO [train.py:763] (4/8) Epoch 12, batch 2800, loss[loss=0.1576, simple_loss=0.246, pruned_loss=0.0346, over 7150.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2817, pruned_loss=0.04653, over 1422042.71 frames.], batch size: 17, lr: 5.89e-04
2022-04-29 04:15:37,559 INFO [train.py:763] (4/8) Epoch 12, batch 2850, loss[loss=0.2311, simple_loss=0.3335, pruned_loss=0.06441, over 7376.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2824, pruned_loss=0.04652, over 1427723.44 frames.], batch size: 23, lr: 5.88e-04
2022-04-29 04:16:43,202 INFO [train.py:763] (4/8) Epoch 12, batch 2900, loss[loss=0.1794, simple_loss=0.2631, pruned_loss=0.04786, over 7359.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2826, pruned_loss=0.04641, over 1425260.51 frames.], batch size: 19, lr: 5.88e-04
2022-04-29 04:17:49,200 INFO [train.py:763] (4/8) Epoch 12, batch 2950, loss[loss=0.2139, simple_loss=0.3153, pruned_loss=0.05622, over 7447.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2817, pruned_loss=0.04604, over 1427085.81 frames.], batch size: 22, lr: 5.88e-04
2022-04-29 04:18:54,865 INFO [train.py:763] (4/8) Epoch 12, batch 3000, loss[loss=0.1457, simple_loss=0.2321, pruned_loss=0.02967, over 7282.00 frames.], tot_loss[loss=0.1875, simple_loss=0.282, pruned_loss=0.04656, over 1427079.77 frames.], batch size: 17, lr: 5.88e-04
2022-04-29 04:18:54,866 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 04:19:10,345 INFO [train.py:792] (4/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
2022-04-29 04:20:16,204 INFO [train.py:763] (4/8) Epoch 12, batch 3050, loss[loss=0.1535, simple_loss=0.2481, pruned_loss=0.02947, over 7152.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2816, pruned_loss=0.04642, over 1427821.12 frames.], batch size: 17, lr: 5.87e-04
2022-04-29 04:21:32,106 INFO [train.py:763] (4/8) Epoch 12, batch 3100, loss[loss=0.1963, simple_loss=0.3044, pruned_loss=0.04407, over 7115.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2804, pruned_loss=0.04565, over 1427426.54 frames.], batch size: 21, lr: 5.87e-04
2022-04-29 04:22:37,467 INFO [train.py:763] (4/8) Epoch 12, batch 3150, loss[loss=0.1973, simple_loss=0.2896, pruned_loss=0.05249, over 7331.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2815, pruned_loss=0.04596, over 1424510.70 frames.], batch size: 25, lr: 5.87e-04
2022-04-29 04:23:52,367 INFO [train.py:763] (4/8) Epoch 12, batch 3200, loss[loss=0.2582, simple_loss=0.33, pruned_loss=0.09319, over 5023.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2824, pruned_loss=0.04616, over 1425726.35 frames.], batch size: 52, lr: 5.87e-04
2022-04-29 04:25:17,147 INFO [train.py:763] (4/8) Epoch 12, batch 3250, loss[loss=0.1454, simple_loss=0.2321, pruned_loss=0.02937, over 7275.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2812, pruned_loss=0.04556, over 1428699.22 frames.], batch size: 17, lr: 5.86e-04
2022-04-29 04:26:23,033 INFO [train.py:763] (4/8) Epoch 12, batch 3300, loss[loss=0.1778, simple_loss=0.2799, pruned_loss=0.03787, over 7335.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2808, pruned_loss=0.0455, over 1428433.92 frames.], batch size: 20, lr: 5.86e-04
2022-04-29 04:27:37,931 INFO [train.py:763] (4/8) Epoch 12, batch 3350, loss[loss=0.1826, simple_loss=0.2603, pruned_loss=0.0525, over 7003.00 frames.], tot_loss[loss=0.187, simple_loss=0.2814, pruned_loss=0.04634, over 1420788.05 frames.], batch size: 16, lr: 5.86e-04
2022-04-29 04:29:03,557 INFO [train.py:763] (4/8) Epoch 12, batch 3400, loss[loss=0.1955, simple_loss=0.294, pruned_loss=0.04848, over 7384.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2826, pruned_loss=0.04663, over 1424334.96 frames.], batch size: 23, lr: 5.86e-04
2022-04-29 04:30:18,593 INFO [train.py:763] (4/8) Epoch 12, batch 3450, loss[loss=0.1689, simple_loss=0.2686, pruned_loss=0.03454, over 7411.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2831, pruned_loss=0.04705, over 1412340.83 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:31:24,819 INFO [train.py:763] (4/8) Epoch 12, batch 3500, loss[loss=0.1803, simple_loss=0.2745, pruned_loss=0.04306, over 6762.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2825, pruned_loss=0.04683, over 1414291.11 frames.], batch size: 31, lr: 5.85e-04
2022-04-29 04:32:31,884 INFO [train.py:763] (4/8) Epoch 12, batch 3550, loss[loss=0.1665, simple_loss=0.2579, pruned_loss=0.0375, over 6995.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2826, pruned_loss=0.04714, over 1420010.74 frames.], batch size: 16, lr: 5.85e-04
2022-04-29 04:33:38,540 INFO [train.py:763] (4/8) Epoch 12, batch 3600, loss[loss=0.1899, simple_loss=0.2663, pruned_loss=0.0567, over 7287.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2821, pruned_loss=0.04677, over 1420007.91 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:34:44,018 INFO [train.py:763] (4/8) Epoch 12, batch 3650, loss[loss=0.222, simple_loss=0.3154, pruned_loss=0.0643, over 7415.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2827, pruned_loss=0.0469, over 1422902.90 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:35:49,776 INFO [train.py:763] (4/8) Epoch 12, batch 3700, loss[loss=0.1633, simple_loss=0.2535, pruned_loss=0.03655, over 7263.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2805, pruned_loss=0.04605, over 1423768.27 frames.], batch size: 19, lr: 5.84e-04
2022-04-29 04:36:55,380 INFO [train.py:763] (4/8) Epoch 12, batch 3750, loss[loss=0.1881, simple_loss=0.2869, pruned_loss=0.04469, over 7415.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2798, pruned_loss=0.04572, over 1424288.90 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:38:01,435 INFO [train.py:763] (4/8) Epoch 12, batch 3800, loss[loss=0.1903, simple_loss=0.294, pruned_loss=0.0433, over 7018.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2802, pruned_loss=0.04548, over 1429003.14 frames.], batch size: 28, lr: 5.84e-04
2022-04-29 04:39:06,786 INFO [train.py:763] (4/8) Epoch 12, batch 3850, loss[loss=0.1867, simple_loss=0.2763, pruned_loss=0.04853, over 7201.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2814, pruned_loss=0.04571, over 1426029.00 frames.], batch size: 22, lr: 5.83e-04
2022-04-29 04:40:13,128 INFO [train.py:763] (4/8) Epoch 12, batch 3900, loss[loss=0.1818, simple_loss=0.2831, pruned_loss=0.0403, over 7296.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2814, pruned_loss=0.0455, over 1424790.96 frames.], batch size: 24, lr: 5.83e-04
2022-04-29 04:41:18,534 INFO [train.py:763] (4/8) Epoch 12, batch 3950, loss[loss=0.1777, simple_loss=0.2763, pruned_loss=0.03961, over 7197.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2813, pruned_loss=0.04552, over 1423968.88 frames.], batch size: 23, lr: 5.83e-04
2022-04-29 04:42:24,200 INFO [train.py:763] (4/8) Epoch 12, batch 4000, loss[loss=0.1805, simple_loss=0.2712, pruned_loss=0.04492, over 7111.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2817, pruned_loss=0.04593, over 1423274.22 frames.], batch size: 17, lr: 5.83e-04
2022-04-29 04:43:29,489 INFO [train.py:763] (4/8) Epoch 12, batch 4050, loss[loss=0.198, simple_loss=0.2988, pruned_loss=0.04862, over 7240.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2811, pruned_loss=0.04574, over 1425171.18 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:44:35,687 INFO [train.py:763] (4/8) Epoch 12, batch 4100, loss[loss=0.196, simple_loss=0.2959, pruned_loss=0.04803, over 7145.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2804, pruned_loss=0.04601, over 1424841.95 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:45:41,164 INFO [train.py:763] (4/8) Epoch 12, batch 4150, loss[loss=0.163, simple_loss=0.2544, pruned_loss=0.03576, over 7439.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2818, pruned_loss=0.04646, over 1419708.74 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:46:48,354 INFO [train.py:763] (4/8) Epoch 12, batch 4200, loss[loss=0.176, simple_loss=0.2794, pruned_loss=0.03629, over 7144.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2804, pruned_loss=0.04561, over 1420507.86 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:47:54,426 INFO [train.py:763] (4/8) Epoch 12, batch 4250, loss[loss=0.1791, simple_loss=0.2819, pruned_loss=0.03812, over 7198.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2798, pruned_loss=0.04535, over 1418748.83 frames.], batch size: 26, lr: 5.81e-04
2022-04-29 04:49:00,802 INFO [train.py:763] (4/8) Epoch 12, batch 4300, loss[loss=0.1799, simple_loss=0.2771, pruned_loss=0.04131, over 7426.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2811, pruned_loss=0.04596, over 1415824.62 frames.], batch size: 20, lr: 5.81e-04
2022-04-29 04:50:06,807 INFO [train.py:763] (4/8) Epoch 12, batch 4350, loss[loss=0.1446, simple_loss=0.2332, pruned_loss=0.02797, over 6995.00 frames.], tot_loss[loss=0.1868, simple_loss=0.281, pruned_loss=0.04637, over 1411676.29 frames.], batch size: 16, lr: 5.81e-04
2022-04-29 04:51:13,413 INFO [train.py:763] (4/8) Epoch 12, batch 4400, loss[loss=0.2398, simple_loss=0.3268, pruned_loss=0.07635, over 5172.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2797, pruned_loss=0.04593, over 1410899.77 frames.], batch size: 52, lr: 5.81e-04
2022-04-29 04:52:19,269 INFO [train.py:763] (4/8) Epoch 12, batch 4450, loss[loss=0.205, simple_loss=0.3006, pruned_loss=0.05477, over 7296.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2792, pruned_loss=0.04561, over 1408514.80 frames.], batch size: 24, lr: 5.81e-04
2022-04-29 04:53:25,176 INFO [train.py:763] (4/8) Epoch 12, batch 4500, loss[loss=0.1823, simple_loss=0.2801, pruned_loss=0.0422, over 7415.00 frames.], tot_loss[loss=0.186, simple_loss=0.2799, pruned_loss=0.04601, over 1389621.61 frames.], batch size: 21, lr: 5.80e-04
2022-04-29 04:54:31,134 INFO [train.py:763] (4/8) Epoch 12, batch 4550, loss[loss=0.2014, simple_loss=0.2919, pruned_loss=0.05545, over 5065.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2837, pruned_loss=0.04798, over 1355371.98 frames.], batch size: 52, lr: 5.80e-04
2022-04-29 04:56:09,893 INFO [train.py:763] (4/8) Epoch 13, batch 0, loss[loss=0.2105, simple_loss=0.3069, pruned_loss=0.05701, over 7395.00 frames.], tot_loss[loss=0.2105, simple_loss=0.3069, pruned_loss=0.05701, over 7395.00 frames.], batch size: 23, lr: 5.61e-04
2022-04-29 04:57:15,970 INFO [train.py:763] (4/8) Epoch 13, batch 50, loss[loss=0.2437, simple_loss=0.3266, pruned_loss=0.08041, over 7121.00 frames.], tot_loss[loss=0.182, simple_loss=0.2761, pruned_loss=0.04398, over 322352.42 frames.], batch size: 21, lr: 5.61e-04
2022-04-29 04:58:22,261 INFO [train.py:763] (4/8) Epoch 13, batch 100, loss[loss=0.1936, simple_loss=0.2795, pruned_loss=0.05392, over 7151.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2783, pruned_loss=0.0437, over 572349.91 frames.], batch size: 20, lr: 5.61e-04
2022-04-29 04:59:28,139 INFO [train.py:763] (4/8) Epoch 13, batch 150, loss[loss=0.1684, simple_loss=0.2499, pruned_loss=0.04345, over 6999.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2764, pruned_loss=0.04328, over 763183.24 frames.], batch size: 16, lr: 5.61e-04
2022-04-29 05:00:33,583 INFO [train.py:763] (4/8) Epoch 13, batch 200, loss[loss=0.1979, simple_loss=0.2922, pruned_loss=0.05176, over 7202.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2781, pruned_loss=0.04362, over 910394.04 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:01:39,400 INFO [train.py:763] (4/8) Epoch 13, batch 250, loss[loss=0.2002, simple_loss=0.2947, pruned_loss=0.05282, over 7219.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2788, pruned_loss=0.04417, over 1026070.35 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:02:44,820 INFO [train.py:763] (4/8) Epoch 13, batch 300, loss[loss=0.178, simple_loss=0.2807, pruned_loss=0.03761, over 7413.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2805, pruned_loss=0.04405, over 1112761.88 frames.], batch size: 21, lr: 5.60e-04
2022-04-29 05:03:50,335 INFO [train.py:763] (4/8) Epoch 13, batch 350, loss[loss=0.1833, simple_loss=0.2808, pruned_loss=0.04288, over 7412.00 frames.], tot_loss[loss=0.185, simple_loss=0.2804, pruned_loss=0.04475, over 1180699.86 frames.], batch size: 20, lr: 5.60e-04
2022-04-29 05:04:55,868 INFO [train.py:763] (4/8) Epoch 13, batch 400, loss[loss=0.1848, simple_loss=0.2874, pruned_loss=0.04112, over 7008.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2805, pruned_loss=0.04486, over 1230628.48 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:06:01,967 INFO [train.py:763] (4/8) Epoch 13, batch 450, loss[loss=0.2022, simple_loss=0.2976, pruned_loss=0.05335, over 6416.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2799, pruned_loss=0.04454, over 1273381.22 frames.], batch size: 37, lr: 5.59e-04
2022-04-29 05:07:07,982 INFO [train.py:763] (4/8) Epoch 13, batch 500, loss[loss=0.2074, simple_loss=0.3033, pruned_loss=0.05572, over 7078.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2792, pruned_loss=0.04431, over 1301701.50 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:08:13,587 INFO [train.py:763] (4/8) Epoch 13, batch 550, loss[loss=0.1849, simple_loss=0.2889, pruned_loss=0.04049, over 6392.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2798, pruned_loss=0.0445, over 1326479.72 frames.], batch size: 38, lr: 5.59e-04
2022-04-29 05:09:19,615 INFO [train.py:763] (4/8) Epoch 13, batch 600, loss[loss=0.1991, simple_loss=0.2976, pruned_loss=0.05035, over 7321.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2792, pruned_loss=0.04445, over 1348717.72 frames.], batch size: 21, lr: 5.59e-04
2022-04-29 05:10:25,761 INFO [train.py:763] (4/8) Epoch 13, batch 650, loss[loss=0.187, simple_loss=0.2808, pruned_loss=0.04657, over 7064.00 frames.], tot_loss[loss=0.1849, simple_loss=0.28, pruned_loss=0.0449, over 1361444.11 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:11:32,548 INFO [train.py:763] (4/8) Epoch 13, batch 700, loss[loss=0.167, simple_loss=0.2594, pruned_loss=0.03727, over 7283.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2797, pruned_loss=0.0447, over 1376477.25 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:12:37,743 INFO [train.py:763] (4/8) Epoch 13, batch 750, loss[loss=0.2199, simple_loss=0.311, pruned_loss=0.0644, over 7210.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2797, pruned_loss=0.04452, over 1383192.77 frames.], batch size: 23, lr: 5.58e-04
2022-04-29 05:13:44,374 INFO [train.py:763] (4/8) Epoch 13, batch 800, loss[loss=0.2081, simple_loss=0.3042, pruned_loss=0.05596, over 7287.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2804, pruned_loss=0.04427, over 1392066.68 frames.], batch size: 25, lr: 5.58e-04
2022-04-29 05:14:50,890 INFO [train.py:763] (4/8) Epoch 13, batch 850, loss[loss=0.1765, simple_loss=0.2778, pruned_loss=0.03758, over 7208.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2797, pruned_loss=0.04409, over 1399844.69 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:15:57,546 INFO [train.py:763] (4/8) Epoch 13, batch 900, loss[loss=0.1767, simple_loss=0.2612, pruned_loss=0.0461, over 7177.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04465, over 1403065.14 frames.], batch size: 18, lr: 5.57e-04
2022-04-29 05:17:04,245 INFO [train.py:763] (4/8) Epoch 13, batch 950, loss[loss=0.1649, simple_loss=0.2614, pruned_loss=0.03425, over 7224.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2808, pruned_loss=0.04466, over 1403727.26 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:18:11,092 INFO [train.py:763] (4/8) Epoch 13, batch 1000, loss[loss=0.2152, simple_loss=0.3065, pruned_loss=0.06194, over 7191.00 frames.], tot_loss[loss=0.185, simple_loss=0.2804, pruned_loss=0.04483, over 1410745.82 frames.], batch size: 22, lr: 5.57e-04
2022-04-29 05:19:17,013 INFO [train.py:763] (4/8) Epoch 13, batch 1050, loss[loss=0.1783, simple_loss=0.2754, pruned_loss=0.04062, over 7413.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2801, pruned_loss=0.04479, over 1410523.29 frames.], batch size: 21, lr: 5.56e-04
2022-04-29 05:20:22,744 INFO [train.py:763] (4/8) Epoch 13, batch 1100, loss[loss=0.1766, simple_loss=0.2801, pruned_loss=0.03654, over 6784.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2799, pruned_loss=0.0446, over 1410644.52 frames.], batch size: 31, lr: 5.56e-04
2022-04-29 05:21:28,693 INFO [train.py:763] (4/8) Epoch 13, batch 1150, loss[loss=0.2011, simple_loss=0.2985, pruned_loss=0.05183, over 7350.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2811, pruned_loss=0.04537, over 1410090.69 frames.], batch size: 22, lr: 5.56e-04
2022-04-29 05:22:34,607 INFO [train.py:763] (4/8) Epoch 13, batch 1200, loss[loss=0.2139, simple_loss=0.2945, pruned_loss=0.06668, over 4965.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2806, pruned_loss=0.04498, over 1410196.03 frames.], batch size: 54, lr: 5.56e-04
2022-04-29 05:23:40,298 INFO [train.py:763] (4/8) Epoch 13, batch 1250, loss[loss=0.197, simple_loss=0.295, pruned_loss=0.04949, over 7434.00 frames.], tot_loss[loss=0.1857, simple_loss=0.281, pruned_loss=0.04514, over 1414177.70 frames.], batch size: 20, lr: 5.56e-04
2022-04-29 05:24:45,574 INFO [train.py:763] (4/8) Epoch 13, batch 1300, loss[loss=0.1755, simple_loss=0.2684, pruned_loss=0.0413, over 7257.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2808, pruned_loss=0.04506, over 1417841.92 frames.], batch size: 19, lr: 5.55e-04
2022-04-29 05:25:51,456 INFO [train.py:763] (4/8) Epoch 13, batch 1350, loss[loss=0.162, simple_loss=0.2606, pruned_loss=0.03171, over 7265.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2794, pruned_loss=0.04438, over 1422020.82 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:26:57,106 INFO [train.py:763] (4/8) Epoch 13, batch 1400, loss[loss=0.153, simple_loss=0.24, pruned_loss=0.03298, over 7175.00 frames.], tot_loss[loss=0.184, simple_loss=0.2796, pruned_loss=0.04419, over 1417929.88 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:28:02,589 INFO [train.py:763] (4/8) Epoch 13, batch 1450, loss[loss=0.1396, simple_loss=0.233, pruned_loss=0.02308, over 7271.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2789, pruned_loss=0.04404, over 1421444.90 frames.], batch size: 17, lr: 5.55e-04
2022-04-29 05:29:08,107 INFO [train.py:763] (4/8) Epoch 13, batch 1500, loss[loss=0.1689, simple_loss=0.2572, pruned_loss=0.04029, over 7281.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2774, pruned_loss=0.04338, over 1422211.10 frames.], batch size: 17, lr: 5.54e-04
2022-04-29 05:30:14,044 INFO [train.py:763] (4/8) Epoch 13, batch 1550, loss[loss=0.1983, simple_loss=0.2862, pruned_loss=0.05525, over 6590.00 frames.], tot_loss[loss=0.1828, simple_loss=0.278, pruned_loss=0.04382, over 1417303.68 frames.], batch size: 38, lr: 5.54e-04
2022-04-29 05:31:19,476 INFO [train.py:763] (4/8) Epoch 13, batch 1600, loss[loss=0.1605, simple_loss=0.2636, pruned_loss=0.02871, over 7415.00 frames.], tot_loss[loss=0.1838, simple_loss=0.279, pruned_loss=0.04435, over 1416503.84 frames.], batch size: 21, lr: 5.54e-04
2022-04-29 05:32:25,606 INFO [train.py:763] (4/8) Epoch 13, batch 1650, loss[loss=0.1646, simple_loss=0.2652, pruned_loss=0.03196, over 7227.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2797, pruned_loss=0.04464, over 1419045.93 frames.], batch size: 20, lr: 5.54e-04
2022-04-29 05:33:31,236 INFO [train.py:763] (4/8) Epoch 13, batch 1700, loss[loss=0.1757, simple_loss=0.2684, pruned_loss=0.04147, over 6356.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2802, pruned_loss=0.04447, over 1418449.58 frames.], batch size: 37, lr: 5.54e-04
2022-04-29 05:34:36,765 INFO [train.py:763] (4/8) Epoch 13, batch 1750, loss[loss=0.1561, simple_loss=0.2435, pruned_loss=0.03438, over 7274.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2794, pruned_loss=0.04444, over 1420929.18 frames.], batch size: 17, lr: 5.53e-04
2022-04-29 05:35:42,699 INFO [train.py:763] (4/8) Epoch 13, batch 1800, loss[loss=0.1903, simple_loss=0.2824, pruned_loss=0.0491, over 7148.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2789, pruned_loss=0.04407, over 1425005.27 frames.], batch size: 20, lr: 5.53e-04
2022-04-29 05:36:48,184 INFO [train.py:763] (4/8) Epoch 13, batch 1850, loss[loss=0.2285, simple_loss=0.3128, pruned_loss=0.07208, over 7290.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2795, pruned_loss=0.0446, over 1425027.22 frames.], batch size: 25, lr: 5.53e-04
2022-04-29 05:37:54,117 INFO [train.py:763] (4/8) Epoch 13, batch 1900, loss[loss=0.1838, simple_loss=0.2788, pruned_loss=0.0444, over 6537.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2798, pruned_loss=0.04472, over 1421371.52 frames.], batch size: 38, lr: 5.53e-04
2022-04-29 05:39:00,690 INFO [train.py:763] (4/8) Epoch 13, batch 1950, loss[loss=0.1695, simple_loss=0.253, pruned_loss=0.04299, over 7250.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2799, pruned_loss=0.04474, over 1422933.28 frames.], batch size: 19, lr: 5.52e-04
2022-04-29 05:40:07,431 INFO [train.py:763] (4/8) Epoch 13, batch 2000, loss[loss=0.1868, simple_loss=0.2887, pruned_loss=0.0424, over 7343.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2796, pruned_loss=0.04465, over 1424590.65 frames.], batch size: 22, lr: 5.52e-04
2022-04-29 05:41:13,023 INFO [train.py:763] (4/8) Epoch 13, batch 2050, loss[loss=0.1858, simple_loss=0.2811, pruned_loss=0.04527, over 7373.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2797, pruned_loss=0.04499, over 1426073.68 frames.], batch size: 23, lr: 5.52e-04
2022-04-29 05:42:18,152 INFO [train.py:763] (4/8) Epoch 13, batch 2100, loss[loss=0.2063, simple_loss=0.3061, pruned_loss=0.0532, over 7227.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2808, pruned_loss=0.0453, over 1425290.57 frames.], batch size: 20, lr: 5.52e-04
2022-04-29 05:43:24,240 INFO [train.py:763] (4/8) Epoch 13, batch 2150, loss[loss=0.2184, simple_loss=0.3008, pruned_loss=0.06801, over 7191.00 frames.], tot_loss[loss=0.185, simple_loss=0.2803, pruned_loss=0.04484, over 1427894.63 frames.], batch size: 26, lr: 5.52e-04
2022-04-29 05:44:29,756 INFO [train.py:763] (4/8) Epoch 13, batch 2200, loss[loss=0.1568, simple_loss=0.2493, pruned_loss=0.03215, over 7435.00 frames.], tot_loss[loss=0.1849, simple_loss=0.28, pruned_loss=0.04489, over 1425994.76 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:45:35,366 INFO [train.py:763] (4/8) Epoch 13, batch 2250, loss[loss=0.1937, simple_loss=0.2938, pruned_loss=0.04677, over 7239.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2805, pruned_loss=0.04488, over 1427589.04 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:46:41,458 INFO [train.py:763] (4/8) Epoch 13, batch 2300, loss[loss=0.2164, simple_loss=0.3109, pruned_loss=0.06094, over 7044.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2794, pruned_loss=0.04458, over 1428191.11 frames.], batch size: 28, lr: 5.51e-04
2022-04-29 05:47:46,890 INFO [train.py:763] (4/8) Epoch 13, batch 2350, loss[loss=0.2073, simple_loss=0.2992, pruned_loss=0.05774, over 5283.00 frames.], tot_loss[loss=0.184, simple_loss=0.2789, pruned_loss=0.04454, over 1426978.91 frames.], batch size: 52, lr: 5.51e-04
2022-04-29 05:48:52,767 INFO [train.py:763] (4/8) Epoch 13, batch 2400, loss[loss=0.1833, simple_loss=0.264, pruned_loss=0.05127, over 7286.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2781, pruned_loss=0.0441, over 1428585.42 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:49:58,371 INFO [train.py:763] (4/8) Epoch 13, batch 2450, loss[loss=0.2025, simple_loss=0.2951, pruned_loss=0.05493, over 6817.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2785, pruned_loss=0.04437, over 1431323.39 frames.], batch size: 31, lr: 5.50e-04
2022-04-29 05:51:03,648 INFO [train.py:763] (4/8) Epoch 13, batch 2500, loss[loss=0.1636, simple_loss=0.2561, pruned_loss=0.03549, over 7277.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2797, pruned_loss=0.04487, over 1427467.96 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:52:08,889 INFO [train.py:763] (4/8) Epoch 13, batch 2550, loss[loss=0.2028, simple_loss=0.297, pruned_loss=0.05428, over 7303.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2797, pruned_loss=0.04498, over 1423192.88 frames.], batch size: 25, lr: 5.50e-04
2022-04-29 05:53:14,607 INFO [train.py:763] (4/8) Epoch 13, batch 2600, loss[loss=0.1811, simple_loss=0.2865, pruned_loss=0.0379, over 7414.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2795, pruned_loss=0.04453, over 1419516.64 frames.], batch size: 21, lr: 5.50e-04
2022-04-29 05:54:20,018 INFO [train.py:763] (4/8) Epoch 13, batch 2650, loss[loss=0.1815, simple_loss=0.2752, pruned_loss=0.04387, over 7119.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2796, pruned_loss=0.04453, over 1417946.04 frames.], batch size: 21, lr: 5.49e-04
2022-04-29 05:55:25,826 INFO [train.py:763] (4/8) Epoch 13, batch 2700, loss[loss=0.1911, simple_loss=0.2712, pruned_loss=0.05552, over 6988.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2789, pruned_loss=0.04434, over 1421887.13 frames.], batch size: 16, lr: 5.49e-04
2022-04-29 05:56:31,324 INFO [train.py:763] (4/8) Epoch 13, batch 2750, loss[loss=0.1799, simple_loss=0.282, pruned_loss=0.03889, over 7306.00 frames.], tot_loss[loss=0.183, simple_loss=0.2782, pruned_loss=0.04385, over 1427069.95 frames.], batch size: 24, lr: 5.49e-04
2022-04-29 05:57:36,852 INFO [train.py:763] (4/8) Epoch 13, batch 2800, loss[loss=0.1577, simple_loss=0.2461, pruned_loss=0.03462, over 7132.00 frames.], tot_loss[loss=0.183, simple_loss=0.2782, pruned_loss=0.04391, over 1425221.27 frames.], batch size: 17, lr: 5.49e-04
2022-04-29 05:58:42,724 INFO [train.py:763] (4/8) Epoch 13, batch 2850, loss[loss=0.2064, simple_loss=0.3019, pruned_loss=0.05542, over 7409.00 frames.], tot_loss[loss=0.183, simple_loss=0.2778, pruned_loss=0.0441, over 1426529.13 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 05:59:48,435 INFO [train.py:763] (4/8) Epoch 13, batch 2900, loss[loss=0.1654, simple_loss=0.2672, pruned_loss=0.03177, over 7122.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2785, pruned_loss=0.04415, over 1427889.06 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 06:00:53,879 INFO [train.py:763] (4/8) Epoch 13, batch 2950, loss[loss=0.2242, simple_loss=0.3187, pruned_loss=0.06487, over 7191.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2788, pruned_loss=0.0437, over 1429806.02 frames.], batch size: 23, lr: 5.48e-04
2022-04-29 06:01:59,745 INFO [train.py:763] (4/8) Epoch 13, batch 3000, loss[loss=0.183, simple_loss=0.2766, pruned_loss=0.04474, over 7279.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2779, pruned_loss=0.04349, over 1430449.59 frames.], batch size: 24, lr: 5.48e-04
2022-04-29 06:01:59,746 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 06:02:15,158 INFO [train.py:792] (4/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
2022-04-29 06:03:21,970 INFO [train.py:763] (4/8) Epoch 13, batch 3050, loss[loss=0.1671, simple_loss=0.2533, pruned_loss=0.04043, over 7287.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2781, pruned_loss=0.04384, over 1430669.85 frames.], batch size: 17, lr: 5.48e-04
2022-04-29 06:04:29,181 INFO [train.py:763] (4/8) Epoch 13, batch 3100, loss[loss=0.1862, simple_loss=0.2825, pruned_loss=0.04497, over 7204.00 frames.], tot_loss[loss=0.183, simple_loss=0.278, pruned_loss=0.04394, over 1432503.58 frames.], batch size: 23, lr: 5.47e-04
2022-04-29 06:05:35,703 INFO [train.py:763] (4/8) Epoch 13, batch 3150, loss[loss=0.2115, simple_loss=0.2984, pruned_loss=0.06233, over 4972.00 frames.], tot_loss[loss=0.182, simple_loss=0.277, pruned_loss=0.04351, over 1429974.09 frames.], batch size: 52, lr: 5.47e-04
2022-04-29 06:06:41,342 INFO [train.py:763] (4/8) Epoch 13, batch 3200, loss[loss=0.1799, simple_loss=0.2809, pruned_loss=0.03952, over 7327.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2772, pruned_loss=0.04368, over 1430450.09 frames.], batch size: 22, lr: 5.47e-04
2022-04-29 06:07:46,882 INFO [train.py:763] (4/8) Epoch 13, batch 3250, loss[loss=0.2211, simple_loss=0.311, pruned_loss=0.06558, over 7136.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2781, pruned_loss=0.04415, over 1427398.54 frames.], batch size: 26, lr: 5.47e-04
2022-04-29 06:08:52,445 INFO [train.py:763] (4/8) Epoch 13, batch 3300, loss[loss=0.1604, simple_loss=0.2524, pruned_loss=0.03422, over 7169.00 frames.], tot_loss[loss=0.184, simple_loss=0.2785, pruned_loss=0.04473, over 1424098.22 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:09:57,826 INFO [train.py:763] (4/8) Epoch 13, batch 3350, loss[loss=0.1687, simple_loss=0.2626, pruned_loss=0.03741, over 7412.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2787, pruned_loss=0.04445, over 1426327.28 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:11:03,347 INFO [train.py:763] (4/8) Epoch 13, batch 3400, loss[loss=0.1752, simple_loss=0.2603, pruned_loss=0.04506, over 7178.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2788, pruned_loss=0.04455, over 1427982.53 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:12:10,251 INFO [train.py:763] (4/8) Epoch 13, batch 3450, loss[loss=0.1781, simple_loss=0.28, pruned_loss=0.03808, over 7112.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2787, pruned_loss=0.04433, over 1426376.17 frames.], batch size: 21, lr: 5.46e-04
2022-04-29 06:13:16,582 INFO [train.py:763] (4/8) Epoch 13, batch 3500, loss[loss=0.1804, simple_loss=0.284, pruned_loss=0.03845, over 7331.00 frames.], tot_loss[loss=0.183, simple_loss=0.2777, pruned_loss=0.0441, over 1427975.20 frames.], batch size: 22, lr: 5.46e-04
2022-04-29 06:14:22,078 INFO [train.py:763] (4/8) Epoch 13, batch 3550, loss[loss=0.1999, simple_loss=0.293, pruned_loss=0.05338, over 7318.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2781, pruned_loss=0.04428, over 1428080.39 frames.], batch size: 21, lr: 5.45e-04
2022-04-29 06:15:27,776 INFO [train.py:763] (4/8) Epoch 13, batch 3600, loss[loss=0.1715, simple_loss=0.2798, pruned_loss=0.03163, over 7353.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2772, pruned_loss=0.044, over 1430230.14 frames.], batch size: 19, lr: 5.45e-04
2022-04-29 06:16:33,705 INFO [train.py:763] (4/8) Epoch 13, batch 3650, loss[loss=0.1989, simple_loss=0.2981, pruned_loss=0.04982, over 7230.00 frames.], tot_loss[loss=0.182, simple_loss=0.2767, pruned_loss=0.04366, over 1430013.62 frames.], batch size: 20, lr: 5.45e-04
2022-04-29 06:17:39,180 INFO [train.py:763] (4/8) Epoch 13, batch 3700, loss[loss=0.2333, simple_loss=0.335, pruned_loss=0.06578, over 7281.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2778, pruned_loss=0.04385, over 1421423.92 frames.], batch size: 24, lr: 5.45e-04
2022-04-29 06:18:44,835 INFO [train.py:763] (4/8) Epoch 13, batch 3750, loss[loss=0.214, simple_loss=0.2939, pruned_loss=0.06702, over 4963.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2786, pruned_loss=0.04447, over 1419538.50 frames.], batch size: 52, lr: 5.45e-04
2022-04-29 06:19:51,469 INFO [train.py:763] (4/8) Epoch 13, batch 3800, loss[loss=0.1464, simple_loss=0.2466, pruned_loss=0.02313, over 6989.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2791, pruned_loss=0.0443, over 1419366.62 frames.], batch size: 16, lr: 5.44e-04
2022-04-29 06:20:57,069 INFO [train.py:763] (4/8) Epoch 13, batch 3850, loss[loss=0.1969, simple_loss=0.2962, pruned_loss=0.04876, over 7209.00 frames.], tot_loss[loss=0.1838, simple_loss=0.279, pruned_loss=0.04424, over 1420228.85 frames.], batch size: 22, lr: 5.44e-04
2022-04-29 06:22:02,332 INFO [train.py:763] (4/8) Epoch 13, batch 3900, loss[loss=0.1777, simple_loss=0.2789, pruned_loss=0.03822, over 7316.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2798, pruned_loss=0.04476, over 1422517.64 frames.], batch size: 21, lr: 5.44e-04
2022-04-29 06:23:08,128 INFO [train.py:763] (4/8) Epoch 13, batch 3950, loss[loss=0.2231, simple_loss=0.2971, pruned_loss=0.07458, over 5360.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2792, pruned_loss=0.04435, over 1421967.83 frames.], batch size: 52, lr: 5.44e-04
2022-04-29 06:24:13,267 INFO [train.py:763] (4/8) Epoch 13, batch 4000, loss[loss=0.1935, simple_loss=0.2971, pruned_loss=0.04499, over 7339.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2799, pruned_loss=0.04425, over 1423555.23 frames.], batch size: 22, lr: 5.43e-04
2022-04-29 06:25:19,010 INFO [train.py:763] (4/8) Epoch 13, batch 4050, loss[loss=0.1594, simple_loss=0.2587, pruned_loss=0.03008, over 6820.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2793, pruned_loss=0.04402, over 1424779.74 frames.], batch size: 15, lr: 5.43e-04
2022-04-29 06:26:24,352 INFO [train.py:763] (4/8) Epoch 13, batch 4100, loss[loss=0.1927, simple_loss=0.2832, pruned_loss=0.05106, over 6702.00 frames.], tot_loss[loss=0.184, simple_loss=0.279, pruned_loss=0.04455, over 1421384.00 frames.], batch size: 31, lr: 5.43e-04
2022-04-29 06:27:29,931 INFO [train.py:763] (4/8) Epoch 13, batch 4150, loss[loss=0.1847, simple_loss=0.2928, pruned_loss=0.0383, over 7227.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2786, pruned_loss=0.04412, over 1419686.59 frames.], batch size: 21, lr: 5.43e-04
2022-04-29 06:28:36,034 INFO [train.py:763] (4/8) Epoch 13, batch 4200, loss[loss=0.1606, simple_loss=0.2503, pruned_loss=0.03545, over 7286.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2773, pruned_loss=0.0436, over 1420839.95 frames.], batch size: 17, lr: 5.43e-04
2022-04-29 06:29:41,275 INFO [train.py:763] (4/8) Epoch 13, batch 4250, loss[loss=0.201, simple_loss=0.2939, pruned_loss=0.05405, over 6319.00 frames.], tot_loss[loss=0.183, simple_loss=0.2779, pruned_loss=0.04404, over 1415153.48 frames.], batch size: 38, lr: 5.42e-04
2022-04-29 06:30:47,743 INFO [train.py:763] (4/8) Epoch 13, batch 4300, loss[loss=0.2049, simple_loss=0.3071, pruned_loss=0.0513, over 7218.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2787, pruned_loss=0.04439, over 1412042.43 frames.], batch size: 21, lr: 5.42e-04
2022-04-29 06:31:53,158 INFO [train.py:763] (4/8) Epoch 13, batch 4350, loss[loss=0.1378, simple_loss=0.2237, pruned_loss=0.02591, over 6774.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2786, pruned_loss=0.04423, over 1408134.47 frames.], batch size: 15, lr: 5.42e-04
2022-04-29 06:33:10,014 INFO [train.py:763] (4/8) Epoch 13, batch 4400, loss[loss=0.2049, simple_loss=0.3135, pruned_loss=0.04819, over 7148.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2787, pruned_loss=0.04438, over 1402840.95 frames.], batch size: 20, lr: 5.42e-04
2022-04-29 06:34:14,929 INFO [train.py:763] (4/8) Epoch 13, batch 4450, loss[loss=0.2233, simple_loss=0.3013, pruned_loss=0.07264, over 4894.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.0443, over 1392979.29 frames.], batch size: 52, lr: 5.42e-04
2022-04-29 06:35:30,492 INFO [train.py:763] (4/8) Epoch 13, batch 4500, loss[loss=0.2098, simple_loss=0.2974, pruned_loss=0.06104, over 5253.00 frames.], tot_loss[loss=0.185, simple_loss=0.2801, pruned_loss=0.04496, over 1377561.03 frames.], batch size: 53, lr: 5.41e-04
2022-04-29 06:36:35,406 INFO [train.py:763] (4/8) Epoch 13, batch 4550, loss[loss=0.2253, simple_loss=0.3186, pruned_loss=0.06601, over 6802.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2799, pruned_loss=0.04528, over 1367019.92 frames.], batch size: 31, lr: 5.41e-04
2022-04-29 06:38:13,966 INFO [train.py:763] (4/8) Epoch 14, batch 0, loss[loss=0.1941, simple_loss=0.2933, pruned_loss=0.04744, over 7035.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2933, pruned_loss=0.04744, over 7035.00 frames.], batch size: 28, lr: 5.25e-04
2022-04-29 06:39:20,733 INFO [train.py:763] (4/8) Epoch 14, batch 50, loss[loss=0.2431, simple_loss=0.3189, pruned_loss=0.08369, over 4799.00 frames.], tot_loss[loss=0.1843, simple_loss=0.28, pruned_loss=0.04426, over 321467.83 frames.], batch size: 52, lr: 5.24e-04
2022-04-29 06:40:45,782 INFO [train.py:763] (4/8) Epoch 14, batch 100, loss[loss=0.2275, simple_loss=0.3141, pruned_loss=0.07039, over 7162.00 frames.], tot_loss[loss=0.184, simple_loss=0.2796, pruned_loss=0.0442, over 567783.24 frames.], batch size: 18, lr: 5.24e-04
2022-04-29 06:41:59,829 INFO [train.py:763] (4/8) Epoch 14, batch 150, loss[loss=0.1751, simple_loss=0.2818, pruned_loss=0.03419, over 7116.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2812, pruned_loss=0.04408, over 758455.26 frames.], batch size: 21, lr: 5.24e-04
2022-04-29 06:43:06,513 INFO [train.py:763] (4/8) Epoch 14, batch 200, loss[loss=0.1827, simple_loss=0.2835, pruned_loss=0.04092, over 7328.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2818, pruned_loss=0.04448, over 902557.72 frames.], batch size: 20, lr: 5.24e-04
2022-04-29 06:44:23,223 INFO [train.py:763] (4/8) Epoch 14, batch 250, loss[loss=0.2078, simple_loss=0.3057, pruned_loss=0.05498, over 6359.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2814, pruned_loss=0.0445, over 1019715.61 frames.], batch size: 37, lr: 5.24e-04
2022-04-29 06:45:48,391 INFO [train.py:763] (4/8) Epoch 14, batch 300, loss[loss=0.1605, simple_loss=0.2562, pruned_loss=0.03235, over 7125.00 frames.], tot_loss[loss=0.1832, simple_loss=0.279, pruned_loss=0.04368, over 1109010.53 frames.], batch size: 17, lr: 5.23e-04
2022-04-29 06:46:55,901 INFO [train.py:763] (4/8) Epoch 14, batch 350, loss[loss=0.1603, simple_loss=0.2498, pruned_loss=0.03537, over 7217.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2789, pruned_loss=0.04386, over 1171653.22 frames.], batch size: 16, lr: 5.23e-04
2022-04-29 06:48:03,000 INFO [train.py:763] (4/8) Epoch 14, batch 400, loss[loss=0.1642, simple_loss=0.279, pruned_loss=0.02469, over 7150.00 frames.], tot_loss[loss=0.183, simple_loss=0.2787, pruned_loss=0.04369, over 1226809.61 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:49:01,684 INFO [train.py:763] (4/8) Epoch 14, batch 450, loss[loss=0.1802, simple_loss=0.276, pruned_loss=0.04226, over 7169.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2782, pruned_loss=0.04325, over 1271413.96 frames.], batch size: 19, lr: 5.23e-04
2022-04-29 06:50:05,438 INFO [train.py:763] (4/8) Epoch 14, batch 500, loss[loss=0.1729, simple_loss=0.2609, pruned_loss=0.04247, over 7434.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2776, pruned_loss=0.04306, over 1303016.21 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:51:07,459 INFO [train.py:763] (4/8) Epoch 14, batch 550, loss[loss=0.1485, simple_loss=0.2351, pruned_loss=0.0309, over 7279.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2772, pruned_loss=0.04271, over 1331696.60 frames.], batch size: 18, lr: 5.22e-04
2022-04-29 06:52:12,671 INFO [train.py:763] (4/8) Epoch 14, batch 600, loss[loss=0.1715, simple_loss=0.2639, pruned_loss=0.0395, over 7243.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2771, pruned_loss=0.0428, over 1354565.79 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:53:18,166 INFO [train.py:763] (4/8) Epoch 14, batch 650, loss[loss=0.2016, simple_loss=0.3058, pruned_loss=0.04866, over 7348.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2773, pruned_loss=0.04256, over 1369237.97 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:54:23,429 INFO [train.py:763] (4/8) Epoch 14, batch 700, loss[loss=0.182, simple_loss=0.2804, pruned_loss=0.04182, over 7334.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2779, pruned_loss=0.04272, over 1382959.77 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:55:28,864 INFO [train.py:763] (4/8) Epoch 14, batch 750, loss[loss=0.1801, simple_loss=0.2899, pruned_loss=0.03508, over 7318.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2775, pruned_loss=0.04264, over 1391522.86 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:56:34,176 INFO [train.py:763] (4/8) Epoch 14, batch 800, loss[loss=0.1742, simple_loss=0.2756, pruned_loss=0.03636, over 7342.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2774, pruned_loss=0.04238, over 1399803.96 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 06:57:40,705 INFO [train.py:763] (4/8) Epoch 14, batch 850, loss[loss=0.1698, simple_loss=0.2618, pruned_loss=0.03894, over 7132.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2774, pruned_loss=0.04208, over 1402331.44 frames.], batch size: 17, lr: 5.21e-04
2022-04-29 06:58:46,052 INFO [train.py:763] (4/8) Epoch 14, batch 900, loss[loss=0.1841, simple_loss=0.2714, pruned_loss=0.04839, over 7264.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2777, pruned_loss=0.0426, over 1397215.78 frames.], batch size: 19, lr: 5.21e-04
2022-04-29 06:59:51,291 INFO [train.py:763] (4/8) Epoch 14, batch 950, loss[loss=0.2219, simple_loss=0.32, pruned_loss=0.06191, over 7328.00 frames.], tot_loss[loss=0.1825, simple_loss=0.279, pruned_loss=0.04299, over 1405566.48 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 07:00:56,951 INFO [train.py:763] (4/8) Epoch 14, batch 1000, loss[loss=0.1866, simple_loss=0.2936, pruned_loss=0.0398, over 7152.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2789, pruned_loss=0.04301, over 1406560.53 frames.], batch size: 28, lr: 5.21e-04
2022-04-29 07:02:02,195 INFO [train.py:763] (4/8) Epoch 14, batch 1050, loss[loss=0.1736, simple_loss=0.259, pruned_loss=0.04409, over 7284.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2783, pruned_loss=0.04261, over 1412692.24 frames.], batch size: 18, lr: 5.20e-04
2022-04-29 07:03:07,567 INFO [train.py:763] (4/8) Epoch 14, batch 1100, loss[loss=0.1827, simple_loss=0.2655, pruned_loss=0.04996, over 7278.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2779, pruned_loss=0.04275, over 1416328.98 frames.], batch size: 17, lr: 5.20e-04
2022-04-29 07:04:13,186 INFO [train.py:763] (4/8) Epoch 14, batch 1150, loss[loss=0.1893, simple_loss=0.2875, pruned_loss=0.04554, over 7420.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04298, over 1420803.88 frames.], batch size: 21, lr: 5.20e-04
2022-04-29 07:05:18,950 INFO [train.py:763] (4/8) Epoch 14, batch 1200, loss[loss=0.1953, simple_loss=0.2861, pruned_loss=0.05223, over 7434.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2777, pruned_loss=0.04293, over 1422571.78 frames.], batch size: 20, lr: 5.20e-04
2022-04-29 07:06:24,244 INFO [train.py:763] (4/8) Epoch 14, batch 1250, loss[loss=0.1793, simple_loss=0.267, pruned_loss=0.0458, over 7355.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.0428, over 1425146.70 frames.], batch size: 19, lr: 5.20e-04
2022-04-29 07:07:29,932 INFO [train.py:763] (4/8) Epoch 14, batch 1300, loss[loss=0.1752, simple_loss=0.272, pruned_loss=0.03917, over 6363.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2772, pruned_loss=0.04286, over 1419124.88 frames.], batch size: 37, lr: 5.19e-04
2022-04-29 07:08:35,856 INFO [train.py:763] (4/8) Epoch 14, batch 1350, loss[loss=0.1704, simple_loss=0.2501, pruned_loss=0.04529, over 7002.00 frames.], tot_loss[loss=0.182, simple_loss=0.2781, pruned_loss=0.04297, over 1420480.00 frames.], batch size: 16, lr: 5.19e-04
2022-04-29 07:09:40,885 INFO [train.py:763] (4/8) Epoch 14, batch 1400, loss[loss=0.215, simple_loss=0.3131, pruned_loss=0.05845, over 7304.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2777, pruned_loss=0.04281, over 1420374.15 frames.], batch size: 24, lr: 5.19e-04
2022-04-29 07:10:46,112 INFO [train.py:763] (4/8) Epoch 14, batch 1450, loss[loss=0.1618, simple_loss=0.2617, pruned_loss=0.03091, over 7356.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2776, pruned_loss=0.04259, over 1417888.40 frames.], batch size: 23, lr: 5.19e-04
2022-04-29 07:11:52,454 INFO [train.py:763] (4/8) Epoch 14, batch 1500, loss[loss=0.1672, simple_loss=0.2781, pruned_loss=0.02813, over 7151.00 frames.], tot_loss[loss=0.182, simple_loss=0.2781, pruned_loss=0.04298, over 1411528.34 frames.], batch size: 20, lr: 5.19e-04
2022-04-29 07:12:59,675 INFO [train.py:763] (4/8) Epoch 14, batch 1550, loss[loss=0.1889, simple_loss=0.2962, pruned_loss=0.04083, over 7112.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2773, pruned_loss=0.04277, over 1416369.55 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:14:06,937 INFO [train.py:763] (4/8) Epoch 14, batch 1600, loss[loss=0.168, simple_loss=0.2709, pruned_loss=0.0325, over 7407.00 frames.], tot_loss[loss=0.1812, simple_loss=0.277, pruned_loss=0.04271, over 1418723.82 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:15:13,438 INFO [train.py:763] (4/8) Epoch 14, batch 1650, loss[loss=0.2021, simple_loss=0.2903, pruned_loss=0.05699, over 7188.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2761, pruned_loss=0.04227, over 1424090.75 frames.], batch size: 23, lr: 5.18e-04
2022-04-29 07:16:19,624 INFO [train.py:763] (4/8) Epoch 14, batch 1700, loss[loss=0.1859, simple_loss=0.2797, pruned_loss=0.04608, over 7304.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2757, pruned_loss=0.04237, over 1427695.09 frames.], batch size: 25, lr: 5.18e-04
2022-04-29 07:17:25,759 INFO [train.py:763] (4/8) Epoch 14, batch 1750, loss[loss=0.1822, simple_loss=0.2865, pruned_loss=0.03893, over 7069.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2762, pruned_loss=0.04301, over 1430510.69 frames.], batch size: 28, lr: 5.18e-04
2022-04-29 07:18:30,995 INFO [train.py:763] (4/8) Epoch 14, batch 1800, loss[loss=0.1488, simple_loss=0.2339, pruned_loss=0.03189, over 7280.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2765, pruned_loss=0.04293, over 1428027.54 frames.], batch size: 17, lr: 5.17e-04
2022-04-29 07:19:36,654 INFO [train.py:763] (4/8) Epoch 14, batch 1850, loss[loss=0.1693, simple_loss=0.2664, pruned_loss=0.03613, over 7148.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2768, pruned_loss=0.04249, over 1432297.32 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:20:42,275 INFO [train.py:763] (4/8) Epoch 14, batch 1900, loss[loss=0.1834, simple_loss=0.2945, pruned_loss=0.0362, over 7103.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2761, pruned_loss=0.04205, over 1431679.01 frames.], batch size: 21, lr: 5.17e-04
2022-04-29 07:21:47,861 INFO [train.py:763] (4/8) Epoch 14, batch 1950, loss[loss=0.1654, simple_loss=0.2619, pruned_loss=0.03442, over 7269.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2763, pruned_loss=0.04235, over 1431506.01 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:22:53,273 INFO [train.py:763] (4/8) Epoch 14, batch 2000, loss[loss=0.1963, simple_loss=0.2853, pruned_loss=0.05363, over 6477.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2773, pruned_loss=0.04327, over 1427057.67 frames.], batch size: 37, lr: 5.17e-04
2022-04-29 07:23:58,400 INFO [train.py:763] (4/8) Epoch 14, batch 2050, loss[loss=0.1502, simple_loss=0.2572, pruned_loss=0.02163, over 7327.00 frames.], tot_loss[loss=0.1816, simple_loss=0.277, pruned_loss=0.0431, over 1429266.34 frames.], batch size: 25, lr: 5.16e-04
2022-04-29 07:25:03,739 INFO [train.py:763] (4/8) Epoch 14, batch 2100, loss[loss=0.1801, simple_loss=0.2667, pruned_loss=0.04677, over 7403.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2771, pruned_loss=0.04354, over 1422676.24 frames.], batch size: 18, lr: 5.16e-04
2022-04-29 07:26:09,018 INFO [train.py:763] (4/8) Epoch 14, batch 2150, loss[loss=0.1841, simple_loss=0.2809, pruned_loss=0.04366, over 7220.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2771, pruned_loss=0.04332, over 1420072.93 frames.], batch size: 22, lr: 5.16e-04
2022-04-29 07:27:14,549 INFO [train.py:763] (4/8) Epoch 14, batch 2200, loss[loss=0.1637, simple_loss=0.2708, pruned_loss=0.02831, over 7438.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2772, pruned_loss=0.04307, over 1420519.98 frames.], batch size: 20, lr: 5.16e-04
2022-04-29 07:28:19,749 INFO [train.py:763] (4/8) Epoch 14, batch 2250, loss[loss=0.196, simple_loss=0.294, pruned_loss=0.049, over 7054.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2772, pruned_loss=0.04307, over 1421352.73 frames.], batch size: 28, lr: 5.16e-04
2022-04-29 07:29:24,984 INFO [train.py:763] (4/8) Epoch 14, batch 2300, loss[loss=0.1961, simple_loss=0.2736, pruned_loss=0.05935, over 7277.00 frames.], tot_loss[loss=0.182, simple_loss=0.2778, pruned_loss=0.0431, over 1421783.69 frames.], batch size: 16, lr: 5.15e-04
2022-04-29 07:30:30,165 INFO [train.py:763] (4/8) Epoch 14, batch 2350, loss[loss=0.1442, simple_loss=0.2325, pruned_loss=0.02789, over 7414.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2769, pruned_loss=0.04277, over 1424839.95 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:31:35,491 INFO [train.py:763] (4/8) Epoch 14, batch 2400, loss[loss=0.1474, simple_loss=0.2372, pruned_loss=0.02883, over 7410.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2786, pruned_loss=0.04359, over 1422349.52 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:32:40,928 INFO [train.py:763] (4/8) Epoch 14, batch 2450, loss[loss=0.1778, simple_loss=0.2781, pruned_loss=0.03873, over 7412.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2781, pruned_loss=0.04322, over 1423622.97 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:33:46,234 INFO [train.py:763] (4/8) Epoch 14, batch 2500, loss[loss=0.1838, simple_loss=0.2941, pruned_loss=0.03677, over 7325.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2793, pruned_loss=0.04355, over 1424775.35 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:34:51,431 INFO [train.py:763] (4/8) Epoch 14, batch 2550, loss[loss=0.1652, simple_loss=0.2568, pruned_loss=0.03682, over 7175.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2786, pruned_loss=0.04308, over 1427733.42 frames.], batch size: 18, lr: 5.14e-04
2022-04-29 07:35:56,546 INFO [train.py:763] (4/8) Epoch 14, batch 2600, loss[loss=0.2177, simple_loss=0.3053, pruned_loss=0.06505, over 7215.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2801, pruned_loss=0.04408, over 1421837.16 frames.], batch size: 23, lr: 5.14e-04
2022-04-29 07:37:01,618 INFO [train.py:763] (4/8) Epoch 14, batch 2650, loss[loss=0.1887, simple_loss=0.288, pruned_loss=0.04473, over 7289.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2794, pruned_loss=0.0437, over 1422591.21 frames.], batch size: 25, lr: 5.14e-04
2022-04-29 07:38:06,934 INFO [train.py:763] (4/8) Epoch 14, batch 2700, loss[loss=0.1545, simple_loss=0.2585, pruned_loss=0.02522, over 7308.00 frames.], tot_loss[loss=0.1827, simple_loss=0.279, pruned_loss=0.04322, over 1424526.31 frames.], batch size: 21, lr: 5.14e-04
2022-04-29 07:39:12,132 INFO [train.py:763] (4/8) Epoch 14, batch 2750, loss[loss=0.1976, simple_loss=0.2855, pruned_loss=0.05487, over 7288.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2782, pruned_loss=0.04279, over 1424109.52 frames.], batch size: 24, lr: 5.14e-04
2022-04-29 07:40:17,442 INFO [train.py:763] (4/8) Epoch 14, batch 2800, loss[loss=0.1773, simple_loss=0.2761, pruned_loss=0.03932, over 7143.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2773, pruned_loss=0.04227, over 1427273.35 frames.], batch size: 20, lr: 5.14e-04
2022-04-29 07:41:22,759 INFO [train.py:763] (4/8) Epoch 14, batch 2850, loss[loss=0.1953, simple_loss=0.2831, pruned_loss=0.05372, over 7194.00 frames.], tot_loss[loss=0.181, simple_loss=0.2774, pruned_loss=0.04227, over 1428358.85 frames.], batch size: 16, lr: 5.13e-04
2022-04-29 07:42:28,524 INFO [train.py:763] (4/8) Epoch 14, batch 2900, loss[loss=0.1652, simple_loss=0.2804, pruned_loss=0.02499, over 7412.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2776, pruned_loss=0.04256, over 1424487.07 frames.], batch size: 23, lr: 5.13e-04
2022-04-29 07:43:34,054 INFO [train.py:763] (4/8) Epoch 14, batch 2950, loss[loss=0.1749, simple_loss=0.2722, pruned_loss=0.03879, over 7436.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2772, pruned_loss=0.04261, over 1424446.43 frames.], batch size: 20, lr: 5.13e-04
2022-04-29 07:44:39,580 INFO [train.py:763] (4/8) Epoch 14, batch 3000, loss[loss=0.1572, simple_loss=0.2582, pruned_loss=0.02809, over 7154.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2773, pruned_loss=0.04254, over 1423377.62 frames.], batch size: 19, lr: 5.13e-04
2022-04-29 07:44:39,581 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 07:44:54,980 INFO [train.py:792] (4/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
2022-04-29 07:46:00,329 INFO [train.py:763] (4/8) Epoch 14, batch 3050, loss[loss=0.1648, simple_loss=0.2534, pruned_loss=0.03813, over 7215.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2772, pruned_loss=0.04257, over 1426147.09 frames.], batch size: 16, lr: 5.13e-04
2022-04-29 07:47:05,873 INFO [train.py:763] (4/8) Epoch 14, batch 3100, loss[loss=0.1623, simple_loss=0.264, pruned_loss=0.03031, over 7325.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2782, pruned_loss=0.04299, over 1421723.05 frames.], batch size: 20, lr: 5.12e-04
2022-04-29 07:48:12,212 INFO [train.py:763] (4/8) Epoch 14, batch 3150, loss[loss=0.1693, simple_loss=0.2534, pruned_loss=0.04265, over 7286.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2768, pruned_loss=0.0423, over 1426906.60 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:49:18,808 INFO [train.py:763] (4/8) Epoch 14, batch 3200, loss[loss=0.1951, simple_loss=0.2884, pruned_loss=0.05086, over 7126.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2764, pruned_loss=0.04231, over 1427429.98 frames.], batch size: 28, lr: 5.12e-04
2022-04-29 07:50:24,259 INFO [train.py:763] (4/8) Epoch 14, batch 3250, loss[loss=0.1839, simple_loss=0.2819, pruned_loss=0.04288, over 7052.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2759, pruned_loss=0.04235, over 1427774.18 frames.], batch size: 18, lr: 5.12e-04
2022-04-29 07:51:29,737 INFO [train.py:763] (4/8) Epoch 14, batch 3300, loss[loss=0.1488, simple_loss=0.2365, pruned_loss=0.03058, over 7284.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2753, pruned_loss=0.042, over 1426479.06 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:52:35,056 INFO [train.py:763] (4/8) Epoch 14, batch 3350, loss[loss=0.2169, simple_loss=0.3026, pruned_loss=0.06556, over 7203.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2768, pruned_loss=0.0425, over 1426251.59 frames.], batch size: 23, lr: 5.11e-04
2022-04-29 07:53:40,777 INFO [train.py:763] (4/8) Epoch 14, batch 3400, loss[loss=0.2141, simple_loss=0.3123, pruned_loss=0.05797, over 7236.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2776, pruned_loss=0.04272, over 1422454.90 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:54:45,990 INFO [train.py:763] (4/8) Epoch 14, batch 3450, loss[loss=0.1887, simple_loss=0.2873, pruned_loss=0.045, over 7032.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2788, pruned_loss=0.0437, over 1420009.17 frames.], batch size: 28, lr: 5.11e-04
2022-04-29 07:55:51,600 INFO [train.py:763] (4/8) Epoch 14, batch 3500, loss[loss=0.2029, simple_loss=0.2988, pruned_loss=0.0535, over 7163.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2781, pruned_loss=0.04359, over 1425130.17 frames.], batch size: 26, lr: 5.11e-04
2022-04-29 07:56:57,020 INFO [train.py:763] (4/8) Epoch 14, batch 3550, loss[loss=0.1766, simple_loss=0.2751, pruned_loss=0.03908, over 7238.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2777, pruned_loss=0.04346, over 1426865.74 frames.], batch size: 20, lr: 5.11e-04
2022-04-29 07:58:03,506 INFO [train.py:763] (4/8) Epoch 14, batch 3600, loss[loss=0.1822, simple_loss=0.2815, pruned_loss=0.04142, over 7314.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2778, pruned_loss=0.04376, over 1423131.29 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:59:08,916 INFO [train.py:763] (4/8) Epoch 14, batch 3650, loss[loss=0.2031, simple_loss=0.2975, pruned_loss=0.05439, over 7256.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2782, pruned_loss=0.04425, over 1424227.02 frames.], batch size: 19, lr: 5.10e-04
2022-04-29 08:00:14,234 INFO [train.py:763] (4/8) Epoch 14, batch 3700, loss[loss=0.1822, simple_loss=0.2768, pruned_loss=0.04382, over 7426.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2787, pruned_loss=0.04386, over 1420641.44 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:01:19,992 INFO [train.py:763] (4/8) Epoch 14, batch 3750, loss[loss=0.2068, simple_loss=0.2994, pruned_loss=0.05711, over 4899.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2773, pruned_loss=0.04298, over 1422716.55 frames.], batch size: 52, lr: 5.10e-04
2022-04-29 08:02:27,023 INFO [train.py:763] (4/8) Epoch 14, batch 3800, loss[loss=0.1672, simple_loss=0.2532, pruned_loss=0.04059, over 7056.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2777, pruned_loss=0.04291, over 1424891.84 frames.], batch size: 18, lr: 5.10e-04
2022-04-29 08:03:33,820 INFO [train.py:763] (4/8) Epoch 14, batch 3850, loss[loss=0.1902, simple_loss=0.2974, pruned_loss=0.0415, over 7243.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2788, pruned_loss=0.04322, over 1427642.01 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:04:40,264 INFO [train.py:763] (4/8) Epoch 14, batch 3900, loss[loss=0.1647, simple_loss=0.2507, pruned_loss=0.03937, over 7264.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.0428, over 1425552.69 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:05:46,497 INFO [train.py:763] (4/8) Epoch 14, batch 3950, loss[loss=0.1898, simple_loss=0.2897, pruned_loss=0.04492, over 7357.00 frames.], tot_loss[loss=0.181, simple_loss=0.2769, pruned_loss=0.04253, over 1421590.36 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:06:52,810 INFO [train.py:763] (4/8) Epoch 14, batch 4000, loss[loss=0.1756, simple_loss=0.2903, pruned_loss=0.03042, over 7216.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2774, pruned_loss=0.04279, over 1421871.66 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:07:57,991 INFO [train.py:763] (4/8) Epoch 14, batch 4050, loss[loss=0.2004, simple_loss=0.3062, pruned_loss=0.04731, over 7217.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2779, pruned_loss=0.04247, over 1426139.54 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:09:03,253 INFO [train.py:763] (4/8) Epoch 14, batch 4100, loss[loss=0.2038, simple_loss=0.3053, pruned_loss=0.05109, over 7190.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2782, pruned_loss=0.04279, over 1416397.61 frames.], batch size: 23, lr: 5.09e-04
2022-04-29 08:10:08,497 INFO [train.py:763] (4/8) Epoch 14, batch 4150, loss[loss=0.2159, simple_loss=0.3028, pruned_loss=0.06453, over 5052.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2787, pruned_loss=0.04302, over 1410915.42 frames.], batch size: 53, lr: 5.08e-04
2022-04-29 08:11:13,730 INFO [train.py:763] (4/8) Epoch 14, batch 4200, loss[loss=0.1545, simple_loss=0.2542, pruned_loss=0.02738, over 7232.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2766, pruned_loss=0.04229, over 1410738.85 frames.], batch size: 20, lr: 5.08e-04
2022-04-29 08:12:19,793 INFO [train.py:763] (4/8) Epoch 14, batch 4250, loss[loss=0.1522, simple_loss=0.2444, pruned_loss=0.03005, over 7067.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2769, pruned_loss=0.04263, over 1408917.45 frames.], batch size: 18, lr: 5.08e-04
2022-04-29 08:13:25,927 INFO [train.py:763] (4/8) Epoch 14, batch 4300, loss[loss=0.1516, simple_loss=0.2378, pruned_loss=0.03268, over 6751.00 frames.], tot_loss[loss=0.181, simple_loss=0.2767, pruned_loss=0.04264, over 1403738.02 frames.], batch size: 15, lr: 5.08e-04
2022-04-29 08:14:30,945 INFO [train.py:763] (4/8) Epoch 14, batch 4350, loss[loss=0.1971, simple_loss=0.2937, pruned_loss=0.05024, over 7319.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2767, pruned_loss=0.04226, over 1407638.14 frames.], batch size: 21, lr: 5.08e-04
2022-04-29 08:15:37,005 INFO [train.py:763] (4/8) Epoch 14, batch 4400, loss[loss=0.1875, simple_loss=0.2933, pruned_loss=0.04086, over 7165.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2756, pruned_loss=0.04156, over 1410905.82 frames.], batch size: 19, lr: 5.08e-04
2022-04-29 08:16:42,685 INFO [train.py:763] (4/8) Epoch 14, batch 4450, loss[loss=0.174, simple_loss=0.2702, pruned_loss=0.03891, over 7169.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2743, pruned_loss=0.04163, over 1402648.86 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:17:47,610 INFO [train.py:763] (4/8) Epoch 14, batch 4500, loss[loss=0.1552, simple_loss=0.2513, pruned_loss=0.02959, over 7058.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2751, pruned_loss=0.04202, over 1394431.54 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:18:51,943 INFO [train.py:763] (4/8) Epoch 14, batch 4550, loss[loss=0.223, simple_loss=0.3248, pruned_loss=0.06063, over 4799.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2766, pruned_loss=0.04304, over 1366698.80 frames.], batch size: 52, lr: 5.07e-04
2022-04-29 08:20:20,831 INFO [train.py:763] (4/8) Epoch 15, batch 0, loss[loss=0.1906, simple_loss=0.2977, pruned_loss=0.04173, over 7290.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2977, pruned_loss=0.04173, over 7290.00 frames.], batch size: 24, lr: 4.92e-04
2022-04-29 08:21:27,544 INFO [train.py:763] (4/8) Epoch 15, batch 50, loss[loss=0.1682, simple_loss=0.2568, pruned_loss=0.03975, over 7413.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2744, pruned_loss=0.0399, over 321012.42 frames.], batch size: 18, lr: 4.92e-04
2022-04-29 08:22:33,674 INFO [train.py:763] (4/8) Epoch 15, batch 100, loss[loss=0.1674, simple_loss=0.27, pruned_loss=0.03238, over 7316.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2751, pruned_loss=0.04151, over 563694.52 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:23:40,360 INFO [train.py:763] (4/8) Epoch 15, batch 150, loss[loss=0.1828, simple_loss=0.2865, pruned_loss=0.03952, over 7154.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2748, pruned_loss=0.04071, over 754035.99 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:24:46,766 INFO [train.py:763] (4/8) Epoch 15, batch 200, loss[loss=0.1581, simple_loss=0.2629, pruned_loss=0.02667, over 7125.00 frames.], tot_loss[loss=0.1781, simple_loss=0.274, pruned_loss=0.04104, over 897138.27 frames.], batch size: 21, lr: 4.91e-04
2022-04-29 08:25:52,225 INFO [train.py:763] (4/8) Epoch 15, batch 250, loss[loss=0.1593, simple_loss=0.2497, pruned_loss=0.03442, over 7159.00 frames.], tot_loss[loss=0.1777, simple_loss=0.274, pruned_loss=0.04072, over 1013587.28 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:26:57,837 INFO [train.py:763] (4/8) Epoch 15, batch 300, loss[loss=0.1535, simple_loss=0.2422, pruned_loss=0.03236, over 7162.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2742, pruned_loss=0.04146, over 1108233.83 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:28:03,216 INFO [train.py:763] (4/8) Epoch 15, batch 350, loss[loss=0.169, simple_loss=0.2638, pruned_loss=0.03715, over 7267.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2741, pruned_loss=0.04082, over 1179531.45 frames.], batch size: 18, lr: 4.91e-04
2022-04-29 08:29:08,688 INFO [train.py:763] (4/8) Epoch 15, batch 400, loss[loss=0.1663, simple_loss=0.269, pruned_loss=0.03181, over 7259.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2754, pruned_loss=0.04111, over 1233446.30 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:30:14,238 INFO [train.py:763] (4/8) Epoch 15, batch 450, loss[loss=0.1694, simple_loss=0.2594, pruned_loss=0.03966, over 7425.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2754, pruned_loss=0.04077, over 1281482.43 frames.], batch size: 20, lr: 4.91e-04
2022-04-29 08:31:19,780 INFO [train.py:763] (4/8) Epoch 15, batch 500, loss[loss=0.2013, simple_loss=0.2889, pruned_loss=0.05683, over 7178.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2765, pruned_loss=0.04132, over 1318162.93 frames.], batch size: 23, lr: 4.90e-04
2022-04-29 08:32:25,944 INFO [train.py:763] (4/8) Epoch 15, batch 550, loss[loss=0.1591, simple_loss=0.2456, pruned_loss=0.03636, over 7279.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2754, pruned_loss=0.04084, over 1345214.04 frames.], batch size: 18, lr: 4.90e-04
2022-04-29 08:33:31,107 INFO [train.py:763] (4/8) Epoch 15, batch 600, loss[loss=0.1644, simple_loss=0.2625, pruned_loss=0.03317, over 7171.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2744, pruned_loss=0.0405, over 1361525.44 frames.], batch size: 19, lr: 4.90e-04
2022-04-29 08:34:36,398 INFO [train.py:763] (4/8) Epoch 15, batch 650, loss[loss=0.1724, simple_loss=0.2811, pruned_loss=0.03184, over 6285.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2743, pruned_loss=0.04034, over 1373308.13 frames.], batch size: 37, lr: 4.90e-04
2022-04-29 08:35:42,057 INFO [train.py:763] (4/8) Epoch 15, batch 700, loss[loss=0.1649, simple_loss=0.2725, pruned_loss=0.02866, over 7180.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2738, pruned_loss=0.04037, over 1385353.18 frames.], batch size: 28, lr: 4.90e-04
2022-04-29 08:36:47,191 INFO [train.py:763] (4/8) Epoch 15, batch 750, loss[loss=0.144, simple_loss=0.235, pruned_loss=0.02655, over 7162.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2747, pruned_loss=0.04107, over 1394377.17 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:37:53,214 INFO [train.py:763] (4/8) Epoch 15, batch 800, loss[loss=0.1601, simple_loss=0.2594, pruned_loss=0.03036, over 7264.00 frames.], tot_loss[loss=0.179, simple_loss=0.2752, pruned_loss=0.0414, over 1402061.34 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:39:00,103 INFO [train.py:763] (4/8) Epoch 15, batch 850, loss[loss=0.1844, simple_loss=0.2847, pruned_loss=0.04205, over 7148.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2753, pruned_loss=0.04104, over 1405079.44 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:40:05,801 INFO [train.py:763] (4/8) Epoch 15, batch 900, loss[loss=0.1668, simple_loss=0.2548, pruned_loss=0.03937, over 7370.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2754, pruned_loss=0.041, over 1403678.88 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:41:11,037 INFO [train.py:763] (4/8) Epoch 15, batch 950, loss[loss=0.1785, simple_loss=0.2714, pruned_loss=0.0428, over 7426.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2747, pruned_loss=0.04112, over 1406519.31 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:42:16,441 INFO [train.py:763] (4/8) Epoch 15, batch 1000, loss[loss=0.1905, simple_loss=0.2919, pruned_loss=0.04458, over 7294.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2745, pruned_loss=0.0411, over 1411903.48 frames.], batch size: 25, lr: 4.89e-04
2022-04-29 08:43:21,670 INFO [train.py:763] (4/8) Epoch 15, batch 1050, loss[loss=0.1924, simple_loss=0.2784, pruned_loss=0.05314, over 7337.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2749, pruned_loss=0.04129, over 1417360.78 frames.], batch size: 20, lr: 4.88e-04
2022-04-29 08:44:28,811 INFO [train.py:763] (4/8) Epoch 15, batch 1100, loss[loss=0.1602, simple_loss=0.2664, pruned_loss=0.02704, over 7352.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2751, pruned_loss=0.04151, over 1421507.79 frames.], batch size: 19, lr: 4.88e-04
2022-04-29 08:45:35,099 INFO [train.py:763] (4/8) Epoch 15, batch 1150, loss[loss=0.2132, simple_loss=0.3087, pruned_loss=0.05885, over 5001.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2742, pruned_loss=0.04112, over 1421620.33 frames.], batch size: 52, lr: 4.88e-04
2022-04-29 08:46:40,370 INFO [train.py:763] (4/8) Epoch 15, batch 1200, loss[loss=0.1831, simple_loss=0.2886, pruned_loss=0.03875, over 7125.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2744, pruned_loss=0.04166, over 1419283.29 frames.], batch size: 21, lr: 4.88e-04
2022-04-29 08:47:45,859 INFO [train.py:763] (4/8) Epoch 15, batch 1250, loss[loss=0.1441, simple_loss=0.2391, pruned_loss=0.0246, over 6803.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2737, pruned_loss=0.04153, over 1419527.76 frames.], batch size: 15, lr: 4.88e-04
2022-04-29 08:48:51,148 INFO [train.py:763] (4/8) Epoch 15, batch 1300, loss[loss=0.19, simple_loss=0.2944, pruned_loss=0.04277, over 7204.00 frames.], tot_loss[loss=0.1797, simple_loss=0.275, pruned_loss=0.04219, over 1425469.82 frames.], batch size: 22, lr: 4.88e-04
2022-04-29 08:49:56,769 INFO [train.py:763] (4/8) Epoch 15, batch 1350, loss[loss=0.1731, simple_loss=0.273, pruned_loss=0.03663, over 7157.00 frames.], tot_loss[loss=0.1804, simple_loss=0.276, pruned_loss=0.04239, over 1418599.81 frames.], batch size: 19, lr: 4.87e-04
2022-04-29 08:51:13,198 INFO [train.py:763] (4/8) Epoch 15, batch 1400, loss[loss=0.1926, simple_loss=0.2873, pruned_loss=0.04898, over 7318.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2758, pruned_loss=0.042, over 1417320.29 frames.], batch size: 22, lr: 4.87e-04
2022-04-29 08:52:20,207 INFO [train.py:763] (4/8) Epoch 15, batch 1450, loss[loss=0.199, simple_loss=0.2991, pruned_loss=0.04947, over 7421.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2754, pruned_loss=0.04119, over 1423017.23 frames.], batch size: 21, lr: 4.87e-04
2022-04-29 08:53:25,683 INFO [train.py:763] (4/8) Epoch 15, batch 1500, loss[loss=0.2008, simple_loss=0.2879, pruned_loss=0.05683, over 7205.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2753, pruned_loss=0.04086, over 1422406.57 frames.], batch size: 23, lr: 4.87e-04
2022-04-29 08:54:40,088 INFO [train.py:763] (4/8) Epoch 15, batch 1550, loss[loss=0.1474, simple_loss=0.2332, pruned_loss=0.03083, over 6758.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2751, pruned_loss=0.04102, over 1419485.95 frames.], batch size: 15, lr: 4.87e-04
2022-04-29 08:56:03,994 INFO [train.py:763] (4/8) Epoch 15, batch 1600, loss[loss=0.1993, simple_loss=0.2877, pruned_loss=0.05541, over 6826.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2755, pruned_loss=0.04111, over 1421874.49 frames.], batch size: 15, lr: 4.87e-04
2022-04-29 08:57:19,953 INFO [train.py:763] (4/8) Epoch 15, batch 1650, loss[loss=0.1663, simple_loss=0.2619, pruned_loss=0.0354, over 7147.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2749, pruned_loss=0.04062, over 1423610.27 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 08:58:25,679 INFO [train.py:763] (4/8) Epoch 15, batch 1700, loss[loss=0.1955, simple_loss=0.2762, pruned_loss=0.05741, over 7419.00 frames.], tot_loss[loss=0.1783, simple_loss=0.275, pruned_loss=0.04082, over 1423918.91 frames.], batch size: 18, lr: 4.86e-04
2022-04-29 08:59:40,114 INFO [train.py:763] (4/8) Epoch 15, batch 1750, loss[loss=0.1746, simple_loss=0.2803, pruned_loss=0.03444, over 7387.00 frames.], tot_loss[loss=0.1792, simple_loss=0.276, pruned_loss=0.04116, over 1423694.42 frames.], batch size: 23, lr: 4.86e-04
2022-04-29 09:00:47,094 INFO [train.py:763] (4/8) Epoch 15, batch 1800, loss[loss=0.1472, simple_loss=0.2432, pruned_loss=0.02556, over 7360.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2759, pruned_loss=0.04094, over 1422609.32 frames.], batch size: 19, lr: 4.86e-04
2022-04-29 09:02:11,302 INFO [train.py:763] (4/8) Epoch 15, batch 1850, loss[loss=0.1837, simple_loss=0.2863, pruned_loss=0.04053, over 7151.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2754, pruned_loss=0.04114, over 1424978.98 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 09:03:16,746 INFO [train.py:763] (4/8) Epoch 15, batch 1900, loss[loss=0.1949, simple_loss=0.2925, pruned_loss=0.04866, over 7297.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2752, pruned_loss=0.04124, over 1429452.01 frames.], batch size: 25, lr: 4.86e-04
2022-04-29 09:04:23,830 INFO [train.py:763] (4/8) Epoch 15, batch 1950, loss[loss=0.1973, simple_loss=0.2878, pruned_loss=0.05342, over 7217.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2754, pruned_loss=0.04102, over 1430626.73 frames.], batch size: 23, lr: 4.85e-04
2022-04-29 09:05:29,695 INFO [train.py:763] (4/8) Epoch 15, batch 2000, loss[loss=0.2308, simple_loss=0.3146, pruned_loss=0.0735, over 5165.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2761, pruned_loss=0.04125, over 1423111.79 frames.], batch size: 52, lr: 4.85e-04
2022-04-29 09:06:36,277 INFO [train.py:763] (4/8) Epoch 15, batch 2050, loss[loss=0.1841, simple_loss=0.2896, pruned_loss=0.03931, over 6270.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2771, pruned_loss=0.0417, over 1421670.06 frames.], batch size: 37, lr: 4.85e-04
2022-04-29 09:07:41,963 INFO [train.py:763] (4/8) Epoch 15, batch 2100, loss[loss=0.1761, simple_loss=0.2829, pruned_loss=0.03464, over 7104.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2773, pruned_loss=0.04178, over 1423093.56 frames.], batch size: 21, lr: 4.85e-04
2022-04-29 09:08:48,742 INFO [train.py:763] (4/8) Epoch 15, batch 2150, loss[loss=0.1735, simple_loss=0.2743, pruned_loss=0.03637, over 7250.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2781, pruned_loss=0.04205, over 1418547.80 frames.], batch size: 19, lr: 4.85e-04
2022-04-29 09:09:53,837 INFO [train.py:763] (4/8) Epoch 15, batch 2200, loss[loss=0.2157, simple_loss=0.3092, pruned_loss=0.06108, over 7202.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2778, pruned_loss=0.0417, over 1415984.31 frames.], batch size: 22, lr: 4.84e-04
2022-04-29 09:10:59,455 INFO [train.py:763] (4/8) Epoch 15, batch 2250, loss[loss=0.1825, simple_loss=0.2979, pruned_loss=0.0335, over 7412.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2779, pruned_loss=0.04235, over 1417630.48 frames.], batch size: 21, lr: 4.84e-04
2022-04-29 09:12:05,739 INFO [train.py:763] (4/8) Epoch 15, batch 2300, loss[loss=0.2118, simple_loss=0.296, pruned_loss=0.06378, over 7210.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2775, pruned_loss=0.04209, over 1419032.49 frames.], batch size: 23, lr: 4.84e-04
2022-04-29 09:13:13,273 INFO [train.py:763] (4/8) Epoch 15, batch 2350, loss[loss=0.1869, simple_loss=0.2956, pruned_loss=0.03908, over 7292.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2768, pruned_loss=0.04168, over 1421659.50 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:14:19,338 INFO [train.py:763] (4/8) Epoch 15, batch 2400, loss[loss=0.189, simple_loss=0.2914, pruned_loss=0.04325, over 7316.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2761, pruned_loss=0.04175, over 1425648.81 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:15:24,433 INFO [train.py:763] (4/8) Epoch 15, batch 2450, loss[loss=0.1913, simple_loss=0.2903, pruned_loss=0.04619, over 6767.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2762, pruned_loss=0.04161, over 1423847.92 frames.], batch size: 31, lr: 4.84e-04
2022-04-29 09:16:31,163 INFO [train.py:763] (4/8) Epoch 15, batch 2500, loss[loss=0.1567, simple_loss=0.2599, pruned_loss=0.0267, over 7227.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2752, pruned_loss=0.04164, over 1427343.78 frames.], batch size: 21, lr: 4.83e-04
2022-04-29 09:17:37,362 INFO [train.py:763] (4/8) Epoch 15, batch 2550, loss[loss=0.1805, simple_loss=0.271, pruned_loss=0.04502, over 7150.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2739, pruned_loss=0.04131, over 1424044.40 frames.], batch size: 20, lr: 4.83e-04
2022-04-29 09:18:44,499 INFO [train.py:763] (4/8) Epoch 15, batch 2600, loss[loss=0.1478, simple_loss=0.2387, pruned_loss=0.02845, over 7355.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2736, pruned_loss=0.04133, over 1423360.68 frames.], batch size: 19, lr: 4.83e-04
2022-04-29 09:19:51,208 INFO [train.py:763] (4/8) Epoch 15, batch 2650, loss[loss=0.2016, simple_loss=0.2908, pruned_loss=0.05616, over 7363.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2739, pruned_loss=0.04155, over 1424208.91 frames.], batch size: 23, lr: 4.83e-04
2022-04-29 09:20:56,492 INFO [train.py:763] (4/8) Epoch 15, batch 2700, loss[loss=0.2153, simple_loss=0.3162, pruned_loss=0.05722, over 7187.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2746, pruned_loss=0.04184, over 1421734.17 frames.], batch size: 26, lr: 4.83e-04
2022-04-29 09:22:02,816 INFO [train.py:763] (4/8) Epoch 15, batch 2750, loss[loss=0.1648, simple_loss=0.2562, pruned_loss=0.03673, over 7279.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2747, pruned_loss=0.04151, over 1426484.71 frames.], batch size: 18, lr: 4.83e-04
2022-04-29 09:23:10,084 INFO [train.py:763] (4/8) Epoch 15, batch 2800, loss[loss=0.1851, simple_loss=0.2762, pruned_loss=0.047, over 7224.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2746, pruned_loss=0.04131, over 1427625.42 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:24:17,264 INFO [train.py:763] (4/8) Epoch 15, batch 2850, loss[loss=0.1638, simple_loss=0.2638, pruned_loss=0.03188, over 7177.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.04232, over 1426475.56 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:25:24,198 INFO [train.py:763] (4/8) Epoch 15, batch 2900, loss[loss=0.1744, simple_loss=0.2512, pruned_loss=0.04881, over 7162.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2762, pruned_loss=0.0425, over 1429137.24 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:26:29,781 INFO [train.py:763] (4/8) Epoch 15, batch 2950, loss[loss=0.1818, simple_loss=0.2933, pruned_loss=0.03518, over 7353.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04202, over 1425059.03 frames.], batch size: 22, lr: 4.82e-04
2022-04-29 09:27:35,042 INFO [train.py:763] (4/8) Epoch 15, batch 3000, loss[loss=0.1778, simple_loss=0.2859, pruned_loss=0.03485, over 7413.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2766, pruned_loss=0.04204, over 1429060.73 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:27:35,043 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 09:27:50,494 INFO [train.py:792] (4/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
2022-04-29 09:28:57,619 INFO [train.py:763] (4/8) Epoch 15, batch 3050, loss[loss=0.1442, simple_loss=0.2363, pruned_loss=0.02601, over 7403.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04192, over 1427419.60 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:30:04,538 INFO [train.py:763] (4/8) Epoch 15, batch 3100, loss[loss=0.2023, simple_loss=0.2956, pruned_loss=0.05454, over 7197.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2756, pruned_loss=0.04213, over 1427281.91 frames.], batch size: 23, lr: 4.81e-04
2022-04-29 09:31:11,564 INFO [train.py:763] (4/8) Epoch 15, batch 3150, loss[loss=0.1888, simple_loss=0.2871, pruned_loss=0.04522, over 7167.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2747, pruned_loss=0.04129, over 1424399.74 frames.], batch size: 18, lr: 4.81e-04
2022-04-29 09:32:29,189 INFO [train.py:763] (4/8) Epoch 15, batch 3200, loss[loss=0.2018, simple_loss=0.3127, pruned_loss=0.04542, over 7282.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2754, pruned_loss=0.04138, over 1424650.01 frames.], batch size: 24, lr: 4.81e-04
2022-04-29 09:33:36,692 INFO [train.py:763] (4/8) Epoch 15, batch 3250, loss[loss=0.1911, simple_loss=0.2861, pruned_loss=0.0481, over 7325.00 frames.], tot_loss[loss=0.179, simple_loss=0.2752, pruned_loss=0.04138, over 1426277.23 frames.], batch size: 21, lr: 4.81e-04
2022-04-29 09:34:43,460 INFO [train.py:763] (4/8) Epoch 15, batch 3300, loss[loss=0.201, simple_loss=0.2964, pruned_loss=0.05275, over 7333.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2757, pruned_loss=0.04133, over 1430524.70 frames.], batch size: 25, lr: 4.81e-04
2022-04-29 09:35:50,323 INFO [train.py:763] (4/8) Epoch 15, batch 3350, loss[loss=0.1614, simple_loss=0.264, pruned_loss=0.02942, over 7237.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2756, pruned_loss=0.04115, over 1432340.04 frames.], batch size: 20, lr: 4.81e-04
2022-04-29 09:36:57,529 INFO [train.py:763] (4/8) Epoch 15, batch 3400, loss[loss=0.1928, simple_loss=0.2985, pruned_loss=0.04357, over 7070.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2759, pruned_loss=0.04135, over 1429302.94 frames.], batch size: 28, lr: 4.80e-04
2022-04-29 09:38:05,023 INFO [train.py:763] (4/8) Epoch 15, batch 3450, loss[loss=0.1462, simple_loss=0.243, pruned_loss=0.0247, over 7354.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04139, over 1430540.42 frames.], batch size: 19, lr: 4.80e-04
2022-04-29 09:39:11,457 INFO [train.py:763] (4/8) Epoch 15, batch 3500, loss[loss=0.1711, simple_loss=0.2788, pruned_loss=0.03177, over 7321.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2756, pruned_loss=0.04158, over 1428937.74 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:40:16,433 INFO [train.py:763] (4/8) Epoch 15, batch 3550, loss[loss=0.2023, simple_loss=0.2902, pruned_loss=0.05724, over 7141.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2769, pruned_loss=0.04229, over 1424125.22 frames.], batch size: 26, lr: 4.80e-04
2022-04-29 09:41:21,619 INFO [train.py:763] (4/8) Epoch 15, batch 3600, loss[loss=0.1676, simple_loss=0.272, pruned_loss=0.03162, over 7316.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2767, pruned_loss=0.04218, over 1425814.07 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:42:26,931 INFO [train.py:763] (4/8) Epoch 15, batch 3650, loss[loss=0.164, simple_loss=0.2519, pruned_loss=0.03804, over 7278.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04194, over 1425997.58 frames.], batch size: 18, lr: 4.80e-04
2022-04-29 09:43:33,154 INFO [train.py:763] (4/8) Epoch 15, batch 3700, loss[loss=0.1563, simple_loss=0.2517, pruned_loss=0.0305, over 6805.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2756, pruned_loss=0.04166, over 1423835.54 frames.], batch size: 15, lr: 4.79e-04
2022-04-29 09:44:39,837 INFO [train.py:763] (4/8) Epoch 15, batch 3750, loss[loss=0.2105, simple_loss=0.3219, pruned_loss=0.04953, over 7278.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2761, pruned_loss=0.0417, over 1420995.12 frames.], batch size: 25, lr: 4.79e-04
2022-04-29 09:45:46,799 INFO [train.py:763] (4/8) Epoch 15, batch 3800, loss[loss=0.1683, simple_loss=0.2598, pruned_loss=0.03837, over 7134.00 frames.], tot_loss[loss=0.1795, simple_loss=0.276, pruned_loss=0.04151, over 1425500.65 frames.], batch size: 17, lr: 4.79e-04
2022-04-29 09:46:53,782 INFO [train.py:763] (4/8) Epoch 15, batch 3850, loss[loss=0.1609, simple_loss=0.2525, pruned_loss=0.03468, over 7276.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2763, pruned_loss=0.04197, over 1421346.74 frames.], batch size: 18, lr: 4.79e-04
2022-04-29 09:48:00,484 INFO [train.py:763] (4/8) Epoch 15, batch 3900, loss[loss=0.1988, simple_loss=0.3053, pruned_loss=0.04617, over 7222.00 frames.], tot_loss[loss=0.18, simple_loss=0.2762, pruned_loss=0.04193, over 1423181.14 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:49:06,577 INFO [train.py:763] (4/8) Epoch 15, batch 3950, loss[loss=0.2003, simple_loss=0.2907, pruned_loss=0.05495, over 7229.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2766, pruned_loss=0.04214, over 1422062.44 frames.], batch size: 20, lr: 4.79e-04
2022-04-29 09:50:13,627 INFO [train.py:763] (4/8) Epoch 15, batch 4000, loss[loss=0.1685, simple_loss=0.2692, pruned_loss=0.03394, over 7324.00 frames.], tot_loss[loss=0.1803, simple_loss=0.277, pruned_loss=0.04178, over 1419552.55 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:51:19,314 INFO [train.py:763] (4/8) Epoch 15, batch 4050, loss[loss=0.1632, simple_loss=0.2594, pruned_loss=0.03354, over 7157.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2767, pruned_loss=0.04174, over 1417413.09 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:52:24,920 INFO [train.py:763] (4/8) Epoch 15, batch 4100, loss[loss=0.1611, simple_loss=0.2555, pruned_loss=0.03333, over 7168.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2758, pruned_loss=0.04147, over 1422723.32 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:53:30,115 INFO [train.py:763] (4/8) Epoch 15, batch 4150, loss[loss=0.1923, simple_loss=0.2997, pruned_loss=0.0425, over 6997.00 frames.], tot_loss[loss=0.1798, simple_loss=0.276, pruned_loss=0.04178, over 1417223.79 frames.], batch size: 28, lr: 4.78e-04
2022-04-29 09:54:36,326 INFO [train.py:763] (4/8) Epoch 15, batch 4200, loss[loss=0.1495, simple_loss=0.2379, pruned_loss=0.03056, over 7005.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2746, pruned_loss=0.04116, over 1416960.11 frames.], batch size: 16, lr: 4.78e-04
2022-04-29 09:55:43,464 INFO [train.py:763] (4/8) Epoch 15, batch 4250, loss[loss=0.1813, simple_loss=0.2775, pruned_loss=0.04255, over 7154.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2742, pruned_loss=0.0413, over 1417015.79 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:56:48,658 INFO [train.py:763] (4/8) Epoch 15, batch 4300, loss[loss=0.1781, simple_loss=0.2713, pruned_loss=0.04242, over 6796.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2735, pruned_loss=0.041, over 1412862.37 frames.], batch size: 31, lr: 4.78e-04
2022-04-29 09:57:53,918 INFO [train.py:763] (4/8) Epoch 15, batch 4350, loss[loss=0.1633, simple_loss=0.2508, pruned_loss=0.03784, over 7167.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2727, pruned_loss=0.04044, over 1416175.33 frames.], batch size: 18, lr: 4.77e-04
2022-04-29 09:59:00,569 INFO [train.py:763] (4/8) Epoch 15, batch 4400, loss[loss=0.1676, simple_loss=0.2777, pruned_loss=0.02876, over 7116.00 frames.], tot_loss[loss=0.1771, simple_loss=0.273, pruned_loss=0.04064, over 1416975.44 frames.], batch size: 21, lr: 4.77e-04
2022-04-29 10:00:06,757 INFO [train.py:763] (4/8) Epoch 15, batch 4450, loss[loss=0.2133, simple_loss=0.3104, pruned_loss=0.05809, over 7200.00 frames.], tot_loss[loss=0.178, simple_loss=0.2738, pruned_loss=0.04104, over 1411646.50 frames.], batch size: 22, lr: 4.77e-04
2022-04-29 10:01:11,551 INFO [train.py:763] (4/8) Epoch 15, batch 4500, loss[loss=0.1458, simple_loss=0.2425, pruned_loss=0.0245, over 7126.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2746, pruned_loss=0.04143, over 1402023.88 frames.], batch size: 17, lr: 4.77e-04
2022-04-29 10:02:15,682 INFO [train.py:763] (4/8) Epoch 15, batch 4550, loss[loss=0.211, simple_loss=0.3009, pruned_loss=0.06051, over 4829.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2783, pruned_loss=0.04396, over 1350417.75 frames.], batch size: 52, lr: 4.77e-04
2022-04-29 10:03:53,496 INFO [train.py:763] (4/8) Epoch 16, batch 0, loss[loss=0.2052, simple_loss=0.3117, pruned_loss=0.04939, over 7099.00 frames.], tot_loss[loss=0.2052, simple_loss=0.3117, pruned_loss=0.04939, over 7099.00 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:04:59,092 INFO [train.py:763] (4/8) Epoch 16, batch 50, loss[loss=0.1827, simple_loss=0.2829, pruned_loss=0.04121, over 7317.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2827, pruned_loss=0.04438, over 317712.01 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:06:04,339 INFO [train.py:763] (4/8) Epoch 16, batch 100, loss[loss=0.1705, simple_loss=0.2757, pruned_loss=0.03263, over 7158.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2769, pruned_loss=0.04125, over 560029.82 frames.], batch size: 20, lr: 4.63e-04
2022-04-29 10:07:09,681 INFO [train.py:763] (4/8) Epoch 16, batch 150, loss[loss=0.1604, simple_loss=0.2513, pruned_loss=0.03474, over 6999.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2745, pruned_loss=0.0401, over 747820.24 frames.], batch size: 16, lr: 4.63e-04
2022-04-29 10:08:15,061 INFO [train.py:763] (4/8) Epoch 16, batch 200, loss[loss=0.1469, simple_loss=0.2342, pruned_loss=0.02978, over 7139.00 frames.], tot_loss[loss=0.1787, simple_loss=0.276, pruned_loss=0.0407, over 896524.46 frames.], batch size: 17, lr: 4.63e-04
2022-04-29 10:09:20,553 INFO [train.py:763] (4/8) Epoch 16, batch 250, loss[loss=0.1711, simple_loss=0.2701, pruned_loss=0.036, over 7252.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2752, pruned_loss=0.04003, over 1016061.64 frames.], batch size: 19, lr: 4.63e-04
2022-04-29 10:10:25,846 INFO [train.py:763] (4/8) Epoch 16, batch 300, loss[loss=0.1569, simple_loss=0.2516, pruned_loss=0.03107, over 7460.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2762, pruned_loss=0.04045, over 1101917.74 frames.], batch size: 19, lr: 4.62e-04
2022-04-29 10:11:32,019 INFO [train.py:763] (4/8) Epoch 16, batch 350, loss[loss=0.1564, simple_loss=0.2471, pruned_loss=0.03281, over 6819.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2756, pruned_loss=0.04059, over 1172309.52 frames.], batch size: 15, lr: 4.62e-04
2022-04-29 10:12:37,985 INFO [train.py:763] (4/8) Epoch 16, batch 400, loss[loss=0.2154, simple_loss=0.2957, pruned_loss=0.06757, over 5264.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2755, pruned_loss=0.04049, over 1228036.77 frames.], batch size: 52, lr: 4.62e-04
2022-04-29 10:13:43,445 INFO [train.py:763] (4/8) Epoch 16, batch 450, loss[loss=0.1893, simple_loss=0.28, pruned_loss=0.04927, over 7361.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2756, pruned_loss=0.04045, over 1269479.81 frames.], batch size: 19, lr: 4.62e-04
2022-04-29 10:14:49,054 INFO [train.py:763] (4/8) Epoch 16, batch 500, loss[loss=0.138, simple_loss=0.233, pruned_loss=0.02145, over 7169.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2742, pruned_loss=0.04006, over 1302539.27 frames.], batch size: 18, lr: 4.62e-04
2022-04-29 10:15:54,719 INFO [train.py:763] (4/8) Epoch 16, batch 550, loss[loss=0.1792, simple_loss=0.268, pruned_loss=0.04521, over 7129.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2737, pruned_loss=0.04029, over 1328140.59 frames.], batch size: 17, lr: 4.62e-04
2022-04-29 10:17:00,203 INFO [train.py:763] (4/8) Epoch 16, batch 600, loss[loss=0.1903, simple_loss=0.2933, pruned_loss=0.04365, over 7011.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2745, pruned_loss=0.04102, over 1343659.10 frames.], batch size: 28, lr: 4.62e-04
2022-04-29 10:18:05,530 INFO [train.py:763] (4/8) Epoch 16, batch 650, loss[loss=0.1885, simple_loss=0.2872, pruned_loss=0.04486, over 7339.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2758, pruned_loss=0.0418, over 1361830.98 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:19:10,728 INFO [train.py:763] (4/8) Epoch 16, batch 700, loss[loss=0.1679, simple_loss=0.2634, pruned_loss=0.03618, over 7260.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2771, pruned_loss=0.0421, over 1368844.71 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:20:16,738 INFO [train.py:763] (4/8) Epoch 16, batch 750, loss[loss=0.1616, simple_loss=0.261, pruned_loss=0.0311, over 7140.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2774, pruned_loss=0.04187, over 1378166.62 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:21:21,856 INFO [train.py:763] (4/8) Epoch 16, batch 800, loss[loss=0.1595, simple_loss=0.2673, pruned_loss=0.02583, over 7175.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2777, pruned_loss=0.0419, over 1388607.77 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:22:27,306 INFO [train.py:763] (4/8) Epoch 16, batch 850, loss[loss=0.1773, simple_loss=0.2697, pruned_loss=0.04242, over 6318.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2763, pruned_loss=0.04154, over 1396489.28 frames.], batch size: 37, lr: 4.61e-04
2022-04-29 10:23:32,963 INFO [train.py:763] (4/8) Epoch 16, batch 900, loss[loss=0.1891, simple_loss=0.2913, pruned_loss=0.04344, over 7342.00 frames.], tot_loss[loss=0.1801, simple_loss=0.277, pruned_loss=0.04162, over 1407997.39 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:24:38,446 INFO [train.py:763] (4/8) Epoch 16, batch 950, loss[loss=0.154, simple_loss=0.2424, pruned_loss=0.03282, over 7135.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2763, pruned_loss=0.04127, over 1412509.40 frames.], batch size: 17, lr: 4.60e-04
2022-04-29 10:25:44,697 INFO [train.py:763] (4/8) Epoch 16, batch 1000, loss[loss=0.1741, simple_loss=0.2763, pruned_loss=0.036, over 7109.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2762, pruned_loss=0.04106, over 1417020.40 frames.], batch size: 21, lr: 4.60e-04
2022-04-29 10:26:51,176 INFO [train.py:763] (4/8) Epoch 16, batch 1050, loss[loss=0.1799, simple_loss=0.2804, pruned_loss=0.03968, over 7352.00 frames.], tot_loss[loss=0.1785, simple_loss=0.275, pruned_loss=0.04094, over 1421048.69 frames.], batch size: 22, lr: 4.60e-04
2022-04-29 10:27:57,453 INFO [train.py:763] (4/8) Epoch 16, batch 1100, loss[loss=0.1783, simple_loss=0.281, pruned_loss=0.03784, over 7259.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2754, pruned_loss=0.04101, over 1421190.65 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:29:02,471 INFO [train.py:763] (4/8) Epoch 16, batch 1150, loss[loss=0.1862, simple_loss=0.2815, pruned_loss=0.04541, over 7301.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2761, pruned_loss=0.04129, over 1422018.14 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:30:08,050 INFO [train.py:763] (4/8) Epoch 16, batch 1200, loss[loss=0.2383, simple_loss=0.3386, pruned_loss=0.06905, over 7284.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2755, pruned_loss=0.04108, over 1419826.61 frames.], batch size: 25, lr: 4.60e-04
2022-04-29 10:31:13,264 INFO [train.py:763] (4/8) Epoch 16, batch 1250, loss[loss=0.1586, simple_loss=0.2488, pruned_loss=0.03418, over 7278.00 frames.], tot_loss[loss=0.18, simple_loss=0.277, pruned_loss=0.04152, over 1415593.97 frames.], batch size: 18, lr: 4.60e-04
2022-04-29 10:32:19,085 INFO [train.py:763] (4/8) Epoch 16, batch 1300, loss[loss=0.1784, simple_loss=0.2802, pruned_loss=0.0383, over 7341.00 frames.], tot_loss[loss=0.18, simple_loss=0.2767, pruned_loss=0.04171, over 1414083.23 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:33:25,808 INFO [train.py:763] (4/8) Epoch 16, batch 1350, loss[loss=0.1466, simple_loss=0.2492, pruned_loss=0.02205, over 7006.00 frames.], tot_loss[loss=0.1795, simple_loss=0.276, pruned_loss=0.04152, over 1419480.29 frames.], batch size: 16, lr: 4.59e-04
2022-04-29 10:34:32,887 INFO [train.py:763] (4/8) Epoch 16, batch 1400, loss[loss=0.1868, simple_loss=0.2953, pruned_loss=0.03912, over 7153.00 frames.], tot_loss[loss=0.179, simple_loss=0.2754, pruned_loss=0.04132, over 1420429.34 frames.], batch size: 20, lr: 4.59e-04
2022-04-29 10:35:38,352 INFO [train.py:763] (4/8) Epoch 16, batch 1450, loss[loss=0.1779, simple_loss=0.2774, pruned_loss=0.03926, over 7344.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2754, pruned_loss=0.04098, over 1418979.59 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:36:43,996 INFO [train.py:763] (4/8) Epoch 16, batch 1500, loss[loss=0.1842, simple_loss=0.2797, pruned_loss=0.04434, over 7253.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2741, pruned_loss=0.04052, over 1424562.55 frames.], batch size: 19, lr: 4.59e-04
2022-04-29 10:37:49,277 INFO [train.py:763] (4/8) Epoch 16, batch 1550, loss[loss=0.166, simple_loss=0.28, pruned_loss=0.02603, over 7227.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2743, pruned_loss=0.04053, over 1422573.29 frames.], batch size: 21, lr: 4.59e-04
2022-04-29 10:38:55,267 INFO [train.py:763] (4/8) Epoch 16, batch 1600, loss[loss=0.1632, simple_loss=0.2554, pruned_loss=0.03548, over 7423.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2742, pruned_loss=0.04055, over 1426818.99 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:40:00,453 INFO [train.py:763] (4/8) Epoch 16, batch 1650, loss[loss=0.1701, simple_loss=0.278, pruned_loss=0.03106, over 7406.00 frames.], tot_loss[loss=0.1778, simple_loss=0.275, pruned_loss=0.04036, over 1428486.94 frames.], batch size: 21, lr: 4.58e-04
2022-04-29 10:41:05,541 INFO [train.py:763] (4/8) Epoch 16, batch 1700, loss[loss=0.2419, simple_loss=0.3242, pruned_loss=0.07982, over 5250.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2758, pruned_loss=0.04101, over 1423064.29 frames.], batch size: 53, lr: 4.58e-04
2022-04-29 10:42:10,600 INFO [train.py:763] (4/8) Epoch 16, batch 1750, loss[loss=0.1957, simple_loss=0.288, pruned_loss=0.05164, over 7387.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2766, pruned_loss=0.04137, over 1414529.27 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:43:15,522 INFO [train.py:763] (4/8) Epoch 16, batch 1800, loss[loss=0.1921, simple_loss=0.292, pruned_loss=0.04615, over 7216.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2767, pruned_loss=0.04142, over 1415392.71 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:44:20,683 INFO [train.py:763] (4/8) Epoch 16, batch 1850, loss[loss=0.1747, simple_loss=0.2744, pruned_loss=0.03755, over 6578.00 frames.], tot_loss[loss=0.18, simple_loss=0.277, pruned_loss=0.04152, over 1417001.54 frames.], batch size: 38, lr: 4.58e-04
2022-04-29 10:45:26,186 INFO [train.py:763] (4/8) Epoch 16, batch 1900, loss[loss=0.1665, simple_loss=0.2667, pruned_loss=0.03318, over 7435.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2765, pruned_loss=0.04155, over 1421485.16 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:46:31,346 INFO [train.py:763] (4/8) Epoch 16, batch 1950, loss[loss=0.1658, simple_loss=0.2719, pruned_loss=0.02984, over 7321.00 frames.], tot_loss[loss=0.179, simple_loss=0.2756, pruned_loss=0.04125, over 1423240.96 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:47:36,624 INFO [train.py:763] (4/8) Epoch 16, batch 2000, loss[loss=0.1566, simple_loss=0.2489, pruned_loss=0.03215, over 7260.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2763, pruned_loss=0.04125, over 1424364.55 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:48:44,155 INFO [train.py:763] (4/8) Epoch 16, batch 2050, loss[loss=0.1672, simple_loss=0.255, pruned_loss=0.03972, over 7424.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2745, pruned_loss=0.04048, over 1427356.58 frames.], batch size: 18, lr: 4.57e-04
2022-04-29 10:49:51,118 INFO [train.py:763] (4/8) Epoch 16, batch 2100, loss[loss=0.2007, simple_loss=0.3025, pruned_loss=0.04944, over 7410.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2744, pruned_loss=0.04016, over 1427830.38 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:50:57,992 INFO [train.py:763] (4/8) Epoch 16, batch 2150, loss[loss=0.1623, simple_loss=0.2527, pruned_loss=0.03596, over 7358.00 frames.], tot_loss[loss=0.1769, simple_loss=0.274, pruned_loss=0.03993, over 1423652.13 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:52:04,703 INFO [train.py:763] (4/8) Epoch 16, batch 2200, loss[loss=0.1923, simple_loss=0.2919, pruned_loss=0.04636, over 7344.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2735, pruned_loss=0.03955, over 1420969.55 frames.], batch size: 22, lr: 4.57e-04
2022-04-29 10:53:10,673 INFO [train.py:763] (4/8) Epoch 16, batch 2250, loss[loss=0.1819, simple_loss=0.2854, pruned_loss=0.03917, over 7414.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2744, pruned_loss=0.04007, over 1422979.16 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:54:16,233 INFO [train.py:763] (4/8) Epoch 16, batch 2300, loss[loss=0.2362, simple_loss=0.3221, pruned_loss=0.07519, over 7312.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2746, pruned_loss=0.04012, over 1422553.58 frames.], batch size: 24, lr: 4.56e-04
2022-04-29 10:55:22,547 INFO [train.py:763] (4/8) Epoch 16, batch 2350, loss[loss=0.1838, simple_loss=0.2813, pruned_loss=0.04318, over 7384.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2736, pruned_loss=0.0395, over 1425879.15 frames.], batch size: 23, lr: 4.56e-04
2022-04-29 10:56:28,585 INFO [train.py:763] (4/8) Epoch 16, batch 2400, loss[loss=0.158, simple_loss=0.2513, pruned_loss=0.03234, over 6972.00 frames.], tot_loss[loss=0.176, simple_loss=0.2734, pruned_loss=0.03935, over 1424381.20 frames.], batch size: 16, lr: 4.56e-04
2022-04-29 10:57:34,906 INFO [train.py:763] (4/8) Epoch 16, batch 2450, loss[loss=0.1921, simple_loss=0.3027, pruned_loss=0.04077, over 7340.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2734, pruned_loss=0.04, over 1424504.41 frames.], batch size: 22, lr: 4.56e-04
2022-04-29 10:58:41,491 INFO [train.py:763] (4/8) Epoch 16, batch 2500, loss[loss=0.2064, simple_loss=0.2973, pruned_loss=0.05776, over 7217.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2718, pruned_loss=0.03949, over 1423753.01 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:59:48,420 INFO [train.py:763] (4/8) Epoch 16, batch 2550, loss[loss=0.1838, simple_loss=0.2819, pruned_loss=0.04286, over 7210.00 frames.], tot_loss[loss=0.176, simple_loss=0.2724, pruned_loss=0.03979, over 1418869.76 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 11:00:54,057 INFO [train.py:763] (4/8) Epoch 16, batch 2600, loss[loss=0.216, simple_loss=0.322, pruned_loss=0.05495, over 7067.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2733, pruned_loss=0.04016, over 1421846.64 frames.], batch size: 28, lr: 4.55e-04
2022-04-29 11:01:59,322 INFO [train.py:763] (4/8) Epoch 16, batch 2650, loss[loss=0.1604, simple_loss=0.2638, pruned_loss=0.0285, over 7353.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2735, pruned_loss=0.04017, over 1420453.95 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:03:04,680 INFO [train.py:763] (4/8) Epoch 16, batch 2700, loss[loss=0.1902, simple_loss=0.2971, pruned_loss=0.04163, over 7327.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2722, pruned_loss=0.03954, over 1423231.04 frames.], batch size: 22, lr: 4.55e-04
2022-04-29 11:04:10,089 INFO [train.py:763] (4/8) Epoch 16, batch 2750, loss[loss=0.1958, simple_loss=0.2915, pruned_loss=0.0501, over 7160.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2731, pruned_loss=0.04003, over 1423374.69 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:05:15,587 INFO [train.py:763] (4/8) Epoch 16, batch 2800, loss[loss=0.2081, simple_loss=0.2935, pruned_loss=0.06136, over 4718.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2729, pruned_loss=0.04003, over 1422185.29 frames.], batch size: 52, lr: 4.55e-04
2022-04-29 11:06:20,604 INFO [train.py:763] (4/8) Epoch 16, batch 2850, loss[loss=0.1784, simple_loss=0.2827, pruned_loss=0.03704, over 7314.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2739, pruned_loss=0.04021, over 1421480.09 frames.], batch size: 21, lr: 4.55e-04
2022-04-29 11:07:35,850 INFO [train.py:763] (4/8) Epoch 16, batch 2900, loss[loss=0.1914, simple_loss=0.2876, pruned_loss=0.04756, over 7227.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2733, pruned_loss=0.04008, over 1417778.38 frames.], batch size: 20, lr: 4.55e-04
2022-04-29 11:08:42,368 INFO [train.py:763] (4/8) Epoch 16, batch 2950, loss[loss=0.1611, simple_loss=0.2543, pruned_loss=0.03389, over 7280.00 frames.], tot_loss[loss=0.177, simple_loss=0.2738, pruned_loss=0.04011, over 1418992.08 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:09:49,124 INFO [train.py:763] (4/8) Epoch 16, batch 3000, loss[loss=0.1827, simple_loss=0.2712, pruned_loss=0.04711, over 7148.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2738, pruned_loss=0.03982, over 1423605.34 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:09:49,125 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 11:10:05,042 INFO [train.py:792] (4/8) Epoch 16, validation: loss=0.1677, simple_loss=0.2693, pruned_loss=0.03309, over 698248.00 frames.
2022-04-29 11:11:10,308 INFO [train.py:763] (4/8) Epoch 16, batch 3050, loss[loss=0.1835, simple_loss=0.2743, pruned_loss=0.04635, over 6404.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2743, pruned_loss=0.04037, over 1422639.45 frames.], batch size: 37, lr: 4.54e-04
2022-04-29 11:12:42,599 INFO [train.py:763] (4/8) Epoch 16, batch 3100, loss[loss=0.1779, simple_loss=0.2841, pruned_loss=0.03587, over 7276.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2752, pruned_loss=0.04076, over 1419508.91 frames.], batch size: 25, lr: 4.54e-04
2022-04-29 11:13:48,019 INFO [train.py:763] (4/8) Epoch 16, batch 3150, loss[loss=0.1628, simple_loss=0.2637, pruned_loss=0.03098, over 7325.00 frames.], tot_loss[loss=0.1783, simple_loss=0.275, pruned_loss=0.04083, over 1418469.32 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:15:03,458 INFO [train.py:763] (4/8) Epoch 16, batch 3200, loss[loss=0.1663, simple_loss=0.2635, pruned_loss=0.03454, over 7354.00 frames.], tot_loss[loss=0.178, simple_loss=0.2747, pruned_loss=0.04068, over 1418648.35 frames.], batch size: 19, lr: 4.54e-04
2022-04-29 11:16:27,095 INFO [train.py:763] (4/8) Epoch 16, batch 3250, loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.0346, over 7068.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2745, pruned_loss=0.04049, over 1424530.82 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:17:32,420 INFO [train.py:763] (4/8) Epoch 16, batch 3300, loss[loss=0.2012, simple_loss=0.3044, pruned_loss=0.04898, over 7164.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2756, pruned_loss=0.04108, over 1424504.42 frames.], batch size: 19, lr: 4.53e-04
2022-04-29 11:18:47,352 INFO [train.py:763] (4/8) Epoch 16, batch 3350, loss[loss=0.2174, simple_loss=0.3133, pruned_loss=0.06076, over 7341.00 frames.], tot_loss[loss=0.1791, simple_loss=0.276, pruned_loss=0.04109, over 1425549.48 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:19:53,999 INFO [train.py:763] (4/8) Epoch 16, batch 3400, loss[loss=0.1798, simple_loss=0.2937, pruned_loss=0.03293, over 7145.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2757, pruned_loss=0.04087, over 1422725.38 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:21:00,495 INFO [train.py:763] (4/8) Epoch 16, batch 3450, loss[loss=0.1932, simple_loss=0.3025, pruned_loss=0.04194, over 7326.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2739, pruned_loss=0.04041, over 1424292.03 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:22:05,834 INFO [train.py:763] (4/8) Epoch 16, batch 3500, loss[loss=0.1788, simple_loss=0.2791, pruned_loss=0.03923, over 7207.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2739, pruned_loss=0.04043, over 1424665.13 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:23:10,997 INFO [train.py:763] (4/8) Epoch 16, batch 3550, loss[loss=0.1744, simple_loss=0.2827, pruned_loss=0.03301, over 7118.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2746, pruned_loss=0.04034, over 1427262.36 frames.], batch size: 21, lr: 4.53e-04
2022-04-29 11:24:16,264 INFO [train.py:763] (4/8) Epoch 16, batch 3600, loss[loss=0.162, simple_loss=0.2557, pruned_loss=0.03413, over 7275.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2746, pruned_loss=0.04044, over 1428925.60 frames.], batch size: 18, lr: 4.52e-04
2022-04-29 11:25:21,851 INFO [train.py:763] (4/8) Epoch 16, batch 3650, loss[loss=0.1567, simple_loss=0.267, pruned_loss=0.02324, over 7316.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2729, pruned_loss=0.03994, over 1432022.22 frames.], batch size: 21, lr: 4.52e-04
2022-04-29 11:26:27,133 INFO [train.py:763] (4/8) Epoch 16, batch 3700, loss[loss=0.144, simple_loss=0.249, pruned_loss=0.01949, over 7152.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2729, pruned_loss=0.03983, over 1431670.33 frames.], batch size: 20, lr: 4.52e-04
2022-04-29 11:27:34,285 INFO [train.py:763] (4/8) Epoch 16, batch 3750, loss[loss=0.1705, simple_loss=0.2711, pruned_loss=0.03497, over 6105.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2732, pruned_loss=0.04003, over 1428213.52 frames.], batch size: 37, lr: 4.52e-04
2022-04-29 11:28:40,551 INFO [train.py:763] (4/8) Epoch 16, batch 3800, loss[loss=0.1775, simple_loss=0.2842, pruned_loss=0.03543, over 6390.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2745, pruned_loss=0.04046, over 1426716.24 frames.], batch size: 37, lr: 4.52e-04
2022-04-29 11:29:46,869 INFO [train.py:763] (4/8) Epoch 16, batch 3850, loss[loss=0.152, simple_loss=0.2475, pruned_loss=0.0282, over 6986.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2745, pruned_loss=0.04032, over 1425915.04 frames.], batch size: 16, lr: 4.52e-04
2022-04-29 11:30:53,554 INFO [train.py:763] (4/8) Epoch 16, batch 3900, loss[loss=0.1707, simple_loss=0.2681, pruned_loss=0.03666, over 7202.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.03989, over 1428487.71 frames.], batch size: 22, lr: 4.52e-04
2022-04-29 11:32:00,326 INFO [train.py:763] (4/8) Epoch 16, batch 3950, loss[loss=0.1669, simple_loss=0.2669, pruned_loss=0.03346, over 7221.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.0397, over 1427510.62 frames.], batch size: 23, lr: 4.51e-04
2022-04-29 11:33:05,767 INFO [train.py:763] (4/8) Epoch 16, batch 4000, loss[loss=0.1343, simple_loss=0.23, pruned_loss=0.01928, over 7288.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2737, pruned_loss=0.03973, over 1428179.01 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:34:12,297 INFO [train.py:763] (4/8) Epoch 16, batch 4050, loss[loss=0.2059, simple_loss=0.2966, pruned_loss=0.05762, over 6811.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03971, over 1424620.01 frames.], batch size: 31, lr: 4.51e-04
2022-04-29 11:35:18,250 INFO [train.py:763] (4/8) Epoch 16, batch 4100, loss[loss=0.1883, simple_loss=0.2894, pruned_loss=0.04354, over 6480.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2744, pruned_loss=0.0401, over 1423968.52 frames.], batch size: 38, lr: 4.51e-04
2022-04-29 11:36:24,673 INFO [train.py:763] (4/8) Epoch 16, batch 4150, loss[loss=0.1456, simple_loss=0.2384, pruned_loss=0.02639, over 7129.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2728, pruned_loss=0.0395, over 1423230.18 frames.], batch size: 17, lr: 4.51e-04
2022-04-29 11:37:30,199 INFO [train.py:763] (4/8) Epoch 16, batch 4200, loss[loss=0.1888, simple_loss=0.2816, pruned_loss=0.04799, over 7160.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2731, pruned_loss=0.03971, over 1422528.35 frames.], batch size: 26, lr: 4.51e-04
2022-04-29 11:38:36,626 INFO [train.py:763] (4/8) Epoch 16, batch 4250, loss[loss=0.1712, simple_loss=0.2628, pruned_loss=0.03981, over 7290.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2743, pruned_loss=0.04027, over 1423039.15 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:39:43,731 INFO [train.py:763] (4/8) Epoch 16, batch 4300, loss[loss=0.1819, simple_loss=0.2813, pruned_loss=0.04129, over 7064.00 frames.], tot_loss[loss=0.177, simple_loss=0.2735, pruned_loss=0.04021, over 1422155.31 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:40:49,810 INFO [train.py:763] (4/8) Epoch 16, batch 4350, loss[loss=0.1548, simple_loss=0.2455, pruned_loss=0.03206, over 7171.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2738, pruned_loss=0.04048, over 1421268.23 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:41:55,138 INFO [train.py:763] (4/8) Epoch 16, batch 4400, loss[loss=0.1731, simple_loss=0.2723, pruned_loss=0.03699, over 7231.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2743, pruned_loss=0.04054, over 1419232.02 frames.], batch size: 21, lr: 4.50e-04
2022-04-29 11:43:00,288 INFO [train.py:763] (4/8) Epoch 16, batch 4450, loss[loss=0.1686, simple_loss=0.2538, pruned_loss=0.04167, over 7135.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2751, pruned_loss=0.04083, over 1415583.30 frames.], batch size: 17, lr: 4.50e-04
2022-04-29 11:44:06,063 INFO [train.py:763] (4/8) Epoch 16, batch 4500, loss[loss=0.1837, simple_loss=0.283, pruned_loss=0.04219, over 7235.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2736, pruned_loss=0.04052, over 1414374.97 frames.], batch size: 20, lr: 4.50e-04
2022-04-29 11:45:13,646 INFO [train.py:763] (4/8) Epoch 16, batch 4550, loss[loss=0.1892, simple_loss=0.2865, pruned_loss=0.04598, over 4835.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2734, pruned_loss=0.04119, over 1378922.80 frames.], batch size: 53, lr: 4.50e-04
2022-04-29 11:46:42,221 INFO [train.py:763] (4/8) Epoch 17, batch 0, loss[loss=0.1967, simple_loss=0.2882, pruned_loss=0.05257, over 7230.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2882, pruned_loss=0.05257, over 7230.00 frames.], batch size: 20, lr: 4.38e-04
2022-04-29 11:47:48,724 INFO [train.py:763] (4/8) Epoch 17, batch 50, loss[loss=0.183, simple_loss=0.263, pruned_loss=0.05149, over 7018.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2685, pruned_loss=0.03835, over 324080.45 frames.], batch size: 16, lr: 4.38e-04
2022-04-29 11:48:54,537 INFO [train.py:763] (4/8) Epoch 17, batch 100, loss[loss=0.1512, simple_loss=0.2485, pruned_loss=0.02694, over 7169.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2714, pruned_loss=0.03903, over 565859.67 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:50:00,284 INFO [train.py:763] (4/8) Epoch 17, batch 150, loss[loss=0.2018, simple_loss=0.3038, pruned_loss=0.04988, over 7139.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2738, pruned_loss=0.03991, over 752787.87 frames.], batch size: 20, lr: 4.37e-04
2022-04-29 11:51:07,234 INFO [train.py:763] (4/8) Epoch 17, batch 200, loss[loss=0.1582, simple_loss=0.2519, pruned_loss=0.03226, over 7158.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2743, pruned_loss=0.03975, over 903627.44 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:52:14,161 INFO [train.py:763] (4/8) Epoch 17, batch 250, loss[loss=0.1707, simple_loss=0.272, pruned_loss=0.03472, over 6642.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2747, pruned_loss=0.03945, over 1021125.86 frames.], batch size: 31, lr: 4.37e-04
2022-04-29 11:53:19,798 INFO [train.py:763] (4/8) Epoch 17, batch 300, loss[loss=0.1906, simple_loss=0.2892, pruned_loss=0.04595, over 7019.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2745, pruned_loss=0.03926, over 1104532.20 frames.], batch size: 28, lr: 4.37e-04
2022-04-29 11:54:25,512 INFO [train.py:763] (4/8) Epoch 17, batch 350, loss[loss=0.1767, simple_loss=0.2868, pruned_loss=0.03324, over 7334.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2723, pruned_loss=0.03882, over 1171993.64 frames.], batch size: 22, lr: 4.37e-04
2022-04-29 11:55:31,575 INFO [train.py:763] (4/8) Epoch 17, batch 400, loss[loss=0.1487, simple_loss=0.2409, pruned_loss=0.02828, over 6806.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2727, pruned_loss=0.03927, over 1232113.50 frames.], batch size: 15, lr: 4.37e-04
2022-04-29 11:56:37,247 INFO [train.py:763] (4/8) Epoch 17, batch 450, loss[loss=0.1845, simple_loss=0.2827, pruned_loss=0.04316, over 7215.00 frames.], tot_loss[loss=0.176, simple_loss=0.2733, pruned_loss=0.03935, over 1276051.53 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:57:42,947 INFO [train.py:763] (4/8) Epoch 17, batch 500, loss[loss=0.1787, simple_loss=0.2803, pruned_loss=0.03853, over 7332.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03925, over 1313253.82 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:58:48,659 INFO [train.py:763] (4/8) Epoch 17, batch 550, loss[loss=0.1505, simple_loss=0.2413, pruned_loss=0.02987, over 7127.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2727, pruned_loss=0.03913, over 1339822.08 frames.], batch size: 17, lr: 4.36e-04
2022-04-29 11:59:54,494 INFO [train.py:763] (4/8) Epoch 17, batch 600, loss[loss=0.1812, simple_loss=0.2837, pruned_loss=0.03937, over 6375.00 frames.], tot_loss[loss=0.177, simple_loss=0.274, pruned_loss=0.04005, over 1357011.20 frames.], batch size: 37, lr: 4.36e-04
2022-04-29 12:01:00,139 INFO [train.py:763] (4/8) Epoch 17, batch 650, loss[loss=0.2126, simple_loss=0.2977, pruned_loss=0.06375, over 5149.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2731, pruned_loss=0.03967, over 1369810.08 frames.], batch size: 53, lr: 4.36e-04
2022-04-29 12:02:07,660 INFO [train.py:763] (4/8) Epoch 17, batch 700, loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03145, over 7325.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2731, pruned_loss=0.03955, over 1381264.25 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:03:15,580 INFO [train.py:763] (4/8) Epoch 17, batch 750, loss[loss=0.1575, simple_loss=0.2465, pruned_loss=0.03419, over 7414.00 frames.], tot_loss[loss=0.1754, simple_loss=0.272, pruned_loss=0.03936, over 1391935.28 frames.], batch size: 18, lr: 4.36e-04
2022-04-29 12:04:22,596 INFO [train.py:763] (4/8) Epoch 17, batch 800, loss[loss=0.1933, simple_loss=0.2867, pruned_loss=0.05, over 7321.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2709, pruned_loss=0.03874, over 1403618.86 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:05:28,618 INFO [train.py:763] (4/8) Epoch 17, batch 850, loss[loss=0.2073, simple_loss=0.2938, pruned_loss=0.06038, over 7409.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2705, pruned_loss=0.0385, over 1406121.33 frames.], batch size: 21, lr: 4.35e-04
2022-04-29 12:06:34,118 INFO [train.py:763] (4/8) Epoch 17, batch 900, loss[loss=0.2179, simple_loss=0.3154, pruned_loss=0.06021, over 7209.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03933, over 1406299.75 frames.], batch size: 22, lr: 4.35e-04
2022-04-29 12:07:40,032 INFO [train.py:763] (4/8) Epoch 17, batch 950, loss[loss=0.1534, simple_loss=0.2536, pruned_loss=0.02662, over 7264.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2723, pruned_loss=0.03903, over 1409456.87 frames.], batch size: 19, lr: 4.35e-04
2022-04-29 12:08:46,272 INFO [train.py:763] (4/8) Epoch 17, batch 1000, loss[loss=0.1795, simple_loss=0.2841, pruned_loss=0.03745, over 7275.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2726, pruned_loss=0.03903, over 1413976.66 frames.], batch size: 24, lr: 4.35e-04
2022-04-29 12:09:52,066 INFO [train.py:763] (4/8) Epoch 17, batch 1050, loss[loss=0.1549, simple_loss=0.2401, pruned_loss=0.03482, over 7277.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2721, pruned_loss=0.03864, over 1416034.37 frames.], batch size: 17, lr: 4.35e-04
2022-04-29 12:10:57,967 INFO [train.py:763] (4/8) Epoch 17, batch 1100, loss[loss=0.1785, simple_loss=0.2772, pruned_loss=0.03989, over 7292.00 frames.], tot_loss[loss=0.176, simple_loss=0.273, pruned_loss=0.03948, over 1419710.34 frames.], batch size: 25, lr: 4.35e-04
2022-04-29 12:12:04,943 INFO [train.py:763] (4/8) Epoch 17, batch 1150, loss[loss=0.1677, simple_loss=0.2609, pruned_loss=0.0373, over 7381.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2722, pruned_loss=0.03922, over 1419016.57 frames.], batch size: 23, lr: 4.35e-04
2022-04-29 12:13:12,219 INFO [train.py:763] (4/8) Epoch 17, batch 1200, loss[loss=0.1635, simple_loss=0.2517, pruned_loss=0.03763, over 7280.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2729, pruned_loss=0.0397, over 1415987.28 frames.], batch size: 18, lr: 4.34e-04
2022-04-29 12:14:19,343 INFO [train.py:763] (4/8) Epoch 17, batch 1250, loss[loss=0.187, simple_loss=0.2869, pruned_loss=0.04361, over 7409.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2728, pruned_loss=0.0395, over 1417297.10 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:15:25,172 INFO [train.py:763] (4/8) Epoch 17, batch 1300, loss[loss=0.1651, simple_loss=0.2771, pruned_loss=0.02649, over 7152.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2725, pruned_loss=0.03949, over 1418828.21 frames.], batch size: 26, lr: 4.34e-04
2022-04-29 12:16:30,495 INFO [train.py:763] (4/8) Epoch 17, batch 1350, loss[loss=0.1783, simple_loss=0.2675, pruned_loss=0.04455, over 7424.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.03986, over 1421920.63 frames.], batch size: 17, lr: 4.34e-04
2022-04-29 12:17:36,045 INFO [train.py:763] (4/8) Epoch 17, batch 1400, loss[loss=0.1744, simple_loss=0.2782, pruned_loss=0.03531, over 7120.00 frames.], tot_loss[loss=0.177, simple_loss=0.2739, pruned_loss=0.04006, over 1423542.89 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:18:41,487 INFO [train.py:763] (4/8) Epoch 17, batch 1450, loss[loss=0.1897, simple_loss=0.2916, pruned_loss=0.04395, over 7149.00 frames.], tot_loss[loss=0.1768, simple_loss=0.274, pruned_loss=0.03973, over 1421766.38 frames.], batch size: 20, lr: 4.34e-04
2022-04-29 12:19:47,538 INFO [train.py:763] (4/8) Epoch 17, batch 1500, loss[loss=0.1661, simple_loss=0.268, pruned_loss=0.03207, over 7277.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2748, pruned_loss=0.04027, over 1414203.31 frames.], batch size: 25, lr: 4.34e-04
2022-04-29 12:20:53,499 INFO [train.py:763] (4/8) Epoch 17, batch 1550, loss[loss=0.165, simple_loss=0.2666, pruned_loss=0.03164, over 7153.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03991, over 1421421.66 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:21:59,195 INFO [train.py:763] (4/8) Epoch 17, batch 1600, loss[loss=0.1795, simple_loss=0.27, pruned_loss=0.0445, over 7426.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2747, pruned_loss=0.04044, over 1423644.63 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:23:04,502 INFO [train.py:763] (4/8) Epoch 17, batch 1650, loss[loss=0.1438, simple_loss=0.2321, pruned_loss=0.02779, over 7291.00 frames.], tot_loss[loss=0.178, simple_loss=0.2751, pruned_loss=0.04048, over 1422783.92 frames.], batch size: 17, lr: 4.33e-04
2022-04-29 12:24:09,898 INFO [train.py:763] (4/8) Epoch 17, batch 1700, loss[loss=0.1895, simple_loss=0.2825, pruned_loss=0.04823, over 7358.00 frames.], tot_loss[loss=0.178, simple_loss=0.2751, pruned_loss=0.04042, over 1425564.80 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:25:15,252 INFO [train.py:763] (4/8) Epoch 17, batch 1750, loss[loss=0.2129, simple_loss=0.3115, pruned_loss=0.05714, over 7307.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2742, pruned_loss=0.03971, over 1426007.50 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:26:20,535 INFO [train.py:763] (4/8) Epoch 17, batch 1800, loss[loss=0.1511, simple_loss=0.2631, pruned_loss=0.01958, over 7230.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03981, over 1430199.51 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:27:26,283 INFO [train.py:763] (4/8) Epoch 17, batch 1850, loss[loss=0.2151, simple_loss=0.3007, pruned_loss=0.06477, over 4771.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2732, pruned_loss=0.04017, over 1428139.59 frames.], batch size: 52, lr: 4.33e-04
2022-04-29 12:28:31,338 INFO [train.py:763] (4/8) Epoch 17, batch 1900, loss[loss=0.1788, simple_loss=0.2814, pruned_loss=0.03807, over 7306.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2749, pruned_loss=0.0403, over 1428456.82 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:29:36,728 INFO [train.py:763] (4/8) Epoch 17, batch 1950, loss[loss=0.1802, simple_loss=0.2902, pruned_loss=0.03509, over 7318.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2753, pruned_loss=0.04067, over 1424966.19 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:30:42,615 INFO [train.py:763] (4/8) Epoch 17, batch 2000, loss[loss=0.2457, simple_loss=0.3189, pruned_loss=0.08625, over 4821.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2745, pruned_loss=0.04044, over 1425313.34 frames.], batch size: 52, lr: 4.32e-04
2022-04-29 12:31:59,160 INFO [train.py:763] (4/8) Epoch 17, batch 2050, loss[loss=0.188, simple_loss=0.2962, pruned_loss=0.03987, over 7122.00 frames.], tot_loss[loss=0.1769, simple_loss=0.274, pruned_loss=0.03992, over 1420442.37 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:33:04,641 INFO [train.py:763] (4/8) Epoch 17, batch 2100, loss[loss=0.1875, simple_loss=0.2899, pruned_loss=0.04251, over 6861.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2733, pruned_loss=0.03973, over 1416281.27 frames.], batch size: 31, lr: 4.32e-04
2022-04-29 12:34:11,525 INFO [train.py:763] (4/8) Epoch 17, batch 2150, loss[loss=0.1734, simple_loss=0.2752, pruned_loss=0.0358, over 7224.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03933, over 1418086.00 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:35:18,268 INFO [train.py:763] (4/8) Epoch 17, batch 2200, loss[loss=0.1504, simple_loss=0.2413, pruned_loss=0.02979, over 7198.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2726, pruned_loss=0.0392, over 1421069.55 frames.], batch size: 16, lr: 4.32e-04
2022-04-29 12:36:23,939 INFO [train.py:763] (4/8) Epoch 17, batch 2250, loss[loss=0.1468, simple_loss=0.2408, pruned_loss=0.02634, over 7006.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2726, pruned_loss=0.03925, over 1424103.60 frames.], batch size: 16, lr: 4.32e-04
2022-04-29 12:37:31,403 INFO [train.py:763] (4/8) Epoch 17, batch 2300, loss[loss=0.1886, simple_loss=0.2898, pruned_loss=0.04372, over 7145.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2728, pruned_loss=0.03923, over 1426619.51 frames.], batch size: 20, lr: 4.31e-04
2022-04-29 12:38:38,622 INFO [train.py:763] (4/8) Epoch 17, batch 2350, loss[loss=0.1998, simple_loss=0.2932, pruned_loss=0.05327, over 7157.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2717, pruned_loss=0.03898, over 1426767.68 frames.], batch size: 26, lr: 4.31e-04
2022-04-29 12:39:44,062 INFO [train.py:763] (4/8) Epoch 17, batch 2400, loss[loss=0.1885, simple_loss=0.2894, pruned_loss=0.04381, over 6387.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2716, pruned_loss=0.03872, over 1424705.16 frames.], batch size: 38, lr: 4.31e-04
2022-04-29 12:40:49,288 INFO [train.py:763] (4/8) Epoch 17, batch 2450, loss[loss=0.1389, simple_loss=0.2421, pruned_loss=0.0179, over 7172.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2706, pruned_loss=0.03825, over 1425979.10 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:41:54,331 INFO [train.py:763] (4/8) Epoch 17, batch 2500, loss[loss=0.2028, simple_loss=0.3003, pruned_loss=0.05267, over 7114.00 frames.], tot_loss[loss=0.176, simple_loss=0.273, pruned_loss=0.03953, over 1419198.91 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:42:59,723 INFO [train.py:763] (4/8) Epoch 17, batch 2550, loss[loss=0.1697, simple_loss=0.2687, pruned_loss=0.03533, over 7315.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03937, over 1418627.36 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:44:04,848 INFO [train.py:763] (4/8) Epoch 17, batch 2600, loss[loss=0.17, simple_loss=0.26, pruned_loss=0.04004, over 6829.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2743, pruned_loss=0.03998, over 1418127.62 frames.], batch size: 15, lr: 4.31e-04
2022-04-29 12:45:10,698 INFO [train.py:763] (4/8) Epoch 17, batch 2650, loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03846, over 7352.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2742, pruned_loss=0.03974, over 1419164.98 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:46:17,006 INFO [train.py:763] (4/8) Epoch 17, batch 2700, loss[loss=0.1339, simple_loss=0.2254, pruned_loss=0.02119, over 7275.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2729, pruned_loss=0.0394, over 1419328.22 frames.], batch size: 18, lr: 4.30e-04
2022-04-29 12:47:22,077 INFO [train.py:763] (4/8) Epoch 17, batch 2750, loss[loss=0.1765, simple_loss=0.2721, pruned_loss=0.04045, over 7148.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2733, pruned_loss=0.03957, over 1418293.39 frames.], batch size: 20, lr: 4.30e-04
2022-04-29 12:48:28,857 INFO [train.py:763] (4/8) Epoch 17, batch 2800, loss[loss=0.1884, simple_loss=0.2867, pruned_loss=0.0451, over 7321.00 frames.], tot_loss[loss=0.176, simple_loss=0.2729, pruned_loss=0.03953, over 1418017.37 frames.], batch size: 21, lr: 4.30e-04
2022-04-29 12:49:34,422 INFO [train.py:763] (4/8) Epoch 17, batch 2850, loss[loss=0.1919, simple_loss=0.2925, pruned_loss=0.04559, over 7302.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03903, over 1420725.46 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:50:39,886 INFO [train.py:763] (4/8) Epoch 17, batch 2900, loss[loss=0.16, simple_loss=0.2614, pruned_loss=0.02929, over 7211.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2729, pruned_loss=0.03905, over 1423711.71 frames.], batch size: 22, lr: 4.30e-04
2022-04-29 12:51:46,361 INFO [train.py:763] (4/8) Epoch 17, batch 2950, loss[loss=0.1835, simple_loss=0.2831, pruned_loss=0.04193, over 6332.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2727, pruned_loss=0.03903, over 1420796.54 frames.], batch size: 37, lr: 4.30e-04
2022-04-29 12:52:52,635 INFO [train.py:763] (4/8) Epoch 17, batch 3000, loss[loss=0.196, simple_loss=0.2968, pruned_loss=0.04766, over 7296.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2735, pruned_loss=0.03939, over 1419484.82 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:52:52,636 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 12:53:07,981 INFO [train.py:792] (4/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
2022-04-29 12:54:13,314 INFO [train.py:763] (4/8) Epoch 17, batch 3050, loss[loss=0.1657, simple_loss=0.2685, pruned_loss=0.03146, over 7115.00 frames.], tot_loss[loss=0.1756, simple_loss=0.273, pruned_loss=0.03912, over 1419023.96 frames.], batch size: 21, lr: 4.29e-04
2022-04-29 12:55:18,433 INFO [train.py:763] (4/8) Epoch 17, batch 3100, loss[loss=0.1894, simple_loss=0.2794, pruned_loss=0.04963, over 7238.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2731, pruned_loss=0.03908, over 1419727.22 frames.], batch size: 20, lr: 4.29e-04
2022-04-29 12:56:23,979 INFO [train.py:763] (4/8) Epoch 17, batch 3150, loss[loss=0.1795, simple_loss=0.2794, pruned_loss=0.03979, over 7256.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2734, pruned_loss=0.03952, over 1421710.99 frames.], batch size: 19, lr: 4.29e-04
2022-04-29 12:57:29,296 INFO [train.py:763] (4/8) Epoch 17, batch 3200, loss[loss=0.1837, simple_loss=0.2838, pruned_loss=0.04187, over 6764.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03938, over 1419753.64 frames.], batch size: 31, lr: 4.29e-04
2022-04-29 12:58:34,630 INFO [train.py:763] (4/8) Epoch 17, batch 3250, loss[loss=0.1923, simple_loss=0.2825, pruned_loss=0.05104, over 7370.00 frames.], tot_loss[loss=0.1749, simple_loss=0.272, pruned_loss=0.03891, over 1423163.88 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 12:59:42,205 INFO [train.py:763] (4/8) Epoch 17, batch 3300, loss[loss=0.1427, simple_loss=0.2408, pruned_loss=0.02229, over 7168.00 frames.], tot_loss[loss=0.175, simple_loss=0.272, pruned_loss=0.03896, over 1426730.55 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:00:47,851 INFO [train.py:763] (4/8) Epoch 17, batch 3350, loss[loss=0.1408, simple_loss=0.2305, pruned_loss=0.02555, over 7400.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2729, pruned_loss=0.03923, over 1426038.81 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:01:54,343 INFO [train.py:763] (4/8) Epoch 17, batch 3400, loss[loss=0.1953, simple_loss=0.2872, pruned_loss=0.05174, over 7365.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2732, pruned_loss=0.03928, over 1430066.83 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 13:02:59,883 INFO [train.py:763] (4/8) Epoch 17, batch 3450, loss[loss=0.1751, simple_loss=0.2646, pruned_loss=0.04283, over 7433.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2729, pruned_loss=0.03885, over 1430474.43 frames.], batch size: 18, lr: 4.28e-04
2022-04-29 13:04:05,572 INFO [train.py:763] (4/8) Epoch 17, batch 3500, loss[loss=0.1799, simple_loss=0.2862, pruned_loss=0.03679, over 6471.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03877, over 1433062.12 frames.], batch size: 38, lr: 4.28e-04
2022-04-29 13:05:11,601 INFO [train.py:763] (4/8) Epoch 17, batch 3550, loss[loss=0.1518, simple_loss=0.2465, pruned_loss=0.02855, over 7204.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2734, pruned_loss=0.03907, over 1431292.82 frames.], batch size: 23, lr: 4.28e-04
2022-04-29 13:06:17,356 INFO [train.py:763] (4/8) Epoch 17, batch 3600, loss[loss=0.207, simple_loss=0.2941, pruned_loss=0.05994, over 7220.00 frames.], tot_loss[loss=0.1756, simple_loss=0.273, pruned_loss=0.0391, over 1432419.15 frames.], batch size: 21, lr: 4.28e-04
2022-04-29 13:07:22,976 INFO [train.py:763] (4/8) Epoch 17, batch 3650, loss[loss=0.192, simple_loss=0.2969, pruned_loss=0.04354, over 7349.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2725, pruned_loss=0.03866, over 1423418.62 frames.], batch size: 22, lr: 4.28e-04
2022-04-29 13:08:28,132 INFO [train.py:763] (4/8) Epoch 17, batch 3700, loss[loss=0.1516, simple_loss=0.2381, pruned_loss=0.0325, over 6998.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2732, pruned_loss=0.03908, over 1424466.88 frames.], batch size: 16, lr: 4.28e-04
2022-04-29 13:09:33,325 INFO [train.py:763] (4/8) Epoch 17, batch 3750, loss[loss=0.1907, simple_loss=0.2895, pruned_loss=0.04595, over 7290.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2741, pruned_loss=0.03888, over 1426425.79 frames.], batch size: 25, lr: 4.28e-04
2022-04-29 13:10:39,692 INFO [train.py:763] (4/8) Epoch 17, batch 3800, loss[loss=0.1823, simple_loss=0.2718, pruned_loss=0.04637, over 7359.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2734, pruned_loss=0.03907, over 1426371.33 frames.], batch size: 19, lr: 4.28e-04
2022-04-29 13:11:45,016 INFO [train.py:763] (4/8) Epoch 17, batch 3850, loss[loss=0.1415, simple_loss=0.2385, pruned_loss=0.02228, over 7410.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03934, over 1424684.38 frames.], batch size: 18, lr: 4.27e-04
2022-04-29 13:12:50,423 INFO [train.py:763] (4/8) Epoch 17, batch 3900, loss[loss=0.1769, simple_loss=0.2867, pruned_loss=0.03357, over 7103.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2727, pruned_loss=0.03916, over 1421673.55 frames.], batch size: 21, lr: 4.27e-04
2022-04-29 13:13:55,776 INFO [train.py:763] (4/8) Epoch 17, batch 3950, loss[loss=0.2187, simple_loss=0.3168, pruned_loss=0.06035, over 7094.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2724, pruned_loss=0.03921, over 1423373.90 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:15:01,124 INFO [train.py:763] (4/8) Epoch 17, batch 4000, loss[loss=0.1516, simple_loss=0.2392, pruned_loss=0.03196, over 7228.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2723, pruned_loss=0.03909, over 1423795.59 frames.], batch size: 16, lr: 4.27e-04
2022-04-29 13:16:06,980 INFO [train.py:763] (4/8) Epoch 17, batch 4050, loss[loss=0.1693, simple_loss=0.2672, pruned_loss=0.03568, over 7067.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2731, pruned_loss=0.03933, over 1427484.36 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:17:12,349 INFO [train.py:763] (4/8) Epoch 17, batch 4100, loss[loss=0.1804, simple_loss=0.2779, pruned_loss=0.04147, over 7155.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2722, pruned_loss=0.03863, over 1423976.53 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:18:18,022 INFO [train.py:763] (4/8) Epoch 17, batch 4150, loss[loss=0.1602, simple_loss=0.2639, pruned_loss=0.02824, over 7319.00 frames.], tot_loss[loss=0.1757, simple_loss=0.273, pruned_loss=0.03922, over 1423295.44 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:19:24,061 INFO [train.py:763] (4/8) Epoch 17, batch 4200, loss[loss=0.1471, simple_loss=0.2499, pruned_loss=0.02218, over 7009.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2715, pruned_loss=0.03877, over 1423350.52 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:20:29,202 INFO [train.py:763] (4/8) Epoch 17, batch 4250, loss[loss=0.1978, simple_loss=0.2922, pruned_loss=0.05174, over 6662.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2713, pruned_loss=0.03866, over 1419160.95 frames.], batch size: 31, lr: 4.26e-04
2022-04-29 13:21:35,159 INFO [train.py:763] (4/8) Epoch 17, batch 4300, loss[loss=0.1462, simple_loss=0.2286, pruned_loss=0.03187, over 6991.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2696, pruned_loss=0.0381, over 1419472.87 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:22:49,722 INFO [train.py:763] (4/8) Epoch 17, batch 4350, loss[loss=0.1772, simple_loss=0.2788, pruned_loss=0.03778, over 7226.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2697, pruned_loss=0.03833, over 1407035.02 frames.], batch size: 21, lr: 4.26e-04
2022-04-29 13:23:54,550 INFO [train.py:763] (4/8) Epoch 17, batch 4400, loss[loss=0.1422, simple_loss=0.2448, pruned_loss=0.01981, over 7074.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2712, pruned_loss=0.039, over 1402354.20 frames.], batch size: 18, lr: 4.26e-04
2022-04-29 13:24:59,615 INFO [train.py:763] (4/8) Epoch 17, batch 4450, loss[loss=0.1633, simple_loss=0.2612, pruned_loss=0.03273, over 6512.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2727, pruned_loss=0.03922, over 1392897.62 frames.], batch size: 38, lr: 4.26e-04
2022-04-29 13:26:04,072 INFO [train.py:763] (4/8) Epoch 17, batch 4500, loss[loss=0.1667, simple_loss=0.2548, pruned_loss=0.03934, over 6986.00 frames.], tot_loss[loss=0.177, simple_loss=0.2743, pruned_loss=0.03989, over 1379677.09 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:27:09,433 INFO [train.py:763] (4/8) Epoch 17, batch 4550, loss[loss=0.1587, simple_loss=0.2517, pruned_loss=0.03282, over 7155.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2747, pruned_loss=0.04072, over 1369677.78 frames.], batch size: 19, lr: 4.26e-04
2022-04-29 13:29:06,464 INFO [train.py:763] (4/8) Epoch 18, batch 0, loss[loss=0.1916, simple_loss=0.2912, pruned_loss=0.04599, over 7288.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2912, pruned_loss=0.04599, over 7288.00 frames.], batch size: 25, lr: 4.15e-04
2022-04-29 13:30:22,085 INFO [train.py:763] (4/8) Epoch 18, batch 50, loss[loss=0.2257, simple_loss=0.3173, pruned_loss=0.06702, over 7344.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2723, pruned_loss=0.0386, over 325062.81 frames.], batch size: 22, lr: 4.15e-04
2022-04-29 13:31:37,249 INFO [train.py:763] (4/8) Epoch 18, batch 100, loss[loss=0.1803, simple_loss=0.2903, pruned_loss=0.03519, over 7326.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2706, pruned_loss=0.03712, over 574335.21 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:32:51,550 INFO [train.py:763] (4/8) Epoch 18, batch 150, loss[loss=0.1691, simple_loss=0.271, pruned_loss=0.0336, over 7217.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2685, pruned_loss=0.03639, over 764234.45 frames.], batch size: 21, lr: 4.14e-04
2022-04-29 13:33:57,481 INFO [train.py:763] (4/8) Epoch 18, batch 200, loss[loss=0.1418, simple_loss=0.2227, pruned_loss=0.03041, over 7272.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2698, pruned_loss=0.03769, over 909932.67 frames.], batch size: 17, lr: 4.14e-04
2022-04-29 13:35:11,767 INFO [train.py:763] (4/8) Epoch 18, batch 250, loss[loss=0.1711, simple_loss=0.2763, pruned_loss=0.03295, over 6716.00 frames.], tot_loss[loss=0.174, simple_loss=0.271, pruned_loss=0.03853, over 1025379.81 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:36:17,270 INFO [train.py:763] (4/8) Epoch 18, batch 300, loss[loss=0.1745, simple_loss=0.2839, pruned_loss=0.03256, over 7233.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2719, pruned_loss=0.03831, over 1115470.62 frames.], batch size: 20, lr: 4.14e-04
2022-04-29 13:37:24,205 INFO [train.py:763] (4/8) Epoch 18, batch 350, loss[loss=0.2084, simple_loss=0.3102, pruned_loss=0.05329, over 6752.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2704, pruned_loss=0.03738, over 1182450.18 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:38:31,273 INFO [train.py:763] (4/8) Epoch 18, batch 400, loss[loss=0.1554, simple_loss=0.2561, pruned_loss=0.02739, over 7068.00 frames.], tot_loss[loss=0.174, simple_loss=0.2713, pruned_loss=0.03835, over 1233072.01 frames.], batch size: 18, lr: 4.14e-04
2022-04-29 13:39:38,716 INFO [train.py:763] (4/8) Epoch 18, batch 450, loss[loss=0.1801, simple_loss=0.278, pruned_loss=0.04112, over 7337.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.0381, over 1275395.06 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:40:45,465 INFO [train.py:763] (4/8) Epoch 18, batch 500, loss[loss=0.143, simple_loss=0.2384, pruned_loss=0.02374, over 7136.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2719, pruned_loss=0.03811, over 1306094.23 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:41:52,279 INFO [train.py:763] (4/8) Epoch 18, batch 550, loss[loss=0.1666, simple_loss=0.2605, pruned_loss=0.03633, over 7288.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2712, pruned_loss=0.03771, over 1335795.56 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:42:57,721 INFO [train.py:763] (4/8) Epoch 18, batch 600, loss[loss=0.1591, simple_loss=0.2545, pruned_loss=0.03184, over 7285.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2715, pruned_loss=0.03835, over 1356386.24 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:44:04,376 INFO [train.py:763] (4/8) Epoch 18, batch 650, loss[loss=0.1719, simple_loss=0.2747, pruned_loss=0.03452, over 7119.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03778, over 1375726.28 frames.], batch size: 21, lr: 4.13e-04
2022-04-29 13:45:09,471 INFO [train.py:763] (4/8) Epoch 18, batch 700, loss[loss=0.2061, simple_loss=0.2972, pruned_loss=0.05743, over 5116.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.03818, over 1386114.55 frames.], batch size: 52, lr: 4.13e-04
2022-04-29 13:46:15,213 INFO [train.py:763] (4/8) Epoch 18, batch 750, loss[loss=0.155, simple_loss=0.2503, pruned_loss=0.02987, over 7158.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2714, pruned_loss=0.03788, over 1394669.67 frames.], batch size: 19, lr: 4.13e-04
2022-04-29 13:47:20,147 INFO [train.py:763] (4/8) Epoch 18, batch 800, loss[loss=0.1489, simple_loss=0.262, pruned_loss=0.01792, over 6777.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2723, pruned_loss=0.03812, over 1396941.95 frames.], batch size: 31, lr: 4.13e-04
2022-04-29 13:48:26,401 INFO [train.py:763] (4/8) Epoch 18, batch 850, loss[loss=0.1689, simple_loss=0.2635, pruned_loss=0.03714, over 7058.00 frames.], tot_loss[loss=0.1747, simple_loss=0.273, pruned_loss=0.03818, over 1404882.50 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:49:33,105 INFO [train.py:763] (4/8) Epoch 18, batch 900, loss[loss=0.1565, simple_loss=0.2476, pruned_loss=0.03269, over 6795.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2734, pruned_loss=0.0384, over 1410092.11 frames.], batch size: 15, lr: 4.12e-04
2022-04-29 13:50:38,403 INFO [train.py:763] (4/8) Epoch 18, batch 950, loss[loss=0.2046, simple_loss=0.2925, pruned_loss=0.05828, over 7366.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2732, pruned_loss=0.03865, over 1412140.53 frames.], batch size: 23, lr: 4.12e-04
2022-04-29 13:51:45,512 INFO [train.py:763] (4/8) Epoch 18, batch 1000, loss[loss=0.1904, simple_loss=0.2944, pruned_loss=0.04316, over 7139.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2737, pruned_loss=0.03873, over 1419354.25 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:52:52,988 INFO [train.py:763] (4/8) Epoch 18, batch 1050, loss[loss=0.2031, simple_loss=0.3053, pruned_loss=0.05049, over 7317.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2731, pruned_loss=0.03851, over 1417733.40 frames.], batch size: 25, lr: 4.12e-04
2022-04-29 13:53:58,529 INFO [train.py:763] (4/8) Epoch 18, batch 1100, loss[loss=0.1645, simple_loss=0.2621, pruned_loss=0.03351, over 7321.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2718, pruned_loss=0.03799, over 1418662.38 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:55:03,936 INFO [train.py:763] (4/8) Epoch 18, batch 1150, loss[loss=0.154, simple_loss=0.2593, pruned_loss=0.02433, over 7308.00 frames.], tot_loss[loss=0.174, simple_loss=0.2717, pruned_loss=0.0382, over 1419172.24 frames.], batch size: 24, lr: 4.12e-04
2022-04-29 13:56:09,831 INFO [train.py:763] (4/8) Epoch 18, batch 1200, loss[loss=0.2234, simple_loss=0.3202, pruned_loss=0.06326, over 4937.00 frames.], tot_loss[loss=0.1745, simple_loss=0.272, pruned_loss=0.03852, over 1413427.69 frames.], batch size: 52, lr: 4.12e-04
2022-04-29 13:57:15,049 INFO [train.py:763] (4/8) Epoch 18, batch 1250, loss[loss=0.1671, simple_loss=0.2685, pruned_loss=0.03281, over 7112.00 frames.], tot_loss[loss=0.1742, simple_loss=0.272, pruned_loss=0.0382, over 1414117.88 frames.], batch size: 21, lr: 4.12e-04
2022-04-29 13:58:20,082 INFO [train.py:763] (4/8) Epoch 18, batch 1300, loss[loss=0.2103, simple_loss=0.2975, pruned_loss=0.06156, over 7173.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2732, pruned_loss=0.03879, over 1413734.48 frames.], batch size: 19, lr: 4.12e-04
2022-04-29 13:59:25,397 INFO [train.py:763] (4/8) Epoch 18, batch 1350, loss[loss=0.1882, simple_loss=0.2904, pruned_loss=0.04304, over 7111.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2741, pruned_loss=0.03912, over 1411902.99 frames.], batch size: 28, lr: 4.11e-04
2022-04-29 14:00:32,445 INFO [train.py:763] (4/8) Epoch 18, batch 1400, loss[loss=0.1641, simple_loss=0.2536, pruned_loss=0.03735, over 7064.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2728, pruned_loss=0.0388, over 1409699.98 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:01:39,694 INFO [train.py:763] (4/8) Epoch 18, batch 1450, loss[loss=0.1864, simple_loss=0.2888, pruned_loss=0.04197, over 7313.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2719, pruned_loss=0.03847, over 1417438.21 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:02:45,981 INFO [train.py:763] (4/8) Epoch 18, batch 1500, loss[loss=0.1758, simple_loss=0.2723, pruned_loss=0.03964, over 7253.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2726, pruned_loss=0.03848, over 1421329.39 frames.], batch size: 19, lr: 4.11e-04
2022-04-29 14:03:53,117 INFO [train.py:763] (4/8) Epoch 18, batch 1550, loss[loss=0.2004, simple_loss=0.2988, pruned_loss=0.05102, over 7414.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2714, pruned_loss=0.03789, over 1424262.47 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:04:58,306 INFO [train.py:763] (4/8) Epoch 18, batch 1600, loss[loss=0.1773, simple_loss=0.2704, pruned_loss=0.04208, over 7198.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2709, pruned_loss=0.03779, over 1423239.72 frames.], batch size: 22, lr: 4.11e-04
2022-04-29 14:06:03,946 INFO [train.py:763] (4/8) Epoch 18, batch 1650, loss[loss=0.1434, simple_loss=0.2472, pruned_loss=0.01973, over 7156.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2711, pruned_loss=0.03782, over 1422105.66 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:07:10,554 INFO [train.py:763] (4/8) Epoch 18, batch 1700, loss[loss=0.1492, simple_loss=0.2372, pruned_loss=0.0306, over 7162.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2714, pruned_loss=0.03819, over 1422845.24 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:08:17,581 INFO [train.py:763] (4/8) Epoch 18, batch 1750, loss[loss=0.1732, simple_loss=0.2753, pruned_loss=0.03558, over 7148.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2722, pruned_loss=0.03818, over 1414839.90 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:09:24,693 INFO [train.py:763] (4/8) Epoch 18, batch 1800, loss[loss=0.1719, simple_loss=0.276, pruned_loss=0.03385, over 7254.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2733, pruned_loss=0.03793, over 1415778.59 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:10:32,224 INFO [train.py:763] (4/8) Epoch 18, batch 1850, loss[loss=0.1858, simple_loss=0.2784, pruned_loss=0.04662, over 7279.00 frames.], tot_loss[loss=0.1746, simple_loss=0.273, pruned_loss=0.03815, over 1421757.93 frames.], batch size: 24, lr: 4.10e-04
2022-04-29 14:11:39,560 INFO [train.py:763] (4/8) Epoch 18, batch 1900, loss[loss=0.1539, simple_loss=0.2543, pruned_loss=0.02673, over 7107.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2724, pruned_loss=0.03826, over 1418909.76 frames.], batch size: 28, lr: 4.10e-04
2022-04-29 14:12:46,671 INFO [train.py:763] (4/8) Epoch 18, batch 1950, loss[loss=0.1507, simple_loss=0.2376, pruned_loss=0.03187, over 6998.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2729, pruned_loss=0.03843, over 1419088.52 frames.], batch size: 16, lr: 4.10e-04
2022-04-29 14:13:51,988 INFO [train.py:763] (4/8) Epoch 18, batch 2000, loss[loss=0.1588, simple_loss=0.2576, pruned_loss=0.02996, over 7148.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2722, pruned_loss=0.03811, over 1423045.39 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:14:57,422 INFO [train.py:763] (4/8) Epoch 18, batch 2050, loss[loss=0.1903, simple_loss=0.294, pruned_loss=0.04334, over 7295.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2718, pruned_loss=0.03778, over 1423873.26 frames.], batch size: 25, lr: 4.10e-04
2022-04-29 14:16:02,572 INFO [train.py:763] (4/8) Epoch 18, batch 2100, loss[loss=0.1692, simple_loss=0.2634, pruned_loss=0.03749, over 7158.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2728, pruned_loss=0.03783, over 1424470.26 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:17:08,136 INFO [train.py:763] (4/8) Epoch 18, batch 2150, loss[loss=0.1814, simple_loss=0.2865, pruned_loss=0.03815, over 7220.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2726, pruned_loss=0.03796, over 1420594.72 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:18:13,397 INFO [train.py:763] (4/8) Epoch 18, batch 2200, loss[loss=0.1865, simple_loss=0.2928, pruned_loss=0.04011, over 7120.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2718, pruned_loss=0.03779, over 1425096.34 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:19:18,569 INFO [train.py:763] (4/8) Epoch 18, batch 2250, loss[loss=0.1748, simple_loss=0.2783, pruned_loss=0.03562, over 6434.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2719, pruned_loss=0.0381, over 1423953.15 frames.], batch size: 38, lr: 4.09e-04
2022-04-29 14:20:23,886 INFO [train.py:763] (4/8) Epoch 18, batch 2300, loss[loss=0.1878, simple_loss=0.2798, pruned_loss=0.04784, over 7374.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.03794, over 1425942.08 frames.], batch size: 23, lr: 4.09e-04
2022-04-29 14:21:28,906 INFO [train.py:763] (4/8) Epoch 18, batch 2350, loss[loss=0.1596, simple_loss=0.2451, pruned_loss=0.03706, over 7281.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2717, pruned_loss=0.03811, over 1422823.14 frames.], batch size: 17, lr: 4.09e-04
2022-04-29 14:22:34,035 INFO [train.py:763] (4/8) Epoch 18, batch 2400, loss[loss=0.1797, simple_loss=0.2787, pruned_loss=0.04038, over 7147.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2721, pruned_loss=0.03845, over 1418791.83 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:23:41,075 INFO [train.py:763] (4/8) Epoch 18, batch 2450, loss[loss=0.1783, simple_loss=0.2731, pruned_loss=0.04173, over 7146.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2713, pruned_loss=0.03813, over 1421408.90 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:24:46,854 INFO [train.py:763] (4/8) Epoch 18, batch 2500, loss[loss=0.167, simple_loss=0.2683, pruned_loss=0.03285, over 7183.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2708, pruned_loss=0.03836, over 1421345.53 frames.], batch size: 26, lr: 4.09e-04
2022-04-29 14:25:51,850 INFO [train.py:763] (4/8) Epoch 18, batch 2550, loss[loss=0.1777, simple_loss=0.2781, pruned_loss=0.03862, over 7263.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2705, pruned_loss=0.0384, over 1421187.23 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:26:57,009 INFO [train.py:763] (4/8) Epoch 18, batch 2600, loss[loss=0.1591, simple_loss=0.2461, pruned_loss=0.03609, over 7004.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2717, pruned_loss=0.03921, over 1425432.47 frames.], batch size: 16, lr: 4.08e-04
2022-04-29 14:28:02,329 INFO [train.py:763] (4/8) Epoch 18, batch 2650, loss[loss=0.2006, simple_loss=0.2995, pruned_loss=0.05091, over 7281.00 frames.], tot_loss[loss=0.175, simple_loss=0.2719, pruned_loss=0.03907, over 1426884.87 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:29:08,094 INFO [train.py:763] (4/8) Epoch 18, batch 2700, loss[loss=0.1974, simple_loss=0.3002, pruned_loss=0.04732, over 7290.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2719, pruned_loss=0.03876, over 1429719.70 frames.], batch size: 25, lr: 4.08e-04
2022-04-29 14:30:14,901 INFO [train.py:763] (4/8) Epoch 18, batch 2750, loss[loss=0.1882, simple_loss=0.2879, pruned_loss=0.04422, over 7411.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03873, over 1428996.88 frames.], batch size: 21, lr: 4.08e-04
2022-04-29 14:31:21,336 INFO [train.py:763] (4/8) Epoch 18, batch 2800, loss[loss=0.1951, simple_loss=0.2936, pruned_loss=0.04831, over 7065.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2722, pruned_loss=0.03848, over 1430218.45 frames.], batch size: 18, lr: 4.08e-04
2022-04-29 14:32:26,505 INFO [train.py:763] (4/8) Epoch 18, batch 2850, loss[loss=0.1699, simple_loss=0.2777, pruned_loss=0.03106, over 7154.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2726, pruned_loss=0.03863, over 1427629.73 frames.], batch size: 19, lr: 4.08e-04
2022-04-29 14:33:31,779 INFO [train.py:763] (4/8) Epoch 18, batch 2900, loss[loss=0.1799, simple_loss=0.2791, pruned_loss=0.0403, over 7140.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.03782, over 1424852.32 frames.], batch size: 26, lr: 4.08e-04
2022-04-29 14:34:37,290 INFO [train.py:763] (4/8) Epoch 18, batch 2950, loss[loss=0.1571, simple_loss=0.241, pruned_loss=0.0366, over 7281.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2714, pruned_loss=0.03749, over 1430459.22 frames.], batch size: 17, lr: 4.08e-04
2022-04-29 14:35:43,262 INFO [train.py:763] (4/8) Epoch 18, batch 3000, loss[loss=0.1758, simple_loss=0.2702, pruned_loss=0.04071, over 5374.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2708, pruned_loss=0.03748, over 1430471.76 frames.], batch size: 53, lr: 4.07e-04
2022-04-29 14:35:43,262 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 14:35:58,559 INFO [train.py:792] (4/8) Epoch 18, validation: loss=0.1668, simple_loss=0.2671, pruned_loss=0.03324, over 698248.00 frames.
2022-04-29 14:37:05,447 INFO [train.py:763] (4/8) Epoch 18, batch 3050, loss[loss=0.2009, simple_loss=0.2945, pruned_loss=0.05366, over 7196.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03752, over 1431498.53 frames.], batch size: 23, lr: 4.07e-04
2022-04-29 14:38:12,643 INFO [train.py:763] (4/8) Epoch 18, batch 3100, loss[loss=0.1705, simple_loss=0.2655, pruned_loss=0.0377, over 6327.00 frames.], tot_loss[loss=0.1729, simple_loss=0.271, pruned_loss=0.03742, over 1432159.73 frames.], batch size: 37, lr: 4.07e-04
2022-04-29 14:39:19,390 INFO [train.py:763] (4/8) Epoch 18, batch 3150, loss[loss=0.1565, simple_loss=0.2465, pruned_loss=0.03328, over 7283.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2718, pruned_loss=0.03776, over 1428942.05 frames.], batch size: 18, lr: 4.07e-04
2022-04-29 14:40:26,376 INFO [train.py:763] (4/8) Epoch 18, batch 3200, loss[loss=0.1816, simple_loss=0.2822, pruned_loss=0.04056, over 7150.00 frames.], tot_loss[loss=0.174, simple_loss=0.2723, pruned_loss=0.03789, over 1427645.63 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:41:32,517 INFO [train.py:763] (4/8) Epoch 18, batch 3250, loss[loss=0.1593, simple_loss=0.2567, pruned_loss=0.03099, over 7350.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2728, pruned_loss=0.0381, over 1424538.07 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:42:37,738 INFO [train.py:763] (4/8) Epoch 18, batch 3300, loss[loss=0.1781, simple_loss=0.2708, pruned_loss=0.0427, over 6438.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2737, pruned_loss=0.03873, over 1425235.66 frames.], batch size: 37, lr: 4.07e-04
2022-04-29 14:43:43,235 INFO [train.py:763] (4/8) Epoch 18, batch 3350, loss[loss=0.2194, simple_loss=0.3091, pruned_loss=0.06484, over 7115.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2732, pruned_loss=0.03848, over 1424537.31 frames.], batch size: 21, lr: 4.07e-04
2022-04-29 14:44:48,481 INFO [train.py:763] (4/8) Epoch 18, batch 3400, loss[loss=0.1562, simple_loss=0.2431, pruned_loss=0.03464, over 7276.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2726, pruned_loss=0.0386, over 1424706.04 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:45:53,980 INFO [train.py:763] (4/8) Epoch 18, batch 3450, loss[loss=0.1475, simple_loss=0.2444, pruned_loss=0.02533, over 7351.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2721, pruned_loss=0.03874, over 1420633.98 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:46:59,195 INFO [train.py:763] (4/8) Epoch 18, batch 3500, loss[loss=0.1645, simple_loss=0.2535, pruned_loss=0.03775, over 7271.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2711, pruned_loss=0.03825, over 1422844.98 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:48:04,600 INFO [train.py:763] (4/8) Epoch 18, batch 3550, loss[loss=0.159, simple_loss=0.2509, pruned_loss=0.03353, over 7141.00 frames.], tot_loss[loss=0.174, simple_loss=0.2712, pruned_loss=0.03836, over 1423229.24 frames.], batch size: 17, lr: 4.06e-04
2022-04-29 14:49:09,816 INFO [train.py:763] (4/8) Epoch 18, batch 3600, loss[loss=0.1944, simple_loss=0.2898, pruned_loss=0.04949, over 7202.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.03871, over 1420978.23 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:50:14,978 INFO [train.py:763] (4/8) Epoch 18, batch 3650, loss[loss=0.148, simple_loss=0.2429, pruned_loss=0.02655, over 7321.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2723, pruned_loss=0.03846, over 1414717.27 frames.], batch size: 20, lr: 4.06e-04
2022-04-29 14:51:20,199 INFO [train.py:763] (4/8) Epoch 18, batch 3700, loss[loss=0.1815, simple_loss=0.2817, pruned_loss=0.04068, over 7411.00 frames.], tot_loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.03866, over 1416781.15 frames.], batch size: 21, lr: 4.06e-04
2022-04-29 14:52:25,585 INFO [train.py:763] (4/8) Epoch 18, batch 3750, loss[loss=0.1792, simple_loss=0.2811, pruned_loss=0.03868, over 7383.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2725, pruned_loss=0.03884, over 1413089.04 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:53:30,893 INFO [train.py:763] (4/8) Epoch 18, batch 3800, loss[loss=0.1554, simple_loss=0.2487, pruned_loss=0.03107, over 7343.00 frames.], tot_loss[loss=0.1752, simple_loss=0.273, pruned_loss=0.03876, over 1418601.43 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:54:36,406 INFO [train.py:763] (4/8) Epoch 18, batch 3850, loss[loss=0.1497, simple_loss=0.2473, pruned_loss=0.02605, over 7167.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2725, pruned_loss=0.03886, over 1416850.23 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:55:41,213 INFO [train.py:763] (4/8) Epoch 18, batch 3900, loss[loss=0.1678, simple_loss=0.276, pruned_loss=0.02976, over 7110.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2729, pruned_loss=0.03867, over 1414632.58 frames.], batch size: 21, lr: 4.05e-04
2022-04-29 14:56:46,298 INFO [train.py:763] (4/8) Epoch 18, batch 3950, loss[loss=0.1782, simple_loss=0.2771, pruned_loss=0.03969, over 7169.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2727, pruned_loss=0.0387, over 1416444.90 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:57:51,525 INFO [train.py:763] (4/8) Epoch 18, batch 4000, loss[loss=0.1856, simple_loss=0.2872, pruned_loss=0.04206, over 5072.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2727, pruned_loss=0.0389, over 1417154.51 frames.], batch size: 53, lr: 4.05e-04
2022-04-29 14:58:57,194 INFO [train.py:763] (4/8) Epoch 18, batch 4050, loss[loss=0.1334, simple_loss=0.2269, pruned_loss=0.02, over 6851.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2717, pruned_loss=0.03857, over 1416120.32 frames.], batch size: 15, lr: 4.05e-04
2022-04-29 15:00:03,349 INFO [train.py:763] (4/8) Epoch 18, batch 4100, loss[loss=0.2154, simple_loss=0.305, pruned_loss=0.06296, over 4851.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2722, pruned_loss=0.03906, over 1416366.83 frames.], batch size: 52, lr: 4.05e-04
2022-04-29 15:01:09,075 INFO [train.py:763] (4/8) Epoch 18, batch 4150, loss[loss=0.1676, simple_loss=0.261, pruned_loss=0.03713, over 7379.00 frames.], tot_loss[loss=0.1748, simple_loss=0.272, pruned_loss=0.03882, over 1421280.54 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:02:16,181 INFO [train.py:763] (4/8) Epoch 18, batch 4200, loss[loss=0.1898, simple_loss=0.2845, pruned_loss=0.04757, over 7205.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2711, pruned_loss=0.03819, over 1420026.08 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:03:23,608 INFO [train.py:763] (4/8) Epoch 18, batch 4250, loss[loss=0.1471, simple_loss=0.2362, pruned_loss=0.02906, over 6798.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03783, over 1419858.09 frames.], batch size: 15, lr: 4.04e-04
2022-04-29 15:04:28,930 INFO [train.py:763] (4/8) Epoch 18, batch 4300, loss[loss=0.1911, simple_loss=0.2863, pruned_loss=0.04794, over 7172.00 frames.], tot_loss[loss=0.173, simple_loss=0.2705, pruned_loss=0.03773, over 1419296.48 frames.], batch size: 26, lr: 4.04e-04
2022-04-29 15:05:35,077 INFO [train.py:763] (4/8) Epoch 18, batch 4350, loss[loss=0.1489, simple_loss=0.2372, pruned_loss=0.03027, over 7158.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2695, pruned_loss=0.03746, over 1416709.74 frames.], batch size: 18, lr: 4.04e-04
2022-04-29 15:06:42,524 INFO [train.py:763] (4/8) Epoch 18, batch 4400, loss[loss=0.1929, simple_loss=0.2924, pruned_loss=0.04666, over 6230.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2699, pruned_loss=0.03784, over 1412256.48 frames.], batch size: 38, lr: 4.04e-04
2022-04-29 15:07:48,909 INFO [train.py:763] (4/8) Epoch 18, batch 4450, loss[loss=0.1477, simple_loss=0.2289, pruned_loss=0.03323, over 7269.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2685, pruned_loss=0.03763, over 1407420.11 frames.], batch size: 16, lr: 4.04e-04
2022-04-29 15:08:55,423 INFO [train.py:763] (4/8) Epoch 18, batch 4500, loss[loss=0.1701, simple_loss=0.2647, pruned_loss=0.0377, over 7147.00 frames.], tot_loss[loss=0.1738, simple_loss=0.27, pruned_loss=0.03882, over 1394028.26 frames.], batch size: 20, lr: 4.04e-04
2022-04-29 15:10:01,680 INFO [train.py:763] (4/8) Epoch 18, batch 4550, loss[loss=0.1842, simple_loss=0.2876, pruned_loss=0.04044, over 6422.00 frames.], tot_loss[loss=0.174, simple_loss=0.2696, pruned_loss=0.03921, over 1366208.75 frames.], batch size: 37, lr: 4.04e-04
2022-04-29 15:11:30,591 INFO [train.py:763] (4/8) Epoch 19, batch 0, loss[loss=0.1559, simple_loss=0.2615, pruned_loss=0.02514, over 7352.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2615, pruned_loss=0.02514, over 7352.00 frames.], batch size: 19, lr: 3.94e-04
2022-04-29 15:12:36,738 INFO [train.py:763] (4/8) Epoch 19, batch 50, loss[loss=0.1614, simple_loss=0.2576, pruned_loss=0.0326, over 7265.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2716, pruned_loss=0.03692, over 320481.96 frames.], batch size: 18, lr: 3.94e-04
2022-04-29 15:13:42,678 INFO [train.py:763] (4/8) Epoch 19, batch 100, loss[loss=0.1796, simple_loss=0.2707, pruned_loss=0.0442, over 5117.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2709, pruned_loss=0.03708, over 565573.73 frames.], batch size: 52, lr: 3.94e-04
2022-04-29 15:14:48,874 INFO [train.py:763] (4/8) Epoch 19, batch 150, loss[loss=0.1721, simple_loss=0.2806, pruned_loss=0.03176, over 7319.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2738, pruned_loss=0.03736, over 755436.19 frames.], batch size: 21, lr: 3.94e-04
2022-04-29 15:15:54,339 INFO [train.py:763] (4/8) Epoch 19, batch 200, loss[loss=0.1708, simple_loss=0.2765, pruned_loss=0.03258, over 7329.00 frames.], tot_loss[loss=0.1746, simple_loss=0.274, pruned_loss=0.03763, over 903001.14 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:17:00,297 INFO [train.py:763] (4/8) Epoch 19, batch 250, loss[loss=0.1776, simple_loss=0.2889, pruned_loss=0.03316, over 7333.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2727, pruned_loss=0.03725, over 1022438.30 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:18:06,647 INFO [train.py:763] (4/8) Epoch 19, batch 300, loss[loss=0.1666, simple_loss=0.2659, pruned_loss=0.0337, over 7183.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2732, pruned_loss=0.03726, over 1111675.97 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:19:12,751 INFO [train.py:763] (4/8) Epoch 19, batch 350, loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03022, over 7145.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2734, pruned_loss=0.03751, over 1183866.61 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:20:18,120 INFO [train.py:763] (4/8) Epoch 19, batch 400, loss[loss=0.1973, simple_loss=0.3031, pruned_loss=0.04576, over 7152.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2745, pruned_loss=0.03805, over 1236919.89 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:21:23,454 INFO [train.py:763] (4/8) Epoch 19, batch 450, loss[loss=0.1932, simple_loss=0.297, pruned_loss=0.04468, over 7373.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2742, pruned_loss=0.03775, over 1274714.46 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:22:28,663 INFO [train.py:763] (4/8) Epoch 19, batch 500, loss[loss=0.1499, simple_loss=0.2545, pruned_loss=0.02263, over 7217.00 frames.], tot_loss[loss=0.1739, simple_loss=0.273, pruned_loss=0.03743, over 1306916.14 frames.], batch size: 21, lr: 3.93e-04
2022-04-29 15:23:34,242 INFO [train.py:763] (4/8) Epoch 19, batch 550, loss[loss=0.1947, simple_loss=0.2884, pruned_loss=0.05054, over 6761.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2723, pruned_loss=0.03736, over 1333609.76 frames.], batch size: 31, lr: 3.93e-04
2022-04-29 15:24:40,466 INFO [train.py:763] (4/8) Epoch 19, batch 600, loss[loss=0.1579, simple_loss=0.2533, pruned_loss=0.03126, over 7159.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2713, pruned_loss=0.037, over 1356049.75 frames.], batch size: 18, lr: 3.93e-04
2022-04-29 15:25:45,941 INFO [train.py:763] (4/8) Epoch 19, batch 650, loss[loss=0.1699, simple_loss=0.2689, pruned_loss=0.0354, over 7167.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2707, pruned_loss=0.03688, over 1369700.89 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:26:51,169 INFO [train.py:763] (4/8) Epoch 19, batch 700, loss[loss=0.1879, simple_loss=0.2895, pruned_loss=0.04318, over 7245.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2719, pruned_loss=0.03722, over 1383457.79 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:27:56,782 INFO [train.py:763] (4/8) Epoch 19, batch 750, loss[loss=0.1676, simple_loss=0.275, pruned_loss=0.03016, over 7298.00 frames.], tot_loss[loss=0.173, simple_loss=0.271, pruned_loss=0.03747, over 1393680.48 frames.], batch size: 25, lr: 3.92e-04
2022-04-29 15:29:03,456 INFO [train.py:763] (4/8) Epoch 19, batch 800, loss[loss=0.1508, simple_loss=0.2411, pruned_loss=0.03022, over 7417.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2705, pruned_loss=0.03733, over 1402859.28 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:30:19,513 INFO [train.py:763] (4/8) Epoch 19, batch 850, loss[loss=0.1983, simple_loss=0.2968, pruned_loss=0.04995, over 7077.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2708, pruned_loss=0.03749, over 1410720.69 frames.], batch size: 28, lr: 3.92e-04
2022-04-29 15:31:25,288 INFO [train.py:763] (4/8) Epoch 19, batch 900, loss[loss=0.1922, simple_loss=0.2834, pruned_loss=0.05046, over 7356.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2698, pruned_loss=0.03749, over 1415822.68 frames.], batch size: 19, lr: 3.92e-04
2022-04-29 15:32:30,745 INFO [train.py:763] (4/8) Epoch 19, batch 950, loss[loss=0.1898, simple_loss=0.2882, pruned_loss=0.04571, over 7229.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2711, pruned_loss=0.03812, over 1419729.41 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:33:36,031 INFO [train.py:763] (4/8) Epoch 19, batch 1000, loss[loss=0.1936, simple_loss=0.2797, pruned_loss=0.0537, over 7287.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2702, pruned_loss=0.03777, over 1420562.06 frames.], batch size: 24, lr: 3.92e-04
2022-04-29 15:34:41,368 INFO [train.py:763] (4/8) Epoch 19, batch 1050, loss[loss=0.1791, simple_loss=0.2784, pruned_loss=0.03994, over 7179.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2707, pruned_loss=0.03782, over 1419417.07 frames.], batch size: 22, lr: 3.92e-04
2022-04-29 15:35:47,009 INFO [train.py:763] (4/8) Epoch 19, batch 1100, loss[loss=0.1806, simple_loss=0.2699, pruned_loss=0.04568, over 7218.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2709, pruned_loss=0.038, over 1416113.13 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:36:52,333 INFO [train.py:763] (4/8) Epoch 19, batch 1150, loss[loss=0.182, simple_loss=0.2839, pruned_loss=0.04005, over 7280.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03824, over 1420281.07 frames.], batch size: 24, lr: 3.91e-04
2022-04-29 15:38:08,753 INFO [train.py:763] (4/8) Epoch 19, batch 1200, loss[loss=0.2049, simple_loss=0.3061, pruned_loss=0.05182, over 7340.00 frames.], tot_loss[loss=0.173, simple_loss=0.2704, pruned_loss=0.03775, over 1425010.63 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:39:14,189 INFO [train.py:763] (4/8) Epoch 19, batch 1250, loss[loss=0.1525, simple_loss=0.2349, pruned_loss=0.03509, over 7149.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2704, pruned_loss=0.03791, over 1425995.28 frames.], batch size: 17, lr: 3.91e-04
2022-04-29 15:40:19,874 INFO [train.py:763] (4/8) Epoch 19, batch 1300, loss[loss=0.1693, simple_loss=0.276, pruned_loss=0.03127, over 7103.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2705, pruned_loss=0.03792, over 1427021.46 frames.], batch size: 21, lr: 3.91e-04
2022-04-29 15:41:25,077 INFO [train.py:763] (4/8) Epoch 19, batch 1350, loss[loss=0.1902, simple_loss=0.2895, pruned_loss=0.04549, over 7204.00 frames.], tot_loss[loss=0.173, simple_loss=0.2703, pruned_loss=0.03783, over 1428699.30 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:42:30,861 INFO [train.py:763] (4/8) Epoch 19, batch 1400, loss[loss=0.1909, simple_loss=0.2913, pruned_loss=0.04526, over 7195.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2704, pruned_loss=0.03766, over 1430023.53 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:43:46,243 INFO [train.py:763] (4/8) Epoch 19, batch 1450, loss[loss=0.2015, simple_loss=0.2923, pruned_loss=0.05537, over 7217.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2715, pruned_loss=0.03808, over 1429147.78 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:45:09,718 INFO [train.py:763] (4/8) Epoch 19, batch 1500, loss[loss=0.2075, simple_loss=0.3016, pruned_loss=0.05669, over 7369.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2731, pruned_loss=0.03886, over 1427368.73 frames.], batch size: 23, lr: 3.91e-04
2022-04-29 15:46:15,425 INFO [train.py:763] (4/8) Epoch 19, batch 1550, loss[loss=0.1564, simple_loss=0.249, pruned_loss=0.03187, over 7441.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2721, pruned_loss=0.03854, over 1429085.41 frames.], batch size: 20, lr: 3.91e-04
2022-04-29 15:47:30,074 INFO [train.py:763] (4/8) Epoch 19, batch 1600, loss[loss=0.1871, simple_loss=0.2889, pruned_loss=0.04267, over 7324.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2714, pruned_loss=0.03819, over 1424595.06 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:48:53,933 INFO [train.py:763] (4/8) Epoch 19, batch 1650, loss[loss=0.1845, simple_loss=0.2881, pruned_loss=0.04049, over 7195.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.0378, over 1422338.13 frames.], batch size: 23, lr: 3.90e-04
2022-04-29 15:50:08,826 INFO [train.py:763] (4/8) Epoch 19, batch 1700, loss[loss=0.1422, simple_loss=0.2471, pruned_loss=0.01866, over 7159.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03765, over 1421226.89 frames.], batch size: 19, lr: 3.90e-04
2022-04-29 15:51:14,399 INFO [train.py:763] (4/8) Epoch 19, batch 1750, loss[loss=0.1708, simple_loss=0.2725, pruned_loss=0.03457, over 7338.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2702, pruned_loss=0.03722, over 1426369.49 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:52:19,997 INFO [train.py:763] (4/8) Epoch 19, batch 1800, loss[loss=0.1899, simple_loss=0.2985, pruned_loss=0.04064, over 7298.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03715, over 1426306.84 frames.], batch size: 25, lr: 3.90e-04
2022-04-29 15:53:25,555 INFO [train.py:763] (4/8) Epoch 19, batch 1850, loss[loss=0.1702, simple_loss=0.2649, pruned_loss=0.03776, over 7061.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2707, pruned_loss=0.03711, over 1429321.09 frames.], batch size: 18, lr: 3.90e-04
2022-04-29 15:54:30,870 INFO [train.py:763] (4/8) Epoch 19, batch 1900, loss[loss=0.1646, simple_loss=0.2652, pruned_loss=0.03205, over 7244.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2716, pruned_loss=0.03747, over 1429853.16 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:55:38,243 INFO [train.py:763] (4/8) Epoch 19, batch 1950, loss[loss=0.172, simple_loss=0.2818, pruned_loss=0.03115, over 6414.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2711, pruned_loss=0.0374, over 1430512.27 frames.], batch size: 38, lr: 3.90e-04
2022-04-29 15:56:45,557 INFO [train.py:763] (4/8) Epoch 19, batch 2000, loss[loss=0.1518, simple_loss=0.2615, pruned_loss=0.02108, over 7236.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2704, pruned_loss=0.03754, over 1431242.03 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:57:52,836 INFO [train.py:763] (4/8) Epoch 19, batch 2050, loss[loss=0.1728, simple_loss=0.2749, pruned_loss=0.03541, over 7222.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2695, pruned_loss=0.03719, over 1430471.81 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 15:58:58,690 INFO [train.py:763] (4/8) Epoch 19, batch 2100, loss[loss=0.1806, simple_loss=0.2728, pruned_loss=0.04423, over 7431.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2698, pruned_loss=0.03725, over 1432307.13 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:00:05,503 INFO [train.py:763] (4/8) Epoch 19, batch 2150, loss[loss=0.1978, simple_loss=0.2937, pruned_loss=0.05094, over 7209.00 frames.], tot_loss[loss=0.172, simple_loss=0.2699, pruned_loss=0.03709, over 1425848.57 frames.], batch size: 22, lr: 3.89e-04
2022-04-29 16:01:11,304 INFO [train.py:763] (4/8) Epoch 19, batch 2200, loss[loss=0.1529, simple_loss=0.2375, pruned_loss=0.03414, over 6808.00 frames.], tot_loss[loss=0.1727, simple_loss=0.27, pruned_loss=0.03763, over 1421538.81 frames.], batch size: 15, lr: 3.89e-04
2022-04-29 16:02:17,295 INFO [train.py:763] (4/8) Epoch 19, batch 2250, loss[loss=0.1786, simple_loss=0.2893, pruned_loss=0.03396, over 7132.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2704, pruned_loss=0.03768, over 1423581.61 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:03:23,074 INFO [train.py:763] (4/8) Epoch 19, batch 2300, loss[loss=0.1681, simple_loss=0.2696, pruned_loss=0.03336, over 7374.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2699, pruned_loss=0.03737, over 1423759.80 frames.], batch size: 23, lr: 3.89e-04
2022-04-29 16:04:28,767 INFO [train.py:763] (4/8) Epoch 19, batch 2350, loss[loss=0.1929, simple_loss=0.2937, pruned_loss=0.04612, over 7321.00 frames.], tot_loss[loss=0.1734, simple_loss=0.271, pruned_loss=0.03793, over 1422135.94 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 16:05:34,123 INFO [train.py:763] (4/8) Epoch 19, batch 2400, loss[loss=0.1563, simple_loss=0.2597, pruned_loss=0.0265, over 7444.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03689, over 1424585.96 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:06:39,692 INFO [train.py:763] (4/8) Epoch 19, batch 2450, loss[loss=0.1804, simple_loss=0.2801, pruned_loss=0.04035, over 7123.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2698, pruned_loss=0.03724, over 1427630.04 frames.], batch size: 28, lr: 3.89e-04
2022-04-29 16:07:45,460 INFO [train.py:763] (4/8) Epoch 19, batch 2500, loss[loss=0.1965, simple_loss=0.3023, pruned_loss=0.04534, over 7212.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2694, pruned_loss=0.03743, over 1426217.76 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:08:50,994 INFO [train.py:763] (4/8) Epoch 19, batch 2550, loss[loss=0.1995, simple_loss=0.3006, pruned_loss=0.04914, over 7330.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2706, pruned_loss=0.03792, over 1424848.00 frames.], batch size: 20, lr: 3.88e-04
2022-04-29 16:09:56,807 INFO [train.py:763] (4/8) Epoch 19, batch 2600, loss[loss=0.1867, simple_loss=0.2784, pruned_loss=0.04754, over 6731.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03803, over 1425452.18 frames.], batch size: 31, lr: 3.88e-04
2022-04-29 16:11:03,363 INFO [train.py:763] (4/8) Epoch 19, batch 2650, loss[loss=0.1615, simple_loss=0.2436, pruned_loss=0.03971, over 7020.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2705, pruned_loss=0.038, over 1427405.76 frames.], batch size: 16, lr: 3.88e-04
2022-04-29 16:12:10,009 INFO [train.py:763] (4/8) Epoch 19, batch 2700, loss[loss=0.1926, simple_loss=0.2851, pruned_loss=0.05008, over 7381.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2707, pruned_loss=0.03802, over 1428483.18 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:13:17,136 INFO [train.py:763] (4/8) Epoch 19, batch 2750, loss[loss=0.1656, simple_loss=0.2679, pruned_loss=0.03169, over 7211.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2709, pruned_loss=0.03778, over 1427289.63 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:14:22,705 INFO [train.py:763] (4/8) Epoch 19, batch 2800, loss[loss=0.1775, simple_loss=0.2777, pruned_loss=0.03862, over 7148.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.03739, over 1430977.12 frames.], batch size: 18, lr: 3.88e-04
2022-04-29 16:15:28,759 INFO [train.py:763] (4/8) Epoch 19, batch 2850, loss[loss=0.152, simple_loss=0.2613, pruned_loss=0.02132, over 7405.00 frames.], tot_loss[loss=0.173, simple_loss=0.2709, pruned_loss=0.0375, over 1432617.22 frames.], batch size: 21, lr: 3.88e-04
2022-04-29 16:16:34,845 INFO [train.py:763] (4/8) Epoch 19, batch 2900, loss[loss=0.1815, simple_loss=0.2872, pruned_loss=0.03792, over 7190.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2695, pruned_loss=0.03709, over 1428343.16 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:17:40,404 INFO [train.py:763] (4/8) Epoch 19, batch 2950, loss[loss=0.1656, simple_loss=0.2686, pruned_loss=0.0313, over 7224.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2705, pruned_loss=0.03763, over 1432430.04 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:18:45,954 INFO [train.py:763] (4/8) Epoch 19, batch 3000, loss[loss=0.2046, simple_loss=0.2972, pruned_loss=0.05601, over 7382.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2712, pruned_loss=0.03746, over 1431264.95 frames.], batch size: 23, lr: 3.87e-04
2022-04-29 16:18:45,955 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 16:19:01,554 INFO [train.py:792] (4/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
2022-04-29 16:20:06,918 INFO [train.py:763] (4/8) Epoch 19, batch 3050, loss[loss=0.1643, simple_loss=0.261, pruned_loss=0.03377, over 7152.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2705, pruned_loss=0.03716, over 1432455.52 frames.], batch size: 19, lr: 3.87e-04
2022-04-29 16:21:12,179 INFO [train.py:763] (4/8) Epoch 19, batch 3100, loss[loss=0.1827, simple_loss=0.276, pruned_loss=0.0447, over 7121.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2707, pruned_loss=0.03717, over 1431857.40 frames.], batch size: 21, lr: 3.87e-04
2022-04-29 16:22:17,530 INFO [train.py:763] (4/8) Epoch 19, batch 3150, loss[loss=0.1699, simple_loss=0.2694, pruned_loss=0.03521, over 7268.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2707, pruned_loss=0.03731, over 1432714.48 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:23:23,023 INFO [train.py:763] (4/8) Epoch 19, batch 3200, loss[loss=0.1862, simple_loss=0.2855, pruned_loss=0.04347, over 6733.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2698, pruned_loss=0.03693, over 1431535.49 frames.], batch size: 31, lr: 3.87e-04
2022-04-29 16:24:28,067 INFO [train.py:763] (4/8) Epoch 19, batch 3250, loss[loss=0.1546, simple_loss=0.2481, pruned_loss=0.0306, over 7060.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2702, pruned_loss=0.03735, over 1428428.15 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:25:34,718 INFO [train.py:763] (4/8) Epoch 19, batch 3300, loss[loss=0.1513, simple_loss=0.2387, pruned_loss=0.03199, over 7140.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2699, pruned_loss=0.03751, over 1426522.41 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:26:41,781 INFO [train.py:763] (4/8) Epoch 19, batch 3350, loss[loss=0.1756, simple_loss=0.2777, pruned_loss=0.03678, over 7142.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2701, pruned_loss=0.03769, over 1427299.90 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:27:47,540 INFO [train.py:763] (4/8) Epoch 19, batch 3400, loss[loss=0.127, simple_loss=0.2117, pruned_loss=0.02119, over 7281.00 frames.], tot_loss[loss=0.1727, simple_loss=0.27, pruned_loss=0.03767, over 1427275.97 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:28:53,013 INFO [train.py:763] (4/8) Epoch 19, batch 3450, loss[loss=0.1657, simple_loss=0.2715, pruned_loss=0.02992, over 7226.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03783, over 1425203.89 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:29:58,520 INFO [train.py:763] (4/8) Epoch 19, batch 3500, loss[loss=0.1557, simple_loss=0.2559, pruned_loss=0.02772, over 7262.00 frames.], tot_loss[loss=0.1723, simple_loss=0.27, pruned_loss=0.03726, over 1424111.40 frames.], batch size: 19, lr: 3.86e-04
2022-04-29 16:31:03,658 INFO [train.py:763] (4/8) Epoch 19, batch 3550, loss[loss=0.1778, simple_loss=0.2783, pruned_loss=0.03862, over 7120.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2712, pruned_loss=0.03759, over 1427011.06 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:32:09,189 INFO [train.py:763] (4/8) Epoch 19, batch 3600, loss[loss=0.2039, simple_loss=0.3051, pruned_loss=0.05133, over 7190.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2721, pruned_loss=0.03783, over 1429456.38 frames.], batch size: 23, lr: 3.86e-04
2022-04-29 16:33:15,436 INFO [train.py:763] (4/8) Epoch 19, batch 3650, loss[loss=0.1862, simple_loss=0.2951, pruned_loss=0.03862, over 7316.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2719, pruned_loss=0.03771, over 1430704.81 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:34:21,091 INFO [train.py:763] (4/8) Epoch 19, batch 3700, loss[loss=0.138, simple_loss=0.2328, pruned_loss=0.02159, over 7161.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2718, pruned_loss=0.03749, over 1432336.67 frames.], batch size: 18, lr: 3.86e-04
2022-04-29 16:35:26,769 INFO [train.py:763] (4/8) Epoch 19, batch 3750, loss[loss=0.1825, simple_loss=0.2907, pruned_loss=0.03714, over 7051.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2712, pruned_loss=0.03715, over 1426089.08 frames.], batch size: 28, lr: 3.86e-04
2022-04-29 16:36:32,304 INFO [train.py:763] (4/8) Epoch 19, batch 3800, loss[loss=0.1688, simple_loss=0.266, pruned_loss=0.03586, over 7325.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2707, pruned_loss=0.03702, over 1421532.67 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:37:37,905 INFO [train.py:763] (4/8) Epoch 19, batch 3850, loss[loss=0.1571, simple_loss=0.2444, pruned_loss=0.03494, over 7269.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2706, pruned_loss=0.03716, over 1419921.47 frames.], batch size: 17, lr: 3.86e-04
2022-04-29 16:38:44,164 INFO [train.py:763] (4/8) Epoch 19, batch 3900, loss[loss=0.1713, simple_loss=0.2734, pruned_loss=0.03464, over 7109.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2712, pruned_loss=0.03727, over 1417029.01 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:39:50,746 INFO [train.py:763] (4/8) Epoch 19, batch 3950, loss[loss=0.1565, simple_loss=0.2528, pruned_loss=0.03009, over 7335.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2712, pruned_loss=0.03757, over 1410862.47 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:40:57,111 INFO [train.py:763] (4/8) Epoch 19, batch 4000, loss[loss=0.1592, simple_loss=0.2522, pruned_loss=0.03311, over 7158.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2708, pruned_loss=0.03724, over 1409056.20 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:42:03,324 INFO [train.py:763] (4/8) Epoch 19, batch 4050, loss[loss=0.1755, simple_loss=0.2703, pruned_loss=0.04033, over 7334.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2705, pruned_loss=0.03757, over 1405810.39 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:43:09,188 INFO [train.py:763] (4/8) Epoch 19, batch 4100, loss[loss=0.1556, simple_loss=0.2537, pruned_loss=0.02874, over 7285.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2692, pruned_loss=0.03745, over 1406622.31 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:44:14,859 INFO [train.py:763] (4/8) Epoch 19, batch 4150, loss[loss=0.1606, simple_loss=0.2585, pruned_loss=0.03131, over 7081.00 frames.], tot_loss[loss=0.1709, simple_loss=0.268, pruned_loss=0.03687, over 1410073.10 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:45:20,202 INFO [train.py:763] (4/8) Epoch 19, batch 4200, loss[loss=0.1549, simple_loss=0.2384, pruned_loss=0.03577, over 7239.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2685, pruned_loss=0.03692, over 1405584.03 frames.], batch size: 16, lr: 3.85e-04
2022-04-29 16:46:26,005 INFO [train.py:763] (4/8) Epoch 19, batch 4250, loss[loss=0.1914, simple_loss=0.2908, pruned_loss=0.04605, over 7200.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2676, pruned_loss=0.03691, over 1402680.25 frames.], batch size: 23, lr: 3.85e-04
2022-04-29 16:47:31,493 INFO [train.py:763] (4/8) Epoch 19, batch 4300, loss[loss=0.1956, simple_loss=0.2968, pruned_loss=0.04727, over 7220.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2688, pruned_loss=0.03728, over 1400984.05 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:48:37,206 INFO [train.py:763] (4/8) Epoch 19, batch 4350, loss[loss=0.2224, simple_loss=0.2985, pruned_loss=0.07312, over 5003.00 frames.], tot_loss[loss=0.1703, simple_loss=0.267, pruned_loss=0.03685, over 1404644.73 frames.], batch size: 53, lr: 3.84e-04
2022-04-29 16:49:42,590 INFO [train.py:763] (4/8) Epoch 19, batch 4400, loss[loss=0.1841, simple_loss=0.286, pruned_loss=0.04114, over 7163.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2659, pruned_loss=0.03643, over 1399650.26 frames.], batch size: 19, lr: 3.84e-04
2022-04-29 16:50:47,786 INFO [train.py:763] (4/8) Epoch 19, batch 4450, loss[loss=0.14, simple_loss=0.2363, pruned_loss=0.02182, over 6777.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2658, pruned_loss=0.03646, over 1390449.93 frames.], batch size: 15, lr: 3.84e-04
2022-04-29 16:51:52,272 INFO [train.py:763] (4/8) Epoch 19, batch 4500, loss[loss=0.176, simple_loss=0.2803, pruned_loss=0.03583, over 7193.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2671, pruned_loss=0.03689, over 1382479.32 frames.], batch size: 23, lr: 3.84e-04
2022-04-29 16:52:57,054 INFO [train.py:763] (4/8) Epoch 19, batch 4550, loss[loss=0.1643, simple_loss=0.2628, pruned_loss=0.0329, over 6466.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2706, pruned_loss=0.03904, over 1337096.85 frames.], batch size: 38, lr: 3.84e-04
2022-04-29 16:54:25,839 INFO [train.py:763] (4/8) Epoch 20, batch 0, loss[loss=0.1836, simple_loss=0.2652, pruned_loss=0.051, over 7000.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2652, pruned_loss=0.051, over 7000.00 frames.], batch size: 16, lr: 3.75e-04
2022-04-29 16:55:32,592 INFO [train.py:763] (4/8) Epoch 20, batch 50, loss[loss=0.164, simple_loss=0.2714, pruned_loss=0.02827, over 6457.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2697, pruned_loss=0.03739, over 323710.65 frames.], batch size: 37, lr: 3.75e-04
2022-04-29 16:56:38,000 INFO [train.py:763] (4/8) Epoch 20, batch 100, loss[loss=0.1692, simple_loss=0.2639, pruned_loss=0.03725, over 6790.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2709, pruned_loss=0.03701, over 567174.44 frames.], batch size: 15, lr: 3.75e-04
2022-04-29 16:57:44,561 INFO [train.py:763] (4/8) Epoch 20, batch 150, loss[loss=0.149, simple_loss=0.2456, pruned_loss=0.02618, over 7171.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2702, pruned_loss=0.03739, over 756383.37 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 16:58:49,750 INFO [train.py:763] (4/8) Epoch 20, batch 200, loss[loss=0.1785, simple_loss=0.2819, pruned_loss=0.03754, over 6818.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2717, pruned_loss=0.0379, over 901518.65 frames.], batch size: 31, lr: 3.75e-04
2022-04-29 16:59:55,578 INFO [train.py:763] (4/8) Epoch 20, batch 250, loss[loss=0.1962, simple_loss=0.2967, pruned_loss=0.04789, over 7160.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2705, pruned_loss=0.03751, over 1012758.67 frames.], batch size: 19, lr: 3.75e-04
2022-04-29 17:01:00,761 INFO [train.py:763] (4/8) Epoch 20, batch 300, loss[loss=0.1388, simple_loss=0.2342, pruned_loss=0.02165, over 7285.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03705, over 1102175.40 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 17:02:05,606 INFO [train.py:763] (4/8) Epoch 20, batch 350, loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02881, over 7260.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2709, pruned_loss=0.03733, over 1170177.98 frames.], batch size: 19, lr: 3.74e-04
2022-04-29 17:03:10,955 INFO [train.py:763] (4/8) Epoch 20, batch 400, loss[loss=0.1487, simple_loss=0.2386, pruned_loss=0.02938, over 7061.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2702, pruned_loss=0.03705, over 1229316.87 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:04:16,932 INFO [train.py:763] (4/8) Epoch 20, batch 450, loss[loss=0.1459, simple_loss=0.247, pruned_loss=0.02241, over 7457.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03719, over 1272456.09 frames.], batch size: 19, lr: 3.74e-04
2022-04-29 17:05:22,373 INFO [train.py:763] (4/8) Epoch 20, batch 500, loss[loss=0.1828, simple_loss=0.2813, pruned_loss=0.04215, over 7065.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2715, pruned_loss=0.03778, over 1310966.40 frames.], batch size: 28, lr: 3.74e-04
2022-04-29 17:06:27,714 INFO [train.py:763] (4/8) Epoch 20, batch 550, loss[loss=0.1582, simple_loss=0.2507, pruned_loss=0.03282, over 6813.00 frames.], tot_loss[loss=0.1727, simple_loss=0.271, pruned_loss=0.03719, over 1337035.86 frames.], batch size: 15, lr: 3.74e-04
2022-04-29 17:07:34,454 INFO [train.py:763] (4/8) Epoch 20, batch 600, loss[loss=0.1827, simple_loss=0.2723, pruned_loss=0.04656, over 7205.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2708, pruned_loss=0.03691, over 1355592.49 frames.], batch size: 22, lr: 3.74e-04
2022-04-29 17:08:41,618 INFO [train.py:763] (4/8) Epoch 20, batch 650, loss[loss=0.1393, simple_loss=0.2259, pruned_loss=0.02636, over 7134.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2689, pruned_loss=0.03666, over 1370486.23 frames.], batch size: 17, lr: 3.74e-04
2022-04-29 17:09:47,491 INFO [train.py:763] (4/8) Epoch 20, batch 700, loss[loss=0.1761, simple_loss=0.2809, pruned_loss=0.03562, over 7240.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03685, over 1380968.87 frames.], batch size: 20, lr: 3.74e-04
2022-04-29 17:10:53,616 INFO [train.py:763] (4/8) Epoch 20, batch 750, loss[loss=0.1512, simple_loss=0.2357, pruned_loss=0.03334, over 7434.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03693, over 1386025.83 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:11:58,915 INFO [train.py:763] (4/8) Epoch 20, batch 800, loss[loss=0.1862, simple_loss=0.2755, pruned_loss=0.0485, over 7238.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2691, pruned_loss=0.03697, over 1384267.57 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:13:05,455 INFO [train.py:763] (4/8) Epoch 20, batch 850, loss[loss=0.1756, simple_loss=0.2782, pruned_loss=0.03644, over 7309.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2686, pruned_loss=0.03691, over 1391515.94 frames.], batch size: 25, lr: 3.73e-04
2022-04-29 17:14:10,904 INFO [train.py:763] (4/8) Epoch 20, batch 900, loss[loss=0.1694, simple_loss=0.2787, pruned_loss=0.02999, over 7239.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2682, pruned_loss=0.03682, over 1400552.89 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:15:15,945 INFO [train.py:763] (4/8) Epoch 20, batch 950, loss[loss=0.1818, simple_loss=0.2945, pruned_loss=0.03459, over 7337.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2688, pruned_loss=0.03675, over 1406037.44 frames.], batch size: 22, lr: 3.73e-04
2022-04-29 17:16:21,949 INFO [train.py:763] (4/8) Epoch 20, batch 1000, loss[loss=0.1978, simple_loss=0.2924, pruned_loss=0.05163, over 7178.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03691, over 1404840.08 frames.], batch size: 23, lr: 3.73e-04
2022-04-29 17:17:26,879 INFO [train.py:763] (4/8) Epoch 20, batch 1050, loss[loss=0.1551, simple_loss=0.2641, pruned_loss=0.02304, over 7405.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2706, pruned_loss=0.03689, over 1406030.53 frames.], batch size: 21, lr: 3.73e-04
2022-04-29 17:18:32,319 INFO [train.py:763] (4/8) Epoch 20, batch 1100, loss[loss=0.166, simple_loss=0.2512, pruned_loss=0.04036, over 6802.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2689, pruned_loss=0.03661, over 1407449.65 frames.], batch size: 15, lr: 3.73e-04
2022-04-29 17:19:37,612 INFO [train.py:763] (4/8) Epoch 20, batch 1150, loss[loss=0.2092, simple_loss=0.2992, pruned_loss=0.05964, over 7290.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2684, pruned_loss=0.03662, over 1412732.67 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:20:42,596 INFO [train.py:763] (4/8) Epoch 20, batch 1200, loss[loss=0.1464, simple_loss=0.2385, pruned_loss=0.02714, over 7295.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2687, pruned_loss=0.03686, over 1415801.05 frames.], batch size: 18, lr: 3.73e-04
2022-04-29 17:21:47,930 INFO [train.py:763] (4/8) Epoch 20, batch 1250, loss[loss=0.2034, simple_loss=0.2956, pruned_loss=0.05556, over 7298.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2679, pruned_loss=0.03672, over 1418214.28 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:22:53,223 INFO [train.py:763] (4/8) Epoch 20, batch 1300, loss[loss=0.1389, simple_loss=0.239, pruned_loss=0.01942, over 7065.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2675, pruned_loss=0.03651, over 1417010.03 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:23:59,017 INFO [train.py:763] (4/8) Epoch 20, batch 1350, loss[loss=0.1708, simple_loss=0.2763, pruned_loss=0.03268, over 7333.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2666, pruned_loss=0.03594, over 1423751.65 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:25:04,571 INFO [train.py:763] (4/8) Epoch 20, batch 1400, loss[loss=0.1948, simple_loss=0.2932, pruned_loss=0.0482, over 7388.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2682, pruned_loss=0.03648, over 1426151.92 frames.], batch size: 23, lr: 3.72e-04
2022-04-29 17:26:11,035 INFO [train.py:763] (4/8) Epoch 20, batch 1450, loss[loss=0.215, simple_loss=0.2979, pruned_loss=0.06607, over 4711.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2683, pruned_loss=0.03665, over 1420561.73 frames.], batch size: 52, lr: 3.72e-04
2022-04-29 17:27:17,681 INFO [train.py:763] (4/8) Epoch 20, batch 1500, loss[loss=0.1741, simple_loss=0.283, pruned_loss=0.03261, over 7336.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2694, pruned_loss=0.03682, over 1419017.60 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:28:24,675 INFO [train.py:763] (4/8) Epoch 20, batch 1550, loss[loss=0.1664, simple_loss=0.2698, pruned_loss=0.03153, over 6775.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2692, pruned_loss=0.03659, over 1420456.02 frames.], batch size: 31, lr: 3.72e-04
2022-04-29 17:29:31,790 INFO [train.py:763] (4/8) Epoch 20, batch 1600, loss[loss=0.1965, simple_loss=0.2913, pruned_loss=0.05087, over 7340.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2705, pruned_loss=0.03662, over 1421984.64 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:30:38,859 INFO [train.py:763] (4/8) Epoch 20, batch 1650, loss[loss=0.147, simple_loss=0.2468, pruned_loss=0.02357, over 7312.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2708, pruned_loss=0.03688, over 1422633.86 frames.], batch size: 20, lr: 3.72e-04
2022-04-29 17:31:46,135 INFO [train.py:763] (4/8) Epoch 20, batch 1700, loss[loss=0.1745, simple_loss=0.2784, pruned_loss=0.03532, over 7337.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2706, pruned_loss=0.03703, over 1422675.62 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:32:52,729 INFO [train.py:763] (4/8) Epoch 20, batch 1750, loss[loss=0.1574, simple_loss=0.2514, pruned_loss=0.03167, over 7410.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2697, pruned_loss=0.03672, over 1423675.66 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:33:59,655 INFO [train.py:763] (4/8) Epoch 20, batch 1800, loss[loss=0.1585, simple_loss=0.2688, pruned_loss=0.0241, over 7206.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2691, pruned_loss=0.03615, over 1425123.42 frames.], batch size: 23, lr: 3.71e-04
2022-04-29 17:35:06,941 INFO [train.py:763] (4/8) Epoch 20, batch 1850, loss[loss=0.1346, simple_loss=0.2283, pruned_loss=0.0205, over 7408.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03672, over 1423780.00 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:36:12,557 INFO [train.py:763] (4/8) Epoch 20, batch 1900, loss[loss=0.1674, simple_loss=0.2665, pruned_loss=0.03419, over 7160.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2696, pruned_loss=0.03687, over 1425344.50 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:37:18,020 INFO [train.py:763] (4/8) Epoch 20, batch 1950, loss[loss=0.154, simple_loss=0.2594, pruned_loss=0.02426, over 7258.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2687, pruned_loss=0.03644, over 1428464.84 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:38:24,301 INFO [train.py:763] (4/8) Epoch 20, batch 2000, loss[loss=0.162, simple_loss=0.2666, pruned_loss=0.02872, over 6734.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2681, pruned_loss=0.03622, over 1424609.80 frames.], batch size: 31, lr: 3.71e-04
2022-04-29 17:39:29,412 INFO [train.py:763] (4/8) Epoch 20, batch 2050, loss[loss=0.1674, simple_loss=0.2649, pruned_loss=0.03497, over 7227.00 frames.], tot_loss[loss=0.1711, simple_loss=0.269, pruned_loss=0.03659, over 1424803.46 frames.], batch size: 21, lr: 3.71e-04
2022-04-29 17:40:35,599 INFO [train.py:763] (4/8) Epoch 20, batch 2100, loss[loss=0.182, simple_loss=0.2705, pruned_loss=0.04674, over 7066.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2688, pruned_loss=0.03655, over 1423586.85 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:41:42,814 INFO [train.py:763] (4/8) Epoch 20, batch 2150, loss[loss=0.1499, simple_loss=0.2384, pruned_loss=0.03068, over 7206.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03631, over 1421574.78 frames.], batch size: 16, lr: 3.71e-04
2022-04-29 17:42:48,994 INFO [train.py:763] (4/8) Epoch 20, batch 2200, loss[loss=0.1885, simple_loss=0.2881, pruned_loss=0.04446, over 7211.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2685, pruned_loss=0.03653, over 1424052.33 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:43:54,359 INFO [train.py:763] (4/8) Epoch 20, batch 2250, loss[loss=0.1693, simple_loss=0.2658, pruned_loss=0.03644, over 7206.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2688, pruned_loss=0.03665, over 1425145.66 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:45:01,605 INFO [train.py:763] (4/8) Epoch 20, batch 2300, loss[loss=0.1916, simple_loss=0.2728, pruned_loss=0.05517, over 4953.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2677, pruned_loss=0.0365, over 1422857.58 frames.], batch size: 52, lr: 3.71e-04
2022-04-29 17:46:08,267 INFO [train.py:763] (4/8) Epoch 20, batch 2350, loss[loss=0.1907, simple_loss=0.2948, pruned_loss=0.04329, over 7288.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2691, pruned_loss=0.03677, over 1419021.00 frames.], batch size: 24, lr: 3.70e-04
2022-04-29 17:47:15,535 INFO [train.py:763] (4/8) Epoch 20, batch 2400, loss[loss=0.1687, simple_loss=0.2696, pruned_loss=0.03386, over 7215.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2686, pruned_loss=0.0365, over 1421308.81 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:48:22,378 INFO [train.py:763] (4/8) Epoch 20, batch 2450, loss[loss=0.1927, simple_loss=0.2856, pruned_loss=0.04993, over 7173.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2681, pruned_loss=0.03619, over 1422015.52 frames.], batch size: 19, lr: 3.70e-04
2022-04-29 17:49:29,422 INFO [train.py:763] (4/8) Epoch 20, batch 2500, loss[loss=0.1581, simple_loss=0.2649, pruned_loss=0.02566, over 7413.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2678, pruned_loss=0.03631, over 1422859.45 frames.], batch size: 21, lr: 3.70e-04
2022-04-29 17:50:36,099 INFO [train.py:763] (4/8) Epoch 20, batch 2550, loss[loss=0.1811, simple_loss=0.2782, pruned_loss=0.04203, over 5091.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2682, pruned_loss=0.03638, over 1420266.20 frames.], batch size: 52, lr: 3.70e-04
2022-04-29 17:51:41,443 INFO [train.py:763] (4/8) Epoch 20, batch 2600, loss[loss=0.1861, simple_loss=0.2851, pruned_loss=0.04355, over 7063.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2698, pruned_loss=0.03719, over 1420869.42 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:52:58,238 INFO [train.py:763] (4/8) Epoch 20, batch 2650, loss[loss=0.1743, simple_loss=0.2717, pruned_loss=0.03847, over 7320.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2703, pruned_loss=0.03758, over 1416412.96 frames.], batch size: 20, lr: 3.70e-04
2022-04-29 17:54:04,065 INFO [train.py:763] (4/8) Epoch 20, batch 2700, loss[loss=0.1611, simple_loss=0.2576, pruned_loss=0.03231, over 7411.00 frames.], tot_loss[loss=0.1722, simple_loss=0.27, pruned_loss=0.0372, over 1419971.54 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:55:10,581 INFO [train.py:763] (4/8) Epoch 20, batch 2750, loss[loss=0.1679, simple_loss=0.2562, pruned_loss=0.03982, over 7160.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03779, over 1421409.94 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:56:15,900 INFO [train.py:763] (4/8) Epoch 20, batch 2800, loss[loss=0.1767, simple_loss=0.2855, pruned_loss=0.03399, over 7390.00 frames.], tot_loss[loss=0.1726, simple_loss=0.27, pruned_loss=0.03765, over 1425312.29 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:57:21,235 INFO [train.py:763] (4/8) Epoch 20, batch 2850, loss[loss=0.1764, simple_loss=0.2849, pruned_loss=0.03395, over 7195.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2698, pruned_loss=0.03738, over 1421126.78 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 17:58:26,457 INFO [train.py:763] (4/8) Epoch 20, batch 2900, loss[loss=0.1564, simple_loss=0.2635, pruned_loss=0.02465, over 7018.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03686, over 1416443.00 frames.], batch size: 28, lr: 3.69e-04
2022-04-29 17:59:31,727 INFO [train.py:763] (4/8) Epoch 20, batch 2950, loss[loss=0.1913, simple_loss=0.2801, pruned_loss=0.05126, over 7356.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2694, pruned_loss=0.03659, over 1414278.02 frames.], batch size: 19, lr: 3.69e-04
2022-04-29 18:01:03,483 INFO [train.py:763] (4/8) Epoch 20, batch 3000, loss[loss=0.1879, simple_loss=0.2824, pruned_loss=0.04666, over 6824.00 frames.], tot_loss[loss=0.1714, simple_loss=0.269, pruned_loss=0.03696, over 1414267.06 frames.], batch size: 31, lr: 3.69e-04
2022-04-29 18:01:03,484 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 18:01:18,758 INFO [train.py:792] (4/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
2022-04-29 18:02:33,643 INFO [train.py:763] (4/8) Epoch 20, batch 3050, loss[loss=0.1447, simple_loss=0.2253, pruned_loss=0.03205, over 7287.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2689, pruned_loss=0.03714, over 1414554.53 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:03:49,733 INFO [train.py:763] (4/8) Epoch 20, batch 3100, loss[loss=0.1911, simple_loss=0.2829, pruned_loss=0.04963, over 7381.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2699, pruned_loss=0.03762, over 1413835.66 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 18:05:13,900 INFO [train.py:763] (4/8) Epoch 20, batch 3150, loss[loss=0.2083, simple_loss=0.3128, pruned_loss=0.0519, over 7277.00 frames.], tot_loss[loss=0.1726, simple_loss=0.27, pruned_loss=0.03757, over 1418173.72 frames.], batch size: 24, lr: 3.69e-04
2022-04-29 18:06:18,920 INFO [train.py:763] (4/8) Epoch 20, batch 3200, loss[loss=0.1711, simple_loss=0.2707, pruned_loss=0.03581, over 7317.00 frames.], tot_loss[loss=0.173, simple_loss=0.2707, pruned_loss=0.03763, over 1422988.15 frames.], batch size: 21, lr: 3.69e-04
2022-04-29 18:07:24,048 INFO [train.py:763] (4/8) Epoch 20, batch 3250, loss[loss=0.1929, simple_loss=0.2847, pruned_loss=0.05061, over 7069.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.0374, over 1421749.93 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:08:29,710 INFO [train.py:763] (4/8) Epoch 20, batch 3300, loss[loss=0.1563, simple_loss=0.2419, pruned_loss=0.03536, over 7137.00 frames.], tot_loss[loss=0.1708, simple_loss=0.269, pruned_loss=0.03626, over 1423218.80 frames.], batch size: 17, lr: 3.69e-04
2022-04-29 18:09:35,969 INFO [train.py:763] (4/8) Epoch 20, batch 3350, loss[loss=0.1835, simple_loss=0.2745, pruned_loss=0.04624, over 7227.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2686, pruned_loss=0.03628, over 1419336.38 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:10:42,809 INFO [train.py:763] (4/8) Epoch 20, batch 3400, loss[loss=0.1795, simple_loss=0.2756, pruned_loss=0.04176, over 6423.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2689, pruned_loss=0.03643, over 1415664.57 frames.], batch size: 38, lr: 3.68e-04
2022-04-29 18:11:49,525 INFO [train.py:763] (4/8) Epoch 20, batch 3450, loss[loss=0.1738, simple_loss=0.2838, pruned_loss=0.03194, over 7317.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2703, pruned_loss=0.03709, over 1413872.78 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:12:54,737 INFO [train.py:763] (4/8) Epoch 20, batch 3500, loss[loss=0.1819, simple_loss=0.2897, pruned_loss=0.03706, over 7090.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2713, pruned_loss=0.0376, over 1408882.00 frames.], batch size: 28, lr: 3.68e-04
2022-04-29 18:14:00,242 INFO [train.py:763] (4/8) Epoch 20, batch 3550, loss[loss=0.1292, simple_loss=0.2186, pruned_loss=0.01996, over 7285.00 frames.], tot_loss[loss=0.173, simple_loss=0.271, pruned_loss=0.03746, over 1413317.00 frames.], batch size: 17, lr: 3.68e-04
2022-04-29 18:15:05,499 INFO [train.py:763] (4/8) Epoch 20, batch 3600, loss[loss=0.1784, simple_loss=0.28, pruned_loss=0.03837, over 7367.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2715, pruned_loss=0.03759, over 1411037.53 frames.], batch size: 23, lr: 3.68e-04
2022-04-29 18:16:10,758 INFO [train.py:763] (4/8) Epoch 20, batch 3650, loss[loss=0.1849, simple_loss=0.2856, pruned_loss=0.04213, over 7134.00 frames.], tot_loss[loss=0.1725, simple_loss=0.271, pruned_loss=0.03697, over 1413239.84 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:17:15,966 INFO [train.py:763] (4/8) Epoch 20, batch 3700, loss[loss=0.176, simple_loss=0.2721, pruned_loss=0.03992, over 7318.00 frames.], tot_loss[loss=0.1716, simple_loss=0.27, pruned_loss=0.03663, over 1413803.00 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:18:22,129 INFO [train.py:763] (4/8) Epoch 20, batch 3750, loss[loss=0.1913, simple_loss=0.2886, pruned_loss=0.04702, over 7315.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2694, pruned_loss=0.03643, over 1416602.98 frames.], batch size: 25, lr: 3.68e-04
2022-04-29 18:19:27,281 INFO [train.py:763] (4/8) Epoch 20, batch 3800, loss[loss=0.1846, simple_loss=0.2937, pruned_loss=0.03773, over 7187.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2694, pruned_loss=0.03657, over 1418241.18 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:20:33,278 INFO [train.py:763] (4/8) Epoch 20, batch 3850, loss[loss=0.155, simple_loss=0.259, pruned_loss=0.02553, over 7328.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2698, pruned_loss=0.03658, over 1418737.84 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:21:38,665 INFO [train.py:763] (4/8) Epoch 20, batch 3900, loss[loss=0.1748, simple_loss=0.2733, pruned_loss=0.03815, over 7257.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2699, pruned_loss=0.03662, over 1422620.96 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:22:44,409 INFO [train.py:763] (4/8) Epoch 20, batch 3950, loss[loss=0.1654, simple_loss=0.2592, pruned_loss=0.03577, over 7400.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2703, pruned_loss=0.0369, over 1417218.24 frames.], batch size: 18, lr: 3.67e-04
2022-04-29 18:23:51,277 INFO [train.py:763] (4/8) Epoch 20, batch 4000, loss[loss=0.1532, simple_loss=0.2457, pruned_loss=0.03035, over 7359.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2698, pruned_loss=0.03642, over 1421005.74 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:24:58,614 INFO [train.py:763] (4/8) Epoch 20, batch 4050, loss[loss=0.2156, simple_loss=0.3029, pruned_loss=0.06417, over 5006.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2688, pruned_loss=0.03622, over 1418395.92 frames.], batch size: 52, lr: 3.67e-04
2022-04-29 18:26:05,421 INFO [train.py:763] (4/8) Epoch 20, batch 4100, loss[loss=0.1706, simple_loss=0.2786, pruned_loss=0.03133, over 7213.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2693, pruned_loss=0.03652, over 1410047.17 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:27:10,990 INFO [train.py:763] (4/8) Epoch 20, batch 4150, loss[loss=0.1595, simple_loss=0.2572, pruned_loss=0.03087, over 7074.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2701, pruned_loss=0.03641, over 1411393.07 frames.], batch size: 18, lr: 3.67e-04
2022-04-29 18:28:16,323 INFO [train.py:763] (4/8) Epoch 20, batch 4200, loss[loss=0.1724, simple_loss=0.2692, pruned_loss=0.03783, over 6789.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2701, pruned_loss=0.03666, over 1410720.10 frames.], batch size: 31, lr: 3.67e-04
2022-04-29 18:29:32,305 INFO [train.py:763] (4/8) Epoch 20, batch 4250, loss[loss=0.175, simple_loss=0.2863, pruned_loss=0.03183, over 7223.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2689, pruned_loss=0.03617, over 1415448.50 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:30:38,988 INFO [train.py:763] (4/8) Epoch 20, batch 4300, loss[loss=0.1701, simple_loss=0.2756, pruned_loss=0.03232, over 7268.00 frames.], tot_loss[loss=0.1698, simple_loss=0.268, pruned_loss=0.03579, over 1416107.47 frames.], batch size: 24, lr: 3.67e-04
2022-04-29 18:31:45,007 INFO [train.py:763] (4/8) Epoch 20, batch 4350, loss[loss=0.1812, simple_loss=0.2775, pruned_loss=0.04249, over 7224.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2688, pruned_loss=0.03607, over 1415606.22 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:32:52,212 INFO [train.py:763] (4/8) Epoch 20, batch 4400, loss[loss=0.1617, simple_loss=0.2521, pruned_loss=0.03569, over 7163.00 frames.], tot_loss[loss=0.17, simple_loss=0.2686, pruned_loss=0.03567, over 1415569.63 frames.], batch size: 18, lr: 3.66e-04
2022-04-29 18:33:58,452 INFO [train.py:763] (4/8) Epoch 20, batch 4450, loss[loss=0.1456, simple_loss=0.2324, pruned_loss=0.02936, over 6991.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03561, over 1407293.23 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:35:05,722 INFO [train.py:763] (4/8) Epoch 20, batch 4500, loss[loss=0.1441, simple_loss=0.2293, pruned_loss=0.02945, over 6995.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2693, pruned_loss=0.036, over 1409692.50 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:36:13,269 INFO [train.py:763] (4/8) Epoch 20, batch 4550, loss[loss=0.213, simple_loss=0.2969, pruned_loss=0.06457, over 4744.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2684, pruned_loss=0.03613, over 1394404.66 frames.], batch size: 53, lr: 3.66e-04
2022-04-29 18:37:42,386 INFO [train.py:763] (4/8) Epoch 21, batch 0, loss[loss=0.189, simple_loss=0.2908, pruned_loss=0.04355, over 7311.00 frames.], tot_loss[loss=0.189, simple_loss=0.2908, pruned_loss=0.04355, over 7311.00 frames.], batch size: 25, lr: 3.58e-04
2022-04-29 18:38:48,206 INFO [train.py:763] (4/8) Epoch 21, batch 50, loss[loss=0.1504, simple_loss=0.2499, pruned_loss=0.02546, over 7168.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2707, pruned_loss=0.03759, over 317814.56 frames.], batch size: 18, lr: 3.58e-04
2022-04-29 18:39:53,570 INFO [train.py:763] (4/8) Epoch 21, batch 100, loss[loss=0.158, simple_loss=0.2616, pruned_loss=0.02714, over 7110.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.03585, over 564305.61 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:41:00,340 INFO [train.py:763] (4/8) Epoch 21, batch 150, loss[loss=0.1748, simple_loss=0.2806, pruned_loss=0.03448, over 7322.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2689, pruned_loss=0.03573, over 753738.33 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:42:07,755 INFO [train.py:763] (4/8) Epoch 21, batch 200, loss[loss=0.1675, simple_loss=0.2674, pruned_loss=0.03385, over 7347.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2688, pruned_loss=0.03577, over 902215.42 frames.], batch size: 22, lr: 3.58e-04
2022-04-29 18:43:14,296 INFO [train.py:763] (4/8) Epoch 21, batch 250, loss[loss=0.1766, simple_loss=0.2774, pruned_loss=0.03792, over 7257.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2701, pruned_loss=0.03683, over 1016114.72 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:44:19,570 INFO [train.py:763] (4/8) Epoch 21, batch 300, loss[loss=0.1818, simple_loss=0.2835, pruned_loss=0.04008, over 7228.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2703, pruned_loss=0.03673, over 1108987.97 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:45:25,081 INFO [train.py:763] (4/8) Epoch 21, batch 350, loss[loss=0.1629, simple_loss=0.2664, pruned_loss=0.02973, over 7153.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2697, pruned_loss=0.03657, over 1178668.22 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:46:30,616 INFO [train.py:763] (4/8) Epoch 21, batch 400, loss[loss=0.1708, simple_loss=0.2756, pruned_loss=0.03303, over 7217.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2694, pruned_loss=0.03607, over 1230638.34 frames.], batch size: 21, lr: 3.57e-04
2022-04-29 18:47:36,039 INFO [train.py:763] (4/8) Epoch 21, batch 450, loss[loss=0.2029, simple_loss=0.3033, pruned_loss=0.05127, over 5170.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03556, over 1274231.42 frames.], batch size: 52, lr: 3.57e-04
2022-04-29 18:48:41,847 INFO [train.py:763] (4/8) Epoch 21, batch 500, loss[loss=0.1727, simple_loss=0.2808, pruned_loss=0.03226, over 7304.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2697, pruned_loss=0.03558, over 1309520.37 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:49:47,434 INFO [train.py:763] (4/8) Epoch 21, batch 550, loss[loss=0.1647, simple_loss=0.2587, pruned_loss=0.03537, over 7433.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2703, pruned_loss=0.03607, over 1332473.57 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:50:53,639 INFO [train.py:763] (4/8) Epoch 21, batch 600, loss[loss=0.1553, simple_loss=0.2634, pruned_loss=0.02362, over 7339.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2687, pruned_loss=0.03578, over 1353906.04 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:51:58,877 INFO [train.py:763] (4/8) Epoch 21, batch 650, loss[loss=0.187, simple_loss=0.2869, pruned_loss=0.04354, over 7326.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2703, pruned_loss=0.03627, over 1369351.82 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:53:04,510 INFO [train.py:763] (4/8) Epoch 21, batch 700, loss[loss=0.2023, simple_loss=0.3035, pruned_loss=0.0505, over 7308.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2699, pruned_loss=0.03627, over 1378375.59 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:54:10,368 INFO [train.py:763] (4/8) Epoch 21, batch 750, loss[loss=0.1702, simple_loss=0.2624, pruned_loss=0.03896, over 7156.00 frames.], tot_loss[loss=0.171, simple_loss=0.2693, pruned_loss=0.03628, over 1387122.80 frames.], batch size: 18, lr: 3.57e-04
2022-04-29 18:55:16,595 INFO [train.py:763] (4/8) Epoch 21, batch 800, loss[loss=0.1796, simple_loss=0.2751, pruned_loss=0.04201, over 7287.00 frames.], tot_loss[loss=0.171, simple_loss=0.2696, pruned_loss=0.03621, over 1399717.84 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 18:56:22,302 INFO [train.py:763] (4/8) Epoch 21, batch 850, loss[loss=0.1819, simple_loss=0.2688, pruned_loss=0.04755, over 7409.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2698, pruned_loss=0.03647, over 1405085.93 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:57:27,449 INFO [train.py:763] (4/8) Epoch 21, batch 900, loss[loss=0.1463, simple_loss=0.2485, pruned_loss=0.02206, over 6459.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2692, pruned_loss=0.03607, over 1410015.42 frames.], batch size: 38, lr: 3.56e-04
2022-04-29 18:58:32,833 INFO [train.py:763] (4/8) Epoch 21, batch 950, loss[loss=0.1599, simple_loss=0.2576, pruned_loss=0.03111, over 7297.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2687, pruned_loss=0.03589, over 1411967.98 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:59:38,148 INFO [train.py:763] (4/8) Epoch 21, batch 1000, loss[loss=0.174, simple_loss=0.2699, pruned_loss=0.03909, over 7167.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03687, over 1411855.32 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:00:44,769 INFO [train.py:763] (4/8) Epoch 21, batch 1050, loss[loss=0.1635, simple_loss=0.2619, pruned_loss=0.03251, over 7325.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2694, pruned_loss=0.03647, over 1415453.18 frames.], batch size: 22, lr: 3.56e-04
2022-04-29 19:01:50,752 INFO [train.py:763] (4/8) Epoch 21, batch 1100, loss[loss=0.1777, simple_loss=0.2789, pruned_loss=0.0383, over 6157.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2693, pruned_loss=0.03618, over 1418407.38 frames.], batch size: 37, lr: 3.56e-04
2022-04-29 19:02:56,400 INFO [train.py:763] (4/8) Epoch 21, batch 1150, loss[loss=0.18, simple_loss=0.2775, pruned_loss=0.04124, over 7270.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2682, pruned_loss=0.03575, over 1421052.27 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:04:02,096 INFO [train.py:763] (4/8) Epoch 21, batch 1200, loss[loss=0.1782, simple_loss=0.2884, pruned_loss=0.03401, over 7295.00 frames.], tot_loss[loss=0.1696, simple_loss=0.268, pruned_loss=0.03558, over 1422125.45 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 19:05:07,718 INFO [train.py:763] (4/8) Epoch 21, batch 1250, loss[loss=0.1537, simple_loss=0.2309, pruned_loss=0.03826, over 7004.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2685, pruned_loss=0.03601, over 1421707.76 frames.], batch size: 16, lr: 3.56e-04
2022-04-29 19:06:13,268 INFO [train.py:763] (4/8) Epoch 21, batch 1300, loss[loss=0.1642, simple_loss=0.2689, pruned_loss=0.02979, over 7158.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2678, pruned_loss=0.03559, over 1419914.44 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:07:19,446 INFO [train.py:763] (4/8) Epoch 21, batch 1350, loss[loss=0.2034, simple_loss=0.3097, pruned_loss=0.04858, over 7418.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03551, over 1424256.14 frames.], batch size: 21, lr: 3.55e-04
2022-04-29 19:08:24,892 INFO [train.py:763] (4/8) Epoch 21, batch 1400, loss[loss=0.1872, simple_loss=0.2842, pruned_loss=0.04508, over 7210.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2665, pruned_loss=0.0353, over 1420085.06 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:09:30,407 INFO [train.py:763] (4/8) Epoch 21, batch 1450, loss[loss=0.1707, simple_loss=0.2655, pruned_loss=0.03793, over 7433.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03539, over 1424357.35 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:10:36,215 INFO [train.py:763] (4/8) Epoch 21, batch 1500, loss[loss=0.156, simple_loss=0.263, pruned_loss=0.02448, over 7244.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2671, pruned_loss=0.03556, over 1426551.63 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:11:42,020 INFO [train.py:763] (4/8) Epoch 21, batch 1550, loss[loss=0.1759, simple_loss=0.278, pruned_loss=0.03683, over 7229.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.0353, over 1428633.89 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:12:47,946 INFO [train.py:763] (4/8) Epoch 21, batch 1600, loss[loss=0.1347, simple_loss=0.2235, pruned_loss=0.02296, over 7212.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2667, pruned_loss=0.03503, over 1430096.43 frames.], batch size: 16, lr: 3.55e-04
2022-04-29 19:13:54,882 INFO [train.py:763] (4/8) Epoch 21, batch 1650, loss[loss=0.208, simple_loss=0.3001, pruned_loss=0.05791, over 6684.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2669, pruned_loss=0.03523, over 1431527.19 frames.], batch size: 31, lr: 3.55e-04
2022-04-29 19:15:01,796 INFO [train.py:763] (4/8) Epoch 21, batch 1700, loss[loss=0.1967, simple_loss=0.3013, pruned_loss=0.04609, over 7339.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2665, pruned_loss=0.03516, over 1433578.08 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:16:08,175 INFO [train.py:763] (4/8) Epoch 21, batch 1750, loss[loss=0.1821, simple_loss=0.2829, pruned_loss=0.04066, over 7229.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.03537, over 1433343.07 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:17:14,196 INFO [train.py:763] (4/8) Epoch 21, batch 1800, loss[loss=0.1575, simple_loss=0.2476, pruned_loss=0.0337, over 7283.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2662, pruned_loss=0.03544, over 1430848.34 frames.], batch size: 17, lr: 3.55e-04
2022-04-29 19:18:19,472 INFO [train.py:763] (4/8) Epoch 21, batch 1850, loss[loss=0.1794, simple_loss=0.2832, pruned_loss=0.03778, over 6332.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2662, pruned_loss=0.03536, over 1427076.72 frames.], batch size: 37, lr: 3.55e-04
2022-04-29 19:19:25,203 INFO [train.py:763] (4/8) Epoch 21, batch 1900, loss[loss=0.2231, simple_loss=0.2999, pruned_loss=0.07312, over 4825.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2665, pruned_loss=0.03555, over 1425466.42 frames.], batch size: 53, lr: 3.54e-04
2022-04-29 19:20:31,905 INFO [train.py:763] (4/8) Epoch 21, batch 1950, loss[loss=0.1663, simple_loss=0.2479, pruned_loss=0.04234, over 7281.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2668, pruned_loss=0.03597, over 1426580.05 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:21:37,658 INFO [train.py:763] (4/8) Epoch 21, batch 2000, loss[loss=0.1678, simple_loss=0.2729, pruned_loss=0.03132, over 7324.00 frames.], tot_loss[loss=0.169, simple_loss=0.267, pruned_loss=0.03547, over 1428793.07 frames.], batch size: 20, lr: 3.54e-04
2022-04-29 19:22:44,041 INFO [train.py:763] (4/8) Epoch 21, batch 2050, loss[loss=0.135, simple_loss=0.2228, pruned_loss=0.02364, over 7289.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2675, pruned_loss=0.03562, over 1429181.31 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:23:50,502 INFO [train.py:763] (4/8) Epoch 21, batch 2100, loss[loss=0.1513, simple_loss=0.2374, pruned_loss=0.03258, over 7409.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2687, pruned_loss=0.03619, over 1428193.80 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:24:56,267 INFO [train.py:763] (4/8) Epoch 21, batch 2150, loss[loss=0.1573, simple_loss=0.2451, pruned_loss=0.03473, over 7171.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2686, pruned_loss=0.03613, over 1423509.44 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:26:02,247 INFO [train.py:763] (4/8) Epoch 21, batch 2200, loss[loss=0.1653, simple_loss=0.272, pruned_loss=0.02926, over 7118.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03575, over 1426275.49 frames.], batch size: 21, lr: 3.54e-04
2022-04-29 19:27:08,590 INFO [train.py:763] (4/8) Epoch 21, batch 2250, loss[loss=0.1407, simple_loss=0.2367, pruned_loss=0.02233, over 6844.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2684, pruned_loss=0.03556, over 1423730.81 frames.], batch size: 15, lr: 3.54e-04
2022-04-29 19:28:14,981 INFO [train.py:763] (4/8) Epoch 21, batch 2300, loss[loss=0.2159, simple_loss=0.2947, pruned_loss=0.06853, over 5068.00 frames.], tot_loss[loss=0.17, simple_loss=0.2686, pruned_loss=0.03567, over 1424937.10 frames.], batch size: 52, lr: 3.54e-04
2022-04-29 19:29:21,490 INFO [train.py:763] (4/8) Epoch 21, batch 2350, loss[loss=0.1823, simple_loss=0.2757, pruned_loss=0.04451, over 6409.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03559, over 1426792.77 frames.], batch size: 37, lr: 3.54e-04
2022-04-29 19:30:28,259 INFO [train.py:763] (4/8) Epoch 21, batch 2400, loss[loss=0.1453, simple_loss=0.2373, pruned_loss=0.02671, over 7134.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2676, pruned_loss=0.03554, over 1427324.21 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:31:33,884 INFO [train.py:763] (4/8) Epoch 21, batch 2450, loss[loss=0.1523, simple_loss=0.2452, pruned_loss=0.02967, over 7280.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2681, pruned_loss=0.03583, over 1425693.28 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:32:39,516 INFO [train.py:763] (4/8) Epoch 21, batch 2500, loss[loss=0.1774, simple_loss=0.2742, pruned_loss=0.04032, over 7412.00 frames.], tot_loss[loss=0.17, simple_loss=0.2684, pruned_loss=0.03583, over 1423560.52 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:33:46,124 INFO [train.py:763] (4/8) Epoch 21, batch 2550, loss[loss=0.1765, simple_loss=0.2717, pruned_loss=0.04065, over 7445.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2689, pruned_loss=0.03601, over 1423460.05 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:34:52,129 INFO [train.py:763] (4/8) Epoch 21, batch 2600, loss[loss=0.1571, simple_loss=0.252, pruned_loss=0.03105, over 7161.00 frames.], tot_loss[loss=0.171, simple_loss=0.2696, pruned_loss=0.0362, over 1419629.65 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:35:58,114 INFO [train.py:763] (4/8) Epoch 21, batch 2650, loss[loss=0.1433, simple_loss=0.2412, pruned_loss=0.0227, over 7258.00 frames.], tot_loss[loss=0.1695, simple_loss=0.268, pruned_loss=0.03545, over 1423004.45 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:37:03,415 INFO [train.py:763] (4/8) Epoch 21, batch 2700, loss[loss=0.1571, simple_loss=0.2448, pruned_loss=0.03468, over 7179.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2673, pruned_loss=0.03512, over 1421658.44 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:38:08,436 INFO [train.py:763] (4/8) Epoch 21, batch 2750, loss[loss=0.156, simple_loss=0.2513, pruned_loss=0.0304, over 7060.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03537, over 1421577.13 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:39:13,884 INFO [train.py:763] (4/8) Epoch 21, batch 2800, loss[loss=0.1467, simple_loss=0.24, pruned_loss=0.02666, over 7284.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03531, over 1421734.94 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:40:19,365 INFO [train.py:763] (4/8) Epoch 21, batch 2850, loss[loss=0.1747, simple_loss=0.2822, pruned_loss=0.03354, over 7167.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2682, pruned_loss=0.0356, over 1419707.96 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:41:24,552 INFO [train.py:763] (4/8) Epoch 21, batch 2900, loss[loss=0.1286, simple_loss=0.2298, pruned_loss=0.01367, over 7154.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2673, pruned_loss=0.03521, over 1421779.18 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:42:30,256 INFO [train.py:763] (4/8) Epoch 21, batch 2950, loss[loss=0.1681, simple_loss=0.2643, pruned_loss=0.03593, over 7418.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2682, pruned_loss=0.03556, over 1421695.86 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:43:36,681 INFO [train.py:763] (4/8) Epoch 21, batch 3000, loss[loss=0.1629, simple_loss=0.2517, pruned_loss=0.037, over 7155.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2681, pruned_loss=0.03542, over 1426074.68 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:43:36,682 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 19:43:52,055 INFO [train.py:792] (4/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
2022-04-29 19:44:57,936 INFO [train.py:763] (4/8) Epoch 21, batch 3050, loss[loss=0.1774, simple_loss=0.2812, pruned_loss=0.03683, over 7107.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2676, pruned_loss=0.03544, over 1427780.48 frames.], batch size: 28, lr: 3.52e-04
2022-04-29 19:46:03,952 INFO [train.py:763] (4/8) Epoch 21, batch 3100, loss[loss=0.2082, simple_loss=0.2895, pruned_loss=0.06346, over 5148.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2668, pruned_loss=0.03554, over 1428166.12 frames.], batch size: 52, lr: 3.52e-04
2022-04-29 19:47:10,166 INFO [train.py:763] (4/8) Epoch 21, batch 3150, loss[loss=0.1873, simple_loss=0.2946, pruned_loss=0.03996, over 7413.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2663, pruned_loss=0.03497, over 1426182.99 frames.], batch size: 21, lr: 3.52e-04
2022-04-29 19:48:15,882 INFO [train.py:763] (4/8) Epoch 21, batch 3200, loss[loss=0.1608, simple_loss=0.2557, pruned_loss=0.03293, over 7074.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2659, pruned_loss=0.03462, over 1426876.44 frames.], batch size: 18, lr: 3.52e-04
2022-04-29 19:49:21,825 INFO [train.py:763] (4/8) Epoch 21, batch 3250, loss[loss=0.1461, simple_loss=0.2339, pruned_loss=0.02917, over 7416.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2668, pruned_loss=0.03483, over 1428401.71 frames.], batch size: 17, lr: 3.52e-04
2022-04-29 19:50:27,762 INFO [train.py:763] (4/8) Epoch 21, batch 3300, loss[loss=0.1724, simple_loss=0.2657, pruned_loss=0.03954, over 7427.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2684, pruned_loss=0.03523, over 1430210.43 frames.], batch size: 20, lr: 3.52e-04
2022-04-29 19:51:34,064 INFO [train.py:763] (4/8) Epoch 21, batch 3350, loss[loss=0.1728, simple_loss=0.2754, pruned_loss=0.03511, over 7360.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2693, pruned_loss=0.03561, over 1428790.11 frames.], batch size: 19, lr: 3.52e-04
2022-04-29 19:52:40,197 INFO [train.py:763] (4/8) Epoch 21, batch 3400, loss[loss=0.1535, simple_loss=0.2428, pruned_loss=0.0321, over 7131.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2695, pruned_loss=0.03594, over 1425179.36 frames.], batch size: 17, lr: 3.52e-04
2022-04-29 19:53:45,691 INFO [train.py:763] (4/8) Epoch 21, batch 3450, loss[loss=0.1538, simple_loss=0.2639, pruned_loss=0.02183, over 7349.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2692, pruned_loss=0.03577, over 1426850.11 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:54:51,958 INFO [train.py:763] (4/8) Epoch 21, batch 3500, loss[loss=0.1625, simple_loss=0.2728, pruned_loss=0.02616, over 7341.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03583, over 1429482.95 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:55:58,075 INFO [train.py:763] (4/8) Epoch 21, batch 3550, loss[loss=0.1861, simple_loss=0.2828, pruned_loss=0.0447, over 6755.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2694, pruned_loss=0.03618, over 1427464.33 frames.], batch size: 31, lr: 3.52e-04
2022-04-29 19:57:04,812 INFO [train.py:763] (4/8) Epoch 21, batch 3600, loss[loss=0.1501, simple_loss=0.2453, pruned_loss=0.02744, over 7302.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2689, pruned_loss=0.03643, over 1422321.02 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 19:58:10,361 INFO [train.py:763] (4/8) Epoch 21, batch 3650, loss[loss=0.188, simple_loss=0.2962, pruned_loss=0.03994, over 7374.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.03586, over 1423708.32 frames.], batch size: 23, lr: 3.51e-04
2022-04-29 19:59:15,681 INFO [train.py:763] (4/8) Epoch 21, batch 3700, loss[loss=0.1783, simple_loss=0.2799, pruned_loss=0.03836, over 7221.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03561, over 1426808.61 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:00:21,229 INFO [train.py:763] (4/8) Epoch 21, batch 3750, loss[loss=0.173, simple_loss=0.2548, pruned_loss=0.04557, over 6992.00 frames.], tot_loss[loss=0.17, simple_loss=0.2682, pruned_loss=0.03587, over 1430774.38 frames.], batch size: 16, lr: 3.51e-04
2022-04-29 20:01:26,919 INFO [train.py:763] (4/8) Epoch 21, batch 3800, loss[loss=0.219, simple_loss=0.3068, pruned_loss=0.06563, over 5236.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2678, pruned_loss=0.03552, over 1425282.37 frames.], batch size: 52, lr: 3.51e-04
2022-04-29 20:02:32,209 INFO [train.py:763] (4/8) Epoch 21, batch 3850, loss[loss=0.181, simple_loss=0.2765, pruned_loss=0.0427, over 7232.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2682, pruned_loss=0.03557, over 1427751.31 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:03:37,827 INFO [train.py:763] (4/8) Epoch 21, batch 3900, loss[loss=0.1655, simple_loss=0.2639, pruned_loss=0.03356, over 6413.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2671, pruned_loss=0.03507, over 1427600.40 frames.], batch size: 37, lr: 3.51e-04
2022-04-29 20:04:43,329 INFO [train.py:763] (4/8) Epoch 21, batch 3950, loss[loss=0.1517, simple_loss=0.2451, pruned_loss=0.02917, over 7274.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2674, pruned_loss=0.03507, over 1425861.41 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 20:05:50,730 INFO [train.py:763] (4/8) Epoch 21, batch 4000, loss[loss=0.1782, simple_loss=0.2876, pruned_loss=0.0344, over 7325.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2685, pruned_loss=0.03552, over 1425965.88 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:06:57,083 INFO [train.py:763] (4/8) Epoch 21, batch 4050, loss[loss=0.1526, simple_loss=0.2465, pruned_loss=0.02934, over 7365.00 frames.], tot_loss[loss=0.1698, simple_loss=0.268, pruned_loss=0.03579, over 1423900.38 frames.], batch size: 19, lr: 3.51e-04
2022-04-29 20:08:02,545 INFO [train.py:763] (4/8) Epoch 21, batch 4100, loss[loss=0.1713, simple_loss=0.2747, pruned_loss=0.03396, over 7316.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2684, pruned_loss=0.03566, over 1424945.95 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:09:08,412 INFO [train.py:763] (4/8) Epoch 21, batch 4150, loss[loss=0.1677, simple_loss=0.2647, pruned_loss=0.03529, over 7076.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2684, pruned_loss=0.03588, over 1420132.87 frames.], batch size: 18, lr: 3.51e-04
2022-04-29 20:10:23,427 INFO [train.py:763] (4/8) Epoch 21, batch 4200, loss[loss=0.1791, simple_loss=0.2897, pruned_loss=0.03428, over 7146.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2688, pruned_loss=0.0359, over 1416222.44 frames.], batch size: 20, lr: 3.50e-04
2022-04-29 20:11:28,555 INFO [train.py:763] (4/8) Epoch 21, batch 4250, loss[loss=0.1868, simple_loss=0.285, pruned_loss=0.0443, over 6704.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2695, pruned_loss=0.03659, over 1409837.41 frames.], batch size: 31, lr: 3.50e-04
2022-04-29 20:12:34,517 INFO [train.py:763] (4/8) Epoch 21, batch 4300, loss[loss=0.1685, simple_loss=0.2699, pruned_loss=0.03358, over 7290.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2691, pruned_loss=0.03615, over 1411645.41 frames.], batch size: 24, lr: 3.50e-04
2022-04-29 20:13:40,097 INFO [train.py:763] (4/8) Epoch 21, batch 4350, loss[loss=0.1746, simple_loss=0.2825, pruned_loss=0.03338, over 7334.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2689, pruned_loss=0.03587, over 1409175.87 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:14:45,316 INFO [train.py:763] (4/8) Epoch 21, batch 4400, loss[loss=0.1662, simple_loss=0.2691, pruned_loss=0.03163, over 7120.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2694, pruned_loss=0.03612, over 1403948.80 frames.], batch size: 21, lr: 3.50e-04
2022-04-29 20:15:50,786 INFO [train.py:763] (4/8) Epoch 21, batch 4450, loss[loss=0.1715, simple_loss=0.2691, pruned_loss=0.03692, over 7341.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2705, pruned_loss=0.03631, over 1399789.73 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:17:22,857 INFO [train.py:763] (4/8) Epoch 21, batch 4500, loss[loss=0.1742, simple_loss=0.2813, pruned_loss=0.03358, over 7024.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2727, pruned_loss=0.03733, over 1388642.31 frames.], batch size: 28, lr: 3.50e-04
2022-04-29 20:18:27,308 INFO [train.py:763] (4/8) Epoch 21, batch 4550, loss[loss=0.1817, simple_loss=0.2781, pruned_loss=0.04264, over 5309.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2741, pruned_loss=0.03809, over 1347640.55 frames.], batch size: 52, lr: 3.50e-04
2022-04-29 20:20:15,476 INFO [train.py:763] (4/8) Epoch 22, batch 0, loss[loss=0.1492, simple_loss=0.2404, pruned_loss=0.02898, over 6794.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2404, pruned_loss=0.02898, over 6794.00 frames.], batch size: 15, lr: 3.42e-04
2022-04-29 20:21:30,523 INFO [train.py:763] (4/8) Epoch 22, batch 50, loss[loss=0.165, simple_loss=0.264, pruned_loss=0.03301, over 7163.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2694, pruned_loss=0.03708, over 319812.35 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:22:35,940 INFO [train.py:763] (4/8) Epoch 22, batch 100, loss[loss=0.1597, simple_loss=0.2523, pruned_loss=0.03352, over 7281.00 frames.], tot_loss[loss=0.17, simple_loss=0.2698, pruned_loss=0.03506, over 566250.07 frames.], batch size: 18, lr: 3.42e-04
2022-04-29 20:23:41,419 INFO [train.py:763] (4/8) Epoch 22, batch 150, loss[loss=0.1809, simple_loss=0.2788, pruned_loss=0.0415, over 7297.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2711, pruned_loss=0.03551, over 753072.04 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:24:46,880 INFO [train.py:763] (4/8) Epoch 22, batch 200, loss[loss=0.1719, simple_loss=0.2699, pruned_loss=0.03701, over 6502.00 frames.], tot_loss[loss=0.1696, simple_loss=0.269, pruned_loss=0.03504, over 901996.47 frames.], batch size: 38, lr: 3.42e-04
2022-04-29 20:25:52,441 INFO [train.py:763] (4/8) Epoch 22, batch 250, loss[loss=0.1647, simple_loss=0.2651, pruned_loss=0.03211, over 7229.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2688, pruned_loss=0.03484, over 1017260.81 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:26:58,032 INFO [train.py:763] (4/8) Epoch 22, batch 300, loss[loss=0.1653, simple_loss=0.2685, pruned_loss=0.0311, over 7163.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2684, pruned_loss=0.03514, over 1103601.34 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:28:05,352 INFO [train.py:763] (4/8) Epoch 22, batch 350, loss[loss=0.1848, simple_loss=0.2724, pruned_loss=0.04862, over 7335.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03508, over 1178110.56 frames.], batch size: 22, lr: 3.42e-04
2022-04-29 20:29:12,804 INFO [train.py:763] (4/8) Epoch 22, batch 400, loss[loss=0.1748, simple_loss=0.2797, pruned_loss=0.03492, over 7206.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03503, over 1231907.60 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:30:18,162 INFO [train.py:763] (4/8) Epoch 22, batch 450, loss[loss=0.1875, simple_loss=0.2864, pruned_loss=0.04429, over 7279.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2683, pruned_loss=0.0351, over 1272623.67 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:31:24,301 INFO [train.py:763] (4/8) Epoch 22, batch 500, loss[loss=0.1332, simple_loss=0.2373, pruned_loss=0.01454, over 7218.00 frames.], tot_loss[loss=0.1696, simple_loss=0.269, pruned_loss=0.03516, over 1308687.67 frames.], batch size: 16, lr: 3.41e-04
2022-04-29 20:32:31,784 INFO [train.py:763] (4/8) Epoch 22, batch 550, loss[loss=0.1606, simple_loss=0.2584, pruned_loss=0.03136, over 7319.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2676, pruned_loss=0.03512, over 1337609.10 frames.], batch size: 24, lr: 3.41e-04
2022-04-29 20:33:39,037 INFO [train.py:763] (4/8) Epoch 22, batch 600, loss[loss=0.1879, simple_loss=0.2778, pruned_loss=0.04895, over 7113.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2679, pruned_loss=0.0352, over 1359697.48 frames.], batch size: 21, lr: 3.41e-04
2022-04-29 20:34:44,741 INFO [train.py:763] (4/8) Epoch 22, batch 650, loss[loss=0.1672, simple_loss=0.2671, pruned_loss=0.03372, over 6847.00 frames.], tot_loss[loss=0.1695, simple_loss=0.268, pruned_loss=0.03548, over 1374725.13 frames.], batch size: 31, lr: 3.41e-04
2022-04-29 20:35:51,882 INFO [train.py:763] (4/8) Epoch 22, batch 700, loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03213, over 5054.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2685, pruned_loss=0.03544, over 1381787.26 frames.], batch size: 52, lr: 3.41e-04
2022-04-29 20:36:59,159 INFO [train.py:763] (4/8) Epoch 22, batch 750, loss[loss=0.1854, simple_loss=0.289, pruned_loss=0.04092, over 7193.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2688, pruned_loss=0.03537, over 1393037.52 frames.], batch size: 23, lr: 3.41e-04
2022-04-29 20:38:05,931 INFO [train.py:763] (4/8) Epoch 22, batch 800, loss[loss=0.1597, simple_loss=0.2488, pruned_loss=0.03525, over 7361.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2693, pruned_loss=0.0358, over 1396325.56 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:39:11,693 INFO [train.py:763] (4/8) Epoch 22, batch 850, loss[loss=0.1499, simple_loss=0.2469, pruned_loss=0.02645, over 7431.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2686, pruned_loss=0.03551, over 1404688.27 frames.], batch size: 20, lr: 3.41e-04
2022-04-29 20:40:16,907 INFO [train.py:763] (4/8) Epoch 22, batch 900, loss[loss=0.154, simple_loss=0.2523, pruned_loss=0.02789, over 7154.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2693, pruned_loss=0.03563, over 1408935.04 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:41:22,119 INFO [train.py:763] (4/8) Epoch 22, batch 950, loss[loss=0.1833, simple_loss=0.28, pruned_loss=0.04329, over 7025.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2688, pruned_loss=0.03538, over 1411044.40 frames.], batch size: 28, lr: 3.41e-04
2022-04-29 20:42:27,343 INFO [train.py:763] (4/8) Epoch 22, batch 1000, loss[loss=0.156, simple_loss=0.2538, pruned_loss=0.0291, over 7360.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2682, pruned_loss=0.03483, over 1418039.09 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:43:32,803 INFO [train.py:763] (4/8) Epoch 22, batch 1050, loss[loss=0.2365, simple_loss=0.3107, pruned_loss=0.08117, over 5068.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2678, pruned_loss=0.03483, over 1419037.61 frames.], batch size: 52, lr: 3.41e-04
2022-04-29 20:44:37,786 INFO [train.py:763] (4/8) Epoch 22, batch 1100, loss[loss=0.1627, simple_loss=0.2519, pruned_loss=0.03679, over 7283.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2685, pruned_loss=0.03524, over 1418904.95 frames.], batch size: 17, lr: 3.40e-04
2022-04-29 20:45:43,152 INFO [train.py:763] (4/8) Epoch 22, batch 1150, loss[loss=0.151, simple_loss=0.2446, pruned_loss=0.02871, over 7429.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2679, pruned_loss=0.03496, over 1423237.67 frames.], batch size: 20, lr: 3.40e-04
2022-04-29 20:46:49,114 INFO [train.py:763] (4/8) Epoch 22, batch 1200, loss[loss=0.1653, simple_loss=0.2627, pruned_loss=0.03393, over 7292.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2679, pruned_loss=0.03515, over 1422257.10 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:47:55,635 INFO [train.py:763] (4/8) Epoch 22, batch 1250, loss[loss=0.1661, simple_loss=0.2461, pruned_loss=0.04306, over 6749.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03471, over 1425468.50 frames.], batch size: 15, lr: 3.40e-04
2022-04-29 20:49:00,847 INFO [train.py:763] (4/8) Epoch 22, batch 1300, loss[loss=0.1753, simple_loss=0.2865, pruned_loss=0.03205, over 7191.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03455, over 1428316.20 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:50:07,451 INFO [train.py:763] (4/8) Epoch 22, batch 1350, loss[loss=0.1555, simple_loss=0.2516, pruned_loss=0.02974, over 7274.00 frames.], tot_loss[loss=0.1673, simple_loss=0.266, pruned_loss=0.03431, over 1428675.50 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:51:13,803 INFO [train.py:763] (4/8) Epoch 22, batch 1400, loss[loss=0.1561, simple_loss=0.2499, pruned_loss=0.03118, over 7121.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.03436, over 1428149.74 frames.], batch size: 21, lr: 3.40e-04
2022-04-29 20:52:19,583 INFO [train.py:763] (4/8) Epoch 22, batch 1450, loss[loss=0.1524, simple_loss=0.2458, pruned_loss=0.02947, over 7403.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2655, pruned_loss=0.03411, over 1422784.75 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:53:25,449 INFO [train.py:763] (4/8) Epoch 22, batch 1500, loss[loss=0.1821, simple_loss=0.2832, pruned_loss=0.04053, over 7079.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2648, pruned_loss=0.03411, over 1423579.06 frames.], batch size: 28, lr: 3.40e-04
2022-04-29 20:54:31,377 INFO [train.py:763] (4/8) Epoch 22, batch 1550, loss[loss=0.1676, simple_loss=0.2715, pruned_loss=0.03183, over 7351.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2656, pruned_loss=0.0345, over 1414761.05 frames.], batch size: 19, lr: 3.40e-04
2022-04-29 20:55:37,829 INFO [train.py:763] (4/8) Epoch 22, batch 1600, loss[loss=0.1677, simple_loss=0.2713, pruned_loss=0.03203, over 7218.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2662, pruned_loss=0.03472, over 1413849.83 frames.], batch size: 21, lr: 3.40e-04
2022-04-29 20:56:43,433 INFO [train.py:763] (4/8) Epoch 22, batch 1650, loss[loss=0.1723, simple_loss=0.2649, pruned_loss=0.03984, over 7393.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2666, pruned_loss=0.03518, over 1417027.29 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:57:48,935 INFO [train.py:763] (4/8) Epoch 22, batch 1700, loss[loss=0.149, simple_loss=0.2471, pruned_loss=0.02549, over 7410.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03519, over 1417813.26 frames.], batch size: 18, lr: 3.39e-04
2022-04-29 20:58:54,069 INFO [train.py:763] (4/8) Epoch 22, batch 1750, loss[loss=0.2117, simple_loss=0.3063, pruned_loss=0.05853, over 7181.00 frames.], tot_loss[loss=0.1696, simple_loss=0.268, pruned_loss=0.03559, over 1416316.36 frames.], batch size: 26, lr: 3.39e-04
2022-04-29 20:59:59,907 INFO [train.py:763] (4/8) Epoch 22, batch 1800, loss[loss=0.2033, simple_loss=0.3096, pruned_loss=0.04849, over 5367.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03563, over 1412746.66 frames.], batch size: 52, lr: 3.39e-04
2022-04-29 21:01:05,539 INFO [train.py:763] (4/8) Epoch 22, batch 1850, loss[loss=0.1465, simple_loss=0.2384, pruned_loss=0.02729, over 7426.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03538, over 1417133.89 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:02:10,913 INFO [train.py:763] (4/8) Epoch 22, batch 1900, loss[loss=0.1723, simple_loss=0.2798, pruned_loss=0.03237, over 7142.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2677, pruned_loss=0.03555, over 1420326.60 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:03:17,151 INFO [train.py:763] (4/8) Epoch 22, batch 1950, loss[loss=0.1607, simple_loss=0.266, pruned_loss=0.02775, over 7141.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03554, over 1417717.58 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:04:22,496 INFO [train.py:763] (4/8) Epoch 22, batch 2000, loss[loss=0.1641, simple_loss=0.26, pruned_loss=0.03415, over 7262.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2682, pruned_loss=0.03513, over 1421444.49 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:05:28,497 INFO [train.py:763] (4/8) Epoch 22, batch 2050, loss[loss=0.1879, simple_loss=0.293, pruned_loss=0.0414, over 7239.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2685, pruned_loss=0.03517, over 1425525.65 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:06:35,597 INFO [train.py:763] (4/8) Epoch 22, batch 2100, loss[loss=0.1643, simple_loss=0.279, pruned_loss=0.02481, over 7210.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03518, over 1419736.44 frames.], batch size: 23, lr: 3.39e-04
2022-04-29 21:07:42,146 INFO [train.py:763] (4/8) Epoch 22, batch 2150, loss[loss=0.166, simple_loss=0.2626, pruned_loss=0.0347, over 7160.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2676, pruned_loss=0.03506, over 1420969.35 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:08:47,295 INFO [train.py:763] (4/8) Epoch 22, batch 2200, loss[loss=0.1901, simple_loss=0.2863, pruned_loss=0.0469, over 7158.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03517, over 1416043.87 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:09:53,559 INFO [train.py:763] (4/8) Epoch 22, batch 2250, loss[loss=0.1633, simple_loss=0.2603, pruned_loss=0.03314, over 7161.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2673, pruned_loss=0.03506, over 1412206.43 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:11:00,713 INFO [train.py:763] (4/8) Epoch 22, batch 2300, loss[loss=0.1565, simple_loss=0.2721, pruned_loss=0.02045, over 7325.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2659, pruned_loss=0.03439, over 1413895.95 frames.], batch size: 21, lr: 3.38e-04
2022-04-29 21:12:07,637 INFO [train.py:763] (4/8) Epoch 22, batch 2350, loss[loss=0.1837, simple_loss=0.2938, pruned_loss=0.03685, over 7330.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03479, over 1416602.51 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:13:14,356 INFO [train.py:763] (4/8) Epoch 22, batch 2400, loss[loss=0.182, simple_loss=0.2863, pruned_loss=0.0388, over 7290.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2682, pruned_loss=0.03518, over 1419119.12 frames.], batch size: 24, lr: 3.38e-04
2022-04-29 21:14:19,600 INFO [train.py:763] (4/8) Epoch 22, batch 2450, loss[loss=0.1815, simple_loss=0.2816, pruned_loss=0.04072, over 7187.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2697, pruned_loss=0.03598, over 1423105.56 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:15:24,877 INFO [train.py:763] (4/8) Epoch 22, batch 2500, loss[loss=0.1484, simple_loss=0.2525, pruned_loss=0.02218, over 6350.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03569, over 1421016.12 frames.], batch size: 37, lr: 3.38e-04
2022-04-29 21:16:30,043 INFO [train.py:763] (4/8) Epoch 22, batch 2550, loss[loss=0.1937, simple_loss=0.2875, pruned_loss=0.04996, over 7374.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2679, pruned_loss=0.03551, over 1421905.46 frames.], batch size: 23, lr: 3.38e-04
2022-04-29 21:17:35,649 INFO [train.py:763] (4/8) Epoch 22, batch 2600, loss[loss=0.15, simple_loss=0.2588, pruned_loss=0.0206, over 7342.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2673, pruned_loss=0.03504, over 1425964.76 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:18:41,154 INFO [train.py:763] (4/8) Epoch 22, batch 2650, loss[loss=0.1624, simple_loss=0.2679, pruned_loss=0.02839, over 7285.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2667, pruned_loss=0.03485, over 1422777.04 frames.], batch size: 25, lr: 3.38e-04
2022-04-29 21:19:46,640 INFO [train.py:763] (4/8) Epoch 22, batch 2700, loss[loss=0.1551, simple_loss=0.2556, pruned_loss=0.02727, over 7161.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2667, pruned_loss=0.03471, over 1423119.58 frames.], batch size: 19, lr: 3.38e-04
2022-04-29 21:20:54,005 INFO [train.py:763] (4/8) Epoch 22, batch 2750, loss[loss=0.1545, simple_loss=0.2532, pruned_loss=0.02788, over 7172.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2667, pruned_loss=0.03506, over 1420919.63 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:22:00,022 INFO [train.py:763] (4/8) Epoch 22, batch 2800, loss[loss=0.1544, simple_loss=0.2502, pruned_loss=0.02925, over 7171.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2671, pruned_loss=0.03555, over 1420135.01 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:23:05,436 INFO [train.py:763] (4/8) Epoch 22, batch 2850, loss[loss=0.1619, simple_loss=0.2741, pruned_loss=0.02484, over 7101.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2664, pruned_loss=0.03506, over 1421824.29 frames.], batch size: 28, lr: 3.38e-04
2022-04-29 21:24:10,662 INFO [train.py:763] (4/8) Epoch 22, batch 2900, loss[loss=0.1652, simple_loss=0.2651, pruned_loss=0.03269, over 7327.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2667, pruned_loss=0.03494, over 1423441.96 frames.], batch size: 25, lr: 3.37e-04
2022-04-29 21:25:15,970 INFO [train.py:763] (4/8) Epoch 22, batch 2950, loss[loss=0.1703, simple_loss=0.2766, pruned_loss=0.03204, over 7198.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.03515, over 1424430.46 frames.], batch size: 22, lr: 3.37e-04
2022-04-29 21:26:20,972 INFO [train.py:763] (4/8) Epoch 22, batch 3000, loss[loss=0.1284, simple_loss=0.2181, pruned_loss=0.01938, over 7002.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2672, pruned_loss=0.03503, over 1423324.35 frames.], batch size: 16, lr: 3.37e-04
2022-04-29 21:26:20,973 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 21:26:36,379 INFO [train.py:792] (4/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
2022-04-29 21:27:41,666 INFO [train.py:763] (4/8) Epoch 22, batch 3050, loss[loss=0.1601, simple_loss=0.2519, pruned_loss=0.03418, over 7151.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2676, pruned_loss=0.03534, over 1426208.56 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:28:58,460 INFO [train.py:763] (4/8) Epoch 22, batch 3100, loss[loss=0.1594, simple_loss=0.2566, pruned_loss=0.03114, over 7232.00 frames.], tot_loss[loss=0.168, simple_loss=0.2663, pruned_loss=0.03487, over 1425767.69 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:30:03,940 INFO [train.py:763] (4/8) Epoch 22, batch 3150, loss[loss=0.1545, simple_loss=0.2449, pruned_loss=0.03199, over 7324.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2656, pruned_loss=0.03468, over 1427194.70 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:31:09,274 INFO [train.py:763] (4/8) Epoch 22, batch 3200, loss[loss=0.1772, simple_loss=0.2778, pruned_loss=0.03826, over 7110.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2659, pruned_loss=0.03478, over 1428227.07 frames.], batch size: 21, lr: 3.37e-04
2022-04-29 21:32:14,547 INFO [train.py:763] (4/8) Epoch 22, batch 3250, loss[loss=0.1708, simple_loss=0.2757, pruned_loss=0.03298, over 6371.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03506, over 1422072.79 frames.], batch size: 38, lr: 3.37e-04
2022-04-29 21:33:19,826 INFO [train.py:763] (4/8) Epoch 22, batch 3300, loss[loss=0.1777, simple_loss=0.2719, pruned_loss=0.04174, over 7322.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2677, pruned_loss=0.03497, over 1422739.92 frames.], batch size: 24, lr: 3.37e-04
2022-04-29 21:34:25,355 INFO [train.py:763] (4/8) Epoch 22, batch 3350, loss[loss=0.1977, simple_loss=0.2973, pruned_loss=0.04904, over 7146.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2668, pruned_loss=0.03478, over 1427025.68 frames.], batch size: 26, lr: 3.37e-04
2022-04-29 21:35:30,549 INFO [train.py:763] (4/8) Epoch 22, batch 3400, loss[loss=0.1757, simple_loss=0.2668, pruned_loss=0.04229, over 7157.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2667, pruned_loss=0.03511, over 1427899.71 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:36:36,027 INFO [train.py:763] (4/8) Epoch 22, batch 3450, loss[loss=0.149, simple_loss=0.2346, pruned_loss=0.03175, over 7296.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2657, pruned_loss=0.03469, over 1429907.22 frames.], batch size: 16, lr: 3.37e-04
2022-04-29 21:37:41,465 INFO [train.py:763] (4/8) Epoch 22, batch 3500, loss[loss=0.1395, simple_loss=0.2294, pruned_loss=0.02479, over 6816.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2655, pruned_loss=0.03435, over 1430635.51 frames.], batch size: 15, lr: 3.37e-04
2022-04-29 21:38:46,761 INFO [train.py:763] (4/8) Epoch 22, batch 3550, loss[loss=0.1334, simple_loss=0.2252, pruned_loss=0.02085, over 7417.00 frames.], tot_loss[loss=0.167, simple_loss=0.2653, pruned_loss=0.03432, over 1430084.87 frames.], batch size: 18, lr: 3.36e-04
2022-04-29 21:39:52,002 INFO [train.py:763] (4/8) Epoch 22, batch 3600, loss[loss=0.1608, simple_loss=0.2488, pruned_loss=0.0364, over 7286.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2656, pruned_loss=0.0341, over 1431418.61 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:40:57,415 INFO [train.py:763] (4/8) Epoch 22, batch 3650, loss[loss=0.1682, simple_loss=0.271, pruned_loss=0.03271, over 6506.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2656, pruned_loss=0.03386, over 1431623.75 frames.], batch size: 37, lr: 3.36e-04
2022-04-29 21:42:03,750 INFO [train.py:763] (4/8) Epoch 22, batch 3700, loss[loss=0.1828, simple_loss=0.2793, pruned_loss=0.04309, over 7153.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03365, over 1430165.91 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:43:09,190 INFO [train.py:763] (4/8) Epoch 22, batch 3750, loss[loss=0.1534, simple_loss=0.2383, pruned_loss=0.03426, over 7277.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03379, over 1427968.25 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:44:14,438 INFO [train.py:763] (4/8) Epoch 22, batch 3800, loss[loss=0.1751, simple_loss=0.2787, pruned_loss=0.03575, over 7382.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03417, over 1429831.14 frames.], batch size: 23, lr: 3.36e-04
2022-04-29 21:45:19,889 INFO [train.py:763] (4/8) Epoch 22, batch 3850, loss[loss=0.212, simple_loss=0.3017, pruned_loss=0.06119, over 7073.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.03418, over 1430366.77 frames.], batch size: 28, lr: 3.36e-04
2022-04-29 21:46:26,371 INFO [train.py:763] (4/8) Epoch 22, batch 3900, loss[loss=0.1848, simple_loss=0.2823, pruned_loss=0.0436, over 7111.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2666, pruned_loss=0.03494, over 1430897.80 frames.], batch size: 21, lr: 3.36e-04
2022-04-29 21:47:31,491 INFO [train.py:763] (4/8) Epoch 22, batch 3950, loss[loss=0.1715, simple_loss=0.2677, pruned_loss=0.03769, over 7160.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03475, over 1430174.28 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:48:36,595 INFO [train.py:763] (4/8) Epoch 22, batch 4000, loss[loss=0.1566, simple_loss=0.2544, pruned_loss=0.02944, over 7283.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2667, pruned_loss=0.03457, over 1427166.79 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:49:42,508 INFO [train.py:763] (4/8) Epoch 22, batch 4050, loss[loss=0.1612, simple_loss=0.2445, pruned_loss=0.03899, over 6817.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2681, pruned_loss=0.03507, over 1422096.71 frames.], batch size: 15, lr: 3.36e-04
2022-04-29 21:50:49,117 INFO [train.py:763] (4/8) Epoch 22, batch 4100, loss[loss=0.1621, simple_loss=0.2436, pruned_loss=0.04031, over 6785.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03544, over 1419262.98 frames.], batch size: 15, lr: 3.36e-04
2022-04-29 21:51:54,116 INFO [train.py:763] (4/8) Epoch 22, batch 4150, loss[loss=0.164, simple_loss=0.2653, pruned_loss=0.03137, over 7327.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2682, pruned_loss=0.03498, over 1418515.35 frames.], batch size: 21, lr: 3.35e-04
2022-04-29 21:52:59,299 INFO [train.py:763] (4/8) Epoch 22, batch 4200, loss[loss=0.1572, simple_loss=0.2338, pruned_loss=0.04034, over 7009.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2689, pruned_loss=0.03506, over 1422776.29 frames.], batch size: 16, lr: 3.35e-04
2022-04-29 21:54:05,490 INFO [train.py:763] (4/8) Epoch 22, batch 4250, loss[loss=0.171, simple_loss=0.2687, pruned_loss=0.03667, over 7241.00 frames.], tot_loss[loss=0.169, simple_loss=0.2686, pruned_loss=0.03469, over 1424243.99 frames.], batch size: 20, lr: 3.35e-04
2022-04-29 21:55:12,485 INFO [train.py:763] (4/8) Epoch 22, batch 4300, loss[loss=0.165, simple_loss=0.2578, pruned_loss=0.03608, over 7165.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.03471, over 1421204.45 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:56:19,737 INFO [train.py:763] (4/8) Epoch 22, batch 4350, loss[loss=0.1308, simple_loss=0.2268, pruned_loss=0.01744, over 7225.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2664, pruned_loss=0.03487, over 1422914.81 frames.], batch size: 16, lr: 3.35e-04
2022-04-29 21:57:26,788 INFO [train.py:763] (4/8) Epoch 22, batch 4400, loss[loss=0.1663, simple_loss=0.2644, pruned_loss=0.03413, over 7067.00 frames.], tot_loss[loss=0.168, simple_loss=0.2663, pruned_loss=0.03489, over 1420980.42 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:58:31,943 INFO [train.py:763] (4/8) Epoch 22, batch 4450, loss[loss=0.2307, simple_loss=0.3149, pruned_loss=0.07328, over 4924.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2669, pruned_loss=0.03524, over 1415039.73 frames.], batch size: 52, lr: 3.35e-04
2022-04-29 21:59:36,916 INFO [train.py:763] (4/8) Epoch 22, batch 4500, loss[loss=0.1491, simple_loss=0.2433, pruned_loss=0.02749, over 7066.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03548, over 1413779.82 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 22:00:41,210 INFO [train.py:763] (4/8) Epoch 22, batch 4550, loss[loss=0.1862, simple_loss=0.266, pruned_loss=0.05321, over 5091.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2702, pruned_loss=0.03697, over 1354652.23 frames.], batch size: 52, lr: 3.35e-04
2022-04-29 22:02:00,630 INFO [train.py:763] (4/8) Epoch 23, batch 0, loss[loss=0.1675, simple_loss=0.2553, pruned_loss=0.03986, over 6778.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2553, pruned_loss=0.03986, over 6778.00 frames.], batch size: 15, lr: 3.28e-04
2022-04-29 22:03:02,940 INFO [train.py:763] (4/8) Epoch 23, batch 50, loss[loss=0.1546, simple_loss=0.2437, pruned_loss=0.03275, over 7275.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03363, over 316728.80 frames.], batch size: 17, lr: 3.28e-04
2022-04-29 22:04:05,006 INFO [train.py:763] (4/8) Epoch 23, batch 100, loss[loss=0.1894, simple_loss=0.2948, pruned_loss=0.04205, over 7328.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03368, over 567391.81 frames.], batch size: 20, lr: 3.28e-04
2022-04-29 22:05:10,553 INFO [train.py:763] (4/8) Epoch 23, batch 150, loss[loss=0.1931, simple_loss=0.2887, pruned_loss=0.04877, over 7377.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2681, pruned_loss=0.03446, over 753268.96 frames.], batch size: 23, lr: 3.28e-04
2022-04-29 22:06:15,910 INFO [train.py:763] (4/8) Epoch 23, batch 200, loss[loss=0.1757, simple_loss=0.2832, pruned_loss=0.03405, over 7212.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03401, over 904089.04 frames.], batch size: 22, lr: 3.28e-04
2022-04-29 22:07:21,261 INFO [train.py:763] (4/8) Epoch 23, batch 250, loss[loss=0.1603, simple_loss=0.2667, pruned_loss=0.02698, over 7416.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.0347, over 1016621.35 frames.], batch size: 21, lr: 3.28e-04
2022-04-29 22:08:27,017 INFO [train.py:763] (4/8) Epoch 23, batch 300, loss[loss=0.1734, simple_loss=0.274, pruned_loss=0.03638, over 7140.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2668, pruned_loss=0.03473, over 1107664.52 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:09:32,879 INFO [train.py:763] (4/8) Epoch 23, batch 350, loss[loss=0.1853, simple_loss=0.2808, pruned_loss=0.04491, over 7284.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03524, over 1179376.63 frames.], batch size: 25, lr: 3.27e-04
2022-04-29 22:10:38,044 INFO [train.py:763] (4/8) Epoch 23, batch 400, loss[loss=0.1676, simple_loss=0.2665, pruned_loss=0.03435, over 7303.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2655, pruned_loss=0.0349, over 1230676.75 frames.], batch size: 24, lr: 3.27e-04
2022-04-29 22:11:43,823 INFO [train.py:763] (4/8) Epoch 23, batch 450, loss[loss=0.1661, simple_loss=0.2691, pruned_loss=0.03152, over 7140.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2656, pruned_loss=0.03432, over 1276638.54 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:12:49,134 INFO [train.py:763] (4/8) Epoch 23, batch 500, loss[loss=0.1562, simple_loss=0.2469, pruned_loss=0.03271, over 7361.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2657, pruned_loss=0.0342, over 1308378.03 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:13:54,751 INFO [train.py:763] (4/8) Epoch 23, batch 550, loss[loss=0.1882, simple_loss=0.2993, pruned_loss=0.03851, over 7214.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2659, pruned_loss=0.0342, over 1336359.55 frames.], batch size: 22, lr: 3.27e-04
2022-04-29 22:15:00,600 INFO [train.py:763] (4/8) Epoch 23, batch 600, loss[loss=0.1663, simple_loss=0.2578, pruned_loss=0.03736, over 7361.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2647, pruned_loss=0.03403, over 1354178.23 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:16:06,053 INFO [train.py:763] (4/8) Epoch 23, batch 650, loss[loss=0.179, simple_loss=0.2766, pruned_loss=0.04074, over 7361.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2652, pruned_loss=0.03408, over 1365925.03 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:17:12,009 INFO [train.py:763] (4/8) Epoch 23, batch 700, loss[loss=0.1973, simple_loss=0.2972, pruned_loss=0.04865, over 7170.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2646, pruned_loss=0.0344, over 1382236.68 frames.], batch size: 26, lr: 3.27e-04
2022-04-29 22:18:17,839 INFO [train.py:763] (4/8) Epoch 23, batch 750, loss[loss=0.157, simple_loss=0.2438, pruned_loss=0.03509, over 6987.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2656, pruned_loss=0.03442, over 1392120.20 frames.], batch size: 16, lr: 3.27e-04
2022-04-29 22:19:23,431 INFO [train.py:763] (4/8) Epoch 23, batch 800, loss[loss=0.1748, simple_loss=0.2672, pruned_loss=0.04117, over 7258.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2653, pruned_loss=0.0344, over 1399087.20 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:20:28,942 INFO [train.py:763] (4/8) Epoch 23, batch 850, loss[loss=0.1865, simple_loss=0.2829, pruned_loss=0.04505, over 6957.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2652, pruned_loss=0.03422, over 1405053.57 frames.], batch size: 32, lr: 3.27e-04
2022-04-29 22:21:34,329 INFO [train.py:763] (4/8) Epoch 23, batch 900, loss[loss=0.1523, simple_loss=0.2598, pruned_loss=0.02242, over 7437.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2651, pruned_loss=0.0341, over 1410862.82 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:22:49,567 INFO [train.py:763] (4/8) Epoch 23, batch 950, loss[loss=0.1568, simple_loss=0.2591, pruned_loss=0.02719, over 6338.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03372, over 1415433.19 frames.], batch size: 37, lr: 3.26e-04
2022-04-29 22:23:55,237 INFO [train.py:763] (4/8) Epoch 23, batch 1000, loss[loss=0.1986, simple_loss=0.2967, pruned_loss=0.05021, over 7315.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.03417, over 1416778.01 frames.], batch size: 21, lr: 3.26e-04
2022-04-29 22:25:00,701 INFO [train.py:763] (4/8) Epoch 23, batch 1050, loss[loss=0.1445, simple_loss=0.2522, pruned_loss=0.01838, over 7230.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2663, pruned_loss=0.0342, over 1410203.27 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:26:07,025 INFO [train.py:763] (4/8) Epoch 23, batch 1100, loss[loss=0.1572, simple_loss=0.2664, pruned_loss=0.02402, over 7142.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2663, pruned_loss=0.03446, over 1409906.03 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:27:12,598 INFO [train.py:763] (4/8) Epoch 23, batch 1150, loss[loss=0.1583, simple_loss=0.2609, pruned_loss=0.02785, over 6278.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2659, pruned_loss=0.03437, over 1413403.53 frames.], batch size: 37, lr: 3.26e-04
2022-04-29 22:28:17,831 INFO [train.py:763] (4/8) Epoch 23, batch 1200, loss[loss=0.148, simple_loss=0.2443, pruned_loss=0.02586, over 7176.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2653, pruned_loss=0.03406, over 1415796.50 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:29:23,307 INFO [train.py:763] (4/8) Epoch 23, batch 1250, loss[loss=0.1504, simple_loss=0.2478, pruned_loss=0.02648, over 7329.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2648, pruned_loss=0.03402, over 1417169.87 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:30:28,891 INFO [train.py:763] (4/8) Epoch 23, batch 1300, loss[loss=0.1799, simple_loss=0.2846, pruned_loss=0.03757, over 6772.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.0337, over 1418825.06 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:31:51,693 INFO [train.py:763] (4/8) Epoch 23, batch 1350, loss[loss=0.1519, simple_loss=0.2494, pruned_loss=0.02721, over 7415.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.03343, over 1425050.81 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:32:57,242 INFO [train.py:763] (4/8) Epoch 23, batch 1400, loss[loss=0.1673, simple_loss=0.2632, pruned_loss=0.03568, over 7191.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2648, pruned_loss=0.03322, over 1423827.57 frames.], batch size: 26, lr: 3.26e-04
2022-04-29 22:34:20,486 INFO [train.py:763] (4/8) Epoch 23, batch 1450, loss[loss=0.1574, simple_loss=0.2631, pruned_loss=0.02583, over 7142.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03365, over 1422021.36 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:35:53,261 INFO [train.py:763] (4/8) Epoch 23, batch 1500, loss[loss=0.1792, simple_loss=0.278, pruned_loss=0.04018, over 7139.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.03415, over 1421040.76 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:36:59,419 INFO [train.py:763] (4/8) Epoch 23, batch 1550, loss[loss=0.1705, simple_loss=0.2765, pruned_loss=0.03221, over 6722.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2653, pruned_loss=0.03416, over 1421270.47 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:38:04,557 INFO [train.py:763] (4/8) Epoch 23, batch 1600, loss[loss=0.1921, simple_loss=0.2832, pruned_loss=0.05051, over 7336.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03429, over 1422903.37 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:39:10,551 INFO [train.py:763] (4/8) Epoch 23, batch 1650, loss[loss=0.1538, simple_loss=0.2508, pruned_loss=0.02839, over 6789.00 frames.], tot_loss[loss=0.168, simple_loss=0.267, pruned_loss=0.03444, over 1414694.45 frames.], batch size: 15, lr: 3.25e-04
2022-04-29 22:40:17,826 INFO [train.py:763] (4/8) Epoch 23, batch 1700, loss[loss=0.1872, simple_loss=0.2901, pruned_loss=0.04219, over 7331.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2679, pruned_loss=0.03456, over 1418144.89 frames.], batch size: 21, lr: 3.25e-04
2022-04-29 22:41:24,852 INFO [train.py:763] (4/8) Epoch 23, batch 1750, loss[loss=0.1418, simple_loss=0.2362, pruned_loss=0.02372, over 7056.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2678, pruned_loss=0.03451, over 1420038.70 frames.], batch size: 18, lr: 3.25e-04
2022-04-29 22:42:30,370 INFO [train.py:763] (4/8) Epoch 23, batch 1800, loss[loss=0.1861, simple_loss=0.2815, pruned_loss=0.04534, over 7331.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2676, pruned_loss=0.03471, over 1420075.99 frames.], batch size: 22, lr: 3.25e-04
2022-04-29 22:43:35,679 INFO [train.py:763] (4/8) Epoch 23, batch 1850, loss[loss=0.1687, simple_loss=0.2694, pruned_loss=0.03402, over 7278.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2673, pruned_loss=0.03445, over 1423609.06 frames.], batch size: 24, lr: 3.25e-04
2022-04-29 22:44:41,102 INFO [train.py:763] (4/8) Epoch 23, batch 1900, loss[loss=0.1709, simple_loss=0.2747, pruned_loss=0.03357, over 7022.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2674, pruned_loss=0.0344, over 1421846.77 frames.], batch size: 28, lr: 3.25e-04
2022-04-29 22:45:46,546 INFO [train.py:763] (4/8) Epoch 23, batch 1950, loss[loss=0.1827, simple_loss=0.2949, pruned_loss=0.03526, over 7107.00 frames.], tot_loss[loss=0.1684, simple_loss=0.268, pruned_loss=0.03435, over 1423554.75 frames.], batch size: 21, lr: 3.25e-04
2022-04-29 22:46:52,056 INFO [train.py:763] (4/8) Epoch 23, batch 2000, loss[loss=0.1651, simple_loss=0.2612, pruned_loss=0.03451, over 5038.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2692, pruned_loss=0.0351, over 1422049.90 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:47:58,952 INFO [train.py:763] (4/8) Epoch 23, batch 2050, loss[loss=0.1555, simple_loss=0.2598, pruned_loss=0.02559, over 7429.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2695, pruned_loss=0.03562, over 1422076.78 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:49:05,147 INFO [train.py:763] (4/8) Epoch 23, batch 2100, loss[loss=0.1423, simple_loss=0.2312, pruned_loss=0.0267, over 7009.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2684, pruned_loss=0.03536, over 1423518.67 frames.], batch size: 16, lr: 3.25e-04
2022-04-29 22:50:10,652 INFO [train.py:763] (4/8) Epoch 23, batch 2150, loss[loss=0.2066, simple_loss=0.2914, pruned_loss=0.06093, over 5271.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2678, pruned_loss=0.0353, over 1420898.51 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:51:16,163 INFO [train.py:763] (4/8) Epoch 23, batch 2200, loss[loss=0.1396, simple_loss=0.2319, pruned_loss=0.02363, over 7142.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03488, over 1420475.44 frames.], batch size: 17, lr: 3.25e-04
2022-04-29 22:52:21,331 INFO [train.py:763] (4/8) Epoch 23, batch 2250, loss[loss=0.1823, simple_loss=0.2824, pruned_loss=0.0411, over 7331.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2677, pruned_loss=0.03503, over 1410138.95 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 22:53:28,270 INFO [train.py:763] (4/8) Epoch 23, batch 2300, loss[loss=0.1713, simple_loss=0.2694, pruned_loss=0.03664, over 7259.00 frames.], tot_loss[loss=0.168, simple_loss=0.2669, pruned_loss=0.03455, over 1416648.80 frames.], batch size: 17, lr: 3.24e-04
2022-04-29 22:54:34,463 INFO [train.py:763] (4/8) Epoch 23, batch 2350, loss[loss=0.1647, simple_loss=0.2772, pruned_loss=0.02608, over 7327.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.0345, over 1418304.17 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 22:55:39,709 INFO [train.py:763] (4/8) Epoch 23, batch 2400, loss[loss=0.152, simple_loss=0.2394, pruned_loss=0.03234, over 6808.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2678, pruned_loss=0.03462, over 1421898.48 frames.], batch size: 15, lr: 3.24e-04
2022-04-29 22:56:45,972 INFO [train.py:763] (4/8) Epoch 23, batch 2450, loss[loss=0.1663, simple_loss=0.2746, pruned_loss=0.02904, over 7233.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2666, pruned_loss=0.03425, over 1418715.91 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 22:57:51,397 INFO [train.py:763] (4/8) Epoch 23, batch 2500, loss[loss=0.1549, simple_loss=0.2524, pruned_loss=0.02866, over 7311.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03442, over 1418969.34 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 22:58:56,884 INFO [train.py:763] (4/8) Epoch 23, batch 2550, loss[loss=0.2002, simple_loss=0.2801, pruned_loss=0.06014, over 5014.00 frames.], tot_loss[loss=0.167, simple_loss=0.2658, pruned_loss=0.03414, over 1415440.15 frames.], batch size: 54, lr: 3.24e-04
2022-04-29 23:00:02,919 INFO [train.py:763] (4/8) Epoch 23, batch 2600, loss[loss=0.1423, simple_loss=0.2364, pruned_loss=0.02415, over 7278.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03481, over 1418736.49 frames.], batch size: 18, lr: 3.24e-04
2022-04-29 23:01:08,568 INFO [train.py:763] (4/8) Epoch 23, batch 2650, loss[loss=0.1545, simple_loss=0.2568, pruned_loss=0.02609, over 7312.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.0345, over 1417147.38 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:02:14,021 INFO [train.py:763] (4/8) Epoch 23, batch 2700, loss[loss=0.1797, simple_loss=0.2876, pruned_loss=0.0359, over 7334.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2674, pruned_loss=0.03437, over 1421843.50 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 23:03:19,897 INFO [train.py:763] (4/8) Epoch 23, batch 2750, loss[loss=0.1581, simple_loss=0.2576, pruned_loss=0.02934, over 7419.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2665, pruned_loss=0.03431, over 1424837.19 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:04:25,095 INFO [train.py:763] (4/8) Epoch 23, batch 2800, loss[loss=0.1801, simple_loss=0.2819, pruned_loss=0.03912, over 7246.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2679, pruned_loss=0.03443, over 1421867.50 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 23:05:30,273 INFO [train.py:763] (4/8) Epoch 23, batch 2850, loss[loss=0.1442, simple_loss=0.2474, pruned_loss=0.02054, over 7366.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2684, pruned_loss=0.0345, over 1422102.97 frames.], batch size: 19, lr: 3.24e-04
2022-04-29 23:06:35,472 INFO [train.py:763] (4/8) Epoch 23, batch 2900, loss[loss=0.183, simple_loss=0.283, pruned_loss=0.04151, over 7314.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2683, pruned_loss=0.03451, over 1422744.96 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 23:07:40,683 INFO [train.py:763] (4/8) Epoch 23, batch 2950, loss[loss=0.1592, simple_loss=0.2451, pruned_loss=0.03665, over 7285.00 frames.], tot_loss[loss=0.1685, simple_loss=0.268, pruned_loss=0.03451, over 1426450.77 frames.], batch size: 17, lr: 3.23e-04
2022-04-29 23:08:45,891 INFO [train.py:763] (4/8) Epoch 23, batch 3000, loss[loss=0.2054, simple_loss=0.3029, pruned_loss=0.05392, over 7123.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2688, pruned_loss=0.03486, over 1422212.70 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:08:45,892 INFO [train.py:783] (4/8) Computing validation loss
2022-04-29 23:09:01,228 INFO [train.py:792] (4/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
2022-04-29 23:10:07,036 INFO [train.py:763] (4/8) Epoch 23, batch 3050, loss[loss=0.1588, simple_loss=0.2515, pruned_loss=0.03308, over 7289.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2679, pruned_loss=0.03484, over 1417544.15 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:11:12,527 INFO [train.py:763] (4/8) Epoch 23, batch 3100, loss[loss=0.1756, simple_loss=0.2775, pruned_loss=0.03682, over 6705.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2674, pruned_loss=0.03485, over 1420861.62 frames.], batch size: 31, lr: 3.23e-04
2022-04-29 23:12:19,057 INFO [train.py:763] (4/8) Epoch 23, batch 3150, loss[loss=0.1382, simple_loss=0.2326, pruned_loss=0.02192, over 7014.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2665, pruned_loss=0.03451, over 1421744.92 frames.], batch size: 16, lr: 3.23e-04
2022-04-29 23:13:26,790 INFO [train.py:763] (4/8) Epoch 23, batch 3200, loss[loss=0.17, simple_loss=0.2754, pruned_loss=0.03227, over 7318.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03436, over 1425990.67 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:14:33,553 INFO [train.py:763] (4/8) Epoch 23, batch 3250, loss[loss=0.1644, simple_loss=0.2571, pruned_loss=0.03583, over 7161.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03411, over 1427929.13 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:15:38,816 INFO [train.py:763] (4/8) Epoch 23, batch 3300, loss[loss=0.1983, simple_loss=0.308, pruned_loss=0.04434, over 7274.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2675, pruned_loss=0.03439, over 1427677.27 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:16:45,585 INFO [train.py:763] (4/8) Epoch 23, batch 3350, loss[loss=0.1739, simple_loss=0.2701, pruned_loss=0.03889, over 7300.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2678, pruned_loss=0.0347, over 1423974.63 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:17:51,523 INFO [train.py:763] (4/8) Epoch 23, batch 3400, loss[loss=0.1456, simple_loss=0.2332, pruned_loss=0.02903, over 7358.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03457, over 1427699.34 frames.], batch size: 19, lr: 3.23e-04
2022-04-29 23:18:56,729 INFO [train.py:763] (4/8) Epoch 23, batch 3450, loss[loss=0.1606, simple_loss=0.2732, pruned_loss=0.024, over 7316.00 frames.], tot_loss[loss=0.169, simple_loss=0.2685, pruned_loss=0.03471, over 1423351.31 frames.], batch size: 22, lr: 3.23e-04
2022-04-29 23:20:02,250 INFO [train.py:763] (4/8) Epoch 23, batch 3500, loss[loss=0.1477, simple_loss=0.2347, pruned_loss=0.03042, over 6847.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2661, pruned_loss=0.03377, over 1421814.00 frames.], batch size: 15, lr: 3.23e-04
2022-04-29 23:21:08,250 INFO [train.py:763] (4/8) Epoch 23, batch 3550, loss[loss=0.1643, simple_loss=0.2677, pruned_loss=0.03049, over 7110.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03436, over 1423261.38 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:22:13,611 INFO [train.py:763] (4/8) Epoch 23, batch 3600, loss[loss=0.1352, simple_loss=0.2348, pruned_loss=0.0178, over 7055.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2665, pruned_loss=0.03436, over 1422381.77 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:23:18,840 INFO [train.py:763] (4/8) Epoch 23, batch 3650, loss[loss=0.1675, simple_loss=0.2505, pruned_loss=0.04224, over 7354.00 frames.], tot_loss[loss=0.1681, simple_loss=0.267, pruned_loss=0.03459, over 1423953.36 frames.], batch size: 19, lr: 3.22e-04
2022-04-29 23:24:24,041 INFO [train.py:763] (4/8) Epoch 23, batch 3700, loss[loss=0.1538, simple_loss=0.2635, pruned_loss=0.0221, over 6373.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2666, pruned_loss=0.03419, over 1420976.64 frames.], batch size: 38, lr: 3.22e-04
2022-04-29 23:25:30,842 INFO [train.py:763] (4/8) Epoch 23, batch 3750, loss[loss=0.1672, simple_loss=0.2622, pruned_loss=0.03613, over 7277.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2672, pruned_loss=0.03435, over 1422053.08 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:26:37,716 INFO [train.py:763] (4/8) Epoch 23, batch 3800, loss[loss=0.1462, simple_loss=0.2514, pruned_loss=0.02046, over 7429.00 frames.], tot_loss[loss=0.1678, simple_loss=0.267, pruned_loss=0.03429, over 1423838.13 frames.], batch size: 20, lr: 3.22e-04
2022-04-29 23:27:43,263 INFO [train.py:763] (4/8) Epoch 23, batch 3850, loss[loss=0.1745, simple_loss=0.2786, pruned_loss=0.03523, over 5202.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2671, pruned_loss=0.03429, over 1419763.21 frames.], batch size: 52, lr: 3.22e-04
2022-04-29 23:28:48,633 INFO [train.py:763] (4/8) Epoch 23, batch 3900, loss[loss=0.1814, simple_loss=0.2803, pruned_loss=0.04126, over 6674.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2671, pruned_loss=0.0348, over 1416808.18 frames.], batch size: 31, lr: 3.22e-04
2022-04-29 23:29:53,688 INFO [train.py:763] (4/8) Epoch 23, batch 3950, loss[loss=0.1302, simple_loss=0.231, pruned_loss=0.01464, over 7128.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2672, pruned_loss=0.03457, over 1416955.13 frames.], batch size: 17, lr: 3.22e-04
2022-04-29 23:30:59,585 INFO [train.py:763] (4/8) Epoch 23, batch 4000, loss[loss=0.1821, simple_loss=0.2922, pruned_loss=0.03599, over 7202.00 frames.], tot_loss[loss=0.1688, simple_loss=0.268, pruned_loss=0.03475, over 1415211.34 frames.], batch size: 22, lr: 3.22e-04
2022-04-29 23:32:05,450 INFO [train.py:763] (4/8) Epoch 23, batch 4050, loss[loss=0.1981, simple_loss=0.2942, pruned_loss=0.05106, over 4837.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2679, pruned_loss=0.03457, over 1416061.60 frames.], batch size: 54, lr: 3.22e-04
2022-04-29 23:33:10,716 INFO [train.py:763] (4/8) Epoch 23, batch 4100, loss[loss=0.1412, simple_loss=0.2332, pruned_loss=0.02456, over 7279.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2672, pruned_loss=0.03424, over 1416673.89 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:34:16,152 INFO [train.py:763] (4/8) Epoch 23, batch 4150, loss[loss=0.1385, simple_loss=0.227, pruned_loss=0.02494, over 6997.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2666, pruned_loss=0.03392, over 1418886.92 frames.], batch size: 16, lr: 3.22e-04
2022-04-29 23:35:21,250 INFO [train.py:763] (4/8) Epoch 23, batch 4200, loss[loss=0.1469, simple_loss=0.243, pruned_loss=0.02534, over 7266.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2676, pruned_loss=0.03431, over 1419680.68 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:36:26,914 INFO [train.py:763] (4/8) Epoch 23, batch 4250, loss[loss=0.2136, simple_loss=0.3198, pruned_loss=0.0537, over 7382.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2679, pruned_loss=0.03476, over 1417729.94 frames.], batch size: 23, lr: 3.22e-04
2022-04-29 23:37:32,233 INFO [train.py:763] (4/8) Epoch 23, batch 4300, loss[loss=0.1425, simple_loss=0.2338, pruned_loss=0.02554, over 6795.00 frames.], tot_loss[loss=0.168, simple_loss=0.2669, pruned_loss=0.03458, over 1416790.45 frames.], batch size: 15, lr: 3.21e-04
2022-04-29 23:38:37,629 INFO [train.py:763] (4/8) Epoch 23, batch 4350, loss[loss=0.1908, simple_loss=0.2883, pruned_loss=0.04659, over 6767.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2678, pruned_loss=0.03518, over 1414024.61 frames.], batch size: 31, lr: 3.21e-04
2022-04-29 23:39:43,229 INFO [train.py:763] (4/8) Epoch 23, batch 4400, loss[loss=0.1597, simple_loss=0.2774, pruned_loss=0.02102, over 6219.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2683, pruned_loss=0.03559, over 1408087.29 frames.], batch size: 37, lr: 3.21e-04
2022-04-29 23:40:48,373 INFO [train.py:763] (4/8) Epoch 23, batch 4450, loss[loss=0.1947, simple_loss=0.2938, pruned_loss=0.04777, over 6458.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03521, over 1410156.38 frames.], batch size: 38, lr: 3.21e-04
2022-04-29 23:41:53,041 INFO [train.py:763] (4/8) Epoch 23, batch 4500, loss[loss=0.1715, simple_loss=0.2797, pruned_loss=0.03161, over 6351.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03533, over 1397825.98 frames.], batch size: 37, lr: 3.21e-04
2022-04-29 23:42:58,310 INFO [train.py:763] (4/8) Epoch 23, batch 4550, loss[loss=0.1714, simple_loss=0.2826, pruned_loss=0.03004, over 7294.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2681, pruned_loss=0.03557, over 1386589.21 frames.], batch size: 24, lr: 3.21e-04
2022-04-29 23:44:17,933 INFO [train.py:763] (4/8) Epoch 24, batch 0, loss[loss=0.1864, simple_loss=0.2813, pruned_loss=0.04574, over 7068.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2813, pruned_loss=0.04574, over 7068.00 frames.], batch size: 18, lr: 3.15e-04
2022-04-29 23:45:23,857 INFO [train.py:763] (4/8) Epoch 24, batch 50, loss[loss=0.1648, simple_loss=0.255, pruned_loss=0.03736, over 7259.00 frames.], tot_loss[loss=0.171, simple_loss=0.2691, pruned_loss=0.03646, over 321874.34 frames.], batch size: 19, lr: 3.15e-04
2022-04-29 23:46:30,362 INFO [train.py:763] (4/8) Epoch 24, batch 100, loss[loss=0.1509, simple_loss=0.2538, pruned_loss=0.02402, over 7324.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2664, pruned_loss=0.03462, over 569961.46 frames.], batch size: 20, lr: 3.15e-04
2022-04-29 23:47:35,974 INFO [train.py:763] (4/8) Epoch 24, batch 150, loss[loss=0.1627, simple_loss=0.2671, pruned_loss=0.02912, over 7315.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2675, pruned_loss=0.03462, over 761240.26 frames.], batch size: 21, lr: 3.14e-04
2022-04-29 23:48:41,592 INFO [train.py:763] (4/8) Epoch 24, batch 200, loss[loss=0.163, simple_loss=0.2455, pruned_loss=0.04027, over 7228.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03492, over 906700.74 frames.], batch size: 16, lr: 3.14e-04
2022-04-29 23:49:46,882 INFO [train.py:763] (4/8) Epoch 24, batch 250, loss[loss=0.1797, simple_loss=0.2859, pruned_loss=0.03677, over 7237.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03448, over 1018577.70 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:50:52,234 INFO [train.py:763] (4/8) Epoch 24, batch 300, loss[loss=0.168, simple_loss=0.258, pruned_loss=0.03895, over 7149.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03509, over 1112860.31 frames.], batch size: 19, lr: 3.14e-04
2022-04-29 23:51:57,519 INFO [train.py:763] (4/8) Epoch 24, batch 350, loss[loss=0.1567, simple_loss=0.2603, pruned_loss=0.02655, over 7193.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2669, pruned_loss=0.03502, over 1182565.13 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:53:03,340 INFO [train.py:763] (4/8) Epoch 24, batch 400, loss[loss=0.1954, simple_loss=0.3075, pruned_loss=0.04161, over 7233.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2668, pruned_loss=0.03447, over 1236671.98 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:54:08,671 INFO [train.py:763] (4/8) Epoch 24, batch 450, loss[loss=0.165, simple_loss=0.2651, pruned_loss=0.03247, over 7076.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03421, over 1277870.09 frames.], batch size: 28, lr: 3.14e-04
2022-04-29 23:55:14,210 INFO [train.py:763] (4/8) Epoch 24, batch 500, loss[loss=0.1707, simple_loss=0.2652, pruned_loss=0.03807, over 7164.00 frames.], tot_loss[loss=0.1671, simple_loss=0.266, pruned_loss=0.03413, over 1313362.17 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:56:20,425 INFO [train.py:763] (4/8) Epoch 24, batch 550, loss[loss=0.1495, simple_loss=0.2437, pruned_loss=0.02763, over 7173.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2662, pruned_loss=0.03375, over 1340089.45 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:57:26,717 INFO [train.py:763] (4/8) Epoch 24, batch 600, loss[loss=0.1693, simple_loss=0.2645, pruned_loss=0.03701, over 7189.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.03401, over 1359395.27 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:58:32,094 INFO [train.py:763] (4/8) Epoch 24, batch 650, loss[loss=0.1414, simple_loss=0.2303, pruned_loss=0.02624, over 7305.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03379, over 1371568.14 frames.], batch size: 17, lr: 3.14e-04
2022-04-29 23:59:38,741 INFO [train.py:763] (4/8) Epoch 24, batch 700, loss[loss=0.1401, simple_loss=0.2268, pruned_loss=0.02663, over 6839.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03392, over 1388087.83 frames.], batch size: 15, lr: 3.14e-04
2022-04-30 00:00:44,925 INFO [train.py:763] (4/8) Epoch 24, batch 750, loss[loss=0.163, simple_loss=0.2564, pruned_loss=0.03475, over 7237.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.03416, over 1399026.56 frames.], batch size: 20, lr: 3.14e-04
2022-04-30 00:01:50,607 INFO [train.py:763] (4/8) Epoch 24, batch 800, loss[loss=0.1735, simple_loss=0.278, pruned_loss=0.03454, over 7415.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03407, over 1405689.75 frames.], batch size: 21, lr: 3.14e-04
2022-04-30 00:02:56,128 INFO [train.py:763] (4/8) Epoch 24, batch 850, loss[loss=0.1614, simple_loss=0.2725, pruned_loss=0.02517, over 7321.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2655, pruned_loss=0.03349, over 1407646.18 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:04:01,369 INFO [train.py:763] (4/8) Epoch 24, batch 900, loss[loss=0.1975, simple_loss=0.3061, pruned_loss=0.0444, over 7359.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2664, pruned_loss=0.03421, over 1409883.65 frames.], batch size: 25, lr: 3.13e-04
2022-04-30 00:05:07,032 INFO [train.py:763] (4/8) Epoch 24, batch 950, loss[loss=0.1932, simple_loss=0.2924, pruned_loss=0.04703, over 5055.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03449, over 1405575.44 frames.], batch size: 52, lr: 3.13e-04
2022-04-30 00:06:12,842 INFO [train.py:763] (4/8) Epoch 24, batch 1000, loss[loss=0.1597, simple_loss=0.2615, pruned_loss=0.02892, over 7413.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2664, pruned_loss=0.03419, over 1411983.47 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:07:18,485 INFO [train.py:763] (4/8) Epoch 24, batch 1050, loss[loss=0.1524, simple_loss=0.2579, pruned_loss=0.02341, over 7310.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2667, pruned_loss=0.03384, over 1418692.69 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:08:23,984 INFO [train.py:763] (4/8) Epoch 24, batch 1100, loss[loss=0.1815, simple_loss=0.2912, pruned_loss=0.03593, over 7345.00 frames.], tot_loss[loss=0.166, simple_loss=0.2653, pruned_loss=0.03335, over 1421484.40 frames.], batch size: 22, lr: 3.13e-04
2022-04-30 00:09:29,775 INFO [train.py:763] (4/8) Epoch 24, batch 1150, loss[loss=0.1747, simple_loss=0.2771, pruned_loss=0.03619, over 7206.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03375, over 1425083.24 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:10:35,399 INFO [train.py:763] (4/8) Epoch 24, batch 1200, loss[loss=0.1845, simple_loss=0.2898, pruned_loss=0.03959, over 7358.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03387, over 1424918.22 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:11:41,671 INFO [train.py:763] (4/8) Epoch 24, batch 1250, loss[loss=0.1842, simple_loss=0.2779, pruned_loss=0.04521, over 7151.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2657, pruned_loss=0.03438, over 1423083.57 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:12:47,620 INFO [train.py:763] (4/8) Epoch 24, batch 1300, loss[loss=0.1441, simple_loss=0.2376, pruned_loss=0.02535, over 6823.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.03451, over 1421999.95 frames.], batch size: 15, lr: 3.13e-04
2022-04-30 00:13:53,403 INFO [train.py:763] (4/8) Epoch 24, batch 1350, loss[loss=0.1702, simple_loss=0.2789, pruned_loss=0.03075, over 6424.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2662, pruned_loss=0.03471, over 1423012.51 frames.], batch size: 38, lr: 3.13e-04
2022-04-30 00:14:58,833 INFO [train.py:763] (4/8) Epoch 24, batch 1400, loss[loss=0.1688, simple_loss=0.2593, pruned_loss=0.03921, over 7271.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.0346, over 1427801.73 frames.], batch size: 17, lr: 3.13e-04
2022-04-30 00:16:04,288 INFO [train.py:763] (4/8) Epoch 24, batch 1450, loss[loss=0.1616, simple_loss=0.2638, pruned_loss=0.02967, over 7145.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2661, pruned_loss=0.03457, over 1423406.80 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:17:11,224 INFO [train.py:763] (4/8) Epoch 24, batch 1500, loss[loss=0.1916, simple_loss=0.2969, pruned_loss=0.04316, over 6688.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.03422, over 1422119.57 frames.], batch size: 31, lr: 3.13e-04
2022-04-30 00:18:17,536 INFO [train.py:763] (4/8) Epoch 24, batch 1550, loss[loss=0.1526, simple_loss=0.2525, pruned_loss=0.02632, over 7290.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2668, pruned_loss=0.03444, over 1422943.68 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:19:23,704 INFO [train.py:763] (4/8) Epoch 24, batch 1600, loss[loss=0.1363, simple_loss=0.2343, pruned_loss=0.01921, over 7219.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2663, pruned_loss=0.0343, over 1421580.29 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:20:29,912 INFO [train.py:763] (4/8) Epoch 24, batch 1650, loss[loss=0.1628, simple_loss=0.2599, pruned_loss=0.0329, over 7227.00 frames.], tot_loss[loss=0.1674, simple_loss=0.266, pruned_loss=0.03444, over 1422650.07 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:21:35,718 INFO [train.py:763] (4/8) Epoch 24, batch 1700, loss[loss=0.184, simple_loss=0.2853, pruned_loss=0.04137, over 7379.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2658, pruned_loss=0.03435, over 1421314.11 frames.], batch size: 23, lr: 3.12e-04
2022-04-30 00:22:40,920 INFO [train.py:763] (4/8) Epoch 24, batch 1750, loss[loss=0.1389, simple_loss=0.2328, pruned_loss=0.02256, over 7148.00 frames.], tot_loss[loss=0.1675, simple_loss=0.266, pruned_loss=0.03446, over 1422970.39 frames.], batch size: 17, lr: 3.12e-04
2022-04-30 00:23:47,084 INFO [train.py:763] (4/8) Epoch 24, batch 1800, loss[loss=0.1479, simple_loss=0.2434, pruned_loss=0.02625, over 7013.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2661, pruned_loss=0.03438, over 1422443.04 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:24:52,827 INFO [train.py:763] (4/8) Epoch 24, batch 1850, loss[loss=0.1844, simple_loss=0.2651, pruned_loss=0.0518, over 7243.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2658, pruned_loss=0.03443, over 1419560.66 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:26:09,444 INFO [train.py:763] (4/8) Epoch 24, batch 1900, loss[loss=0.1874, simple_loss=0.287, pruned_loss=0.04389, over 7274.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2662, pruned_loss=0.03466, over 1421102.02 frames.], batch size: 25, lr: 3.12e-04
2022-04-30 00:27:15,222 INFO [train.py:763] (4/8) Epoch 24, batch 1950, loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03395, over 7255.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2662, pruned_loss=0.03478, over 1423188.45 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:28:21,026 INFO [train.py:763] (4/8) Epoch 24, batch 2000, loss[loss=0.1536, simple_loss=0.2533, pruned_loss=0.02697, over 7161.00 frames.], tot_loss[loss=0.1674, simple_loss=0.266, pruned_loss=0.0344, over 1424391.04 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:29:27,103 INFO [train.py:763] (4/8) Epoch 24, batch 2050, loss[loss=0.182, simple_loss=0.2883, pruned_loss=0.03782, over 7332.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2653, pruned_loss=0.03422, over 1428588.12 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:30:32,482 INFO [train.py:763] (4/8) Epoch 24, batch 2100, loss[loss=0.1881, simple_loss=0.2742, pruned_loss=0.05095, over 7255.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2655, pruned_loss=0.03428, over 1424881.26 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:31:37,972 INFO [train.py:763] (4/8) Epoch 24, batch 2150, loss[loss=0.16, simple_loss=0.2567, pruned_loss=0.03166, over 7421.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2664, pruned_loss=0.03458, over 1423383.87 frames.], batch size: 20, lr: 3.12e-04
2022-04-30 00:32:43,331 INFO [train.py:763] (4/8) Epoch 24, batch 2200, loss[loss=0.1619, simple_loss=0.2479, pruned_loss=0.03797, over 7231.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2654, pruned_loss=0.0339, over 1422231.28 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:33:49,447 INFO [train.py:763] (4/8) Epoch 24, batch 2250, loss[loss=0.1605, simple_loss=0.2626, pruned_loss=0.02923, over 7070.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2651, pruned_loss=0.03418, over 1418238.03 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:34:55,311 INFO [train.py:763] (4/8) Epoch 24, batch 2300, loss[loss=0.1501, simple_loss=0.2419, pruned_loss=0.02916, over 7195.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2647, pruned_loss=0.03394, over 1419557.54 frames.], batch size: 16, lr: 3.11e-04
2022-04-30 00:36:01,133 INFO [train.py:763] (4/8) Epoch 24, batch 2350, loss[loss=0.161, simple_loss=0.268, pruned_loss=0.02698, over 7308.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2646, pruned_loss=0.03381, over 1420253.41 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:37:06,713 INFO [train.py:763] (4/8) Epoch 24, batch 2400, loss[loss=0.1734, simple_loss=0.2682, pruned_loss=0.0393, over 7353.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2653, pruned_loss=0.03376, over 1424732.38 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:38:21,819 INFO [train.py:763] (4/8) Epoch 24, batch 2450, loss[loss=0.141, simple_loss=0.234, pruned_loss=0.02401, over 7135.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03393, over 1423844.21 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:39:27,184 INFO [train.py:763] (4/8) Epoch 24, batch 2500, loss[loss=0.1734, simple_loss=0.2789, pruned_loss=0.0339, over 7403.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2652, pruned_loss=0.03395, over 1423652.04 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:40:32,702 INFO [train.py:763] (4/8) Epoch 24, batch 2550, loss[loss=0.1761, simple_loss=0.266, pruned_loss=0.04311, over 7414.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2659, pruned_loss=0.03398, over 1424403.58 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:41:38,100 INFO [train.py:763] (4/8) Epoch 24, batch 2600, loss[loss=0.1579, simple_loss=0.2453, pruned_loss=0.03522, over 7137.00 frames.], tot_loss[loss=0.1674, simple_loss=0.266, pruned_loss=0.03437, over 1421928.88 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:42:43,677 INFO [train.py:763] (4/8) Epoch 24, batch 2650, loss[loss=0.1664, simple_loss=0.264, pruned_loss=0.03443, over 7208.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2666, pruned_loss=0.03425, over 1424023.53 frames.], batch size: 22, lr: 3.11e-04
2022-04-30 00:43:49,270 INFO [train.py:763] (4/8) Epoch 24, batch 2700, loss[loss=0.159, simple_loss=0.2547, pruned_loss=0.03171, over 7060.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2661, pruned_loss=0.03409, over 1426405.56 frames.], batch size: 18, lr: 3.11e-04
2022-04-30 00:44:54,688 INFO [train.py:763] (4/8) Epoch 24, batch 2750, loss[loss=0.1678, simple_loss=0.2769, pruned_loss=0.02942, over 7137.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2657, pruned_loss=0.03442, over 1421406.97 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:46:00,208 INFO [train.py:763] (4/8) Epoch 24, batch 2800, loss[loss=0.1553, simple_loss=0.2512, pruned_loss=0.02968, over 7257.00 frames.], tot_loss[loss=0.1665, simple_loss=0.265, pruned_loss=0.03399, over 1422160.41 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:47:22,974 INFO [train.py:763] (4/8) Epoch 24, batch 2850, loss[loss=0.1713, simple_loss=0.2706, pruned_loss=0.03607, over 7433.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2652, pruned_loss=0.0338, over 1420313.64 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:48:28,452 INFO [train.py:763] (4/8) Epoch 24, batch 2900, loss[loss=0.169, simple_loss=0.2746, pruned_loss=0.03172, over 7213.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2667, pruned_loss=0.03419, over 1420937.35 frames.], batch size: 23, lr: 3.11e-04
2022-04-30 00:49:52,261 INFO [train.py:763] (4/8) Epoch 24, batch 2950, loss[loss=0.1751, simple_loss=0.2852, pruned_loss=0.03254, over 7108.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2666, pruned_loss=0.03396, over 1425981.02 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:51:06,863 INFO [train.py:763] (4/8) Epoch 24, batch 3000, loss[loss=0.1714, simple_loss=0.2706, pruned_loss=0.03606, over 6639.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2648, pruned_loss=0.03319, over 1428572.35 frames.], batch size: 31, lr: 3.10e-04
2022-04-30 00:51:06,864 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 00:51:22,143 INFO [train.py:792] (4/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
2022-04-30 00:52:37,060 INFO [train.py:763] (4/8) Epoch 24, batch 3050, loss[loss=0.1627, simple_loss=0.2754, pruned_loss=0.02504, over 7102.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2649, pruned_loss=0.03333, over 1429137.27 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 00:53:42,765 INFO [train.py:763] (4/8) Epoch 24, batch 3100, loss[loss=0.1438, simple_loss=0.2301, pruned_loss=0.02878, over 6773.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2644, pruned_loss=0.03325, over 1428856.33 frames.], batch size: 15, lr: 3.10e-04
2022-04-30 00:54:48,068 INFO [train.py:763] (4/8) Epoch 24, batch 3150, loss[loss=0.1553, simple_loss=0.2504, pruned_loss=0.03008, over 7262.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2643, pruned_loss=0.0331, over 1430260.97 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:55:53,498 INFO [train.py:763] (4/8) Epoch 24, batch 3200, loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03064, over 5288.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03285, over 1429585.25 frames.], batch size: 53, lr: 3.10e-04
2022-04-30 00:56:59,203 INFO [train.py:763] (4/8) Epoch 24, batch 3250, loss[loss=0.1729, simple_loss=0.2721, pruned_loss=0.03685, over 7232.00 frames.], tot_loss[loss=0.165, simple_loss=0.264, pruned_loss=0.03297, over 1426652.14 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 00:58:05,419 INFO [train.py:763] (4/8) Epoch 24, batch 3300, loss[loss=0.1551, simple_loss=0.2534, pruned_loss=0.02842, over 7164.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03304, over 1425933.37 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:59:11,081 INFO [train.py:763] (4/8) Epoch 24, batch 3350, loss[loss=0.1885, simple_loss=0.2815, pruned_loss=0.04772, over 7270.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03379, over 1422035.61 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 01:00:16,803 INFO [train.py:763] (4/8) Epoch 24, batch 3400, loss[loss=0.1439, simple_loss=0.2413, pruned_loss=0.02324, over 7291.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2644, pruned_loss=0.03321, over 1424115.55 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:01:22,330 INFO [train.py:763] (4/8) Epoch 24, batch 3450, loss[loss=0.1741, simple_loss=0.275, pruned_loss=0.03662, over 7216.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2653, pruned_loss=0.0336, over 1420636.38 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 01:02:27,609 INFO [train.py:763] (4/8) Epoch 24, batch 3500, loss[loss=0.1475, simple_loss=0.2415, pruned_loss=0.02671, over 7139.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03392, over 1422554.74 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:03:33,195 INFO [train.py:763] (4/8) Epoch 24, batch 3550, loss[loss=0.1522, simple_loss=0.2535, pruned_loss=0.02542, over 7340.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2661, pruned_loss=0.03408, over 1423418.02 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:04:38,395 INFO [train.py:763] (4/8) Epoch 24, batch 3600, loss[loss=0.1835, simple_loss=0.2829, pruned_loss=0.04207, over 7203.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2665, pruned_loss=0.03423, over 1421868.06 frames.], batch size: 23, lr: 3.10e-04
2022-04-30 01:05:45,314 INFO [train.py:763] (4/8) Epoch 24, batch 3650, loss[loss=0.1802, simple_loss=0.2749, pruned_loss=0.04272, over 6685.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03392, over 1418929.90 frames.], batch size: 38, lr: 3.10e-04
2022-04-30 01:06:51,859 INFO [train.py:763] (4/8) Epoch 24, batch 3700, loss[loss=0.1611, simple_loss=0.2616, pruned_loss=0.03034, over 7428.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2647, pruned_loss=0.03349, over 1421756.74 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:07:57,541 INFO [train.py:763] (4/8) Epoch 24, batch 3750, loss[loss=0.1705, simple_loss=0.2746, pruned_loss=0.0332, over 7381.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03335, over 1424089.32 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:09:02,949 INFO [train.py:763] (4/8) Epoch 24, batch 3800, loss[loss=0.1928, simple_loss=0.2847, pruned_loss=0.0505, over 5070.00 frames.], tot_loss[loss=0.1652, simple_loss=0.264, pruned_loss=0.03325, over 1422679.95 frames.], batch size: 52, lr: 3.09e-04
2022-04-30 01:10:08,027 INFO [train.py:763] (4/8) Epoch 24, batch 3850, loss[loss=0.1619, simple_loss=0.2454, pruned_loss=0.03923, over 7270.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.0334, over 1421831.69 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:11:13,746 INFO [train.py:763] (4/8) Epoch 24, batch 3900, loss[loss=0.1719, simple_loss=0.2643, pruned_loss=0.03973, over 7260.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.0337, over 1421392.71 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:12:19,226 INFO [train.py:763] (4/8) Epoch 24, batch 3950, loss[loss=0.1275, simple_loss=0.2198, pruned_loss=0.01757, over 7419.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03337, over 1423421.79 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:13:24,348 INFO [train.py:763] (4/8) Epoch 24, batch 4000, loss[loss=0.1651, simple_loss=0.2786, pruned_loss=0.02581, over 7316.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03306, over 1422727.37 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:14:29,874 INFO [train.py:763] (4/8) Epoch 24, batch 4050, loss[loss=0.1757, simple_loss=0.2836, pruned_loss=0.03386, over 7424.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03257, over 1420977.08 frames.], batch size: 20, lr: 3.09e-04
2022-04-30 01:15:36,735 INFO [train.py:763] (4/8) Epoch 24, batch 4100, loss[loss=0.1841, simple_loss=0.2896, pruned_loss=0.03931, over 6353.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.033, over 1421921.94 frames.], batch size: 37, lr: 3.09e-04
2022-04-30 01:16:43,482 INFO [train.py:763] (4/8) Epoch 24, batch 4150, loss[loss=0.1908, simple_loss=0.2832, pruned_loss=0.04916, over 7224.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03302, over 1418162.91 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:17:50,167 INFO [train.py:763] (4/8) Epoch 24, batch 4200, loss[loss=0.1657, simple_loss=0.2777, pruned_loss=0.02682, over 7208.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2673, pruned_loss=0.03388, over 1420363.09 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:18:56,565 INFO [train.py:763] (4/8) Epoch 24, batch 4250, loss[loss=0.1687, simple_loss=0.261, pruned_loss=0.03816, over 6179.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2668, pruned_loss=0.034, over 1414616.24 frames.], batch size: 37, lr: 3.09e-04
2022-04-30 01:20:02,370 INFO [train.py:763] (4/8) Epoch 24, batch 4300, loss[loss=0.1501, simple_loss=0.2514, pruned_loss=0.02439, over 7152.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2656, pruned_loss=0.03372, over 1413903.06 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:21:09,409 INFO [train.py:763] (4/8) Epoch 24, batch 4350, loss[loss=0.191, simple_loss=0.2921, pruned_loss=0.04496, over 7302.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03385, over 1414369.52 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:22:16,101 INFO [train.py:763] (4/8) Epoch 24, batch 4400, loss[loss=0.1733, simple_loss=0.2703, pruned_loss=0.03821, over 7291.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03375, over 1413120.05 frames.], batch size: 24, lr: 3.09e-04
2022-04-30 01:23:21,721 INFO [train.py:763] (4/8) Epoch 24, batch 4450, loss[loss=0.1795, simple_loss=0.2818, pruned_loss=0.03864, over 7320.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2669, pruned_loss=0.03431, over 1404052.92 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:24:28,204 INFO [train.py:763] (4/8) Epoch 24, batch 4500, loss[loss=0.1821, simple_loss=0.2791, pruned_loss=0.04253, over 5420.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2687, pruned_loss=0.03532, over 1389661.68 frames.], batch size: 52, lr: 3.08e-04
2022-04-30 01:25:32,948 INFO [train.py:763] (4/8) Epoch 24, batch 4550, loss[loss=0.1911, simple_loss=0.2872, pruned_loss=0.04754, over 5137.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2703, pruned_loss=0.03558, over 1351727.19 frames.], batch size: 53, lr: 3.08e-04
2022-04-30 01:26:52,284 INFO [train.py:763] (4/8) Epoch 25, batch 0, loss[loss=0.1856, simple_loss=0.2991, pruned_loss=0.03611, over 7221.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2991, pruned_loss=0.03611, over 7221.00 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:27:58,470 INFO [train.py:763] (4/8) Epoch 25, batch 50, loss[loss=0.1619, simple_loss=0.2721, pruned_loss=0.02585, over 7319.00 frames.], tot_loss[loss=0.164, simple_loss=0.2621, pruned_loss=0.03292, over 322033.49 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:29:03,629 INFO [train.py:763] (4/8) Epoch 25, batch 100, loss[loss=0.1993, simple_loss=0.2877, pruned_loss=0.05547, over 5451.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2633, pruned_loss=0.03257, over 566782.34 frames.], batch size: 52, lr: 3.02e-04
2022-04-30 01:30:08,881 INFO [train.py:763] (4/8) Epoch 25, batch 150, loss[loss=0.1641, simple_loss=0.254, pruned_loss=0.03706, over 7280.00 frames.], tot_loss[loss=0.165, simple_loss=0.265, pruned_loss=0.03248, over 760588.48 frames.], batch size: 17, lr: 3.02e-04
2022-04-30 01:31:14,492 INFO [train.py:763] (4/8) Epoch 25, batch 200, loss[loss=0.1862, simple_loss=0.2937, pruned_loss=0.03938, over 7387.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2644, pruned_loss=0.03248, over 907331.77 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:32:20,360 INFO [train.py:763] (4/8) Epoch 25, batch 250, loss[loss=0.1778, simple_loss=0.2755, pruned_loss=0.04002, over 7211.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03387, over 1019144.80 frames.], batch size: 22, lr: 3.02e-04
2022-04-30 01:33:26,236 INFO [train.py:763] (4/8) Epoch 25, batch 300, loss[loss=0.1575, simple_loss=0.2621, pruned_loss=0.02646, over 7324.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2671, pruned_loss=0.03416, over 1105157.46 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:34:31,515 INFO [train.py:763] (4/8) Epoch 25, batch 350, loss[loss=0.1553, simple_loss=0.2536, pruned_loss=0.02846, over 7170.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03373, over 1174738.48 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:35:36,788 INFO [train.py:763] (4/8) Epoch 25, batch 400, loss[loss=0.122, simple_loss=0.2114, pruned_loss=0.01635, over 7408.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03367, over 1232076.70 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:36:42,352 INFO [train.py:763] (4/8) Epoch 25, batch 450, loss[loss=0.1774, simple_loss=0.2812, pruned_loss=0.03677, over 7398.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2646, pruned_loss=0.03322, over 1273276.97 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:37:47,500 INFO [train.py:763] (4/8) Epoch 25, batch 500, loss[loss=0.1798, simple_loss=0.2763, pruned_loss=0.04166, over 7388.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.0335, over 1302012.98 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:38:52,806 INFO [train.py:763] (4/8) Epoch 25, batch 550, loss[loss=0.1899, simple_loss=0.2993, pruned_loss=0.04031, over 7227.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2651, pruned_loss=0.03317, over 1327455.15 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:39:58,984 INFO [train.py:763] (4/8) Epoch 25, batch 600, loss[loss=0.1828, simple_loss=0.2851, pruned_loss=0.0402, over 7076.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03329, over 1345851.64 frames.], batch size: 28, lr: 3.02e-04
2022-04-30 01:41:04,679 INFO [train.py:763] (4/8) Epoch 25, batch 650, loss[loss=0.144, simple_loss=0.2432, pruned_loss=0.02238, over 7335.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2643, pruned_loss=0.03316, over 1360106.34 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:42:10,706 INFO [train.py:763] (4/8) Epoch 25, batch 700, loss[loss=0.1902, simple_loss=0.2935, pruned_loss=0.04338, over 7147.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2634, pruned_loss=0.03281, over 1373854.50 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:43:16,095 INFO [train.py:763] (4/8) Epoch 25, batch 750, loss[loss=0.1461, simple_loss=0.2443, pruned_loss=0.024, over 7444.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2636, pruned_loss=0.03266, over 1389504.60 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:44:20,962 INFO [train.py:763] (4/8) Epoch 25, batch 800, loss[loss=0.1936, simple_loss=0.2997, pruned_loss=0.04372, over 6712.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2651, pruned_loss=0.03326, over 1394941.21 frames.], batch size: 31, lr: 3.01e-04
2022-04-30 01:45:26,282 INFO [train.py:763] (4/8) Epoch 25, batch 850, loss[loss=0.1715, simple_loss=0.2788, pruned_loss=0.03215, over 7109.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2656, pruned_loss=0.03309, over 1406017.71 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:46:33,098 INFO [train.py:763] (4/8) Epoch 25, batch 900, loss[loss=0.1475, simple_loss=0.2314, pruned_loss=0.03178, over 6817.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03344, over 1406538.16 frames.], batch size: 15, lr: 3.01e-04
2022-04-30 01:47:40,153 INFO [train.py:763] (4/8) Epoch 25, batch 950, loss[loss=0.1363, simple_loss=0.2236, pruned_loss=0.02452, over 7285.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2646, pruned_loss=0.03306, over 1413129.31 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:48:46,805 INFO [train.py:763] (4/8) Epoch 25, batch 1000, loss[loss=0.1597, simple_loss=0.2655, pruned_loss=0.02697, over 7111.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2647, pruned_loss=0.0331, over 1412305.39 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:49:52,611 INFO [train.py:763] (4/8) Epoch 25, batch 1050, loss[loss=0.2162, simple_loss=0.3005, pruned_loss=0.06595, over 5187.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03342, over 1413866.44 frames.], batch size: 52, lr: 3.01e-04
2022-04-30 01:50:59,147 INFO [train.py:763] (4/8) Epoch 25, batch 1100, loss[loss=0.1677, simple_loss=0.2745, pruned_loss=0.03043, over 7125.00 frames.], tot_loss[loss=0.1663, simple_loss=0.266, pruned_loss=0.03335, over 1414312.96 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:52:04,511 INFO [train.py:763] (4/8) Epoch 25, batch 1150, loss[loss=0.1949, simple_loss=0.2962, pruned_loss=0.04682, over 7373.00 frames.], tot_loss[loss=0.167, simple_loss=0.2664, pruned_loss=0.03383, over 1418168.98 frames.], batch size: 23, lr: 3.01e-04
2022-04-30 01:53:10,906 INFO [train.py:763] (4/8) Epoch 25, batch 1200, loss[loss=0.1518, simple_loss=0.2352, pruned_loss=0.03422, over 7139.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03379, over 1422716.03 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:54:16,904 INFO [train.py:763] (4/8) Epoch 25, batch 1250, loss[loss=0.1687, simple_loss=0.2704, pruned_loss=0.03353, over 7312.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03367, over 1424783.10 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:55:23,798 INFO [train.py:763] (4/8) Epoch 25, batch 1300, loss[loss=0.1524, simple_loss=0.2491, pruned_loss=0.02781, over 7422.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03372, over 1427994.63 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:56:30,373 INFO [train.py:763] (4/8) Epoch 25, batch 1350, loss[loss=0.1649, simple_loss=0.2743, pruned_loss=0.0277, over 7316.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2661, pruned_loss=0.03401, over 1427870.30 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:57:36,862 INFO [train.py:763] (4/8) Epoch 25, batch 1400, loss[loss=0.1815, simple_loss=0.2807, pruned_loss=0.04117, over 7330.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2668, pruned_loss=0.03441, over 1428756.55 frames.], batch size: 22, lr: 3.01e-04
2022-04-30 01:58:42,268 INFO [train.py:763] (4/8) Epoch 25, batch 1450, loss[loss=0.1531, simple_loss=0.2465, pruned_loss=0.02986, over 6981.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2669, pruned_loss=0.03448, over 1430086.42 frames.], batch size: 16, lr: 3.01e-04
2022-04-30 01:59:49,359 INFO [train.py:763] (4/8) Epoch 25, batch 1500, loss[loss=0.1704, simple_loss=0.2697, pruned_loss=0.0355, over 7214.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.03425, over 1428156.38 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:00:55,045 INFO [train.py:763] (4/8) Epoch 25, batch 1550, loss[loss=0.1354, simple_loss=0.2283, pruned_loss=0.02128, over 7118.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03439, over 1427185.14 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:02:00,071 INFO [train.py:763] (4/8) Epoch 25, batch 1600, loss[loss=0.1722, simple_loss=0.2784, pruned_loss=0.033, over 7133.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2668, pruned_loss=0.03429, over 1424080.83 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:03:05,632 INFO [train.py:763] (4/8) Epoch 25, batch 1650, loss[loss=0.1728, simple_loss=0.2688, pruned_loss=0.03846, over 7050.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2645, pruned_loss=0.03318, over 1425475.48 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:04:10,608 INFO [train.py:763] (4/8) Epoch 25, batch 1700, loss[loss=0.1785, simple_loss=0.2792, pruned_loss=0.03893, over 7329.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03314, over 1425639.82 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:05:15,839 INFO [train.py:763] (4/8) Epoch 25, batch 1750, loss[loss=0.1338, simple_loss=0.2261, pruned_loss=0.0207, over 7144.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2651, pruned_loss=0.03281, over 1424760.09 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:06:21,039 INFO [train.py:763] (4/8) Epoch 25, batch 1800, loss[loss=0.1572, simple_loss=0.264, pruned_loss=0.02517, over 7149.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03279, over 1421667.40 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:07:26,299 INFO [train.py:763] (4/8) Epoch 25, batch 1850, loss[loss=0.1575, simple_loss=0.2616, pruned_loss=0.02665, over 7427.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03296, over 1422572.06 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:08:31,444 INFO [train.py:763] (4/8) Epoch 25, batch 1900, loss[loss=0.166, simple_loss=0.2554, pruned_loss=0.03828, over 7135.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.03302, over 1423538.44 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:09:36,776 INFO [train.py:763] (4/8) Epoch 25, batch 1950, loss[loss=0.2345, simple_loss=0.312, pruned_loss=0.07849, over 4972.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03367, over 1421382.56 frames.], batch size: 52, lr: 3.00e-04
2022-04-30 02:10:42,027 INFO [train.py:763] (4/8) Epoch 25, batch 2000, loss[loss=0.1598, simple_loss=0.2579, pruned_loss=0.03081, over 7157.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2659, pruned_loss=0.03357, over 1417543.46 frames.], batch size: 19, lr: 3.00e-04
2022-04-30 02:11:47,908 INFO [train.py:763] (4/8) Epoch 25, batch 2050, loss[loss=0.1715, simple_loss=0.2814, pruned_loss=0.03078, over 7318.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.03341, over 1419140.71 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:12:54,271 INFO [train.py:763] (4/8) Epoch 25, batch 2100, loss[loss=0.1736, simple_loss=0.2696, pruned_loss=0.03886, over 7214.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2664, pruned_loss=0.03402, over 1418371.00 frames.], batch size: 22, lr: 3.00e-04
2022-04-30 02:13:59,521 INFO [train.py:763] (4/8) Epoch 25, batch 2150, loss[loss=0.1551, simple_loss=0.2436, pruned_loss=0.03329, over 7163.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2674, pruned_loss=0.03422, over 1420600.09 frames.], batch size: 18, lr: 3.00e-04
2022-04-30 02:15:05,482 INFO [train.py:763] (4/8) Epoch 25, batch 2200, loss[loss=0.1939, simple_loss=0.292, pruned_loss=0.04793, over 7077.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2671, pruned_loss=0.03401, over 1422691.06 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:16:11,383 INFO [train.py:763] (4/8) Epoch 25, batch 2250, loss[loss=0.1718, simple_loss=0.2647, pruned_loss=0.03938, over 7377.00 frames.], tot_loss[loss=0.1668, simple_loss=0.266, pruned_loss=0.03382, over 1424595.72 frames.], batch size: 23, lr: 3.00e-04
2022-04-30 02:17:16,592 INFO [train.py:763] (4/8) Epoch 25, batch 2300, loss[loss=0.1441, simple_loss=0.2421, pruned_loss=0.02302, over 7065.00 frames.], tot_loss[loss=0.167, simple_loss=0.2665, pruned_loss=0.03369, over 1424713.67 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:18:23,380 INFO [train.py:763] (4/8) Epoch 25, batch 2350, loss[loss=0.1507, simple_loss=0.251, pruned_loss=0.02519, over 7252.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03336, over 1425148.72 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:19:30,573 INFO [train.py:763] (4/8) Epoch 25, batch 2400, loss[loss=0.1848, simple_loss=0.2954, pruned_loss=0.0371, over 7387.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03327, over 1422665.92 frames.], batch size: 23, lr: 2.99e-04
2022-04-30 02:20:35,957 INFO [train.py:763] (4/8) Epoch 25, batch 2450, loss[loss=0.1587, simple_loss=0.2633, pruned_loss=0.02703, over 6790.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03336, over 1420620.22 frames.], batch size: 31, lr: 2.99e-04
2022-04-30 02:21:42,821 INFO [train.py:763] (4/8) Epoch 25, batch 2500, loss[loss=0.167, simple_loss=0.2775, pruned_loss=0.02828, over 7362.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2641, pruned_loss=0.03311, over 1421810.90 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:22:48,784 INFO [train.py:763] (4/8) Epoch 25, batch 2550, loss[loss=0.1428, simple_loss=0.2411, pruned_loss=0.02222, over 7413.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2649, pruned_loss=0.03333, over 1424769.80 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:23:56,376 INFO [train.py:763] (4/8) Epoch 25, batch 2600, loss[loss=0.1654, simple_loss=0.2706, pruned_loss=0.03016, over 7159.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03353, over 1422876.99 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:25:02,539 INFO [train.py:763] (4/8) Epoch 25, batch 2650, loss[loss=0.193, simple_loss=0.2963, pruned_loss=0.04486, over 7107.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2655, pruned_loss=0.03332, over 1419284.59 frames.], batch size: 28, lr: 2.99e-04
2022-04-30 02:26:07,755 INFO [train.py:763] (4/8) Epoch 25, batch 2700, loss[loss=0.1476, simple_loss=0.244, pruned_loss=0.02561, over 7261.00 frames.], tot_loss[loss=0.1655, simple_loss=0.265, pruned_loss=0.033, over 1419946.07 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:27:12,938 INFO [train.py:763] (4/8) Epoch 25, batch 2750, loss[loss=0.2107, simple_loss=0.2985, pruned_loss=0.06148, over 7277.00 frames.], tot_loss[loss=0.167, simple_loss=0.2661, pruned_loss=0.03397, over 1412986.25 frames.], batch size: 25, lr: 2.99e-04
2022-04-30 02:28:19,372 INFO [train.py:763] (4/8) Epoch 25, batch 2800, loss[loss=0.1519, simple_loss=0.2501, pruned_loss=0.0269, over 7265.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2649, pruned_loss=0.03341, over 1415600.40 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:29:24,928 INFO [train.py:763] (4/8) Epoch 25, batch 2850, loss[loss=0.1631, simple_loss=0.2679, pruned_loss=0.02916, over 7416.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.0328, over 1410600.29 frames.], batch size: 21, lr: 2.99e-04
2022-04-30 02:30:30,619 INFO [train.py:763] (4/8) Epoch 25, batch 2900, loss[loss=0.1725, simple_loss=0.2819, pruned_loss=0.03161, over 7145.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03265, over 1416953.03 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:31:35,882 INFO [train.py:763] (4/8) Epoch 25, batch 2950, loss[loss=0.1708, simple_loss=0.2723, pruned_loss=0.03462, over 7328.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2653, pruned_loss=0.03283, over 1417628.81 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:32:41,159 INFO [train.py:763] (4/8) Epoch 25, batch 3000, loss[loss=0.1473, simple_loss=0.2466, pruned_loss=0.02401, over 6474.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2652, pruned_loss=0.0326, over 1421992.01 frames.], batch size: 38, lr: 2.99e-04
2022-04-30 02:32:41,160 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 02:32:56,272 INFO [train.py:792] (4/8) Epoch 25, validation: loss=0.1697, simple_loss=0.2684, pruned_loss=0.03548, over 698248.00 frames.
2022-04-30 02:34:02,072 INFO [train.py:763] (4/8) Epoch 25, batch 3050, loss[loss=0.1445, simple_loss=0.2548, pruned_loss=0.01709, over 7343.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2661, pruned_loss=0.03267, over 1421804.94 frames.], batch size: 22, lr: 2.99e-04
2022-04-30 02:35:09,273 INFO [train.py:763] (4/8) Epoch 25, batch 3100, loss[loss=0.1454, simple_loss=0.2534, pruned_loss=0.01871, over 7251.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2657, pruned_loss=0.03275, over 1418672.03 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:36:16,360 INFO [train.py:763] (4/8) Epoch 25, batch 3150, loss[loss=0.1507, simple_loss=0.2442, pruned_loss=0.02864, over 7131.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2654, pruned_loss=0.03302, over 1417896.39 frames.], batch size: 17, lr: 2.98e-04
2022-04-30 02:37:22,256 INFO [train.py:763] (4/8) Epoch 25, batch 3200, loss[loss=0.1528, simple_loss=0.2537, pruned_loss=0.02598, over 7150.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2654, pruned_loss=0.03305, over 1421173.57 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:38:29,211 INFO [train.py:763] (4/8) Epoch 25, batch 3250, loss[loss=0.1586, simple_loss=0.247, pruned_loss=0.03515, over 7276.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03259, over 1424395.31 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:39:35,756 INFO [train.py:763] (4/8) Epoch 25, batch 3300, loss[loss=0.1779, simple_loss=0.2872, pruned_loss=0.03431, over 7157.00 frames.], tot_loss[loss=0.1656, simple_loss=0.265, pruned_loss=0.03309, over 1417668.94 frames.], batch size: 26, lr: 2.98e-04
2022-04-30 02:40:42,705 INFO [train.py:763] (4/8) Epoch 25, batch 3350, loss[loss=0.1961, simple_loss=0.2913, pruned_loss=0.0505, over 7309.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2659, pruned_loss=0.0335, over 1413971.96 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:41:49,870 INFO [train.py:763] (4/8) Epoch 25, batch 3400, loss[loss=0.1714, simple_loss=0.2701, pruned_loss=0.0363, over 6407.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03294, over 1418817.48 frames.], batch size: 38, lr: 2.98e-04
2022-04-30 02:42:55,392 INFO [train.py:763] (4/8) Epoch 25, batch 3450, loss[loss=0.1786, simple_loss=0.2669, pruned_loss=0.04517, over 7162.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03333, over 1418674.11 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:44:00,602 INFO [train.py:763] (4/8) Epoch 25, batch 3500, loss[loss=0.1824, simple_loss=0.2821, pruned_loss=0.04141, over 7378.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2657, pruned_loss=0.03386, over 1417308.02 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:45:06,555 INFO [train.py:763] (4/8) Epoch 25, batch 3550, loss[loss=0.1578, simple_loss=0.2659, pruned_loss=0.02489, over 7405.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03339, over 1420223.56 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:46:12,315 INFO [train.py:763] (4/8) Epoch 25, batch 3600, loss[loss=0.1908, simple_loss=0.2893, pruned_loss=0.04616, over 7199.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03385, over 1425375.12 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:47:18,086 INFO [train.py:763] (4/8) Epoch 25, batch 3650, loss[loss=0.1486, simple_loss=0.2459, pruned_loss=0.02561, over 7263.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2657, pruned_loss=0.034, over 1427155.21 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:48:25,753 INFO [train.py:763] (4/8) Epoch 25, batch 3700, loss[loss=0.1742, simple_loss=0.2652, pruned_loss=0.04164, over 7061.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03397, over 1424644.90 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:49:32,856 INFO [train.py:763] (4/8) Epoch 25, batch 3750, loss[loss=0.1571, simple_loss=0.2529, pruned_loss=0.03059, over 7158.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03374, over 1423072.53 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:50:38,245 INFO [train.py:763] (4/8) Epoch 25, batch 3800, loss[loss=0.1566, simple_loss=0.2578, pruned_loss=0.02768, over 6460.00 frames.], tot_loss[loss=0.166, simple_loss=0.2649, pruned_loss=0.03355, over 1420388.83 frames.], batch size: 38, lr: 2.98e-04
2022-04-30 02:51:43,562 INFO [train.py:763] (4/8) Epoch 25, batch 3850, loss[loss=0.1724, simple_loss=0.2741, pruned_loss=0.03535, over 7141.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2653, pruned_loss=0.03384, over 1418364.83 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:52:57,809 INFO [train.py:763] (4/8) Epoch 25, batch 3900, loss[loss=0.1661, simple_loss=0.2612, pruned_loss=0.03556, over 7407.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2662, pruned_loss=0.03398, over 1420600.05 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 02:54:03,673 INFO [train.py:763] (4/8) Epoch 25, batch 3950, loss[loss=0.1584, simple_loss=0.2664, pruned_loss=0.02518, over 7237.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03366, over 1425493.11 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:55:09,637 INFO [train.py:763] (4/8) Epoch 25, batch 4000, loss[loss=0.151, simple_loss=0.2509, pruned_loss=0.02552, over 7430.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2642, pruned_loss=0.03339, over 1418664.54 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:56:14,885 INFO [train.py:763] (4/8) Epoch 25, batch 4050, loss[loss=0.1573, simple_loss=0.27, pruned_loss=0.02234, over 7400.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03336, over 1420163.75 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:57:21,066 INFO [train.py:763] (4/8) Epoch 25, batch 4100, loss[loss=0.1735, simple_loss=0.2663, pruned_loss=0.0403, over 7417.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2651, pruned_loss=0.03392, over 1417679.07 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:58:26,414 INFO [train.py:763] (4/8) Epoch 25, batch 4150, loss[loss=0.1598, simple_loss=0.263, pruned_loss=0.02833, over 7255.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2644, pruned_loss=0.03337, over 1422760.87 frames.], batch size: 19, lr: 2.97e-04
2022-04-30 02:59:32,217 INFO [train.py:763] (4/8) Epoch 25, batch 4200, loss[loss=0.1774, simple_loss=0.2826, pruned_loss=0.03608, over 7041.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03347, over 1418869.14 frames.], batch size: 28, lr: 2.97e-04
2022-04-30 03:00:37,738 INFO [train.py:763] (4/8) Epoch 25, batch 4250, loss[loss=0.1569, simple_loss=0.2471, pruned_loss=0.03335, over 7157.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.0335, over 1418393.75 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:01:43,167 INFO [train.py:763] (4/8) Epoch 25, batch 4300, loss[loss=0.2098, simple_loss=0.3157, pruned_loss=0.05197, over 7163.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2653, pruned_loss=0.0338, over 1422355.69 frames.], batch size: 26, lr: 2.97e-04
2022-04-30 03:03:06,201 INFO [train.py:763] (4/8) Epoch 25, batch 4350, loss[loss=0.1527, simple_loss=0.2526, pruned_loss=0.0264, over 7245.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2658, pruned_loss=0.03422, over 1415550.84 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:04:20,103 INFO [train.py:763] (4/8) Epoch 25, batch 4400, loss[loss=0.1437, simple_loss=0.2296, pruned_loss=0.02893, over 7061.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.03408, over 1416050.32 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:05:34,207 INFO [train.py:763] (4/8) Epoch 25, batch 4450, loss[loss=0.1729, simple_loss=0.271, pruned_loss=0.03739, over 7314.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.0338, over 1414868.07 frames.], batch size: 24, lr: 2.97e-04
2022-04-30 03:06:39,191 INFO [train.py:763] (4/8) Epoch 25, batch 4500, loss[loss=0.156, simple_loss=0.2504, pruned_loss=0.03082, over 7321.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2658, pruned_loss=0.03393, over 1398624.87 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:08:11,348 INFO [train.py:763] (4/8) Epoch 25, batch 4550, loss[loss=0.1942, simple_loss=0.2854, pruned_loss=0.05155, over 5126.00 frames.], tot_loss[loss=0.168, simple_loss=0.2668, pruned_loss=0.03457, over 1388352.60 frames.], batch size: 53, lr: 2.97e-04
2022-04-30 03:09:39,541 INFO [train.py:763] (4/8) Epoch 26, batch 0, loss[loss=0.1803, simple_loss=0.2749, pruned_loss=0.04278, over 7169.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2749, pruned_loss=0.04278, over 7169.00 frames.], batch size: 18, lr: 2.91e-04
2022-04-30 03:10:45,447 INFO [train.py:763] (4/8) Epoch 26, batch 50, loss[loss=0.1277, simple_loss=0.2159, pruned_loss=0.01974, over 7279.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2631, pruned_loss=0.03354, over 319095.51 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:11:50,709 INFO [train.py:763] (4/8) Epoch 26, batch 100, loss[loss=0.1355, simple_loss=0.2249, pruned_loss=0.02303, over 7280.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03177, over 562074.72 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:12:56,048 INFO [train.py:763] (4/8) Epoch 26, batch 150, loss[loss=0.155, simple_loss=0.2608, pruned_loss=0.02461, over 6317.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03219, over 750393.47 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:14:01,245 INFO [train.py:763] (4/8) Epoch 26, batch 200, loss[loss=0.1608, simple_loss=0.2642, pruned_loss=0.02868, over 7137.00 frames.], tot_loss[loss=0.1649, simple_loss=0.264, pruned_loss=0.03289, over 893659.22 frames.], batch size: 26, lr: 2.91e-04
2022-04-30 03:15:07,039 INFO [train.py:763] (4/8) Epoch 26, batch 250, loss[loss=0.167, simple_loss=0.2696, pruned_loss=0.03221, over 6623.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2657, pruned_loss=0.03355, over 1005362.79 frames.], batch size: 38, lr: 2.91e-04
2022-04-30 03:16:13,119 INFO [train.py:763] (4/8) Epoch 26, batch 300, loss[loss=0.164, simple_loss=0.2667, pruned_loss=0.03063, over 6441.00 frames.], tot_loss[loss=0.166, simple_loss=0.2658, pruned_loss=0.03314, over 1099965.80 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:17:18,444 INFO [train.py:763] (4/8) Epoch 26, batch 350, loss[loss=0.1629, simple_loss=0.2743, pruned_loss=0.02577, over 6654.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2641, pruned_loss=0.03284, over 1167534.73 frames.], batch size: 31, lr: 2.91e-04
2022-04-30 03:18:23,746 INFO [train.py:763] (4/8) Epoch 26, batch 400, loss[loss=0.1576, simple_loss=0.2647, pruned_loss=0.02521, over 7141.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03298, over 1227671.16 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:19:29,468 INFO [train.py:763] (4/8) Epoch 26, batch 450, loss[loss=0.1497, simple_loss=0.25, pruned_loss=0.02472, over 7232.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03302, over 1275298.22 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:20:34,843 INFO [train.py:763] (4/8) Epoch 26, batch 500, loss[loss=0.2191, simple_loss=0.314, pruned_loss=0.06209, over 4892.00 frames.], tot_loss[loss=0.165, simple_loss=0.2644, pruned_loss=0.03279, over 1307089.22 frames.], batch size: 52, lr: 2.91e-04
2022-04-30 03:21:40,166 INFO [train.py:763] (4/8) Epoch 26, batch 550, loss[loss=0.1771, simple_loss=0.2761, pruned_loss=0.03907, over 7199.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03287, over 1332300.81 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:22:45,576 INFO [train.py:763] (4/8) Epoch 26, batch 600, loss[loss=0.1488, simple_loss=0.2423, pruned_loss=0.02764, over 7250.00 frames.], tot_loss[loss=0.166, simple_loss=0.2656, pruned_loss=0.03319, over 1355362.59 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:23:51,102 INFO [train.py:763] (4/8) Epoch 26, batch 650, loss[loss=0.1547, simple_loss=0.238, pruned_loss=0.03566, over 7278.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.03305, over 1372433.52 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:24:56,237 INFO [train.py:763] (4/8) Epoch 26, batch 700, loss[loss=0.2026, simple_loss=0.3006, pruned_loss=0.05227, over 7117.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03309, over 1381353.62 frames.], batch size: 21, lr: 2.90e-04
2022-04-30 03:26:12,123 INFO [train.py:763] (4/8) Epoch 26, batch 750, loss[loss=0.173, simple_loss=0.2735, pruned_loss=0.03626, over 7144.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03267, over 1390285.91 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:27:17,950 INFO [train.py:763] (4/8) Epoch 26, batch 800, loss[loss=0.143, simple_loss=0.2352, pruned_loss=0.0254, over 7232.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03287, over 1396086.73 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:28:23,822 INFO [train.py:763] (4/8) Epoch 26, batch 850, loss[loss=0.1899, simple_loss=0.2846, pruned_loss=0.04763, over 5233.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2664, pruned_loss=0.0334, over 1398715.23 frames.], batch size: 52, lr: 2.90e-04
2022-04-30 03:29:29,376 INFO [train.py:763] (4/8) Epoch 26, batch 900, loss[loss=0.1488, simple_loss=0.239, pruned_loss=0.02936, over 7405.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03299, over 1408238.06 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:30:35,249 INFO [train.py:763] (4/8) Epoch 26, batch 950, loss[loss=0.1511, simple_loss=0.247, pruned_loss=0.02758, over 6835.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2648, pruned_loss=0.03268, over 1409274.05 frames.], batch size: 15, lr: 2.90e-04
2022-04-30 03:31:40,714 INFO [train.py:763] (4/8) Epoch 26, batch 1000, loss[loss=0.166, simple_loss=0.2733, pruned_loss=0.0293, over 7297.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2655, pruned_loss=0.03307, over 1412789.86 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:32:46,142 INFO [train.py:763] (4/8) Epoch 26, batch 1050, loss[loss=0.1756, simple_loss=0.2798, pruned_loss=0.03568, over 7210.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2657, pruned_loss=0.03321, over 1418044.95 frames.], batch size: 23, lr: 2.90e-04
2022-04-30 03:33:51,496 INFO [train.py:763] (4/8) Epoch 26, batch 1100, loss[loss=0.1842, simple_loss=0.2686, pruned_loss=0.04986, over 7197.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2646, pruned_loss=0.03266, over 1421690.14 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:34:56,892 INFO [train.py:763] (4/8) Epoch 26, batch 1150, loss[loss=0.1393, simple_loss=0.2291, pruned_loss=0.02475, over 7159.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2648, pruned_loss=0.03288, over 1423590.98 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:36:02,471 INFO [train.py:763] (4/8) Epoch 26, batch 1200, loss[loss=0.1799, simple_loss=0.2812, pruned_loss=0.03926, over 7277.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.03277, over 1427318.40 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:37:08,325 INFO [train.py:763] (4/8) Epoch 26, batch 1250, loss[loss=0.1697, simple_loss=0.2745, pruned_loss=0.03245, over 6556.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03257, over 1427887.29 frames.], batch size: 38, lr: 2.90e-04
2022-04-30 03:38:14,024 INFO [train.py:763] (4/8) Epoch 26, batch 1300, loss[loss=0.1334, simple_loss=0.2343, pruned_loss=0.01623, over 7272.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2639, pruned_loss=0.03283, over 1424383.87 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:39:20,365 INFO [train.py:763] (4/8) Epoch 26, batch 1350, loss[loss=0.1585, simple_loss=0.2425, pruned_loss=0.03721, over 7416.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2628, pruned_loss=0.03252, over 1427408.95 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:40:25,488 INFO [train.py:763] (4/8) Epoch 26, batch 1400, loss[loss=0.1737, simple_loss=0.2654, pruned_loss=0.04101, over 7189.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2622, pruned_loss=0.03222, over 1419380.58 frames.], batch size: 23, lr: 2.89e-04
2022-04-30 03:41:30,973 INFO [train.py:763] (4/8) Epoch 26, batch 1450, loss[loss=0.1525, simple_loss=0.2473, pruned_loss=0.02888, over 7276.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.03262, over 1420931.90 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:42:36,426 INFO [train.py:763] (4/8) Epoch 26, batch 1500, loss[loss=0.1714, simple_loss=0.2657, pruned_loss=0.0385, over 5008.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03237, over 1417046.25 frames.], batch size: 52, lr: 2.89e-04
2022-04-30 03:43:42,570 INFO [train.py:763] (4/8) Epoch 26, batch 1550, loss[loss=0.1533, simple_loss=0.269, pruned_loss=0.01881, over 7119.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03209, over 1420229.76 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:44:49,278 INFO [train.py:763] (4/8) Epoch 26, batch 1600, loss[loss=0.1458, simple_loss=0.2462, pruned_loss=0.02264, over 7261.00 frames.], tot_loss[loss=0.163, simple_loss=0.2621, pruned_loss=0.03196, over 1423711.53 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:45:54,874 INFO [train.py:763] (4/8) Epoch 26, batch 1650, loss[loss=0.1596, simple_loss=0.2714, pruned_loss=0.02392, over 7207.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03182, over 1427505.60 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:47:00,373 INFO [train.py:763] (4/8) Epoch 26, batch 1700, loss[loss=0.1528, simple_loss=0.2585, pruned_loss=0.02359, over 7328.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03178, over 1429114.56 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:48:06,016 INFO [train.py:763] (4/8) Epoch 26, batch 1750, loss[loss=0.1915, simple_loss=0.2911, pruned_loss=0.04597, over 7113.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2632, pruned_loss=0.03225, over 1429731.37 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:49:13,271 INFO [train.py:763] (4/8) Epoch 26, batch 1800, loss[loss=0.154, simple_loss=0.256, pruned_loss=0.02606, over 7120.00 frames.], tot_loss[loss=0.164, simple_loss=0.263, pruned_loss=0.03244, over 1427058.65 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:50:19,933 INFO [train.py:763] (4/8) Epoch 26, batch 1850, loss[loss=0.2189, simple_loss=0.3029, pruned_loss=0.06747, over 4791.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03268, over 1427370.32 frames.], batch size: 53, lr: 2.89e-04
2022-04-30 03:51:25,626 INFO [train.py:763] (4/8) Epoch 26, batch 1900, loss[loss=0.1526, simple_loss=0.2531, pruned_loss=0.02605, over 7362.00 frames.], tot_loss[loss=0.164, simple_loss=0.2625, pruned_loss=0.03276, over 1426342.74 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:52:30,899 INFO [train.py:763] (4/8) Epoch 26, batch 1950, loss[loss=0.1699, simple_loss=0.2717, pruned_loss=0.0341, over 6546.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2631, pruned_loss=0.03277, over 1423702.17 frames.], batch size: 37, lr: 2.89e-04
2022-04-30 03:53:36,218 INFO [train.py:763] (4/8) Epoch 26, batch 2000, loss[loss=0.162, simple_loss=0.2695, pruned_loss=0.02731, over 6690.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2622, pruned_loss=0.03252, over 1422342.53 frames.], batch size: 31, lr: 2.89e-04
2022-04-30 03:54:41,494 INFO [train.py:763] (4/8) Epoch 26, batch 2050, loss[loss=0.1809, simple_loss=0.2771, pruned_loss=0.04233, over 7165.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2638, pruned_loss=0.03291, over 1425840.93 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:55:48,141 INFO [train.py:763] (4/8) Epoch 26, batch 2100, loss[loss=0.187, simple_loss=0.2936, pruned_loss=0.04023, over 7211.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2635, pruned_loss=0.03273, over 1423716.75 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:56:54,313 INFO [train.py:763] (4/8) Epoch 26, batch 2150, loss[loss=0.164, simple_loss=0.2622, pruned_loss=0.03293, over 7333.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2645, pruned_loss=0.03298, over 1427079.06 frames.], batch size: 25, lr: 2.89e-04
2022-04-30 03:57:59,844 INFO [train.py:763] (4/8) Epoch 26, batch 2200, loss[loss=0.177, simple_loss=0.2775, pruned_loss=0.03831, over 7231.00 frames.], tot_loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03287, over 1425359.49 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 03:59:06,001 INFO [train.py:763] (4/8) Epoch 26, batch 2250, loss[loss=0.1465, simple_loss=0.2429, pruned_loss=0.02502, over 7430.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2645, pruned_loss=0.03325, over 1430970.16 frames.], batch size: 17, lr: 2.88e-04
2022-04-30 04:00:11,169 INFO [train.py:763] (4/8) Epoch 26, batch 2300, loss[loss=0.1716, simple_loss=0.2631, pruned_loss=0.04005, over 7137.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03334, over 1432471.51 frames.], batch size: 17, lr: 2.88e-04
2022-04-30 04:01:17,208 INFO [train.py:763] (4/8) Epoch 26, batch 2350, loss[loss=0.1475, simple_loss=0.2537, pruned_loss=0.02062, over 7156.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03368, over 1430741.40 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:02:24,606 INFO [train.py:763] (4/8) Epoch 26, batch 2400, loss[loss=0.1933, simple_loss=0.2901, pruned_loss=0.04821, over 7293.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.0343, over 1431970.19 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:03:31,273 INFO [train.py:763] (4/8) Epoch 26, batch 2450, loss[loss=0.1755, simple_loss=0.2815, pruned_loss=0.03469, over 7238.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03377, over 1435537.97 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:04:36,617 INFO [train.py:763] (4/8) Epoch 26, batch 2500, loss[loss=0.1767, simple_loss=0.2837, pruned_loss=0.03483, over 7224.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.0338, over 1437246.84 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:05:41,761 INFO [train.py:763] (4/8) Epoch 26, batch 2550, loss[loss=0.1685, simple_loss=0.278, pruned_loss=0.02953, over 6838.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2652, pruned_loss=0.03328, over 1434178.21 frames.], batch size: 31, lr: 2.88e-04
2022-04-30 04:06:47,198 INFO [train.py:763] (4/8) Epoch 26, batch 2600, loss[loss=0.1372, simple_loss=0.2254, pruned_loss=0.02454, over 6819.00 frames.], tot_loss[loss=0.166, simple_loss=0.2653, pruned_loss=0.03338, over 1434282.55 frames.], batch size: 15, lr: 2.88e-04
2022-04-30 04:07:52,614 INFO [train.py:763] (4/8) Epoch 26, batch 2650, loss[loss=0.1839, simple_loss=0.2928, pruned_loss=0.03746, over 7279.00 frames.], tot_loss[loss=0.166, simple_loss=0.2654, pruned_loss=0.03324, over 1430845.07 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:08:58,039 INFO [train.py:763] (4/8) Epoch 26, batch 2700, loss[loss=0.1543, simple_loss=0.2664, pruned_loss=0.02106, over 7344.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2661, pruned_loss=0.0335, over 1428605.03 frames.], batch size: 22, lr: 2.88e-04
2022-04-30 04:10:03,922 INFO [train.py:763] (4/8) Epoch 26, batch 2750, loss[loss=0.1661, simple_loss=0.2661, pruned_loss=0.03308, over 7165.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2652, pruned_loss=0.03293, over 1427752.70 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:11:09,743 INFO [train.py:763] (4/8) Epoch 26, batch 2800, loss[loss=0.1696, simple_loss=0.268, pruned_loss=0.03561, over 7302.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2649, pruned_loss=0.03298, over 1427546.40 frames.], batch size: 25, lr: 2.88e-04
2022-04-30 04:12:16,484 INFO [train.py:763] (4/8) Epoch 26, batch 2850, loss[loss=0.1532, simple_loss=0.2566, pruned_loss=0.02485, over 7257.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2649, pruned_loss=0.03278, over 1426387.53 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:13:21,767 INFO [train.py:763] (4/8) Epoch 26, batch 2900, loss[loss=0.1488, simple_loss=0.242, pruned_loss=0.0278, over 7162.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03296, over 1425700.66 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:14:26,916 INFO [train.py:763] (4/8) Epoch 26, batch 2950, loss[loss=0.1818, simple_loss=0.278, pruned_loss=0.04278, over 7114.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.03301, over 1419691.69 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,482 INFO [train.py:763] (4/8) Epoch 26, batch 3000, loss[loss=0.1745, simple_loss=0.2811, pruned_loss=0.03398, over 7410.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2649, pruned_loss=0.03283, over 1419697.19 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,483 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 04:15:47,843 INFO [train.py:792] (4/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
2022-04-30 04:16:54,019 INFO [train.py:763] (4/8) Epoch 26, batch 3050, loss[loss=0.1836, simple_loss=0.2936, pruned_loss=0.03682, over 7109.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2642, pruned_loss=0.03296, over 1411680.95 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:17:59,869 INFO [train.py:763] (4/8) Epoch 26, batch 3100, loss[loss=0.1525, simple_loss=0.254, pruned_loss=0.0255, over 7313.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2655, pruned_loss=0.03343, over 1417704.40 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:19:05,970 INFO [train.py:763] (4/8) Epoch 26, batch 3150, loss[loss=0.1799, simple_loss=0.2737, pruned_loss=0.04303, over 7208.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03367, over 1417672.80 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:20:11,637 INFO [train.py:763] (4/8) Epoch 26, batch 3200, loss[loss=0.1838, simple_loss=0.286, pruned_loss=0.04083, over 7206.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2656, pruned_loss=0.03359, over 1420638.32 frames.], batch size: 23, lr: 2.87e-04
2022-04-30 04:21:17,156 INFO [train.py:763] (4/8) Epoch 26, batch 3250, loss[loss=0.171, simple_loss=0.2795, pruned_loss=0.0313, over 6515.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03366, over 1421405.60 frames.], batch size: 38, lr: 2.87e-04
2022-04-30 04:22:22,720 INFO [train.py:763] (4/8) Epoch 26, batch 3300, loss[loss=0.1532, simple_loss=0.2585, pruned_loss=0.02395, over 6814.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03386, over 1420618.12 frames.], batch size: 31, lr: 2.87e-04
2022-04-30 04:23:27,751 INFO [train.py:763] (4/8) Epoch 26, batch 3350, loss[loss=0.1631, simple_loss=0.2738, pruned_loss=0.02619, over 7331.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2672, pruned_loss=0.03388, over 1421070.46 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:24:33,264 INFO [train.py:763] (4/8) Epoch 26, batch 3400, loss[loss=0.157, simple_loss=0.271, pruned_loss=0.02147, over 7147.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2667, pruned_loss=0.03353, over 1418355.60 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:25:38,624 INFO [train.py:763] (4/8) Epoch 26, batch 3450, loss[loss=0.1617, simple_loss=0.2624, pruned_loss=0.03046, over 7338.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2669, pruned_loss=0.0333, over 1421367.36 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:26:44,096 INFO [train.py:763] (4/8) Epoch 26, batch 3500, loss[loss=0.1397, simple_loss=0.231, pruned_loss=0.02414, over 6779.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2662, pruned_loss=0.03331, over 1423478.10 frames.], batch size: 15, lr: 2.87e-04
2022-04-30 04:27:49,683 INFO [train.py:763] (4/8) Epoch 26, batch 3550, loss[loss=0.1736, simple_loss=0.2663, pruned_loss=0.04043, over 5118.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2657, pruned_loss=0.03323, over 1416902.05 frames.], batch size: 52, lr: 2.87e-04
2022-04-30 04:28:54,782 INFO [train.py:763] (4/8) Epoch 26, batch 3600, loss[loss=0.1538, simple_loss=0.2564, pruned_loss=0.0256, over 7150.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2663, pruned_loss=0.0333, over 1414182.25 frames.], batch size: 19, lr: 2.87e-04
2022-04-30 04:30:00,884 INFO [train.py:763] (4/8) Epoch 26, batch 3650, loss[loss=0.1468, simple_loss=0.2381, pruned_loss=0.02775, over 7061.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2662, pruned_loss=0.03339, over 1413725.68 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:31:07,243 INFO [train.py:763] (4/8) Epoch 26, batch 3700, loss[loss=0.1553, simple_loss=0.2446, pruned_loss=0.03298, over 7293.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03304, over 1413037.73 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:32:12,925 INFO [train.py:763] (4/8) Epoch 26, batch 3750, loss[loss=0.1677, simple_loss=0.2778, pruned_loss=0.02877, over 7224.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2639, pruned_loss=0.03276, over 1416691.97 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:33:19,994 INFO [train.py:763] (4/8) Epoch 26, batch 3800, loss[loss=0.1452, simple_loss=0.2468, pruned_loss=0.02179, over 7328.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2627, pruned_loss=0.03247, over 1420875.97 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:34:26,370 INFO [train.py:763] (4/8) Epoch 26, batch 3850, loss[loss=0.145, simple_loss=0.2411, pruned_loss=0.02449, over 7426.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03333, over 1413623.94 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:35:31,741 INFO [train.py:763] (4/8) Epoch 26, batch 3900, loss[loss=0.1777, simple_loss=0.2826, pruned_loss=0.03637, over 7027.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03338, over 1414799.55 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:36:37,005 INFO [train.py:763] (4/8) Epoch 26, batch 3950, loss[loss=0.171, simple_loss=0.2759, pruned_loss=0.03303, over 7346.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2644, pruned_loss=0.03293, over 1419206.12 frames.], batch size: 19, lr: 2.86e-04
2022-04-30 04:37:42,771 INFO [train.py:763] (4/8) Epoch 26, batch 4000, loss[loss=0.1638, simple_loss=0.26, pruned_loss=0.03378, over 7122.00 frames.], tot_loss[loss=0.164, simple_loss=0.2629, pruned_loss=0.03257, over 1424342.31 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:38:48,117 INFO [train.py:763] (4/8) Epoch 26, batch 4050, loss[loss=0.1682, simple_loss=0.2671, pruned_loss=0.03466, over 7339.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2636, pruned_loss=0.03261, over 1425356.91 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:39:53,362 INFO [train.py:763] (4/8) Epoch 26, batch 4100, loss[loss=0.1728, simple_loss=0.2721, pruned_loss=0.0367, over 7323.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03225, over 1423401.36 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:40:58,509 INFO [train.py:763] (4/8) Epoch 26, batch 4150, loss[loss=0.1573, simple_loss=0.2584, pruned_loss=0.02807, over 7114.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03226, over 1420772.70 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:42:03,898 INFO [train.py:763] (4/8) Epoch 26, batch 4200, loss[loss=0.1629, simple_loss=0.2724, pruned_loss=0.02669, over 7322.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2635, pruned_loss=0.03266, over 1422020.84 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:43:08,776 INFO [train.py:763] (4/8) Epoch 26, batch 4250, loss[loss=0.1401, simple_loss=0.2482, pruned_loss=0.01599, over 7409.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03292, over 1414883.50 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:44:14,517 INFO [train.py:763] (4/8) Epoch 26, batch 4300, loss[loss=0.1611, simple_loss=0.2646, pruned_loss=0.02875, over 6720.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2654, pruned_loss=0.03325, over 1414051.75 frames.], batch size: 31, lr: 2.86e-04
2022-04-30 04:45:19,673 INFO [train.py:763] (4/8) Epoch 26, batch 4350, loss[loss=0.148, simple_loss=0.237, pruned_loss=0.0295, over 7002.00 frames.], tot_loss[loss=0.165, simple_loss=0.2646, pruned_loss=0.03271, over 1413547.10 frames.], batch size: 16, lr: 2.86e-04
2022-04-30 04:46:24,703 INFO [train.py:763] (4/8) Epoch 26, batch 4400, loss[loss=0.1621, simple_loss=0.2584, pruned_loss=0.03293, over 6304.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2654, pruned_loss=0.0335, over 1400213.17 frames.], batch size: 37, lr: 2.86e-04
2022-04-30 04:47:29,333 INFO [train.py:763] (4/8) Epoch 26, batch 4450, loss[loss=0.173, simple_loss=0.2732, pruned_loss=0.03645, over 7340.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2648, pruned_loss=0.03329, over 1397602.21 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:48:34,526 INFO [train.py:763] (4/8) Epoch 26, batch 4500, loss[loss=0.1651, simple_loss=0.2605, pruned_loss=0.03484, over 7163.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2654, pruned_loss=0.03412, over 1387762.45 frames.], batch size: 18, lr: 2.86e-04
2022-04-30 04:49:39,406 INFO [train.py:763] (4/8) Epoch 26, batch 4550, loss[loss=0.1948, simple_loss=0.2838, pruned_loss=0.05289, over 4754.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2646, pruned_loss=0.03433, over 1369727.33 frames.], batch size: 52, lr: 2.86e-04
2022-04-30 04:51:07,355 INFO [train.py:763] (4/8) Epoch 27, batch 0, loss[loss=0.1578, simple_loss=0.251, pruned_loss=0.03226, over 7260.00 frames.], tot_loss[loss=0.1578, simple_loss=0.251, pruned_loss=0.03226, over 7260.00 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:52:13,082 INFO [train.py:763] (4/8) Epoch 27, batch 50, loss[loss=0.1483, simple_loss=0.2506, pruned_loss=0.02296, over 7252.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2648, pruned_loss=0.0327, over 321685.06 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:53:19,206 INFO [train.py:763] (4/8) Epoch 27, batch 100, loss[loss=0.1723, simple_loss=0.2671, pruned_loss=0.03881, over 7142.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2633, pruned_loss=0.03151, over 565208.32 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 04:54:25,257 INFO [train.py:763] (4/8) Epoch 27, batch 150, loss[loss=0.1549, simple_loss=0.2558, pruned_loss=0.02699, over 6432.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2647, pruned_loss=0.03173, over 753782.76 frames.], batch size: 37, lr: 2.80e-04
2022-04-30 04:55:31,373 INFO [train.py:763] (4/8) Epoch 27, batch 200, loss[loss=0.1744, simple_loss=0.2838, pruned_loss=0.03248, over 7200.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2643, pruned_loss=0.03145, over 900121.44 frames.], batch size: 23, lr: 2.80e-04
2022-04-30 04:56:38,004 INFO [train.py:763] (4/8) Epoch 27, batch 250, loss[loss=0.1843, simple_loss=0.2866, pruned_loss=0.04098, over 7315.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2638, pruned_loss=0.03138, over 1015713.48 frames.], batch size: 24, lr: 2.80e-04
2022-04-30 04:57:44,217 INFO [train.py:763] (4/8) Epoch 27, batch 300, loss[loss=0.1629, simple_loss=0.2559, pruned_loss=0.03492, over 6782.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2641, pruned_loss=0.03154, over 1105210.16 frames.], batch size: 31, lr: 2.80e-04
2022-04-30 04:58:50,090 INFO [train.py:763] (4/8) Epoch 27, batch 350, loss[loss=0.1636, simple_loss=0.2621, pruned_loss=0.0326, over 7157.00 frames.], tot_loss[loss=0.163, simple_loss=0.2632, pruned_loss=0.0314, over 1177704.34 frames.], batch size: 19, lr: 2.80e-04
2022-04-30 04:59:56,367 INFO [train.py:763] (4/8) Epoch 27, batch 400, loss[loss=0.1428, simple_loss=0.2434, pruned_loss=0.02116, over 7133.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03157, over 1234284.87 frames.], batch size: 17, lr: 2.80e-04
2022-04-30 05:01:02,253 INFO [train.py:763] (4/8) Epoch 27, batch 450, loss[loss=0.1614, simple_loss=0.2668, pruned_loss=0.02796, over 7301.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03192, over 1271433.48 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:02:08,164 INFO [train.py:763] (4/8) Epoch 27, batch 500, loss[loss=0.1778, simple_loss=0.2794, pruned_loss=0.03807, over 7308.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03202, over 1308771.09 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:03:14,021 INFO [train.py:763] (4/8) Epoch 27, batch 550, loss[loss=0.1568, simple_loss=0.2542, pruned_loss=0.02972, over 7068.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2633, pruned_loss=0.03214, over 1331262.45 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:04:19,655 INFO [train.py:763] (4/8) Epoch 27, batch 600, loss[loss=0.151, simple_loss=0.2489, pruned_loss=0.02655, over 7338.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2634, pruned_loss=0.03219, over 1349916.80 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 05:05:24,798 INFO [train.py:763] (4/8) Epoch 27, batch 650, loss[loss=0.1773, simple_loss=0.2801, pruned_loss=0.03723, over 7078.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2638, pruned_loss=0.03232, over 1367098.81 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:06:40,258 INFO [train.py:763] (4/8) Epoch 27, batch 700, loss[loss=0.1492, simple_loss=0.2427, pruned_loss=0.02787, over 7069.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03252, over 1380986.31 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:07:46,092 INFO [train.py:763] (4/8) Epoch 27, batch 750, loss[loss=0.1556, simple_loss=0.2691, pruned_loss=0.02106, over 7221.00 frames.], tot_loss[loss=0.1642, simple_loss=0.263, pruned_loss=0.03267, over 1392033.21 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:08:51,493 INFO [train.py:763] (4/8) Epoch 27, batch 800, loss[loss=0.1862, simple_loss=0.2826, pruned_loss=0.04489, over 7129.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2637, pruned_loss=0.03271, over 1398600.07 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:09:56,916 INFO [train.py:763] (4/8) Epoch 27, batch 850, loss[loss=0.1684, simple_loss=0.2795, pruned_loss=0.02864, over 7329.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03229, over 1406258.37 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:11:02,105 INFO [train.py:763] (4/8) Epoch 27, batch 900, loss[loss=0.1437, simple_loss=0.2334, pruned_loss=0.027, over 7003.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03255, over 1407530.96 frames.], batch size: 16, lr: 2.80e-04
2022-04-30 05:12:07,290 INFO [train.py:763] (4/8) Epoch 27, batch 950, loss[loss=0.1309, simple_loss=0.2353, pruned_loss=0.01327, over 7154.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2638, pruned_loss=0.03267, over 1410284.78 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:13:12,788 INFO [train.py:763] (4/8) Epoch 27, batch 1000, loss[loss=0.1766, simple_loss=0.2803, pruned_loss=0.03645, over 7435.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03266, over 1415789.44 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:14:18,814 INFO [train.py:763] (4/8) Epoch 27, batch 1050, loss[loss=0.1543, simple_loss=0.2554, pruned_loss=0.02654, over 7413.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2644, pruned_loss=0.0329, over 1416326.90 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:15:25,040 INFO [train.py:763] (4/8) Epoch 27, batch 1100, loss[loss=0.1392, simple_loss=0.2369, pruned_loss=0.02073, over 7063.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.03255, over 1414776.58 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:16:31,239 INFO [train.py:763] (4/8) Epoch 27, batch 1150, loss[loss=0.1844, simple_loss=0.2847, pruned_loss=0.04203, over 7187.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2639, pruned_loss=0.0327, over 1420667.18 frames.], batch size: 23, lr: 2.79e-04
2022-04-30 05:17:47,506 INFO [train.py:763] (4/8) Epoch 27, batch 1200, loss[loss=0.141, simple_loss=0.2385, pruned_loss=0.02172, over 7149.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.03205, over 1424538.12 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:19:01,883 INFO [train.py:763] (4/8) Epoch 27, batch 1250, loss[loss=0.1543, simple_loss=0.245, pruned_loss=0.03178, over 7126.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03207, over 1422355.39 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:20:26,019 INFO [train.py:763] (4/8) Epoch 27, batch 1300, loss[loss=0.1539, simple_loss=0.251, pruned_loss=0.02838, over 7289.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.0324, over 1418876.07 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:21:31,872 INFO [train.py:763] (4/8) Epoch 27, batch 1350, loss[loss=0.1546, simple_loss=0.2469, pruned_loss=0.03111, over 7360.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2639, pruned_loss=0.03262, over 1418808.28 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:22:37,301 INFO [train.py:763] (4/8) Epoch 27, batch 1400, loss[loss=0.1686, simple_loss=0.2614, pruned_loss=0.03789, over 7067.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2631, pruned_loss=0.03251, over 1418871.26 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:24:10,241 INFO [train.py:763] (4/8) Epoch 27, batch 1450, loss[loss=0.1381, simple_loss=0.2483, pruned_loss=0.01396, over 7331.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2612, pruned_loss=0.03174, over 1421633.74 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:25:16,093 INFO [train.py:763] (4/8) Epoch 27, batch 1500, loss[loss=0.1678, simple_loss=0.2744, pruned_loss=0.03058, over 7107.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2623, pruned_loss=0.032, over 1423656.85 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:26:21,997 INFO [train.py:763] (4/8) Epoch 27, batch 1550, loss[loss=0.1417, simple_loss=0.2383, pruned_loss=0.02258, over 6795.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.0326, over 1420586.46 frames.], batch size: 15, lr: 2.79e-04
2022-04-30 05:27:29,032 INFO [train.py:763] (4/8) Epoch 27, batch 1600, loss[loss=0.174, simple_loss=0.283, pruned_loss=0.03254, over 7425.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03206, over 1424605.98 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:28:35,018 INFO [train.py:763] (4/8) Epoch 27, batch 1650, loss[loss=0.1402, simple_loss=0.2285, pruned_loss=0.02601, over 7059.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2621, pruned_loss=0.03198, over 1425661.27 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:29:41,340 INFO [train.py:763] (4/8) Epoch 27, batch 1700, loss[loss=0.1388, simple_loss=0.2345, pruned_loss=0.02156, over 7355.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.032, over 1427201.81 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:30:48,488 INFO [train.py:763] (4/8) Epoch 27, batch 1750, loss[loss=0.1717, simple_loss=0.2712, pruned_loss=0.03607, over 6811.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03197, over 1428367.68 frames.], batch size: 31, lr: 2.79e-04
2022-04-30 05:31:54,569 INFO [train.py:763] (4/8) Epoch 27, batch 1800, loss[loss=0.1619, simple_loss=0.2729, pruned_loss=0.02548, over 7221.00 frames.], tot_loss[loss=0.164, simple_loss=0.2631, pruned_loss=0.03243, over 1427104.31 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:33:00,690 INFO [train.py:763] (4/8) Epoch 27, batch 1850, loss[loss=0.1539, simple_loss=0.2473, pruned_loss=0.03029, over 7169.00 frames.], tot_loss[loss=0.1641, simple_loss=0.263, pruned_loss=0.03255, over 1429872.25 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:34:06,839 INFO [train.py:763] (4/8) Epoch 27, batch 1900, loss[loss=0.1574, simple_loss=0.2554, pruned_loss=0.02969, over 7279.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2627, pruned_loss=0.03221, over 1430372.42 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:35:13,647 INFO [train.py:763] (4/8) Epoch 27, batch 1950, loss[loss=0.1915, simple_loss=0.2957, pruned_loss=0.04363, over 6555.00 frames.], tot_loss[loss=0.1639, simple_loss=0.263, pruned_loss=0.03244, over 1425337.47 frames.], batch size: 37, lr: 2.78e-04
2022-04-30 05:36:20,335 INFO [train.py:763] (4/8) Epoch 27, batch 2000, loss[loss=0.1522, simple_loss=0.2581, pruned_loss=0.02316, over 7219.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2633, pruned_loss=0.03245, over 1424314.99 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:37:26,470 INFO [train.py:763] (4/8) Epoch 27, batch 2050, loss[loss=0.172, simple_loss=0.2694, pruned_loss=0.03733, over 7214.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2642, pruned_loss=0.03264, over 1423047.61 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:38:32,944 INFO [train.py:763] (4/8) Epoch 27, batch 2100, loss[loss=0.1666, simple_loss=0.2723, pruned_loss=0.03046, over 7281.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03212, over 1423319.63 frames.], batch size: 25, lr: 2.78e-04
2022-04-30 05:39:38,767 INFO [train.py:763] (4/8) Epoch 27, batch 2150, loss[loss=0.1324, simple_loss=0.2287, pruned_loss=0.01807, over 7116.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03235, over 1422164.58 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:40:44,411 INFO [train.py:763] (4/8) Epoch 27, batch 2200, loss[loss=0.171, simple_loss=0.2689, pruned_loss=0.03657, over 7314.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2642, pruned_loss=0.0325, over 1421428.31 frames.], batch size: 24, lr: 2.78e-04
2022-04-30 05:41:50,156 INFO [train.py:763] (4/8) Epoch 27, batch 2250, loss[loss=0.1468, simple_loss=0.2519, pruned_loss=0.02086, over 7341.00 frames.], tot_loss[loss=0.1644, simple_loss=0.264, pruned_loss=0.03246, over 1424321.80 frames.], batch size: 22, lr: 2.78e-04
2022-04-30 05:42:56,032 INFO [train.py:763] (4/8) Epoch 27, batch 2300, loss[loss=0.1555, simple_loss=0.262, pruned_loss=0.0245, over 7141.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.0326, over 1421299.03 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:44:01,764 INFO [train.py:763] (4/8) Epoch 27, batch 2350, loss[loss=0.175, simple_loss=0.2783, pruned_loss=0.03583, over 7159.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03213, over 1419657.10 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:45:08,043 INFO [train.py:763] (4/8) Epoch 27, batch 2400, loss[loss=0.2008, simple_loss=0.2986, pruned_loss=0.05146, over 7206.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03271, over 1422651.57 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:46:14,163 INFO [train.py:763] (4/8) Epoch 27, batch 2450, loss[loss=0.1746, simple_loss=0.2862, pruned_loss=0.03151, over 6333.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03238, over 1422913.35 frames.], batch size: 37, lr: 2.78e-04
2022-04-30 05:47:19,801 INFO [train.py:763] (4/8) Epoch 27, batch 2500, loss[loss=0.1502, simple_loss=0.2423, pruned_loss=0.02903, over 7273.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2643, pruned_loss=0.03303, over 1420504.06 frames.], batch size: 16, lr: 2.78e-04
2022-04-30 05:48:25,889 INFO [train.py:763] (4/8) Epoch 27, batch 2550, loss[loss=0.1608, simple_loss=0.2601, pruned_loss=0.03074, over 7261.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2641, pruned_loss=0.03272, over 1421714.88 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:49:31,723 INFO [train.py:763] (4/8) Epoch 27, batch 2600, loss[loss=0.1551, simple_loss=0.2661, pruned_loss=0.02204, over 7231.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03235, over 1421698.61 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:50:37,395 INFO [train.py:763] (4/8) Epoch 27, batch 2650, loss[loss=0.1413, simple_loss=0.2308, pruned_loss=0.02589, over 7021.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2642, pruned_loss=0.03249, over 1420534.42 frames.], batch size: 16, lr: 2.78e-04
2022-04-30 05:51:42,951 INFO [train.py:763] (4/8) Epoch 27, batch 2700, loss[loss=0.189, simple_loss=0.2933, pruned_loss=0.04239, over 7320.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2641, pruned_loss=0.03239, over 1422563.36 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:52:49,035 INFO [train.py:763] (4/8) Epoch 27, batch 2750, loss[loss=0.139, simple_loss=0.2353, pruned_loss=0.0214, over 7234.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2652, pruned_loss=0.03288, over 1420475.47 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:53:54,754 INFO [train.py:763] (4/8) Epoch 27, batch 2800, loss[loss=0.1528, simple_loss=0.2486, pruned_loss=0.02855, over 7236.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2653, pruned_loss=0.03308, over 1416809.69 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 05:55:00,518 INFO [train.py:763] (4/8) Epoch 27, batch 2850, loss[loss=0.1497, simple_loss=0.2435, pruned_loss=0.02793, over 7141.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03293, over 1421173.48 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 05:56:06,156 INFO [train.py:763] (4/8) Epoch 27, batch 2900, loss[loss=0.1969, simple_loss=0.2991, pruned_loss=0.04742, over 7311.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2652, pruned_loss=0.03297, over 1420281.89 frames.], batch size: 25, lr: 2.77e-04
2022-04-30 05:57:11,708 INFO [train.py:763] (4/8) Epoch 27, batch 2950, loss[loss=0.1593, simple_loss=0.2544, pruned_loss=0.03213, over 7203.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2655, pruned_loss=0.03272, over 1423096.40 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 05:58:18,058 INFO [train.py:763] (4/8) Epoch 27, batch 3000, loss[loss=0.1866, simple_loss=0.2908, pruned_loss=0.04123, over 7060.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2649, pruned_loss=0.03234, over 1424923.31 frames.], batch size: 28, lr: 2.77e-04
2022-04-30 05:58:18,059 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 05:58:33,165 INFO [train.py:792] (4/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
2022-04-30 05:59:40,072 INFO [train.py:763] (4/8) Epoch 27, batch 3050, loss[loss=0.1347, simple_loss=0.2271, pruned_loss=0.02112, over 7132.00 frames.], tot_loss[loss=0.165, simple_loss=0.2647, pruned_loss=0.03263, over 1426246.62 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 06:00:45,832 INFO [train.py:763] (4/8) Epoch 27, batch 3100, loss[loss=0.1658, simple_loss=0.2667, pruned_loss=0.03246, over 7368.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.0324, over 1424650.02 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:01:51,940 INFO [train.py:763] (4/8) Epoch 27, batch 3150, loss[loss=0.1419, simple_loss=0.2298, pruned_loss=0.02706, over 7402.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03226, over 1423439.17 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:02:58,130 INFO [train.py:763] (4/8) Epoch 27, batch 3200, loss[loss=0.17, simple_loss=0.2728, pruned_loss=0.03366, over 7318.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.0321, over 1424173.71 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:04:04,074 INFO [train.py:763] (4/8) Epoch 27, batch 3250, loss[loss=0.1536, simple_loss=0.2594, pruned_loss=0.02397, over 7171.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03196, over 1424100.15 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:05:10,045 INFO [train.py:763] (4/8) Epoch 27, batch 3300, loss[loss=0.1529, simple_loss=0.2369, pruned_loss=0.03446, over 6993.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03206, over 1423382.42 frames.], batch size: 16, lr: 2.77e-04
2022-04-30 06:06:16,450 INFO [train.py:763] (4/8) Epoch 27, batch 3350, loss[loss=0.1664, simple_loss=0.2676, pruned_loss=0.03259, over 7359.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03212, over 1420970.86 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:07:23,072 INFO [train.py:763] (4/8) Epoch 27, batch 3400, loss[loss=0.1626, simple_loss=0.2723, pruned_loss=0.02648, over 7321.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03238, over 1422409.75 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:08:29,073 INFO [train.py:763] (4/8) Epoch 27, batch 3450, loss[loss=0.1929, simple_loss=0.2854, pruned_loss=0.05022, over 7210.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03215, over 1423621.13 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:09:34,960 INFO [train.py:763] (4/8) Epoch 27, batch 3500, loss[loss=0.1579, simple_loss=0.254, pruned_loss=0.03088, over 7061.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03216, over 1422570.81 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:10:40,825 INFO [train.py:763] (4/8) Epoch 27, batch 3550, loss[loss=0.1491, simple_loss=0.2613, pruned_loss=0.01843, over 7322.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.03243, over 1423651.49 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:11:46,445 INFO [train.py:763] (4/8) Epoch 27, batch 3600, loss[loss=0.173, simple_loss=0.2593, pruned_loss=0.04333, over 7070.00 frames.], tot_loss[loss=0.165, simple_loss=0.2648, pruned_loss=0.03261, over 1423552.17 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:12:52,024 INFO [train.py:763] (4/8) Epoch 27, batch 3650, loss[loss=0.1921, simple_loss=0.2906, pruned_loss=0.04673, over 7407.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2639, pruned_loss=0.03238, over 1423027.71 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:13:58,379 INFO [train.py:763] (4/8) Epoch 27, batch 3700, loss[loss=0.1483, simple_loss=0.2553, pruned_loss=0.02065, over 7440.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2641, pruned_loss=0.03246, over 1423084.16 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:15:04,061 INFO [train.py:763] (4/8) Epoch 27, batch 3750, loss[loss=0.1766, simple_loss=0.2804, pruned_loss=0.03638, over 5007.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.0328, over 1419896.60 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:16:10,306 INFO [train.py:763] (4/8) Epoch 27, batch 3800, loss[loss=0.1825, simple_loss=0.258, pruned_loss=0.05356, over 7273.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.0326, over 1422519.41 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:17:16,532 INFO [train.py:763] (4/8) Epoch 27, batch 3850, loss[loss=0.1472, simple_loss=0.2538, pruned_loss=0.02031, over 7160.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03273, over 1426019.45 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:18:22,907 INFO [train.py:763] (4/8) Epoch 27, batch 3900, loss[loss=0.1697, simple_loss=0.2677, pruned_loss=0.03582, over 7201.00 frames.], tot_loss[loss=0.1648, simple_loss=0.264, pruned_loss=0.03274, over 1424595.34 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:19:28,538 INFO [train.py:763] (4/8) Epoch 27, batch 3950, loss[loss=0.1728, simple_loss=0.2844, pruned_loss=0.03056, over 7204.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03257, over 1426376.28 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:20:34,796 INFO [train.py:763] (4/8) Epoch 27, batch 4000, loss[loss=0.1647, simple_loss=0.275, pruned_loss=0.0272, over 6765.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2626, pruned_loss=0.03211, over 1423063.50 frames.], batch size: 31, lr: 2.76e-04
2022-04-30 06:21:40,916 INFO [train.py:763] (4/8) Epoch 27, batch 4050, loss[loss=0.1907, simple_loss=0.2904, pruned_loss=0.04547, over 4786.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03251, over 1416451.30 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:22:47,107 INFO [train.py:763] (4/8) Epoch 27, batch 4100, loss[loss=0.1592, simple_loss=0.2334, pruned_loss=0.04247, over 7120.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2636, pruned_loss=0.03251, over 1418196.70 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:24:03,943 INFO [train.py:763] (4/8) Epoch 27, batch 4150, loss[loss=0.1518, simple_loss=0.2529, pruned_loss=0.02536, over 7154.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.03256, over 1423242.69 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:25:09,374 INFO [train.py:763] (4/8) Epoch 27, batch 4200, loss[loss=0.1709, simple_loss=0.2678, pruned_loss=0.03701, over 5258.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2647, pruned_loss=0.03278, over 1417990.09 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:26:15,105 INFO [train.py:763] (4/8) Epoch 27, batch 4250, loss[loss=0.1553, simple_loss=0.2502, pruned_loss=0.03025, over 7057.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.03261, over 1416278.65 frames.], batch size: 18, lr: 2.76e-04
2022-04-30 06:27:21,138 INFO [train.py:763] (4/8) Epoch 27, batch 4300, loss[loss=0.1401, simple_loss=0.2395, pruned_loss=0.02036, over 7142.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03219, over 1417901.14 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:28:27,401 INFO [train.py:763] (4/8) Epoch 27, batch 4350, loss[loss=0.1632, simple_loss=0.2731, pruned_loss=0.0267, over 7214.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03195, over 1417619.14 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:29:33,355 INFO [train.py:763] (4/8) Epoch 27, batch 4400, loss[loss=0.1766, simple_loss=0.2743, pruned_loss=0.0395, over 6405.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2634, pruned_loss=0.03245, over 1409732.99 frames.], batch size: 37, lr: 2.76e-04
2022-04-30 06:30:39,366 INFO [train.py:763] (4/8) Epoch 27, batch 4450, loss[loss=0.1488, simple_loss=0.2445, pruned_loss=0.0265, over 7244.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03248, over 1402780.97 frames.], batch size: 16, lr: 2.76e-04
2022-04-30 06:31:44,895 INFO [train.py:763] (4/8) Epoch 27, batch 4500, loss[loss=0.1824, simple_loss=0.2956, pruned_loss=0.03462, over 7214.00 frames.], tot_loss[loss=0.165, simple_loss=0.2645, pruned_loss=0.03281, over 1390587.74 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:32:50,034 INFO [train.py:763] (4/8) Epoch 27, batch 4550, loss[loss=0.1605, simple_loss=0.2696, pruned_loss=0.02567, over 6295.00 frames.], tot_loss[loss=0.166, simple_loss=0.2653, pruned_loss=0.03336, over 1359042.69 frames.], batch size: 37, lr: 2.76e-04
2022-04-30 06:34:19,195 INFO [train.py:763] (4/8) Epoch 28, batch 0, loss[loss=0.1634, simple_loss=0.2666, pruned_loss=0.03003, over 7088.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2666, pruned_loss=0.03003, over 7088.00 frames.], batch size: 28, lr: 2.71e-04
2022-04-30 06:35:24,836 INFO [train.py:763] (4/8) Epoch 28, batch 50, loss[loss=0.1931, simple_loss=0.291, pruned_loss=0.0476, over 7290.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03202, over 323729.87 frames.], batch size: 24, lr: 2.71e-04
2022-04-30 06:36:31,681 INFO [train.py:763] (4/8) Epoch 28, batch 100, loss[loss=0.1736, simple_loss=0.2755, pruned_loss=0.03588, over 7317.00 frames.], tot_loss[loss=0.1625, simple_loss=0.262, pruned_loss=0.03148, over 569664.10 frames.], batch size: 21, lr: 2.71e-04
2022-04-30 06:37:37,369 INFO [train.py:763] (4/8) Epoch 28, batch 150, loss[loss=0.163, simple_loss=0.259, pruned_loss=0.0335, over 7246.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2627, pruned_loss=0.03143, over 760289.67 frames.], batch size: 20, lr: 2.71e-04
2022-04-30 06:38:43,638 INFO [train.py:763] (4/8) Epoch 28, batch 200, loss[loss=0.1526, simple_loss=0.2523, pruned_loss=0.02638, over 7063.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03141, over 908963.08 frames.], batch size: 18, lr: 2.71e-04
2022-04-30 06:39:49,238 INFO [train.py:763] (4/8) Epoch 28, batch 250, loss[loss=0.1817, simple_loss=0.2797, pruned_loss=0.04185, over 4876.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03141, over 1019693.45 frames.], batch size: 53, lr: 2.71e-04
2022-04-30 06:40:54,481 INFO [train.py:763] (4/8) Epoch 28, batch 300, loss[loss=0.1645, simple_loss=0.2696, pruned_loss=0.02967, over 7164.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.0316, over 1109020.22 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:41:59,621 INFO [train.py:763] (4/8) Epoch 28, batch 350, loss[loss=0.1615, simple_loss=0.2506, pruned_loss=0.03617, over 7070.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03163, over 1180313.51 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:43:05,885 INFO [train.py:763] (4/8) Epoch 28, batch 400, loss[loss=0.1705, simple_loss=0.2844, pruned_loss=0.02829, over 7141.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2639, pruned_loss=0.03192, over 1235358.18 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:44:12,420 INFO [train.py:763] (4/8) Epoch 28, batch 450, loss[loss=0.1671, simple_loss=0.2767, pruned_loss=0.02871, over 7129.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.032, over 1280907.78 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:45:17,936 INFO [train.py:763] (4/8) Epoch 28, batch 500, loss[loss=0.1693, simple_loss=0.2723, pruned_loss=0.03314, over 4646.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03204, over 1308677.27 frames.], batch size: 52, lr: 2.70e-04
2022-04-30 06:46:23,646 INFO [train.py:763] (4/8) Epoch 28, batch 550, loss[loss=0.1704, simple_loss=0.2777, pruned_loss=0.03158, over 7227.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2642, pruned_loss=0.03221, over 1331344.43 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:47:29,777 INFO [train.py:763] (4/8) Epoch 28, batch 600, loss[loss=0.1441, simple_loss=0.2469, pruned_loss=0.0206, over 7253.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2631, pruned_loss=0.03186, over 1349363.94 frames.], batch size: 19, lr: 2.70e-04
2022-04-30 06:48:35,459 INFO [train.py:763] (4/8) Epoch 28, batch 650, loss[loss=0.1834, simple_loss=0.2794, pruned_loss=0.04365, over 7459.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03184, over 1368121.09 frames.], batch size: 19, lr: 2.70e-04
2022-04-30 06:49:42,648 INFO [train.py:763] (4/8) Epoch 28, batch 700, loss[loss=0.1568, simple_loss=0.2557, pruned_loss=0.02899, over 5390.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03234, over 1376414.61 frames.], batch size: 53, lr: 2.70e-04
2022-04-30 06:50:48,227 INFO [train.py:763] (4/8) Epoch 28, batch 750, loss[loss=0.1513, simple_loss=0.2481, pruned_loss=0.02722, over 7443.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2636, pruned_loss=0.0321, over 1382946.14 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:51:53,703 INFO [train.py:763] (4/8) Epoch 28, batch 800, loss[loss=0.1717, simple_loss=0.2725, pruned_loss=0.03551, over 7111.00 frames.], tot_loss[loss=0.164, simple_loss=0.2637, pruned_loss=0.03214, over 1388079.93 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:52:59,915 INFO [train.py:763] (4/8) Epoch 28, batch 850, loss[loss=0.1913, simple_loss=0.2884, pruned_loss=0.04712, over 6259.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.03258, over 1392618.83 frames.], batch size: 37, lr: 2.70e-04
2022-04-30 06:54:06,449 INFO [train.py:763] (4/8) Epoch 28, batch 900, loss[loss=0.1622, simple_loss=0.2707, pruned_loss=0.0269, over 6785.00 frames.], tot_loss[loss=0.164, simple_loss=0.2634, pruned_loss=0.03228, over 1399100.19 frames.], batch size: 31, lr: 2.70e-04
2022-04-30 06:55:12,062 INFO [train.py:763] (4/8) Epoch 28, batch 950, loss[loss=0.1928, simple_loss=0.2932, pruned_loss=0.04616, over 7211.00 frames.], tot_loss[loss=0.164, simple_loss=0.2633, pruned_loss=0.03234, over 1408384.88 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 06:56:17,976 INFO [train.py:763] (4/8) Epoch 28, batch 1000, loss[loss=0.1503, simple_loss=0.234, pruned_loss=0.03329, over 6845.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2623, pruned_loss=0.03192, over 1414438.69 frames.], batch size: 15, lr: 2.70e-04
2022-04-30 06:57:23,495 INFO [train.py:763] (4/8) Epoch 28, batch 1050, loss[loss=0.1724, simple_loss=0.2799, pruned_loss=0.03245, over 7402.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03159, over 1420028.61 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:58:29,246 INFO [train.py:763] (4/8) Epoch 28, batch 1100, loss[loss=0.1375, simple_loss=0.2341, pruned_loss=0.02042, over 7285.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2624, pruned_loss=0.03151, over 1422454.53 frames.], batch size: 17, lr: 2.70e-04
2022-04-30 06:59:35,655 INFO [train.py:763] (4/8) Epoch 28, batch 1150, loss[loss=0.1577, simple_loss=0.2588, pruned_loss=0.02829, over 7133.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03174, over 1421159.38 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:00:40,809 INFO [train.py:763] (4/8) Epoch 28, batch 1200, loss[loss=0.1811, simple_loss=0.28, pruned_loss=0.04105, over 7131.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2645, pruned_loss=0.03185, over 1423442.86 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:01:47,021 INFO [train.py:763] (4/8) Epoch 28, batch 1250, loss[loss=0.158, simple_loss=0.2574, pruned_loss=0.02932, over 7204.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2636, pruned_loss=0.03175, over 1417039.95 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 07:02:52,926 INFO [train.py:763] (4/8) Epoch 28, batch 1300, loss[loss=0.1807, simple_loss=0.2884, pruned_loss=0.03654, over 7147.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2634, pruned_loss=0.03186, over 1419147.51 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:03:58,472 INFO [train.py:763] (4/8) Epoch 28, batch 1350, loss[loss=0.1768, simple_loss=0.2814, pruned_loss=0.03613, over 7114.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03176, over 1425409.77 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:05:04,525 INFO [train.py:763] (4/8) Epoch 28, batch 1400, loss[loss=0.1615, simple_loss=0.2469, pruned_loss=0.03801, over 7258.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03165, over 1426794.11 frames.], batch size: 17, lr: 2.69e-04
2022-04-30 07:06:10,006 INFO [train.py:763] (4/8) Epoch 28, batch 1450, loss[loss=0.1557, simple_loss=0.2614, pruned_loss=0.025, over 7269.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2632, pruned_loss=0.03149, over 1430774.22 frames.], batch size: 24, lr: 2.69e-04
2022-04-30 07:07:16,028 INFO [train.py:763] (4/8) Epoch 28, batch 1500, loss[loss=0.1478, simple_loss=0.2546, pruned_loss=0.02046, over 7322.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2637, pruned_loss=0.03151, over 1427494.87 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:08:21,692 INFO [train.py:763] (4/8) Epoch 28, batch 1550, loss[loss=0.1728, simple_loss=0.2766, pruned_loss=0.03452, over 7222.00 frames.], tot_loss[loss=0.164, simple_loss=0.2644, pruned_loss=0.0318, over 1428606.71 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:09:26,974 INFO [train.py:763] (4/8) Epoch 28, batch 1600, loss[loss=0.1507, simple_loss=0.2433, pruned_loss=0.02909, over 6819.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2646, pruned_loss=0.03191, over 1425885.98 frames.], batch size: 15, lr: 2.69e-04
2022-04-30 07:10:32,954 INFO [train.py:763] (4/8) Epoch 28, batch 1650, loss[loss=0.1547, simple_loss=0.254, pruned_loss=0.02775, over 6834.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2627, pruned_loss=0.03134, over 1427437.58 frames.], batch size: 15, lr: 2.69e-04
2022-04-30 07:11:39,859 INFO [train.py:763] (4/8) Epoch 28, batch 1700, loss[loss=0.1688, simple_loss=0.2564, pruned_loss=0.04057, over 7274.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03139, over 1430184.25 frames.], batch size: 19, lr: 2.69e-04
2022-04-30 07:12:45,210 INFO [train.py:763] (4/8) Epoch 28, batch 1750, loss[loss=0.161, simple_loss=0.2641, pruned_loss=0.02891, over 7123.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03113, over 1432574.09 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:13:50,836 INFO [train.py:763] (4/8) Epoch 28, batch 1800, loss[loss=0.1611, simple_loss=0.2325, pruned_loss=0.04483, over 7000.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2623, pruned_loss=0.03175, over 1422785.18 frames.], batch size: 16, lr: 2.69e-04
2022-04-30 07:14:56,955 INFO [train.py:763] (4/8) Epoch 28, batch 1850, loss[loss=0.1474, simple_loss=0.2447, pruned_loss=0.02507, over 7420.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.032, over 1425164.62 frames.], batch size: 18, lr: 2.69e-04
2022-04-30 07:16:02,988 INFO [train.py:763] (4/8) Epoch 28, batch 1900, loss[loss=0.172, simple_loss=0.2706, pruned_loss=0.03666, over 7223.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03189, over 1425650.85 frames.], batch size: 26, lr: 2.69e-04
2022-04-30 07:17:09,676 INFO [train.py:763] (4/8) Epoch 28, batch 1950, loss[loss=0.1791, simple_loss=0.2809, pruned_loss=0.0387, over 7309.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03189, over 1427969.72 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:18:15,509 INFO [train.py:763] (4/8) Epoch 28, batch 2000, loss[loss=0.1632, simple_loss=0.271, pruned_loss=0.02774, over 7181.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03164, over 1431081.78 frames.], batch size: 23, lr: 2.69e-04
2022-04-30 07:19:21,141 INFO [train.py:763] (4/8) Epoch 28, batch 2050, loss[loss=0.1747, simple_loss=0.2757, pruned_loss=0.03683, over 7314.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03193, over 1424440.51 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:20:26,742 INFO [train.py:763] (4/8) Epoch 28, batch 2100, loss[loss=0.1575, simple_loss=0.2643, pruned_loss=0.02535, over 7283.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03199, over 1426973.36 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:21:33,840 INFO [train.py:763] (4/8) Epoch 28, batch 2150, loss[loss=0.1603, simple_loss=0.2738, pruned_loss=0.02341, over 7228.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03171, over 1427990.85 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:22:48,758 INFO [train.py:763] (4/8) Epoch 28, batch 2200, loss[loss=0.1968, simple_loss=0.2883, pruned_loss=0.05264, over 7307.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03184, over 1422174.01 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:23:56,112 INFO [train.py:763] (4/8) Epoch 28, batch 2250, loss[loss=0.1629, simple_loss=0.2703, pruned_loss=0.02771, over 7107.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2632, pruned_loss=0.03175, over 1425652.83 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:25:01,833 INFO [train.py:763] (4/8) Epoch 28, batch 2300, loss[loss=0.1881, simple_loss=0.293, pruned_loss=0.04157, over 7276.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03181, over 1427020.93 frames.], batch size: 24, lr: 2.68e-04
2022-04-30 07:26:07,546 INFO [train.py:763] (4/8) Epoch 28, batch 2350, loss[loss=0.1741, simple_loss=0.2782, pruned_loss=0.03502, over 7062.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03212, over 1424369.71 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:27:14,913 INFO [train.py:763] (4/8) Epoch 28, batch 2400, loss[loss=0.1615, simple_loss=0.2558, pruned_loss=0.03363, over 7357.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2624, pruned_loss=0.03202, over 1426195.61 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:28:20,436 INFO [train.py:763] (4/8) Epoch 28, batch 2450, loss[loss=0.1492, simple_loss=0.2533, pruned_loss=0.02259, over 7112.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2634, pruned_loss=0.03282, over 1416451.48 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:29:26,087 INFO [train.py:763] (4/8) Epoch 28, batch 2500, loss[loss=0.1507, simple_loss=0.2479, pruned_loss=0.0268, over 7419.00 frames.], tot_loss[loss=0.164, simple_loss=0.2626, pruned_loss=0.03266, over 1419691.18 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:30:32,239 INFO [train.py:763] (4/8) Epoch 28, batch 2550, loss[loss=0.1625, simple_loss=0.2579, pruned_loss=0.03352, over 7152.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2626, pruned_loss=0.03257, over 1416920.70 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:31:37,897 INFO [train.py:763] (4/8) Epoch 28, batch 2600, loss[loss=0.1795, simple_loss=0.2825, pruned_loss=0.03822, over 7203.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2623, pruned_loss=0.0327, over 1415042.08 frames.], batch size: 23, lr: 2.68e-04
2022-04-30 07:32:43,453 INFO [train.py:763] (4/8) Epoch 28, batch 2650, loss[loss=0.1597, simple_loss=0.2532, pruned_loss=0.03315, over 7418.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2622, pruned_loss=0.03247, over 1418102.68 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:33:59,642 INFO [train.py:763] (4/8) Epoch 28, batch 2700, loss[loss=0.2022, simple_loss=0.2817, pruned_loss=0.06131, over 4967.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2618, pruned_loss=0.03264, over 1417990.29 frames.], batch size: 53, lr: 2.68e-04
2022-04-30 07:35:13,947 INFO [train.py:763] (4/8) Epoch 28, batch 2750, loss[loss=0.1819, simple_loss=0.2955, pruned_loss=0.03421, over 7313.00 frames.], tot_loss[loss=0.164, simple_loss=0.2624, pruned_loss=0.03279, over 1413647.84 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:36:28,353 INFO [train.py:763] (4/8) Epoch 28, batch 2800, loss[loss=0.1677, simple_loss=0.2671, pruned_loss=0.03411, over 7334.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2628, pruned_loss=0.03216, over 1416845.16 frames.], batch size: 22, lr: 2.68e-04
2022-04-30 07:37:44,241 INFO [train.py:763] (4/8) Epoch 28, batch 2850, loss[loss=0.1455, simple_loss=0.2458, pruned_loss=0.02257, over 7251.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2629, pruned_loss=0.0322, over 1418001.04 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:38:58,496 INFO [train.py:763] (4/8) Epoch 28, batch 2900, loss[loss=0.1553, simple_loss=0.2401, pruned_loss=0.03525, over 7257.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2628, pruned_loss=0.03236, over 1417683.63 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:40:13,605 INFO [train.py:763] (4/8) Epoch 28, batch 2950, loss[loss=0.1318, simple_loss=0.2216, pruned_loss=0.021, over 7138.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2618, pruned_loss=0.03227, over 1418443.57 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:41:27,527 INFO [train.py:763] (4/8) Epoch 28, batch 3000, loss[loss=0.1491, simple_loss=0.258, pruned_loss=0.02015, over 7239.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2626, pruned_loss=0.03201, over 1419514.56 frames.], batch size: 20, lr: 2.68e-04
2022-04-30 07:41:27,528 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 07:41:44,125 INFO [train.py:792] (4/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
2022-04-30 07:42:49,821 INFO [train.py:763] (4/8) Epoch 28, batch 3050, loss[loss=0.1526, simple_loss=0.2421, pruned_loss=0.03157, over 7159.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2621, pruned_loss=0.0319, over 1422340.50 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:43:55,526 INFO [train.py:763] (4/8) Epoch 28, batch 3100, loss[loss=0.145, simple_loss=0.2373, pruned_loss=0.02633, over 7282.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2619, pruned_loss=0.03188, over 1419576.73 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:45:01,627 INFO [train.py:763] (4/8) Epoch 28, batch 3150, loss[loss=0.1649, simple_loss=0.2718, pruned_loss=0.02905, over 7210.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03168, over 1423735.23 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:46:07,728 INFO [train.py:763] (4/8) Epoch 28, batch 3200, loss[loss=0.1589, simple_loss=0.2652, pruned_loss=0.02627, over 7121.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03168, over 1423954.81 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:47:14,366 INFO [train.py:763] (4/8) Epoch 28, batch 3250, loss[loss=0.1603, simple_loss=0.2526, pruned_loss=0.03402, over 6809.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2618, pruned_loss=0.03154, over 1422951.72 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:48:20,826 INFO [train.py:763] (4/8) Epoch 28, batch 3300, loss[loss=0.183, simple_loss=0.2818, pruned_loss=0.04206, over 7213.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03187, over 1422344.96 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 07:49:26,928 INFO [train.py:763] (4/8) Epoch 28, batch 3350, loss[loss=0.1619, simple_loss=0.2693, pruned_loss=0.02729, over 7015.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.03201, over 1419575.25 frames.], batch size: 28, lr: 2.67e-04
2022-04-30 07:50:33,794 INFO [train.py:763] (4/8) Epoch 28, batch 3400, loss[loss=0.1592, simple_loss=0.2472, pruned_loss=0.03559, over 7063.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03219, over 1418615.47 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:51:39,844 INFO [train.py:763] (4/8) Epoch 28, batch 3450, loss[loss=0.1443, simple_loss=0.2374, pruned_loss=0.02557, over 7276.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2632, pruned_loss=0.03217, over 1420958.64 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 07:52:45,405 INFO [train.py:763] (4/8) Epoch 28, batch 3500, loss[loss=0.1596, simple_loss=0.2587, pruned_loss=0.03024, over 6841.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03211, over 1420129.66 frames.], batch size: 31, lr: 2.67e-04
2022-04-30 07:53:50,883 INFO [train.py:763] (4/8) Epoch 28, batch 3550, loss[loss=0.1497, simple_loss=0.236, pruned_loss=0.03167, over 7290.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2625, pruned_loss=0.03208, over 1423753.25 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:54:56,699 INFO [train.py:763] (4/8) Epoch 28, batch 3600, loss[loss=0.1648, simple_loss=0.2578, pruned_loss=0.03589, over 6814.00 frames.], tot_loss[loss=0.164, simple_loss=0.263, pruned_loss=0.03245, over 1424104.64 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:56:02,358 INFO [train.py:763] (4/8) Epoch 28, batch 3650, loss[loss=0.1758, simple_loss=0.277, pruned_loss=0.03734, over 7339.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2629, pruned_loss=0.03234, over 1427375.59 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 07:57:08,119 INFO [train.py:763] (4/8) Epoch 28, batch 3700, loss[loss=0.1722, simple_loss=0.2798, pruned_loss=0.03228, over 7200.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2629, pruned_loss=0.03239, over 1428316.27 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 07:58:13,559 INFO [train.py:763] (4/8) Epoch 28, batch 3750, loss[loss=0.1914, simple_loss=0.2924, pruned_loss=0.04525, over 4892.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2635, pruned_loss=0.03272, over 1427374.48 frames.], batch size: 52, lr: 2.67e-04
2022-04-30 07:59:19,060 INFO [train.py:763] (4/8) Epoch 28, batch 3800, loss[loss=0.1533, simple_loss=0.257, pruned_loss=0.02478, over 7431.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2634, pruned_loss=0.03261, over 1428048.87 frames.], batch size: 20, lr: 2.67e-04
2022-04-30 08:00:24,608 INFO [train.py:763] (4/8) Epoch 28, batch 3850, loss[loss=0.178, simple_loss=0.2904, pruned_loss=0.03277, over 7377.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2632, pruned_loss=0.03247, over 1428527.95 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 08:01:31,042 INFO [train.py:763] (4/8) Epoch 28, batch 3900, loss[loss=0.1757, simple_loss=0.2728, pruned_loss=0.03933, over 7287.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03226, over 1431047.94 frames.], batch size: 24, lr: 2.67e-04
2022-04-30 08:02:37,684 INFO [train.py:763] (4/8) Epoch 28, batch 3950, loss[loss=0.1481, simple_loss=0.2471, pruned_loss=0.02452, over 7407.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2652, pruned_loss=0.03248, over 1432099.17 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 08:03:44,062 INFO [train.py:763] (4/8) Epoch 28, batch 4000, loss[loss=0.1746, simple_loss=0.2812, pruned_loss=0.03401, over 7336.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2653, pruned_loss=0.03241, over 1431389.53 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:04:50,782 INFO [train.py:763] (4/8) Epoch 28, batch 4050, loss[loss=0.1569, simple_loss=0.2506, pruned_loss=0.03161, over 7280.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2658, pruned_loss=0.0322, over 1430052.23 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 08:05:55,977 INFO [train.py:763] (4/8) Epoch 28, batch 4100, loss[loss=0.1734, simple_loss=0.2862, pruned_loss=0.03033, over 7340.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2653, pruned_loss=0.0319, over 1430077.62 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:07:02,628 INFO [train.py:763] (4/8) Epoch 28, batch 4150, loss[loss=0.1764, simple_loss=0.2788, pruned_loss=0.03696, over 7313.00 frames.], tot_loss[loss=0.164, simple_loss=0.2645, pruned_loss=0.03174, over 1423407.06 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 08:08:09,140 INFO [train.py:763] (4/8) Epoch 28, batch 4200, loss[loss=0.157, simple_loss=0.2493, pruned_loss=0.03236, over 7270.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2647, pruned_loss=0.03204, over 1420674.51 frames.], batch size: 19, lr: 2.66e-04
2022-04-30 08:09:14,664 INFO [train.py:763] (4/8) Epoch 28, batch 4250, loss[loss=0.1804, simple_loss=0.2772, pruned_loss=0.04177, over 6761.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03155, over 1421150.00 frames.], batch size: 31, lr: 2.66e-04
2022-04-30 08:10:19,662 INFO [train.py:763] (4/8) Epoch 28, batch 4300, loss[loss=0.1627, simple_loss=0.2574, pruned_loss=0.03397, over 7172.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03121, over 1417143.40 frames.], batch size: 18, lr: 2.66e-04
2022-04-30 08:11:24,964 INFO [train.py:763] (4/8) Epoch 28, batch 4350, loss[loss=0.1691, simple_loss=0.2711, pruned_loss=0.03352, over 7323.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03115, over 1418729.48 frames.], batch size: 21, lr: 2.66e-04
2022-04-30 08:12:30,141 INFO [train.py:763] (4/8) Epoch 28, batch 4400, loss[loss=0.1719, simple_loss=0.2732, pruned_loss=0.03529, over 7288.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03158, over 1410914.75 frames.], batch size: 24, lr: 2.66e-04
2022-04-30 08:13:35,271 INFO [train.py:763] (4/8) Epoch 28, batch 4450, loss[loss=0.1464, simple_loss=0.2467, pruned_loss=0.02309, over 6459.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 1402458.26 frames.], batch size: 38, lr: 2.66e-04
2022-04-30 08:14:40,127 INFO [train.py:763] (4/8) Epoch 28, batch 4500, loss[loss=0.1696, simple_loss=0.2688, pruned_loss=0.03517, over 7217.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.03246, over 1379920.45 frames.], batch size: 22, lr: 2.66e-04
2022-04-30 08:15:45,360 INFO [train.py:763] (4/8) Epoch 28, batch 4550, loss[loss=0.1608, simple_loss=0.2577, pruned_loss=0.03192, over 5127.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2653, pruned_loss=0.03294, over 1361342.91 frames.], batch size: 53, lr: 2.66e-04
2022-04-30 08:17:05,887 INFO [train.py:763] (4/8) Epoch 29, batch 0, loss[loss=0.1528, simple_loss=0.2549, pruned_loss=0.02534, over 7328.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2549, pruned_loss=0.02534, over 7328.00 frames.], batch size: 20, lr: 2.62e-04
2022-04-30 08:18:11,688 INFO [train.py:763] (4/8) Epoch 29, batch 50, loss[loss=0.1799, simple_loss=0.272, pruned_loss=0.04394, over 7262.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03159, over 324155.40 frames.], batch size: 18, lr: 2.62e-04
2022-04-30 08:19:17,257 INFO [train.py:763] (4/8) Epoch 29, batch 100, loss[loss=0.1572, simple_loss=0.2458, pruned_loss=0.03428, over 7271.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03165, over 572277.78 frames.], batch size: 17, lr: 2.62e-04
2022-04-30 08:20:22,568 INFO [train.py:763] (4/8) Epoch 29, batch 150, loss[loss=0.199, simple_loss=0.2933, pruned_loss=0.05236, over 7312.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2623, pruned_loss=0.03189, over 750052.66 frames.], batch size: 24, lr: 2.62e-04
2022-04-30 08:21:28,002 INFO [train.py:763] (4/8) Epoch 29, batch 200, loss[loss=0.1506, simple_loss=0.2481, pruned_loss=0.02652, over 7365.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2614, pruned_loss=0.03154, over 899513.15 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:22:33,077 INFO [train.py:763] (4/8) Epoch 29, batch 250, loss[loss=0.1466, simple_loss=0.2466, pruned_loss=0.0233, over 6773.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2635, pruned_loss=0.03221, over 1015493.24 frames.], batch size: 15, lr: 2.61e-04
2022-04-30 08:23:39,495 INFO [train.py:763] (4/8) Epoch 29, batch 300, loss[loss=0.1597, simple_loss=0.2518, pruned_loss=0.03379, over 7272.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2644, pruned_loss=0.03242, over 1107385.25 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:24:46,636 INFO [train.py:763] (4/8) Epoch 29, batch 350, loss[loss=0.1502, simple_loss=0.2465, pruned_loss=0.02697, over 7327.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03216, over 1180192.57 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:25:52,369 INFO [train.py:763] (4/8) Epoch 29, batch 400, loss[loss=0.1728, simple_loss=0.2783, pruned_loss=0.03366, over 7288.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03186, over 1236496.55 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:26:57,828 INFO [train.py:763] (4/8) Epoch 29, batch 450, loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03058, over 7421.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03136, over 1278461.30 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:28:03,213 INFO [train.py:763] (4/8) Epoch 29, batch 500, loss[loss=0.169, simple_loss=0.2638, pruned_loss=0.03714, over 7319.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03111, over 1307124.10 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:29:08,669 INFO [train.py:763] (4/8) Epoch 29, batch 550, loss[loss=0.1722, simple_loss=0.2753, pruned_loss=0.03454, over 7292.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 1335188.74 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:30:14,684 INFO [train.py:763] (4/8) Epoch 29, batch 600, loss[loss=0.1506, simple_loss=0.2527, pruned_loss=0.02425, over 7175.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03133, over 1351069.38 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:31:20,871 INFO [train.py:763] (4/8) Epoch 29, batch 650, loss[loss=0.1633, simple_loss=0.2537, pruned_loss=0.03643, over 7070.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03139, over 1366098.67 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:32:27,044 INFO [train.py:763] (4/8) Epoch 29, batch 700, loss[loss=0.1399, simple_loss=0.2426, pruned_loss=0.01862, over 7317.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2632, pruned_loss=0.0316, over 1375272.56 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:33:32,280 INFO [train.py:763] (4/8) Epoch 29, batch 750, loss[loss=0.1428, simple_loss=0.2492, pruned_loss=0.01816, over 7236.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03191, over 1381902.96 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:34:37,540 INFO [train.py:763] (4/8) Epoch 29, batch 800, loss[loss=0.1499, simple_loss=0.2515, pruned_loss=0.0242, over 7340.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03147, over 1387825.66 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:35:43,020 INFO [train.py:763] (4/8) Epoch 29, batch 850, loss[loss=0.1558, simple_loss=0.2634, pruned_loss=0.02408, over 7055.00 frames.], tot_loss[loss=0.162, simple_loss=0.2613, pruned_loss=0.03141, over 1396268.05 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:36:48,527 INFO [train.py:763] (4/8) Epoch 29, batch 900, loss[loss=0.1774, simple_loss=0.2726, pruned_loss=0.04106, over 7213.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.0316, over 1399545.88 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:37:53,907 INFO [train.py:763] (4/8) Epoch 29, batch 950, loss[loss=0.1625, simple_loss=0.2706, pruned_loss=0.02722, over 7442.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.0317, over 1405996.25 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:38:59,972 INFO [train.py:763] (4/8) Epoch 29, batch 1000, loss[loss=0.1521, simple_loss=0.2605, pruned_loss=0.02179, over 7147.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03207, over 1410474.11 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:40:06,268 INFO [train.py:763] (4/8) Epoch 29, batch 1050, loss[loss=0.1345, simple_loss=0.2246, pruned_loss=0.0222, over 7292.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03194, over 1407395.06 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:41:11,503 INFO [train.py:763] (4/8) Epoch 29, batch 1100, loss[loss=0.1694, simple_loss=0.2763, pruned_loss=0.03125, over 7322.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2645, pruned_loss=0.03191, over 1416760.59 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:42:16,629 INFO [train.py:763] (4/8) Epoch 29, batch 1150, loss[loss=0.1372, simple_loss=0.2296, pruned_loss=0.0224, over 7006.00 frames.], tot_loss[loss=0.1637, simple_loss=0.264, pruned_loss=0.03171, over 1417718.75 frames.], batch size: 16, lr: 2.61e-04
2022-04-30 08:43:21,909 INFO [train.py:763] (4/8) Epoch 29, batch 1200, loss[loss=0.1669, simple_loss=0.26, pruned_loss=0.03685, over 7141.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2631, pruned_loss=0.03134, over 1422466.17 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:44:27,476 INFO [train.py:763] (4/8) Epoch 29, batch 1250, loss[loss=0.1859, simple_loss=0.2864, pruned_loss=0.04275, over 4956.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03139, over 1417935.62 frames.], batch size: 52, lr: 2.60e-04
2022-04-30 08:45:34,622 INFO [train.py:763] (4/8) Epoch 29, batch 1300, loss[loss=0.17, simple_loss=0.2654, pruned_loss=0.03728, over 7338.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03109, over 1419032.60 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 08:46:42,212 INFO [train.py:763] (4/8) Epoch 29, batch 1350, loss[loss=0.1529, simple_loss=0.2577, pruned_loss=0.02408, over 6701.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.0316, over 1419669.16 frames.], batch size: 38, lr: 2.60e-04
2022-04-30 08:47:48,985 INFO [train.py:763] (4/8) Epoch 29, batch 1400, loss[loss=0.1654, simple_loss=0.2611, pruned_loss=0.03483, over 6861.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03161, over 1420012.71 frames.], batch size: 15, lr: 2.60e-04
2022-04-30 08:48:56,271 INFO [train.py:763] (4/8) Epoch 29, batch 1450, loss[loss=0.1734, simple_loss=0.2725, pruned_loss=0.03711, over 7102.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2623, pruned_loss=0.03134, over 1418136.16 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:50:03,375 INFO [train.py:763] (4/8) Epoch 29, batch 1500, loss[loss=0.1511, simple_loss=0.2535, pruned_loss=0.02434, over 7261.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03179, over 1417000.17 frames.], batch size: 19, lr: 2.60e-04
2022-04-30 08:51:09,975 INFO [train.py:763] (4/8) Epoch 29, batch 1550, loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03396, over 7219.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2629, pruned_loss=0.0314, over 1418252.69 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 08:52:16,969 INFO [train.py:763] (4/8) Epoch 29, batch 1600, loss[loss=0.1822, simple_loss=0.2767, pruned_loss=0.04387, over 7322.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03194, over 1419789.83 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:53:22,971 INFO [train.py:763] (4/8) Epoch 29, batch 1650, loss[loss=0.1624, simple_loss=0.2782, pruned_loss=0.02328, over 7166.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03157, over 1424067.16 frames.], batch size: 26, lr: 2.60e-04
2022-04-30 08:54:28,289 INFO [train.py:763] (4/8) Epoch 29, batch 1700, loss[loss=0.1887, simple_loss=0.2817, pruned_loss=0.04781, over 7143.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.03152, over 1426125.21 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 08:55:35,254 INFO [train.py:763] (4/8) Epoch 29, batch 1750, loss[loss=0.1743, simple_loss=0.2781, pruned_loss=0.03521, over 7149.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03142, over 1421751.57 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 08:56:42,192 INFO [train.py:763] (4/8) Epoch 29, batch 1800, loss[loss=0.1873, simple_loss=0.2865, pruned_loss=0.04401, over 4938.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.0315, over 1418941.88 frames.], batch size: 52, lr: 2.60e-04
2022-04-30 08:57:49,260 INFO [train.py:763] (4/8) Epoch 29, batch 1850, loss[loss=0.195, simple_loss=0.296, pruned_loss=0.04695, over 7116.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.0319, over 1423527.42 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:58:55,864 INFO [train.py:763] (4/8) Epoch 29, batch 1900, loss[loss=0.138, simple_loss=0.2272, pruned_loss=0.02438, over 7228.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2632, pruned_loss=0.03202, over 1426016.65 frames.], batch size: 16, lr: 2.60e-04
2022-04-30 09:00:01,477 INFO [train.py:763] (4/8) Epoch 29, batch 1950, loss[loss=0.1293, simple_loss=0.2198, pruned_loss=0.01947, over 7268.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.0316, over 1428148.56 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:01:06,699 INFO [train.py:763] (4/8) Epoch 29, batch 2000, loss[loss=0.1517, simple_loss=0.2612, pruned_loss=0.02116, over 7342.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03158, over 1430623.42 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 09:02:12,104 INFO [train.py:763] (4/8) Epoch 29, batch 2050, loss[loss=0.191, simple_loss=0.2912, pruned_loss=0.04541, over 7211.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2622, pruned_loss=0.03132, over 1430929.81 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 09:03:17,245 INFO [train.py:763] (4/8) Epoch 29, batch 2100, loss[loss=0.1627, simple_loss=0.275, pruned_loss=0.02519, over 7145.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03138, over 1430883.84 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 09:04:22,315 INFO [train.py:763] (4/8) Epoch 29, batch 2150, loss[loss=0.154, simple_loss=0.2512, pruned_loss=0.02844, over 7116.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03178, over 1430061.62 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:05:27,759 INFO [train.py:763] (4/8) Epoch 29, batch 2200, loss[loss=0.1675, simple_loss=0.2707, pruned_loss=0.03218, over 7298.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03171, over 1424345.23 frames.], batch size: 24, lr: 2.60e-04
2022-04-30 09:06:32,908 INFO [train.py:763] (4/8) Epoch 29, batch 2250, loss[loss=0.1605, simple_loss=0.2727, pruned_loss=0.02416, over 7235.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03197, over 1422542.89 frames.], batch size: 26, lr: 2.59e-04
2022-04-30 09:07:38,516 INFO [train.py:763] (4/8) Epoch 29, batch 2300, loss[loss=0.1259, simple_loss=0.2311, pruned_loss=0.01035, over 7327.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03183, over 1419779.32 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:08:43,785 INFO [train.py:763] (4/8) Epoch 29, batch 2350, loss[loss=0.1746, simple_loss=0.2865, pruned_loss=0.03129, over 7341.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.03184, over 1421019.46 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:09:49,526 INFO [train.py:763] (4/8) Epoch 29, batch 2400, loss[loss=0.1804, simple_loss=0.2815, pruned_loss=0.0396, over 7323.00 frames.], tot_loss[loss=0.163, simple_loss=0.263, pruned_loss=0.03149, over 1422827.24 frames.], batch size: 25, lr: 2.59e-04
2022-04-30 09:10:55,174 INFO [train.py:763] (4/8) Epoch 29, batch 2450, loss[loss=0.1652, simple_loss=0.2631, pruned_loss=0.03366, over 7133.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03108, over 1427487.60 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:12:00,710 INFO [train.py:763] (4/8) Epoch 29, batch 2500, loss[loss=0.1393, simple_loss=0.2334, pruned_loss=0.02258, over 6808.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03114, over 1430763.27 frames.], batch size: 15, lr: 2.59e-04
2022-04-30 09:13:06,078 INFO [train.py:763] (4/8) Epoch 29, batch 2550, loss[loss=0.1379, simple_loss=0.23, pruned_loss=0.02288, over 7415.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03107, over 1427433.36 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:14:11,172 INFO [train.py:763] (4/8) Epoch 29, batch 2600, loss[loss=0.1658, simple_loss=0.266, pruned_loss=0.03278, over 7114.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03108, over 1426745.51 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:15:16,452 INFO [train.py:763] (4/8) Epoch 29, batch 2650, loss[loss=0.1456, simple_loss=0.2414, pruned_loss=0.02494, over 7155.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03088, over 1428624.13 frames.], batch size: 17, lr: 2.59e-04
2022-04-30 09:16:21,499 INFO [train.py:763] (4/8) Epoch 29, batch 2700, loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03018, over 7123.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2622, pruned_loss=0.0313, over 1429527.56 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:17:27,764 INFO [train.py:763] (4/8) Epoch 29, batch 2750, loss[loss=0.1514, simple_loss=0.2606, pruned_loss=0.02109, over 7229.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03158, over 1425234.62 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:18:33,542 INFO [train.py:763] (4/8) Epoch 29, batch 2800, loss[loss=0.1619, simple_loss=0.2651, pruned_loss=0.02934, over 7346.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03172, over 1425314.21 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:19:39,943 INFO [train.py:763] (4/8) Epoch 29, batch 2850, loss[loss=0.1617, simple_loss=0.2693, pruned_loss=0.02707, over 7227.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.0317, over 1419414.57 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:20:45,379 INFO [train.py:763] (4/8) Epoch 29, batch 2900, loss[loss=0.1385, simple_loss=0.2323, pruned_loss=0.02237, over 7000.00 frames.], tot_loss[loss=0.1618, simple_loss=0.261, pruned_loss=0.03125, over 1421955.13 frames.], batch size: 16, lr: 2.59e-04
2022-04-30 09:22:01,683 INFO [train.py:763] (4/8) Epoch 29, batch 2950, loss[loss=0.1506, simple_loss=0.257, pruned_loss=0.02208, over 6455.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.031, over 1423389.81 frames.], batch size: 38, lr: 2.59e-04
2022-04-30 09:23:07,149 INFO [train.py:763] (4/8) Epoch 29, batch 3000, loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03595, over 7106.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2605, pruned_loss=0.03092, over 1425643.16 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:23:07,150 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 09:23:22,371 INFO [train.py:792] (4/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
2022-04-30 09:24:27,447 INFO [train.py:763] (4/8) Epoch 29, batch 3050, loss[loss=0.167, simple_loss=0.2786, pruned_loss=0.02777, over 7121.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03116, over 1427111.34 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:25:32,592 INFO [train.py:763] (4/8) Epoch 29, batch 3100, loss[loss=0.1712, simple_loss=0.2788, pruned_loss=0.03178, over 7410.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03099, over 1427576.46 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:26:38,419 INFO [train.py:763] (4/8) Epoch 29, batch 3150, loss[loss=0.1477, simple_loss=0.2498, pruned_loss=0.0228, over 7157.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03085, over 1422688.14 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:27:44,831 INFO [train.py:763] (4/8) Epoch 29, batch 3200, loss[loss=0.1797, simple_loss=0.2811, pruned_loss=0.03914, over 7265.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.0302, over 1425925.77 frames.], batch size: 19, lr: 2.59e-04
2022-04-30 09:28:51,939 INFO [train.py:763] (4/8) Epoch 29, batch 3250, loss[loss=0.1621, simple_loss=0.2754, pruned_loss=0.02444, over 7060.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.0308, over 1421167.34 frames.], batch size: 28, lr: 2.59e-04
2022-04-30 09:29:57,732 INFO [train.py:763] (4/8) Epoch 29, batch 3300, loss[loss=0.1518, simple_loss=0.2571, pruned_loss=0.02326, over 7337.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03065, over 1424157.38 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:31:03,709 INFO [train.py:763] (4/8) Epoch 29, batch 3350, loss[loss=0.1299, simple_loss=0.217, pruned_loss=0.02138, over 7281.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.03101, over 1428281.76 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:32:09,338 INFO [train.py:763] (4/8) Epoch 29, batch 3400, loss[loss=0.1686, simple_loss=0.2627, pruned_loss=0.03723, over 5279.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2601, pruned_loss=0.03059, over 1424950.18 frames.], batch size: 52, lr: 2.58e-04
2022-04-30 09:33:15,078 INFO [train.py:763] (4/8) Epoch 29, batch 3450, loss[loss=0.1837, simple_loss=0.2919, pruned_loss=0.03769, over 7291.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.03104, over 1420905.69 frames.], batch size: 24, lr: 2.58e-04
2022-04-30 09:34:21,146 INFO [train.py:763] (4/8) Epoch 29, batch 3500, loss[loss=0.2021, simple_loss=0.3078, pruned_loss=0.04815, over 7207.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03139, over 1423381.07 frames.], batch size: 26, lr: 2.58e-04
2022-04-30 09:35:26,534 INFO [train.py:763] (4/8) Epoch 29, batch 3550, loss[loss=0.1557, simple_loss=0.2478, pruned_loss=0.03182, over 7169.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03125, over 1423198.89 frames.], batch size: 18, lr: 2.58e-04
2022-04-30 09:36:32,236 INFO [train.py:763] (4/8) Epoch 29, batch 3600, loss[loss=0.1471, simple_loss=0.2493, pruned_loss=0.02244, over 7263.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03149, over 1427276.24 frames.], batch size: 19, lr: 2.58e-04
2022-04-30 09:37:46,876 INFO [train.py:763] (4/8) Epoch 29, batch 3650, loss[loss=0.1658, simple_loss=0.2728, pruned_loss=0.02939, over 6749.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2622, pruned_loss=0.03158, over 1428797.83 frames.], batch size: 31, lr: 2.58e-04
2022-04-30 09:38:52,210 INFO [train.py:763] (4/8) Epoch 29, batch 3700, loss[loss=0.1352, simple_loss=0.234, pruned_loss=0.01826, over 7275.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03134, over 1429471.84 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:39:59,118 INFO [train.py:763] (4/8) Epoch 29, batch 3750, loss[loss=0.1722, simple_loss=0.2829, pruned_loss=0.03076, over 7087.00 frames.], tot_loss[loss=0.1629, simple_loss=0.263, pruned_loss=0.03144, over 1432182.03 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:41:05,832 INFO [train.py:763] (4/8) Epoch 29, batch 3800, loss[loss=0.1736, simple_loss=0.2764, pruned_loss=0.03542, over 7219.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2636, pruned_loss=0.03183, over 1425106.63 frames.], batch size: 22, lr: 2.58e-04
2022-04-30 09:42:11,176 INFO [train.py:763] (4/8) Epoch 29, batch 3850, loss[loss=0.1423, simple_loss=0.2308, pruned_loss=0.02691, over 6778.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2623, pruned_loss=0.03149, over 1425841.26 frames.], batch size: 15, lr: 2.58e-04
2022-04-30 09:43:16,813 INFO [train.py:763] (4/8) Epoch 29, batch 3900, loss[loss=0.1623, simple_loss=0.2478, pruned_loss=0.03838, over 7145.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03147, over 1425958.27 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:44:22,546 INFO [train.py:763] (4/8) Epoch 29, batch 3950, loss[loss=0.194, simple_loss=0.2965, pruned_loss=0.04573, over 7383.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03235, over 1420774.28 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:45:27,971 INFO [train.py:763] (4/8) Epoch 29, batch 4000, loss[loss=0.1815, simple_loss=0.2773, pruned_loss=0.04286, over 7301.00 frames.], tot_loss[loss=0.1653, simple_loss=0.265, pruned_loss=0.03276, over 1418599.98 frames.], batch size: 25, lr: 2.58e-04
2022-04-30 09:46:33,247 INFO [train.py:763] (4/8) Epoch 29, batch 4050, loss[loss=0.1637, simple_loss=0.2762, pruned_loss=0.02558, over 7044.00 frames.], tot_loss[loss=0.1645, simple_loss=0.264, pruned_loss=0.0325, over 1419188.67 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:47:39,262 INFO [train.py:763] (4/8) Epoch 29, batch 4100, loss[loss=0.1724, simple_loss=0.2856, pruned_loss=0.02963, over 7317.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03227, over 1420740.51 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:48:45,600 INFO [train.py:763] (4/8) Epoch 29, batch 4150, loss[loss=0.1728, simple_loss=0.2726, pruned_loss=0.03643, over 7228.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2625, pruned_loss=0.03183, over 1420852.04 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:50:00,120 INFO [train.py:763] (4/8) Epoch 29, batch 4200, loss[loss=0.1573, simple_loss=0.2572, pruned_loss=0.02868, over 7416.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2628, pruned_loss=0.03189, over 1421696.84 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:51:13,962 INFO [train.py:763] (4/8) Epoch 29, batch 4250, loss[loss=0.1763, simple_loss=0.2811, pruned_loss=0.03578, over 7371.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.0322, over 1415638.79 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:52:28,884 INFO [train.py:763] (4/8) Epoch 29, batch 4300, loss[loss=0.1403, simple_loss=0.23, pruned_loss=0.02528, over 7303.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2634, pruned_loss=0.03177, over 1419265.30 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:53:43,987 INFO [train.py:763] (4/8) Epoch 29, batch 4350, loss[loss=0.1748, simple_loss=0.2668, pruned_loss=0.04135, over 7242.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03161, over 1421597.60 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:54:58,496 INFO [train.py:763] (4/8) Epoch 29, batch 4400, loss[loss=0.1563, simple_loss=0.2613, pruned_loss=0.02564, over 7234.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03141, over 1417828.76 frames.], batch size: 20, lr: 2.57e-04
2022-04-30 09:56:12,785 INFO [train.py:763] (4/8) Epoch 29, batch 4450, loss[loss=0.1555, simple_loss=0.2592, pruned_loss=0.02591, over 6185.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03078, over 1412237.69 frames.], batch size: 37, lr: 2.57e-04
2022-04-30 09:57:17,981 INFO [train.py:763] (4/8) Epoch 29, batch 4500, loss[loss=0.2087, simple_loss=0.2935, pruned_loss=0.06189, over 5165.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03133, over 1397055.23 frames.], batch size: 52, lr: 2.57e-04
2022-04-30 09:58:32,302 INFO [train.py:763] (4/8) Epoch 29, batch 4550, loss[loss=0.1975, simple_loss=0.2839, pruned_loss=0.05551, over 5033.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2645, pruned_loss=0.03255, over 1357056.87 frames.], batch size: 53, lr: 2.57e-04
2022-04-30 10:00:01,318 INFO [train.py:763] (4/8) Epoch 30, batch 0, loss[loss=0.1363, simple_loss=0.2294, pruned_loss=0.02162, over 7329.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2294, pruned_loss=0.02162, over 7329.00 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:01:06,992 INFO [train.py:763] (4/8) Epoch 30, batch 50, loss[loss=0.1538, simple_loss=0.2569, pruned_loss=0.02538, over 7264.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03126, over 316384.33 frames.], batch size: 19, lr: 2.53e-04
2022-04-30 10:02:12,183 INFO [train.py:763] (4/8) Epoch 30, batch 100, loss[loss=0.1674, simple_loss=0.2741, pruned_loss=0.03034, over 7390.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2626, pruned_loss=0.03076, over 560676.50 frames.], batch size: 23, lr: 2.53e-04
2022-04-30 10:03:17,804 INFO [train.py:763] (4/8) Epoch 30, batch 150, loss[loss=0.1563, simple_loss=0.2647, pruned_loss=0.02393, over 7203.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03124, over 755563.67 frames.], batch size: 22, lr: 2.53e-04
2022-04-30 10:04:23,870 INFO [train.py:763] (4/8) Epoch 30, batch 200, loss[loss=0.1982, simple_loss=0.2824, pruned_loss=0.05699, over 5378.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03118, over 901112.20 frames.], batch size: 52, lr: 2.53e-04
2022-04-30 10:05:29,993 INFO [train.py:763] (4/8) Epoch 30, batch 250, loss[loss=0.166, simple_loss=0.27, pruned_loss=0.031, over 7304.00 frames.], tot_loss[loss=0.164, simple_loss=0.2641, pruned_loss=0.03196, over 1015909.04 frames.], batch size: 25, lr: 2.53e-04
2022-04-30 10:06:35,953 INFO [train.py:763] (4/8) Epoch 30, batch 300, loss[loss=0.1586, simple_loss=0.2613, pruned_loss=0.02795, over 7320.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03232, over 1108251.26 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:07:41,449 INFO [train.py:763] (4/8) Epoch 30, batch 350, loss[loss=0.1409, simple_loss=0.251, pruned_loss=0.01544, over 7167.00 frames.], tot_loss[loss=0.163, simple_loss=0.2631, pruned_loss=0.03143, over 1175595.04 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:08:46,853 INFO [train.py:763] (4/8) Epoch 30, batch 400, loss[loss=0.1874, simple_loss=0.2863, pruned_loss=0.04425, over 7219.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2633, pruned_loss=0.03179, over 1226631.51 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:09:52,319 INFO [train.py:763] (4/8) Epoch 30, batch 450, loss[loss=0.2145, simple_loss=0.3001, pruned_loss=0.0644, over 7173.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2643, pruned_loss=0.03194, over 1268039.61 frames.], batch size: 26, lr: 2.53e-04
2022-04-30 10:10:57,855 INFO [train.py:763] (4/8) Epoch 30, batch 500, loss[loss=0.1478, simple_loss=0.2349, pruned_loss=0.03036, over 7275.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03178, over 1302524.38 frames.], batch size: 17, lr: 2.53e-04
2022-04-30 10:12:03,590 INFO [train.py:763] (4/8) Epoch 30, batch 550, loss[loss=0.1731, simple_loss=0.271, pruned_loss=0.03762, over 7413.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03226, over 1329249.19 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:13:09,438 INFO [train.py:763] (4/8) Epoch 30, batch 600, loss[loss=0.173, simple_loss=0.2572, pruned_loss=0.0444, over 7075.00 frames.], tot_loss[loss=0.165, simple_loss=0.265, pruned_loss=0.03248, over 1348392.77 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:14:15,861 INFO [train.py:763] (4/8) Epoch 30, batch 650, loss[loss=0.1689, simple_loss=0.2732, pruned_loss=0.03233, over 7151.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2643, pruned_loss=0.03212, over 1369595.77 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:15:21,892 INFO [train.py:763] (4/8) Epoch 30, batch 700, loss[loss=0.1273, simple_loss=0.2203, pruned_loss=0.01716, over 7208.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2639, pruned_loss=0.03221, over 1379978.14 frames.], batch size: 16, lr: 2.52e-04
2022-04-30 10:16:28,667 INFO [train.py:763] (4/8) Epoch 30, batch 750, loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.03343, over 7244.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2632, pruned_loss=0.03184, over 1387339.69 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:17:34,224 INFO [train.py:763] (4/8) Epoch 30, batch 800, loss[loss=0.1595, simple_loss=0.2522, pruned_loss=0.03341, over 7321.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03153, over 1395216.46 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:18:39,958 INFO [train.py:763] (4/8) Epoch 30, batch 850, loss[loss=0.1588, simple_loss=0.2648, pruned_loss=0.02644, over 7415.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03123, over 1399920.61 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:19:45,738 INFO [train.py:763] (4/8) Epoch 30, batch 900, loss[loss=0.1432, simple_loss=0.2324, pruned_loss=0.02698, over 7232.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2607, pruned_loss=0.03089, over 1404753.59 frames.], batch size: 16, lr: 2.52e-04
2022-04-30 10:20:52,496 INFO [train.py:763] (4/8) Epoch 30, batch 950, loss[loss=0.1613, simple_loss=0.2631, pruned_loss=0.02972, over 7037.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2609, pruned_loss=0.03105, over 1406330.23 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:21:58,498 INFO [train.py:763] (4/8) Epoch 30, batch 1000, loss[loss=0.1576, simple_loss=0.2655, pruned_loss=0.02483, over 7334.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2611, pruned_loss=0.03099, over 1409005.11 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:23:03,969 INFO [train.py:763] (4/8) Epoch 30, batch 1050, loss[loss=0.1693, simple_loss=0.2715, pruned_loss=0.03356, over 7043.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03111, over 1410565.85 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:24:09,735 INFO [train.py:763] (4/8) Epoch 30, batch 1100, loss[loss=0.1481, simple_loss=0.2561, pruned_loss=0.0201, over 7067.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.0309, over 1415875.52 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:25:15,757 INFO [train.py:763] (4/8) Epoch 30, batch 1150, loss[loss=0.1556, simple_loss=0.2486, pruned_loss=0.03131, over 7061.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03039, over 1417531.00 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:26:21,662 INFO [train.py:763] (4/8) Epoch 30, batch 1200, loss[loss=0.1898, simple_loss=0.2942, pruned_loss=0.04268, over 7202.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2605, pruned_loss=0.03049, over 1418856.08 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:27:27,464 INFO [train.py:763] (4/8) Epoch 30, batch 1250, loss[loss=0.1565, simple_loss=0.2473, pruned_loss=0.03283, over 7404.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03099, over 1417872.76 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:28:33,935 INFO [train.py:763] (4/8) Epoch 30, batch 1300, loss[loss=0.1572, simple_loss=0.259, pruned_loss=0.02774, over 7199.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03102, over 1417924.42 frames.], batch size: 26, lr: 2.52e-04
2022-04-30 10:29:40,213 INFO [train.py:763] (4/8) Epoch 30, batch 1350, loss[loss=0.1435, simple_loss=0.2391, pruned_loss=0.02391, over 7137.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03164, over 1415250.54 frames.], batch size: 17, lr: 2.52e-04
2022-04-30 10:30:45,701 INFO [train.py:763] (4/8) Epoch 30, batch 1400, loss[loss=0.1764, simple_loss=0.2719, pruned_loss=0.04046, over 7334.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03118, over 1419399.83 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:31:51,066 INFO [train.py:763] (4/8) Epoch 30, batch 1450, loss[loss=0.1544, simple_loss=0.2592, pruned_loss=0.02482, over 7141.00 frames.], tot_loss[loss=0.162, simple_loss=0.262, pruned_loss=0.03096, over 1420722.93 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:32:56,515 INFO [train.py:763] (4/8) Epoch 30, batch 1500, loss[loss=0.1743, simple_loss=0.2746, pruned_loss=0.03698, over 7292.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03122, over 1426329.87 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:34:02,179 INFO [train.py:763] (4/8) Epoch 30, batch 1550, loss[loss=0.1952, simple_loss=0.2854, pruned_loss=0.05249, over 7342.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03106, over 1427973.60 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:35:07,676 INFO [train.py:763] (4/8) Epoch 30, batch 1600, loss[loss=0.1394, simple_loss=0.2441, pruned_loss=0.01728, over 7255.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03056, over 1428579.31 frames.], batch size: 19, lr: 2.52e-04
2022-04-30 10:36:13,948 INFO [train.py:763] (4/8) Epoch 30, batch 1650, loss[loss=0.1453, simple_loss=0.2493, pruned_loss=0.02067, over 7124.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03031, over 1428857.99 frames.], batch size: 21, lr: 2.52e-04
2022-04-30 10:37:20,414 INFO [train.py:763] (4/8) Epoch 30, batch 1700, loss[loss=0.1917, simple_loss=0.2938, pruned_loss=0.04478, over 7281.00 frames.], tot_loss[loss=0.1607, simple_loss=0.26, pruned_loss=0.0307, over 1425336.28 frames.], batch size: 24, lr: 2.52e-04
2022-04-30 10:38:27,154 INFO [train.py:763] (4/8) Epoch 30, batch 1750, loss[loss=0.1878, simple_loss=0.2817, pruned_loss=0.04694, over 7372.00 frames.], tot_loss[loss=0.1617, simple_loss=0.261, pruned_loss=0.03116, over 1427676.08 frames.], batch size: 23, lr: 2.52e-04
2022-04-30 10:39:33,030 INFO [train.py:763] (4/8) Epoch 30, batch 1800, loss[loss=0.1245, simple_loss=0.219, pruned_loss=0.01499, over 7429.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03123, over 1423244.44 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:40:38,991 INFO [train.py:763] (4/8) Epoch 30, batch 1850, loss[loss=0.1319, simple_loss=0.2307, pruned_loss=0.01656, over 7144.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2608, pruned_loss=0.03079, over 1422223.31 frames.], batch size: 17, lr: 2.51e-04
2022-04-30 10:41:45,825 INFO [train.py:763] (4/8) Epoch 30, batch 1900, loss[loss=0.1533, simple_loss=0.2474, pruned_loss=0.02964, over 7322.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2606, pruned_loss=0.03078, over 1425443.80 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:42:51,808 INFO [train.py:763] (4/8) Epoch 30, batch 1950, loss[loss=0.1721, simple_loss=0.2794, pruned_loss=0.0324, over 7368.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03063, over 1424641.72 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:43:59,473 INFO [train.py:763] (4/8) Epoch 30, batch 2000, loss[loss=0.1825, simple_loss=0.271, pruned_loss=0.04701, over 7164.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.0302, over 1426441.15 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:45:05,769 INFO [train.py:763] (4/8) Epoch 30, batch 2050, loss[loss=0.1653, simple_loss=0.2634, pruned_loss=0.03357, over 7200.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2594, pruned_loss=0.03071, over 1423970.64 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:46:11,291 INFO [train.py:763] (4/8) Epoch 30, batch 2100, loss[loss=0.1709, simple_loss=0.2742, pruned_loss=0.03382, over 7163.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2612, pruned_loss=0.03112, over 1422560.40 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:47:17,301 INFO [train.py:763] (4/8) Epoch 30, batch 2150, loss[loss=0.1757, simple_loss=0.2725, pruned_loss=0.03944, over 7167.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03037, over 1426266.72 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:48:22,846 INFO [train.py:763] (4/8) Epoch 30, batch 2200, loss[loss=0.1709, simple_loss=0.2655, pruned_loss=0.03821, over 7064.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03061, over 1427799.22 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:49:28,453 INFO [train.py:763] (4/8) Epoch 30, batch 2250, loss[loss=0.1961, simple_loss=0.304, pruned_loss=0.04412, over 7189.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03095, over 1427275.53 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:50:34,513 INFO [train.py:763] (4/8) Epoch 30, batch 2300, loss[loss=0.1636, simple_loss=0.2573, pruned_loss=0.0349, over 7259.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03122, over 1430066.33 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:51:40,501 INFO [train.py:763] (4/8) Epoch 30, batch 2350, loss[loss=0.1447, simple_loss=0.2523, pruned_loss=0.01859, over 7064.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03137, over 1429707.33 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:52:46,203 INFO [train.py:763] (4/8) Epoch 30, batch 2400, loss[loss=0.1681, simple_loss=0.2695, pruned_loss=0.03332, over 7222.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2628, pruned_loss=0.03194, over 1428720.77 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:53:51,751 INFO [train.py:763] (4/8) Epoch 30, batch 2450, loss[loss=0.1427, simple_loss=0.2619, pruned_loss=0.01177, over 7213.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.0319, over 1423968.24 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:54:57,031 INFO [train.py:763] (4/8) Epoch 30, batch 2500, loss[loss=0.1562, simple_loss=0.2615, pruned_loss=0.02546, over 7354.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.03179, over 1426559.93 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:56:03,556 INFO [train.py:763] (4/8) Epoch 30, batch 2550, loss[loss=0.1761, simple_loss=0.2788, pruned_loss=0.0367, over 7181.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2629, pruned_loss=0.03192, over 1428365.66 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:57:09,405 INFO [train.py:763] (4/8) Epoch 30, batch 2600, loss[loss=0.1322, simple_loss=0.2249, pruned_loss=0.01973, over 7421.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03146, over 1427852.75 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:58:15,102 INFO [train.py:763] (4/8) Epoch 30, batch 2650, loss[loss=0.1665, simple_loss=0.2689, pruned_loss=0.03208, over 7409.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03115, over 1425068.89 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:59:20,428 INFO [train.py:763] (4/8) Epoch 30, batch 2700, loss[loss=0.1699, simple_loss=0.2761, pruned_loss=0.03187, over 7265.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.0312, over 1418951.21 frames.], batch size: 25, lr: 2.51e-04
2022-04-30 11:00:26,174 INFO [train.py:763] (4/8) Epoch 30, batch 2750, loss[loss=0.1735, simple_loss=0.2819, pruned_loss=0.03254, over 7138.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.0313, over 1419667.13 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 11:01:31,733 INFO [train.py:763] (4/8) Epoch 30, batch 2800, loss[loss=0.1685, simple_loss=0.2675, pruned_loss=0.03472, over 7168.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03124, over 1421893.73 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 11:02:36,835 INFO [train.py:763] (4/8) Epoch 30, batch 2850, loss[loss=0.1962, simple_loss=0.3054, pruned_loss=0.04348, over 7204.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03075, over 1418892.65 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 11:03:42,110 INFO [train.py:763] (4/8) Epoch 30, batch 2900, loss[loss=0.1567, simple_loss=0.2616, pruned_loss=0.02589, over 7118.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2622, pruned_loss=0.03104, over 1422524.28 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 11:04:47,457 INFO [train.py:763] (4/8) Epoch 30, batch 2950, loss[loss=0.1559, simple_loss=0.2597, pruned_loss=0.02604, over 7265.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03062, over 1421503.71 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:05:53,064 INFO [train.py:763] (4/8) Epoch 30, batch 3000, loss[loss=0.1631, simple_loss=0.26, pruned_loss=0.0331, over 7334.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03089, over 1421390.35 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:05:53,065 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 11:06:08,153 INFO [train.py:792] (4/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
2022-04-30 11:07:13,671 INFO [train.py:763] (4/8) Epoch 30, batch 3050, loss[loss=0.1523, simple_loss=0.2495, pruned_loss=0.02759, over 6976.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03117, over 1421426.56 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:08:19,231 INFO [train.py:763] (4/8) Epoch 30, batch 3100, loss[loss=0.165, simple_loss=0.2642, pruned_loss=0.03291, over 7275.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03117, over 1425846.44 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:09:24,925 INFO [train.py:763] (4/8) Epoch 30, batch 3150, loss[loss=0.1473, simple_loss=0.2415, pruned_loss=0.02657, over 7004.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2613, pruned_loss=0.03116, over 1424820.54 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:10:31,193 INFO [train.py:763] (4/8) Epoch 30, batch 3200, loss[loss=0.1786, simple_loss=0.2991, pruned_loss=0.02906, over 7195.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2615, pruned_loss=0.03114, over 1415641.93 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:11:37,934 INFO [train.py:763] (4/8) Epoch 30, batch 3250, loss[loss=0.1837, simple_loss=0.2906, pruned_loss=0.03846, over 7143.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03132, over 1414483.78 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:12:45,385 INFO [train.py:763] (4/8) Epoch 30, batch 3300, loss[loss=0.1251, simple_loss=0.2134, pruned_loss=0.01841, over 7284.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03111, over 1422071.28 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:13:51,983 INFO [train.py:763] (4/8) Epoch 30, batch 3350, loss[loss=0.1499, simple_loss=0.2496, pruned_loss=0.02509, over 7205.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03115, over 1421372.38 frames.], batch size: 21, lr: 2.50e-04
2022-04-30 11:14:57,140 INFO [train.py:763] (4/8) Epoch 30, batch 3400, loss[loss=0.169, simple_loss=0.2819, pruned_loss=0.02807, over 7269.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.02999, over 1420386.28 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:16:02,379 INFO [train.py:763] (4/8) Epoch 30, batch 3450, loss[loss=0.1613, simple_loss=0.2661, pruned_loss=0.02822, over 6585.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03033, over 1424678.48 frames.], batch size: 38, lr: 2.50e-04
2022-04-30 11:17:08,604 INFO [train.py:763] (4/8) Epoch 30, batch 3500, loss[loss=0.164, simple_loss=0.2743, pruned_loss=0.02683, over 7370.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03015, over 1426738.05 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:18:14,697 INFO [train.py:763] (4/8) Epoch 30, batch 3550, loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03064, over 7428.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.0304, over 1428099.28 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:19:20,435 INFO [train.py:763] (4/8) Epoch 30, batch 3600, loss[loss=0.1728, simple_loss=0.2893, pruned_loss=0.02814, over 7271.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03062, over 1423310.35 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:20:25,885 INFO [train.py:763] (4/8) Epoch 30, batch 3650, loss[loss=0.1458, simple_loss=0.2431, pruned_loss=0.02422, over 7155.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2619, pruned_loss=0.03086, over 1422287.87 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:21:32,099 INFO [train.py:763] (4/8) Epoch 30, batch 3700, loss[loss=0.1416, simple_loss=0.2327, pruned_loss=0.02522, over 7284.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03062, over 1425041.60 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:22:38,024 INFO [train.py:763] (4/8) Epoch 30, batch 3750, loss[loss=0.1437, simple_loss=0.2449, pruned_loss=0.02129, over 7255.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03126, over 1422919.93 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:23:45,243 INFO [train.py:763] (4/8) Epoch 30, batch 3800, loss[loss=0.1691, simple_loss=0.2568, pruned_loss=0.0407, over 7275.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2612, pruned_loss=0.03131, over 1425741.20 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:24:50,557 INFO [train.py:763] (4/8) Epoch 30, batch 3850, loss[loss=0.1591, simple_loss=0.2548, pruned_loss=0.03164, over 7055.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2614, pruned_loss=0.03156, over 1424918.44 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:25:56,094 INFO [train.py:763] (4/8) Epoch 30, batch 3900, loss[loss=0.1629, simple_loss=0.2675, pruned_loss=0.02921, over 7310.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2609, pruned_loss=0.03134, over 1428906.23 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:27:01,583 INFO [train.py:763] (4/8) Epoch 30, batch 3950, loss[loss=0.1535, simple_loss=0.2527, pruned_loss=0.02711, over 7359.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2607, pruned_loss=0.03121, over 1428385.24 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:28:06,969 INFO [train.py:763] (4/8) Epoch 30, batch 4000, loss[loss=0.1367, simple_loss=0.236, pruned_loss=0.01874, over 7163.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2613, pruned_loss=0.03125, over 1426181.64 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:29:11,956 INFO [train.py:763] (4/8) Epoch 30, batch 4050, loss[loss=0.1805, simple_loss=0.2921, pruned_loss=0.03438, over 7279.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03174, over 1425731.81 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:30:18,166 INFO [train.py:763] (4/8) Epoch 30, batch 4100, loss[loss=0.1606, simple_loss=0.2662, pruned_loss=0.02749, over 7155.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03159, over 1427673.80 frames.], batch size: 19, lr: 2.49e-04
2022-04-30 11:31:24,157 INFO [train.py:763] (4/8) Epoch 30, batch 4150, loss[loss=0.1727, simple_loss=0.2758, pruned_loss=0.03482, over 7107.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03121, over 1428884.46 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:32:29,728 INFO [train.py:763] (4/8) Epoch 30, batch 4200, loss[loss=0.1457, simple_loss=0.2327, pruned_loss=0.02938, over 6752.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03114, over 1430807.29 frames.], batch size: 15, lr: 2.49e-04
2022-04-30 11:33:35,005 INFO [train.py:763] (4/8) Epoch 30, batch 4250, loss[loss=0.1737, simple_loss=0.2798, pruned_loss=0.03381, over 7150.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03142, over 1427201.97 frames.], batch size: 26, lr: 2.49e-04
2022-04-30 11:34:41,233 INFO [train.py:763] (4/8) Epoch 30, batch 4300, loss[loss=0.1662, simple_loss=0.2667, pruned_loss=0.03286, over 7292.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03082, over 1429885.01 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:35:46,139 INFO [train.py:763] (4/8) Epoch 30, batch 4350, loss[loss=0.1644, simple_loss=0.2774, pruned_loss=0.02575, over 7124.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2617, pruned_loss=0.03086, over 1420648.93 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:36:51,028 INFO [train.py:763] (4/8) Epoch 30, batch 4400, loss[loss=0.1822, simple_loss=0.2884, pruned_loss=0.03796, over 7107.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2622, pruned_loss=0.03098, over 1411234.07 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:37:56,306 INFO [train.py:763] (4/8) Epoch 30, batch 4450, loss[loss=0.165, simple_loss=0.2709, pruned_loss=0.02955, over 6429.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03066, over 1410189.70 frames.], batch size: 37, lr: 2.49e-04
2022-04-30 11:39:02,206 INFO [train.py:763] (4/8) Epoch 30, batch 4500, loss[loss=0.1698, simple_loss=0.279, pruned_loss=0.03027, over 6322.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2628, pruned_loss=0.03125, over 1385238.33 frames.], batch size: 37, lr: 2.49e-04
2022-04-30 11:40:07,226 INFO [train.py:763] (4/8) Epoch 30, batch 4550, loss[loss=0.1893, simple_loss=0.278, pruned_loss=0.05034, over 5159.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2639, pruned_loss=0.03174, over 1355648.89 frames.], batch size: 52, lr: 2.49e-04
2022-04-30 11:41:35,694 INFO [train.py:763] (4/8) Epoch 31, batch 0, loss[loss=0.2016, simple_loss=0.2981, pruned_loss=0.05256, over 4966.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2981, pruned_loss=0.05256, over 4966.00 frames.], batch size: 52, lr: 2.45e-04
2022-04-30 11:42:41,155 INFO [train.py:763] (4/8) Epoch 31, batch 50, loss[loss=0.2042, simple_loss=0.3084, pruned_loss=0.05005, over 6411.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2659, pruned_loss=0.0323, over 319555.49 frames.], batch size: 37, lr: 2.45e-04
2022-04-30 11:43:46,468 INFO [train.py:763] (4/8) Epoch 31, batch 100, loss[loss=0.18, simple_loss=0.286, pruned_loss=0.037, over 7320.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2643, pruned_loss=0.03218, over 565951.27 frames.], batch size: 25, lr: 2.45e-04
2022-04-30 11:44:52,569 INFO [train.py:763] (4/8) Epoch 31, batch 150, loss[loss=0.1813, simple_loss=0.2886, pruned_loss=0.03704, over 7127.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2632, pruned_loss=0.03155, over 757837.90 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:45:58,813 INFO [train.py:763] (4/8) Epoch 31, batch 200, loss[loss=0.1485, simple_loss=0.2507, pruned_loss=0.02313, over 7008.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03158, over 902333.12 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:47:04,080 INFO [train.py:763] (4/8) Epoch 31, batch 250, loss[loss=0.1539, simple_loss=0.2585, pruned_loss=0.02464, over 7311.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03087, over 1022295.18 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:48:09,433 INFO [train.py:763] (4/8) Epoch 31, batch 300, loss[loss=0.1759, simple_loss=0.2821, pruned_loss=0.03484, over 7314.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03181, over 1112995.79 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:49:14,698 INFO [train.py:763] (4/8) Epoch 31, batch 350, loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03087, over 7048.00 frames.], tot_loss[loss=0.163, simple_loss=0.2627, pruned_loss=0.03163, over 1181049.98 frames.], batch size: 28, lr: 2.45e-04
2022-04-30 11:50:20,234 INFO [train.py:763] (4/8) Epoch 31, batch 400, loss[loss=0.1831, simple_loss=0.2852, pruned_loss=0.04051, over 7196.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03186, over 1236382.95 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:51:25,625 INFO [train.py:763] (4/8) Epoch 31, batch 450, loss[loss=0.1579, simple_loss=0.2657, pruned_loss=0.025, over 7321.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03102, over 1276951.17 frames.], batch size: 21, lr: 2.45e-04
2022-04-30 11:52:41,064 INFO [train.py:763] (4/8) Epoch 31, batch 500, loss[loss=0.1628, simple_loss=0.2679, pruned_loss=0.02881, over 7339.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03097, over 1313347.27 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:53:47,760 INFO [train.py:763] (4/8) Epoch 31, batch 550, loss[loss=0.1507, simple_loss=0.2586, pruned_loss=0.0214, over 7321.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03111, over 1341251.00 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:54:53,974 INFO [train.py:763] (4/8) Epoch 31, batch 600, loss[loss=0.1265, simple_loss=0.2224, pruned_loss=0.01528, over 7138.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.031, over 1363764.35 frames.], batch size: 17, lr: 2.45e-04
2022-04-30 11:55:59,908 INFO [train.py:763] (4/8) Epoch 31, batch 650, loss[loss=0.1481, simple_loss=0.2357, pruned_loss=0.03021, over 7003.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2607, pruned_loss=0.03092, over 1379637.12 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:57:06,460 INFO [train.py:763] (4/8) Epoch 31, batch 700, loss[loss=0.1588, simple_loss=0.2565, pruned_loss=0.0306, over 7188.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03121, over 1387907.03 frames.], batch size: 23, lr: 2.45e-04
2022-04-30 11:58:13,268 INFO [train.py:763] (4/8) Epoch 31, batch 750, loss[loss=0.1709, simple_loss=0.2704, pruned_loss=0.03568, over 7109.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03122, over 1396513.49 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 11:59:18,734 INFO [train.py:763] (4/8) Epoch 31, batch 800, loss[loss=0.1517, simple_loss=0.2455, pruned_loss=0.02894, over 7264.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03102, over 1401117.27 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:00:24,034 INFO [train.py:763] (4/8) Epoch 31, batch 850, loss[loss=0.1693, simple_loss=0.2774, pruned_loss=0.03063, over 7287.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2622, pruned_loss=0.03096, over 1408641.70 frames.], batch size: 25, lr: 2.44e-04
2022-04-30 12:01:28,731 INFO [train.py:763] (4/8) Epoch 31, batch 900, loss[loss=0.1891, simple_loss=0.2974, pruned_loss=0.04042, over 7338.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2635, pruned_loss=0.0312, over 1411196.63 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:02:34,058 INFO [train.py:763] (4/8) Epoch 31, batch 950, loss[loss=0.1272, simple_loss=0.2214, pruned_loss=0.01652, over 6823.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03093, over 1412030.83 frames.], batch size: 15, lr: 2.44e-04
2022-04-30 12:03:39,303 INFO [train.py:763] (4/8) Epoch 31, batch 1000, loss[loss=0.1605, simple_loss=0.2591, pruned_loss=0.03093, over 7426.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.03096, over 1415581.06 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:04:53,737 INFO [train.py:763] (4/8) Epoch 31, batch 1050, loss[loss=0.1636, simple_loss=0.2702, pruned_loss=0.02848, over 7229.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03069, over 1420165.99 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:05:59,153 INFO [train.py:763] (4/8) Epoch 31, batch 1100, loss[loss=0.2114, simple_loss=0.312, pruned_loss=0.05542, over 7226.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03065, over 1418422.47 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:07:23,560 INFO [train.py:763] (4/8) Epoch 31, batch 1150, loss[loss=0.1565, simple_loss=0.2442, pruned_loss=0.03436, over 7151.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03077, over 1422022.14 frames.], batch size: 17, lr: 2.44e-04
2022-04-30 12:08:30,097 INFO [train.py:763] (4/8) Epoch 31, batch 1200, loss[loss=0.1626, simple_loss=0.274, pruned_loss=0.02558, over 7411.00 frames.], tot_loss[loss=0.161, simple_loss=0.2614, pruned_loss=0.03031, over 1424374.20 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:09:54,552 INFO [train.py:763] (4/8) Epoch 31, batch 1250, loss[loss=0.1756, simple_loss=0.2804, pruned_loss=0.03539, over 7197.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03078, over 1418370.15 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:11:00,224 INFO [train.py:763] (4/8) Epoch 31, batch 1300, loss[loss=0.1746, simple_loss=0.2759, pruned_loss=0.03664, over 7145.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.03084, over 1423758.09 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:12:14,866 INFO [train.py:763] (4/8) Epoch 31, batch 1350, loss[loss=0.1559, simple_loss=0.2607, pruned_loss=0.02553, over 7333.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03129, over 1421760.00 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:13:22,476 INFO [train.py:763] (4/8) Epoch 31, batch 1400, loss[loss=0.1735, simple_loss=0.2779, pruned_loss=0.03452, over 7233.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.03116, over 1422149.87 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:14:38,779 INFO [train.py:763] (4/8) Epoch 31, batch 1450, loss[loss=0.1585, simple_loss=0.2614, pruned_loss=0.02787, over 7330.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.0311, over 1423836.30 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:15:46,109 INFO [train.py:763] (4/8) Epoch 31, batch 1500, loss[loss=0.1759, simple_loss=0.2704, pruned_loss=0.04069, over 5161.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03043, over 1422802.87 frames.], batch size: 53, lr: 2.44e-04
2022-04-30 12:16:51,626 INFO [train.py:763] (4/8) Epoch 31, batch 1550, loss[loss=0.1494, simple_loss=0.2402, pruned_loss=0.0293, over 7426.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03018, over 1421349.62 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:17:56,937 INFO [train.py:763] (4/8) Epoch 31, batch 1600, loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03514, over 7194.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03066, over 1417673.79 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:19:02,302 INFO [train.py:763] (4/8) Epoch 31, batch 1650, loss[loss=0.1446, simple_loss=0.2477, pruned_loss=0.02079, over 7423.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03066, over 1416874.45 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:20:07,948 INFO [train.py:763] (4/8) Epoch 31, batch 1700, loss[loss=0.1628, simple_loss=0.273, pruned_loss=0.02634, over 7109.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03098, over 1412010.85 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:21:14,750 INFO [train.py:763] (4/8) Epoch 31, batch 1750, loss[loss=0.2065, simple_loss=0.2899, pruned_loss=0.06157, over 5102.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.03116, over 1408957.37 frames.], batch size: 52, lr: 2.44e-04
2022-04-30 12:22:33,258 INFO [train.py:763] (4/8) Epoch 31, batch 1800, loss[loss=0.1609, simple_loss=0.265, pruned_loss=0.0284, over 7229.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03144, over 1410448.86 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:23:40,149 INFO [train.py:763] (4/8) Epoch 31, batch 1850, loss[loss=0.1243, simple_loss=0.2177, pruned_loss=0.01546, over 6994.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03139, over 1405914.55 frames.], batch size: 16, lr: 2.44e-04
2022-04-30 12:24:46,004 INFO [train.py:763] (4/8) Epoch 31, batch 1900, loss[loss=0.1555, simple_loss=0.258, pruned_loss=0.02651, over 7351.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03093, over 1411717.05 frames.], batch size: 19, lr: 2.44e-04
2022-04-30 12:25:51,347 INFO [train.py:763] (4/8) Epoch 31, batch 1950, loss[loss=0.1447, simple_loss=0.2416, pruned_loss=0.02394, over 7361.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03105, over 1417706.00 frames.], batch size: 19, lr: 2.43e-04
2022-04-30 12:26:56,755 INFO [train.py:763] (4/8) Epoch 31, batch 2000, loss[loss=0.1345, simple_loss=0.2309, pruned_loss=0.01905, over 7279.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2616, pruned_loss=0.03134, over 1419014.15 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:28:01,917 INFO [train.py:763] (4/8) Epoch 31, batch 2050, loss[loss=0.1532, simple_loss=0.2647, pruned_loss=0.02091, over 7150.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2617, pruned_loss=0.0315, over 1416279.73 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:29:07,871 INFO [train.py:763] (4/8) Epoch 31, batch 2100, loss[loss=0.1321, simple_loss=0.2224, pruned_loss=0.02088, over 7190.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03233, over 1416818.69 frames.], batch size: 16, lr: 2.43e-04
2022-04-30 12:30:13,150 INFO [train.py:763] (4/8) Epoch 31, batch 2150, loss[loss=0.1682, simple_loss=0.2734, pruned_loss=0.03152, over 7221.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2646, pruned_loss=0.03226, over 1420833.07 frames.], batch size: 21, lr: 2.43e-04
2022-04-30 12:31:18,645 INFO [train.py:763] (4/8) Epoch 31, batch 2200, loss[loss=0.1833, simple_loss=0.2879, pruned_loss=0.03937, over 7205.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2631, pruned_loss=0.03202, over 1423320.85 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:32:23,983 INFO [train.py:763] (4/8) Epoch 31, batch 2250, loss[loss=0.1363, simple_loss=0.2333, pruned_loss=0.0197, over 7068.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.0317, over 1424844.21 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:33:30,741 INFO [train.py:763] (4/8) Epoch 31, batch 2300, loss[loss=0.1773, simple_loss=0.2924, pruned_loss=0.03106, over 7341.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03168, over 1422210.30 frames.], batch size: 22, lr: 2.43e-04
2022-04-30 12:34:36,638 INFO [train.py:763] (4/8) Epoch 31, batch 2350, loss[loss=0.1573, simple_loss=0.2548, pruned_loss=0.02988, over 7288.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03157, over 1425471.76 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:35:41,754 INFO [train.py:763] (4/8) Epoch 31, batch 2400, loss[loss=0.1597, simple_loss=0.2637, pruned_loss=0.0278, over 7321.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.032, over 1420430.33 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:36:47,279 INFO [train.py:763] (4/8) Epoch 31, batch 2450, loss[loss=0.1878, simple_loss=0.2834, pruned_loss=0.04608, over 7197.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03164, over 1421683.60 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:37:52,784 INFO [train.py:763] (4/8) Epoch 31, batch 2500, loss[loss=0.1638, simple_loss=0.2464, pruned_loss=0.04064, over 7276.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2615, pruned_loss=0.03145, over 1424678.06 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:38:58,015 INFO [train.py:763] (4/8) Epoch 31, batch 2550, loss[loss=0.1853, simple_loss=0.2878, pruned_loss=0.04137, over 7325.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2617, pruned_loss=0.03154, over 1421824.32 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:40:03,277 INFO [train.py:763] (4/8) Epoch 31, batch 2600, loss[loss=0.1716, simple_loss=0.2543, pruned_loss=0.04443, over 7133.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03161, over 1420407.58 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:41:08,491 INFO [train.py:763] (4/8) Epoch 31, batch 2650, loss[loss=0.1618, simple_loss=0.2662, pruned_loss=0.02867, over 7160.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03117, over 1422654.56 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:42:15,310 INFO [train.py:763] (4/8) Epoch 31, batch 2700, loss[loss=0.1581, simple_loss=0.2591, pruned_loss=0.02853, over 7314.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2616, pruned_loss=0.03103, over 1421924.65 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:43:20,587 INFO [train.py:763] (4/8) Epoch 31, batch 2750, loss[loss=0.1891, simple_loss=0.2945, pruned_loss=0.04186, over 7067.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03086, over 1425169.76 frames.], batch size: 28, lr: 2.43e-04
2022-04-30 12:44:27,118 INFO [train.py:763] (4/8) Epoch 31, batch 2800, loss[loss=0.1493, simple_loss=0.2421, pruned_loss=0.02821, over 7405.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03071, over 1424339.04 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:45:34,092 INFO [train.py:763] (4/8) Epoch 31, batch 2850, loss[loss=0.1618, simple_loss=0.2685, pruned_loss=0.02758, over 6343.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03029, over 1421368.94 frames.], batch size: 37, lr: 2.43e-04
2022-04-30 12:46:39,725 INFO [train.py:763] (4/8) Epoch 31, batch 2900, loss[loss=0.1889, simple_loss=0.2914, pruned_loss=0.04321, over 7232.00 frames.], tot_loss[loss=0.162, simple_loss=0.2624, pruned_loss=0.03079, over 1426015.93 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:47:44,743 INFO [train.py:763] (4/8) Epoch 31, batch 2950, loss[loss=0.1794, simple_loss=0.2857, pruned_loss=0.0366, over 7176.00 frames.], tot_loss[loss=0.1625, simple_loss=0.263, pruned_loss=0.03097, over 1418536.17 frames.], batch size: 23, lr: 2.43e-04
2022-04-30 12:48:50,664 INFO [train.py:763] (4/8) Epoch 31, batch 3000, loss[loss=0.1666, simple_loss=0.2731, pruned_loss=0.03002, over 7438.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2636, pruned_loss=0.03098, over 1419785.61 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:48:50,665 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 12:49:05,872 INFO [train.py:792] (4/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
2022-04-30 12:50:12,205 INFO [train.py:763] (4/8) Epoch 31, batch 3050, loss[loss=0.1715, simple_loss=0.2779, pruned_loss=0.03255, over 7322.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2631, pruned_loss=0.03129, over 1423182.20 frames.], batch size: 25, lr: 2.43e-04
2022-04-30 12:51:18,203 INFO [train.py:763] (4/8) Epoch 31, batch 3100, loss[loss=0.1655, simple_loss=0.2712, pruned_loss=0.02995, over 7113.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2624, pruned_loss=0.03091, over 1425925.46 frames.], batch size: 28, lr: 2.42e-04
2022-04-30 12:52:23,637 INFO [train.py:763] (4/8) Epoch 31, batch 3150, loss[loss=0.146, simple_loss=0.2277, pruned_loss=0.03218, over 7258.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.03084, over 1423798.98 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 12:53:29,083 INFO [train.py:763] (4/8) Epoch 31, batch 3200, loss[loss=0.1524, simple_loss=0.261, pruned_loss=0.02185, over 7107.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2624, pruned_loss=0.03093, over 1425896.66 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:54:36,151 INFO [train.py:763] (4/8) Epoch 31, batch 3250, loss[loss=0.1721, simple_loss=0.2675, pruned_loss=0.03835, over 7342.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03101, over 1427038.52 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 12:55:42,934 INFO [train.py:763] (4/8) Epoch 31, batch 3300, loss[loss=0.1824, simple_loss=0.2853, pruned_loss=0.03971, over 7427.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.03112, over 1423742.33 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:56:50,141 INFO [train.py:763] (4/8) Epoch 31, batch 3350, loss[loss=0.1533, simple_loss=0.2563, pruned_loss=0.0251, over 7315.00 frames.], tot_loss[loss=0.161, simple_loss=0.2605, pruned_loss=0.03081, over 1425555.86 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:57:56,830 INFO [train.py:763] (4/8) Epoch 31, batch 3400, loss[loss=0.1538, simple_loss=0.253, pruned_loss=0.02726, over 7333.00 frames.], tot_loss[loss=0.162, simple_loss=0.2616, pruned_loss=0.03117, over 1422017.18 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:59:03,243 INFO [train.py:763] (4/8) Epoch 31, batch 3450, loss[loss=0.184, simple_loss=0.2931, pruned_loss=0.03743, over 7209.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2622, pruned_loss=0.03108, over 1424828.65 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:00:08,920 INFO [train.py:763] (4/8) Epoch 31, batch 3500, loss[loss=0.2044, simple_loss=0.2849, pruned_loss=0.06193, over 7285.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03099, over 1428490.27 frames.], batch size: 24, lr: 2.42e-04
2022-04-30 13:01:14,840 INFO [train.py:763] (4/8) Epoch 31, batch 3550, loss[loss=0.1924, simple_loss=0.2896, pruned_loss=0.04763, over 7394.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03066, over 1431331.14 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:02:21,335 INFO [train.py:763] (4/8) Epoch 31, batch 3600, loss[loss=0.1577, simple_loss=0.2661, pruned_loss=0.02466, over 6301.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2601, pruned_loss=0.03036, over 1428812.24 frames.], batch size: 37, lr: 2.42e-04
2022-04-30 13:03:26,534 INFO [train.py:763] (4/8) Epoch 31, batch 3650, loss[loss=0.1571, simple_loss=0.2628, pruned_loss=0.02571, over 7230.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03011, over 1428257.33 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:04:32,081 INFO [train.py:763] (4/8) Epoch 31, batch 3700, loss[loss=0.1364, simple_loss=0.2242, pruned_loss=0.02433, over 7138.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02988, over 1430530.31 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 13:05:36,812 INFO [train.py:763] (4/8) Epoch 31, batch 3750, loss[loss=0.1721, simple_loss=0.2768, pruned_loss=0.03371, over 7189.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03024, over 1424568.01 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:06:42,584 INFO [train.py:763] (4/8) Epoch 31, batch 3800, loss[loss=0.1581, simple_loss=0.2574, pruned_loss=0.0294, over 7388.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03016, over 1425915.70 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:07:47,975 INFO [train.py:763] (4/8) Epoch 31, batch 3850, loss[loss=0.1616, simple_loss=0.2655, pruned_loss=0.02885, over 7428.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.0301, over 1428472.28 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:08:53,255 INFO [train.py:763] (4/8) Epoch 31, batch 3900, loss[loss=0.1454, simple_loss=0.2477, pruned_loss=0.02152, over 7166.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03017, over 1429256.89 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:09:58,648 INFO [train.py:763] (4/8) Epoch 31, batch 3950, loss[loss=0.1585, simple_loss=0.2704, pruned_loss=0.0233, over 7224.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03034, over 1424312.34 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:11:04,246 INFO [train.py:763] (4/8) Epoch 31, batch 4000, loss[loss=0.1565, simple_loss=0.2517, pruned_loss=0.03066, over 7409.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03075, over 1422315.02 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:12:09,630 INFO [train.py:763] (4/8) Epoch 31, batch 4050, loss[loss=0.1674, simple_loss=0.2787, pruned_loss=0.02811, over 7367.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03068, over 1419681.06 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:13:15,758 INFO [train.py:763] (4/8) Epoch 31, batch 4100, loss[loss=0.1797, simple_loss=0.2835, pruned_loss=0.03789, over 7209.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03073, over 1418074.97 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:14:21,773 INFO [train.py:763] (4/8) Epoch 31, batch 4150, loss[loss=0.1874, simple_loss=0.289, pruned_loss=0.04289, over 7220.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03067, over 1422511.46 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:15:28,685 INFO [train.py:763] (4/8) Epoch 31, batch 4200, loss[loss=0.1507, simple_loss=0.244, pruned_loss=0.02869, over 7327.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03022, over 1422040.15 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:16:35,571 INFO [train.py:763] (4/8) Epoch 31, batch 4250, loss[loss=0.1711, simple_loss=0.2628, pruned_loss=0.0397, over 7255.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2601, pruned_loss=0.03068, over 1421050.91 frames.], batch size: 19, lr: 2.42e-04
2022-04-30 13:17:40,849 INFO [train.py:763] (4/8) Epoch 31, batch 4300, loss[loss=0.1419, simple_loss=0.2422, pruned_loss=0.02084, over 7416.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2597, pruned_loss=0.0304, over 1420808.01 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:18:46,140 INFO [train.py:763] (4/8) Epoch 31, batch 4350, loss[loss=0.1338, simple_loss=0.2322, pruned_loss=0.0177, over 7174.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.03082, over 1420217.08 frames.], batch size: 18, lr: 2.41e-04
2022-04-30 13:19:51,340 INFO [train.py:763] (4/8) Epoch 31, batch 4400, loss[loss=0.1538, simple_loss=0.2562, pruned_loss=0.02567, over 7331.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.03135, over 1406356.00 frames.], batch size: 25, lr: 2.41e-04
2022-04-30 13:20:56,964 INFO [train.py:763] (4/8) Epoch 31, batch 4450, loss[loss=0.1401, simple_loss=0.242, pruned_loss=0.01908, over 7268.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.0315, over 1404037.73 frames.], batch size: 16, lr: 2.41e-04
2022-04-30 13:22:02,213 INFO [train.py:763] (4/8) Epoch 31, batch 4500, loss[loss=0.1594, simple_loss=0.2622, pruned_loss=0.0283, over 6734.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03161, over 1395258.86 frames.], batch size: 31, lr: 2.41e-04
2022-04-30 13:23:07,076 INFO [train.py:763] (4/8) Epoch 31, batch 4550, loss[loss=0.1835, simple_loss=0.2776, pruned_loss=0.04469, over 4807.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2625, pruned_loss=0.03203, over 1358182.56 frames.], batch size: 52, lr: 2.41e-04
2022-04-30 13:24:35,146 INFO [train.py:763] (4/8) Epoch 32, batch 0, loss[loss=0.1579, simple_loss=0.2542, pruned_loss=0.0308, over 6752.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2542, pruned_loss=0.0308, over 6752.00 frames.], batch size: 31, lr: 2.38e-04
2022-04-30 13:25:38,916 INFO [train.py:763] (4/8) Epoch 32, batch 50, loss[loss=0.1812, simple_loss=0.2693, pruned_loss=0.04658, over 5344.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2611, pruned_loss=0.02971, over 314555.03 frames.], batch size: 52, lr: 2.38e-04
2022-04-30 13:26:41,352 INFO [train.py:763] (4/8) Epoch 32, batch 100, loss[loss=0.1678, simple_loss=0.2731, pruned_loss=0.03128, over 6537.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2609, pruned_loss=0.0299, over 559836.77 frames.], batch size: 38, lr: 2.38e-04
2022-04-30 13:27:47,090 INFO [train.py:763] (4/8) Epoch 32, batch 150, loss[loss=0.1845, simple_loss=0.282, pruned_loss=0.04348, over 7218.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2617, pruned_loss=0.03029, over 751469.26 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:28:52,458 INFO [train.py:763] (4/8) Epoch 32, batch 200, loss[loss=0.152, simple_loss=0.2489, pruned_loss=0.02756, over 7015.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.02982, over 893961.58 frames.], batch size: 16, lr: 2.37e-04
2022-04-30 13:29:57,591 INFO [train.py:763] (4/8) Epoch 32, batch 250, loss[loss=0.1496, simple_loss=0.2514, pruned_loss=0.02391, over 7222.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2605, pruned_loss=0.02927, over 1009119.59 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:31:03,085 INFO [train.py:763] (4/8) Epoch 32, batch 300, loss[loss=0.193, simple_loss=0.2969, pruned_loss=0.04455, over 6749.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2619, pruned_loss=0.03037, over 1092877.00 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:32:10,105 INFO [train.py:763] (4/8) Epoch 32, batch 350, loss[loss=0.1506, simple_loss=0.2474, pruned_loss=0.02694, over 7413.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2615, pruned_loss=0.03031, over 1164120.52 frames.], batch size: 18, lr: 2.37e-04
2022-04-30 13:33:15,976 INFO [train.py:763] (4/8) Epoch 32, batch 400, loss[loss=0.1337, simple_loss=0.2323, pruned_loss=0.01758, over 7431.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.02993, over 1220736.18 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:34:21,563 INFO [train.py:763] (4/8) Epoch 32, batch 450, loss[loss=0.1661, simple_loss=0.272, pruned_loss=0.03014, over 6716.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03003, over 1262875.72 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:35:26,872 INFO [train.py:763] (4/8) Epoch 32, batch 500, loss[loss=0.1718, simple_loss=0.2737, pruned_loss=0.03494, over 7210.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.03061, over 1300960.09 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:36:32,828 INFO [train.py:763] (4/8) Epoch 32, batch 550, loss[loss=0.1741, simple_loss=0.2718, pruned_loss=0.03823, over 7308.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2631, pruned_loss=0.03082, over 1329458.80 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:37:38,141 INFO [train.py:763] (4/8) Epoch 32, batch 600, loss[loss=0.1664, simple_loss=0.2641, pruned_loss=0.03438, over 7300.00 frames.], tot_loss[loss=0.162, simple_loss=0.2627, pruned_loss=0.03067, over 1347460.60 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:38:43,400 INFO [train.py:763] (4/8) Epoch 32, batch 650, loss[loss=0.1808, simple_loss=0.2835, pruned_loss=0.03907, over 7188.00 frames.], tot_loss[loss=0.1624, simple_loss=0.263, pruned_loss=0.03086, over 1364589.79 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:39:48,619 INFO [train.py:763] (4/8) Epoch 32, batch 700, loss[loss=0.1574, simple_loss=0.2418, pruned_loss=0.03654, over 7151.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2632, pruned_loss=0.03104, over 1375225.16 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:40:55,072 INFO [train.py:763] (4/8) Epoch 32, batch 750, loss[loss=0.1525, simple_loss=0.2571, pruned_loss=0.02399, over 7218.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2629, pruned_loss=0.03102, over 1381171.96 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:42:02,249 INFO [train.py:763] (4/8) Epoch 32, batch 800, loss[loss=0.1565, simple_loss=0.2634, pruned_loss=0.02477, over 7441.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03118, over 1392454.41 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:43:08,536 INFO [train.py:763] (4/8) Epoch 32, batch 850, loss[loss=0.1663, simple_loss=0.2707, pruned_loss=0.03091, over 7382.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03127, over 1399514.03 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:44:14,303 INFO [train.py:763] (4/8) Epoch 32, batch 900, loss[loss=0.1641, simple_loss=0.2724, pruned_loss=0.02788, over 7183.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03119, over 1408882.89 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:45:21,093 INFO [train.py:763] (4/8) Epoch 32, batch 950, loss[loss=0.1571, simple_loss=0.2524, pruned_loss=0.03087, over 7429.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03104, over 1414424.03 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:46:27,362 INFO [train.py:763] (4/8) Epoch 32, batch 1000, loss[loss=0.1654, simple_loss=0.2762, pruned_loss=0.02724, over 7229.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2617, pruned_loss=0.03088, over 1414408.87 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:47:33,311 INFO [train.py:763] (4/8) Epoch 32, batch 1050, loss[loss=0.1454, simple_loss=0.2447, pruned_loss=0.02308, over 7147.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03069, over 1413522.17 frames.], batch size: 28, lr: 2.37e-04
2022-04-30 13:48:38,617 INFO [train.py:763] (4/8) Epoch 32, batch 1100, loss[loss=0.1682, simple_loss=0.2657, pruned_loss=0.03539, over 7291.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03089, over 1418175.37 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:49:45,240 INFO [train.py:763] (4/8) Epoch 32, batch 1150, loss[loss=0.1846, simple_loss=0.2797, pruned_loss=0.04478, over 7216.00 frames.], tot_loss[loss=0.161, simple_loss=0.2614, pruned_loss=0.03032, over 1419588.01 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:50:50,719 INFO [train.py:763] (4/8) Epoch 32, batch 1200, loss[loss=0.1726, simple_loss=0.272, pruned_loss=0.03659, over 7193.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2619, pruned_loss=0.0304, over 1422547.27 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:51:56,746 INFO [train.py:763] (4/8) Epoch 32, batch 1250, loss[loss=0.1627, simple_loss=0.2673, pruned_loss=0.02906, over 6500.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2618, pruned_loss=0.03028, over 1420991.14 frames.], batch size: 38, lr: 2.37e-04
2022-04-30 13:53:02,500 INFO [train.py:763] (4/8) Epoch 32, batch 1300, loss[loss=0.1812, simple_loss=0.283, pruned_loss=0.03972, over 7226.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03063, over 1421428.21 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:54:10,198 INFO [train.py:763] (4/8) Epoch 32, batch 1350, loss[loss=0.1543, simple_loss=0.2493, pruned_loss=0.02968, over 7267.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03084, over 1421485.63 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:55:17,149 INFO [train.py:763] (4/8) Epoch 32, batch 1400, loss[loss=0.1361, simple_loss=0.2444, pruned_loss=0.01392, over 7140.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2614, pruned_loss=0.03066, over 1422254.54 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 13:56:22,418 INFO [train.py:763] (4/8) Epoch 32, batch 1450, loss[loss=0.1672, simple_loss=0.2727, pruned_loss=0.03089, over 6548.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.0308, over 1424630.78 frames.], batch size: 31, lr: 2.36e-04
2022-04-30 13:57:27,824 INFO [train.py:763] (4/8) Epoch 32, batch 1500, loss[loss=0.1564, simple_loss=0.2573, pruned_loss=0.02774, over 4747.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03101, over 1422028.86 frames.], batch size: 53, lr: 2.36e-04
2022-04-30 13:58:33,076 INFO [train.py:763] (4/8) Epoch 32, batch 1550, loss[loss=0.1648, simple_loss=0.269, pruned_loss=0.03025, over 7212.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.0314, over 1418553.61 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 13:59:38,325 INFO [train.py:763] (4/8) Epoch 32, batch 1600, loss[loss=0.1733, simple_loss=0.2778, pruned_loss=0.03438, over 7414.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.0312, over 1421004.34 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:00:43,684 INFO [train.py:763] (4/8) Epoch 32, batch 1650, loss[loss=0.1621, simple_loss=0.2662, pruned_loss=0.02901, over 7214.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03057, over 1421134.56 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:01:48,786 INFO [train.py:763] (4/8) Epoch 32, batch 1700, loss[loss=0.1675, simple_loss=0.277, pruned_loss=0.02902, over 7270.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03036, over 1422662.84 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:02:54,183 INFO [train.py:763] (4/8) Epoch 32, batch 1750, loss[loss=0.1636, simple_loss=0.2603, pruned_loss=0.03346, over 7032.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2627, pruned_loss=0.03118, over 1415521.30 frames.], batch size: 28, lr: 2.36e-04
2022-04-30 14:03:59,640 INFO [train.py:763] (4/8) Epoch 32, batch 1800, loss[loss=0.1569, simple_loss=0.2557, pruned_loss=0.02912, over 7266.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2618, pruned_loss=0.03062, over 1419091.77 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:05:06,114 INFO [train.py:763] (4/8) Epoch 32, batch 1850, loss[loss=0.1523, simple_loss=0.252, pruned_loss=0.02628, over 7312.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.0306, over 1422223.53 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:06:21,241 INFO [train.py:763] (4/8) Epoch 32, batch 1900, loss[loss=0.1673, simple_loss=0.2705, pruned_loss=0.03208, over 7379.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03041, over 1425316.79 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:07:26,669 INFO [train.py:763] (4/8) Epoch 32, batch 1950, loss[loss=0.1634, simple_loss=0.2647, pruned_loss=0.03103, over 7262.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03078, over 1423869.99 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:08:33,677 INFO [train.py:763] (4/8) Epoch 32, batch 2000, loss[loss=0.1833, simple_loss=0.2911, pruned_loss=0.03769, over 6524.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2623, pruned_loss=0.03117, over 1425892.96 frames.], batch size: 38, lr: 2.36e-04
2022-04-30 14:09:39,826 INFO [train.py:763] (4/8) Epoch 32, batch 2050, loss[loss=0.1602, simple_loss=0.2523, pruned_loss=0.034, over 7153.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2616, pruned_loss=0.03073, over 1427135.84 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:10:45,529 INFO [train.py:763] (4/8) Epoch 32, batch 2100, loss[loss=0.1315, simple_loss=0.2264, pruned_loss=0.01829, over 7161.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.03071, over 1428263.75 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:11:52,553 INFO [train.py:763] (4/8) Epoch 32, batch 2150, loss[loss=0.1354, simple_loss=0.2284, pruned_loss=0.02118, over 7414.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03079, over 1428416.38 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:12:58,732 INFO [train.py:763] (4/8) Epoch 32, batch 2200, loss[loss=0.1864, simple_loss=0.2821, pruned_loss=0.04531, over 5100.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03102, over 1422708.58 frames.], batch size: 52, lr: 2.36e-04
2022-04-30 14:14:05,700 INFO [train.py:763] (4/8) Epoch 32, batch 2250, loss[loss=0.1585, simple_loss=0.2632, pruned_loss=0.02688, over 7182.00 frames.], tot_loss[loss=0.1617, simple_loss=0.261, pruned_loss=0.03119, over 1420379.89 frames.], batch size: 26, lr: 2.36e-04
2022-04-30 14:15:12,722 INFO [train.py:763] (4/8) Epoch 32, batch 2300, loss[loss=0.166, simple_loss=0.2622, pruned_loss=0.03494, over 7212.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2601, pruned_loss=0.031, over 1417957.41 frames.], batch size: 22, lr: 2.36e-04
2022-04-30 14:16:18,547 INFO [train.py:763] (4/8) Epoch 32, batch 2350, loss[loss=0.1396, simple_loss=0.2329, pruned_loss=0.02316, over 6787.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2591, pruned_loss=0.03067, over 1420932.21 frames.], batch size: 15, lr: 2.36e-04
2022-04-30 14:17:25,996 INFO [train.py:763] (4/8) Epoch 32, batch 2400, loss[loss=0.1544, simple_loss=0.2513, pruned_loss=0.02882, over 7429.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2585, pruned_loss=0.03039, over 1422868.41 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 14:18:32,876 INFO [train.py:763] (4/8) Epoch 32, batch 2450, loss[loss=0.1627, simple_loss=0.2571, pruned_loss=0.03421, over 7258.00 frames.], tot_loss[loss=0.1598, simple_loss=0.259, pruned_loss=0.0303, over 1424971.93 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:19:38,453 INFO [train.py:763] (4/8) Epoch 32, batch 2500, loss[loss=0.1633, simple_loss=0.2728, pruned_loss=0.0269, over 7316.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2588, pruned_loss=0.03026, over 1427050.31 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:20:45,068 INFO [train.py:763] (4/8) Epoch 32, batch 2550, loss[loss=0.1686, simple_loss=0.2667, pruned_loss=0.03523, over 7370.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2585, pruned_loss=0.03026, over 1427310.45 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:21:59,921 INFO [train.py:763] (4/8) Epoch 32, batch 2600, loss[loss=0.1863, simple_loss=0.2908, pruned_loss=0.04085, over 7204.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2591, pruned_loss=0.03056, over 1427714.52 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:23:23,009 INFO [train.py:763] (4/8) Epoch 32, batch 2650, loss[loss=0.1454, simple_loss=0.2346, pruned_loss=0.02808, over 7259.00 frames.], tot_loss[loss=0.1608, simple_loss=0.26, pruned_loss=0.03082, over 1423247.71 frames.], batch size: 16, lr: 2.35e-04
2022-04-30 14:24:36,937 INFO [train.py:763] (4/8) Epoch 32, batch 2700, loss[loss=0.1741, simple_loss=0.2763, pruned_loss=0.03601, over 7430.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2597, pruned_loss=0.0304, over 1424323.92 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:25:51,352 INFO [train.py:763] (4/8) Epoch 32, batch 2750, loss[loss=0.1571, simple_loss=0.2471, pruned_loss=0.03356, over 7285.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2605, pruned_loss=0.03089, over 1425079.59 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:26:57,659 INFO [train.py:763] (4/8) Epoch 32, batch 2800, loss[loss=0.1684, simple_loss=0.2669, pruned_loss=0.03498, over 7198.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2594, pruned_loss=0.03052, over 1424312.03 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:28:12,041 INFO [train.py:763] (4/8) Epoch 32, batch 2850, loss[loss=0.1592, simple_loss=0.2602, pruned_loss=0.02909, over 7320.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2591, pruned_loss=0.0303, over 1425601.27 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:29:27,081 INFO [train.py:763] (4/8) Epoch 32, batch 2900, loss[loss=0.1649, simple_loss=0.2674, pruned_loss=0.03118, over 7300.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2595, pruned_loss=0.03044, over 1425714.62 frames.], batch size: 25, lr: 2.35e-04
2022-04-30 14:30:33,972 INFO [train.py:763] (4/8) Epoch 32, batch 2950, loss[loss=0.1396, simple_loss=0.2488, pruned_loss=0.01524, over 7420.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03024, over 1427798.97 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:31:40,117 INFO [train.py:763] (4/8) Epoch 32, batch 3000, loss[loss=0.1248, simple_loss=0.2199, pruned_loss=0.01484, over 7056.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.0299, over 1426687.78 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:31:40,119 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 14:31:55,318 INFO [train.py:792] (4/8) Epoch 32, validation: loss=0.1696, simple_loss=0.2645, pruned_loss=0.0374, over 698248.00 frames.
2022-04-30 14:33:01,764 INFO [train.py:763] (4/8) Epoch 32, batch 3050, loss[loss=0.1581, simple_loss=0.2651, pruned_loss=0.02553, over 6412.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02993, over 1422204.30 frames.], batch size: 37, lr: 2.35e-04
2022-04-30 14:34:07,504 INFO [train.py:763] (4/8) Epoch 32, batch 3100, loss[loss=0.1754, simple_loss=0.2869, pruned_loss=0.03194, over 7397.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02967, over 1422909.44 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:35:13,883 INFO [train.py:763] (4/8) Epoch 32, batch 3150, loss[loss=0.1358, simple_loss=0.2298, pruned_loss=0.02091, over 7068.00 frames.], tot_loss[loss=0.1592, simple_loss=0.259, pruned_loss=0.02972, over 1420986.16 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:36:20,354 INFO [train.py:763] (4/8) Epoch 32, batch 3200, loss[loss=0.1485, simple_loss=0.2368, pruned_loss=0.03011, over 7234.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02947, over 1421865.13 frames.], batch size: 16, lr: 2.35e-04
2022-04-30 14:37:25,784 INFO [train.py:763] (4/8) Epoch 32, batch 3250, loss[loss=0.1403, simple_loss=0.2428, pruned_loss=0.01891, over 7282.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02918, over 1419705.57 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:38:31,358 INFO [train.py:763] (4/8) Epoch 32, batch 3300, loss[loss=0.169, simple_loss=0.2711, pruned_loss=0.03344, over 7231.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02937, over 1424062.33 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:39:37,082 INFO [train.py:763] (4/8) Epoch 32, batch 3350, loss[loss=0.1542, simple_loss=0.2532, pruned_loss=0.02761, over 7325.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2586, pruned_loss=0.02937, over 1428099.09 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:40:43,410 INFO [train.py:763] (4/8) Epoch 32, batch 3400, loss[loss=0.1388, simple_loss=0.2351, pruned_loss=0.02121, over 7286.00 frames.], tot_loss[loss=0.159, simple_loss=0.2587, pruned_loss=0.02959, over 1427819.23 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:41:50,115 INFO [train.py:763] (4/8) Epoch 32, batch 3450, loss[loss=0.1521, simple_loss=0.2473, pruned_loss=0.02843, over 7321.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02975, over 1431505.87 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:42:56,322 INFO [train.py:763] (4/8) Epoch 32, batch 3500, loss[loss=0.1889, simple_loss=0.2883, pruned_loss=0.0448, over 7377.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03045, over 1428390.61 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:44:01,645 INFO [train.py:763] (4/8) Epoch 32, batch 3550, loss[loss=0.1648, simple_loss=0.2501, pruned_loss=0.0397, over 7415.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.0307, over 1427172.61 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:45:06,992 INFO [train.py:763] (4/8) Epoch 32, batch 3600, loss[loss=0.1337, simple_loss=0.2277, pruned_loss=0.01983, over 7320.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03065, over 1424306.58 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:46:12,675 INFO [train.py:763] (4/8) Epoch 32, batch 3650, loss[loss=0.1435, simple_loss=0.2453, pruned_loss=0.02084, over 7332.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03021, over 1424573.73 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:47:18,399 INFO [train.py:763] (4/8) Epoch 32, batch 3700, loss[loss=0.1476, simple_loss=0.2365, pruned_loss=0.02934, over 7274.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03014, over 1427467.54 frames.], batch size: 17, lr: 2.35e-04
2022-04-30 14:48:25,076 INFO [train.py:763] (4/8) Epoch 32, batch 3750, loss[loss=0.1582, simple_loss=0.2606, pruned_loss=0.02795, over 7221.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02999, over 1427560.84 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:49:30,589 INFO [train.py:763] (4/8) Epoch 32, batch 3800, loss[loss=0.1816, simple_loss=0.2925, pruned_loss=0.03532, over 7188.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02986, over 1428182.53 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:50:35,837 INFO [train.py:763] (4/8) Epoch 32, batch 3850, loss[loss=0.1489, simple_loss=0.2573, pruned_loss=0.02022, over 7327.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2598, pruned_loss=0.0302, over 1428889.14 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:51:41,189 INFO [train.py:763] (4/8) Epoch 32, batch 3900, loss[loss=0.154, simple_loss=0.2465, pruned_loss=0.0307, over 6808.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03037, over 1428827.13 frames.], batch size: 15, lr: 2.35e-04
2022-04-30 14:52:46,605 INFO [train.py:763] (4/8) Epoch 32, batch 3950, loss[loss=0.164, simple_loss=0.2589, pruned_loss=0.03456, over 7396.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03044, over 1431341.94 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:53:52,264 INFO [train.py:763] (4/8) Epoch 32, batch 4000, loss[loss=0.1603, simple_loss=0.2659, pruned_loss=0.02737, over 6189.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03009, over 1431761.85 frames.], batch size: 38, lr: 2.34e-04
2022-04-30 14:54:57,657 INFO [train.py:763] (4/8) Epoch 32, batch 4050, loss[loss=0.1598, simple_loss=0.2509, pruned_loss=0.03441, over 7283.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03018, over 1428755.11 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:56:02,791 INFO [train.py:763] (4/8) Epoch 32, batch 4100, loss[loss=0.1722, simple_loss=0.2701, pruned_loss=0.03713, over 7192.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03035, over 1423969.10 frames.], batch size: 26, lr: 2.34e-04
2022-04-30 14:57:08,459 INFO [train.py:763] (4/8) Epoch 32, batch 4150, loss[loss=0.1848, simple_loss=0.2597, pruned_loss=0.05497, over 6776.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2608, pruned_loss=0.03032, over 1423460.40 frames.], batch size: 15, lr: 2.34e-04
2022-04-30 14:58:14,264 INFO [train.py:763] (4/8) Epoch 32, batch 4200, loss[loss=0.143, simple_loss=0.2397, pruned_loss=0.02319, over 7265.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03015, over 1421313.19 frames.], batch size: 19, lr: 2.34e-04
2022-04-30 14:59:19,679 INFO [train.py:763] (4/8) Epoch 32, batch 4250, loss[loss=0.1559, simple_loss=0.2635, pruned_loss=0.02418, over 7427.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03011, over 1421734.68 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:00:26,350 INFO [train.py:763] (4/8) Epoch 32, batch 4300, loss[loss=0.1462, simple_loss=0.2572, pruned_loss=0.01757, over 6800.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02985, over 1420014.48 frames.], batch size: 31, lr: 2.34e-04
2022-04-30 15:01:32,992 INFO [train.py:763] (4/8) Epoch 32, batch 4350, loss[loss=0.1713, simple_loss=0.2744, pruned_loss=0.03407, over 7210.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02982, over 1415199.70 frames.], batch size: 21, lr: 2.34e-04
2022-04-30 15:02:38,276 INFO [train.py:763] (4/8) Epoch 32, batch 4400, loss[loss=0.162, simple_loss=0.2606, pruned_loss=0.03166, over 7144.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02979, over 1414438.79 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:03:43,363 INFO [train.py:763] (4/8) Epoch 32, batch 4450, loss[loss=0.1694, simple_loss=0.2766, pruned_loss=0.03108, over 7337.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02964, over 1407734.82 frames.], batch size: 22, lr: 2.34e-04
2022-04-30 15:04:48,245 INFO [train.py:763] (4/8) Epoch 32, batch 4500, loss[loss=0.1495, simple_loss=0.2562, pruned_loss=0.02137, over 7142.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02953, over 1397746.78 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:05:53,075 INFO [train.py:763] (4/8) Epoch 32, batch 4550, loss[loss=0.1667, simple_loss=0.2639, pruned_loss=0.03473, over 5352.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02983, over 1376617.59 frames.], batch size: 52, lr: 2.34e-04
2022-04-30 15:07:21,083 INFO [train.py:763] (4/8) Epoch 33, batch 0, loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03228, over 7433.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2479, pruned_loss=0.03228, over 7433.00 frames.], batch size: 20, lr: 2.31e-04
2022-04-30 15:08:26,671 INFO [train.py:763] (4/8) Epoch 33, batch 50, loss[loss=0.1838, simple_loss=0.2873, pruned_loss=0.04013, over 7125.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2585, pruned_loss=0.03082, over 325050.57 frames.], batch size: 28, lr: 2.30e-04
2022-04-30 15:09:31,880 INFO [train.py:763] (4/8) Epoch 33, batch 100, loss[loss=0.1722, simple_loss=0.2734, pruned_loss=0.03545, over 7109.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03094, over 566833.15 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:10:37,375 INFO [train.py:763] (4/8) Epoch 33, batch 150, loss[loss=0.143, simple_loss=0.2513, pruned_loss=0.01731, over 7062.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2587, pruned_loss=0.02992, over 755737.81 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:11:42,895 INFO [train.py:763] (4/8) Epoch 33, batch 200, loss[loss=0.1423, simple_loss=0.2389, pruned_loss=0.0229, over 7270.00 frames.], tot_loss[loss=0.1595, simple_loss=0.259, pruned_loss=0.02999, over 905554.75 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:12:48,572 INFO [train.py:763] (4/8) Epoch 33, batch 250, loss[loss=0.1957, simple_loss=0.2886, pruned_loss=0.05139, over 4793.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2596, pruned_loss=0.03016, over 1012041.31 frames.], batch size: 52, lr: 2.30e-04
2022-04-30 15:13:55,816 INFO [train.py:763] (4/8) Epoch 33, batch 300, loss[loss=0.1526, simple_loss=0.2552, pruned_loss=0.02506, over 7362.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03021, over 1102665.62 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:15:01,946 INFO [train.py:763] (4/8) Epoch 33, batch 350, loss[loss=0.1335, simple_loss=0.2335, pruned_loss=0.01679, over 7174.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2611, pruned_loss=0.03024, over 1167737.06 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:16:08,892 INFO [train.py:763] (4/8) Epoch 33, batch 400, loss[loss=0.1649, simple_loss=0.2705, pruned_loss=0.02963, over 7415.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02979, over 1228510.68 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:17:14,697 INFO [train.py:763] (4/8) Epoch 33, batch 450, loss[loss=0.1855, simple_loss=0.2576, pruned_loss=0.0567, over 7399.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03048, over 1273177.17 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:18:21,051 INFO [train.py:763] (4/8) Epoch 33, batch 500, loss[loss=0.1803, simple_loss=0.2771, pruned_loss=0.04175, over 7305.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03062, over 1306496.85 frames.], batch size: 24, lr: 2.30e-04
2022-04-30 15:19:26,288 INFO [train.py:763] (4/8) Epoch 33, batch 550, loss[loss=0.1777, simple_loss=0.2731, pruned_loss=0.04112, over 6468.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03074, over 1329628.50 frames.], batch size: 37, lr: 2.30e-04
2022-04-30 15:20:43,083 INFO [train.py:763] (4/8) Epoch 33, batch 600, loss[loss=0.1753, simple_loss=0.2778, pruned_loss=0.03643, over 7299.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2615, pruned_loss=0.03052, over 1352511.41 frames.], batch size: 25, lr: 2.30e-04
2022-04-30 15:21:48,328 INFO [train.py:763] (4/8) Epoch 33, batch 650, loss[loss=0.1351, simple_loss=0.232, pruned_loss=0.01915, over 7173.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03053, over 1370579.15 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:22:53,611 INFO [train.py:763] (4/8) Epoch 33, batch 700, loss[loss=0.1448, simple_loss=0.2302, pruned_loss=0.02967, over 7140.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03012, over 1377888.91 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:23:58,783 INFO [train.py:763] (4/8) Epoch 33, batch 750, loss[loss=0.1935, simple_loss=0.2957, pruned_loss=0.04563, over 7165.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03031, over 1389072.09 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:25:05,620 INFO [train.py:763] (4/8) Epoch 33, batch 800, loss[loss=0.1451, simple_loss=0.2315, pruned_loss=0.02939, over 7271.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03073, over 1394622.73 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:26:11,923 INFO [train.py:763] (4/8) Epoch 33, batch 850, loss[loss=0.155, simple_loss=0.2597, pruned_loss=0.02515, over 6547.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.03018, over 1404614.73 frames.], batch size: 38, lr: 2.30e-04
2022-04-30 15:27:17,420 INFO [train.py:763] (4/8) Epoch 33, batch 900, loss[loss=0.1989, simple_loss=0.2957, pruned_loss=0.05107, over 5014.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.0299, over 1409326.05 frames.], batch size: 52, lr: 2.30e-04
2022-04-30 15:28:22,821 INFO [train.py:763] (4/8) Epoch 33, batch 950, loss[loss=0.1665, simple_loss=0.259, pruned_loss=0.03699, over 7277.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2595, pruned_loss=0.03007, over 1408010.97 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:29:28,253 INFO [train.py:763] (4/8) Epoch 33, batch 1000, loss[loss=0.1517, simple_loss=0.2561, pruned_loss=0.02368, over 7431.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03035, over 1409872.27 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:30:33,669 INFO [train.py:763] (4/8) Epoch 33, batch 1050, loss[loss=0.1434, simple_loss=0.245, pruned_loss=0.02096, over 7150.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03005, over 1415841.51 frames.], batch size: 19, lr: 2.30e-04
2022-04-30 15:31:40,467 INFO [train.py:763] (4/8) Epoch 33, batch 1100, loss[loss=0.1621, simple_loss=0.2692, pruned_loss=0.02747, over 6571.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03017, over 1413821.34 frames.], batch size: 38, lr: 2.30e-04
2022-04-30 15:32:45,929 INFO [train.py:763] (4/8) Epoch 33, batch 1150, loss[loss=0.1626, simple_loss=0.2617, pruned_loss=0.03174, over 7420.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03001, over 1416872.54 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:33:51,341 INFO [train.py:763] (4/8) Epoch 33, batch 1200, loss[loss=0.1925, simple_loss=0.2888, pruned_loss=0.0481, over 7194.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02987, over 1420973.43 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:34:56,631 INFO [train.py:763] (4/8) Epoch 33, batch 1250, loss[loss=0.1832, simple_loss=0.2875, pruned_loss=0.03944, over 7353.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02974, over 1419273.64 frames.], batch size: 22, lr: 2.30e-04
2022-04-30 15:36:02,615 INFO [train.py:763] (4/8) Epoch 33, batch 1300, loss[loss=0.1526, simple_loss=0.2531, pruned_loss=0.02604, over 7171.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2596, pruned_loss=0.03006, over 1418977.78 frames.], batch size: 26, lr: 2.30e-04
2022-04-30 15:37:09,762 INFO [train.py:763] (4/8) Epoch 33, batch 1350, loss[loss=0.1757, simple_loss=0.2811, pruned_loss=0.03513, over 7218.00 frames.], tot_loss[loss=0.159, simple_loss=0.2588, pruned_loss=0.02961, over 1419877.12 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:38:16,825 INFO [train.py:763] (4/8) Epoch 33, batch 1400, loss[loss=0.1494, simple_loss=0.2515, pruned_loss=0.02367, over 7261.00 frames.], tot_loss[loss=0.1586, simple_loss=0.258, pruned_loss=0.02958, over 1422952.04 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:39:22,841 INFO [train.py:763] (4/8) Epoch 33, batch 1450, loss[loss=0.1726, simple_loss=0.2662, pruned_loss=0.03949, over 7417.00 frames.], tot_loss[loss=0.1586, simple_loss=0.258, pruned_loss=0.02953, over 1426396.97 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:40:28,337 INFO [train.py:763] (4/8) Epoch 33, batch 1500, loss[loss=0.2001, simple_loss=0.3025, pruned_loss=0.04889, over 7393.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2592, pruned_loss=0.02992, over 1424765.53 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:41:33,823 INFO [train.py:763] (4/8) Epoch 33, batch 1550, loss[loss=0.1518, simple_loss=0.2525, pruned_loss=0.02551, over 7306.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.03031, over 1422098.96 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:42:39,065 INFO [train.py:763] (4/8) Epoch 33, batch 1600, loss[loss=0.1541, simple_loss=0.2539, pruned_loss=0.02717, over 7332.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.03026, over 1422770.38 frames.], batch size: 20, lr: 2.29e-04
2022-04-30 15:43:46,167 INFO [train.py:763] (4/8) Epoch 33, batch 1650, loss[loss=0.1676, simple_loss=0.2698, pruned_loss=0.0327, over 7218.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2607, pruned_loss=0.03006, over 1422477.18 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 15:44:53,517 INFO [train.py:763] (4/8) Epoch 33, batch 1700, loss[loss=0.1783, simple_loss=0.2756, pruned_loss=0.04052, over 7392.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.02981, over 1426387.06 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:46:00,130 INFO [train.py:763] (4/8) Epoch 33, batch 1750, loss[loss=0.1641, simple_loss=0.2665, pruned_loss=0.03088, over 7078.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03005, over 1421681.60 frames.], batch size: 28, lr: 2.29e-04
2022-04-30 15:47:05,292 INFO [train.py:763] (4/8) Epoch 33, batch 1800, loss[loss=0.1899, simple_loss=0.2618, pruned_loss=0.05898, over 7286.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03013, over 1423014.02 frames.], batch size: 17, lr: 2.29e-04
2022-04-30 15:48:11,896 INFO [train.py:763] (4/8) Epoch 33, batch 1850, loss[loss=0.1603, simple_loss=0.2694, pruned_loss=0.02558, over 7316.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03022, over 1415489.62 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:49:17,340 INFO [train.py:763] (4/8) Epoch 33, batch 1900, loss[loss=0.1656, simple_loss=0.2686, pruned_loss=0.03131, over 6793.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2596, pruned_loss=0.03002, over 1411100.17 frames.], batch size: 31, lr: 2.29e-04
2022-04-30 15:50:23,825 INFO [train.py:763] (4/8) Epoch 33, batch 1950, loss[loss=0.1473, simple_loss=0.2397, pruned_loss=0.02745, over 6980.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03033, over 1417278.59 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 15:51:31,072 INFO [train.py:763] (4/8) Epoch 33, batch 2000, loss[loss=0.1425, simple_loss=0.2393, pruned_loss=0.02287, over 7405.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03013, over 1421545.26 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:52:37,439 INFO [train.py:763] (4/8) Epoch 33, batch 2050, loss[loss=0.1703, simple_loss=0.2778, pruned_loss=0.03137, over 7206.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2594, pruned_loss=0.02977, over 1420758.86 frames.], batch size: 26, lr: 2.29e-04
2022-04-30 15:53:42,707 INFO [train.py:763] (4/8) Epoch 33, batch 2100, loss[loss=0.1601, simple_loss=0.2679, pruned_loss=0.02617, over 7217.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02977, over 1423552.53 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:54:47,940 INFO [train.py:763] (4/8) Epoch 33, batch 2150, loss[loss=0.1742, simple_loss=0.2759, pruned_loss=0.03619, over 7297.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2601, pruned_loss=0.03007, over 1422981.08 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:55:53,178 INFO [train.py:763] (4/8) Epoch 33, batch 2200, loss[loss=0.1812, simple_loss=0.2754, pruned_loss=0.04346, over 7314.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2615, pruned_loss=0.03033, over 1426024.43 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:56:58,872 INFO [train.py:763] (4/8) Epoch 33, batch 2250, loss[loss=0.1574, simple_loss=0.2423, pruned_loss=0.03628, over 7285.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2618, pruned_loss=0.03091, over 1423090.74 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:58:05,269 INFO [train.py:763] (4/8) Epoch 33, batch 2300, loss[loss=0.153, simple_loss=0.2414, pruned_loss=0.03232, over 7152.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03074, over 1423890.79 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:59:10,706 INFO [train.py:763] (4/8) Epoch 33, batch 2350, loss[loss=0.1327, simple_loss=0.2313, pruned_loss=0.01706, over 7154.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2609, pruned_loss=0.03037, over 1425028.86 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 16:00:16,786 INFO [train.py:763] (4/8) Epoch 33, batch 2400, loss[loss=0.1695, simple_loss=0.2647, pruned_loss=0.03712, over 7374.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03033, over 1426068.11 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 16:01:22,889 INFO [train.py:763] (4/8) Epoch 33, batch 2450, loss[loss=0.1618, simple_loss=0.2592, pruned_loss=0.03221, over 7217.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03062, over 1421071.61 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 16:02:28,044 INFO [train.py:763] (4/8) Epoch 33, batch 2500, loss[loss=0.1386, simple_loss=0.2253, pruned_loss=0.02593, over 7008.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03063, over 1419379.44 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 16:03:33,221 INFO [train.py:763] (4/8) Epoch 33, batch 2550, loss[loss=0.1575, simple_loss=0.2634, pruned_loss=0.02583, over 7337.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03101, over 1421008.14 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:04:38,850 INFO [train.py:763] (4/8) Epoch 33, batch 2600, loss[loss=0.1329, simple_loss=0.2366, pruned_loss=0.01461, over 7060.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03122, over 1419797.16 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 16:05:45,687 INFO [train.py:763] (4/8) Epoch 33, batch 2650, loss[loss=0.1474, simple_loss=0.2607, pruned_loss=0.01699, over 7339.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03093, over 1420557.40 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:06:52,532 INFO [train.py:763] (4/8) Epoch 33, batch 2700, loss[loss=0.1345, simple_loss=0.2271, pruned_loss=0.02095, over 7285.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.0309, over 1425225.98 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:07:59,666 INFO [train.py:763] (4/8) Epoch 33, batch 2750, loss[loss=0.1584, simple_loss=0.2634, pruned_loss=0.02668, over 7316.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03078, over 1423561.37 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:09:06,751 INFO [train.py:763] (4/8) Epoch 33, batch 2800, loss[loss=0.1369, simple_loss=0.2316, pruned_loss=0.02112, over 7403.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03056, over 1428919.30 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:10:13,295 INFO [train.py:763] (4/8) Epoch 33, batch 2850, loss[loss=0.1778, simple_loss=0.2797, pruned_loss=0.03792, over 7223.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03063, over 1430197.74 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:11:18,327 INFO [train.py:763] (4/8) Epoch 33, batch 2900, loss[loss=0.1636, simple_loss=0.2672, pruned_loss=0.02997, over 7151.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.0303, over 1426590.21 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:12:24,333 INFO [train.py:763] (4/8) Epoch 33, batch 2950, loss[loss=0.1613, simple_loss=0.271, pruned_loss=0.02578, over 7145.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2595, pruned_loss=0.02986, over 1426351.88 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:13:31,369 INFO [train.py:763] (4/8) Epoch 33, batch 3000, loss[loss=0.1559, simple_loss=0.2537, pruned_loss=0.029, over 7349.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02997, over 1427518.06 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:13:31,370 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 16:13:46,765 INFO [train.py:792] (4/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
2022-04-30 16:14:51,744 INFO [train.py:763] (4/8) Epoch 33, batch 3050, loss[loss=0.1606, simple_loss=0.2586, pruned_loss=0.03126, over 7355.00 frames.], tot_loss[loss=0.1608, simple_loss=0.261, pruned_loss=0.03028, over 1427744.45 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:15:58,062 INFO [train.py:763] (4/8) Epoch 33, batch 3100, loss[loss=0.151, simple_loss=0.2446, pruned_loss=0.0287, over 7256.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2612, pruned_loss=0.03016, over 1430157.30 frames.], batch size: 16, lr: 2.28e-04
2022-04-30 16:17:04,961 INFO [train.py:763] (4/8) Epoch 33, batch 3150, loss[loss=0.1344, simple_loss=0.2226, pruned_loss=0.02315, over 7288.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02982, over 1430164.57 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:18:11,842 INFO [train.py:763] (4/8) Epoch 33, batch 3200, loss[loss=0.1934, simple_loss=0.287, pruned_loss=0.04987, over 5094.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03016, over 1425912.75 frames.], batch size: 52, lr: 2.28e-04
2022-04-30 16:19:17,471 INFO [train.py:763] (4/8) Epoch 33, batch 3250, loss[loss=0.1689, simple_loss=0.2655, pruned_loss=0.03612, over 7123.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03027, over 1423291.26 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:20:22,897 INFO [train.py:763] (4/8) Epoch 33, batch 3300, loss[loss=0.2125, simple_loss=0.3088, pruned_loss=0.05813, over 7026.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03064, over 1419634.30 frames.], batch size: 28, lr: 2.28e-04
2022-04-30 16:21:28,690 INFO [train.py:763] (4/8) Epoch 33, batch 3350, loss[loss=0.1705, simple_loss=0.278, pruned_loss=0.03155, over 7145.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2594, pruned_loss=0.03004, over 1421909.46 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:22:44,379 INFO [train.py:763] (4/8) Epoch 33, batch 3400, loss[loss=0.1621, simple_loss=0.2663, pruned_loss=0.02894, over 7193.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02985, over 1422452.87 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:23:50,288 INFO [train.py:763] (4/8) Epoch 33, batch 3450, loss[loss=0.1571, simple_loss=0.2468, pruned_loss=0.03364, over 6996.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2587, pruned_loss=0.02981, over 1427849.20 frames.], batch size: 16, lr: 2.28e-04
2022-04-30 16:24:55,491 INFO [train.py:763] (4/8) Epoch 33, batch 3500, loss[loss=0.1466, simple_loss=0.2442, pruned_loss=0.02453, over 7214.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03012, over 1429425.18 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:26:01,143 INFO [train.py:763] (4/8) Epoch 33, batch 3550, loss[loss=0.1438, simple_loss=0.2289, pruned_loss=0.0294, over 7300.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03008, over 1431406.63 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:27:06,625 INFO [train.py:763] (4/8) Epoch 33, batch 3600, loss[loss=0.174, simple_loss=0.2749, pruned_loss=0.03655, over 7320.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03041, over 1432964.14 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:28:13,474 INFO [train.py:763] (4/8) Epoch 33, batch 3650, loss[loss=0.1489, simple_loss=0.252, pruned_loss=0.02292, over 6432.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03072, over 1428072.97 frames.], batch size: 38, lr: 2.28e-04
2022-04-30 16:29:20,522 INFO [train.py:763] (4/8) Epoch 33, batch 3700, loss[loss=0.1592, simple_loss=0.2621, pruned_loss=0.0281, over 7231.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2595, pruned_loss=0.03042, over 1425139.18 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:30:26,038 INFO [train.py:763] (4/8) Epoch 33, batch 3750, loss[loss=0.1768, simple_loss=0.2864, pruned_loss=0.03363, over 7280.00 frames.], tot_loss[loss=0.16, simple_loss=0.2593, pruned_loss=0.03038, over 1422816.79 frames.], batch size: 24, lr: 2.28e-04
2022-04-30 16:31:31,698 INFO [train.py:763] (4/8) Epoch 33, batch 3800, loss[loss=0.1534, simple_loss=0.264, pruned_loss=0.02142, over 7142.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03006, over 1426270.56 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:32:38,579 INFO [train.py:763] (4/8) Epoch 33, batch 3850, loss[loss=0.18, simple_loss=0.2745, pruned_loss=0.04273, over 7200.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2597, pruned_loss=0.03057, over 1427754.18 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:33:45,459 INFO [train.py:763] (4/8) Epoch 33, batch 3900, loss[loss=0.1732, simple_loss=0.2741, pruned_loss=0.03609, over 7205.00 frames.], tot_loss[loss=0.1605, simple_loss=0.26, pruned_loss=0.0305, over 1426667.48 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:34:52,420 INFO [train.py:763] (4/8) Epoch 33, batch 3950, loss[loss=0.1537, simple_loss=0.2592, pruned_loss=0.02413, over 7323.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03063, over 1423594.41 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:35:59,190 INFO [train.py:763] (4/8) Epoch 33, batch 4000, loss[loss=0.1549, simple_loss=0.2517, pruned_loss=0.02908, over 7074.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2613, pruned_loss=0.03059, over 1424539.68 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:37:13,141 INFO [train.py:763] (4/8) Epoch 33, batch 4050, loss[loss=0.1541, simple_loss=0.258, pruned_loss=0.02505, over 7198.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03074, over 1419349.85 frames.], batch size: 26, lr: 2.27e-04
2022-04-30 16:38:27,103 INFO [train.py:763] (4/8) Epoch 33, batch 4100, loss[loss=0.1689, simple_loss=0.2753, pruned_loss=0.03121, over 6203.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03048, over 1419794.14 frames.], batch size: 37, lr: 2.27e-04
2022-04-30 16:39:41,391 INFO [train.py:763] (4/8) Epoch 33, batch 4150, loss[loss=0.1478, simple_loss=0.2399, pruned_loss=0.02782, over 7428.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 1418317.79 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:40:55,328 INFO [train.py:763] (4/8) Epoch 33, batch 4200, loss[loss=0.195, simple_loss=0.2993, pruned_loss=0.04532, over 7229.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03016, over 1420561.36 frames.], batch size: 20, lr: 2.27e-04
2022-04-30 16:42:02,046 INFO [train.py:763] (4/8) Epoch 33, batch 4250, loss[loss=0.1575, simple_loss=0.2562, pruned_loss=0.02939, over 7141.00 frames.], tot_loss[loss=0.161, simple_loss=0.2615, pruned_loss=0.03027, over 1420297.37 frames.], batch size: 17, lr: 2.27e-04
2022-04-30 16:43:17,916 INFO [train.py:763] (4/8) Epoch 33, batch 4300, loss[loss=0.1367, simple_loss=0.2263, pruned_loss=0.02361, over 6976.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2611, pruned_loss=0.02997, over 1420610.19 frames.], batch size: 16, lr: 2.27e-04
2022-04-30 16:44:24,674 INFO [train.py:763] (4/8) Epoch 33, batch 4350, loss[loss=0.154, simple_loss=0.2444, pruned_loss=0.03181, over 7193.00 frames.], tot_loss[loss=0.162, simple_loss=0.2627, pruned_loss=0.0306, over 1416527.33 frames.], batch size: 16, lr: 2.27e-04
2022-04-30 16:45:48,492 INFO [train.py:763] (4/8) Epoch 33, batch 4400, loss[loss=0.1692, simple_loss=0.2573, pruned_loss=0.04057, over 7153.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 1417769.32 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:46:53,553 INFO [train.py:763] (4/8) Epoch 33, batch 4450, loss[loss=0.1713, simple_loss=0.2817, pruned_loss=0.03048, over 7196.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03031, over 1402768.51 frames.], batch size: 23, lr: 2.27e-04
2022-04-30 16:48:00,200 INFO [train.py:763] (4/8) Epoch 33, batch 4500, loss[loss=0.2303, simple_loss=0.3122, pruned_loss=0.07421, over 4679.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03004, over 1393564.21 frames.], batch size: 53, lr: 2.27e-04
2022-04-30 16:49:05,828 INFO [train.py:763] (4/8) Epoch 33, batch 4550, loss[loss=0.1837, simple_loss=0.2752, pruned_loss=0.04606, over 4813.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2627, pruned_loss=0.03085, over 1352783.96 frames.], batch size: 53, lr: 2.27e-04
2022-04-30 16:50:25,376 INFO [train.py:763] (4/8) Epoch 34, batch 0, loss[loss=0.1798, simple_loss=0.2864, pruned_loss=0.03656, over 7232.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2864, pruned_loss=0.03656, over 7232.00 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:51:31,602 INFO [train.py:763] (4/8) Epoch 34, batch 50, loss[loss=0.1603, simple_loss=0.2638, pruned_loss=0.02839, over 7302.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03021, over 317609.43 frames.], batch size: 24, lr: 2.24e-04
2022-04-30 16:52:37,601 INFO [train.py:763] (4/8) Epoch 34, batch 100, loss[loss=0.1813, simple_loss=0.2868, pruned_loss=0.03788, over 7176.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02989, over 566986.02 frames.], batch size: 26, lr: 2.24e-04
2022-04-30 16:53:43,308 INFO [train.py:763] (4/8) Epoch 34, batch 150, loss[loss=0.1823, simple_loss=0.2804, pruned_loss=0.04212, over 7381.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03009, over 760141.60 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:54:49,441 INFO [train.py:763] (4/8) Epoch 34, batch 200, loss[loss=0.172, simple_loss=0.2627, pruned_loss=0.04069, over 7062.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03018, over 909183.09 frames.], batch size: 18, lr: 2.24e-04
2022-04-30 16:55:56,554 INFO [train.py:763] (4/8) Epoch 34, batch 250, loss[loss=0.1507, simple_loss=0.2481, pruned_loss=0.0266, over 7235.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03042, over 1026448.56 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:57:03,052 INFO [train.py:763] (4/8) Epoch 34, batch 300, loss[loss=0.1471, simple_loss=0.2423, pruned_loss=0.0259, over 7157.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03006, over 1113077.40 frames.], batch size: 19, lr: 2.24e-04
2022-04-30 16:58:08,936 INFO [train.py:763] (4/8) Epoch 34, batch 350, loss[loss=0.1756, simple_loss=0.2761, pruned_loss=0.03758, over 7206.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2586, pruned_loss=0.03004, over 1184970.46 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:59:14,457 INFO [train.py:763] (4/8) Epoch 34, batch 400, loss[loss=0.1671, simple_loss=0.2703, pruned_loss=0.03199, over 7322.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03043, over 1239013.62 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 17:00:20,016 INFO [train.py:763] (4/8) Epoch 34, batch 450, loss[loss=0.1834, simple_loss=0.2916, pruned_loss=0.03762, over 6692.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.0301, over 1283434.70 frames.], batch size: 31, lr: 2.24e-04
2022-04-30 17:01:26,960 INFO [train.py:763] (4/8) Epoch 34, batch 500, loss[loss=0.1461, simple_loss=0.2528, pruned_loss=0.01969, over 7327.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2596, pruned_loss=0.02999, over 1312781.49 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:02:32,701 INFO [train.py:763] (4/8) Epoch 34, batch 550, loss[loss=0.1325, simple_loss=0.2171, pruned_loss=0.02398, over 7076.00 frames.], tot_loss[loss=0.159, simple_loss=0.2587, pruned_loss=0.0296, over 1334020.10 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:03:38,760 INFO [train.py:763] (4/8) Epoch 34, batch 600, loss[loss=0.1422, simple_loss=0.243, pruned_loss=0.02068, over 7333.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2589, pruned_loss=0.02966, over 1353136.20 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:04:44,664 INFO [train.py:763] (4/8) Epoch 34, batch 650, loss[loss=0.1347, simple_loss=0.2382, pruned_loss=0.01555, over 7163.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.0293, over 1372177.76 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:05:50,785 INFO [train.py:763] (4/8) Epoch 34, batch 700, loss[loss=0.1486, simple_loss=0.2441, pruned_loss=0.02653, over 7293.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02962, over 1386662.09 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:06:58,023 INFO [train.py:763] (4/8) Epoch 34, batch 750, loss[loss=0.1449, simple_loss=0.2501, pruned_loss=0.01984, over 7258.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2584, pruned_loss=0.02935, over 1393978.82 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:08:04,368 INFO [train.py:763] (4/8) Epoch 34, batch 800, loss[loss=0.1673, simple_loss=0.2783, pruned_loss=0.02813, over 7223.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2586, pruned_loss=0.02918, over 1403165.37 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:09:09,693 INFO [train.py:763] (4/8) Epoch 34, batch 850, loss[loss=0.1883, simple_loss=0.2812, pruned_loss=0.0477, over 7282.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02914, over 1403054.09 frames.], batch size: 24, lr: 2.23e-04
2022-04-30 17:10:15,225 INFO [train.py:763] (4/8) Epoch 34, batch 900, loss[loss=0.1771, simple_loss=0.2722, pruned_loss=0.04103, over 5108.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02887, over 1406376.64 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:11:21,164 INFO [train.py:763] (4/8) Epoch 34, batch 950, loss[loss=0.1465, simple_loss=0.2391, pruned_loss=0.02696, over 7262.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02918, over 1410518.06 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:12:27,411 INFO [train.py:763] (4/8) Epoch 34, batch 1000, loss[loss=0.1848, simple_loss=0.2887, pruned_loss=0.04039, over 6750.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02944, over 1412099.13 frames.], batch size: 31, lr: 2.23e-04
2022-04-30 17:13:34,597 INFO [train.py:763] (4/8) Epoch 34, batch 1050, loss[loss=0.1623, simple_loss=0.2784, pruned_loss=0.02309, over 7411.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02921, over 1416320.73 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:14:40,034 INFO [train.py:763] (4/8) Epoch 34, batch 1100, loss[loss=0.1568, simple_loss=0.2547, pruned_loss=0.02948, over 7350.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02909, over 1420019.24 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:15:45,148 INFO [train.py:763] (4/8) Epoch 34, batch 1150, loss[loss=0.1707, simple_loss=0.2683, pruned_loss=0.03655, over 7205.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02911, over 1421797.22 frames.], batch size: 23, lr: 2.23e-04
2022-04-30 17:16:50,470 INFO [train.py:763] (4/8) Epoch 34, batch 1200, loss[loss=0.1476, simple_loss=0.2388, pruned_loss=0.02821, over 7274.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02923, over 1425766.54 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:17:56,080 INFO [train.py:763] (4/8) Epoch 34, batch 1250, loss[loss=0.1752, simple_loss=0.292, pruned_loss=0.02922, over 7329.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02981, over 1425077.70 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:19:02,071 INFO [train.py:763] (4/8) Epoch 34, batch 1300, loss[loss=0.1634, simple_loss=0.264, pruned_loss=0.03139, over 7014.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03032, over 1421230.40 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:20:07,319 INFO [train.py:763] (4/8) Epoch 34, batch 1350, loss[loss=0.1688, simple_loss=0.2763, pruned_loss=0.0306, over 7047.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03021, over 1423852.12 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:21:12,462 INFO [train.py:763] (4/8) Epoch 34, batch 1400, loss[loss=0.1312, simple_loss=0.2305, pruned_loss=0.01593, over 7315.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03041, over 1421153.25 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:22:17,955 INFO [train.py:763] (4/8) Epoch 34, batch 1450, loss[loss=0.167, simple_loss=0.2688, pruned_loss=0.03264, over 7265.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03034, over 1418456.49 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:23:24,433 INFO [train.py:763] (4/8) Epoch 34, batch 1500, loss[loss=0.1388, simple_loss=0.2352, pruned_loss=0.02125, over 7132.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.03052, over 1419596.01 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:24:29,697 INFO [train.py:763] (4/8) Epoch 34, batch 1550, loss[loss=0.1923, simple_loss=0.2982, pruned_loss=0.04322, over 7226.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03081, over 1420037.11 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:25:36,472 INFO [train.py:763] (4/8) Epoch 34, batch 1600, loss[loss=0.1876, simple_loss=0.2908, pruned_loss=0.04222, over 7119.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03095, over 1422217.46 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:26:43,358 INFO [train.py:763] (4/8) Epoch 34, batch 1650, loss[loss=0.1425, simple_loss=0.2383, pruned_loss=0.02331, over 7402.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03041, over 1426649.49 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:27:48,833 INFO [train.py:763] (4/8) Epoch 34, batch 1700, loss[loss=0.1904, simple_loss=0.2837, pruned_loss=0.04852, over 5277.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.03031, over 1426258.12 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:28:54,320 INFO [train.py:763] (4/8) Epoch 34, batch 1750, loss[loss=0.1433, simple_loss=0.2422, pruned_loss=0.02221, over 7164.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2592, pruned_loss=0.03007, over 1425872.33 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:29:59,723 INFO [train.py:763] (4/8) Epoch 34, batch 1800, loss[loss=0.1804, simple_loss=0.2808, pruned_loss=0.03997, over 7277.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2582, pruned_loss=0.02938, over 1429587.24 frames.], batch size: 25, lr: 2.23e-04
2022-04-30 17:31:04,980 INFO [train.py:763] (4/8) Epoch 34, batch 1850, loss[loss=0.145, simple_loss=0.2493, pruned_loss=0.02036, over 7061.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2584, pruned_loss=0.02987, over 1426174.91 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:32:10,317 INFO [train.py:763] (4/8) Epoch 34, batch 1900, loss[loss=0.1853, simple_loss=0.2773, pruned_loss=0.04671, over 7383.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2589, pruned_loss=0.03007, over 1426426.39 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:33:15,840 INFO [train.py:763] (4/8) Epoch 34, batch 1950, loss[loss=0.149, simple_loss=0.2408, pruned_loss=0.02859, over 7142.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2589, pruned_loss=0.02992, over 1424957.55 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:34:22,078 INFO [train.py:763] (4/8) Epoch 34, batch 2000, loss[loss=0.1623, simple_loss=0.2647, pruned_loss=0.02993, over 6639.00 frames.], tot_loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03014, over 1420848.22 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:35:27,873 INFO [train.py:763] (4/8) Epoch 34, batch 2050, loss[loss=0.159, simple_loss=0.2637, pruned_loss=0.02715, over 7115.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03039, over 1422348.26 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:36:33,091 INFO [train.py:763] (4/8) Epoch 34, batch 2100, loss[loss=0.1505, simple_loss=0.2622, pruned_loss=0.01937, over 7426.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03036, over 1425153.49 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:37:40,124 INFO [train.py:763] (4/8) Epoch 34, batch 2150, loss[loss=0.1535, simple_loss=0.257, pruned_loss=0.02503, over 6200.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02985, over 1427858.34 frames.], batch size: 37, lr: 2.22e-04
2022-04-30 17:38:46,194 INFO [train.py:763] (4/8) Epoch 34, batch 2200, loss[loss=0.1555, simple_loss=0.2572, pruned_loss=0.02688, over 7434.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02967, over 1424560.27 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:39:51,383 INFO [train.py:763] (4/8) Epoch 34, batch 2250, loss[loss=0.1428, simple_loss=0.2323, pruned_loss=0.02668, over 7276.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02962, over 1422343.78 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:40:56,556 INFO [train.py:763] (4/8) Epoch 34, batch 2300, loss[loss=0.1632, simple_loss=0.2727, pruned_loss=0.02688, over 7166.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02936, over 1418655.86 frames.], batch size: 26, lr: 2.22e-04
2022-04-30 17:42:01,777 INFO [train.py:763] (4/8) Epoch 34, batch 2350, loss[loss=0.1615, simple_loss=0.2761, pruned_loss=0.02341, over 7123.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02967, over 1416666.82 frames.], batch size: 28, lr: 2.22e-04
2022-04-30 17:43:08,012 INFO [train.py:763] (4/8) Epoch 34, batch 2400, loss[loss=0.1454, simple_loss=0.2287, pruned_loss=0.03105, over 7009.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02946, over 1422368.34 frames.], batch size: 16, lr: 2.22e-04
2022-04-30 17:44:15,062 INFO [train.py:763] (4/8) Epoch 34, batch 2450, loss[loss=0.1572, simple_loss=0.2532, pruned_loss=0.03061, over 7429.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02914, over 1422597.99 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:45:22,379 INFO [train.py:763] (4/8) Epoch 34, batch 2500, loss[loss=0.1713, simple_loss=0.2686, pruned_loss=0.037, over 6515.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2583, pruned_loss=0.02929, over 1423951.32 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:46:28,711 INFO [train.py:763] (4/8) Epoch 34, batch 2550, loss[loss=0.1632, simple_loss=0.2763, pruned_loss=0.02509, over 7106.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.0297, over 1423997.38 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:47:35,754 INFO [train.py:763] (4/8) Epoch 34, batch 2600, loss[loss=0.1974, simple_loss=0.2967, pruned_loss=0.04904, over 7198.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02978, over 1424306.42 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 17:48:40,938 INFO [train.py:763] (4/8) Epoch 34, batch 2650, loss[loss=0.1891, simple_loss=0.292, pruned_loss=0.04309, over 7190.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02973, over 1422743.91 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:49:46,277 INFO [train.py:763] (4/8) Epoch 34, batch 2700, loss[loss=0.1566, simple_loss=0.2674, pruned_loss=0.02293, over 7112.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02976, over 1424543.98 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:50:51,541 INFO [train.py:763] (4/8) Epoch 34, batch 2750, loss[loss=0.1616, simple_loss=0.2624, pruned_loss=0.03045, over 7318.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03024, over 1424180.39 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:51:57,727 INFO [train.py:763] (4/8) Epoch 34, batch 2800, loss[loss=0.1496, simple_loss=0.2469, pruned_loss=0.02617, over 7332.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.02998, over 1425189.81 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:53:04,496 INFO [train.py:763] (4/8) Epoch 34, batch 2850, loss[loss=0.1472, simple_loss=0.2512, pruned_loss=0.02158, over 7155.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.02998, over 1423835.40 frames.], batch size: 19, lr: 2.22e-04
2022-04-30 17:54:11,622 INFO [train.py:763] (4/8) Epoch 34, batch 2900, loss[loss=0.1726, simple_loss=0.2712, pruned_loss=0.03706, over 6387.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03023, over 1422609.11 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:55:17,490 INFO [train.py:763] (4/8) Epoch 34, batch 2950, loss[loss=0.146, simple_loss=0.2317, pruned_loss=0.03016, over 6822.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03022, over 1416405.17 frames.], batch size: 15, lr: 2.22e-04
2022-04-30 17:56:22,954 INFO [train.py:763] (4/8) Epoch 34, batch 3000, loss[loss=0.1947, simple_loss=0.2874, pruned_loss=0.05106, over 7379.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.0301, over 1420575.04 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:56:22,954 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 17:56:38,271 INFO [train.py:792] (4/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
2022-04-30 17:57:44,331 INFO [train.py:763] (4/8) Epoch 34, batch 3050, loss[loss=0.1654, simple_loss=0.2641, pruned_loss=0.0334, over 7241.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02983, over 1423424.54 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:58:51,169 INFO [train.py:763] (4/8) Epoch 34, batch 3100, loss[loss=0.159, simple_loss=0.2621, pruned_loss=0.028, over 7377.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03003, over 1420598.32 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:59:56,667 INFO [train.py:763] (4/8) Epoch 34, batch 3150, loss[loss=0.1814, simple_loss=0.2826, pruned_loss=0.04006, over 7211.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02974, over 1424147.70 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:01:02,257 INFO [train.py:763] (4/8) Epoch 34, batch 3200, loss[loss=0.1743, simple_loss=0.2706, pruned_loss=0.03896, over 7222.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.0298, over 1428167.00 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:02:09,377 INFO [train.py:763] (4/8) Epoch 34, batch 3250, loss[loss=0.1512, simple_loss=0.2443, pruned_loss=0.029, over 7438.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2598, pruned_loss=0.02965, over 1427125.30 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:03:15,758 INFO [train.py:763] (4/8) Epoch 34, batch 3300, loss[loss=0.1606, simple_loss=0.2568, pruned_loss=0.03222, over 7437.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02956, over 1428718.65 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:04:21,124 INFO [train.py:763] (4/8) Epoch 34, batch 3350, loss[loss=0.155, simple_loss=0.258, pruned_loss=0.02597, over 7432.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02919, over 1431931.98 frames.], batch size: 20, lr: 2.21e-04
2022-04-30 18:05:26,505 INFO [train.py:763] (4/8) Epoch 34, batch 3400, loss[loss=0.1739, simple_loss=0.2637, pruned_loss=0.042, over 7282.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02958, over 1429043.47 frames.], batch size: 18, lr: 2.21e-04
2022-04-30 18:06:31,933 INFO [train.py:763] (4/8) Epoch 34, batch 3450, loss[loss=0.1364, simple_loss=0.2242, pruned_loss=0.02426, over 7014.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02961, over 1431565.93 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:07:37,448 INFO [train.py:763] (4/8) Epoch 34, batch 3500, loss[loss=0.1546, simple_loss=0.2642, pruned_loss=0.02244, over 7336.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02917, over 1429957.10 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:08:42,508 INFO [train.py:763] (4/8) Epoch 34, batch 3550, loss[loss=0.1622, simple_loss=0.2664, pruned_loss=0.02902, over 6768.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02904, over 1422442.45 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:09:48,190 INFO [train.py:763] (4/8) Epoch 34, batch 3600, loss[loss=0.1843, simple_loss=0.2861, pruned_loss=0.04121, over 7206.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02925, over 1421001.24 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:10:55,325 INFO [train.py:763] (4/8) Epoch 34, batch 3650, loss[loss=0.1687, simple_loss=0.2657, pruned_loss=0.03591, over 7315.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.0297, over 1422019.27 frames.], batch size: 25, lr: 2.21e-04
2022-04-30 18:12:01,491 INFO [train.py:763] (4/8) Epoch 34, batch 3700, loss[loss=0.164, simple_loss=0.2715, pruned_loss=0.02829, over 6457.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02951, over 1420738.19 frames.], batch size: 37, lr: 2.21e-04
2022-04-30 18:13:06,699 INFO [train.py:763] (4/8) Epoch 34, batch 3750, loss[loss=0.192, simple_loss=0.2942, pruned_loss=0.04495, over 4977.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02968, over 1418062.55 frames.], batch size: 52, lr: 2.21e-04
2022-04-30 18:14:11,983 INFO [train.py:763] (4/8) Epoch 34, batch 3800, loss[loss=0.1606, simple_loss=0.2736, pruned_loss=0.02379, over 6767.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.0295, over 1418857.66 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:15:17,333 INFO [train.py:763] (4/8) Epoch 34, batch 3850, loss[loss=0.1778, simple_loss=0.2793, pruned_loss=0.03814, over 7289.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2602, pruned_loss=0.02968, over 1422123.18 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:16:23,808 INFO [train.py:763] (4/8) Epoch 34, batch 3900, loss[loss=0.1425, simple_loss=0.2336, pruned_loss=0.02573, over 6787.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2615, pruned_loss=0.03046, over 1418075.36 frames.], batch size: 15, lr: 2.21e-04
2022-04-30 18:17:30,966 INFO [train.py:763] (4/8) Epoch 34, batch 3950, loss[loss=0.142, simple_loss=0.2323, pruned_loss=0.02588, over 7137.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2611, pruned_loss=0.0303, over 1419690.62 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:18:37,950 INFO [train.py:763] (4/8) Epoch 34, batch 4000, loss[loss=0.155, simple_loss=0.2383, pruned_loss=0.0358, over 7001.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03012, over 1419038.17 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:19:54,711 INFO [train.py:763] (4/8) Epoch 34, batch 4050, loss[loss=0.1666, simple_loss=0.2752, pruned_loss=0.029, over 6298.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2609, pruned_loss=0.03012, over 1422131.06 frames.], batch size: 37, lr: 2.21e-04
2022-04-30 18:21:01,770 INFO [train.py:763] (4/8) Epoch 34, batch 4100, loss[loss=0.1459, simple_loss=0.2501, pruned_loss=0.02083, over 7214.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2602, pruned_loss=0.02966, over 1426685.77 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:22:08,648 INFO [train.py:763] (4/8) Epoch 34, batch 4150, loss[loss=0.1375, simple_loss=0.2409, pruned_loss=0.0171, over 7316.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02985, over 1424724.60 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:23:15,039 INFO [train.py:763] (4/8) Epoch 34, batch 4200, loss[loss=0.1713, simple_loss=0.2716, pruned_loss=0.03548, over 7319.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.03004, over 1423134.36 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:24:20,536 INFO [train.py:763] (4/8) Epoch 34, batch 4250, loss[loss=0.1306, simple_loss=0.2262, pruned_loss=0.01748, over 7284.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.0295, over 1427770.31 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:25:25,961 INFO [train.py:763] (4/8) Epoch 34, batch 4300, loss[loss=0.1925, simple_loss=0.295, pruned_loss=0.04494, over 7151.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.0298, over 1419024.69 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:26:32,708 INFO [train.py:763] (4/8) Epoch 34, batch 4350, loss[loss=0.1803, simple_loss=0.2816, pruned_loss=0.0395, over 7281.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.0303, over 1414507.56 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:27:38,204 INFO [train.py:763] (4/8) Epoch 34, batch 4400, loss[loss=0.1504, simple_loss=0.2563, pruned_loss=0.02223, over 7166.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03037, over 1408857.65 frames.], batch size: 19, lr: 2.21e-04
2022-04-30 18:28:42,659 INFO [train.py:763] (4/8) Epoch 34, batch 4450, loss[loss=0.1643, simple_loss=0.268, pruned_loss=0.03036, over 6831.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2606, pruned_loss=0.03028, over 1393963.81 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:29:47,243 INFO [train.py:763] (4/8) Epoch 34, batch 4500, loss[loss=0.1763, simple_loss=0.2806, pruned_loss=0.03597, over 7187.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2617, pruned_loss=0.03096, over 1380886.18 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:30:51,772 INFO [train.py:763] (4/8) Epoch 34, batch 4550, loss[loss=0.1941, simple_loss=0.2848, pruned_loss=0.05172, over 4875.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2634, pruned_loss=0.03169, over 1355457.40 frames.], batch size: 53, lr: 2.21e-04
2022-04-30 18:32:11,385 INFO [train.py:763] (4/8) Epoch 35, batch 0, loss[loss=0.1405, simple_loss=0.2458, pruned_loss=0.01766, over 7342.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2458, pruned_loss=0.01766, over 7342.00 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:33:17,372 INFO [train.py:763] (4/8) Epoch 35, batch 50, loss[loss=0.1519, simple_loss=0.2521, pruned_loss=0.02586, over 7418.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2578, pruned_loss=0.02999, over 316325.16 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:34:22,742 INFO [train.py:763] (4/8) Epoch 35, batch 100, loss[loss=0.1837, simple_loss=0.2775, pruned_loss=0.04494, over 4849.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02867, over 561351.72 frames.], batch size: 52, lr: 2.17e-04
2022-04-30 18:35:28,400 INFO [train.py:763] (4/8) Epoch 35, batch 150, loss[loss=0.1457, simple_loss=0.243, pruned_loss=0.02415, over 7234.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2573, pruned_loss=0.02895, over 750116.94 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:36:34,084 INFO [train.py:763] (4/8) Epoch 35, batch 200, loss[loss=0.1521, simple_loss=0.2611, pruned_loss=0.02157, over 7317.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02868, over 900273.30 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:37:50,840 INFO [train.py:763] (4/8) Epoch 35, batch 250, loss[loss=0.1433, simple_loss=0.2353, pruned_loss=0.02569, over 7151.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2577, pruned_loss=0.02924, over 1020133.80 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:38:58,239 INFO [train.py:763] (4/8) Epoch 35, batch 300, loss[loss=0.1707, simple_loss=0.2738, pruned_loss=0.03377, over 7183.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.02923, over 1105227.55 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:40:05,543 INFO [train.py:763] (4/8) Epoch 35, batch 350, loss[loss=0.1748, simple_loss=0.2749, pruned_loss=0.03732, over 6707.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02907, over 1174549.64 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:41:12,765 INFO [train.py:763] (4/8) Epoch 35, batch 400, loss[loss=0.1693, simple_loss=0.2862, pruned_loss=0.02615, over 7203.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02955, over 1230995.24 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:42:19,848 INFO [train.py:763] (4/8) Epoch 35, batch 450, loss[loss=0.1927, simple_loss=0.2884, pruned_loss=0.04852, over 7157.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2604, pruned_loss=0.02929, over 1278783.08 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:43:25,152 INFO [train.py:763] (4/8) Epoch 35, batch 500, loss[loss=0.1846, simple_loss=0.2878, pruned_loss=0.04065, over 7187.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2619, pruned_loss=0.0298, over 1310802.81 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:44:30,965 INFO [train.py:763] (4/8) Epoch 35, batch 550, loss[loss=0.1462, simple_loss=0.2427, pruned_loss=0.02491, over 7437.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2624, pruned_loss=0.02994, over 1336699.17 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:45:37,225 INFO [train.py:763] (4/8) Epoch 35, batch 600, loss[loss=0.1767, simple_loss=0.2695, pruned_loss=0.04192, over 7222.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2608, pruned_loss=0.02975, over 1359055.77 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:46:44,897 INFO [train.py:763] (4/8) Epoch 35, batch 650, loss[loss=0.1387, simple_loss=0.238, pruned_loss=0.01977, over 7160.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02935, over 1373512.06 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:47:52,732 INFO [train.py:763] (4/8) Epoch 35, batch 700, loss[loss=0.1379, simple_loss=0.2426, pruned_loss=0.01657, over 7252.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02923, over 1385518.38 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:48:58,270 INFO [train.py:763] (4/8) Epoch 35, batch 750, loss[loss=0.1639, simple_loss=0.2668, pruned_loss=0.03047, over 7329.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02942, over 1385569.30 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:50:03,732 INFO [train.py:763] (4/8) Epoch 35, batch 800, loss[loss=0.1646, simple_loss=0.271, pruned_loss=0.0291, over 7415.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02927, over 1393639.66 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:51:09,199 INFO [train.py:763] (4/8) Epoch 35, batch 850, loss[loss=0.1721, simple_loss=0.2791, pruned_loss=0.0325, over 7226.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.0297, over 1394699.21 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:52:23,428 INFO [train.py:763] (4/8) Epoch 35, batch 900, loss[loss=0.1667, simple_loss=0.2688, pruned_loss=0.03228, over 6875.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.0297, over 1401564.73 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:53:37,764 INFO [train.py:763] (4/8) Epoch 35, batch 950, loss[loss=0.1366, simple_loss=0.2261, pruned_loss=0.02358, over 6988.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02987, over 1404981.42 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 18:54:42,877 INFO [train.py:763] (4/8) Epoch 35, batch 1000, loss[loss=0.1476, simple_loss=0.244, pruned_loss=0.02561, over 7285.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02943, over 1406859.15 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 18:55:57,239 INFO [train.py:763] (4/8) Epoch 35, batch 1050, loss[loss=0.1495, simple_loss=0.2507, pruned_loss=0.02414, over 7361.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02915, over 1406818.28 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:57:20,298 INFO [train.py:763] (4/8) Epoch 35, batch 1100, loss[loss=0.157, simple_loss=0.2565, pruned_loss=0.02869, over 7202.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02941, over 1407406.51 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:58:25,985 INFO [train.py:763] (4/8) Epoch 35, batch 1150, loss[loss=0.1673, simple_loss=0.2721, pruned_loss=0.03121, over 7295.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02912, over 1413235.05 frames.], batch size: 24, lr: 2.17e-04
2022-04-30 18:59:32,074 INFO [train.py:763] (4/8) Epoch 35, batch 1200, loss[loss=0.1382, simple_loss=0.2279, pruned_loss=0.02426, over 7273.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2603, pruned_loss=0.02968, over 1409998.85 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:00:55,257 INFO [train.py:763] (4/8) Epoch 35, batch 1250, loss[loss=0.1631, simple_loss=0.2558, pruned_loss=0.03516, over 6987.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02944, over 1410861.40 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:02:00,723 INFO [train.py:763] (4/8) Epoch 35, batch 1300, loss[loss=0.1451, simple_loss=0.2421, pruned_loss=0.024, over 7130.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03002, over 1414874.18 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:03:07,765 INFO [train.py:763] (4/8) Epoch 35, batch 1350, loss[loss=0.1589, simple_loss=0.2522, pruned_loss=0.03275, over 7264.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03021, over 1419601.68 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 19:04:12,913 INFO [train.py:763] (4/8) Epoch 35, batch 1400, loss[loss=0.143, simple_loss=0.2406, pruned_loss=0.02264, over 6985.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03035, over 1418127.43 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:05:18,833 INFO [train.py:763] (4/8) Epoch 35, batch 1450, loss[loss=0.1454, simple_loss=0.238, pruned_loss=0.02637, over 6781.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2604, pruned_loss=0.03029, over 1414818.79 frames.], batch size: 15, lr: 2.17e-04
2022-04-30 19:06:24,725 INFO [train.py:763] (4/8) Epoch 35, batch 1500, loss[loss=0.1446, simple_loss=0.2582, pruned_loss=0.01552, over 7322.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.0301, over 1418819.08 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 19:07:30,577 INFO [train.py:763] (4/8) Epoch 35, batch 1550, loss[loss=0.1684, simple_loss=0.2769, pruned_loss=0.02995, over 7235.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2609, pruned_loss=0.02978, over 1420675.69 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 19:08:36,015 INFO [train.py:763] (4/8) Epoch 35, batch 1600, loss[loss=0.1831, simple_loss=0.2826, pruned_loss=0.04181, over 7388.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02923, over 1420247.71 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:09:42,621 INFO [train.py:763] (4/8) Epoch 35, batch 1650, loss[loss=0.1484, simple_loss=0.2446, pruned_loss=0.02604, over 7169.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2595, pruned_loss=0.02917, over 1421081.74 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:10:49,563 INFO [train.py:763] (4/8) Epoch 35, batch 1700, loss[loss=0.1645, simple_loss=0.2706, pruned_loss=0.02919, over 7273.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2607, pruned_loss=0.02934, over 1423622.99 frames.], batch size: 25, lr: 2.16e-04
2022-04-30 19:11:56,502 INFO [train.py:763] (4/8) Epoch 35, batch 1750, loss[loss=0.175, simple_loss=0.2657, pruned_loss=0.04213, over 7270.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2616, pruned_loss=0.03015, over 1419340.96 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:13:03,547 INFO [train.py:763] (4/8) Epoch 35, batch 1800, loss[loss=0.164, simple_loss=0.2608, pruned_loss=0.03362, over 7192.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2617, pruned_loss=0.03008, over 1422057.79 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:14:09,378 INFO [train.py:763] (4/8) Epoch 35, batch 1850, loss[loss=0.1707, simple_loss=0.2766, pruned_loss=0.03238, over 7116.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2612, pruned_loss=0.02988, over 1424994.82 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:15:15,150 INFO [train.py:763] (4/8) Epoch 35, batch 1900, loss[loss=0.1483, simple_loss=0.2587, pruned_loss=0.01898, over 6786.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2608, pruned_loss=0.02964, over 1425446.73 frames.], batch size: 31, lr: 2.16e-04
2022-04-30 19:16:21,439 INFO [train.py:763] (4/8) Epoch 35, batch 1950, loss[loss=0.139, simple_loss=0.2445, pruned_loss=0.01677, over 7243.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.02975, over 1423293.01 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:17:27,459 INFO [train.py:763] (4/8) Epoch 35, batch 2000, loss[loss=0.1392, simple_loss=0.2289, pruned_loss=0.02473, over 6996.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02991, over 1420878.04 frames.], batch size: 16, lr: 2.16e-04
2022-04-30 19:18:34,496 INFO [train.py:763] (4/8) Epoch 35, batch 2050, loss[loss=0.2157, simple_loss=0.3187, pruned_loss=0.05634, over 7319.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2613, pruned_loss=0.0301, over 1425305.88 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:19:40,350 INFO [train.py:763] (4/8) Epoch 35, batch 2100, loss[loss=0.1609, simple_loss=0.2642, pruned_loss=0.02882, over 7415.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2603, pruned_loss=0.02953, over 1423875.44 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:20:47,325 INFO [train.py:763] (4/8) Epoch 35, batch 2150, loss[loss=0.1455, simple_loss=0.2474, pruned_loss=0.02178, over 7268.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02911, over 1426009.01 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:21:54,056 INFO [train.py:763] (4/8) Epoch 35, batch 2200, loss[loss=0.1475, simple_loss=0.2485, pruned_loss=0.02323, over 7415.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02903, over 1425471.76 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:23:01,260 INFO [train.py:763] (4/8) Epoch 35, batch 2250, loss[loss=0.1555, simple_loss=0.2689, pruned_loss=0.02109, over 7331.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2598, pruned_loss=0.02902, over 1422199.39 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:24:07,984 INFO [train.py:763] (4/8) Epoch 35, batch 2300, loss[loss=0.1404, simple_loss=0.2331, pruned_loss=0.0239, over 7134.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.029, over 1425587.06 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:25:12,952 INFO [train.py:763] (4/8) Epoch 35, batch 2350, loss[loss=0.1935, simple_loss=0.281, pruned_loss=0.05301, over 5179.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02945, over 1424314.51 frames.], batch size: 52, lr: 2.16e-04
2022-04-30 19:26:18,888 INFO [train.py:763] (4/8) Epoch 35, batch 2400, loss[loss=0.1459, simple_loss=0.2396, pruned_loss=0.02606, over 7408.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02912, over 1426987.09 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:27:24,048 INFO [train.py:763] (4/8) Epoch 35, batch 2450, loss[loss=0.1696, simple_loss=0.2761, pruned_loss=0.03159, over 7155.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02962, over 1422288.90 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:28:30,197 INFO [train.py:763] (4/8) Epoch 35, batch 2500, loss[loss=0.1474, simple_loss=0.252, pruned_loss=0.02143, over 7147.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2585, pruned_loss=0.02956, over 1426366.79 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:29:36,781 INFO [train.py:763] (4/8) Epoch 35, batch 2550, loss[loss=0.1497, simple_loss=0.2521, pruned_loss=0.02368, over 7361.00 frames.], tot_loss[loss=0.159, simple_loss=0.2587, pruned_loss=0.02962, over 1422478.08 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:30:41,921 INFO [train.py:763] (4/8) Epoch 35, batch 2600, loss[loss=0.148, simple_loss=0.2508, pruned_loss=0.02262, over 7164.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.02974, over 1423453.32 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:31:47,693 INFO [train.py:763] (4/8) Epoch 35, batch 2650, loss[loss=0.2222, simple_loss=0.3116, pruned_loss=0.06641, over 5492.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02977, over 1422395.22 frames.], batch size: 52, lr: 2.16e-04
2022-04-30 19:32:53,211 INFO [train.py:763] (4/8) Epoch 35, batch 2700, loss[loss=0.1448, simple_loss=0.252, pruned_loss=0.01883, over 7323.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02966, over 1423380.33 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:33:59,267 INFO [train.py:763] (4/8) Epoch 35, batch 2750, loss[loss=0.1572, simple_loss=0.2691, pruned_loss=0.0226, over 7124.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02965, over 1425661.16 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:35:05,455 INFO [train.py:763] (4/8) Epoch 35, batch 2800, loss[loss=0.1657, simple_loss=0.2737, pruned_loss=0.02884, over 7197.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2583, pruned_loss=0.02911, over 1426980.75 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:36:12,138 INFO [train.py:763] (4/8) Epoch 35, batch 2850, loss[loss=0.1379, simple_loss=0.2258, pruned_loss=0.02501, over 7258.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2584, pruned_loss=0.02931, over 1427615.03 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:37:18,074 INFO [train.py:763] (4/8) Epoch 35, batch 2900, loss[loss=0.1444, simple_loss=0.2433, pruned_loss=0.02279, over 7259.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2578, pruned_loss=0.02933, over 1426364.42 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:38:23,359 INFO [train.py:763] (4/8) Epoch 35, batch 2950, loss[loss=0.1537, simple_loss=0.2521, pruned_loss=0.02765, over 7171.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.02953, over 1424668.69 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:39:28,870 INFO [train.py:763] (4/8) Epoch 35, batch 3000, loss[loss=0.1281, simple_loss=0.2264, pruned_loss=0.0149, over 7160.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2603, pruned_loss=0.03002, over 1421977.73 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:39:28,871 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 19:39:43,929 INFO [train.py:792] (4/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
2022-04-30 19:40:49,415 INFO [train.py:763] (4/8) Epoch 35, batch 3050, loss[loss=0.1642, simple_loss=0.2587, pruned_loss=0.03488, over 7304.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.03002, over 1424929.50 frames.], batch size: 24, lr: 2.16e-04
2022-04-30 19:41:55,471 INFO [train.py:763] (4/8) Epoch 35, batch 3100, loss[loss=0.1785, simple_loss=0.2796, pruned_loss=0.03869, over 7298.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2612, pruned_loss=0.03002, over 1429244.62 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:43:02,575 INFO [train.py:763] (4/8) Epoch 35, batch 3150, loss[loss=0.1736, simple_loss=0.2697, pruned_loss=0.03874, over 7379.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03035, over 1427328.30 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:44:09,425 INFO [train.py:763] (4/8) Epoch 35, batch 3200, loss[loss=0.1388, simple_loss=0.2322, pruned_loss=0.02273, over 7127.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03036, over 1421393.17 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:45:15,565 INFO [train.py:763] (4/8) Epoch 35, batch 3250, loss[loss=0.1526, simple_loss=0.2577, pruned_loss=0.02374, over 5210.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2608, pruned_loss=0.0305, over 1419032.08 frames.], batch size: 52, lr: 2.15e-04
2022-04-30 19:46:21,010 INFO [train.py:763] (4/8) Epoch 35, batch 3300, loss[loss=0.1826, simple_loss=0.2862, pruned_loss=0.03948, over 7208.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03038, over 1422208.08 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:47:26,297 INFO [train.py:763] (4/8) Epoch 35, batch 3350, loss[loss=0.1588, simple_loss=0.2644, pruned_loss=0.02657, over 7195.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02995, over 1426303.85 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:48:32,220 INFO [train.py:763] (4/8) Epoch 35, batch 3400, loss[loss=0.1576, simple_loss=0.2493, pruned_loss=0.03301, over 7255.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02984, over 1424646.40 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:49:37,615 INFO [train.py:763] (4/8) Epoch 35, batch 3450, loss[loss=0.13, simple_loss=0.2166, pruned_loss=0.02177, over 7281.00 frames.], tot_loss[loss=0.159, simple_loss=0.2594, pruned_loss=0.02937, over 1422208.25 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:50:43,216 INFO [train.py:763] (4/8) Epoch 35, batch 3500, loss[loss=0.1679, simple_loss=0.2757, pruned_loss=0.03007, over 7406.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02939, over 1419327.70 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:51:48,954 INFO [train.py:763] (4/8) Epoch 35, batch 3550, loss[loss=0.1875, simple_loss=0.2809, pruned_loss=0.04704, over 7045.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02945, over 1423017.64 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 19:52:54,514 INFO [train.py:763] (4/8) Epoch 35, batch 3600, loss[loss=0.1605, simple_loss=0.2643, pruned_loss=0.02837, over 7269.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02936, over 1421465.12 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:54:00,483 INFO [train.py:763] (4/8) Epoch 35, batch 3650, loss[loss=0.1721, simple_loss=0.2799, pruned_loss=0.0322, over 7275.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.0291, over 1423396.03 frames.], batch size: 24, lr: 2.15e-04
2022-04-30 19:55:05,852 INFO [train.py:763] (4/8) Epoch 35, batch 3700, loss[loss=0.1585, simple_loss=0.2688, pruned_loss=0.02415, over 7117.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02913, over 1426299.28 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:56:11,427 INFO [train.py:763] (4/8) Epoch 35, batch 3750, loss[loss=0.1781, simple_loss=0.2719, pruned_loss=0.04218, over 7332.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2582, pruned_loss=0.02913, over 1425906.16 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 19:57:16,644 INFO [train.py:763] (4/8) Epoch 35, batch 3800, loss[loss=0.1426, simple_loss=0.2393, pruned_loss=0.023, over 7362.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.0296, over 1427733.25 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:58:21,845 INFO [train.py:763] (4/8) Epoch 35, batch 3850, loss[loss=0.1297, simple_loss=0.2191, pruned_loss=0.02018, over 7008.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2605, pruned_loss=0.02962, over 1423550.36 frames.], batch size: 16, lr: 2.15e-04
2022-04-30 19:59:27,365 INFO [train.py:763] (4/8) Epoch 35, batch 3900, loss[loss=0.1663, simple_loss=0.2687, pruned_loss=0.03188, over 7221.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02974, over 1425801.41 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:00:33,648 INFO [train.py:763] (4/8) Epoch 35, batch 3950, loss[loss=0.148, simple_loss=0.2565, pruned_loss=0.01973, over 6669.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2613, pruned_loss=0.03001, over 1423888.12 frames.], batch size: 31, lr: 2.15e-04
2022-04-30 20:01:41,040 INFO [train.py:763] (4/8) Epoch 35, batch 4000, loss[loss=0.1608, simple_loss=0.2663, pruned_loss=0.02767, over 6967.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2614, pruned_loss=0.03004, over 1424141.82 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 20:02:46,170 INFO [train.py:763] (4/8) Epoch 35, batch 4050, loss[loss=0.1685, simple_loss=0.2732, pruned_loss=0.03184, over 7222.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2607, pruned_loss=0.02936, over 1426587.06 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:03:51,644 INFO [train.py:763] (4/8) Epoch 35, batch 4100, loss[loss=0.141, simple_loss=0.2316, pruned_loss=0.02518, over 7115.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02955, over 1426780.35 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 20:04:57,463 INFO [train.py:763] (4/8) Epoch 35, batch 4150, loss[loss=0.1825, simple_loss=0.2842, pruned_loss=0.04039, over 7201.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2598, pruned_loss=0.0295, over 1418572.48 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:06:03,148 INFO [train.py:763] (4/8) Epoch 35, batch 4200, loss[loss=0.1463, simple_loss=0.2505, pruned_loss=0.02108, over 7239.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02972, over 1416900.28 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:07:09,098 INFO [train.py:763] (4/8) Epoch 35, batch 4250, loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03683, over 7208.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2598, pruned_loss=0.03, over 1416010.60 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:08:14,295 INFO [train.py:763] (4/8) Epoch 35, batch 4300, loss[loss=0.1546, simple_loss=0.2586, pruned_loss=0.02528, over 7205.00 frames.], tot_loss[loss=0.1593, simple_loss=0.259, pruned_loss=0.02981, over 1412192.90 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:09:20,405 INFO [train.py:763] (4/8) Epoch 35, batch 4350, loss[loss=0.1584, simple_loss=0.2565, pruned_loss=0.03019, over 7422.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2573, pruned_loss=0.02951, over 1410070.94 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:10:26,455 INFO [train.py:763] (4/8) Epoch 35, batch 4400, loss[loss=0.1395, simple_loss=0.2415, pruned_loss=0.01878, over 7376.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2566, pruned_loss=0.02912, over 1414386.78 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:11:33,063 INFO [train.py:763] (4/8) Epoch 35, batch 4450, loss[loss=0.1456, simple_loss=0.2479, pruned_loss=0.02171, over 7213.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2564, pruned_loss=0.02934, over 1405497.87 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:12:39,699 INFO [train.py:763] (4/8) Epoch 35, batch 4500, loss[loss=0.1601, simple_loss=0.269, pruned_loss=0.02561, over 7221.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2569, pruned_loss=0.02973, over 1393493.35 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:13:46,213 INFO [train.py:763] (4/8) Epoch 35, batch 4550, loss[loss=0.1604, simple_loss=0.2649, pruned_loss=0.02792, over 7267.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2578, pruned_loss=0.03076, over 1355723.04 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:15:13,848 INFO [train.py:763] (4/8) Epoch 36, batch 0, loss[loss=0.1886, simple_loss=0.3008, pruned_loss=0.03825, over 7351.00 frames.], tot_loss[loss=0.1886, simple_loss=0.3008, pruned_loss=0.03825, over 7351.00 frames.], batch size: 22, lr: 2.12e-04
2022-04-30 20:16:19,177 INFO [train.py:763] (4/8) Epoch 36, batch 50, loss[loss=0.1427, simple_loss=0.2502, pruned_loss=0.01763, over 7071.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2624, pruned_loss=0.02989, over 320858.64 frames.], batch size: 18, lr: 2.12e-04
2022-04-30 20:17:24,378 INFO [train.py:763] (4/8) Epoch 36, batch 100, loss[loss=0.1603, simple_loss=0.2572, pruned_loss=0.03167, over 7323.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2607, pruned_loss=0.02927, over 566414.79 frames.], batch size: 20, lr: 2.12e-04
2022-04-30 20:18:29,495 INFO [train.py:763] (4/8) Epoch 36, batch 150, loss[loss=0.1457, simple_loss=0.2436, pruned_loss=0.02383, over 7015.00 frames.], tot_loss[loss=0.16, simple_loss=0.2608, pruned_loss=0.02961, over 754204.41 frames.], batch size: 28, lr: 2.11e-04
2022-04-30 20:19:34,473 INFO [train.py:763] (4/8) Epoch 36, batch 200, loss[loss=0.1484, simple_loss=0.2586, pruned_loss=0.0191, over 7311.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2633, pruned_loss=0.03024, over 905432.47 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:20:39,729 INFO [train.py:763] (4/8) Epoch 36, batch 250, loss[loss=0.1576, simple_loss=0.255, pruned_loss=0.03016, over 7246.00 frames.], tot_loss[loss=0.1607, simple_loss=0.262, pruned_loss=0.02966, over 1016321.20 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:21:45,224 INFO [train.py:763] (4/8) Epoch 36, batch 300, loss[loss=0.1675, simple_loss=0.2807, pruned_loss=0.02719, over 7330.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2605, pruned_loss=0.02921, over 1103478.58 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:22:50,515 INFO [train.py:763] (4/8) Epoch 36, batch 350, loss[loss=0.1332, simple_loss=0.2242, pruned_loss=0.0211, over 7162.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2604, pruned_loss=0.02912, over 1172220.42 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:23:55,932 INFO [train.py:763] (4/8) Epoch 36, batch 400, loss[loss=0.1429, simple_loss=0.2454, pruned_loss=0.02019, over 7230.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2605, pruned_loss=0.0293, over 1231622.69 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:25:01,046 INFO [train.py:763] (4/8) Epoch 36, batch 450, loss[loss=0.1625, simple_loss=0.2755, pruned_loss=0.02473, over 7146.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2611, pruned_loss=0.02909, over 1275945.12 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:26:07,075 INFO [train.py:763] (4/8) Epoch 36, batch 500, loss[loss=0.1616, simple_loss=0.2721, pruned_loss=0.02551, over 7233.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2613, pruned_loss=0.02943, over 1306077.48 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:27:14,406 INFO [train.py:763] (4/8) Epoch 36, batch 550, loss[loss=0.151, simple_loss=0.2551, pruned_loss=0.02343, over 7071.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2614, pruned_loss=0.02956, over 1322656.88 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:28:22,076 INFO [train.py:763] (4/8) Epoch 36, batch 600, loss[loss=0.1809, simple_loss=0.2744, pruned_loss=0.04366, over 7442.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2595, pruned_loss=0.0288, over 1347723.96 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:29:29,896 INFO [train.py:763] (4/8) Epoch 36, batch 650, loss[loss=0.1269, simple_loss=0.222, pruned_loss=0.01594, over 7131.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2573, pruned_loss=0.02825, over 1367193.52 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:30:35,968 INFO [train.py:763] (4/8) Epoch 36, batch 700, loss[loss=0.1641, simple_loss=0.2696, pruned_loss=0.0293, over 7231.00 frames.], tot_loss[loss=0.1572, simple_loss=0.258, pruned_loss=0.02821, over 1380256.28 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:31:41,362 INFO [train.py:763] (4/8) Epoch 36, batch 750, loss[loss=0.1397, simple_loss=0.2381, pruned_loss=0.02071, over 7157.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2569, pruned_loss=0.02797, over 1388824.04 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:32:47,557 INFO [train.py:763] (4/8) Epoch 36, batch 800, loss[loss=0.1263, simple_loss=0.2217, pruned_loss=0.01551, over 7395.00 frames.], tot_loss[loss=0.156, simple_loss=0.2565, pruned_loss=0.0278, over 1398808.80 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:33:53,515 INFO [train.py:763] (4/8) Epoch 36, batch 850, loss[loss=0.1554, simple_loss=0.2445, pruned_loss=0.03312, over 7265.00 frames.], tot_loss[loss=0.157, simple_loss=0.2573, pruned_loss=0.02837, over 1398469.95 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:34:59,124 INFO [train.py:763] (4/8) Epoch 36, batch 900, loss[loss=0.1322, simple_loss=0.2309, pruned_loss=0.01674, over 7061.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2571, pruned_loss=0.02807, over 1407072.60 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:36:04,436 INFO [train.py:763] (4/8) Epoch 36, batch 950, loss[loss=0.1519, simple_loss=0.2335, pruned_loss=0.03512, over 7314.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02845, over 1410362.11 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:37:09,728 INFO [train.py:763] (4/8) Epoch 36, batch 1000, loss[loss=0.1768, simple_loss=0.2813, pruned_loss=0.03613, over 6669.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2582, pruned_loss=0.02839, over 1413303.24 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:38:15,274 INFO [train.py:763] (4/8) Epoch 36, batch 1050, loss[loss=0.176, simple_loss=0.2816, pruned_loss=0.03523, over 7358.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02843, over 1417574.63 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:39:20,503 INFO [train.py:763] (4/8) Epoch 36, batch 1100, loss[loss=0.169, simple_loss=0.2763, pruned_loss=0.0309, over 7218.00 frames.], tot_loss[loss=0.1572, simple_loss=0.258, pruned_loss=0.02827, over 1418507.36 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:40:26,422 INFO [train.py:763] (4/8) Epoch 36, batch 1150, loss[loss=0.1605, simple_loss=0.2567, pruned_loss=0.03221, over 4888.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02842, over 1417587.27 frames.], batch size: 52, lr: 2.11e-04
2022-04-30 20:41:32,752 INFO [train.py:763] (4/8) Epoch 36, batch 1200, loss[loss=0.1553, simple_loss=0.2588, pruned_loss=0.0259, over 7153.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02882, over 1420168.44 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:42:37,805 INFO [train.py:763] (4/8) Epoch 36, batch 1250, loss[loss=0.1651, simple_loss=0.2714, pruned_loss=0.02937, over 7205.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2595, pruned_loss=0.02863, over 1420090.02 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:43:42,980 INFO [train.py:763] (4/8) Epoch 36, batch 1300, loss[loss=0.1452, simple_loss=0.236, pruned_loss=0.02723, over 7128.00 frames.], tot_loss[loss=0.1588, simple_loss=0.26, pruned_loss=0.0288, over 1422485.84 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:44:48,207 INFO [train.py:763] (4/8) Epoch 36, batch 1350, loss[loss=0.1516, simple_loss=0.2515, pruned_loss=0.02579, over 7064.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02919, over 1418235.73 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:45:54,979 INFO [train.py:763] (4/8) Epoch 36, batch 1400, loss[loss=0.141, simple_loss=0.2406, pruned_loss=0.0207, over 7020.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02907, over 1418556.91 frames.], batch size: 16, lr: 2.11e-04
2022-04-30 20:47:00,115 INFO [train.py:763] (4/8) Epoch 36, batch 1450, loss[loss=0.1622, simple_loss=0.263, pruned_loss=0.03071, over 7296.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.0291, over 1420165.49 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:48:05,222 INFO [train.py:763] (4/8) Epoch 36, batch 1500, loss[loss=0.1713, simple_loss=0.2773, pruned_loss=0.03266, over 7309.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.0292, over 1416562.04 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:49:10,948 INFO [train.py:763] (4/8) Epoch 36, batch 1550, loss[loss=0.1703, simple_loss=0.2777, pruned_loss=0.03144, over 6805.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02926, over 1410269.33 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:50:16,845 INFO [train.py:763] (4/8) Epoch 36, batch 1600, loss[loss=0.1876, simple_loss=0.2911, pruned_loss=0.04211, over 7382.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.029, over 1410192.12 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:51:24,010 INFO [train.py:763] (4/8) Epoch 36, batch 1650, loss[loss=0.1742, simple_loss=0.279, pruned_loss=0.03475, over 7197.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02883, over 1414104.54 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:52:38,228 INFO [train.py:763] (4/8) Epoch 36, batch 1700, loss[loss=0.1452, simple_loss=0.2392, pruned_loss=0.02558, over 7153.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.0291, over 1412789.86 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:53:43,581 INFO [train.py:763] (4/8) Epoch 36, batch 1750, loss[loss=0.1514, simple_loss=0.2502, pruned_loss=0.02634, over 7353.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02954, over 1407534.61 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:54:48,729 INFO [train.py:763] (4/8) Epoch 36, batch 1800, loss[loss=0.1529, simple_loss=0.251, pruned_loss=0.02738, over 7296.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02965, over 1410530.87 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 20:55:54,034 INFO [train.py:763] (4/8) Epoch 36, batch 1850, loss[loss=0.1471, simple_loss=0.2489, pruned_loss=0.02261, over 7260.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02924, over 1411649.66 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:56:59,657 INFO [train.py:763] (4/8) Epoch 36, batch 1900, loss[loss=0.1588, simple_loss=0.2651, pruned_loss=0.02629, over 6737.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02899, over 1417237.99 frames.], batch size: 31, lr: 2.10e-04
2022-04-30 20:58:07,232 INFO [train.py:763] (4/8) Epoch 36, batch 1950, loss[loss=0.1582, simple_loss=0.2697, pruned_loss=0.02334, over 7229.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02889, over 1420356.69 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 20:59:14,629 INFO [train.py:763] (4/8) Epoch 36, batch 2000, loss[loss=0.154, simple_loss=0.2729, pruned_loss=0.01758, over 7429.00 frames.], tot_loss[loss=0.1582, simple_loss=0.259, pruned_loss=0.02874, over 1416779.33 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:00:22,191 INFO [train.py:763] (4/8) Epoch 36, batch 2050, loss[loss=0.1603, simple_loss=0.2628, pruned_loss=0.02885, over 7235.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2586, pruned_loss=0.02852, over 1419820.76 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:01:28,529 INFO [train.py:763] (4/8) Epoch 36, batch 2100, loss[loss=0.1762, simple_loss=0.28, pruned_loss=0.0362, over 7148.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2586, pruned_loss=0.02842, over 1420274.33 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:02:35,092 INFO [train.py:763] (4/8) Epoch 36, batch 2150, loss[loss=0.1615, simple_loss=0.267, pruned_loss=0.02802, over 7416.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2592, pruned_loss=0.02865, over 1417452.83 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:03:42,381 INFO [train.py:763] (4/8) Epoch 36, batch 2200, loss[loss=0.1742, simple_loss=0.2695, pruned_loss=0.03944, over 7259.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02915, over 1418710.40 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:04:49,050 INFO [train.py:763] (4/8) Epoch 36, batch 2250, loss[loss=0.1695, simple_loss=0.275, pruned_loss=0.03199, over 7141.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2596, pruned_loss=0.02944, over 1419482.59 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:05:54,015 INFO [train.py:763] (4/8) Epoch 36, batch 2300, loss[loss=0.1767, simple_loss=0.2748, pruned_loss=0.0393, over 7217.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02929, over 1419298.60 frames.], batch size: 23, lr: 2.10e-04
2022-04-30 21:06:59,112 INFO [train.py:763] (4/8) Epoch 36, batch 2350, loss[loss=0.1418, simple_loss=0.2323, pruned_loss=0.0256, over 7295.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02975, over 1413239.45 frames.], batch size: 17, lr: 2.10e-04
2022-04-30 21:08:06,479 INFO [train.py:763] (4/8) Epoch 36, batch 2400, loss[loss=0.1943, simple_loss=0.2867, pruned_loss=0.05095, over 7292.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02983, over 1419845.59 frames.], batch size: 25, lr: 2.10e-04
2022-04-30 21:09:12,590 INFO [train.py:763] (4/8) Epoch 36, batch 2450, loss[loss=0.1787, simple_loss=0.2848, pruned_loss=0.03625, over 7213.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2596, pruned_loss=0.02978, over 1425230.39 frames.], batch size: 26, lr: 2.10e-04
2022-04-30 21:10:36,028 INFO [train.py:763] (4/8) Epoch 36, batch 2500, loss[loss=0.1432, simple_loss=0.2562, pruned_loss=0.01507, over 7164.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02901, over 1427810.12 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:11:41,251 INFO [train.py:763] (4/8) Epoch 36, batch 2550, loss[loss=0.1636, simple_loss=0.2614, pruned_loss=0.03293, over 7287.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02917, over 1428543.36 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 21:12:55,221 INFO [train.py:763] (4/8) Epoch 36, batch 2600, loss[loss=0.1588, simple_loss=0.2534, pruned_loss=0.03213, over 7213.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02918, over 1424943.15 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:14:18,380 INFO [train.py:763] (4/8) Epoch 36, batch 2650, loss[loss=0.1439, simple_loss=0.253, pruned_loss=0.0174, over 7202.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02917, over 1429018.12 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:15:32,419 INFO [train.py:763] (4/8) Epoch 36, batch 2700, loss[loss=0.1624, simple_loss=0.2677, pruned_loss=0.02857, over 6239.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2587, pruned_loss=0.0292, over 1424744.01 frames.], batch size: 37, lr: 2.10e-04
2022-04-30 21:16:46,238 INFO [train.py:763] (4/8) Epoch 36, batch 2750, loss[loss=0.1733, simple_loss=0.2688, pruned_loss=0.03888, over 5092.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02895, over 1425140.23 frames.], batch size: 54, lr: 2.10e-04
2022-04-30 21:17:52,032 INFO [train.py:763] (4/8) Epoch 36, batch 2800, loss[loss=0.1441, simple_loss=0.2393, pruned_loss=0.02441, over 7282.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.0287, over 1429839.69 frames.], batch size: 18, lr: 2.10e-04
2022-04-30 21:19:07,513 INFO [train.py:763] (4/8) Epoch 36, batch 2850, loss[loss=0.1472, simple_loss=0.2606, pruned_loss=0.01693, over 6300.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02862, over 1428322.13 frames.], batch size: 37, lr: 2.10e-04
2022-04-30 21:20:12,991 INFO [train.py:763] (4/8) Epoch 36, batch 2900, loss[loss=0.1208, simple_loss=0.2189, pruned_loss=0.01132, over 7006.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.02824, over 1429039.48 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:21:20,750 INFO [train.py:763] (4/8) Epoch 36, batch 2950, loss[loss=0.1481, simple_loss=0.2488, pruned_loss=0.02365, over 7424.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02847, over 1425975.48 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:22:27,896 INFO [train.py:763] (4/8) Epoch 36, batch 3000, loss[loss=0.1758, simple_loss=0.2726, pruned_loss=0.03956, over 7229.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02889, over 1422306.13 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:22:27,897 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 21:22:43,065 INFO [train.py:792] (4/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
2022-04-30 21:23:48,278 INFO [train.py:763] (4/8) Epoch 36, batch 3050, loss[loss=0.1483, simple_loss=0.2367, pruned_loss=0.02989, over 6770.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02941, over 1420288.04 frames.], batch size: 15, lr: 2.10e-04
2022-04-30 21:24:54,038 INFO [train.py:763] (4/8) Epoch 36, batch 3100, loss[loss=0.1479, simple_loss=0.2387, pruned_loss=0.02852, over 7067.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02901, over 1419394.57 frames.], batch size: 18, lr: 2.10e-04
2022-04-30 21:26:01,267 INFO [train.py:763] (4/8) Epoch 36, batch 3150, loss[loss=0.1361, simple_loss=0.2336, pruned_loss=0.01929, over 7008.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02892, over 1419076.55 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:27:07,745 INFO [train.py:763] (4/8) Epoch 36, batch 3200, loss[loss=0.1719, simple_loss=0.2634, pruned_loss=0.04021, over 5183.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02871, over 1419882.65 frames.], batch size: 52, lr: 2.10e-04
2022-04-30 21:28:14,746 INFO [train.py:763] (4/8) Epoch 36, batch 3250, loss[loss=0.1742, simple_loss=0.2696, pruned_loss=0.03937, over 7208.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02896, over 1420100.33 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:29:20,184 INFO [train.py:763] (4/8) Epoch 36, batch 3300, loss[loss=0.1619, simple_loss=0.2751, pruned_loss=0.02439, over 7428.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02908, over 1417618.45 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:30:25,143 INFO [train.py:763] (4/8) Epoch 36, batch 3350, loss[loss=0.1879, simple_loss=0.2883, pruned_loss=0.0437, over 7361.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02958, over 1413838.13 frames.], batch size: 23, lr: 2.09e-04
2022-04-30 21:31:31,783 INFO [train.py:763] (4/8) Epoch 36, batch 3400, loss[loss=0.1372, simple_loss=0.2293, pruned_loss=0.02259, over 7133.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2607, pruned_loss=0.02932, over 1418119.87 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:32:37,217 INFO [train.py:763] (4/8) Epoch 36, batch 3450, loss[loss=0.1348, simple_loss=0.2267, pruned_loss=0.02147, over 7293.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02901, over 1421696.92 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:33:42,448 INFO [train.py:763] (4/8) Epoch 36, batch 3500, loss[loss=0.1456, simple_loss=0.2447, pruned_loss=0.02329, over 7352.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02866, over 1418988.32 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:34:47,627 INFO [train.py:763] (4/8) Epoch 36, batch 3550, loss[loss=0.1374, simple_loss=0.2303, pruned_loss=0.02226, over 6787.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02833, over 1415229.92 frames.], batch size: 15, lr: 2.09e-04
2022-04-30 21:35:54,816 INFO [train.py:763] (4/8) Epoch 36, batch 3600, loss[loss=0.1275, simple_loss=0.2193, pruned_loss=0.01784, over 6999.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.0285, over 1421164.86 frames.], batch size: 16, lr: 2.09e-04
2022-04-30 21:37:01,776 INFO [train.py:763] (4/8) Epoch 36, batch 3650, loss[loss=0.156, simple_loss=0.2558, pruned_loss=0.02809, over 7154.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2576, pruned_loss=0.0283, over 1423714.34 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:38:08,982 INFO [train.py:763] (4/8) Epoch 36, batch 3700, loss[loss=0.1597, simple_loss=0.2623, pruned_loss=0.02851, over 7234.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2576, pruned_loss=0.02844, over 1426574.83 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:39:14,209 INFO [train.py:763] (4/8) Epoch 36, batch 3750, loss[loss=0.1877, simple_loss=0.2857, pruned_loss=0.04489, over 7305.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2591, pruned_loss=0.02862, over 1423142.49 frames.], batch size: 24, lr: 2.09e-04
2022-04-30 21:40:19,601 INFO [train.py:763] (4/8) Epoch 36, batch 3800, loss[loss=0.127, simple_loss=0.2237, pruned_loss=0.01517, over 7281.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.0283, over 1425015.75 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:41:25,002 INFO [train.py:763] (4/8) Epoch 36, batch 3850, loss[loss=0.176, simple_loss=0.2729, pruned_loss=0.03951, over 5062.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02826, over 1423691.48 frames.], batch size: 55, lr: 2.09e-04
2022-04-30 21:42:30,255 INFO [train.py:763] (4/8) Epoch 36, batch 3900, loss[loss=0.1508, simple_loss=0.258, pruned_loss=0.02176, over 7323.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02856, over 1425448.46 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:43:35,818 INFO [train.py:763] (4/8) Epoch 36, batch 3950, loss[loss=0.1418, simple_loss=0.2347, pruned_loss=0.0245, over 7287.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02869, over 1426334.39 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:44:41,517 INFO [train.py:763] (4/8) Epoch 36, batch 4000, loss[loss=0.1624, simple_loss=0.2617, pruned_loss=0.03153, over 7151.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.0285, over 1426664.84 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:45:48,398 INFO [train.py:763] (4/8) Epoch 36, batch 4050, loss[loss=0.1441, simple_loss=0.2419, pruned_loss=0.0231, over 7143.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2578, pruned_loss=0.02899, over 1426018.53 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:46:54,629 INFO [train.py:763] (4/8) Epoch 36, batch 4100, loss[loss=0.1904, simple_loss=0.2906, pruned_loss=0.04506, over 7308.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02909, over 1423775.41 frames.], batch size: 25, lr: 2.09e-04
2022-04-30 21:48:00,280 INFO [train.py:763] (4/8) Epoch 36, batch 4150, loss[loss=0.1512, simple_loss=0.2525, pruned_loss=0.02493, over 7224.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02844, over 1425936.69 frames.], batch size: 21, lr: 2.09e-04
2022-04-30 21:49:06,724 INFO [train.py:763] (4/8) Epoch 36, batch 4200, loss[loss=0.167, simple_loss=0.2705, pruned_loss=0.03171, over 7340.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02838, over 1428273.78 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:50:13,176 INFO [train.py:763] (4/8) Epoch 36, batch 4250, loss[loss=0.1744, simple_loss=0.2713, pruned_loss=0.03874, over 7214.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02869, over 1431237.56 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:51:18,747 INFO [train.py:763] (4/8) Epoch 36, batch 4300, loss[loss=0.1444, simple_loss=0.24, pruned_loss=0.02438, over 7331.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02881, over 1425582.24 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:52:24,304 INFO [train.py:763] (4/8) Epoch 36, batch 4350, loss[loss=0.1615, simple_loss=0.2622, pruned_loss=0.03037, over 7341.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02877, over 1430570.82 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:53:30,947 INFO [train.py:763] (4/8) Epoch 36, batch 4400, loss[loss=0.1827, simple_loss=0.2883, pruned_loss=0.03849, over 7333.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.029, over 1422135.45 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:54:38,266 INFO [train.py:763] (4/8) Epoch 36, batch 4450, loss[loss=0.1393, simple_loss=0.2374, pruned_loss=0.02056, over 7420.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02875, over 1421331.58 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:55:43,444 INFO [train.py:763] (4/8) Epoch 36, batch 4500, loss[loss=0.1426, simple_loss=0.2442, pruned_loss=0.02045, over 7280.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02885, over 1416576.10 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:56:47,987 INFO [train.py:763] (4/8) Epoch 36, batch 4550, loss[loss=0.1562, simple_loss=0.2624, pruned_loss=0.02502, over 6534.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02906, over 1392779.34 frames.], batch size: 38, lr: 2.09e-04
2022-04-30 21:58:07,227 INFO [train.py:763] (4/8) Epoch 37, batch 0, loss[loss=0.1442, simple_loss=0.2535, pruned_loss=0.01748, over 7361.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2535, pruned_loss=0.01748, over 7361.00 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 21:59:13,879 INFO [train.py:763] (4/8) Epoch 37, batch 50, loss[loss=0.1535, simple_loss=0.2641, pruned_loss=0.02142, over 6419.00 frames.], tot_loss[loss=0.155, simple_loss=0.2571, pruned_loss=0.02649, over 322538.22 frames.], batch size: 38, lr: 2.06e-04
2022-04-30 22:00:20,503 INFO [train.py:763] (4/8) Epoch 37, batch 100, loss[loss=0.1419, simple_loss=0.2489, pruned_loss=0.01747, over 7272.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2618, pruned_loss=0.02935, over 560122.35 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:01:27,279 INFO [train.py:763] (4/8) Epoch 37, batch 150, loss[loss=0.1748, simple_loss=0.2813, pruned_loss=0.03408, over 7377.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2611, pruned_loss=0.02856, over 747987.31 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:02:34,173 INFO [train.py:763] (4/8) Epoch 37, batch 200, loss[loss=0.1559, simple_loss=0.2627, pruned_loss=0.0246, over 7419.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2587, pruned_loss=0.0283, over 896617.31 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:03:39,629 INFO [train.py:763] (4/8) Epoch 37, batch 250, loss[loss=0.1447, simple_loss=0.243, pruned_loss=0.02317, over 7357.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.0283, over 1014822.75 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:04:45,205 INFO [train.py:763] (4/8) Epoch 37, batch 300, loss[loss=0.1434, simple_loss=0.2454, pruned_loss=0.02066, over 7227.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2588, pruned_loss=0.02842, over 1105939.34 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:05:51,654 INFO [train.py:763] (4/8) Epoch 37, batch 350, loss[loss=0.1618, simple_loss=0.257, pruned_loss=0.03327, over 7263.00 frames.], tot_loss[loss=0.1581, simple_loss=0.259, pruned_loss=0.02862, over 1172964.90 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:06:57,559 INFO [train.py:763] (4/8) Epoch 37, batch 400, loss[loss=0.1432, simple_loss=0.2412, pruned_loss=0.02259, over 7275.00 frames.], tot_loss[loss=0.1579, simple_loss=0.259, pruned_loss=0.02846, over 1232977.21 frames.], batch size: 17, lr: 2.06e-04
2022-04-30 22:08:03,012 INFO [train.py:763] (4/8) Epoch 37, batch 450, loss[loss=0.1672, simple_loss=0.2772, pruned_loss=0.02857, over 7110.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02856, over 1276160.89 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:09:09,215 INFO [train.py:763] (4/8) Epoch 37, batch 500, loss[loss=0.1417, simple_loss=0.2308, pruned_loss=0.02628, over 7279.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2568, pruned_loss=0.02825, over 1312086.02 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:10:16,142 INFO [train.py:763] (4/8) Epoch 37, batch 550, loss[loss=0.1466, simple_loss=0.2426, pruned_loss=0.02531, over 7328.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02863, over 1336190.69 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:11:22,960 INFO [train.py:763] (4/8) Epoch 37, batch 600, loss[loss=0.183, simple_loss=0.2813, pruned_loss=0.04235, over 7382.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2599, pruned_loss=0.02909, over 1357628.33 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:12:30,630 INFO [train.py:763] (4/8) Epoch 37, batch 650, loss[loss=0.1666, simple_loss=0.2766, pruned_loss=0.02826, over 7332.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2602, pruned_loss=0.02909, over 1374312.38 frames.], batch size: 22, lr: 2.06e-04
2022-04-30 22:13:38,153 INFO [train.py:763] (4/8) Epoch 37, batch 700, loss[loss=0.1575, simple_loss=0.2477, pruned_loss=0.0337, over 7170.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2594, pruned_loss=0.029, over 1386451.07 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:14:45,727 INFO [train.py:763] (4/8) Epoch 37, batch 750, loss[loss=0.1793, simple_loss=0.2852, pruned_loss=0.03667, over 7378.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02902, over 1400858.93 frames.], batch size: 23, lr: 2.05e-04
2022-04-30 22:15:51,453 INFO [train.py:763] (4/8) Epoch 37, batch 800, loss[loss=0.1463, simple_loss=0.236, pruned_loss=0.02833, over 7413.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02889, over 1408545.76 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:16:56,736 INFO [train.py:763] (4/8) Epoch 37, batch 850, loss[loss=0.1406, simple_loss=0.2383, pruned_loss=0.02142, over 7343.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2595, pruned_loss=0.0287, over 1411137.54 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:18:02,417 INFO [train.py:763] (4/8) Epoch 37, batch 900, loss[loss=0.1819, simple_loss=0.2708, pruned_loss=0.04649, over 7295.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2584, pruned_loss=0.02827, over 1413026.70 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:19:07,693 INFO [train.py:763] (4/8) Epoch 37, batch 950, loss[loss=0.1502, simple_loss=0.243, pruned_loss=0.02869, over 7279.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2592, pruned_loss=0.02868, over 1418634.94 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:20:12,872 INFO [train.py:763] (4/8) Epoch 37, batch 1000, loss[loss=0.1681, simple_loss=0.2773, pruned_loss=0.02944, over 7212.00 frames.], tot_loss[loss=0.159, simple_loss=0.2598, pruned_loss=0.02913, over 1420786.22 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:21:18,156 INFO [train.py:763] (4/8) Epoch 37, batch 1050, loss[loss=0.1493, simple_loss=0.2644, pruned_loss=0.0171, over 7339.00 frames.], tot_loss[loss=0.159, simple_loss=0.2601, pruned_loss=0.02897, over 1422043.73 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:22:25,731 INFO [train.py:763] (4/8) Epoch 37, batch 1100, loss[loss=0.1326, simple_loss=0.2282, pruned_loss=0.01847, over 6771.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2605, pruned_loss=0.02898, over 1424802.13 frames.], batch size: 15, lr: 2.05e-04
2022-04-30 22:23:31,640 INFO [train.py:763] (4/8) Epoch 37, batch 1150, loss[loss=0.1426, simple_loss=0.2333, pruned_loss=0.02595, over 7276.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2608, pruned_loss=0.0291, over 1421918.92 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:24:36,965 INFO [train.py:763] (4/8) Epoch 37, batch 1200, loss[loss=0.1679, simple_loss=0.2757, pruned_loss=0.03008, over 7203.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2608, pruned_loss=0.02908, over 1424172.62 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:25:43,864 INFO [train.py:763] (4/8) Epoch 37, batch 1250, loss[loss=0.1621, simple_loss=0.2695, pruned_loss=0.02738, over 6476.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02917, over 1427719.41 frames.], batch size: 38, lr: 2.05e-04
2022-04-30 22:26:50,669 INFO [train.py:763] (4/8) Epoch 37, batch 1300, loss[loss=0.1377, simple_loss=0.2314, pruned_loss=0.02203, over 7259.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2605, pruned_loss=0.02946, over 1427717.41 frames.], batch size: 17, lr: 2.05e-04
2022-04-30 22:27:56,058 INFO [train.py:763] (4/8) Epoch 37, batch 1350, loss[loss=0.1572, simple_loss=0.2559, pruned_loss=0.02924, over 7114.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02907, over 1420964.30 frames.], batch size: 21, lr: 2.05e-04
2022-04-30 22:29:02,055 INFO [train.py:763] (4/8) Epoch 37, batch 1400, loss[loss=0.1619, simple_loss=0.2661, pruned_loss=0.02888, over 7282.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02907, over 1421191.94 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:30:07,326 INFO [train.py:763] (4/8) Epoch 37, batch 1450, loss[loss=0.1556, simple_loss=0.2646, pruned_loss=0.02333, over 7223.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02888, over 1425250.24 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:31:13,180 INFO [train.py:763] (4/8) Epoch 37, batch 1500, loss[loss=0.1382, simple_loss=0.2446, pruned_loss=0.01588, over 7279.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2592, pruned_loss=0.02857, over 1425164.55 frames.], batch size: 25, lr: 2.05e-04
2022-04-30 22:32:18,522 INFO [train.py:763] (4/8) Epoch 37, batch 1550, loss[loss=0.1351, simple_loss=0.2368, pruned_loss=0.01672, over 7235.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2591, pruned_loss=0.02859, over 1422445.24 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:33:23,881 INFO [train.py:763] (4/8) Epoch 37, batch 1600, loss[loss=0.1475, simple_loss=0.2455, pruned_loss=0.02476, over 7268.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2602, pruned_loss=0.02905, over 1425617.17 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:34:29,218 INFO [train.py:763] (4/8) Epoch 37, batch 1650, loss[loss=0.1731, simple_loss=0.2899, pruned_loss=0.02809, over 7069.00 frames.], tot_loss[loss=0.159, simple_loss=0.2599, pruned_loss=0.029, over 1424775.28 frames.], batch size: 28, lr: 2.05e-04
2022-04-30 22:35:34,590 INFO [train.py:763] (4/8) Epoch 37, batch 1700, loss[loss=0.1387, simple_loss=0.2275, pruned_loss=0.02494, over 7174.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02914, over 1423185.33 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:36:40,243 INFO [train.py:763] (4/8) Epoch 37, batch 1750, loss[loss=0.1841, simple_loss=0.2755, pruned_loss=0.04631, over 5230.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02938, over 1422289.61 frames.], batch size: 54, lr: 2.05e-04
2022-04-30 22:37:45,568 INFO [train.py:763] (4/8) Epoch 37, batch 1800, loss[loss=0.1579, simple_loss=0.2681, pruned_loss=0.0239, over 7322.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02936, over 1419031.14 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:38:50,831 INFO [train.py:763] (4/8) Epoch 37, batch 1850, loss[loss=0.1366, simple_loss=0.2376, pruned_loss=0.0178, over 7277.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02908, over 1421221.54 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:39:57,178 INFO [train.py:763] (4/8) Epoch 37, batch 1900, loss[loss=0.1521, simple_loss=0.2393, pruned_loss=0.03249, over 6808.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02919, over 1424243.44 frames.], batch size: 15, lr: 2.05e-04
2022-04-30 22:41:04,597 INFO [train.py:763] (4/8) Epoch 37, batch 1950, loss[loss=0.1369, simple_loss=0.2392, pruned_loss=0.01731, over 7243.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2603, pruned_loss=0.02932, over 1427060.90 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:42:12,274 INFO [train.py:763] (4/8) Epoch 37, batch 2000, loss[loss=0.1413, simple_loss=0.2305, pruned_loss=0.02605, over 7412.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02911, over 1427436.20 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:43:17,404 INFO [train.py:763] (4/8) Epoch 37, batch 2050, loss[loss=0.1445, simple_loss=0.236, pruned_loss=0.02648, over 7263.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02948, over 1424227.88 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:44:22,372 INFO [train.py:763] (4/8) Epoch 37, batch 2100, loss[loss=0.1559, simple_loss=0.2601, pruned_loss=0.02588, over 7171.00 frames.], tot_loss[loss=0.16, simple_loss=0.2607, pruned_loss=0.02965, over 1418507.34 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:45:27,585 INFO [train.py:763] (4/8) Epoch 37, batch 2150, loss[loss=0.1484, simple_loss=0.2456, pruned_loss=0.0256, over 7073.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2607, pruned_loss=0.02974, over 1418455.05 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:46:32,463 INFO [train.py:763] (4/8) Epoch 37, batch 2200, loss[loss=0.1423, simple_loss=0.2443, pruned_loss=0.02011, over 7059.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2615, pruned_loss=0.03009, over 1419679.13 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:47:37,560 INFO [train.py:763] (4/8) Epoch 37, batch 2250, loss[loss=0.1581, simple_loss=0.2576, pruned_loss=0.02934, over 6300.00 frames.], tot_loss[loss=0.161, simple_loss=0.2617, pruned_loss=0.03017, over 1418749.94 frames.], batch size: 38, lr: 2.05e-04
2022-04-30 22:48:44,663 INFO [train.py:763] (4/8) Epoch 37, batch 2300, loss[loss=0.1838, simple_loss=0.2741, pruned_loss=0.04679, over 7058.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2611, pruned_loss=0.0297, over 1422400.77 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:49:50,011 INFO [train.py:763] (4/8) Epoch 37, batch 2350, loss[loss=0.1546, simple_loss=0.2574, pruned_loss=0.02592, over 7335.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2606, pruned_loss=0.02962, over 1420082.73 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:50:55,499 INFO [train.py:763] (4/8) Epoch 37, batch 2400, loss[loss=0.1481, simple_loss=0.2453, pruned_loss=0.02546, over 7398.00 frames.], tot_loss[loss=0.159, simple_loss=0.2596, pruned_loss=0.0292, over 1424304.09 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:52:02,203 INFO [train.py:763] (4/8) Epoch 37, batch 2450, loss[loss=0.1853, simple_loss=0.2838, pruned_loss=0.04342, over 7322.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02921, over 1425927.29 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:53:07,499 INFO [train.py:763] (4/8) Epoch 37, batch 2500, loss[loss=0.144, simple_loss=0.2418, pruned_loss=0.02305, over 7168.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02917, over 1425601.50 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:54:13,274 INFO [train.py:763] (4/8) Epoch 37, batch 2550, loss[loss=0.1336, simple_loss=0.2347, pruned_loss=0.01623, over 7179.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02898, over 1423488.20 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:55:19,536 INFO [train.py:763] (4/8) Epoch 37, batch 2600, loss[loss=0.1684, simple_loss=0.2736, pruned_loss=0.03156, over 7435.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02911, over 1422594.87 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:56:24,704 INFO [train.py:763] (4/8) Epoch 37, batch 2650, loss[loss=0.1667, simple_loss=0.2712, pruned_loss=0.03112, over 7211.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.0292, over 1424324.95 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 22:57:30,426 INFO [train.py:763] (4/8) Epoch 37, batch 2700, loss[loss=0.1612, simple_loss=0.255, pruned_loss=0.03374, over 7232.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02878, over 1425192.07 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:58:35,697 INFO [train.py:763] (4/8) Epoch 37, batch 2750, loss[loss=0.1496, simple_loss=0.2469, pruned_loss=0.02615, over 7360.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02882, over 1426712.87 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 22:59:42,056 INFO [train.py:763] (4/8) Epoch 37, batch 2800, loss[loss=0.1582, simple_loss=0.2582, pruned_loss=0.02913, over 7279.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02855, over 1425055.77 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:00:49,136 INFO [train.py:763] (4/8) Epoch 37, batch 2850, loss[loss=0.1507, simple_loss=0.2626, pruned_loss=0.01933, over 7419.00 frames.], tot_loss[loss=0.1576, simple_loss=0.258, pruned_loss=0.0286, over 1425196.36 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:01:56,133 INFO [train.py:763] (4/8) Epoch 37, batch 2900, loss[loss=0.1264, simple_loss=0.2236, pruned_loss=0.01456, over 7132.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02862, over 1425382.33 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:03:03,257 INFO [train.py:763] (4/8) Epoch 37, batch 2950, loss[loss=0.1257, simple_loss=0.2204, pruned_loss=0.01548, over 7394.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02859, over 1430366.51 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:04:10,176 INFO [train.py:763] (4/8) Epoch 37, batch 3000, loss[loss=0.1823, simple_loss=0.2829, pruned_loss=0.04084, over 7205.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.02865, over 1429496.39 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:04:10,177 INFO [train.py:783] (4/8) Computing validation loss
2022-04-30 23:04:25,434 INFO [train.py:792] (4/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
2022-04-30 23:05:32,514 INFO [train.py:763] (4/8) Epoch 37, batch 3050, loss[loss=0.152, simple_loss=0.2472, pruned_loss=0.02843, over 7168.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02903, over 1429960.60 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:06:38,291 INFO [train.py:763] (4/8) Epoch 37, batch 3100, loss[loss=0.178, simple_loss=0.2802, pruned_loss=0.03791, over 7215.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02892, over 1422760.95 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:07:53,026 INFO [train.py:763] (4/8) Epoch 37, batch 3150, loss[loss=0.1819, simple_loss=0.2827, pruned_loss=0.04055, over 7379.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02918, over 1421482.26 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:08:58,932 INFO [train.py:763] (4/8) Epoch 37, batch 3200, loss[loss=0.1713, simple_loss=0.2733, pruned_loss=0.03468, over 7106.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02899, over 1426006.23 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:10:06,286 INFO [train.py:763] (4/8) Epoch 37, batch 3250, loss[loss=0.1548, simple_loss=0.2488, pruned_loss=0.03046, over 7274.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02916, over 1426438.04 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:11:13,121 INFO [train.py:763] (4/8) Epoch 37, batch 3300, loss[loss=0.1686, simple_loss=0.2772, pruned_loss=0.02997, over 7235.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02899, over 1426023.66 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:12:18,272 INFO [train.py:763] (4/8) Epoch 37, batch 3350, loss[loss=0.1814, simple_loss=0.274, pruned_loss=0.04435, over 7181.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2601, pruned_loss=0.02917, over 1427190.85 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:13:23,564 INFO [train.py:763] (4/8) Epoch 37, batch 3400, loss[loss=0.1553, simple_loss=0.2573, pruned_loss=0.02664, over 6784.00 frames.], tot_loss[loss=0.1593, simple_loss=0.26, pruned_loss=0.02923, over 1430814.90 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:14:28,969 INFO [train.py:763] (4/8) Epoch 37, batch 3450, loss[loss=0.1534, simple_loss=0.2509, pruned_loss=0.02791, over 7439.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02949, over 1432616.30 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:15:34,294 INFO [train.py:763] (4/8) Epoch 37, batch 3500, loss[loss=0.1515, simple_loss=0.2517, pruned_loss=0.02561, over 7230.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.02926, over 1430474.34 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:16:39,545 INFO [train.py:763] (4/8) Epoch 37, batch 3550, loss[loss=0.1645, simple_loss=0.2724, pruned_loss=0.02831, over 7144.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2605, pruned_loss=0.02947, over 1430821.89 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:17:44,638 INFO [train.py:763] (4/8) Epoch 37, batch 3600, loss[loss=0.1663, simple_loss=0.2732, pruned_loss=0.02973, over 6678.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02936, over 1429322.27 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:18:50,216 INFO [train.py:763] (4/8) Epoch 37, batch 3650, loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03207, over 7120.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2594, pruned_loss=0.02919, over 1431987.46 frames.], batch size: 28, lr: 2.04e-04
2022-04-30 23:19:55,915 INFO [train.py:763] (4/8) Epoch 37, batch 3700, loss[loss=0.2019, simple_loss=0.3052, pruned_loss=0.04933, over 7285.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02965, over 1423280.13 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:21:00,945 INFO [train.py:763] (4/8) Epoch 37, batch 3750, loss[loss=0.1547, simple_loss=0.2596, pruned_loss=0.02488, over 7162.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2598, pruned_loss=0.02952, over 1418271.14 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:22:07,061 INFO [train.py:763] (4/8) Epoch 37, batch 3800, loss[loss=0.1906, simple_loss=0.2852, pruned_loss=0.04796, over 7384.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02967, over 1418542.81 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:23:12,317 INFO [train.py:763] (4/8) Epoch 37, batch 3850, loss[loss=0.1485, simple_loss=0.2459, pruned_loss=0.02554, over 7109.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2588, pruned_loss=0.02946, over 1420572.89 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:24:18,020 INFO [train.py:763] (4/8) Epoch 37, batch 3900, loss[loss=0.1605, simple_loss=0.2618, pruned_loss=0.02965, over 7329.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2577, pruned_loss=0.02933, over 1422671.18 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:25:32,657 INFO [train.py:763] (4/8) Epoch 37, batch 3950, loss[loss=0.1675, simple_loss=0.2678, pruned_loss=0.03364, over 7190.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2578, pruned_loss=0.02937, over 1417849.56 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:26:37,875 INFO [train.py:763] (4/8) Epoch 37, batch 4000, loss[loss=0.1359, simple_loss=0.2334, pruned_loss=0.01917, over 7148.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2572, pruned_loss=0.02895, over 1417685.90 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:28:01,969 INFO [train.py:763] (4/8) Epoch 37, batch 4050, loss[loss=0.1409, simple_loss=0.2395, pruned_loss=0.02114, over 7293.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2571, pruned_loss=0.02888, over 1410683.66 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:29:07,113 INFO [train.py:763] (4/8) Epoch 37, batch 4100, loss[loss=0.1728, simple_loss=0.274, pruned_loss=0.03578, over 7219.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02859, over 1412939.86 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:30:21,705 INFO [train.py:763] (4/8) Epoch 37, batch 4150, loss[loss=0.1683, simple_loss=0.2653, pruned_loss=0.03559, over 7261.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2566, pruned_loss=0.02854, over 1412915.59 frames.], batch size: 19, lr: 2.03e-04
2022-04-30 23:31:36,368 INFO [train.py:763] (4/8) Epoch 37, batch 4200, loss[loss=0.1484, simple_loss=0.2517, pruned_loss=0.02251, over 7301.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2562, pruned_loss=0.02826, over 1413949.40 frames.], batch size: 24, lr: 2.03e-04
2022-04-30 23:32:51,950 INFO [train.py:763] (4/8) Epoch 37, batch 4250, loss[loss=0.153, simple_loss=0.2505, pruned_loss=0.02771, over 7229.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2565, pruned_loss=0.02835, over 1414174.04 frames.], batch size: 20, lr: 2.03e-04
2022-04-30 23:33:58,662 INFO [train.py:763] (4/8) Epoch 37, batch 4300, loss[loss=0.199, simple_loss=0.2957, pruned_loss=0.05112, over 5236.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2552, pruned_loss=0.02819, over 1411922.68 frames.], batch size: 53, lr: 2.03e-04
2022-04-30 23:35:04,833 INFO [train.py:763] (4/8) Epoch 37, batch 4350, loss[loss=0.1295, simple_loss=0.2219, pruned_loss=0.01851, over 6985.00 frames.], tot_loss[loss=0.155, simple_loss=0.2543, pruned_loss=0.02789, over 1413930.34 frames.], batch size: 16, lr: 2.03e-04
2022-04-30 23:36:10,336 INFO [train.py:763] (4/8) Epoch 37, batch 4400, loss[loss=0.1631, simple_loss=0.2533, pruned_loss=0.03643, over 6797.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2549, pruned_loss=0.02816, over 1414479.08 frames.], batch size: 15, lr: 2.03e-04
2022-04-30 23:37:17,175 INFO [train.py:763] (4/8) Epoch 37, batch 4450, loss[loss=0.1451, simple_loss=0.2374, pruned_loss=0.02641, over 6798.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2539, pruned_loss=0.02774, over 1405851.06 frames.], batch size: 15, lr: 2.03e-04
2022-04-30 23:38:22,784 INFO [train.py:763] (4/8) Epoch 37, batch 4500, loss[loss=0.1536, simple_loss=0.2485, pruned_loss=0.0293, over 6505.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2539, pruned_loss=0.02781, over 1380332.80 frames.], batch size: 38, lr: 2.03e-04
2022-04-30 23:39:28,658 INFO [train.py:763] (4/8) Epoch 37, batch 4550, loss[loss=0.1994, simple_loss=0.2821, pruned_loss=0.05833, over 4717.00 frames.], tot_loss[loss=0.1555, simple_loss=0.254, pruned_loss=0.02852, over 1354254.13 frames.], batch size: 52, lr: 2.03e-04
2022-04-30 23:40:56,598 INFO [train.py:763] (4/8) Epoch 38, batch 0, loss[loss=0.1571, simple_loss=0.2521, pruned_loss=0.03102, over 7265.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2521, pruned_loss=0.03102, over 7265.00 frames.], batch size: 19, lr: 2.01e-04
2022-04-30 23:42:03,204 INFO [train.py:763] (4/8) Epoch 38, batch 50, loss[loss=0.1555, simple_loss=0.2698, pruned_loss=0.0206, over 7149.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2616, pruned_loss=0.02944, over 320035.83 frames.], batch size: 20, lr: 2.01e-04
2022-04-30 23:43:10,054 INFO [train.py:763] (4/8) Epoch 38, batch 100, loss[loss=0.153, simple_loss=0.2643, pruned_loss=0.02084, over 6864.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2604, pruned_loss=0.02906, over 565903.69 frames.], batch size: 31, lr: 2.01e-04
2022-04-30 23:44:16,791 INFO [train.py:763] (4/8) Epoch 38, batch 150, loss[loss=0.1514, simple_loss=0.2495, pruned_loss=0.02663, over 7159.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.0287, over 754395.03 frames.], batch size: 18, lr: 2.01e-04
2022-04-30 23:45:22,778 INFO [train.py:763] (4/8) Epoch 38, batch 200, loss[loss=0.1429, simple_loss=0.2438, pruned_loss=0.02096, over 7436.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2584, pruned_loss=0.02899, over 901765.01 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:46:29,135 INFO [train.py:763] (4/8) Epoch 38, batch 250, loss[loss=0.1515, simple_loss=0.2588, pruned_loss=0.02207, over 6386.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02909, over 1017341.98 frames.], batch size: 38, lr: 2.00e-04
2022-04-30 23:47:35,373 INFO [train.py:763] (4/8) Epoch 38, batch 300, loss[loss=0.1605, simple_loss=0.26, pruned_loss=0.03055, over 7433.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02878, over 1112670.01 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:48:41,448 INFO [train.py:763] (4/8) Epoch 38, batch 350, loss[loss=0.1596, simple_loss=0.263, pruned_loss=0.02811, over 7272.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02882, over 1179446.53 frames.], batch size: 24, lr: 2.00e-04
2022-04-30 23:49:47,492 INFO [train.py:763] (4/8) Epoch 38, batch 400, loss[loss=0.1669, simple_loss=0.2749, pruned_loss=0.02943, over 7212.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.0291, over 1229376.67 frames.], batch size: 21, lr: 2.00e-04
2022-04-30 23:50:53,869 INFO [train.py:763] (4/8) Epoch 38, batch 450, loss[loss=0.1625, simple_loss=0.278, pruned_loss=0.02351, over 7195.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2579, pruned_loss=0.02871, over 1274809.47 frames.], batch size: 23, lr: 2.00e-04
2022-04-30 23:52:00,167 INFO [train.py:763] (4/8) Epoch 38, batch 500, loss[loss=0.1651, simple_loss=0.2724, pruned_loss=0.02887, over 7142.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02871, over 1301890.51 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:53:06,419 INFO [train.py:763] (4/8) Epoch 38, batch 550, loss[loss=0.1587, simple_loss=0.2529, pruned_loss=0.03225, over 7435.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02898, over 1327561.12 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:54:12,144 INFO [train.py:763] (4/8) Epoch 38, batch 600, loss[loss=0.1422, simple_loss=0.2468, pruned_loss=0.01882, over 7159.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.02858, over 1345876.64 frames.], batch size: 18, lr: 2.00e-04
2022-04-30 23:55:17,889 INFO [train.py:763] (4/8) Epoch 38, batch 650, loss[loss=0.1302, simple_loss=0.2225, pruned_loss=0.01896, over 7284.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.02825, over 1365815.38 frames.], batch size: 17, lr: 2.00e-04
2022-04-30 23:56:23,408 INFO [train.py:763] (4/8) Epoch 38, batch 700, loss[loss=0.1419, simple_loss=0.2445, pruned_loss=0.01965, over 6821.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2564, pruned_loss=0.02761, over 1378543.43 frames.], batch size: 15, lr: 2.00e-04
2022-04-30 23:57:28,959 INFO [train.py:763] (4/8) Epoch 38, batch 750, loss[loss=0.1547, simple_loss=0.2601, pruned_loss=0.02465, over 6273.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2567, pruned_loss=0.02774, over 1386917.15 frames.], batch size: 37, lr: 2.00e-04
2022-04-30 23:58:35,117 INFO [train.py:763] (4/8) Epoch 38, batch 800, loss[loss=0.1623, simple_loss=0.2652, pruned_loss=0.02971, over 7231.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2575, pruned_loss=0.02821, over 1399535.20 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:59:41,182 INFO [train.py:763] (4/8) Epoch 38, batch 850, loss[loss=0.2057, simple_loss=0.2957, pruned_loss=0.05783, over 7120.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2565, pruned_loss=0.0282, over 1405114.16 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:00:47,049 INFO [train.py:763] (4/8) Epoch 38, batch 900, loss[loss=0.1519, simple_loss=0.2556, pruned_loss=0.02414, over 7420.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.0286, over 1402946.51 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:01:52,974 INFO [train.py:763] (4/8) Epoch 38, batch 950, loss[loss=0.151, simple_loss=0.2362, pruned_loss=0.03286, over 7135.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02885, over 1404291.37 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:02:58,567 INFO [train.py:763] (4/8) Epoch 38, batch 1000, loss[loss=0.1738, simple_loss=0.2755, pruned_loss=0.03609, over 7360.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02899, over 1407408.04 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:04:03,995 INFO [train.py:763] (4/8) Epoch 38, batch 1050, loss[loss=0.1473, simple_loss=0.2534, pruned_loss=0.02063, over 6992.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2584, pruned_loss=0.02925, over 1410721.33 frames.], batch size: 32, lr: 2.00e-04
2022-05-01 00:05:09,982 INFO [train.py:763] (4/8) Epoch 38, batch 1100, loss[loss=0.1676, simple_loss=0.2687, pruned_loss=0.03324, over 7381.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2581, pruned_loss=0.02919, over 1415986.45 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:06:15,676 INFO [train.py:763] (4/8) Epoch 38, batch 1150, loss[loss=0.1492, simple_loss=0.2449, pruned_loss=0.02681, over 7276.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2573, pruned_loss=0.02888, over 1419845.69 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:07:21,223 INFO [train.py:763] (4/8) Epoch 38, batch 1200, loss[loss=0.1578, simple_loss=0.2592, pruned_loss=0.02821, over 6833.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2578, pruned_loss=0.02917, over 1421747.70 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:08:27,091 INFO [train.py:763] (4/8) Epoch 38, batch 1250, loss[loss=0.158, simple_loss=0.2639, pruned_loss=0.02608, over 7429.00 frames.], tot_loss[loss=0.158, simple_loss=0.2577, pruned_loss=0.02915, over 1421529.55 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:09:34,183 INFO [train.py:763] (4/8) Epoch 38, batch 1300, loss[loss=0.1379, simple_loss=0.2365, pruned_loss=0.01964, over 7258.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.02861, over 1425000.98 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:10:39,849 INFO [train.py:763] (4/8) Epoch 38, batch 1350, loss[loss=0.1675, simple_loss=0.2758, pruned_loss=0.02961, over 7335.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02864, over 1424725.93 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:11:45,174 INFO [train.py:763] (4/8) Epoch 38, batch 1400, loss[loss=0.1405, simple_loss=0.2395, pruned_loss=0.02077, over 7168.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02885, over 1423016.68 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:12:50,402 INFO [train.py:763] (4/8) Epoch 38, batch 1450, loss[loss=0.1714, simple_loss=0.2769, pruned_loss=0.03293, over 7277.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2592, pruned_loss=0.02911, over 1423596.53 frames.], batch size: 25, lr: 2.00e-04
2022-05-01 00:13:55,955 INFO [train.py:763] (4/8) Epoch 38, batch 1500, loss[loss=0.1561, simple_loss=0.2682, pruned_loss=0.02199, over 7114.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02911, over 1422487.70 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:15:03,014 INFO [train.py:763] (4/8) Epoch 38, batch 1550, loss[loss=0.1758, simple_loss=0.2691, pruned_loss=0.04119, over 7197.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02864, over 1423286.36 frames.], batch size: 22, lr: 2.00e-04
2022-05-01 00:16:09,258 INFO [train.py:763] (4/8) Epoch 38, batch 1600, loss[loss=0.1852, simple_loss=0.2951, pruned_loss=0.03761, over 6725.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02899, over 1425301.87 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:17:15,070 INFO [train.py:763] (4/8) Epoch 38, batch 1650, loss[loss=0.1654, simple_loss=0.2729, pruned_loss=0.02895, over 7220.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2576, pruned_loss=0.02884, over 1423855.72 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:18:31,383 INFO [train.py:763] (4/8) Epoch 38, batch 1700, loss[loss=0.1596, simple_loss=0.2568, pruned_loss=0.03122, over 7032.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.02881, over 1425745.74 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:19:36,539 INFO [train.py:763] (4/8) Epoch 38, batch 1750, loss[loss=0.1549, simple_loss=0.2532, pruned_loss=0.02827, over 7431.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02888, over 1425116.99 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:20:42,261 INFO [train.py:763] (4/8) Epoch 38, batch 1800, loss[loss=0.1836, simple_loss=0.2926, pruned_loss=0.03726, over 7204.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2601, pruned_loss=0.0295, over 1422989.56 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:21:47,719 INFO [train.py:763] (4/8) Epoch 38, batch 1850, loss[loss=0.1563, simple_loss=0.2612, pruned_loss=0.02575, over 7169.00 frames.], tot_loss[loss=0.1592, simple_loss=0.26, pruned_loss=0.02926, over 1420161.28 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:22:54,645 INFO [train.py:763] (4/8) Epoch 38, batch 1900, loss[loss=0.1483, simple_loss=0.2418, pruned_loss=0.02742, over 7298.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02924, over 1423414.47 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:24:00,339 INFO [train.py:763] (4/8) Epoch 38, batch 1950, loss[loss=0.1645, simple_loss=0.2691, pruned_loss=0.02992, over 7333.00 frames.], tot_loss[loss=0.1595, simple_loss=0.26, pruned_loss=0.02949, over 1423532.46 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:25:06,437 INFO [train.py:763] (4/8) Epoch 38, batch 2000, loss[loss=0.1413, simple_loss=0.2422, pruned_loss=0.02022, over 7258.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2597, pruned_loss=0.02923, over 1423368.83 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:26:13,052 INFO [train.py:763] (4/8) Epoch 38, batch 2050, loss[loss=0.1636, simple_loss=0.2618, pruned_loss=0.03274, over 7341.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02942, over 1421999.42 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:27:18,296 INFO [train.py:763] (4/8) Epoch 38, batch 2100, loss[loss=0.1438, simple_loss=0.238, pruned_loss=0.02485, over 6762.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02889, over 1423585.62 frames.], batch size: 15, lr: 1.99e-04
2022-05-01 00:28:25,362 INFO [train.py:763] (4/8) Epoch 38, batch 2150, loss[loss=0.1632, simple_loss=0.2541, pruned_loss=0.0362, over 7254.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02878, over 1421137.77 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:29:31,361 INFO [train.py:763] (4/8) Epoch 38, batch 2200, loss[loss=0.1664, simple_loss=0.2708, pruned_loss=0.03104, over 7224.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02904, over 1421740.64 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:30:38,809 INFO [train.py:763] (4/8) Epoch 38, batch 2250, loss[loss=0.1551, simple_loss=0.2609, pruned_loss=0.0247, over 7148.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02885, over 1424943.37 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:31:44,072 INFO [train.py:763] (4/8) Epoch 38, batch 2300, loss[loss=0.1472, simple_loss=0.2437, pruned_loss=0.02539, over 7168.00 frames.], tot_loss[loss=0.158, simple_loss=0.2588, pruned_loss=0.02854, over 1424837.88 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:32:50,157 INFO [train.py:763] (4/8) Epoch 38, batch 2350, loss[loss=0.1437, simple_loss=0.2564, pruned_loss=0.0155, over 7238.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2582, pruned_loss=0.02827, over 1426470.13 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:33:55,522 INFO [train.py:763] (4/8) Epoch 38, batch 2400, loss[loss=0.1605, simple_loss=0.2627, pruned_loss=0.02913, over 7143.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2576, pruned_loss=0.02831, over 1428529.74 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:35:01,017 INFO [train.py:763] (4/8) Epoch 38, batch 2450, loss[loss=0.1513, simple_loss=0.243, pruned_loss=0.02976, over 7404.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2573, pruned_loss=0.02828, over 1429562.32 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:36:06,992 INFO [train.py:763] (4/8) Epoch 38, batch 2500, loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.02855, over 7410.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2563, pruned_loss=0.02801, over 1427550.60 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:37:12,697 INFO [train.py:763] (4/8) Epoch 38, batch 2550, loss[loss=0.1384, simple_loss=0.2368, pruned_loss=0.02005, over 7419.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2562, pruned_loss=0.02829, over 1432169.04 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:38:18,034 INFO [train.py:763] (4/8) Epoch 38, batch 2600, loss[loss=0.1674, simple_loss=0.2682, pruned_loss=0.0333, over 7153.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.02859, over 1429784.85 frames.], batch size: 26, lr: 1.99e-04
2022-05-01 00:39:23,360 INFO [train.py:763] (4/8) Epoch 38, batch 2650, loss[loss=0.1708, simple_loss=0.2699, pruned_loss=0.03583, over 7050.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02862, over 1430634.77 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 00:40:27,510 INFO [train.py:763] (4/8) Epoch 38, batch 2700, loss[loss=0.1834, simple_loss=0.281, pruned_loss=0.04293, over 7336.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.02843, over 1428823.56 frames.], batch size: 25, lr: 1.99e-04
2022-05-01 00:41:33,246 INFO [train.py:763] (4/8) Epoch 38, batch 2750, loss[loss=0.1437, simple_loss=0.2407, pruned_loss=0.02339, over 7159.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2571, pruned_loss=0.02835, over 1430057.17 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:42:38,764 INFO [train.py:763] (4/8) Epoch 38, batch 2800, loss[loss=0.1742, simple_loss=0.2771, pruned_loss=0.03566, over 7335.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02865, over 1426959.80 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:43:44,126 INFO [train.py:763] (4/8) Epoch 38, batch 2850, loss[loss=0.157, simple_loss=0.2663, pruned_loss=0.02385, over 6365.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.0285, over 1426927.47 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:44:49,672 INFO [train.py:763] (4/8) Epoch 38, batch 2900, loss[loss=0.1782, simple_loss=0.2823, pruned_loss=0.03704, over 7320.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2586, pruned_loss=0.02837, over 1425059.71 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:45:55,139 INFO [train.py:763] (4/8) Epoch 38, batch 2950, loss[loss=0.145, simple_loss=0.2569, pruned_loss=0.01659, over 7331.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2579, pruned_loss=0.02828, over 1427773.00 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:47:00,413 INFO [train.py:763] (4/8) Epoch 38, batch 3000, loss[loss=0.1546, simple_loss=0.2574, pruned_loss=0.02595, over 7233.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2592, pruned_loss=0.02889, over 1428814.42 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:47:00,414 INFO [train.py:783] (4/8) Computing validation loss
2022-05-01 00:47:15,873 INFO [train.py:792] (4/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
2022-05-01 00:48:21,028 INFO [train.py:763] (4/8) Epoch 38, batch 3050, loss[loss=0.1451, simple_loss=0.2353, pruned_loss=0.02744, over 7136.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.0288, over 1425877.37 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:49:26,202 INFO [train.py:763] (4/8) Epoch 38, batch 3100, loss[loss=0.1707, simple_loss=0.2765, pruned_loss=0.03243, over 6484.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2587, pruned_loss=0.02895, over 1418210.33 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:50:31,503 INFO [train.py:763] (4/8) Epoch 38, batch 3150, loss[loss=0.1543, simple_loss=0.2588, pruned_loss=0.0249, over 7396.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02848, over 1423252.24 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:51:36,873 INFO [train.py:763] (4/8) Epoch 38, batch 3200, loss[loss=0.1763, simple_loss=0.2804, pruned_loss=0.03608, over 6417.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02857, over 1424584.91 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:52:42,219 INFO [train.py:763] (4/8) Epoch 38, batch 3250, loss[loss=0.1625, simple_loss=0.2668, pruned_loss=0.02909, over 6288.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2573, pruned_loss=0.02824, over 1424415.78 frames.], batch size: 37, lr: 1.99e-04
2022-05-01 00:53:47,528 INFO [train.py:763] (4/8) Epoch 38, batch 3300, loss[loss=0.1624, simple_loss=0.2668, pruned_loss=0.02896, over 7165.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2571, pruned_loss=0.02819, over 1424455.38 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:54:52,912 INFO [train.py:763] (4/8) Epoch 38, batch 3350, loss[loss=0.1506, simple_loss=0.2477, pruned_loss=0.02671, over 7138.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2563, pruned_loss=0.02772, over 1426955.05 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:55:59,021 INFO [train.py:763] (4/8) Epoch 38, batch 3400, loss[loss=0.1583, simple_loss=0.2609, pruned_loss=0.02783, over 7363.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2563, pruned_loss=0.02778, over 1426949.32 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:57:06,505 INFO [train.py:763] (4/8) Epoch 38, batch 3450, loss[loss=0.1873, simple_loss=0.2893, pruned_loss=0.04268, over 7218.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02847, over 1419182.42 frames.], batch size: 23, lr: 1.99e-04
2022-05-01 00:58:13,607 INFO [train.py:763] (4/8) Epoch 38, batch 3500, loss[loss=0.1494, simple_loss=0.2587, pruned_loss=0.02002, over 7159.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02842, over 1421055.33 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:59:19,211 INFO [train.py:763] (4/8) Epoch 38, batch 3550, loss[loss=0.149, simple_loss=0.2516, pruned_loss=0.02315, over 7350.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2577, pruned_loss=0.02893, over 1423612.76 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 01:00:25,362 INFO [train.py:763] (4/8) Epoch 38, batch 3600, loss[loss=0.1349, simple_loss=0.231, pruned_loss=0.01946, over 7279.00 frames.], tot_loss[loss=0.1579, simple_loss=0.258, pruned_loss=0.02893, over 1423785.63 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 01:01:30,571 INFO [train.py:763] (4/8) Epoch 38, batch 3650, loss[loss=0.1613, simple_loss=0.2739, pruned_loss=0.02438, over 7009.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02883, over 1425014.37 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 01:02:35,701 INFO [train.py:763] (4/8) Epoch 38, batch 3700, loss[loss=0.1445, simple_loss=0.2443, pruned_loss=0.02236, over 6494.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02897, over 1421605.47 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 01:03:41,345 INFO [train.py:763] (4/8) Epoch 38, batch 3750, loss[loss=0.1542, simple_loss=0.2639, pruned_loss=0.02225, over 7186.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2583, pruned_loss=0.02907, over 1415413.39 frames.], batch size: 23, lr: 1.98e-04
2022-05-01 01:04:46,826 INFO [train.py:763] (4/8) Epoch 38, batch 3800, loss[loss=0.1764, simple_loss=0.2761, pruned_loss=0.03829, over 7360.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02881, over 1421588.59 frames.], batch size: 19, lr: 1.98e-04
2022-05-01 01:05:52,023 INFO [train.py:763] (4/8) Epoch 38, batch 3850, loss[loss=0.1841, simple_loss=0.275, pruned_loss=0.04661, over 5018.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02898, over 1419002.06 frames.], batch size: 52, lr: 1.98e-04
2022-05-01 01:06:57,231 INFO [train.py:763] (4/8) Epoch 38, batch 3900, loss[loss=0.1677, simple_loss=0.2652, pruned_loss=0.03515, over 7041.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02886, over 1420521.70 frames.], batch size: 28, lr: 1.98e-04
2022-05-01 01:08:02,834 INFO [train.py:763] (4/8) Epoch 38, batch 3950, loss[loss=0.1806, simple_loss=0.284, pruned_loss=0.03861, over 7287.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2584, pruned_loss=0.02857, over 1422356.10 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:09:08,084 INFO [train.py:763] (4/8) Epoch 38, batch 4000, loss[loss=0.1565, simple_loss=0.2645, pruned_loss=0.02429, over 6758.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02852, over 1425625.36 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:10:13,450 INFO [train.py:763] (4/8) Epoch 38, batch 4050, loss[loss=0.1626, simple_loss=0.2673, pruned_loss=0.02898, over 6781.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02867, over 1423750.32 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:11:18,893 INFO [train.py:763] (4/8) Epoch 38, batch 4100, loss[loss=0.157, simple_loss=0.266, pruned_loss=0.02404, over 7213.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02854, over 1422206.15 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:12:24,272 INFO [train.py:763] (4/8) Epoch 38, batch 4150, loss[loss=0.1625, simple_loss=0.2789, pruned_loss=0.02304, over 7216.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02853, over 1419253.91 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:13:30,544 INFO [train.py:763] (4/8) Epoch 38, batch 4200, loss[loss=0.1442, simple_loss=0.2471, pruned_loss=0.02067, over 6791.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.029, over 1419349.59 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:14:35,879 INFO [train.py:763] (4/8) Epoch 38, batch 4250, loss[loss=0.1549, simple_loss=0.2504, pruned_loss=0.02967, over 7144.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2585, pruned_loss=0.02892, over 1416124.69 frames.], batch size: 17, lr: 1.98e-04
2022-05-01 01:15:41,251 INFO [train.py:763] (4/8) Epoch 38, batch 4300, loss[loss=0.1684, simple_loss=0.2787, pruned_loss=0.0291, over 7299.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2596, pruned_loss=0.02906, over 1417808.57 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:16:46,654 INFO [train.py:763] (4/8) Epoch 38, batch 4350, loss[loss=0.1272, simple_loss=0.2277, pruned_loss=0.01336, over 7436.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02925, over 1414611.78 frames.], batch size: 20, lr: 1.98e-04
2022-05-01 01:17:51,772 INFO [train.py:763] (4/8) Epoch 38, batch 4400, loss[loss=0.1581, simple_loss=0.2625, pruned_loss=0.02687, over 7330.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2611, pruned_loss=0.02981, over 1411148.04 frames.], batch size: 22, lr: 1.98e-04
2022-05-01 01:18:57,808 INFO [train.py:763] (4/8) Epoch 38, batch 4450, loss[loss=0.1547, simple_loss=0.2401, pruned_loss=0.03468, over 7011.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2624, pruned_loss=0.03027, over 1398272.30 frames.], batch size: 16, lr: 1.98e-04
2022-05-01 01:20:03,894 INFO [train.py:763] (4/8) Epoch 38, batch 4500, loss[loss=0.1562, simple_loss=0.2513, pruned_loss=0.03052, over 7172.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2624, pruned_loss=0.03038, over 1387670.37 frames.], batch size: 18, lr: 1.98e-04
2022-05-01 01:21:09,321 INFO [train.py:763] (4/8) Epoch 38, batch 4550, loss[loss=0.183, simple_loss=0.2821, pruned_loss=0.04192, over 5102.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2643, pruned_loss=0.03161, over 1350076.98 frames.], batch size: 52, lr: 1.98e-04
2022-05-01 01:22:39,304 INFO [train.py:763] (4/8) Epoch 39, batch 0, loss[loss=0.1753, simple_loss=0.2766, pruned_loss=0.03694, over 7270.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2766, pruned_loss=0.03694, over 7270.00 frames.], batch size: 24, lr: 1.96e-04
2022-05-01 01:23:44,999 INFO [train.py:763] (4/8) Epoch 39, batch 50, loss[loss=0.1325, simple_loss=0.2302, pruned_loss=0.01738, over 7270.00 frames.], tot_loss[loss=0.162, simple_loss=0.2629, pruned_loss=0.03051, over 317080.74 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:24:50,352 INFO [train.py:763] (4/8) Epoch 39, batch 100, loss[loss=0.1447, simple_loss=0.2425, pruned_loss=0.0234, over 7355.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2594, pruned_loss=0.02898, over 562578.41 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:25:56,215 INFO [train.py:763] (4/8) Epoch 39, batch 150, loss[loss=0.1766, simple_loss=0.2854, pruned_loss=0.03396, over 7233.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2553, pruned_loss=0.02828, over 754541.86 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:27:01,293 INFO [train.py:763] (4/8) Epoch 39, batch 200, loss[loss=0.1365, simple_loss=0.2255, pruned_loss=0.02376, over 7411.00 frames.], tot_loss[loss=0.158, simple_loss=0.2578, pruned_loss=0.0291, over 903420.33 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:28:06,658 INFO [train.py:763] (4/8) Epoch 39, batch 250, loss[loss=0.2021, simple_loss=0.3004, pruned_loss=0.05195, over 7122.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2587, pruned_loss=0.02957, over 1016514.75 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:29:11,526 INFO [train.py:763] (4/8) Epoch 39, batch 300, loss[loss=0.1788, simple_loss=0.2796, pruned_loss=0.03894, over 7277.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02939, over 1107343.11 frames.], batch size: 24, lr: 1.95e-04
2022-05-01 01:30:16,874 INFO [train.py:763] (4/8) Epoch 39, batch 350, loss[loss=0.1375, simple_loss=0.2405, pruned_loss=0.01723, over 7154.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02926, over 1172429.48 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:31:22,219 INFO [train.py:763] (4/8) Epoch 39, batch 400, loss[loss=0.1706, simple_loss=0.2697, pruned_loss=0.03571, over 7200.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02952, over 1229830.21 frames.], batch size: 26, lr: 1.95e-04
2022-05-01 01:32:27,456 INFO [train.py:763] (4/8) Epoch 39, batch 450, loss[loss=0.1799, simple_loss=0.2805, pruned_loss=0.0397, over 7301.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02878, over 1273803.01 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:33:32,869 INFO [train.py:763] (4/8) Epoch 39, batch 500, loss[loss=0.1442, simple_loss=0.2462, pruned_loss=0.02108, over 7325.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2575, pruned_loss=0.02877, over 1305284.24 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:34:38,280 INFO [train.py:763] (4/8) Epoch 39, batch 550, loss[loss=0.1616, simple_loss=0.2561, pruned_loss=0.03351, over 7235.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2573, pruned_loss=0.0288, over 1327379.97 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:35:43,496 INFO [train.py:763] (4/8) Epoch 39, batch 600, loss[loss=0.1559, simple_loss=0.2497, pruned_loss=0.03111, over 7258.00 frames.], tot_loss[loss=0.1571, simple_loss=0.257, pruned_loss=0.0286, over 1349511.09 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:36:48,736 INFO [train.py:763] (4/8) Epoch 39, batch 650, loss[loss=0.151, simple_loss=0.2527, pruned_loss=0.02469, over 7229.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2573, pruned_loss=0.02868, over 1368916.32 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:37:53,920 INFO [train.py:763] (4/8) Epoch 39, batch 700, loss[loss=0.1308, simple_loss=0.221, pruned_loss=0.02034, over 7283.00 frames.], tot_loss[loss=0.1579, simple_loss=0.258, pruned_loss=0.02896, over 1381842.65 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:38:59,262 INFO [train.py:763] (4/8) Epoch 39, batch 750, loss[loss=0.1642, simple_loss=0.2576, pruned_loss=0.03542, over 7359.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02867, over 1387711.32 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:40:04,490 INFO [train.py:763] (4/8) Epoch 39, batch 800, loss[loss=0.1663, simple_loss=0.271, pruned_loss=0.03082, over 7118.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02842, over 1396549.07 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:41:18,500 INFO [train.py:763] (4/8) Epoch 39, batch 850, loss[loss=0.1296, simple_loss=0.228, pruned_loss=0.01566, over 7127.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2588, pruned_loss=0.02878, over 1403034.20 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:42:32,263 INFO [train.py:763] (4/8) Epoch 39, batch 900, loss[loss=0.1666, simple_loss=0.2694, pruned_loss=0.03194, over 7181.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02883, over 1409056.80 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:43:55,209 INFO [train.py:763] (4/8) Epoch 39, batch 950, loss[loss=0.1764, simple_loss=0.2705, pruned_loss=0.04111, over 5248.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.0291, over 1411490.40 frames.], batch size: 52, lr: 1.95e-04
2022-05-01 01:45:01,220 INFO [train.py:763] (4/8) Epoch 39, batch 1000, loss[loss=0.1612, simple_loss=0.2776, pruned_loss=0.0224, over 7118.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02906, over 1409904.42 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:46:06,269 INFO [train.py:763] (4/8) Epoch 39, batch 1050, loss[loss=0.1551, simple_loss=0.2588, pruned_loss=0.0257, over 7219.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02908, over 1408843.80 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:47:29,491 INFO [train.py:763] (4/8) Epoch 39, batch 1100, loss[loss=0.1638, simple_loss=0.2627, pruned_loss=0.03246, over 7165.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02867, over 1408508.01 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:48:43,940 INFO [train.py:763] (4/8) Epoch 39, batch 1150, loss[loss=0.1732, simple_loss=0.2791, pruned_loss=0.03363, over 6801.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02866, over 1415661.49 frames.], batch size: 31, lr: 1.95e-04
2022-05-01 01:49:48,901 INFO [train.py:763] (4/8) Epoch 39, batch 1200, loss[loss=0.1597, simple_loss=0.2654, pruned_loss=0.02697, over 6389.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02895, over 1418449.59 frames.], batch size: 37, lr: 1.95e-04
2022-05-01 01:50:54,367 INFO [train.py:763] (4/8) Epoch 39, batch 1250, loss[loss=0.1537, simple_loss=0.2561, pruned_loss=0.02562, over 7328.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2587, pruned_loss=0.02887, over 1422379.59 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:51:59,439 INFO [train.py:763] (4/8) Epoch 39, batch 1300, loss[loss=0.1697, simple_loss=0.2705, pruned_loss=0.03451, over 7438.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02887, over 1422582.85 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:53:04,814 INFO [train.py:763] (4/8) Epoch 39, batch 1350, loss[loss=0.1622, simple_loss=0.2642, pruned_loss=0.0301, over 6304.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02865, over 1421844.47 frames.], batch size: 38, lr: 1.95e-04
2022-05-01 01:54:11,087 INFO [train.py:763] (4/8) Epoch 39, batch 1400, loss[loss=0.1604, simple_loss=0.264, pruned_loss=0.02836, over 6427.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02862, over 1423743.02 frames.], batch size: 37, lr: 1.95e-04
2022-05-01 01:55:16,350 INFO [train.py:763] (4/8) Epoch 39, batch 1450, loss[loss=0.1938, simple_loss=0.2998, pruned_loss=0.04392, over 7183.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2584, pruned_loss=0.02851, over 1425155.03 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:56:21,442 INFO [train.py:763] (4/8) Epoch 39, batch 1500, loss[loss=0.1422, simple_loss=0.237, pruned_loss=0.02373, over 7134.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02871, over 1425959.79 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:57:28,664 INFO [train.py:763] (4/8) Epoch 39, batch 1550, loss[loss=0.1551, simple_loss=0.2637, pruned_loss=0.02326, over 7210.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2574, pruned_loss=0.02856, over 1423651.95 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:58:35,228 INFO [train.py:763] (4/8) Epoch 39, batch 1600, loss[loss=0.1462, simple_loss=0.2501, pruned_loss=0.02111, over 7091.00 frames.], tot_loss[loss=0.1569, simple_loss=0.257, pruned_loss=0.02834, over 1426366.89 frames.], batch size: 28, lr: 1.95e-04
2022-05-01 01:59:41,355 INFO [train.py:763] (4/8) Epoch 39, batch 1650, loss[loss=0.2179, simple_loss=0.3039, pruned_loss=0.06598, over 4837.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2575, pruned_loss=0.02847, over 1419746.50 frames.], batch size: 52, lr: 1.95e-04
2022-05-01 02:00:47,161 INFO [train.py:763] (4/8) Epoch 39, batch 1700, loss[loss=0.1181, simple_loss=0.2051, pruned_loss=0.01556, over 7407.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2576, pruned_loss=0.02873, over 1413416.22 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 02:01:53,359 INFO [train.py:763] (4/8) Epoch 39, batch 1750, loss[loss=0.1473, simple_loss=0.2439, pruned_loss=0.0254, over 7319.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02869, over 1415537.62 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 02:02:58,279 INFO [train.py:763] (4/8) Epoch 39, batch 1800, loss[loss=0.1568, simple_loss=0.2611, pruned_loss=0.02622, over 7344.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.02874, over 1418475.19 frames.], batch size: 22, lr: 1.95e-04
2022-05-01 02:04:03,599 INFO [train.py:763] (4/8) Epoch 39, batch 1850, loss[loss=0.1505, simple_loss=0.2486, pruned_loss=0.02622, over 7067.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02865, over 1421491.69 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 02:05:08,882 INFO [train.py:763] (4/8) Epoch 39, batch 1900, loss[loss=0.1385, simple_loss=0.2375, pruned_loss=0.0197, over 7149.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02849, over 1424958.21 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:06:14,309 INFO [train.py:763] (4/8) Epoch 39, batch 1950, loss[loss=0.1701, simple_loss=0.2633, pruned_loss=0.03847, over 4888.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2583, pruned_loss=0.02854, over 1418865.18 frames.], batch size: 53, lr: 1.94e-04
2022-05-01 02:07:19,645 INFO [train.py:763] (4/8) Epoch 39, batch 2000, loss[loss=0.152, simple_loss=0.2421, pruned_loss=0.03094, over 7064.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.0283, over 1422228.92 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:08:24,808 INFO [train.py:763] (4/8) Epoch 39, batch 2050, loss[loss=0.1374, simple_loss=0.24, pruned_loss=0.01742, over 7425.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2574, pruned_loss=0.028, over 1426150.36 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:09:30,528 INFO [train.py:763] (4/8) Epoch 39, batch 2100, loss[loss=0.1506, simple_loss=0.2338, pruned_loss=0.03375, over 7412.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2571, pruned_loss=0.0278, over 1424775.40 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:10:35,927 INFO [train.py:763] (4/8) Epoch 39, batch 2150, loss[loss=0.16, simple_loss=0.2575, pruned_loss=0.03119, over 7144.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2574, pruned_loss=0.02808, over 1428920.49 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:11:43,126 INFO [train.py:763] (4/8) Epoch 39, batch 2200, loss[loss=0.155, simple_loss=0.2502, pruned_loss=0.02986, over 7236.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2571, pruned_loss=0.02805, over 1431622.85 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:12:48,268 INFO [train.py:763] (4/8) Epoch 39, batch 2250, loss[loss=0.1701, simple_loss=0.2813, pruned_loss=0.0295, over 7187.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02847, over 1429346.31 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:13:53,526 INFO [train.py:763] (4/8) Epoch 39, batch 2300, loss[loss=0.1412, simple_loss=0.2443, pruned_loss=0.0191, over 7429.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2564, pruned_loss=0.02814, over 1426463.75 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:15:00,684 INFO [train.py:763] (4/8) Epoch 39, batch 2350, loss[loss=0.1779, simple_loss=0.2812, pruned_loss=0.03736, over 7334.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2562, pruned_loss=0.02804, over 1425633.13 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:16:07,732 INFO [train.py:763] (4/8) Epoch 39, batch 2400, loss[loss=0.1594, simple_loss=0.2652, pruned_loss=0.02678, over 7202.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2565, pruned_loss=0.02827, over 1425972.57 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:17:13,326 INFO [train.py:763] (4/8) Epoch 39, batch 2450, loss[loss=0.1869, simple_loss=0.2804, pruned_loss=0.04666, over 7039.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02861, over 1421061.35 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:18:19,516 INFO [train.py:763] (4/8) Epoch 39, batch 2500, loss[loss=0.1429, simple_loss=0.2444, pruned_loss=0.02068, over 7407.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2569, pruned_loss=0.02836, over 1417986.29 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:19:24,723 INFO [train.py:763] (4/8) Epoch 39, batch 2550, loss[loss=0.1812, simple_loss=0.2811, pruned_loss=0.04067, over 7034.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2573, pruned_loss=0.02877, over 1418287.12 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:20:31,561 INFO [train.py:763] (4/8) Epoch 39, batch 2600, loss[loss=0.1708, simple_loss=0.2723, pruned_loss=0.03463, over 7331.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2571, pruned_loss=0.0289, over 1418026.70 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:21:37,533 INFO [train.py:763] (4/8) Epoch 39, batch 2650, loss[loss=0.1727, simple_loss=0.2634, pruned_loss=0.04098, over 7166.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2578, pruned_loss=0.02891, over 1420205.81 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:22:43,384 INFO [train.py:763] (4/8) Epoch 39, batch 2700, loss[loss=0.1564, simple_loss=0.2634, pruned_loss=0.02467, over 7121.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.0285, over 1421787.43 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:23:48,609 INFO [train.py:763] (4/8) Epoch 39, batch 2750, loss[loss=0.1611, simple_loss=0.2719, pruned_loss=0.02514, over 7286.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2579, pruned_loss=0.02827, over 1425175.77 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:24:53,687 INFO [train.py:763] (4/8) Epoch 39, batch 2800, loss[loss=0.1682, simple_loss=0.2676, pruned_loss=0.03442, over 7057.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02889, over 1421539.01 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:25:58,653 INFO [train.py:763] (4/8) Epoch 39, batch 2850, loss[loss=0.1397, simple_loss=0.2483, pruned_loss=0.01555, over 6307.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02853, over 1418633.40 frames.], batch size: 38, lr: 1.94e-04
2022-05-01 02:27:03,579 INFO [train.py:763] (4/8) Epoch 39, batch 2900, loss[loss=0.1674, simple_loss=0.2695, pruned_loss=0.03265, over 7073.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2582, pruned_loss=0.02829, over 1419010.90 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:28:08,498 INFO [train.py:763] (4/8) Epoch 39, batch 2950, loss[loss=0.1605, simple_loss=0.2736, pruned_loss=0.02371, over 7304.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2597, pruned_loss=0.02896, over 1418454.83 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:29:13,393 INFO [train.py:763] (4/8) Epoch 39, batch 3000, loss[loss=0.162, simple_loss=0.2645, pruned_loss=0.02975, over 7324.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2599, pruned_loss=0.02938, over 1413418.54 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:29:13,395 INFO [train.py:783] (4/8) Computing validation loss
2022-05-01 02:29:28,415 INFO [train.py:792] (4/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
2022-05-01 02:30:33,955 INFO [train.py:763] (4/8) Epoch 39, batch 3050, loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03018, over 7354.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02912, over 1415661.46 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:31:41,152 INFO [train.py:763] (4/8) Epoch 39, batch 3100, loss[loss=0.1912, simple_loss=0.2855, pruned_loss=0.0485, over 7138.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02905, over 1417856.17 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:32:47,800 INFO [train.py:763] (4/8) Epoch 39, batch 3150, loss[loss=0.1735, simple_loss=0.2794, pruned_loss=0.03378, over 7151.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02846, over 1421645.44 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:33:53,384 INFO [train.py:763] (4/8) Epoch 39, batch 3200, loss[loss=0.1769, simple_loss=0.2774, pruned_loss=0.03818, over 4898.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02848, over 1422528.21 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:34:58,486 INFO [train.py:763] (4/8) Epoch 39, batch 3250, loss[loss=0.1833, simple_loss=0.2852, pruned_loss=0.04071, over 7370.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2583, pruned_loss=0.02822, over 1421133.08 frames.], batch size: 23, lr: 1.94e-04
2022-05-01 02:36:03,623 INFO [train.py:763] (4/8) Epoch 39, batch 3300, loss[loss=0.178, simple_loss=0.2851, pruned_loss=0.0355, over 7125.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.02831, over 1419704.54 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:37:08,798 INFO [train.py:763] (4/8) Epoch 39, batch 3350, loss[loss=0.1464, simple_loss=0.2492, pruned_loss=0.02174, over 7119.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02853, over 1418341.05 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:38:14,797 INFO [train.py:763] (4/8) Epoch 39, batch 3400, loss[loss=0.1498, simple_loss=0.2541, pruned_loss=0.02276, over 7161.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02828, over 1418411.30 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:39:20,469 INFO [train.py:763] (4/8) Epoch 39, batch 3450, loss[loss=0.1415, simple_loss=0.2319, pruned_loss=0.02549, over 7280.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.0283, over 1417271.46 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:40:25,649 INFO [train.py:763] (4/8) Epoch 39, batch 3500, loss[loss=0.1585, simple_loss=0.2707, pruned_loss=0.0232, over 7325.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2583, pruned_loss=0.02864, over 1418297.55 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:41:31,486 INFO [train.py:763] (4/8) Epoch 39, batch 3550, loss[loss=0.1504, simple_loss=0.2476, pruned_loss=0.02655, over 7076.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02848, over 1419001.95 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:42:37,765 INFO [train.py:763] (4/8) Epoch 39, batch 3600, loss[loss=0.2004, simple_loss=0.2872, pruned_loss=0.05682, over 5057.00 frames.], tot_loss[loss=0.158, simple_loss=0.2579, pruned_loss=0.02901, over 1416335.17 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:43:44,821 INFO [train.py:763] (4/8) Epoch 39, batch 3650, loss[loss=0.1696, simple_loss=0.2724, pruned_loss=0.03337, over 6486.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02853, over 1418086.18 frames.], batch size: 37, lr: 1.94e-04
2022-05-01 02:44:50,053 INFO [train.py:763] (4/8) Epoch 39, batch 3700, loss[loss=0.1439, simple_loss=0.2356, pruned_loss=0.02612, over 7141.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2578, pruned_loss=0.02839, over 1422235.44 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:45:55,094 INFO [train.py:763] (4/8) Epoch 39, batch 3750, loss[loss=0.155, simple_loss=0.2547, pruned_loss=0.02768, over 7346.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2586, pruned_loss=0.02835, over 1418366.31 frames.], batch size: 19, lr: 1.93e-04
2022-05-01 02:47:00,704 INFO [train.py:763] (4/8) Epoch 39, batch 3800, loss[loss=0.1266, simple_loss=0.2259, pruned_loss=0.01362, over 6989.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2584, pruned_loss=0.0281, over 1423573.69 frames.], batch size: 16, lr: 1.93e-04
2022-05-01 02:48:07,767 INFO [train.py:763] (4/8) Epoch 39, batch 3850, loss[loss=0.1758, simple_loss=0.2789, pruned_loss=0.03631, over 7435.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2578, pruned_loss=0.0279, over 1419455.97 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:49:13,629 INFO [train.py:763] (4/8) Epoch 39, batch 3900, loss[loss=0.1899, simple_loss=0.2882, pruned_loss=0.04583, over 7202.00 frames.], tot_loss[loss=0.1571, simple_loss=0.258, pruned_loss=0.02807, over 1420367.15 frames.], batch size: 23, lr: 1.93e-04
2022-05-01 02:50:20,005 INFO [train.py:763] (4/8) Epoch 39, batch 3950, loss[loss=0.1556, simple_loss=0.2359, pruned_loss=0.03764, over 7064.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.02834, over 1416018.97 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:51:25,344 INFO [train.py:763] (4/8) Epoch 39, batch 4000, loss[loss=0.1454, simple_loss=0.2346, pruned_loss=0.02814, over 7124.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02859, over 1416122.50 frames.], batch size: 17, lr: 1.93e-04
2022-05-01 02:52:30,793 INFO [train.py:763] (4/8) Epoch 39, batch 4050, loss[loss=0.1688, simple_loss=0.2877, pruned_loss=0.02492, over 7207.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02856, over 1421153.60 frames.], batch size: 22, lr: 1.93e-04
2022-05-01 02:53:35,943 INFO [train.py:763] (4/8) Epoch 39, batch 4100, loss[loss=0.1569, simple_loss=0.2652, pruned_loss=0.02435, over 7227.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02854, over 1422019.41 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 02:54:41,368 INFO [train.py:763] (4/8) Epoch 39, batch 4150, loss[loss=0.1705, simple_loss=0.2635, pruned_loss=0.03874, over 7276.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02865, over 1424023.04 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:55:46,807 INFO [train.py:763] (4/8) Epoch 39, batch 4200, loss[loss=0.1625, simple_loss=0.2639, pruned_loss=0.03061, over 7155.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2592, pruned_loss=0.02894, over 1425288.56 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:56:52,114 INFO [train.py:763] (4/8) Epoch 39, batch 4250, loss[loss=0.1523, simple_loss=0.2542, pruned_loss=0.02518, over 7305.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02886, over 1419967.88 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:57:57,421 INFO [train.py:763] (4/8) Epoch 39, batch 4300, loss[loss=0.1362, simple_loss=0.2345, pruned_loss=0.01897, over 7170.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02861, over 1421465.96 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:59:02,810 INFO [train.py:763] (4/8) Epoch 39, batch 4350, loss[loss=0.1553, simple_loss=0.2638, pruned_loss=0.02345, over 7330.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.0282, over 1423079.01 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 03:00:09,026 INFO [train.py:763] (4/8) Epoch 39, batch 4400, loss[loss=0.1686, simple_loss=0.2705, pruned_loss=0.03332, over 6686.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02828, over 1422591.98 frames.], batch size: 31, lr: 1.93e-04
2022-05-01 03:01:14,004 INFO [train.py:763] (4/8) Epoch 39, batch 4450, loss[loss=0.1606, simple_loss=0.2554, pruned_loss=0.03295, over 7158.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02861, over 1410385.85 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 03:02:19,219 INFO [train.py:763] (4/8) Epoch 39, batch 4500, loss[loss=0.1775, simple_loss=0.2777, pruned_loss=0.03864, over 7219.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2597, pruned_loss=0.02909, over 1402540.64 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 03:03:25,868 INFO [train.py:763] (4/8) Epoch 39, batch 4550, loss[loss=0.1294, simple_loss=0.2235, pruned_loss=0.01771, over 6817.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2561, pruned_loss=0.02846, over 1395377.89 frames.], batch size: 15, lr: 1.93e-04
2022-05-01 03:04:15,423 INFO [train.py:971] (4/8) Done!