2022-04-28 06:39:03,133 INFO [train.py:827] (3/8) Training started
2022-04-28 06:39:03,133 INFO [train.py:837] (3/8) Device: cuda:3
2022-04-28 06:39:03,161 INFO [train.py:846] (3/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', '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] (3/8) About to create model
2022-04-28 06:39:03,698 INFO [train.py:852] (3/8) Number of model parameters: 118129516
2022-04-28 06:39:09,726 INFO [train.py:858] (3/8) Using DDP
2022-04-28 06:39:10,514 INFO [asr_datamodule.py:391] (3/8) About to get train-clean-100 cuts
2022-04-28 06:39:16,609 INFO [asr_datamodule.py:398] (3/8) About to get train-clean-360 cuts
2022-04-28 06:39:41,349 INFO [asr_datamodule.py:405] (3/8) About to get train-other-500 cuts
2022-04-28 06:40:23,607 INFO [asr_datamodule.py:209] (3/8) Enable MUSAN
2022-04-28 06:40:23,607 INFO [asr_datamodule.py:210] (3/8) About to get Musan cuts
2022-04-28 06:40:24,878 INFO [asr_datamodule.py:238] (3/8) Enable SpecAugment
2022-04-28 06:40:24,878 INFO [asr_datamodule.py:239] (3/8) Time warp factor: 80
2022-04-28 06:40:24,878 INFO [asr_datamodule.py:251] (3/8) Num frame mask: 10
2022-04-28 06:40:24,879 INFO [asr_datamodule.py:264] (3/8) About to create train dataset
2022-04-28 06:40:24,879 INFO [asr_datamodule.py:292] (3/8) Using BucketingSampler.
2022-04-28 06:40:29,471 INFO [asr_datamodule.py:308] (3/8) About to create train dataloader
2022-04-28 06:40:29,472 INFO [asr_datamodule.py:412] (3/8) About to get dev-clean cuts
2022-04-28 06:40:29,734 INFO [asr_datamodule.py:417] (3/8) About to get dev-other cuts
2022-04-28 06:40:29,861 INFO [asr_datamodule.py:339] (3/8) About to create dev dataset
2022-04-28 06:40:29,872 INFO [asr_datamodule.py:358] (3/8) About to create dev dataloader
2022-04-28 06:40:29,872 INFO [train.py:987] (3/8) 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] (3/8) Reducer buckets have been rebuilt in this iteration.
2022-04-28 06:41:17,063 INFO [train.py:763] (3/8) Epoch 0, batch 0, loss[loss=0.6591, simple_loss=1.318, pruned_loss=6.96, over 7286.00 frames.], tot_loss[loss=0.6591, simple_loss=1.318, pruned_loss=6.96, over 7286.00 frames.], batch size: 17, lr: 3.00e-03
2022-04-28 06:42:23,567 INFO [train.py:763] (3/8) Epoch 0, batch 50, loss[loss=0.5193, simple_loss=1.039, pruned_loss=6.583, over 7145.00 frames.], tot_loss[loss=0.5747, simple_loss=1.149, pruned_loss=6.964, over 323403.14 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:43:30,298 INFO [train.py:763] (3/8) Epoch 0, batch 100, loss[loss=0.411, simple_loss=0.8219, pruned_loss=6.742, over 6984.00 frames.], tot_loss[loss=0.5154, simple_loss=1.031, pruned_loss=6.882, over 566246.52 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:44:37,535 INFO [train.py:763] (3/8) Epoch 0, batch 150, loss[loss=0.3859, simple_loss=0.7718, pruned_loss=6.642, over 7004.00 frames.], tot_loss[loss=0.4783, simple_loss=0.9566, pruned_loss=6.865, over 757306.73 frames.], batch size: 16, lr: 3.00e-03
2022-04-28 06:45:44,956 INFO [train.py:763] (3/8) Epoch 0, batch 200, loss[loss=0.4048, simple_loss=0.8095, pruned_loss=6.759, over 7266.00 frames.], tot_loss[loss=0.4534, simple_loss=0.9067, pruned_loss=6.838, over 907523.01 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:46:50,979 INFO [train.py:763] (3/8) Epoch 0, batch 250, loss[loss=0.4213, simple_loss=0.8427, pruned_loss=6.787, over 7310.00 frames.], tot_loss[loss=0.4355, simple_loss=0.871, pruned_loss=6.793, over 1016093.93 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:47:58,724 INFO [train.py:763] (3/8) Epoch 0, batch 300, loss[loss=0.4254, simple_loss=0.8508, pruned_loss=6.779, over 7303.00 frames.], tot_loss[loss=0.4239, simple_loss=0.8479, pruned_loss=6.766, over 1108842.22 frames.], batch size: 25, lr: 3.00e-03
2022-04-28 06:49:06,197 INFO [train.py:763] (3/8) Epoch 0, batch 350, loss[loss=0.4013, simple_loss=0.8026, pruned_loss=6.636, over 7272.00 frames.], tot_loss[loss=0.4135, simple_loss=0.827, pruned_loss=6.727, over 1178352.97 frames.], batch size: 19, lr: 3.00e-03
2022-04-28 06:50:12,116 INFO [train.py:763] (3/8) Epoch 0, batch 400, loss[loss=0.3873, simple_loss=0.7746, pruned_loss=6.655, over 7426.00 frames.], tot_loss[loss=0.4037, simple_loss=0.8074, pruned_loss=6.702, over 1231098.69 frames.], batch size: 21, lr: 3.00e-03
2022-04-28 06:51:17,801 INFO [train.py:763] (3/8) Epoch 0, batch 450, loss[loss=0.3379, simple_loss=0.6758, pruned_loss=6.633, over 7410.00 frames.], tot_loss[loss=0.3907, simple_loss=0.7813, pruned_loss=6.681, over 1268383.12 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:52:24,499 INFO [train.py:763] (3/8) Epoch 0, batch 500, loss[loss=0.3106, simple_loss=0.6211, pruned_loss=6.684, over 7209.00 frames.], tot_loss[loss=0.3749, simple_loss=0.7498, pruned_loss=6.672, over 1303984.82 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:53:29,995 INFO [train.py:763] (3/8) Epoch 0, batch 550, loss[loss=0.3325, simple_loss=0.6651, pruned_loss=6.796, over 7336.00 frames.], tot_loss[loss=0.3607, simple_loss=0.7214, pruned_loss=6.673, over 1330274.69 frames.], batch size: 22, lr: 2.99e-03
2022-04-28 06:54:36,573 INFO [train.py:763] (3/8) Epoch 0, batch 600, loss[loss=0.2981, simple_loss=0.5962, pruned_loss=6.667, over 7123.00 frames.], tot_loss[loss=0.3454, simple_loss=0.6909, pruned_loss=6.665, over 1351262.06 frames.], batch size: 21, lr: 2.99e-03
2022-04-28 06:55:42,124 INFO [train.py:763] (3/8) Epoch 0, batch 650, loss[loss=0.236, simple_loss=0.4719, pruned_loss=6.504, over 6989.00 frames.], tot_loss[loss=0.3313, simple_loss=0.6626, pruned_loss=6.654, over 1369457.65 frames.], batch size: 16, lr: 2.99e-03
2022-04-28 06:56:47,773 INFO [train.py:763] (3/8) Epoch 0, batch 700, loss[loss=0.279, simple_loss=0.5581, pruned_loss=6.664, over 7191.00 frames.], tot_loss[loss=0.3174, simple_loss=0.6348, pruned_loss=6.64, over 1381348.24 frames.], batch size: 23, lr: 2.99e-03
2022-04-28 06:57:54,484 INFO [train.py:763] (3/8) Epoch 0, batch 750, loss[loss=0.2568, simple_loss=0.5136, pruned_loss=6.518, over 7285.00 frames.], tot_loss[loss=0.3057, simple_loss=0.6114, pruned_loss=6.626, over 1393501.81 frames.], batch size: 17, lr: 2.98e-03
2022-04-28 06:59:01,267 INFO [train.py:763] (3/8) Epoch 0, batch 800, loss[loss=0.2705, simple_loss=0.541, pruned_loss=6.718, over 7125.00 frames.], tot_loss[loss=0.2949, simple_loss=0.5897, pruned_loss=6.616, over 1398570.79 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:00:07,431 INFO [train.py:763] (3/8) Epoch 0, batch 850, loss[loss=0.2628, simple_loss=0.5256, pruned_loss=6.656, over 7227.00 frames.], tot_loss[loss=0.2851, simple_loss=0.5702, pruned_loss=6.604, over 1403582.62 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:01:13,427 INFO [train.py:763] (3/8) Epoch 0, batch 900, loss[loss=0.2266, simple_loss=0.4533, pruned_loss=6.543, over 7309.00 frames.], tot_loss[loss=0.2758, simple_loss=0.5516, pruned_loss=6.592, over 1409101.19 frames.], batch size: 21, lr: 2.98e-03
2022-04-28 07:02:19,010 INFO [train.py:763] (3/8) Epoch 0, batch 950, loss[loss=0.2107, simple_loss=0.4213, pruned_loss=6.461, over 6992.00 frames.], tot_loss[loss=0.2692, simple_loss=0.5385, pruned_loss=6.583, over 1405256.02 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:03:26,141 INFO [train.py:763] (3/8) Epoch 0, batch 1000, loss[loss=0.21, simple_loss=0.42, pruned_loss=6.459, over 6986.00 frames.], tot_loss[loss=0.263, simple_loss=0.5259, pruned_loss=6.577, over 1405591.55 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:04:32,977 INFO [train.py:763] (3/8) Epoch 0, batch 1050, loss[loss=0.2129, simple_loss=0.4258, pruned_loss=6.519, over 6981.00 frames.], tot_loss[loss=0.2577, simple_loss=0.5153, pruned_loss=6.574, over 1407974.34 frames.], batch size: 16, lr: 2.97e-03
2022-04-28 07:05:39,529 INFO [train.py:763] (3/8) Epoch 0, batch 1100, loss[loss=0.245, simple_loss=0.49, pruned_loss=6.702, over 7189.00 frames.], tot_loss[loss=0.2523, simple_loss=0.5045, pruned_loss=6.577, over 1411438.35 frames.], batch size: 22, lr: 2.96e-03
2022-04-28 07:06:46,910 INFO [train.py:763] (3/8) Epoch 0, batch 1150, loss[loss=0.2295, simple_loss=0.459, pruned_loss=6.474, over 6718.00 frames.], tot_loss[loss=0.2473, simple_loss=0.4947, pruned_loss=6.57, over 1412961.63 frames.], batch size: 31, lr: 2.96e-03
2022-04-28 07:07:52,782 INFO [train.py:763] (3/8) Epoch 0, batch 1200, loss[loss=0.2432, simple_loss=0.4864, pruned_loss=6.748, over 7170.00 frames.], tot_loss[loss=0.2429, simple_loss=0.4858, pruned_loss=6.571, over 1420534.59 frames.], batch size: 26, lr: 2.96e-03
2022-04-28 07:08:58,129 INFO [train.py:763] (3/8) Epoch 0, batch 1250, loss[loss=0.2201, simple_loss=0.4403, pruned_loss=6.615, over 7377.00 frames.], tot_loss[loss=0.2396, simple_loss=0.4791, pruned_loss=6.576, over 1414521.35 frames.], batch size: 23, lr: 2.95e-03
2022-04-28 07:10:04,043 INFO [train.py:763] (3/8) Epoch 0, batch 1300, loss[loss=0.2232, simple_loss=0.4465, pruned_loss=6.726, over 7293.00 frames.], tot_loss[loss=0.2362, simple_loss=0.4725, pruned_loss=6.582, over 1421685.22 frames.], batch size: 24, lr: 2.95e-03
2022-04-28 07:11:09,799 INFO [train.py:763] (3/8) Epoch 0, batch 1350, loss[loss=0.2141, simple_loss=0.4281, pruned_loss=6.59, over 7152.00 frames.], tot_loss[loss=0.2321, simple_loss=0.4642, pruned_loss=6.576, over 1422653.87 frames.], batch size: 20, lr: 2.95e-03
2022-04-28 07:12:15,113 INFO [train.py:763] (3/8) Epoch 0, batch 1400, loss[loss=0.2264, simple_loss=0.4529, pruned_loss=6.604, over 7284.00 frames.], tot_loss[loss=0.2306, simple_loss=0.4612, pruned_loss=6.588, over 1418905.51 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:13:21,016 INFO [train.py:763] (3/8) Epoch 0, batch 1450, loss[loss=0.1859, simple_loss=0.3718, pruned_loss=6.425, over 7135.00 frames.], tot_loss[loss=0.2275, simple_loss=0.455, pruned_loss=6.583, over 1419921.19 frames.], batch size: 17, lr: 2.94e-03
2022-04-28 07:14:26,711 INFO [train.py:763] (3/8) Epoch 0, batch 1500, loss[loss=0.2171, simple_loss=0.4343, pruned_loss=6.556, over 7311.00 frames.], tot_loss[loss=0.2248, simple_loss=0.4497, pruned_loss=6.578, over 1422729.33 frames.], batch size: 24, lr: 2.94e-03
2022-04-28 07:15:32,247 INFO [train.py:763] (3/8) Epoch 0, batch 1550, loss[loss=0.2203, simple_loss=0.4405, pruned_loss=6.576, over 7116.00 frames.], tot_loss[loss=0.2226, simple_loss=0.4451, pruned_loss=6.575, over 1423077.22 frames.], batch size: 21, lr: 2.93e-03
2022-04-28 07:16:38,326 INFO [train.py:763] (3/8) Epoch 0, batch 1600, loss[loss=0.2056, simple_loss=0.4113, pruned_loss=6.591, over 7324.00 frames.], tot_loss[loss=0.2206, simple_loss=0.4411, pruned_loss=6.571, over 1421181.38 frames.], batch size: 20, lr: 2.93e-03
2022-04-28 07:17:45,336 INFO [train.py:763] (3/8) Epoch 0, batch 1650, loss[loss=0.1888, simple_loss=0.3776, pruned_loss=6.444, over 7157.00 frames.], tot_loss[loss=0.2186, simple_loss=0.4371, pruned_loss=6.567, over 1422480.46 frames.], batch size: 18, lr: 2.92e-03
2022-04-28 07:18:51,995 INFO [train.py:763] (3/8) Epoch 0, batch 1700, loss[loss=0.2069, simple_loss=0.4138, pruned_loss=6.457, over 6334.00 frames.], tot_loss[loss=0.2168, simple_loss=0.4335, pruned_loss=6.562, over 1417828.34 frames.], batch size: 38, lr: 2.92e-03
2022-04-28 07:19:58,695 INFO [train.py:763] (3/8) Epoch 0, batch 1750, loss[loss=0.2272, simple_loss=0.4544, pruned_loss=6.471, over 6621.00 frames.], tot_loss[loss=0.2152, simple_loss=0.4304, pruned_loss=6.565, over 1418934.94 frames.], batch size: 38, lr: 2.91e-03
2022-04-28 07:21:06,365 INFO [train.py:763] (3/8) Epoch 0, batch 1800, loss[loss=0.2156, simple_loss=0.4312, pruned_loss=6.555, over 7116.00 frames.], tot_loss[loss=0.2136, simple_loss=0.4273, pruned_loss=6.563, over 1418714.12 frames.], batch size: 28, lr: 2.91e-03
2022-04-28 07:22:12,423 INFO [train.py:763] (3/8) Epoch 0, batch 1850, loss[loss=0.2382, simple_loss=0.4764, pruned_loss=6.467, over 5004.00 frames.], tot_loss[loss=0.211, simple_loss=0.422, pruned_loss=6.558, over 1419431.03 frames.], batch size: 52, lr: 2.91e-03
2022-04-28 07:23:18,917 INFO [train.py:763] (3/8) Epoch 0, batch 1900, loss[loss=0.2133, simple_loss=0.4267, pruned_loss=6.629, over 7248.00 frames.], tot_loss[loss=0.2101, simple_loss=0.4201, pruned_loss=6.565, over 1419624.75 frames.], batch size: 19, lr: 2.90e-03
2022-04-28 07:24:26,526 INFO [train.py:763] (3/8) Epoch 0, batch 1950, loss[loss=0.2146, simple_loss=0.4291, pruned_loss=6.632, over 7322.00 frames.], tot_loss[loss=0.2087, simple_loss=0.4175, pruned_loss=6.565, over 1422771.08 frames.], batch size: 21, lr: 2.90e-03
2022-04-28 07:25:34,070 INFO [train.py:763] (3/8) Epoch 0, batch 2000, loss[loss=0.179, simple_loss=0.3581, pruned_loss=6.433, over 6742.00 frames.], tot_loss[loss=0.2079, simple_loss=0.4158, pruned_loss=6.564, over 1422270.75 frames.], batch size: 15, lr: 2.89e-03
2022-04-28 07:26:39,960 INFO [train.py:763] (3/8) Epoch 0, batch 2050, loss[loss=0.2116, simple_loss=0.4232, pruned_loss=6.482, over 7191.00 frames.], tot_loss[loss=0.2063, simple_loss=0.4125, pruned_loss=6.559, over 1420582.21 frames.], batch size: 26, lr: 2.89e-03
2022-04-28 07:27:45,821 INFO [train.py:763] (3/8) Epoch 0, batch 2100, loss[loss=0.198, simple_loss=0.396, pruned_loss=6.424, over 7164.00 frames.], tot_loss[loss=0.2056, simple_loss=0.4111, pruned_loss=6.564, over 1417459.10 frames.], batch size: 18, lr: 2.88e-03
2022-04-28 07:28:51,549 INFO [train.py:763] (3/8) Epoch 0, batch 2150, loss[loss=0.2219, simple_loss=0.4438, pruned_loss=6.664, over 7339.00 frames.], tot_loss[loss=0.2046, simple_loss=0.4091, pruned_loss=6.57, over 1421295.59 frames.], batch size: 22, lr: 2.88e-03
2022-04-28 07:29:57,476 INFO [train.py:763] (3/8) Epoch 0, batch 2200, loss[loss=0.1941, simple_loss=0.3882, pruned_loss=6.565, over 7305.00 frames.], tot_loss[loss=0.2041, simple_loss=0.4081, pruned_loss=6.578, over 1421420.28 frames.], batch size: 25, lr: 2.87e-03
2022-04-28 07:31:03,288 INFO [train.py:763] (3/8) Epoch 0, batch 2250, loss[loss=0.2127, simple_loss=0.4254, pruned_loss=6.688, over 7220.00 frames.], tot_loss[loss=0.2034, simple_loss=0.4068, pruned_loss=6.579, over 1420276.68 frames.], batch size: 21, lr: 2.86e-03
2022-04-28 07:32:08,989 INFO [train.py:763] (3/8) Epoch 0, batch 2300, loss[loss=0.1917, simple_loss=0.3833, pruned_loss=6.454, over 7250.00 frames.], tot_loss[loss=0.203, simple_loss=0.406, pruned_loss=6.575, over 1415383.16 frames.], batch size: 19, lr: 2.86e-03
2022-04-28 07:33:14,407 INFO [train.py:763] (3/8) Epoch 0, batch 2350, loss[loss=0.2398, simple_loss=0.4796, pruned_loss=6.595, over 5102.00 frames.], tot_loss[loss=0.2029, simple_loss=0.4058, pruned_loss=6.583, over 1415362.38 frames.], batch size: 53, lr: 2.85e-03
2022-04-28 07:34:20,287 INFO [train.py:763] (3/8) Epoch 0, batch 2400, loss[loss=0.1835, simple_loss=0.367, pruned_loss=6.645, over 7420.00 frames.], tot_loss[loss=0.202, simple_loss=0.404, pruned_loss=6.584, over 1410723.73 frames.], batch size: 20, lr: 2.85e-03
2022-04-28 07:35:25,716 INFO [train.py:763] (3/8) Epoch 0, batch 2450, loss[loss=0.2073, simple_loss=0.4145, pruned_loss=6.558, over 5040.00 frames.], tot_loss[loss=0.2013, simple_loss=0.4025, pruned_loss=6.584, over 1411730.22 frames.], batch size: 52, lr: 2.84e-03
2022-04-28 07:36:32,807 INFO [train.py:763] (3/8) Epoch 0, batch 2500, loss[loss=0.1739, simple_loss=0.3478, pruned_loss=6.588, over 7335.00 frames.], tot_loss[loss=0.2001, simple_loss=0.4003, pruned_loss=6.584, over 1418121.25 frames.], batch size: 20, lr: 2.84e-03
2022-04-28 07:37:40,455 INFO [train.py:763] (3/8) Epoch 0, batch 2550, loss[loss=0.1741, simple_loss=0.3482, pruned_loss=6.432, over 7399.00 frames.], tot_loss[loss=0.2003, simple_loss=0.4005, pruned_loss=6.591, over 1418795.00 frames.], batch size: 18, lr: 2.83e-03
2022-04-28 07:38:46,543 INFO [train.py:763] (3/8) Epoch 0, batch 2600, loss[loss=0.2123, simple_loss=0.4247, pruned_loss=6.734, over 7235.00 frames.], tot_loss[loss=0.1985, simple_loss=0.397, pruned_loss=6.594, over 1421164.74 frames.], batch size: 20, lr: 2.83e-03
2022-04-28 07:39:52,335 INFO [train.py:763] (3/8) Epoch 0, batch 2650, loss[loss=0.1898, simple_loss=0.3795, pruned_loss=6.531, over 7233.00 frames.], tot_loss[loss=0.1973, simple_loss=0.3946, pruned_loss=6.594, over 1422649.81 frames.], batch size: 20, lr: 2.82e-03
2022-04-28 07:40:58,203 INFO [train.py:763] (3/8) Epoch 0, batch 2700, loss[loss=0.1965, simple_loss=0.393, pruned_loss=6.642, over 7143.00 frames.], tot_loss[loss=0.1967, simple_loss=0.3935, pruned_loss=6.593, over 1422168.41 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:42:03,316 INFO [train.py:763] (3/8) Epoch 0, batch 2750, loss[loss=0.2051, simple_loss=0.4102, pruned_loss=6.62, over 7330.00 frames.], tot_loss[loss=0.1965, simple_loss=0.393, pruned_loss=6.596, over 1423011.67 frames.], batch size: 20, lr: 2.81e-03
2022-04-28 07:43:09,946 INFO [train.py:763] (3/8) Epoch 0, batch 2800, loss[loss=0.2026, simple_loss=0.4052, pruned_loss=6.639, over 7152.00 frames.], tot_loss[loss=0.1962, simple_loss=0.3925, pruned_loss=6.6, over 1422896.90 frames.], batch size: 20, lr: 2.80e-03
2022-04-28 07:44:16,827 INFO [train.py:763] (3/8) Epoch 0, batch 2850, loss[loss=0.1733, simple_loss=0.3466, pruned_loss=6.534, over 7363.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3909, pruned_loss=6.598, over 1425502.37 frames.], batch size: 19, lr: 2.80e-03
2022-04-28 07:45:22,337 INFO [train.py:763] (3/8) Epoch 0, batch 2900, loss[loss=0.1737, simple_loss=0.3475, pruned_loss=6.605, over 7326.00 frames.], tot_loss[loss=0.1956, simple_loss=0.3913, pruned_loss=6.605, over 1421114.12 frames.], batch size: 20, lr: 2.79e-03
2022-04-28 07:46:27,653 INFO [train.py:763] (3/8) Epoch 0, batch 2950, loss[loss=0.2009, simple_loss=0.4019, pruned_loss=6.603, over 7154.00 frames.], tot_loss[loss=0.1948, simple_loss=0.3896, pruned_loss=6.603, over 1417170.69 frames.], batch size: 26, lr: 2.78e-03
2022-04-28 07:47:32,888 INFO [train.py:763] (3/8) Epoch 0, batch 3000, loss[loss=0.3321, simple_loss=0.3866, pruned_loss=1.388, over 7277.00 frames.], tot_loss[loss=0.2266, simple_loss=0.3881, pruned_loss=6.578, over 1420734.00 frames.], batch size: 17, lr: 2.78e-03
2022-04-28 07:47:32,889 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 07:47:50,998 INFO [train.py:792] (3/8) Epoch 0, validation: loss=2.072, simple_loss=0.4419, pruned_loss=1.851, over 698248.00 frames.
2022-04-28 07:48:57,674 INFO [train.py:763] (3/8) Epoch 0, batch 3050, loss[loss=0.299, simple_loss=0.4077, pruned_loss=0.9521, over 6540.00 frames.], tot_loss[loss=0.251, simple_loss=0.3972, pruned_loss=5.394, over 1419628.85 frames.], batch size: 38, lr: 2.77e-03
2022-04-28 07:50:04,084 INFO [train.py:763] (3/8) Epoch 0, batch 3100, loss[loss=0.2609, simple_loss=0.411, pruned_loss=0.554, over 7415.00 frames.], tot_loss[loss=0.252, simple_loss=0.3925, pruned_loss=4.333, over 1425455.85 frames.], batch size: 21, lr: 2.77e-03
2022-04-28 07:51:10,054 INFO [train.py:763] (3/8) Epoch 0, batch 3150, loss[loss=0.2334, simple_loss=0.3948, pruned_loss=0.3602, over 7406.00 frames.], tot_loss[loss=0.2466, simple_loss=0.3882, pruned_loss=3.461, over 1426568.49 frames.], batch size: 21, lr: 2.76e-03
2022-04-28 07:52:16,817 INFO [train.py:763] (3/8) Epoch 0, batch 3200, loss[loss=0.2368, simple_loss=0.4131, pruned_loss=0.3028, over 7289.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3884, pruned_loss=2.77, over 1423379.09 frames.], batch size: 24, lr: 2.75e-03
2022-04-28 07:53:24,321 INFO [train.py:763] (3/8) Epoch 0, batch 3250, loss[loss=0.2321, simple_loss=0.4108, pruned_loss=0.2668, over 7154.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3881, pruned_loss=2.215, over 1423404.25 frames.], batch size: 20, lr: 2.75e-03
2022-04-28 07:54:30,946 INFO [train.py:763] (3/8) Epoch 0, batch 3300, loss[loss=0.2359, simple_loss=0.4185, pruned_loss=0.2666, over 7376.00 frames.], tot_loss[loss=0.2329, simple_loss=0.3875, pruned_loss=1.784, over 1418291.28 frames.], batch size: 23, lr: 2.74e-03
2022-04-28 07:55:37,623 INFO [train.py:763] (3/8) Epoch 0, batch 3350, loss[loss=0.2155, simple_loss=0.3871, pruned_loss=0.2197, over 7291.00 frames.], tot_loss[loss=0.2285, simple_loss=0.3863, pruned_loss=1.433, over 1423372.89 frames.], batch size: 24, lr: 2.73e-03
2022-04-28 07:56:43,235 INFO [train.py:763] (3/8) Epoch 0, batch 3400, loss[loss=0.2167, simple_loss=0.3909, pruned_loss=0.2125, over 7251.00 frames.], tot_loss[loss=0.225, simple_loss=0.3855, pruned_loss=1.163, over 1423833.96 frames.], batch size: 19, lr: 2.73e-03
2022-04-28 07:57:49,071 INFO [train.py:763] (3/8) Epoch 0, batch 3450, loss[loss=0.2171, simple_loss=0.3937, pruned_loss=0.2026, over 7318.00 frames.], tot_loss[loss=0.2222, simple_loss=0.3851, pruned_loss=0.951, over 1423510.24 frames.], batch size: 25, lr: 2.72e-03
2022-04-28 07:58:54,327 INFO [train.py:763] (3/8) Epoch 0, batch 3500, loss[loss=0.2201, simple_loss=0.3976, pruned_loss=0.2133, over 7120.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3837, pruned_loss=0.7842, over 1421099.69 frames.], batch size: 26, lr: 2.72e-03
2022-04-28 08:00:00,008 INFO [train.py:763] (3/8) Epoch 0, batch 3550, loss[loss=0.2339, simple_loss=0.422, pruned_loss=0.2288, over 7216.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3821, pruned_loss=0.6524, over 1422566.67 frames.], batch size: 21, lr: 2.71e-03
2022-04-28 08:01:06,048 INFO [train.py:763] (3/8) Epoch 0, batch 3600, loss[loss=0.2053, simple_loss=0.3711, pruned_loss=0.1972, over 7014.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3807, pruned_loss=0.5497, over 1421319.77 frames.], batch size: 16, lr: 2.70e-03
2022-04-28 08:02:21,060 INFO [train.py:763] (3/8) Epoch 0, batch 3650, loss[loss=0.2235, simple_loss=0.4099, pruned_loss=0.1858, over 7223.00 frames.], tot_loss[loss=0.2121, simple_loss=0.3789, pruned_loss=0.4669, over 1422641.22 frames.], batch size: 21, lr: 2.70e-03
2022-04-28 08:04:03,465 INFO [train.py:763] (3/8) Epoch 0, batch 3700, loss[loss=0.2295, simple_loss=0.4139, pruned_loss=0.2252, over 6763.00 frames.], tot_loss[loss=0.2099, simple_loss=0.3767, pruned_loss=0.4016, over 1426182.49 frames.], batch size: 31, lr: 2.69e-03
2022-04-28 08:05:34,887 INFO [train.py:763] (3/8) Epoch 0, batch 3750, loss[loss=0.1941, simple_loss=0.3529, pruned_loss=0.1767, over 7278.00 frames.], tot_loss[loss=0.2088, simple_loss=0.376, pruned_loss=0.3536, over 1418547.04 frames.], batch size: 18, lr: 2.68e-03
2022-04-28 08:06:40,595 INFO [train.py:763] (3/8) Epoch 0, batch 3800, loss[loss=0.1803, simple_loss=0.3307, pruned_loss=0.1493, over 7129.00 frames.], tot_loss[loss=0.2073, simple_loss=0.3748, pruned_loss=0.3125, over 1418421.52 frames.], batch size: 17, lr: 2.68e-03
2022-04-28 08:07:46,189 INFO [train.py:763] (3/8) Epoch 0, batch 3850, loss[loss=0.1806, simple_loss=0.3314, pruned_loss=0.149, over 7115.00 frames.], tot_loss[loss=0.206, simple_loss=0.3737, pruned_loss=0.2798, over 1423719.25 frames.], batch size: 17, lr: 2.67e-03
2022-04-28 08:08:52,445 INFO [train.py:763] (3/8) Epoch 0, batch 3900, loss[loss=0.181, simple_loss=0.3345, pruned_loss=0.1375, over 6791.00 frames.], tot_loss[loss=0.2061, simple_loss=0.3745, pruned_loss=0.2571, over 1420164.38 frames.], batch size: 15, lr: 2.66e-03
2022-04-28 08:09:58,857 INFO [train.py:763] (3/8) Epoch 0, batch 3950, loss[loss=0.172, simple_loss=0.3179, pruned_loss=0.1309, over 6811.00 frames.], tot_loss[loss=0.2043, simple_loss=0.3721, pruned_loss=0.2357, over 1417660.74 frames.], batch size: 15, lr: 2.66e-03
2022-04-28 08:11:04,204 INFO [train.py:763] (3/8) Epoch 0, batch 4000, loss[loss=0.2012, simple_loss=0.3737, pruned_loss=0.1433, over 7315.00 frames.], tot_loss[loss=0.2034, simple_loss=0.3713, pruned_loss=0.2189, over 1420355.05 frames.], batch size: 21, lr: 2.65e-03
2022-04-28 08:12:09,508 INFO [train.py:763] (3/8) Epoch 0, batch 4050, loss[loss=0.2102, simple_loss=0.3883, pruned_loss=0.16, over 7080.00 frames.], tot_loss[loss=0.2028, simple_loss=0.3709, pruned_loss=0.2061, over 1421153.61 frames.], batch size: 28, lr: 2.64e-03
2022-04-28 08:13:15,838 INFO [train.py:763] (3/8) Epoch 0, batch 4100, loss[loss=0.1914, simple_loss=0.354, pruned_loss=0.1436, over 7263.00 frames.], tot_loss[loss=0.2017, simple_loss=0.3694, pruned_loss=0.1954, over 1421277.27 frames.], batch size: 19, lr: 2.64e-03
2022-04-28 08:14:22,419 INFO [train.py:763] (3/8) Epoch 0, batch 4150, loss[loss=0.173, simple_loss=0.3225, pruned_loss=0.1175, over 7053.00 frames.], tot_loss[loss=0.2012, simple_loss=0.3689, pruned_loss=0.1868, over 1425540.50 frames.], batch size: 18, lr: 2.63e-03
2022-04-28 08:15:27,427 INFO [train.py:763] (3/8) Epoch 0, batch 4200, loss[loss=0.1988, simple_loss=0.3674, pruned_loss=0.1511, over 7188.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3692, pruned_loss=0.1807, over 1425353.84 frames.], batch size: 22, lr: 2.63e-03
2022-04-28 08:16:32,482 INFO [train.py:763] (3/8) Epoch 0, batch 4250, loss[loss=0.185, simple_loss=0.3445, pruned_loss=0.1273, over 7443.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3693, pruned_loss=0.1763, over 1422948.95 frames.], batch size: 20, lr: 2.62e-03
2022-04-28 08:17:38,264 INFO [train.py:763] (3/8) Epoch 0, batch 4300, loss[loss=0.2089, simple_loss=0.3866, pruned_loss=0.1556, over 7109.00 frames.], tot_loss[loss=0.2013, simple_loss=0.37, pruned_loss=0.1726, over 1422769.15 frames.], batch size: 28, lr: 2.61e-03
2022-04-28 08:18:43,769 INFO [train.py:763] (3/8) Epoch 0, batch 4350, loss[loss=0.1965, simple_loss=0.3624, pruned_loss=0.1529, over 7429.00 frames.], tot_loss[loss=0.2019, simple_loss=0.3711, pruned_loss=0.1703, over 1426555.38 frames.], batch size: 20, lr: 2.61e-03
2022-04-28 08:19:48,916 INFO [train.py:763] (3/8) Epoch 0, batch 4400, loss[loss=0.1777, simple_loss=0.3277, pruned_loss=0.1379, over 7259.00 frames.], tot_loss[loss=0.2016, simple_loss=0.3709, pruned_loss=0.1674, over 1424384.01 frames.], batch size: 18, lr: 2.60e-03
2022-04-28 08:20:54,081 INFO [train.py:763] (3/8) Epoch 0, batch 4450, loss[loss=0.1953, simple_loss=0.3622, pruned_loss=0.1415, over 7442.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3703, pruned_loss=0.1636, over 1423952.19 frames.], batch size: 20, lr: 2.59e-03
2022-04-28 08:21:59,571 INFO [train.py:763] (3/8) Epoch 0, batch 4500, loss[loss=0.2065, simple_loss=0.3797, pruned_loss=0.1664, over 6380.00 frames.], tot_loss[loss=0.2011, simple_loss=0.3705, pruned_loss=0.1621, over 1414028.66 frames.], batch size: 37, lr: 2.59e-03
2022-04-28 08:23:05,615 INFO [train.py:763] (3/8) Epoch 0, batch 4550, loss[loss=0.2224, simple_loss=0.4069, pruned_loss=0.1891, over 4890.00 frames.], tot_loss[loss=0.202, simple_loss=0.3722, pruned_loss=0.1619, over 1395020.08 frames.], batch size: 52, lr: 2.58e-03
2022-04-28 08:24:44,864 INFO [train.py:763] (3/8) Epoch 1, batch 0, loss[loss=0.2171, simple_loss=0.3997, pruned_loss=0.1722, over 7129.00 frames.], tot_loss[loss=0.2171, simple_loss=0.3997, pruned_loss=0.1722, over 7129.00 frames.], batch size: 26, lr: 2.56e-03
2022-04-28 08:25:50,517 INFO [train.py:763] (3/8) Epoch 1, batch 50, loss[loss=0.2162, simple_loss=0.4003, pruned_loss=0.1608, over 7240.00 frames.], tot_loss[loss=0.2007, simple_loss=0.3701, pruned_loss=0.1561, over 312501.62 frames.], batch size: 20, lr: 2.55e-03
2022-04-28 08:26:56,237 INFO [train.py:763] (3/8) Epoch 1, batch 100, loss[loss=0.1916, simple_loss=0.3561, pruned_loss=0.1356, over 7435.00 frames.], tot_loss[loss=0.1983, simple_loss=0.3664, pruned_loss=0.1511, over 560531.87 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:28:01,395 INFO [train.py:763] (3/8) Epoch 1, batch 150, loss[loss=0.2159, simple_loss=0.3984, pruned_loss=0.1675, over 7319.00 frames.], tot_loss[loss=0.1981, simple_loss=0.3661, pruned_loss=0.1501, over 751999.35 frames.], batch size: 20, lr: 2.54e-03
2022-04-28 08:29:06,944 INFO [train.py:763] (3/8) Epoch 1, batch 200, loss[loss=0.1681, simple_loss=0.3158, pruned_loss=0.1021, over 7164.00 frames.], tot_loss[loss=0.1962, simple_loss=0.3631, pruned_loss=0.1469, over 900815.75 frames.], batch size: 19, lr: 2.53e-03
2022-04-28 08:30:12,404 INFO [train.py:763] (3/8) Epoch 1, batch 250, loss[loss=0.1856, simple_loss=0.3475, pruned_loss=0.1187, over 7365.00 frames.], tot_loss[loss=0.1977, simple_loss=0.3655, pruned_loss=0.1491, over 1015868.22 frames.], batch size: 23, lr: 2.53e-03
2022-04-28 08:31:17,599 INFO [train.py:763] (3/8) Epoch 1, batch 300, loss[loss=0.1909, simple_loss=0.354, pruned_loss=0.1384, over 7248.00 frames.], tot_loss[loss=0.1973, simple_loss=0.3649, pruned_loss=0.1479, over 1104837.50 frames.], batch size: 19, lr: 2.52e-03
2022-04-28 08:32:23,178 INFO [train.py:763] (3/8) Epoch 1, batch 350, loss[loss=0.2108, simple_loss=0.3893, pruned_loss=0.1616, over 7221.00 frames.], tot_loss[loss=0.1963, simple_loss=0.3633, pruned_loss=0.1464, over 1173510.03 frames.], batch size: 21, lr: 2.51e-03
2022-04-28 08:33:29,295 INFO [train.py:763] (3/8) Epoch 1, batch 400, loss[loss=0.1892, simple_loss=0.3501, pruned_loss=0.1415, over 7142.00 frames.], tot_loss[loss=0.1967, simple_loss=0.364, pruned_loss=0.1472, over 1230998.95 frames.], batch size: 20, lr: 2.51e-03
2022-04-28 08:34:36,147 INFO [train.py:763] (3/8) Epoch 1, batch 450, loss[loss=0.1839, simple_loss=0.3396, pruned_loss=0.1411, over 7159.00 frames.], tot_loss[loss=0.1961, simple_loss=0.3631, pruned_loss=0.1458, over 1276287.79 frames.], batch size: 19, lr: 2.50e-03
2022-04-28 08:35:42,351 INFO [train.py:763] (3/8) Epoch 1, batch 500, loss[loss=0.1771, simple_loss=0.3316, pruned_loss=0.1128, over 7159.00 frames.], tot_loss[loss=0.195, simple_loss=0.3613, pruned_loss=0.1439, over 1308449.04 frames.], batch size: 18, lr: 2.49e-03
2022-04-28 08:36:48,843 INFO [train.py:763] (3/8) Epoch 1, batch 550, loss[loss=0.1923, simple_loss=0.3581, pruned_loss=0.1324, over 7353.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3614, pruned_loss=0.144, over 1333085.05 frames.], batch size: 19, lr: 2.49e-03
2022-04-28 08:37:55,692 INFO [train.py:763] (3/8) Epoch 1, batch 600, loss[loss=0.1972, simple_loss=0.3664, pruned_loss=0.1395, over 7393.00 frames.], tot_loss[loss=0.1946, simple_loss=0.3607, pruned_loss=0.1424, over 1354487.39 frames.], batch size: 23, lr: 2.48e-03
2022-04-28 08:39:01,283 INFO [train.py:763] (3/8) Epoch 1, batch 650, loss[loss=0.18, simple_loss=0.3356, pruned_loss=0.122, over 7284.00 frames.], tot_loss[loss=0.1941, simple_loss=0.3598, pruned_loss=0.1421, over 1368347.16 frames.], batch size: 18, lr: 2.48e-03
2022-04-28 08:40:06,978 INFO [train.py:763] (3/8) Epoch 1, batch 700, loss[loss=0.2087, simple_loss=0.3833, pruned_loss=0.1708, over 4815.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3592, pruned_loss=0.1416, over 1378889.63 frames.], batch size: 52, lr: 2.47e-03
2022-04-28 08:41:12,395 INFO [train.py:763] (3/8) Epoch 1, batch 750, loss[loss=0.1913, simple_loss=0.3532, pruned_loss=0.147, over 7250.00 frames.], tot_loss[loss=0.1939, simple_loss=0.3595, pruned_loss=0.1411, over 1389699.37 frames.], batch size: 19, lr: 2.46e-03
2022-04-28 08:42:18,200 INFO [train.py:763] (3/8) Epoch 1, batch 800, loss[loss=0.1936, simple_loss=0.3601, pruned_loss=0.1355, over 7067.00 frames.], tot_loss[loss=0.1931, simple_loss=0.3584, pruned_loss=0.1395, over 1399842.22 frames.], batch size: 18, lr: 2.46e-03
2022-04-28 08:43:24,113 INFO [train.py:763] (3/8) Epoch 1, batch 850, loss[loss=0.1773, simple_loss=0.3318, pruned_loss=0.1138, over 7319.00 frames.], tot_loss[loss=0.1935, simple_loss=0.359, pruned_loss=0.1399, over 1407280.54 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:44:29,823 INFO [train.py:763] (3/8) Epoch 1, batch 900, loss[loss=0.1655, simple_loss=0.3109, pruned_loss=0.1005, over 7439.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3593, pruned_loss=0.1403, over 1412767.27 frames.], batch size: 20, lr: 2.45e-03
2022-04-28 08:45:35,248 INFO [train.py:763] (3/8) Epoch 1, batch 950, loss[loss=0.1853, simple_loss=0.3475, pruned_loss=0.1151, over 7258.00 frames.], tot_loss[loss=0.1937, simple_loss=0.3594, pruned_loss=0.1401, over 1415108.49 frames.], batch size: 19, lr: 2.44e-03
2022-04-28 08:46:40,816 INFO [train.py:763] (3/8) Epoch 1, batch 1000, loss[loss=0.2023, simple_loss=0.3755, pruned_loss=0.1455, over 6757.00 frames.], tot_loss[loss=0.1917, simple_loss=0.356, pruned_loss=0.1368, over 1417402.66 frames.], batch size: 31, lr: 2.43e-03
2022-04-28 08:47:46,477 INFO [train.py:763] (3/8) Epoch 1, batch 1050, loss[loss=0.2025, simple_loss=0.3745, pruned_loss=0.1527, over 7416.00 frames.], tot_loss[loss=0.1917, simple_loss=0.3561, pruned_loss=0.1371, over 1419257.46 frames.], batch size: 20, lr: 2.43e-03
2022-04-28 08:48:51,692 INFO [train.py:763] (3/8) Epoch 1, batch 1100, loss[loss=0.1802, simple_loss=0.3353, pruned_loss=0.1256, over 7162.00 frames.], tot_loss[loss=0.1913, simple_loss=0.3555, pruned_loss=0.1362, over 1420237.86 frames.], batch size: 18, lr: 2.42e-03
2022-04-28 08:49:57,303 INFO [train.py:763] (3/8) Epoch 1, batch 1150, loss[loss=0.2009, simple_loss=0.3714, pruned_loss=0.1522, over 7231.00 frames.], tot_loss[loss=0.1908, simple_loss=0.3545, pruned_loss=0.1353, over 1424691.75 frames.], batch size: 20, lr: 2.41e-03
2022-04-28 08:51:02,489 INFO [train.py:763] (3/8) Epoch 1, batch 1200, loss[loss=0.2017, simple_loss=0.3755, pruned_loss=0.1396, over 7075.00 frames.], tot_loss[loss=0.191, simple_loss=0.355, pruned_loss=0.1352, over 1423636.08 frames.], batch size: 28, lr: 2.41e-03
2022-04-28 08:52:07,804 INFO [train.py:763] (3/8) Epoch 1, batch 1250, loss[loss=0.1935, simple_loss=0.3558, pruned_loss=0.1563, over 7281.00 frames.], tot_loss[loss=0.1908, simple_loss=0.3547, pruned_loss=0.1341, over 1423222.84 frames.], batch size: 18, lr: 2.40e-03
2022-04-28 08:53:12,958 INFO [train.py:763] (3/8) Epoch 1, batch 1300, loss[loss=0.1993, simple_loss=0.372, pruned_loss=0.1333, over 7220.00 frames.], tot_loss[loss=0.1911, simple_loss=0.3553, pruned_loss=0.1345, over 1418053.02 frames.], batch size: 21, lr: 2.40e-03
2022-04-28 08:54:18,349 INFO [train.py:763] (3/8) Epoch 1, batch 1350, loss[loss=0.1585, simple_loss=0.2956, pruned_loss=0.1068, over 7270.00 frames.], tot_loss[loss=0.1904, simple_loss=0.3541, pruned_loss=0.1338, over 1421759.04 frames.], batch size: 17, lr: 2.39e-03
2022-04-28 08:55:23,449 INFO [train.py:763] (3/8) Epoch 1, batch 1400, loss[loss=0.2279, simple_loss=0.4177, pruned_loss=0.1907, over 7216.00 frames.], tot_loss[loss=0.1906, simple_loss=0.3546, pruned_loss=0.1335, over 1419586.16 frames.], batch size: 21, lr: 2.39e-03
2022-04-28 08:56:28,947 INFO [train.py:763] (3/8) Epoch 1, batch 1450, loss[loss=0.3652, simple_loss=0.3961, pruned_loss=0.1671, over 7156.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3568, pruned_loss=0.1371, over 1423030.85 frames.], batch size: 26, lr: 2.38e-03
2022-04-28 08:57:34,411 INFO [train.py:763] (3/8) Epoch 1, batch 1500, loss[loss=0.3182, simple_loss=0.3701, pruned_loss=0.1331, over 6254.00 frames.], tot_loss[loss=0.2403, simple_loss=0.3583, pruned_loss=0.1376, over 1422633.09 frames.], batch size: 37, lr: 2.37e-03
2022-04-28 08:58:40,147 INFO [train.py:763] (3/8) Epoch 1, batch 1550, loss[loss=0.3011, simple_loss=0.3482, pruned_loss=0.127, over 7429.00 frames.], tot_loss[loss=0.2573, simple_loss=0.359, pruned_loss=0.1372, over 1425413.13 frames.], batch size: 20, lr: 2.37e-03
2022-04-28 08:59:47,367 INFO [train.py:763] (3/8) Epoch 1, batch 1600, loss[loss=0.2807, simple_loss=0.3386, pruned_loss=0.1114, over 7161.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3574, pruned_loss=0.1353, over 1424012.72 frames.], batch size: 18, lr: 2.36e-03
2022-04-28 09:00:52,892 INFO [train.py:763] (3/8) Epoch 1, batch 1650, loss[loss=0.2906, simple_loss=0.3567, pruned_loss=0.1123, over 7434.00 frames.], tot_loss[loss=0.2765, simple_loss=0.3575, pruned_loss=0.1338, over 1424367.98 frames.], batch size: 20, lr: 2.36e-03
2022-04-28 09:01:59,214 INFO [train.py:763] (3/8) Epoch 1, batch 1700, loss[loss=0.3563, simple_loss=0.3834, pruned_loss=0.1646, over 7408.00 frames.], tot_loss[loss=0.2821, simple_loss=0.3561, pruned_loss=0.1321, over 1422976.99 frames.], batch size: 21, lr: 2.35e-03
2022-04-28 09:03:06,112 INFO [train.py:763] (3/8) Epoch 1, batch 1750, loss[loss=0.3168, simple_loss=0.3474, pruned_loss=0.1431, over 7277.00 frames.], tot_loss[loss=0.2883, simple_loss=0.3568, pruned_loss=0.1317, over 1422950.96 frames.], batch size: 18, lr: 2.34e-03
2022-04-28 09:04:13,393 INFO [train.py:763] (3/8) Epoch 1, batch 1800, loss[loss=0.3154, simple_loss=0.3527, pruned_loss=0.1391, over 7359.00 frames.], tot_loss[loss=0.2927, simple_loss=0.3569, pruned_loss=0.1312, over 1424332.01 frames.], batch size: 19, lr: 2.34e-03
2022-04-28 09:05:20,642 INFO [train.py:763] (3/8) Epoch 1, batch 1850, loss[loss=0.2359, simple_loss=0.3097, pruned_loss=0.08102, over 7336.00 frames.], tot_loss[loss=0.2938, simple_loss=0.3554, pruned_loss=0.1293, over 1424036.70 frames.], batch size: 20, lr: 2.33e-03
2022-04-28 09:06:26,263 INFO [train.py:763] (3/8) Epoch 1, batch 1900, loss[loss=0.2622, simple_loss=0.3122, pruned_loss=0.106, over 7005.00 frames.], tot_loss[loss=0.2966, simple_loss=0.3568, pruned_loss=0.1285, over 1427593.81 frames.], batch size: 16, lr: 2.33e-03
2022-04-28 09:07:32,757 INFO [train.py:763] (3/8) Epoch 1, batch 1950, loss[loss=0.2416, simple_loss=0.2949, pruned_loss=0.09414, over 7275.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3567, pruned_loss=0.1279, over 1428309.76 frames.], batch size: 18, lr: 2.32e-03
2022-04-28 09:08:38,160 INFO [train.py:763] (3/8) Epoch 1, batch 2000, loss[loss=0.2634, simple_loss=0.3305, pruned_loss=0.09811, over 7128.00 frames.], tot_loss[loss=0.3006, simple_loss=0.3578, pruned_loss=0.128, over 1422495.94 frames.], batch size: 21, lr: 2.32e-03
2022-04-28 09:09:44,439 INFO [train.py:763] (3/8) Epoch 1, batch 2050, loss[loss=0.3454, simple_loss=0.3857, pruned_loss=0.1525, over 7043.00 frames.], tot_loss[loss=0.3015, simple_loss=0.3574, pruned_loss=0.1277, over 1423781.57 frames.], batch size: 28, lr: 2.31e-03
2022-04-28 09:10:49,767 INFO [train.py:763] (3/8) Epoch 1, batch 2100, loss[loss=0.3116, simple_loss=0.3565, pruned_loss=0.1334, over 7404.00 frames.], tot_loss[loss=0.3008, simple_loss=0.3566, pruned_loss=0.1263, over 1424995.42 frames.], batch size: 18, lr: 2.31e-03
2022-04-28 09:11:55,363 INFO [train.py:763] (3/8) Epoch 1, batch 2150, loss[loss=0.328, simple_loss=0.3823, pruned_loss=0.1368, over 7406.00 frames.], tot_loss[loss=0.3001, simple_loss=0.3557, pruned_loss=0.1252, over 1423940.05 frames.], batch size: 21, lr: 2.30e-03
2022-04-28 09:13:01,255 INFO [train.py:763] (3/8) Epoch 1, batch 2200, loss[loss=0.3882, simple_loss=0.4153, pruned_loss=0.1806, over 7127.00 frames.], tot_loss[loss=0.2985, simple_loss=0.3541, pruned_loss=0.1237, over 1423702.32 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:14:06,868 INFO [train.py:763] (3/8) Epoch 1, batch 2250, loss[loss=0.2792, simple_loss=0.3399, pruned_loss=0.1092, over 7213.00 frames.], tot_loss[loss=0.2977, simple_loss=0.3533, pruned_loss=0.1228, over 1424254.80 frames.], batch size: 21, lr: 2.29e-03
2022-04-28 09:15:14,110 INFO [train.py:763] (3/8) Epoch 1, batch 2300, loss[loss=0.352, simple_loss=0.3939, pruned_loss=0.155, over 7199.00 frames.], tot_loss[loss=0.298, simple_loss=0.3538, pruned_loss=0.1225, over 1425339.37 frames.], batch size: 22, lr: 2.28e-03
2022-04-28 09:16:21,357 INFO [train.py:763] (3/8) Epoch 1, batch 2350, loss[loss=0.2883, simple_loss=0.3583, pruned_loss=0.1092, over 7235.00 frames.], tot_loss[loss=0.3001, simple_loss=0.3554, pruned_loss=0.1234, over 1422922.03 frames.], batch size: 20, lr: 2.28e-03
2022-04-28 09:17:26,498 INFO [train.py:763] (3/8) Epoch 1, batch 2400, loss[loss=0.2989, simple_loss=0.3694, pruned_loss=0.1141, over 7333.00 frames.], tot_loss[loss=0.2992, simple_loss=0.3549, pruned_loss=0.1226, over 1422964.16 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:18:31,929 INFO [train.py:763] (3/8) Epoch 1, batch 2450, loss[loss=0.3197, simple_loss=0.3761, pruned_loss=0.1317, over 7312.00 frames.], tot_loss[loss=0.2982, simple_loss=0.3548, pruned_loss=0.1215, over 1426971.41 frames.], batch size: 21, lr: 2.27e-03
2022-04-28 09:19:37,096 INFO [train.py:763] (3/8) Epoch 1, batch 2500, loss[loss=0.3668, simple_loss=0.4044, pruned_loss=0.1646, over 7147.00 frames.], tot_loss[loss=0.2994, simple_loss=0.3554, pruned_loss=0.1222, over 1427097.79 frames.], batch size: 26, lr: 2.26e-03
2022-04-28 09:20:43,299 INFO [train.py:763] (3/8) Epoch 1, batch 2550, loss[loss=0.2994, simple_loss=0.3439, pruned_loss=0.1275, over 7003.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3548, pruned_loss=0.1219, over 1427392.07 frames.], batch size: 16, lr: 2.26e-03
2022-04-28 09:21:48,826 INFO [train.py:763] (3/8) Epoch 1, batch 2600, loss[loss=0.2847, simple_loss=0.3528, pruned_loss=0.1083, over 7167.00 frames.], tot_loss[loss=0.297, simple_loss=0.3535, pruned_loss=0.1205, over 1429605.77 frames.], batch size: 26, lr: 2.25e-03
2022-04-28 09:22:54,015 INFO [train.py:763] (3/8) Epoch 1, batch 2650, loss[loss=0.3446, simple_loss=0.3895, pruned_loss=0.1499, over 6252.00 frames.], tot_loss[loss=0.297, simple_loss=0.3536, pruned_loss=0.1204, over 1427459.31 frames.], batch size: 38, lr: 2.25e-03
2022-04-28 09:24:00,440 INFO [train.py:763] (3/8) Epoch 1, batch 2700, loss[loss=0.3508, simple_loss=0.3974, pruned_loss=0.1521, over 6910.00 frames.], tot_loss[loss=0.2962, simple_loss=0.3533, pruned_loss=0.1198, over 1426874.39 frames.], batch size: 31, lr: 2.24e-03
2022-04-28 09:25:06,554 INFO [train.py:763] (3/8) Epoch 1, batch 2750, loss[loss=0.2507, simple_loss=0.3294, pruned_loss=0.08596, over 7310.00 frames.], tot_loss[loss=0.2949, simple_loss=0.3525, pruned_loss=0.1188, over 1423631.50 frames.], batch size: 24, lr: 2.24e-03
2022-04-28 09:26:12,249 INFO [train.py:763] (3/8) Epoch 1, batch 2800, loss[loss=0.2922, simple_loss=0.3575, pruned_loss=0.1135, over 7212.00 frames.], tot_loss[loss=0.294, simple_loss=0.3522, pruned_loss=0.118, over 1426147.89 frames.], batch size: 23, lr: 2.23e-03
2022-04-28 09:27:17,544 INFO [train.py:763] (3/8) Epoch 1, batch 2850, loss[loss=0.2998, simple_loss=0.3704, pruned_loss=0.1146, over 7306.00 frames.], tot_loss[loss=0.2928, simple_loss=0.3511, pruned_loss=0.1173, over 1425850.38 frames.], batch size: 24, lr: 2.23e-03
2022-04-28 09:28:22,520 INFO [train.py:763] (3/8) Epoch 1, batch 2900, loss[loss=0.2373, simple_loss=0.3232, pruned_loss=0.07568, over 7228.00 frames.], tot_loss[loss=0.2934, simple_loss=0.3521, pruned_loss=0.1174, over 1420238.58 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:29:27,935 INFO [train.py:763] (3/8) Epoch 1, batch 2950, loss[loss=0.3206, simple_loss=0.3778, pruned_loss=0.1317, over 7241.00 frames.], tot_loss[loss=0.2924, simple_loss=0.3517, pruned_loss=0.1166, over 1421146.35 frames.], batch size: 20, lr: 2.22e-03
2022-04-28 09:30:33,552 INFO [train.py:763] (3/8) Epoch 1, batch 3000, loss[loss=0.2713, simple_loss=0.3265, pruned_loss=0.108, over 7272.00 frames.], tot_loss[loss=0.2905, simple_loss=0.3501, pruned_loss=0.1155, over 1424548.74 frames.], batch size: 17, lr: 2.21e-03
2022-04-28 09:30:33,553 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 09:30:49,513 INFO [train.py:792] (3/8) Epoch 1, validation: loss=0.217, simple_loss=0.3099, pruned_loss=0.06207, over 698248.00 frames.
2022-04-28 09:31:55,882 INFO [train.py:763] (3/8) Epoch 1, batch 3050, loss[loss=0.2463, simple_loss=0.3112, pruned_loss=0.09072, over 7280.00 frames.], tot_loss[loss=0.2897, simple_loss=0.3494, pruned_loss=0.115, over 1420750.64 frames.], batch size: 18, lr: 2.20e-03
2022-04-28 09:33:01,968 INFO [train.py:763] (3/8) Epoch 1, batch 3100, loss[loss=0.3339, simple_loss=0.3644, pruned_loss=0.1518, over 5102.00 frames.], tot_loss[loss=0.2901, simple_loss=0.3497, pruned_loss=0.1152, over 1420787.48 frames.], batch size: 53, lr: 2.20e-03
2022-04-28 09:34:07,383 INFO [train.py:763] (3/8) Epoch 1, batch 3150, loss[loss=0.2537, simple_loss=0.3082, pruned_loss=0.09959, over 6869.00 frames.], tot_loss[loss=0.2885, simple_loss=0.3492, pruned_loss=0.114, over 1423414.16 frames.], batch size: 15, lr: 2.19e-03
2022-04-28 09:35:13,546 INFO [train.py:763] (3/8) Epoch 1, batch 3200, loss[loss=0.3742, simple_loss=0.3908, pruned_loss=0.1788, over 5050.00 frames.], tot_loss[loss=0.2901, simple_loss=0.3503, pruned_loss=0.1149, over 1412674.07 frames.], batch size: 52, lr: 2.19e-03
2022-04-28 09:36:19,396 INFO [train.py:763] (3/8) Epoch 1, batch 3250, loss[loss=0.3096, simple_loss=0.3683, pruned_loss=0.1255, over 7205.00 frames.], tot_loss[loss=0.29, simple_loss=0.3504, pruned_loss=0.1149, over 1415152.56 frames.], batch size: 23, lr: 2.18e-03
2022-04-28 09:37:26,021 INFO [train.py:763] (3/8) Epoch 1, batch 3300, loss[loss=0.3665, simple_loss=0.4206, pruned_loss=0.1562, over 7193.00 frames.], tot_loss[loss=0.2878, simple_loss=0.3486, pruned_loss=0.1135, over 1420337.19 frames.], batch size: 22, lr: 2.18e-03
2022-04-28 09:38:31,142 INFO [train.py:763] (3/8) Epoch 1, batch 3350, loss[loss=0.3248, simple_loss=0.3883, pruned_loss=0.1306, over 7147.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3497, pruned_loss=0.1138, over 1423476.62 frames.], batch size: 26, lr: 2.18e-03
2022-04-28 09:39:36,458 INFO [train.py:763] (3/8) Epoch 1, batch 3400, loss[loss=0.2504, simple_loss=0.3069, pruned_loss=0.09696, over 7130.00 frames.], tot_loss[loss=0.2884, simple_loss=0.3495, pruned_loss=0.1137, over 1424628.17 frames.], batch size: 17, lr: 2.17e-03
2022-04-28 09:40:52,291 INFO [train.py:763] (3/8) Epoch 1, batch 3450, loss[loss=0.322, simple_loss=0.3859, pruned_loss=0.129, over 7307.00 frames.], tot_loss[loss=0.2877, simple_loss=0.3495, pruned_loss=0.1129, over 1427760.24 frames.], batch size: 24, lr: 2.17e-03
2022-04-28 09:41:59,070 INFO [train.py:763] (3/8) Epoch 1, batch 3500, loss[loss=0.352, simple_loss=0.3979, pruned_loss=0.153, over 6506.00 frames.], tot_loss[loss=0.2887, simple_loss=0.3502, pruned_loss=0.1136, over 1424470.04 frames.], batch size: 37, lr: 2.16e-03
2022-04-28 09:43:05,801 INFO [train.py:763] (3/8) Epoch 1, batch 3550, loss[loss=0.2981, simple_loss=0.3602, pruned_loss=0.118, over 7305.00 frames.], tot_loss[loss=0.2874, simple_loss=0.3497, pruned_loss=0.1125, over 1423645.98 frames.], batch size: 25, lr: 2.16e-03
2022-04-28 09:44:12,973 INFO [train.py:763] (3/8) Epoch 1, batch 3600, loss[loss=0.2681, simple_loss=0.3447, pruned_loss=0.09579, over 7234.00 frames.], tot_loss[loss=0.2875, simple_loss=0.35, pruned_loss=0.1126, over 1424839.98 frames.], batch size: 20, lr: 2.15e-03
2022-04-28 09:45:20,592 INFO [train.py:763] (3/8) Epoch 1, batch 3650, loss[loss=0.2878, simple_loss=0.3369, pruned_loss=0.1193, over 6784.00 frames.], tot_loss[loss=0.288, simple_loss=0.3506, pruned_loss=0.1127, over 1426672.25 frames.], batch size: 15, lr: 2.15e-03
2022-04-28 09:46:27,938 INFO [train.py:763] (3/8) Epoch 1, batch 3700, loss[loss=0.2887, simple_loss=0.3551, pruned_loss=0.1111, over 7171.00 frames.], tot_loss[loss=0.2892, simple_loss=0.352, pruned_loss=0.1132, over 1428183.52 frames.], batch size: 19, lr: 2.14e-03
2022-04-28 09:47:33,410 INFO [train.py:763] (3/8) Epoch 1, batch 3750, loss[loss=0.3173, simple_loss=0.3703, pruned_loss=0.1321, over 7262.00 frames.], tot_loss[loss=0.2878, simple_loss=0.3511, pruned_loss=0.1122, over 1428965.72 frames.], batch size: 24, lr: 2.14e-03
2022-04-28 09:48:38,885 INFO [train.py:763] (3/8) Epoch 1, batch 3800, loss[loss=0.2295, simple_loss=0.3083, pruned_loss=0.07535, over 6825.00 frames.], tot_loss[loss=0.2861, simple_loss=0.3496, pruned_loss=0.1113, over 1428445.87 frames.], batch size: 15, lr: 2.13e-03
2022-04-28 09:49:44,145 INFO [train.py:763] (3/8) Epoch 1, batch 3850, loss[loss=0.3156, simple_loss=0.3892, pruned_loss=0.121, over 7179.00 frames.], tot_loss[loss=0.2861, simple_loss=0.3496, pruned_loss=0.1112, over 1429883.36 frames.], batch size: 26, lr: 2.13e-03
2022-04-28 09:50:49,544 INFO [train.py:763] (3/8) Epoch 1, batch 3900, loss[loss=0.3121, simple_loss=0.3736, pruned_loss=0.1253, over 7284.00 frames.], tot_loss[loss=0.2846, simple_loss=0.3483, pruned_loss=0.1104, over 1429165.40 frames.], batch size: 24, lr: 2.12e-03
2022-04-28 09:51:55,498 INFO [train.py:763] (3/8) Epoch 1, batch 3950, loss[loss=0.3043, simple_loss=0.3662, pruned_loss=0.1212, over 7121.00 frames.], tot_loss[loss=0.2833, simple_loss=0.3472, pruned_loss=0.1097, over 1427113.11 frames.], batch size: 21, lr: 2.12e-03
2022-04-28 09:53:01,242 INFO [train.py:763] (3/8) Epoch 1, batch 4000, loss[loss=0.2822, simple_loss=0.3546, pruned_loss=0.1049, over 7198.00 frames.], tot_loss[loss=0.2838, simple_loss=0.3478, pruned_loss=0.1099, over 1427778.52 frames.], batch size: 22, lr: 2.11e-03
2022-04-28 09:54:07,049 INFO [train.py:763] (3/8) Epoch 1, batch 4050, loss[loss=0.2996, simple_loss=0.3594, pruned_loss=0.1199, over 6747.00 frames.], tot_loss[loss=0.2836, simple_loss=0.3476, pruned_loss=0.1098, over 1426400.14 frames.], batch size: 31, lr: 2.11e-03
2022-04-28 09:55:12,316 INFO [train.py:763] (3/8) Epoch 1, batch 4100, loss[loss=0.3653, simple_loss=0.3982, pruned_loss=0.1662, over 7212.00 frames.], tot_loss[loss=0.2843, simple_loss=0.3478, pruned_loss=0.1104, over 1420953.05 frames.], batch size: 21, lr: 2.10e-03
2022-04-28 09:56:17,393 INFO [train.py:763] (3/8) Epoch 1, batch 4150, loss[loss=0.3213, simple_loss=0.3722, pruned_loss=0.1352, over 6691.00 frames.], tot_loss[loss=0.2832, simple_loss=0.3468, pruned_loss=0.1098, over 1419702.65 frames.], batch size: 31, lr: 2.10e-03
2022-04-28 09:57:22,844 INFO [train.py:763] (3/8) Epoch 1, batch 4200, loss[loss=0.2751, simple_loss=0.3228, pruned_loss=0.1137, over 7274.00 frames.], tot_loss[loss=0.2833, simple_loss=0.3463, pruned_loss=0.1102, over 1418888.28 frames.], batch size: 18, lr: 2.10e-03
2022-04-28 09:58:27,890 INFO [train.py:763] (3/8) Epoch 1, batch 4250, loss[loss=0.2595, simple_loss=0.3277, pruned_loss=0.0956, over 7275.00 frames.], tot_loss[loss=0.2849, simple_loss=0.3474, pruned_loss=0.1112, over 1414619.92 frames.], batch size: 18, lr: 2.09e-03
2022-04-28 09:59:34,312 INFO [train.py:763] (3/8) Epoch 1, batch 4300, loss[loss=0.3273, simple_loss=0.402, pruned_loss=0.1263, over 7319.00 frames.], tot_loss[loss=0.2854, simple_loss=0.348, pruned_loss=0.1114, over 1413457.47 frames.], batch size: 25, lr: 2.09e-03
2022-04-28 10:00:39,971 INFO [train.py:763] (3/8) Epoch 1, batch 4350, loss[loss=0.2396, simple_loss=0.3074, pruned_loss=0.08584, over 7416.00 frames.], tot_loss[loss=0.286, simple_loss=0.3486, pruned_loss=0.1117, over 1414018.66 frames.], batch size: 17, lr: 2.08e-03
2022-04-28 10:01:45,335 INFO [train.py:763] (3/8) Epoch 1, batch 4400, loss[loss=0.3054, simple_loss=0.3614, pruned_loss=0.1247, over 7313.00 frames.], tot_loss[loss=0.2845, simple_loss=0.3473, pruned_loss=0.1108, over 1408409.61 frames.], batch size: 21, lr: 2.08e-03
2022-04-28 10:02:50,267 INFO [train.py:763] (3/8) Epoch 1, batch 4450, loss[loss=0.306, simple_loss=0.3587, pruned_loss=0.1267, over 6505.00 frames.], tot_loss[loss=0.2846, simple_loss=0.348, pruned_loss=0.1107, over 1402315.76 frames.], batch size: 38, lr: 2.07e-03
2022-04-28 10:03:55,335 INFO [train.py:763] (3/8) Epoch 1, batch 4500, loss[loss=0.3043, simple_loss=0.3584, pruned_loss=0.1252, over 6309.00 frames.], tot_loss[loss=0.2852, simple_loss=0.3477, pruned_loss=0.1114, over 1387904.09 frames.], batch size: 37, lr: 2.07e-03
2022-04-28 10:04:59,434 INFO [train.py:763] (3/8) Epoch 1, batch 4550, loss[loss=0.3562, simple_loss=0.3947, pruned_loss=0.1589, over 5031.00 frames.], tot_loss[loss=0.2886, simple_loss=0.3503, pruned_loss=0.1135, over 1356416.92 frames.], batch size: 52, lr: 2.06e-03
2022-04-28 10:06:27,054 INFO [train.py:763] (3/8) Epoch 2, batch 0, loss[loss=0.2988, simple_loss=0.3439, pruned_loss=0.1269, over 7287.00 frames.], tot_loss[loss=0.2988, simple_loss=0.3439, pruned_loss=0.1269, over 7287.00 frames.], batch size: 17, lr: 2.02e-03
2022-04-28 10:07:33,519 INFO [train.py:763] (3/8) Epoch 2, batch 50, loss[loss=0.2667, simple_loss=0.3382, pruned_loss=0.09766, over 7294.00 frames.], tot_loss[loss=0.2812, simple_loss=0.3447, pruned_loss=0.1088, over 323246.44 frames.], batch size: 25, lr: 2.02e-03
2022-04-28 10:08:39,165 INFO [train.py:763] (3/8) Epoch 2, batch 100, loss[loss=0.2428, simple_loss=0.304, pruned_loss=0.09081, over 6994.00 frames.], tot_loss[loss=0.2739, simple_loss=0.3411, pruned_loss=0.1034, over 570552.73 frames.], batch size: 16, lr: 2.01e-03
2022-04-28 10:09:45,123 INFO [train.py:763] (3/8) Epoch 2, batch 150, loss[loss=0.3067, simple_loss=0.3554, pruned_loss=0.129, over 6751.00 frames.], tot_loss[loss=0.2736, simple_loss=0.34, pruned_loss=0.1036, over 763010.74 frames.], batch size: 31, lr: 2.01e-03
2022-04-28 10:10:50,699 INFO [train.py:763] (3/8) Epoch 2, batch 200, loss[loss=0.2896, simple_loss=0.336, pruned_loss=0.1216, over 6793.00 frames.], tot_loss[loss=0.276, simple_loss=0.3414, pruned_loss=0.1053, over 901224.23 frames.], batch size: 15, lr: 2.00e-03
2022-04-28 10:11:56,042 INFO [train.py:763] (3/8) Epoch 2, batch 250, loss[loss=0.2661, simple_loss=0.3337, pruned_loss=0.09928, over 7362.00 frames.], tot_loss[loss=0.2783, simple_loss=0.3439, pruned_loss=0.1063, over 1012314.16 frames.], batch size: 19, lr: 2.00e-03
2022-04-28 10:13:01,577 INFO [train.py:763] (3/8) Epoch 2, batch 300, loss[loss=0.2691, simple_loss=0.3437, pruned_loss=0.09723, over 6875.00 frames.], tot_loss[loss=0.2799, simple_loss=0.3454, pruned_loss=0.1072, over 1102553.98 frames.], batch size: 31, lr: 2.00e-03
2022-04-28 10:14:07,026 INFO [train.py:763] (3/8) Epoch 2, batch 350, loss[loss=0.2772, simple_loss=0.3571, pruned_loss=0.09866, over 7319.00 frames.], tot_loss[loss=0.2793, simple_loss=0.3455, pruned_loss=0.1065, over 1172913.33 frames.], batch size: 21, lr: 1.99e-03
2022-04-28 10:15:12,737 INFO [train.py:763] (3/8) Epoch 2, batch 400, loss[loss=0.3615, simple_loss=0.3911, pruned_loss=0.1659, over 7286.00 frames.], tot_loss[loss=0.2799, simple_loss=0.3459, pruned_loss=0.107, over 1223735.30 frames.], batch size: 24, lr: 1.99e-03
2022-04-28 10:16:17,703 INFO [train.py:763] (3/8) Epoch 2, batch 450, loss[loss=0.284, simple_loss=0.3562, pruned_loss=0.1059, over 7212.00 frames.], tot_loss[loss=0.279, simple_loss=0.3452, pruned_loss=0.1064, over 1264029.34 frames.], batch size: 22, lr: 1.98e-03
2022-04-28 10:17:41,017 INFO [train.py:763] (3/8) Epoch 2, batch 500, loss[loss=0.2659, simple_loss=0.3241, pruned_loss=0.1039, over 7008.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3444, pruned_loss=0.1062, over 1301957.86 frames.], batch size: 16, lr: 1.98e-03
2022-04-28 10:19:24,489 INFO [train.py:763] (3/8) Epoch 2, batch 550, loss[loss=0.3032, simple_loss=0.3647, pruned_loss=0.1208, over 7219.00 frames.], tot_loss[loss=0.2777, simple_loss=0.3442, pruned_loss=0.1057, over 1331694.48 frames.], batch size: 21, lr: 1.98e-03
2022-04-28 10:20:31,148 INFO [train.py:763] (3/8) Epoch 2, batch 600, loss[loss=0.3859, simple_loss=0.4385, pruned_loss=0.1667, over 7285.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3433, pruned_loss=0.1052, over 1352069.80 frames.], batch size: 25, lr: 1.97e-03
2022-04-28 10:21:56,819 INFO [train.py:763] (3/8) Epoch 2, batch 650, loss[loss=0.2859, simple_loss=0.3614, pruned_loss=0.1052, over 7374.00 frames.], tot_loss[loss=0.2769, simple_loss=0.3432, pruned_loss=0.1053, over 1366875.24 frames.], batch size: 19, lr: 1.97e-03
2022-04-28 10:23:03,992 INFO [train.py:763] (3/8) Epoch 2, batch 700, loss[loss=0.2431, simple_loss=0.3362, pruned_loss=0.07503, over 7214.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3421, pruned_loss=0.1043, over 1377307.84 frames.], batch size: 21, lr: 1.96e-03
2022-04-28 10:24:09,348 INFO [train.py:763] (3/8) Epoch 2, batch 750, loss[loss=0.267, simple_loss=0.3524, pruned_loss=0.09076, over 7191.00 frames.], tot_loss[loss=0.2753, simple_loss=0.3425, pruned_loss=0.1041, over 1390766.76 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:25:14,623 INFO [train.py:763] (3/8) Epoch 2, batch 800, loss[loss=0.2858, simple_loss=0.3538, pruned_loss=0.1088, over 7204.00 frames.], tot_loss[loss=0.2763, simple_loss=0.3438, pruned_loss=0.1044, over 1401396.70 frames.], batch size: 23, lr: 1.96e-03
2022-04-28 10:26:20,181 INFO [train.py:763] (3/8) Epoch 2, batch 850, loss[loss=0.3026, simple_loss=0.3657, pruned_loss=0.1198, over 7300.00 frames.], tot_loss[loss=0.2746, simple_loss=0.3424, pruned_loss=0.1034, over 1409380.36 frames.], batch size: 25, lr: 1.95e-03
2022-04-28 10:27:26,276 INFO [train.py:763] (3/8) Epoch 2, batch 900, loss[loss=0.2578, simple_loss=0.3215, pruned_loss=0.09709, over 7064.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3437, pruned_loss=0.1039, over 1412461.02 frames.], batch size: 18, lr: 1.95e-03
2022-04-28 10:28:31,600 INFO [train.py:763] (3/8) Epoch 2, batch 950, loss[loss=0.2806, simple_loss=0.3528, pruned_loss=0.1042, over 7145.00 frames.], tot_loss[loss=0.2752, simple_loss=0.343, pruned_loss=0.1037, over 1417775.95 frames.], batch size: 20, lr: 1.94e-03
2022-04-28 10:29:36,671 INFO [train.py:763] (3/8) Epoch 2, batch 1000, loss[loss=0.3447, simple_loss=0.4038, pruned_loss=0.1428, over 6775.00 frames.], tot_loss[loss=0.2755, simple_loss=0.3437, pruned_loss=0.1036, over 1417221.79 frames.], batch size: 31, lr: 1.94e-03
2022-04-28 10:30:41,951 INFO [train.py:763] (3/8) Epoch 2, batch 1050, loss[loss=0.2629, simple_loss=0.3414, pruned_loss=0.09216, over 7276.00 frames.], tot_loss[loss=0.2741, simple_loss=0.3431, pruned_loss=0.1026, over 1414728.26 frames.], batch size: 18, lr: 1.94e-03
2022-04-28 10:31:48,320 INFO [train.py:763] (3/8) Epoch 2, batch 1100, loss[loss=0.2846, simple_loss=0.3538, pruned_loss=0.1077, over 7220.00 frames.], tot_loss[loss=0.2747, simple_loss=0.3439, pruned_loss=0.1027, over 1419485.17 frames.], batch size: 21, lr: 1.93e-03
2022-04-28 10:32:55,818 INFO [train.py:763] (3/8) Epoch 2, batch 1150, loss[loss=0.2582, simple_loss=0.3277, pruned_loss=0.09435, over 7232.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3436, pruned_loss=0.1031, over 1420379.86 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:34:03,563 INFO [train.py:763] (3/8) Epoch 2, batch 1200, loss[loss=0.2669, simple_loss=0.3361, pruned_loss=0.09883, over 7425.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3417, pruned_loss=0.1015, over 1424105.19 frames.], batch size: 20, lr: 1.93e-03
2022-04-28 10:35:11,225 INFO [train.py:763] (3/8) Epoch 2, batch 1250, loss[loss=0.3314, simple_loss=0.3892, pruned_loss=0.1368, over 7412.00 frames.], tot_loss[loss=0.2706, simple_loss=0.3397, pruned_loss=0.1007, over 1424704.93 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:36:17,277 INFO [train.py:763] (3/8) Epoch 2, batch 1300, loss[loss=0.2391, simple_loss=0.3251, pruned_loss=0.07651, over 7327.00 frames.], tot_loss[loss=0.2709, simple_loss=0.3399, pruned_loss=0.101, over 1426309.98 frames.], batch size: 21, lr: 1.92e-03
2022-04-28 10:37:22,331 INFO [train.py:763] (3/8) Epoch 2, batch 1350, loss[loss=0.2551, simple_loss=0.3221, pruned_loss=0.09408, over 7410.00 frames.], tot_loss[loss=0.273, simple_loss=0.3418, pruned_loss=0.1021, over 1425666.14 frames.], batch size: 20, lr: 1.91e-03
2022-04-28 10:38:27,402 INFO [train.py:763] (3/8) Epoch 2, batch 1400, loss[loss=0.2513, simple_loss=0.3266, pruned_loss=0.08799, over 7167.00 frames.], tot_loss[loss=0.2727, simple_loss=0.3418, pruned_loss=0.1018, over 1423035.80 frames.], batch size: 19, lr: 1.91e-03
2022-04-28 10:39:32,821 INFO [train.py:763] (3/8) Epoch 2, batch 1450, loss[loss=0.2073, simple_loss=0.2794, pruned_loss=0.06759, over 7149.00 frames.], tot_loss[loss=0.2731, simple_loss=0.3418, pruned_loss=0.1022, over 1419400.92 frames.], batch size: 17, lr: 1.91e-03
2022-04-28 10:40:38,389 INFO [train.py:763] (3/8) Epoch 2, batch 1500, loss[loss=0.2772, simple_loss=0.3546, pruned_loss=0.09993, over 7317.00 frames.], tot_loss[loss=0.2721, simple_loss=0.3416, pruned_loss=0.1013, over 1416504.42 frames.], batch size: 21, lr: 1.90e-03
2022-04-28 10:41:43,973 INFO [train.py:763] (3/8) Epoch 2, batch 1550, loss[loss=0.2419, simple_loss=0.304, pruned_loss=0.0899, over 7146.00 frames.], tot_loss[loss=0.2716, simple_loss=0.3414, pruned_loss=0.1009, over 1421073.62 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:42:49,541 INFO [train.py:763] (3/8) Epoch 2, batch 1600, loss[loss=0.2608, simple_loss=0.3217, pruned_loss=0.09993, over 7143.00 frames.], tot_loss[loss=0.2696, simple_loss=0.3399, pruned_loss=0.09969, over 1423026.72 frames.], batch size: 19, lr: 1.90e-03
2022-04-28 10:43:56,344 INFO [train.py:763] (3/8) Epoch 2, batch 1650, loss[loss=0.2441, simple_loss=0.3229, pruned_loss=0.08264, over 7434.00 frames.], tot_loss[loss=0.2678, simple_loss=0.3383, pruned_loss=0.09867, over 1426578.67 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:45:02,821 INFO [train.py:763] (3/8) Epoch 2, batch 1700, loss[loss=0.2609, simple_loss=0.3332, pruned_loss=0.09437, over 7151.00 frames.], tot_loss[loss=0.2683, simple_loss=0.3384, pruned_loss=0.09912, over 1417441.84 frames.], batch size: 20, lr: 1.89e-03
2022-04-28 10:46:08,589 INFO [train.py:763] (3/8) Epoch 2, batch 1750, loss[loss=0.2323, simple_loss=0.3112, pruned_loss=0.07668, over 7238.00 frames.], tot_loss[loss=0.267, simple_loss=0.3377, pruned_loss=0.09811, over 1424420.81 frames.], batch size: 20, lr: 1.88e-03
2022-04-28 10:47:13,948 INFO [train.py:763] (3/8) Epoch 2, batch 1800, loss[loss=0.2857, simple_loss=0.3572, pruned_loss=0.1071, over 7122.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3379, pruned_loss=0.09849, over 1417587.95 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:48:20,968 INFO [train.py:763] (3/8) Epoch 2, batch 1850, loss[loss=0.2694, simple_loss=0.3434, pruned_loss=0.09774, over 7416.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3377, pruned_loss=0.09837, over 1418937.63 frames.], batch size: 21, lr: 1.88e-03
2022-04-28 10:49:26,578 INFO [train.py:763] (3/8) Epoch 2, batch 1900, loss[loss=0.2457, simple_loss=0.3132, pruned_loss=0.08912, over 7173.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3378, pruned_loss=0.09878, over 1417187.12 frames.], batch size: 18, lr: 1.87e-03
2022-04-28 10:50:31,922 INFO [train.py:763] (3/8) Epoch 2, batch 1950, loss[loss=0.3024, simple_loss=0.3563, pruned_loss=0.1243, over 6927.00 frames.], tot_loss[loss=0.2662, simple_loss=0.3363, pruned_loss=0.09804, over 1418027.60 frames.], batch size: 31, lr: 1.87e-03
2022-04-28 10:51:37,333 INFO [train.py:763] (3/8) Epoch 2, batch 2000, loss[loss=0.2817, simple_loss=0.3434, pruned_loss=0.11, over 7155.00 frames.], tot_loss[loss=0.2647, simple_loss=0.3354, pruned_loss=0.09703, over 1422289.59 frames.], batch size: 19, lr: 1.87e-03
2022-04-28 10:52:43,639 INFO [train.py:763] (3/8) Epoch 2, batch 2050, loss[loss=0.3043, simple_loss=0.3677, pruned_loss=0.1204, over 5460.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3387, pruned_loss=0.0989, over 1422067.48 frames.], batch size: 53, lr: 1.86e-03
2022-04-28 10:53:49,750 INFO [train.py:763] (3/8) Epoch 2, batch 2100, loss[loss=0.2571, simple_loss=0.3453, pruned_loss=0.08444, over 7316.00 frames.], tot_loss[loss=0.2677, simple_loss=0.3384, pruned_loss=0.09844, over 1425034.63 frames.], batch size: 21, lr: 1.86e-03
2022-04-28 10:54:55,190 INFO [train.py:763] (3/8) Epoch 2, batch 2150, loss[loss=0.239, simple_loss=0.3332, pruned_loss=0.07242, over 7223.00 frames.], tot_loss[loss=0.2685, simple_loss=0.339, pruned_loss=0.09905, over 1426363.90 frames.], batch size: 20, lr: 1.86e-03
2022-04-28 10:56:00,715 INFO [train.py:763] (3/8) Epoch 2, batch 2200, loss[loss=0.276, simple_loss=0.344, pruned_loss=0.1041, over 7153.00 frames.], tot_loss[loss=0.2678, simple_loss=0.3382, pruned_loss=0.09864, over 1425028.58 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:57:05,938 INFO [train.py:763] (3/8) Epoch 2, batch 2250, loss[loss=0.2476, simple_loss=0.3241, pruned_loss=0.08556, over 7328.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3393, pruned_loss=0.09853, over 1424730.28 frames.], batch size: 20, lr: 1.85e-03
2022-04-28 10:58:11,384 INFO [train.py:763] (3/8) Epoch 2, batch 2300, loss[loss=0.2167, simple_loss=0.2973, pruned_loss=0.06802, over 7361.00 frames.], tot_loss[loss=0.2674, simple_loss=0.3379, pruned_loss=0.09841, over 1413465.58 frames.], batch size: 19, lr: 1.85e-03
2022-04-28 10:59:16,566 INFO [train.py:763] (3/8) Epoch 2, batch 2350, loss[loss=0.2419, simple_loss=0.3126, pruned_loss=0.08559, over 7258.00 frames.], tot_loss[loss=0.2661, simple_loss=0.337, pruned_loss=0.09761, over 1415198.47 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:00:21,740 INFO [train.py:763] (3/8) Epoch 2, batch 2400, loss[loss=0.3105, simple_loss=0.3581, pruned_loss=0.1315, over 7260.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3381, pruned_loss=0.09856, over 1418363.22 frames.], batch size: 19, lr: 1.84e-03
2022-04-28 11:01:26,803 INFO [train.py:763] (3/8) Epoch 2, batch 2450, loss[loss=0.3054, simple_loss=0.3781, pruned_loss=0.1163, over 7241.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3387, pruned_loss=0.0989, over 1415074.53 frames.], batch size: 20, lr: 1.84e-03
2022-04-28 11:02:32,497 INFO [train.py:763] (3/8) Epoch 2, batch 2500, loss[loss=0.28, simple_loss=0.3531, pruned_loss=0.1034, over 7166.00 frames.], tot_loss[loss=0.2678, simple_loss=0.3378, pruned_loss=0.0989, over 1413412.88 frames.], batch size: 19, lr: 1.83e-03
2022-04-28 11:03:38,313 INFO [train.py:763] (3/8) Epoch 2, batch 2550, loss[loss=0.2539, simple_loss=0.3457, pruned_loss=0.08106, over 7226.00 frames.], tot_loss[loss=0.2676, simple_loss=0.3373, pruned_loss=0.099, over 1412331.30 frames.], batch size: 21, lr: 1.83e-03
2022-04-28 11:04:44,221 INFO [train.py:763] (3/8) Epoch 2, batch 2600, loss[loss=0.2932, simple_loss=0.3579, pruned_loss=0.1143, over 7286.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3356, pruned_loss=0.09777, over 1418374.95 frames.], batch size: 18, lr: 1.83e-03
2022-04-28 11:05:50,133 INFO [train.py:763] (3/8) Epoch 2, batch 2650, loss[loss=0.2526, simple_loss=0.3364, pruned_loss=0.08439, over 7335.00 frames.], tot_loss[loss=0.2649, simple_loss=0.335, pruned_loss=0.09735, over 1418568.30 frames.], batch size: 20, lr: 1.82e-03
2022-04-28 11:06:55,493 INFO [train.py:763] (3/8) Epoch 2, batch 2700, loss[loss=0.217, simple_loss=0.2961, pruned_loss=0.06895, over 7059.00 frames.], tot_loss[loss=0.2656, simple_loss=0.3362, pruned_loss=0.09748, over 1419745.02 frames.], batch size: 18, lr: 1.82e-03
2022-04-28 11:08:01,949 INFO [train.py:763] (3/8) Epoch 2, batch 2750, loss[loss=0.3346, simple_loss=0.3803, pruned_loss=0.1445, over 7201.00 frames.], tot_loss[loss=0.2649, simple_loss=0.3356, pruned_loss=0.0971, over 1419758.89 frames.], batch size: 26, lr: 1.82e-03
2022-04-28 11:09:07,550 INFO [train.py:763] (3/8) Epoch 2, batch 2800, loss[loss=0.3156, simple_loss=0.3669, pruned_loss=0.1321, over 5088.00 frames.], tot_loss[loss=0.2632, simple_loss=0.3346, pruned_loss=0.09593, over 1418844.91 frames.], batch size: 53, lr: 1.81e-03
2022-04-28 11:10:13,391 INFO [train.py:763] (3/8) Epoch 2, batch 2850, loss[loss=0.2859, simple_loss=0.3703, pruned_loss=0.1007, over 7217.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3353, pruned_loss=0.09591, over 1421864.45 frames.], batch size: 21, lr: 1.81e-03
2022-04-28 11:11:19,191 INFO [train.py:763] (3/8) Epoch 2, batch 2900, loss[loss=0.2919, simple_loss=0.36, pruned_loss=0.1119, over 6367.00 frames.], tot_loss[loss=0.2635, simple_loss=0.3351, pruned_loss=0.09593, over 1418456.20 frames.], batch size: 38, lr: 1.81e-03
2022-04-28 11:12:24,869 INFO [train.py:763] (3/8) Epoch 2, batch 2950, loss[loss=0.2372, simple_loss=0.3116, pruned_loss=0.08137, over 7193.00 frames.], tot_loss[loss=0.264, simple_loss=0.3359, pruned_loss=0.09604, over 1417829.72 frames.], batch size: 26, lr: 1.80e-03
2022-04-28 11:13:30,378 INFO [train.py:763] (3/8) Epoch 2, batch 3000, loss[loss=0.2598, simple_loss=0.3353, pruned_loss=0.09211, over 7326.00 frames.], tot_loss[loss=0.2636, simple_loss=0.3357, pruned_loss=0.09575, over 1420871.66 frames.], batch size: 22, lr: 1.80e-03
2022-04-28 11:13:30,379 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 11:13:45,774 INFO [train.py:792] (3/8) 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] (3/8) Epoch 2, batch 3050, loss[loss=0.27, simple_loss=0.3493, pruned_loss=0.09538, over 7410.00 frames.], tot_loss[loss=0.2636, simple_loss=0.336, pruned_loss=0.09562, over 1425764.70 frames.], batch size: 21, lr: 1.80e-03
2022-04-28 11:15:57,115 INFO [train.py:763] (3/8) Epoch 2, batch 3100, loss[loss=0.2363, simple_loss=0.3077, pruned_loss=0.0824, over 7279.00 frames.], tot_loss[loss=0.2625, simple_loss=0.3351, pruned_loss=0.09496, over 1428796.25 frames.], batch size: 18, lr: 1.79e-03
2022-04-28 11:17:02,758 INFO [train.py:763] (3/8) Epoch 2, batch 3150, loss[loss=0.3086, simple_loss=0.3658, pruned_loss=0.1257, over 7220.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3344, pruned_loss=0.09537, over 1423132.96 frames.], batch size: 21, lr: 1.79e-03
2022-04-28 11:18:08,969 INFO [train.py:763] (3/8) Epoch 2, batch 3200, loss[loss=0.3005, simple_loss=0.3833, pruned_loss=0.1088, over 7379.00 frames.], tot_loss[loss=0.2634, simple_loss=0.3357, pruned_loss=0.09559, over 1426068.13 frames.], batch size: 23, lr: 1.79e-03
2022-04-28 11:19:14,935 INFO [train.py:763] (3/8) Epoch 2, batch 3250, loss[loss=0.2516, simple_loss=0.3252, pruned_loss=0.08896, over 7161.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3365, pruned_loss=0.09624, over 1427058.96 frames.], batch size: 19, lr: 1.79e-03
2022-04-28 11:20:20,952 INFO [train.py:763] (3/8) Epoch 2, batch 3300, loss[loss=0.2492, simple_loss=0.3302, pruned_loss=0.08409, over 7208.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3344, pruned_loss=0.09419, over 1429553.12 frames.], batch size: 26, lr: 1.78e-03
2022-04-28 11:21:25,809 INFO [train.py:763] (3/8) Epoch 2, batch 3350, loss[loss=0.2457, simple_loss=0.3149, pruned_loss=0.08831, over 7278.00 frames.], tot_loss[loss=0.2624, simple_loss=0.335, pruned_loss=0.09494, over 1426452.23 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:22:30,851 INFO [train.py:763] (3/8) Epoch 2, batch 3400, loss[loss=0.2081, simple_loss=0.2743, pruned_loss=0.07093, over 7405.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3355, pruned_loss=0.09536, over 1424298.76 frames.], batch size: 18, lr: 1.78e-03
2022-04-28 11:23:36,217 INFO [train.py:763] (3/8) Epoch 2, batch 3450, loss[loss=0.2458, simple_loss=0.325, pruned_loss=0.08336, over 7258.00 frames.], tot_loss[loss=0.264, simple_loss=0.3359, pruned_loss=0.09609, over 1419848.24 frames.], batch size: 19, lr: 1.77e-03
2022-04-28 11:24:41,580 INFO [train.py:763] (3/8) Epoch 2, batch 3500, loss[loss=0.3051, simple_loss=0.3609, pruned_loss=0.1246, over 7312.00 frames.], tot_loss[loss=0.2624, simple_loss=0.3345, pruned_loss=0.09514, over 1420938.55 frames.], batch size: 25, lr: 1.77e-03
2022-04-28 11:25:47,025 INFO [train.py:763] (3/8) Epoch 2, batch 3550, loss[loss=0.2518, simple_loss=0.3205, pruned_loss=0.09155, over 7203.00 frames.], tot_loss[loss=0.2643, simple_loss=0.3359, pruned_loss=0.09633, over 1419299.07 frames.], batch size: 21, lr: 1.77e-03
2022-04-28 11:26:52,370 INFO [train.py:763] (3/8) Epoch 2, batch 3600, loss[loss=0.3011, simple_loss=0.3682, pruned_loss=0.117, over 7305.00 frames.], tot_loss[loss=0.2614, simple_loss=0.3331, pruned_loss=0.09484, over 1421282.05 frames.], batch size: 24, lr: 1.76e-03
2022-04-28 11:27:57,957 INFO [train.py:763] (3/8) Epoch 2, batch 3650, loss[loss=0.3013, simple_loss=0.3666, pruned_loss=0.118, over 7373.00 frames.], tot_loss[loss=0.2603, simple_loss=0.3324, pruned_loss=0.09408, over 1421034.58 frames.], batch size: 23, lr: 1.76e-03
2022-04-28 11:29:03,179 INFO [train.py:763] (3/8) Epoch 2, batch 3700, loss[loss=0.2386, simple_loss=0.311, pruned_loss=0.08315, over 7420.00 frames.], tot_loss[loss=0.2596, simple_loss=0.3325, pruned_loss=0.09339, over 1417434.90 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:30:08,699 INFO [train.py:763] (3/8) Epoch 2, batch 3750, loss[loss=0.2547, simple_loss=0.3231, pruned_loss=0.09318, over 7285.00 frames.], tot_loss[loss=0.2591, simple_loss=0.3323, pruned_loss=0.09297, over 1423070.64 frames.], batch size: 18, lr: 1.76e-03
2022-04-28 11:31:14,665 INFO [train.py:763] (3/8) Epoch 2, batch 3800, loss[loss=0.2399, simple_loss=0.3101, pruned_loss=0.08479, over 7173.00 frames.], tot_loss[loss=0.2588, simple_loss=0.3319, pruned_loss=0.0928, over 1422739.13 frames.], batch size: 18, lr: 1.75e-03
2022-04-28 11:32:20,648 INFO [train.py:763] (3/8) Epoch 2, batch 3850, loss[loss=0.2471, simple_loss=0.3364, pruned_loss=0.07889, over 7336.00 frames.], tot_loss[loss=0.2595, simple_loss=0.3325, pruned_loss=0.09327, over 1421009.72 frames.], batch size: 22, lr: 1.75e-03
2022-04-28 11:33:26,576 INFO [train.py:763] (3/8) Epoch 2, batch 3900, loss[loss=0.2541, simple_loss=0.3377, pruned_loss=0.08523, over 7332.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3311, pruned_loss=0.09218, over 1423021.28 frames.], batch size: 20, lr: 1.75e-03
2022-04-28 11:34:31,994 INFO [train.py:763] (3/8) Epoch 2, batch 3950, loss[loss=0.2683, simple_loss=0.3475, pruned_loss=0.09455, over 7324.00 frames.], tot_loss[loss=0.2581, simple_loss=0.3316, pruned_loss=0.0923, over 1420704.13 frames.], batch size: 21, lr: 1.74e-03
2022-04-28 11:35:37,600 INFO [train.py:763] (3/8) Epoch 2, batch 4000, loss[loss=0.2792, simple_loss=0.3558, pruned_loss=0.1013, over 7339.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3306, pruned_loss=0.0909, over 1425238.82 frames.], batch size: 22, lr: 1.74e-03
2022-04-28 11:36:44,078 INFO [train.py:763] (3/8) Epoch 2, batch 4050, loss[loss=0.2701, simple_loss=0.3484, pruned_loss=0.09589, over 7442.00 frames.], tot_loss[loss=0.2562, simple_loss=0.3306, pruned_loss=0.09091, over 1425399.93 frames.], batch size: 20, lr: 1.74e-03
2022-04-28 11:37:49,242 INFO [train.py:763] (3/8) Epoch 2, batch 4100, loss[loss=0.231, simple_loss=0.3013, pruned_loss=0.08032, over 7075.00 frames.], tot_loss[loss=0.2575, simple_loss=0.331, pruned_loss=0.09195, over 1415821.35 frames.], batch size: 18, lr: 1.73e-03
2022-04-28 11:38:54,189 INFO [train.py:763] (3/8) Epoch 2, batch 4150, loss[loss=0.2784, simple_loss=0.3504, pruned_loss=0.1031, over 7109.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3311, pruned_loss=0.09183, over 1420929.66 frames.], batch size: 21, lr: 1.73e-03
2022-04-28 11:40:00,863 INFO [train.py:763] (3/8) Epoch 2, batch 4200, loss[loss=0.3055, simple_loss=0.3686, pruned_loss=0.1211, over 7096.00 frames.], tot_loss[loss=0.2582, simple_loss=0.3319, pruned_loss=0.09227, over 1420503.00 frames.], batch size: 28, lr: 1.73e-03
2022-04-28 11:41:07,990 INFO [train.py:763] (3/8) Epoch 2, batch 4250, loss[loss=0.2882, simple_loss=0.3549, pruned_loss=0.1107, over 7207.00 frames.], tot_loss[loss=0.2579, simple_loss=0.3314, pruned_loss=0.09215, over 1420834.87 frames.], batch size: 22, lr: 1.73e-03
2022-04-28 11:42:14,754 INFO [train.py:763] (3/8) Epoch 2, batch 4300, loss[loss=0.2149, simple_loss=0.2985, pruned_loss=0.0656, over 7075.00 frames.], tot_loss[loss=0.2577, simple_loss=0.3318, pruned_loss=0.09176, over 1422622.58 frames.], batch size: 18, lr: 1.72e-03
2022-04-28 11:43:21,901 INFO [train.py:763] (3/8) Epoch 2, batch 4350, loss[loss=0.267, simple_loss=0.3476, pruned_loss=0.09321, over 7148.00 frames.], tot_loss[loss=0.2585, simple_loss=0.3323, pruned_loss=0.09235, over 1424781.44 frames.], batch size: 20, lr: 1.72e-03
2022-04-28 11:44:27,744 INFO [train.py:763] (3/8) Epoch 2, batch 4400, loss[loss=0.284, simple_loss=0.3551, pruned_loss=0.1065, over 7281.00 frames.], tot_loss[loss=0.2599, simple_loss=0.333, pruned_loss=0.09343, over 1419747.74 frames.], batch size: 25, lr: 1.72e-03
2022-04-28 11:45:33,250 INFO [train.py:763] (3/8) Epoch 2, batch 4450, loss[loss=0.3052, simple_loss=0.3744, pruned_loss=0.118, over 7335.00 frames.], tot_loss[loss=0.2609, simple_loss=0.3341, pruned_loss=0.09388, over 1411978.70 frames.], batch size: 22, lr: 1.71e-03
2022-04-28 11:46:38,403 INFO [train.py:763] (3/8) Epoch 2, batch 4500, loss[loss=0.217, simple_loss=0.304, pruned_loss=0.06498, over 7122.00 frames.], tot_loss[loss=0.2604, simple_loss=0.3341, pruned_loss=0.09333, over 1405984.40 frames.], batch size: 21, lr: 1.71e-03
2022-04-28 11:47:42,632 INFO [train.py:763] (3/8) Epoch 2, batch 4550, loss[loss=0.2676, simple_loss=0.3331, pruned_loss=0.1011, over 6474.00 frames.], tot_loss[loss=0.264, simple_loss=0.3372, pruned_loss=0.09536, over 1378709.99 frames.], batch size: 38, lr: 1.71e-03
2022-04-28 11:49:10,863 INFO [train.py:763] (3/8) Epoch 3, batch 0, loss[loss=0.2993, simple_loss=0.3749, pruned_loss=0.1118, over 7193.00 frames.], tot_loss[loss=0.2993, simple_loss=0.3749, pruned_loss=0.1118, over 7193.00 frames.], batch size: 23, lr: 1.66e-03
2022-04-28 11:50:17,404 INFO [train.py:763] (3/8) Epoch 3, batch 50, loss[loss=0.1835, simple_loss=0.2603, pruned_loss=0.05334, over 7286.00 frames.], tot_loss[loss=0.2587, simple_loss=0.3318, pruned_loss=0.09278, over 317772.87 frames.], batch size: 17, lr: 1.66e-03
2022-04-28 11:51:23,921 INFO [train.py:763] (3/8) Epoch 3, batch 100, loss[loss=0.2255, simple_loss=0.2912, pruned_loss=0.07989, over 7282.00 frames.], tot_loss[loss=0.2542, simple_loss=0.3281, pruned_loss=0.09013, over 563897.81 frames.], batch size: 17, lr: 1.65e-03
2022-04-28 11:52:29,495 INFO [train.py:763] (3/8) Epoch 3, batch 150, loss[loss=0.2701, simple_loss=0.3531, pruned_loss=0.09358, over 7313.00 frames.], tot_loss[loss=0.255, simple_loss=0.3292, pruned_loss=0.09046, over 756021.97 frames.], batch size: 22, lr: 1.65e-03
2022-04-28 11:53:34,974 INFO [train.py:763] (3/8) Epoch 3, batch 200, loss[loss=0.2716, simple_loss=0.3458, pruned_loss=0.09877, over 7206.00 frames.], tot_loss[loss=0.256, simple_loss=0.3304, pruned_loss=0.09079, over 905394.62 frames.], batch size: 23, lr: 1.65e-03
2022-04-28 11:54:40,982 INFO [train.py:763] (3/8) Epoch 3, batch 250, loss[loss=0.2268, simple_loss=0.3156, pruned_loss=0.06901, over 7342.00 frames.], tot_loss[loss=0.2567, simple_loss=0.331, pruned_loss=0.09116, over 1016912.78 frames.], batch size: 22, lr: 1.64e-03
2022-04-28 11:55:46,609 INFO [train.py:763] (3/8) Epoch 3, batch 300, loss[loss=0.2723, simple_loss=0.3387, pruned_loss=0.103, over 7374.00 frames.], tot_loss[loss=0.2539, simple_loss=0.3292, pruned_loss=0.08928, over 1111039.37 frames.], batch size: 23, lr: 1.64e-03
2022-04-28 11:56:52,028 INFO [train.py:763] (3/8) Epoch 3, batch 350, loss[loss=0.2489, simple_loss=0.341, pruned_loss=0.07835, over 7315.00 frames.], tot_loss[loss=0.2535, simple_loss=0.3287, pruned_loss=0.08911, over 1182498.00 frames.], batch size: 21, lr: 1.64e-03
2022-04-28 11:57:57,844 INFO [train.py:763] (3/8) Epoch 3, batch 400, loss[loss=0.2738, simple_loss=0.3456, pruned_loss=0.101, over 7231.00 frames.], tot_loss[loss=0.2526, simple_loss=0.3274, pruned_loss=0.08885, over 1232053.12 frames.], batch size: 20, lr: 1.64e-03
2022-04-28 11:59:03,270 INFO [train.py:763] (3/8) Epoch 3, batch 450, loss[loss=0.293, simple_loss=0.354, pruned_loss=0.116, over 7147.00 frames.], tot_loss[loss=0.2533, simple_loss=0.3277, pruned_loss=0.08942, over 1274362.18 frames.], batch size: 20, lr: 1.63e-03
2022-04-28 12:00:09,021 INFO [train.py:763] (3/8) Epoch 3, batch 500, loss[loss=0.2269, simple_loss=0.3135, pruned_loss=0.07009, over 7151.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3294, pruned_loss=0.08966, over 1303456.41 frames.], batch size: 19, lr: 1.63e-03
2022-04-28 12:01:14,926 INFO [train.py:763] (3/8) Epoch 3, batch 550, loss[loss=0.2422, simple_loss=0.3134, pruned_loss=0.08555, over 7150.00 frames.], tot_loss[loss=0.2544, simple_loss=0.3298, pruned_loss=0.08954, over 1329816.73 frames.], batch size: 18, lr: 1.63e-03
2022-04-28 12:02:20,843 INFO [train.py:763] (3/8) Epoch 3, batch 600, loss[loss=0.2798, simple_loss=0.3414, pruned_loss=0.1091, over 6508.00 frames.], tot_loss[loss=0.2534, simple_loss=0.3292, pruned_loss=0.08881, over 1346996.11 frames.], batch size: 38, lr: 1.63e-03
2022-04-28 12:03:27,785 INFO [train.py:763] (3/8) Epoch 3, batch 650, loss[loss=0.2647, simple_loss=0.3531, pruned_loss=0.08817, over 7436.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3292, pruned_loss=0.08829, over 1367544.66 frames.], batch size: 20, lr: 1.62e-03
2022-04-28 12:04:35,116 INFO [train.py:763] (3/8) Epoch 3, batch 700, loss[loss=0.2594, simple_loss=0.3326, pruned_loss=0.0931, over 7269.00 frames.], tot_loss[loss=0.2502, simple_loss=0.327, pruned_loss=0.0867, over 1384556.92 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:05:41,310 INFO [train.py:763] (3/8) Epoch 3, batch 750, loss[loss=0.2224, simple_loss=0.3112, pruned_loss=0.06678, over 7315.00 frames.], tot_loss[loss=0.2501, simple_loss=0.3268, pruned_loss=0.08672, over 1392084.09 frames.], batch size: 24, lr: 1.62e-03
2022-04-28 12:06:46,992 INFO [train.py:763] (3/8) Epoch 3, batch 800, loss[loss=0.2136, simple_loss=0.2996, pruned_loss=0.06379, over 7271.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3279, pruned_loss=0.0876, over 1396751.04 frames.], batch size: 19, lr: 1.62e-03
2022-04-28 12:07:53,459 INFO [train.py:763] (3/8) Epoch 3, batch 850, loss[loss=0.2098, simple_loss=0.2934, pruned_loss=0.06313, over 7064.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3276, pruned_loss=0.08687, over 1406741.63 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:09:00,227 INFO [train.py:763] (3/8) Epoch 3, batch 900, loss[loss=0.3034, simple_loss=0.373, pruned_loss=0.1169, over 7118.00 frames.], tot_loss[loss=0.251, simple_loss=0.3278, pruned_loss=0.08707, over 1414678.85 frames.], batch size: 21, lr: 1.61e-03
2022-04-28 12:10:06,504 INFO [train.py:763] (3/8) Epoch 3, batch 950, loss[loss=0.2621, simple_loss=0.3415, pruned_loss=0.0914, over 7179.00 frames.], tot_loss[loss=0.25, simple_loss=0.3269, pruned_loss=0.08653, over 1420087.45 frames.], batch size: 26, lr: 1.61e-03
2022-04-28 12:11:12,747 INFO [train.py:763] (3/8) Epoch 3, batch 1000, loss[loss=0.2125, simple_loss=0.2877, pruned_loss=0.06868, over 7283.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3273, pruned_loss=0.087, over 1420569.69 frames.], batch size: 18, lr: 1.61e-03
2022-04-28 12:12:18,772 INFO [train.py:763] (3/8) Epoch 3, batch 1050, loss[loss=0.2773, simple_loss=0.3502, pruned_loss=0.1022, over 6759.00 frames.], tot_loss[loss=0.251, simple_loss=0.3276, pruned_loss=0.08723, over 1419473.49 frames.], batch size: 31, lr: 1.60e-03
2022-04-28 12:13:24,397 INFO [train.py:763] (3/8) Epoch 3, batch 1100, loss[loss=0.2817, simple_loss=0.3583, pruned_loss=0.1025, over 7411.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3266, pruned_loss=0.08706, over 1419923.69 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:14:28,836 INFO [train.py:763] (3/8) Epoch 3, batch 1150, loss[loss=0.2721, simple_loss=0.3494, pruned_loss=0.09742, over 7325.00 frames.], tot_loss[loss=0.2529, simple_loss=0.3288, pruned_loss=0.08843, over 1417517.31 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:15:35,087 INFO [train.py:763] (3/8) Epoch 3, batch 1200, loss[loss=0.281, simple_loss=0.3497, pruned_loss=0.1062, over 7324.00 frames.], tot_loss[loss=0.2528, simple_loss=0.3289, pruned_loss=0.08839, over 1415241.81 frames.], batch size: 21, lr: 1.60e-03
2022-04-28 12:16:40,630 INFO [train.py:763] (3/8) Epoch 3, batch 1250, loss[loss=0.2011, simple_loss=0.2813, pruned_loss=0.06045, over 6902.00 frames.], tot_loss[loss=0.251, simple_loss=0.3275, pruned_loss=0.08727, over 1413492.93 frames.], batch size: 15, lr: 1.59e-03
2022-04-28 12:17:46,151 INFO [train.py:763] (3/8) Epoch 3, batch 1300, loss[loss=0.2929, simple_loss=0.3643, pruned_loss=0.1107, over 7191.00 frames.], tot_loss[loss=0.2506, simple_loss=0.3271, pruned_loss=0.08703, over 1416879.85 frames.], batch size: 23, lr: 1.59e-03
2022-04-28 12:18:51,892 INFO [train.py:763] (3/8) Epoch 3, batch 1350, loss[loss=0.2575, simple_loss=0.3287, pruned_loss=0.09315, over 7232.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3276, pruned_loss=0.08784, over 1416030.62 frames.], batch size: 20, lr: 1.59e-03
2022-04-28 12:19:57,901 INFO [train.py:763] (3/8) Epoch 3, batch 1400, loss[loss=0.2654, simple_loss=0.341, pruned_loss=0.09491, over 7199.00 frames.], tot_loss[loss=0.25, simple_loss=0.3263, pruned_loss=0.08685, over 1418969.47 frames.], batch size: 22, lr: 1.59e-03
2022-04-28 12:21:03,056 INFO [train.py:763] (3/8) Epoch 3, batch 1450, loss[loss=0.2344, simple_loss=0.3162, pruned_loss=0.07632, over 7284.00 frames.], tot_loss[loss=0.2509, simple_loss=0.3275, pruned_loss=0.0872, over 1420670.83 frames.], batch size: 24, lr: 1.59e-03
2022-04-28 12:22:08,501 INFO [train.py:763] (3/8) Epoch 3, batch 1500, loss[loss=0.2459, simple_loss=0.3294, pruned_loss=0.08119, over 7303.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3265, pruned_loss=0.08643, over 1417802.87 frames.], batch size: 24, lr: 1.58e-03
2022-04-28 12:23:13,999 INFO [train.py:763] (3/8) Epoch 3, batch 1550, loss[loss=0.3125, simple_loss=0.3656, pruned_loss=0.1297, over 4985.00 frames.], tot_loss[loss=0.2504, simple_loss=0.3272, pruned_loss=0.08681, over 1416847.88 frames.], batch size: 52, lr: 1.58e-03
2022-04-28 12:24:20,148 INFO [train.py:763] (3/8) Epoch 3, batch 1600, loss[loss=0.2539, simple_loss=0.3286, pruned_loss=0.08959, over 7342.00 frames.], tot_loss[loss=0.2517, simple_loss=0.3284, pruned_loss=0.0875, over 1414398.11 frames.], batch size: 25, lr: 1.58e-03
2022-04-28 12:25:26,868 INFO [train.py:763] (3/8) Epoch 3, batch 1650, loss[loss=0.2429, simple_loss=0.3331, pruned_loss=0.07633, over 7321.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3267, pruned_loss=0.08638, over 1416418.40 frames.], batch size: 20, lr: 1.58e-03
2022-04-28 12:26:34,038 INFO [train.py:763] (3/8) Epoch 3, batch 1700, loss[loss=0.2491, simple_loss=0.3299, pruned_loss=0.0842, over 7142.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3274, pruned_loss=0.08605, over 1420088.45 frames.], batch size: 20, lr: 1.57e-03
2022-04-28 12:27:40,151 INFO [train.py:763] (3/8) Epoch 3, batch 1750, loss[loss=0.2742, simple_loss=0.3546, pruned_loss=0.09687, over 7209.00 frames.], tot_loss[loss=0.2503, simple_loss=0.3274, pruned_loss=0.08656, over 1420035.36 frames.], batch size: 22, lr: 1.57e-03
2022-04-28 12:28:45,188 INFO [train.py:763] (3/8) Epoch 3, batch 1800, loss[loss=0.2545, simple_loss=0.3334, pruned_loss=0.08783, over 7220.00 frames.], tot_loss[loss=0.2511, simple_loss=0.3286, pruned_loss=0.08679, over 1422323.19 frames.], batch size: 21, lr: 1.57e-03
2022-04-28 12:29:50,458 INFO [train.py:763] (3/8) Epoch 3, batch 1850, loss[loss=0.2294, simple_loss=0.3107, pruned_loss=0.07402, over 7135.00 frames.], tot_loss[loss=0.2512, simple_loss=0.3285, pruned_loss=0.087, over 1420176.01 frames.], batch size: 17, lr: 1.57e-03
2022-04-28 12:30:57,295 INFO [train.py:763] (3/8) Epoch 3, batch 1900, loss[loss=0.193, simple_loss=0.2813, pruned_loss=0.05236, over 7156.00 frames.], tot_loss[loss=0.252, simple_loss=0.329, pruned_loss=0.08752, over 1423502.99 frames.], batch size: 19, lr: 1.56e-03
2022-04-28 12:32:03,219 INFO [train.py:763] (3/8) Epoch 3, batch 1950, loss[loss=0.2613, simple_loss=0.3407, pruned_loss=0.09091, over 6346.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3279, pruned_loss=0.08622, over 1428052.42 frames.], batch size: 37, lr: 1.56e-03
2022-04-28 12:33:17,823 INFO [train.py:763] (3/8) Epoch 3, batch 2000, loss[loss=0.2995, simple_loss=0.3588, pruned_loss=0.1201, over 7109.00 frames.], tot_loss[loss=0.2516, simple_loss=0.3289, pruned_loss=0.08713, over 1425444.18 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:35:10,046 INFO [train.py:763] (3/8) Epoch 3, batch 2050, loss[loss=0.2738, simple_loss=0.3445, pruned_loss=0.1016, over 6786.00 frames.], tot_loss[loss=0.2515, simple_loss=0.3286, pruned_loss=0.08723, over 1422587.60 frames.], batch size: 31, lr: 1.56e-03
2022-04-28 12:36:15,498 INFO [train.py:763] (3/8) Epoch 3, batch 2100, loss[loss=0.2424, simple_loss=0.3287, pruned_loss=0.07801, over 7317.00 frames.], tot_loss[loss=0.2495, simple_loss=0.3267, pruned_loss=0.08616, over 1420432.28 frames.], batch size: 21, lr: 1.56e-03
2022-04-28 12:37:29,640 INFO [train.py:763] (3/8) Epoch 3, batch 2150, loss[loss=0.2415, simple_loss=0.3292, pruned_loss=0.07694, over 7331.00 frames.], tot_loss[loss=0.2489, simple_loss=0.3263, pruned_loss=0.08576, over 1423116.48 frames.], batch size: 22, lr: 1.55e-03
2022-04-28 12:38:44,719 INFO [train.py:763] (3/8) Epoch 3, batch 2200, loss[loss=0.2855, simple_loss=0.3632, pruned_loss=0.1039, over 7224.00 frames.], tot_loss[loss=0.2478, simple_loss=0.3253, pruned_loss=0.08519, over 1424820.71 frames.], batch size: 21, lr: 1.55e-03
2022-04-28 12:40:02,462 INFO [train.py:763] (3/8) Epoch 3, batch 2250, loss[loss=0.2973, simple_loss=0.3494, pruned_loss=0.1226, over 4867.00 frames.], tot_loss[loss=0.2485, simple_loss=0.3261, pruned_loss=0.08546, over 1426303.19 frames.], batch size: 52, lr: 1.55e-03
2022-04-28 12:41:07,752 INFO [train.py:763] (3/8) Epoch 3, batch 2300, loss[loss=0.2662, simple_loss=0.3452, pruned_loss=0.09361, over 7168.00 frames.], tot_loss[loss=0.2486, simple_loss=0.3264, pruned_loss=0.08537, over 1429617.62 frames.], batch size: 19, lr: 1.55e-03
2022-04-28 12:42:14,641 INFO [train.py:763] (3/8) Epoch 3, batch 2350, loss[loss=0.2172, simple_loss=0.3008, pruned_loss=0.06684, over 7337.00 frames.], tot_loss[loss=0.2473, simple_loss=0.3254, pruned_loss=0.08458, over 1431407.50 frames.], batch size: 20, lr: 1.54e-03
2022-04-28 12:43:19,979 INFO [train.py:763] (3/8) Epoch 3, batch 2400, loss[loss=0.2615, simple_loss=0.3507, pruned_loss=0.08611, over 7320.00 frames.], tot_loss[loss=0.2481, simple_loss=0.3268, pruned_loss=0.0847, over 1433411.98 frames.], batch size: 25, lr: 1.54e-03
2022-04-28 12:44:25,915 INFO [train.py:763] (3/8) Epoch 3, batch 2450, loss[loss=0.2616, simple_loss=0.3386, pruned_loss=0.09231, over 7375.00 frames.], tot_loss[loss=0.248, simple_loss=0.3266, pruned_loss=0.08473, over 1436408.36 frames.], batch size: 23, lr: 1.54e-03
2022-04-28 12:45:31,562 INFO [train.py:763] (3/8) Epoch 3, batch 2500, loss[loss=0.2653, simple_loss=0.3348, pruned_loss=0.09784, over 7149.00 frames.], tot_loss[loss=0.2484, simple_loss=0.3266, pruned_loss=0.08505, over 1434830.84 frames.], batch size: 19, lr: 1.54e-03
2022-04-28 12:46:36,893 INFO [train.py:763] (3/8) Epoch 3, batch 2550, loss[loss=0.2151, simple_loss=0.2866, pruned_loss=0.07179, over 7423.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3264, pruned_loss=0.08513, over 1427109.57 frames.], batch size: 18, lr: 1.54e-03
2022-04-28 12:47:42,408 INFO [train.py:763] (3/8) Epoch 3, batch 2600, loss[loss=0.2694, simple_loss=0.3461, pruned_loss=0.09636, over 7236.00 frames.], tot_loss[loss=0.2497, simple_loss=0.3274, pruned_loss=0.08595, over 1426127.13 frames.], batch size: 20, lr: 1.53e-03
2022-04-28 12:48:47,821 INFO [train.py:763] (3/8) Epoch 3, batch 2650, loss[loss=0.1799, simple_loss=0.2653, pruned_loss=0.04725, over 6989.00 frames.], tot_loss[loss=0.2518, simple_loss=0.3292, pruned_loss=0.08722, over 1420386.71 frames.], batch size: 16, lr: 1.53e-03
2022-04-28 12:49:52,900 INFO [train.py:763] (3/8) Epoch 3, batch 2700, loss[loss=0.223, simple_loss=0.2899, pruned_loss=0.07811, over 6792.00 frames.], tot_loss[loss=0.2507, simple_loss=0.3284, pruned_loss=0.08647, over 1418573.55 frames.], batch size: 15, lr: 1.53e-03
2022-04-28 12:50:58,280 INFO [train.py:763] (3/8) Epoch 3, batch 2750, loss[loss=0.2, simple_loss=0.2929, pruned_loss=0.05351, over 7267.00 frames.], tot_loss[loss=0.2483, simple_loss=0.3269, pruned_loss=0.08485, over 1421703.83 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:52:03,626 INFO [train.py:763] (3/8) Epoch 3, batch 2800, loss[loss=0.2358, simple_loss=0.316, pruned_loss=0.07785, over 7144.00 frames.], tot_loss[loss=0.246, simple_loss=0.325, pruned_loss=0.08351, over 1424263.85 frames.], batch size: 19, lr: 1.53e-03
2022-04-28 12:53:09,247 INFO [train.py:763] (3/8) Epoch 3, batch 2850, loss[loss=0.3212, simple_loss=0.3717, pruned_loss=0.1354, over 4873.00 frames.], tot_loss[loss=0.2467, simple_loss=0.3252, pruned_loss=0.08409, over 1423469.41 frames.], batch size: 53, lr: 1.52e-03
2022-04-28 12:54:14,535 INFO [train.py:763] (3/8) Epoch 3, batch 2900, loss[loss=0.2688, simple_loss=0.356, pruned_loss=0.09082, over 6780.00 frames.], tot_loss[loss=0.2463, simple_loss=0.3244, pruned_loss=0.08407, over 1424057.43 frames.], batch size: 31, lr: 1.52e-03
2022-04-28 12:55:20,287 INFO [train.py:763] (3/8) Epoch 3, batch 2950, loss[loss=0.2816, simple_loss=0.3436, pruned_loss=0.1098, over 7101.00 frames.], tot_loss[loss=0.2457, simple_loss=0.3241, pruned_loss=0.0837, over 1428068.61 frames.], batch size: 28, lr: 1.52e-03
2022-04-28 12:56:25,610 INFO [train.py:763] (3/8) Epoch 3, batch 3000, loss[loss=0.2355, simple_loss=0.3198, pruned_loss=0.07558, over 7152.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3241, pruned_loss=0.08355, over 1426593.01 frames.], batch size: 20, lr: 1.52e-03
2022-04-28 12:56:25,612 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 12:56:40,877 INFO [train.py:792] (3/8) Epoch 3, validation: loss=0.1917, simple_loss=0.2967, pruned_loss=0.04336, over 698248.00 frames.
2022-04-28 12:57:46,580 INFO [train.py:763] (3/8) Epoch 3, batch 3050, loss[loss=0.1986, simple_loss=0.3035, pruned_loss=0.04685, over 7117.00 frames.], tot_loss[loss=0.2452, simple_loss=0.3239, pruned_loss=0.08328, over 1421560.76 frames.], batch size: 21, lr: 1.51e-03
2022-04-28 12:58:52,512 INFO [train.py:763] (3/8) Epoch 3, batch 3100, loss[loss=0.2529, simple_loss=0.3327, pruned_loss=0.08659, over 7298.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3229, pruned_loss=0.08342, over 1418196.02 frames.], batch size: 24, lr: 1.51e-03
2022-04-28 12:59:58,115 INFO [train.py:763] (3/8) Epoch 3, batch 3150, loss[loss=0.2564, simple_loss=0.3291, pruned_loss=0.09188, over 7306.00 frames.], tot_loss[loss=0.2441, simple_loss=0.323, pruned_loss=0.08262, over 1422882.34 frames.], batch size: 25, lr: 1.51e-03
2022-04-28 13:01:03,461 INFO [train.py:763] (3/8) Epoch 3, batch 3200, loss[loss=0.228, simple_loss=0.3107, pruned_loss=0.07271, over 7060.00 frames.], tot_loss[loss=0.2428, simple_loss=0.3216, pruned_loss=0.08198, over 1423768.81 frames.], batch size: 18, lr: 1.51e-03
2022-04-28 13:02:09,451 INFO [train.py:763] (3/8) Epoch 3, batch 3250, loss[loss=0.2123, simple_loss=0.3042, pruned_loss=0.06017, over 7260.00 frames.], tot_loss[loss=0.2447, simple_loss=0.3232, pruned_loss=0.08309, over 1423780.11 frames.], batch size: 19, lr: 1.51e-03
2022-04-28 13:03:16,230 INFO [train.py:763] (3/8) Epoch 3, batch 3300, loss[loss=0.2346, simple_loss=0.3346, pruned_loss=0.06728, over 7203.00 frames.], tot_loss[loss=0.2455, simple_loss=0.3243, pruned_loss=0.0834, over 1422316.24 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:04:22,925 INFO [train.py:763] (3/8) Epoch 3, batch 3350, loss[loss=0.3063, simple_loss=0.3746, pruned_loss=0.1191, over 6369.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3231, pruned_loss=0.0829, over 1420675.88 frames.], batch size: 38, lr: 1.50e-03
2022-04-28 13:05:28,642 INFO [train.py:763] (3/8) Epoch 3, batch 3400, loss[loss=0.2073, simple_loss=0.2866, pruned_loss=0.064, over 6983.00 frames.], tot_loss[loss=0.2456, simple_loss=0.3238, pruned_loss=0.08365, over 1421135.41 frames.], batch size: 16, lr: 1.50e-03
2022-04-28 13:06:35,009 INFO [train.py:763] (3/8) Epoch 3, batch 3450, loss[loss=0.2212, simple_loss=0.3047, pruned_loss=0.06887, over 7166.00 frames.], tot_loss[loss=0.2426, simple_loss=0.3214, pruned_loss=0.08188, over 1426098.07 frames.], batch size: 18, lr: 1.50e-03
2022-04-28 13:07:42,191 INFO [train.py:763] (3/8) Epoch 3, batch 3500, loss[loss=0.2389, simple_loss=0.3243, pruned_loss=0.07669, over 7367.00 frames.], tot_loss[loss=0.2417, simple_loss=0.3207, pruned_loss=0.08137, over 1428044.56 frames.], batch size: 23, lr: 1.50e-03
2022-04-28 13:08:48,563 INFO [train.py:763] (3/8) Epoch 3, batch 3550, loss[loss=0.2879, simple_loss=0.3506, pruned_loss=0.1126, over 7305.00 frames.], tot_loss[loss=0.2431, simple_loss=0.3214, pruned_loss=0.08237, over 1429470.48 frames.], batch size: 24, lr: 1.49e-03
2022-04-28 13:09:55,525 INFO [train.py:763] (3/8) Epoch 3, batch 3600, loss[loss=0.1912, simple_loss=0.2675, pruned_loss=0.05748, over 6994.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3216, pruned_loss=0.08265, over 1428409.42 frames.], batch size: 16, lr: 1.49e-03
2022-04-28 13:11:02,049 INFO [train.py:763] (3/8) Epoch 3, batch 3650, loss[loss=0.2097, simple_loss=0.277, pruned_loss=0.07121, over 7128.00 frames.], tot_loss[loss=0.2433, simple_loss=0.3215, pruned_loss=0.08259, over 1429094.60 frames.], batch size: 17, lr: 1.49e-03
2022-04-28 13:12:07,903 INFO [train.py:763] (3/8) Epoch 3, batch 3700, loss[loss=0.1735, simple_loss=0.2579, pruned_loss=0.04455, over 7011.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3216, pruned_loss=0.08271, over 1427542.32 frames.], batch size: 16, lr: 1.49e-03
2022-04-28 13:13:15,359 INFO [train.py:763] (3/8) Epoch 3, batch 3750, loss[loss=0.2595, simple_loss=0.3343, pruned_loss=0.09238, over 7432.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3201, pruned_loss=0.08208, over 1425509.22 frames.], batch size: 20, lr: 1.49e-03
2022-04-28 13:14:22,356 INFO [train.py:763] (3/8) Epoch 3, batch 3800, loss[loss=0.1983, simple_loss=0.2852, pruned_loss=0.05569, over 7060.00 frames.], tot_loss[loss=0.2422, simple_loss=0.3199, pruned_loss=0.08224, over 1422190.91 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:15:29,714 INFO [train.py:763] (3/8) Epoch 3, batch 3850, loss[loss=0.1994, simple_loss=0.279, pruned_loss=0.05996, over 7416.00 frames.], tot_loss[loss=0.242, simple_loss=0.3198, pruned_loss=0.08212, over 1425809.25 frames.], batch size: 18, lr: 1.48e-03
2022-04-28 13:16:35,236 INFO [train.py:763] (3/8) Epoch 3, batch 3900, loss[loss=0.3282, simple_loss=0.3896, pruned_loss=0.1334, over 4951.00 frames.], tot_loss[loss=0.2435, simple_loss=0.3214, pruned_loss=0.08278, over 1426290.27 frames.], batch size: 52, lr: 1.48e-03
2022-04-28 13:17:41,252 INFO [train.py:763] (3/8) Epoch 3, batch 3950, loss[loss=0.2054, simple_loss=0.2753, pruned_loss=0.0677, over 6831.00 frames.], tot_loss[loss=0.243, simple_loss=0.3209, pruned_loss=0.08255, over 1423897.64 frames.], batch size: 15, lr: 1.48e-03
2022-04-28 13:18:46,786 INFO [train.py:763] (3/8) Epoch 3, batch 4000, loss[loss=0.2691, simple_loss=0.3461, pruned_loss=0.09606, over 7211.00 frames.], tot_loss[loss=0.2449, simple_loss=0.3227, pruned_loss=0.08358, over 1416610.02 frames.], batch size: 21, lr: 1.48e-03
2022-04-28 13:19:52,130 INFO [train.py:763] (3/8) Epoch 3, batch 4050, loss[loss=0.2505, simple_loss=0.33, pruned_loss=0.08553, over 7412.00 frames.], tot_loss[loss=0.2459, simple_loss=0.3237, pruned_loss=0.08406, over 1419076.35 frames.], batch size: 21, lr: 1.47e-03
2022-04-28 13:20:58,242 INFO [train.py:763] (3/8) Epoch 3, batch 4100, loss[loss=0.2665, simple_loss=0.3461, pruned_loss=0.09349, over 6448.00 frames.], tot_loss[loss=0.2453, simple_loss=0.3232, pruned_loss=0.08372, over 1420862.54 frames.], batch size: 37, lr: 1.47e-03
2022-04-28 13:22:04,070 INFO [train.py:763] (3/8) Epoch 3, batch 4150, loss[loss=0.2504, simple_loss=0.3092, pruned_loss=0.09579, over 7413.00 frames.], tot_loss[loss=0.2445, simple_loss=0.3221, pruned_loss=0.08344, over 1423297.51 frames.], batch size: 17, lr: 1.47e-03
2022-04-28 13:23:11,044 INFO [train.py:763] (3/8) Epoch 3, batch 4200, loss[loss=0.2081, simple_loss=0.2971, pruned_loss=0.05954, over 7161.00 frames.], tot_loss[loss=0.2452, simple_loss=0.323, pruned_loss=0.08367, over 1421376.47 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:24:18,326 INFO [train.py:763] (3/8) Epoch 3, batch 4250, loss[loss=0.1982, simple_loss=0.2833, pruned_loss=0.05652, over 7352.00 frames.], tot_loss[loss=0.2434, simple_loss=0.3212, pruned_loss=0.0828, over 1413751.13 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:25:24,087 INFO [train.py:763] (3/8) Epoch 3, batch 4300, loss[loss=0.2823, simple_loss=0.3614, pruned_loss=0.1016, over 7359.00 frames.], tot_loss[loss=0.2419, simple_loss=0.3193, pruned_loss=0.08224, over 1411651.89 frames.], batch size: 19, lr: 1.47e-03
2022-04-28 13:26:29,894 INFO [train.py:763] (3/8) Epoch 3, batch 4350, loss[loss=0.2313, simple_loss=0.3095, pruned_loss=0.07655, over 6314.00 frames.], tot_loss[loss=0.238, simple_loss=0.316, pruned_loss=0.08, over 1409483.02 frames.], batch size: 37, lr: 1.46e-03
2022-04-28 13:27:35,678 INFO [train.py:763] (3/8) Epoch 3, batch 4400, loss[loss=0.2174, simple_loss=0.3041, pruned_loss=0.06535, over 7080.00 frames.], tot_loss[loss=0.2372, simple_loss=0.3152, pruned_loss=0.07962, over 1408074.82 frames.], batch size: 18, lr: 1.46e-03
2022-04-28 13:28:41,562 INFO [train.py:763] (3/8) Epoch 3, batch 4450, loss[loss=0.2985, simple_loss=0.3665, pruned_loss=0.1152, over 7382.00 frames.], tot_loss[loss=0.2381, simple_loss=0.3154, pruned_loss=0.08041, over 1400762.16 frames.], batch size: 23, lr: 1.46e-03
2022-04-28 13:29:46,949 INFO [train.py:763] (3/8) Epoch 3, batch 4500, loss[loss=0.2787, simple_loss=0.3642, pruned_loss=0.09662, over 6353.00 frames.], tot_loss[loss=0.2393, simple_loss=0.3166, pruned_loss=0.08098, over 1395706.18 frames.], batch size: 37, lr: 1.46e-03
2022-04-28 13:30:51,039 INFO [train.py:763] (3/8) Epoch 3, batch 4550, loss[loss=0.3009, simple_loss=0.3631, pruned_loss=0.1194, over 5575.00 frames.], tot_loss[loss=0.2439, simple_loss=0.3208, pruned_loss=0.08347, over 1361425.63 frames.], batch size: 52, lr: 1.46e-03
2022-04-28 13:32:20,223 INFO [train.py:763] (3/8) Epoch 4, batch 0, loss[loss=0.2494, simple_loss=0.3301, pruned_loss=0.08433, over 7202.00 frames.], tot_loss[loss=0.2494, simple_loss=0.3301, pruned_loss=0.08433, over 7202.00 frames.], batch size: 23, lr: 1.40e-03
2022-04-28 13:33:26,506 INFO [train.py:763] (3/8) Epoch 4, batch 50, loss[loss=0.2771, simple_loss=0.3536, pruned_loss=0.1003, over 7344.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3198, pruned_loss=0.08031, over 320763.36 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:34:31,939 INFO [train.py:763] (3/8) Epoch 4, batch 100, loss[loss=0.2595, simple_loss=0.3402, pruned_loss=0.0894, over 7331.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3203, pruned_loss=0.0795, over 566612.13 frames.], batch size: 22, lr: 1.40e-03
2022-04-28 13:35:37,380 INFO [train.py:763] (3/8) Epoch 4, batch 150, loss[loss=0.2697, simple_loss=0.3442, pruned_loss=0.09763, over 4900.00 frames.], tot_loss[loss=0.24, simple_loss=0.3204, pruned_loss=0.07981, over 754758.21 frames.], batch size: 52, lr: 1.40e-03
2022-04-28 13:36:43,012 INFO [train.py:763] (3/8) Epoch 4, batch 200, loss[loss=0.2437, simple_loss=0.3185, pruned_loss=0.08443, over 7158.00 frames.], tot_loss[loss=0.2402, simple_loss=0.3202, pruned_loss=0.08012, over 903373.54 frames.], batch size: 19, lr: 1.40e-03
2022-04-28 13:37:48,979 INFO [train.py:763] (3/8) Epoch 4, batch 250, loss[loss=0.2462, simple_loss=0.3291, pruned_loss=0.08171, over 7339.00 frames.], tot_loss[loss=0.2396, simple_loss=0.3211, pruned_loss=0.07905, over 1021318.73 frames.], batch size: 22, lr: 1.39e-03
2022-04-28 13:38:55,652 INFO [train.py:763] (3/8) Epoch 4, batch 300, loss[loss=0.184, simple_loss=0.2694, pruned_loss=0.04934, over 7283.00 frames.], tot_loss[loss=0.2374, simple_loss=0.3191, pruned_loss=0.07783, over 1113029.69 frames.], batch size: 17, lr: 1.39e-03
2022-04-28 13:40:02,792 INFO [train.py:763] (3/8) Epoch 4, batch 350, loss[loss=0.217, simple_loss=0.3076, pruned_loss=0.06324, over 7162.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3172, pruned_loss=0.07724, over 1181009.37 frames.], batch size: 19, lr: 1.39e-03
2022-04-28 13:41:09,481 INFO [train.py:763] (3/8) Epoch 4, batch 400, loss[loss=0.2415, simple_loss=0.3255, pruned_loss=0.0787, over 7038.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3166, pruned_loss=0.07708, over 1232263.26 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:42:15,468 INFO [train.py:763] (3/8) Epoch 4, batch 450, loss[loss=0.2687, simple_loss=0.3363, pruned_loss=0.1005, over 7101.00 frames.], tot_loss[loss=0.2361, simple_loss=0.317, pruned_loss=0.07767, over 1274230.78 frames.], batch size: 28, lr: 1.39e-03
2022-04-28 13:43:21,271 INFO [train.py:763] (3/8) Epoch 4, batch 500, loss[loss=0.2678, simple_loss=0.3404, pruned_loss=0.09754, over 7323.00 frames.], tot_loss[loss=0.2369, simple_loss=0.3176, pruned_loss=0.07811, over 1309360.96 frames.], batch size: 21, lr: 1.39e-03
2022-04-28 13:44:28,335 INFO [train.py:763] (3/8) Epoch 4, batch 550, loss[loss=0.2697, simple_loss=0.3469, pruned_loss=0.09627, over 6674.00 frames.], tot_loss[loss=0.2363, simple_loss=0.3169, pruned_loss=0.07782, over 1333520.40 frames.], batch size: 31, lr: 1.38e-03
2022-04-28 13:45:33,790 INFO [train.py:763] (3/8) Epoch 4, batch 600, loss[loss=0.2546, simple_loss=0.3137, pruned_loss=0.0977, over 6977.00 frames.], tot_loss[loss=0.2355, simple_loss=0.3159, pruned_loss=0.07753, over 1355790.06 frames.], batch size: 16, lr: 1.38e-03
2022-04-28 13:46:39,056 INFO [train.py:763] (3/8) Epoch 4, batch 650, loss[loss=0.2152, simple_loss=0.3014, pruned_loss=0.06448, over 7322.00 frames.], tot_loss[loss=0.2354, simple_loss=0.3159, pruned_loss=0.07746, over 1370802.20 frames.], batch size: 20, lr: 1.38e-03
2022-04-28 13:47:44,004 INFO [train.py:763] (3/8) Epoch 4, batch 700, loss[loss=0.293, simple_loss=0.3784, pruned_loss=0.1038, over 7289.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3176, pruned_loss=0.07849, over 1379760.26 frames.], batch size: 25, lr: 1.38e-03
2022-04-28 13:48:49,479 INFO [train.py:763] (3/8) Epoch 4, batch 750, loss[loss=0.2146, simple_loss=0.3, pruned_loss=0.06461, over 7059.00 frames.], tot_loss[loss=0.237, simple_loss=0.3173, pruned_loss=0.07842, over 1384466.95 frames.], batch size: 18, lr: 1.38e-03
2022-04-28 13:49:55,002 INFO [train.py:763] (3/8) Epoch 4, batch 800, loss[loss=0.2543, simple_loss=0.3279, pruned_loss=0.09029, over 7058.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3151, pruned_loss=0.07731, over 1396238.00 frames.], batch size: 18, lr: 1.38e-03
2022-04-28 13:50:59,966 INFO [train.py:763] (3/8) Epoch 4, batch 850, loss[loss=0.2114, simple_loss=0.2939, pruned_loss=0.06444, over 7064.00 frames.], tot_loss[loss=0.2349, simple_loss=0.3152, pruned_loss=0.07725, over 1394678.78 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:52:05,756 INFO [train.py:763] (3/8) Epoch 4, batch 900, loss[loss=0.2988, simple_loss=0.3491, pruned_loss=0.1242, over 7309.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3151, pruned_loss=0.07757, over 1402605.66 frames.], batch size: 21, lr: 1.37e-03
2022-04-28 13:53:12,230 INFO [train.py:763] (3/8) Epoch 4, batch 950, loss[loss=0.2312, simple_loss=0.3175, pruned_loss=0.07244, over 7152.00 frames.], tot_loss[loss=0.2346, simple_loss=0.3148, pruned_loss=0.07716, over 1406805.82 frames.], batch size: 28, lr: 1.37e-03
2022-04-28 13:54:19,381 INFO [train.py:763] (3/8) Epoch 4, batch 1000, loss[loss=0.2249, simple_loss=0.3086, pruned_loss=0.07058, over 7074.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3145, pruned_loss=0.07685, over 1411488.04 frames.], batch size: 18, lr: 1.37e-03
2022-04-28 13:55:24,900 INFO [train.py:763] (3/8) Epoch 4, batch 1050, loss[loss=0.2323, simple_loss=0.3184, pruned_loss=0.07315, over 7308.00 frames.], tot_loss[loss=0.2354, simple_loss=0.316, pruned_loss=0.07736, over 1417529.33 frames.], batch size: 24, lr: 1.37e-03
2022-04-28 13:56:29,980 INFO [train.py:763] (3/8) Epoch 4, batch 1100, loss[loss=0.2287, simple_loss=0.3132, pruned_loss=0.07215, over 6207.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3165, pruned_loss=0.07762, over 1412824.29 frames.], batch size: 37, lr: 1.37e-03
2022-04-28 13:57:36,086 INFO [train.py:763] (3/8) Epoch 4, batch 1150, loss[loss=0.2748, simple_loss=0.3499, pruned_loss=0.09982, over 7429.00 frames.], tot_loss[loss=0.236, simple_loss=0.3168, pruned_loss=0.07758, over 1415389.26 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 13:58:41,143 INFO [train.py:763] (3/8) Epoch 4, batch 1200, loss[loss=0.2517, simple_loss=0.3298, pruned_loss=0.08683, over 6263.00 frames.], tot_loss[loss=0.2359, simple_loss=0.3165, pruned_loss=0.07764, over 1417696.84 frames.], batch size: 37, lr: 1.36e-03
2022-04-28 13:59:46,359 INFO [train.py:763] (3/8) Epoch 4, batch 1250, loss[loss=0.2273, simple_loss=0.3064, pruned_loss=0.07407, over 7266.00 frames.], tot_loss[loss=0.236, simple_loss=0.3166, pruned_loss=0.0777, over 1413680.34 frames.], batch size: 19, lr: 1.36e-03
2022-04-28 14:00:51,530 INFO [train.py:763] (3/8) Epoch 4, batch 1300, loss[loss=0.2328, simple_loss=0.3105, pruned_loss=0.07752, over 7322.00 frames.], tot_loss[loss=0.2364, simple_loss=0.3173, pruned_loss=0.07776, over 1416933.30 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:01:57,422 INFO [train.py:763] (3/8) Epoch 4, batch 1350, loss[loss=0.2047, simple_loss=0.2863, pruned_loss=0.0615, over 7134.00 frames.], tot_loss[loss=0.2362, simple_loss=0.3173, pruned_loss=0.07755, over 1423181.70 frames.], batch size: 17, lr: 1.36e-03
2022-04-28 14:03:02,793 INFO [train.py:763] (3/8) Epoch 4, batch 1400, loss[loss=0.1828, simple_loss=0.2769, pruned_loss=0.04435, over 7235.00 frames.], tot_loss[loss=0.2373, simple_loss=0.3186, pruned_loss=0.07802, over 1419370.61 frames.], batch size: 20, lr: 1.36e-03
2022-04-28 14:04:07,963 INFO [train.py:763] (3/8) Epoch 4, batch 1450, loss[loss=0.2244, simple_loss=0.2922, pruned_loss=0.07832, over 7002.00 frames.], tot_loss[loss=0.237, simple_loss=0.3186, pruned_loss=0.07765, over 1419477.08 frames.], batch size: 16, lr: 1.35e-03
2022-04-28 14:05:14,090 INFO [train.py:763] (3/8) Epoch 4, batch 1500, loss[loss=0.2197, simple_loss=0.3078, pruned_loss=0.06577, over 7327.00 frames.], tot_loss[loss=0.2353, simple_loss=0.317, pruned_loss=0.07678, over 1423123.28 frames.], batch size: 20, lr: 1.35e-03
2022-04-28 14:06:19,705 INFO [train.py:763] (3/8) Epoch 4, batch 1550, loss[loss=0.2365, simple_loss=0.3336, pruned_loss=0.06966, over 7390.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3153, pruned_loss=0.07607, over 1425196.25 frames.], batch size: 23, lr: 1.35e-03
2022-04-28 14:07:24,977 INFO [train.py:763] (3/8) Epoch 4, batch 1600, loss[loss=0.2387, simple_loss=0.3308, pruned_loss=0.07324, over 7293.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3158, pruned_loss=0.07621, over 1424451.46 frames.], batch size: 25, lr: 1.35e-03
2022-04-28 14:08:30,204 INFO [train.py:763] (3/8) Epoch 4, batch 1650, loss[loss=0.2481, simple_loss=0.34, pruned_loss=0.07813, over 7100.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3162, pruned_loss=0.07597, over 1422762.79 frames.], batch size: 21, lr: 1.35e-03
2022-04-28 14:09:35,799 INFO [train.py:763] (3/8) Epoch 4, batch 1700, loss[loss=0.2647, simple_loss=0.3562, pruned_loss=0.08661, over 7340.00 frames.], tot_loss[loss=0.2337, simple_loss=0.3159, pruned_loss=0.07576, over 1424899.92 frames.], batch size: 22, lr: 1.35e-03
2022-04-28 14:10:42,772 INFO [train.py:763] (3/8) Epoch 4, batch 1750, loss[loss=0.2582, simple_loss=0.3401, pruned_loss=0.08818, over 7293.00 frames.], tot_loss[loss=0.2334, simple_loss=0.3153, pruned_loss=0.07574, over 1424133.03 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:11:49,092 INFO [train.py:763] (3/8) Epoch 4, batch 1800, loss[loss=0.2258, simple_loss=0.3124, pruned_loss=0.06957, over 7321.00 frames.], tot_loss[loss=0.2326, simple_loss=0.3148, pruned_loss=0.07521, over 1426573.99 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:12:54,649 INFO [train.py:763] (3/8) Epoch 4, batch 1850, loss[loss=0.2667, simple_loss=0.3525, pruned_loss=0.0904, over 6295.00 frames.], tot_loss[loss=0.2348, simple_loss=0.3165, pruned_loss=0.0766, over 1426523.74 frames.], batch size: 37, lr: 1.34e-03
2022-04-28 14:13:59,950 INFO [train.py:763] (3/8) Epoch 4, batch 1900, loss[loss=0.2082, simple_loss=0.301, pruned_loss=0.05769, over 7115.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3162, pruned_loss=0.07625, over 1427918.60 frames.], batch size: 21, lr: 1.34e-03
2022-04-28 14:15:05,361 INFO [train.py:763] (3/8) Epoch 4, batch 1950, loss[loss=0.2237, simple_loss=0.3002, pruned_loss=0.07361, over 7162.00 frames.], tot_loss[loss=0.233, simple_loss=0.3151, pruned_loss=0.07542, over 1428612.73 frames.], batch size: 18, lr: 1.34e-03
2022-04-28 14:16:10,982 INFO [train.py:763] (3/8) Epoch 4, batch 2000, loss[loss=0.2463, simple_loss=0.3405, pruned_loss=0.07608, over 7305.00 frames.], tot_loss[loss=0.2332, simple_loss=0.3154, pruned_loss=0.07546, over 1426267.34 frames.], batch size: 25, lr: 1.34e-03
2022-04-28 14:17:16,769 INFO [train.py:763] (3/8) Epoch 4, batch 2050, loss[loss=0.2417, simple_loss=0.3229, pruned_loss=0.08021, over 7286.00 frames.], tot_loss[loss=0.2319, simple_loss=0.314, pruned_loss=0.07487, over 1430699.38 frames.], batch size: 24, lr: 1.34e-03
2022-04-28 14:18:22,258 INFO [train.py:763] (3/8) Epoch 4, batch 2100, loss[loss=0.2116, simple_loss=0.2908, pruned_loss=0.06616, over 7395.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3137, pruned_loss=0.07492, over 1433763.38 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:19:27,835 INFO [train.py:763] (3/8) Epoch 4, batch 2150, loss[loss=0.2141, simple_loss=0.3005, pruned_loss=0.06386, over 7070.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3148, pruned_loss=0.07536, over 1432502.62 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:20:34,206 INFO [train.py:763] (3/8) Epoch 4, batch 2200, loss[loss=0.2312, simple_loss=0.3267, pruned_loss=0.06789, over 7334.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3141, pruned_loss=0.07518, over 1434485.99 frames.], batch size: 22, lr: 1.33e-03
2022-04-28 14:21:39,758 INFO [train.py:763] (3/8) Epoch 4, batch 2250, loss[loss=0.236, simple_loss=0.3394, pruned_loss=0.06634, over 7374.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3143, pruned_loss=0.07555, over 1432252.86 frames.], batch size: 23, lr: 1.33e-03
2022-04-28 14:22:45,297 INFO [train.py:763] (3/8) Epoch 4, batch 2300, loss[loss=0.1996, simple_loss=0.2679, pruned_loss=0.06562, over 7282.00 frames.], tot_loss[loss=0.2341, simple_loss=0.3155, pruned_loss=0.07639, over 1430686.53 frames.], batch size: 17, lr: 1.33e-03
2022-04-28 14:23:50,801 INFO [train.py:763] (3/8) Epoch 4, batch 2350, loss[loss=0.216, simple_loss=0.2932, pruned_loss=0.06941, over 7417.00 frames.], tot_loss[loss=0.2351, simple_loss=0.3165, pruned_loss=0.07686, over 1434125.76 frames.], batch size: 18, lr: 1.33e-03
2022-04-28 14:24:56,453 INFO [train.py:763] (3/8) Epoch 4, batch 2400, loss[loss=0.2202, simple_loss=0.2987, pruned_loss=0.07087, over 7213.00 frames.], tot_loss[loss=0.2347, simple_loss=0.3159, pruned_loss=0.07678, over 1435757.90 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:26:01,946 INFO [train.py:763] (3/8) Epoch 4, batch 2450, loss[loss=0.2148, simple_loss=0.294, pruned_loss=0.06775, over 7277.00 frames.], tot_loss[loss=0.2342, simple_loss=0.3158, pruned_loss=0.07633, over 1434908.74 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:27:09,067 INFO [train.py:763] (3/8) Epoch 4, batch 2500, loss[loss=0.2693, simple_loss=0.3618, pruned_loss=0.0884, over 7216.00 frames.], tot_loss[loss=0.2345, simple_loss=0.3156, pruned_loss=0.07667, over 1432697.29 frames.], batch size: 22, lr: 1.32e-03
2022-04-28 14:28:14,996 INFO [train.py:763] (3/8) Epoch 4, batch 2550, loss[loss=0.2365, simple_loss=0.3269, pruned_loss=0.07304, over 7143.00 frames.], tot_loss[loss=0.234, simple_loss=0.3153, pruned_loss=0.07642, over 1433546.34 frames.], batch size: 20, lr: 1.32e-03
2022-04-28 14:29:20,317 INFO [train.py:763] (3/8) Epoch 4, batch 2600, loss[loss=0.2816, simple_loss=0.3496, pruned_loss=0.1068, over 7314.00 frames.], tot_loss[loss=0.2343, simple_loss=0.3157, pruned_loss=0.07641, over 1431974.10 frames.], batch size: 21, lr: 1.32e-03
2022-04-28 14:30:26,096 INFO [train.py:763] (3/8) Epoch 4, batch 2650, loss[loss=0.2173, simple_loss=0.2886, pruned_loss=0.073, over 6989.00 frames.], tot_loss[loss=0.2339, simple_loss=0.3157, pruned_loss=0.07608, over 1430318.68 frames.], batch size: 16, lr: 1.32e-03
2022-04-28 14:31:31,705 INFO [train.py:763] (3/8) Epoch 4, batch 2700, loss[loss=0.2109, simple_loss=0.2863, pruned_loss=0.06776, over 7271.00 frames.], tot_loss[loss=0.2325, simple_loss=0.3146, pruned_loss=0.07516, over 1431837.26 frames.], batch size: 18, lr: 1.32e-03
2022-04-28 14:32:38,236 INFO [train.py:763] (3/8) Epoch 4, batch 2750, loss[loss=0.2039, simple_loss=0.2835, pruned_loss=0.06214, over 7354.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3139, pruned_loss=0.0749, over 1432838.68 frames.], batch size: 19, lr: 1.31e-03
2022-04-28 14:33:43,918 INFO [train.py:763] (3/8) Epoch 4, batch 2800, loss[loss=0.1994, simple_loss=0.2841, pruned_loss=0.05734, over 7146.00 frames.], tot_loss[loss=0.2306, simple_loss=0.3131, pruned_loss=0.07406, over 1433560.90 frames.], batch size: 17, lr: 1.31e-03
2022-04-28 14:34:49,325 INFO [train.py:763] (3/8) Epoch 4, batch 2850, loss[loss=0.2315, simple_loss=0.3165, pruned_loss=0.07322, over 6708.00 frames.], tot_loss[loss=0.23, simple_loss=0.3128, pruned_loss=0.07364, over 1430282.89 frames.], batch size: 31, lr: 1.31e-03
2022-04-28 14:35:55,985 INFO [train.py:763] (3/8) Epoch 4, batch 2900, loss[loss=0.2456, simple_loss=0.3222, pruned_loss=0.08451, over 7276.00 frames.], tot_loss[loss=0.2301, simple_loss=0.3129, pruned_loss=0.07368, over 1428955.02 frames.], batch size: 24, lr: 1.31e-03
2022-04-28 14:37:01,945 INFO [train.py:763] (3/8) Epoch 4, batch 2950, loss[loss=0.2145, simple_loss=0.3076, pruned_loss=0.06065, over 7349.00 frames.], tot_loss[loss=0.2288, simple_loss=0.3118, pruned_loss=0.07293, over 1429569.13 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:38:07,793 INFO [train.py:763] (3/8) Epoch 4, batch 3000, loss[loss=0.2256, simple_loss=0.3164, pruned_loss=0.06737, over 7182.00 frames.], tot_loss[loss=0.2295, simple_loss=0.3122, pruned_loss=0.07339, over 1425911.86 frames.], batch size: 26, lr: 1.31e-03
2022-04-28 14:38:07,793 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 14:38:23,246 INFO [train.py:792] (3/8) 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] (3/8) Epoch 4, batch 3050, loss[loss=0.2387, simple_loss=0.3288, pruned_loss=0.07433, over 7208.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3123, pruned_loss=0.0731, over 1430024.83 frames.], batch size: 22, lr: 1.31e-03
2022-04-28 14:40:34,110 INFO [train.py:763] (3/8) Epoch 4, batch 3100, loss[loss=0.2086, simple_loss=0.3114, pruned_loss=0.05287, over 7238.00 frames.], tot_loss[loss=0.2296, simple_loss=0.3126, pruned_loss=0.07336, over 1428603.28 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:41:39,918 INFO [train.py:763] (3/8) Epoch 4, batch 3150, loss[loss=0.2229, simple_loss=0.3222, pruned_loss=0.06177, over 7311.00 frames.], tot_loss[loss=0.2297, simple_loss=0.313, pruned_loss=0.07324, over 1429274.32 frames.], batch size: 25, lr: 1.30e-03
2022-04-28 14:42:46,506 INFO [train.py:763] (3/8) Epoch 4, batch 3200, loss[loss=0.1798, simple_loss=0.2714, pruned_loss=0.04405, over 7355.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3128, pruned_loss=0.07296, over 1430274.99 frames.], batch size: 19, lr: 1.30e-03
2022-04-28 14:43:52,376 INFO [train.py:763] (3/8) Epoch 4, batch 3250, loss[loss=0.2014, simple_loss=0.2805, pruned_loss=0.06116, over 7165.00 frames.], tot_loss[loss=0.2283, simple_loss=0.3112, pruned_loss=0.07266, over 1427641.99 frames.], batch size: 18, lr: 1.30e-03
2022-04-28 14:44:57,965 INFO [train.py:763] (3/8) Epoch 4, batch 3300, loss[loss=0.2139, simple_loss=0.3124, pruned_loss=0.05772, over 7172.00 frames.], tot_loss[loss=0.2303, simple_loss=0.3129, pruned_loss=0.07383, over 1422864.29 frames.], batch size: 26, lr: 1.30e-03
2022-04-28 14:46:03,553 INFO [train.py:763] (3/8) Epoch 4, batch 3350, loss[loss=0.3125, simple_loss=0.3662, pruned_loss=0.1294, over 7111.00 frames.], tot_loss[loss=0.2305, simple_loss=0.3131, pruned_loss=0.0739, over 1425610.99 frames.], batch size: 21, lr: 1.30e-03
2022-04-28 14:47:08,814 INFO [train.py:763] (3/8) Epoch 4, batch 3400, loss[loss=0.2124, simple_loss=0.3026, pruned_loss=0.06111, over 7227.00 frames.], tot_loss[loss=0.232, simple_loss=0.3146, pruned_loss=0.07466, over 1427632.91 frames.], batch size: 20, lr: 1.30e-03
2022-04-28 14:48:14,157 INFO [train.py:763] (3/8) Epoch 4, batch 3450, loss[loss=0.2539, simple_loss=0.3361, pruned_loss=0.08583, over 7212.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3134, pruned_loss=0.07423, over 1427761.10 frames.], batch size: 23, lr: 1.29e-03
2022-04-28 14:49:37,445 INFO [train.py:763] (3/8) Epoch 4, batch 3500, loss[loss=0.2659, simple_loss=0.3343, pruned_loss=0.09875, over 7322.00 frames.], tot_loss[loss=0.2317, simple_loss=0.3142, pruned_loss=0.07455, over 1430406.49 frames.], batch size: 20, lr: 1.29e-03
2022-04-28 14:50:52,144 INFO [train.py:763] (3/8) Epoch 4, batch 3550, loss[loss=0.2293, simple_loss=0.3191, pruned_loss=0.06981, over 7408.00 frames.], tot_loss[loss=0.2316, simple_loss=0.3142, pruned_loss=0.07445, over 1425156.27 frames.], batch size: 21, lr: 1.29e-03
2022-04-28 14:51:57,840 INFO [train.py:763] (3/8) Epoch 4, batch 3600, loss[loss=0.1907, simple_loss=0.2791, pruned_loss=0.05111, over 7258.00 frames.], tot_loss[loss=0.2312, simple_loss=0.3131, pruned_loss=0.07459, over 1420663.90 frames.], batch size: 19, lr: 1.29e-03
2022-04-28 14:53:23,230 INFO [train.py:763] (3/8) Epoch 4, batch 3650, loss[loss=0.2173, simple_loss=0.306, pruned_loss=0.06429, over 6692.00 frames.], tot_loss[loss=0.2333, simple_loss=0.3155, pruned_loss=0.07551, over 1415372.73 frames.], batch size: 31, lr: 1.29e-03
2022-04-28 14:54:39,016 INFO [train.py:763] (3/8) Epoch 4, batch 3700, loss[loss=0.2385, simple_loss=0.3183, pruned_loss=0.07939, over 7169.00 frames.], tot_loss[loss=0.2318, simple_loss=0.3137, pruned_loss=0.07496, over 1420419.42 frames.], batch size: 18, lr: 1.29e-03
2022-04-28 14:55:53,480 INFO [train.py:763] (3/8) Epoch 4, batch 3750, loss[loss=0.1699, simple_loss=0.255, pruned_loss=0.04235, over 6817.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3151, pruned_loss=0.07524, over 1420678.15 frames.], batch size: 15, lr: 1.29e-03
2022-04-28 14:56:59,177 INFO [train.py:763] (3/8) Epoch 4, batch 3800, loss[loss=0.1923, simple_loss=0.2793, pruned_loss=0.05265, over 7281.00 frames.], tot_loss[loss=0.2322, simple_loss=0.315, pruned_loss=0.07475, over 1422210.29 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 14:58:05,503 INFO [train.py:763] (3/8) Epoch 4, batch 3850, loss[loss=0.2945, simple_loss=0.3759, pruned_loss=0.1066, over 7416.00 frames.], tot_loss[loss=0.232, simple_loss=0.3146, pruned_loss=0.07469, over 1421653.53 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 14:59:11,127 INFO [train.py:763] (3/8) Epoch 4, batch 3900, loss[loss=0.236, simple_loss=0.3256, pruned_loss=0.07324, over 7179.00 frames.], tot_loss[loss=0.2311, simple_loss=0.3138, pruned_loss=0.07422, over 1418361.02 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:00:16,491 INFO [train.py:763] (3/8) Epoch 4, batch 3950, loss[loss=0.2672, simple_loss=0.3498, pruned_loss=0.09227, over 7410.00 frames.], tot_loss[loss=0.2311, simple_loss=0.314, pruned_loss=0.07407, over 1415305.96 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:01:21,848 INFO [train.py:763] (3/8) Epoch 4, batch 4000, loss[loss=0.237, simple_loss=0.3254, pruned_loss=0.0743, over 7434.00 frames.], tot_loss[loss=0.2298, simple_loss=0.3134, pruned_loss=0.07303, over 1418016.13 frames.], batch size: 20, lr: 1.28e-03
2022-04-28 15:02:27,495 INFO [train.py:763] (3/8) Epoch 4, batch 4050, loss[loss=0.2609, simple_loss=0.3562, pruned_loss=0.08278, over 7206.00 frames.], tot_loss[loss=0.2302, simple_loss=0.3136, pruned_loss=0.07342, over 1420934.69 frames.], batch size: 21, lr: 1.28e-03
2022-04-28 15:03:34,095 INFO [train.py:763] (3/8) Epoch 4, batch 4100, loss[loss=0.2214, simple_loss=0.2985, pruned_loss=0.07211, over 7278.00 frames.], tot_loss[loss=0.2322, simple_loss=0.3158, pruned_loss=0.07435, over 1417595.15 frames.], batch size: 18, lr: 1.28e-03
2022-04-28 15:04:40,946 INFO [train.py:763] (3/8) Epoch 4, batch 4150, loss[loss=0.2229, simple_loss=0.3146, pruned_loss=0.06557, over 7199.00 frames.], tot_loss[loss=0.2324, simple_loss=0.3157, pruned_loss=0.0746, over 1415733.36 frames.], batch size: 22, lr: 1.27e-03
2022-04-28 15:05:47,254 INFO [train.py:763] (3/8) Epoch 4, batch 4200, loss[loss=0.2199, simple_loss=0.3002, pruned_loss=0.06985, over 7121.00 frames.], tot_loss[loss=0.232, simple_loss=0.3149, pruned_loss=0.07458, over 1413812.16 frames.], batch size: 17, lr: 1.27e-03
2022-04-28 15:06:53,140 INFO [train.py:763] (3/8) Epoch 4, batch 4250, loss[loss=0.1894, simple_loss=0.2738, pruned_loss=0.05254, over 7074.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3151, pruned_loss=0.07521, over 1415145.95 frames.], batch size: 18, lr: 1.27e-03
2022-04-28 15:07:59,469 INFO [train.py:763] (3/8) Epoch 4, batch 4300, loss[loss=0.2299, simple_loss=0.3167, pruned_loss=0.07156, over 7135.00 frames.], tot_loss[loss=0.2336, simple_loss=0.316, pruned_loss=0.07556, over 1415383.28 frames.], batch size: 20, lr: 1.27e-03
2022-04-28 15:09:04,573 INFO [train.py:763] (3/8) Epoch 4, batch 4350, loss[loss=0.2142, simple_loss=0.2973, pruned_loss=0.06556, over 7403.00 frames.], tot_loss[loss=0.2328, simple_loss=0.3157, pruned_loss=0.07497, over 1414077.70 frames.], batch size: 21, lr: 1.27e-03
2022-04-28 15:10:09,733 INFO [train.py:763] (3/8) Epoch 4, batch 4400, loss[loss=0.2333, simple_loss=0.3069, pruned_loss=0.07987, over 7254.00 frames.], tot_loss[loss=0.2318, simple_loss=0.315, pruned_loss=0.07433, over 1410838.88 frames.], batch size: 19, lr: 1.27e-03
2022-04-28 15:11:14,749 INFO [train.py:763] (3/8) Epoch 4, batch 4450, loss[loss=0.2389, simple_loss=0.3242, pruned_loss=0.07686, over 6688.00 frames.], tot_loss[loss=0.2327, simple_loss=0.3155, pruned_loss=0.07497, over 1404177.00 frames.], batch size: 31, lr: 1.27e-03
2022-04-28 15:12:19,723 INFO [train.py:763] (3/8) Epoch 4, batch 4500, loss[loss=0.2651, simple_loss=0.337, pruned_loss=0.09663, over 5192.00 frames.], tot_loss[loss=0.235, simple_loss=0.3176, pruned_loss=0.07621, over 1395423.54 frames.], batch size: 52, lr: 1.27e-03
2022-04-28 15:13:25,331 INFO [train.py:763] (3/8) Epoch 4, batch 4550, loss[loss=0.3101, simple_loss=0.3715, pruned_loss=0.1244, over 4867.00 frames.], tot_loss[loss=0.2392, simple_loss=0.3203, pruned_loss=0.07902, over 1342688.04 frames.], batch size: 53, lr: 1.26e-03
2022-04-28 15:14:53,626 INFO [train.py:763] (3/8) Epoch 5, batch 0, loss[loss=0.2496, simple_loss=0.3136, pruned_loss=0.09284, over 7159.00 frames.], tot_loss[loss=0.2496, simple_loss=0.3136, pruned_loss=0.09284, over 7159.00 frames.], batch size: 19, lr: 1.21e-03
2022-04-28 15:15:59,876 INFO [train.py:763] (3/8) Epoch 5, batch 50, loss[loss=0.2691, simple_loss=0.3385, pruned_loss=0.0998, over 5390.00 frames.], tot_loss[loss=0.2309, simple_loss=0.3109, pruned_loss=0.0754, over 319409.40 frames.], batch size: 52, lr: 1.21e-03
2022-04-28 15:17:05,483 INFO [train.py:763] (3/8) Epoch 5, batch 100, loss[loss=0.2015, simple_loss=0.3049, pruned_loss=0.04903, over 7142.00 frames.], tot_loss[loss=0.2297, simple_loss=0.3132, pruned_loss=0.07307, over 562526.84 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:18:11,202 INFO [train.py:763] (3/8) Epoch 5, batch 150, loss[loss=0.239, simple_loss=0.3184, pruned_loss=0.07974, over 6830.00 frames.], tot_loss[loss=0.2293, simple_loss=0.3129, pruned_loss=0.0728, over 750142.26 frames.], batch size: 31, lr: 1.21e-03
2022-04-28 15:19:17,537 INFO [train.py:763] (3/8) Epoch 5, batch 200, loss[loss=0.2177, simple_loss=0.3059, pruned_loss=0.06478, over 7410.00 frames.], tot_loss[loss=0.228, simple_loss=0.3124, pruned_loss=0.07185, over 899810.20 frames.], batch size: 18, lr: 1.21e-03
2022-04-28 15:20:23,013 INFO [train.py:763] (3/8) Epoch 5, batch 250, loss[loss=0.2512, simple_loss=0.331, pruned_loss=0.08574, over 7334.00 frames.], tot_loss[loss=0.2281, simple_loss=0.3129, pruned_loss=0.07171, over 1020056.72 frames.], batch size: 22, lr: 1.21e-03
2022-04-28 15:21:29,012 INFO [train.py:763] (3/8) Epoch 5, batch 300, loss[loss=0.1851, simple_loss=0.2809, pruned_loss=0.04464, over 7252.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3098, pruned_loss=0.07038, over 1112626.94 frames.], batch size: 20, lr: 1.21e-03
2022-04-28 15:22:35,196 INFO [train.py:763] (3/8) Epoch 5, batch 350, loss[loss=0.2365, simple_loss=0.3067, pruned_loss=0.08314, over 7330.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3074, pruned_loss=0.06939, over 1185944.42 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:23:40,934 INFO [train.py:763] (3/8) Epoch 5, batch 400, loss[loss=0.2259, simple_loss=0.3206, pruned_loss=0.06561, over 7384.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3096, pruned_loss=0.07027, over 1237075.85 frames.], batch size: 23, lr: 1.20e-03
2022-04-28 15:24:46,896 INFO [train.py:763] (3/8) Epoch 5, batch 450, loss[loss=0.1852, simple_loss=0.27, pruned_loss=0.05019, over 6742.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3093, pruned_loss=0.07008, over 1279493.64 frames.], batch size: 15, lr: 1.20e-03
2022-04-28 15:25:52,437 INFO [train.py:763] (3/8) Epoch 5, batch 500, loss[loss=0.2938, simple_loss=0.3559, pruned_loss=0.1159, over 4926.00 frames.], tot_loss[loss=0.2257, simple_loss=0.3106, pruned_loss=0.07037, over 1308574.49 frames.], batch size: 52, lr: 1.20e-03
2022-04-28 15:26:57,642 INFO [train.py:763] (3/8) Epoch 5, batch 550, loss[loss=0.2388, simple_loss=0.3324, pruned_loss=0.07262, over 6467.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3102, pruned_loss=0.06982, over 1332343.54 frames.], batch size: 38, lr: 1.20e-03
2022-04-28 15:28:04,518 INFO [train.py:763] (3/8) Epoch 5, batch 600, loss[loss=0.2245, simple_loss=0.3141, pruned_loss=0.06744, over 7140.00 frames.], tot_loss[loss=0.2243, simple_loss=0.3095, pruned_loss=0.06959, over 1352268.64 frames.], batch size: 20, lr: 1.20e-03
2022-04-28 15:29:09,667 INFO [train.py:763] (3/8) Epoch 5, batch 650, loss[loss=0.2562, simple_loss=0.3364, pruned_loss=0.08798, over 7416.00 frames.], tot_loss[loss=0.2239, simple_loss=0.3092, pruned_loss=0.06925, over 1366798.17 frames.], batch size: 21, lr: 1.20e-03
2022-04-28 15:30:15,010 INFO [train.py:763] (3/8) Epoch 5, batch 700, loss[loss=0.1995, simple_loss=0.2825, pruned_loss=0.05828, over 7244.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3099, pruned_loss=0.06957, over 1378845.37 frames.], batch size: 16, lr: 1.20e-03
2022-04-28 15:31:20,299 INFO [train.py:763] (3/8) Epoch 5, batch 750, loss[loss=0.2686, simple_loss=0.3445, pruned_loss=0.09631, over 7218.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3116, pruned_loss=0.07049, over 1388515.61 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:32:25,891 INFO [train.py:763] (3/8) Epoch 5, batch 800, loss[loss=0.2265, simple_loss=0.3105, pruned_loss=0.07125, over 7219.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3111, pruned_loss=0.06986, over 1398875.18 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:33:31,213 INFO [train.py:763] (3/8) Epoch 5, batch 850, loss[loss=0.23, simple_loss=0.3136, pruned_loss=0.07324, over 7183.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3102, pruned_loss=0.06974, over 1403858.90 frames.], batch size: 23, lr: 1.19e-03
2022-04-28 15:34:36,542 INFO [train.py:763] (3/8) Epoch 5, batch 900, loss[loss=0.2009, simple_loss=0.2924, pruned_loss=0.05471, over 7404.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3105, pruned_loss=0.07013, over 1405419.46 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:35:42,334 INFO [train.py:763] (3/8) Epoch 5, batch 950, loss[loss=0.2024, simple_loss=0.2783, pruned_loss=0.06322, over 7123.00 frames.], tot_loss[loss=0.2253, simple_loss=0.3103, pruned_loss=0.07015, over 1406418.79 frames.], batch size: 17, lr: 1.19e-03
2022-04-28 15:36:47,761 INFO [train.py:763] (3/8) Epoch 5, batch 1000, loss[loss=0.2073, simple_loss=0.3024, pruned_loss=0.05612, over 7419.00 frames.], tot_loss[loss=0.2256, simple_loss=0.3107, pruned_loss=0.07022, over 1408060.91 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:37:53,890 INFO [train.py:763] (3/8) Epoch 5, batch 1050, loss[loss=0.2394, simple_loss=0.3228, pruned_loss=0.07802, over 7327.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3101, pruned_loss=0.07007, over 1413052.16 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:39:10,231 INFO [train.py:763] (3/8) Epoch 5, batch 1100, loss[loss=0.2145, simple_loss=0.3016, pruned_loss=0.06373, over 7314.00 frames.], tot_loss[loss=0.2267, simple_loss=0.3114, pruned_loss=0.07102, over 1408623.15 frames.], batch size: 21, lr: 1.19e-03
2022-04-28 15:40:16,762 INFO [train.py:763] (3/8) Epoch 5, batch 1150, loss[loss=0.2561, simple_loss=0.3342, pruned_loss=0.08901, over 7147.00 frames.], tot_loss[loss=0.2261, simple_loss=0.3113, pruned_loss=0.07047, over 1413686.10 frames.], batch size: 20, lr: 1.19e-03
2022-04-28 15:41:22,501 INFO [train.py:763] (3/8) Epoch 5, batch 1200, loss[loss=0.2643, simple_loss=0.3387, pruned_loss=0.09498, over 7193.00 frames.], tot_loss[loss=0.2259, simple_loss=0.3108, pruned_loss=0.07047, over 1414486.52 frames.], batch size: 26, lr: 1.18e-03
2022-04-28 15:42:28,993 INFO [train.py:763] (3/8) Epoch 5, batch 1250, loss[loss=0.22, simple_loss=0.3125, pruned_loss=0.06379, over 7145.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3103, pruned_loss=0.07026, over 1413785.46 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:43:35,958 INFO [train.py:763] (3/8) Epoch 5, batch 1300, loss[loss=0.171, simple_loss=0.2657, pruned_loss=0.03815, over 7361.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3101, pruned_loss=0.0704, over 1412468.20 frames.], batch size: 19, lr: 1.18e-03
2022-04-28 15:44:42,293 INFO [train.py:763] (3/8) Epoch 5, batch 1350, loss[loss=0.2455, simple_loss=0.3281, pruned_loss=0.08149, over 7105.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3099, pruned_loss=0.07087, over 1415747.34 frames.], batch size: 28, lr: 1.18e-03
2022-04-28 15:45:48,504 INFO [train.py:763] (3/8) Epoch 5, batch 1400, loss[loss=0.2207, simple_loss=0.3096, pruned_loss=0.06587, over 7342.00 frames.], tot_loss[loss=0.2254, simple_loss=0.3099, pruned_loss=0.07046, over 1419902.31 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:46:53,764 INFO [train.py:763] (3/8) Epoch 5, batch 1450, loss[loss=0.2215, simple_loss=0.309, pruned_loss=0.06699, over 7427.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3097, pruned_loss=0.0701, over 1420771.79 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:47:59,048 INFO [train.py:763] (3/8) Epoch 5, batch 1500, loss[loss=0.2205, simple_loss=0.3226, pruned_loss=0.05923, over 7144.00 frames.], tot_loss[loss=0.2258, simple_loss=0.3102, pruned_loss=0.07069, over 1422079.09 frames.], batch size: 20, lr: 1.18e-03
2022-04-28 15:49:04,608 INFO [train.py:763] (3/8) Epoch 5, batch 1550, loss[loss=0.189, simple_loss=0.2762, pruned_loss=0.05089, over 7284.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3097, pruned_loss=0.07008, over 1423644.38 frames.], batch size: 17, lr: 1.18e-03
2022-04-28 15:50:09,899 INFO [train.py:763] (3/8) Epoch 5, batch 1600, loss[loss=0.2479, simple_loss=0.315, pruned_loss=0.09042, over 7418.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3094, pruned_loss=0.07026, over 1416123.84 frames.], batch size: 20, lr: 1.17e-03
2022-04-28 15:51:15,387 INFO [train.py:763] (3/8) Epoch 5, batch 1650, loss[loss=0.239, simple_loss=0.3376, pruned_loss=0.07017, over 7295.00 frames.], tot_loss[loss=0.2245, simple_loss=0.3089, pruned_loss=0.07009, over 1415498.06 frames.], batch size: 25, lr: 1.17e-03
2022-04-28 15:52:21,475 INFO [train.py:763] (3/8) Epoch 5, batch 1700, loss[loss=0.2462, simple_loss=0.3355, pruned_loss=0.0784, over 7209.00 frames.], tot_loss[loss=0.2249, simple_loss=0.3091, pruned_loss=0.07029, over 1412836.38 frames.], batch size: 22, lr: 1.17e-03
2022-04-28 15:53:26,972 INFO [train.py:763] (3/8) Epoch 5, batch 1750, loss[loss=0.2186, simple_loss=0.2907, pruned_loss=0.07327, over 7263.00 frames.], tot_loss[loss=0.2259, simple_loss=0.31, pruned_loss=0.07094, over 1409557.81 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:54:32,246 INFO [train.py:763] (3/8) Epoch 5, batch 1800, loss[loss=0.3161, simple_loss=0.3596, pruned_loss=0.1363, over 5229.00 frames.], tot_loss[loss=0.2262, simple_loss=0.3103, pruned_loss=0.07102, over 1411476.35 frames.], batch size: 53, lr: 1.17e-03
2022-04-28 15:55:37,884 INFO [train.py:763] (3/8) Epoch 5, batch 1850, loss[loss=0.2294, simple_loss=0.3024, pruned_loss=0.07817, over 7152.00 frames.], tot_loss[loss=0.2263, simple_loss=0.3102, pruned_loss=0.07122, over 1415392.22 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:56:43,238 INFO [train.py:763] (3/8) Epoch 5, batch 1900, loss[loss=0.2138, simple_loss=0.2889, pruned_loss=0.06934, over 7135.00 frames.], tot_loss[loss=0.2252, simple_loss=0.3095, pruned_loss=0.07041, over 1414380.01 frames.], batch size: 17, lr: 1.17e-03
2022-04-28 15:57:48,604 INFO [train.py:763] (3/8) Epoch 5, batch 1950, loss[loss=0.1921, simple_loss=0.2902, pruned_loss=0.04701, over 7116.00 frames.], tot_loss[loss=0.224, simple_loss=0.3093, pruned_loss=0.06939, over 1419652.80 frames.], batch size: 21, lr: 1.17e-03
2022-04-28 15:58:54,742 INFO [train.py:763] (3/8) Epoch 5, batch 2000, loss[loss=0.2165, simple_loss=0.2873, pruned_loss=0.07282, over 7257.00 frames.], tot_loss[loss=0.2251, simple_loss=0.3097, pruned_loss=0.07025, over 1423275.66 frames.], batch size: 18, lr: 1.17e-03
2022-04-28 15:59:59,953 INFO [train.py:763] (3/8) Epoch 5, batch 2050, loss[loss=0.2274, simple_loss=0.3186, pruned_loss=0.0681, over 7100.00 frames.], tot_loss[loss=0.2247, simple_loss=0.3099, pruned_loss=0.06978, over 1423104.14 frames.], batch size: 28, lr: 1.16e-03
2022-04-28 16:01:06,584 INFO [train.py:763] (3/8) Epoch 5, batch 2100, loss[loss=0.238, simple_loss=0.3231, pruned_loss=0.07647, over 6504.00 frames.], tot_loss[loss=0.2244, simple_loss=0.3097, pruned_loss=0.06953, over 1424751.19 frames.], batch size: 37, lr: 1.16e-03
2022-04-28 16:02:12,117 INFO [train.py:763] (3/8) Epoch 5, batch 2150, loss[loss=0.23, simple_loss=0.318, pruned_loss=0.07099, over 7144.00 frames.], tot_loss[loss=0.2238, simple_loss=0.3091, pruned_loss=0.06923, over 1429939.60 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:03:17,457 INFO [train.py:763] (3/8) Epoch 5, batch 2200, loss[loss=0.2724, simple_loss=0.3567, pruned_loss=0.0941, over 7141.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3092, pruned_loss=0.06901, over 1426532.41 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:04:22,913 INFO [train.py:763] (3/8) Epoch 5, batch 2250, loss[loss=0.2232, simple_loss=0.3065, pruned_loss=0.06991, over 7352.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3085, pruned_loss=0.06884, over 1424673.71 frames.], batch size: 19, lr: 1.16e-03
2022-04-28 16:05:29,057 INFO [train.py:763] (3/8) Epoch 5, batch 2300, loss[loss=0.2105, simple_loss=0.2948, pruned_loss=0.06315, over 7304.00 frames.], tot_loss[loss=0.2242, simple_loss=0.3091, pruned_loss=0.06962, over 1421730.37 frames.], batch size: 24, lr: 1.16e-03
2022-04-28 16:06:35,242 INFO [train.py:763] (3/8) Epoch 5, batch 2350, loss[loss=0.2403, simple_loss=0.3365, pruned_loss=0.07208, over 7214.00 frames.], tot_loss[loss=0.2232, simple_loss=0.3082, pruned_loss=0.06915, over 1421508.20 frames.], batch size: 21, lr: 1.16e-03
2022-04-28 16:07:41,475 INFO [train.py:763] (3/8) Epoch 5, batch 2400, loss[loss=0.2509, simple_loss=0.3356, pruned_loss=0.08314, over 7330.00 frames.], tot_loss[loss=0.223, simple_loss=0.3076, pruned_loss=0.06921, over 1422548.72 frames.], batch size: 20, lr: 1.16e-03
2022-04-28 16:08:47,664 INFO [train.py:763] (3/8) Epoch 5, batch 2450, loss[loss=0.1969, simple_loss=0.28, pruned_loss=0.05693, over 7245.00 frames.], tot_loss[loss=0.222, simple_loss=0.3066, pruned_loss=0.06868, over 1422962.87 frames.], batch size: 16, lr: 1.16e-03
2022-04-28 16:09:52,914 INFO [train.py:763] (3/8) Epoch 5, batch 2500, loss[loss=0.2522, simple_loss=0.3469, pruned_loss=0.07875, over 7318.00 frames.], tot_loss[loss=0.222, simple_loss=0.3069, pruned_loss=0.06854, over 1422096.22 frames.], batch size: 22, lr: 1.15e-03
2022-04-28 16:10:59,310 INFO [train.py:763] (3/8) Epoch 5, batch 2550, loss[loss=0.2175, simple_loss=0.3073, pruned_loss=0.06384, over 6924.00 frames.], tot_loss[loss=0.2223, simple_loss=0.3071, pruned_loss=0.06874, over 1423501.31 frames.], batch size: 15, lr: 1.15e-03
2022-04-28 16:12:05,355 INFO [train.py:763] (3/8) Epoch 5, batch 2600, loss[loss=0.2388, simple_loss=0.3259, pruned_loss=0.07587, over 7316.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3075, pruned_loss=0.06877, over 1425884.88 frames.], batch size: 21, lr: 1.15e-03
2022-04-28 16:13:10,877 INFO [train.py:763] (3/8) Epoch 5, batch 2650, loss[loss=0.2431, simple_loss=0.3347, pruned_loss=0.07576, over 7256.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3083, pruned_loss=0.06853, over 1423993.62 frames.], batch size: 25, lr: 1.15e-03
2022-04-28 16:14:16,438 INFO [train.py:763] (3/8) Epoch 5, batch 2700, loss[loss=0.24, simple_loss=0.3119, pruned_loss=0.08408, over 6833.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3079, pruned_loss=0.06787, over 1426345.81 frames.], batch size: 15, lr: 1.15e-03
2022-04-28 16:15:15,067 INFO [train.py:763] (3/8) Epoch 5, batch 2750, loss[loss=0.2557, simple_loss=0.3435, pruned_loss=0.08393, over 7241.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3088, pruned_loss=0.06833, over 1424056.77 frames.], batch size: 20, lr: 1.15e-03
2022-04-28 16:16:11,915 INFO [train.py:763] (3/8) Epoch 5, batch 2800, loss[loss=0.2283, simple_loss=0.3099, pruned_loss=0.07332, over 7275.00 frames.], tot_loss[loss=0.2232, simple_loss=0.309, pruned_loss=0.06872, over 1421933.66 frames.], batch size: 18, lr: 1.15e-03
2022-04-28 16:17:08,606 INFO [train.py:763] (3/8) Epoch 5, batch 2850, loss[loss=0.1722, simple_loss=0.2595, pruned_loss=0.04244, over 7287.00 frames.], tot_loss[loss=0.2237, simple_loss=0.3093, pruned_loss=0.06907, over 1419142.59 frames.], batch size: 17, lr: 1.15e-03
2022-04-28 16:18:06,396 INFO [train.py:763] (3/8) Epoch 5, batch 2900, loss[loss=0.2383, simple_loss=0.3247, pruned_loss=0.07599, over 6741.00 frames.], tot_loss[loss=0.2233, simple_loss=0.3091, pruned_loss=0.06875, over 1419958.58 frames.], batch size: 31, lr: 1.15e-03
2022-04-28 16:19:04,268 INFO [train.py:763] (3/8) Epoch 5, batch 2950, loss[loss=0.2453, simple_loss=0.3432, pruned_loss=0.07376, over 7140.00 frames.], tot_loss[loss=0.2231, simple_loss=0.3089, pruned_loss=0.06862, over 1419826.37 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,110 INFO [train.py:763] (3/8) Epoch 5, batch 3000, loss[loss=0.211, simple_loss=0.2964, pruned_loss=0.06285, over 7242.00 frames.], tot_loss[loss=0.2221, simple_loss=0.3082, pruned_loss=0.068, over 1420074.66 frames.], batch size: 20, lr: 1.14e-03
2022-04-28 16:19:58,111 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 16:20:13,357 INFO [train.py:792] (3/8) 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] (3/8) Epoch 5, batch 3050, loss[loss=0.2363, simple_loss=0.3235, pruned_loss=0.07454, over 7194.00 frames.], tot_loss[loss=0.221, simple_loss=0.307, pruned_loss=0.06748, over 1426243.22 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:22:24,937 INFO [train.py:763] (3/8) Epoch 5, batch 3100, loss[loss=0.2342, simple_loss=0.3162, pruned_loss=0.07606, over 7335.00 frames.], tot_loss[loss=0.221, simple_loss=0.3065, pruned_loss=0.06781, over 1423998.86 frames.], batch size: 22, lr: 1.14e-03
2022-04-28 16:23:30,173 INFO [train.py:763] (3/8) Epoch 5, batch 3150, loss[loss=0.2485, simple_loss=0.3354, pruned_loss=0.08083, over 7203.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3074, pruned_loss=0.0682, over 1424261.99 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:24:36,690 INFO [train.py:763] (3/8) Epoch 5, batch 3200, loss[loss=0.2412, simple_loss=0.3266, pruned_loss=0.0779, over 7223.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3081, pruned_loss=0.06856, over 1425500.81 frames.], batch size: 21, lr: 1.14e-03
2022-04-28 16:25:42,633 INFO [train.py:763] (3/8) Epoch 5, batch 3250, loss[loss=0.2126, simple_loss=0.298, pruned_loss=0.06363, over 7362.00 frames.], tot_loss[loss=0.2235, simple_loss=0.3089, pruned_loss=0.06912, over 1425071.95 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:26:48,948 INFO [train.py:763] (3/8) Epoch 5, batch 3300, loss[loss=0.2901, simple_loss=0.3566, pruned_loss=0.1118, over 7196.00 frames.], tot_loss[loss=0.225, simple_loss=0.3099, pruned_loss=0.07001, over 1420590.20 frames.], batch size: 23, lr: 1.14e-03
2022-04-28 16:27:54,259 INFO [train.py:763] (3/8) Epoch 5, batch 3350, loss[loss=0.2203, simple_loss=0.307, pruned_loss=0.06683, over 7259.00 frames.], tot_loss[loss=0.223, simple_loss=0.3083, pruned_loss=0.06889, over 1425112.84 frames.], batch size: 19, lr: 1.14e-03
2022-04-28 16:28:59,513 INFO [train.py:763] (3/8) Epoch 5, batch 3400, loss[loss=0.2551, simple_loss=0.3437, pruned_loss=0.08328, over 7294.00 frames.], tot_loss[loss=0.2234, simple_loss=0.3084, pruned_loss=0.06915, over 1425115.90 frames.], batch size: 24, lr: 1.14e-03
2022-04-28 16:30:05,194 INFO [train.py:763] (3/8) Epoch 5, batch 3450, loss[loss=0.2375, simple_loss=0.3318, pruned_loss=0.07161, over 7423.00 frames.], tot_loss[loss=0.2249, simple_loss=0.31, pruned_loss=0.06986, over 1427431.02 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:31:11,004 INFO [train.py:763] (3/8) Epoch 5, batch 3500, loss[loss=0.2121, simple_loss=0.3077, pruned_loss=0.05827, over 7196.00 frames.], tot_loss[loss=0.2236, simple_loss=0.3084, pruned_loss=0.06938, over 1424010.56 frames.], batch size: 22, lr: 1.13e-03
2022-04-28 16:32:16,130 INFO [train.py:763] (3/8) Epoch 5, batch 3550, loss[loss=0.2229, simple_loss=0.3111, pruned_loss=0.06732, over 7322.00 frames.], tot_loss[loss=0.2228, simple_loss=0.3077, pruned_loss=0.06896, over 1426926.50 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:33:21,407 INFO [train.py:763] (3/8) Epoch 5, batch 3600, loss[loss=0.216, simple_loss=0.2972, pruned_loss=0.06736, over 7178.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3069, pruned_loss=0.06834, over 1428014.36 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:34:27,111 INFO [train.py:763] (3/8) Epoch 5, batch 3650, loss[loss=0.2036, simple_loss=0.2914, pruned_loss=0.05789, over 7417.00 frames.], tot_loss[loss=0.2216, simple_loss=0.3066, pruned_loss=0.06833, over 1426720.54 frames.], batch size: 21, lr: 1.13e-03
2022-04-28 16:35:34,071 INFO [train.py:763] (3/8) Epoch 5, batch 3700, loss[loss=0.2238, simple_loss=0.3088, pruned_loss=0.06937, over 7242.00 frames.], tot_loss[loss=0.222, simple_loss=0.307, pruned_loss=0.0685, over 1424810.84 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:36:39,371 INFO [train.py:763] (3/8) Epoch 5, batch 3750, loss[loss=0.2323, simple_loss=0.3165, pruned_loss=0.07401, over 7383.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3068, pruned_loss=0.06847, over 1423674.49 frames.], batch size: 23, lr: 1.13e-03
2022-04-28 16:37:46,338 INFO [train.py:763] (3/8) Epoch 5, batch 3800, loss[loss=0.2427, simple_loss=0.3369, pruned_loss=0.0742, over 7230.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3066, pruned_loss=0.0686, over 1420121.15 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:38:51,773 INFO [train.py:763] (3/8) Epoch 5, batch 3850, loss[loss=0.2114, simple_loss=0.3056, pruned_loss=0.05858, over 7434.00 frames.], tot_loss[loss=0.2225, simple_loss=0.3075, pruned_loss=0.0688, over 1420883.75 frames.], batch size: 20, lr: 1.13e-03
2022-04-28 16:39:57,099 INFO [train.py:763] (3/8) Epoch 5, batch 3900, loss[loss=0.1715, simple_loss=0.2525, pruned_loss=0.04522, over 7405.00 frames.], tot_loss[loss=0.2219, simple_loss=0.3071, pruned_loss=0.06838, over 1425236.06 frames.], batch size: 18, lr: 1.13e-03
2022-04-28 16:41:04,042 INFO [train.py:763] (3/8) Epoch 5, batch 3950, loss[loss=0.2117, simple_loss=0.3037, pruned_loss=0.05991, over 7318.00 frames.], tot_loss[loss=0.2191, simple_loss=0.3047, pruned_loss=0.06674, over 1425123.90 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:42:10,956 INFO [train.py:763] (3/8) Epoch 5, batch 4000, loss[loss=0.2718, simple_loss=0.3522, pruned_loss=0.09567, over 7217.00 frames.], tot_loss[loss=0.2196, simple_loss=0.3053, pruned_loss=0.06699, over 1427337.98 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:43:18,250 INFO [train.py:763] (3/8) Epoch 5, batch 4050, loss[loss=0.2585, simple_loss=0.3504, pruned_loss=0.08332, over 7295.00 frames.], tot_loss[loss=0.2189, simple_loss=0.305, pruned_loss=0.06646, over 1428195.39 frames.], batch size: 24, lr: 1.12e-03
2022-04-28 16:44:25,534 INFO [train.py:763] (3/8) Epoch 5, batch 4100, loss[loss=0.1852, simple_loss=0.274, pruned_loss=0.04816, over 7419.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3039, pruned_loss=0.06624, over 1427763.10 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:45:32,376 INFO [train.py:763] (3/8) Epoch 5, batch 4150, loss[loss=0.2454, simple_loss=0.3365, pruned_loss=0.07717, over 6783.00 frames.], tot_loss[loss=0.2179, simple_loss=0.3037, pruned_loss=0.06606, over 1427251.51 frames.], batch size: 31, lr: 1.12e-03
2022-04-28 16:46:39,133 INFO [train.py:763] (3/8) Epoch 5, batch 4200, loss[loss=0.2394, simple_loss=0.3268, pruned_loss=0.07594, over 7123.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3027, pruned_loss=0.06582, over 1429563.69 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:47:45,474 INFO [train.py:763] (3/8) Epoch 5, batch 4250, loss[loss=0.2437, simple_loss=0.325, pruned_loss=0.08126, over 7378.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3031, pruned_loss=0.06652, over 1430213.47 frames.], batch size: 23, lr: 1.12e-03
2022-04-28 16:48:52,195 INFO [train.py:763] (3/8) Epoch 5, batch 4300, loss[loss=0.2123, simple_loss=0.2886, pruned_loss=0.068, over 7056.00 frames.], tot_loss[loss=0.2185, simple_loss=0.3036, pruned_loss=0.06667, over 1424919.49 frames.], batch size: 18, lr: 1.12e-03
2022-04-28 16:49:59,887 INFO [train.py:763] (3/8) Epoch 5, batch 4350, loss[loss=0.2299, simple_loss=0.3189, pruned_loss=0.0704, over 7208.00 frames.], tot_loss[loss=0.2184, simple_loss=0.3032, pruned_loss=0.06682, over 1424554.25 frames.], batch size: 21, lr: 1.12e-03
2022-04-28 16:51:07,555 INFO [train.py:763] (3/8) Epoch 5, batch 4400, loss[loss=0.2035, simple_loss=0.2917, pruned_loss=0.05768, over 7434.00 frames.], tot_loss[loss=0.218, simple_loss=0.3028, pruned_loss=0.06661, over 1422119.60 frames.], batch size: 20, lr: 1.12e-03
2022-04-28 16:52:13,249 INFO [train.py:763] (3/8) Epoch 5, batch 4450, loss[loss=0.189, simple_loss=0.2689, pruned_loss=0.05456, over 7269.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3035, pruned_loss=0.06756, over 1408887.89 frames.], batch size: 17, lr: 1.11e-03
2022-04-28 16:53:19,249 INFO [train.py:763] (3/8) Epoch 5, batch 4500, loss[loss=0.2594, simple_loss=0.3416, pruned_loss=0.08858, over 7234.00 frames.], tot_loss[loss=0.2175, simple_loss=0.3015, pruned_loss=0.0667, over 1408174.23 frames.], batch size: 20, lr: 1.11e-03
2022-04-28 16:54:23,898 INFO [train.py:763] (3/8) Epoch 5, batch 4550, loss[loss=0.2776, simple_loss=0.354, pruned_loss=0.1006, over 4971.00 frames.], tot_loss[loss=0.2227, simple_loss=0.3053, pruned_loss=0.07007, over 1358900.20 frames.], batch size: 52, lr: 1.11e-03
2022-04-28 16:55:51,903 INFO [train.py:763] (3/8) Epoch 6, batch 0, loss[loss=0.2257, simple_loss=0.303, pruned_loss=0.07419, over 7411.00 frames.], tot_loss[loss=0.2257, simple_loss=0.303, pruned_loss=0.07419, over 7411.00 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:56:58,094 INFO [train.py:763] (3/8) Epoch 6, batch 50, loss[loss=0.1748, simple_loss=0.2648, pruned_loss=0.04246, over 7407.00 frames.], tot_loss[loss=0.2182, simple_loss=0.3045, pruned_loss=0.06592, over 322484.23 frames.], batch size: 18, lr: 1.07e-03
2022-04-28 16:58:04,027 INFO [train.py:763] (3/8) Epoch 6, batch 100, loss[loss=0.1751, simple_loss=0.2733, pruned_loss=0.03848, over 7151.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3024, pruned_loss=0.06412, over 567527.01 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 16:59:09,767 INFO [train.py:763] (3/8) Epoch 6, batch 150, loss[loss=0.2169, simple_loss=0.2972, pruned_loss=0.06829, over 7143.00 frames.], tot_loss[loss=0.2162, simple_loss=0.3034, pruned_loss=0.06448, over 756775.45 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:00:15,499 INFO [train.py:763] (3/8) Epoch 6, batch 200, loss[loss=0.2233, simple_loss=0.3125, pruned_loss=0.06705, over 7368.00 frames.], tot_loss[loss=0.2164, simple_loss=0.304, pruned_loss=0.06444, over 905510.79 frames.], batch size: 23, lr: 1.06e-03
2022-04-28 17:01:29,828 INFO [train.py:763] (3/8) Epoch 6, batch 250, loss[loss=0.2219, simple_loss=0.311, pruned_loss=0.06636, over 7146.00 frames.], tot_loss[loss=0.2165, simple_loss=0.3043, pruned_loss=0.06435, over 1019818.21 frames.], batch size: 20, lr: 1.06e-03
2022-04-28 17:02:45,513 INFO [train.py:763] (3/8) Epoch 6, batch 300, loss[loss=0.1846, simple_loss=0.2554, pruned_loss=0.05686, over 6810.00 frames.], tot_loss[loss=0.2187, simple_loss=0.3059, pruned_loss=0.06574, over 1105336.52 frames.], batch size: 15, lr: 1.06e-03
2022-04-28 17:03:59,806 INFO [train.py:763] (3/8) Epoch 6, batch 350, loss[loss=0.2034, simple_loss=0.2967, pruned_loss=0.05503, over 7119.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3051, pruned_loss=0.06555, over 1176099.63 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:05:05,097 INFO [train.py:763] (3/8) Epoch 6, batch 400, loss[loss=0.2219, simple_loss=0.2956, pruned_loss=0.0741, over 7169.00 frames.], tot_loss[loss=0.2193, simple_loss=0.3063, pruned_loss=0.06609, over 1228714.95 frames.], batch size: 18, lr: 1.06e-03
2022-04-28 17:06:20,538 INFO [train.py:763] (3/8) Epoch 6, batch 450, loss[loss=0.2316, simple_loss=0.3252, pruned_loss=0.06897, over 7350.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3053, pruned_loss=0.06545, over 1274356.42 frames.], batch size: 19, lr: 1.06e-03
2022-04-28 17:07:44,115 INFO [train.py:763] (3/8) Epoch 6, batch 500, loss[loss=0.2203, simple_loss=0.3133, pruned_loss=0.06367, over 6410.00 frames.], tot_loss[loss=0.2186, simple_loss=0.3058, pruned_loss=0.06574, over 1303847.66 frames.], batch size: 38, lr: 1.06e-03
2022-04-28 17:08:59,113 INFO [train.py:763] (3/8) Epoch 6, batch 550, loss[loss=0.2228, simple_loss=0.3156, pruned_loss=0.06504, over 7120.00 frames.], tot_loss[loss=0.2181, simple_loss=0.3051, pruned_loss=0.06557, over 1329005.27 frames.], batch size: 21, lr: 1.06e-03
2022-04-28 17:10:13,642 INFO [train.py:763] (3/8) Epoch 6, batch 600, loss[loss=0.2065, simple_loss=0.3038, pruned_loss=0.0546, over 7084.00 frames.], tot_loss[loss=0.2177, simple_loss=0.3052, pruned_loss=0.06512, over 1347867.23 frames.], batch size: 28, lr: 1.06e-03
2022-04-28 17:11:19,491 INFO [train.py:763] (3/8) Epoch 6, batch 650, loss[loss=0.2392, simple_loss=0.3166, pruned_loss=0.08093, over 5092.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3032, pruned_loss=0.06418, over 1364662.76 frames.], batch size: 53, lr: 1.05e-03
2022-04-28 17:12:25,177 INFO [train.py:763] (3/8) Epoch 6, batch 700, loss[loss=0.2136, simple_loss=0.2987, pruned_loss=0.06429, over 7176.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3026, pruned_loss=0.06402, over 1379718.38 frames.], batch size: 18, lr: 1.05e-03
2022-04-28 17:13:31,498 INFO [train.py:763] (3/8) Epoch 6, batch 750, loss[loss=0.2204, simple_loss=0.3155, pruned_loss=0.06265, over 6894.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3021, pruned_loss=0.0636, over 1392253.94 frames.], batch size: 31, lr: 1.05e-03
2022-04-28 17:14:37,093 INFO [train.py:763] (3/8) Epoch 6, batch 800, loss[loss=0.2019, simple_loss=0.3107, pruned_loss=0.04653, over 7339.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3016, pruned_loss=0.06394, over 1392106.89 frames.], batch size: 20, lr: 1.05e-03
2022-04-28 17:15:43,492 INFO [train.py:763] (3/8) Epoch 6, batch 850, loss[loss=0.238, simple_loss=0.3278, pruned_loss=0.07411, over 7272.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3016, pruned_loss=0.06388, over 1398590.68 frames.], batch size: 24, lr: 1.05e-03
2022-04-28 17:16:48,952 INFO [train.py:763] (3/8) Epoch 6, batch 900, loss[loss=0.2127, simple_loss=0.3118, pruned_loss=0.05682, over 7379.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3037, pruned_loss=0.06555, over 1404096.87 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:17:54,044 INFO [train.py:763] (3/8) Epoch 6, batch 950, loss[loss=0.2365, simple_loss=0.3295, pruned_loss=0.07173, over 7377.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3048, pruned_loss=0.06542, over 1408673.17 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:18:59,562 INFO [train.py:763] (3/8) Epoch 6, batch 1000, loss[loss=0.2261, simple_loss=0.316, pruned_loss=0.0681, over 7384.00 frames.], tot_loss[loss=0.218, simple_loss=0.3046, pruned_loss=0.06569, over 1408615.57 frames.], batch size: 23, lr: 1.05e-03
2022-04-28 17:20:06,058 INFO [train.py:763] (3/8) Epoch 6, batch 1050, loss[loss=0.2106, simple_loss=0.2965, pruned_loss=0.06237, over 7169.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3043, pruned_loss=0.06527, over 1415101.83 frames.], batch size: 19, lr: 1.05e-03
2022-04-28 17:21:12,150 INFO [train.py:763] (3/8) Epoch 6, batch 1100, loss[loss=0.2583, simple_loss=0.3389, pruned_loss=0.08879, over 7287.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3035, pruned_loss=0.06455, over 1418849.86 frames.], batch size: 25, lr: 1.05e-03
2022-04-28 17:22:18,726 INFO [train.py:763] (3/8) Epoch 6, batch 1150, loss[loss=0.174, simple_loss=0.2708, pruned_loss=0.03862, over 7133.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3034, pruned_loss=0.06411, over 1416990.86 frames.], batch size: 17, lr: 1.05e-03
2022-04-28 17:23:26,112 INFO [train.py:763] (3/8) Epoch 6, batch 1200, loss[loss=0.1791, simple_loss=0.2574, pruned_loss=0.05039, over 7276.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3037, pruned_loss=0.06449, over 1413064.51 frames.], batch size: 16, lr: 1.04e-03
2022-04-28 17:24:33,315 INFO [train.py:763] (3/8) Epoch 6, batch 1250, loss[loss=0.2285, simple_loss=0.3123, pruned_loss=0.07235, over 7236.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3029, pruned_loss=0.06403, over 1414784.92 frames.], batch size: 20, lr: 1.04e-03
2022-04-28 17:25:39,227 INFO [train.py:763] (3/8) Epoch 6, batch 1300, loss[loss=0.1836, simple_loss=0.2637, pruned_loss=0.05178, over 7286.00 frames.], tot_loss[loss=0.2155, simple_loss=0.3024, pruned_loss=0.0643, over 1416862.28 frames.], batch size: 17, lr: 1.04e-03
2022-04-28 17:26:44,443 INFO [train.py:763] (3/8) Epoch 6, batch 1350, loss[loss=0.2456, simple_loss=0.3169, pruned_loss=0.08712, over 7420.00 frames.], tot_loss[loss=0.2164, simple_loss=0.3031, pruned_loss=0.06488, over 1422395.80 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:27:49,617 INFO [train.py:763] (3/8) Epoch 6, batch 1400, loss[loss=0.2235, simple_loss=0.3062, pruned_loss=0.07046, over 7150.00 frames.], tot_loss[loss=0.2178, simple_loss=0.3044, pruned_loss=0.06556, over 1420337.53 frames.], batch size: 19, lr: 1.04e-03
2022-04-28 17:28:55,364 INFO [train.py:763] (3/8) Epoch 6, batch 1450, loss[loss=0.2255, simple_loss=0.3151, pruned_loss=0.06798, over 6783.00 frames.], tot_loss[loss=0.218, simple_loss=0.305, pruned_loss=0.06545, over 1419867.53 frames.], batch size: 31, lr: 1.04e-03
2022-04-28 17:30:00,748 INFO [train.py:763] (3/8) Epoch 6, batch 1500, loss[loss=0.2182, simple_loss=0.3147, pruned_loss=0.06079, over 7416.00 frames.], tot_loss[loss=0.218, simple_loss=0.3053, pruned_loss=0.06538, over 1422805.55 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:31:05,969 INFO [train.py:763] (3/8) Epoch 6, batch 1550, loss[loss=0.2459, simple_loss=0.3357, pruned_loss=0.07802, over 7153.00 frames.], tot_loss[loss=0.2166, simple_loss=0.3038, pruned_loss=0.0647, over 1417831.94 frames.], batch size: 26, lr: 1.04e-03
2022-04-28 17:32:11,539 INFO [train.py:763] (3/8) Epoch 6, batch 1600, loss[loss=0.231, simple_loss=0.3235, pruned_loss=0.06921, over 7123.00 frames.], tot_loss[loss=0.2158, simple_loss=0.3031, pruned_loss=0.0642, over 1424094.47 frames.], batch size: 21, lr: 1.04e-03
2022-04-28 17:33:16,936 INFO [train.py:763] (3/8) Epoch 6, batch 1650, loss[loss=0.1972, simple_loss=0.2964, pruned_loss=0.04905, over 7062.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3029, pruned_loss=0.06396, over 1417701.04 frames.], batch size: 18, lr: 1.04e-03
2022-04-28 17:34:24,084 INFO [train.py:763] (3/8) Epoch 6, batch 1700, loss[loss=0.2031, simple_loss=0.3019, pruned_loss=0.05218, over 7209.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3018, pruned_loss=0.06372, over 1417014.76 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:35:30,120 INFO [train.py:763] (3/8) Epoch 6, batch 1750, loss[loss=0.2672, simple_loss=0.3453, pruned_loss=0.09457, over 7337.00 frames.], tot_loss[loss=0.2147, simple_loss=0.3018, pruned_loss=0.06385, over 1412083.35 frames.], batch size: 22, lr: 1.04e-03
2022-04-28 17:36:35,227 INFO [train.py:763] (3/8) Epoch 6, batch 1800, loss[loss=0.2233, simple_loss=0.3074, pruned_loss=0.06957, over 7251.00 frames.], tot_loss[loss=0.2161, simple_loss=0.3032, pruned_loss=0.06451, over 1414722.04 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:37:41,017 INFO [train.py:763] (3/8) Epoch 6, batch 1850, loss[loss=0.1906, simple_loss=0.2766, pruned_loss=0.05234, over 6999.00 frames.], tot_loss[loss=0.2151, simple_loss=0.302, pruned_loss=0.06413, over 1416870.31 frames.], batch size: 16, lr: 1.03e-03
2022-04-28 17:38:46,201 INFO [train.py:763] (3/8) Epoch 6, batch 1900, loss[loss=0.2153, simple_loss=0.3048, pruned_loss=0.06286, over 7075.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3024, pruned_loss=0.06423, over 1413986.50 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:39:52,668 INFO [train.py:763] (3/8) Epoch 6, batch 1950, loss[loss=0.2131, simple_loss=0.2965, pruned_loss=0.06488, over 7272.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3013, pruned_loss=0.06417, over 1416859.38 frames.], batch size: 18, lr: 1.03e-03
2022-04-28 17:40:59,181 INFO [train.py:763] (3/8) Epoch 6, batch 2000, loss[loss=0.2456, simple_loss=0.3343, pruned_loss=0.07842, over 7328.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3014, pruned_loss=0.06388, over 1417139.16 frames.], batch size: 25, lr: 1.03e-03
2022-04-28 17:42:06,056 INFO [train.py:763] (3/8) Epoch 6, batch 2050, loss[loss=0.209, simple_loss=0.3033, pruned_loss=0.05732, over 7270.00 frames.], tot_loss[loss=0.216, simple_loss=0.3026, pruned_loss=0.06473, over 1414930.25 frames.], batch size: 24, lr: 1.03e-03
2022-04-28 17:43:12,553 INFO [train.py:763] (3/8) Epoch 6, batch 2100, loss[loss=0.1876, simple_loss=0.2731, pruned_loss=0.05106, over 7011.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3013, pruned_loss=0.06382, over 1418261.81 frames.], batch size: 16, lr: 1.03e-03
2022-04-28 17:44:19,359 INFO [train.py:763] (3/8) Epoch 6, batch 2150, loss[loss=0.2291, simple_loss=0.3236, pruned_loss=0.06729, over 7407.00 frames.], tot_loss[loss=0.2149, simple_loss=0.3019, pruned_loss=0.0639, over 1423738.95 frames.], batch size: 21, lr: 1.03e-03
2022-04-28 17:45:25,694 INFO [train.py:763] (3/8) Epoch 6, batch 2200, loss[loss=0.2046, simple_loss=0.2841, pruned_loss=0.0625, over 7134.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3021, pruned_loss=0.06439, over 1422097.25 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:46:32,098 INFO [train.py:763] (3/8) Epoch 6, batch 2250, loss[loss=0.2137, simple_loss=0.2873, pruned_loss=0.07009, over 7280.00 frames.], tot_loss[loss=0.2155, simple_loss=0.302, pruned_loss=0.06454, over 1416065.24 frames.], batch size: 17, lr: 1.03e-03
2022-04-28 17:47:38,686 INFO [train.py:763] (3/8) Epoch 6, batch 2300, loss[loss=0.2369, simple_loss=0.3138, pruned_loss=0.07995, over 7197.00 frames.], tot_loss[loss=0.2148, simple_loss=0.3014, pruned_loss=0.06411, over 1419019.34 frames.], batch size: 23, lr: 1.03e-03
2022-04-28 17:48:44,943 INFO [train.py:763] (3/8) Epoch 6, batch 2350, loss[loss=0.2423, simple_loss=0.3337, pruned_loss=0.07541, over 7415.00 frames.], tot_loss[loss=0.2154, simple_loss=0.302, pruned_loss=0.06437, over 1418203.24 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:49:50,848 INFO [train.py:763] (3/8) Epoch 6, batch 2400, loss[loss=0.1764, simple_loss=0.27, pruned_loss=0.04142, over 7275.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3017, pruned_loss=0.06438, over 1421715.37 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:50:56,968 INFO [train.py:763] (3/8) Epoch 6, batch 2450, loss[loss=0.2357, simple_loss=0.3252, pruned_loss=0.07313, over 7421.00 frames.], tot_loss[loss=0.2156, simple_loss=0.3021, pruned_loss=0.06454, over 1417968.10 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:52:02,801 INFO [train.py:763] (3/8) Epoch 6, batch 2500, loss[loss=0.2586, simple_loss=0.3454, pruned_loss=0.08592, over 7331.00 frames.], tot_loss[loss=0.2167, simple_loss=0.3034, pruned_loss=0.06501, over 1417922.49 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 17:53:08,641 INFO [train.py:763] (3/8) Epoch 6, batch 2550, loss[loss=0.2519, simple_loss=0.3158, pruned_loss=0.09403, over 7429.00 frames.], tot_loss[loss=0.2172, simple_loss=0.3038, pruned_loss=0.06532, over 1424258.73 frames.], batch size: 20, lr: 1.02e-03
2022-04-28 17:54:14,768 INFO [train.py:763] (3/8) Epoch 6, batch 2600, loss[loss=0.2255, simple_loss=0.3016, pruned_loss=0.07469, over 7166.00 frames.], tot_loss[loss=0.218, simple_loss=0.3041, pruned_loss=0.06593, over 1418627.83 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:55:21,045 INFO [train.py:763] (3/8) Epoch 6, batch 2650, loss[loss=0.1985, simple_loss=0.2813, pruned_loss=0.05783, over 7169.00 frames.], tot_loss[loss=0.2173, simple_loss=0.3034, pruned_loss=0.06562, over 1417792.43 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:56:26,531 INFO [train.py:763] (3/8) Epoch 6, batch 2700, loss[loss=0.1774, simple_loss=0.2634, pruned_loss=0.04569, over 6784.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3032, pruned_loss=0.06531, over 1419324.67 frames.], batch size: 15, lr: 1.02e-03
2022-04-28 17:57:32,628 INFO [train.py:763] (3/8) Epoch 6, batch 2750, loss[loss=0.197, simple_loss=0.2733, pruned_loss=0.06036, over 7404.00 frames.], tot_loss[loss=0.2169, simple_loss=0.3032, pruned_loss=0.06531, over 1420077.56 frames.], batch size: 18, lr: 1.02e-03
2022-04-28 17:58:39,120 INFO [train.py:763] (3/8) Epoch 6, batch 2800, loss[loss=0.182, simple_loss=0.2582, pruned_loss=0.05293, over 6998.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3026, pruned_loss=0.06503, over 1418249.09 frames.], batch size: 16, lr: 1.02e-03
2022-04-28 17:59:46,048 INFO [train.py:763] (3/8) Epoch 6, batch 2850, loss[loss=0.23, simple_loss=0.324, pruned_loss=0.06802, over 7316.00 frames.], tot_loss[loss=0.2142, simple_loss=0.301, pruned_loss=0.06367, over 1423210.24 frames.], batch size: 21, lr: 1.02e-03
2022-04-28 18:00:52,207 INFO [train.py:763] (3/8) Epoch 6, batch 2900, loss[loss=0.268, simple_loss=0.339, pruned_loss=0.09846, over 4715.00 frames.], tot_loss[loss=0.214, simple_loss=0.301, pruned_loss=0.0635, over 1425139.96 frames.], batch size: 52, lr: 1.02e-03
2022-04-28 18:01:57,561 INFO [train.py:763] (3/8) Epoch 6, batch 2950, loss[loss=0.2323, simple_loss=0.3214, pruned_loss=0.07165, over 7311.00 frames.], tot_loss[loss=0.2146, simple_loss=0.3021, pruned_loss=0.06356, over 1425626.68 frames.], batch size: 25, lr: 1.01e-03
2022-04-28 18:03:03,519 INFO [train.py:763] (3/8) Epoch 6, batch 3000, loss[loss=0.2597, simple_loss=0.3497, pruned_loss=0.08483, over 7190.00 frames.], tot_loss[loss=0.2154, simple_loss=0.3031, pruned_loss=0.06385, over 1427093.14 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:03:03,520 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 18:03:18,818 INFO [train.py:792] (3/8) Epoch 6, validation: loss=0.1749, simple_loss=0.2793, pruned_loss=0.03525, over 698248.00 frames.
2022-04-28 18:04:24,348 INFO [train.py:763] (3/8) Epoch 6, batch 3050, loss[loss=0.2302, simple_loss=0.324, pruned_loss=0.06823, over 7203.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3028, pruned_loss=0.06388, over 1427861.16 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:05:30,258 INFO [train.py:763] (3/8) Epoch 6, batch 3100, loss[loss=0.201, simple_loss=0.2978, pruned_loss=0.05212, over 7147.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3017, pruned_loss=0.06295, over 1425202.45 frames.], batch size: 26, lr: 1.01e-03
2022-04-28 18:06:36,920 INFO [train.py:763] (3/8) Epoch 6, batch 3150, loss[loss=0.2381, simple_loss=0.316, pruned_loss=0.08013, over 7117.00 frames.], tot_loss[loss=0.214, simple_loss=0.3021, pruned_loss=0.06294, over 1428601.11 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:07:42,732 INFO [train.py:763] (3/8) Epoch 6, batch 3200, loss[loss=0.1992, simple_loss=0.2953, pruned_loss=0.05154, over 7338.00 frames.], tot_loss[loss=0.2141, simple_loss=0.3023, pruned_loss=0.06296, over 1425597.50 frames.], batch size: 22, lr: 1.01e-03
2022-04-28 18:08:48,608 INFO [train.py:763] (3/8) Epoch 6, batch 3250, loss[loss=0.2188, simple_loss=0.3155, pruned_loss=0.061, over 6989.00 frames.], tot_loss[loss=0.2139, simple_loss=0.3017, pruned_loss=0.06304, over 1425250.82 frames.], batch size: 28, lr: 1.01e-03
2022-04-28 18:09:54,855 INFO [train.py:763] (3/8) Epoch 6, batch 3300, loss[loss=0.1957, simple_loss=0.2883, pruned_loss=0.05156, over 7143.00 frames.], tot_loss[loss=0.2143, simple_loss=0.3024, pruned_loss=0.06313, over 1419876.24 frames.], batch size: 20, lr: 1.01e-03
2022-04-28 18:11:00,641 INFO [train.py:763] (3/8) Epoch 6, batch 3350, loss[loss=0.1973, simple_loss=0.2831, pruned_loss=0.05576, over 7153.00 frames.], tot_loss[loss=0.2132, simple_loss=0.3017, pruned_loss=0.06241, over 1420345.94 frames.], batch size: 19, lr: 1.01e-03
2022-04-28 18:12:05,974 INFO [train.py:763] (3/8) Epoch 6, batch 3400, loss[loss=0.2177, simple_loss=0.313, pruned_loss=0.06121, over 7105.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3017, pruned_loss=0.06282, over 1422838.68 frames.], batch size: 21, lr: 1.01e-03
2022-04-28 18:13:11,470 INFO [train.py:763] (3/8) Epoch 6, batch 3450, loss[loss=0.2371, simple_loss=0.3345, pruned_loss=0.06983, over 7266.00 frames.], tot_loss[loss=0.2138, simple_loss=0.3018, pruned_loss=0.06286, over 1420769.19 frames.], batch size: 24, lr: 1.01e-03
2022-04-28 18:14:16,740 INFO [train.py:763] (3/8) Epoch 6, batch 3500, loss[loss=0.2134, simple_loss=0.3127, pruned_loss=0.05709, over 7220.00 frames.], tot_loss[loss=0.2136, simple_loss=0.302, pruned_loss=0.0626, over 1422335.77 frames.], batch size: 21, lr: 1.01e-03
2022-04-28 18:15:22,307 INFO [train.py:763] (3/8) Epoch 6, batch 3550, loss[loss=0.2351, simple_loss=0.3253, pruned_loss=0.0724, over 7377.00 frames.], tot_loss[loss=0.2136, simple_loss=0.3015, pruned_loss=0.06279, over 1424048.60 frames.], batch size: 23, lr: 1.01e-03
2022-04-28 18:16:27,535 INFO [train.py:763] (3/8) Epoch 6, batch 3600, loss[loss=0.1997, simple_loss=0.3018, pruned_loss=0.04878, over 7219.00 frames.], tot_loss[loss=0.2138, simple_loss=0.302, pruned_loss=0.06283, over 1425197.92 frames.], batch size: 21, lr: 1.00e-03
2022-04-28 18:17:32,792 INFO [train.py:763] (3/8) Epoch 6, batch 3650, loss[loss=0.2628, simple_loss=0.3422, pruned_loss=0.09168, over 7070.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3017, pruned_loss=0.06246, over 1422140.89 frames.], batch size: 28, lr: 1.00e-03
2022-04-28 18:18:39,443 INFO [train.py:763] (3/8) Epoch 6, batch 3700, loss[loss=0.2268, simple_loss=0.3071, pruned_loss=0.07331, over 7423.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3012, pruned_loss=0.06269, over 1423427.30 frames.], batch size: 20, lr: 1.00e-03
2022-04-28 18:19:44,869 INFO [train.py:763] (3/8) Epoch 6, batch 3750, loss[loss=0.2469, simple_loss=0.3128, pruned_loss=0.09048, over 5002.00 frames.], tot_loss[loss=0.2134, simple_loss=0.3012, pruned_loss=0.06285, over 1424139.94 frames.], batch size: 53, lr: 1.00e-03
2022-04-28 18:20:50,221 INFO [train.py:763] (3/8) Epoch 6, batch 3800, loss[loss=0.2211, simple_loss=0.3124, pruned_loss=0.06492, over 7356.00 frames.], tot_loss[loss=0.2133, simple_loss=0.3012, pruned_loss=0.06272, over 1421989.85 frames.], batch size: 19, lr: 1.00e-03
2022-04-28 18:21:56,430 INFO [train.py:763] (3/8) Epoch 6, batch 3850, loss[loss=0.1682, simple_loss=0.2562, pruned_loss=0.04012, over 7113.00 frames.], tot_loss[loss=0.2126, simple_loss=0.3, pruned_loss=0.06256, over 1424954.14 frames.], batch size: 17, lr: 1.00e-03
2022-04-28 18:23:02,742 INFO [train.py:763] (3/8) Epoch 6, batch 3900, loss[loss=0.1623, simple_loss=0.2532, pruned_loss=0.0357, over 7162.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2992, pruned_loss=0.06211, over 1425879.32 frames.], batch size: 18, lr: 1.00e-03
2022-04-28 18:24:08,624 INFO [train.py:763] (3/8) Epoch 6, batch 3950, loss[loss=0.2056, simple_loss=0.2995, pruned_loss=0.05586, over 7338.00 frames.], tot_loss[loss=0.211, simple_loss=0.2987, pruned_loss=0.0616, over 1427160.47 frames.], batch size: 22, lr: 9.99e-04
2022-04-28 18:25:14,070 INFO [train.py:763] (3/8) Epoch 6, batch 4000, loss[loss=0.2778, simple_loss=0.3573, pruned_loss=0.09917, over 6727.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2994, pruned_loss=0.06199, over 1431726.03 frames.], batch size: 31, lr: 9.98e-04
2022-04-28 18:26:19,666 INFO [train.py:763] (3/8) Epoch 6, batch 4050, loss[loss=0.1963, simple_loss=0.2881, pruned_loss=0.0522, over 7157.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2986, pruned_loss=0.06177, over 1429464.06 frames.], batch size: 18, lr: 9.98e-04
2022-04-28 18:27:25,501 INFO [train.py:763] (3/8) Epoch 6, batch 4100, loss[loss=0.2615, simple_loss=0.3512, pruned_loss=0.08592, over 7109.00 frames.], tot_loss[loss=0.212, simple_loss=0.2997, pruned_loss=0.06217, over 1424816.24 frames.], batch size: 21, lr: 9.97e-04
2022-04-28 18:28:32,062 INFO [train.py:763] (3/8) Epoch 6, batch 4150, loss[loss=0.2489, simple_loss=0.3308, pruned_loss=0.08348, over 7214.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3002, pruned_loss=0.06216, over 1426015.36 frames.], batch size: 23, lr: 9.96e-04
2022-04-28 18:29:37,830 INFO [train.py:763] (3/8) Epoch 6, batch 4200, loss[loss=0.1832, simple_loss=0.2696, pruned_loss=0.04842, over 7286.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2998, pruned_loss=0.06177, over 1428057.17 frames.], batch size: 17, lr: 9.95e-04
2022-04-28 18:30:43,249 INFO [train.py:763] (3/8) Epoch 6, batch 4250, loss[loss=0.2554, simple_loss=0.3404, pruned_loss=0.08527, over 7425.00 frames.], tot_loss[loss=0.2135, simple_loss=0.3013, pruned_loss=0.06291, over 1423247.37 frames.], batch size: 20, lr: 9.95e-04
2022-04-28 18:31:48,728 INFO [train.py:763] (3/8) Epoch 6, batch 4300, loss[loss=0.2585, simple_loss=0.3395, pruned_loss=0.08876, over 7234.00 frames.], tot_loss[loss=0.2145, simple_loss=0.3022, pruned_loss=0.06342, over 1417864.55 frames.], batch size: 20, lr: 9.94e-04
2022-04-28 18:32:54,885 INFO [train.py:763] (3/8) Epoch 6, batch 4350, loss[loss=0.2147, simple_loss=0.3038, pruned_loss=0.06281, over 6336.00 frames.], tot_loss[loss=0.213, simple_loss=0.3013, pruned_loss=0.06237, over 1411951.01 frames.], batch size: 38, lr: 9.93e-04
2022-04-28 18:34:00,597 INFO [train.py:763] (3/8) Epoch 6, batch 4400, loss[loss=0.2293, simple_loss=0.32, pruned_loss=0.06931, over 6772.00 frames.], tot_loss[loss=0.2135, simple_loss=0.301, pruned_loss=0.06297, over 1413986.23 frames.], batch size: 31, lr: 9.92e-04
2022-04-28 18:35:07,312 INFO [train.py:763] (3/8) Epoch 6, batch 4450, loss[loss=0.2151, simple_loss=0.3019, pruned_loss=0.06414, over 7210.00 frames.], tot_loss[loss=0.2142, simple_loss=0.3017, pruned_loss=0.06336, over 1408421.51 frames.], batch size: 22, lr: 9.92e-04
2022-04-28 18:36:23,319 INFO [train.py:763] (3/8) Epoch 6, batch 4500, loss[loss=0.2312, simple_loss=0.3214, pruned_loss=0.07044, over 7214.00 frames.], tot_loss[loss=0.2153, simple_loss=0.3026, pruned_loss=0.06399, over 1405368.53 frames.], batch size: 22, lr: 9.91e-04
2022-04-28 18:37:28,288 INFO [train.py:763] (3/8) Epoch 6, batch 4550, loss[loss=0.2417, simple_loss=0.3172, pruned_loss=0.08311, over 4494.00 frames.], tot_loss[loss=0.2163, simple_loss=0.3038, pruned_loss=0.06434, over 1390215.88 frames.], batch size: 52, lr: 9.90e-04
2022-04-28 18:38:57,444 INFO [train.py:763] (3/8) Epoch 7, batch 0, loss[loss=0.2208, simple_loss=0.3213, pruned_loss=0.06009, over 7332.00 frames.], tot_loss[loss=0.2208, simple_loss=0.3213, pruned_loss=0.06009, over 7332.00 frames.], batch size: 22, lr: 9.49e-04
2022-04-28 18:40:02,641 INFO [train.py:763] (3/8) Epoch 7, batch 50, loss[loss=0.2069, simple_loss=0.2827, pruned_loss=0.06553, over 7137.00 frames.], tot_loss[loss=0.2131, simple_loss=0.3028, pruned_loss=0.06171, over 320764.07 frames.], batch size: 17, lr: 9.48e-04
2022-04-28 18:41:07,850 INFO [train.py:763] (3/8) Epoch 7, batch 100, loss[loss=0.1898, simple_loss=0.2854, pruned_loss=0.04712, over 7264.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2987, pruned_loss=0.05876, over 568903.63 frames.], batch size: 25, lr: 9.48e-04
2022-04-28 18:42:13,273 INFO [train.py:763] (3/8) Epoch 7, batch 150, loss[loss=0.2287, simple_loss=0.3173, pruned_loss=0.07009, over 7116.00 frames.], tot_loss[loss=0.2081, simple_loss=0.298, pruned_loss=0.05912, over 758048.30 frames.], batch size: 21, lr: 9.47e-04
2022-04-28 18:43:19,110 INFO [train.py:763] (3/8) Epoch 7, batch 200, loss[loss=0.2063, simple_loss=0.3035, pruned_loss=0.05458, over 7215.00 frames.], tot_loss[loss=0.21, simple_loss=0.2993, pruned_loss=0.06031, over 907014.98 frames.], batch size: 22, lr: 9.46e-04
2022-04-28 18:44:24,613 INFO [train.py:763] (3/8) Epoch 7, batch 250, loss[loss=0.2057, simple_loss=0.296, pruned_loss=0.05767, over 7121.00 frames.], tot_loss[loss=0.2093, simple_loss=0.299, pruned_loss=0.05981, over 1020289.29 frames.], batch size: 21, lr: 9.46e-04
2022-04-28 18:45:29,824 INFO [train.py:763] (3/8) Epoch 7, batch 300, loss[loss=0.1844, simple_loss=0.2717, pruned_loss=0.04853, over 7070.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2994, pruned_loss=0.0601, over 1106021.37 frames.], batch size: 18, lr: 9.45e-04
2022-04-28 18:46:35,548 INFO [train.py:763] (3/8) Epoch 7, batch 350, loss[loss=0.2225, simple_loss=0.3165, pruned_loss=0.06424, over 7110.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2982, pruned_loss=0.06044, over 1177793.37 frames.], batch size: 21, lr: 9.44e-04
2022-04-28 18:47:40,823 INFO [train.py:763] (3/8) Epoch 7, batch 400, loss[loss=0.2616, simple_loss=0.3334, pruned_loss=0.09491, over 4856.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2996, pruned_loss=0.06139, over 1230569.38 frames.], batch size: 52, lr: 9.43e-04
2022-04-28 18:48:46,397 INFO [train.py:763] (3/8) Epoch 7, batch 450, loss[loss=0.1758, simple_loss=0.2559, pruned_loss=0.0478, over 6711.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2986, pruned_loss=0.06081, over 1271386.13 frames.], batch size: 15, lr: 9.43e-04
2022-04-28 18:49:51,764 INFO [train.py:763] (3/8) Epoch 7, batch 500, loss[loss=0.2434, simple_loss=0.333, pruned_loss=0.07688, over 7198.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2974, pruned_loss=0.06006, over 1304516.48 frames.], batch size: 23, lr: 9.42e-04
2022-04-28 18:50:57,360 INFO [train.py:763] (3/8) Epoch 7, batch 550, loss[loss=0.2138, simple_loss=0.312, pruned_loss=0.05782, over 7208.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2974, pruned_loss=0.05961, over 1332309.96 frames.], batch size: 23, lr: 9.41e-04
2022-04-28 18:52:02,631 INFO [train.py:763] (3/8) Epoch 7, batch 600, loss[loss=0.2145, simple_loss=0.3143, pruned_loss=0.05734, over 7220.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2998, pruned_loss=0.06077, over 1352486.15 frames.], batch size: 21, lr: 9.41e-04
2022-04-28 18:53:08,461 INFO [train.py:763] (3/8) Epoch 7, batch 650, loss[loss=0.2004, simple_loss=0.2883, pruned_loss=0.05625, over 7259.00 frames.], tot_loss[loss=0.2101, simple_loss=0.299, pruned_loss=0.06061, over 1368026.76 frames.], batch size: 19, lr: 9.40e-04
2022-04-28 18:54:13,817 INFO [train.py:763] (3/8) Epoch 7, batch 700, loss[loss=0.2562, simple_loss=0.3231, pruned_loss=0.09472, over 5277.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2995, pruned_loss=0.06103, over 1377767.63 frames.], batch size: 52, lr: 9.39e-04
2022-04-28 18:55:19,474 INFO [train.py:763] (3/8) Epoch 7, batch 750, loss[loss=0.1837, simple_loss=0.2736, pruned_loss=0.04687, over 7357.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2991, pruned_loss=0.0609, over 1385656.94 frames.], batch size: 19, lr: 9.39e-04
2022-04-28 18:56:26,108 INFO [train.py:763] (3/8) Epoch 7, batch 800, loss[loss=0.1988, simple_loss=0.2949, pruned_loss=0.05138, over 6301.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3009, pruned_loss=0.06174, over 1390665.73 frames.], batch size: 37, lr: 9.38e-04
2022-04-28 18:57:33,277 INFO [train.py:763] (3/8) Epoch 7, batch 850, loss[loss=0.1698, simple_loss=0.2616, pruned_loss=0.03896, over 7429.00 frames.], tot_loss[loss=0.2096, simple_loss=0.2984, pruned_loss=0.06043, over 1398862.29 frames.], batch size: 18, lr: 9.37e-04
2022-04-28 18:58:40,226 INFO [train.py:763] (3/8) Epoch 7, batch 900, loss[loss=0.2358, simple_loss=0.3232, pruned_loss=0.07422, over 6780.00 frames.], tot_loss[loss=0.21, simple_loss=0.2985, pruned_loss=0.0608, over 1399378.58 frames.], batch size: 31, lr: 9.36e-04
2022-04-28 18:59:46,946 INFO [train.py:763] (3/8) Epoch 7, batch 950, loss[loss=0.2344, simple_loss=0.3147, pruned_loss=0.07709, over 7234.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2987, pruned_loss=0.06054, over 1404811.03 frames.], batch size: 20, lr: 9.36e-04
2022-04-28 19:00:52,051 INFO [train.py:763] (3/8) Epoch 7, batch 1000, loss[loss=0.2114, simple_loss=0.313, pruned_loss=0.05487, over 7225.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2991, pruned_loss=0.0605, over 1408856.36 frames.], batch size: 21, lr: 9.35e-04
2022-04-28 19:01:58,577 INFO [train.py:763] (3/8) Epoch 7, batch 1050, loss[loss=0.2296, simple_loss=0.296, pruned_loss=0.08156, over 7133.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2994, pruned_loss=0.06067, over 1407484.71 frames.], batch size: 17, lr: 9.34e-04
2022-04-28 19:03:05,227 INFO [train.py:763] (3/8) Epoch 7, batch 1100, loss[loss=0.2224, simple_loss=0.3124, pruned_loss=0.06619, over 7201.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2985, pruned_loss=0.06043, over 1412260.67 frames.], batch size: 22, lr: 9.34e-04
2022-04-28 19:04:11,932 INFO [train.py:763] (3/8) Epoch 7, batch 1150, loss[loss=0.3239, simple_loss=0.3767, pruned_loss=0.1355, over 4713.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2994, pruned_loss=0.06057, over 1416709.12 frames.], batch size: 52, lr: 9.33e-04
2022-04-28 19:05:18,438 INFO [train.py:763] (3/8) Epoch 7, batch 1200, loss[loss=0.1953, simple_loss=0.2956, pruned_loss=0.0475, over 7158.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2996, pruned_loss=0.06068, over 1419881.51 frames.], batch size: 20, lr: 9.32e-04
2022-04-28 19:06:24,031 INFO [train.py:763] (3/8) Epoch 7, batch 1250, loss[loss=0.1967, simple_loss=0.2828, pruned_loss=0.05529, over 7270.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2986, pruned_loss=0.06063, over 1419410.12 frames.], batch size: 18, lr: 9.32e-04
2022-04-28 19:07:30,157 INFO [train.py:763] (3/8) Epoch 7, batch 1300, loss[loss=0.1884, simple_loss=0.2899, pruned_loss=0.04348, over 7150.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2995, pruned_loss=0.06093, over 1416269.74 frames.], batch size: 20, lr: 9.31e-04
2022-04-28 19:08:35,480 INFO [train.py:763] (3/8) Epoch 7, batch 1350, loss[loss=0.2244, simple_loss=0.3069, pruned_loss=0.07099, over 7156.00 frames.], tot_loss[loss=0.2122, simple_loss=0.3009, pruned_loss=0.06177, over 1414935.59 frames.], batch size: 19, lr: 9.30e-04
2022-04-28 19:09:41,318 INFO [train.py:763] (3/8) Epoch 7, batch 1400, loss[loss=0.1874, simple_loss=0.2746, pruned_loss=0.05015, over 7266.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2997, pruned_loss=0.06078, over 1416084.96 frames.], batch size: 18, lr: 9.30e-04
2022-04-28 19:10:48,153 INFO [train.py:763] (3/8) Epoch 7, batch 1450, loss[loss=0.2356, simple_loss=0.3154, pruned_loss=0.07795, over 7168.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2999, pruned_loss=0.0608, over 1416158.79 frames.], batch size: 18, lr: 9.29e-04
2022-04-28 19:11:54,399 INFO [train.py:763] (3/8) Epoch 7, batch 1500, loss[loss=0.1788, simple_loss=0.2702, pruned_loss=0.04367, over 7411.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2984, pruned_loss=0.06024, over 1416427.03 frames.], batch size: 18, lr: 9.28e-04
2022-04-28 19:12:59,476 INFO [train.py:763] (3/8) Epoch 7, batch 1550, loss[loss=0.2019, simple_loss=0.2904, pruned_loss=0.05668, over 7205.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2989, pruned_loss=0.06009, over 1421406.59 frames.], batch size: 22, lr: 9.28e-04
2022-04-28 19:14:04,514 INFO [train.py:763] (3/8) Epoch 7, batch 1600, loss[loss=0.2247, simple_loss=0.3159, pruned_loss=0.06673, over 6343.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2999, pruned_loss=0.06061, over 1421615.16 frames.], batch size: 37, lr: 9.27e-04
2022-04-28 19:15:09,643 INFO [train.py:763] (3/8) Epoch 7, batch 1650, loss[loss=0.214, simple_loss=0.3177, pruned_loss=0.05518, over 7266.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2995, pruned_loss=0.06049, over 1419953.32 frames.], batch size: 24, lr: 9.26e-04
2022-04-28 19:16:15,822 INFO [train.py:763] (3/8) Epoch 7, batch 1700, loss[loss=0.1874, simple_loss=0.2816, pruned_loss=0.04656, over 7316.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2999, pruned_loss=0.06066, over 1420311.58 frames.], batch size: 21, lr: 9.26e-04
2022-04-28 19:17:22,173 INFO [train.py:763] (3/8) Epoch 7, batch 1750, loss[loss=0.2427, simple_loss=0.3342, pruned_loss=0.07566, over 7337.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2996, pruned_loss=0.0606, over 1420788.30 frames.], batch size: 22, lr: 9.25e-04
2022-04-28 19:18:45,817 INFO [train.py:763] (3/8) Epoch 7, batch 1800, loss[loss=0.2065, simple_loss=0.3031, pruned_loss=0.05496, over 7331.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2977, pruned_loss=0.05952, over 1421929.54 frames.], batch size: 22, lr: 9.24e-04
2022-04-28 19:19:59,991 INFO [train.py:763] (3/8) Epoch 7, batch 1850, loss[loss=0.1926, simple_loss=0.291, pruned_loss=0.04714, over 7236.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2986, pruned_loss=0.05997, over 1423384.37 frames.], batch size: 20, lr: 9.24e-04
2022-04-28 19:21:23,367 INFO [train.py:763] (3/8) Epoch 7, batch 1900, loss[loss=0.198, simple_loss=0.2902, pruned_loss=0.05286, over 7295.00 frames.], tot_loss[loss=0.207, simple_loss=0.2961, pruned_loss=0.05901, over 1423120.64 frames.], batch size: 25, lr: 9.23e-04
2022-04-28 19:22:40,068 INFO [train.py:763] (3/8) Epoch 7, batch 1950, loss[loss=0.1723, simple_loss=0.2569, pruned_loss=0.04383, over 6995.00 frames.], tot_loss[loss=0.207, simple_loss=0.2959, pruned_loss=0.0591, over 1427187.77 frames.], batch size: 16, lr: 9.22e-04
2022-04-28 19:23:47,452 INFO [train.py:763] (3/8) Epoch 7, batch 2000, loss[loss=0.2331, simple_loss=0.321, pruned_loss=0.07257, over 7121.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2978, pruned_loss=0.06004, over 1427472.10 frames.], batch size: 21, lr: 9.22e-04
2022-04-28 19:25:02,869 INFO [train.py:763] (3/8) Epoch 7, batch 2050, loss[loss=0.2263, simple_loss=0.3129, pruned_loss=0.0698, over 5223.00 frames.], tot_loss[loss=0.2093, simple_loss=0.2985, pruned_loss=0.06009, over 1422043.50 frames.], batch size: 52, lr: 9.21e-04
2022-04-28 19:26:07,937 INFO [train.py:763] (3/8) Epoch 7, batch 2100, loss[loss=0.2199, simple_loss=0.3165, pruned_loss=0.06168, over 7224.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2989, pruned_loss=0.06027, over 1418439.48 frames.], batch size: 20, lr: 9.20e-04
2022-04-28 19:27:22,247 INFO [train.py:763] (3/8) Epoch 7, batch 2150, loss[loss=0.2408, simple_loss=0.318, pruned_loss=0.0818, over 7196.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2975, pruned_loss=0.05984, over 1419933.76 frames.], batch size: 22, lr: 9.20e-04
2022-04-28 19:28:27,687 INFO [train.py:763] (3/8) Epoch 7, batch 2200, loss[loss=0.2427, simple_loss=0.3283, pruned_loss=0.07852, over 7296.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2967, pruned_loss=0.05975, over 1418098.83 frames.], batch size: 24, lr: 9.19e-04
2022-04-28 19:29:32,842 INFO [train.py:763] (3/8) Epoch 7, batch 2250, loss[loss=0.1823, simple_loss=0.2765, pruned_loss=0.04407, over 7206.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2961, pruned_loss=0.06, over 1412833.92 frames.], batch size: 23, lr: 9.18e-04
2022-04-28 19:30:38,170 INFO [train.py:763] (3/8) Epoch 7, batch 2300, loss[loss=0.1962, simple_loss=0.2789, pruned_loss=0.05676, over 7411.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2953, pruned_loss=0.05942, over 1413246.96 frames.], batch size: 18, lr: 9.18e-04
2022-04-28 19:31:43,912 INFO [train.py:763] (3/8) Epoch 7, batch 2350, loss[loss=0.1882, simple_loss=0.2812, pruned_loss=0.04764, over 7068.00 frames.], tot_loss[loss=0.207, simple_loss=0.2955, pruned_loss=0.05926, over 1413293.10 frames.], batch size: 18, lr: 9.17e-04
2022-04-28 19:32:50,592 INFO [train.py:763] (3/8) Epoch 7, batch 2400, loss[loss=0.1579, simple_loss=0.2529, pruned_loss=0.0315, over 7263.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2958, pruned_loss=0.05935, over 1416692.58 frames.], batch size: 19, lr: 9.16e-04
2022-04-28 19:33:55,902 INFO [train.py:763] (3/8) Epoch 7, batch 2450, loss[loss=0.2192, simple_loss=0.3061, pruned_loss=0.06621, over 7281.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2963, pruned_loss=0.05926, over 1422886.78 frames.], batch size: 24, lr: 9.16e-04
2022-04-28 19:35:01,301 INFO [train.py:763] (3/8) Epoch 7, batch 2500, loss[loss=0.1991, simple_loss=0.2885, pruned_loss=0.05484, over 7325.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2979, pruned_loss=0.06022, over 1421094.52 frames.], batch size: 21, lr: 9.15e-04
2022-04-28 19:36:06,925 INFO [train.py:763] (3/8) Epoch 7, batch 2550, loss[loss=0.1939, simple_loss=0.2816, pruned_loss=0.05306, over 7364.00 frames.], tot_loss[loss=0.208, simple_loss=0.2969, pruned_loss=0.05952, over 1425974.82 frames.], batch size: 19, lr: 9.14e-04
2022-04-28 19:37:12,483 INFO [train.py:763] (3/8) Epoch 7, batch 2600, loss[loss=0.1937, simple_loss=0.275, pruned_loss=0.05618, over 6816.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2962, pruned_loss=0.0592, over 1425646.05 frames.], batch size: 15, lr: 9.14e-04
2022-04-28 19:38:17,713 INFO [train.py:763] (3/8) Epoch 7, batch 2650, loss[loss=0.1989, simple_loss=0.2997, pruned_loss=0.04901, over 7101.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2969, pruned_loss=0.05917, over 1426352.57 frames.], batch size: 21, lr: 9.13e-04
2022-04-28 19:39:23,648 INFO [train.py:763] (3/8) Epoch 7, batch 2700, loss[loss=0.1682, simple_loss=0.2507, pruned_loss=0.04281, over 6781.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2971, pruned_loss=0.05952, over 1428481.82 frames.], batch size: 15, lr: 9.12e-04
2022-04-28 19:40:30,719 INFO [train.py:763] (3/8) Epoch 7, batch 2750, loss[loss=0.1894, simple_loss=0.2634, pruned_loss=0.05772, over 6990.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2962, pruned_loss=0.05917, over 1427034.70 frames.], batch size: 16, lr: 9.12e-04
2022-04-28 19:41:36,692 INFO [train.py:763] (3/8) Epoch 7, batch 2800, loss[loss=0.2155, simple_loss=0.2988, pruned_loss=0.06609, over 7143.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2959, pruned_loss=0.05893, over 1427780.65 frames.], batch size: 20, lr: 9.11e-04
2022-04-28 19:42:43,485 INFO [train.py:763] (3/8) Epoch 7, batch 2850, loss[loss=0.2673, simple_loss=0.3463, pruned_loss=0.09418, over 7202.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2968, pruned_loss=0.05916, over 1426617.16 frames.], batch size: 22, lr: 9.11e-04
2022-04-28 19:43:49,294 INFO [train.py:763] (3/8) Epoch 7, batch 2900, loss[loss=0.172, simple_loss=0.2552, pruned_loss=0.04438, over 7143.00 frames.], tot_loss[loss=0.2082, simple_loss=0.298, pruned_loss=0.05923, over 1425775.94 frames.], batch size: 17, lr: 9.10e-04
2022-04-28 19:44:55,755 INFO [train.py:763] (3/8) Epoch 7, batch 2950, loss[loss=0.1788, simple_loss=0.2657, pruned_loss=0.046, over 7070.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2958, pruned_loss=0.05871, over 1425120.82 frames.], batch size: 18, lr: 9.09e-04
2022-04-28 19:46:01,159 INFO [train.py:763] (3/8) Epoch 7, batch 3000, loss[loss=0.2769, simple_loss=0.3432, pruned_loss=0.1053, over 5148.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2961, pruned_loss=0.05878, over 1420681.02 frames.], batch size: 52, lr: 9.09e-04
2022-04-28 19:46:01,159 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 19:46:16,423 INFO [train.py:792] (3/8) Epoch 7, validation: loss=0.1713, simple_loss=0.2754, pruned_loss=0.03361, over 698248.00 frames.
2022-04-28 19:47:23,038 INFO [train.py:763] (3/8) Epoch 7, batch 3050, loss[loss=0.2348, simple_loss=0.323, pruned_loss=0.07335, over 6376.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2961, pruned_loss=0.05904, over 1413917.53 frames.], batch size: 38, lr: 9.08e-04
2022-04-28 19:48:28,734 INFO [train.py:763] (3/8) Epoch 7, batch 3100, loss[loss=0.1732, simple_loss=0.2616, pruned_loss=0.04242, over 7261.00 frames.], tot_loss[loss=0.206, simple_loss=0.2953, pruned_loss=0.0583, over 1419190.63 frames.], batch size: 19, lr: 9.07e-04
2022-04-28 19:49:34,313 INFO [train.py:763] (3/8) Epoch 7, batch 3150, loss[loss=0.1782, simple_loss=0.2692, pruned_loss=0.04363, over 7433.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2938, pruned_loss=0.05806, over 1421215.33 frames.], batch size: 20, lr: 9.07e-04
2022-04-28 19:50:39,918 INFO [train.py:763] (3/8) Epoch 7, batch 3200, loss[loss=0.185, simple_loss=0.2844, pruned_loss=0.04282, over 7430.00 frames.], tot_loss[loss=0.2038, simple_loss=0.293, pruned_loss=0.05728, over 1424109.20 frames.], batch size: 20, lr: 9.06e-04
2022-04-28 19:51:45,166 INFO [train.py:763] (3/8) Epoch 7, batch 3250, loss[loss=0.2401, simple_loss=0.3131, pruned_loss=0.08353, over 7023.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2947, pruned_loss=0.05809, over 1422568.56 frames.], batch size: 28, lr: 9.05e-04
2022-04-28 19:52:50,680 INFO [train.py:763] (3/8) Epoch 7, batch 3300, loss[loss=0.2423, simple_loss=0.3315, pruned_loss=0.07656, over 6712.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2943, pruned_loss=0.05799, over 1421363.24 frames.], batch size: 31, lr: 9.05e-04
2022-04-28 19:53:56,155 INFO [train.py:763] (3/8) Epoch 7, batch 3350, loss[loss=0.1799, simple_loss=0.2771, pruned_loss=0.04131, over 7433.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2952, pruned_loss=0.05852, over 1419344.97 frames.], batch size: 20, lr: 9.04e-04
2022-04-28 19:55:01,741 INFO [train.py:763] (3/8) Epoch 7, batch 3400, loss[loss=0.2159, simple_loss=0.3083, pruned_loss=0.06171, over 6804.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2953, pruned_loss=0.05866, over 1417821.72 frames.], batch size: 31, lr: 9.04e-04
2022-04-28 19:56:08,385 INFO [train.py:763] (3/8) Epoch 7, batch 3450, loss[loss=0.2296, simple_loss=0.3011, pruned_loss=0.07906, over 7406.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2968, pruned_loss=0.05936, over 1420938.31 frames.], batch size: 18, lr: 9.03e-04
2022-04-28 19:57:15,787 INFO [train.py:763] (3/8) Epoch 7, batch 3500, loss[loss=0.2491, simple_loss=0.3337, pruned_loss=0.08224, over 7360.00 frames.], tot_loss[loss=0.209, simple_loss=0.2982, pruned_loss=0.05993, over 1420884.58 frames.], batch size: 23, lr: 9.02e-04
2022-04-28 19:58:22,785 INFO [train.py:763] (3/8) Epoch 7, batch 3550, loss[loss=0.2298, simple_loss=0.3232, pruned_loss=0.06821, over 7259.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2973, pruned_loss=0.05981, over 1422581.75 frames.], batch size: 19, lr: 9.02e-04
2022-04-28 19:59:29,956 INFO [train.py:763] (3/8) Epoch 7, batch 3600, loss[loss=0.1805, simple_loss=0.2696, pruned_loss=0.04568, over 7268.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2963, pruned_loss=0.05929, over 1422050.81 frames.], batch size: 17, lr: 9.01e-04
2022-04-28 20:00:37,036 INFO [train.py:763] (3/8) Epoch 7, batch 3650, loss[loss=0.2088, simple_loss=0.2943, pruned_loss=0.06167, over 7410.00 frames.], tot_loss[loss=0.2086, simple_loss=0.2977, pruned_loss=0.05975, over 1416565.97 frames.], batch size: 21, lr: 9.01e-04
2022-04-28 20:01:42,540 INFO [train.py:763] (3/8) Epoch 7, batch 3700, loss[loss=0.2422, simple_loss=0.3387, pruned_loss=0.07287, over 7223.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2973, pruned_loss=0.05959, over 1420122.93 frames.], batch size: 21, lr: 9.00e-04
2022-04-28 20:02:49,191 INFO [train.py:763] (3/8) Epoch 7, batch 3750, loss[loss=0.1919, simple_loss=0.2935, pruned_loss=0.04514, over 7162.00 frames.], tot_loss[loss=0.2082, simple_loss=0.2975, pruned_loss=0.0595, over 1416580.73 frames.], batch size: 19, lr: 8.99e-04
2022-04-28 20:03:54,761 INFO [train.py:763] (3/8) Epoch 7, batch 3800, loss[loss=0.2516, simple_loss=0.3327, pruned_loss=0.08526, over 7282.00 frames.], tot_loss[loss=0.209, simple_loss=0.2983, pruned_loss=0.05988, over 1420114.42 frames.], batch size: 24, lr: 8.99e-04
2022-04-28 20:05:00,507 INFO [train.py:763] (3/8) Epoch 7, batch 3850, loss[loss=0.21, simple_loss=0.3007, pruned_loss=0.0596, over 7212.00 frames.], tot_loss[loss=0.2098, simple_loss=0.2995, pruned_loss=0.06003, over 1418290.29 frames.], batch size: 21, lr: 8.98e-04
2022-04-28 20:06:06,736 INFO [train.py:763] (3/8) Epoch 7, batch 3900, loss[loss=0.22, simple_loss=0.3184, pruned_loss=0.06078, over 7443.00 frames.], tot_loss[loss=0.208, simple_loss=0.2979, pruned_loss=0.05906, over 1422211.43 frames.], batch size: 20, lr: 8.97e-04
2022-04-28 20:07:13,247 INFO [train.py:763] (3/8) Epoch 7, batch 3950, loss[loss=0.1845, simple_loss=0.2721, pruned_loss=0.04848, over 7001.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2957, pruned_loss=0.05742, over 1424635.18 frames.], batch size: 16, lr: 8.97e-04
2022-04-28 20:08:18,735 INFO [train.py:763] (3/8) Epoch 7, batch 4000, loss[loss=0.1897, simple_loss=0.2828, pruned_loss=0.04824, over 7154.00 frames.], tot_loss[loss=0.2062, simple_loss=0.2968, pruned_loss=0.0578, over 1423476.85 frames.], batch size: 20, lr: 8.96e-04
2022-04-28 20:09:23,869 INFO [train.py:763] (3/8) Epoch 7, batch 4050, loss[loss=0.22, simple_loss=0.3, pruned_loss=0.07002, over 7418.00 frames.], tot_loss[loss=0.2057, simple_loss=0.296, pruned_loss=0.05773, over 1426051.48 frames.], batch size: 21, lr: 8.96e-04
2022-04-28 20:10:29,411 INFO [train.py:763] (3/8) Epoch 7, batch 4100, loss[loss=0.1873, simple_loss=0.2753, pruned_loss=0.04962, over 7266.00 frames.], tot_loss[loss=0.206, simple_loss=0.296, pruned_loss=0.05803, over 1419639.46 frames.], batch size: 17, lr: 8.95e-04
2022-04-28 20:11:34,140 INFO [train.py:763] (3/8) Epoch 7, batch 4150, loss[loss=0.2148, simple_loss=0.308, pruned_loss=0.06084, over 7335.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2967, pruned_loss=0.05819, over 1413980.50 frames.], batch size: 22, lr: 8.94e-04
2022-04-28 20:12:39,365 INFO [train.py:763] (3/8) Epoch 7, batch 4200, loss[loss=0.193, simple_loss=0.2877, pruned_loss=0.04914, over 7147.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2979, pruned_loss=0.05858, over 1416357.55 frames.], batch size: 20, lr: 8.94e-04
2022-04-28 20:13:44,889 INFO [train.py:763] (3/8) Epoch 7, batch 4250, loss[loss=0.2311, simple_loss=0.3255, pruned_loss=0.06833, over 7197.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2974, pruned_loss=0.05856, over 1420132.83 frames.], batch size: 22, lr: 8.93e-04
2022-04-28 20:14:50,388 INFO [train.py:763] (3/8) Epoch 7, batch 4300, loss[loss=0.2157, simple_loss=0.3145, pruned_loss=0.05849, over 7338.00 frames.], tot_loss[loss=0.2063, simple_loss=0.2963, pruned_loss=0.05809, over 1419487.93 frames.], batch size: 21, lr: 8.93e-04
2022-04-28 20:15:55,683 INFO [train.py:763] (3/8) Epoch 7, batch 4350, loss[loss=0.2376, simple_loss=0.3408, pruned_loss=0.0672, over 7101.00 frames.], tot_loss[loss=0.2057, simple_loss=0.2956, pruned_loss=0.05786, over 1415211.22 frames.], batch size: 21, lr: 8.92e-04
2022-04-28 20:17:01,780 INFO [train.py:763] (3/8) Epoch 7, batch 4400, loss[loss=0.2152, simple_loss=0.2993, pruned_loss=0.06557, over 7120.00 frames.], tot_loss[loss=0.2046, simple_loss=0.2942, pruned_loss=0.05745, over 1417543.95 frames.], batch size: 28, lr: 8.91e-04
2022-04-28 20:18:08,979 INFO [train.py:763] (3/8) Epoch 7, batch 4450, loss[loss=0.2373, simple_loss=0.3227, pruned_loss=0.07593, over 7327.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2942, pruned_loss=0.05765, over 1417461.50 frames.], batch size: 20, lr: 8.91e-04
2022-04-28 20:19:16,355 INFO [train.py:763] (3/8) Epoch 7, batch 4500, loss[loss=0.1699, simple_loss=0.2621, pruned_loss=0.03886, over 7150.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2937, pruned_loss=0.05763, over 1415771.81 frames.], batch size: 18, lr: 8.90e-04
2022-04-28 20:20:24,251 INFO [train.py:763] (3/8) Epoch 7, batch 4550, loss[loss=0.1628, simple_loss=0.2415, pruned_loss=0.04211, over 7272.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2934, pruned_loss=0.05873, over 1398004.18 frames.], batch size: 17, lr: 8.90e-04
2022-04-28 20:21:52,804 INFO [train.py:763] (3/8) Epoch 8, batch 0, loss[loss=0.1998, simple_loss=0.2952, pruned_loss=0.05223, over 7209.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2952, pruned_loss=0.05223, over 7209.00 frames.], batch size: 23, lr: 8.54e-04
2022-04-28 20:22:58,561 INFO [train.py:763] (3/8) Epoch 8, batch 50, loss[loss=0.2193, simple_loss=0.3121, pruned_loss=0.06322, over 7138.00 frames.], tot_loss[loss=0.2075, simple_loss=0.297, pruned_loss=0.05904, over 319899.55 frames.], batch size: 28, lr: 8.53e-04
2022-04-28 20:24:03,943 INFO [train.py:763] (3/8) Epoch 8, batch 100, loss[loss=0.1947, simple_loss=0.2933, pruned_loss=0.04802, over 7231.00 frames.], tot_loss[loss=0.2042, simple_loss=0.2943, pruned_loss=0.05703, over 567553.44 frames.], batch size: 20, lr: 8.53e-04
2022-04-28 20:25:10,090 INFO [train.py:763] (3/8) Epoch 8, batch 150, loss[loss=0.2322, simple_loss=0.3178, pruned_loss=0.07328, over 5320.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2954, pruned_loss=0.05723, over 754762.86 frames.], batch size: 52, lr: 8.52e-04
2022-04-28 20:26:16,005 INFO [train.py:763] (3/8) Epoch 8, batch 200, loss[loss=0.2286, simple_loss=0.3187, pruned_loss=0.0693, over 7216.00 frames.], tot_loss[loss=0.2043, simple_loss=0.295, pruned_loss=0.05675, over 904272.50 frames.], batch size: 22, lr: 8.51e-04
2022-04-28 20:27:21,273 INFO [train.py:763] (3/8) Epoch 8, batch 250, loss[loss=0.1926, simple_loss=0.2842, pruned_loss=0.05055, over 7430.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2943, pruned_loss=0.05629, over 1020367.28 frames.], batch size: 20, lr: 8.51e-04
2022-04-28 20:28:27,033 INFO [train.py:763] (3/8) Epoch 8, batch 300, loss[loss=0.1923, simple_loss=0.2919, pruned_loss=0.04636, over 7328.00 frames.], tot_loss[loss=0.2049, simple_loss=0.2953, pruned_loss=0.05725, over 1106005.68 frames.], batch size: 22, lr: 8.50e-04
2022-04-28 20:29:32,796 INFO [train.py:763] (3/8) Epoch 8, batch 350, loss[loss=0.2081, simple_loss=0.2945, pruned_loss=0.06082, over 7154.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2926, pruned_loss=0.05593, over 1180274.35 frames.], batch size: 19, lr: 8.50e-04
2022-04-28 20:30:38,285 INFO [train.py:763] (3/8) Epoch 8, batch 400, loss[loss=0.1798, simple_loss=0.2646, pruned_loss=0.0475, over 7129.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2932, pruned_loss=0.05626, over 1239370.10 frames.], batch size: 17, lr: 8.49e-04
2022-04-28 20:31:43,712 INFO [train.py:763] (3/8) Epoch 8, batch 450, loss[loss=0.1624, simple_loss=0.2615, pruned_loss=0.03162, over 7247.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2927, pruned_loss=0.05614, over 1278917.60 frames.], batch size: 19, lr: 8.49e-04
2022-04-28 20:32:50,561 INFO [train.py:763] (3/8) Epoch 8, batch 500, loss[loss=0.1841, simple_loss=0.2611, pruned_loss=0.05355, over 7414.00 frames.], tot_loss[loss=0.204, simple_loss=0.2942, pruned_loss=0.05697, over 1311890.49 frames.], batch size: 18, lr: 8.48e-04
2022-04-28 20:33:57,711 INFO [train.py:763] (3/8) Epoch 8, batch 550, loss[loss=0.2025, simple_loss=0.2911, pruned_loss=0.05693, over 7456.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2939, pruned_loss=0.05626, over 1340114.67 frames.], batch size: 19, lr: 8.48e-04
2022-04-28 20:35:03,798 INFO [train.py:763] (3/8) Epoch 8, batch 600, loss[loss=0.1903, simple_loss=0.2858, pruned_loss=0.04735, over 7078.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2935, pruned_loss=0.05588, over 1361587.71 frames.], batch size: 18, lr: 8.47e-04
2022-04-28 20:36:09,108 INFO [train.py:763] (3/8) Epoch 8, batch 650, loss[loss=0.2055, simple_loss=0.2983, pruned_loss=0.05633, over 7358.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2943, pruned_loss=0.05623, over 1374983.32 frames.], batch size: 19, lr: 8.46e-04
2022-04-28 20:37:14,552 INFO [train.py:763] (3/8) Epoch 8, batch 700, loss[loss=0.1976, simple_loss=0.2852, pruned_loss=0.05505, over 7441.00 frames.], tot_loss[loss=0.202, simple_loss=0.2933, pruned_loss=0.05538, over 1387061.48 frames.], batch size: 20, lr: 8.46e-04
2022-04-28 20:38:20,313 INFO [train.py:763] (3/8) Epoch 8, batch 750, loss[loss=0.1904, simple_loss=0.2805, pruned_loss=0.05021, over 7174.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2926, pruned_loss=0.05523, over 1390520.33 frames.], batch size: 18, lr: 8.45e-04
2022-04-28 20:39:25,912 INFO [train.py:763] (3/8) Epoch 8, batch 800, loss[loss=0.2019, simple_loss=0.3008, pruned_loss=0.05148, over 7399.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2926, pruned_loss=0.05552, over 1396565.97 frames.], batch size: 23, lr: 8.45e-04
2022-04-28 20:40:32,528 INFO [train.py:763] (3/8) Epoch 8, batch 850, loss[loss=0.1968, simple_loss=0.3002, pruned_loss=0.04668, over 7316.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2929, pruned_loss=0.05579, over 1402113.76 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:41:39,526 INFO [train.py:763] (3/8) Epoch 8, batch 900, loss[loss=0.2479, simple_loss=0.3311, pruned_loss=0.08233, over 7221.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2924, pruned_loss=0.05531, over 1410811.27 frames.], batch size: 21, lr: 8.44e-04
2022-04-28 20:42:46,672 INFO [train.py:763] (3/8) Epoch 8, batch 950, loss[loss=0.1888, simple_loss=0.2917, pruned_loss=0.04299, over 7331.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2924, pruned_loss=0.05524, over 1408278.03 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:43:53,791 INFO [train.py:763] (3/8) Epoch 8, batch 1000, loss[loss=0.1848, simple_loss=0.2725, pruned_loss=0.04851, over 7440.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2921, pruned_loss=0.05527, over 1412877.81 frames.], batch size: 20, lr: 8.43e-04
2022-04-28 20:45:00,937 INFO [train.py:763] (3/8) Epoch 8, batch 1050, loss[loss=0.1769, simple_loss=0.2609, pruned_loss=0.04643, over 7251.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2924, pruned_loss=0.05548, over 1417717.22 frames.], batch size: 19, lr: 8.42e-04
2022-04-28 20:46:07,160 INFO [train.py:763] (3/8) Epoch 8, batch 1100, loss[loss=0.1728, simple_loss=0.2569, pruned_loss=0.04438, over 7272.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2941, pruned_loss=0.05599, over 1420165.16 frames.], batch size: 17, lr: 8.41e-04
2022-04-28 20:47:12,899 INFO [train.py:763] (3/8) Epoch 8, batch 1150, loss[loss=0.1997, simple_loss=0.2941, pruned_loss=0.05263, over 7296.00 frames.], tot_loss[loss=0.203, simple_loss=0.2935, pruned_loss=0.05625, over 1420192.14 frames.], batch size: 25, lr: 8.41e-04
2022-04-28 20:48:18,241 INFO [train.py:763] (3/8) Epoch 8, batch 1200, loss[loss=0.1722, simple_loss=0.2645, pruned_loss=0.03997, over 7436.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2925, pruned_loss=0.05563, over 1420707.11 frames.], batch size: 20, lr: 8.40e-04
2022-04-28 20:49:23,427 INFO [train.py:763] (3/8) Epoch 8, batch 1250, loss[loss=0.1784, simple_loss=0.2563, pruned_loss=0.05022, over 6792.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2912, pruned_loss=0.05495, over 1416180.05 frames.], batch size: 15, lr: 8.40e-04
2022-04-28 20:50:29,921 INFO [train.py:763] (3/8) Epoch 8, batch 1300, loss[loss=0.226, simple_loss=0.3046, pruned_loss=0.07368, over 7161.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2921, pruned_loss=0.05541, over 1413088.70 frames.], batch size: 19, lr: 8.39e-04
2022-04-28 20:51:37,148 INFO [train.py:763] (3/8) Epoch 8, batch 1350, loss[loss=0.1885, simple_loss=0.2728, pruned_loss=0.05215, over 7411.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2927, pruned_loss=0.05587, over 1418502.58 frames.], batch size: 20, lr: 8.39e-04
2022-04-28 20:52:43,211 INFO [train.py:763] (3/8) Epoch 8, batch 1400, loss[loss=0.2135, simple_loss=0.31, pruned_loss=0.0585, over 7222.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2926, pruned_loss=0.05606, over 1415140.87 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:53:48,891 INFO [train.py:763] (3/8) Epoch 8, batch 1450, loss[loss=0.1981, simple_loss=0.293, pruned_loss=0.0516, over 7321.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2914, pruned_loss=0.05555, over 1419866.44 frames.], batch size: 21, lr: 8.38e-04
2022-04-28 20:54:55,523 INFO [train.py:763] (3/8) Epoch 8, batch 1500, loss[loss=0.1963, simple_loss=0.2964, pruned_loss=0.04812, over 7234.00 frames.], tot_loss[loss=0.201, simple_loss=0.2916, pruned_loss=0.05518, over 1422997.63 frames.], batch size: 20, lr: 8.37e-04
2022-04-28 20:56:02,359 INFO [train.py:763] (3/8) Epoch 8, batch 1550, loss[loss=0.1993, simple_loss=0.2925, pruned_loss=0.05307, over 7208.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2913, pruned_loss=0.05514, over 1422444.40 frames.], batch size: 22, lr: 8.37e-04
2022-04-28 20:57:08,587 INFO [train.py:763] (3/8) Epoch 8, batch 1600, loss[loss=0.1983, simple_loss=0.2819, pruned_loss=0.0574, over 7055.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2925, pruned_loss=0.05517, over 1420359.31 frames.], batch size: 18, lr: 8.36e-04
2022-04-28 20:58:15,579 INFO [train.py:763] (3/8) Epoch 8, batch 1650, loss[loss=0.198, simple_loss=0.2906, pruned_loss=0.05268, over 7116.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2929, pruned_loss=0.05585, over 1422013.79 frames.], batch size: 21, lr: 8.35e-04
2022-04-28 20:59:22,335 INFO [train.py:763] (3/8) Epoch 8, batch 1700, loss[loss=0.1874, simple_loss=0.2874, pruned_loss=0.04368, over 7148.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2932, pruned_loss=0.05556, over 1420810.96 frames.], batch size: 20, lr: 8.35e-04
2022-04-28 21:00:28,778 INFO [train.py:763] (3/8) Epoch 8, batch 1750, loss[loss=0.1983, simple_loss=0.3038, pruned_loss=0.04647, over 7316.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2928, pruned_loss=0.05573, over 1422840.65 frames.], batch size: 21, lr: 8.34e-04
2022-04-28 21:01:33,979 INFO [train.py:763] (3/8) Epoch 8, batch 1800, loss[loss=0.2229, simple_loss=0.3221, pruned_loss=0.06186, over 7230.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2937, pruned_loss=0.05626, over 1419386.31 frames.], batch size: 20, lr: 8.34e-04
2022-04-28 21:02:39,282 INFO [train.py:763] (3/8) Epoch 8, batch 1850, loss[loss=0.1866, simple_loss=0.2849, pruned_loss=0.04413, over 7224.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2941, pruned_loss=0.05638, over 1421768.10 frames.], batch size: 20, lr: 8.33e-04
2022-04-28 21:03:44,675 INFO [train.py:763] (3/8) Epoch 8, batch 1900, loss[loss=0.2057, simple_loss=0.2905, pruned_loss=0.06045, over 7160.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2948, pruned_loss=0.05673, over 1420030.35 frames.], batch size: 19, lr: 8.33e-04
2022-04-28 21:04:50,204 INFO [train.py:763] (3/8) Epoch 8, batch 1950, loss[loss=0.2159, simple_loss=0.3079, pruned_loss=0.06195, over 7111.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2934, pruned_loss=0.05581, over 1421378.35 frames.], batch size: 21, lr: 8.32e-04
2022-04-28 21:05:55,498 INFO [train.py:763] (3/8) Epoch 8, batch 2000, loss[loss=0.2104, simple_loss=0.3088, pruned_loss=0.05597, over 7273.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2922, pruned_loss=0.05472, over 1422643.83 frames.], batch size: 24, lr: 8.32e-04
2022-04-28 21:07:00,730 INFO [train.py:763] (3/8) Epoch 8, batch 2050, loss[loss=0.1765, simple_loss=0.2639, pruned_loss=0.04457, over 7283.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2925, pruned_loss=0.05534, over 1420990.67 frames.], batch size: 17, lr: 8.31e-04
2022-04-28 21:08:05,936 INFO [train.py:763] (3/8) Epoch 8, batch 2100, loss[loss=0.1953, simple_loss=0.2765, pruned_loss=0.05704, over 7264.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2923, pruned_loss=0.05521, over 1423188.47 frames.], batch size: 19, lr: 8.31e-04
2022-04-28 21:09:08,023 INFO [train.py:763] (3/8) Epoch 8, batch 2150, loss[loss=0.2179, simple_loss=0.2931, pruned_loss=0.0713, over 7067.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2924, pruned_loss=0.05534, over 1426053.70 frames.], batch size: 18, lr: 8.30e-04
2022-04-28 21:10:14,557 INFO [train.py:763] (3/8) Epoch 8, batch 2200, loss[loss=0.1774, simple_loss=0.2616, pruned_loss=0.04658, over 7295.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2917, pruned_loss=0.05506, over 1424231.28 frames.], batch size: 17, lr: 8.30e-04
2022-04-28 21:11:21,396 INFO [train.py:763] (3/8) Epoch 8, batch 2250, loss[loss=0.206, simple_loss=0.2924, pruned_loss=0.05979, over 7157.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2925, pruned_loss=0.05544, over 1424714.72 frames.], batch size: 18, lr: 8.29e-04
2022-04-28 21:12:26,807 INFO [train.py:763] (3/8) Epoch 8, batch 2300, loss[loss=0.191, simple_loss=0.2839, pruned_loss=0.04907, over 7154.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2924, pruned_loss=0.05532, over 1426228.31 frames.], batch size: 20, lr: 8.29e-04
2022-04-28 21:13:32,125 INFO [train.py:763] (3/8) Epoch 8, batch 2350, loss[loss=0.2199, simple_loss=0.3101, pruned_loss=0.06488, over 6728.00 frames.], tot_loss[loss=0.2022, simple_loss=0.293, pruned_loss=0.05566, over 1424905.36 frames.], batch size: 31, lr: 8.28e-04
2022-04-28 21:14:37,449 INFO [train.py:763] (3/8) Epoch 8, batch 2400, loss[loss=0.2078, simple_loss=0.2851, pruned_loss=0.06526, over 7287.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2931, pruned_loss=0.05579, over 1424967.43 frames.], batch size: 18, lr: 8.28e-04
2022-04-28 21:15:42,877 INFO [train.py:763] (3/8) Epoch 8, batch 2450, loss[loss=0.1831, simple_loss=0.2663, pruned_loss=0.04992, over 7406.00 frames.], tot_loss[loss=0.2022, simple_loss=0.293, pruned_loss=0.05571, over 1425996.51 frames.], batch size: 18, lr: 8.27e-04
2022-04-28 21:16:48,163 INFO [train.py:763] (3/8) Epoch 8, batch 2500, loss[loss=0.2424, simple_loss=0.3421, pruned_loss=0.07134, over 7206.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2943, pruned_loss=0.05652, over 1423671.70 frames.], batch size: 22, lr: 8.27e-04
2022-04-28 21:17:53,462 INFO [train.py:763] (3/8) Epoch 8, batch 2550, loss[loss=0.1981, simple_loss=0.2792, pruned_loss=0.05848, over 7141.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2933, pruned_loss=0.05629, over 1421083.83 frames.], batch size: 17, lr: 8.26e-04
2022-04-28 21:18:58,783 INFO [train.py:763] (3/8) Epoch 8, batch 2600, loss[loss=0.2474, simple_loss=0.3299, pruned_loss=0.0825, over 7365.00 frames.], tot_loss[loss=0.2044, simple_loss=0.2945, pruned_loss=0.05719, over 1418526.56 frames.], batch size: 23, lr: 8.25e-04
2022-04-28 21:20:03,878 INFO [train.py:763] (3/8) Epoch 8, batch 2650, loss[loss=0.2484, simple_loss=0.3181, pruned_loss=0.08939, over 5211.00 frames.], tot_loss[loss=0.2036, simple_loss=0.2937, pruned_loss=0.05671, over 1417279.85 frames.], batch size: 52, lr: 8.25e-04
2022-04-28 21:21:09,314 INFO [train.py:763] (3/8) Epoch 8, batch 2700, loss[loss=0.1868, simple_loss=0.2943, pruned_loss=0.03966, over 7328.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2936, pruned_loss=0.05605, over 1418850.47 frames.], batch size: 22, lr: 8.24e-04
2022-04-28 21:22:14,615 INFO [train.py:763] (3/8) Epoch 8, batch 2750, loss[loss=0.2061, simple_loss=0.29, pruned_loss=0.06109, over 7324.00 frames.], tot_loss[loss=0.2023, simple_loss=0.293, pruned_loss=0.05582, over 1423170.22 frames.], batch size: 20, lr: 8.24e-04
2022-04-28 21:23:20,616 INFO [train.py:763] (3/8) Epoch 8, batch 2800, loss[loss=0.1989, simple_loss=0.2957, pruned_loss=0.05106, over 7184.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2931, pruned_loss=0.05614, over 1426557.03 frames.], batch size: 22, lr: 8.23e-04
2022-04-28 21:24:26,772 INFO [train.py:763] (3/8) Epoch 8, batch 2850, loss[loss=0.1965, simple_loss=0.2987, pruned_loss=0.04715, over 7155.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2927, pruned_loss=0.05554, over 1428849.65 frames.], batch size: 19, lr: 8.23e-04
2022-04-28 21:25:32,042 INFO [train.py:763] (3/8) Epoch 8, batch 2900, loss[loss=0.2124, simple_loss=0.306, pruned_loss=0.05934, over 7327.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2925, pruned_loss=0.05535, over 1426815.29 frames.], batch size: 21, lr: 8.22e-04
2022-04-28 21:26:37,470 INFO [train.py:763] (3/8) Epoch 8, batch 2950, loss[loss=0.178, simple_loss=0.2602, pruned_loss=0.04787, over 7276.00 frames.], tot_loss[loss=0.2039, simple_loss=0.2943, pruned_loss=0.05672, over 1422571.23 frames.], batch size: 18, lr: 8.22e-04
2022-04-28 21:27:43,085 INFO [train.py:763] (3/8) Epoch 8, batch 3000, loss[loss=0.2032, simple_loss=0.2968, pruned_loss=0.05479, over 7305.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2942, pruned_loss=0.05672, over 1420768.49 frames.], batch size: 24, lr: 8.21e-04
2022-04-28 21:27:43,086 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 21:27:58,489 INFO [train.py:792] (3/8) Epoch 8, validation: loss=0.1715, simple_loss=0.2766, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 21:29:04,151 INFO [train.py:763] (3/8) Epoch 8, batch 3050, loss[loss=0.1938, simple_loss=0.2828, pruned_loss=0.05246, over 7325.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2936, pruned_loss=0.0566, over 1417245.41 frames.], batch size: 20, lr: 8.21e-04
2022-04-28 21:30:09,330 INFO [train.py:763] (3/8) Epoch 8, batch 3100, loss[loss=0.2687, simple_loss=0.3505, pruned_loss=0.09348, over 6716.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2953, pruned_loss=0.05762, over 1412759.49 frames.], batch size: 31, lr: 8.20e-04
2022-04-28 21:31:14,875 INFO [train.py:763] (3/8) Epoch 8, batch 3150, loss[loss=0.1913, simple_loss=0.2908, pruned_loss=0.04593, over 7151.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2942, pruned_loss=0.057, over 1417245.74 frames.], batch size: 19, lr: 8.20e-04
2022-04-28 21:32:20,533 INFO [train.py:763] (3/8) Epoch 8, batch 3200, loss[loss=0.2119, simple_loss=0.3006, pruned_loss=0.06158, over 7148.00 frames.], tot_loss[loss=0.203, simple_loss=0.2932, pruned_loss=0.05646, over 1420538.50 frames.], batch size: 20, lr: 8.19e-04
2022-04-28 21:33:34,630 INFO [train.py:763] (3/8) Epoch 8, batch 3250, loss[loss=0.249, simple_loss=0.3215, pruned_loss=0.0882, over 5133.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2931, pruned_loss=0.05657, over 1418905.65 frames.], batch size: 54, lr: 8.19e-04
2022-04-28 21:34:51,671 INFO [train.py:763] (3/8) Epoch 8, batch 3300, loss[loss=0.1998, simple_loss=0.2916, pruned_loss=0.05401, over 7218.00 frames.], tot_loss[loss=0.2019, simple_loss=0.292, pruned_loss=0.05595, over 1419169.99 frames.], batch size: 22, lr: 8.18e-04
2022-04-28 21:36:05,890 INFO [train.py:763] (3/8) Epoch 8, batch 3350, loss[loss=0.1838, simple_loss=0.2716, pruned_loss=0.04801, over 7247.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2921, pruned_loss=0.0556, over 1423203.03 frames.], batch size: 19, lr: 8.18e-04
2022-04-28 21:37:39,078 INFO [train.py:763] (3/8) Epoch 8, batch 3400, loss[loss=0.2156, simple_loss=0.3102, pruned_loss=0.06052, over 6740.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2927, pruned_loss=0.05541, over 1421616.06 frames.], batch size: 31, lr: 8.17e-04
2022-04-28 21:38:45,185 INFO [train.py:763] (3/8) Epoch 8, batch 3450, loss[loss=0.1988, simple_loss=0.2832, pruned_loss=0.05724, over 7402.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2935, pruned_loss=0.05615, over 1423832.00 frames.], batch size: 18, lr: 8.17e-04
2022-04-28 21:40:00,474 INFO [train.py:763] (3/8) Epoch 8, batch 3500, loss[loss=0.1953, simple_loss=0.2871, pruned_loss=0.05179, over 7151.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2937, pruned_loss=0.0564, over 1424690.79 frames.], batch size: 19, lr: 8.16e-04
2022-04-28 21:41:15,117 INFO [train.py:763] (3/8) Epoch 8, batch 3550, loss[loss=0.1777, simple_loss=0.2669, pruned_loss=0.04426, over 7174.00 frames.], tot_loss[loss=0.203, simple_loss=0.2933, pruned_loss=0.0563, over 1426081.22 frames.], batch size: 18, lr: 8.16e-04
2022-04-28 21:42:20,506 INFO [train.py:763] (3/8) Epoch 8, batch 3600, loss[loss=0.2082, simple_loss=0.2865, pruned_loss=0.06491, over 7270.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2933, pruned_loss=0.05607, over 1423985.55 frames.], batch size: 18, lr: 8.15e-04
2022-04-28 21:43:26,012 INFO [train.py:763] (3/8) Epoch 8, batch 3650, loss[loss=0.1838, simple_loss=0.2609, pruned_loss=0.05333, over 7147.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2926, pruned_loss=0.05552, over 1425997.27 frames.], batch size: 17, lr: 8.15e-04
2022-04-28 21:44:39,930 INFO [train.py:763] (3/8) Epoch 8, batch 3700, loss[loss=0.2132, simple_loss=0.31, pruned_loss=0.05814, over 7298.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2934, pruned_loss=0.05573, over 1426817.84 frames.], batch size: 25, lr: 8.14e-04
2022-04-28 21:45:45,258 INFO [train.py:763] (3/8) Epoch 8, batch 3750, loss[loss=0.192, simple_loss=0.2889, pruned_loss=0.04758, over 7421.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2933, pruned_loss=0.05546, over 1425021.35 frames.], batch size: 20, lr: 8.14e-04
2022-04-28 21:46:51,549 INFO [train.py:763] (3/8) Epoch 8, batch 3800, loss[loss=0.1712, simple_loss=0.2611, pruned_loss=0.04065, over 7416.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2941, pruned_loss=0.05591, over 1426924.96 frames.], batch size: 18, lr: 8.13e-04
2022-04-28 21:47:57,461 INFO [train.py:763] (3/8) Epoch 8, batch 3850, loss[loss=0.1751, simple_loss=0.2624, pruned_loss=0.04396, over 7280.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2937, pruned_loss=0.0559, over 1429016.29 frames.], batch size: 17, lr: 8.13e-04
2022-04-28 21:49:03,315 INFO [train.py:763] (3/8) Epoch 8, batch 3900, loss[loss=0.2668, simple_loss=0.3321, pruned_loss=0.1007, over 4598.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2946, pruned_loss=0.05617, over 1426186.95 frames.], batch size: 52, lr: 8.12e-04
2022-04-28 21:50:08,720 INFO [train.py:763] (3/8) Epoch 8, batch 3950, loss[loss=0.2219, simple_loss=0.315, pruned_loss=0.06439, over 6658.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2938, pruned_loss=0.05586, over 1427218.16 frames.], batch size: 31, lr: 8.12e-04
2022-04-28 21:51:14,796 INFO [train.py:763] (3/8) Epoch 8, batch 4000, loss[loss=0.1922, simple_loss=0.2854, pruned_loss=0.04954, over 7231.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2945, pruned_loss=0.05598, over 1426724.13 frames.], batch size: 21, lr: 8.11e-04
2022-04-28 21:52:21,952 INFO [train.py:763] (3/8) Epoch 8, batch 4050, loss[loss=0.1556, simple_loss=0.2425, pruned_loss=0.0344, over 7413.00 frames.], tot_loss[loss=0.2028, simple_loss=0.2938, pruned_loss=0.05592, over 1426235.95 frames.], batch size: 18, lr: 8.11e-04
2022-04-28 21:53:28,735 INFO [train.py:763] (3/8) Epoch 8, batch 4100, loss[loss=0.1684, simple_loss=0.2525, pruned_loss=0.04215, over 7128.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2929, pruned_loss=0.05526, over 1426476.25 frames.], batch size: 17, lr: 8.10e-04
2022-04-28 21:54:34,089 INFO [train.py:763] (3/8) Epoch 8, batch 4150, loss[loss=0.2268, simple_loss=0.326, pruned_loss=0.06383, over 7070.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2924, pruned_loss=0.05545, over 1421752.82 frames.], batch size: 28, lr: 8.10e-04
2022-04-28 21:55:39,788 INFO [train.py:763] (3/8) Epoch 8, batch 4200, loss[loss=0.2036, simple_loss=0.2829, pruned_loss=0.06212, over 7317.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2905, pruned_loss=0.05459, over 1423844.85 frames.], batch size: 20, lr: 8.09e-04
2022-04-28 21:56:45,196 INFO [train.py:763] (3/8) Epoch 8, batch 4250, loss[loss=0.1697, simple_loss=0.2653, pruned_loss=0.03703, over 7140.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2912, pruned_loss=0.05523, over 1419721.92 frames.], batch size: 17, lr: 8.09e-04
2022-04-28 21:57:50,931 INFO [train.py:763] (3/8) Epoch 8, batch 4300, loss[loss=0.2034, simple_loss=0.2914, pruned_loss=0.05767, over 7408.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2903, pruned_loss=0.05539, over 1415378.38 frames.], batch size: 21, lr: 8.08e-04
2022-04-28 21:58:56,621 INFO [train.py:763] (3/8) Epoch 8, batch 4350, loss[loss=0.1663, simple_loss=0.2569, pruned_loss=0.0379, over 7303.00 frames.], tot_loss[loss=0.1998, simple_loss=0.29, pruned_loss=0.05484, over 1420776.33 frames.], batch size: 17, lr: 8.08e-04
2022-04-28 22:00:02,321 INFO [train.py:763] (3/8) Epoch 8, batch 4400, loss[loss=0.2016, simple_loss=0.2935, pruned_loss=0.05489, over 7086.00 frames.], tot_loss[loss=0.2, simple_loss=0.2902, pruned_loss=0.05493, over 1416912.45 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:01:09,618 INFO [train.py:763] (3/8) Epoch 8, batch 4450, loss[loss=0.2254, simple_loss=0.3174, pruned_loss=0.06676, over 7051.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2892, pruned_loss=0.05511, over 1411342.60 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:02:15,953 INFO [train.py:763] (3/8) Epoch 8, batch 4500, loss[loss=0.2115, simple_loss=0.2987, pruned_loss=0.06214, over 7076.00 frames.], tot_loss[loss=0.202, simple_loss=0.2908, pruned_loss=0.05656, over 1393787.27 frames.], batch size: 28, lr: 8.07e-04
2022-04-28 22:03:19,879 INFO [train.py:763] (3/8) Epoch 8, batch 4550, loss[loss=0.2186, simple_loss=0.3074, pruned_loss=0.06487, over 6163.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2957, pruned_loss=0.05908, over 1353784.64 frames.], batch size: 37, lr: 8.06e-04
2022-04-28 22:04:39,797 INFO [train.py:763] (3/8) Epoch 9, batch 0, loss[loss=0.1968, simple_loss=0.2983, pruned_loss=0.04764, over 7412.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2983, pruned_loss=0.04764, over 7412.00 frames.], batch size: 21, lr: 7.75e-04
2022-04-28 22:05:45,912 INFO [train.py:763] (3/8) Epoch 9, batch 50, loss[loss=0.2049, simple_loss=0.3043, pruned_loss=0.05277, over 7194.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2944, pruned_loss=0.05584, over 321561.75 frames.], batch size: 23, lr: 7.74e-04
2022-04-28 22:06:51,597 INFO [train.py:763] (3/8) Epoch 9, batch 100, loss[loss=0.2157, simple_loss=0.2928, pruned_loss=0.06931, over 5039.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2912, pruned_loss=0.05422, over 557162.87 frames.], batch size: 52, lr: 7.74e-04
2022-04-28 22:07:57,279 INFO [train.py:763] (3/8) Epoch 9, batch 150, loss[loss=0.1983, simple_loss=0.2929, pruned_loss=0.05186, over 7438.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2904, pruned_loss=0.05269, over 750619.71 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:09:03,714 INFO [train.py:763] (3/8) Epoch 9, batch 200, loss[loss=0.1812, simple_loss=0.2845, pruned_loss=0.03895, over 7436.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2903, pruned_loss=0.05196, over 897776.72 frames.], batch size: 20, lr: 7.73e-04
2022-04-28 22:10:10,398 INFO [train.py:763] (3/8) Epoch 9, batch 250, loss[loss=0.1918, simple_loss=0.2853, pruned_loss=0.04919, over 7171.00 frames.], tot_loss[loss=0.1993, simple_loss=0.2919, pruned_loss=0.05332, over 1010016.64 frames.], batch size: 18, lr: 7.72e-04
2022-04-28 22:11:16,228 INFO [train.py:763] (3/8) Epoch 9, batch 300, loss[loss=0.1677, simple_loss=0.2694, pruned_loss=0.03295, over 7312.00 frames.], tot_loss[loss=0.1987, simple_loss=0.291, pruned_loss=0.05322, over 1103940.30 frames.], batch size: 20, lr: 7.72e-04
2022-04-28 22:12:21,603 INFO [train.py:763] (3/8) Epoch 9, batch 350, loss[loss=0.2002, simple_loss=0.299, pruned_loss=0.05068, over 7191.00 frames.], tot_loss[loss=0.1986, simple_loss=0.291, pruned_loss=0.05315, over 1172625.35 frames.], batch size: 23, lr: 7.71e-04
2022-04-28 22:13:26,943 INFO [train.py:763] (3/8) Epoch 9, batch 400, loss[loss=0.2081, simple_loss=0.3046, pruned_loss=0.0558, over 7172.00 frames.], tot_loss[loss=0.1992, simple_loss=0.292, pruned_loss=0.05319, over 1222766.80 frames.], batch size: 26, lr: 7.71e-04
2022-04-28 22:14:32,125 INFO [train.py:763] (3/8) Epoch 9, batch 450, loss[loss=0.1972, simple_loss=0.2905, pruned_loss=0.05197, over 6391.00 frames.], tot_loss[loss=0.1995, simple_loss=0.2923, pruned_loss=0.05336, over 1261894.81 frames.], batch size: 38, lr: 7.71e-04
2022-04-28 22:15:37,756 INFO [train.py:763] (3/8) Epoch 9, batch 500, loss[loss=0.2041, simple_loss=0.3, pruned_loss=0.05409, over 7148.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2923, pruned_loss=0.05349, over 1297078.80 frames.], batch size: 19, lr: 7.70e-04
2022-04-28 22:16:43,391 INFO [train.py:763] (3/8) Epoch 9, batch 550, loss[loss=0.187, simple_loss=0.28, pruned_loss=0.04699, over 7122.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2917, pruned_loss=0.05307, over 1324718.04 frames.], batch size: 17, lr: 7.70e-04
2022-04-28 22:17:49,458 INFO [train.py:763] (3/8) Epoch 9, batch 600, loss[loss=0.1794, simple_loss=0.2696, pruned_loss=0.04458, over 7284.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2907, pruned_loss=0.05286, over 1345649.46 frames.], batch size: 18, lr: 7.69e-04
2022-04-28 22:18:54,911 INFO [train.py:763] (3/8) Epoch 9, batch 650, loss[loss=0.2203, simple_loss=0.3163, pruned_loss=0.06218, over 7176.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2908, pruned_loss=0.05313, over 1362020.64 frames.], batch size: 26, lr: 7.69e-04
2022-04-28 22:20:00,485 INFO [train.py:763] (3/8) Epoch 9, batch 700, loss[loss=0.1971, simple_loss=0.287, pruned_loss=0.05366, over 7306.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2899, pruned_loss=0.05283, over 1376436.69 frames.], batch size: 25, lr: 7.68e-04
2022-04-28 22:21:06,841 INFO [train.py:763] (3/8) Epoch 9, batch 750, loss[loss=0.1832, simple_loss=0.2761, pruned_loss=0.04516, over 7426.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2894, pruned_loss=0.05289, over 1387152.80 frames.], batch size: 20, lr: 7.68e-04
2022-04-28 22:22:12,199 INFO [train.py:763] (3/8) Epoch 9, batch 800, loss[loss=0.2123, simple_loss=0.308, pruned_loss=0.05823, over 7298.00 frames.], tot_loss[loss=0.197, simple_loss=0.2887, pruned_loss=0.0527, over 1394104.95 frames.], batch size: 24, lr: 7.67e-04
2022-04-28 22:23:17,412 INFO [train.py:763] (3/8) Epoch 9, batch 850, loss[loss=0.2186, simple_loss=0.3078, pruned_loss=0.06467, over 6484.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2901, pruned_loss=0.05348, over 1396474.27 frames.], batch size: 38, lr: 7.67e-04
2022-04-28 22:24:22,755 INFO [train.py:763] (3/8) Epoch 9, batch 900, loss[loss=0.2195, simple_loss=0.3095, pruned_loss=0.06472, over 7318.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2904, pruned_loss=0.05367, over 1406603.43 frames.], batch size: 21, lr: 7.66e-04
2022-04-28 22:25:27,953 INFO [train.py:763] (3/8) Epoch 9, batch 950, loss[loss=0.2022, simple_loss=0.3098, pruned_loss=0.04726, over 7143.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2914, pruned_loss=0.05396, over 1407447.75 frames.], batch size: 26, lr: 7.66e-04
2022-04-28 22:26:33,998 INFO [train.py:763] (3/8) Epoch 9, batch 1000, loss[loss=0.1917, simple_loss=0.2877, pruned_loss=0.0478, over 7330.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2908, pruned_loss=0.05329, over 1414631.14 frames.], batch size: 20, lr: 7.66e-04
2022-04-28 22:27:40,362 INFO [train.py:763] (3/8) Epoch 9, batch 1050, loss[loss=0.2065, simple_loss=0.2977, pruned_loss=0.0576, over 7046.00 frames.], tot_loss[loss=0.1989, simple_loss=0.291, pruned_loss=0.05337, over 1416716.51 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:28:46,001 INFO [train.py:763] (3/8) Epoch 9, batch 1100, loss[loss=0.1955, simple_loss=0.2925, pruned_loss=0.04919, over 7121.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2916, pruned_loss=0.05376, over 1417728.81 frames.], batch size: 28, lr: 7.65e-04
2022-04-28 22:29:52,329 INFO [train.py:763] (3/8) Epoch 9, batch 1150, loss[loss=0.1959, simple_loss=0.2867, pruned_loss=0.05256, over 7324.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2912, pruned_loss=0.0535, over 1422086.22 frames.], batch size: 20, lr: 7.64e-04
2022-04-28 22:30:57,644 INFO [train.py:763] (3/8) Epoch 9, batch 1200, loss[loss=0.1873, simple_loss=0.2923, pruned_loss=0.04119, over 7198.00 frames.], tot_loss[loss=0.1998, simple_loss=0.2919, pruned_loss=0.05378, over 1420687.40 frames.], batch size: 23, lr: 7.64e-04
2022-04-28 22:32:04,403 INFO [train.py:763] (3/8) Epoch 9, batch 1250, loss[loss=0.1534, simple_loss=0.2452, pruned_loss=0.03079, over 7275.00 frames.], tot_loss[loss=0.1996, simple_loss=0.2916, pruned_loss=0.05376, over 1418361.42 frames.], batch size: 17, lr: 7.63e-04
2022-04-28 22:33:11,155 INFO [train.py:763] (3/8) Epoch 9, batch 1300, loss[loss=0.1896, simple_loss=0.2776, pruned_loss=0.05085, over 7004.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2902, pruned_loss=0.05319, over 1415862.83 frames.], batch size: 16, lr: 7.63e-04
2022-04-28 22:34:16,572 INFO [train.py:763] (3/8) Epoch 9, batch 1350, loss[loss=0.1977, simple_loss=0.299, pruned_loss=0.04819, over 7324.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2909, pruned_loss=0.05366, over 1416537.15 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:35:21,675 INFO [train.py:763] (3/8) Epoch 9, batch 1400, loss[loss=0.1977, simple_loss=0.2914, pruned_loss=0.05198, over 7116.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2921, pruned_loss=0.05387, over 1419294.23 frames.], batch size: 21, lr: 7.62e-04
2022-04-28 22:36:27,460 INFO [train.py:763] (3/8) Epoch 9, batch 1450, loss[loss=0.2358, simple_loss=0.3327, pruned_loss=0.06949, over 7325.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2907, pruned_loss=0.05352, over 1420788.26 frames.], batch size: 25, lr: 7.62e-04
2022-04-28 22:37:33,360 INFO [train.py:763] (3/8) Epoch 9, batch 1500, loss[loss=0.2134, simple_loss=0.3117, pruned_loss=0.05752, over 5170.00 frames.], tot_loss[loss=0.1991, simple_loss=0.2913, pruned_loss=0.0535, over 1416172.00 frames.], batch size: 53, lr: 7.61e-04
2022-04-28 22:38:38,708 INFO [train.py:763] (3/8) Epoch 9, batch 1550, loss[loss=0.1896, simple_loss=0.2776, pruned_loss=0.05084, over 7350.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2904, pruned_loss=0.05252, over 1420249.15 frames.], batch size: 19, lr: 7.61e-04
2022-04-28 22:39:43,989 INFO [train.py:763] (3/8) Epoch 9, batch 1600, loss[loss=0.1933, simple_loss=0.2865, pruned_loss=0.05005, over 7266.00 frames.], tot_loss[loss=0.198, simple_loss=0.2904, pruned_loss=0.0528, over 1419474.28 frames.], batch size: 19, lr: 7.60e-04
2022-04-28 22:40:50,100 INFO [train.py:763] (3/8) Epoch 9, batch 1650, loss[loss=0.1864, simple_loss=0.2851, pruned_loss=0.04387, over 7418.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2907, pruned_loss=0.05346, over 1417564.98 frames.], batch size: 21, lr: 7.60e-04
2022-04-28 22:41:56,341 INFO [train.py:763] (3/8) Epoch 9, batch 1700, loss[loss=0.2471, simple_loss=0.3417, pruned_loss=0.07626, over 7293.00 frames.], tot_loss[loss=0.198, simple_loss=0.29, pruned_loss=0.05298, over 1414873.83 frames.], batch size: 24, lr: 7.59e-04
2022-04-28 22:43:01,518 INFO [train.py:763] (3/8) Epoch 9, batch 1750, loss[loss=0.2097, simple_loss=0.2868, pruned_loss=0.06631, over 7238.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2905, pruned_loss=0.05333, over 1405919.03 frames.], batch size: 16, lr: 7.59e-04
2022-04-28 22:44:07,086 INFO [train.py:763] (3/8) Epoch 9, batch 1800, loss[loss=0.1787, simple_loss=0.2774, pruned_loss=0.03998, over 7350.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2908, pruned_loss=0.05353, over 1411323.20 frames.], batch size: 19, lr: 7.59e-04
2022-04-28 22:45:14,103 INFO [train.py:763] (3/8) Epoch 9, batch 1850, loss[loss=0.2059, simple_loss=0.2963, pruned_loss=0.0578, over 7366.00 frames.], tot_loss[loss=0.1997, simple_loss=0.2913, pruned_loss=0.05404, over 1412125.96 frames.], batch size: 19, lr: 7.58e-04
2022-04-28 22:46:21,653 INFO [train.py:763] (3/8) Epoch 9, batch 1900, loss[loss=0.1945, simple_loss=0.284, pruned_loss=0.05249, over 7278.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2904, pruned_loss=0.05347, over 1415868.02 frames.], batch size: 18, lr: 7.58e-04
2022-04-28 22:47:28,653 INFO [train.py:763] (3/8) Epoch 9, batch 1950, loss[loss=0.2336, simple_loss=0.3253, pruned_loss=0.07097, over 7218.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2901, pruned_loss=0.05332, over 1414893.19 frames.], batch size: 23, lr: 7.57e-04
2022-04-28 22:48:34,055 INFO [train.py:763] (3/8) Epoch 9, batch 2000, loss[loss=0.2231, simple_loss=0.3168, pruned_loss=0.06476, over 7224.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2898, pruned_loss=0.05329, over 1417720.57 frames.], batch size: 20, lr: 7.57e-04
2022-04-28 22:49:39,699 INFO [train.py:763] (3/8) Epoch 9, batch 2050, loss[loss=0.2195, simple_loss=0.3143, pruned_loss=0.06235, over 7182.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2902, pruned_loss=0.05312, over 1419860.10 frames.], batch size: 23, lr: 7.56e-04
2022-04-28 22:50:45,163 INFO [train.py:763] (3/8) Epoch 9, batch 2100, loss[loss=0.1952, simple_loss=0.2977, pruned_loss=0.04642, over 7152.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2889, pruned_loss=0.05198, over 1424277.29 frames.], batch size: 20, lr: 7.56e-04
2022-04-28 22:51:50,836 INFO [train.py:763] (3/8) Epoch 9, batch 2150, loss[loss=0.1432, simple_loss=0.2347, pruned_loss=0.02589, over 7419.00 frames.], tot_loss[loss=0.1945, simple_loss=0.287, pruned_loss=0.05096, over 1426126.24 frames.], batch size: 18, lr: 7.56e-04
2022-04-28 22:52:56,057 INFO [train.py:763] (3/8) Epoch 9, batch 2200, loss[loss=0.223, simple_loss=0.3078, pruned_loss=0.06914, over 6453.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2889, pruned_loss=0.05179, over 1426362.59 frames.], batch size: 38, lr: 7.55e-04
2022-04-28 22:54:01,586 INFO [train.py:763] (3/8) Epoch 9, batch 2250, loss[loss=0.1905, simple_loss=0.2872, pruned_loss=0.04689, over 7321.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2883, pruned_loss=0.05169, over 1427930.42 frames.], batch size: 21, lr: 7.55e-04
2022-04-28 22:55:07,219 INFO [train.py:763] (3/8) Epoch 9, batch 2300, loss[loss=0.2033, simple_loss=0.3026, pruned_loss=0.05197, over 7140.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2903, pruned_loss=0.05259, over 1425697.66 frames.], batch size: 20, lr: 7.54e-04
2022-04-28 22:56:13,146 INFO [train.py:763] (3/8) Epoch 9, batch 2350, loss[loss=0.2358, simple_loss=0.3219, pruned_loss=0.0749, over 7216.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2892, pruned_loss=0.05279, over 1423795.85 frames.], batch size: 22, lr: 7.54e-04
2022-04-28 22:57:18,359 INFO [train.py:763] (3/8) Epoch 9, batch 2400, loss[loss=0.1731, simple_loss=0.2664, pruned_loss=0.03994, over 7288.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2889, pruned_loss=0.05266, over 1426027.39 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:58:24,894 INFO [train.py:763] (3/8) Epoch 9, batch 2450, loss[loss=0.1614, simple_loss=0.2462, pruned_loss=0.0383, over 7074.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2885, pruned_loss=0.05262, over 1429672.60 frames.], batch size: 18, lr: 7.53e-04
2022-04-28 22:59:30,586 INFO [train.py:763] (3/8) Epoch 9, batch 2500, loss[loss=0.2058, simple_loss=0.2978, pruned_loss=0.05688, over 7318.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2889, pruned_loss=0.05336, over 1428067.52 frames.], batch size: 21, lr: 7.53e-04
2022-04-28 23:00:35,850 INFO [train.py:763] (3/8) Epoch 9, batch 2550, loss[loss=0.1936, simple_loss=0.2962, pruned_loss=0.04548, over 7220.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2895, pruned_loss=0.05354, over 1426288.70 frames.], batch size: 21, lr: 7.52e-04
2022-04-28 23:01:42,061 INFO [train.py:763] (3/8) Epoch 9, batch 2600, loss[loss=0.222, simple_loss=0.3167, pruned_loss=0.06367, over 7177.00 frames.], tot_loss[loss=0.1992, simple_loss=0.2903, pruned_loss=0.05404, over 1429681.75 frames.], batch size: 26, lr: 7.52e-04
2022-04-28 23:02:47,158 INFO [train.py:763] (3/8) Epoch 9, batch 2650, loss[loss=0.2116, simple_loss=0.3036, pruned_loss=0.05981, over 7325.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2913, pruned_loss=0.05447, over 1425316.39 frames.], batch size: 22, lr: 7.51e-04
2022-04-28 23:03:53,444 INFO [train.py:763] (3/8) Epoch 9, batch 2700, loss[loss=0.2221, simple_loss=0.3078, pruned_loss=0.06817, over 6906.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2899, pruned_loss=0.0536, over 1425756.39 frames.], batch size: 31, lr: 7.51e-04
2022-04-28 23:04:58,883 INFO [train.py:763] (3/8) Epoch 9, batch 2750, loss[loss=0.2156, simple_loss=0.2993, pruned_loss=0.06591, over 6795.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2886, pruned_loss=0.05253, over 1423769.43 frames.], batch size: 31, lr: 7.50e-04
2022-04-28 23:06:04,502 INFO [train.py:763] (3/8) Epoch 9, batch 2800, loss[loss=0.2089, simple_loss=0.3042, pruned_loss=0.05684, over 7372.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2879, pruned_loss=0.05213, over 1429183.86 frames.], batch size: 23, lr: 7.50e-04
2022-04-28 23:07:09,870 INFO [train.py:763] (3/8) Epoch 9, batch 2850, loss[loss=0.223, simple_loss=0.3252, pruned_loss=0.06036, over 7336.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2883, pruned_loss=0.05222, over 1426595.97 frames.], batch size: 22, lr: 7.50e-04
2022-04-28 23:08:15,554 INFO [train.py:763] (3/8) Epoch 9, batch 2900, loss[loss=0.1982, simple_loss=0.3073, pruned_loss=0.04457, over 7114.00 frames.], tot_loss[loss=0.1961, simple_loss=0.288, pruned_loss=0.05214, over 1426350.60 frames.], batch size: 21, lr: 7.49e-04
2022-04-28 23:09:22,015 INFO [train.py:763] (3/8) Epoch 9, batch 2950, loss[loss=0.1822, simple_loss=0.2712, pruned_loss=0.04662, over 7292.00 frames.], tot_loss[loss=0.196, simple_loss=0.2879, pruned_loss=0.05209, over 1426165.75 frames.], batch size: 18, lr: 7.49e-04
2022-04-28 23:10:28,990 INFO [train.py:763] (3/8) Epoch 9, batch 3000, loss[loss=0.2004, simple_loss=0.2839, pruned_loss=0.05846, over 7303.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2884, pruned_loss=0.05261, over 1425757.56 frames.], batch size: 17, lr: 7.48e-04
2022-04-28 23:10:28,991 INFO [train.py:783] (3/8) Computing validation loss
2022-04-28 23:10:44,551 INFO [train.py:792] (3/8) Epoch 9, validation: loss=0.1713, simple_loss=0.276, pruned_loss=0.03324, over 698248.00 frames.
2022-04-28 23:11:50,375 INFO [train.py:763] (3/8) Epoch 9, batch 3050, loss[loss=0.2055, simple_loss=0.3008, pruned_loss=0.05511, over 7153.00 frames.], tot_loss[loss=0.197, simple_loss=0.2883, pruned_loss=0.05283, over 1426458.93 frames.], batch size: 19, lr: 7.48e-04
2022-04-28 23:12:55,854 INFO [train.py:763] (3/8) Epoch 9, batch 3100, loss[loss=0.1866, simple_loss=0.292, pruned_loss=0.0406, over 7112.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2896, pruned_loss=0.05299, over 1429176.59 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:14:01,344 INFO [train.py:763] (3/8) Epoch 9, batch 3150, loss[loss=0.209, simple_loss=0.2916, pruned_loss=0.06315, over 7319.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2887, pruned_loss=0.05218, over 1425759.31 frames.], batch size: 21, lr: 7.47e-04
2022-04-28 23:15:07,615 INFO [train.py:763] (3/8) Epoch 9, batch 3200, loss[loss=0.1949, simple_loss=0.2962, pruned_loss=0.04679, over 7242.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2878, pruned_loss=0.05182, over 1425917.03 frames.], batch size: 20, lr: 7.47e-04
2022-04-28 23:16:13,885 INFO [train.py:763] (3/8) Epoch 9, batch 3250, loss[loss=0.1786, simple_loss=0.2724, pruned_loss=0.04243, over 7419.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2887, pruned_loss=0.05225, over 1426589.80 frames.], batch size: 21, lr: 7.46e-04
2022-04-28 23:17:19,390 INFO [train.py:763] (3/8) Epoch 9, batch 3300, loss[loss=0.2261, simple_loss=0.3239, pruned_loss=0.06416, over 7214.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2883, pruned_loss=0.05205, over 1427739.83 frames.], batch size: 22, lr: 7.46e-04
2022-04-28 23:18:25,153 INFO [train.py:763] (3/8) Epoch 9, batch 3350, loss[loss=0.2005, simple_loss=0.2835, pruned_loss=0.05872, over 7197.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2888, pruned_loss=0.05247, over 1428622.50 frames.], batch size: 23, lr: 7.45e-04
2022-04-28 23:19:31,230 INFO [train.py:763] (3/8) Epoch 9, batch 3400, loss[loss=0.156, simple_loss=0.2414, pruned_loss=0.03533, over 7267.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2883, pruned_loss=0.05264, over 1424815.22 frames.], batch size: 17, lr: 7.45e-04
2022-04-28 23:20:36,537 INFO [train.py:763] (3/8) Epoch 9, batch 3450, loss[loss=0.1955, simple_loss=0.2854, pruned_loss=0.05282, over 7275.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2878, pruned_loss=0.052, over 1424435.13 frames.], batch size: 24, lr: 7.45e-04
2022-04-28 23:21:42,130 INFO [train.py:763] (3/8) Epoch 9, batch 3500, loss[loss=0.2246, simple_loss=0.3161, pruned_loss=0.06656, over 7403.00 frames.], tot_loss[loss=0.196, simple_loss=0.2879, pruned_loss=0.05209, over 1424982.43 frames.], batch size: 21, lr: 7.44e-04
2022-04-28 23:22:49,854 INFO [train.py:763] (3/8) Epoch 9, batch 3550, loss[loss=0.2033, simple_loss=0.3022, pruned_loss=0.05218, over 7063.00 frames.], tot_loss[loss=0.1954, simple_loss=0.2873, pruned_loss=0.05172, over 1427518.85 frames.], batch size: 28, lr: 7.44e-04
2022-04-28 23:23:55,515 INFO [train.py:763] (3/8) Epoch 9, batch 3600, loss[loss=0.1722, simple_loss=0.272, pruned_loss=0.03618, over 7132.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2874, pruned_loss=0.052, over 1427744.25 frames.], batch size: 28, lr: 7.43e-04
2022-04-28 23:25:02,072 INFO [train.py:763] (3/8) Epoch 9, batch 3650, loss[loss=0.1658, simple_loss=0.2608, pruned_loss=0.03537, over 7060.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2866, pruned_loss=0.05159, over 1423120.04 frames.], batch size: 18, lr: 7.43e-04
2022-04-28 23:26:07,306 INFO [train.py:763] (3/8) Epoch 9, batch 3700, loss[loss=0.1554, simple_loss=0.2436, pruned_loss=0.03356, over 7282.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2869, pruned_loss=0.05126, over 1425178.30 frames.], batch size: 17, lr: 7.43e-04
2022-04-28 23:27:12,604 INFO [train.py:763] (3/8) Epoch 9, batch 3750, loss[loss=0.1723, simple_loss=0.2707, pruned_loss=0.03699, over 7166.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2873, pruned_loss=0.05121, over 1427638.16 frames.], batch size: 19, lr: 7.42e-04
2022-04-28 23:28:17,823 INFO [train.py:763] (3/8) Epoch 9, batch 3800, loss[loss=0.2008, simple_loss=0.3014, pruned_loss=0.05008, over 7436.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2868, pruned_loss=0.0511, over 1425752.59 frames.], batch size: 20, lr: 7.42e-04
2022-04-28 23:29:23,009 INFO [train.py:763] (3/8) Epoch 9, batch 3850, loss[loss=0.1703, simple_loss=0.2589, pruned_loss=0.04088, over 7059.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2891, pruned_loss=0.05221, over 1425191.43 frames.], batch size: 18, lr: 7.41e-04
2022-04-28 23:30:28,553 INFO [train.py:763] (3/8) Epoch 9, batch 3900, loss[loss=0.2002, simple_loss=0.2843, pruned_loss=0.05802, over 7162.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2884, pruned_loss=0.05202, over 1426933.65 frames.], batch size: 19, lr: 7.41e-04
2022-04-28 23:31:35,176 INFO [train.py:763] (3/8) Epoch 9, batch 3950, loss[loss=0.2227, simple_loss=0.3013, pruned_loss=0.07209, over 5072.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2889, pruned_loss=0.05225, over 1421676.77 frames.], batch size: 52, lr: 7.41e-04
2022-04-28 23:32:42,031 INFO [train.py:763] (3/8) Epoch 9, batch 4000, loss[loss=0.2566, simple_loss=0.3406, pruned_loss=0.08633, over 7250.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2893, pruned_loss=0.0527, over 1422893.05 frames.], batch size: 19, lr: 7.40e-04
2022-04-28 23:33:47,287 INFO [train.py:763] (3/8) Epoch 9, batch 4050, loss[loss=0.2211, simple_loss=0.2915, pruned_loss=0.07538, over 7120.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2888, pruned_loss=0.05253, over 1423021.14 frames.], batch size: 17, lr: 7.40e-04
2022-04-28 23:34:53,526 INFO [train.py:763] (3/8) Epoch 9, batch 4100, loss[loss=0.1962, simple_loss=0.3009, pruned_loss=0.0457, over 7313.00 frames.], tot_loss[loss=0.1969, simple_loss=0.289, pruned_loss=0.05239, over 1425298.93 frames.], batch size: 21, lr: 7.39e-04
2022-04-28 23:35:59,479 INFO [train.py:763] (3/8) Epoch 9, batch 4150, loss[loss=0.1733, simple_loss=0.259, pruned_loss=0.04378, over 7398.00 frames.], tot_loss[loss=0.197, simple_loss=0.2892, pruned_loss=0.05245, over 1425070.06 frames.], batch size: 18, lr: 7.39e-04
2022-04-28 23:37:04,698 INFO [train.py:763] (3/8) Epoch 9, batch 4200, loss[loss=0.2234, simple_loss=0.3053, pruned_loss=0.07077, over 7289.00 frames.], tot_loss[loss=0.197, simple_loss=0.289, pruned_loss=0.05244, over 1426593.90 frames.], batch size: 24, lr: 7.39e-04
2022-04-28 23:38:10,555 INFO [train.py:763] (3/8) Epoch 9, batch 4250, loss[loss=0.1818, simple_loss=0.2655, pruned_loss=0.04901, over 7267.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2899, pruned_loss=0.05292, over 1422375.39 frames.], batch size: 17, lr: 7.38e-04
2022-04-28 23:39:16,464 INFO [train.py:763] (3/8) Epoch 9, batch 4300, loss[loss=0.2276, simple_loss=0.3161, pruned_loss=0.0695, over 7288.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2903, pruned_loss=0.05322, over 1416453.54 frames.], batch size: 24, lr: 7.38e-04
2022-04-28 23:40:22,452 INFO [train.py:763] (3/8) Epoch 9, batch 4350, loss[loss=0.2676, simple_loss=0.3437, pruned_loss=0.09574, over 5170.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2926, pruned_loss=0.05441, over 1407817.37 frames.], batch size: 52, lr: 7.37e-04
2022-04-28 23:41:28,472 INFO [train.py:763] (3/8) Epoch 9, batch 4400, loss[loss=0.1749, simple_loss=0.2734, pruned_loss=0.03818, over 7208.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2937, pruned_loss=0.05475, over 1411019.72 frames.], batch size: 22, lr: 7.37e-04
2022-04-28 23:42:35,221 INFO [train.py:763] (3/8) Epoch 9, batch 4450, loss[loss=0.2177, simple_loss=0.3058, pruned_loss=0.06479, over 5307.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2939, pruned_loss=0.0547, over 1395854.63 frames.], batch size: 52, lr: 7.37e-04
2022-04-28 23:43:41,391 INFO [train.py:763] (3/8) Epoch 9, batch 4500, loss[loss=0.184, simple_loss=0.2842, pruned_loss=0.04193, over 7143.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2926, pruned_loss=0.05446, over 1391851.50 frames.], batch size: 20, lr: 7.36e-04
2022-04-28 23:44:47,990 INFO [train.py:763] (3/8) Epoch 9, batch 4550, loss[loss=0.2075, simple_loss=0.3004, pruned_loss=0.0573, over 7179.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2926, pruned_loss=0.05531, over 1370304.42 frames.], batch size: 26, lr: 7.36e-04
2022-04-28 23:46:26,279 INFO [train.py:763] (3/8) Epoch 10, batch 0, loss[loss=0.1885, simple_loss=0.2681, pruned_loss=0.05442, over 7434.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2681, pruned_loss=0.05442, over 7434.00 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:47:32,324 INFO [train.py:763] (3/8) Epoch 10, batch 50, loss[loss=0.1881, simple_loss=0.2851, pruned_loss=0.04557, over 7427.00 frames.], tot_loss[loss=0.193, simple_loss=0.288, pruned_loss=0.049, over 322750.35 frames.], batch size: 20, lr: 7.08e-04
2022-04-28 23:48:38,908 INFO [train.py:763] (3/8) Epoch 10, batch 100, loss[loss=0.1552, simple_loss=0.2581, pruned_loss=0.02611, over 7280.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2873, pruned_loss=0.0492, over 567033.27 frames.], batch size: 18, lr: 7.08e-04
2022-04-28 23:49:55,133 INFO [train.py:763] (3/8) Epoch 10, batch 150, loss[loss=0.164, simple_loss=0.2562, pruned_loss=0.0359, over 6782.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2894, pruned_loss=0.05107, over 759735.15 frames.], batch size: 15, lr: 7.07e-04
2022-04-28 23:51:18,545 INFO [train.py:763] (3/8) Epoch 10, batch 200, loss[loss=0.1676, simple_loss=0.2612, pruned_loss=0.03699, over 7430.00 frames.], tot_loss[loss=0.1947, simple_loss=0.2885, pruned_loss=0.05042, over 907386.09 frames.], batch size: 18, lr: 7.07e-04
2022-04-28 23:52:32,863 INFO [train.py:763] (3/8) Epoch 10, batch 250, loss[loss=0.1906, simple_loss=0.2899, pruned_loss=0.04562, over 6273.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2874, pruned_loss=0.05015, over 1023497.28 frames.], batch size: 38, lr: 7.06e-04
2022-04-28 23:53:48,225 INFO [train.py:763] (3/8) Epoch 10, batch 300, loss[loss=0.2513, simple_loss=0.3245, pruned_loss=0.08906, over 4987.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2872, pruned_loss=0.05055, over 1114221.35 frames.], batch size: 52, lr: 7.06e-04
2022-04-28 23:54:53,616 INFO [train.py:763] (3/8) Epoch 10, batch 350, loss[loss=0.2168, simple_loss=0.3105, pruned_loss=0.06152, over 6681.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2875, pruned_loss=0.05079, over 1186938.82 frames.], batch size: 31, lr: 7.06e-04
2022-04-28 23:56:17,500 INFO [train.py:763] (3/8) Epoch 10, batch 400, loss[loss=0.1882, simple_loss=0.2824, pruned_loss=0.04699, over 7433.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2872, pruned_loss=0.0506, over 1241109.49 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:57:23,252 INFO [train.py:763] (3/8) Epoch 10, batch 450, loss[loss=0.2253, simple_loss=0.3112, pruned_loss=0.06969, over 7239.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2857, pruned_loss=0.05041, over 1280538.39 frames.], batch size: 20, lr: 7.05e-04
2022-04-28 23:58:37,642 INFO [train.py:763] (3/8) Epoch 10, batch 500, loss[loss=0.1935, simple_loss=0.2841, pruned_loss=0.05146, over 7331.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2857, pruned_loss=0.05005, over 1315238.30 frames.], batch size: 20, lr: 7.04e-04
2022-04-28 23:59:42,723 INFO [train.py:763] (3/8) Epoch 10, batch 550, loss[loss=0.2115, simple_loss=0.3072, pruned_loss=0.05789, over 7072.00 frames.], tot_loss[loss=0.193, simple_loss=0.286, pruned_loss=0.05, over 1340685.35 frames.], batch size: 18, lr: 7.04e-04
2022-04-29 00:00:47,812 INFO [train.py:763] (3/8) Epoch 10, batch 600, loss[loss=0.1572, simple_loss=0.2406, pruned_loss=0.03689, over 6993.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2863, pruned_loss=0.05015, over 1359558.93 frames.], batch size: 16, lr: 7.04e-04
2022-04-29 00:01:53,007 INFO [train.py:763] (3/8) Epoch 10, batch 650, loss[loss=0.1931, simple_loss=0.2727, pruned_loss=0.05677, over 7159.00 frames.], tot_loss[loss=0.195, simple_loss=0.2875, pruned_loss=0.05122, over 1364980.90 frames.], batch size: 17, lr: 7.03e-04
2022-04-29 00:02:58,036 INFO [train.py:763] (3/8) Epoch 10, batch 700, loss[loss=0.1839, simple_loss=0.2712, pruned_loss=0.04824, over 7198.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2884, pruned_loss=0.05151, over 1375654.92 frames.], batch size: 16, lr: 7.03e-04
2022-04-29 00:04:03,194 INFO [train.py:763] (3/8) Epoch 10, batch 750, loss[loss=0.1904, simple_loss=0.287, pruned_loss=0.04696, over 7141.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2884, pruned_loss=0.05135, over 1382755.11 frames.], batch size: 20, lr: 7.03e-04
2022-04-29 00:05:08,472 INFO [train.py:763] (3/8) Epoch 10, batch 800, loss[loss=0.2038, simple_loss=0.3007, pruned_loss=0.05347, over 7115.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2874, pruned_loss=0.05049, over 1394075.19 frames.], batch size: 26, lr: 7.02e-04
2022-04-29 00:06:13,825 INFO [train.py:763] (3/8) Epoch 10, batch 850, loss[loss=0.2408, simple_loss=0.3305, pruned_loss=0.07558, over 7335.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2874, pruned_loss=0.05025, over 1398461.98 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:07:19,242 INFO [train.py:763] (3/8) Epoch 10, batch 900, loss[loss=0.1784, simple_loss=0.2781, pruned_loss=0.0394, over 7433.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2863, pruned_loss=0.04976, over 1406864.46 frames.], batch size: 20, lr: 7.02e-04
2022-04-29 00:08:24,540 INFO [train.py:763] (3/8) Epoch 10, batch 950, loss[loss=0.1925, simple_loss=0.2864, pruned_loss=0.04925, over 7000.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2866, pruned_loss=0.05044, over 1408762.86 frames.], batch size: 16, lr: 7.01e-04
2022-04-29 00:09:29,919 INFO [train.py:763] (3/8) Epoch 10, batch 1000, loss[loss=0.1846, simple_loss=0.2823, pruned_loss=0.04343, over 7351.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2872, pruned_loss=0.05065, over 1413414.88 frames.], batch size: 25, lr: 7.01e-04
2022-04-29 00:10:35,516 INFO [train.py:763] (3/8) Epoch 10, batch 1050, loss[loss=0.1967, simple_loss=0.2889, pruned_loss=0.0523, over 7265.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2889, pruned_loss=0.05171, over 1409098.29 frames.], batch size: 19, lr: 7.00e-04
2022-04-29 00:11:41,109 INFO [train.py:763] (3/8) Epoch 10, batch 1100, loss[loss=0.1861, simple_loss=0.2682, pruned_loss=0.05197, over 7168.00 frames.], tot_loss[loss=0.195, simple_loss=0.2879, pruned_loss=0.051, over 1413361.07 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:12:46,584 INFO [train.py:763] (3/8) Epoch 10, batch 1150, loss[loss=0.2011, simple_loss=0.2748, pruned_loss=0.06364, over 7071.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2868, pruned_loss=0.05044, over 1417273.01 frames.], batch size: 18, lr: 7.00e-04
2022-04-29 00:13:53,263 INFO [train.py:763] (3/8) Epoch 10, batch 1200, loss[loss=0.1755, simple_loss=0.259, pruned_loss=0.04597, over 7239.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2857, pruned_loss=0.05093, over 1419943.09 frames.], batch size: 16, lr: 6.99e-04
2022-04-29 00:14:58,980 INFO [train.py:763] (3/8) Epoch 10, batch 1250, loss[loss=0.1906, simple_loss=0.2775, pruned_loss=0.0518, over 7144.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2855, pruned_loss=0.05055, over 1424252.03 frames.], batch size: 17, lr: 6.99e-04
2022-04-29 00:16:04,762 INFO [train.py:763] (3/8) Epoch 10, batch 1300, loss[loss=0.2202, simple_loss=0.3168, pruned_loss=0.06178, over 7323.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2855, pruned_loss=0.05076, over 1421429.68 frames.], batch size: 21, lr: 6.99e-04
2022-04-29 00:17:11,805 INFO [train.py:763] (3/8) Epoch 10, batch 1350, loss[loss=0.1963, simple_loss=0.2985, pruned_loss=0.04708, over 7321.00 frames.], tot_loss[loss=0.1953, simple_loss=0.287, pruned_loss=0.05177, over 1424786.01 frames.], batch size: 21, lr: 6.98e-04
2022-04-29 00:18:18,354 INFO [train.py:763] (3/8) Epoch 10, batch 1400, loss[loss=0.1963, simple_loss=0.2775, pruned_loss=0.0576, over 7156.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2864, pruned_loss=0.0514, over 1428090.87 frames.], batch size: 19, lr: 6.98e-04
2022-04-29 00:19:25,279 INFO [train.py:763] (3/8) Epoch 10, batch 1450, loss[loss=0.1818, simple_loss=0.2679, pruned_loss=0.04787, over 7275.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2866, pruned_loss=0.05098, over 1428283.80 frames.], batch size: 17, lr: 6.97e-04
2022-04-29 00:20:30,750 INFO [train.py:763] (3/8) Epoch 10, batch 1500, loss[loss=0.1971, simple_loss=0.2973, pruned_loss=0.04848, over 7039.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2856, pruned_loss=0.05065, over 1425948.82 frames.], batch size: 28, lr: 6.97e-04
2022-04-29 00:21:36,428 INFO [train.py:763] (3/8) Epoch 10, batch 1550, loss[loss=0.1942, simple_loss=0.2736, pruned_loss=0.05738, over 7447.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2861, pruned_loss=0.05068, over 1424219.95 frames.], batch size: 20, lr: 6.97e-04
2022-04-29 00:22:41,607 INFO [train.py:763] (3/8) Epoch 10, batch 1600, loss[loss=0.2272, simple_loss=0.3273, pruned_loss=0.06353, over 6796.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2868, pruned_loss=0.05093, over 1418572.90 frames.], batch size: 31, lr: 6.96e-04
2022-04-29 00:23:47,730 INFO [train.py:763] (3/8) Epoch 10, batch 1650, loss[loss=0.1517, simple_loss=0.2377, pruned_loss=0.03289, over 6765.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2858, pruned_loss=0.05042, over 1418140.81 frames.], batch size: 15, lr: 6.96e-04
2022-04-29 00:24:52,735 INFO [train.py:763] (3/8) Epoch 10, batch 1700, loss[loss=0.2004, simple_loss=0.2835, pruned_loss=0.05866, over 7188.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2855, pruned_loss=0.05007, over 1417824.88 frames.], batch size: 16, lr: 6.96e-04
2022-04-29 00:25:58,396 INFO [train.py:763] (3/8) Epoch 10, batch 1750, loss[loss=0.1978, simple_loss=0.2972, pruned_loss=0.04921, over 7118.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2849, pruned_loss=0.04989, over 1414543.49 frames.], batch size: 21, lr: 6.95e-04
2022-04-29 00:27:03,848 INFO [train.py:763] (3/8) Epoch 10, batch 1800, loss[loss=0.2273, simple_loss=0.3148, pruned_loss=0.06991, over 5156.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2863, pruned_loss=0.05059, over 1415097.10 frames.], batch size: 53, lr: 6.95e-04
2022-04-29 00:28:10,765 INFO [train.py:763] (3/8) Epoch 10, batch 1850, loss[loss=0.2397, simple_loss=0.3225, pruned_loss=0.07841, over 6353.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2859, pruned_loss=0.05028, over 1418700.40 frames.], batch size: 37, lr: 6.95e-04
2022-04-29 00:29:17,822 INFO [train.py:763] (3/8) Epoch 10, batch 1900, loss[loss=0.1933, simple_loss=0.2992, pruned_loss=0.04373, over 7316.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2855, pruned_loss=0.05006, over 1423181.22 frames.], batch size: 21, lr: 6.94e-04
2022-04-29 00:30:24,812 INFO [train.py:763] (3/8) Epoch 10, batch 1950, loss[loss=0.1891, simple_loss=0.2798, pruned_loss=0.04918, over 7361.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2859, pruned_loss=0.05082, over 1422719.87 frames.], batch size: 19, lr: 6.94e-04
2022-04-29 00:31:31,794 INFO [train.py:763] (3/8) Epoch 10, batch 2000, loss[loss=0.1925, simple_loss=0.2775, pruned_loss=0.05377, over 7157.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2864, pruned_loss=0.05052, over 1423785.71 frames.], batch size: 18, lr: 6.93e-04
2022-04-29 00:32:38,660 INFO [train.py:763] (3/8) Epoch 10, batch 2050, loss[loss=0.2029, simple_loss=0.2809, pruned_loss=0.06247, over 7265.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2862, pruned_loss=0.05028, over 1425686.94 frames.], batch size: 17, lr: 6.93e-04
2022-04-29 00:33:45,454 INFO [train.py:763] (3/8) Epoch 10, batch 2100, loss[loss=0.2125, simple_loss=0.3078, pruned_loss=0.0586, over 7379.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2864, pruned_loss=0.05008, over 1426077.08 frames.], batch size: 23, lr: 6.93e-04
2022-04-29 00:35:01,073 INFO [train.py:763] (3/8) Epoch 10, batch 2150, loss[loss=0.1998, simple_loss=0.2843, pruned_loss=0.05762, over 7160.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2869, pruned_loss=0.05064, over 1425799.85 frames.], batch size: 18, lr: 6.92e-04
2022-04-29 00:36:06,564 INFO [train.py:763] (3/8) Epoch 10, batch 2200, loss[loss=0.197, simple_loss=0.298, pruned_loss=0.04801, over 7234.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2867, pruned_loss=0.05103, over 1423544.50 frames.], batch size: 20, lr: 6.92e-04
2022-04-29 00:37:11,926 INFO [train.py:763] (3/8) Epoch 10, batch 2250, loss[loss=0.2012, simple_loss=0.2993, pruned_loss=0.05154, over 7327.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2881, pruned_loss=0.05151, over 1426975.08 frames.], batch size: 22, lr: 6.92e-04
2022-04-29 00:38:17,409 INFO [train.py:763] (3/8) Epoch 10, batch 2300, loss[loss=0.1796, simple_loss=0.2748, pruned_loss=0.04216, over 7146.00 frames.], tot_loss[loss=0.1957, simple_loss=0.288, pruned_loss=0.0517, over 1427502.75 frames.], batch size: 26, lr: 6.91e-04
2022-04-29 00:39:22,702 INFO [train.py:763] (3/8) Epoch 10, batch 2350, loss[loss=0.2347, simple_loss=0.3187, pruned_loss=0.07533, over 6802.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2865, pruned_loss=0.05087, over 1429985.88 frames.], batch size: 31, lr: 6.91e-04
2022-04-29 00:40:27,865 INFO [train.py:763] (3/8) Epoch 10, batch 2400, loss[loss=0.1681, simple_loss=0.28, pruned_loss=0.02811, over 7315.00 frames.], tot_loss[loss=0.1934, simple_loss=0.286, pruned_loss=0.05043, over 1423556.28 frames.], batch size: 21, lr: 6.91e-04
2022-04-29 00:41:33,298 INFO [train.py:763] (3/8) Epoch 10, batch 2450, loss[loss=0.1794, simple_loss=0.2546, pruned_loss=0.05213, over 7008.00 frames.], tot_loss[loss=0.192, simple_loss=0.2843, pruned_loss=0.04978, over 1423890.94 frames.], batch size: 16, lr: 6.90e-04
2022-04-29 00:42:38,513 INFO [train.py:763] (3/8) Epoch 10, batch 2500, loss[loss=0.1834, simple_loss=0.2671, pruned_loss=0.04982, over 7150.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2852, pruned_loss=0.05014, over 1422937.09 frames.], batch size: 19, lr: 6.90e-04
2022-04-29 00:43:44,251 INFO [train.py:763] (3/8) Epoch 10, batch 2550, loss[loss=0.1643, simple_loss=0.2488, pruned_loss=0.03993, over 6770.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2846, pruned_loss=0.04951, over 1426701.89 frames.], batch size: 15, lr: 6.90e-04
2022-04-29 00:44:51,067 INFO [train.py:763] (3/8) Epoch 10, batch 2600, loss[loss=0.2018, simple_loss=0.298, pruned_loss=0.05287, over 7381.00 frames.], tot_loss[loss=0.193, simple_loss=0.2852, pruned_loss=0.05035, over 1428152.98 frames.], batch size: 23, lr: 6.89e-04
2022-04-29 00:45:56,181 INFO [train.py:763] (3/8) Epoch 10, batch 2650, loss[loss=0.1813, simple_loss=0.2713, pruned_loss=0.04562, over 7005.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2859, pruned_loss=0.05054, over 1423822.27 frames.], batch size: 16, lr: 6.89e-04
2022-04-29 00:47:01,611 INFO [train.py:763] (3/8) Epoch 10, batch 2700, loss[loss=0.2135, simple_loss=0.299, pruned_loss=0.06402, over 7409.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2865, pruned_loss=0.05058, over 1426848.60 frames.], batch size: 21, lr: 6.89e-04
2022-04-29 00:48:08,164 INFO [train.py:763] (3/8) Epoch 10, batch 2750, loss[loss=0.1858, simple_loss=0.2709, pruned_loss=0.05034, over 7278.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2856, pruned_loss=0.05028, over 1426048.70 frames.], batch size: 18, lr: 6.88e-04
2022-04-29 00:49:13,513 INFO [train.py:763] (3/8) Epoch 10, batch 2800, loss[loss=0.2081, simple_loss=0.2982, pruned_loss=0.05901, over 7163.00 frames.], tot_loss[loss=0.1937, simple_loss=0.2861, pruned_loss=0.05068, over 1424668.22 frames.], batch size: 19, lr: 6.88e-04
2022-04-29 00:50:19,051 INFO [train.py:763] (3/8) Epoch 10, batch 2850, loss[loss=0.1923, simple_loss=0.2897, pruned_loss=0.0475, over 7317.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2855, pruned_loss=0.05039, over 1424318.77 frames.], batch size: 21, lr: 6.87e-04
2022-04-29 00:51:24,554 INFO [train.py:763] (3/8) Epoch 10, batch 2900, loss[loss=0.2033, simple_loss=0.3017, pruned_loss=0.05251, over 7176.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2852, pruned_loss=0.0503, over 1427288.01 frames.], batch size: 23, lr: 6.87e-04
2022-04-29 00:52:30,306 INFO [train.py:763] (3/8) Epoch 10, batch 2950, loss[loss=0.194, simple_loss=0.289, pruned_loss=0.04948, over 7203.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2858, pruned_loss=0.05036, over 1424753.40 frames.], batch size: 22, lr: 6.87e-04
2022-04-29 00:53:36,006 INFO [train.py:763] (3/8) Epoch 10, batch 3000, loss[loss=0.168, simple_loss=0.2608, pruned_loss=0.03761, over 7172.00 frames.], tot_loss[loss=0.194, simple_loss=0.2867, pruned_loss=0.05068, over 1423474.49 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:53:36,008 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 00:53:51,271 INFO [train.py:792] (3/8) Epoch 10, validation: loss=0.1689, simple_loss=0.2722, pruned_loss=0.03283, over 698248.00 frames.
2022-04-29 00:54:57,775 INFO [train.py:763] (3/8) Epoch 10, batch 3050, loss[loss=0.1917, simple_loss=0.2844, pruned_loss=0.04948, over 7157.00 frames.], tot_loss[loss=0.193, simple_loss=0.2858, pruned_loss=0.05011, over 1428212.91 frames.], batch size: 26, lr: 6.86e-04
2022-04-29 00:56:03,586 INFO [train.py:763] (3/8) Epoch 10, batch 3100, loss[loss=0.1483, simple_loss=0.2444, pruned_loss=0.02612, over 7423.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2871, pruned_loss=0.05101, over 1425626.13 frames.], batch size: 18, lr: 6.86e-04
2022-04-29 00:57:10,795 INFO [train.py:763] (3/8) Epoch 10, batch 3150, loss[loss=0.1704, simple_loss=0.2629, pruned_loss=0.0389, over 7275.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2866, pruned_loss=0.05112, over 1428306.88 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:58:16,971 INFO [train.py:763] (3/8) Epoch 10, batch 3200, loss[loss=0.1562, simple_loss=0.2475, pruned_loss=0.03241, over 7165.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2855, pruned_loss=0.05083, over 1430087.55 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 00:59:22,561 INFO [train.py:763] (3/8) Epoch 10, batch 3250, loss[loss=0.1832, simple_loss=0.2691, pruned_loss=0.04861, over 7062.00 frames.], tot_loss[loss=0.1938, simple_loss=0.286, pruned_loss=0.05077, over 1431547.13 frames.], batch size: 18, lr: 6.85e-04
2022-04-29 01:00:29,376 INFO [train.py:763] (3/8) Epoch 10, batch 3300, loss[loss=0.2015, simple_loss=0.2877, pruned_loss=0.05761, over 6517.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2859, pruned_loss=0.05043, over 1431543.33 frames.], batch size: 38, lr: 6.84e-04
2022-04-29 01:01:36,447 INFO [train.py:763] (3/8) Epoch 10, batch 3350, loss[loss=0.1944, simple_loss=0.2899, pruned_loss=0.04942, over 7126.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2861, pruned_loss=0.05034, over 1425109.36 frames.], batch size: 21, lr: 6.84e-04
2022-04-29 01:02:41,921 INFO [train.py:763] (3/8) Epoch 10, batch 3400, loss[loss=0.1869, simple_loss=0.2637, pruned_loss=0.05504, over 7005.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2865, pruned_loss=0.05058, over 1421354.29 frames.], batch size: 16, lr: 6.84e-04
2022-04-29 01:03:47,411 INFO [train.py:763] (3/8) Epoch 10, batch 3450, loss[loss=0.1919, simple_loss=0.2922, pruned_loss=0.04582, over 7114.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2863, pruned_loss=0.04991, over 1424015.71 frames.], batch size: 21, lr: 6.83e-04
2022-04-29 01:04:52,721 INFO [train.py:763] (3/8) Epoch 10, batch 3500, loss[loss=0.1762, simple_loss=0.2621, pruned_loss=0.04515, over 7413.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2854, pruned_loss=0.04958, over 1424828.79 frames.], batch size: 18, lr: 6.83e-04
2022-04-29 01:05:58,211 INFO [train.py:763] (3/8) Epoch 10, batch 3550, loss[loss=0.1834, simple_loss=0.2816, pruned_loss=0.04261, over 6546.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2866, pruned_loss=0.05013, over 1424027.39 frames.], batch size: 38, lr: 6.83e-04
2022-04-29 01:07:03,431 INFO [train.py:763] (3/8) Epoch 10, batch 3600, loss[loss=0.1991, simple_loss=0.282, pruned_loss=0.05808, over 6523.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2873, pruned_loss=0.05089, over 1419434.68 frames.], batch size: 38, lr: 6.82e-04
2022-04-29 01:08:09,034 INFO [train.py:763] (3/8) Epoch 10, batch 3650, loss[loss=0.2109, simple_loss=0.3174, pruned_loss=0.05221, over 7115.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2876, pruned_loss=0.05067, over 1421788.34 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:09:14,317 INFO [train.py:763] (3/8) Epoch 10, batch 3700, loss[loss=0.1966, simple_loss=0.2987, pruned_loss=0.04726, over 7114.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2878, pruned_loss=0.05069, over 1417654.60 frames.], batch size: 21, lr: 6.82e-04
2022-04-29 01:10:20,242 INFO [train.py:763] (3/8) Epoch 10, batch 3750, loss[loss=0.204, simple_loss=0.288, pruned_loss=0.06003, over 7428.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2887, pruned_loss=0.05077, over 1424091.78 frames.], batch size: 20, lr: 6.81e-04
2022-04-29 01:11:26,040 INFO [train.py:763] (3/8) Epoch 10, batch 3800, loss[loss=0.2318, simple_loss=0.3187, pruned_loss=0.07244, over 7254.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2891, pruned_loss=0.05138, over 1422662.48 frames.], batch size: 24, lr: 6.81e-04
2022-04-29 01:12:32,917 INFO [train.py:763] (3/8) Epoch 10, batch 3850, loss[loss=0.1937, simple_loss=0.2966, pruned_loss=0.04538, over 7213.00 frames.], tot_loss[loss=0.1945, simple_loss=0.288, pruned_loss=0.05052, over 1426801.18 frames.], batch size: 22, lr: 6.81e-04
2022-04-29 01:13:40,343 INFO [train.py:763] (3/8) Epoch 10, batch 3900, loss[loss=0.1986, simple_loss=0.2932, pruned_loss=0.05195, over 7384.00 frames.], tot_loss[loss=0.194, simple_loss=0.2874, pruned_loss=0.05034, over 1428108.34 frames.], batch size: 23, lr: 6.80e-04
2022-04-29 01:14:47,716 INFO [train.py:763] (3/8) Epoch 10, batch 3950, loss[loss=0.1884, simple_loss=0.2874, pruned_loss=0.04467, over 7424.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2865, pruned_loss=0.05003, over 1426725.01 frames.], batch size: 20, lr: 6.80e-04
2022-04-29 01:15:53,612 INFO [train.py:763] (3/8) Epoch 10, batch 4000, loss[loss=0.2123, simple_loss=0.3155, pruned_loss=0.05452, over 7220.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2864, pruned_loss=0.05035, over 1418318.36 frames.], batch size: 21, lr: 6.80e-04
2022-04-29 01:17:00,541 INFO [train.py:763] (3/8) Epoch 10, batch 4050, loss[loss=0.1993, simple_loss=0.2852, pruned_loss=0.05669, over 7196.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2859, pruned_loss=0.05018, over 1418631.24 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:18:07,362 INFO [train.py:763] (3/8) Epoch 10, batch 4100, loss[loss=0.1919, simple_loss=0.3058, pruned_loss=0.03904, over 7202.00 frames.], tot_loss[loss=0.1942, simple_loss=0.2871, pruned_loss=0.05062, over 1417721.70 frames.], batch size: 22, lr: 6.79e-04
2022-04-29 01:19:14,030 INFO [train.py:763] (3/8) Epoch 10, batch 4150, loss[loss=0.2245, simple_loss=0.3143, pruned_loss=0.06729, over 6801.00 frames.], tot_loss[loss=0.195, simple_loss=0.2881, pruned_loss=0.05091, over 1415431.22 frames.], batch size: 31, lr: 6.79e-04
2022-04-29 01:20:19,801 INFO [train.py:763] (3/8) Epoch 10, batch 4200, loss[loss=0.2138, simple_loss=0.3005, pruned_loss=0.06356, over 7019.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2876, pruned_loss=0.05101, over 1415944.62 frames.], batch size: 28, lr: 6.78e-04
2022-04-29 01:21:26,029 INFO [train.py:763] (3/8) Epoch 10, batch 4250, loss[loss=0.2211, simple_loss=0.2936, pruned_loss=0.07433, over 5091.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2873, pruned_loss=0.05076, over 1415098.24 frames.], batch size: 52, lr: 6.78e-04
2022-04-29 01:22:31,075 INFO [train.py:763] (3/8) Epoch 10, batch 4300, loss[loss=0.2567, simple_loss=0.336, pruned_loss=0.0887, over 5047.00 frames.], tot_loss[loss=0.195, simple_loss=0.2873, pruned_loss=0.05129, over 1411350.47 frames.], batch size: 52, lr: 6.78e-04
2022-04-29 01:23:36,196 INFO [train.py:763] (3/8) Epoch 10, batch 4350, loss[loss=0.1652, simple_loss=0.2663, pruned_loss=0.03204, over 7230.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2887, pruned_loss=0.05143, over 1410391.61 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:24:41,259 INFO [train.py:763] (3/8) Epoch 10, batch 4400, loss[loss=0.2079, simple_loss=0.3007, pruned_loss=0.05759, over 7208.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2886, pruned_loss=0.05119, over 1416203.13 frames.], batch size: 22, lr: 6.77e-04
2022-04-29 01:25:46,576 INFO [train.py:763] (3/8) Epoch 10, batch 4450, loss[loss=0.1678, simple_loss=0.2677, pruned_loss=0.03395, over 7241.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2895, pruned_loss=0.05145, over 1418592.07 frames.], batch size: 20, lr: 6.77e-04
2022-04-29 01:26:52,301 INFO [train.py:763] (3/8) Epoch 10, batch 4500, loss[loss=0.2435, simple_loss=0.3245, pruned_loss=0.08125, over 5335.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2911, pruned_loss=0.05235, over 1410805.69 frames.], batch size: 52, lr: 6.76e-04
2022-04-29 01:27:57,100 INFO [train.py:763] (3/8) Epoch 10, batch 4550, loss[loss=0.2329, simple_loss=0.3197, pruned_loss=0.07305, over 5504.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2931, pruned_loss=0.05493, over 1346643.32 frames.], batch size: 53, lr: 6.76e-04
2022-04-29 01:29:26,055 INFO [train.py:763] (3/8) Epoch 11, batch 0, loss[loss=0.1914, simple_loss=0.2921, pruned_loss=0.04536, over 7410.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2921, pruned_loss=0.04536, over 7410.00 frames.], batch size: 21, lr: 6.52e-04
2022-04-29 01:30:32,265 INFO [train.py:763] (3/8) Epoch 11, batch 50, loss[loss=0.2366, simple_loss=0.3203, pruned_loss=0.07641, over 4928.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2858, pruned_loss=0.05004, over 319368.90 frames.], batch size: 53, lr: 6.52e-04
2022-04-29 01:31:38,378 INFO [train.py:763] (3/8) Epoch 11, batch 100, loss[loss=0.1656, simple_loss=0.2619, pruned_loss=0.03468, over 6407.00 frames.], tot_loss[loss=0.194, simple_loss=0.2871, pruned_loss=0.05041, over 559314.75 frames.], batch size: 37, lr: 6.51e-04
2022-04-29 01:32:44,336 INFO [train.py:763] (3/8) Epoch 11, batch 150, loss[loss=0.1841, simple_loss=0.2667, pruned_loss=0.05079, over 7271.00 frames.], tot_loss[loss=0.1945, simple_loss=0.2882, pruned_loss=0.0504, over 749657.30 frames.], batch size: 17, lr: 6.51e-04
2022-04-29 01:33:50,248 INFO [train.py:763] (3/8) Epoch 11, batch 200, loss[loss=0.2333, simple_loss=0.3236, pruned_loss=0.07146, over 7204.00 frames.], tot_loss[loss=0.1955, simple_loss=0.289, pruned_loss=0.05104, over 897370.64 frames.], batch size: 22, lr: 6.51e-04
2022-04-29 01:34:55,807 INFO [train.py:763] (3/8) Epoch 11, batch 250, loss[loss=0.1768, simple_loss=0.2682, pruned_loss=0.04273, over 6692.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2874, pruned_loss=0.04967, over 1014252.58 frames.], batch size: 31, lr: 6.50e-04
2022-04-29 01:36:01,202 INFO [train.py:763] (3/8) Epoch 11, batch 300, loss[loss=0.2095, simple_loss=0.3061, pruned_loss=0.05643, over 7211.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2867, pruned_loss=0.04883, over 1099657.36 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:37:06,905 INFO [train.py:763] (3/8) Epoch 11, batch 350, loss[loss=0.191, simple_loss=0.2942, pruned_loss=0.0439, over 7340.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2853, pruned_loss=0.04841, over 1166668.55 frames.], batch size: 22, lr: 6.50e-04
2022-04-29 01:38:12,675 INFO [train.py:763] (3/8) Epoch 11, batch 400, loss[loss=0.2036, simple_loss=0.3051, pruned_loss=0.05102, over 7347.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2849, pruned_loss=0.04827, over 1220987.53 frames.], batch size: 22, lr: 6.49e-04
2022-04-29 01:39:18,302 INFO [train.py:763] (3/8) Epoch 11, batch 450, loss[loss=0.1803, simple_loss=0.271, pruned_loss=0.04478, over 7166.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2837, pruned_loss=0.04769, over 1269346.26 frames.], batch size: 19, lr: 6.49e-04
2022-04-29 01:40:24,054 INFO [train.py:763] (3/8) Epoch 11, batch 500, loss[loss=0.2086, simple_loss=0.3126, pruned_loss=0.05228, over 7373.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2842, pruned_loss=0.04811, over 1303302.84 frames.], batch size: 23, lr: 6.49e-04
2022-04-29 01:41:30,080 INFO [train.py:763] (3/8) Epoch 11, batch 550, loss[loss=0.1703, simple_loss=0.2762, pruned_loss=0.03222, over 7410.00 frames.], tot_loss[loss=0.1888, simple_loss=0.283, pruned_loss=0.04735, over 1329725.98 frames.], batch size: 21, lr: 6.48e-04
2022-04-29 01:42:36,718 INFO [train.py:763] (3/8) Epoch 11, batch 600, loss[loss=0.209, simple_loss=0.3163, pruned_loss=0.05083, over 7323.00 frames.], tot_loss[loss=0.19, simple_loss=0.2838, pruned_loss=0.04811, over 1348862.10 frames.], batch size: 22, lr: 6.48e-04
2022-04-29 01:43:44,063 INFO [train.py:763] (3/8) Epoch 11, batch 650, loss[loss=0.1813, simple_loss=0.292, pruned_loss=0.03531, over 7378.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2822, pruned_loss=0.04716, over 1370202.07 frames.], batch size: 23, lr: 6.48e-04
2022-04-29 01:44:51,066 INFO [train.py:763] (3/8) Epoch 11, batch 700, loss[loss=0.1932, simple_loss=0.2934, pruned_loss=0.04653, over 7282.00 frames.], tot_loss[loss=0.1891, simple_loss=0.283, pruned_loss=0.04759, over 1381103.82 frames.], batch size: 24, lr: 6.47e-04
2022-04-29 01:45:57,536 INFO [train.py:763] (3/8) Epoch 11, batch 750, loss[loss=0.1687, simple_loss=0.2617, pruned_loss=0.03784, over 7325.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2836, pruned_loss=0.04776, over 1386389.72 frames.], batch size: 20, lr: 6.47e-04
2022-04-29 01:47:03,479 INFO [train.py:763] (3/8) Epoch 11, batch 800, loss[loss=0.186, simple_loss=0.2781, pruned_loss=0.04697, over 7405.00 frames.], tot_loss[loss=0.19, simple_loss=0.2837, pruned_loss=0.04813, over 1398338.69 frames.], batch size: 18, lr: 6.47e-04
2022-04-29 01:48:08,963 INFO [train.py:763] (3/8) Epoch 11, batch 850, loss[loss=0.198, simple_loss=0.2866, pruned_loss=0.05466, over 6691.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2848, pruned_loss=0.04827, over 1402815.12 frames.], batch size: 31, lr: 6.46e-04
2022-04-29 01:49:14,789 INFO [train.py:763] (3/8) Epoch 11, batch 900, loss[loss=0.1799, simple_loss=0.2852, pruned_loss=0.03732, over 7337.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2849, pruned_loss=0.04826, over 1407805.23 frames.], batch size: 22, lr: 6.46e-04
2022-04-29 01:50:20,607 INFO [train.py:763] (3/8) Epoch 11, batch 950, loss[loss=0.1557, simple_loss=0.2609, pruned_loss=0.02529, over 7425.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2845, pruned_loss=0.04805, over 1413019.48 frames.], batch size: 20, lr: 6.46e-04
2022-04-29 01:51:27,136 INFO [train.py:763] (3/8) Epoch 11, batch 1000, loss[loss=0.19, simple_loss=0.286, pruned_loss=0.04699, over 7154.00 frames.], tot_loss[loss=0.191, simple_loss=0.2852, pruned_loss=0.04841, over 1415885.08 frames.], batch size: 19, lr: 6.46e-04
2022-04-29 01:52:32,489 INFO [train.py:763] (3/8) Epoch 11, batch 1050, loss[loss=0.1443, simple_loss=0.2314, pruned_loss=0.02855, over 7003.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2845, pruned_loss=0.04796, over 1415344.97 frames.], batch size: 16, lr: 6.45e-04
2022-04-29 01:53:38,688 INFO [train.py:763] (3/8) Epoch 11, batch 1100, loss[loss=0.1639, simple_loss=0.2629, pruned_loss=0.03246, over 7151.00 frames.], tot_loss[loss=0.191, simple_loss=0.2857, pruned_loss=0.04815, over 1417779.09 frames.], batch size: 19, lr: 6.45e-04
2022-04-29 01:54:45,797 INFO [train.py:763] (3/8) Epoch 11, batch 1150, loss[loss=0.213, simple_loss=0.3019, pruned_loss=0.06211, over 5114.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2852, pruned_loss=0.04813, over 1420568.38 frames.], batch size: 53, lr: 6.45e-04
2022-04-29 01:55:51,956 INFO [train.py:763] (3/8) Epoch 11, batch 1200, loss[loss=0.2065, simple_loss=0.2988, pruned_loss=0.05708, over 7114.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2852, pruned_loss=0.04823, over 1423428.16 frames.], batch size: 21, lr: 6.44e-04
2022-04-29 01:56:57,797 INFO [train.py:763] (3/8) Epoch 11, batch 1250, loss[loss=0.1896, simple_loss=0.2745, pruned_loss=0.05233, over 7001.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2851, pruned_loss=0.04879, over 1424543.17 frames.], batch size: 16, lr: 6.44e-04
2022-04-29 01:58:03,702 INFO [train.py:763] (3/8) Epoch 11, batch 1300, loss[loss=0.1596, simple_loss=0.2572, pruned_loss=0.03106, over 7319.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2849, pruned_loss=0.0484, over 1426378.55 frames.], batch size: 20, lr: 6.44e-04
2022-04-29 01:59:10,164 INFO [train.py:763] (3/8) Epoch 11, batch 1350, loss[loss=0.1856, simple_loss=0.2885, pruned_loss=0.04136, over 7324.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2847, pruned_loss=0.04846, over 1424306.88 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:00:15,526 INFO [train.py:763] (3/8) Epoch 11, batch 1400, loss[loss=0.2014, simple_loss=0.3043, pruned_loss=0.04922, over 7325.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2836, pruned_loss=0.04807, over 1421634.74 frames.], batch size: 21, lr: 6.43e-04
2022-04-29 02:01:21,165 INFO [train.py:763] (3/8) Epoch 11, batch 1450, loss[loss=0.1773, simple_loss=0.2684, pruned_loss=0.04307, over 7073.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2843, pruned_loss=0.04835, over 1422000.20 frames.], batch size: 18, lr: 6.43e-04
2022-04-29 02:02:28,454 INFO [train.py:763] (3/8) Epoch 11, batch 1500, loss[loss=0.2027, simple_loss=0.3007, pruned_loss=0.0523, over 7193.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2835, pruned_loss=0.04776, over 1425593.18 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:03:33,958 INFO [train.py:763] (3/8) Epoch 11, batch 1550, loss[loss=0.2067, simple_loss=0.3075, pruned_loss=0.05296, over 7231.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2829, pruned_loss=0.04774, over 1424429.92 frames.], batch size: 20, lr: 6.42e-04
2022-04-29 02:04:39,634 INFO [train.py:763] (3/8) Epoch 11, batch 1600, loss[loss=0.1718, simple_loss=0.261, pruned_loss=0.0413, over 7359.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2841, pruned_loss=0.0484, over 1424814.85 frames.], batch size: 19, lr: 6.42e-04
2022-04-29 02:06:04,015 INFO [train.py:763] (3/8) Epoch 11, batch 1650, loss[loss=0.2028, simple_loss=0.291, pruned_loss=0.05732, over 7375.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2837, pruned_loss=0.04823, over 1425851.96 frames.], batch size: 23, lr: 6.42e-04
2022-04-29 02:07:17,966 INFO [train.py:763] (3/8) Epoch 11, batch 1700, loss[loss=0.1887, simple_loss=0.2868, pruned_loss=0.04533, over 7222.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2839, pruned_loss=0.04785, over 1426769.99 frames.], batch size: 21, lr: 6.41e-04
2022-04-29 02:08:33,274 INFO [train.py:763] (3/8) Epoch 11, batch 1750, loss[loss=0.2038, simple_loss=0.298, pruned_loss=0.05478, over 7144.00 frames.], tot_loss[loss=0.19, simple_loss=0.2838, pruned_loss=0.04808, over 1428217.91 frames.], batch size: 26, lr: 6.41e-04
2022-04-29 02:09:47,985 INFO [train.py:763] (3/8) Epoch 11, batch 1800, loss[loss=0.1454, simple_loss=0.2377, pruned_loss=0.02659, over 7003.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2829, pruned_loss=0.04779, over 1428562.96 frames.], batch size: 16, lr: 6.41e-04
2022-04-29 02:11:03,170 INFO [train.py:763] (3/8) Epoch 11, batch 1850, loss[loss=0.2186, simple_loss=0.3117, pruned_loss=0.06275, over 7181.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2837, pruned_loss=0.04834, over 1426731.56 frames.], batch size: 26, lr: 6.40e-04
2022-04-29 02:12:18,078 INFO [train.py:763] (3/8) Epoch 11, batch 1900, loss[loss=0.205, simple_loss=0.2941, pruned_loss=0.058, over 7433.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2829, pruned_loss=0.04785, over 1429239.69 frames.], batch size: 20, lr: 6.40e-04
2022-04-29 02:13:32,348 INFO [train.py:763] (3/8) Epoch 11, batch 1950, loss[loss=0.1812, simple_loss=0.2613, pruned_loss=0.05058, over 6992.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2831, pruned_loss=0.04838, over 1428248.07 frames.], batch size: 16, lr: 6.40e-04
2022-04-29 02:14:38,124 INFO [train.py:763] (3/8) Epoch 11, batch 2000, loss[loss=0.1878, simple_loss=0.2829, pruned_loss=0.04638, over 6554.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2836, pruned_loss=0.04867, over 1426508.48 frames.], batch size: 38, lr: 6.39e-04
2022-04-29 02:15:44,446 INFO [train.py:763] (3/8) Epoch 11, batch 2050, loss[loss=0.2014, simple_loss=0.2919, pruned_loss=0.05544, over 7376.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2837, pruned_loss=0.04868, over 1424370.78 frames.], batch size: 23, lr: 6.39e-04
2022-04-29 02:16:50,750 INFO [train.py:763] (3/8) Epoch 11, batch 2100, loss[loss=0.1981, simple_loss=0.2982, pruned_loss=0.04902, over 6778.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2833, pruned_loss=0.04832, over 1428106.74 frames.], batch size: 31, lr: 6.39e-04
2022-04-29 02:17:57,122 INFO [train.py:763] (3/8) Epoch 11, batch 2150, loss[loss=0.1775, simple_loss=0.2584, pruned_loss=0.0483, over 6789.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2839, pruned_loss=0.04863, over 1422337.50 frames.], batch size: 15, lr: 6.38e-04
2022-04-29 02:19:03,271 INFO [train.py:763] (3/8) Epoch 11, batch 2200, loss[loss=0.1809, simple_loss=0.2777, pruned_loss=0.04207, over 7425.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2833, pruned_loss=0.04811, over 1426740.29 frames.], batch size: 20, lr: 6.38e-04
2022-04-29 02:20:09,533 INFO [train.py:763] (3/8) Epoch 11, batch 2250, loss[loss=0.1591, simple_loss=0.2574, pruned_loss=0.03043, over 7137.00 frames.], tot_loss[loss=0.1894, simple_loss=0.283, pruned_loss=0.04789, over 1426163.22 frames.], batch size: 17, lr: 6.38e-04
2022-04-29 02:21:16,306 INFO [train.py:763] (3/8) Epoch 11, batch 2300, loss[loss=0.1657, simple_loss=0.2608, pruned_loss=0.03528, over 7361.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2839, pruned_loss=0.04821, over 1424385.67 frames.], batch size: 19, lr: 6.38e-04
2022-04-29 02:22:22,093 INFO [train.py:763] (3/8) Epoch 11, batch 2350, loss[loss=0.1945, simple_loss=0.2875, pruned_loss=0.05069, over 7280.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2843, pruned_loss=0.04836, over 1426176.92 frames.], batch size: 24, lr: 6.37e-04
2022-04-29 02:23:28,143 INFO [train.py:763] (3/8) Epoch 11, batch 2400, loss[loss=0.1781, simple_loss=0.2759, pruned_loss=0.0401, over 7117.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2839, pruned_loss=0.04778, over 1428076.17 frames.], batch size: 21, lr: 6.37e-04
2022-04-29 02:24:33,621 INFO [train.py:763] (3/8) Epoch 11, batch 2450, loss[loss=0.2061, simple_loss=0.3138, pruned_loss=0.0492, over 7235.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2851, pruned_loss=0.04861, over 1425751.12 frames.], batch size: 20, lr: 6.37e-04
2022-04-29 02:25:39,227 INFO [train.py:763] (3/8) Epoch 11, batch 2500, loss[loss=0.1798, simple_loss=0.2621, pruned_loss=0.04877, over 7058.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2842, pruned_loss=0.04865, over 1425406.97 frames.], batch size: 18, lr: 6.36e-04
2022-04-29 02:26:45,645 INFO [train.py:763] (3/8) Epoch 11, batch 2550, loss[loss=0.1393, simple_loss=0.2325, pruned_loss=0.02301, over 7282.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2849, pruned_loss=0.04891, over 1428248.01 frames.], batch size: 17, lr: 6.36e-04
2022-04-29 02:27:50,865 INFO [train.py:763] (3/8) Epoch 11, batch 2600, loss[loss=0.1837, simple_loss=0.2888, pruned_loss=0.03928, over 7291.00 frames.], tot_loss[loss=0.1908, simple_loss=0.284, pruned_loss=0.04878, over 1422572.05 frames.], batch size: 24, lr: 6.36e-04
2022-04-29 02:28:56,395 INFO [train.py:763] (3/8) Epoch 11, batch 2650, loss[loss=0.1989, simple_loss=0.2909, pruned_loss=0.05349, over 7262.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2849, pruned_loss=0.04882, over 1418986.95 frames.], batch size: 19, lr: 6.36e-04
2022-04-29 02:30:03,348 INFO [train.py:763] (3/8) Epoch 11, batch 2700, loss[loss=0.182, simple_loss=0.2907, pruned_loss=0.03667, over 7309.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2847, pruned_loss=0.04873, over 1422710.23 frames.], batch size: 25, lr: 6.35e-04
2022-04-29 02:31:08,820 INFO [train.py:763] (3/8) Epoch 11, batch 2750, loss[loss=0.1779, simple_loss=0.2749, pruned_loss=0.04048, over 7435.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2832, pruned_loss=0.04764, over 1425323.65 frames.], batch size: 20, lr: 6.35e-04
2022-04-29 02:32:14,647 INFO [train.py:763] (3/8) Epoch 11, batch 2800, loss[loss=0.2079, simple_loss=0.3037, pruned_loss=0.05608, over 7111.00 frames.], tot_loss[loss=0.1891, simple_loss=0.283, pruned_loss=0.04763, over 1426319.55 frames.], batch size: 21, lr: 6.35e-04
2022-04-29 02:33:21,115 INFO [train.py:763] (3/8) Epoch 11, batch 2850, loss[loss=0.1997, simple_loss=0.3051, pruned_loss=0.04711, over 7327.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2826, pruned_loss=0.04747, over 1428473.58 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:34:28,402 INFO [train.py:763] (3/8) Epoch 11, batch 2900, loss[loss=0.2039, simple_loss=0.3001, pruned_loss=0.05383, over 7297.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2838, pruned_loss=0.04817, over 1424949.66 frames.], batch size: 24, lr: 6.34e-04
2022-04-29 02:35:35,071 INFO [train.py:763] (3/8) Epoch 11, batch 2950, loss[loss=0.2364, simple_loss=0.3224, pruned_loss=0.07521, over 7227.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2838, pruned_loss=0.04845, over 1421156.92 frames.], batch size: 21, lr: 6.34e-04
2022-04-29 02:36:40,644 INFO [train.py:763] (3/8) Epoch 11, batch 3000, loss[loss=0.1954, simple_loss=0.2853, pruned_loss=0.05281, over 7279.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2833, pruned_loss=0.04826, over 1422846.71 frames.], batch size: 25, lr: 6.33e-04
2022-04-29 02:36:40,645 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 02:36:55,964 INFO [train.py:792] (3/8) Epoch 11, validation: loss=0.1677, simple_loss=0.2702, pruned_loss=0.03262, over 698248.00 frames.
2022-04-29 02:38:01,324 INFO [train.py:763] (3/8) Epoch 11, batch 3050, loss[loss=0.1876, simple_loss=0.2969, pruned_loss=0.0392, over 7370.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2848, pruned_loss=0.0488, over 1420554.21 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:39:06,998 INFO [train.py:763] (3/8) Epoch 11, batch 3100, loss[loss=0.1846, simple_loss=0.2799, pruned_loss=0.04464, over 7324.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2842, pruned_loss=0.0483, over 1422351.31 frames.], batch size: 20, lr: 6.33e-04
2022-04-29 02:40:14,524 INFO [train.py:763] (3/8) Epoch 11, batch 3150, loss[loss=0.2028, simple_loss=0.2902, pruned_loss=0.05774, over 7366.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2846, pruned_loss=0.04851, over 1424817.51 frames.], batch size: 23, lr: 6.33e-04
2022-04-29 02:41:19,856 INFO [train.py:763] (3/8) Epoch 11, batch 3200, loss[loss=0.1871, simple_loss=0.2831, pruned_loss=0.04553, over 7118.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2844, pruned_loss=0.04832, over 1424747.12 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:42:26,203 INFO [train.py:763] (3/8) Epoch 11, batch 3250, loss[loss=0.1865, simple_loss=0.2882, pruned_loss=0.04237, over 7422.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2842, pruned_loss=0.04867, over 1425496.13 frames.], batch size: 21, lr: 6.32e-04
2022-04-29 02:43:31,317 INFO [train.py:763] (3/8) Epoch 11, batch 3300, loss[loss=0.1932, simple_loss=0.2779, pruned_loss=0.05426, over 7006.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2855, pruned_loss=0.04914, over 1425806.24 frames.], batch size: 16, lr: 6.32e-04
2022-04-29 02:44:36,748 INFO [train.py:763] (3/8) Epoch 11, batch 3350, loss[loss=0.1637, simple_loss=0.2558, pruned_loss=0.03583, over 7283.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2853, pruned_loss=0.04872, over 1426566.41 frames.], batch size: 18, lr: 6.31e-04
2022-04-29 02:45:42,397 INFO [train.py:763] (3/8) Epoch 11, batch 3400, loss[loss=0.2089, simple_loss=0.2869, pruned_loss=0.0655, over 6611.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2861, pruned_loss=0.04923, over 1421170.59 frames.], batch size: 38, lr: 6.31e-04
2022-04-29 02:46:49,527 INFO [train.py:763] (3/8) Epoch 11, batch 3450, loss[loss=0.1987, simple_loss=0.2958, pruned_loss=0.05082, over 7111.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2852, pruned_loss=0.04925, over 1419760.84 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:47:56,122 INFO [train.py:763] (3/8) Epoch 11, batch 3500, loss[loss=0.1607, simple_loss=0.2603, pruned_loss=0.0306, over 7308.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2856, pruned_loss=0.0489, over 1425366.44 frames.], batch size: 21, lr: 6.31e-04
2022-04-29 02:49:02,211 INFO [train.py:763] (3/8) Epoch 11, batch 3550, loss[loss=0.181, simple_loss=0.2631, pruned_loss=0.04942, over 7015.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2855, pruned_loss=0.04916, over 1423614.81 frames.], batch size: 16, lr: 6.30e-04
2022-04-29 02:50:08,007 INFO [train.py:763] (3/8) Epoch 11, batch 3600, loss[loss=0.2251, simple_loss=0.3153, pruned_loss=0.06743, over 7235.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2862, pruned_loss=0.04916, over 1425165.22 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:51:13,363 INFO [train.py:763] (3/8) Epoch 11, batch 3650, loss[loss=0.1855, simple_loss=0.2828, pruned_loss=0.04414, over 7440.00 frames.], tot_loss[loss=0.192, simple_loss=0.2861, pruned_loss=0.049, over 1425087.73 frames.], batch size: 20, lr: 6.30e-04
2022-04-29 02:52:20,064 INFO [train.py:763] (3/8) Epoch 11, batch 3700, loss[loss=0.1983, simple_loss=0.2953, pruned_loss=0.05067, over 6858.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2851, pruned_loss=0.04858, over 1421768.85 frames.], batch size: 31, lr: 6.29e-04
2022-04-29 02:53:25,479 INFO [train.py:763] (3/8) Epoch 11, batch 3750, loss[loss=0.2061, simple_loss=0.314, pruned_loss=0.04907, over 7369.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2845, pruned_loss=0.04825, over 1425965.90 frames.], batch size: 23, lr: 6.29e-04
2022-04-29 02:54:30,950 INFO [train.py:763] (3/8) Epoch 11, batch 3800, loss[loss=0.189, simple_loss=0.294, pruned_loss=0.04205, over 7129.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2843, pruned_loss=0.04804, over 1428242.19 frames.], batch size: 26, lr: 6.29e-04
2022-04-29 02:55:36,105 INFO [train.py:763] (3/8) Epoch 11, batch 3850, loss[loss=0.2078, simple_loss=0.2983, pruned_loss=0.05867, over 7121.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2848, pruned_loss=0.04805, over 1430049.42 frames.], batch size: 21, lr: 6.29e-04
2022-04-29 02:56:41,383 INFO [train.py:763] (3/8) Epoch 11, batch 3900, loss[loss=0.1661, simple_loss=0.2673, pruned_loss=0.03247, over 7441.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2836, pruned_loss=0.04694, over 1431160.04 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:57:46,958 INFO [train.py:763] (3/8) Epoch 11, batch 3950, loss[loss=0.1869, simple_loss=0.2899, pruned_loss=0.04194, over 7229.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2827, pruned_loss=0.0469, over 1432445.10 frames.], batch size: 20, lr: 6.28e-04
2022-04-29 02:58:52,090 INFO [train.py:763] (3/8) Epoch 11, batch 4000, loss[loss=0.1858, simple_loss=0.2847, pruned_loss=0.04342, over 7408.00 frames.], tot_loss[loss=0.1894, simple_loss=0.2834, pruned_loss=0.04767, over 1427433.95 frames.], batch size: 21, lr: 6.28e-04
2022-04-29 02:59:57,356 INFO [train.py:763] (3/8) Epoch 11, batch 4050, loss[loss=0.1876, simple_loss=0.2837, pruned_loss=0.04579, over 7426.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2842, pruned_loss=0.04821, over 1425471.83 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:01:03,190 INFO [train.py:763] (3/8) Epoch 11, batch 4100, loss[loss=0.179, simple_loss=0.2711, pruned_loss=0.04339, over 7333.00 frames.], tot_loss[loss=0.19, simple_loss=0.2837, pruned_loss=0.04816, over 1421234.62 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:02:08,242 INFO [train.py:763] (3/8) Epoch 11, batch 4150, loss[loss=0.1795, simple_loss=0.266, pruned_loss=0.04647, over 7233.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2839, pruned_loss=0.04787, over 1421841.75 frames.], batch size: 20, lr: 6.27e-04
2022-04-29 03:03:14,695 INFO [train.py:763] (3/8) Epoch 11, batch 4200, loss[loss=0.1694, simple_loss=0.2779, pruned_loss=0.03046, over 7330.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2845, pruned_loss=0.0482, over 1420674.34 frames.], batch size: 22, lr: 6.27e-04
2022-04-29 03:04:21,492 INFO [train.py:763] (3/8) Epoch 11, batch 4250, loss[loss=0.1727, simple_loss=0.2642, pruned_loss=0.04063, over 7409.00 frames.], tot_loss[loss=0.1895, simple_loss=0.2834, pruned_loss=0.04779, over 1424606.81 frames.], batch size: 18, lr: 6.26e-04
2022-04-29 03:05:27,592 INFO [train.py:763] (3/8) Epoch 11, batch 4300, loss[loss=0.1984, simple_loss=0.2995, pruned_loss=0.04866, over 7241.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2835, pruned_loss=0.04816, over 1418266.09 frames.], batch size: 20, lr: 6.26e-04
2022-04-29 03:06:35,253 INFO [train.py:763] (3/8) Epoch 11, batch 4350, loss[loss=0.1741, simple_loss=0.2893, pruned_loss=0.02945, over 7219.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2812, pruned_loss=0.04713, over 1419899.56 frames.], batch size: 22, lr: 6.26e-04
2022-04-29 03:07:41,464 INFO [train.py:763] (3/8) Epoch 11, batch 4400, loss[loss=0.2224, simple_loss=0.3249, pruned_loss=0.05997, over 7309.00 frames.], tot_loss[loss=0.1874, simple_loss=0.281, pruned_loss=0.04693, over 1417940.88 frames.], batch size: 21, lr: 6.25e-04
2022-04-29 03:08:47,763 INFO [train.py:763] (3/8) Epoch 11, batch 4450, loss[loss=0.1827, simple_loss=0.2809, pruned_loss=0.04227, over 6114.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2802, pruned_loss=0.04701, over 1406034.88 frames.], batch size: 37, lr: 6.25e-04
2022-04-29 03:09:54,259 INFO [train.py:763] (3/8) Epoch 11, batch 4500, loss[loss=0.2037, simple_loss=0.3068, pruned_loss=0.05032, over 6301.00 frames.], tot_loss[loss=0.1883, simple_loss=0.281, pruned_loss=0.04777, over 1389160.14 frames.], batch size: 37, lr: 6.25e-04
2022-04-29 03:10:59,841 INFO [train.py:763] (3/8) Epoch 11, batch 4550, loss[loss=0.2471, simple_loss=0.3184, pruned_loss=0.08788, over 4926.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2831, pruned_loss=0.04955, over 1349856.65 frames.], batch size: 52, lr: 6.25e-04
2022-04-29 03:12:38,229 INFO [train.py:763] (3/8) Epoch 12, batch 0, loss[loss=0.2144, simple_loss=0.3071, pruned_loss=0.06088, over 7150.00 frames.], tot_loss[loss=0.2144, simple_loss=0.3071, pruned_loss=0.06088, over 7150.00 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:13:44,617 INFO [train.py:763] (3/8) Epoch 12, batch 50, loss[loss=0.1796, simple_loss=0.2826, pruned_loss=0.03832, over 7234.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2831, pruned_loss=0.04611, over 319090.60 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:14:50,356 INFO [train.py:763] (3/8) Epoch 12, batch 100, loss[loss=0.2173, simple_loss=0.3098, pruned_loss=0.06244, over 7185.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2862, pruned_loss=0.04769, over 565148.95 frames.], batch size: 23, lr: 6.03e-04
2022-04-29 03:15:56,440 INFO [train.py:763] (3/8) Epoch 12, batch 150, loss[loss=0.1687, simple_loss=0.2615, pruned_loss=0.03795, over 7146.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2864, pruned_loss=0.04726, over 754598.50 frames.], batch size: 20, lr: 6.03e-04
2022-04-29 03:17:02,801 INFO [train.py:763] (3/8) Epoch 12, batch 200, loss[loss=0.1844, simple_loss=0.2891, pruned_loss=0.03983, over 7136.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2835, pruned_loss=0.04672, over 900051.56 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:18:09,054 INFO [train.py:763] (3/8) Epoch 12, batch 250, loss[loss=0.1616, simple_loss=0.2513, pruned_loss=0.03592, over 7219.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2826, pruned_loss=0.04632, over 1014152.92 frames.], batch size: 16, lr: 6.02e-04
2022-04-29 03:19:15,280 INFO [train.py:763] (3/8) Epoch 12, batch 300, loss[loss=0.2076, simple_loss=0.3062, pruned_loss=0.0545, over 7152.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2819, pruned_loss=0.04613, over 1103088.56 frames.], batch size: 20, lr: 6.02e-04
2022-04-29 03:20:20,570 INFO [train.py:763] (3/8) Epoch 12, batch 350, loss[loss=0.1776, simple_loss=0.2849, pruned_loss=0.03518, over 7063.00 frames.], tot_loss[loss=0.1868, simple_loss=0.282, pruned_loss=0.04576, over 1175320.09 frames.], batch size: 28, lr: 6.01e-04
2022-04-29 03:21:26,172 INFO [train.py:763] (3/8) Epoch 12, batch 400, loss[loss=0.1738, simple_loss=0.273, pruned_loss=0.0373, over 7358.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2824, pruned_loss=0.04624, over 1232494.79 frames.], batch size: 19, lr: 6.01e-04
2022-04-29 03:22:31,836 INFO [train.py:763] (3/8) Epoch 12, batch 450, loss[loss=0.1727, simple_loss=0.2747, pruned_loss=0.03535, over 7325.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2818, pruned_loss=0.04641, over 1276109.12 frames.], batch size: 21, lr: 6.01e-04
2022-04-29 03:23:38,034 INFO [train.py:763] (3/8) Epoch 12, batch 500, loss[loss=0.1915, simple_loss=0.2881, pruned_loss=0.04743, over 6390.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2799, pruned_loss=0.04534, over 1309883.07 frames.], batch size: 37, lr: 6.01e-04
2022-04-29 03:24:43,944 INFO [train.py:763] (3/8) Epoch 12, batch 550, loss[loss=0.1914, simple_loss=0.2911, pruned_loss=0.04583, over 7388.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2803, pruned_loss=0.04605, over 1332619.58 frames.], batch size: 23, lr: 6.00e-04
2022-04-29 03:25:49,963 INFO [train.py:763] (3/8) Epoch 12, batch 600, loss[loss=0.1679, simple_loss=0.2579, pruned_loss=0.03895, over 6789.00 frames.], tot_loss[loss=0.1855, simple_loss=0.279, pruned_loss=0.046, over 1346407.32 frames.], batch size: 15, lr: 6.00e-04
2022-04-29 03:26:55,896 INFO [train.py:763] (3/8) Epoch 12, batch 650, loss[loss=0.1808, simple_loss=0.2671, pruned_loss=0.04728, over 7290.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2802, pruned_loss=0.0461, over 1366602.52 frames.], batch size: 18, lr: 6.00e-04
2022-04-29 03:28:02,297 INFO [train.py:763] (3/8) Epoch 12, batch 700, loss[loss=0.1665, simple_loss=0.2516, pruned_loss=0.04069, over 6774.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2813, pruned_loss=0.04655, over 1383657.70 frames.], batch size: 15, lr: 6.00e-04
2022-04-29 03:29:07,993 INFO [train.py:763] (3/8) Epoch 12, batch 750, loss[loss=0.188, simple_loss=0.289, pruned_loss=0.04349, over 7181.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2813, pruned_loss=0.04621, over 1395552.26 frames.], batch size: 23, lr: 5.99e-04
2022-04-29 03:30:14,227 INFO [train.py:763] (3/8) Epoch 12, batch 800, loss[loss=0.1759, simple_loss=0.2796, pruned_loss=0.03606, over 7226.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2816, pruned_loss=0.04603, over 1404982.32 frames.], batch size: 22, lr: 5.99e-04
2022-04-29 03:31:20,651 INFO [train.py:763] (3/8) Epoch 12, batch 850, loss[loss=0.1617, simple_loss=0.2554, pruned_loss=0.03403, over 7138.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2823, pruned_loss=0.04668, over 1411039.88 frames.], batch size: 17, lr: 5.99e-04
2022-04-29 03:32:27,843 INFO [train.py:763] (3/8) Epoch 12, batch 900, loss[loss=0.1608, simple_loss=0.2618, pruned_loss=0.0299, over 7322.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2815, pruned_loss=0.04639, over 1413876.40 frames.], batch size: 20, lr: 5.99e-04
2022-04-29 03:33:44,135 INFO [train.py:763] (3/8) Epoch 12, batch 950, loss[loss=0.1659, simple_loss=0.2717, pruned_loss=0.03002, over 7198.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2819, pruned_loss=0.04614, over 1414701.95 frames.], batch size: 26, lr: 5.98e-04
2022-04-29 03:34:49,703 INFO [train.py:763] (3/8) Epoch 12, batch 1000, loss[loss=0.2444, simple_loss=0.3375, pruned_loss=0.0757, over 6323.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2819, pruned_loss=0.04587, over 1415056.48 frames.], batch size: 37, lr: 5.98e-04
2022-04-29 03:35:56,179 INFO [train.py:763] (3/8) Epoch 12, batch 1050, loss[loss=0.1985, simple_loss=0.2961, pruned_loss=0.05047, over 7265.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2811, pruned_loss=0.04592, over 1416536.99 frames.], batch size: 19, lr: 5.98e-04
2022-04-29 03:37:02,296 INFO [train.py:763] (3/8) Epoch 12, batch 1100, loss[loss=0.2033, simple_loss=0.3035, pruned_loss=0.05148, over 7383.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2816, pruned_loss=0.04588, over 1422180.56 frames.], batch size: 23, lr: 5.97e-04
2022-04-29 03:38:08,854 INFO [train.py:763] (3/8) Epoch 12, batch 1150, loss[loss=0.1681, simple_loss=0.2518, pruned_loss=0.04219, over 7328.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2807, pruned_loss=0.04575, over 1425019.71 frames.], batch size: 20, lr: 5.97e-04
2022-04-29 03:39:15,119 INFO [train.py:763] (3/8) Epoch 12, batch 1200, loss[loss=0.2443, simple_loss=0.3205, pruned_loss=0.08408, over 4797.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2808, pruned_loss=0.04606, over 1420856.24 frames.], batch size: 54, lr: 5.97e-04
2022-04-29 03:40:21,632 INFO [train.py:763] (3/8) Epoch 12, batch 1250, loss[loss=0.1879, simple_loss=0.2877, pruned_loss=0.04409, over 7154.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2808, pruned_loss=0.04612, over 1418950.75 frames.], batch size: 19, lr: 5.97e-04
2022-04-29 03:41:28,265 INFO [train.py:763] (3/8) Epoch 12, batch 1300, loss[loss=0.1794, simple_loss=0.2684, pruned_loss=0.0452, over 7068.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2808, pruned_loss=0.04617, over 1418472.10 frames.], batch size: 18, lr: 5.96e-04
2022-04-29 03:42:33,925 INFO [train.py:763] (3/8) Epoch 12, batch 1350, loss[loss=0.2225, simple_loss=0.2975, pruned_loss=0.07371, over 5303.00 frames.], tot_loss[loss=0.188, simple_loss=0.2821, pruned_loss=0.04694, over 1416062.73 frames.], batch size: 53, lr: 5.96e-04
2022-04-29 03:43:39,826 INFO [train.py:763] (3/8) Epoch 12, batch 1400, loss[loss=0.1935, simple_loss=0.289, pruned_loss=0.04903, over 7295.00 frames.], tot_loss[loss=0.1877, simple_loss=0.282, pruned_loss=0.04675, over 1415420.03 frames.], batch size: 25, lr: 5.96e-04
2022-04-29 03:44:45,260 INFO [train.py:763] (3/8) Epoch 12, batch 1450, loss[loss=0.1785, simple_loss=0.2846, pruned_loss=0.03622, over 7317.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2825, pruned_loss=0.04659, over 1413551.86 frames.], batch size: 21, lr: 5.96e-04
2022-04-29 03:45:51,846 INFO [train.py:763] (3/8) Epoch 12, batch 1500, loss[loss=0.2077, simple_loss=0.3019, pruned_loss=0.05675, over 7198.00 frames.], tot_loss[loss=0.1873, simple_loss=0.282, pruned_loss=0.04636, over 1417518.08 frames.], batch size: 23, lr: 5.95e-04
2022-04-29 03:46:59,219 INFO [train.py:763] (3/8) Epoch 12, batch 1550, loss[loss=0.2034, simple_loss=0.3091, pruned_loss=0.04888, over 7152.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2819, pruned_loss=0.04621, over 1419251.56 frames.], batch size: 28, lr: 5.95e-04
2022-04-29 03:48:05,681 INFO [train.py:763] (3/8) Epoch 12, batch 1600, loss[loss=0.1952, simple_loss=0.2842, pruned_loss=0.0531, over 7299.00 frames.], tot_loss[loss=0.1875, simple_loss=0.282, pruned_loss=0.04647, over 1418705.95 frames.], batch size: 25, lr: 5.95e-04
2022-04-29 03:49:11,827 INFO [train.py:763] (3/8) Epoch 12, batch 1650, loss[loss=0.1819, simple_loss=0.2857, pruned_loss=0.03909, over 7285.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2815, pruned_loss=0.04594, over 1422389.24 frames.], batch size: 24, lr: 5.95e-04
2022-04-29 03:50:17,593 INFO [train.py:763] (3/8) Epoch 12, batch 1700, loss[loss=0.1554, simple_loss=0.253, pruned_loss=0.02885, over 7120.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2813, pruned_loss=0.04605, over 1417712.41 frames.], batch size: 17, lr: 5.94e-04
2022-04-29 03:51:23,274 INFO [train.py:763] (3/8) Epoch 12, batch 1750, loss[loss=0.1987, simple_loss=0.2989, pruned_loss=0.04925, over 7134.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2798, pruned_loss=0.04522, over 1422103.49 frames.], batch size: 26, lr: 5.94e-04
2022-04-29 03:52:29,188 INFO [train.py:763] (3/8) Epoch 12, batch 1800, loss[loss=0.1947, simple_loss=0.2701, pruned_loss=0.05962, over 6981.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2803, pruned_loss=0.04527, over 1427266.37 frames.], batch size: 16, lr: 5.94e-04
2022-04-29 03:53:35,385 INFO [train.py:763] (3/8) Epoch 12, batch 1850, loss[loss=0.1983, simple_loss=0.2951, pruned_loss=0.0508, over 7331.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2798, pruned_loss=0.0448, over 1427934.03 frames.], batch size: 22, lr: 5.94e-04
2022-04-29 03:54:41,516 INFO [train.py:763] (3/8) Epoch 12, batch 1900, loss[loss=0.1702, simple_loss=0.2705, pruned_loss=0.03495, over 7238.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2807, pruned_loss=0.04492, over 1428204.87 frames.], batch size: 20, lr: 5.93e-04
2022-04-29 03:55:47,355 INFO [train.py:763] (3/8) Epoch 12, batch 1950, loss[loss=0.1962, simple_loss=0.2872, pruned_loss=0.05259, over 7271.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2807, pruned_loss=0.04492, over 1428133.49 frames.], batch size: 17, lr: 5.93e-04
2022-04-29 03:56:53,844 INFO [train.py:763] (3/8) Epoch 12, batch 2000, loss[loss=0.1665, simple_loss=0.2529, pruned_loss=0.04003, over 6992.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2803, pruned_loss=0.04552, over 1427993.61 frames.], batch size: 16, lr: 5.93e-04
2022-04-29 03:57:59,757 INFO [train.py:763] (3/8) Epoch 12, batch 2050, loss[loss=0.1877, simple_loss=0.2767, pruned_loss=0.04935, over 7161.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2809, pruned_loss=0.04639, over 1421297.90 frames.], batch size: 19, lr: 5.93e-04
2022-04-29 03:59:05,459 INFO [train.py:763] (3/8) Epoch 12, batch 2100, loss[loss=0.1762, simple_loss=0.2698, pruned_loss=0.04126, over 7154.00 frames.], tot_loss[loss=0.187, simple_loss=0.2814, pruned_loss=0.04631, over 1420998.37 frames.], batch size: 19, lr: 5.92e-04
2022-04-29 04:00:11,330 INFO [train.py:763] (3/8) Epoch 12, batch 2150, loss[loss=0.1474, simple_loss=0.2449, pruned_loss=0.02494, over 7279.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2816, pruned_loss=0.0461, over 1421381.26 frames.], batch size: 18, lr: 5.92e-04
2022-04-29 04:01:17,159 INFO [train.py:763] (3/8) Epoch 12, batch 2200, loss[loss=0.1751, simple_loss=0.2796, pruned_loss=0.03528, over 7335.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2809, pruned_loss=0.04579, over 1422539.17 frames.], batch size: 20, lr: 5.92e-04
2022-04-29 04:02:23,225 INFO [train.py:763] (3/8) Epoch 12, batch 2250, loss[loss=0.1793, simple_loss=0.2732, pruned_loss=0.04273, over 7032.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2809, pruned_loss=0.04598, over 1420746.05 frames.], batch size: 28, lr: 5.91e-04
2022-04-29 04:03:29,734 INFO [train.py:763] (3/8) Epoch 12, batch 2300, loss[loss=0.2029, simple_loss=0.2868, pruned_loss=0.05948, over 7107.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2818, pruned_loss=0.04636, over 1423940.11 frames.], batch size: 21, lr: 5.91e-04
2022-04-29 04:04:36,292 INFO [train.py:763] (3/8) Epoch 12, batch 2350, loss[loss=0.1731, simple_loss=0.2652, pruned_loss=0.04046, over 7160.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2818, pruned_loss=0.04648, over 1425287.20 frames.], batch size: 19, lr: 5.91e-04
2022-04-29 04:05:42,053 INFO [train.py:763] (3/8) Epoch 12, batch 2400, loss[loss=0.1792, simple_loss=0.2679, pruned_loss=0.0452, over 7129.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2812, pruned_loss=0.04597, over 1426420.66 frames.], batch size: 17, lr: 5.91e-04
2022-04-29 04:06:47,899 INFO [train.py:763] (3/8) Epoch 12, batch 2450, loss[loss=0.2053, simple_loss=0.3143, pruned_loss=0.04811, over 7224.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2818, pruned_loss=0.04631, over 1425893.50 frames.], batch size: 21, lr: 5.90e-04
2022-04-29 04:07:54,985 INFO [train.py:763] (3/8) Epoch 12, batch 2500, loss[loss=0.1667, simple_loss=0.2638, pruned_loss=0.03481, over 7272.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2834, pruned_loss=0.04706, over 1426931.44 frames.], batch size: 18, lr: 5.90e-04
2022-04-29 04:09:01,286 INFO [train.py:763] (3/8) Epoch 12, batch 2550, loss[loss=0.167, simple_loss=0.2544, pruned_loss=0.03976, over 6790.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2831, pruned_loss=0.04748, over 1428740.04 frames.], batch size: 15, lr: 5.90e-04
2022-04-29 04:10:08,002 INFO [train.py:763] (3/8) Epoch 12, batch 2600, loss[loss=0.1536, simple_loss=0.2446, pruned_loss=0.03128, over 6794.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2821, pruned_loss=0.04687, over 1424695.23 frames.], batch size: 15, lr: 5.90e-04
2022-04-29 04:11:13,659 INFO [train.py:763] (3/8) Epoch 12, batch 2650, loss[loss=0.1782, simple_loss=0.2671, pruned_loss=0.04468, over 7007.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2827, pruned_loss=0.04681, over 1422747.42 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:12:19,554 INFO [train.py:763] (3/8) Epoch 12, batch 2700, loss[loss=0.1787, simple_loss=0.2566, pruned_loss=0.05044, over 7002.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2813, pruned_loss=0.04646, over 1424222.47 frames.], batch size: 16, lr: 5.89e-04
2022-04-29 04:13:25,129 INFO [train.py:763] (3/8) Epoch 12, batch 2750, loss[loss=0.1995, simple_loss=0.3053, pruned_loss=0.04683, over 7109.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2815, pruned_loss=0.04683, over 1421572.90 frames.], batch size: 21, lr: 5.89e-04
2022-04-29 04:14:30,847 INFO [train.py:763] (3/8) Epoch 12, batch 2800, loss[loss=0.1502, simple_loss=0.2398, pruned_loss=0.03034, over 7114.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2828, pruned_loss=0.04708, over 1420944.01 frames.], batch size: 17, lr: 5.89e-04
2022-04-29 04:15:37,559 INFO [train.py:763] (3/8) Epoch 12, batch 2850, loss[loss=0.2109, simple_loss=0.3029, pruned_loss=0.05947, over 7398.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2829, pruned_loss=0.0468, over 1427301.15 frames.], batch size: 23, lr: 5.88e-04
2022-04-29 04:16:43,202 INFO [train.py:763] (3/8) Epoch 12, batch 2900, loss[loss=0.1719, simple_loss=0.2645, pruned_loss=0.03971, over 7357.00 frames.], tot_loss[loss=0.189, simple_loss=0.2841, pruned_loss=0.04699, over 1424903.86 frames.], batch size: 19, lr: 5.88e-04
2022-04-29 04:17:49,201 INFO [train.py:763] (3/8) Epoch 12, batch 2950, loss[loss=0.1824, simple_loss=0.2781, pruned_loss=0.04336, over 7115.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2821, pruned_loss=0.04589, over 1426784.53 frames.], batch size: 21, lr: 5.88e-04
2022-04-29 04:18:54,866 INFO [train.py:763] (3/8) Epoch 12, batch 3000, loss[loss=0.1638, simple_loss=0.2539, pruned_loss=0.03686, over 7281.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2822, pruned_loss=0.04581, over 1427613.48 frames.], batch size: 17, lr: 5.88e-04
2022-04-29 04:18:54,867 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 04:19:10,345 INFO [train.py:792] (3/8) Epoch 12, validation: loss=0.1673, simple_loss=0.27, pruned_loss=0.03225, over 698248.00 frames.
2022-04-29 04:20:16,213 INFO [train.py:763] (3/8) Epoch 12, batch 3050, loss[loss=0.1779, simple_loss=0.2675, pruned_loss=0.04416, over 7131.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2818, pruned_loss=0.04549, over 1428380.07 frames.], batch size: 17, lr: 5.87e-04
2022-04-29 04:21:32,106 INFO [train.py:763] (3/8) Epoch 12, batch 3100, loss[loss=0.1851, simple_loss=0.2846, pruned_loss=0.04281, over 7106.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2811, pruned_loss=0.04522, over 1427301.64 frames.], batch size: 21, lr: 5.87e-04
2022-04-29 04:22:37,467 INFO [train.py:763] (3/8) Epoch 12, batch 3150, loss[loss=0.2246, simple_loss=0.3241, pruned_loss=0.06253, over 7306.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2822, pruned_loss=0.04562, over 1424448.53 frames.], batch size: 25, lr: 5.87e-04
2022-04-29 04:23:52,369 INFO [train.py:763] (3/8) Epoch 12, batch 3200, loss[loss=0.2543, simple_loss=0.3311, pruned_loss=0.0887, over 5257.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2825, pruned_loss=0.04596, over 1425861.00 frames.], batch size: 52, lr: 5.87e-04
2022-04-29 04:25:17,144 INFO [train.py:763] (3/8) Epoch 12, batch 3250, loss[loss=0.1443, simple_loss=0.2355, pruned_loss=0.02654, over 7286.00 frames.], tot_loss[loss=0.1859, simple_loss=0.281, pruned_loss=0.0454, over 1428591.16 frames.], batch size: 17, lr: 5.86e-04
2022-04-29 04:26:23,034 INFO [train.py:763] (3/8) Epoch 12, batch 3300, loss[loss=0.1841, simple_loss=0.2846, pruned_loss=0.04182, over 7334.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2811, pruned_loss=0.04556, over 1427905.41 frames.], batch size: 20, lr: 5.86e-04
2022-04-29 04:27:37,931 INFO [train.py:763] (3/8) Epoch 12, batch 3350, loss[loss=0.1685, simple_loss=0.253, pruned_loss=0.04199, over 7417.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2816, pruned_loss=0.04607, over 1421287.19 frames.], batch size: 17, lr: 5.86e-04
2022-04-29 04:29:03,558 INFO [train.py:763] (3/8) Epoch 12, batch 3400, loss[loss=0.2035, simple_loss=0.2904, pruned_loss=0.05833, over 7364.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2821, pruned_loss=0.04603, over 1424661.56 frames.], batch size: 23, lr: 5.86e-04
2022-04-29 04:30:18,595 INFO [train.py:763] (3/8) Epoch 12, batch 3450, loss[loss=0.18, simple_loss=0.2611, pruned_loss=0.04941, over 7410.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2824, pruned_loss=0.0466, over 1413498.10 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:31:24,819 INFO [train.py:763] (3/8) Epoch 12, batch 3500, loss[loss=0.187, simple_loss=0.2949, pruned_loss=0.03949, over 6798.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2831, pruned_loss=0.04675, over 1415882.45 frames.], batch size: 31, lr: 5.85e-04
2022-04-29 04:32:31,885 INFO [train.py:763] (3/8) Epoch 12, batch 3550, loss[loss=0.1518, simple_loss=0.2433, pruned_loss=0.0302, over 6996.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2826, pruned_loss=0.04681, over 1420943.10 frames.], batch size: 16, lr: 5.85e-04
2022-04-29 04:33:38,541 INFO [train.py:763] (3/8) Epoch 12, batch 3600, loss[loss=0.1686, simple_loss=0.2552, pruned_loss=0.04097, over 7273.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2821, pruned_loss=0.04654, over 1420793.84 frames.], batch size: 18, lr: 5.85e-04
2022-04-29 04:34:44,019 INFO [train.py:763] (3/8) Epoch 12, batch 3650, loss[loss=0.2174, simple_loss=0.3176, pruned_loss=0.05863, over 7407.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2829, pruned_loss=0.04683, over 1423538.30 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:35:49,778 INFO [train.py:763] (3/8) Epoch 12, batch 3700, loss[loss=0.1655, simple_loss=0.264, pruned_loss=0.03343, over 7256.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2818, pruned_loss=0.04642, over 1424679.39 frames.], batch size: 19, lr: 5.84e-04
2022-04-29 04:36:55,380 INFO [train.py:763] (3/8) Epoch 12, batch 3750, loss[loss=0.1766, simple_loss=0.2808, pruned_loss=0.03624, over 7417.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2818, pruned_loss=0.04638, over 1425058.13 frames.], batch size: 21, lr: 5.84e-04
2022-04-29 04:38:01,435 INFO [train.py:763] (3/8) Epoch 12, batch 3800, loss[loss=0.2119, simple_loss=0.3056, pruned_loss=0.05913, over 7105.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2823, pruned_loss=0.04666, over 1428741.61 frames.], batch size: 28, lr: 5.84e-04
2022-04-29 04:39:06,787 INFO [train.py:763] (3/8) Epoch 12, batch 3850, loss[loss=0.2091, simple_loss=0.3028, pruned_loss=0.05775, over 7205.00 frames.], tot_loss[loss=0.189, simple_loss=0.2836, pruned_loss=0.04717, over 1426863.06 frames.], batch size: 22, lr: 5.83e-04
2022-04-29 04:40:13,129 INFO [train.py:763] (3/8) Epoch 12, batch 3900, loss[loss=0.2251, simple_loss=0.3105, pruned_loss=0.06988, over 7292.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2826, pruned_loss=0.04636, over 1425862.84 frames.], batch size: 24, lr: 5.83e-04
2022-04-29 04:41:18,536 INFO [train.py:763] (3/8) Epoch 12, batch 3950, loss[loss=0.216, simple_loss=0.3129, pruned_loss=0.0596, over 7203.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2829, pruned_loss=0.04649, over 1424683.04 frames.], batch size: 23, lr: 5.83e-04
2022-04-29 04:42:24,201 INFO [train.py:763] (3/8) Epoch 12, batch 4000, loss[loss=0.1718, simple_loss=0.2618, pruned_loss=0.04085, over 7147.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2827, pruned_loss=0.04683, over 1422986.01 frames.], batch size: 17, lr: 5.83e-04
2022-04-29 04:43:29,489 INFO [train.py:763] (3/8) Epoch 12, batch 4050, loss[loss=0.1716, simple_loss=0.2686, pruned_loss=0.03728, over 7232.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2815, pruned_loss=0.04612, over 1424915.90 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:44:35,687 INFO [train.py:763] (3/8) Epoch 12, batch 4100, loss[loss=0.2225, simple_loss=0.3259, pruned_loss=0.05952, over 7141.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2799, pruned_loss=0.04536, over 1424751.62 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:45:41,162 INFO [train.py:763] (3/8) Epoch 12, batch 4150, loss[loss=0.1537, simple_loss=0.2503, pruned_loss=0.02857, over 7439.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2814, pruned_loss=0.04578, over 1421014.14 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:46:48,355 INFO [train.py:763] (3/8) Epoch 12, batch 4200, loss[loss=0.2048, simple_loss=0.3021, pruned_loss=0.05377, over 7146.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2808, pruned_loss=0.0458, over 1421957.78 frames.], batch size: 20, lr: 5.82e-04
2022-04-29 04:47:54,427 INFO [train.py:763] (3/8) Epoch 12, batch 4250, loss[loss=0.1724, simple_loss=0.2797, pruned_loss=0.03252, over 7173.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2801, pruned_loss=0.04522, over 1418904.35 frames.], batch size: 26, lr: 5.81e-04
2022-04-29 04:49:00,803 INFO [train.py:763] (3/8) Epoch 12, batch 4300, loss[loss=0.1636, simple_loss=0.2664, pruned_loss=0.03045, over 7431.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2804, pruned_loss=0.04563, over 1416329.14 frames.], batch size: 20, lr: 5.81e-04
2022-04-29 04:50:06,808 INFO [train.py:763] (3/8) Epoch 12, batch 4350, loss[loss=0.1605, simple_loss=0.2573, pruned_loss=0.03189, over 7000.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2803, pruned_loss=0.04545, over 1410501.42 frames.], batch size: 16, lr: 5.81e-04
2022-04-29 04:51:13,413 INFO [train.py:763] (3/8) Epoch 12, batch 4400, loss[loss=0.1985, simple_loss=0.283, pruned_loss=0.05696, over 4715.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2789, pruned_loss=0.04534, over 1408916.47 frames.], batch size: 52, lr: 5.81e-04
2022-04-29 04:52:19,270 INFO [train.py:763] (3/8) Epoch 12, batch 4450, loss[loss=0.214, simple_loss=0.3077, pruned_loss=0.06015, over 7272.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2781, pruned_loss=0.04509, over 1406676.39 frames.], batch size: 24, lr: 5.81e-04
2022-04-29 04:53:25,177 INFO [train.py:763] (3/8) Epoch 12, batch 4500, loss[loss=0.193, simple_loss=0.2942, pruned_loss=0.04589, over 7409.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2802, pruned_loss=0.04628, over 1389118.60 frames.], batch size: 21, lr: 5.80e-04
2022-04-29 04:54:31,135 INFO [train.py:763] (3/8) Epoch 12, batch 4550, loss[loss=0.1891, simple_loss=0.2817, pruned_loss=0.04823, over 5204.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2831, pruned_loss=0.04772, over 1355687.60 frames.], batch size: 53, lr: 5.80e-04
2022-04-29 04:56:09,896 INFO [train.py:763] (3/8) Epoch 13, batch 0, loss[loss=0.1795, simple_loss=0.2732, pruned_loss=0.04295, over 7372.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2732, pruned_loss=0.04295, over 7372.00 frames.], batch size: 23, lr: 5.61e-04
2022-04-29 04:57:15,971 INFO [train.py:763] (3/8) Epoch 13, batch 50, loss[loss=0.2234, simple_loss=0.3084, pruned_loss=0.0692, over 7128.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2788, pruned_loss=0.04668, over 322832.62 frames.], batch size: 21, lr: 5.61e-04
2022-04-29 04:58:22,262 INFO [train.py:763] (3/8) Epoch 13, batch 100, loss[loss=0.2051, simple_loss=0.288, pruned_loss=0.06111, over 7157.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2797, pruned_loss=0.04562, over 572516.28 frames.], batch size: 20, lr: 5.61e-04
2022-04-29 04:59:28,140 INFO [train.py:763] (3/8) Epoch 13, batch 150, loss[loss=0.1687, simple_loss=0.2473, pruned_loss=0.04506, over 6970.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2775, pruned_loss=0.04416, over 762723.50 frames.], batch size: 16, lr: 5.61e-04
2022-04-29 05:00:33,584 INFO [train.py:763] (3/8) Epoch 13, batch 200, loss[loss=0.1681, simple_loss=0.2753, pruned_loss=0.03046, over 7210.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2785, pruned_loss=0.04426, over 910092.89 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:01:39,401 INFO [train.py:763] (3/8) Epoch 13, batch 250, loss[loss=0.2028, simple_loss=0.2994, pruned_loss=0.05303, over 7204.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2803, pruned_loss=0.04522, over 1026340.24 frames.], batch size: 22, lr: 5.60e-04
2022-04-29 05:02:44,821 INFO [train.py:763] (3/8) Epoch 13, batch 300, loss[loss=0.1837, simple_loss=0.2765, pruned_loss=0.0454, over 7408.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2823, pruned_loss=0.04559, over 1113087.03 frames.], batch size: 21, lr: 5.60e-04
2022-04-29 05:03:50,335 INFO [train.py:763] (3/8) Epoch 13, batch 350, loss[loss=0.1705, simple_loss=0.2657, pruned_loss=0.03769, over 7439.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2804, pruned_loss=0.0451, over 1180950.21 frames.], batch size: 20, lr: 5.60e-04
2022-04-29 05:04:55,868 INFO [train.py:763] (3/8) Epoch 13, batch 400, loss[loss=0.2026, simple_loss=0.3037, pruned_loss=0.05076, over 7066.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2802, pruned_loss=0.04527, over 1231303.58 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:06:01,968 INFO [train.py:763] (3/8) Epoch 13, batch 450, loss[loss=0.1873, simple_loss=0.2901, pruned_loss=0.04229, over 6513.00 frames.], tot_loss[loss=0.186, simple_loss=0.2812, pruned_loss=0.04542, over 1273270.46 frames.], batch size: 37, lr: 5.59e-04
2022-04-29 05:07:07,983 INFO [train.py:763] (3/8) Epoch 13, batch 500, loss[loss=0.2116, simple_loss=0.3093, pruned_loss=0.05695, over 7094.00 frames.], tot_loss[loss=0.1852, simple_loss=0.28, pruned_loss=0.04518, over 1301910.85 frames.], batch size: 28, lr: 5.59e-04
2022-04-29 05:08:13,588 INFO [train.py:763] (3/8) Epoch 13, batch 550, loss[loss=0.1838, simple_loss=0.2887, pruned_loss=0.03946, over 6254.00 frames.], tot_loss[loss=0.185, simple_loss=0.28, pruned_loss=0.04503, over 1326667.79 frames.], batch size: 37, lr: 5.59e-04
2022-04-29 05:09:19,616 INFO [train.py:763] (3/8) Epoch 13, batch 600, loss[loss=0.1643, simple_loss=0.2698, pruned_loss=0.0294, over 7321.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2797, pruned_loss=0.04477, over 1348789.35 frames.], batch size: 21, lr: 5.59e-04
2022-04-29 05:10:25,762 INFO [train.py:763] (3/8) Epoch 13, batch 650, loss[loss=0.1652, simple_loss=0.257, pruned_loss=0.03671, over 7069.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2807, pruned_loss=0.0453, over 1361942.71 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:11:32,548 INFO [train.py:763] (3/8) Epoch 13, batch 700, loss[loss=0.1544, simple_loss=0.2517, pruned_loss=0.02854, over 7263.00 frames.], tot_loss[loss=0.1853, simple_loss=0.28, pruned_loss=0.04528, over 1377272.19 frames.], batch size: 18, lr: 5.58e-04
2022-04-29 05:12:37,744 INFO [train.py:763] (3/8) Epoch 13, batch 750, loss[loss=0.2162, simple_loss=0.3119, pruned_loss=0.06018, over 7194.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2794, pruned_loss=0.04512, over 1383395.77 frames.], batch size: 23, lr: 5.58e-04
2022-04-29 05:13:44,375 INFO [train.py:763] (3/8) Epoch 13, batch 800, loss[loss=0.2061, simple_loss=0.297, pruned_loss=0.05759, over 7311.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2801, pruned_loss=0.04522, over 1392901.47 frames.], batch size: 25, lr: 5.58e-04
2022-04-29 05:14:50,890 INFO [train.py:763] (3/8) Epoch 13, batch 850, loss[loss=0.1838, simple_loss=0.2911, pruned_loss=0.03828, over 7219.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2793, pruned_loss=0.04461, over 1400825.09 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:15:57,547 INFO [train.py:763] (3/8) Epoch 13, batch 900, loss[loss=0.1915, simple_loss=0.2738, pruned_loss=0.0546, over 7169.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2796, pruned_loss=0.04493, over 1403732.07 frames.], batch size: 18, lr: 5.57e-04
2022-04-29 05:17:04,245 INFO [train.py:763] (3/8) Epoch 13, batch 950, loss[loss=0.1879, simple_loss=0.2898, pruned_loss=0.04296, over 7227.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2799, pruned_loss=0.04468, over 1403900.50 frames.], batch size: 21, lr: 5.57e-04
2022-04-29 05:18:11,092 INFO [train.py:763] (3/8) Epoch 13, batch 1000, loss[loss=0.2154, simple_loss=0.3029, pruned_loss=0.064, over 7217.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2792, pruned_loss=0.04452, over 1410604.79 frames.], batch size: 22, lr: 5.57e-04
2022-04-29 05:19:17,014 INFO [train.py:763] (3/8) Epoch 13, batch 1050, loss[loss=0.2238, simple_loss=0.3076, pruned_loss=0.07001, over 7414.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2782, pruned_loss=0.04442, over 1411015.47 frames.], batch size: 21, lr: 5.56e-04
2022-04-29 05:20:22,745 INFO [train.py:763] (3/8) Epoch 13, batch 1100, loss[loss=0.208, simple_loss=0.2966, pruned_loss=0.05968, over 6804.00 frames.], tot_loss[loss=0.1832, simple_loss=0.278, pruned_loss=0.04414, over 1410268.80 frames.], batch size: 31, lr: 5.56e-04
2022-04-29 05:21:28,694 INFO [train.py:763] (3/8) Epoch 13, batch 1150, loss[loss=0.189, simple_loss=0.3013, pruned_loss=0.03829, over 7337.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2793, pruned_loss=0.04419, over 1410315.50 frames.], batch size: 22, lr: 5.56e-04
2022-04-29 05:22:34,607 INFO [train.py:763] (3/8) Epoch 13, batch 1200, loss[loss=0.2109, simple_loss=0.2971, pruned_loss=0.06237, over 4719.00 frames.], tot_loss[loss=0.1845, simple_loss=0.28, pruned_loss=0.04447, over 1409694.47 frames.], batch size: 54, lr: 5.56e-04
2022-04-29 05:23:40,299 INFO [train.py:763] (3/8) Epoch 13, batch 1250, loss[loss=0.1951, simple_loss=0.2905, pruned_loss=0.0498, over 7440.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2807, pruned_loss=0.04472, over 1413959.31 frames.], batch size: 20, lr: 5.56e-04
2022-04-29 05:24:45,575 INFO [train.py:763] (3/8) Epoch 13, batch 1300, loss[loss=0.1516, simple_loss=0.2481, pruned_loss=0.0276, over 7262.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2801, pruned_loss=0.04413, over 1417326.71 frames.], batch size: 19, lr: 5.55e-04
2022-04-29 05:25:51,457 INFO [train.py:763] (3/8) Epoch 13, batch 1350, loss[loss=0.1459, simple_loss=0.2323, pruned_loss=0.02973, over 7273.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2793, pruned_loss=0.04394, over 1421083.74 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:26:57,106 INFO [train.py:763] (3/8) Epoch 13, batch 1400, loss[loss=0.1707, simple_loss=0.261, pruned_loss=0.04025, over 7185.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2801, pruned_loss=0.0445, over 1417119.37 frames.], batch size: 18, lr: 5.55e-04
2022-04-29 05:28:02,590 INFO [train.py:763] (3/8) Epoch 13, batch 1450, loss[loss=0.1607, simple_loss=0.2482, pruned_loss=0.0366, over 7286.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2794, pruned_loss=0.0442, over 1420721.02 frames.], batch size: 17, lr: 5.55e-04
2022-04-29 05:29:08,107 INFO [train.py:763] (3/8) Epoch 13, batch 1500, loss[loss=0.1938, simple_loss=0.272, pruned_loss=0.05781, over 7264.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2781, pruned_loss=0.04378, over 1423113.72 frames.], batch size: 17, lr: 5.54e-04
2022-04-29 05:30:14,045 INFO [train.py:763] (3/8) Epoch 13, batch 1550, loss[loss=0.2127, simple_loss=0.3038, pruned_loss=0.0608, over 6510.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2784, pruned_loss=0.0439, over 1417856.95 frames.], batch size: 38, lr: 5.54e-04
2022-04-29 05:31:19,477 INFO [train.py:763] (3/8) Epoch 13, batch 1600, loss[loss=0.1944, simple_loss=0.302, pruned_loss=0.04336, over 7414.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2795, pruned_loss=0.04411, over 1416280.03 frames.], batch size: 21, lr: 5.54e-04
2022-04-29 05:32:25,607 INFO [train.py:763] (3/8) Epoch 13, batch 1650, loss[loss=0.1773, simple_loss=0.2772, pruned_loss=0.03865, over 7237.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2804, pruned_loss=0.04452, over 1418541.42 frames.], batch size: 20, lr: 5.54e-04
2022-04-29 05:33:31,237 INFO [train.py:763] (3/8) Epoch 13, batch 1700, loss[loss=0.1724, simple_loss=0.2682, pruned_loss=0.03833, over 6451.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2803, pruned_loss=0.04458, over 1418537.20 frames.], batch size: 38, lr: 5.54e-04
2022-04-29 05:34:36,766 INFO [train.py:763] (3/8) Epoch 13, batch 1750, loss[loss=0.1451, simple_loss=0.233, pruned_loss=0.02863, over 7272.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2796, pruned_loss=0.04401, over 1421649.52 frames.], batch size: 17, lr: 5.53e-04
2022-04-29 05:35:42,700 INFO [train.py:763] (3/8) Epoch 13, batch 1800, loss[loss=0.212, simple_loss=0.3119, pruned_loss=0.05603, over 7136.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2785, pruned_loss=0.04348, over 1426583.75 frames.], batch size: 20, lr: 5.53e-04
2022-04-29 05:36:48,185 INFO [train.py:763] (3/8) Epoch 13, batch 1850, loss[loss=0.2124, simple_loss=0.3061, pruned_loss=0.05939, over 7315.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2792, pruned_loss=0.04398, over 1426173.16 frames.], batch size: 25, lr: 5.53e-04
2022-04-29 05:37:54,118 INFO [train.py:763] (3/8) Epoch 13, batch 1900, loss[loss=0.2163, simple_loss=0.3183, pruned_loss=0.05711, over 6492.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2804, pruned_loss=0.04459, over 1421300.73 frames.], batch size: 38, lr: 5.53e-04
2022-04-29 05:39:00,689 INFO [train.py:763] (3/8) Epoch 13, batch 1950, loss[loss=0.1672, simple_loss=0.2607, pruned_loss=0.0368, over 7247.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2806, pruned_loss=0.04454, over 1423050.46 frames.], batch size: 19, lr: 5.52e-04
2022-04-29 05:40:07,432 INFO [train.py:763] (3/8) Epoch 13, batch 2000, loss[loss=0.2002, simple_loss=0.3092, pruned_loss=0.04557, over 7340.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2805, pruned_loss=0.04453, over 1424430.77 frames.], batch size: 22, lr: 5.52e-04
2022-04-29 05:41:13,023 INFO [train.py:763] (3/8) Epoch 13, batch 2050, loss[loss=0.221, simple_loss=0.3196, pruned_loss=0.06116, over 7383.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2801, pruned_loss=0.04447, over 1425749.71 frames.], batch size: 23, lr: 5.52e-04
2022-04-29 05:42:18,152 INFO [train.py:763] (3/8) Epoch 13, batch 2100, loss[loss=0.1935, simple_loss=0.2893, pruned_loss=0.04885, over 7249.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2802, pruned_loss=0.04403, over 1425090.33 frames.], batch size: 20, lr: 5.52e-04
2022-04-29 05:43:24,241 INFO [train.py:763] (3/8) Epoch 13, batch 2150, loss[loss=0.2088, simple_loss=0.3017, pruned_loss=0.05795, over 7127.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2796, pruned_loss=0.0437, over 1427722.38 frames.], batch size: 26, lr: 5.52e-04
2022-04-29 05:44:29,757 INFO [train.py:763] (3/8) Epoch 13, batch 2200, loss[loss=0.1938, simple_loss=0.2974, pruned_loss=0.04512, over 7438.00 frames.], tot_loss[loss=0.184, simple_loss=0.2798, pruned_loss=0.04407, over 1426616.52 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:45:35,367 INFO [train.py:763] (3/8) Epoch 13, batch 2250, loss[loss=0.1969, simple_loss=0.2985, pruned_loss=0.04766, over 7222.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2793, pruned_loss=0.04406, over 1427892.66 frames.], batch size: 20, lr: 5.51e-04
2022-04-29 05:46:41,459 INFO [train.py:763] (3/8) Epoch 13, batch 2300, loss[loss=0.1947, simple_loss=0.2914, pruned_loss=0.04899, over 7062.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2785, pruned_loss=0.04381, over 1427752.34 frames.], batch size: 28, lr: 5.51e-04
2022-04-29 05:47:46,890 INFO [train.py:763] (3/8) Epoch 13, batch 2350, loss[loss=0.2279, simple_loss=0.3047, pruned_loss=0.07552, over 5173.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2789, pruned_loss=0.04416, over 1427329.92 frames.], batch size: 52, lr: 5.51e-04
2022-04-29 05:48:52,768 INFO [train.py:763] (3/8) Epoch 13, batch 2400, loss[loss=0.182, simple_loss=0.2606, pruned_loss=0.05168, over 7290.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2782, pruned_loss=0.04382, over 1427777.65 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:49:58,371 INFO [train.py:763] (3/8) Epoch 13, batch 2450, loss[loss=0.1997, simple_loss=0.3078, pruned_loss=0.04586, over 6728.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2797, pruned_loss=0.04427, over 1429996.81 frames.], batch size: 31, lr: 5.50e-04
2022-04-29 05:51:03,649 INFO [train.py:763] (3/8) Epoch 13, batch 2500, loss[loss=0.1716, simple_loss=0.2575, pruned_loss=0.04281, over 7277.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2802, pruned_loss=0.04459, over 1426156.54 frames.], batch size: 17, lr: 5.50e-04
2022-04-29 05:52:08,890 INFO [train.py:763] (3/8) Epoch 13, batch 2550, loss[loss=0.2182, simple_loss=0.3168, pruned_loss=0.05978, over 7320.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2812, pruned_loss=0.0452, over 1422708.99 frames.], batch size: 25, lr: 5.50e-04
2022-04-29 05:53:14,608 INFO [train.py:763] (3/8) Epoch 13, batch 2600, loss[loss=0.1808, simple_loss=0.2741, pruned_loss=0.04373, over 7404.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2806, pruned_loss=0.04487, over 1419183.25 frames.], batch size: 21, lr: 5.50e-04
2022-04-29 05:54:20,019 INFO [train.py:763] (3/8) Epoch 13, batch 2650, loss[loss=0.2316, simple_loss=0.3267, pruned_loss=0.06828, over 7102.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2813, pruned_loss=0.04523, over 1416528.52 frames.], batch size: 21, lr: 5.49e-04
2022-04-29 05:55:25,827 INFO [train.py:763] (3/8) Epoch 13, batch 2700, loss[loss=0.1594, simple_loss=0.2458, pruned_loss=0.03652, over 7008.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2811, pruned_loss=0.04508, over 1421282.17 frames.], batch size: 16, lr: 5.49e-04
2022-04-29 05:56:31,325 INFO [train.py:763] (3/8) Epoch 13, batch 2750, loss[loss=0.2035, simple_loss=0.2991, pruned_loss=0.05396, over 7283.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2799, pruned_loss=0.0447, over 1426627.49 frames.], batch size: 24, lr: 5.49e-04
2022-04-29 05:57:36,853 INFO [train.py:763] (3/8) Epoch 13, batch 2800, loss[loss=0.1685, simple_loss=0.2549, pruned_loss=0.0411, over 7146.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2791, pruned_loss=0.04461, over 1425699.61 frames.], batch size: 17, lr: 5.49e-04
2022-04-29 05:58:42,724 INFO [train.py:763] (3/8) Epoch 13, batch 2850, loss[loss=0.1884, simple_loss=0.2806, pruned_loss=0.04812, over 7420.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2786, pruned_loss=0.04423, over 1426746.47 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 05:59:48,436 INFO [train.py:763] (3/8) Epoch 13, batch 2900, loss[loss=0.1809, simple_loss=0.2841, pruned_loss=0.03888, over 7124.00 frames.], tot_loss[loss=0.1835, simple_loss=0.279, pruned_loss=0.04403, over 1427962.68 frames.], batch size: 21, lr: 5.48e-04
2022-04-29 06:00:53,880 INFO [train.py:763] (3/8) Epoch 13, batch 2950, loss[loss=0.2019, simple_loss=0.2907, pruned_loss=0.05654, over 7183.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2799, pruned_loss=0.04439, over 1429047.23 frames.], batch size: 23, lr: 5.48e-04
2022-04-29 06:01:59,746 INFO [train.py:763] (3/8) Epoch 13, batch 3000, loss[loss=0.194, simple_loss=0.2926, pruned_loss=0.04765, over 7298.00 frames.], tot_loss[loss=0.184, simple_loss=0.2788, pruned_loss=0.04466, over 1430502.82 frames.], batch size: 24, lr: 5.48e-04
2022-04-29 06:01:59,747 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 06:02:15,158 INFO [train.py:792] (3/8) Epoch 13, validation: loss=0.1677, simple_loss=0.2714, pruned_loss=0.03198, over 698248.00 frames.
2022-04-29 06:03:21,966 INFO [train.py:763] (3/8) Epoch 13, batch 3050, loss[loss=0.1589, simple_loss=0.2465, pruned_loss=0.03565, over 7288.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2793, pruned_loss=0.04523, over 1430541.77 frames.], batch size: 17, lr: 5.48e-04
2022-04-29 06:04:29,181 INFO [train.py:763] (3/8) Epoch 13, batch 3100, loss[loss=0.2055, simple_loss=0.2952, pruned_loss=0.05787, over 7183.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2799, pruned_loss=0.04539, over 1431428.69 frames.], batch size: 23, lr: 5.47e-04
2022-04-29 06:05:35,704 INFO [train.py:763] (3/8) Epoch 13, batch 3150, loss[loss=0.2397, simple_loss=0.3155, pruned_loss=0.08195, over 5340.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2783, pruned_loss=0.04455, over 1430617.57 frames.], batch size: 52, lr: 5.47e-04
2022-04-29 06:06:41,344 INFO [train.py:763] (3/8) Epoch 13, batch 3200, loss[loss=0.1738, simple_loss=0.2783, pruned_loss=0.03461, over 7332.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2784, pruned_loss=0.04417, over 1429881.59 frames.], batch size: 22, lr: 5.47e-04
2022-04-29 06:07:46,883 INFO [train.py:763] (3/8) Epoch 13, batch 3250, loss[loss=0.2265, simple_loss=0.3277, pruned_loss=0.0626, over 7149.00 frames.], tot_loss[loss=0.184, simple_loss=0.2792, pruned_loss=0.04439, over 1427095.58 frames.], batch size: 26, lr: 5.47e-04
2022-04-29 06:08:52,446 INFO [train.py:763] (3/8) Epoch 13, batch 3300, loss[loss=0.1602, simple_loss=0.2587, pruned_loss=0.03089, over 7154.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2794, pruned_loss=0.04447, over 1423418.60 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:09:57,826 INFO [train.py:763] (3/8) Epoch 13, batch 3350, loss[loss=0.1595, simple_loss=0.2496, pruned_loss=0.03468, over 7408.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2782, pruned_loss=0.04366, over 1425667.85 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:11:03,348 INFO [train.py:763] (3/8) Epoch 13, batch 3400, loss[loss=0.1868, simple_loss=0.2796, pruned_loss=0.04695, over 7157.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2791, pruned_loss=0.04382, over 1426341.11 frames.], batch size: 18, lr: 5.46e-04
2022-04-29 06:12:10,252 INFO [train.py:763] (3/8) Epoch 13, batch 3450, loss[loss=0.1866, simple_loss=0.2917, pruned_loss=0.04074, over 7124.00 frames.], tot_loss[loss=0.184, simple_loss=0.2799, pruned_loss=0.04405, over 1425636.18 frames.], batch size: 21, lr: 5.46e-04
2022-04-29 06:13:16,582 INFO [train.py:763] (3/8) Epoch 13, batch 3500, loss[loss=0.1972, simple_loss=0.3013, pruned_loss=0.0466, over 7332.00 frames.], tot_loss[loss=0.184, simple_loss=0.2795, pruned_loss=0.04424, over 1428579.55 frames.], batch size: 22, lr: 5.46e-04
2022-04-29 06:14:22,079 INFO [train.py:763] (3/8) Epoch 13, batch 3550, loss[loss=0.1801, simple_loss=0.2827, pruned_loss=0.03875, over 7320.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2793, pruned_loss=0.04424, over 1428419.79 frames.], batch size: 21, lr: 5.45e-04
2022-04-29 06:15:27,778 INFO [train.py:763] (3/8) Epoch 13, batch 3600, loss[loss=0.1609, simple_loss=0.2602, pruned_loss=0.03081, over 7341.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2778, pruned_loss=0.0435, over 1431555.31 frames.], batch size: 19, lr: 5.45e-04
2022-04-29 06:16:33,706 INFO [train.py:763] (3/8) Epoch 13, batch 3650, loss[loss=0.1833, simple_loss=0.2845, pruned_loss=0.04105, over 7233.00 frames.], tot_loss[loss=0.183, simple_loss=0.2783, pruned_loss=0.04391, over 1430336.50 frames.], batch size: 20, lr: 5.45e-04
2022-04-29 06:17:39,181 INFO [train.py:763] (3/8) Epoch 13, batch 3700, loss[loss=0.2062, simple_loss=0.3096, pruned_loss=0.05135, over 7287.00 frames.], tot_loss[loss=0.1843, simple_loss=0.279, pruned_loss=0.04478, over 1422469.84 frames.], batch size: 24, lr: 5.45e-04
2022-04-29 06:18:44,836 INFO [train.py:763] (3/8) Epoch 13, batch 3750, loss[loss=0.2286, simple_loss=0.3152, pruned_loss=0.07097, over 5284.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2793, pruned_loss=0.04495, over 1421329.90 frames.], batch size: 52, lr: 5.45e-04
2022-04-29 06:19:51,469 INFO [train.py:763] (3/8) Epoch 13, batch 3800, loss[loss=0.1576, simple_loss=0.2496, pruned_loss=0.03285, over 6999.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2798, pruned_loss=0.04503, over 1419982.19 frames.], batch size: 16, lr: 5.44e-04
2022-04-29 06:20:57,070 INFO [train.py:763] (3/8) Epoch 13, batch 3850, loss[loss=0.2209, simple_loss=0.3161, pruned_loss=0.0628, over 7210.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2804, pruned_loss=0.04513, over 1419900.38 frames.], batch size: 22, lr: 5.44e-04
2022-04-29 06:22:02,332 INFO [train.py:763] (3/8) Epoch 13, batch 3900, loss[loss=0.1825, simple_loss=0.2813, pruned_loss=0.04183, over 7319.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2811, pruned_loss=0.04575, over 1422099.42 frames.], batch size: 21, lr: 5.44e-04
2022-04-29 06:23:08,128 INFO [train.py:763] (3/8) Epoch 13, batch 3950, loss[loss=0.2341, simple_loss=0.3119, pruned_loss=0.07818, over 5049.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2796, pruned_loss=0.04503, over 1419773.71 frames.], batch size: 53, lr: 5.44e-04
2022-04-29 06:24:13,267 INFO [train.py:763] (3/8) Epoch 13, batch 4000, loss[loss=0.1799, simple_loss=0.2919, pruned_loss=0.03399, over 7334.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2801, pruned_loss=0.04522, over 1421248.26 frames.], batch size: 22, lr: 5.43e-04
2022-04-29 06:25:19,011 INFO [train.py:763] (3/8) Epoch 13, batch 4050, loss[loss=0.1683, simple_loss=0.2605, pruned_loss=0.03805, over 7268.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2791, pruned_loss=0.0451, over 1423474.05 frames.], batch size: 16, lr: 5.43e-04
2022-04-29 06:26:24,353 INFO [train.py:763] (3/8) Epoch 13, batch 4100, loss[loss=0.2071, simple_loss=0.2969, pruned_loss=0.05868, over 6946.00 frames.], tot_loss[loss=0.1847, simple_loss=0.279, pruned_loss=0.0452, over 1421016.26 frames.], batch size: 32, lr: 5.43e-04
2022-04-29 06:27:29,931 INFO [train.py:763] (3/8) Epoch 13, batch 4150, loss[loss=0.1916, simple_loss=0.2912, pruned_loss=0.04599, over 7214.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2783, pruned_loss=0.04463, over 1420250.72 frames.], batch size: 21, lr: 5.43e-04
2022-04-29 06:28:36,035 INFO [train.py:763] (3/8) Epoch 13, batch 4200, loss[loss=0.1405, simple_loss=0.2367, pruned_loss=0.02218, over 7276.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2767, pruned_loss=0.04415, over 1422366.65 frames.], batch size: 17, lr: 5.43e-04
2022-04-29 06:29:41,276 INFO [train.py:763] (3/8) Epoch 13, batch 4250, loss[loss=0.1925, simple_loss=0.287, pruned_loss=0.04897, over 6348.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2767, pruned_loss=0.04392, over 1416189.82 frames.], batch size: 37, lr: 5.42e-04
2022-04-29 06:30:47,743 INFO [train.py:763] (3/8) Epoch 13, batch 4300, loss[loss=0.1801, simple_loss=0.2736, pruned_loss=0.04327, over 7220.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2783, pruned_loss=0.0446, over 1411570.74 frames.], batch size: 21, lr: 5.42e-04
2022-04-29 06:31:53,159 INFO [train.py:763] (3/8) Epoch 13, batch 4350, loss[loss=0.1388, simple_loss=0.2252, pruned_loss=0.02622, over 7238.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2776, pruned_loss=0.04432, over 1408809.26 frames.], batch size: 16, lr: 5.42e-04
2022-04-29 06:33:10,015 INFO [train.py:763] (3/8) Epoch 13, batch 4400, loss[loss=0.1979, simple_loss=0.2969, pruned_loss=0.04943, over 7137.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2779, pruned_loss=0.04424, over 1403677.41 frames.], batch size: 20, lr: 5.42e-04
2022-04-29 06:34:14,930 INFO [train.py:763] (3/8) Epoch 13, batch 4450, loss[loss=0.2085, simple_loss=0.2997, pruned_loss=0.05867, over 5241.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2794, pruned_loss=0.04465, over 1394241.28 frames.], batch size: 52, lr: 5.42e-04
2022-04-29 06:35:30,493 INFO [train.py:763] (3/8) Epoch 13, batch 4500, loss[loss=0.2278, simple_loss=0.3123, pruned_loss=0.07165, over 4564.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2801, pruned_loss=0.04568, over 1378340.69 frames.], batch size: 52, lr: 5.41e-04
2022-04-29 06:36:35,410 INFO [train.py:763] (3/8) Epoch 13, batch 4550, loss[loss=0.179, simple_loss=0.2699, pruned_loss=0.04402, over 6792.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2809, pruned_loss=0.04601, over 1368359.36 frames.], batch size: 31, lr: 5.41e-04
2022-04-29 06:38:13,963 INFO [train.py:763] (3/8) Epoch 14, batch 0, loss[loss=0.2005, simple_loss=0.2976, pruned_loss=0.05172, over 7022.00 frames.], tot_loss[loss=0.2005, simple_loss=0.2976, pruned_loss=0.05172, over 7022.00 frames.], batch size: 28, lr: 5.25e-04
2022-04-29 06:39:20,734 INFO [train.py:763] (3/8) Epoch 14, batch 50, loss[loss=0.2324, simple_loss=0.313, pruned_loss=0.07592, over 5037.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2801, pruned_loss=0.04352, over 322042.74 frames.], batch size: 52, lr: 5.24e-04
2022-04-29 06:40:45,784 INFO [train.py:763] (3/8) Epoch 14, batch 100, loss[loss=0.2418, simple_loss=0.3171, pruned_loss=0.08323, over 7174.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2782, pruned_loss=0.04249, over 568673.93 frames.], batch size: 18, lr: 5.24e-04
2022-04-29 06:41:59,830 INFO [train.py:763] (3/8) Epoch 14, batch 150, loss[loss=0.165, simple_loss=0.2608, pruned_loss=0.03464, over 7118.00 frames.], tot_loss[loss=0.182, simple_loss=0.2797, pruned_loss=0.0422, over 758912.12 frames.], batch size: 21, lr: 5.24e-04
2022-04-29 06:43:06,513 INFO [train.py:763] (3/8) Epoch 14, batch 200, loss[loss=0.1829, simple_loss=0.2779, pruned_loss=0.04396, over 7331.00 frames.], tot_loss[loss=0.183, simple_loss=0.2798, pruned_loss=0.04306, over 903442.69 frames.], batch size: 20, lr: 5.24e-04
2022-04-29 06:44:23,223 INFO [train.py:763] (3/8) Epoch 14, batch 250, loss[loss=0.1929, simple_loss=0.2832, pruned_loss=0.05128, over 6399.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2807, pruned_loss=0.04414, over 1020110.19 frames.], batch size: 38, lr: 5.24e-04
2022-04-29 06:45:48,391 INFO [train.py:763] (3/8) Epoch 14, batch 300, loss[loss=0.1659, simple_loss=0.2529, pruned_loss=0.0394, over 7130.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2785, pruned_loss=0.04318, over 1110433.74 frames.], batch size: 17, lr: 5.23e-04
2022-04-29 06:46:55,901 INFO [train.py:763] (3/8) Epoch 14, batch 350, loss[loss=0.1677, simple_loss=0.2467, pruned_loss=0.04433, over 6803.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2778, pruned_loss=0.04352, over 1171838.01 frames.], batch size: 15, lr: 5.23e-04
2022-04-29 06:48:03,001 INFO [train.py:763] (3/8) Epoch 14, batch 400, loss[loss=0.2051, simple_loss=0.3031, pruned_loss=0.05356, over 7156.00 frames.], tot_loss[loss=0.1831, simple_loss=0.278, pruned_loss=0.04411, over 1227426.98 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:49:01,687 INFO [train.py:763] (3/8) Epoch 14, batch 450, loss[loss=0.1827, simple_loss=0.2733, pruned_loss=0.04598, over 7164.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2777, pruned_loss=0.04385, over 1272081.73 frames.], batch size: 19, lr: 5.23e-04
2022-04-29 06:50:05,439 INFO [train.py:763] (3/8) Epoch 14, batch 500, loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.03365, over 7441.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2778, pruned_loss=0.04394, over 1303848.69 frames.], batch size: 20, lr: 5.23e-04
2022-04-29 06:51:07,459 INFO [train.py:763] (3/8) Epoch 14, batch 550, loss[loss=0.187, simple_loss=0.2737, pruned_loss=0.05019, over 7289.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2776, pruned_loss=0.04364, over 1332242.30 frames.], batch size: 18, lr: 5.22e-04
2022-04-29 06:52:12,672 INFO [train.py:763] (3/8) Epoch 14, batch 600, loss[loss=0.1495, simple_loss=0.2538, pruned_loss=0.02259, over 7229.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2775, pruned_loss=0.04339, over 1355348.80 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:53:18,167 INFO [train.py:763] (3/8) Epoch 14, batch 650, loss[loss=0.1818, simple_loss=0.2835, pruned_loss=0.04009, over 7343.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2773, pruned_loss=0.04291, over 1370008.08 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:54:23,430 INFO [train.py:763] (3/8) Epoch 14, batch 700, loss[loss=0.1827, simple_loss=0.285, pruned_loss=0.04014, over 7320.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2777, pruned_loss=0.04333, over 1382897.49 frames.], batch size: 20, lr: 5.22e-04
2022-04-29 06:55:28,865 INFO [train.py:763] (3/8) Epoch 14, batch 750, loss[loss=0.1928, simple_loss=0.2885, pruned_loss=0.04852, over 7331.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2782, pruned_loss=0.04363, over 1391447.73 frames.], batch size: 22, lr: 5.22e-04
2022-04-29 06:56:34,176 INFO [train.py:763] (3/8) Epoch 14, batch 800, loss[loss=0.1835, simple_loss=0.2793, pruned_loss=0.04383, over 7341.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2781, pruned_loss=0.04325, over 1399422.21 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 06:57:40,706 INFO [train.py:763] (3/8) Epoch 14, batch 850, loss[loss=0.1788, simple_loss=0.2674, pruned_loss=0.04516, over 7152.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2782, pruned_loss=0.04353, over 1401281.07 frames.], batch size: 17, lr: 5.21e-04
2022-04-29 06:58:46,053 INFO [train.py:763] (3/8) Epoch 14, batch 900, loss[loss=0.2036, simple_loss=0.2939, pruned_loss=0.05664, over 7276.00 frames.], tot_loss[loss=0.183, simple_loss=0.2783, pruned_loss=0.04383, over 1396011.85 frames.], batch size: 19, lr: 5.21e-04
2022-04-29 06:59:51,292 INFO [train.py:763] (3/8) Epoch 14, batch 950, loss[loss=0.1914, simple_loss=0.2829, pruned_loss=0.0499, over 7334.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2789, pruned_loss=0.04363, over 1404889.85 frames.], batch size: 22, lr: 5.21e-04
2022-04-29 07:00:56,952 INFO [train.py:763] (3/8) Epoch 14, batch 1000, loss[loss=0.1951, simple_loss=0.2934, pruned_loss=0.04837, over 7070.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2791, pruned_loss=0.04359, over 1406703.77 frames.], batch size: 28, lr: 5.21e-04
2022-04-29 07:02:02,196 INFO [train.py:763] (3/8) Epoch 14, batch 1050, loss[loss=0.1595, simple_loss=0.2551, pruned_loss=0.03198, over 7283.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2785, pruned_loss=0.0435, over 1412978.68 frames.], batch size: 18, lr: 5.20e-04
2022-04-29 07:03:07,568 INFO [train.py:763] (3/8) Epoch 14, batch 1100, loss[loss=0.1645, simple_loss=0.2493, pruned_loss=0.03992, over 7273.00 frames.], tot_loss[loss=0.1835, simple_loss=0.279, pruned_loss=0.044, over 1416977.49 frames.], batch size: 17, lr: 5.20e-04
2022-04-29 07:04:13,187 INFO [train.py:763] (3/8) Epoch 14, batch 1150, loss[loss=0.1867, simple_loss=0.2861, pruned_loss=0.04368, over 7408.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2784, pruned_loss=0.04369, over 1421482.95 frames.], batch size: 21, lr: 5.20e-04
2022-04-29 07:05:18,947 INFO [train.py:763] (3/8) Epoch 14, batch 1200, loss[loss=0.1744, simple_loss=0.2717, pruned_loss=0.0385, over 7443.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2777, pruned_loss=0.04376, over 1423118.39 frames.], batch size: 20, lr: 5.20e-04
2022-04-29 07:06:24,245 INFO [train.py:763] (3/8) Epoch 14, batch 1250, loss[loss=0.1603, simple_loss=0.249, pruned_loss=0.03573, over 7352.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2776, pruned_loss=0.04326, over 1426342.19 frames.], batch size: 19, lr: 5.20e-04
2022-04-29 07:07:29,933 INFO [train.py:763] (3/8) Epoch 14, batch 1300, loss[loss=0.1837, simple_loss=0.2848, pruned_loss=0.04136, over 6551.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2774, pruned_loss=0.04343, over 1420253.91 frames.], batch size: 38, lr: 5.19e-04
2022-04-29 07:08:35,854 INFO [train.py:763] (3/8) Epoch 14, batch 1350, loss[loss=0.1644, simple_loss=0.25, pruned_loss=0.0394, over 7005.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2779, pruned_loss=0.04371, over 1422177.91 frames.], batch size: 16, lr: 5.19e-04
2022-04-29 07:09:40,886 INFO [train.py:763] (3/8) Epoch 14, batch 1400, loss[loss=0.1866, simple_loss=0.2895, pruned_loss=0.04184, over 7275.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2777, pruned_loss=0.04362, over 1421426.91 frames.], batch size: 24, lr: 5.19e-04
2022-04-29 07:10:46,113 INFO [train.py:763] (3/8) Epoch 14, batch 1450, loss[loss=0.1922, simple_loss=0.2887, pruned_loss=0.04786, over 7374.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2779, pruned_loss=0.04378, over 1418863.23 frames.], batch size: 23, lr: 5.19e-04
2022-04-29 07:11:52,455 INFO [train.py:763] (3/8) Epoch 14, batch 1500, loss[loss=0.1756, simple_loss=0.2717, pruned_loss=0.0397, over 7147.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2783, pruned_loss=0.04402, over 1412495.10 frames.], batch size: 20, lr: 5.19e-04
2022-04-29 07:12:59,675 INFO [train.py:763] (3/8) Epoch 14, batch 1550, loss[loss=0.16, simple_loss=0.2704, pruned_loss=0.02478, over 7115.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2774, pruned_loss=0.04353, over 1417381.52 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:14:06,936 INFO [train.py:763] (3/8) Epoch 14, batch 1600, loss[loss=0.1879, simple_loss=0.2893, pruned_loss=0.04328, over 7419.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2776, pruned_loss=0.04362, over 1418884.95 frames.], batch size: 21, lr: 5.18e-04
2022-04-29 07:15:13,438 INFO [train.py:763] (3/8) Epoch 14, batch 1650, loss[loss=0.1953, simple_loss=0.2942, pruned_loss=0.04824, over 7190.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2769, pruned_loss=0.04309, over 1424188.23 frames.], batch size: 23, lr: 5.18e-04
2022-04-29 07:16:19,624 INFO [train.py:763] (3/8) Epoch 14, batch 1700, loss[loss=0.1735, simple_loss=0.2831, pruned_loss=0.03192, over 7307.00 frames.], tot_loss[loss=0.181, simple_loss=0.2763, pruned_loss=0.04283, over 1427830.60 frames.], batch size: 25, lr: 5.18e-04
2022-04-29 07:17:25,760 INFO [train.py:763] (3/8) Epoch 14, batch 1750, loss[loss=0.1896, simple_loss=0.2913, pruned_loss=0.04396, over 7035.00 frames.], tot_loss[loss=0.1805, simple_loss=0.276, pruned_loss=0.04251, over 1431018.25 frames.], batch size: 28, lr: 5.18e-04
2022-04-29 07:18:30,996 INFO [train.py:763] (3/8) Epoch 14, batch 1800, loss[loss=0.1671, simple_loss=0.2478, pruned_loss=0.04318, over 7289.00 frames.], tot_loss[loss=0.181, simple_loss=0.2764, pruned_loss=0.04278, over 1428406.69 frames.], batch size: 17, lr: 5.17e-04
2022-04-29 07:19:36,652 INFO [train.py:763] (3/8) Epoch 14, batch 1850, loss[loss=0.1778, simple_loss=0.2655, pruned_loss=0.04504, over 7159.00 frames.], tot_loss[loss=0.1803, simple_loss=0.276, pruned_loss=0.0423, over 1432668.56 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:20:42,276 INFO [train.py:763] (3/8) Epoch 14, batch 1900, loss[loss=0.1762, simple_loss=0.285, pruned_loss=0.03377, over 7104.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2759, pruned_loss=0.04187, over 1432411.72 frames.], batch size: 21, lr: 5.17e-04
2022-04-29 07:21:47,862 INFO [train.py:763] (3/8) Epoch 14, batch 1950, loss[loss=0.1779, simple_loss=0.2731, pruned_loss=0.04132, over 7290.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2752, pruned_loss=0.04174, over 1432711.21 frames.], batch size: 18, lr: 5.17e-04
2022-04-29 07:22:53,274 INFO [train.py:763] (3/8) Epoch 14, batch 2000, loss[loss=0.2308, simple_loss=0.3185, pruned_loss=0.07156, over 6512.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2757, pruned_loss=0.04222, over 1427801.20 frames.], batch size: 38, lr: 5.17e-04
2022-04-29 07:23:58,401 INFO [train.py:763] (3/8) Epoch 14, batch 2050, loss[loss=0.1662, simple_loss=0.2713, pruned_loss=0.03055, over 7276.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2763, pruned_loss=0.0425, over 1429030.03 frames.], batch size: 25, lr: 5.16e-04
2022-04-29 07:25:03,740 INFO [train.py:763] (3/8) Epoch 14, batch 2100, loss[loss=0.1794, simple_loss=0.2675, pruned_loss=0.04566, over 7438.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2761, pruned_loss=0.04261, over 1422526.73 frames.], batch size: 18, lr: 5.16e-04
2022-04-29 07:26:09,018 INFO [train.py:763] (3/8) Epoch 14, batch 2150, loss[loss=0.2197, simple_loss=0.3067, pruned_loss=0.06632, over 7202.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2758, pruned_loss=0.04236, over 1421403.99 frames.], batch size: 22, lr: 5.16e-04
2022-04-29 07:27:14,550 INFO [train.py:763] (3/8) Epoch 14, batch 2200, loss[loss=0.1801, simple_loss=0.2799, pruned_loss=0.04011, over 7427.00 frames.], tot_loss[loss=0.181, simple_loss=0.2766, pruned_loss=0.04276, over 1420463.95 frames.], batch size: 20, lr: 5.16e-04
2022-04-29 07:28:19,750 INFO [train.py:763] (3/8) Epoch 14, batch 2250, loss[loss=0.1963, simple_loss=0.2945, pruned_loss=0.04903, over 7085.00 frames.], tot_loss[loss=0.1813, simple_loss=0.277, pruned_loss=0.04281, over 1420867.72 frames.], batch size: 28, lr: 5.16e-04
2022-04-29 07:29:24,991 INFO [train.py:763] (3/8) Epoch 14, batch 2300, loss[loss=0.1604, simple_loss=0.251, pruned_loss=0.03489, over 6798.00 frames.], tot_loss[loss=0.1811, simple_loss=0.277, pruned_loss=0.04263, over 1420570.05 frames.], batch size: 15, lr: 5.15e-04
2022-04-29 07:30:30,166 INFO [train.py:763] (3/8) Epoch 14, batch 2350, loss[loss=0.1607, simple_loss=0.2469, pruned_loss=0.0372, over 7410.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2771, pruned_loss=0.04275, over 1423468.34 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:31:35,492 INFO [train.py:763] (3/8) Epoch 14, batch 2400, loss[loss=0.1778, simple_loss=0.2657, pruned_loss=0.04494, over 7423.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2782, pruned_loss=0.04343, over 1421421.88 frames.], batch size: 18, lr: 5.15e-04
2022-04-29 07:32:40,929 INFO [train.py:763] (3/8) Epoch 14, batch 2450, loss[loss=0.173, simple_loss=0.2793, pruned_loss=0.03334, over 7408.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2786, pruned_loss=0.04349, over 1422739.51 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:33:46,234 INFO [train.py:763] (3/8) Epoch 14, batch 2500, loss[loss=0.1597, simple_loss=0.2586, pruned_loss=0.03043, over 7316.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2792, pruned_loss=0.04395, over 1423996.58 frames.], batch size: 21, lr: 5.15e-04
2022-04-29 07:34:51,431 INFO [train.py:763] (3/8) Epoch 14, batch 2550, loss[loss=0.2099, simple_loss=0.2908, pruned_loss=0.06455, over 7169.00 frames.], tot_loss[loss=0.184, simple_loss=0.2793, pruned_loss=0.04431, over 1426651.63 frames.], batch size: 18, lr: 5.14e-04
2022-04-29 07:35:56,546 INFO [train.py:763] (3/8) Epoch 14, batch 2600, loss[loss=0.1903, simple_loss=0.2865, pruned_loss=0.04705, over 7192.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2799, pruned_loss=0.04457, over 1420731.58 frames.], batch size: 23, lr: 5.14e-04
2022-04-29 07:37:01,619 INFO [train.py:763] (3/8) Epoch 14, batch 2650, loss[loss=0.2024, simple_loss=0.2989, pruned_loss=0.05301, over 7283.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2796, pruned_loss=0.04437, over 1421290.55 frames.], batch size: 25, lr: 5.14e-04
2022-04-29 07:38:06,935 INFO [train.py:763] (3/8) Epoch 14, batch 2700, loss[loss=0.1718, simple_loss=0.2823, pruned_loss=0.03069, over 7324.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2796, pruned_loss=0.04377, over 1423980.75 frames.], batch size: 21, lr: 5.14e-04
2022-04-29 07:39:12,133 INFO [train.py:763] (3/8) Epoch 14, batch 2750, loss[loss=0.2067, simple_loss=0.3116, pruned_loss=0.05085, over 7261.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2797, pruned_loss=0.04371, over 1424839.55 frames.], batch size: 24, lr: 5.14e-04
2022-04-29 07:40:17,443 INFO [train.py:763] (3/8) Epoch 14, batch 2800, loss[loss=0.188, simple_loss=0.287, pruned_loss=0.04448, over 7155.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2786, pruned_loss=0.04324, over 1428382.70 frames.], batch size: 20, lr: 5.14e-04
2022-04-29 07:41:22,759 INFO [train.py:763] (3/8) Epoch 14, batch 2850, loss[loss=0.1972, simple_loss=0.2725, pruned_loss=0.06099, over 6830.00 frames.], tot_loss[loss=0.1828, simple_loss=0.2787, pruned_loss=0.04341, over 1427997.21 frames.], batch size: 15, lr: 5.13e-04
2022-04-29 07:42:28,525 INFO [train.py:763] (3/8) Epoch 14, batch 2900, loss[loss=0.1773, simple_loss=0.2802, pruned_loss=0.03722, over 7388.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2784, pruned_loss=0.0433, over 1422676.19 frames.], batch size: 23, lr: 5.13e-04
2022-04-29 07:43:34,054 INFO [train.py:763] (3/8) Epoch 14, batch 2950, loss[loss=0.1903, simple_loss=0.281, pruned_loss=0.04979, over 7426.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2783, pruned_loss=0.04346, over 1424070.87 frames.], batch size: 20, lr: 5.13e-04
2022-04-29 07:44:39,584 INFO [train.py:763] (3/8) Epoch 14, batch 3000, loss[loss=0.1915, simple_loss=0.2786, pruned_loss=0.0522, over 7158.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2778, pruned_loss=0.04382, over 1421940.06 frames.], batch size: 19, lr: 5.13e-04
2022-04-29 07:44:39,585 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 07:44:54,980 INFO [train.py:792] (3/8) Epoch 14, validation: loss=0.1687, simple_loss=0.2708, pruned_loss=0.03331, over 698248.00 frames.
2022-04-29 07:46:00,330 INFO [train.py:763] (3/8) Epoch 14, batch 3050, loss[loss=0.1956, simple_loss=0.2762, pruned_loss=0.05752, over 7218.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2779, pruned_loss=0.04355, over 1424986.43 frames.], batch size: 16, lr: 5.13e-04
2022-04-29 07:47:05,874 INFO [train.py:763] (3/8) Epoch 14, batch 3100, loss[loss=0.1813, simple_loss=0.2774, pruned_loss=0.04256, over 7334.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2787, pruned_loss=0.0438, over 1422001.41 frames.], batch size: 20, lr: 5.12e-04
2022-04-29 07:48:12,216 INFO [train.py:763] (3/8) Epoch 14, batch 3150, loss[loss=0.1867, simple_loss=0.2728, pruned_loss=0.0503, over 7276.00 frames.], tot_loss[loss=0.1827, simple_loss=0.278, pruned_loss=0.04364, over 1426803.47 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:49:18,809 INFO [train.py:763] (3/8) Epoch 14, batch 3200, loss[loss=0.1652, simple_loss=0.2722, pruned_loss=0.02905, over 7090.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2772, pruned_loss=0.04333, over 1427426.94 frames.], batch size: 28, lr: 5.12e-04
2022-04-29 07:50:24,260 INFO [train.py:763] (3/8) Epoch 14, batch 3250, loss[loss=0.1689, simple_loss=0.2646, pruned_loss=0.03662, over 7440.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2775, pruned_loss=0.04349, over 1428190.21 frames.], batch size: 19, lr: 5.12e-04
2022-04-29 07:51:29,738 INFO [train.py:763] (3/8) Epoch 14, batch 3300, loss[loss=0.1926, simple_loss=0.2784, pruned_loss=0.05347, over 7281.00 frames.], tot_loss[loss=0.181, simple_loss=0.2763, pruned_loss=0.04281, over 1426835.49 frames.], batch size: 17, lr: 5.12e-04
2022-04-29 07:52:35,057 INFO [train.py:763] (3/8) Epoch 14, batch 3350, loss[loss=0.2056, simple_loss=0.3016, pruned_loss=0.05476, over 7192.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2769, pruned_loss=0.04295, over 1426317.16 frames.], batch size: 23, lr: 5.11e-04
2022-04-29 07:53:40,778 INFO [train.py:763] (3/8) Epoch 14, batch 3400, loss[loss=0.1772, simple_loss=0.2848, pruned_loss=0.03481, over 7224.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2778, pruned_loss=0.04302, over 1423203.67 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:54:45,991 INFO [train.py:763] (3/8) Epoch 14, batch 3450, loss[loss=0.2161, simple_loss=0.3156, pruned_loss=0.05826, over 7031.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2792, pruned_loss=0.04374, over 1420548.47 frames.], batch size: 28, lr: 5.11e-04
2022-04-29 07:55:51,601 INFO [train.py:763] (3/8) Epoch 14, batch 3500, loss[loss=0.205, simple_loss=0.3014, pruned_loss=0.05425, over 7174.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2782, pruned_loss=0.04322, over 1426413.85 frames.], batch size: 26, lr: 5.11e-04
2022-04-29 07:56:57,021 INFO [train.py:763] (3/8) Epoch 14, batch 3550, loss[loss=0.1796, simple_loss=0.2808, pruned_loss=0.03919, over 7227.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2783, pruned_loss=0.04341, over 1428545.76 frames.], batch size: 20, lr: 5.11e-04
2022-04-29 07:58:03,506 INFO [train.py:763] (3/8) Epoch 14, batch 3600, loss[loss=0.2025, simple_loss=0.2948, pruned_loss=0.05513, over 7323.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2783, pruned_loss=0.04375, over 1425337.55 frames.], batch size: 21, lr: 5.11e-04
2022-04-29 07:59:08,916 INFO [train.py:763] (3/8) Epoch 14, batch 3650, loss[loss=0.166, simple_loss=0.2656, pruned_loss=0.03317, over 7268.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2772, pruned_loss=0.04304, over 1425628.47 frames.], batch size: 19, lr: 5.10e-04
2022-04-29 08:00:14,235 INFO [train.py:763] (3/8) Epoch 14, batch 3700, loss[loss=0.1811, simple_loss=0.2664, pruned_loss=0.04794, over 7423.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2778, pruned_loss=0.04341, over 1422712.44 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:01:19,992 INFO [train.py:763] (3/8) Epoch 14, batch 3750, loss[loss=0.2026, simple_loss=0.3012, pruned_loss=0.05207, over 5320.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2772, pruned_loss=0.04282, over 1424039.82 frames.], batch size: 52, lr: 5.10e-04
2022-04-29 08:02:27,023 INFO [train.py:763] (3/8) Epoch 14, batch 3800, loss[loss=0.1973, simple_loss=0.2791, pruned_loss=0.05777, over 7062.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2775, pruned_loss=0.04235, over 1426210.60 frames.], batch size: 18, lr: 5.10e-04
2022-04-29 08:03:33,820 INFO [train.py:763] (3/8) Epoch 14, batch 3850, loss[loss=0.1933, simple_loss=0.2857, pruned_loss=0.05049, over 7234.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2781, pruned_loss=0.04278, over 1428853.99 frames.], batch size: 20, lr: 5.10e-04
2022-04-29 08:04:40,265 INFO [train.py:763] (3/8) Epoch 14, batch 3900, loss[loss=0.1687, simple_loss=0.2673, pruned_loss=0.03509, over 7259.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2768, pruned_loss=0.04237, over 1426465.14 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:05:46,497 INFO [train.py:763] (3/8) Epoch 14, batch 3950, loss[loss=0.1777, simple_loss=0.2752, pruned_loss=0.0401, over 7373.00 frames.], tot_loss[loss=0.18, simple_loss=0.2763, pruned_loss=0.0418, over 1423439.83 frames.], batch size: 19, lr: 5.09e-04
2022-04-29 08:06:52,811 INFO [train.py:763] (3/8) Epoch 14, batch 4000, loss[loss=0.1739, simple_loss=0.2688, pruned_loss=0.03953, over 7208.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2759, pruned_loss=0.04175, over 1423034.09 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:07:57,992 INFO [train.py:763] (3/8) Epoch 14, batch 4050, loss[loss=0.176, simple_loss=0.276, pruned_loss=0.03799, over 7221.00 frames.], tot_loss[loss=0.18, simple_loss=0.2763, pruned_loss=0.04186, over 1427236.13 frames.], batch size: 21, lr: 5.09e-04
2022-04-29 08:09:03,251 INFO [train.py:763] (3/8) Epoch 14, batch 4100, loss[loss=0.1802, simple_loss=0.2874, pruned_loss=0.03651, over 7203.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2768, pruned_loss=0.04235, over 1418167.15 frames.], batch size: 23, lr: 5.09e-04
2022-04-29 08:10:08,498 INFO [train.py:763] (3/8) Epoch 14, batch 4150, loss[loss=0.2172, simple_loss=0.3036, pruned_loss=0.06538, over 5030.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2767, pruned_loss=0.04273, over 1412506.79 frames.], batch size: 52, lr: 5.08e-04
2022-04-29 08:11:13,732 INFO [train.py:763] (3/8) Epoch 14, batch 4200, loss[loss=0.1923, simple_loss=0.2922, pruned_loss=0.0462, over 7231.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2761, pruned_loss=0.04234, over 1411014.77 frames.], batch size: 20, lr: 5.08e-04
2022-04-29 08:12:19,794 INFO [train.py:763] (3/8) Epoch 14, batch 4250, loss[loss=0.1543, simple_loss=0.2503, pruned_loss=0.02917, over 7060.00 frames.], tot_loss[loss=0.18, simple_loss=0.2758, pruned_loss=0.04207, over 1408460.76 frames.], batch size: 18, lr: 5.08e-04
2022-04-29 08:13:25,927 INFO [train.py:763] (3/8) Epoch 14, batch 4300, loss[loss=0.142, simple_loss=0.2343, pruned_loss=0.02482, over 6807.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2765, pruned_loss=0.04247, over 1405161.97 frames.], batch size: 15, lr: 5.08e-04
2022-04-29 08:14:30,946 INFO [train.py:763] (3/8) Epoch 14, batch 4350, loss[loss=0.1919, simple_loss=0.2916, pruned_loss=0.0461, over 7320.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2765, pruned_loss=0.04232, over 1408606.39 frames.], batch size: 21, lr: 5.08e-04
2022-04-29 08:15:37,007 INFO [train.py:763] (3/8) Epoch 14, batch 4400, loss[loss=0.155, simple_loss=0.2464, pruned_loss=0.03185, over 7163.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2759, pruned_loss=0.04197, over 1410962.36 frames.], batch size: 19, lr: 5.08e-04
2022-04-29 08:16:42,686 INFO [train.py:763] (3/8) Epoch 14, batch 4450, loss[loss=0.161, simple_loss=0.2579, pruned_loss=0.03202, over 7168.00 frames.], tot_loss[loss=0.179, simple_loss=0.2743, pruned_loss=0.04185, over 1403355.85 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:17:47,611 INFO [train.py:763] (3/8) Epoch 14, batch 4500, loss[loss=0.1864, simple_loss=0.2701, pruned_loss=0.05132, over 7061.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2755, pruned_loss=0.04246, over 1395204.41 frames.], batch size: 18, lr: 5.07e-04
2022-04-29 08:18:51,943 INFO [train.py:763] (3/8) Epoch 14, batch 4550, loss[loss=0.2246, simple_loss=0.3104, pruned_loss=0.06936, over 4729.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2768, pruned_loss=0.04333, over 1367583.40 frames.], batch size: 53, lr: 5.07e-04
2022-04-29 08:20:20,835 INFO [train.py:763] (3/8) Epoch 15, batch 0, loss[loss=0.1723, simple_loss=0.2768, pruned_loss=0.03385, over 7286.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2768, pruned_loss=0.03385, over 7286.00 frames.], batch size: 24, lr: 4.92e-04
2022-04-29 08:21:27,545 INFO [train.py:763] (3/8) Epoch 15, batch 50, loss[loss=0.1505, simple_loss=0.2401, pruned_loss=0.0305, over 7411.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2764, pruned_loss=0.04157, over 320950.99 frames.], batch size: 18, lr: 4.92e-04
2022-04-29 08:22:33,675 INFO [train.py:763] (3/8) Epoch 15, batch 100, loss[loss=0.1857, simple_loss=0.291, pruned_loss=0.04019, over 7331.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2755, pruned_loss=0.04137, over 564900.20 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:23:40,361 INFO [train.py:763] (3/8) Epoch 15, batch 150, loss[loss=0.17, simple_loss=0.2775, pruned_loss=0.03124, over 7154.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2746, pruned_loss=0.04053, over 754730.49 frames.], batch size: 20, lr: 4.92e-04
2022-04-29 08:24:46,767 INFO [train.py:763] (3/8) Epoch 15, batch 200, loss[loss=0.1909, simple_loss=0.2908, pruned_loss=0.04547, over 7107.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2743, pruned_loss=0.04061, over 898003.38 frames.], batch size: 21, lr: 4.91e-04
2022-04-29 08:25:52,225 INFO [train.py:763] (3/8) Epoch 15, batch 250, loss[loss=0.1435, simple_loss=0.2388, pruned_loss=0.02406, over 7157.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2747, pruned_loss=0.04107, over 1015154.59 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:26:57,837 INFO [train.py:763] (3/8) Epoch 15, batch 300, loss[loss=0.16, simple_loss=0.2661, pruned_loss=0.02694, over 7143.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2745, pruned_loss=0.04115, over 1109476.30 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:28:03,216 INFO [train.py:763] (3/8) Epoch 15, batch 350, loss[loss=0.162, simple_loss=0.2541, pruned_loss=0.03501, over 7272.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2745, pruned_loss=0.04088, over 1180576.11 frames.], batch size: 18, lr: 4.91e-04
2022-04-29 08:29:08,689 INFO [train.py:763] (3/8) Epoch 15, batch 400, loss[loss=0.1749, simple_loss=0.2759, pruned_loss=0.03699, over 7265.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2753, pruned_loss=0.04052, over 1233680.10 frames.], batch size: 19, lr: 4.91e-04
2022-04-29 08:30:14,239 INFO [train.py:763] (3/8) Epoch 15, batch 450, loss[loss=0.159, simple_loss=0.2469, pruned_loss=0.03551, over 7430.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2756, pruned_loss=0.04071, over 1280592.40 frames.], batch size: 20, lr: 4.91e-04
2022-04-29 08:31:19,781 INFO [train.py:763] (3/8) Epoch 15, batch 500, loss[loss=0.1885, simple_loss=0.2906, pruned_loss=0.04313, over 7199.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2765, pruned_loss=0.04098, over 1317530.43 frames.], batch size: 23, lr: 4.90e-04
2022-04-29 08:32:25,945 INFO [train.py:763] (3/8) Epoch 15, batch 550, loss[loss=0.1481, simple_loss=0.2359, pruned_loss=0.03012, over 7284.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2748, pruned_loss=0.04084, over 1344623.99 frames.], batch size: 18, lr: 4.90e-04
2022-04-29 08:33:31,108 INFO [train.py:763] (3/8) Epoch 15, batch 600, loss[loss=0.1717, simple_loss=0.273, pruned_loss=0.03526, over 7167.00 frames.], tot_loss[loss=0.1789, simple_loss=0.275, pruned_loss=0.04136, over 1360517.33 frames.], batch size: 19, lr: 4.90e-04
2022-04-29 08:34:36,399 INFO [train.py:763] (3/8) Epoch 15, batch 650, loss[loss=0.1833, simple_loss=0.2791, pruned_loss=0.04373, over 6418.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2754, pruned_loss=0.04114, over 1373420.77 frames.], batch size: 37, lr: 4.90e-04
2022-04-29 08:35:42,058 INFO [train.py:763] (3/8) Epoch 15, batch 700, loss[loss=0.1904, simple_loss=0.2951, pruned_loss=0.04281, over 7042.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2747, pruned_loss=0.0409, over 1385108.54 frames.], batch size: 28, lr: 4.90e-04
2022-04-29 08:36:47,192 INFO [train.py:763] (3/8) Epoch 15, batch 750, loss[loss=0.1607, simple_loss=0.2534, pruned_loss=0.03398, over 7146.00 frames.], tot_loss[loss=0.178, simple_loss=0.2744, pruned_loss=0.0408, over 1393695.98 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:37:53,215 INFO [train.py:763] (3/8) Epoch 15, batch 800, loss[loss=0.1841, simple_loss=0.2718, pruned_loss=0.04817, over 7256.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2754, pruned_loss=0.04136, over 1401761.88 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:39:00,103 INFO [train.py:763] (3/8) Epoch 15, batch 850, loss[loss=0.1691, simple_loss=0.2654, pruned_loss=0.03635, over 7151.00 frames.], tot_loss[loss=0.1796, simple_loss=0.276, pruned_loss=0.0416, over 1403849.69 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:40:05,802 INFO [train.py:763] (3/8) Epoch 15, batch 900, loss[loss=0.1706, simple_loss=0.2647, pruned_loss=0.03826, over 7339.00 frames.], tot_loss[loss=0.18, simple_loss=0.2763, pruned_loss=0.04185, over 1402965.34 frames.], batch size: 19, lr: 4.89e-04
2022-04-29 08:41:11,038 INFO [train.py:763] (3/8) Epoch 15, batch 950, loss[loss=0.1639, simple_loss=0.2636, pruned_loss=0.03217, over 7423.00 frames.], tot_loss[loss=0.18, simple_loss=0.276, pruned_loss=0.04198, over 1406983.03 frames.], batch size: 20, lr: 4.89e-04
2022-04-29 08:42:16,442 INFO [train.py:763] (3/8) Epoch 15, batch 1000, loss[loss=0.2081, simple_loss=0.2986, pruned_loss=0.05877, over 7285.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2754, pruned_loss=0.04188, over 1412796.45 frames.], batch size: 25, lr: 4.89e-04
2022-04-29 08:43:21,669 INFO [train.py:763] (3/8) Epoch 15, batch 1050, loss[loss=0.1781, simple_loss=0.2841, pruned_loss=0.03607, over 7319.00 frames.], tot_loss[loss=0.18, simple_loss=0.2762, pruned_loss=0.0419, over 1417866.11 frames.], batch size: 20, lr: 4.88e-04
2022-04-29 08:44:28,812 INFO [train.py:763] (3/8) Epoch 15, batch 1100, loss[loss=0.1775, simple_loss=0.2742, pruned_loss=0.04036, over 7351.00 frames.], tot_loss[loss=0.18, simple_loss=0.2763, pruned_loss=0.04183, over 1420091.09 frames.], batch size: 19, lr: 4.88e-04
2022-04-29 08:45:35,099 INFO [train.py:763] (3/8) Epoch 15, batch 1150, loss[loss=0.2383, simple_loss=0.3108, pruned_loss=0.0829, over 5306.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2758, pruned_loss=0.0416, over 1420325.18 frames.], batch size: 52, lr: 4.88e-04
2022-04-29 08:46:40,372 INFO [train.py:763] (3/8) Epoch 15, batch 1200, loss[loss=0.1718, simple_loss=0.2731, pruned_loss=0.03524, over 7120.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2757, pruned_loss=0.04151, over 1417385.39 frames.], batch size: 21, lr: 4.88e-04
2022-04-29 08:47:45,859 INFO [train.py:763] (3/8) Epoch 15, batch 1250, loss[loss=0.1689, simple_loss=0.2533, pruned_loss=0.04227, over 6811.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2753, pruned_loss=0.04147, over 1418309.09 frames.], batch size: 15, lr: 4.88e-04
2022-04-29 08:48:51,149 INFO [train.py:763] (3/8) Epoch 15, batch 1300, loss[loss=0.1766, simple_loss=0.2848, pruned_loss=0.03421, over 7211.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2765, pruned_loss=0.04197, over 1424766.56 frames.], batch size: 22, lr: 4.88e-04
2022-04-29 08:49:56,770 INFO [train.py:763] (3/8) Epoch 15, batch 1350, loss[loss=0.1729, simple_loss=0.2644, pruned_loss=0.04067, over 7163.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2764, pruned_loss=0.04244, over 1417624.64 frames.], batch size: 19, lr: 4.87e-04
2022-04-29 08:51:13,199 INFO [train.py:763] (3/8) Epoch 15, batch 1400, loss[loss=0.1896, simple_loss=0.3006, pruned_loss=0.03935, over 7338.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2759, pruned_loss=0.04225, over 1415649.16 frames.], batch size: 22, lr: 4.87e-04
2022-04-29 08:52:20,208 INFO [train.py:763] (3/8) Epoch 15, batch 1450, loss[loss=0.2196, simple_loss=0.3147, pruned_loss=0.06221, over 7419.00 frames.], tot_loss[loss=0.1799, simple_loss=0.276, pruned_loss=0.04187, over 1422211.04 frames.], batch size: 21, lr: 4.87e-04
2022-04-29 08:53:25,684 INFO [train.py:763] (3/8) Epoch 15, batch 1500, loss[loss=0.1824, simple_loss=0.2871, pruned_loss=0.0389, over 7208.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2768, pruned_loss=0.04229, over 1421842.29 frames.], batch size: 23, lr: 4.87e-04
2022-04-29 08:54:40,090 INFO [train.py:763] (3/8) Epoch 15, batch 1550, loss[loss=0.144, simple_loss=0.2346, pruned_loss=0.02669, over 6760.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2758, pruned_loss=0.04167, over 1419813.51 frames.], batch size: 15, lr: 4.87e-04
2022-04-29 08:56:03,999 INFO [train.py:763] (3/8) Epoch 15, batch 1600, loss[loss=0.1702, simple_loss=0.2653, pruned_loss=0.03756, over 6833.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2763, pruned_loss=0.04173, over 1421959.49 frames.], batch size: 15, lr: 4.87e-04
2022-04-29 08:57:19,954 INFO [train.py:763] (3/8) Epoch 15, batch 1650, loss[loss=0.2065, simple_loss=0.2975, pruned_loss=0.0578, over 7148.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04169, over 1424195.50 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 08:58:25,680 INFO [train.py:763] (3/8) Epoch 15, batch 1700, loss[loss=0.171, simple_loss=0.2549, pruned_loss=0.04353, over 7394.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2756, pruned_loss=0.04141, over 1424451.42 frames.], batch size: 18, lr: 4.86e-04
2022-04-29 08:59:40,115 INFO [train.py:763] (3/8) Epoch 15, batch 1750, loss[loss=0.1965, simple_loss=0.2879, pruned_loss=0.05255, over 7376.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04166, over 1424067.99 frames.], batch size: 23, lr: 4.86e-04
2022-04-29 09:00:47,094 INFO [train.py:763] (3/8) Epoch 15, batch 1800, loss[loss=0.1842, simple_loss=0.2833, pruned_loss=0.04251, over 7368.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2768, pruned_loss=0.04214, over 1421965.58 frames.], batch size: 19, lr: 4.86e-04
2022-04-29 09:02:11,303 INFO [train.py:763] (3/8) Epoch 15, batch 1850, loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03499, over 7145.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2756, pruned_loss=0.04191, over 1424632.74 frames.], batch size: 20, lr: 4.86e-04
2022-04-29 09:03:16,747 INFO [train.py:763] (3/8) Epoch 15, batch 1900, loss[loss=0.1947, simple_loss=0.2907, pruned_loss=0.04934, over 7301.00 frames.], tot_loss[loss=0.1804, simple_loss=0.276, pruned_loss=0.04241, over 1428408.51 frames.], batch size: 25, lr: 4.86e-04
2022-04-29 09:04:23,830 INFO [train.py:763] (3/8) Epoch 15, batch 1950, loss[loss=0.2064, simple_loss=0.3176, pruned_loss=0.04761, over 7204.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2768, pruned_loss=0.04265, over 1429955.03 frames.], batch size: 23, lr: 4.85e-04
2022-04-29 09:05:29,695 INFO [train.py:763] (3/8) Epoch 15, batch 2000, loss[loss=0.2113, simple_loss=0.3104, pruned_loss=0.05605, over 4843.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2772, pruned_loss=0.0427, over 1423731.91 frames.], batch size: 52, lr: 4.85e-04
2022-04-29 09:06:36,278 INFO [train.py:763] (3/8) Epoch 15, batch 2050, loss[loss=0.1735, simple_loss=0.2623, pruned_loss=0.04235, over 6462.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2779, pruned_loss=0.04273, over 1421846.09 frames.], batch size: 38, lr: 4.85e-04
2022-04-29 09:07:41,964 INFO [train.py:763] (3/8) Epoch 15, batch 2100, loss[loss=0.1879, simple_loss=0.2833, pruned_loss=0.0463, over 7115.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2773, pruned_loss=0.04226, over 1422888.23 frames.], batch size: 21, lr: 4.85e-04
2022-04-29 09:08:48,743 INFO [train.py:763] (3/8) Epoch 15, batch 2150, loss[loss=0.1788, simple_loss=0.2852, pruned_loss=0.03613, over 7256.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2771, pruned_loss=0.04199, over 1418883.83 frames.], batch size: 19, lr: 4.85e-04
2022-04-29 09:09:53,838 INFO [train.py:763] (3/8) Epoch 15, batch 2200, loss[loss=0.2025, simple_loss=0.3071, pruned_loss=0.04889, over 7226.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2772, pruned_loss=0.04201, over 1415938.89 frames.], batch size: 22, lr: 4.84e-04
2022-04-29 09:10:59,455 INFO [train.py:763] (3/8) Epoch 15, batch 2250, loss[loss=0.2125, simple_loss=0.3152, pruned_loss=0.0549, over 7405.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2771, pruned_loss=0.0422, over 1418284.32 frames.], batch size: 21, lr: 4.84e-04
2022-04-29 09:12:05,740 INFO [train.py:763] (3/8) Epoch 15, batch 2300, loss[loss=0.1866, simple_loss=0.2842, pruned_loss=0.04447, over 7223.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2773, pruned_loss=0.04225, over 1420104.97 frames.], batch size: 23, lr: 4.84e-04
2022-04-29 09:13:13,274 INFO [train.py:763] (3/8) Epoch 15, batch 2350, loss[loss=0.1985, simple_loss=0.3068, pruned_loss=0.04509, over 7299.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2764, pruned_loss=0.04203, over 1422514.65 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:14:19,339 INFO [train.py:763] (3/8) Epoch 15, batch 2400, loss[loss=0.1895, simple_loss=0.2932, pruned_loss=0.04284, over 7259.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2758, pruned_loss=0.04167, over 1425897.40 frames.], batch size: 25, lr: 4.84e-04
2022-04-29 09:15:24,433 INFO [train.py:763] (3/8) Epoch 15, batch 2450, loss[loss=0.2042, simple_loss=0.3021, pruned_loss=0.05315, over 6755.00 frames.], tot_loss[loss=0.1802, simple_loss=0.276, pruned_loss=0.04219, over 1424660.03 frames.], batch size: 31, lr: 4.84e-04
2022-04-29 09:16:31,163 INFO [train.py:763] (3/8) Epoch 15, batch 2500, loss[loss=0.1805, simple_loss=0.2702, pruned_loss=0.04536, over 7219.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2756, pruned_loss=0.04228, over 1428062.01 frames.], batch size: 21, lr: 4.83e-04
2022-04-29 09:17:37,363 INFO [train.py:763] (3/8) Epoch 15, batch 2550, loss[loss=0.1651, simple_loss=0.2543, pruned_loss=0.03793, over 7144.00 frames.], tot_loss[loss=0.179, simple_loss=0.2744, pruned_loss=0.04184, over 1424893.43 frames.], batch size: 20, lr: 4.83e-04
2022-04-29 09:18:44,500 INFO [train.py:763] (3/8) Epoch 15, batch 2600, loss[loss=0.1559, simple_loss=0.2569, pruned_loss=0.02741, over 7360.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2751, pruned_loss=0.0421, over 1423516.32 frames.], batch size: 19, lr: 4.83e-04
2022-04-29 09:19:51,208 INFO [train.py:763] (3/8) Epoch 15, batch 2650, loss[loss=0.1919, simple_loss=0.2892, pruned_loss=0.04732, over 7375.00 frames.], tot_loss[loss=0.179, simple_loss=0.2747, pruned_loss=0.04162, over 1424356.27 frames.], batch size: 23, lr: 4.83e-04
2022-04-29 09:20:56,492 INFO [train.py:763] (3/8) Epoch 15, batch 2700, loss[loss=0.1757, simple_loss=0.2808, pruned_loss=0.03527, over 7188.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2755, pruned_loss=0.04184, over 1421460.54 frames.], batch size: 26, lr: 4.83e-04
2022-04-29 09:22:02,816 INFO [train.py:763] (3/8) Epoch 15, batch 2750, loss[loss=0.1904, simple_loss=0.2748, pruned_loss=0.05304, over 7276.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2756, pruned_loss=0.04147, over 1425705.41 frames.], batch size: 18, lr: 4.83e-04
2022-04-29 09:23:10,086 INFO [train.py:763] (3/8) Epoch 15, batch 2800, loss[loss=0.1801, simple_loss=0.2876, pruned_loss=0.03629, over 7231.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2759, pruned_loss=0.04122, over 1427582.38 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:24:17,264 INFO [train.py:763] (3/8) Epoch 15, batch 2850, loss[loss=0.1747, simple_loss=0.2646, pruned_loss=0.04242, over 7154.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04172, over 1426517.57 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:25:24,199 INFO [train.py:763] (3/8) Epoch 15, batch 2900, loss[loss=0.1508, simple_loss=0.2607, pruned_loss=0.02045, over 7158.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2755, pruned_loss=0.04096, over 1428856.45 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:26:29,781 INFO [train.py:763] (3/8) Epoch 15, batch 2950, loss[loss=0.1755, simple_loss=0.2796, pruned_loss=0.03565, over 7330.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2759, pruned_loss=0.04146, over 1424888.30 frames.], batch size: 22, lr: 4.82e-04
2022-04-29 09:27:35,043 INFO [train.py:763] (3/8) Epoch 15, batch 3000, loss[loss=0.1787, simple_loss=0.2858, pruned_loss=0.03582, over 7416.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2759, pruned_loss=0.04134, over 1428825.50 frames.], batch size: 21, lr: 4.82e-04
2022-04-29 09:27:35,044 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 09:27:50,494 INFO [train.py:792] (3/8) Epoch 15, validation: loss=0.1668, simple_loss=0.2684, pruned_loss=0.03254, over 698248.00 frames.
2022-04-29 09:28:57,620 INFO [train.py:763] (3/8) Epoch 15, batch 3050, loss[loss=0.1588, simple_loss=0.2472, pruned_loss=0.0352, over 7399.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2757, pruned_loss=0.04158, over 1427590.08 frames.], batch size: 18, lr: 4.82e-04
2022-04-29 09:30:04,539 INFO [train.py:763] (3/8) Epoch 15, batch 3100, loss[loss=0.1982, simple_loss=0.2878, pruned_loss=0.05426, over 7198.00 frames.], tot_loss[loss=0.1791, simple_loss=0.275, pruned_loss=0.04163, over 1426980.90 frames.], batch size: 23, lr: 4.81e-04
2022-04-29 09:31:11,565 INFO [train.py:763] (3/8) Epoch 15, batch 3150, loss[loss=0.1678, simple_loss=0.2572, pruned_loss=0.03923, over 7165.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2749, pruned_loss=0.0417, over 1423986.72 frames.], batch size: 18, lr: 4.81e-04
2022-04-29 09:32:29,190 INFO [train.py:763] (3/8) Epoch 15, batch 3200, loss[loss=0.1765, simple_loss=0.2832, pruned_loss=0.03495, over 7282.00 frames.], tot_loss[loss=0.181, simple_loss=0.2769, pruned_loss=0.04252, over 1423831.31 frames.], batch size: 24, lr: 4.81e-04
2022-04-29 09:33:36,693 INFO [train.py:763] (3/8) Epoch 15, batch 3250, loss[loss=0.2203, simple_loss=0.3095, pruned_loss=0.06552, over 7329.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2761, pruned_loss=0.04243, over 1425334.08 frames.], batch size: 21, lr: 4.81e-04
2022-04-29 09:34:43,458 INFO [train.py:763] (3/8) Epoch 15, batch 3300, loss[loss=0.1888, simple_loss=0.2839, pruned_loss=0.04678, over 7301.00 frames.], tot_loss[loss=0.181, simple_loss=0.2772, pruned_loss=0.04244, over 1429229.53 frames.], batch size: 25, lr: 4.81e-04
2022-04-29 09:35:50,325 INFO [train.py:763] (3/8) Epoch 15, batch 3350, loss[loss=0.1966, simple_loss=0.2889, pruned_loss=0.05214, over 7237.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2757, pruned_loss=0.04185, over 1430806.36 frames.], batch size: 20, lr: 4.81e-04
2022-04-29 09:36:57,530 INFO [train.py:763] (3/8) Epoch 15, batch 3400, loss[loss=0.2057, simple_loss=0.2954, pruned_loss=0.05797, over 7113.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2771, pruned_loss=0.04241, over 1428611.68 frames.], batch size: 28, lr: 4.80e-04
2022-04-29 09:38:05,023 INFO [train.py:763] (3/8) Epoch 15, batch 3450, loss[loss=0.1584, simple_loss=0.2513, pruned_loss=0.03277, over 7355.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2769, pruned_loss=0.04228, over 1429814.39 frames.], batch size: 19, lr: 4.80e-04
2022-04-29 09:39:11,457 INFO [train.py:763] (3/8) Epoch 15, batch 3500, loss[loss=0.1605, simple_loss=0.2748, pruned_loss=0.02308, over 7316.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2764, pruned_loss=0.04192, over 1427936.98 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:40:16,434 INFO [train.py:763] (3/8) Epoch 15, batch 3550, loss[loss=0.2276, simple_loss=0.3281, pruned_loss=0.06353, over 7163.00 frames.], tot_loss[loss=0.181, simple_loss=0.2772, pruned_loss=0.04237, over 1424387.52 frames.], batch size: 26, lr: 4.80e-04
2022-04-29 09:41:21,619 INFO [train.py:763] (3/8) Epoch 15, batch 3600, loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.0318, over 7313.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2759, pruned_loss=0.04157, over 1425886.02 frames.], batch size: 21, lr: 4.80e-04
2022-04-29 09:42:26,932 INFO [train.py:763] (3/8) Epoch 15, batch 3650, loss[loss=0.1751, simple_loss=0.2683, pruned_loss=0.04091, over 7276.00 frames.], tot_loss[loss=0.18, simple_loss=0.2764, pruned_loss=0.04185, over 1426053.72 frames.], batch size: 18, lr: 4.80e-04
2022-04-29 09:43:33,155 INFO [train.py:763] (3/8) Epoch 15, batch 3700, loss[loss=0.1751, simple_loss=0.2586, pruned_loss=0.0458, over 7259.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2755, pruned_loss=0.04183, over 1424136.55 frames.], batch size: 16, lr: 4.79e-04
2022-04-29 09:44:39,837 INFO [train.py:763] (3/8) Epoch 15, batch 3750, loss[loss=0.2025, simple_loss=0.304, pruned_loss=0.05046, over 7320.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2755, pruned_loss=0.04184, over 1421351.90 frames.], batch size: 25, lr: 4.79e-04
2022-04-29 09:45:46,799 INFO [train.py:763] (3/8) Epoch 15, batch 3800, loss[loss=0.1616, simple_loss=0.2523, pruned_loss=0.03551, over 7117.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2764, pruned_loss=0.04209, over 1425118.58 frames.], batch size: 17, lr: 4.79e-04
2022-04-29 09:46:53,782 INFO [train.py:763] (3/8) Epoch 15, batch 3850, loss[loss=0.1747, simple_loss=0.2627, pruned_loss=0.04338, over 7280.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2764, pruned_loss=0.04223, over 1420657.90 frames.], batch size: 18, lr: 4.79e-04
2022-04-29 09:48:00,484 INFO [train.py:763] (3/8) Epoch 15, batch 3900, loss[loss=0.1961, simple_loss=0.2854, pruned_loss=0.05339, over 7216.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2771, pruned_loss=0.04272, over 1422236.81 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:49:06,578 INFO [train.py:763] (3/8) Epoch 15, batch 3950, loss[loss=0.1632, simple_loss=0.2598, pruned_loss=0.03331, over 7237.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.04283, over 1421140.67 frames.], batch size: 20, lr: 4.79e-04
2022-04-29 09:50:13,628 INFO [train.py:763] (3/8) Epoch 15, batch 4000, loss[loss=0.1603, simple_loss=0.2662, pruned_loss=0.0272, over 7322.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2775, pruned_loss=0.04275, over 1419611.72 frames.], batch size: 21, lr: 4.79e-04
2022-04-29 09:51:19,315 INFO [train.py:763] (3/8) Epoch 15, batch 4050, loss[loss=0.1607, simple_loss=0.2573, pruned_loss=0.03206, over 7162.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2771, pruned_loss=0.04222, over 1418481.67 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:52:24,921 INFO [train.py:763] (3/8) Epoch 15, batch 4100, loss[loss=0.1507, simple_loss=0.251, pruned_loss=0.02514, over 7161.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2758, pruned_loss=0.04155, over 1424117.41 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:53:30,116 INFO [train.py:763] (3/8) Epoch 15, batch 4150, loss[loss=0.1989, simple_loss=0.2999, pruned_loss=0.04893, over 7094.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2765, pruned_loss=0.04204, over 1418564.93 frames.], batch size: 28, lr: 4.78e-04
2022-04-29 09:54:36,327 INFO [train.py:763] (3/8) Epoch 15, batch 4200, loss[loss=0.1744, simple_loss=0.2544, pruned_loss=0.04725, over 6998.00 frames.], tot_loss[loss=0.1799, simple_loss=0.276, pruned_loss=0.04195, over 1418602.16 frames.], batch size: 16, lr: 4.78e-04
2022-04-29 09:55:43,465 INFO [train.py:763] (3/8) Epoch 15, batch 4250, loss[loss=0.1417, simple_loss=0.2343, pruned_loss=0.02451, over 7168.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2746, pruned_loss=0.04144, over 1417973.45 frames.], batch size: 18, lr: 4.78e-04
2022-04-29 09:56:48,658 INFO [train.py:763] (3/8) Epoch 15, batch 4300, loss[loss=0.1896, simple_loss=0.2788, pruned_loss=0.05024, over 6752.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2745, pruned_loss=0.04168, over 1413506.28 frames.], batch size: 31, lr: 4.78e-04
2022-04-29 09:57:53,919 INFO [train.py:763] (3/8) Epoch 15, batch 4350, loss[loss=0.1642, simple_loss=0.2567, pruned_loss=0.0359, over 7165.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2749, pruned_loss=0.04136, over 1416199.90 frames.], batch size: 18, lr: 4.77e-04
2022-04-29 09:59:00,569 INFO [train.py:763] (3/8) Epoch 15, batch 4400, loss[loss=0.1888, simple_loss=0.3073, pruned_loss=0.03513, over 7111.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2748, pruned_loss=0.04099, over 1415679.64 frames.], batch size: 21, lr: 4.77e-04
2022-04-29 10:00:06,758 INFO [train.py:763] (3/8) Epoch 15, batch 4450, loss[loss=0.1955, simple_loss=0.2906, pruned_loss=0.05017, over 7198.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2752, pruned_loss=0.04122, over 1410791.35 frames.], batch size: 22, lr: 4.77e-04
2022-04-29 10:01:11,551 INFO [train.py:763] (3/8) Epoch 15, batch 4500, loss[loss=0.1713, simple_loss=0.272, pruned_loss=0.0353, over 7121.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2745, pruned_loss=0.04087, over 1401362.05 frames.], batch size: 17, lr: 4.77e-04
2022-04-29 10:02:15,682 INFO [train.py:763] (3/8) Epoch 15, batch 4550, loss[loss=0.207, simple_loss=0.2982, pruned_loss=0.05784, over 4996.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2773, pruned_loss=0.04281, over 1350665.94 frames.], batch size: 52, lr: 4.77e-04
2022-04-29 10:03:53,497 INFO [train.py:763] (3/8) Epoch 16, batch 0, loss[loss=0.2069, simple_loss=0.3079, pruned_loss=0.05294, over 7102.00 frames.], tot_loss[loss=0.2069, simple_loss=0.3079, pruned_loss=0.05294, over 7102.00 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:04:59,093 INFO [train.py:763] (3/8) Epoch 16, batch 50, loss[loss=0.1813, simple_loss=0.2902, pruned_loss=0.03625, over 7313.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2817, pruned_loss=0.04388, over 316507.97 frames.], batch size: 21, lr: 4.63e-04
2022-04-29 10:06:04,342 INFO [train.py:763] (3/8) Epoch 16, batch 100, loss[loss=0.1717, simple_loss=0.2703, pruned_loss=0.0366, over 7146.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2776, pruned_loss=0.04146, over 559010.00 frames.], batch size: 20, lr: 4.63e-04
2022-04-29 10:07:09,682 INFO [train.py:763] (3/8) Epoch 16, batch 150, loss[loss=0.1519, simple_loss=0.2309, pruned_loss=0.03647, over 6978.00 frames.], tot_loss[loss=0.1784, simple_loss=0.275, pruned_loss=0.04088, over 747502.64 frames.], batch size: 16, lr: 4.63e-04
2022-04-29 10:08:15,062 INFO [train.py:763] (3/8) Epoch 16, batch 200, loss[loss=0.1465, simple_loss=0.2468, pruned_loss=0.02312, over 7138.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2767, pruned_loss=0.04124, over 896596.68 frames.], batch size: 17, lr: 4.63e-04
2022-04-29 10:09:20,554 INFO [train.py:763] (3/8) Epoch 16, batch 250, loss[loss=0.1486, simple_loss=0.2394, pruned_loss=0.02894, over 7261.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2763, pruned_loss=0.04063, over 1016265.38 frames.], batch size: 19, lr: 4.63e-04
2022-04-29 10:10:25,847 INFO [train.py:763] (3/8) Epoch 16, batch 300, loss[loss=0.1625, simple_loss=0.2544, pruned_loss=0.03525, over 7066.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2766, pruned_loss=0.04028, over 1102434.02 frames.], batch size: 18, lr: 4.62e-04
2022-04-29 10:11:32,020 INFO [train.py:763] (3/8) Epoch 16, batch 350, loss[loss=0.1792, simple_loss=0.2668, pruned_loss=0.0458, over 7216.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2746, pruned_loss=0.03962, over 1172353.01 frames.], batch size: 16, lr: 4.62e-04
2022-04-29 10:12:37,990 INFO [train.py:763] (3/8) Epoch 16, batch 400, loss[loss=0.2324, simple_loss=0.3111, pruned_loss=0.07681, over 5340.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2764, pruned_loss=0.04017, over 1228819.74 frames.], batch size: 52, lr: 4.62e-04
2022-04-29 10:13:43,445 INFO [train.py:763] (3/8) Epoch 16, batch 450, loss[loss=0.1677, simple_loss=0.26, pruned_loss=0.03768, over 7353.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2752, pruned_loss=0.03995, over 1268591.94 frames.], batch size: 19, lr: 4.62e-04
2022-04-29 10:14:49,054 INFO [train.py:763] (3/8) Epoch 16, batch 500, loss[loss=0.1375, simple_loss=0.2336, pruned_loss=0.02067, over 7177.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2747, pruned_loss=0.03989, over 1302134.45 frames.], batch size: 18, lr: 4.62e-04
2022-04-29 10:15:54,720 INFO [train.py:763] (3/8) Epoch 16, batch 550, loss[loss=0.1524, simple_loss=0.239, pruned_loss=0.03291, over 7122.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2739, pruned_loss=0.03994, over 1328225.54 frames.], batch size: 17, lr: 4.62e-04
2022-04-29 10:17:00,204 INFO [train.py:763] (3/8) Epoch 16, batch 600, loss[loss=0.2003, simple_loss=0.3004, pruned_loss=0.05009, over 7004.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2741, pruned_loss=0.04026, over 1342969.95 frames.], batch size: 28, lr: 4.62e-04
2022-04-29 10:18:05,531 INFO [train.py:763] (3/8) Epoch 16, batch 650, loss[loss=0.1777, simple_loss=0.2808, pruned_loss=0.03728, over 7337.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2752, pruned_loss=0.04065, over 1360847.81 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:19:10,729 INFO [train.py:763] (3/8) Epoch 16, batch 700, loss[loss=0.1857, simple_loss=0.2763, pruned_loss=0.0475, over 7261.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2764, pruned_loss=0.04139, over 1367871.74 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:20:16,739 INFO [train.py:763] (3/8) Epoch 16, batch 750, loss[loss=0.1984, simple_loss=0.294, pruned_loss=0.05142, over 7146.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2765, pruned_loss=0.0411, over 1376184.57 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:21:21,857 INFO [train.py:763] (3/8) Epoch 16, batch 800, loss[loss=0.1799, simple_loss=0.2752, pruned_loss=0.04232, over 7161.00 frames.], tot_loss[loss=0.1792, simple_loss=0.276, pruned_loss=0.04116, over 1388309.35 frames.], batch size: 19, lr: 4.61e-04
2022-04-29 10:22:27,307 INFO [train.py:763] (3/8) Epoch 16, batch 850, loss[loss=0.1992, simple_loss=0.2947, pruned_loss=0.05183, over 6260.00 frames.], tot_loss[loss=0.1789, simple_loss=0.275, pruned_loss=0.04141, over 1396694.67 frames.], batch size: 37, lr: 4.61e-04
2022-04-29 10:23:32,964 INFO [train.py:763] (3/8) Epoch 16, batch 900, loss[loss=0.1612, simple_loss=0.258, pruned_loss=0.03214, over 7329.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2748, pruned_loss=0.04048, over 1408524.84 frames.], batch size: 20, lr: 4.61e-04
2022-04-29 10:24:38,446 INFO [train.py:763] (3/8) Epoch 16, batch 950, loss[loss=0.1705, simple_loss=0.2534, pruned_loss=0.04376, over 7135.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2742, pruned_loss=0.04028, over 1412464.92 frames.], batch size: 17, lr: 4.60e-04
2022-04-29 10:25:44,698 INFO [train.py:763] (3/8) Epoch 16, batch 1000, loss[loss=0.184, simple_loss=0.2896, pruned_loss=0.03919, over 7117.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2752, pruned_loss=0.04091, over 1417016.00 frames.], batch size: 21, lr: 4.60e-04
2022-04-29 10:26:51,175 INFO [train.py:763] (3/8) Epoch 16, batch 1050, loss[loss=0.2079, simple_loss=0.3026, pruned_loss=0.05659, over 7338.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2749, pruned_loss=0.04097, over 1421238.77 frames.], batch size: 22, lr: 4.60e-04
2022-04-29 10:27:57,453 INFO [train.py:763] (3/8) Epoch 16, batch 1100, loss[loss=0.1721, simple_loss=0.2709, pruned_loss=0.03671, over 7305.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2755, pruned_loss=0.0411, over 1421625.96 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:29:02,472 INFO [train.py:763] (3/8) Epoch 16, batch 1150, loss[loss=0.2068, simple_loss=0.3092, pruned_loss=0.05217, over 7312.00 frames.], tot_loss[loss=0.179, simple_loss=0.2758, pruned_loss=0.04107, over 1422947.43 frames.], batch size: 24, lr: 4.60e-04
2022-04-29 10:30:08,050 INFO [train.py:763] (3/8) Epoch 16, batch 1200, loss[loss=0.2469, simple_loss=0.3479, pruned_loss=0.07301, over 7291.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2756, pruned_loss=0.04093, over 1419086.20 frames.], batch size: 25, lr: 4.60e-04
2022-04-29 10:31:13,265 INFO [train.py:763] (3/8) Epoch 16, batch 1250, loss[loss=0.2155, simple_loss=0.3074, pruned_loss=0.06177, over 7276.00 frames.], tot_loss[loss=0.1791, simple_loss=0.276, pruned_loss=0.0411, over 1415153.30 frames.], batch size: 18, lr: 4.60e-04
2022-04-29 10:32:19,086 INFO [train.py:763] (3/8) Epoch 16, batch 1300, loss[loss=0.2062, simple_loss=0.3116, pruned_loss=0.05038, over 7350.00 frames.], tot_loss[loss=0.1792, simple_loss=0.276, pruned_loss=0.04125, over 1413828.90 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:33:25,809 INFO [train.py:763] (3/8) Epoch 16, batch 1350, loss[loss=0.1527, simple_loss=0.2481, pruned_loss=0.02865, over 6996.00 frames.], tot_loss[loss=0.1793, simple_loss=0.276, pruned_loss=0.04133, over 1419219.71 frames.], batch size: 16, lr: 4.59e-04
2022-04-29 10:34:32,888 INFO [train.py:763] (3/8) Epoch 16, batch 1400, loss[loss=0.1864, simple_loss=0.2808, pruned_loss=0.04601, over 7139.00 frames.], tot_loss[loss=0.178, simple_loss=0.2742, pruned_loss=0.04087, over 1420483.05 frames.], batch size: 20, lr: 4.59e-04
2022-04-29 10:35:38,352 INFO [train.py:763] (3/8) Epoch 16, batch 1450, loss[loss=0.1681, simple_loss=0.273, pruned_loss=0.03164, over 7343.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2744, pruned_loss=0.04059, over 1419381.06 frames.], batch size: 22, lr: 4.59e-04
2022-04-29 10:36:43,997 INFO [train.py:763] (3/8) Epoch 16, batch 1500, loss[loss=0.1511, simple_loss=0.242, pruned_loss=0.03015, over 7249.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2731, pruned_loss=0.04029, over 1425014.51 frames.], batch size: 19, lr: 4.59e-04
2022-04-29 10:37:49,277 INFO [train.py:763] (3/8) Epoch 16, batch 1550, loss[loss=0.1636, simple_loss=0.2725, pruned_loss=0.02731, over 7211.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2734, pruned_loss=0.04065, over 1423079.44 frames.], batch size: 21, lr: 4.59e-04
2022-04-29 10:38:55,268 INFO [train.py:763] (3/8) Epoch 16, batch 1600, loss[loss=0.1521, simple_loss=0.2503, pruned_loss=0.02697, over 7424.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2731, pruned_loss=0.04032, over 1427576.29 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:40:00,454 INFO [train.py:763] (3/8) Epoch 16, batch 1650, loss[loss=0.1722, simple_loss=0.2671, pruned_loss=0.03859, over 7418.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2732, pruned_loss=0.04011, over 1428964.81 frames.], batch size: 21, lr: 4.58e-04
2022-04-29 10:41:05,544 INFO [train.py:763] (3/8) Epoch 16, batch 1700, loss[loss=0.2386, simple_loss=0.3302, pruned_loss=0.07345, over 5361.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2746, pruned_loss=0.04087, over 1423487.35 frames.], batch size: 52, lr: 4.58e-04
2022-04-29 10:42:10,600 INFO [train.py:763] (3/8) Epoch 16, batch 1750, loss[loss=0.208, simple_loss=0.3082, pruned_loss=0.05392, over 7380.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2756, pruned_loss=0.04107, over 1414531.29 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:43:15,523 INFO [train.py:763] (3/8) Epoch 16, batch 1800, loss[loss=0.1963, simple_loss=0.2945, pruned_loss=0.04906, over 7204.00 frames.], tot_loss[loss=0.1794, simple_loss=0.276, pruned_loss=0.04137, over 1415278.88 frames.], batch size: 23, lr: 4.58e-04
2022-04-29 10:44:20,684 INFO [train.py:763] (3/8) Epoch 16, batch 1850, loss[loss=0.1703, simple_loss=0.2699, pruned_loss=0.03538, over 6393.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2759, pruned_loss=0.04099, over 1416272.47 frames.], batch size: 37, lr: 4.58e-04
2022-04-29 10:45:26,186 INFO [train.py:763] (3/8) Epoch 16, batch 1900, loss[loss=0.1753, simple_loss=0.278, pruned_loss=0.03632, over 7443.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2764, pruned_loss=0.04169, over 1420386.67 frames.], batch size: 20, lr: 4.58e-04
2022-04-29 10:46:31,346 INFO [train.py:763] (3/8) Epoch 16, batch 1950, loss[loss=0.1649, simple_loss=0.2753, pruned_loss=0.02726, over 7313.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2759, pruned_loss=0.04144, over 1422363.60 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:47:36,625 INFO [train.py:763] (3/8) Epoch 16, batch 2000, loss[loss=0.1773, simple_loss=0.2637, pruned_loss=0.04542, over 7268.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2761, pruned_loss=0.04153, over 1424539.52 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:48:44,156 INFO [train.py:763] (3/8) Epoch 16, batch 2050, loss[loss=0.162, simple_loss=0.2527, pruned_loss=0.03564, over 7417.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2746, pruned_loss=0.04082, over 1427281.76 frames.], batch size: 18, lr: 4.57e-04
2022-04-29 10:49:51,119 INFO [train.py:763] (3/8) Epoch 16, batch 2100, loss[loss=0.1773, simple_loss=0.2757, pruned_loss=0.03944, over 7415.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2745, pruned_loss=0.04067, over 1428754.35 frames.], batch size: 21, lr: 4.57e-04
2022-04-29 10:50:57,993 INFO [train.py:763] (3/8) Epoch 16, batch 2150, loss[loss=0.1676, simple_loss=0.2676, pruned_loss=0.03381, over 7358.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2745, pruned_loss=0.04055, over 1424554.86 frames.], batch size: 19, lr: 4.57e-04
2022-04-29 10:52:04,704 INFO [train.py:763] (3/8) Epoch 16, batch 2200, loss[loss=0.1828, simple_loss=0.2864, pruned_loss=0.03965, over 7338.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2745, pruned_loss=0.04033, over 1422207.89 frames.], batch size: 22, lr: 4.57e-04
2022-04-29 10:53:10,674 INFO [train.py:763] (3/8) Epoch 16, batch 2250, loss[loss=0.187, simple_loss=0.2888, pruned_loss=0.04255, over 7405.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2749, pruned_loss=0.04079, over 1424316.39 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:54:16,234 INFO [train.py:763] (3/8) Epoch 16, batch 2300, loss[loss=0.2086, simple_loss=0.3048, pruned_loss=0.05621, over 7298.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2755, pruned_loss=0.04109, over 1423255.60 frames.], batch size: 24, lr: 4.56e-04
2022-04-29 10:55:22,548 INFO [train.py:763] (3/8) Epoch 16, batch 2350, loss[loss=0.1798, simple_loss=0.2769, pruned_loss=0.04138, over 7381.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2744, pruned_loss=0.04072, over 1427007.22 frames.], batch size: 23, lr: 4.56e-04
2022-04-29 10:56:28,586 INFO [train.py:763] (3/8) Epoch 16, batch 2400, loss[loss=0.1575, simple_loss=0.242, pruned_loss=0.03656, over 6998.00 frames.], tot_loss[loss=0.1775, simple_loss=0.274, pruned_loss=0.04048, over 1424613.64 frames.], batch size: 16, lr: 4.56e-04
2022-04-29 10:57:34,906 INFO [train.py:763] (3/8) Epoch 16, batch 2450, loss[loss=0.1628, simple_loss=0.2685, pruned_loss=0.02851, over 7329.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2737, pruned_loss=0.04047, over 1424256.78 frames.], batch size: 22, lr: 4.56e-04
2022-04-29 10:58:41,492 INFO [train.py:763] (3/8) Epoch 16, batch 2500, loss[loss=0.2163, simple_loss=0.3069, pruned_loss=0.06283, over 7213.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2728, pruned_loss=0.04048, over 1423513.19 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 10:59:48,421 INFO [train.py:763] (3/8) Epoch 16, batch 2550, loss[loss=0.1747, simple_loss=0.29, pruned_loss=0.02966, over 7223.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2724, pruned_loss=0.04018, over 1418454.31 frames.], batch size: 21, lr: 4.56e-04
2022-04-29 11:00:54,058 INFO [train.py:763] (3/8) Epoch 16, batch 2600, loss[loss=0.1756, simple_loss=0.2813, pruned_loss=0.03492, over 7062.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2739, pruned_loss=0.04034, over 1421102.89 frames.], batch size: 28, lr: 4.55e-04
2022-04-29 11:01:59,324 INFO [train.py:763] (3/8) Epoch 16, batch 2650, loss[loss=0.1679, simple_loss=0.2551, pruned_loss=0.04037, over 7363.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2737, pruned_loss=0.0404, over 1419971.65 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:03:04,682 INFO [train.py:763] (3/8) Epoch 16, batch 2700, loss[loss=0.2013, simple_loss=0.3077, pruned_loss=0.04742, over 7318.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2729, pruned_loss=0.03993, over 1422545.95 frames.], batch size: 22, lr: 4.55e-04
2022-04-29 11:04:10,089 INFO [train.py:763] (3/8) Epoch 16, batch 2750, loss[loss=0.1666, simple_loss=0.2627, pruned_loss=0.03521, over 7148.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2721, pruned_loss=0.03974, over 1421631.46 frames.], batch size: 19, lr: 4.55e-04
2022-04-29 11:05:15,588 INFO [train.py:763] (3/8) Epoch 16, batch 2800, loss[loss=0.2053, simple_loss=0.287, pruned_loss=0.06181, over 5298.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2727, pruned_loss=0.04022, over 1421762.83 frames.], batch size: 52, lr: 4.55e-04
2022-04-29 11:06:20,605 INFO [train.py:763] (3/8) Epoch 16, batch 2850, loss[loss=0.178, simple_loss=0.2828, pruned_loss=0.03655, over 7317.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2732, pruned_loss=0.04044, over 1422229.22 frames.], batch size: 21, lr: 4.55e-04
2022-04-29 11:07:35,851 INFO [train.py:763] (3/8) Epoch 16, batch 2900, loss[loss=0.1801, simple_loss=0.2942, pruned_loss=0.03298, over 7237.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2733, pruned_loss=0.04067, over 1418527.16 frames.], batch size: 20, lr: 4.55e-04
2022-04-29 11:08:42,369 INFO [train.py:763] (3/8) Epoch 16, batch 2950, loss[loss=0.1587, simple_loss=0.2516, pruned_loss=0.03292, over 7274.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2742, pruned_loss=0.04101, over 1419287.62 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:09:49,126 INFO [train.py:763] (3/8) Epoch 16, batch 3000, loss[loss=0.1943, simple_loss=0.2988, pruned_loss=0.04491, over 7144.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2746, pruned_loss=0.04103, over 1423893.38 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:09:49,127 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 11:10:05,042 INFO [train.py:792] (3/8) 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] (3/8) Epoch 16, batch 3050, loss[loss=0.1933, simple_loss=0.2858, pruned_loss=0.05039, over 6269.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04033, over 1423667.82 frames.], batch size: 37, lr: 4.54e-04
2022-04-29 11:12:42,600 INFO [train.py:763] (3/8) Epoch 16, batch 3100, loss[loss=0.1878, simple_loss=0.2854, pruned_loss=0.04508, over 7301.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2746, pruned_loss=0.04057, over 1420455.57 frames.], batch size: 25, lr: 4.54e-04
2022-04-29 11:13:48,020 INFO [train.py:763] (3/8) Epoch 16, batch 3150, loss[loss=0.1731, simple_loss=0.2626, pruned_loss=0.04182, over 7332.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2745, pruned_loss=0.0406, over 1419588.01 frames.], batch size: 20, lr: 4.54e-04
2022-04-29 11:15:03,459 INFO [train.py:763] (3/8) Epoch 16, batch 3200, loss[loss=0.163, simple_loss=0.266, pruned_loss=0.03003, over 7367.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2737, pruned_loss=0.0407, over 1418910.11 frames.], batch size: 19, lr: 4.54e-04
2022-04-29 11:16:27,096 INFO [train.py:763] (3/8) Epoch 16, batch 3250, loss[loss=0.1493, simple_loss=0.2444, pruned_loss=0.0271, over 7056.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2737, pruned_loss=0.04059, over 1424581.30 frames.], batch size: 18, lr: 4.54e-04
2022-04-29 11:17:32,420 INFO [train.py:763] (3/8) Epoch 16, batch 3300, loss[loss=0.199, simple_loss=0.2922, pruned_loss=0.05293, over 7149.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2743, pruned_loss=0.04063, over 1425754.68 frames.], batch size: 19, lr: 4.53e-04
2022-04-29 11:18:47,353 INFO [train.py:763] (3/8) Epoch 16, batch 3350, loss[loss=0.1816, simple_loss=0.286, pruned_loss=0.03858, over 7340.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2742, pruned_loss=0.04019, over 1426494.96 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:19:54,000 INFO [train.py:763] (3/8) Epoch 16, batch 3400, loss[loss=0.178, simple_loss=0.2743, pruned_loss=0.04083, over 7141.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2737, pruned_loss=0.04036, over 1423804.02 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:21:00,495 INFO [train.py:763] (3/8) Epoch 16, batch 3450, loss[loss=0.1825, simple_loss=0.2738, pruned_loss=0.0456, over 7330.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2719, pruned_loss=0.04037, over 1424677.22 frames.], batch size: 20, lr: 4.53e-04
2022-04-29 11:22:05,835 INFO [train.py:763] (3/8) Epoch 16, batch 3500, loss[loss=0.1708, simple_loss=0.2741, pruned_loss=0.03375, over 7214.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2723, pruned_loss=0.04011, over 1424372.08 frames.], batch size: 22, lr: 4.53e-04
2022-04-29 11:23:10,998 INFO [train.py:763] (3/8) Epoch 16, batch 3550, loss[loss=0.1787, simple_loss=0.2869, pruned_loss=0.0352, over 7107.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2734, pruned_loss=0.04035, over 1426698.54 frames.], batch size: 21, lr: 4.53e-04
2022-04-29 11:24:16,265 INFO [train.py:763] (3/8) Epoch 16, batch 3600, loss[loss=0.1563, simple_loss=0.2485, pruned_loss=0.03202, over 7277.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2743, pruned_loss=0.04044, over 1427555.97 frames.], batch size: 18, lr: 4.52e-04
2022-04-29 11:25:21,852 INFO [train.py:763] (3/8) Epoch 16, batch 3650, loss[loss=0.1763, simple_loss=0.2723, pruned_loss=0.04011, over 7320.00 frames.], tot_loss[loss=0.177, simple_loss=0.2738, pruned_loss=0.04014, over 1431062.89 frames.], batch size: 21, lr: 4.52e-04
2022-04-29 11:26:27,134 INFO [train.py:763] (3/8) Epoch 16, batch 3700, loss[loss=0.19, simple_loss=0.2884, pruned_loss=0.0458, over 7142.00 frames.], tot_loss[loss=0.177, simple_loss=0.2735, pruned_loss=0.04024, over 1431244.09 frames.], batch size: 20, lr: 4.52e-04
2022-04-29 11:27:34,286 INFO [train.py:763] (3/8) Epoch 16, batch 3750, loss[loss=0.1973, simple_loss=0.2954, pruned_loss=0.04964, over 6452.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2738, pruned_loss=0.04043, over 1428141.54 frames.], batch size: 38, lr: 4.52e-04
2022-04-29 11:28:40,551 INFO [train.py:763] (3/8) Epoch 16, batch 3800, loss[loss=0.1774, simple_loss=0.2776, pruned_loss=0.03865, over 6462.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2747, pruned_loss=0.0405, over 1426845.33 frames.], batch size: 38, lr: 4.52e-04
2022-04-29 11:29:46,869 INFO [train.py:763] (3/8) Epoch 16, batch 3850, loss[loss=0.1476, simple_loss=0.239, pruned_loss=0.0281, over 6991.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2742, pruned_loss=0.04, over 1426202.37 frames.], batch size: 16, lr: 4.52e-04
2022-04-29 11:30:53,555 INFO [train.py:763] (3/8) Epoch 16, batch 3900, loss[loss=0.1724, simple_loss=0.272, pruned_loss=0.03644, over 7205.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2731, pruned_loss=0.03963, over 1428196.25 frames.], batch size: 22, lr: 4.52e-04
2022-04-29 11:32:00,326 INFO [train.py:763] (3/8) Epoch 16, batch 3950, loss[loss=0.2266, simple_loss=0.3137, pruned_loss=0.06978, over 7187.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2741, pruned_loss=0.04005, over 1427541.96 frames.], batch size: 23, lr: 4.51e-04
2022-04-29 11:33:05,768 INFO [train.py:763] (3/8) Epoch 16, batch 4000, loss[loss=0.1547, simple_loss=0.2441, pruned_loss=0.03268, over 7290.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2736, pruned_loss=0.03998, over 1427732.73 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:34:12,297 INFO [train.py:763] (3/8) Epoch 16, batch 4050, loss[loss=0.1623, simple_loss=0.2702, pruned_loss=0.02719, over 6850.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2734, pruned_loss=0.04021, over 1424406.29 frames.], batch size: 31, lr: 4.51e-04
2022-04-29 11:35:18,250 INFO [train.py:763] (3/8) Epoch 16, batch 4100, loss[loss=0.1776, simple_loss=0.2805, pruned_loss=0.03739, over 6378.00 frames.], tot_loss[loss=0.1773, simple_loss=0.274, pruned_loss=0.04032, over 1423592.36 frames.], batch size: 37, lr: 4.51e-04
2022-04-29 11:36:24,674 INFO [train.py:763] (3/8) Epoch 16, batch 4150, loss[loss=0.1715, simple_loss=0.2552, pruned_loss=0.04393, over 7136.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2731, pruned_loss=0.04009, over 1423428.63 frames.], batch size: 17, lr: 4.51e-04
2022-04-29 11:37:30,201 INFO [train.py:763] (3/8) Epoch 16, batch 4200, loss[loss=0.1887, simple_loss=0.2935, pruned_loss=0.04193, over 7163.00 frames.], tot_loss[loss=0.177, simple_loss=0.2739, pruned_loss=0.04005, over 1422172.27 frames.], batch size: 26, lr: 4.51e-04
2022-04-29 11:38:36,629 INFO [train.py:763] (3/8) Epoch 16, batch 4250, loss[loss=0.1589, simple_loss=0.2575, pruned_loss=0.03017, over 7271.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2745, pruned_loss=0.0401, over 1423034.39 frames.], batch size: 18, lr: 4.51e-04
2022-04-29 11:39:43,731 INFO [train.py:763] (3/8) Epoch 16, batch 4300, loss[loss=0.1688, simple_loss=0.2641, pruned_loss=0.03678, over 7067.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2742, pruned_loss=0.04008, over 1422013.00 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:40:49,811 INFO [train.py:763] (3/8) Epoch 16, batch 4350, loss[loss=0.1861, simple_loss=0.2791, pruned_loss=0.04657, over 7166.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2731, pruned_loss=0.03973, over 1421419.02 frames.], batch size: 18, lr: 4.50e-04
2022-04-29 11:41:55,138 INFO [train.py:763] (3/8) Epoch 16, batch 4400, loss[loss=0.1692, simple_loss=0.2761, pruned_loss=0.0311, over 7222.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2735, pruned_loss=0.03977, over 1419404.82 frames.], batch size: 21, lr: 4.50e-04
2022-04-29 11:43:00,289 INFO [train.py:763] (3/8) Epoch 16, batch 4450, loss[loss=0.1571, simple_loss=0.2463, pruned_loss=0.034, over 7122.00 frames.], tot_loss[loss=0.1779, simple_loss=0.275, pruned_loss=0.04038, over 1414879.15 frames.], batch size: 17, lr: 4.50e-04
2022-04-29 11:44:06,063 INFO [train.py:763] (3/8) Epoch 16, batch 4500, loss[loss=0.1852, simple_loss=0.2823, pruned_loss=0.04404, over 7239.00 frames.], tot_loss[loss=0.177, simple_loss=0.2737, pruned_loss=0.04017, over 1413613.28 frames.], batch size: 20, lr: 4.50e-04
2022-04-29 11:45:13,646 INFO [train.py:763] (3/8) Epoch 16, batch 4550, loss[loss=0.2231, simple_loss=0.3017, pruned_loss=0.07225, over 5102.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2733, pruned_loss=0.04152, over 1376662.09 frames.], batch size: 53, lr: 4.50e-04
2022-04-29 11:46:42,224 INFO [train.py:763] (3/8) Epoch 17, batch 0, loss[loss=0.1891, simple_loss=0.2863, pruned_loss=0.04592, over 7238.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2863, pruned_loss=0.04592, over 7238.00 frames.], batch size: 20, lr: 4.38e-04
2022-04-29 11:47:48,725 INFO [train.py:763] (3/8) Epoch 17, batch 50, loss[loss=0.1707, simple_loss=0.2606, pruned_loss=0.04042, over 7006.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2719, pruned_loss=0.03964, over 323622.16 frames.], batch size: 16, lr: 4.38e-04
2022-04-29 11:48:54,533 INFO [train.py:763] (3/8) Epoch 17, batch 100, loss[loss=0.1681, simple_loss=0.2682, pruned_loss=0.03397, over 7153.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2726, pruned_loss=0.03884, over 565413.99 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:50:00,285 INFO [train.py:763] (3/8) Epoch 17, batch 150, loss[loss=0.1752, simple_loss=0.2805, pruned_loss=0.03497, over 7142.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2736, pruned_loss=0.03883, over 752276.03 frames.], batch size: 20, lr: 4.37e-04
2022-04-29 11:51:07,234 INFO [train.py:763] (3/8) Epoch 17, batch 200, loss[loss=0.1765, simple_loss=0.2699, pruned_loss=0.04153, over 7168.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2739, pruned_loss=0.03918, over 903349.68 frames.], batch size: 18, lr: 4.37e-04
2022-04-29 11:52:14,162 INFO [train.py:763] (3/8) Epoch 17, batch 250, loss[loss=0.1862, simple_loss=0.2798, pruned_loss=0.04631, over 6822.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2741, pruned_loss=0.039, over 1020865.66 frames.], batch size: 31, lr: 4.37e-04
2022-04-29 11:53:19,798 INFO [train.py:763] (3/8) Epoch 17, batch 300, loss[loss=0.1708, simple_loss=0.2775, pruned_loss=0.03205, over 7045.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2739, pruned_loss=0.03875, over 1104183.98 frames.], batch size: 28, lr: 4.37e-04
2022-04-29 11:54:25,512 INFO [train.py:763] (3/8) Epoch 17, batch 350, loss[loss=0.1788, simple_loss=0.2912, pruned_loss=0.03319, over 7337.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2731, pruned_loss=0.03864, over 1172271.06 frames.], batch size: 22, lr: 4.37e-04
2022-04-29 11:55:31,572 INFO [train.py:763] (3/8) Epoch 17, batch 400, loss[loss=0.1433, simple_loss=0.2351, pruned_loss=0.02577, over 7247.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2728, pruned_loss=0.03813, over 1232698.16 frames.], batch size: 16, lr: 4.37e-04
2022-04-29 11:56:37,248 INFO [train.py:763] (3/8) Epoch 17, batch 450, loss[loss=0.1755, simple_loss=0.2693, pruned_loss=0.0408, over 7214.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2738, pruned_loss=0.03866, over 1275635.90 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:57:42,948 INFO [train.py:763] (3/8) Epoch 17, batch 500, loss[loss=0.1973, simple_loss=0.2929, pruned_loss=0.05078, over 7337.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2743, pruned_loss=0.03915, over 1312227.82 frames.], batch size: 22, lr: 4.36e-04
2022-04-29 11:58:48,660 INFO [train.py:763] (3/8) Epoch 17, batch 550, loss[loss=0.1771, simple_loss=0.2643, pruned_loss=0.04496, over 7135.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2735, pruned_loss=0.03882, over 1338684.31 frames.], batch size: 17, lr: 4.36e-04
2022-04-29 11:59:54,498 INFO [train.py:763] (3/8) Epoch 17, batch 600, loss[loss=0.1656, simple_loss=0.2688, pruned_loss=0.03123, over 6427.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2746, pruned_loss=0.03948, over 1356410.62 frames.], batch size: 38, lr: 4.36e-04
2022-04-29 12:01:00,144 INFO [train.py:763] (3/8) Epoch 17, batch 650, loss[loss=0.2086, simple_loss=0.2868, pruned_loss=0.06519, over 4944.00 frames.], tot_loss[loss=0.1766, simple_loss=0.274, pruned_loss=0.03957, over 1369181.40 frames.], batch size: 52, lr: 4.36e-04
2022-04-29 12:02:07,659 INFO [train.py:763] (3/8) Epoch 17, batch 700, loss[loss=0.1819, simple_loss=0.2854, pruned_loss=0.03917, over 7318.00 frames.], tot_loss[loss=0.176, simple_loss=0.2732, pruned_loss=0.03936, over 1380370.78 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:03:15,585 INFO [train.py:763] (3/8) Epoch 17, batch 750, loss[loss=0.1674, simple_loss=0.2675, pruned_loss=0.03369, over 7428.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2719, pruned_loss=0.03888, over 1390921.97 frames.], batch size: 18, lr: 4.36e-04
2022-04-29 12:04:22,597 INFO [train.py:763] (3/8) Epoch 17, batch 800, loss[loss=0.2002, simple_loss=0.303, pruned_loss=0.04871, over 7321.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2715, pruned_loss=0.03851, over 1403512.57 frames.], batch size: 21, lr: 4.36e-04
2022-04-29 12:05:28,619 INFO [train.py:763] (3/8) Epoch 17, batch 850, loss[loss=0.1778, simple_loss=0.2814, pruned_loss=0.03708, over 7409.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2716, pruned_loss=0.03877, over 1406851.92 frames.], batch size: 21, lr: 4.35e-04
2022-04-29 12:06:34,119 INFO [train.py:763] (3/8) Epoch 17, batch 900, loss[loss=0.2064, simple_loss=0.3046, pruned_loss=0.05414, over 7203.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2727, pruned_loss=0.03979, over 1406847.82 frames.], batch size: 22, lr: 4.35e-04
2022-04-29 12:07:40,033 INFO [train.py:763] (3/8) Epoch 17, batch 950, loss[loss=0.1629, simple_loss=0.2671, pruned_loss=0.02932, over 7252.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2739, pruned_loss=0.04017, over 1408938.95 frames.], batch size: 19, lr: 4.35e-04
2022-04-29 12:08:46,272 INFO [train.py:763] (3/8) Epoch 17, batch 1000, loss[loss=0.1738, simple_loss=0.2808, pruned_loss=0.03336, over 7287.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2737, pruned_loss=0.0402, over 1413311.03 frames.], batch size: 24, lr: 4.35e-04
2022-04-29 12:09:52,067 INFO [train.py:763] (3/8) Epoch 17, batch 1050, loss[loss=0.1647, simple_loss=0.2605, pruned_loss=0.03446, over 7281.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2727, pruned_loss=0.03978, over 1414986.55 frames.], batch size: 17, lr: 4.35e-04
2022-04-29 12:10:57,971 INFO [train.py:763] (3/8) Epoch 17, batch 1100, loss[loss=0.1978, simple_loss=0.3033, pruned_loss=0.0462, over 7279.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.03994, over 1419539.55 frames.], batch size: 25, lr: 4.35e-04
2022-04-29 12:12:04,944 INFO [train.py:763] (3/8) Epoch 17, batch 1150, loss[loss=0.209, simple_loss=0.3014, pruned_loss=0.05836, over 7377.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2731, pruned_loss=0.03991, over 1418323.11 frames.], batch size: 23, lr: 4.35e-04
2022-04-29 12:13:12,219 INFO [train.py:763] (3/8) Epoch 17, batch 1200, loss[loss=0.1872, simple_loss=0.2763, pruned_loss=0.04906, over 7286.00 frames.], tot_loss[loss=0.177, simple_loss=0.2734, pruned_loss=0.04031, over 1415952.91 frames.], batch size: 18, lr: 4.34e-04
2022-04-29 12:14:19,344 INFO [train.py:763] (3/8) Epoch 17, batch 1250, loss[loss=0.1727, simple_loss=0.2725, pruned_loss=0.03644, over 7407.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2732, pruned_loss=0.03991, over 1417960.18 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:15:25,173 INFO [train.py:763] (3/8) Epoch 17, batch 1300, loss[loss=0.1476, simple_loss=0.2468, pruned_loss=0.02415, over 7160.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2727, pruned_loss=0.0398, over 1419223.04 frames.], batch size: 26, lr: 4.34e-04
2022-04-29 12:16:30,495 INFO [train.py:763] (3/8) Epoch 17, batch 1350, loss[loss=0.1607, simple_loss=0.251, pruned_loss=0.03517, over 7000.00 frames.], tot_loss[loss=0.1761, simple_loss=0.273, pruned_loss=0.03955, over 1421743.17 frames.], batch size: 16, lr: 4.34e-04
2022-04-29 12:17:36,046 INFO [train.py:763] (3/8) Epoch 17, batch 1400, loss[loss=0.1814, simple_loss=0.2802, pruned_loss=0.0413, over 7118.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2739, pruned_loss=0.03955, over 1423743.48 frames.], batch size: 21, lr: 4.34e-04
2022-04-29 12:18:41,487 INFO [train.py:763] (3/8) Epoch 17, batch 1450, loss[loss=0.1648, simple_loss=0.2714, pruned_loss=0.02908, over 7149.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2744, pruned_loss=0.03975, over 1421742.09 frames.], batch size: 20, lr: 4.34e-04
2022-04-29 12:19:47,539 INFO [train.py:763] (3/8) Epoch 17, batch 1500, loss[loss=0.1707, simple_loss=0.2684, pruned_loss=0.03654, over 7288.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2743, pruned_loss=0.03992, over 1413339.49 frames.], batch size: 25, lr: 4.34e-04
2022-04-29 12:20:53,501 INFO [train.py:763] (3/8) Epoch 17, batch 1550, loss[loss=0.1895, simple_loss=0.2806, pruned_loss=0.04925, over 7156.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2732, pruned_loss=0.03912, over 1420524.97 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:21:59,195 INFO [train.py:763] (3/8) Epoch 17, batch 1600, loss[loss=0.1723, simple_loss=0.2677, pruned_loss=0.03851, over 7432.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2734, pruned_loss=0.03888, over 1421184.26 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:23:04,503 INFO [train.py:763] (3/8) Epoch 17, batch 1650, loss[loss=0.1391, simple_loss=0.2299, pruned_loss=0.0241, over 7283.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2725, pruned_loss=0.03847, over 1421008.87 frames.], batch size: 17, lr: 4.33e-04
2022-04-29 12:24:09,899 INFO [train.py:763] (3/8) Epoch 17, batch 1700, loss[loss=0.1575, simple_loss=0.2603, pruned_loss=0.02733, over 7362.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2731, pruned_loss=0.03866, over 1423734.14 frames.], batch size: 19, lr: 4.33e-04
2022-04-29 12:25:15,253 INFO [train.py:763] (3/8) Epoch 17, batch 1750, loss[loss=0.1891, simple_loss=0.2853, pruned_loss=0.04647, over 7323.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2731, pruned_loss=0.03879, over 1424000.89 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:26:20,536 INFO [train.py:763] (3/8) Epoch 17, batch 1800, loss[loss=0.1632, simple_loss=0.2593, pruned_loss=0.03361, over 7235.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2725, pruned_loss=0.03886, over 1427958.50 frames.], batch size: 20, lr: 4.33e-04
2022-04-29 12:27:26,283 INFO [train.py:763] (3/8) Epoch 17, batch 1850, loss[loss=0.1945, simple_loss=0.2908, pruned_loss=0.04912, over 4792.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2711, pruned_loss=0.03877, over 1426224.65 frames.], batch size: 53, lr: 4.33e-04
2022-04-29 12:28:31,339 INFO [train.py:763] (3/8) Epoch 17, batch 1900, loss[loss=0.1829, simple_loss=0.2907, pruned_loss=0.03759, over 7325.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2729, pruned_loss=0.03928, over 1426270.43 frames.], batch size: 21, lr: 4.33e-04
2022-04-29 12:29:36,730 INFO [train.py:763] (3/8) Epoch 17, batch 1950, loss[loss=0.1953, simple_loss=0.2954, pruned_loss=0.04759, over 7326.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2744, pruned_loss=0.04007, over 1423490.33 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:30:42,616 INFO [train.py:763] (3/8) Epoch 17, batch 2000, loss[loss=0.1848, simple_loss=0.2703, pruned_loss=0.04971, over 4976.00 frames.], tot_loss[loss=0.1759, simple_loss=0.273, pruned_loss=0.03939, over 1423940.51 frames.], batch size: 52, lr: 4.32e-04
2022-04-29 12:31:59,160 INFO [train.py:763] (3/8) Epoch 17, batch 2050, loss[loss=0.1852, simple_loss=0.2829, pruned_loss=0.04376, over 7126.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2732, pruned_loss=0.03969, over 1421010.25 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:33:04,641 INFO [train.py:763] (3/8) Epoch 17, batch 2100, loss[loss=0.242, simple_loss=0.331, pruned_loss=0.07647, over 6860.00 frames.], tot_loss[loss=0.1764, simple_loss=0.273, pruned_loss=0.03991, over 1416866.44 frames.], batch size: 32, lr: 4.32e-04
2022-04-29 12:34:11,526 INFO [train.py:763] (3/8) Epoch 17, batch 2150, loss[loss=0.162, simple_loss=0.2602, pruned_loss=0.03193, over 7230.00 frames.], tot_loss[loss=0.176, simple_loss=0.2726, pruned_loss=0.03976, over 1418481.79 frames.], batch size: 21, lr: 4.32e-04
2022-04-29 12:35:18,268 INFO [train.py:763] (3/8) Epoch 17, batch 2200, loss[loss=0.1911, simple_loss=0.2703, pruned_loss=0.056, over 7269.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2724, pruned_loss=0.03971, over 1420985.50 frames.], batch size: 16, lr: 4.32e-04
2022-04-29 12:36:23,940 INFO [train.py:763] (3/8) Epoch 17, batch 2250, loss[loss=0.165, simple_loss=0.2446, pruned_loss=0.04274, over 7011.00 frames.], tot_loss[loss=0.176, simple_loss=0.2723, pruned_loss=0.0398, over 1424298.56 frames.], batch size: 16, lr: 4.32e-04
2022-04-29 12:37:31,403 INFO [train.py:763] (3/8) Epoch 17, batch 2300, loss[loss=0.1944, simple_loss=0.2934, pruned_loss=0.0477, over 7144.00 frames.], tot_loss[loss=0.177, simple_loss=0.2737, pruned_loss=0.04019, over 1426203.90 frames.], batch size: 20, lr: 4.31e-04
2022-04-29 12:38:38,622 INFO [train.py:763] (3/8) Epoch 17, batch 2350, loss[loss=0.1901, simple_loss=0.3022, pruned_loss=0.03897, over 7174.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2742, pruned_loss=0.04055, over 1425951.20 frames.], batch size: 26, lr: 4.31e-04
2022-04-29 12:39:44,063 INFO [train.py:763] (3/8) Epoch 17, batch 2400, loss[loss=0.1878, simple_loss=0.2964, pruned_loss=0.03967, over 6360.00 frames.], tot_loss[loss=0.177, simple_loss=0.2742, pruned_loss=0.03985, over 1425095.24 frames.], batch size: 37, lr: 4.31e-04
2022-04-29 12:40:49,290 INFO [train.py:763] (3/8) Epoch 17, batch 2450, loss[loss=0.1681, simple_loss=0.2611, pruned_loss=0.03751, over 7148.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2732, pruned_loss=0.0393, over 1426223.45 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:41:54,333 INFO [train.py:763] (3/8) Epoch 17, batch 2500, loss[loss=0.1743, simple_loss=0.2869, pruned_loss=0.03083, over 7119.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2741, pruned_loss=0.03986, over 1418583.18 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:42:59,724 INFO [train.py:763] (3/8) Epoch 17, batch 2550, loss[loss=0.1741, simple_loss=0.281, pruned_loss=0.0336, over 7323.00 frames.], tot_loss[loss=0.176, simple_loss=0.2731, pruned_loss=0.03944, over 1419343.36 frames.], batch size: 21, lr: 4.31e-04
2022-04-29 12:44:04,850 INFO [train.py:763] (3/8) Epoch 17, batch 2600, loss[loss=0.1726, simple_loss=0.2412, pruned_loss=0.05201, over 6815.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2737, pruned_loss=0.04003, over 1418700.25 frames.], batch size: 15, lr: 4.31e-04
2022-04-29 12:45:10,699 INFO [train.py:763] (3/8) Epoch 17, batch 2650, loss[loss=0.1616, simple_loss=0.2598, pruned_loss=0.03172, over 7363.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2729, pruned_loss=0.03963, over 1419275.78 frames.], batch size: 19, lr: 4.31e-04
2022-04-29 12:46:17,006 INFO [train.py:763] (3/8) Epoch 17, batch 2700, loss[loss=0.1513, simple_loss=0.2415, pruned_loss=0.03058, over 7272.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2719, pruned_loss=0.0394, over 1419311.77 frames.], batch size: 18, lr: 4.30e-04
2022-04-29 12:47:22,078 INFO [train.py:763] (3/8) Epoch 17, batch 2750, loss[loss=0.1771, simple_loss=0.2745, pruned_loss=0.03986, over 7149.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2719, pruned_loss=0.03919, over 1416879.16 frames.], batch size: 20, lr: 4.30e-04
2022-04-29 12:48:28,858 INFO [train.py:763] (3/8) Epoch 17, batch 2800, loss[loss=0.1568, simple_loss=0.2607, pruned_loss=0.02641, over 7318.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2713, pruned_loss=0.03898, over 1416371.23 frames.], batch size: 21, lr: 4.30e-04
2022-04-29 12:49:34,423 INFO [train.py:763] (3/8) Epoch 17, batch 2850, loss[loss=0.2267, simple_loss=0.3123, pruned_loss=0.07059, over 7308.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2715, pruned_loss=0.03887, over 1419418.81 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:50:39,886 INFO [train.py:763] (3/8) Epoch 17, batch 2900, loss[loss=0.1898, simple_loss=0.3033, pruned_loss=0.03815, over 7187.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2719, pruned_loss=0.03922, over 1421765.89 frames.], batch size: 22, lr: 4.30e-04
2022-04-29 12:51:46,362 INFO [train.py:763] (3/8) Epoch 17, batch 2950, loss[loss=0.1921, simple_loss=0.2933, pruned_loss=0.04544, over 6398.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2712, pruned_loss=0.03846, over 1418739.57 frames.], batch size: 38, lr: 4.30e-04
2022-04-29 12:52:52,635 INFO [train.py:763] (3/8) Epoch 17, batch 3000, loss[loss=0.2017, simple_loss=0.2924, pruned_loss=0.05547, over 7299.00 frames.], tot_loss[loss=0.1748, simple_loss=0.272, pruned_loss=0.03877, over 1417729.17 frames.], batch size: 25, lr: 4.30e-04
2022-04-29 12:52:52,636 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 12:53:07,981 INFO [train.py:792] (3/8) Epoch 17, validation: loss=0.167, simple_loss=0.268, pruned_loss=0.03296, over 698248.00 frames.
2022-04-29 12:54:13,315 INFO [train.py:763] (3/8) Epoch 17, batch 3050, loss[loss=0.2128, simple_loss=0.3124, pruned_loss=0.05662, over 7123.00 frames.], tot_loss[loss=0.175, simple_loss=0.2719, pruned_loss=0.03903, over 1417547.35 frames.], batch size: 21, lr: 4.29e-04
2022-04-29 12:55:18,434 INFO [train.py:763] (3/8) Epoch 17, batch 3100, loss[loss=0.1423, simple_loss=0.2401, pruned_loss=0.02227, over 7233.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2719, pruned_loss=0.03914, over 1419362.25 frames.], batch size: 20, lr: 4.29e-04
2022-04-29 12:56:23,980 INFO [train.py:763] (3/8) Epoch 17, batch 3150, loss[loss=0.1639, simple_loss=0.2622, pruned_loss=0.03285, over 7253.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2716, pruned_loss=0.03901, over 1421361.33 frames.], batch size: 19, lr: 4.29e-04
2022-04-29 12:57:29,296 INFO [train.py:763] (3/8) Epoch 17, batch 3200, loss[loss=0.1922, simple_loss=0.3033, pruned_loss=0.0406, over 6800.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2718, pruned_loss=0.03917, over 1419338.16 frames.], batch size: 31, lr: 4.29e-04
2022-04-29 12:58:34,631 INFO [train.py:763] (3/8) Epoch 17, batch 3250, loss[loss=0.1641, simple_loss=0.2726, pruned_loss=0.02775, over 7381.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2713, pruned_loss=0.03847, over 1422010.24 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 12:59:42,206 INFO [train.py:763] (3/8) Epoch 17, batch 3300, loss[loss=0.1623, simple_loss=0.2568, pruned_loss=0.03389, over 7150.00 frames.], tot_loss[loss=0.173, simple_loss=0.2704, pruned_loss=0.03775, over 1425908.85 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:00:47,852 INFO [train.py:763] (3/8) Epoch 17, batch 3350, loss[loss=0.1686, simple_loss=0.2597, pruned_loss=0.03872, over 7406.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2713, pruned_loss=0.03804, over 1425984.21 frames.], batch size: 18, lr: 4.29e-04
2022-04-29 13:01:54,344 INFO [train.py:763] (3/8) Epoch 17, batch 3400, loss[loss=0.2066, simple_loss=0.3032, pruned_loss=0.05504, over 7375.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2708, pruned_loss=0.03802, over 1429421.79 frames.], batch size: 23, lr: 4.29e-04
2022-04-29 13:02:59,883 INFO [train.py:763] (3/8) Epoch 17, batch 3450, loss[loss=0.1827, simple_loss=0.275, pruned_loss=0.04517, over 7411.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2714, pruned_loss=0.03786, over 1430388.13 frames.], batch size: 18, lr: 4.28e-04
2022-04-29 13:04:05,572 INFO [train.py:763] (3/8) Epoch 17, batch 3500, loss[loss=0.1838, simple_loss=0.2928, pruned_loss=0.03736, over 6376.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2717, pruned_loss=0.03771, over 1432783.08 frames.], batch size: 38, lr: 4.28e-04
2022-04-29 13:05:11,602 INFO [train.py:763] (3/8) Epoch 17, batch 3550, loss[loss=0.1941, simple_loss=0.2859, pruned_loss=0.0511, over 7191.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2725, pruned_loss=0.03823, over 1431303.72 frames.], batch size: 23, lr: 4.28e-04
2022-04-29 13:06:17,356 INFO [train.py:763] (3/8) Epoch 17, batch 3600, loss[loss=0.2223, simple_loss=0.3155, pruned_loss=0.06453, over 7217.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2729, pruned_loss=0.03865, over 1432384.12 frames.], batch size: 21, lr: 4.28e-04
2022-04-29 13:07:22,977 INFO [train.py:763] (3/8) Epoch 17, batch 3650, loss[loss=0.1632, simple_loss=0.2663, pruned_loss=0.03011, over 7337.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2731, pruned_loss=0.03888, over 1424533.74 frames.], batch size: 22, lr: 4.28e-04
2022-04-29 13:08:28,133 INFO [train.py:763] (3/8) Epoch 17, batch 3700, loss[loss=0.1636, simple_loss=0.2551, pruned_loss=0.0361, over 7011.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2734, pruned_loss=0.03922, over 1425924.18 frames.], batch size: 16, lr: 4.28e-04
2022-04-29 13:09:33,325 INFO [train.py:763] (3/8) Epoch 17, batch 3750, loss[loss=0.1736, simple_loss=0.2766, pruned_loss=0.03528, over 7294.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2739, pruned_loss=0.03893, over 1428223.26 frames.], batch size: 25, lr: 4.28e-04
2022-04-29 13:10:39,693 INFO [train.py:763] (3/8) Epoch 17, batch 3800, loss[loss=0.1893, simple_loss=0.2871, pruned_loss=0.04574, over 7349.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2734, pruned_loss=0.03872, over 1427374.62 frames.], batch size: 19, lr: 4.28e-04
2022-04-29 13:11:45,016 INFO [train.py:763] (3/8) Epoch 17, batch 3850, loss[loss=0.1642, simple_loss=0.2548, pruned_loss=0.03684, over 7400.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2728, pruned_loss=0.03877, over 1425677.87 frames.], batch size: 18, lr: 4.27e-04
2022-04-29 13:12:50,423 INFO [train.py:763] (3/8) Epoch 17, batch 3900, loss[loss=0.1841, simple_loss=0.2926, pruned_loss=0.03775, over 7112.00 frames.], tot_loss[loss=0.175, simple_loss=0.2723, pruned_loss=0.03887, over 1421962.68 frames.], batch size: 21, lr: 4.27e-04
2022-04-29 13:13:55,778 INFO [train.py:763] (3/8) Epoch 17, batch 3950, loss[loss=0.1992, simple_loss=0.2898, pruned_loss=0.05431, over 7056.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2716, pruned_loss=0.03897, over 1423428.58 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:15:01,124 INFO [train.py:763] (3/8) Epoch 17, batch 4000, loss[loss=0.1557, simple_loss=0.2391, pruned_loss=0.03609, over 7238.00 frames.], tot_loss[loss=0.1751, simple_loss=0.272, pruned_loss=0.03906, over 1424113.45 frames.], batch size: 16, lr: 4.27e-04
2022-04-29 13:16:06,980 INFO [train.py:763] (3/8) Epoch 17, batch 4050, loss[loss=0.1735, simple_loss=0.2813, pruned_loss=0.03291, over 6996.00 frames.], tot_loss[loss=0.1746, simple_loss=0.272, pruned_loss=0.0386, over 1427345.84 frames.], batch size: 28, lr: 4.27e-04
2022-04-29 13:17:12,350 INFO [train.py:763] (3/8) Epoch 17, batch 4100, loss[loss=0.1669, simple_loss=0.2642, pruned_loss=0.03475, over 7142.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2717, pruned_loss=0.03865, over 1423200.17 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:18:18,022 INFO [train.py:763] (3/8) Epoch 17, batch 4150, loss[loss=0.1913, simple_loss=0.2735, pruned_loss=0.05458, over 7341.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2724, pruned_loss=0.03919, over 1422027.88 frames.], batch size: 20, lr: 4.27e-04
2022-04-29 13:19:24,062 INFO [train.py:763] (3/8) Epoch 17, batch 4200, loss[loss=0.162, simple_loss=0.2475, pruned_loss=0.03828, over 6993.00 frames.], tot_loss[loss=0.1752, simple_loss=0.272, pruned_loss=0.03915, over 1421929.58 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:20:29,202 INFO [train.py:763] (3/8) Epoch 17, batch 4250, loss[loss=0.2058, simple_loss=0.2971, pruned_loss=0.05729, over 6845.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2725, pruned_loss=0.03958, over 1416882.00 frames.], batch size: 31, lr: 4.26e-04
2022-04-29 13:21:35,159 INFO [train.py:763] (3/8) Epoch 17, batch 4300, loss[loss=0.1669, simple_loss=0.2453, pruned_loss=0.04429, over 7019.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2713, pruned_loss=0.03913, over 1417920.05 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:22:49,723 INFO [train.py:763] (3/8) Epoch 17, batch 4350, loss[loss=0.1782, simple_loss=0.2835, pruned_loss=0.03649, over 7223.00 frames.], tot_loss[loss=0.175, simple_loss=0.2715, pruned_loss=0.03928, over 1406429.39 frames.], batch size: 21, lr: 4.26e-04
2022-04-29 13:23:54,551 INFO [train.py:763] (3/8) Epoch 17, batch 4400, loss[loss=0.1439, simple_loss=0.2415, pruned_loss=0.02312, over 7061.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2731, pruned_loss=0.03993, over 1401603.86 frames.], batch size: 18, lr: 4.26e-04
2022-04-29 13:24:59,616 INFO [train.py:763] (3/8) Epoch 17, batch 4450, loss[loss=0.1811, simple_loss=0.2867, pruned_loss=0.03774, over 6355.00 frames.], tot_loss[loss=0.1778, simple_loss=0.275, pruned_loss=0.04028, over 1393654.07 frames.], batch size: 37, lr: 4.26e-04
2022-04-29 13:26:04,073 INFO [train.py:763] (3/8) Epoch 17, batch 4500, loss[loss=0.1496, simple_loss=0.2399, pruned_loss=0.02969, over 7012.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2752, pruned_loss=0.04026, over 1382232.57 frames.], batch size: 16, lr: 4.26e-04
2022-04-29 13:27:09,434 INFO [train.py:763] (3/8) Epoch 17, batch 4550, loss[loss=0.1734, simple_loss=0.2734, pruned_loss=0.03675, over 7155.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2746, pruned_loss=0.04042, over 1371534.84 frames.], batch size: 19, lr: 4.26e-04
2022-04-29 13:29:06,466 INFO [train.py:763] (3/8) Epoch 18, batch 0, loss[loss=0.1893, simple_loss=0.2869, pruned_loss=0.04591, over 7285.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2869, pruned_loss=0.04591, over 7285.00 frames.], batch size: 25, lr: 4.15e-04
2022-04-29 13:30:22,086 INFO [train.py:763] (3/8) Epoch 18, batch 50, loss[loss=0.2089, simple_loss=0.2981, pruned_loss=0.05986, over 7342.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2743, pruned_loss=0.04009, over 325119.20 frames.], batch size: 22, lr: 4.15e-04
2022-04-29 13:31:37,249 INFO [train.py:763] (3/8) Epoch 18, batch 100, loss[loss=0.1919, simple_loss=0.2921, pruned_loss=0.04586, over 7348.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2718, pruned_loss=0.03776, over 575182.50 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:32:51,551 INFO [train.py:763] (3/8) Epoch 18, batch 150, loss[loss=0.1781, simple_loss=0.2907, pruned_loss=0.03273, over 7211.00 frames.], tot_loss[loss=0.1729, simple_loss=0.271, pruned_loss=0.03736, over 764273.09 frames.], batch size: 21, lr: 4.14e-04
2022-04-29 13:33:57,483 INFO [train.py:763] (3/8) Epoch 18, batch 200, loss[loss=0.1636, simple_loss=0.2518, pruned_loss=0.03775, over 7291.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2709, pruned_loss=0.03778, over 910367.38 frames.], batch size: 17, lr: 4.14e-04
2022-04-29 13:35:11,772 INFO [train.py:763] (3/8) Epoch 18, batch 250, loss[loss=0.1696, simple_loss=0.273, pruned_loss=0.03308, over 6796.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2703, pruned_loss=0.038, over 1025819.17 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:36:17,271 INFO [train.py:763] (3/8) Epoch 18, batch 300, loss[loss=0.1605, simple_loss=0.2581, pruned_loss=0.03139, over 7237.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2696, pruned_loss=0.03769, over 1115574.70 frames.], batch size: 20, lr: 4.14e-04
2022-04-29 13:37:24,206 INFO [train.py:763] (3/8) Epoch 18, batch 350, loss[loss=0.18, simple_loss=0.2918, pruned_loss=0.03409, over 6721.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2689, pruned_loss=0.03725, over 1182319.32 frames.], batch size: 31, lr: 4.14e-04
2022-04-29 13:38:31,273 INFO [train.py:763] (3/8) Epoch 18, batch 400, loss[loss=0.1594, simple_loss=0.2466, pruned_loss=0.03607, over 7064.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2706, pruned_loss=0.03821, over 1234299.15 frames.], batch size: 18, lr: 4.14e-04
2022-04-29 13:39:38,719 INFO [train.py:763] (3/8) Epoch 18, batch 450, loss[loss=0.204, simple_loss=0.3063, pruned_loss=0.05082, over 7338.00 frames.], tot_loss[loss=0.1738, simple_loss=0.271, pruned_loss=0.03825, over 1276357.92 frames.], batch size: 22, lr: 4.14e-04
2022-04-29 13:40:45,466 INFO [train.py:763] (3/8) Epoch 18, batch 500, loss[loss=0.1707, simple_loss=0.2577, pruned_loss=0.04183, over 7129.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2712, pruned_loss=0.03829, over 1306842.96 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:41:52,278 INFO [train.py:763] (3/8) Epoch 18, batch 550, loss[loss=0.1547, simple_loss=0.246, pruned_loss=0.03173, over 7266.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2711, pruned_loss=0.03813, over 1336300.81 frames.], batch size: 17, lr: 4.13e-04
2022-04-29 13:42:57,722 INFO [train.py:763] (3/8) Epoch 18, batch 600, loss[loss=0.1512, simple_loss=0.2463, pruned_loss=0.02812, over 7267.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2711, pruned_loss=0.03799, over 1356946.76 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:44:04,377 INFO [train.py:763] (3/8) Epoch 18, batch 650, loss[loss=0.1571, simple_loss=0.2594, pruned_loss=0.02742, over 7114.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2707, pruned_loss=0.03787, over 1376687.64 frames.], batch size: 21, lr: 4.13e-04
2022-04-29 13:45:09,472 INFO [train.py:763] (3/8) Epoch 18, batch 700, loss[loss=0.2362, simple_loss=0.3149, pruned_loss=0.07876, over 4835.00 frames.], tot_loss[loss=0.174, simple_loss=0.2713, pruned_loss=0.03833, over 1386217.02 frames.], batch size: 52, lr: 4.13e-04
2022-04-29 13:46:15,214 INFO [train.py:763] (3/8) Epoch 18, batch 750, loss[loss=0.1752, simple_loss=0.2703, pruned_loss=0.04006, over 7147.00 frames.], tot_loss[loss=0.173, simple_loss=0.2701, pruned_loss=0.0379, over 1394843.62 frames.], batch size: 19, lr: 4.13e-04
2022-04-29 13:47:20,148 INFO [train.py:763] (3/8) Epoch 18, batch 800, loss[loss=0.1589, simple_loss=0.2671, pruned_loss=0.02541, over 6634.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2714, pruned_loss=0.03858, over 1397616.23 frames.], batch size: 31, lr: 4.13e-04
2022-04-29 13:48:26,402 INFO [train.py:763] (3/8) Epoch 18, batch 850, loss[loss=0.1454, simple_loss=0.2355, pruned_loss=0.02766, over 7069.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2722, pruned_loss=0.03862, over 1405290.93 frames.], batch size: 18, lr: 4.13e-04
2022-04-29 13:49:33,106 INFO [train.py:763] (3/8) Epoch 18, batch 900, loss[loss=0.2029, simple_loss=0.2845, pruned_loss=0.06061, over 6853.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2725, pruned_loss=0.03835, over 1410517.82 frames.], batch size: 15, lr: 4.12e-04
2022-04-29 13:50:38,404 INFO [train.py:763] (3/8) Epoch 18, batch 950, loss[loss=0.1948, simple_loss=0.2939, pruned_loss=0.04788, over 7392.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2727, pruned_loss=0.03851, over 1412929.24 frames.], batch size: 23, lr: 4.12e-04
2022-04-29 13:51:45,513 INFO [train.py:763] (3/8) Epoch 18, batch 1000, loss[loss=0.1642, simple_loss=0.2682, pruned_loss=0.03013, over 7145.00 frames.], tot_loss[loss=0.1751, simple_loss=0.273, pruned_loss=0.03866, over 1420220.78 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:52:52,989 INFO [train.py:763] (3/8) Epoch 18, batch 1050, loss[loss=0.2293, simple_loss=0.3261, pruned_loss=0.06628, over 7307.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2725, pruned_loss=0.03884, over 1417438.83 frames.], batch size: 25, lr: 4.12e-04
2022-04-29 13:53:58,530 INFO [train.py:763] (3/8) Epoch 18, batch 1100, loss[loss=0.1564, simple_loss=0.2579, pruned_loss=0.0274, over 7341.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2713, pruned_loss=0.0386, over 1418592.80 frames.], batch size: 20, lr: 4.12e-04
2022-04-29 13:55:03,937 INFO [train.py:763] (3/8) Epoch 18, batch 1150, loss[loss=0.1933, simple_loss=0.2874, pruned_loss=0.04964, over 7306.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2712, pruned_loss=0.0383, over 1419640.32 frames.], batch size: 24, lr: 4.12e-04
2022-04-29 13:56:09,832 INFO [train.py:763] (3/8) Epoch 18, batch 1200, loss[loss=0.1964, simple_loss=0.2767, pruned_loss=0.05811, over 4976.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2709, pruned_loss=0.03828, over 1413153.00 frames.], batch size: 52, lr: 4.12e-04
2022-04-29 13:57:15,050 INFO [train.py:763] (3/8) Epoch 18, batch 1250, loss[loss=0.1781, simple_loss=0.2853, pruned_loss=0.0354, over 7120.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2701, pruned_loss=0.0377, over 1414814.21 frames.], batch size: 21, lr: 4.12e-04
2022-04-29 13:58:20,082 INFO [train.py:763] (3/8) Epoch 18, batch 1300, loss[loss=0.155, simple_loss=0.2498, pruned_loss=0.03011, over 7157.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2712, pruned_loss=0.03791, over 1415960.04 frames.], batch size: 19, lr: 4.12e-04
2022-04-29 13:59:25,397 INFO [train.py:763] (3/8) Epoch 18, batch 1350, loss[loss=0.214, simple_loss=0.3081, pruned_loss=0.05995, over 7060.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2729, pruned_loss=0.03867, over 1413758.14 frames.], batch size: 28, lr: 4.11e-04
2022-04-29 14:00:32,446 INFO [train.py:763] (3/8) Epoch 18, batch 1400, loss[loss=0.1608, simple_loss=0.2563, pruned_loss=0.03267, over 7075.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2714, pruned_loss=0.03817, over 1412014.56 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:01:39,694 INFO [train.py:763] (3/8) Epoch 18, batch 1450, loss[loss=0.1754, simple_loss=0.2822, pruned_loss=0.03431, over 7308.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2703, pruned_loss=0.03777, over 1418666.51 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:02:45,981 INFO [train.py:763] (3/8) Epoch 18, batch 1500, loss[loss=0.1612, simple_loss=0.2625, pruned_loss=0.02995, over 7259.00 frames.], tot_loss[loss=0.173, simple_loss=0.2706, pruned_loss=0.03766, over 1421962.94 frames.], batch size: 19, lr: 4.11e-04
2022-04-29 14:03:53,118 INFO [train.py:763] (3/8) Epoch 18, batch 1550, loss[loss=0.1937, simple_loss=0.279, pruned_loss=0.05426, over 7414.00 frames.], tot_loss[loss=0.1721, simple_loss=0.27, pruned_loss=0.03713, over 1425203.00 frames.], batch size: 21, lr: 4.11e-04
2022-04-29 14:04:58,306 INFO [train.py:763] (3/8) Epoch 18, batch 1600, loss[loss=0.2095, simple_loss=0.3046, pruned_loss=0.05724, over 7207.00 frames.], tot_loss[loss=0.1724, simple_loss=0.27, pruned_loss=0.03735, over 1424071.09 frames.], batch size: 22, lr: 4.11e-04
2022-04-29 14:06:03,947 INFO [train.py:763] (3/8) Epoch 18, batch 1650, loss[loss=0.1814, simple_loss=0.2756, pruned_loss=0.04358, over 7165.00 frames.], tot_loss[loss=0.1737, simple_loss=0.271, pruned_loss=0.03817, over 1423178.32 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:07:10,557 INFO [train.py:763] (3/8) Epoch 18, batch 1700, loss[loss=0.1698, simple_loss=0.2566, pruned_loss=0.04151, over 7158.00 frames.], tot_loss[loss=0.174, simple_loss=0.2716, pruned_loss=0.03816, over 1423374.98 frames.], batch size: 18, lr: 4.11e-04
2022-04-29 14:08:17,582 INFO [train.py:763] (3/8) Epoch 18, batch 1750, loss[loss=0.1718, simple_loss=0.275, pruned_loss=0.03437, over 7143.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2727, pruned_loss=0.03892, over 1416232.56 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:09:24,694 INFO [train.py:763] (3/8) Epoch 18, batch 1800, loss[loss=0.1715, simple_loss=0.2737, pruned_loss=0.03466, over 7255.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2737, pruned_loss=0.03877, over 1417165.01 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:10:32,225 INFO [train.py:763] (3/8) Epoch 18, batch 1850, loss[loss=0.1907, simple_loss=0.2952, pruned_loss=0.04307, over 7320.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2734, pruned_loss=0.03851, over 1422908.37 frames.], batch size: 24, lr: 4.10e-04
2022-04-29 14:11:39,560 INFO [train.py:763] (3/8) Epoch 18, batch 1900, loss[loss=0.174, simple_loss=0.2786, pruned_loss=0.0347, over 7032.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2732, pruned_loss=0.03871, over 1419659.96 frames.], batch size: 28, lr: 4.10e-04
2022-04-29 14:12:46,672 INFO [train.py:763] (3/8) Epoch 18, batch 1950, loss[loss=0.1397, simple_loss=0.2283, pruned_loss=0.0256, over 7450.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2728, pruned_loss=0.03866, over 1420970.26 frames.], batch size: 17, lr: 4.10e-04
2022-04-29 14:13:51,989 INFO [train.py:763] (3/8) Epoch 18, batch 2000, loss[loss=0.177, simple_loss=0.276, pruned_loss=0.03902, over 7147.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2722, pruned_loss=0.0383, over 1424594.08 frames.], batch size: 20, lr: 4.10e-04
2022-04-29 14:14:57,423 INFO [train.py:763] (3/8) Epoch 18, batch 2050, loss[loss=0.1738, simple_loss=0.2743, pruned_loss=0.03663, over 7294.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2716, pruned_loss=0.0381, over 1424716.97 frames.], batch size: 25, lr: 4.10e-04
2022-04-29 14:16:02,569 INFO [train.py:763] (3/8) Epoch 18, batch 2100, loss[loss=0.1603, simple_loss=0.2614, pruned_loss=0.02954, over 7160.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2718, pruned_loss=0.03786, over 1425190.83 frames.], batch size: 19, lr: 4.10e-04
2022-04-29 14:17:08,133 INFO [train.py:763] (3/8) Epoch 18, batch 2150, loss[loss=0.1812, simple_loss=0.2775, pruned_loss=0.04241, over 7214.00 frames.], tot_loss[loss=0.1733, simple_loss=0.271, pruned_loss=0.03786, over 1421929.59 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:18:13,397 INFO [train.py:763] (3/8) Epoch 18, batch 2200, loss[loss=0.1757, simple_loss=0.2795, pruned_loss=0.03593, over 7104.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2708, pruned_loss=0.03814, over 1426021.95 frames.], batch size: 21, lr: 4.09e-04
2022-04-29 14:19:18,569 INFO [train.py:763] (3/8) Epoch 18, batch 2250, loss[loss=0.1962, simple_loss=0.303, pruned_loss=0.04473, over 6444.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2722, pruned_loss=0.03863, over 1424626.39 frames.], batch size: 38, lr: 4.09e-04
2022-04-29 14:20:23,886 INFO [train.py:763] (3/8) Epoch 18, batch 2300, loss[loss=0.1926, simple_loss=0.294, pruned_loss=0.04564, over 7354.00 frames.], tot_loss[loss=0.175, simple_loss=0.2722, pruned_loss=0.03885, over 1425943.04 frames.], batch size: 23, lr: 4.09e-04
2022-04-29 14:21:28,906 INFO [train.py:763] (3/8) Epoch 18, batch 2350, loss[loss=0.1554, simple_loss=0.2424, pruned_loss=0.03423, over 7271.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2715, pruned_loss=0.0385, over 1423569.03 frames.], batch size: 17, lr: 4.09e-04
2022-04-29 14:22:34,035 INFO [train.py:763] (3/8) Epoch 18, batch 2400, loss[loss=0.1727, simple_loss=0.2733, pruned_loss=0.03601, over 7153.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2718, pruned_loss=0.03855, over 1420309.52 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:23:41,076 INFO [train.py:763] (3/8) Epoch 18, batch 2450, loss[loss=0.187, simple_loss=0.2869, pruned_loss=0.04356, over 7139.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2706, pruned_loss=0.03793, over 1422818.07 frames.], batch size: 20, lr: 4.09e-04
2022-04-29 14:24:46,855 INFO [train.py:763] (3/8) Epoch 18, batch 2500, loss[loss=0.1794, simple_loss=0.2811, pruned_loss=0.03884, over 7190.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2704, pruned_loss=0.0379, over 1421832.64 frames.], batch size: 26, lr: 4.09e-04
2022-04-29 14:25:51,851 INFO [train.py:763] (3/8) Epoch 18, batch 2550, loss[loss=0.2, simple_loss=0.3003, pruned_loss=0.04983, over 7311.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2707, pruned_loss=0.03791, over 1421381.42 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:26:57,010 INFO [train.py:763] (3/8) Epoch 18, batch 2600, loss[loss=0.1736, simple_loss=0.2615, pruned_loss=0.04279, over 6992.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2727, pruned_loss=0.03892, over 1424940.04 frames.], batch size: 16, lr: 4.08e-04
2022-04-29 14:28:02,330 INFO [train.py:763] (3/8) Epoch 18, batch 2650, loss[loss=0.175, simple_loss=0.2742, pruned_loss=0.03794, over 7282.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2729, pruned_loss=0.03914, over 1426794.61 frames.], batch size: 24, lr: 4.08e-04
2022-04-29 14:29:08,095 INFO [train.py:763] (3/8) Epoch 18, batch 2700, loss[loss=0.2086, simple_loss=0.3021, pruned_loss=0.05754, over 7286.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2724, pruned_loss=0.03874, over 1430118.15 frames.], batch size: 25, lr: 4.08e-04
2022-04-29 14:30:14,902 INFO [train.py:763] (3/8) Epoch 18, batch 2750, loss[loss=0.1597, simple_loss=0.2714, pruned_loss=0.02401, over 7417.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03871, over 1429384.45 frames.], batch size: 21, lr: 4.08e-04
2022-04-29 14:31:21,336 INFO [train.py:763] (3/8) Epoch 18, batch 2800, loss[loss=0.1695, simple_loss=0.269, pruned_loss=0.03502, over 7069.00 frames.], tot_loss[loss=0.175, simple_loss=0.2725, pruned_loss=0.03877, over 1430133.53 frames.], batch size: 18, lr: 4.08e-04
2022-04-29 14:32:26,507 INFO [train.py:763] (3/8) Epoch 18, batch 2850, loss[loss=0.1751, simple_loss=0.2752, pruned_loss=0.03753, over 7163.00 frames.], tot_loss[loss=0.1747, simple_loss=0.272, pruned_loss=0.0387, over 1427158.65 frames.], batch size: 19, lr: 4.08e-04
2022-04-29 14:33:31,780 INFO [train.py:763] (3/8) Epoch 18, batch 2900, loss[loss=0.1784, simple_loss=0.2712, pruned_loss=0.04279, over 7145.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2712, pruned_loss=0.03812, over 1424041.20 frames.], batch size: 26, lr: 4.08e-04
2022-04-29 14:34:37,291 INFO [train.py:763] (3/8) Epoch 18, batch 2950, loss[loss=0.1229, simple_loss=0.2169, pruned_loss=0.01448, over 7264.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2715, pruned_loss=0.03789, over 1429958.72 frames.], batch size: 17, lr: 4.08e-04
2022-04-29 14:35:43,262 INFO [train.py:763] (3/8) Epoch 18, batch 3000, loss[loss=0.2298, simple_loss=0.3171, pruned_loss=0.07131, over 5174.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2707, pruned_loss=0.0374, over 1429709.19 frames.], batch size: 52, lr: 4.07e-04
2022-04-29 14:35:43,263 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 14:35:58,559 INFO [train.py:792] (3/8) 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] (3/8) Epoch 18, batch 3050, loss[loss=0.2149, simple_loss=0.3145, pruned_loss=0.05764, over 7181.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2715, pruned_loss=0.03772, over 1431245.90 frames.], batch size: 23, lr: 4.07e-04
2022-04-29 14:38:12,644 INFO [train.py:763] (3/8) Epoch 18, batch 3100, loss[loss=0.1661, simple_loss=0.2755, pruned_loss=0.02833, over 6375.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2717, pruned_loss=0.03754, over 1432083.87 frames.], batch size: 38, lr: 4.07e-04
2022-04-29 14:39:19,391 INFO [train.py:763] (3/8) Epoch 18, batch 3150, loss[loss=0.1513, simple_loss=0.2482, pruned_loss=0.02719, over 7278.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2726, pruned_loss=0.03807, over 1429026.55 frames.], batch size: 18, lr: 4.07e-04
2022-04-29 14:40:26,377 INFO [train.py:763] (3/8) Epoch 18, batch 3200, loss[loss=0.1601, simple_loss=0.262, pruned_loss=0.0291, over 7157.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2719, pruned_loss=0.0379, over 1427260.66 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:41:32,518 INFO [train.py:763] (3/8) Epoch 18, batch 3250, loss[loss=0.1623, simple_loss=0.2712, pruned_loss=0.0267, over 7367.00 frames.], tot_loss[loss=0.174, simple_loss=0.2721, pruned_loss=0.03795, over 1424950.14 frames.], batch size: 19, lr: 4.07e-04
2022-04-29 14:42:37,740 INFO [train.py:763] (3/8) Epoch 18, batch 3300, loss[loss=0.1825, simple_loss=0.2779, pruned_loss=0.04355, over 6262.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2726, pruned_loss=0.03847, over 1424746.07 frames.], batch size: 37, lr: 4.07e-04
2022-04-29 14:43:43,235 INFO [train.py:763] (3/8) Epoch 18, batch 3350, loss[loss=0.1569, simple_loss=0.254, pruned_loss=0.02991, over 7122.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2714, pruned_loss=0.03819, over 1424691.80 frames.], batch size: 21, lr: 4.07e-04
2022-04-29 14:44:48,482 INFO [train.py:763] (3/8) Epoch 18, batch 3400, loss[loss=0.1579, simple_loss=0.2577, pruned_loss=0.02903, over 7280.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2723, pruned_loss=0.03808, over 1425864.94 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:45:53,980 INFO [train.py:763] (3/8) Epoch 18, batch 3450, loss[loss=0.1779, simple_loss=0.2714, pruned_loss=0.04217, over 7358.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2718, pruned_loss=0.03831, over 1421659.28 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:46:59,195 INFO [train.py:763] (3/8) Epoch 18, batch 3500, loss[loss=0.1643, simple_loss=0.2555, pruned_loss=0.03655, over 7268.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2718, pruned_loss=0.03841, over 1423531.75 frames.], batch size: 18, lr: 4.06e-04
2022-04-29 14:48:04,600 INFO [train.py:763] (3/8) Epoch 18, batch 3550, loss[loss=0.1533, simple_loss=0.2361, pruned_loss=0.03532, over 7149.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2713, pruned_loss=0.03825, over 1423941.28 frames.], batch size: 17, lr: 4.06e-04
2022-04-29 14:49:09,816 INFO [train.py:763] (3/8) Epoch 18, batch 3600, loss[loss=0.2043, simple_loss=0.2998, pruned_loss=0.05437, over 7194.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2722, pruned_loss=0.03853, over 1421555.65 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:50:14,978 INFO [train.py:763] (3/8) Epoch 18, batch 3650, loss[loss=0.1487, simple_loss=0.2554, pruned_loss=0.02102, over 7327.00 frames.], tot_loss[loss=0.175, simple_loss=0.2726, pruned_loss=0.03872, over 1414446.81 frames.], batch size: 20, lr: 4.06e-04
2022-04-29 14:51:20,203 INFO [train.py:763] (3/8) Epoch 18, batch 3700, loss[loss=0.1745, simple_loss=0.2793, pruned_loss=0.03487, over 7413.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2734, pruned_loss=0.03892, over 1415911.46 frames.], batch size: 21, lr: 4.06e-04
2022-04-29 14:52:25,582 INFO [train.py:763] (3/8) Epoch 18, batch 3750, loss[loss=0.1982, simple_loss=0.296, pruned_loss=0.05024, over 7380.00 frames.], tot_loss[loss=0.1753, simple_loss=0.273, pruned_loss=0.03873, over 1411839.35 frames.], batch size: 23, lr: 4.06e-04
2022-04-29 14:53:30,893 INFO [train.py:763] (3/8) Epoch 18, batch 3800, loss[loss=0.1603, simple_loss=0.2616, pruned_loss=0.0295, over 7361.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2732, pruned_loss=0.03875, over 1417766.74 frames.], batch size: 19, lr: 4.06e-04
2022-04-29 14:54:36,408 INFO [train.py:763] (3/8) Epoch 18, batch 3850, loss[loss=0.1673, simple_loss=0.2662, pruned_loss=0.03421, over 7176.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2731, pruned_loss=0.03911, over 1415752.93 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:55:41,214 INFO [train.py:763] (3/8) Epoch 18, batch 3900, loss[loss=0.1841, simple_loss=0.2883, pruned_loss=0.03998, over 7121.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2743, pruned_loss=0.03945, over 1413599.68 frames.], batch size: 21, lr: 4.05e-04
2022-04-29 14:56:46,300 INFO [train.py:763] (3/8) Epoch 18, batch 3950, loss[loss=0.1986, simple_loss=0.2869, pruned_loss=0.05514, over 7155.00 frames.], tot_loss[loss=0.176, simple_loss=0.2737, pruned_loss=0.03916, over 1416292.82 frames.], batch size: 18, lr: 4.05e-04
2022-04-29 14:57:51,525 INFO [train.py:763] (3/8) Epoch 18, batch 4000, loss[loss=0.2115, simple_loss=0.2958, pruned_loss=0.06361, over 5488.00 frames.], tot_loss[loss=0.175, simple_loss=0.2727, pruned_loss=0.0387, over 1417832.73 frames.], batch size: 53, lr: 4.05e-04
2022-04-29 14:58:57,191 INFO [train.py:763] (3/8) Epoch 18, batch 4050, loss[loss=0.1447, simple_loss=0.2366, pruned_loss=0.02642, over 7250.00 frames.], tot_loss[loss=0.1743, simple_loss=0.272, pruned_loss=0.03831, over 1416173.23 frames.], batch size: 16, lr: 4.05e-04
2022-04-29 15:00:03,349 INFO [train.py:763] (3/8) Epoch 18, batch 4100, loss[loss=0.1983, simple_loss=0.2921, pruned_loss=0.05223, over 4813.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2718, pruned_loss=0.03846, over 1416572.76 frames.], batch size: 53, lr: 4.05e-04
2022-04-29 15:01:09,076 INFO [train.py:763] (3/8) Epoch 18, batch 4150, loss[loss=0.1844, simple_loss=0.2796, pruned_loss=0.04457, over 7393.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.03796, over 1421702.91 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:02:16,179 INFO [train.py:763] (3/8) Epoch 18, batch 4200, loss[loss=0.1559, simple_loss=0.2544, pruned_loss=0.02876, over 7204.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03769, over 1420133.32 frames.], batch size: 23, lr: 4.05e-04
2022-04-29 15:03:23,609 INFO [train.py:763] (3/8) Epoch 18, batch 4250, loss[loss=0.158, simple_loss=0.2502, pruned_loss=0.03289, over 6827.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2706, pruned_loss=0.03779, over 1419972.05 frames.], batch size: 15, lr: 4.04e-04
2022-04-29 15:04:28,930 INFO [train.py:763] (3/8) Epoch 18, batch 4300, loss[loss=0.1782, simple_loss=0.274, pruned_loss=0.04116, over 7099.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2705, pruned_loss=0.03756, over 1420033.34 frames.], batch size: 26, lr: 4.04e-04
2022-04-29 15:05:35,078 INFO [train.py:763] (3/8) Epoch 18, batch 4350, loss[loss=0.1671, simple_loss=0.2566, pruned_loss=0.03875, over 7158.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2702, pruned_loss=0.03767, over 1417291.25 frames.], batch size: 18, lr: 4.04e-04
2022-04-29 15:06:42,524 INFO [train.py:763] (3/8) Epoch 18, batch 4400, loss[loss=0.2051, simple_loss=0.2978, pruned_loss=0.05621, over 6287.00 frames.], tot_loss[loss=0.174, simple_loss=0.2712, pruned_loss=0.03843, over 1412771.92 frames.], batch size: 37, lr: 4.04e-04
2022-04-29 15:07:48,910 INFO [train.py:763] (3/8) Epoch 18, batch 4450, loss[loss=0.1465, simple_loss=0.2442, pruned_loss=0.02438, over 6778.00 frames.], tot_loss[loss=0.174, simple_loss=0.2706, pruned_loss=0.03869, over 1407423.05 frames.], batch size: 15, lr: 4.04e-04
2022-04-29 15:08:55,423 INFO [train.py:763] (3/8) Epoch 18, batch 4500, loss[loss=0.1828, simple_loss=0.2843, pruned_loss=0.04065, over 7142.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2721, pruned_loss=0.03945, over 1394443.30 frames.], batch size: 20, lr: 4.04e-04
2022-04-29 15:10:01,680 INFO [train.py:763] (3/8) Epoch 18, batch 4550, loss[loss=0.207, simple_loss=0.3124, pruned_loss=0.05081, over 6475.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2717, pruned_loss=0.0397, over 1366970.07 frames.], batch size: 38, lr: 4.04e-04
2022-04-29 15:11:30,592 INFO [train.py:763] (3/8) Epoch 19, batch 0, loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.03154, over 7365.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.03154, over 7365.00 frames.], batch size: 19, lr: 3.94e-04
2022-04-29 15:12:36,740 INFO [train.py:763] (3/8) Epoch 19, batch 50, loss[loss=0.1549, simple_loss=0.2551, pruned_loss=0.02734, over 7282.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2759, pruned_loss=0.03927, over 320425.31 frames.], batch size: 18, lr: 3.94e-04
2022-04-29 15:13:42,678 INFO [train.py:763] (3/8) Epoch 19, batch 100, loss[loss=0.2333, simple_loss=0.3211, pruned_loss=0.07275, over 5046.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2745, pruned_loss=0.03918, over 565831.53 frames.], batch size: 54, lr: 3.94e-04
2022-04-29 15:14:48,875 INFO [train.py:763] (3/8) Epoch 19, batch 150, loss[loss=0.1743, simple_loss=0.282, pruned_loss=0.03329, over 7312.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2759, pruned_loss=0.03928, over 755818.70 frames.], batch size: 21, lr: 3.94e-04
2022-04-29 15:15:54,340 INFO [train.py:763] (3/8) Epoch 19, batch 200, loss[loss=0.1858, simple_loss=0.2992, pruned_loss=0.03622, over 7344.00 frames.], tot_loss[loss=0.176, simple_loss=0.2747, pruned_loss=0.03864, over 903378.55 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:17:00,298 INFO [train.py:763] (3/8) Epoch 19, batch 250, loss[loss=0.1786, simple_loss=0.2781, pruned_loss=0.03954, over 7334.00 frames.], tot_loss[loss=0.1738, simple_loss=0.2727, pruned_loss=0.03745, over 1022482.91 frames.], batch size: 22, lr: 3.93e-04
2022-04-29 15:18:06,651 INFO [train.py:763] (3/8) Epoch 19, batch 300, loss[loss=0.2004, simple_loss=0.2965, pruned_loss=0.05221, over 7202.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2728, pruned_loss=0.03733, over 1112062.55 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:19:12,752 INFO [train.py:763] (3/8) Epoch 19, batch 350, loss[loss=0.192, simple_loss=0.2862, pruned_loss=0.04893, over 7151.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2733, pruned_loss=0.03787, over 1184474.74 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:20:18,121 INFO [train.py:763] (3/8) Epoch 19, batch 400, loss[loss=0.1808, simple_loss=0.289, pruned_loss=0.03628, over 7158.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2728, pruned_loss=0.03771, over 1238001.23 frames.], batch size: 20, lr: 3.93e-04
2022-04-29 15:21:23,457 INFO [train.py:763] (3/8) Epoch 19, batch 450, loss[loss=0.1891, simple_loss=0.2897, pruned_loss=0.04427, over 7387.00 frames.], tot_loss[loss=0.174, simple_loss=0.273, pruned_loss=0.03746, over 1276364.13 frames.], batch size: 23, lr: 3.93e-04
2022-04-29 15:22:28,664 INFO [train.py:763] (3/8) Epoch 19, batch 500, loss[loss=0.1651, simple_loss=0.2667, pruned_loss=0.03172, over 7220.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2734, pruned_loss=0.03768, over 1308156.20 frames.], batch size: 21, lr: 3.93e-04
2022-04-29 15:23:34,245 INFO [train.py:763] (3/8) Epoch 19, batch 550, loss[loss=0.1816, simple_loss=0.2853, pruned_loss=0.03897, over 6732.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2716, pruned_loss=0.03688, over 1334495.93 frames.], batch size: 31, lr: 3.93e-04
2022-04-29 15:24:40,466 INFO [train.py:763] (3/8) Epoch 19, batch 600, loss[loss=0.1539, simple_loss=0.2486, pruned_loss=0.02963, over 7171.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2702, pruned_loss=0.03656, over 1355818.49 frames.], batch size: 18, lr: 3.93e-04
2022-04-29 15:25:45,941 INFO [train.py:763] (3/8) Epoch 19, batch 650, loss[loss=0.1852, simple_loss=0.2763, pruned_loss=0.0471, over 7170.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2703, pruned_loss=0.03695, over 1369709.84 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:26:51,169 INFO [train.py:763] (3/8) Epoch 19, batch 700, loss[loss=0.1937, simple_loss=0.2966, pruned_loss=0.04537, over 7223.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2711, pruned_loss=0.0369, over 1383019.65 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:27:56,783 INFO [train.py:763] (3/8) Epoch 19, batch 750, loss[loss=0.2348, simple_loss=0.3387, pruned_loss=0.06548, over 7297.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2709, pruned_loss=0.03691, over 1393862.55 frames.], batch size: 25, lr: 3.92e-04
2022-04-29 15:29:03,457 INFO [train.py:763] (3/8) Epoch 19, batch 800, loss[loss=0.1683, simple_loss=0.2615, pruned_loss=0.03751, over 7404.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2703, pruned_loss=0.03692, over 1403185.82 frames.], batch size: 18, lr: 3.92e-04
2022-04-29 15:30:19,515 INFO [train.py:763] (3/8) Epoch 19, batch 850, loss[loss=0.1673, simple_loss=0.2723, pruned_loss=0.03115, over 7057.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03717, over 1410997.00 frames.], batch size: 28, lr: 3.92e-04
2022-04-29 15:31:25,289 INFO [train.py:763] (3/8) Epoch 19, batch 900, loss[loss=0.1498, simple_loss=0.2504, pruned_loss=0.02461, over 7350.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2698, pruned_loss=0.03687, over 1416491.09 frames.], batch size: 19, lr: 3.92e-04
2022-04-29 15:32:30,745 INFO [train.py:763] (3/8) Epoch 19, batch 950, loss[loss=0.1604, simple_loss=0.263, pruned_loss=0.02891, over 7236.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2705, pruned_loss=0.03721, over 1419624.54 frames.], batch size: 20, lr: 3.92e-04
2022-04-29 15:33:36,032 INFO [train.py:763] (3/8) Epoch 19, batch 1000, loss[loss=0.2078, simple_loss=0.3056, pruned_loss=0.05499, over 7294.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2711, pruned_loss=0.03737, over 1420716.41 frames.], batch size: 24, lr: 3.92e-04
2022-04-29 15:34:41,368 INFO [train.py:763] (3/8) Epoch 19, batch 1050, loss[loss=0.1903, simple_loss=0.2892, pruned_loss=0.04575, over 7220.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2715, pruned_loss=0.03785, over 1419905.86 frames.], batch size: 22, lr: 3.92e-04
2022-04-29 15:35:47,010 INFO [train.py:763] (3/8) Epoch 19, batch 1100, loss[loss=0.1987, simple_loss=0.2998, pruned_loss=0.04884, over 7200.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2713, pruned_loss=0.03781, over 1415504.83 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:36:52,330 INFO [train.py:763] (3/8) Epoch 19, batch 1150, loss[loss=0.1917, simple_loss=0.2888, pruned_loss=0.04731, over 7315.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2721, pruned_loss=0.03786, over 1419971.63 frames.], batch size: 24, lr: 3.91e-04
2022-04-29 15:38:08,754 INFO [train.py:763] (3/8) Epoch 19, batch 1200, loss[loss=0.1865, simple_loss=0.2816, pruned_loss=0.04565, over 7347.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2708, pruned_loss=0.03725, over 1424822.70 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:39:14,189 INFO [train.py:763] (3/8) Epoch 19, batch 1250, loss[loss=0.1433, simple_loss=0.2444, pruned_loss=0.02106, over 7151.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2705, pruned_loss=0.03731, over 1425595.71 frames.], batch size: 17, lr: 3.91e-04
2022-04-29 15:40:19,874 INFO [train.py:763] (3/8) Epoch 19, batch 1300, loss[loss=0.1841, simple_loss=0.286, pruned_loss=0.0411, over 7124.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2697, pruned_loss=0.03697, over 1427376.46 frames.], batch size: 21, lr: 3.91e-04
2022-04-29 15:41:25,078 INFO [train.py:763] (3/8) Epoch 19, batch 1350, loss[loss=0.1942, simple_loss=0.2898, pruned_loss=0.04929, over 7211.00 frames.], tot_loss[loss=0.1729, simple_loss=0.271, pruned_loss=0.03735, over 1429519.41 frames.], batch size: 22, lr: 3.91e-04
2022-04-29 15:42:30,862 INFO [train.py:763] (3/8) Epoch 19, batch 1400, loss[loss=0.1878, simple_loss=0.2848, pruned_loss=0.04543, over 7184.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2713, pruned_loss=0.03756, over 1431087.93 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:43:46,244 INFO [train.py:763] (3/8) Epoch 19, batch 1450, loss[loss=0.1663, simple_loss=0.27, pruned_loss=0.03125, over 7178.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2715, pruned_loss=0.03756, over 1429092.86 frames.], batch size: 26, lr: 3.91e-04
2022-04-29 15:45:09,719 INFO [train.py:763] (3/8) Epoch 19, batch 1500, loss[loss=0.1933, simple_loss=0.2972, pruned_loss=0.04472, over 7369.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2725, pruned_loss=0.03794, over 1427251.71 frames.], batch size: 23, lr: 3.91e-04
2022-04-29 15:46:15,426 INFO [train.py:763] (3/8) Epoch 19, batch 1550, loss[loss=0.1739, simple_loss=0.2721, pruned_loss=0.0378, over 7438.00 frames.], tot_loss[loss=0.174, simple_loss=0.272, pruned_loss=0.03803, over 1429980.88 frames.], batch size: 20, lr: 3.91e-04
2022-04-29 15:47:30,075 INFO [train.py:763] (3/8) Epoch 19, batch 1600, loss[loss=0.1824, simple_loss=0.283, pruned_loss=0.04097, over 7347.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2726, pruned_loss=0.03818, over 1424679.40 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:48:53,934 INFO [train.py:763] (3/8) Epoch 19, batch 1650, loss[loss=0.204, simple_loss=0.3005, pruned_loss=0.05373, over 7204.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2725, pruned_loss=0.03808, over 1421116.46 frames.], batch size: 23, lr: 3.90e-04
2022-04-29 15:50:08,826 INFO [train.py:763] (3/8) Epoch 19, batch 1700, loss[loss=0.1503, simple_loss=0.2541, pruned_loss=0.02329, over 7163.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2718, pruned_loss=0.0378, over 1419413.48 frames.], batch size: 19, lr: 3.90e-04
2022-04-29 15:51:14,400 INFO [train.py:763] (3/8) Epoch 19, batch 1750, loss[loss=0.1695, simple_loss=0.2701, pruned_loss=0.03451, over 7339.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2722, pruned_loss=0.03764, over 1424793.18 frames.], batch size: 22, lr: 3.90e-04
2022-04-29 15:52:19,998 INFO [train.py:763] (3/8) Epoch 19, batch 1800, loss[loss=0.2013, simple_loss=0.3062, pruned_loss=0.04822, over 7311.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2723, pruned_loss=0.03775, over 1424065.19 frames.], batch size: 25, lr: 3.90e-04
2022-04-29 15:53:25,556 INFO [train.py:763] (3/8) Epoch 19, batch 1850, loss[loss=0.1606, simple_loss=0.2532, pruned_loss=0.03405, over 7065.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2724, pruned_loss=0.03806, over 1426783.48 frames.], batch size: 18, lr: 3.90e-04
2022-04-29 15:54:30,870 INFO [train.py:763] (3/8) Epoch 19, batch 1900, loss[loss=0.1548, simple_loss=0.2501, pruned_loss=0.02981, over 7233.00 frames.], tot_loss[loss=0.174, simple_loss=0.2723, pruned_loss=0.03789, over 1427894.94 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:55:38,244 INFO [train.py:763] (3/8) Epoch 19, batch 1950, loss[loss=0.1691, simple_loss=0.2681, pruned_loss=0.03506, over 6320.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2704, pruned_loss=0.03724, over 1428296.20 frames.], batch size: 37, lr: 3.90e-04
2022-04-29 15:56:45,558 INFO [train.py:763] (3/8) Epoch 19, batch 2000, loss[loss=0.1775, simple_loss=0.275, pruned_loss=0.04005, over 7228.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2695, pruned_loss=0.03674, over 1429189.86 frames.], batch size: 20, lr: 3.90e-04
2022-04-29 15:57:52,841 INFO [train.py:763] (3/8) Epoch 19, batch 2050, loss[loss=0.1592, simple_loss=0.258, pruned_loss=0.03021, over 7223.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2698, pruned_loss=0.03749, over 1428800.86 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 15:58:58,691 INFO [train.py:763] (3/8) Epoch 19, batch 2100, loss[loss=0.173, simple_loss=0.2683, pruned_loss=0.03886, over 7429.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2703, pruned_loss=0.03776, over 1431293.24 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:00:05,504 INFO [train.py:763] (3/8) Epoch 19, batch 2150, loss[loss=0.1934, simple_loss=0.2919, pruned_loss=0.04739, over 7207.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2706, pruned_loss=0.03789, over 1425269.15 frames.], batch size: 22, lr: 3.89e-04
2022-04-29 16:01:11,302 INFO [train.py:763] (3/8) Epoch 19, batch 2200, loss[loss=0.1708, simple_loss=0.2642, pruned_loss=0.03869, over 7241.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2695, pruned_loss=0.03745, over 1420999.13 frames.], batch size: 16, lr: 3.89e-04
2022-04-29 16:02:17,296 INFO [train.py:763] (3/8) Epoch 19, batch 2250, loss[loss=0.1899, simple_loss=0.2791, pruned_loss=0.05036, over 7144.00 frames.], tot_loss[loss=0.1729, simple_loss=0.27, pruned_loss=0.03785, over 1423220.36 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:03:23,074 INFO [train.py:763] (3/8) Epoch 19, batch 2300, loss[loss=0.1878, simple_loss=0.2895, pruned_loss=0.04302, over 7399.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2697, pruned_loss=0.03744, over 1424661.07 frames.], batch size: 23, lr: 3.89e-04
2022-04-29 16:04:28,767 INFO [train.py:763] (3/8) Epoch 19, batch 2350, loss[loss=0.2078, simple_loss=0.296, pruned_loss=0.05977, over 7314.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2699, pruned_loss=0.03759, over 1422342.00 frames.], batch size: 21, lr: 3.89e-04
2022-04-29 16:05:34,126 INFO [train.py:763] (3/8) Epoch 19, batch 2400, loss[loss=0.1807, simple_loss=0.2747, pruned_loss=0.04331, over 7435.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2695, pruned_loss=0.03741, over 1423468.61 frames.], batch size: 20, lr: 3.89e-04
2022-04-29 16:06:39,693 INFO [train.py:763] (3/8) Epoch 19, batch 2450, loss[loss=0.1841, simple_loss=0.281, pruned_loss=0.04361, over 7056.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2688, pruned_loss=0.03725, over 1425993.58 frames.], batch size: 28, lr: 3.89e-04
2022-04-29 16:07:45,461 INFO [train.py:763] (3/8) Epoch 19, batch 2500, loss[loss=0.1925, simple_loss=0.2907, pruned_loss=0.04717, over 7193.00 frames.], tot_loss[loss=0.171, simple_loss=0.2681, pruned_loss=0.03697, over 1424728.20 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:08:50,995 INFO [train.py:763] (3/8) Epoch 19, batch 2550, loss[loss=0.1762, simple_loss=0.2717, pruned_loss=0.04034, over 7340.00 frames.], tot_loss[loss=0.172, simple_loss=0.2694, pruned_loss=0.03728, over 1424077.34 frames.], batch size: 20, lr: 3.88e-04
2022-04-29 16:09:56,807 INFO [train.py:763] (3/8) Epoch 19, batch 2600, loss[loss=0.1985, simple_loss=0.2932, pruned_loss=0.05187, over 6742.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2707, pruned_loss=0.03791, over 1425103.51 frames.], batch size: 31, lr: 3.88e-04
2022-04-29 16:11:03,364 INFO [train.py:763] (3/8) Epoch 19, batch 2650, loss[loss=0.1521, simple_loss=0.2375, pruned_loss=0.0333, over 7007.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2702, pruned_loss=0.03777, over 1426435.02 frames.], batch size: 16, lr: 3.88e-04
2022-04-29 16:12:10,010 INFO [train.py:763] (3/8) Epoch 19, batch 2700, loss[loss=0.1824, simple_loss=0.2824, pruned_loss=0.04122, over 7379.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2699, pruned_loss=0.03751, over 1427261.50 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:13:17,137 INFO [train.py:763] (3/8) Epoch 19, batch 2750, loss[loss=0.1731, simple_loss=0.2715, pruned_loss=0.03733, over 7201.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2703, pruned_loss=0.03744, over 1425725.17 frames.], batch size: 23, lr: 3.88e-04
2022-04-29 16:14:22,711 INFO [train.py:763] (3/8) Epoch 19, batch 2800, loss[loss=0.1587, simple_loss=0.2593, pruned_loss=0.02906, over 7167.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2708, pruned_loss=0.03733, over 1430028.44 frames.], batch size: 18, lr: 3.88e-04
2022-04-29 16:15:28,760 INFO [train.py:763] (3/8) Epoch 19, batch 2850, loss[loss=0.1865, simple_loss=0.2864, pruned_loss=0.04332, over 7407.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2703, pruned_loss=0.03697, over 1432696.38 frames.], batch size: 21, lr: 3.88e-04
2022-04-29 16:16:34,845 INFO [train.py:763] (3/8) Epoch 19, batch 2900, loss[loss=0.1699, simple_loss=0.2726, pruned_loss=0.03364, over 7171.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2697, pruned_loss=0.03693, over 1428095.01 frames.], batch size: 26, lr: 3.88e-04
2022-04-29 16:17:40,405 INFO [train.py:763] (3/8) Epoch 19, batch 2950, loss[loss=0.167, simple_loss=0.2707, pruned_loss=0.03162, over 7231.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2706, pruned_loss=0.03712, over 1431660.54 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:18:45,955 INFO [train.py:763] (3/8) Epoch 19, batch 3000, loss[loss=0.2097, simple_loss=0.306, pruned_loss=0.05673, over 7375.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2715, pruned_loss=0.03753, over 1430393.27 frames.], batch size: 23, lr: 3.87e-04
2022-04-29 16:18:45,956 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 16:19:01,554 INFO [train.py:792] (3/8) Epoch 19, validation: loss=0.1668, simple_loss=0.2663, pruned_loss=0.03363, over 698248.00 frames.
2022-04-29 16:20:06,919 INFO [train.py:763] (3/8) Epoch 19, batch 3050, loss[loss=0.1619, simple_loss=0.2695, pruned_loss=0.02715, over 7162.00 frames.], tot_loss[loss=0.173, simple_loss=0.2713, pruned_loss=0.03739, over 1431960.84 frames.], batch size: 19, lr: 3.87e-04
2022-04-29 16:21:12,180 INFO [train.py:763] (3/8) Epoch 19, batch 3100, loss[loss=0.1505, simple_loss=0.2459, pruned_loss=0.02752, over 7117.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2706, pruned_loss=0.03683, over 1430745.76 frames.], batch size: 21, lr: 3.87e-04
2022-04-29 16:22:17,531 INFO [train.py:763] (3/8) Epoch 19, batch 3150, loss[loss=0.1481, simple_loss=0.2373, pruned_loss=0.02943, over 7273.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2708, pruned_loss=0.03689, over 1431303.34 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:23:23,020 INFO [train.py:763] (3/8) Epoch 19, batch 3200, loss[loss=0.149, simple_loss=0.2475, pruned_loss=0.02524, over 6825.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03691, over 1431831.60 frames.], batch size: 31, lr: 3.87e-04
2022-04-29 16:24:28,065 INFO [train.py:763] (3/8) Epoch 19, batch 3250, loss[loss=0.1591, simple_loss=0.2514, pruned_loss=0.03337, over 7061.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2698, pruned_loss=0.03674, over 1428280.45 frames.], batch size: 18, lr: 3.87e-04
2022-04-29 16:25:34,721 INFO [train.py:763] (3/8) Epoch 19, batch 3300, loss[loss=0.1682, simple_loss=0.262, pruned_loss=0.03718, over 7128.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2699, pruned_loss=0.03658, over 1426539.68 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:26:41,782 INFO [train.py:763] (3/8) Epoch 19, batch 3350, loss[loss=0.1995, simple_loss=0.2925, pruned_loss=0.05331, over 7151.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2692, pruned_loss=0.03664, over 1427117.15 frames.], batch size: 20, lr: 3.87e-04
2022-04-29 16:27:47,541 INFO [train.py:763] (3/8) Epoch 19, batch 3400, loss[loss=0.146, simple_loss=0.2414, pruned_loss=0.02536, over 7253.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2686, pruned_loss=0.03644, over 1426361.18 frames.], batch size: 17, lr: 3.87e-04
2022-04-29 16:28:53,014 INFO [train.py:763] (3/8) Epoch 19, batch 3450, loss[loss=0.1646, simple_loss=0.2722, pruned_loss=0.02848, over 7230.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2697, pruned_loss=0.03664, over 1424989.06 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:29:58,521 INFO [train.py:763] (3/8) Epoch 19, batch 3500, loss[loss=0.1798, simple_loss=0.2795, pruned_loss=0.04008, over 7262.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2703, pruned_loss=0.03662, over 1424010.44 frames.], batch size: 19, lr: 3.86e-04
2022-04-29 16:31:03,659 INFO [train.py:763] (3/8) Epoch 19, batch 3550, loss[loss=0.1649, simple_loss=0.2701, pruned_loss=0.02986, over 7112.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03688, over 1426603.08 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:32:09,190 INFO [train.py:763] (3/8) Epoch 19, batch 3600, loss[loss=0.1892, simple_loss=0.2882, pruned_loss=0.04509, over 7226.00 frames.], tot_loss[loss=0.1719, simple_loss=0.27, pruned_loss=0.0369, over 1429374.72 frames.], batch size: 23, lr: 3.86e-04
2022-04-29 16:33:15,437 INFO [train.py:763] (3/8) Epoch 19, batch 3650, loss[loss=0.1858, simple_loss=0.2925, pruned_loss=0.03951, over 7317.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2699, pruned_loss=0.03687, over 1430884.40 frames.], batch size: 21, lr: 3.86e-04
2022-04-29 16:34:21,091 INFO [train.py:763] (3/8) Epoch 19, batch 3700, loss[loss=0.1596, simple_loss=0.2535, pruned_loss=0.03288, over 7164.00 frames.], tot_loss[loss=0.1716, simple_loss=0.27, pruned_loss=0.03662, over 1432903.92 frames.], batch size: 18, lr: 3.86e-04
2022-04-29 16:35:26,769 INFO [train.py:763] (3/8) Epoch 19, batch 3750, loss[loss=0.1861, simple_loss=0.2835, pruned_loss=0.04428, over 7067.00 frames.], tot_loss[loss=0.171, simple_loss=0.2692, pruned_loss=0.03643, over 1427653.18 frames.], batch size: 28, lr: 3.86e-04
2022-04-29 16:36:32,305 INFO [train.py:763] (3/8) Epoch 19, batch 3800, loss[loss=0.1712, simple_loss=0.2665, pruned_loss=0.03796, over 7332.00 frames.], tot_loss[loss=0.1713, simple_loss=0.269, pruned_loss=0.03686, over 1423407.11 frames.], batch size: 20, lr: 3.86e-04
2022-04-29 16:37:37,905 INFO [train.py:763] (3/8) Epoch 19, batch 3850, loss[loss=0.1633, simple_loss=0.2616, pruned_loss=0.03252, over 7267.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2686, pruned_loss=0.03663, over 1421281.58 frames.], batch size: 17, lr: 3.86e-04
2022-04-29 16:38:44,165 INFO [train.py:763] (3/8) Epoch 19, batch 3900, loss[loss=0.1776, simple_loss=0.2828, pruned_loss=0.03616, over 7116.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2703, pruned_loss=0.03745, over 1418286.78 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:39:50,747 INFO [train.py:763] (3/8) Epoch 19, batch 3950, loss[loss=0.1751, simple_loss=0.2749, pruned_loss=0.03767, over 7331.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2702, pruned_loss=0.0373, over 1411918.27 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:40:57,111 INFO [train.py:763] (3/8) Epoch 19, batch 4000, loss[loss=0.1495, simple_loss=0.2442, pruned_loss=0.02739, over 7158.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2692, pruned_loss=0.03679, over 1409716.56 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:42:03,325 INFO [train.py:763] (3/8) Epoch 19, batch 4050, loss[loss=0.1653, simple_loss=0.2676, pruned_loss=0.03146, over 7325.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2696, pruned_loss=0.03708, over 1407387.10 frames.], batch size: 20, lr: 3.85e-04
2022-04-29 16:43:09,189 INFO [train.py:763] (3/8) Epoch 19, batch 4100, loss[loss=0.1521, simple_loss=0.245, pruned_loss=0.02961, over 7280.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2688, pruned_loss=0.03701, over 1407576.40 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:44:14,859 INFO [train.py:763] (3/8) Epoch 19, batch 4150, loss[loss=0.1822, simple_loss=0.2678, pruned_loss=0.04825, over 7059.00 frames.], tot_loss[loss=0.17, simple_loss=0.2676, pruned_loss=0.0362, over 1411564.58 frames.], batch size: 18, lr: 3.85e-04
2022-04-29 16:45:20,203 INFO [train.py:763] (3/8) Epoch 19, batch 4200, loss[loss=0.1593, simple_loss=0.2448, pruned_loss=0.03693, over 6782.00 frames.], tot_loss[loss=0.17, simple_loss=0.2678, pruned_loss=0.03615, over 1405022.54 frames.], batch size: 15, lr: 3.85e-04
2022-04-29 16:46:26,001 INFO [train.py:763] (3/8) Epoch 19, batch 4250, loss[loss=0.2049, simple_loss=0.2999, pruned_loss=0.05493, over 7176.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2671, pruned_loss=0.03642, over 1403653.56 frames.], batch size: 23, lr: 3.85e-04
2022-04-29 16:47:31,494 INFO [train.py:763] (3/8) Epoch 19, batch 4300, loss[loss=0.1868, simple_loss=0.294, pruned_loss=0.03979, over 7221.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2686, pruned_loss=0.03714, over 1401154.02 frames.], batch size: 21, lr: 3.85e-04
2022-04-29 16:48:37,207 INFO [train.py:763] (3/8) Epoch 19, batch 4350, loss[loss=0.2338, simple_loss=0.3139, pruned_loss=0.07692, over 5282.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2668, pruned_loss=0.03664, over 1404627.16 frames.], batch size: 52, lr: 3.84e-04
2022-04-29 16:49:42,591 INFO [train.py:763] (3/8) Epoch 19, batch 4400, loss[loss=0.1702, simple_loss=0.2755, pruned_loss=0.0324, over 7156.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2667, pruned_loss=0.03651, over 1398267.33 frames.], batch size: 19, lr: 3.84e-04
2022-04-29 16:50:47,790 INFO [train.py:763] (3/8) Epoch 19, batch 4450, loss[loss=0.1708, simple_loss=0.2508, pruned_loss=0.04544, over 6842.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2668, pruned_loss=0.03676, over 1389200.52 frames.], batch size: 15, lr: 3.84e-04
2022-04-29 16:51:52,273 INFO [train.py:763] (3/8) Epoch 19, batch 4500, loss[loss=0.2116, simple_loss=0.3148, pruned_loss=0.05421, over 7186.00 frames.], tot_loss[loss=0.1718, simple_loss=0.269, pruned_loss=0.03727, over 1383858.65 frames.], batch size: 23, lr: 3.84e-04
2022-04-29 16:52:57,055 INFO [train.py:763] (3/8) Epoch 19, batch 4550, loss[loss=0.1779, simple_loss=0.2779, pruned_loss=0.039, over 6567.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2717, pruned_loss=0.0389, over 1339574.56 frames.], batch size: 39, lr: 3.84e-04
2022-04-29 16:54:25,839 INFO [train.py:763] (3/8) Epoch 20, batch 0, loss[loss=0.1853, simple_loss=0.2745, pruned_loss=0.04808, over 7010.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2745, pruned_loss=0.04808, over 7010.00 frames.], batch size: 16, lr: 3.75e-04
2022-04-29 16:55:32,593 INFO [train.py:763] (3/8) Epoch 20, batch 50, loss[loss=0.1632, simple_loss=0.2643, pruned_loss=0.03106, over 6287.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2715, pruned_loss=0.03744, over 322962.62 frames.], batch size: 37, lr: 3.75e-04
2022-04-29 16:56:38,001 INFO [train.py:763] (3/8) Epoch 20, batch 100, loss[loss=0.1499, simple_loss=0.2367, pruned_loss=0.0315, over 6801.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2708, pruned_loss=0.03736, over 566916.91 frames.], batch size: 15, lr: 3.75e-04
2022-04-29 16:57:44,563 INFO [train.py:763] (3/8) Epoch 20, batch 150, loss[loss=0.1486, simple_loss=0.2376, pruned_loss=0.02983, over 7166.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2707, pruned_loss=0.03683, over 755587.93 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 16:58:49,751 INFO [train.py:763] (3/8) Epoch 20, batch 200, loss[loss=0.1726, simple_loss=0.2795, pruned_loss=0.03284, over 6839.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2717, pruned_loss=0.03741, over 900047.27 frames.], batch size: 31, lr: 3.75e-04
2022-04-29 16:59:55,578 INFO [train.py:763] (3/8) Epoch 20, batch 250, loss[loss=0.1641, simple_loss=0.2563, pruned_loss=0.0359, over 7162.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2705, pruned_loss=0.03716, over 1012645.53 frames.], batch size: 19, lr: 3.75e-04
2022-04-29 17:01:00,762 INFO [train.py:763] (3/8) Epoch 20, batch 300, loss[loss=0.1464, simple_loss=0.2467, pruned_loss=0.02305, over 7270.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2699, pruned_loss=0.0364, over 1101309.98 frames.], batch size: 18, lr: 3.75e-04
2022-04-29 17:02:05,606 INFO [train.py:763] (3/8) Epoch 20, batch 350, loss[loss=0.1428, simple_loss=0.2464, pruned_loss=0.01964, over 7269.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2709, pruned_loss=0.03617, over 1169480.81 frames.], batch size: 19, lr: 3.74e-04
2022-04-29 17:03:10,956 INFO [train.py:763] (3/8) Epoch 20, batch 400, loss[loss=0.1565, simple_loss=0.26, pruned_loss=0.02646, over 7070.00 frames.], tot_loss[loss=0.171, simple_loss=0.27, pruned_loss=0.03598, over 1228974.79 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:04:16,933 INFO [train.py:763] (3/8) Epoch 20, batch 450, loss[loss=0.1689, simple_loss=0.2659, pruned_loss=0.03592, over 7066.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2695, pruned_loss=0.036, over 1271267.59 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:05:22,374 INFO [train.py:763] (3/8) Epoch 20, batch 500, loss[loss=0.1817, simple_loss=0.2773, pruned_loss=0.04307, over 7016.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2691, pruned_loss=0.03599, over 1309660.49 frames.], batch size: 28, lr: 3.74e-04
2022-04-29 17:06:27,715 INFO [train.py:763] (3/8) Epoch 20, batch 550, loss[loss=0.1488, simple_loss=0.2428, pruned_loss=0.02746, over 6764.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2686, pruned_loss=0.03581, over 1335918.90 frames.], batch size: 15, lr: 3.74e-04
2022-04-29 17:07:34,455 INFO [train.py:763] (3/8) Epoch 20, batch 600, loss[loss=0.2161, simple_loss=0.3153, pruned_loss=0.05847, over 7199.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2685, pruned_loss=0.03606, over 1355588.17 frames.], batch size: 22, lr: 3.74e-04
2022-04-29 17:08:41,618 INFO [train.py:763] (3/8) Epoch 20, batch 650, loss[loss=0.1424, simple_loss=0.2287, pruned_loss=0.02806, over 7140.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2671, pruned_loss=0.03573, over 1369801.87 frames.], batch size: 17, lr: 3.74e-04
2022-04-29 17:09:47,492 INFO [train.py:763] (3/8) Epoch 20, batch 700, loss[loss=0.1882, simple_loss=0.3009, pruned_loss=0.03774, over 7232.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2677, pruned_loss=0.03593, over 1379659.16 frames.], batch size: 20, lr: 3.74e-04
2022-04-29 17:10:53,616 INFO [train.py:763] (3/8) Epoch 20, batch 750, loss[loss=0.1688, simple_loss=0.2615, pruned_loss=0.03805, over 7416.00 frames.], tot_loss[loss=0.171, simple_loss=0.2686, pruned_loss=0.03671, over 1384685.65 frames.], batch size: 18, lr: 3.74e-04
2022-04-29 17:11:58,917 INFO [train.py:763] (3/8) Epoch 20, batch 800, loss[loss=0.1953, simple_loss=0.29, pruned_loss=0.05031, over 7232.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2682, pruned_loss=0.03638, over 1382902.41 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:13:05,456 INFO [train.py:763] (3/8) Epoch 20, batch 850, loss[loss=0.1778, simple_loss=0.2811, pruned_loss=0.03726, over 7318.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2672, pruned_loss=0.03617, over 1389713.39 frames.], batch size: 25, lr: 3.73e-04
2022-04-29 17:14:10,905 INFO [train.py:763] (3/8) Epoch 20, batch 900, loss[loss=0.192, simple_loss=0.2831, pruned_loss=0.05043, over 7232.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2671, pruned_loss=0.03625, over 1398558.05 frames.], batch size: 20, lr: 3.73e-04
2022-04-29 17:15:15,945 INFO [train.py:763] (3/8) Epoch 20, batch 950, loss[loss=0.1632, simple_loss=0.2664, pruned_loss=0.03001, over 7347.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2676, pruned_loss=0.03604, over 1405355.09 frames.], batch size: 22, lr: 3.73e-04
2022-04-29 17:16:21,949 INFO [train.py:763] (3/8) Epoch 20, batch 1000, loss[loss=0.1857, simple_loss=0.2951, pruned_loss=0.03812, over 7209.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2687, pruned_loss=0.0364, over 1405284.02 frames.], batch size: 23, lr: 3.73e-04
2022-04-29 17:17:26,877 INFO [train.py:763] (3/8) Epoch 20, batch 1050, loss[loss=0.1607, simple_loss=0.2739, pruned_loss=0.02372, over 7399.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2694, pruned_loss=0.03616, over 1406081.02 frames.], batch size: 21, lr: 3.73e-04
2022-04-29 17:18:32,319 INFO [train.py:763] (3/8) Epoch 20, batch 1100, loss[loss=0.1747, simple_loss=0.2621, pruned_loss=0.04366, over 6810.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2687, pruned_loss=0.0362, over 1406639.41 frames.], batch size: 15, lr: 3.73e-04
2022-04-29 17:19:37,613 INFO [train.py:763] (3/8) Epoch 20, batch 1150, loss[loss=0.2024, simple_loss=0.301, pruned_loss=0.0519, over 7325.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2689, pruned_loss=0.03594, over 1412161.92 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:20:42,597 INFO [train.py:763] (3/8) Epoch 20, batch 1200, loss[loss=0.1531, simple_loss=0.2477, pruned_loss=0.02923, over 7281.00 frames.], tot_loss[loss=0.171, simple_loss=0.2698, pruned_loss=0.0361, over 1414390.79 frames.], batch size: 18, lr: 3.73e-04
2022-04-29 17:21:47,930 INFO [train.py:763] (3/8) Epoch 20, batch 1250, loss[loss=0.1828, simple_loss=0.2866, pruned_loss=0.03949, over 7297.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2695, pruned_loss=0.03621, over 1417019.86 frames.], batch size: 24, lr: 3.73e-04
2022-04-29 17:22:53,224 INFO [train.py:763] (3/8) Epoch 20, batch 1300, loss[loss=0.1625, simple_loss=0.2522, pruned_loss=0.03638, over 7068.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2696, pruned_loss=0.03663, over 1415810.98 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:23:59,050 INFO [train.py:763] (3/8) Epoch 20, batch 1350, loss[loss=0.2011, simple_loss=0.303, pruned_loss=0.04956, over 7341.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2692, pruned_loss=0.03628, over 1422957.07 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:25:04,571 INFO [train.py:763] (3/8) Epoch 20, batch 1400, loss[loss=0.194, simple_loss=0.2949, pruned_loss=0.04659, over 7380.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2693, pruned_loss=0.03656, over 1426009.08 frames.], batch size: 23, lr: 3.72e-04
2022-04-29 17:26:11,038 INFO [train.py:763] (3/8) Epoch 20, batch 1450, loss[loss=0.216, simple_loss=0.2966, pruned_loss=0.06764, over 4839.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2685, pruned_loss=0.03615, over 1420009.69 frames.], batch size: 52, lr: 3.72e-04
2022-04-29 17:27:17,681 INFO [train.py:763] (3/8) Epoch 20, batch 1500, loss[loss=0.1724, simple_loss=0.2732, pruned_loss=0.03578, over 7327.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2689, pruned_loss=0.03625, over 1417346.87 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:28:24,676 INFO [train.py:763] (3/8) Epoch 20, batch 1550, loss[loss=0.165, simple_loss=0.2694, pruned_loss=0.03032, over 6762.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2696, pruned_loss=0.03699, over 1420371.41 frames.], batch size: 31, lr: 3.72e-04
2022-04-29 17:29:31,791 INFO [train.py:763] (3/8) Epoch 20, batch 1600, loss[loss=0.1859, simple_loss=0.2976, pruned_loss=0.03712, over 7337.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2706, pruned_loss=0.03723, over 1421518.18 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:30:38,860 INFO [train.py:763] (3/8) Epoch 20, batch 1650, loss[loss=0.1737, simple_loss=0.2792, pruned_loss=0.03416, over 7331.00 frames.], tot_loss[loss=0.172, simple_loss=0.2702, pruned_loss=0.03689, over 1423373.08 frames.], batch size: 20, lr: 3.72e-04
2022-04-29 17:31:46,135 INFO [train.py:763] (3/8) Epoch 20, batch 1700, loss[loss=0.1911, simple_loss=0.2895, pruned_loss=0.04639, over 7328.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2697, pruned_loss=0.03683, over 1423630.87 frames.], batch size: 22, lr: 3.72e-04
2022-04-29 17:32:52,730 INFO [train.py:763] (3/8) Epoch 20, batch 1750, loss[loss=0.1405, simple_loss=0.2422, pruned_loss=0.01936, over 7425.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2701, pruned_loss=0.03699, over 1423829.39 frames.], batch size: 18, lr: 3.72e-04
2022-04-29 17:33:59,656 INFO [train.py:763] (3/8) Epoch 20, batch 1800, loss[loss=0.1798, simple_loss=0.2753, pruned_loss=0.04215, over 7217.00 frames.], tot_loss[loss=0.1711, simple_loss=0.269, pruned_loss=0.03656, over 1424788.52 frames.], batch size: 23, lr: 3.71e-04
2022-04-29 17:35:06,943 INFO [train.py:763] (3/8) Epoch 20, batch 1850, loss[loss=0.1483, simple_loss=0.243, pruned_loss=0.02685, over 7413.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2693, pruned_loss=0.03695, over 1422972.26 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:36:12,557 INFO [train.py:763] (3/8) Epoch 20, batch 1900, loss[loss=0.165, simple_loss=0.2687, pruned_loss=0.03063, over 7156.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2701, pruned_loss=0.03721, over 1424509.89 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:37:18,016 INFO [train.py:763] (3/8) Epoch 20, batch 1950, loss[loss=0.1735, simple_loss=0.2642, pruned_loss=0.04142, over 7273.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2692, pruned_loss=0.03687, over 1427812.67 frames.], batch size: 19, lr: 3.71e-04
2022-04-29 17:38:24,301 INFO [train.py:763] (3/8) Epoch 20, batch 2000, loss[loss=0.1885, simple_loss=0.2919, pruned_loss=0.04257, over 6771.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2683, pruned_loss=0.03665, over 1423670.13 frames.], batch size: 31, lr: 3.71e-04
2022-04-29 17:39:29,413 INFO [train.py:763] (3/8) Epoch 20, batch 2050, loss[loss=0.1831, simple_loss=0.2811, pruned_loss=0.04254, over 7224.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2689, pruned_loss=0.03682, over 1424472.38 frames.], batch size: 21, lr: 3.71e-04
2022-04-29 17:40:35,603 INFO [train.py:763] (3/8) Epoch 20, batch 2100, loss[loss=0.1564, simple_loss=0.2568, pruned_loss=0.02799, over 7066.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2689, pruned_loss=0.03683, over 1422970.20 frames.], batch size: 18, lr: 3.71e-04
2022-04-29 17:41:42,815 INFO [train.py:763] (3/8) Epoch 20, batch 2150, loss[loss=0.1604, simple_loss=0.2537, pruned_loss=0.03353, over 6842.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2694, pruned_loss=0.03721, over 1422314.68 frames.], batch size: 15, lr: 3.71e-04
2022-04-29 17:42:48,993 INFO [train.py:763] (3/8) Epoch 20, batch 2200, loss[loss=0.2056, simple_loss=0.3119, pruned_loss=0.04964, over 7195.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2681, pruned_loss=0.03637, over 1423641.08 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:43:54,361 INFO [train.py:763] (3/8) Epoch 20, batch 2250, loss[loss=0.1797, simple_loss=0.2785, pruned_loss=0.04045, over 7212.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2686, pruned_loss=0.03632, over 1424899.58 frames.], batch size: 22, lr: 3.71e-04
2022-04-29 17:45:01,606 INFO [train.py:763] (3/8) Epoch 20, batch 2300, loss[loss=0.186, simple_loss=0.2811, pruned_loss=0.04546, over 5170.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2685, pruned_loss=0.03666, over 1422989.48 frames.], batch size: 53, lr: 3.71e-04
2022-04-29 17:46:08,267 INFO [train.py:763] (3/8) Epoch 20, batch 2350, loss[loss=0.1898, simple_loss=0.2866, pruned_loss=0.04653, over 7296.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03678, over 1417725.65 frames.], batch size: 24, lr: 3.70e-04
2022-04-29 17:47:15,536 INFO [train.py:763] (3/8) Epoch 20, batch 2400, loss[loss=0.1733, simple_loss=0.2658, pruned_loss=0.04037, over 7215.00 frames.], tot_loss[loss=0.1706, simple_loss=0.269, pruned_loss=0.03615, over 1420638.48 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:48:22,379 INFO [train.py:763] (3/8) Epoch 20, batch 2450, loss[loss=0.1771, simple_loss=0.2851, pruned_loss=0.0346, over 7168.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2692, pruned_loss=0.0361, over 1422089.75 frames.], batch size: 19, lr: 3.70e-04
2022-04-29 17:49:29,423 INFO [train.py:763] (3/8) Epoch 20, batch 2500, loss[loss=0.1651, simple_loss=0.2759, pruned_loss=0.02716, over 7415.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2693, pruned_loss=0.03619, over 1422989.40 frames.], batch size: 21, lr: 3.70e-04
2022-04-29 17:50:36,099 INFO [train.py:763] (3/8) Epoch 20, batch 2550, loss[loss=0.1896, simple_loss=0.2924, pruned_loss=0.04336, over 4625.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2706, pruned_loss=0.03693, over 1420296.52 frames.], batch size: 52, lr: 3.70e-04
2022-04-29 17:51:41,444 INFO [train.py:763] (3/8) Epoch 20, batch 2600, loss[loss=0.1572, simple_loss=0.2522, pruned_loss=0.03106, over 7087.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2712, pruned_loss=0.03722, over 1421519.31 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:52:58,239 INFO [train.py:763] (3/8) Epoch 20, batch 2650, loss[loss=0.1614, simple_loss=0.2617, pruned_loss=0.03053, over 7331.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2716, pruned_loss=0.03753, over 1416381.17 frames.], batch size: 20, lr: 3.70e-04
2022-04-29 17:54:04,061 INFO [train.py:763] (3/8) Epoch 20, batch 2700, loss[loss=0.1647, simple_loss=0.2484, pruned_loss=0.04051, over 7414.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2711, pruned_loss=0.03734, over 1420585.16 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:55:10,585 INFO [train.py:763] (3/8) Epoch 20, batch 2750, loss[loss=0.1625, simple_loss=0.2589, pruned_loss=0.03299, over 7176.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2714, pruned_loss=0.03773, over 1422727.99 frames.], batch size: 18, lr: 3.70e-04
2022-04-29 17:56:15,901 INFO [train.py:763] (3/8) Epoch 20, batch 2800, loss[loss=0.1946, simple_loss=0.2828, pruned_loss=0.05319, over 7373.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2708, pruned_loss=0.03737, over 1426186.55 frames.], batch size: 23, lr: 3.70e-04
2022-04-29 17:57:21,236 INFO [train.py:763] (3/8) Epoch 20, batch 2850, loss[loss=0.1936, simple_loss=0.2851, pruned_loss=0.05107, over 7215.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2701, pruned_loss=0.03722, over 1421571.61 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 17:58:26,461 INFO [train.py:763] (3/8) Epoch 20, batch 2900, loss[loss=0.1732, simple_loss=0.2775, pruned_loss=0.03446, over 7090.00 frames.], tot_loss[loss=0.1732, simple_loss=0.271, pruned_loss=0.03769, over 1417249.58 frames.], batch size: 28, lr: 3.69e-04
2022-04-29 17:59:31,728 INFO [train.py:763] (3/8) Epoch 20, batch 2950, loss[loss=0.162, simple_loss=0.2549, pruned_loss=0.03452, over 7367.00 frames.], tot_loss[loss=0.173, simple_loss=0.2708, pruned_loss=0.03761, over 1415688.14 frames.], batch size: 19, lr: 3.69e-04
2022-04-29 18:01:03,485 INFO [train.py:763] (3/8) Epoch 20, batch 3000, loss[loss=0.1813, simple_loss=0.2859, pruned_loss=0.03831, over 6774.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2708, pruned_loss=0.03773, over 1415409.99 frames.], batch size: 31, lr: 3.69e-04
2022-04-29 18:01:03,486 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 18:01:18,758 INFO [train.py:792] (3/8) Epoch 20, validation: loss=0.1672, simple_loss=0.2663, pruned_loss=0.03407, over 698248.00 frames.
2022-04-29 18:02:33,644 INFO [train.py:763] (3/8) Epoch 20, batch 3050, loss[loss=0.1495, simple_loss=0.2386, pruned_loss=0.03022, over 7303.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2702, pruned_loss=0.03733, over 1416122.24 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:03:49,733 INFO [train.py:763] (3/8) Epoch 20, batch 3100, loss[loss=0.1991, simple_loss=0.3004, pruned_loss=0.0489, over 7364.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2711, pruned_loss=0.03772, over 1414144.29 frames.], batch size: 23, lr: 3.69e-04
2022-04-29 18:05:13,900 INFO [train.py:763] (3/8) Epoch 20, batch 3150, loss[loss=0.205, simple_loss=0.3021, pruned_loss=0.05392, over 7306.00 frames.], tot_loss[loss=0.173, simple_loss=0.2707, pruned_loss=0.03763, over 1418693.73 frames.], batch size: 24, lr: 3.69e-04
2022-04-29 18:06:18,922 INFO [train.py:763] (3/8) Epoch 20, batch 3200, loss[loss=0.1725, simple_loss=0.2852, pruned_loss=0.02994, over 7310.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2717, pruned_loss=0.03756, over 1423030.15 frames.], batch size: 21, lr: 3.69e-04
2022-04-29 18:07:24,049 INFO [train.py:763] (3/8) Epoch 20, batch 3250, loss[loss=0.1625, simple_loss=0.2663, pruned_loss=0.02939, over 7065.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2717, pruned_loss=0.03767, over 1421868.03 frames.], batch size: 18, lr: 3.69e-04
2022-04-29 18:08:29,711 INFO [train.py:763] (3/8) Epoch 20, batch 3300, loss[loss=0.1472, simple_loss=0.2373, pruned_loss=0.02858, over 7140.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2715, pruned_loss=0.03761, over 1423389.77 frames.], batch size: 17, lr: 3.69e-04
2022-04-29 18:09:35,971 INFO [train.py:763] (3/8) Epoch 20, batch 3350, loss[loss=0.1492, simple_loss=0.2453, pruned_loss=0.02653, over 7231.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2704, pruned_loss=0.03706, over 1419212.33 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:10:42,810 INFO [train.py:763] (3/8) Epoch 20, batch 3400, loss[loss=0.1771, simple_loss=0.2832, pruned_loss=0.03551, over 6516.00 frames.], tot_loss[loss=0.173, simple_loss=0.271, pruned_loss=0.03745, over 1416330.03 frames.], batch size: 38, lr: 3.68e-04
2022-04-29 18:11:49,526 INFO [train.py:763] (3/8) Epoch 20, batch 3450, loss[loss=0.1796, simple_loss=0.2765, pruned_loss=0.04132, over 7321.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2715, pruned_loss=0.03765, over 1414850.02 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:12:54,738 INFO [train.py:763] (3/8) Epoch 20, batch 3500, loss[loss=0.1707, simple_loss=0.2796, pruned_loss=0.03085, over 7063.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2717, pruned_loss=0.03781, over 1411068.46 frames.], batch size: 28, lr: 3.68e-04
2022-04-29 18:14:00,242 INFO [train.py:763] (3/8) Epoch 20, batch 3550, loss[loss=0.1503, simple_loss=0.238, pruned_loss=0.03127, over 7302.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2701, pruned_loss=0.03722, over 1415388.59 frames.], batch size: 17, lr: 3.68e-04
2022-04-29 18:15:05,500 INFO [train.py:763] (3/8) Epoch 20, batch 3600, loss[loss=0.162, simple_loss=0.272, pruned_loss=0.02596, over 7366.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2697, pruned_loss=0.03677, over 1412215.91 frames.], batch size: 23, lr: 3.68e-04
2022-04-29 18:16:10,759 INFO [train.py:763] (3/8) Epoch 20, batch 3650, loss[loss=0.1736, simple_loss=0.2722, pruned_loss=0.03757, over 7208.00 frames.], tot_loss[loss=0.171, simple_loss=0.2694, pruned_loss=0.03631, over 1413850.76 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:17:15,967 INFO [train.py:763] (3/8) Epoch 20, batch 3700, loss[loss=0.1494, simple_loss=0.2562, pruned_loss=0.02126, over 7308.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2695, pruned_loss=0.03651, over 1414830.66 frames.], batch size: 21, lr: 3.68e-04
2022-04-29 18:18:22,130 INFO [train.py:763] (3/8) Epoch 20, batch 3750, loss[loss=0.1833, simple_loss=0.2776, pruned_loss=0.04452, over 7315.00 frames.], tot_loss[loss=0.171, simple_loss=0.2694, pruned_loss=0.03633, over 1418139.50 frames.], batch size: 25, lr: 3.68e-04
2022-04-29 18:19:27,284 INFO [train.py:763] (3/8) Epoch 20, batch 3800, loss[loss=0.1777, simple_loss=0.2862, pruned_loss=0.03464, over 7176.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2687, pruned_loss=0.03586, over 1417850.34 frames.], batch size: 26, lr: 3.68e-04
2022-04-29 18:20:33,279 INFO [train.py:763] (3/8) Epoch 20, batch 3850, loss[loss=0.1617, simple_loss=0.2584, pruned_loss=0.03244, over 7321.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2686, pruned_loss=0.03563, over 1419125.79 frames.], batch size: 20, lr: 3.68e-04
2022-04-29 18:21:38,666 INFO [train.py:763] (3/8) Epoch 20, batch 3900, loss[loss=0.1587, simple_loss=0.2447, pruned_loss=0.03632, over 7261.00 frames.], tot_loss[loss=0.17, simple_loss=0.2687, pruned_loss=0.03561, over 1422634.77 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:22:44,410 INFO [train.py:763] (3/8) Epoch 20, batch 3950, loss[loss=0.1555, simple_loss=0.2441, pruned_loss=0.03343, over 7408.00 frames.], tot_loss[loss=0.1712, simple_loss=0.27, pruned_loss=0.03622, over 1418348.72 frames.], batch size: 18, lr: 3.67e-04
2022-04-29 18:23:51,277 INFO [train.py:763] (3/8) Epoch 20, batch 4000, loss[loss=0.1736, simple_loss=0.2713, pruned_loss=0.038, over 7355.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2698, pruned_loss=0.03597, over 1422183.05 frames.], batch size: 19, lr: 3.67e-04
2022-04-29 18:24:58,614 INFO [train.py:763] (3/8) Epoch 20, batch 4050, loss[loss=0.1986, simple_loss=0.2858, pruned_loss=0.05577, over 5025.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2693, pruned_loss=0.03616, over 1419083.29 frames.], batch size: 52, lr: 3.67e-04
2022-04-29 18:26:05,422 INFO [train.py:763] (3/8) Epoch 20, batch 4100, loss[loss=0.1792, simple_loss=0.2771, pruned_loss=0.04064, over 7215.00 frames.], tot_loss[loss=0.172, simple_loss=0.2703, pruned_loss=0.03681, over 1411484.48 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:27:10,991 INFO [train.py:763] (3/8) Epoch 20, batch 4150, loss[loss=0.1547, simple_loss=0.2469, pruned_loss=0.03123, over 7073.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2711, pruned_loss=0.03717, over 1412753.96 frames.], batch size: 18, lr: 3.67e-04
2022-04-29 18:28:16,324 INFO [train.py:763] (3/8) Epoch 20, batch 4200, loss[loss=0.1691, simple_loss=0.2704, pruned_loss=0.03385, over 6657.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2712, pruned_loss=0.03711, over 1412327.70 frames.], batch size: 31, lr: 3.67e-04
2022-04-29 18:29:32,305 INFO [train.py:763] (3/8) Epoch 20, batch 4250, loss[loss=0.1773, simple_loss=0.2858, pruned_loss=0.03442, over 7230.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2699, pruned_loss=0.03636, over 1417057.30 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:30:38,989 INFO [train.py:763] (3/8) Epoch 20, batch 4300, loss[loss=0.1735, simple_loss=0.2766, pruned_loss=0.03518, over 7316.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03599, over 1417152.78 frames.], batch size: 24, lr: 3.67e-04
2022-04-29 18:31:45,007 INFO [train.py:763] (3/8) Epoch 20, batch 4350, loss[loss=0.1797, simple_loss=0.2766, pruned_loss=0.04139, over 7226.00 frames.], tot_loss[loss=0.17, simple_loss=0.2686, pruned_loss=0.03576, over 1415728.13 frames.], batch size: 21, lr: 3.67e-04
2022-04-29 18:32:52,216 INFO [train.py:763] (3/8) Epoch 20, batch 4400, loss[loss=0.1508, simple_loss=0.2455, pruned_loss=0.02803, over 7157.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2691, pruned_loss=0.03619, over 1415808.61 frames.], batch size: 18, lr: 3.66e-04
2022-04-29 18:33:58,453 INFO [train.py:763] (3/8) Epoch 20, batch 4450, loss[loss=0.1348, simple_loss=0.226, pruned_loss=0.02185, over 7014.00 frames.], tot_loss[loss=0.1704, simple_loss=0.269, pruned_loss=0.03591, over 1407618.15 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:35:05,722 INFO [train.py:763] (3/8) Epoch 20, batch 4500, loss[loss=0.1492, simple_loss=0.2396, pruned_loss=0.02944, over 7005.00 frames.], tot_loss[loss=0.1703, simple_loss=0.269, pruned_loss=0.03582, over 1410546.73 frames.], batch size: 16, lr: 3.66e-04
2022-04-29 18:36:13,269 INFO [train.py:763] (3/8) Epoch 20, batch 4550, loss[loss=0.1951, simple_loss=0.2903, pruned_loss=0.04996, over 5097.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2685, pruned_loss=0.03632, over 1395300.42 frames.], batch size: 52, lr: 3.66e-04
2022-04-29 18:37:42,387 INFO [train.py:763] (3/8) Epoch 21, batch 0, loss[loss=0.1886, simple_loss=0.2988, pruned_loss=0.03925, over 7284.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2988, pruned_loss=0.03925, over 7284.00 frames.], batch size: 25, lr: 3.58e-04
2022-04-29 18:38:48,208 INFO [train.py:763] (3/8) Epoch 21, batch 50, loss[loss=0.16, simple_loss=0.2613, pruned_loss=0.02931, over 7163.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2699, pruned_loss=0.03669, over 317776.90 frames.], batch size: 18, lr: 3.58e-04
2022-04-29 18:39:53,570 INFO [train.py:763] (3/8) Epoch 21, batch 100, loss[loss=0.1575, simple_loss=0.2657, pruned_loss=0.02465, over 7118.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2669, pruned_loss=0.03533, over 563466.43 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:41:00,340 INFO [train.py:763] (3/8) Epoch 21, batch 150, loss[loss=0.1676, simple_loss=0.2724, pruned_loss=0.03141, over 7310.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.0354, over 753393.26 frames.], batch size: 21, lr: 3.58e-04
2022-04-29 18:42:07,756 INFO [train.py:763] (3/8) Epoch 21, batch 200, loss[loss=0.159, simple_loss=0.268, pruned_loss=0.02502, over 7335.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2668, pruned_loss=0.03549, over 901299.23 frames.], batch size: 22, lr: 3.58e-04
2022-04-29 18:43:14,297 INFO [train.py:763] (3/8) Epoch 21, batch 250, loss[loss=0.1656, simple_loss=0.2627, pruned_loss=0.03429, over 7252.00 frames.], tot_loss[loss=0.1698, simple_loss=0.268, pruned_loss=0.03581, over 1014418.92 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:44:19,571 INFO [train.py:763] (3/8) Epoch 21, batch 300, loss[loss=0.1736, simple_loss=0.256, pruned_loss=0.04553, over 7228.00 frames.], tot_loss[loss=0.171, simple_loss=0.2692, pruned_loss=0.03646, over 1106575.92 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:45:25,083 INFO [train.py:763] (3/8) Epoch 21, batch 350, loss[loss=0.1518, simple_loss=0.2466, pruned_loss=0.02852, over 7157.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2688, pruned_loss=0.03641, over 1176782.80 frames.], batch size: 19, lr: 3.57e-04
2022-04-29 18:46:30,617 INFO [train.py:763] (3/8) Epoch 21, batch 400, loss[loss=0.1747, simple_loss=0.2764, pruned_loss=0.03657, over 7222.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2684, pruned_loss=0.03611, over 1229513.56 frames.], batch size: 21, lr: 3.57e-04
2022-04-29 18:47:36,040 INFO [train.py:763] (3/8) Epoch 21, batch 450, loss[loss=0.1751, simple_loss=0.272, pruned_loss=0.03915, over 4735.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.0357, over 1272480.46 frames.], batch size: 52, lr: 3.57e-04
2022-04-29 18:48:41,848 INFO [train.py:763] (3/8) Epoch 21, batch 500, loss[loss=0.1794, simple_loss=0.2866, pruned_loss=0.03611, over 7317.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2683, pruned_loss=0.03537, over 1308151.36 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:49:47,435 INFO [train.py:763] (3/8) Epoch 21, batch 550, loss[loss=0.1398, simple_loss=0.2449, pruned_loss=0.01737, over 7432.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2698, pruned_loss=0.03587, over 1331325.03 frames.], batch size: 20, lr: 3.57e-04
2022-04-29 18:50:53,639 INFO [train.py:763] (3/8) Epoch 21, batch 600, loss[loss=0.1621, simple_loss=0.2731, pruned_loss=0.02558, over 7331.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2677, pruned_loss=0.03523, over 1353154.19 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:51:58,877 INFO [train.py:763] (3/8) Epoch 21, batch 650, loss[loss=0.1525, simple_loss=0.2544, pruned_loss=0.0253, over 7333.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2692, pruned_loss=0.03556, over 1368663.23 frames.], batch size: 22, lr: 3.57e-04
2022-04-29 18:53:04,511 INFO [train.py:763] (3/8) Epoch 21, batch 700, loss[loss=0.1805, simple_loss=0.2906, pruned_loss=0.0352, over 7267.00 frames.], tot_loss[loss=0.17, simple_loss=0.2689, pruned_loss=0.03557, over 1378642.46 frames.], batch size: 25, lr: 3.57e-04
2022-04-29 18:54:10,368 INFO [train.py:763] (3/8) Epoch 21, batch 750, loss[loss=0.1665, simple_loss=0.2615, pruned_loss=0.03573, over 7165.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.03571, over 1386512.74 frames.], batch size: 18, lr: 3.57e-04
2022-04-29 18:55:16,596 INFO [train.py:763] (3/8) Epoch 21, batch 800, loss[loss=0.1963, simple_loss=0.2931, pruned_loss=0.04975, over 7285.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2693, pruned_loss=0.03592, over 1399548.32 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 18:56:22,303 INFO [train.py:763] (3/8) Epoch 21, batch 850, loss[loss=0.1556, simple_loss=0.2508, pruned_loss=0.03014, over 7419.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2693, pruned_loss=0.03592, over 1404580.35 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:57:27,449 INFO [train.py:763] (3/8) Epoch 21, batch 900, loss[loss=0.1859, simple_loss=0.2932, pruned_loss=0.0393, over 6395.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2692, pruned_loss=0.03604, over 1408492.61 frames.], batch size: 38, lr: 3.56e-04
2022-04-29 18:58:32,834 INFO [train.py:763] (3/8) Epoch 21, batch 950, loss[loss=0.155, simple_loss=0.2424, pruned_loss=0.03373, over 7270.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2689, pruned_loss=0.03611, over 1410867.29 frames.], batch size: 18, lr: 3.56e-04
2022-04-29 18:59:38,148 INFO [train.py:763] (3/8) Epoch 21, batch 1000, loss[loss=0.1665, simple_loss=0.2601, pruned_loss=0.03647, over 7144.00 frames.], tot_loss[loss=0.1716, simple_loss=0.27, pruned_loss=0.03663, over 1411421.58 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:00:44,771 INFO [train.py:763] (3/8) Epoch 21, batch 1050, loss[loss=0.1506, simple_loss=0.2495, pruned_loss=0.02585, over 7338.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2685, pruned_loss=0.03619, over 1414774.24 frames.], batch size: 22, lr: 3.56e-04
2022-04-29 19:01:50,753 INFO [train.py:763] (3/8) Epoch 21, batch 1100, loss[loss=0.2116, simple_loss=0.3118, pruned_loss=0.05568, over 6403.00 frames.], tot_loss[loss=0.17, simple_loss=0.268, pruned_loss=0.03603, over 1418924.81 frames.], batch size: 37, lr: 3.56e-04
2022-04-29 19:02:56,400 INFO [train.py:763] (3/8) Epoch 21, batch 1150, loss[loss=0.1654, simple_loss=0.2593, pruned_loss=0.03577, over 7263.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2678, pruned_loss=0.03589, over 1419971.69 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:04:02,097 INFO [train.py:763] (3/8) Epoch 21, batch 1200, loss[loss=0.1762, simple_loss=0.2691, pruned_loss=0.04167, over 7329.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2673, pruned_loss=0.03585, over 1421818.54 frames.], batch size: 25, lr: 3.56e-04
2022-04-29 19:05:07,719 INFO [train.py:763] (3/8) Epoch 21, batch 1250, loss[loss=0.157, simple_loss=0.2431, pruned_loss=0.03543, over 7025.00 frames.], tot_loss[loss=0.1701, simple_loss=0.268, pruned_loss=0.03613, over 1420814.57 frames.], batch size: 16, lr: 3.56e-04
2022-04-29 19:06:13,269 INFO [train.py:763] (3/8) Epoch 21, batch 1300, loss[loss=0.1364, simple_loss=0.237, pruned_loss=0.01794, over 7174.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2678, pruned_loss=0.03619, over 1419758.21 frames.], batch size: 19, lr: 3.56e-04
2022-04-29 19:07:19,447 INFO [train.py:763] (3/8) Epoch 21, batch 1350, loss[loss=0.17, simple_loss=0.279, pruned_loss=0.03045, over 7406.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2676, pruned_loss=0.03606, over 1423597.81 frames.], batch size: 21, lr: 3.55e-04
2022-04-29 19:08:24,893 INFO [train.py:763] (3/8) Epoch 21, batch 1400, loss[loss=0.206, simple_loss=0.3066, pruned_loss=0.05265, over 7204.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2672, pruned_loss=0.03597, over 1419976.91 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:09:30,408 INFO [train.py:763] (3/8) Epoch 21, batch 1450, loss[loss=0.1723, simple_loss=0.2715, pruned_loss=0.03652, over 7428.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2682, pruned_loss=0.03606, over 1425204.22 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:10:36,217 INFO [train.py:763] (3/8) Epoch 21, batch 1500, loss[loss=0.1582, simple_loss=0.2691, pruned_loss=0.02366, over 7230.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2668, pruned_loss=0.03565, over 1427008.39 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:11:42,021 INFO [train.py:763] (3/8) Epoch 21, batch 1550, loss[loss=0.1768, simple_loss=0.2789, pruned_loss=0.0373, over 7238.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2667, pruned_loss=0.03529, over 1429445.13 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:12:47,947 INFO [train.py:763] (3/8) Epoch 21, batch 1600, loss[loss=0.1381, simple_loss=0.2294, pruned_loss=0.02337, over 6802.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2662, pruned_loss=0.03494, over 1429929.83 frames.], batch size: 15, lr: 3.55e-04
2022-04-29 19:13:54,882 INFO [train.py:763] (3/8) Epoch 21, batch 1650, loss[loss=0.1791, simple_loss=0.2924, pruned_loss=0.0329, over 6663.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03509, over 1431454.91 frames.], batch size: 31, lr: 3.55e-04
2022-04-29 19:15:01,797 INFO [train.py:763] (3/8) Epoch 21, batch 1700, loss[loss=0.1644, simple_loss=0.2666, pruned_loss=0.03116, over 7336.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2659, pruned_loss=0.03459, over 1433328.49 frames.], batch size: 22, lr: 3.55e-04
2022-04-29 19:16:08,175 INFO [train.py:763] (3/8) Epoch 21, batch 1750, loss[loss=0.171, simple_loss=0.2736, pruned_loss=0.0342, over 7229.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03521, over 1432676.13 frames.], batch size: 20, lr: 3.55e-04
2022-04-29 19:17:14,196 INFO [train.py:763] (3/8) Epoch 21, batch 1800, loss[loss=0.1517, simple_loss=0.2447, pruned_loss=0.02937, over 7274.00 frames.], tot_loss[loss=0.1693, simple_loss=0.267, pruned_loss=0.03579, over 1429760.24 frames.], batch size: 17, lr: 3.55e-04
2022-04-29 19:18:19,480 INFO [train.py:763] (3/8) Epoch 21, batch 1850, loss[loss=0.1777, simple_loss=0.2771, pruned_loss=0.03916, over 6455.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2671, pruned_loss=0.03583, over 1425860.39 frames.], batch size: 38, lr: 3.55e-04
2022-04-29 19:19:25,204 INFO [train.py:763] (3/8) Epoch 21, batch 1900, loss[loss=0.1777, simple_loss=0.2744, pruned_loss=0.04052, over 5010.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2672, pruned_loss=0.03564, over 1424269.37 frames.], batch size: 52, lr: 3.54e-04
2022-04-29 19:20:31,906 INFO [train.py:763] (3/8) Epoch 21, batch 1950, loss[loss=0.1618, simple_loss=0.2449, pruned_loss=0.0393, over 7278.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2671, pruned_loss=0.03573, over 1425201.75 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:21:37,659 INFO [train.py:763] (3/8) Epoch 21, batch 2000, loss[loss=0.2095, simple_loss=0.3084, pruned_loss=0.05528, over 7330.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2676, pruned_loss=0.03555, over 1427703.59 frames.], batch size: 20, lr: 3.54e-04
2022-04-29 19:22:44,041 INFO [train.py:763] (3/8) Epoch 21, batch 2050, loss[loss=0.144, simple_loss=0.2318, pruned_loss=0.02808, over 7271.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2683, pruned_loss=0.03544, over 1428080.54 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:23:50,502 INFO [train.py:763] (3/8) Epoch 21, batch 2100, loss[loss=0.1474, simple_loss=0.2358, pruned_loss=0.02952, over 7412.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03534, over 1427006.75 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:24:56,268 INFO [train.py:763] (3/8) Epoch 21, batch 2150, loss[loss=0.1626, simple_loss=0.2508, pruned_loss=0.03723, over 7164.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.03513, over 1422465.78 frames.], batch size: 18, lr: 3.54e-04
2022-04-29 19:26:02,248 INFO [train.py:763] (3/8) Epoch 21, batch 2200, loss[loss=0.1587, simple_loss=0.2581, pruned_loss=0.02971, over 7121.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03518, over 1425110.73 frames.], batch size: 21, lr: 3.54e-04
2022-04-29 19:27:08,591 INFO [train.py:763] (3/8) Epoch 21, batch 2250, loss[loss=0.1431, simple_loss=0.2288, pruned_loss=0.02873, over 6777.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2671, pruned_loss=0.03512, over 1422886.41 frames.], batch size: 15, lr: 3.54e-04
2022-04-29 19:28:14,981 INFO [train.py:763] (3/8) Epoch 21, batch 2300, loss[loss=0.1763, simple_loss=0.2713, pruned_loss=0.04059, over 4904.00 frames.], tot_loss[loss=0.1695, simple_loss=0.268, pruned_loss=0.03546, over 1424393.98 frames.], batch size: 52, lr: 3.54e-04
2022-04-29 19:29:21,491 INFO [train.py:763] (3/8) Epoch 21, batch 2350, loss[loss=0.1759, simple_loss=0.279, pruned_loss=0.03634, over 6284.00 frames.], tot_loss[loss=0.1694, simple_loss=0.268, pruned_loss=0.03536, over 1426875.17 frames.], batch size: 37, lr: 3.54e-04
2022-04-29 19:30:28,260 INFO [train.py:763] (3/8) Epoch 21, batch 2400, loss[loss=0.1601, simple_loss=0.2509, pruned_loss=0.03467, over 7135.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2675, pruned_loss=0.03574, over 1426709.28 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:31:33,881 INFO [train.py:763] (3/8) Epoch 21, batch 2450, loss[loss=0.1611, simple_loss=0.2509, pruned_loss=0.03571, over 7283.00 frames.], tot_loss[loss=0.1697, simple_loss=0.268, pruned_loss=0.03566, over 1425393.51 frames.], batch size: 17, lr: 3.54e-04
2022-04-29 19:32:39,517 INFO [train.py:763] (3/8) Epoch 21, batch 2500, loss[loss=0.1868, simple_loss=0.2941, pruned_loss=0.03973, over 7420.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2684, pruned_loss=0.0356, over 1423059.42 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:33:46,125 INFO [train.py:763] (3/8) Epoch 21, batch 2550, loss[loss=0.1936, simple_loss=0.2827, pruned_loss=0.05224, over 7067.00 frames.], tot_loss[loss=0.1706, simple_loss=0.269, pruned_loss=0.03604, over 1421639.14 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:34:52,130 INFO [train.py:763] (3/8) Epoch 21, batch 2600, loss[loss=0.1602, simple_loss=0.2482, pruned_loss=0.03615, over 7154.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2698, pruned_loss=0.03629, over 1417451.14 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:35:58,115 INFO [train.py:763] (3/8) Epoch 21, batch 2650, loss[loss=0.198, simple_loss=0.2763, pruned_loss=0.05982, over 7251.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2685, pruned_loss=0.03584, over 1421370.41 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:37:03,416 INFO [train.py:763] (3/8) Epoch 21, batch 2700, loss[loss=0.1682, simple_loss=0.2584, pruned_loss=0.03905, over 7159.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.03536, over 1420506.69 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:38:08,437 INFO [train.py:763] (3/8) Epoch 21, batch 2750, loss[loss=0.1474, simple_loss=0.2428, pruned_loss=0.026, over 7068.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2681, pruned_loss=0.03565, over 1420063.49 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:39:13,884 INFO [train.py:763] (3/8) Epoch 21, batch 2800, loss[loss=0.1717, simple_loss=0.2547, pruned_loss=0.04438, over 7282.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2685, pruned_loss=0.03592, over 1421412.11 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:40:19,366 INFO [train.py:763] (3/8) Epoch 21, batch 2850, loss[loss=0.162, simple_loss=0.2519, pruned_loss=0.03604, over 7155.00 frames.], tot_loss[loss=0.1698, simple_loss=0.268, pruned_loss=0.03576, over 1419524.11 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:41:24,554 INFO [train.py:763] (3/8) Epoch 21, batch 2900, loss[loss=0.1415, simple_loss=0.2456, pruned_loss=0.01864, over 7158.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03536, over 1421422.20 frames.], batch size: 19, lr: 3.53e-04
2022-04-29 19:42:30,254 INFO [train.py:763] (3/8) Epoch 21, batch 2950, loss[loss=0.1701, simple_loss=0.2751, pruned_loss=0.03258, over 7409.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2689, pruned_loss=0.03625, over 1421747.04 frames.], batch size: 21, lr: 3.53e-04
2022-04-29 19:43:36,682 INFO [train.py:763] (3/8) Epoch 21, batch 3000, loss[loss=0.1581, simple_loss=0.2617, pruned_loss=0.0272, over 7158.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2675, pruned_loss=0.03555, over 1426075.57 frames.], batch size: 18, lr: 3.53e-04
2022-04-29 19:43:36,683 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 19:43:52,055 INFO [train.py:792] (3/8) Epoch 21, validation: loss=0.1676, simple_loss=0.2672, pruned_loss=0.03398, over 698248.00 frames.
2022-04-29 19:44:57,937 INFO [train.py:763] (3/8) Epoch 21, batch 3050, loss[loss=0.1805, simple_loss=0.2792, pruned_loss=0.04094, over 7068.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2673, pruned_loss=0.03554, over 1427686.07 frames.], batch size: 28, lr: 3.52e-04
2022-04-29 19:46:03,953 INFO [train.py:763] (3/8) Epoch 21, batch 3100, loss[loss=0.1965, simple_loss=0.2876, pruned_loss=0.05277, over 4966.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2662, pruned_loss=0.03505, over 1428000.12 frames.], batch size: 52, lr: 3.52e-04
2022-04-29 19:47:10,166 INFO [train.py:763] (3/8) Epoch 21, batch 3150, loss[loss=0.1811, simple_loss=0.2796, pruned_loss=0.04128, over 7421.00 frames.], tot_loss[loss=0.1677, simple_loss=0.266, pruned_loss=0.03472, over 1426458.09 frames.], batch size: 21, lr: 3.52e-04
2022-04-29 19:48:15,883 INFO [train.py:763] (3/8) Epoch 21, batch 3200, loss[loss=0.1727, simple_loss=0.2755, pruned_loss=0.03491, over 7443.00 frames.], tot_loss[loss=0.168, simple_loss=0.2664, pruned_loss=0.03478, over 1427984.27 frames.], batch size: 19, lr: 3.52e-04
2022-04-29 19:49:21,826 INFO [train.py:763] (3/8) Epoch 21, batch 3250, loss[loss=0.1357, simple_loss=0.2314, pruned_loss=0.01997, over 7001.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03518, over 1429135.06 frames.], batch size: 16, lr: 3.52e-04
2022-04-29 19:50:27,764 INFO [train.py:763] (3/8) Epoch 21, batch 3300, loss[loss=0.163, simple_loss=0.2609, pruned_loss=0.03254, over 7428.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2684, pruned_loss=0.03543, over 1432023.62 frames.], batch size: 20, lr: 3.52e-04
2022-04-29 19:51:34,061 INFO [train.py:763] (3/8) Epoch 21, batch 3350, loss[loss=0.1594, simple_loss=0.2555, pruned_loss=0.03166, over 7353.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2688, pruned_loss=0.03548, over 1430369.10 frames.], batch size: 19, lr: 3.52e-04
2022-04-29 19:52:40,199 INFO [train.py:763] (3/8) Epoch 21, batch 3400, loss[loss=0.1683, simple_loss=0.2634, pruned_loss=0.0366, over 7140.00 frames.], tot_loss[loss=0.17, simple_loss=0.269, pruned_loss=0.03548, over 1426504.77 frames.], batch size: 17, lr: 3.52e-04
2022-04-29 19:53:45,691 INFO [train.py:763] (3/8) Epoch 21, batch 3450, loss[loss=0.1711, simple_loss=0.2789, pruned_loss=0.03163, over 7320.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2691, pruned_loss=0.03568, over 1428431.09 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:54:51,959 INFO [train.py:763] (3/8) Epoch 21, batch 3500, loss[loss=0.1773, simple_loss=0.2878, pruned_loss=0.03345, over 7339.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2682, pruned_loss=0.03523, over 1431399.76 frames.], batch size: 22, lr: 3.52e-04
2022-04-29 19:55:58,079 INFO [train.py:763] (3/8) Epoch 21, batch 3550, loss[loss=0.1731, simple_loss=0.2704, pruned_loss=0.03796, over 6600.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2689, pruned_loss=0.03538, over 1428646.73 frames.], batch size: 31, lr: 3.52e-04
2022-04-29 19:57:04,813 INFO [train.py:763] (3/8) Epoch 21, batch 3600, loss[loss=0.1563, simple_loss=0.2423, pruned_loss=0.03513, over 7271.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2686, pruned_loss=0.03591, over 1424201.26 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 19:58:10,361 INFO [train.py:763] (3/8) Epoch 21, batch 3650, loss[loss=0.1878, simple_loss=0.2892, pruned_loss=0.04314, over 7368.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2689, pruned_loss=0.03594, over 1425906.23 frames.], batch size: 23, lr: 3.51e-04
2022-04-29 19:59:15,682 INFO [train.py:763] (3/8) Epoch 21, batch 3700, loss[loss=0.1906, simple_loss=0.2794, pruned_loss=0.05092, over 7209.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03575, over 1427685.34 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:00:21,230 INFO [train.py:763] (3/8) Epoch 21, batch 3750, loss[loss=0.1595, simple_loss=0.2522, pruned_loss=0.0334, over 6991.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03577, over 1431221.22 frames.], batch size: 16, lr: 3.51e-04
2022-04-29 20:01:26,920 INFO [train.py:763] (3/8) Epoch 21, batch 3800, loss[loss=0.2095, simple_loss=0.2959, pruned_loss=0.06151, over 5348.00 frames.], tot_loss[loss=0.1687, simple_loss=0.267, pruned_loss=0.03513, over 1425000.42 frames.], batch size: 52, lr: 3.51e-04
2022-04-29 20:02:32,210 INFO [train.py:763] (3/8) Epoch 21, batch 3850, loss[loss=0.193, simple_loss=0.2853, pruned_loss=0.05038, over 7229.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2679, pruned_loss=0.03535, over 1427405.22 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:03:37,823 INFO [train.py:763] (3/8) Epoch 21, batch 3900, loss[loss=0.169, simple_loss=0.2719, pruned_loss=0.03304, over 6462.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2678, pruned_loss=0.03529, over 1427483.54 frames.], batch size: 38, lr: 3.51e-04
2022-04-29 20:04:43,329 INFO [train.py:763] (3/8) Epoch 21, batch 3950, loss[loss=0.1423, simple_loss=0.2262, pruned_loss=0.02921, over 7282.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03505, over 1425968.25 frames.], batch size: 17, lr: 3.51e-04
2022-04-29 20:05:50,732 INFO [train.py:763] (3/8) Epoch 21, batch 4000, loss[loss=0.1815, simple_loss=0.286, pruned_loss=0.03851, over 7327.00 frames.], tot_loss[loss=0.17, simple_loss=0.2685, pruned_loss=0.03577, over 1425682.62 frames.], batch size: 21, lr: 3.51e-04
2022-04-29 20:06:57,084 INFO [train.py:763] (3/8) Epoch 21, batch 4050, loss[loss=0.1657, simple_loss=0.265, pruned_loss=0.03317, over 7366.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03532, over 1423162.69 frames.], batch size: 19, lr: 3.51e-04
2022-04-29 20:08:02,545 INFO [train.py:763] (3/8) Epoch 21, batch 4100, loss[loss=0.168, simple_loss=0.2614, pruned_loss=0.03732, over 7336.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03508, over 1423950.38 frames.], batch size: 20, lr: 3.51e-04
2022-04-29 20:09:08,412 INFO [train.py:763] (3/8) Epoch 21, batch 4150, loss[loss=0.1658, simple_loss=0.2607, pruned_loss=0.03544, over 7066.00 frames.], tot_loss[loss=0.1682, simple_loss=0.267, pruned_loss=0.03468, over 1419382.41 frames.], batch size: 18, lr: 3.51e-04
2022-04-29 20:10:23,428 INFO [train.py:763] (3/8) Epoch 21, batch 4200, loss[loss=0.1718, simple_loss=0.2759, pruned_loss=0.03387, over 7150.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2675, pruned_loss=0.0347, over 1414848.42 frames.], batch size: 20, lr: 3.50e-04
2022-04-29 20:11:28,555 INFO [train.py:763] (3/8) Epoch 21, batch 4250, loss[loss=0.1756, simple_loss=0.2848, pruned_loss=0.0332, over 6739.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2687, pruned_loss=0.03534, over 1408751.75 frames.], batch size: 31, lr: 3.50e-04
2022-04-29 20:12:34,518 INFO [train.py:763] (3/8) Epoch 21, batch 4300, loss[loss=0.1754, simple_loss=0.276, pruned_loss=0.03737, over 7277.00 frames.], tot_loss[loss=0.1698, simple_loss=0.269, pruned_loss=0.03532, over 1411517.15 frames.], batch size: 24, lr: 3.50e-04
2022-04-29 20:13:40,098 INFO [train.py:763] (3/8) Epoch 21, batch 4350, loss[loss=0.1828, simple_loss=0.2877, pruned_loss=0.03897, over 7339.00 frames.], tot_loss[loss=0.17, simple_loss=0.2696, pruned_loss=0.03522, over 1408424.40 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:14:45,317 INFO [train.py:763] (3/8) Epoch 21, batch 4400, loss[loss=0.1646, simple_loss=0.2615, pruned_loss=0.03388, over 7109.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2702, pruned_loss=0.03557, over 1402040.53 frames.], batch size: 21, lr: 3.50e-04
2022-04-29 20:15:50,787 INFO [train.py:763] (3/8) Epoch 21, batch 4450, loss[loss=0.1845, simple_loss=0.2882, pruned_loss=0.04039, over 7341.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2713, pruned_loss=0.03623, over 1398227.16 frames.], batch size: 22, lr: 3.50e-04
2022-04-29 20:17:22,857 INFO [train.py:763] (3/8) Epoch 21, batch 4500, loss[loss=0.1907, simple_loss=0.2919, pruned_loss=0.04471, over 7077.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2724, pruned_loss=0.03739, over 1388007.05 frames.], batch size: 28, lr: 3.50e-04
2022-04-29 20:18:27,308 INFO [train.py:763] (3/8) Epoch 21, batch 4550, loss[loss=0.2169, simple_loss=0.3062, pruned_loss=0.0638, over 5306.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2742, pruned_loss=0.03884, over 1346417.32 frames.], batch size: 52, lr: 3.50e-04
2022-04-29 20:20:15,489 INFO [train.py:763] (3/8) Epoch 22, batch 0, loss[loss=0.1699, simple_loss=0.2652, pruned_loss=0.03728, over 7229.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2652, pruned_loss=0.03728, over 7229.00 frames.], batch size: 16, lr: 3.42e-04
2022-04-29 20:21:30,524 INFO [train.py:763] (3/8) Epoch 22, batch 50, loss[loss=0.1606, simple_loss=0.2569, pruned_loss=0.03214, over 7159.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2695, pruned_loss=0.03715, over 318866.97 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:22:35,942 INFO [train.py:763] (3/8) Epoch 22, batch 100, loss[loss=0.1534, simple_loss=0.2539, pruned_loss=0.02643, over 7292.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2674, pruned_loss=0.0347, over 565150.47 frames.], batch size: 18, lr: 3.42e-04
2022-04-29 20:23:41,420 INFO [train.py:763] (3/8) Epoch 22, batch 150, loss[loss=0.1762, simple_loss=0.2852, pruned_loss=0.03358, over 7305.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2697, pruned_loss=0.03576, over 753243.47 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:24:46,882 INFO [train.py:763] (3/8) Epoch 22, batch 200, loss[loss=0.1528, simple_loss=0.2662, pruned_loss=0.01966, over 6512.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2692, pruned_loss=0.03558, over 901946.34 frames.], batch size: 38, lr: 3.42e-04
2022-04-29 20:25:52,442 INFO [train.py:763] (3/8) Epoch 22, batch 250, loss[loss=0.1908, simple_loss=0.2876, pruned_loss=0.04696, over 7185.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03599, over 1016862.28 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:26:58,033 INFO [train.py:763] (3/8) Epoch 22, batch 300, loss[loss=0.147, simple_loss=0.245, pruned_loss=0.02454, over 7162.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2691, pruned_loss=0.03582, over 1102179.31 frames.], batch size: 19, lr: 3.42e-04
2022-04-29 20:28:05,353 INFO [train.py:763] (3/8) Epoch 22, batch 350, loss[loss=0.1648, simple_loss=0.2792, pruned_loss=0.02521, over 7336.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03512, over 1176665.59 frames.], batch size: 22, lr: 3.42e-04
2022-04-29 20:29:12,804 INFO [train.py:763] (3/8) Epoch 22, batch 400, loss[loss=0.1835, simple_loss=0.2756, pruned_loss=0.04574, over 7186.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2681, pruned_loss=0.03532, over 1229734.12 frames.], batch size: 23, lr: 3.42e-04
2022-04-29 20:30:18,162 INFO [train.py:763] (3/8) Epoch 22, batch 450, loss[loss=0.1631, simple_loss=0.265, pruned_loss=0.03062, over 7247.00 frames.], tot_loss[loss=0.1702, simple_loss=0.269, pruned_loss=0.03568, over 1271303.03 frames.], batch size: 24, lr: 3.42e-04
2022-04-29 20:31:24,302 INFO [train.py:763] (3/8) Epoch 22, batch 500, loss[loss=0.1532, simple_loss=0.2558, pruned_loss=0.02528, over 6778.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2689, pruned_loss=0.03544, over 1306184.39 frames.], batch size: 15, lr: 3.41e-04
2022-04-29 20:32:31,784 INFO [train.py:763] (3/8) Epoch 22, batch 550, loss[loss=0.1598, simple_loss=0.2647, pruned_loss=0.02746, over 7307.00 frames.], tot_loss[loss=0.169, simple_loss=0.268, pruned_loss=0.03506, over 1336534.76 frames.], batch size: 24, lr: 3.41e-04
2022-04-29 20:33:39,038 INFO [train.py:763] (3/8) Epoch 22, batch 600, loss[loss=0.1571, simple_loss=0.2632, pruned_loss=0.02548, over 7119.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2685, pruned_loss=0.03521, over 1358629.56 frames.], batch size: 21, lr: 3.41e-04
2022-04-29 20:34:44,740 INFO [train.py:763] (3/8) Epoch 22, batch 650, loss[loss=0.1773, simple_loss=0.2823, pruned_loss=0.0362, over 6847.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2688, pruned_loss=0.03525, over 1373955.28 frames.], batch size: 31, lr: 3.41e-04
2022-04-29 20:35:51,883 INFO [train.py:763] (3/8) Epoch 22, batch 700, loss[loss=0.205, simple_loss=0.2924, pruned_loss=0.05882, over 4899.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2689, pruned_loss=0.03531, over 1379747.86 frames.], batch size: 52, lr: 3.41e-04
2022-04-29 20:36:59,160 INFO [train.py:763] (3/8) Epoch 22, batch 750, loss[loss=0.2072, simple_loss=0.3037, pruned_loss=0.05541, over 7194.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2693, pruned_loss=0.03547, over 1392239.25 frames.], batch size: 23, lr: 3.41e-04
2022-04-29 20:38:05,932 INFO [train.py:763] (3/8) Epoch 22, batch 800, loss[loss=0.1578, simple_loss=0.2627, pruned_loss=0.02646, over 7368.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2689, pruned_loss=0.03566, over 1395892.76 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:39:11,694 INFO [train.py:763] (3/8) Epoch 22, batch 850, loss[loss=0.1675, simple_loss=0.2712, pruned_loss=0.0319, over 7436.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2692, pruned_loss=0.03576, over 1403493.40 frames.], batch size: 20, lr: 3.41e-04
2022-04-29 20:40:16,908 INFO [train.py:763] (3/8) Epoch 22, batch 900, loss[loss=0.1639, simple_loss=0.2574, pruned_loss=0.03517, over 7160.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2702, pruned_loss=0.03597, over 1408203.46 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:41:22,120 INFO [train.py:763] (3/8) Epoch 22, batch 950, loss[loss=0.1898, simple_loss=0.2955, pruned_loss=0.04206, over 7039.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2703, pruned_loss=0.03565, over 1410175.07 frames.], batch size: 28, lr: 3.41e-04
2022-04-29 20:42:27,344 INFO [train.py:763] (3/8) Epoch 22, batch 1000, loss[loss=0.1735, simple_loss=0.2738, pruned_loss=0.03657, over 7360.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2698, pruned_loss=0.03533, over 1417500.78 frames.], batch size: 19, lr: 3.41e-04
2022-04-29 20:43:32,804 INFO [train.py:763] (3/8) Epoch 22, batch 1050, loss[loss=0.2059, simple_loss=0.2911, pruned_loss=0.06032, over 5286.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2692, pruned_loss=0.03534, over 1418126.30 frames.], batch size: 53, lr: 3.41e-04
2022-04-29 20:44:37,787 INFO [train.py:763] (3/8) Epoch 22, batch 1100, loss[loss=0.1393, simple_loss=0.2239, pruned_loss=0.02731, over 7283.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2693, pruned_loss=0.03559, over 1418237.64 frames.], batch size: 17, lr: 3.40e-04
2022-04-29 20:45:43,153 INFO [train.py:763] (3/8) Epoch 22, batch 1150, loss[loss=0.1582, simple_loss=0.2598, pruned_loss=0.0283, over 7429.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2693, pruned_loss=0.03529, over 1422256.47 frames.], batch size: 20, lr: 3.40e-04
2022-04-29 20:46:49,110 INFO [train.py:763] (3/8) Epoch 22, batch 1200, loss[loss=0.1513, simple_loss=0.2422, pruned_loss=0.03015, over 7286.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2687, pruned_loss=0.03543, over 1421174.80 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:47:55,635 INFO [train.py:763] (3/8) Epoch 22, batch 1250, loss[loss=0.1338, simple_loss=0.2264, pruned_loss=0.02057, over 6829.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2681, pruned_loss=0.03514, over 1424515.23 frames.], batch size: 15, lr: 3.40e-04
2022-04-29 20:49:00,848 INFO [train.py:763] (3/8) Epoch 22, batch 1300, loss[loss=0.1988, simple_loss=0.3018, pruned_loss=0.04793, over 7215.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2675, pruned_loss=0.03482, over 1427649.20 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:50:07,453 INFO [train.py:763] (3/8) Epoch 22, batch 1350, loss[loss=0.1531, simple_loss=0.2382, pruned_loss=0.03398, over 7263.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2665, pruned_loss=0.03448, over 1427473.48 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:51:13,803 INFO [train.py:763] (3/8) Epoch 22, batch 1400, loss[loss=0.1571, simple_loss=0.2647, pruned_loss=0.0247, over 7117.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2662, pruned_loss=0.0343, over 1427525.74 frames.], batch size: 21, lr: 3.40e-04
2022-04-29 20:52:19,583 INFO [train.py:763] (3/8) Epoch 22, batch 1450, loss[loss=0.1509, simple_loss=0.2455, pruned_loss=0.02811, over 7399.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03463, over 1420895.35 frames.], batch size: 18, lr: 3.40e-04
2022-04-29 20:53:25,449 INFO [train.py:763] (3/8) Epoch 22, batch 1500, loss[loss=0.1687, simple_loss=0.2745, pruned_loss=0.03143, over 7091.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03401, over 1422742.02 frames.], batch size: 28, lr: 3.40e-04
2022-04-29 20:54:31,378 INFO [train.py:763] (3/8) Epoch 22, batch 1550, loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03051, over 7346.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03395, over 1414651.91 frames.], batch size: 19, lr: 3.40e-04
2022-04-29 20:55:37,830 INFO [train.py:763] (3/8) Epoch 22, batch 1600, loss[loss=0.1713, simple_loss=0.2709, pruned_loss=0.0359, over 7212.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.0348, over 1412612.89 frames.], batch size: 21, lr: 3.40e-04
2022-04-29 20:56:43,433 INFO [train.py:763] (3/8) Epoch 22, batch 1650, loss[loss=0.1742, simple_loss=0.279, pruned_loss=0.03472, over 7363.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03503, over 1415757.46 frames.], batch size: 23, lr: 3.40e-04
2022-04-29 20:57:48,935 INFO [train.py:763] (3/8) Epoch 22, batch 1700, loss[loss=0.1787, simple_loss=0.2583, pruned_loss=0.0495, over 7395.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2672, pruned_loss=0.03504, over 1416560.56 frames.], batch size: 18, lr: 3.39e-04
2022-04-29 20:58:54,070 INFO [train.py:763] (3/8) Epoch 22, batch 1750, loss[loss=0.1989, simple_loss=0.2899, pruned_loss=0.05395, over 7150.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2685, pruned_loss=0.03548, over 1414983.09 frames.], batch size: 26, lr: 3.39e-04
2022-04-29 20:59:59,907 INFO [train.py:763] (3/8) Epoch 22, batch 1800, loss[loss=0.1909, simple_loss=0.2969, pruned_loss=0.04247, over 4815.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2684, pruned_loss=0.03515, over 1412290.11 frames.], batch size: 52, lr: 3.39e-04
2022-04-29 21:01:05,540 INFO [train.py:763] (3/8) Epoch 22, batch 1850, loss[loss=0.1603, simple_loss=0.2503, pruned_loss=0.03516, over 7419.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2676, pruned_loss=0.03468, over 1417900.51 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:02:10,914 INFO [train.py:763] (3/8) Epoch 22, batch 1900, loss[loss=0.1693, simple_loss=0.2737, pruned_loss=0.03244, over 7143.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03502, over 1421700.96 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:03:17,152 INFO [train.py:763] (3/8) Epoch 22, batch 1950, loss[loss=0.175, simple_loss=0.2812, pruned_loss=0.03442, over 7148.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2678, pruned_loss=0.03535, over 1419119.81 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:04:22,498 INFO [train.py:763] (3/8) Epoch 22, batch 2000, loss[loss=0.164, simple_loss=0.2589, pruned_loss=0.03453, over 7256.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2688, pruned_loss=0.03532, over 1422088.51 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:05:28,498 INFO [train.py:763] (3/8) Epoch 22, batch 2050, loss[loss=0.1703, simple_loss=0.2626, pruned_loss=0.03895, over 7235.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2679, pruned_loss=0.03488, over 1426003.39 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:06:35,597 INFO [train.py:763] (3/8) Epoch 22, batch 2100, loss[loss=0.1939, simple_loss=0.2951, pruned_loss=0.04641, over 7184.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2676, pruned_loss=0.03494, over 1420543.17 frames.], batch size: 23, lr: 3.39e-04
2022-04-29 21:07:42,147 INFO [train.py:763] (3/8) Epoch 22, batch 2150, loss[loss=0.1586, simple_loss=0.2597, pruned_loss=0.02871, over 7157.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2683, pruned_loss=0.03533, over 1421318.54 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:08:47,296 INFO [train.py:763] (3/8) Epoch 22, batch 2200, loss[loss=0.1794, simple_loss=0.2826, pruned_loss=0.03812, over 7152.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2691, pruned_loss=0.03597, over 1416050.79 frames.], batch size: 20, lr: 3.39e-04
2022-04-29 21:09:53,559 INFO [train.py:763] (3/8) Epoch 22, batch 2250, loss[loss=0.1974, simple_loss=0.2813, pruned_loss=0.05675, over 7156.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2689, pruned_loss=0.0361, over 1412341.51 frames.], batch size: 19, lr: 3.39e-04
2022-04-29 21:11:00,714 INFO [train.py:763] (3/8) Epoch 22, batch 2300, loss[loss=0.1727, simple_loss=0.277, pruned_loss=0.03419, over 7319.00 frames.], tot_loss[loss=0.1689, simple_loss=0.267, pruned_loss=0.03538, over 1414013.00 frames.], batch size: 21, lr: 3.38e-04
2022-04-29 21:12:07,637 INFO [train.py:763] (3/8) Epoch 22, batch 2350, loss[loss=0.1825, simple_loss=0.2791, pruned_loss=0.04292, over 7352.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2674, pruned_loss=0.03551, over 1415833.31 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:13:14,357 INFO [train.py:763] (3/8) Epoch 22, batch 2400, loss[loss=0.1751, simple_loss=0.2787, pruned_loss=0.03575, over 7311.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2679, pruned_loss=0.03523, over 1418545.72 frames.], batch size: 24, lr: 3.38e-04
2022-04-29 21:14:19,602 INFO [train.py:763] (3/8) Epoch 22, batch 2450, loss[loss=0.2153, simple_loss=0.3028, pruned_loss=0.06386, over 7194.00 frames.], tot_loss[loss=0.17, simple_loss=0.2687, pruned_loss=0.03562, over 1422425.63 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:15:24,878 INFO [train.py:763] (3/8) Epoch 22, batch 2500, loss[loss=0.1618, simple_loss=0.2649, pruned_loss=0.02935, over 6238.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03508, over 1419767.03 frames.], batch size: 37, lr: 3.38e-04
2022-04-29 21:16:30,044 INFO [train.py:763] (3/8) Epoch 22, batch 2550, loss[loss=0.1984, simple_loss=0.3047, pruned_loss=0.04605, over 7361.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03514, over 1420390.09 frames.], batch size: 23, lr: 3.38e-04
2022-04-29 21:17:35,649 INFO [train.py:763] (3/8) Epoch 22, batch 2600, loss[loss=0.155, simple_loss=0.2653, pruned_loss=0.02228, over 7330.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2672, pruned_loss=0.03531, over 1424743.22 frames.], batch size: 22, lr: 3.38e-04
2022-04-29 21:18:41,155 INFO [train.py:763] (3/8) Epoch 22, batch 2650, loss[loss=0.1792, simple_loss=0.2758, pruned_loss=0.04135, over 7270.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2665, pruned_loss=0.03522, over 1422090.05 frames.], batch size: 25, lr: 3.38e-04
2022-04-29 21:19:46,641 INFO [train.py:763] (3/8) Epoch 22, batch 2700, loss[loss=0.1636, simple_loss=0.2738, pruned_loss=0.02671, over 7158.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2666, pruned_loss=0.03503, over 1421848.89 frames.], batch size: 19, lr: 3.38e-04
2022-04-29 21:20:54,005 INFO [train.py:763] (3/8) Epoch 22, batch 2750, loss[loss=0.1485, simple_loss=0.2475, pruned_loss=0.02478, over 7168.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03512, over 1419792.73 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:22:00,023 INFO [train.py:763] (3/8) Epoch 22, batch 2800, loss[loss=0.1605, simple_loss=0.2558, pruned_loss=0.03264, over 7169.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2671, pruned_loss=0.03554, over 1419449.28 frames.], batch size: 18, lr: 3.38e-04
2022-04-29 21:23:05,436 INFO [train.py:763] (3/8) Epoch 22, batch 2850, loss[loss=0.1622, simple_loss=0.2631, pruned_loss=0.03064, over 7054.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2666, pruned_loss=0.03506, over 1421191.23 frames.], batch size: 28, lr: 3.38e-04
2022-04-29 21:24:10,663 INFO [train.py:763] (3/8) Epoch 22, batch 2900, loss[loss=0.1833, simple_loss=0.2794, pruned_loss=0.04355, over 7280.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2663, pruned_loss=0.03498, over 1422923.57 frames.], batch size: 25, lr: 3.37e-04
2022-04-29 21:25:15,971 INFO [train.py:763] (3/8) Epoch 22, batch 2950, loss[loss=0.1809, simple_loss=0.2884, pruned_loss=0.03673, over 7199.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2671, pruned_loss=0.03533, over 1423749.30 frames.], batch size: 22, lr: 3.37e-04
2022-04-29 21:26:20,972 INFO [train.py:763] (3/8) Epoch 22, batch 3000, loss[loss=0.1451, simple_loss=0.2359, pruned_loss=0.0271, over 7004.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2675, pruned_loss=0.03549, over 1424053.69 frames.], batch size: 16, lr: 3.37e-04
2022-04-29 21:26:20,973 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 21:26:36,379 INFO [train.py:792] (3/8) Epoch 22, validation: loss=0.1681, simple_loss=0.2667, pruned_loss=0.03474, over 698248.00 frames.
2022-04-29 21:27:41,667 INFO [train.py:763] (3/8) Epoch 22, batch 3050, loss[loss=0.1742, simple_loss=0.27, pruned_loss=0.03918, over 7166.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2672, pruned_loss=0.03549, over 1426815.87 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:28:58,460 INFO [train.py:763] (3/8) Epoch 22, batch 3100, loss[loss=0.1517, simple_loss=0.2449, pruned_loss=0.02921, over 7247.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2664, pruned_loss=0.03492, over 1425583.25 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:30:03,940 INFO [train.py:763] (3/8) Epoch 22, batch 3150, loss[loss=0.1756, simple_loss=0.2843, pruned_loss=0.03342, over 7333.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2668, pruned_loss=0.03499, over 1426921.34 frames.], batch size: 20, lr: 3.37e-04
2022-04-29 21:31:09,275 INFO [train.py:763] (3/8) Epoch 22, batch 3200, loss[loss=0.187, simple_loss=0.2991, pruned_loss=0.03747, over 7109.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2671, pruned_loss=0.03519, over 1427536.61 frames.], batch size: 21, lr: 3.37e-04
2022-04-29 21:32:14,548 INFO [train.py:763] (3/8) Epoch 22, batch 3250, loss[loss=0.1521, simple_loss=0.2572, pruned_loss=0.02346, over 6530.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2685, pruned_loss=0.03562, over 1422060.79 frames.], batch size: 39, lr: 3.37e-04
2022-04-29 21:33:19,826 INFO [train.py:763] (3/8) Epoch 22, batch 3300, loss[loss=0.1792, simple_loss=0.2905, pruned_loss=0.03394, over 7281.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2682, pruned_loss=0.03547, over 1423408.32 frames.], batch size: 24, lr: 3.37e-04
2022-04-29 21:34:25,355 INFO [train.py:763] (3/8) Epoch 22, batch 3350, loss[loss=0.1585, simple_loss=0.2545, pruned_loss=0.03123, over 7168.00 frames.], tot_loss[loss=0.1676, simple_loss=0.266, pruned_loss=0.03454, over 1428162.26 frames.], batch size: 26, lr: 3.37e-04
2022-04-29 21:35:30,549 INFO [train.py:763] (3/8) Epoch 22, batch 3400, loss[loss=0.143, simple_loss=0.2458, pruned_loss=0.02017, over 7171.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2666, pruned_loss=0.03461, over 1429492.49 frames.], batch size: 19, lr: 3.37e-04
2022-04-29 21:36:36,028 INFO [train.py:763] (3/8) Epoch 22, batch 3450, loss[loss=0.147, simple_loss=0.2457, pruned_loss=0.02419, over 6863.00 frames.], tot_loss[loss=0.167, simple_loss=0.2656, pruned_loss=0.0342, over 1430405.19 frames.], batch size: 15, lr: 3.37e-04
2022-04-29 21:37:41,466 INFO [train.py:763] (3/8) Epoch 22, batch 3500, loss[loss=0.1678, simple_loss=0.2542, pruned_loss=0.04068, over 7174.00 frames.], tot_loss[loss=0.167, simple_loss=0.2652, pruned_loss=0.03438, over 1431474.13 frames.], batch size: 16, lr: 3.37e-04
2022-04-29 21:38:46,762 INFO [train.py:763] (3/8) Epoch 22, batch 3550, loss[loss=0.1889, simple_loss=0.2664, pruned_loss=0.05571, over 7414.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2655, pruned_loss=0.03467, over 1430867.12 frames.], batch size: 18, lr: 3.36e-04
2022-04-29 21:39:52,003 INFO [train.py:763] (3/8) Epoch 22, batch 3600, loss[loss=0.1404, simple_loss=0.2328, pruned_loss=0.02397, over 7273.00 frames.], tot_loss[loss=0.168, simple_loss=0.2666, pruned_loss=0.03474, over 1432267.50 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:40:57,415 INFO [train.py:763] (3/8) Epoch 22, batch 3650, loss[loss=0.1793, simple_loss=0.2777, pruned_loss=0.04044, over 6413.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2665, pruned_loss=0.03481, over 1431694.82 frames.], batch size: 38, lr: 3.36e-04
2022-04-29 21:42:03,750 INFO [train.py:763] (3/8) Epoch 22, batch 3700, loss[loss=0.1578, simple_loss=0.2656, pruned_loss=0.02502, over 7160.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2673, pruned_loss=0.03489, over 1430944.93 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:43:09,190 INFO [train.py:763] (3/8) Epoch 22, batch 3750, loss[loss=0.1416, simple_loss=0.2371, pruned_loss=0.02309, over 7273.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03512, over 1428276.95 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:44:14,438 INFO [train.py:763] (3/8) Epoch 22, batch 3800, loss[loss=0.2213, simple_loss=0.3102, pruned_loss=0.06616, over 7392.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2678, pruned_loss=0.03516, over 1429433.81 frames.], batch size: 23, lr: 3.36e-04
2022-04-29 21:45:19,889 INFO [train.py:763] (3/8) Epoch 22, batch 3850, loss[loss=0.1873, simple_loss=0.286, pruned_loss=0.04433, over 7048.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2671, pruned_loss=0.03497, over 1429330.36 frames.], batch size: 28, lr: 3.36e-04
2022-04-29 21:46:26,375 INFO [train.py:763] (3/8) Epoch 22, batch 3900, loss[loss=0.1788, simple_loss=0.2837, pruned_loss=0.03692, over 7125.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.03526, over 1429472.75 frames.], batch size: 21, lr: 3.36e-04
2022-04-29 21:47:31,491 INFO [train.py:763] (3/8) Epoch 22, batch 3950, loss[loss=0.1665, simple_loss=0.2571, pruned_loss=0.03797, over 7159.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2682, pruned_loss=0.03544, over 1429097.25 frames.], batch size: 19, lr: 3.36e-04
2022-04-29 21:48:36,596 INFO [train.py:763] (3/8) Epoch 22, batch 4000, loss[loss=0.1664, simple_loss=0.2441, pruned_loss=0.04437, over 7287.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2683, pruned_loss=0.03537, over 1426042.43 frames.], batch size: 17, lr: 3.36e-04
2022-04-29 21:49:42,509 INFO [train.py:763] (3/8) Epoch 22, batch 4050, loss[loss=0.181, simple_loss=0.2714, pruned_loss=0.04525, over 7248.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2695, pruned_loss=0.03587, over 1421013.01 frames.], batch size: 16, lr: 3.36e-04
2022-04-29 21:50:49,117 INFO [train.py:763] (3/8) Epoch 22, batch 4100, loss[loss=0.1584, simple_loss=0.2528, pruned_loss=0.03199, over 6796.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2692, pruned_loss=0.03609, over 1418873.89 frames.], batch size: 15, lr: 3.36e-04
2022-04-29 21:51:54,117 INFO [train.py:763] (3/8) Epoch 22, batch 4150, loss[loss=0.1713, simple_loss=0.2693, pruned_loss=0.03659, over 7324.00 frames.], tot_loss[loss=0.171, simple_loss=0.2697, pruned_loss=0.03617, over 1418683.26 frames.], batch size: 21, lr: 3.35e-04
2022-04-29 21:52:59,299 INFO [train.py:763] (3/8) Epoch 22, batch 4200, loss[loss=0.1489, simple_loss=0.2351, pruned_loss=0.03133, over 7016.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2696, pruned_loss=0.036, over 1422501.91 frames.], batch size: 16, lr: 3.35e-04
2022-04-29 21:54:05,490 INFO [train.py:763] (3/8) Epoch 22, batch 4250, loss[loss=0.1789, simple_loss=0.2833, pruned_loss=0.03718, over 7232.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2687, pruned_loss=0.03547, over 1423202.93 frames.], batch size: 20, lr: 3.35e-04
2022-04-29 21:55:12,485 INFO [train.py:763] (3/8) Epoch 22, batch 4300, loss[loss=0.147, simple_loss=0.2425, pruned_loss=0.0257, over 7155.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.03512, over 1420062.69 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:56:19,737 INFO [train.py:763] (3/8) Epoch 22, batch 4350, loss[loss=0.1493, simple_loss=0.2391, pruned_loss=0.02973, over 6804.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2665, pruned_loss=0.03497, over 1421145.09 frames.], batch size: 15, lr: 3.35e-04
2022-04-29 21:57:26,789 INFO [train.py:763] (3/8) Epoch 22, batch 4400, loss[loss=0.1579, simple_loss=0.2542, pruned_loss=0.03077, over 7059.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2657, pruned_loss=0.03468, over 1418591.51 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 21:58:31,943 INFO [train.py:763] (3/8) Epoch 22, batch 4450, loss[loss=0.2325, simple_loss=0.313, pruned_loss=0.07603, over 4955.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2663, pruned_loss=0.03522, over 1412942.34 frames.], batch size: 52, lr: 3.35e-04
2022-04-29 21:59:36,917 INFO [train.py:763] (3/8) Epoch 22, batch 4500, loss[loss=0.1462, simple_loss=0.2428, pruned_loss=0.02481, over 7062.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2673, pruned_loss=0.03551, over 1412081.80 frames.], batch size: 18, lr: 3.35e-04
2022-04-29 22:00:41,211 INFO [train.py:763] (3/8) Epoch 22, batch 4550, loss[loss=0.1788, simple_loss=0.2816, pruned_loss=0.03803, over 5151.00 frames.], tot_loss[loss=0.173, simple_loss=0.2707, pruned_loss=0.03764, over 1355279.06 frames.], batch size: 52, lr: 3.35e-04
2022-04-29 22:02:00,631 INFO [train.py:763] (3/8) Epoch 23, batch 0, loss[loss=0.1721, simple_loss=0.2475, pruned_loss=0.04835, over 6844.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2475, pruned_loss=0.04835, over 6844.00 frames.], batch size: 15, lr: 3.28e-04
2022-04-29 22:03:02,969 INFO [train.py:763] (3/8) Epoch 23, batch 50, loss[loss=0.1358, simple_loss=0.2332, pruned_loss=0.0192, over 7272.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2661, pruned_loss=0.03463, over 316762.67 frames.], batch size: 17, lr: 3.28e-04
2022-04-29 22:04:05,007 INFO [train.py:763] (3/8) Epoch 23, batch 100, loss[loss=0.177, simple_loss=0.2849, pruned_loss=0.03452, over 7332.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2672, pruned_loss=0.03421, over 568049.26 frames.], batch size: 20, lr: 3.28e-04
2022-04-29 22:05:10,554 INFO [train.py:763] (3/8) Epoch 23, batch 150, loss[loss=0.2005, simple_loss=0.304, pruned_loss=0.04857, over 7379.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2674, pruned_loss=0.03437, over 753495.41 frames.], batch size: 23, lr: 3.28e-04
2022-04-29 22:06:15,912 INFO [train.py:763] (3/8) Epoch 23, batch 200, loss[loss=0.1791, simple_loss=0.2772, pruned_loss=0.04054, over 7195.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2658, pruned_loss=0.03389, over 903947.49 frames.], batch size: 22, lr: 3.28e-04
2022-04-29 22:07:21,262 INFO [train.py:763] (3/8) Epoch 23, batch 250, loss[loss=0.165, simple_loss=0.2725, pruned_loss=0.02873, over 7414.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03379, over 1016293.16 frames.], batch size: 21, lr: 3.28e-04
2022-04-29 22:08:27,022 INFO [train.py:763] (3/8) Epoch 23, batch 300, loss[loss=0.1582, simple_loss=0.2609, pruned_loss=0.02769, over 7150.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2658, pruned_loss=0.03382, over 1107245.45 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:09:32,880 INFO [train.py:763] (3/8) Epoch 23, batch 350, loss[loss=0.1724, simple_loss=0.282, pruned_loss=0.03137, over 7294.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.0338, over 1178596.11 frames.], batch size: 25, lr: 3.27e-04
2022-04-29 22:10:38,044 INFO [train.py:763] (3/8) Epoch 23, batch 400, loss[loss=0.1993, simple_loss=0.2931, pruned_loss=0.05282, over 7274.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2657, pruned_loss=0.03336, over 1228660.81 frames.], batch size: 24, lr: 3.27e-04
2022-04-29 22:11:43,824 INFO [train.py:763] (3/8) Epoch 23, batch 450, loss[loss=0.1518, simple_loss=0.2591, pruned_loss=0.0222, over 7149.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2671, pruned_loss=0.03373, over 1274417.70 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:12:49,134 INFO [train.py:763] (3/8) Epoch 23, batch 500, loss[loss=0.1634, simple_loss=0.2576, pruned_loss=0.03461, over 7355.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2675, pruned_loss=0.03402, over 1306061.69 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:13:54,751 INFO [train.py:763] (3/8) Epoch 23, batch 550, loss[loss=0.1906, simple_loss=0.2877, pruned_loss=0.04674, over 7211.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2671, pruned_loss=0.03427, over 1335181.08 frames.], batch size: 22, lr: 3.27e-04
2022-04-29 22:15:00,600 INFO [train.py:763] (3/8) Epoch 23, batch 600, loss[loss=0.1843, simple_loss=0.285, pruned_loss=0.04177, over 7369.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03394, over 1353004.55 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:16:06,054 INFO [train.py:763] (3/8) Epoch 23, batch 650, loss[loss=0.1395, simple_loss=0.2337, pruned_loss=0.02261, over 7359.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2656, pruned_loss=0.03408, over 1363791.51 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:17:12,009 INFO [train.py:763] (3/8) Epoch 23, batch 700, loss[loss=0.1862, simple_loss=0.2849, pruned_loss=0.04374, over 7128.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2643, pruned_loss=0.0337, over 1380423.58 frames.], batch size: 26, lr: 3.27e-04
2022-04-29 22:18:17,839 INFO [train.py:763] (3/8) Epoch 23, batch 750, loss[loss=0.1412, simple_loss=0.2334, pruned_loss=0.02451, over 6982.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03388, over 1391610.29 frames.], batch size: 16, lr: 3.27e-04
2022-04-29 22:19:23,431 INFO [train.py:763] (3/8) Epoch 23, batch 800, loss[loss=0.1457, simple_loss=0.2359, pruned_loss=0.02777, over 7255.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2649, pruned_loss=0.03379, over 1399010.39 frames.], batch size: 19, lr: 3.27e-04
2022-04-29 22:20:28,943 INFO [train.py:763] (3/8) Epoch 23, batch 850, loss[loss=0.2018, simple_loss=0.2955, pruned_loss=0.05411, over 6771.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2649, pruned_loss=0.03385, over 1405513.06 frames.], batch size: 31, lr: 3.27e-04
2022-04-29 22:21:34,329 INFO [train.py:763] (3/8) Epoch 23, batch 900, loss[loss=0.1592, simple_loss=0.2535, pruned_loss=0.0324, over 7424.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2647, pruned_loss=0.03371, over 1410729.17 frames.], batch size: 20, lr: 3.27e-04
2022-04-29 22:22:49,568 INFO [train.py:763] (3/8) Epoch 23, batch 950, loss[loss=0.1744, simple_loss=0.2784, pruned_loss=0.0352, over 6498.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2634, pruned_loss=0.03317, over 1415294.61 frames.], batch size: 38, lr: 3.26e-04
2022-04-29 22:23:55,238 INFO [train.py:763] (3/8) Epoch 23, batch 1000, loss[loss=0.2006, simple_loss=0.3018, pruned_loss=0.04973, over 7319.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2641, pruned_loss=0.03366, over 1417183.53 frames.], batch size: 21, lr: 3.26e-04
2022-04-29 22:25:00,701 INFO [train.py:763] (3/8) Epoch 23, batch 1050, loss[loss=0.1413, simple_loss=0.2496, pruned_loss=0.0165, over 7232.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2653, pruned_loss=0.03446, over 1411224.24 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:26:07,027 INFO [train.py:763] (3/8) Epoch 23, batch 1100, loss[loss=0.1729, simple_loss=0.2774, pruned_loss=0.03417, over 7140.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2661, pruned_loss=0.0347, over 1411629.52 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:27:12,598 INFO [train.py:763] (3/8) Epoch 23, batch 1150, loss[loss=0.1741, simple_loss=0.2785, pruned_loss=0.03479, over 6505.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2656, pruned_loss=0.03446, over 1415276.43 frames.], batch size: 38, lr: 3.26e-04
2022-04-29 22:28:17,833 INFO [train.py:763] (3/8) Epoch 23, batch 1200, loss[loss=0.1622, simple_loss=0.2546, pruned_loss=0.03493, over 7169.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2661, pruned_loss=0.03429, over 1417498.23 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:29:23,307 INFO [train.py:763] (3/8) Epoch 23, batch 1250, loss[loss=0.1533, simple_loss=0.2593, pruned_loss=0.02364, over 7334.00 frames.], tot_loss[loss=0.167, simple_loss=0.2654, pruned_loss=0.0343, over 1417910.64 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:30:28,892 INFO [train.py:763] (3/8) Epoch 23, batch 1300, loss[loss=0.1685, simple_loss=0.2811, pruned_loss=0.02797, over 6780.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2655, pruned_loss=0.03447, over 1419738.92 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:31:51,694 INFO [train.py:763] (3/8) Epoch 23, batch 1350, loss[loss=0.1483, simple_loss=0.2438, pruned_loss=0.02638, over 7407.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2664, pruned_loss=0.03463, over 1425469.46 frames.], batch size: 18, lr: 3.26e-04
2022-04-29 22:32:57,243 INFO [train.py:763] (3/8) Epoch 23, batch 1400, loss[loss=0.1721, simple_loss=0.2792, pruned_loss=0.03248, over 7182.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2667, pruned_loss=0.03478, over 1424065.71 frames.], batch size: 26, lr: 3.26e-04
2022-04-29 22:34:20,490 INFO [train.py:763] (3/8) Epoch 23, batch 1450, loss[loss=0.1737, simple_loss=0.2756, pruned_loss=0.03589, over 7144.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03469, over 1421917.90 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:35:53,262 INFO [train.py:763] (3/8) Epoch 23, batch 1500, loss[loss=0.171, simple_loss=0.2707, pruned_loss=0.03559, over 7147.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03504, over 1421015.42 frames.], batch size: 20, lr: 3.26e-04
2022-04-29 22:36:59,419 INFO [train.py:763] (3/8) Epoch 23, batch 1550, loss[loss=0.1884, simple_loss=0.2868, pruned_loss=0.04504, over 6639.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2663, pruned_loss=0.03477, over 1421112.91 frames.], batch size: 31, lr: 3.26e-04
2022-04-29 22:38:04,558 INFO [train.py:763] (3/8) Epoch 23, batch 1600, loss[loss=0.1766, simple_loss=0.28, pruned_loss=0.03664, over 7322.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03466, over 1422473.26 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:39:10,553 INFO [train.py:763] (3/8) Epoch 23, batch 1650, loss[loss=0.1504, simple_loss=0.243, pruned_loss=0.02888, over 7237.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2671, pruned_loss=0.03501, over 1414632.61 frames.], batch size: 16, lr: 3.25e-04
2022-04-29 22:40:17,830 INFO [train.py:763] (3/8) Epoch 23, batch 1700, loss[loss=0.1732, simple_loss=0.2786, pruned_loss=0.03389, over 7322.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2672, pruned_loss=0.0353, over 1419161.90 frames.], batch size: 21, lr: 3.25e-04
2022-04-29 22:41:24,853 INFO [train.py:763] (3/8) Epoch 23, batch 1750, loss[loss=0.1478, simple_loss=0.2427, pruned_loss=0.02644, over 7072.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2671, pruned_loss=0.03523, over 1421327.88 frames.], batch size: 18, lr: 3.25e-04
2022-04-29 22:42:30,370 INFO [train.py:763] (3/8) Epoch 23, batch 1800, loss[loss=0.1809, simple_loss=0.2873, pruned_loss=0.03724, over 7331.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2675, pruned_loss=0.03514, over 1421828.36 frames.], batch size: 22, lr: 3.25e-04
2022-04-29 22:43:35,679 INFO [train.py:763] (3/8) Epoch 23, batch 1850, loss[loss=0.1561, simple_loss=0.2707, pruned_loss=0.02076, over 7295.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2677, pruned_loss=0.03503, over 1425628.89 frames.], batch size: 24, lr: 3.25e-04
2022-04-29 22:44:41,102 INFO [train.py:763] (3/8) Epoch 23, batch 1900, loss[loss=0.1668, simple_loss=0.2769, pruned_loss=0.02837, over 7096.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2676, pruned_loss=0.03491, over 1423240.97 frames.], batch size: 28, lr: 3.25e-04
2022-04-29 22:45:46,545 INFO [train.py:763] (3/8) Epoch 23, batch 1950, loss[loss=0.1762, simple_loss=0.2759, pruned_loss=0.03825, over 7448.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2673, pruned_loss=0.03471, over 1424622.93 frames.], batch size: 22, lr: 3.25e-04
2022-04-29 22:46:52,056 INFO [train.py:763] (3/8) Epoch 23, batch 2000, loss[loss=0.1769, simple_loss=0.2641, pruned_loss=0.04482, over 5364.00 frames.], tot_loss[loss=0.1691, simple_loss=0.268, pruned_loss=0.03505, over 1422959.00 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:47:58,953 INFO [train.py:763] (3/8) Epoch 23, batch 2050, loss[loss=0.1436, simple_loss=0.2424, pruned_loss=0.02239, over 7442.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2684, pruned_loss=0.03512, over 1421831.87 frames.], batch size: 20, lr: 3.25e-04
2022-04-29 22:49:05,148 INFO [train.py:763] (3/8) Epoch 23, batch 2100, loss[loss=0.141, simple_loss=0.2316, pruned_loss=0.02521, over 7021.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2677, pruned_loss=0.03478, over 1422960.08 frames.], batch size: 16, lr: 3.25e-04
2022-04-29 22:50:10,653 INFO [train.py:763] (3/8) Epoch 23, batch 2150, loss[loss=0.1772, simple_loss=0.2671, pruned_loss=0.0436, over 4884.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2669, pruned_loss=0.03435, over 1420580.89 frames.], batch size: 52, lr: 3.25e-04
2022-04-29 22:51:16,164 INFO [train.py:763] (3/8) Epoch 23, batch 2200, loss[loss=0.1414, simple_loss=0.235, pruned_loss=0.02388, over 7150.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2661, pruned_loss=0.03422, over 1419625.24 frames.], batch size: 17, lr: 3.25e-04
2022-04-29 22:52:21,331 INFO [train.py:763] (3/8) Epoch 23, batch 2250, loss[loss=0.1652, simple_loss=0.2685, pruned_loss=0.03093, over 7303.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2669, pruned_loss=0.03469, over 1409999.10 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 22:53:28,270 INFO [train.py:763] (3/8) Epoch 23, batch 2300, loss[loss=0.1385, simple_loss=0.2281, pruned_loss=0.02443, over 7299.00 frames.], tot_loss[loss=0.1665, simple_loss=0.265, pruned_loss=0.03398, over 1416437.90 frames.], batch size: 17, lr: 3.24e-04
2022-04-29 22:54:34,464 INFO [train.py:763] (3/8) Epoch 23, batch 2350, loss[loss=0.1587, simple_loss=0.2624, pruned_loss=0.02745, over 7345.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03455, over 1417851.80 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 22:55:39,710 INFO [train.py:763] (3/8) Epoch 23, batch 2400, loss[loss=0.1426, simple_loss=0.2365, pruned_loss=0.02432, over 7224.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2671, pruned_loss=0.03458, over 1421138.95 frames.], batch size: 16, lr: 3.24e-04
2022-04-29 22:56:45,971 INFO [train.py:763] (3/8) Epoch 23, batch 2450, loss[loss=0.1859, simple_loss=0.2777, pruned_loss=0.04709, over 7226.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2673, pruned_loss=0.03496, over 1417199.37 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 22:57:51,398 INFO [train.py:763] (3/8) Epoch 23, batch 2500, loss[loss=0.1684, simple_loss=0.2665, pruned_loss=0.03512, over 7324.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2667, pruned_loss=0.03477, over 1417831.75 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 22:58:56,885 INFO [train.py:763] (3/8) Epoch 23, batch 2550, loss[loss=0.2121, simple_loss=0.3032, pruned_loss=0.06054, over 5096.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2662, pruned_loss=0.03486, over 1413703.77 frames.], batch size: 52, lr: 3.24e-04
2022-04-29 23:00:02,920 INFO [train.py:763] (3/8) Epoch 23, batch 2600, loss[loss=0.1497, simple_loss=0.2499, pruned_loss=0.0248, over 7288.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2673, pruned_loss=0.035, over 1417022.44 frames.], batch size: 18, lr: 3.24e-04
2022-04-29 23:01:08,568 INFO [train.py:763] (3/8) Epoch 23, batch 2650, loss[loss=0.1737, simple_loss=0.2826, pruned_loss=0.03238, over 7327.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2666, pruned_loss=0.03488, over 1417697.15 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:02:14,022 INFO [train.py:763] (3/8) Epoch 23, batch 2700, loss[loss=0.1648, simple_loss=0.2732, pruned_loss=0.02818, over 7342.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2664, pruned_loss=0.03447, over 1422370.82 frames.], batch size: 22, lr: 3.24e-04
2022-04-29 23:03:19,902 INFO [train.py:763] (3/8) Epoch 23, batch 2750, loss[loss=0.1751, simple_loss=0.2827, pruned_loss=0.03376, over 7412.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03428, over 1425740.34 frames.], batch size: 21, lr: 3.24e-04
2022-04-29 23:04:25,096 INFO [train.py:763] (3/8) Epoch 23, batch 2800, loss[loss=0.1601, simple_loss=0.2602, pruned_loss=0.02996, over 7248.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2672, pruned_loss=0.03449, over 1422107.51 frames.], batch size: 20, lr: 3.24e-04
2022-04-29 23:05:30,273 INFO [train.py:763] (3/8) Epoch 23, batch 2850, loss[loss=0.173, simple_loss=0.2742, pruned_loss=0.03587, over 7360.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2689, pruned_loss=0.03509, over 1422749.82 frames.], batch size: 19, lr: 3.24e-04
2022-04-29 23:06:35,472 INFO [train.py:763] (3/8) Epoch 23, batch 2900, loss[loss=0.1577, simple_loss=0.2539, pruned_loss=0.0307, over 7335.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2687, pruned_loss=0.03518, over 1422536.82 frames.], batch size: 25, lr: 3.24e-04
2022-04-29 23:07:40,683 INFO [train.py:763] (3/8) Epoch 23, batch 2950, loss[loss=0.1416, simple_loss=0.2309, pruned_loss=0.02612, over 7316.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2677, pruned_loss=0.0349, over 1426055.43 frames.], batch size: 17, lr: 3.23e-04
2022-04-29 23:08:45,891 INFO [train.py:763] (3/8) Epoch 23, batch 3000, loss[loss=0.2014, simple_loss=0.2873, pruned_loss=0.05773, over 7117.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2674, pruned_loss=0.03517, over 1421785.34 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:08:45,892 INFO [train.py:783] (3/8) Computing validation loss
2022-04-29 23:09:01,228 INFO [train.py:792] (3/8) Epoch 23, validation: loss=0.1683, simple_loss=0.2665, pruned_loss=0.03509, over 698248.00 frames.
2022-04-29 23:10:07,037 INFO [train.py:763] (3/8) Epoch 23, batch 3050, loss[loss=0.1538, simple_loss=0.2462, pruned_loss=0.03074, over 7272.00 frames.], tot_loss[loss=0.169, simple_loss=0.2678, pruned_loss=0.03507, over 1416857.16 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:11:12,528 INFO [train.py:763] (3/8) Epoch 23, batch 3100, loss[loss=0.1745, simple_loss=0.2765, pruned_loss=0.03622, over 6853.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2675, pruned_loss=0.0353, over 1420859.59 frames.], batch size: 31, lr: 3.23e-04
2022-04-29 23:12:19,058 INFO [train.py:763] (3/8) Epoch 23, batch 3150, loss[loss=0.1565, simple_loss=0.2369, pruned_loss=0.03809, over 7424.00 frames.], tot_loss[loss=0.169, simple_loss=0.2674, pruned_loss=0.03524, over 1422731.49 frames.], batch size: 17, lr: 3.23e-04
2022-04-29 23:13:26,791 INFO [train.py:763] (3/8) Epoch 23, batch 3200, loss[loss=0.1584, simple_loss=0.2663, pruned_loss=0.02523, over 7320.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2668, pruned_loss=0.03482, over 1426902.78 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:14:33,553 INFO [train.py:763] (3/8) Epoch 23, batch 3250, loss[loss=0.1631, simple_loss=0.2569, pruned_loss=0.03466, over 7158.00 frames.], tot_loss[loss=0.1684, simple_loss=0.267, pruned_loss=0.03486, over 1428659.35 frames.], batch size: 18, lr: 3.23e-04
2022-04-29 23:15:38,817 INFO [train.py:763] (3/8) Epoch 23, batch 3300, loss[loss=0.176, simple_loss=0.2729, pruned_loss=0.03958, over 7298.00 frames.], tot_loss[loss=0.1685, simple_loss=0.267, pruned_loss=0.03495, over 1428402.25 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:16:45,587 INFO [train.py:763] (3/8) Epoch 23, batch 3350, loss[loss=0.1621, simple_loss=0.2606, pruned_loss=0.03177, over 7268.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2673, pruned_loss=0.03518, over 1424679.68 frames.], batch size: 24, lr: 3.23e-04
2022-04-29 23:17:51,525 INFO [train.py:763] (3/8) Epoch 23, batch 3400, loss[loss=0.1649, simple_loss=0.2544, pruned_loss=0.03772, over 7353.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2672, pruned_loss=0.03507, over 1428322.65 frames.], batch size: 19, lr: 3.23e-04
2022-04-29 23:18:56,727 INFO [train.py:763] (3/8) Epoch 23, batch 3450, loss[loss=0.1543, simple_loss=0.2606, pruned_loss=0.02401, over 7326.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2678, pruned_loss=0.03479, over 1423373.50 frames.], batch size: 22, lr: 3.23e-04
2022-04-29 23:20:02,251 INFO [train.py:763] (3/8) Epoch 23, batch 3500, loss[loss=0.147, simple_loss=0.2392, pruned_loss=0.02738, over 7204.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2665, pruned_loss=0.03461, over 1421730.93 frames.], batch size: 16, lr: 3.23e-04
2022-04-29 23:21:08,251 INFO [train.py:763] (3/8) Epoch 23, batch 3550, loss[loss=0.1932, simple_loss=0.2993, pruned_loss=0.04357, over 7124.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2672, pruned_loss=0.03519, over 1423021.77 frames.], batch size: 21, lr: 3.23e-04
2022-04-29 23:22:13,612 INFO [train.py:763] (3/8) Epoch 23, batch 3600, loss[loss=0.1806, simple_loss=0.2785, pruned_loss=0.04134, over 7065.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2674, pruned_loss=0.03484, over 1422936.26 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:23:18,841 INFO [train.py:763] (3/8) Epoch 23, batch 3650, loss[loss=0.1544, simple_loss=0.2492, pruned_loss=0.02981, over 7362.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2679, pruned_loss=0.03486, over 1423102.07 frames.], batch size: 19, lr: 3.22e-04
2022-04-29 23:24:24,041 INFO [train.py:763] (3/8) Epoch 23, batch 3700, loss[loss=0.1672, simple_loss=0.2727, pruned_loss=0.03085, over 6340.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2683, pruned_loss=0.03522, over 1420648.03 frames.], batch size: 38, lr: 3.22e-04
2022-04-29 23:25:30,842 INFO [train.py:763] (3/8) Epoch 23, batch 3750, loss[loss=0.1364, simple_loss=0.2318, pruned_loss=0.02047, over 7278.00 frames.], tot_loss[loss=0.169, simple_loss=0.2679, pruned_loss=0.03503, over 1421485.17 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:26:37,716 INFO [train.py:763] (3/8) Epoch 23, batch 3800, loss[loss=0.1826, simple_loss=0.2776, pruned_loss=0.04384, over 7426.00 frames.], tot_loss[loss=0.169, simple_loss=0.2677, pruned_loss=0.03518, over 1423496.51 frames.], batch size: 20, lr: 3.22e-04
2022-04-29 23:27:43,263 INFO [train.py:763] (3/8) Epoch 23, batch 3850, loss[loss=0.1938, simple_loss=0.2851, pruned_loss=0.05119, over 5007.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2672, pruned_loss=0.03501, over 1419582.83 frames.], batch size: 52, lr: 3.22e-04
2022-04-29 23:28:48,634 INFO [train.py:763] (3/8) Epoch 23, batch 3900, loss[loss=0.1558, simple_loss=0.2564, pruned_loss=0.02763, over 6761.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2668, pruned_loss=0.03511, over 1417099.66 frames.], batch size: 31, lr: 3.22e-04
2022-04-29 23:29:53,689 INFO [train.py:763] (3/8) Epoch 23, batch 3950, loss[loss=0.1379, simple_loss=0.2254, pruned_loss=0.02514, over 7141.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2668, pruned_loss=0.03492, over 1417096.54 frames.], batch size: 17, lr: 3.22e-04
2022-04-29 23:30:59,586 INFO [train.py:763] (3/8) Epoch 23, batch 4000, loss[loss=0.1969, simple_loss=0.2953, pruned_loss=0.04923, over 7207.00 frames.], tot_loss[loss=0.169, simple_loss=0.2676, pruned_loss=0.0352, over 1415795.78 frames.], batch size: 22, lr: 3.22e-04
2022-04-29 23:32:05,446 INFO [train.py:763] (3/8) Epoch 23, batch 4050, loss[loss=0.1986, simple_loss=0.291, pruned_loss=0.0531, over 5001.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2669, pruned_loss=0.03497, over 1416665.62 frames.], batch size: 52, lr: 3.22e-04
2022-04-29 23:33:10,717 INFO [train.py:763] (3/8) Epoch 23, batch 4100, loss[loss=0.1586, simple_loss=0.2529, pruned_loss=0.03213, over 7271.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03519, over 1417293.61 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:34:16,153 INFO [train.py:763] (3/8) Epoch 23, batch 4150, loss[loss=0.1548, simple_loss=0.2506, pruned_loss=0.02954, over 7422.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2666, pruned_loss=0.03536, over 1419470.11 frames.], batch size: 17, lr: 3.22e-04
2022-04-29 23:35:21,251 INFO [train.py:763] (3/8) Epoch 23, batch 4200, loss[loss=0.1641, simple_loss=0.2589, pruned_loss=0.0347, over 7281.00 frames.], tot_loss[loss=0.1696, simple_loss=0.268, pruned_loss=0.0356, over 1420210.94 frames.], batch size: 18, lr: 3.22e-04
2022-04-29 23:36:26,915 INFO [train.py:763] (3/8) Epoch 23, batch 4250, loss[loss=0.1655, simple_loss=0.2591, pruned_loss=0.03598, over 7392.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2669, pruned_loss=0.03513, over 1417878.08 frames.], batch size: 23, lr: 3.22e-04
2022-04-29 23:37:32,233 INFO [train.py:763] (3/8) Epoch 23, batch 4300, loss[loss=0.1645, simple_loss=0.2653, pruned_loss=0.03186, over 7262.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2656, pruned_loss=0.03486, over 1418190.60 frames.], batch size: 16, lr: 3.21e-04
2022-04-29 23:38:37,630 INFO [train.py:763] (3/8) Epoch 23, batch 4350, loss[loss=0.171, simple_loss=0.2739, pruned_loss=0.03405, over 6827.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2664, pruned_loss=0.03495, over 1415227.08 frames.], batch size: 31, lr: 3.21e-04
2022-04-29 23:39:43,230 INFO [train.py:763] (3/8) Epoch 23, batch 4400, loss[loss=0.1879, simple_loss=0.296, pruned_loss=0.03985, over 6442.00 frames.], tot_loss[loss=0.169, simple_loss=0.2673, pruned_loss=0.03538, over 1408747.70 frames.], batch size: 38, lr: 3.21e-04
2022-04-29 23:40:48,374 INFO [train.py:763] (3/8) Epoch 23, batch 4450, loss[loss=0.1894, simple_loss=0.2899, pruned_loss=0.04441, over 6440.00 frames.], tot_loss[loss=0.168, simple_loss=0.2661, pruned_loss=0.03493, over 1410498.65 frames.], batch size: 38, lr: 3.21e-04
2022-04-29 23:41:53,042 INFO [train.py:763] (3/8) Epoch 23, batch 4500, loss[loss=0.1807, simple_loss=0.2774, pruned_loss=0.04203, over 6378.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2676, pruned_loss=0.03546, over 1396044.29 frames.], batch size: 37, lr: 3.21e-04
2022-04-29 23:42:58,310 INFO [train.py:763] (3/8) Epoch 23, batch 4550, loss[loss=0.1758, simple_loss=0.2871, pruned_loss=0.03223, over 7270.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2677, pruned_loss=0.03541, over 1383720.87 frames.], batch size: 24, lr: 3.21e-04
2022-04-29 23:44:17,935 INFO [train.py:763] (3/8) Epoch 24, batch 0, loss[loss=0.1998, simple_loss=0.296, pruned_loss=0.05181, over 7059.00 frames.], tot_loss[loss=0.1998, simple_loss=0.296, pruned_loss=0.05181, over 7059.00 frames.], batch size: 18, lr: 3.15e-04
2022-04-29 23:45:23,858 INFO [train.py:763] (3/8) Epoch 24, batch 50, loss[loss=0.1841, simple_loss=0.2727, pruned_loss=0.04781, over 7272.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2709, pruned_loss=0.03651, over 321764.34 frames.], batch size: 19, lr: 3.15e-04
2022-04-29 23:46:30,363 INFO [train.py:763] (3/8) Epoch 24, batch 100, loss[loss=0.1561, simple_loss=0.2561, pruned_loss=0.02802, over 7325.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2672, pruned_loss=0.03488, over 569247.89 frames.], batch size: 20, lr: 3.15e-04
2022-04-29 23:47:35,974 INFO [train.py:763] (3/8) Epoch 24, batch 150, loss[loss=0.1593, simple_loss=0.2621, pruned_loss=0.0282, over 7312.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2671, pruned_loss=0.03392, over 760797.64 frames.], batch size: 21, lr: 3.14e-04
2022-04-29 23:48:41,593 INFO [train.py:763] (3/8) Epoch 24, batch 200, loss[loss=0.1565, simple_loss=0.2559, pruned_loss=0.02855, over 6846.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2672, pruned_loss=0.03401, over 906316.26 frames.], batch size: 15, lr: 3.14e-04
2022-04-29 23:49:46,883 INFO [train.py:763] (3/8) Epoch 24, batch 250, loss[loss=0.1721, simple_loss=0.2786, pruned_loss=0.03282, over 7233.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03407, over 1018564.83 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:50:52,234 INFO [train.py:763] (3/8) Epoch 24, batch 300, loss[loss=0.1764, simple_loss=0.2758, pruned_loss=0.03846, over 7151.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2667, pruned_loss=0.03423, over 1112340.12 frames.], batch size: 19, lr: 3.14e-04
2022-04-29 23:51:57,520 INFO [train.py:763] (3/8) Epoch 24, batch 350, loss[loss=0.1834, simple_loss=0.2832, pruned_loss=0.04177, over 7196.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2664, pruned_loss=0.03442, over 1180934.71 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:53:03,341 INFO [train.py:763] (3/8) Epoch 24, batch 400, loss[loss=0.1681, simple_loss=0.2747, pruned_loss=0.03071, over 7250.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2664, pruned_loss=0.03423, over 1236047.88 frames.], batch size: 20, lr: 3.14e-04
2022-04-29 23:54:08,671 INFO [train.py:763] (3/8) Epoch 24, batch 450, loss[loss=0.1677, simple_loss=0.2663, pruned_loss=0.03458, over 7146.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03349, over 1276953.21 frames.], batch size: 28, lr: 3.14e-04
2022-04-29 23:55:14,211 INFO [train.py:763] (3/8) Epoch 24, batch 500, loss[loss=0.172, simple_loss=0.2597, pruned_loss=0.0422, over 7170.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.0334, over 1312530.87 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:56:20,426 INFO [train.py:763] (3/8) Epoch 24, batch 550, loss[loss=0.1509, simple_loss=0.2433, pruned_loss=0.02927, over 7169.00 frames.], tot_loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.03343, over 1339662.81 frames.], batch size: 18, lr: 3.14e-04
2022-04-29 23:57:26,718 INFO [train.py:763] (3/8) Epoch 24, batch 600, loss[loss=0.1833, simple_loss=0.2865, pruned_loss=0.04008, over 7187.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03359, over 1358555.23 frames.], batch size: 23, lr: 3.14e-04
2022-04-29 23:58:32,095 INFO [train.py:763] (3/8) Epoch 24, batch 650, loss[loss=0.1319, simple_loss=0.2177, pruned_loss=0.02305, over 7270.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2638, pruned_loss=0.03352, over 1370406.96 frames.], batch size: 17, lr: 3.14e-04
2022-04-29 23:59:38,742 INFO [train.py:763] (3/8) Epoch 24, batch 700, loss[loss=0.1537, simple_loss=0.2363, pruned_loss=0.03555, over 7222.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2639, pruned_loss=0.03355, over 1386722.25 frames.], batch size: 16, lr: 3.14e-04
2022-04-30 00:00:44,926 INFO [train.py:763] (3/8) Epoch 24, batch 750, loss[loss=0.1702, simple_loss=0.276, pruned_loss=0.03218, over 7235.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2651, pruned_loss=0.03422, over 1397506.20 frames.], batch size: 20, lr: 3.14e-04
2022-04-30 00:01:50,608 INFO [train.py:763] (3/8) Epoch 24, batch 800, loss[loss=0.1986, simple_loss=0.3035, pruned_loss=0.04684, over 7410.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2659, pruned_loss=0.03413, over 1405546.69 frames.], batch size: 21, lr: 3.14e-04
2022-04-30 00:02:56,129 INFO [train.py:763] (3/8) Epoch 24, batch 850, loss[loss=0.1684, simple_loss=0.2787, pruned_loss=0.02905, over 7311.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2659, pruned_loss=0.03397, over 1407052.77 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:04:01,369 INFO [train.py:763] (3/8) Epoch 24, batch 900, loss[loss=0.2072, simple_loss=0.307, pruned_loss=0.05373, over 7289.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2668, pruned_loss=0.03422, over 1409959.06 frames.], batch size: 25, lr: 3.13e-04
2022-04-30 00:05:07,032 INFO [train.py:763] (3/8) Epoch 24, batch 950, loss[loss=0.205, simple_loss=0.2894, pruned_loss=0.06033, over 4898.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2665, pruned_loss=0.03435, over 1405229.20 frames.], batch size: 52, lr: 3.13e-04
2022-04-30 00:06:12,844 INFO [train.py:763] (3/8) Epoch 24, batch 1000, loss[loss=0.1659, simple_loss=0.2638, pruned_loss=0.03396, over 7422.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2664, pruned_loss=0.03432, over 1412521.17 frames.], batch size: 21, lr: 3.13e-04
2022-04-30 00:07:18,487 INFO [train.py:763] (3/8) Epoch 24, batch 1050, loss[loss=0.1536, simple_loss=0.2489, pruned_loss=0.02913, over 7328.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03383, over 1419144.66 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:08:23,984 INFO [train.py:763] (3/8) Epoch 24, batch 1100, loss[loss=0.183, simple_loss=0.2886, pruned_loss=0.0387, over 7343.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2658, pruned_loss=0.03375, over 1421203.36 frames.], batch size: 22, lr: 3.13e-04
2022-04-30 00:09:29,776 INFO [train.py:763] (3/8) Epoch 24, batch 1150, loss[loss=0.1529, simple_loss=0.2525, pruned_loss=0.02666, over 7190.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03371, over 1424447.30 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:10:35,400 INFO [train.py:763] (3/8) Epoch 24, batch 1200, loss[loss=0.171, simple_loss=0.2727, pruned_loss=0.03471, over 7369.00 frames.], tot_loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.03342, over 1424061.89 frames.], batch size: 23, lr: 3.13e-04
2022-04-30 00:11:41,672 INFO [train.py:763] (3/8) Epoch 24, batch 1250, loss[loss=0.1704, simple_loss=0.2667, pruned_loss=0.03711, over 7149.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03357, over 1422295.69 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:12:47,620 INFO [train.py:763] (3/8) Epoch 24, batch 1300, loss[loss=0.1542, simple_loss=0.2453, pruned_loss=0.03151, over 7210.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2644, pruned_loss=0.03342, over 1421698.76 frames.], batch size: 16, lr: 3.13e-04
2022-04-30 00:13:53,404 INFO [train.py:763] (3/8) Epoch 24, batch 1350, loss[loss=0.1749, simple_loss=0.2722, pruned_loss=0.03877, over 6358.00 frames.], tot_loss[loss=0.1659, simple_loss=0.265, pruned_loss=0.03338, over 1420970.78 frames.], batch size: 38, lr: 3.13e-04
2022-04-30 00:14:58,834 INFO [train.py:763] (3/8) Epoch 24, batch 1400, loss[loss=0.152, simple_loss=0.2411, pruned_loss=0.03141, over 7272.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03355, over 1426120.66 frames.], batch size: 17, lr: 3.13e-04
2022-04-30 00:16:04,289 INFO [train.py:763] (3/8) Epoch 24, batch 1450, loss[loss=0.1661, simple_loss=0.2722, pruned_loss=0.02997, over 7137.00 frames.], tot_loss[loss=0.166, simple_loss=0.265, pruned_loss=0.03352, over 1422838.31 frames.], batch size: 20, lr: 3.13e-04
2022-04-30 00:17:11,225 INFO [train.py:763] (3/8) Epoch 24, batch 1500, loss[loss=0.1551, simple_loss=0.2476, pruned_loss=0.0313, over 6759.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03343, over 1421182.81 frames.], batch size: 31, lr: 3.13e-04
2022-04-30 00:18:17,537 INFO [train.py:763] (3/8) Epoch 24, batch 1550, loss[loss=0.1509, simple_loss=0.2436, pruned_loss=0.02911, over 7294.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2659, pruned_loss=0.03383, over 1422407.09 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:19:23,705 INFO [train.py:763] (3/8) Epoch 24, batch 1600, loss[loss=0.1611, simple_loss=0.2453, pruned_loss=0.03839, over 7164.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2655, pruned_loss=0.03379, over 1421791.25 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:20:29,913 INFO [train.py:763] (3/8) Epoch 24, batch 1650, loss[loss=0.1544, simple_loss=0.2581, pruned_loss=0.02537, over 7213.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03338, over 1422705.18 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:21:35,722 INFO [train.py:763] (3/8) Epoch 24, batch 1700, loss[loss=0.1913, simple_loss=0.2893, pruned_loss=0.04661, over 7375.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2656, pruned_loss=0.03388, over 1420546.92 frames.], batch size: 23, lr: 3.12e-04
2022-04-30 00:22:40,921 INFO [train.py:763] (3/8) Epoch 24, batch 1750, loss[loss=0.1484, simple_loss=0.2472, pruned_loss=0.02482, over 7134.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2667, pruned_loss=0.03388, over 1423188.92 frames.], batch size: 17, lr: 3.12e-04
2022-04-30 00:23:47,085 INFO [train.py:763] (3/8) Epoch 24, batch 1800, loss[loss=0.1417, simple_loss=0.2369, pruned_loss=0.02328, over 7010.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2674, pruned_loss=0.03383, over 1423814.27 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:24:52,828 INFO [train.py:763] (3/8) Epoch 24, batch 1850, loss[loss=0.1556, simple_loss=0.25, pruned_loss=0.0306, over 7242.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2673, pruned_loss=0.03418, over 1420882.85 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:26:09,445 INFO [train.py:763] (3/8) Epoch 24, batch 1900, loss[loss=0.1521, simple_loss=0.2576, pruned_loss=0.02325, over 7292.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2673, pruned_loss=0.03404, over 1421995.34 frames.], batch size: 25, lr: 3.12e-04
2022-04-30 00:27:15,223 INFO [train.py:763] (3/8) Epoch 24, batch 1950, loss[loss=0.1492, simple_loss=0.2498, pruned_loss=0.02425, over 7256.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2668, pruned_loss=0.03372, over 1424242.40 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:28:21,027 INFO [train.py:763] (3/8) Epoch 24, batch 2000, loss[loss=0.1704, simple_loss=0.2726, pruned_loss=0.03415, over 7146.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2663, pruned_loss=0.03377, over 1424281.63 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:29:27,104 INFO [train.py:763] (3/8) Epoch 24, batch 2050, loss[loss=0.1923, simple_loss=0.2995, pruned_loss=0.04256, over 7325.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.0335, over 1427562.59 frames.], batch size: 21, lr: 3.12e-04
2022-04-30 00:30:32,483 INFO [train.py:763] (3/8) Epoch 24, batch 2100, loss[loss=0.1395, simple_loss=0.2402, pruned_loss=0.01942, over 7260.00 frames.], tot_loss[loss=0.165, simple_loss=0.264, pruned_loss=0.033, over 1424022.88 frames.], batch size: 19, lr: 3.12e-04
2022-04-30 00:31:37,973 INFO [train.py:763] (3/8) Epoch 24, batch 2150, loss[loss=0.1758, simple_loss=0.2841, pruned_loss=0.03379, over 7437.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2651, pruned_loss=0.03311, over 1422982.46 frames.], batch size: 20, lr: 3.12e-04
2022-04-30 00:32:43,333 INFO [train.py:763] (3/8) Epoch 24, batch 2200, loss[loss=0.1462, simple_loss=0.2479, pruned_loss=0.0222, over 7225.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2653, pruned_loss=0.03345, over 1421903.23 frames.], batch size: 16, lr: 3.12e-04
2022-04-30 00:33:49,448 INFO [train.py:763] (3/8) Epoch 24, batch 2250, loss[loss=0.1546, simple_loss=0.254, pruned_loss=0.02761, over 7067.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2659, pruned_loss=0.03425, over 1417229.21 frames.], batch size: 18, lr: 3.12e-04
2022-04-30 00:34:55,312 INFO [train.py:763] (3/8) Epoch 24, batch 2300, loss[loss=0.1364, simple_loss=0.2198, pruned_loss=0.02648, over 7240.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2654, pruned_loss=0.03399, over 1418211.22 frames.], batch size: 16, lr: 3.11e-04
2022-04-30 00:36:01,133 INFO [train.py:763] (3/8) Epoch 24, batch 2350, loss[loss=0.148, simple_loss=0.2597, pruned_loss=0.01812, over 7317.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2654, pruned_loss=0.03393, over 1419252.38 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:37:06,712 INFO [train.py:763] (3/8) Epoch 24, batch 2400, loss[loss=0.1506, simple_loss=0.2623, pruned_loss=0.01944, over 7360.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2669, pruned_loss=0.03426, over 1423799.34 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:38:21,817 INFO [train.py:763] (3/8) Epoch 24, batch 2450, loss[loss=0.1606, simple_loss=0.2504, pruned_loss=0.03536, over 7142.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2671, pruned_loss=0.03453, over 1423157.65 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:39:27,185 INFO [train.py:763] (3/8) Epoch 24, batch 2500, loss[loss=0.1612, simple_loss=0.2645, pruned_loss=0.02894, over 7404.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2672, pruned_loss=0.03479, over 1423322.15 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:40:32,702 INFO [train.py:763] (3/8) Epoch 24, batch 2550, loss[loss=0.1698, simple_loss=0.273, pruned_loss=0.03336, over 7417.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2675, pruned_loss=0.03503, over 1424350.94 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:41:38,101 INFO [train.py:763] (3/8) Epoch 24, batch 2600, loss[loss=0.1378, simple_loss=0.2271, pruned_loss=0.02425, over 7152.00 frames.], tot_loss[loss=0.1685, simple_loss=0.267, pruned_loss=0.03499, over 1421192.01 frames.], batch size: 17, lr: 3.11e-04
2022-04-30 00:42:43,679 INFO [train.py:763] (3/8) Epoch 24, batch 2650, loss[loss=0.1532, simple_loss=0.2463, pruned_loss=0.03002, over 7206.00 frames.], tot_loss[loss=0.168, simple_loss=0.2669, pruned_loss=0.03456, over 1423020.17 frames.], batch size: 22, lr: 3.11e-04
2022-04-30 00:43:49,271 INFO [train.py:763] (3/8) Epoch 24, batch 2700, loss[loss=0.1595, simple_loss=0.2534, pruned_loss=0.03283, over 7059.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2655, pruned_loss=0.03369, over 1425646.09 frames.], batch size: 18, lr: 3.11e-04
2022-04-30 00:44:54,689 INFO [train.py:763] (3/8) Epoch 24, batch 2750, loss[loss=0.1542, simple_loss=0.2663, pruned_loss=0.02106, over 7140.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2651, pruned_loss=0.03357, over 1420729.18 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:46:00,209 INFO [train.py:763] (3/8) Epoch 24, batch 2800, loss[loss=0.1654, simple_loss=0.2657, pruned_loss=0.03251, over 7251.00 frames.], tot_loss[loss=0.166, simple_loss=0.2646, pruned_loss=0.03371, over 1421249.60 frames.], batch size: 19, lr: 3.11e-04
2022-04-30 00:47:22,975 INFO [train.py:763] (3/8) Epoch 24, batch 2850, loss[loss=0.1706, simple_loss=0.2695, pruned_loss=0.03582, over 7435.00 frames.], tot_loss[loss=0.166, simple_loss=0.265, pruned_loss=0.0335, over 1419966.95 frames.], batch size: 20, lr: 3.11e-04
2022-04-30 00:48:28,454 INFO [train.py:763] (3/8) Epoch 24, batch 2900, loss[loss=0.1753, simple_loss=0.2759, pruned_loss=0.03733, over 7216.00 frames.], tot_loss[loss=0.167, simple_loss=0.266, pruned_loss=0.03398, over 1420562.27 frames.], batch size: 23, lr: 3.11e-04
2022-04-30 00:49:52,262 INFO [train.py:763] (3/8) Epoch 24, batch 2950, loss[loss=0.1794, simple_loss=0.2858, pruned_loss=0.03645, over 7115.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2662, pruned_loss=0.03354, over 1425445.10 frames.], batch size: 21, lr: 3.11e-04
2022-04-30 00:51:06,864 INFO [train.py:763] (3/8) Epoch 24, batch 3000, loss[loss=0.1512, simple_loss=0.2649, pruned_loss=0.01875, over 6729.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2647, pruned_loss=0.03334, over 1429029.18 frames.], batch size: 31, lr: 3.10e-04
2022-04-30 00:51:06,865 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 00:51:22,143 INFO [train.py:792] (3/8) Epoch 24, validation: loss=0.1679, simple_loss=0.2653, pruned_loss=0.03523, over 698248.00 frames.
2022-04-30 00:52:37,061 INFO [train.py:763] (3/8) Epoch 24, batch 3050, loss[loss=0.1746, simple_loss=0.2816, pruned_loss=0.03381, over 7117.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03339, over 1429657.15 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 00:53:42,762 INFO [train.py:763] (3/8) Epoch 24, batch 3100, loss[loss=0.1798, simple_loss=0.2676, pruned_loss=0.04604, over 6802.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.0333, over 1429701.49 frames.], batch size: 15, lr: 3.10e-04
2022-04-30 00:54:48,069 INFO [train.py:763] (3/8) Epoch 24, batch 3150, loss[loss=0.1372, simple_loss=0.2382, pruned_loss=0.01808, over 7251.00 frames.], tot_loss[loss=0.166, simple_loss=0.2652, pruned_loss=0.03334, over 1430511.34 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:55:53,499 INFO [train.py:763] (3/8) Epoch 24, batch 3200, loss[loss=0.1864, simple_loss=0.2742, pruned_loss=0.04928, over 5218.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2641, pruned_loss=0.03322, over 1429135.96 frames.], batch size: 54, lr: 3.10e-04
2022-04-30 00:56:59,203 INFO [train.py:763] (3/8) Epoch 24, batch 3250, loss[loss=0.1882, simple_loss=0.2919, pruned_loss=0.04227, over 7235.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2652, pruned_loss=0.03382, over 1427170.90 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 00:58:05,420 INFO [train.py:763] (3/8) Epoch 24, batch 3300, loss[loss=0.1607, simple_loss=0.2598, pruned_loss=0.03075, over 7152.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2652, pruned_loss=0.03391, over 1425771.99 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 00:59:11,082 INFO [train.py:763] (3/8) Epoch 24, batch 3350, loss[loss=0.162, simple_loss=0.2573, pruned_loss=0.03333, over 7255.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03367, over 1422791.33 frames.], batch size: 19, lr: 3.10e-04
2022-04-30 01:00:16,803 INFO [train.py:763] (3/8) Epoch 24, batch 3400, loss[loss=0.1354, simple_loss=0.2262, pruned_loss=0.02233, over 7282.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2639, pruned_loss=0.03316, over 1424432.32 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:01:22,328 INFO [train.py:763] (3/8) Epoch 24, batch 3450, loss[loss=0.1825, simple_loss=0.2892, pruned_loss=0.03794, over 7234.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2646, pruned_loss=0.03348, over 1421844.40 frames.], batch size: 21, lr: 3.10e-04
2022-04-30 01:02:27,610 INFO [train.py:763] (3/8) Epoch 24, batch 3500, loss[loss=0.1388, simple_loss=0.2312, pruned_loss=0.02315, over 7132.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03371, over 1423432.99 frames.], batch size: 17, lr: 3.10e-04
2022-04-30 01:03:33,196 INFO [train.py:763] (3/8) Epoch 24, batch 3550, loss[loss=0.147, simple_loss=0.2557, pruned_loss=0.01913, over 7322.00 frames.], tot_loss[loss=0.167, simple_loss=0.2661, pruned_loss=0.03397, over 1424578.95 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:04:38,396 INFO [train.py:763] (3/8) Epoch 24, batch 3600, loss[loss=0.208, simple_loss=0.3027, pruned_loss=0.05669, over 7200.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2666, pruned_loss=0.03412, over 1422920.04 frames.], batch size: 23, lr: 3.10e-04
2022-04-30 01:05:45,315 INFO [train.py:763] (3/8) Epoch 24, batch 3650, loss[loss=0.1815, simple_loss=0.2917, pruned_loss=0.03563, over 6424.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2663, pruned_loss=0.03403, over 1419281.40 frames.], batch size: 37, lr: 3.10e-04
2022-04-30 01:06:51,860 INFO [train.py:763] (3/8) Epoch 24, batch 3700, loss[loss=0.1601, simple_loss=0.2614, pruned_loss=0.02939, over 7429.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2653, pruned_loss=0.03373, over 1422320.53 frames.], batch size: 20, lr: 3.10e-04
2022-04-30 01:07:57,542 INFO [train.py:763] (3/8) Epoch 24, batch 3750, loss[loss=0.1749, simple_loss=0.2715, pruned_loss=0.03913, over 7395.00 frames.], tot_loss[loss=0.1663, simple_loss=0.265, pruned_loss=0.03379, over 1424383.14 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:09:02,950 INFO [train.py:763] (3/8) Epoch 24, batch 3800, loss[loss=0.1968, simple_loss=0.2785, pruned_loss=0.05754, over 5089.00 frames.], tot_loss[loss=0.166, simple_loss=0.2644, pruned_loss=0.03379, over 1422212.70 frames.], batch size: 52, lr: 3.09e-04
2022-04-30 01:10:08,027 INFO [train.py:763] (3/8) Epoch 24, batch 3850, loss[loss=0.1659, simple_loss=0.2575, pruned_loss=0.03716, over 7276.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03392, over 1421939.58 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:11:13,747 INFO [train.py:763] (3/8) Epoch 24, batch 3900, loss[loss=0.1547, simple_loss=0.2539, pruned_loss=0.02772, over 7254.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2657, pruned_loss=0.03394, over 1421700.47 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:12:19,227 INFO [train.py:763] (3/8) Epoch 24, batch 3950, loss[loss=0.1803, simple_loss=0.2567, pruned_loss=0.05193, over 7420.00 frames.], tot_loss[loss=0.167, simple_loss=0.266, pruned_loss=0.03399, over 1424188.31 frames.], batch size: 18, lr: 3.09e-04
2022-04-30 01:13:24,349 INFO [train.py:763] (3/8) Epoch 24, batch 4000, loss[loss=0.1786, simple_loss=0.2706, pruned_loss=0.04325, over 7323.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2665, pruned_loss=0.03413, over 1423019.17 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:14:29,871 INFO [train.py:763] (3/8) Epoch 24, batch 4050, loss[loss=0.169, simple_loss=0.2575, pruned_loss=0.04029, over 7430.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2655, pruned_loss=0.03396, over 1421878.69 frames.], batch size: 20, lr: 3.09e-04
2022-04-30 01:15:36,738 INFO [train.py:763] (3/8) Epoch 24, batch 4100, loss[loss=0.196, simple_loss=0.2931, pruned_loss=0.04948, over 6454.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2663, pruned_loss=0.0346, over 1422402.07 frames.], batch size: 38, lr: 3.09e-04
2022-04-30 01:16:43,483 INFO [train.py:763] (3/8) Epoch 24, batch 4150, loss[loss=0.1689, simple_loss=0.2841, pruned_loss=0.02687, over 7220.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2658, pruned_loss=0.03423, over 1418626.17 frames.], batch size: 21, lr: 3.09e-04
2022-04-30 01:17:50,167 INFO [train.py:763] (3/8) Epoch 24, batch 4200, loss[loss=0.1751, simple_loss=0.2794, pruned_loss=0.03543, over 7193.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2677, pruned_loss=0.03459, over 1420486.53 frames.], batch size: 23, lr: 3.09e-04
2022-04-30 01:18:56,566 INFO [train.py:763] (3/8) Epoch 24, batch 4250, loss[loss=0.1627, simple_loss=0.272, pruned_loss=0.02669, over 6163.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2669, pruned_loss=0.0343, over 1415306.46 frames.], batch size: 37, lr: 3.09e-04
2022-04-30 01:20:02,370 INFO [train.py:763] (3/8) Epoch 24, batch 4300, loss[loss=0.1517, simple_loss=0.2552, pruned_loss=0.02417, over 7155.00 frames.], tot_loss[loss=0.167, simple_loss=0.2658, pruned_loss=0.03406, over 1414737.00 frames.], batch size: 19, lr: 3.09e-04
2022-04-30 01:21:09,410 INFO [train.py:763] (3/8) Epoch 24, batch 4350, loss[loss=0.1579, simple_loss=0.2667, pruned_loss=0.02452, over 7325.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.03356, over 1414731.09 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:22:16,102 INFO [train.py:763] (3/8) Epoch 24, batch 4400, loss[loss=0.1566, simple_loss=0.2633, pruned_loss=0.02489, over 7291.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2665, pruned_loss=0.0341, over 1413081.87 frames.], batch size: 24, lr: 3.09e-04
2022-04-30 01:23:21,722 INFO [train.py:763] (3/8) Epoch 24, batch 4450, loss[loss=0.1848, simple_loss=0.2848, pruned_loss=0.04238, over 7287.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2676, pruned_loss=0.03443, over 1403697.95 frames.], batch size: 25, lr: 3.09e-04
2022-04-30 01:24:28,205 INFO [train.py:763] (3/8) Epoch 24, batch 4500, loss[loss=0.1725, simple_loss=0.2642, pruned_loss=0.0404, over 5242.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2689, pruned_loss=0.03536, over 1388376.17 frames.], batch size: 52, lr: 3.08e-04
2022-04-30 01:25:32,950 INFO [train.py:763] (3/8) Epoch 24, batch 4550, loss[loss=0.1934, simple_loss=0.2864, pruned_loss=0.05017, over 5096.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2707, pruned_loss=0.03613, over 1349918.35 frames.], batch size: 52, lr: 3.08e-04
2022-04-30 01:26:52,284 INFO [train.py:763] (3/8) Epoch 25, batch 0, loss[loss=0.1737, simple_loss=0.2849, pruned_loss=0.03132, over 7217.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2849, pruned_loss=0.03132, over 7217.00 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:27:58,471 INFO [train.py:763] (3/8) Epoch 25, batch 50, loss[loss=0.1626, simple_loss=0.2607, pruned_loss=0.03226, over 7323.00 frames.], tot_loss[loss=0.1631, simple_loss=0.262, pruned_loss=0.03213, over 322597.04 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:29:03,632 INFO [train.py:763] (3/8) Epoch 25, batch 100, loss[loss=0.2189, simple_loss=0.3013, pruned_loss=0.0682, over 5037.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03199, over 566612.50 frames.], batch size: 52, lr: 3.02e-04
2022-04-30 01:30:08,886 INFO [train.py:763] (3/8) Epoch 25, batch 150, loss[loss=0.1656, simple_loss=0.2543, pruned_loss=0.03844, over 7290.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2651, pruned_loss=0.03254, over 760092.24 frames.], batch size: 17, lr: 3.02e-04
2022-04-30 01:31:14,494 INFO [train.py:763] (3/8) Epoch 25, batch 200, loss[loss=0.1884, simple_loss=0.2878, pruned_loss=0.04447, over 7371.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03234, over 906395.18 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:32:20,360 INFO [train.py:763] (3/8) Epoch 25, batch 250, loss[loss=0.1846, simple_loss=0.2954, pruned_loss=0.03692, over 7196.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03354, over 1018974.60 frames.], batch size: 22, lr: 3.02e-04
2022-04-30 01:33:26,236 INFO [train.py:763] (3/8) Epoch 25, batch 300, loss[loss=0.1602, simple_loss=0.2683, pruned_loss=0.02612, over 7326.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2656, pruned_loss=0.03369, over 1105366.89 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:34:31,516 INFO [train.py:763] (3/8) Epoch 25, batch 350, loss[loss=0.143, simple_loss=0.2317, pruned_loss=0.02715, over 7157.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03361, over 1174778.59 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:35:36,789 INFO [train.py:763] (3/8) Epoch 25, batch 400, loss[loss=0.1311, simple_loss=0.2239, pruned_loss=0.0191, over 7422.00 frames.], tot_loss[loss=0.166, simple_loss=0.2651, pruned_loss=0.03343, over 1232630.36 frames.], batch size: 18, lr: 3.02e-04
2022-04-30 01:36:42,353 INFO [train.py:763] (3/8) Epoch 25, batch 450, loss[loss=0.1783, simple_loss=0.2876, pruned_loss=0.03454, over 7416.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2642, pruned_loss=0.033, over 1273486.63 frames.], batch size: 21, lr: 3.02e-04
2022-04-30 01:37:47,500 INFO [train.py:763] (3/8) Epoch 25, batch 500, loss[loss=0.1849, simple_loss=0.2841, pruned_loss=0.04288, over 7365.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2649, pruned_loss=0.03318, over 1302952.21 frames.], batch size: 23, lr: 3.02e-04
2022-04-30 01:38:52,812 INFO [train.py:763] (3/8) Epoch 25, batch 550, loss[loss=0.168, simple_loss=0.2797, pruned_loss=0.02814, over 7231.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2644, pruned_loss=0.03275, over 1329459.58 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:39:58,985 INFO [train.py:763] (3/8) Epoch 25, batch 600, loss[loss=0.1805, simple_loss=0.2882, pruned_loss=0.03637, over 7104.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2647, pruned_loss=0.03287, over 1348226.22 frames.], batch size: 28, lr: 3.02e-04
2022-04-30 01:41:04,680 INFO [train.py:763] (3/8) Epoch 25, batch 650, loss[loss=0.176, simple_loss=0.2665, pruned_loss=0.04275, over 7337.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2648, pruned_loss=0.03337, over 1362408.22 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:42:10,707 INFO [train.py:763] (3/8) Epoch 25, batch 700, loss[loss=0.1861, simple_loss=0.2826, pruned_loss=0.04479, over 7143.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2648, pruned_loss=0.03343, over 1375363.45 frames.], batch size: 20, lr: 3.02e-04
2022-04-30 01:43:16,096 INFO [train.py:763] (3/8) Epoch 25, batch 750, loss[loss=0.1497, simple_loss=0.2562, pruned_loss=0.02162, over 7430.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2654, pruned_loss=0.03376, over 1390907.08 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:44:20,963 INFO [train.py:763] (3/8) Epoch 25, batch 800, loss[loss=0.1795, simple_loss=0.2816, pruned_loss=0.03872, over 6868.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2656, pruned_loss=0.03356, over 1396229.21 frames.], batch size: 31, lr: 3.01e-04
2022-04-30 01:45:26,280 INFO [train.py:763] (3/8) Epoch 25, batch 850, loss[loss=0.157, simple_loss=0.2687, pruned_loss=0.02261, over 7123.00 frames.], tot_loss[loss=0.166, simple_loss=0.2657, pruned_loss=0.03314, over 1407111.64 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:46:33,099 INFO [train.py:763] (3/8) Epoch 25, batch 900, loss[loss=0.1359, simple_loss=0.2357, pruned_loss=0.01801, over 7240.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2652, pruned_loss=0.03315, over 1406599.08 frames.], batch size: 16, lr: 3.01e-04
2022-04-30 01:47:40,153 INFO [train.py:763] (3/8) Epoch 25, batch 950, loss[loss=0.157, simple_loss=0.2488, pruned_loss=0.03261, over 7299.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2652, pruned_loss=0.03315, over 1412861.83 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:48:46,808 INFO [train.py:763] (3/8) Epoch 25, batch 1000, loss[loss=0.1834, simple_loss=0.2889, pruned_loss=0.03895, over 7119.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2661, pruned_loss=0.03384, over 1412244.54 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:49:52,613 INFO [train.py:763] (3/8) Epoch 25, batch 1050, loss[loss=0.1763, simple_loss=0.2688, pruned_loss=0.04192, over 4913.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2665, pruned_loss=0.03365, over 1412501.89 frames.], batch size: 53, lr: 3.01e-04
2022-04-30 01:50:59,148 INFO [train.py:763] (3/8) Epoch 25, batch 1100, loss[loss=0.174, simple_loss=0.2845, pruned_loss=0.03168, over 7125.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2662, pruned_loss=0.03346, over 1413888.27 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:52:04,512 INFO [train.py:763] (3/8) Epoch 25, batch 1150, loss[loss=0.1655, simple_loss=0.2632, pruned_loss=0.03389, over 7380.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2655, pruned_loss=0.03317, over 1417233.97 frames.], batch size: 23, lr: 3.01e-04
2022-04-30 01:53:10,908 INFO [train.py:763] (3/8) Epoch 25, batch 1200, loss[loss=0.1445, simple_loss=0.2353, pruned_loss=0.02683, over 7152.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2657, pruned_loss=0.03367, over 1421602.55 frames.], batch size: 17, lr: 3.01e-04
2022-04-30 01:54:16,905 INFO [train.py:763] (3/8) Epoch 25, batch 1250, loss[loss=0.1882, simple_loss=0.2808, pruned_loss=0.04783, over 7328.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03359, over 1424005.39 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:55:23,799 INFO [train.py:763] (3/8) Epoch 25, batch 1300, loss[loss=0.1745, simple_loss=0.283, pruned_loss=0.033, over 7435.00 frames.], tot_loss[loss=0.1661, simple_loss=0.265, pruned_loss=0.03359, over 1427602.39 frames.], batch size: 20, lr: 3.01e-04
2022-04-30 01:56:30,374 INFO [train.py:763] (3/8) Epoch 25, batch 1350, loss[loss=0.1735, simple_loss=0.2728, pruned_loss=0.03708, over 7309.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2655, pruned_loss=0.03363, over 1427354.87 frames.], batch size: 21, lr: 3.01e-04
2022-04-30 01:57:36,863 INFO [train.py:763] (3/8) Epoch 25, batch 1400, loss[loss=0.1856, simple_loss=0.2922, pruned_loss=0.03949, over 7343.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2653, pruned_loss=0.03394, over 1427482.21 frames.], batch size: 22, lr: 3.01e-04
2022-04-30 01:58:42,269 INFO [train.py:763] (3/8) Epoch 25, batch 1450, loss[loss=0.1461, simple_loss=0.2419, pruned_loss=0.02518, over 7006.00 frames.], tot_loss[loss=0.1672, simple_loss=0.266, pruned_loss=0.0342, over 1429224.71 frames.], batch size: 16, lr: 3.01e-04
2022-04-30 01:59:49,360 INFO [train.py:763] (3/8) Epoch 25, batch 1500, loss[loss=0.1928, simple_loss=0.2971, pruned_loss=0.04424, over 7232.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2654, pruned_loss=0.0341, over 1428073.88 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:00:55,046 INFO [train.py:763] (3/8) Epoch 25, batch 1550, loss[loss=0.1453, simple_loss=0.2393, pruned_loss=0.0257, over 7140.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2649, pruned_loss=0.03372, over 1427676.92 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:02:00,072 INFO [train.py:763] (3/8) Epoch 25, batch 1600, loss[loss=0.1642, simple_loss=0.2597, pruned_loss=0.03432, over 7147.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2667, pruned_loss=0.03432, over 1425381.20 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:03:05,633 INFO [train.py:763] (3/8) Epoch 25, batch 1650, loss[loss=0.1816, simple_loss=0.2776, pruned_loss=0.04286, over 7044.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2651, pruned_loss=0.03361, over 1425927.69 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:04:10,609 INFO [train.py:763] (3/8) Epoch 25, batch 1700, loss[loss=0.1644, simple_loss=0.2666, pruned_loss=0.03112, over 7331.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03337, over 1425922.28 frames.], batch size: 21, lr: 3.00e-04
2022-04-30 02:05:15,840 INFO [train.py:763] (3/8) Epoch 25, batch 1750, loss[loss=0.1525, simple_loss=0.247, pruned_loss=0.02897, over 7132.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.0333, over 1425274.93 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:06:21,038 INFO [train.py:763] (3/8) Epoch 25, batch 1800, loss[loss=0.2022, simple_loss=0.2916, pruned_loss=0.05641, over 7137.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2643, pruned_loss=0.03325, over 1421270.87 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:07:26,301 INFO [train.py:763] (3/8) Epoch 25, batch 1850, loss[loss=0.1676, simple_loss=0.2782, pruned_loss=0.02854, over 7422.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2642, pruned_loss=0.03325, over 1422129.12 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:08:31,446 INFO [train.py:763] (3/8) Epoch 25, batch 1900, loss[loss=0.1363, simple_loss=0.2326, pruned_loss=0.01997, over 7151.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2643, pruned_loss=0.03327, over 1422360.15 frames.], batch size: 17, lr: 3.00e-04
2022-04-30 02:09:36,777 INFO [train.py:763] (3/8) Epoch 25, batch 1950, loss[loss=0.1942, simple_loss=0.2894, pruned_loss=0.04946, over 4857.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03345, over 1419668.83 frames.], batch size: 52, lr: 3.00e-04
2022-04-30 02:10:42,028 INFO [train.py:763] (3/8) Epoch 25, batch 2000, loss[loss=0.1426, simple_loss=0.2355, pruned_loss=0.02481, over 7161.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2643, pruned_loss=0.03337, over 1416920.74 frames.], batch size: 19, lr: 3.00e-04
2022-04-30 02:11:47,908 INFO [train.py:763] (3/8) Epoch 25, batch 2050, loss[loss=0.1466, simple_loss=0.2523, pruned_loss=0.02042, over 7322.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2635, pruned_loss=0.03304, over 1418361.44 frames.], batch size: 20, lr: 3.00e-04
2022-04-30 02:12:54,271 INFO [train.py:763] (3/8) Epoch 25, batch 2100, loss[loss=0.1829, simple_loss=0.2716, pruned_loss=0.04715, over 7196.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2645, pruned_loss=0.03358, over 1417141.44 frames.], batch size: 22, lr: 3.00e-04
2022-04-30 02:13:59,535 INFO [train.py:763] (3/8) Epoch 25, batch 2150, loss[loss=0.1521, simple_loss=0.2551, pruned_loss=0.02452, over 7156.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03379, over 1419170.46 frames.], batch size: 18, lr: 3.00e-04
2022-04-30 02:15:05,483 INFO [train.py:763] (3/8) Epoch 25, batch 2200, loss[loss=0.1627, simple_loss=0.2666, pruned_loss=0.02938, over 7108.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2655, pruned_loss=0.03379, over 1421739.47 frames.], batch size: 28, lr: 3.00e-04
2022-04-30 02:16:11,384 INFO [train.py:763] (3/8) Epoch 25, batch 2250, loss[loss=0.1735, simple_loss=0.2793, pruned_loss=0.03384, over 7369.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2649, pruned_loss=0.03366, over 1424322.45 frames.], batch size: 23, lr: 3.00e-04
2022-04-30 02:17:16,593 INFO [train.py:763] (3/8) Epoch 25, batch 2300, loss[loss=0.1576, simple_loss=0.2445, pruned_loss=0.03534, over 7063.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2648, pruned_loss=0.03371, over 1424587.51 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:18:23,381 INFO [train.py:763] (3/8) Epoch 25, batch 2350, loss[loss=0.1529, simple_loss=0.2456, pruned_loss=0.03013, over 7258.00 frames.], tot_loss[loss=0.1656, simple_loss=0.264, pruned_loss=0.03359, over 1424223.54 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:19:30,573 INFO [train.py:763] (3/8) Epoch 25, batch 2400, loss[loss=0.1817, simple_loss=0.2905, pruned_loss=0.03643, over 7368.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2633, pruned_loss=0.03315, over 1422576.81 frames.], batch size: 23, lr: 2.99e-04
2022-04-30 02:20:35,958 INFO [train.py:763] (3/8) Epoch 25, batch 2450, loss[loss=0.1706, simple_loss=0.2671, pruned_loss=0.03701, over 6765.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2641, pruned_loss=0.03358, over 1421631.99 frames.], batch size: 31, lr: 2.99e-04
2022-04-30 02:21:42,822 INFO [train.py:763] (3/8) Epoch 25, batch 2500, loss[loss=0.1538, simple_loss=0.2452, pruned_loss=0.0312, over 7363.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2642, pruned_loss=0.0337, over 1422690.70 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:22:48,786 INFO [train.py:763] (3/8) Epoch 25, batch 2550, loss[loss=0.1365, simple_loss=0.2286, pruned_loss=0.0222, over 7414.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2643, pruned_loss=0.03355, over 1425587.74 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:23:56,377 INFO [train.py:763] (3/8) Epoch 25, batch 2600, loss[loss=0.1641, simple_loss=0.264, pruned_loss=0.03209, over 7156.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2648, pruned_loss=0.03382, over 1423846.54 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:25:02,540 INFO [train.py:763] (3/8) Epoch 25, batch 2650, loss[loss=0.2037, simple_loss=0.2942, pruned_loss=0.05662, over 7111.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2661, pruned_loss=0.0342, over 1418975.23 frames.], batch size: 28, lr: 2.99e-04
2022-04-30 02:26:07,756 INFO [train.py:763] (3/8) Epoch 25, batch 2700, loss[loss=0.1649, simple_loss=0.2587, pruned_loss=0.0355, over 7266.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2667, pruned_loss=0.03423, over 1419732.49 frames.], batch size: 19, lr: 2.99e-04
2022-04-30 02:27:12,939 INFO [train.py:763] (3/8) Epoch 25, batch 2750, loss[loss=0.2071, simple_loss=0.3026, pruned_loss=0.05585, over 7304.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2665, pruned_loss=0.03417, over 1413989.76 frames.], batch size: 25, lr: 2.99e-04
2022-04-30 02:28:19,369 INFO [train.py:763] (3/8) Epoch 25, batch 2800, loss[loss=0.1798, simple_loss=0.2768, pruned_loss=0.04144, over 7281.00 frames.], tot_loss[loss=0.1671, simple_loss=0.266, pruned_loss=0.03407, over 1416580.12 frames.], batch size: 18, lr: 2.99e-04
2022-04-30 02:29:24,932 INFO [train.py:763] (3/8) Epoch 25, batch 2850, loss[loss=0.1551, simple_loss=0.2602, pruned_loss=0.02501, over 7413.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2654, pruned_loss=0.03382, over 1412322.63 frames.], batch size: 21, lr: 2.99e-04
2022-04-30 02:30:30,620 INFO [train.py:763] (3/8) Epoch 25, batch 2900, loss[loss=0.1645, simple_loss=0.267, pruned_loss=0.031, over 7151.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2647, pruned_loss=0.03347, over 1418754.27 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:31:35,883 INFO [train.py:763] (3/8) Epoch 25, batch 2950, loss[loss=0.17, simple_loss=0.2714, pruned_loss=0.0343, over 7324.00 frames.], tot_loss[loss=0.1658, simple_loss=0.265, pruned_loss=0.03326, over 1419284.89 frames.], batch size: 20, lr: 2.99e-04
2022-04-30 02:32:41,161 INFO [train.py:763] (3/8) Epoch 25, batch 3000, loss[loss=0.1606, simple_loss=0.263, pruned_loss=0.02907, over 6254.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2653, pruned_loss=0.03355, over 1423064.68 frames.], batch size: 37, lr: 2.99e-04
2022-04-30 02:32:41,161 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 02:32:56,272 INFO [train.py:792] (3/8) 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] (3/8) Epoch 25, batch 3050, loss[loss=0.165, simple_loss=0.2895, pruned_loss=0.02022, over 7339.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2669, pruned_loss=0.03414, over 1421765.28 frames.], batch size: 22, lr: 2.99e-04
2022-04-30 02:35:09,274 INFO [train.py:763] (3/8) Epoch 25, batch 3100, loss[loss=0.1446, simple_loss=0.239, pruned_loss=0.0251, over 7265.00 frames.], tot_loss[loss=0.167, simple_loss=0.2663, pruned_loss=0.03388, over 1419851.54 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:36:16,360 INFO [train.py:763] (3/8) Epoch 25, batch 3150, loss[loss=0.145, simple_loss=0.2423, pruned_loss=0.02383, over 7134.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2662, pruned_loss=0.03373, over 1419133.24 frames.], batch size: 17, lr: 2.98e-04
2022-04-30 02:37:22,257 INFO [train.py:763] (3/8) Epoch 25, batch 3200, loss[loss=0.1489, simple_loss=0.2522, pruned_loss=0.02279, over 7160.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2661, pruned_loss=0.03365, over 1422035.04 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:38:29,211 INFO [train.py:763] (3/8) Epoch 25, batch 3250, loss[loss=0.1716, simple_loss=0.259, pruned_loss=0.04206, over 7273.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03338, over 1425479.19 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:39:35,763 INFO [train.py:763] (3/8) Epoch 25, batch 3300, loss[loss=0.1847, simple_loss=0.2796, pruned_loss=0.04493, over 7160.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2656, pruned_loss=0.03367, over 1418368.37 frames.], batch size: 26, lr: 2.98e-04
2022-04-30 02:40:42,706 INFO [train.py:763] (3/8) Epoch 25, batch 3350, loss[loss=0.1631, simple_loss=0.2619, pruned_loss=0.0322, over 7328.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2649, pruned_loss=0.03329, over 1415046.74 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:41:49,871 INFO [train.py:763] (3/8) Epoch 25, batch 3400, loss[loss=0.1786, simple_loss=0.2751, pruned_loss=0.04101, over 6284.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2646, pruned_loss=0.03359, over 1419920.11 frames.], batch size: 37, lr: 2.98e-04
2022-04-30 02:42:55,392 INFO [train.py:763] (3/8) Epoch 25, batch 3450, loss[loss=0.1524, simple_loss=0.2469, pruned_loss=0.02894, over 7167.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.03345, over 1419707.41 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:44:00,603 INFO [train.py:763] (3/8) Epoch 25, batch 3500, loss[loss=0.1884, simple_loss=0.2882, pruned_loss=0.04431, over 7390.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2652, pruned_loss=0.03357, over 1419539.24 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:45:06,556 INFO [train.py:763] (3/8) Epoch 25, batch 3550, loss[loss=0.1566, simple_loss=0.2529, pruned_loss=0.03017, over 7416.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2645, pruned_loss=0.03342, over 1421862.41 frames.], batch size: 21, lr: 2.98e-04
2022-04-30 02:46:12,315 INFO [train.py:763] (3/8) Epoch 25, batch 3600, loss[loss=0.1736, simple_loss=0.2781, pruned_loss=0.03453, over 7206.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2643, pruned_loss=0.03348, over 1426145.77 frames.], batch size: 23, lr: 2.98e-04
2022-04-30 02:47:18,087 INFO [train.py:763] (3/8) Epoch 25, batch 3650, loss[loss=0.1599, simple_loss=0.2497, pruned_loss=0.03502, over 7262.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2647, pruned_loss=0.03331, over 1426630.15 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:48:25,754 INFO [train.py:763] (3/8) Epoch 25, batch 3700, loss[loss=0.1665, simple_loss=0.268, pruned_loss=0.03254, over 7071.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2641, pruned_loss=0.03311, over 1423928.58 frames.], batch size: 18, lr: 2.98e-04
2022-04-30 02:49:32,857 INFO [train.py:763] (3/8) Epoch 25, batch 3750, loss[loss=0.1582, simple_loss=0.2561, pruned_loss=0.03014, over 7160.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03354, over 1422107.44 frames.], batch size: 19, lr: 2.98e-04
2022-04-30 02:50:38,246 INFO [train.py:763] (3/8) Epoch 25, batch 3800, loss[loss=0.1518, simple_loss=0.2627, pruned_loss=0.02048, over 6593.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03293, over 1419718.18 frames.], batch size: 38, lr: 2.98e-04
2022-04-30 02:51:43,563 INFO [train.py:763] (3/8) Epoch 25, batch 3850, loss[loss=0.1566, simple_loss=0.2643, pruned_loss=0.02447, over 7146.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2645, pruned_loss=0.03313, over 1417900.30 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:52:57,810 INFO [train.py:763] (3/8) Epoch 25, batch 3900, loss[loss=0.1628, simple_loss=0.2498, pruned_loss=0.0379, over 7421.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2649, pruned_loss=0.03325, over 1420591.46 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 02:54:03,674 INFO [train.py:763] (3/8) Epoch 25, batch 3950, loss[loss=0.1858, simple_loss=0.292, pruned_loss=0.03973, over 7223.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2646, pruned_loss=0.03326, over 1424972.58 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:55:09,637 INFO [train.py:763] (3/8) Epoch 25, batch 4000, loss[loss=0.1593, simple_loss=0.2574, pruned_loss=0.03055, over 7430.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2645, pruned_loss=0.03361, over 1418438.18 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 02:56:14,886 INFO [train.py:763] (3/8) Epoch 25, batch 4050, loss[loss=0.1595, simple_loss=0.2654, pruned_loss=0.02679, over 7426.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03334, over 1420039.00 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:57:21,067 INFO [train.py:763] (3/8) Epoch 25, batch 4100, loss[loss=0.156, simple_loss=0.2593, pruned_loss=0.02633, over 7408.00 frames.], tot_loss[loss=0.166, simple_loss=0.2648, pruned_loss=0.03363, over 1417972.14 frames.], batch size: 21, lr: 2.97e-04
2022-04-30 02:58:26,415 INFO [train.py:763] (3/8) Epoch 25, batch 4150, loss[loss=0.1674, simple_loss=0.2736, pruned_loss=0.03057, over 7254.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2634, pruned_loss=0.03273, over 1423048.63 frames.], batch size: 19, lr: 2.97e-04
2022-04-30 02:59:32,218 INFO [train.py:763] (3/8) Epoch 25, batch 4200, loss[loss=0.2023, simple_loss=0.3014, pruned_loss=0.05154, over 6999.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2638, pruned_loss=0.03294, over 1419352.58 frames.], batch size: 28, lr: 2.97e-04
2022-04-30 03:00:37,739 INFO [train.py:763] (3/8) Epoch 25, batch 4250, loss[loss=0.1456, simple_loss=0.2477, pruned_loss=0.02172, over 7168.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2642, pruned_loss=0.03299, over 1419946.07 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:01:43,168 INFO [train.py:763] (3/8) Epoch 25, batch 4300, loss[loss=0.2202, simple_loss=0.3184, pruned_loss=0.06093, over 7176.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2652, pruned_loss=0.03352, over 1422545.85 frames.], batch size: 26, lr: 2.97e-04
2022-04-30 03:03:06,202 INFO [train.py:763] (3/8) Epoch 25, batch 4350, loss[loss=0.1706, simple_loss=0.2721, pruned_loss=0.03459, over 7239.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03337, over 1415865.95 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:04:20,099 INFO [train.py:763] (3/8) Epoch 25, batch 4400, loss[loss=0.1592, simple_loss=0.2581, pruned_loss=0.0301, over 7072.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2661, pruned_loss=0.03353, over 1415532.24 frames.], batch size: 18, lr: 2.97e-04
2022-04-30 03:05:34,209 INFO [train.py:763] (3/8) Epoch 25, batch 4450, loss[loss=0.174, simple_loss=0.2773, pruned_loss=0.03531, over 7283.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2662, pruned_loss=0.03327, over 1413421.02 frames.], batch size: 24, lr: 2.97e-04
2022-04-30 03:06:39,192 INFO [train.py:763] (3/8) Epoch 25, batch 4500, loss[loss=0.183, simple_loss=0.2756, pruned_loss=0.04523, over 7329.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2658, pruned_loss=0.0336, over 1396504.23 frames.], batch size: 20, lr: 2.97e-04
2022-04-30 03:08:11,349 INFO [train.py:763] (3/8) Epoch 25, batch 4550, loss[loss=0.2299, simple_loss=0.3248, pruned_loss=0.06753, over 5009.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2658, pruned_loss=0.0336, over 1387550.74 frames.], batch size: 52, lr: 2.97e-04
2022-04-30 03:09:39,544 INFO [train.py:763] (3/8) Epoch 26, batch 0, loss[loss=0.1666, simple_loss=0.2597, pruned_loss=0.03677, over 7164.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2597, pruned_loss=0.03677, over 7164.00 frames.], batch size: 18, lr: 2.91e-04
2022-04-30 03:10:45,448 INFO [train.py:763] (3/8) Epoch 26, batch 50, loss[loss=0.1333, simple_loss=0.2246, pruned_loss=0.02103, over 7288.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2646, pruned_loss=0.03339, over 318517.66 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:11:50,709 INFO [train.py:763] (3/8) Epoch 26, batch 100, loss[loss=0.1389, simple_loss=0.2272, pruned_loss=0.02529, over 7282.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03282, over 562473.89 frames.], batch size: 17, lr: 2.91e-04
2022-04-30 03:12:56,048 INFO [train.py:763] (3/8) Epoch 26, batch 150, loss[loss=0.1836, simple_loss=0.2858, pruned_loss=0.04073, over 6355.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03247, over 749976.92 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:14:01,245 INFO [train.py:763] (3/8) Epoch 26, batch 200, loss[loss=0.1709, simple_loss=0.2689, pruned_loss=0.03647, over 7210.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2645, pruned_loss=0.03327, over 893133.86 frames.], batch size: 26, lr: 2.91e-04
2022-04-30 03:15:07,039 INFO [train.py:763] (3/8) Epoch 26, batch 250, loss[loss=0.1931, simple_loss=0.2883, pruned_loss=0.04895, over 6310.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2657, pruned_loss=0.03345, over 1006162.28 frames.], batch size: 38, lr: 2.91e-04
2022-04-30 03:16:13,120 INFO [train.py:763] (3/8) Epoch 26, batch 300, loss[loss=0.1699, simple_loss=0.285, pruned_loss=0.02737, over 6400.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2648, pruned_loss=0.033, over 1100116.37 frames.], batch size: 37, lr: 2.91e-04
2022-04-30 03:17:18,445 INFO [train.py:763] (3/8) Epoch 26, batch 350, loss[loss=0.1632, simple_loss=0.2729, pruned_loss=0.02674, over 6807.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2632, pruned_loss=0.03233, over 1169068.42 frames.], batch size: 31, lr: 2.91e-04
2022-04-30 03:18:23,747 INFO [train.py:763] (3/8) Epoch 26, batch 400, loss[loss=0.1521, simple_loss=0.2587, pruned_loss=0.02275, over 7148.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2632, pruned_loss=0.03223, over 1229065.72 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:19:29,468 INFO [train.py:763] (3/8) Epoch 26, batch 450, loss[loss=0.1625, simple_loss=0.2608, pruned_loss=0.03206, over 7245.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.032, over 1276193.79 frames.], batch size: 20, lr: 2.91e-04
2022-04-30 03:20:34,844 INFO [train.py:763] (3/8) Epoch 26, batch 500, loss[loss=0.1997, simple_loss=0.2849, pruned_loss=0.05722, over 5293.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2636, pruned_loss=0.03187, over 1308174.00 frames.], batch size: 52, lr: 2.91e-04
2022-04-30 03:21:40,167 INFO [train.py:763] (3/8) Epoch 26, batch 550, loss[loss=0.1689, simple_loss=0.2788, pruned_loss=0.02948, over 7209.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2641, pruned_loss=0.03207, over 1332598.66 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:22:45,576 INFO [train.py:763] (3/8) Epoch 26, batch 600, loss[loss=0.1387, simple_loss=0.2401, pruned_loss=0.0187, over 7256.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03252, over 1355215.01 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:23:51,104 INFO [train.py:763] (3/8) Epoch 26, batch 650, loss[loss=0.1757, simple_loss=0.2481, pruned_loss=0.05168, over 7278.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2631, pruned_loss=0.03221, over 1372132.88 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:24:56,239 INFO [train.py:763] (3/8) Epoch 26, batch 700, loss[loss=0.171, simple_loss=0.2739, pruned_loss=0.0341, over 7117.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.03265, over 1380861.55 frames.], batch size: 21, lr: 2.90e-04
2022-04-30 03:26:12,124 INFO [train.py:763] (3/8) Epoch 26, batch 750, loss[loss=0.1689, simple_loss=0.2707, pruned_loss=0.03352, over 7146.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03249, over 1388937.45 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:27:17,956 INFO [train.py:763] (3/8) Epoch 26, batch 800, loss[loss=0.1744, simple_loss=0.2702, pruned_loss=0.03927, over 7231.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2633, pruned_loss=0.0326, over 1395142.65 frames.], batch size: 20, lr: 2.90e-04
2022-04-30 03:28:23,823 INFO [train.py:763] (3/8) Epoch 26, batch 850, loss[loss=0.1674, simple_loss=0.2603, pruned_loss=0.03723, over 5021.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03313, over 1397565.10 frames.], batch size: 52, lr: 2.90e-04
2022-04-30 03:29:29,377 INFO [train.py:763] (3/8) Epoch 26, batch 900, loss[loss=0.1556, simple_loss=0.2537, pruned_loss=0.02875, over 7398.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2637, pruned_loss=0.03292, over 1407272.33 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:30:35,250 INFO [train.py:763] (3/8) Epoch 26, batch 950, loss[loss=0.1574, simple_loss=0.2473, pruned_loss=0.03377, over 6778.00 frames.], tot_loss[loss=0.1648, simple_loss=0.264, pruned_loss=0.0328, over 1408173.61 frames.], batch size: 15, lr: 2.90e-04
2022-04-30 03:31:40,714 INFO [train.py:763] (3/8) Epoch 26, batch 1000, loss[loss=0.1562, simple_loss=0.2649, pruned_loss=0.0238, over 7298.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03257, over 1411970.43 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:32:46,139 INFO [train.py:763] (3/8) Epoch 26, batch 1050, loss[loss=0.1856, simple_loss=0.2853, pruned_loss=0.04294, over 7199.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03254, over 1417403.56 frames.], batch size: 23, lr: 2.90e-04
2022-04-30 03:33:51,496 INFO [train.py:763] (3/8) Epoch 26, batch 1100, loss[loss=0.1813, simple_loss=0.2819, pruned_loss=0.04037, over 7206.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2638, pruned_loss=0.03236, over 1422045.60 frames.], batch size: 22, lr: 2.90e-04
2022-04-30 03:34:56,892 INFO [train.py:763] (3/8) Epoch 26, batch 1150, loss[loss=0.1387, simple_loss=0.2347, pruned_loss=0.02134, over 7163.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2648, pruned_loss=0.03249, over 1423104.61 frames.], batch size: 19, lr: 2.90e-04
2022-04-30 03:36:02,471 INFO [train.py:763] (3/8) Epoch 26, batch 1200, loss[loss=0.1801, simple_loss=0.2859, pruned_loss=0.03721, over 7301.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2648, pruned_loss=0.0327, over 1427022.13 frames.], batch size: 24, lr: 2.90e-04
2022-04-30 03:37:08,327 INFO [train.py:763] (3/8) Epoch 26, batch 1250, loss[loss=0.1645, simple_loss=0.2685, pruned_loss=0.03021, over 6348.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2642, pruned_loss=0.03269, over 1427095.06 frames.], batch size: 37, lr: 2.90e-04
2022-04-30 03:38:14,025 INFO [train.py:763] (3/8) Epoch 26, batch 1300, loss[loss=0.1444, simple_loss=0.2375, pruned_loss=0.02561, over 7287.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2637, pruned_loss=0.03258, over 1423652.67 frames.], batch size: 18, lr: 2.90e-04
2022-04-30 03:39:20,369 INFO [train.py:763] (3/8) Epoch 26, batch 1350, loss[loss=0.139, simple_loss=0.2342, pruned_loss=0.02187, over 7416.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2623, pruned_loss=0.03229, over 1427348.37 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:40:25,489 INFO [train.py:763] (3/8) Epoch 26, batch 1400, loss[loss=0.1969, simple_loss=0.2852, pruned_loss=0.05434, over 7205.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2623, pruned_loss=0.03276, over 1419380.96 frames.], batch size: 23, lr: 2.89e-04
2022-04-30 03:41:30,974 INFO [train.py:763] (3/8) Epoch 26, batch 1450, loss[loss=0.1588, simple_loss=0.2517, pruned_loss=0.03296, over 7274.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2624, pruned_loss=0.03298, over 1422053.09 frames.], batch size: 18, lr: 2.89e-04
2022-04-30 03:42:36,427 INFO [train.py:763] (3/8) Epoch 26, batch 1500, loss[loss=0.1673, simple_loss=0.2628, pruned_loss=0.03592, over 5547.00 frames.], tot_loss[loss=0.164, simple_loss=0.2625, pruned_loss=0.03282, over 1418014.02 frames.], batch size: 52, lr: 2.89e-04
2022-04-30 03:43:42,576 INFO [train.py:763] (3/8) Epoch 26, batch 1550, loss[loss=0.163, simple_loss=0.2666, pruned_loss=0.02969, over 7115.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03239, over 1421193.34 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:44:49,278 INFO [train.py:763] (3/8) Epoch 26, batch 1600, loss[loss=0.1425, simple_loss=0.2367, pruned_loss=0.02414, over 7256.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2612, pruned_loss=0.03195, over 1424377.70 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:45:54,875 INFO [train.py:763] (3/8) Epoch 26, batch 1650, loss[loss=0.1589, simple_loss=0.2648, pruned_loss=0.02647, over 7159.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2618, pruned_loss=0.03177, over 1428182.02 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:47:00,373 INFO [train.py:763] (3/8) Epoch 26, batch 1700, loss[loss=0.1853, simple_loss=0.2854, pruned_loss=0.0426, over 7351.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2621, pruned_loss=0.03184, over 1429914.06 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:48:06,017 INFO [train.py:763] (3/8) Epoch 26, batch 1750, loss[loss=0.1742, simple_loss=0.2778, pruned_loss=0.03529, over 7137.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2627, pruned_loss=0.03208, over 1430499.04 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:49:13,271 INFO [train.py:763] (3/8) Epoch 26, batch 1800, loss[loss=0.1741, simple_loss=0.2778, pruned_loss=0.03522, over 7107.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2632, pruned_loss=0.03251, over 1428494.01 frames.], batch size: 21, lr: 2.89e-04
2022-04-30 03:50:19,934 INFO [train.py:763] (3/8) Epoch 26, batch 1850, loss[loss=0.1813, simple_loss=0.278, pruned_loss=0.04232, over 4933.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2636, pruned_loss=0.03282, over 1429077.75 frames.], batch size: 52, lr: 2.89e-04
2022-04-30 03:51:25,627 INFO [train.py:763] (3/8) Epoch 26, batch 1900, loss[loss=0.1495, simple_loss=0.2434, pruned_loss=0.02781, over 7360.00 frames.], tot_loss[loss=0.165, simple_loss=0.2635, pruned_loss=0.03328, over 1428313.11 frames.], batch size: 19, lr: 2.89e-04
2022-04-30 03:52:30,899 INFO [train.py:763] (3/8) Epoch 26, batch 1950, loss[loss=0.1698, simple_loss=0.2759, pruned_loss=0.03187, over 6313.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2635, pruned_loss=0.0334, over 1424897.36 frames.], batch size: 37, lr: 2.89e-04
2022-04-30 03:53:36,218 INFO [train.py:763] (3/8) Epoch 26, batch 2000, loss[loss=0.1806, simple_loss=0.2835, pruned_loss=0.03886, over 6777.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2634, pruned_loss=0.03341, over 1423165.97 frames.], batch size: 31, lr: 2.89e-04
2022-04-30 03:54:41,491 INFO [train.py:763] (3/8) Epoch 26, batch 2050, loss[loss=0.1697, simple_loss=0.2718, pruned_loss=0.03382, over 7123.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2638, pruned_loss=0.03347, over 1425966.19 frames.], batch size: 26, lr: 2.89e-04
2022-04-30 03:55:48,141 INFO [train.py:763] (3/8) Epoch 26, batch 2100, loss[loss=0.1726, simple_loss=0.2788, pruned_loss=0.03322, over 7192.00 frames.], tot_loss[loss=0.1652, simple_loss=0.264, pruned_loss=0.0332, over 1424379.48 frames.], batch size: 22, lr: 2.89e-04
2022-04-30 03:56:54,314 INFO [train.py:763] (3/8) Epoch 26, batch 2150, loss[loss=0.2039, simple_loss=0.298, pruned_loss=0.05489, over 7313.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2653, pruned_loss=0.0335, over 1427677.09 frames.], batch size: 25, lr: 2.89e-04
2022-04-30 03:57:59,844 INFO [train.py:763] (3/8) Epoch 26, batch 2200, loss[loss=0.1822, simple_loss=0.278, pruned_loss=0.04322, over 7225.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2645, pruned_loss=0.03331, over 1425962.15 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 03:59:06,003 INFO [train.py:763] (3/8) Epoch 26, batch 2250, loss[loss=0.1382, simple_loss=0.2348, pruned_loss=0.02077, over 6998.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2645, pruned_loss=0.03293, over 1431077.00 frames.], batch size: 16, lr: 2.88e-04
2022-04-30 04:00:11,170 INFO [train.py:763] (3/8) Epoch 26, batch 2300, loss[loss=0.1346, simple_loss=0.2282, pruned_loss=0.02047, over 7137.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2646, pruned_loss=0.03288, over 1433315.30 frames.], batch size: 17, lr: 2.88e-04
2022-04-30 04:01:17,205 INFO [train.py:763] (3/8) Epoch 26, batch 2350, loss[loss=0.1739, simple_loss=0.2826, pruned_loss=0.03261, over 7139.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2654, pruned_loss=0.03361, over 1431156.09 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:02:24,606 INFO [train.py:763] (3/8) Epoch 26, batch 2400, loss[loss=0.172, simple_loss=0.2693, pruned_loss=0.03735, over 7296.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2656, pruned_loss=0.03356, over 1432882.38 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:03:31,273 INFO [train.py:763] (3/8) Epoch 26, batch 2450, loss[loss=0.1541, simple_loss=0.2615, pruned_loss=0.02334, over 7226.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2642, pruned_loss=0.03282, over 1435364.18 frames.], batch size: 20, lr: 2.88e-04
2022-04-30 04:04:36,617 INFO [train.py:763] (3/8) Epoch 26, batch 2500, loss[loss=0.1643, simple_loss=0.2696, pruned_loss=0.02947, over 7211.00 frames.], tot_loss[loss=0.1648, simple_loss=0.264, pruned_loss=0.03278, over 1437471.13 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:05:41,761 INFO [train.py:763] (3/8) Epoch 26, batch 2550, loss[loss=0.1651, simple_loss=0.2745, pruned_loss=0.0279, over 6823.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2636, pruned_loss=0.03246, over 1435007.49 frames.], batch size: 31, lr: 2.88e-04
2022-04-30 04:06:47,199 INFO [train.py:763] (3/8) Epoch 26, batch 2600, loss[loss=0.168, simple_loss=0.258, pruned_loss=0.03902, over 7229.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.03261, over 1434966.21 frames.], batch size: 16, lr: 2.88e-04
2022-04-30 04:07:52,615 INFO [train.py:763] (3/8) Epoch 26, batch 2650, loss[loss=0.2067, simple_loss=0.3045, pruned_loss=0.05449, over 7268.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2643, pruned_loss=0.03293, over 1431176.91 frames.], batch size: 24, lr: 2.88e-04
2022-04-30 04:08:58,040 INFO [train.py:763] (3/8) Epoch 26, batch 2700, loss[loss=0.1553, simple_loss=0.262, pruned_loss=0.02432, over 7337.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2644, pruned_loss=0.03306, over 1429115.58 frames.], batch size: 22, lr: 2.88e-04
2022-04-30 04:10:03,923 INFO [train.py:763] (3/8) Epoch 26, batch 2750, loss[loss=0.1816, simple_loss=0.2735, pruned_loss=0.04485, over 7164.00 frames.], tot_loss[loss=0.165, simple_loss=0.2641, pruned_loss=0.03292, over 1428239.44 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:11:09,744 INFO [train.py:763] (3/8) Epoch 26, batch 2800, loss[loss=0.1829, simple_loss=0.277, pruned_loss=0.04436, over 7305.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03294, over 1427436.74 frames.], batch size: 25, lr: 2.88e-04
2022-04-30 04:12:16,485 INFO [train.py:763] (3/8) Epoch 26, batch 2850, loss[loss=0.1563, simple_loss=0.261, pruned_loss=0.02577, over 7246.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2647, pruned_loss=0.03303, over 1426982.58 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:13:21,768 INFO [train.py:763] (3/8) Epoch 26, batch 2900, loss[loss=0.1296, simple_loss=0.2269, pruned_loss=0.01618, over 7156.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2647, pruned_loss=0.03281, over 1426513.53 frames.], batch size: 19, lr: 2.88e-04
2022-04-30 04:14:26,917 INFO [train.py:763] (3/8) Epoch 26, batch 2950, loss[loss=0.1713, simple_loss=0.2765, pruned_loss=0.03302, over 7112.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03338, over 1420205.99 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,482 INFO [train.py:763] (3/8) Epoch 26, batch 3000, loss[loss=0.1606, simple_loss=0.2688, pruned_loss=0.02617, over 7415.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2646, pruned_loss=0.03275, over 1419055.52 frames.], batch size: 21, lr: 2.88e-04
2022-04-30 04:15:32,483 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 04:15:47,843 INFO [train.py:792] (3/8) Epoch 26, validation: loss=0.1682, simple_loss=0.2653, pruned_loss=0.03549, over 698248.00 frames.
2022-04-30 04:16:54,020 INFO [train.py:763] (3/8) Epoch 26, batch 3050, loss[loss=0.153, simple_loss=0.2604, pruned_loss=0.02278, over 7113.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2644, pruned_loss=0.03327, over 1411405.60 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:17:59,869 INFO [train.py:763] (3/8) Epoch 26, batch 3100, loss[loss=0.1826, simple_loss=0.287, pruned_loss=0.03908, over 7319.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2658, pruned_loss=0.03332, over 1417236.85 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:19:05,971 INFO [train.py:763] (3/8) Epoch 26, batch 3150, loss[loss=0.1871, simple_loss=0.2808, pruned_loss=0.04669, over 7213.00 frames.], tot_loss[loss=0.166, simple_loss=0.2654, pruned_loss=0.03332, over 1417895.17 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:20:11,638 INFO [train.py:763] (3/8) Epoch 26, batch 3200, loss[loss=0.1976, simple_loss=0.2874, pruned_loss=0.0539, over 7184.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2657, pruned_loss=0.03378, over 1418751.29 frames.], batch size: 23, lr: 2.87e-04
2022-04-30 04:21:17,156 INFO [train.py:763] (3/8) Epoch 26, batch 3250, loss[loss=0.1821, simple_loss=0.287, pruned_loss=0.03864, over 6449.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2644, pruned_loss=0.03342, over 1420424.88 frames.], batch size: 37, lr: 2.87e-04
2022-04-30 04:22:22,721 INFO [train.py:763] (3/8) Epoch 26, batch 3300, loss[loss=0.1511, simple_loss=0.2585, pruned_loss=0.02185, over 6668.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2641, pruned_loss=0.03319, over 1419445.63 frames.], batch size: 31, lr: 2.87e-04
2022-04-30 04:23:27,752 INFO [train.py:763] (3/8) Epoch 26, batch 3350, loss[loss=0.1632, simple_loss=0.2714, pruned_loss=0.02748, over 7329.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2658, pruned_loss=0.03375, over 1420234.84 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:24:33,265 INFO [train.py:763] (3/8) Epoch 26, batch 3400, loss[loss=0.1585, simple_loss=0.2557, pruned_loss=0.03067, over 7144.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2656, pruned_loss=0.03339, over 1417538.66 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:25:38,625 INFO [train.py:763] (3/8) Epoch 26, batch 3450, loss[loss=0.1653, simple_loss=0.2695, pruned_loss=0.03049, over 7332.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2657, pruned_loss=0.03338, over 1421255.59 frames.], batch size: 22, lr: 2.87e-04
2022-04-30 04:26:44,097 INFO [train.py:763] (3/8) Epoch 26, batch 3500, loss[loss=0.1478, simple_loss=0.2423, pruned_loss=0.0266, over 6840.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03275, over 1423466.54 frames.], batch size: 15, lr: 2.87e-04
2022-04-30 04:27:49,683 INFO [train.py:763] (3/8) Epoch 26, batch 3550, loss[loss=0.197, simple_loss=0.2867, pruned_loss=0.05362, over 5060.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03255, over 1417185.12 frames.], batch size: 52, lr: 2.87e-04
2022-04-30 04:28:54,782 INFO [train.py:763] (3/8) Epoch 26, batch 3600, loss[loss=0.1508, simple_loss=0.2539, pruned_loss=0.02387, over 7156.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2647, pruned_loss=0.03262, over 1415474.10 frames.], batch size: 19, lr: 2.87e-04
2022-04-30 04:30:00,884 INFO [train.py:763] (3/8) Epoch 26, batch 3650, loss[loss=0.1583, simple_loss=0.2553, pruned_loss=0.03066, over 7072.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2643, pruned_loss=0.03275, over 1414126.68 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:31:07,244 INFO [train.py:763] (3/8) Epoch 26, batch 3700, loss[loss=0.1548, simple_loss=0.2489, pruned_loss=0.03033, over 7282.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2647, pruned_loss=0.03298, over 1413224.71 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:32:12,926 INFO [train.py:763] (3/8) Epoch 26, batch 3750, loss[loss=0.1872, simple_loss=0.286, pruned_loss=0.04418, over 7205.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03259, over 1416803.91 frames.], batch size: 21, lr: 2.87e-04
2022-04-30 04:33:19,999 INFO [train.py:763] (3/8) Epoch 26, batch 3800, loss[loss=0.1476, simple_loss=0.2423, pruned_loss=0.02652, over 7319.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03234, over 1420751.04 frames.], batch size: 20, lr: 2.87e-04
2022-04-30 04:34:26,371 INFO [train.py:763] (3/8) Epoch 26, batch 3850, loss[loss=0.1492, simple_loss=0.2524, pruned_loss=0.02297, over 7407.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2648, pruned_loss=0.0328, over 1414619.95 frames.], batch size: 18, lr: 2.87e-04
2022-04-30 04:35:31,742 INFO [train.py:763] (3/8) Epoch 26, batch 3900, loss[loss=0.1703, simple_loss=0.2766, pruned_loss=0.03206, over 7120.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03288, over 1415733.38 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:36:37,006 INFO [train.py:763] (3/8) Epoch 26, batch 3950, loss[loss=0.1566, simple_loss=0.2399, pruned_loss=0.03666, over 7352.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2642, pruned_loss=0.03266, over 1420515.81 frames.], batch size: 19, lr: 2.86e-04
2022-04-30 04:37:42,771 INFO [train.py:763] (3/8) Epoch 26, batch 4000, loss[loss=0.1549, simple_loss=0.263, pruned_loss=0.02338, over 7106.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03258, over 1425319.02 frames.], batch size: 28, lr: 2.86e-04
2022-04-30 04:38:48,118 INFO [train.py:763] (3/8) Epoch 26, batch 4050, loss[loss=0.1719, simple_loss=0.2704, pruned_loss=0.0367, over 7330.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2643, pruned_loss=0.03251, over 1426118.25 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:39:53,363 INFO [train.py:763] (3/8) Epoch 26, batch 4100, loss[loss=0.1461, simple_loss=0.2413, pruned_loss=0.02541, over 7338.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2641, pruned_loss=0.0327, over 1424903.83 frames.], batch size: 20, lr: 2.86e-04
2022-04-30 04:40:58,511 INFO [train.py:763] (3/8) Epoch 26, batch 4150, loss[loss=0.1834, simple_loss=0.287, pruned_loss=0.03988, over 7107.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2649, pruned_loss=0.03297, over 1422501.53 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:42:03,903 INFO [train.py:763] (3/8) Epoch 26, batch 4200, loss[loss=0.1629, simple_loss=0.2787, pruned_loss=0.02361, over 7335.00 frames.], tot_loss[loss=0.1646, simple_loss=0.264, pruned_loss=0.03262, over 1423836.14 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:43:08,778 INFO [train.py:763] (3/8) Epoch 26, batch 4250, loss[loss=0.154, simple_loss=0.2697, pruned_loss=0.01912, over 7423.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.0329, over 1417097.81 frames.], batch size: 21, lr: 2.86e-04
2022-04-30 04:44:14,517 INFO [train.py:763] (3/8) Epoch 26, batch 4300, loss[loss=0.1678, simple_loss=0.2705, pruned_loss=0.0326, over 6812.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2655, pruned_loss=0.03276, over 1416430.83 frames.], batch size: 31, lr: 2.86e-04
2022-04-30 04:45:19,674 INFO [train.py:763] (3/8) Epoch 26, batch 4350, loss[loss=0.1503, simple_loss=0.2354, pruned_loss=0.03258, over 6998.00 frames.], tot_loss[loss=0.1662, simple_loss=0.266, pruned_loss=0.03325, over 1415950.91 frames.], batch size: 16, lr: 2.86e-04
2022-04-30 04:46:24,703 INFO [train.py:763] (3/8) Epoch 26, batch 4400, loss[loss=0.1689, simple_loss=0.2819, pruned_loss=0.02798, over 6350.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2669, pruned_loss=0.03361, over 1402637.15 frames.], batch size: 38, lr: 2.86e-04
2022-04-30 04:47:29,333 INFO [train.py:763] (3/8) Epoch 26, batch 4450, loss[loss=0.1759, simple_loss=0.2805, pruned_loss=0.03564, over 7333.00 frames.], tot_loss[loss=0.1664, simple_loss=0.266, pruned_loss=0.03341, over 1397162.58 frames.], batch size: 22, lr: 2.86e-04
2022-04-30 04:48:34,527 INFO [train.py:763] (3/8) Epoch 26, batch 4500, loss[loss=0.1609, simple_loss=0.2626, pruned_loss=0.02956, over 7154.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2654, pruned_loss=0.03341, over 1387707.82 frames.], batch size: 18, lr: 2.86e-04
2022-04-30 04:49:39,411 INFO [train.py:763] (3/8) Epoch 26, batch 4550, loss[loss=0.2158, simple_loss=0.3021, pruned_loss=0.06475, over 5036.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2642, pruned_loss=0.03354, over 1370609.90 frames.], batch size: 52, lr: 2.86e-04
2022-04-30 04:51:07,355 INFO [train.py:763] (3/8) Epoch 27, batch 0, loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04139, over 7263.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2598, pruned_loss=0.04139, over 7263.00 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:52:13,082 INFO [train.py:763] (3/8) Epoch 27, batch 50, loss[loss=0.1527, simple_loss=0.249, pruned_loss=0.02823, over 7256.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2646, pruned_loss=0.03314, over 321702.64 frames.], batch size: 19, lr: 2.81e-04
2022-04-30 04:53:19,207 INFO [train.py:763] (3/8) Epoch 27, batch 100, loss[loss=0.1984, simple_loss=0.2991, pruned_loss=0.04885, over 7150.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2654, pruned_loss=0.03309, over 565290.18 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 04:54:25,261 INFO [train.py:763] (3/8) Epoch 27, batch 150, loss[loss=0.148, simple_loss=0.2532, pruned_loss=0.02135, over 6463.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2653, pruned_loss=0.03254, over 753903.81 frames.], batch size: 38, lr: 2.80e-04
2022-04-30 04:55:31,374 INFO [train.py:763] (3/8) Epoch 27, batch 200, loss[loss=0.1781, simple_loss=0.2833, pruned_loss=0.03648, over 7181.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2653, pruned_loss=0.03231, over 899776.13 frames.], batch size: 23, lr: 2.80e-04
2022-04-30 04:56:38,001 INFO [train.py:763] (3/8) Epoch 27, batch 250, loss[loss=0.1796, simple_loss=0.2777, pruned_loss=0.0408, over 7299.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2648, pruned_loss=0.03226, over 1015515.71 frames.], batch size: 24, lr: 2.80e-04
2022-04-30 04:57:44,218 INFO [train.py:763] (3/8) Epoch 27, batch 300, loss[loss=0.1688, simple_loss=0.2577, pruned_loss=0.03997, over 6807.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2639, pruned_loss=0.03179, over 1105034.66 frames.], batch size: 31, lr: 2.80e-04
2022-04-30 04:58:50,090 INFO [train.py:763] (3/8) Epoch 27, batch 350, loss[loss=0.1459, simple_loss=0.2501, pruned_loss=0.02087, over 7170.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03115, over 1177103.03 frames.], batch size: 19, lr: 2.80e-04
2022-04-30 04:59:56,368 INFO [train.py:763] (3/8) Epoch 27, batch 400, loss[loss=0.1451, simple_loss=0.2358, pruned_loss=0.02721, over 7125.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2635, pruned_loss=0.03169, over 1233410.67 frames.], batch size: 17, lr: 2.80e-04
2022-04-30 05:01:02,254 INFO [train.py:763] (3/8) Epoch 27, batch 450, loss[loss=0.1652, simple_loss=0.2676, pruned_loss=0.03138, over 7277.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2638, pruned_loss=0.03196, over 1270591.34 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:02:08,166 INFO [train.py:763] (3/8) Epoch 27, batch 500, loss[loss=0.1634, simple_loss=0.2669, pruned_loss=0.02992, over 7315.00 frames.], tot_loss[loss=0.1639, simple_loss=0.264, pruned_loss=0.03186, over 1307705.52 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:03:14,026 INFO [train.py:763] (3/8) Epoch 27, batch 550, loss[loss=0.1586, simple_loss=0.2496, pruned_loss=0.03378, over 7077.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2645, pruned_loss=0.03263, over 1330189.37 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:04:19,655 INFO [train.py:763] (3/8) Epoch 27, batch 600, loss[loss=0.1914, simple_loss=0.2917, pruned_loss=0.04555, over 7328.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2635, pruned_loss=0.03233, over 1348415.59 frames.], batch size: 20, lr: 2.80e-04
2022-04-30 05:05:24,802 INFO [train.py:763] (3/8) Epoch 27, batch 650, loss[loss=0.1744, simple_loss=0.2878, pruned_loss=0.03053, over 6982.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2642, pruned_loss=0.03222, over 1366051.40 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:06:40,258 INFO [train.py:763] (3/8) Epoch 27, batch 700, loss[loss=0.1604, simple_loss=0.2639, pruned_loss=0.02844, over 7066.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2636, pruned_loss=0.0318, over 1379566.74 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:07:46,096 INFO [train.py:763] (3/8) Epoch 27, batch 750, loss[loss=0.1743, simple_loss=0.2865, pruned_loss=0.03104, over 7213.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03171, over 1390346.22 frames.], batch size: 21, lr: 2.80e-04
2022-04-30 05:08:51,494 INFO [train.py:763] (3/8) Epoch 27, batch 800, loss[loss=0.1554, simple_loss=0.2571, pruned_loss=0.02683, over 7119.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2633, pruned_loss=0.03164, over 1397378.88 frames.], batch size: 28, lr: 2.80e-04
2022-04-30 05:09:56,917 INFO [train.py:763] (3/8) Epoch 27, batch 850, loss[loss=0.1763, simple_loss=0.2842, pruned_loss=0.0342, over 7295.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2632, pruned_loss=0.03151, over 1406000.75 frames.], batch size: 25, lr: 2.80e-04
2022-04-30 05:11:02,106 INFO [train.py:763] (3/8) Epoch 27, batch 900, loss[loss=0.1553, simple_loss=0.2484, pruned_loss=0.03108, over 7007.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03209, over 1408627.28 frames.], batch size: 16, lr: 2.80e-04
2022-04-30 05:12:07,292 INFO [train.py:763] (3/8) Epoch 27, batch 950, loss[loss=0.164, simple_loss=0.2584, pruned_loss=0.03476, over 7160.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2654, pruned_loss=0.03245, over 1410559.41 frames.], batch size: 18, lr: 2.80e-04
2022-04-30 05:13:12,789 INFO [train.py:763] (3/8) Epoch 27, batch 1000, loss[loss=0.1422, simple_loss=0.2476, pruned_loss=0.01841, over 7428.00 frames.], tot_loss[loss=0.1649, simple_loss=0.265, pruned_loss=0.03245, over 1415820.94 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:14:18,817 INFO [train.py:763] (3/8) Epoch 27, batch 1050, loss[loss=0.1833, simple_loss=0.279, pruned_loss=0.0438, over 7414.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2655, pruned_loss=0.03289, over 1415566.98 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:15:25,041 INFO [train.py:763] (3/8) Epoch 27, batch 1100, loss[loss=0.1674, simple_loss=0.2639, pruned_loss=0.03541, over 7071.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2651, pruned_loss=0.03287, over 1415070.44 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:16:31,240 INFO [train.py:763] (3/8) Epoch 27, batch 1150, loss[loss=0.166, simple_loss=0.2758, pruned_loss=0.02811, over 7201.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2638, pruned_loss=0.03256, over 1420181.10 frames.], batch size: 23, lr: 2.79e-04
2022-04-30 05:17:47,513 INFO [train.py:763] (3/8) Epoch 27, batch 1200, loss[loss=0.1844, simple_loss=0.2789, pruned_loss=0.045, over 7129.00 frames.], tot_loss[loss=0.1637, simple_loss=0.263, pruned_loss=0.03222, over 1424597.32 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:19:01,884 INFO [train.py:763] (3/8) Epoch 27, batch 1250, loss[loss=0.1576, simple_loss=0.2434, pruned_loss=0.0359, over 7154.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2638, pruned_loss=0.0324, over 1422019.19 frames.], batch size: 17, lr: 2.79e-04
2022-04-30 05:20:26,020 INFO [train.py:763] (3/8) Epoch 27, batch 1300, loss[loss=0.1317, simple_loss=0.2304, pruned_loss=0.01648, over 7290.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03253, over 1418090.83 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:21:31,874 INFO [train.py:763] (3/8) Epoch 27, batch 1350, loss[loss=0.1506, simple_loss=0.2396, pruned_loss=0.03081, over 7364.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2638, pruned_loss=0.03269, over 1418536.09 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:22:37,302 INFO [train.py:763] (3/8) Epoch 27, batch 1400, loss[loss=0.1379, simple_loss=0.23, pruned_loss=0.02291, over 7075.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2633, pruned_loss=0.0327, over 1418856.10 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:24:10,242 INFO [train.py:763] (3/8) Epoch 27, batch 1450, loss[loss=0.1721, simple_loss=0.2715, pruned_loss=0.0363, over 7325.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2618, pruned_loss=0.03254, over 1420807.95 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:25:16,094 INFO [train.py:763] (3/8) Epoch 27, batch 1500, loss[loss=0.1767, simple_loss=0.2821, pruned_loss=0.03562, over 7129.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2629, pruned_loss=0.03276, over 1422976.76 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:26:22,002 INFO [train.py:763] (3/8) Epoch 27, batch 1550, loss[loss=0.1274, simple_loss=0.2155, pruned_loss=0.01965, over 7197.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2631, pruned_loss=0.03289, over 1420368.18 frames.], batch size: 16, lr: 2.79e-04
2022-04-30 05:27:29,033 INFO [train.py:763] (3/8) Epoch 27, batch 1600, loss[loss=0.1723, simple_loss=0.2771, pruned_loss=0.03379, over 7398.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2626, pruned_loss=0.03262, over 1424516.48 frames.], batch size: 21, lr: 2.79e-04
2022-04-30 05:28:35,019 INFO [train.py:763] (3/8) Epoch 27, batch 1650, loss[loss=0.1616, simple_loss=0.2493, pruned_loss=0.03692, over 7067.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2624, pruned_loss=0.03233, over 1425722.56 frames.], batch size: 18, lr: 2.79e-04
2022-04-30 05:29:41,343 INFO [train.py:763] (3/8) Epoch 27, batch 1700, loss[loss=0.1543, simple_loss=0.2545, pruned_loss=0.02705, over 7344.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03158, over 1427010.51 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:30:48,494 INFO [train.py:763] (3/8) Epoch 27, batch 1750, loss[loss=0.1662, simple_loss=0.2687, pruned_loss=0.03182, over 6877.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2625, pruned_loss=0.03228, over 1428822.88 frames.], batch size: 31, lr: 2.79e-04
2022-04-30 05:31:54,570 INFO [train.py:763] (3/8) Epoch 27, batch 1800, loss[loss=0.1705, simple_loss=0.2841, pruned_loss=0.02846, over 7238.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2623, pruned_loss=0.03234, over 1427930.06 frames.], batch size: 20, lr: 2.79e-04
2022-04-30 05:33:00,731 INFO [train.py:763] (3/8) Epoch 27, batch 1850, loss[loss=0.1541, simple_loss=0.2519, pruned_loss=0.02817, over 7149.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2626, pruned_loss=0.03248, over 1430347.19 frames.], batch size: 19, lr: 2.79e-04
2022-04-30 05:34:06,840 INFO [train.py:763] (3/8) Epoch 27, batch 1900, loss[loss=0.1412, simple_loss=0.2374, pruned_loss=0.02252, over 7279.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2638, pruned_loss=0.03276, over 1430169.05 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:35:13,648 INFO [train.py:763] (3/8) Epoch 27, batch 1950, loss[loss=0.1786, simple_loss=0.2684, pruned_loss=0.04443, over 6560.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2638, pruned_loss=0.03295, over 1426011.25 frames.], batch size: 39, lr: 2.78e-04
2022-04-30 05:36:20,336 INFO [train.py:763] (3/8) Epoch 27, batch 2000, loss[loss=0.1576, simple_loss=0.263, pruned_loss=0.02615, over 7218.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2637, pruned_loss=0.03258, over 1425295.19 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:37:26,477 INFO [train.py:763] (3/8) Epoch 27, batch 2050, loss[loss=0.1794, simple_loss=0.2824, pruned_loss=0.03816, over 7208.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2641, pruned_loss=0.03259, over 1423907.85 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:38:32,947 INFO [train.py:763] (3/8) Epoch 27, batch 2100, loss[loss=0.1893, simple_loss=0.2905, pruned_loss=0.04399, over 7306.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2636, pruned_loss=0.03199, over 1423402.42 frames.], batch size: 25, lr: 2.78e-04
2022-04-30 05:39:38,768 INFO [train.py:763] (3/8) Epoch 27, batch 2150, loss[loss=0.146, simple_loss=0.245, pruned_loss=0.02355, over 7131.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2642, pruned_loss=0.03229, over 1422280.17 frames.], batch size: 17, lr: 2.78e-04
2022-04-30 05:40:44,415 INFO [train.py:763] (3/8) Epoch 27, batch 2200, loss[loss=0.1668, simple_loss=0.2667, pruned_loss=0.03349, over 7268.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2645, pruned_loss=0.03235, over 1420581.20 frames.], batch size: 24, lr: 2.78e-04
2022-04-30 05:41:50,157 INFO [train.py:763] (3/8) Epoch 27, batch 2250, loss[loss=0.1686, simple_loss=0.2722, pruned_loss=0.03256, over 7330.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2643, pruned_loss=0.03264, over 1423544.13 frames.], batch size: 22, lr: 2.78e-04
2022-04-30 05:42:56,036 INFO [train.py:763] (3/8) Epoch 27, batch 2300, loss[loss=0.1698, simple_loss=0.2633, pruned_loss=0.0381, over 7146.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2649, pruned_loss=0.03285, over 1421629.72 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:44:01,765 INFO [train.py:763] (3/8) Epoch 27, batch 2350, loss[loss=0.1478, simple_loss=0.2494, pruned_loss=0.02312, over 7169.00 frames.], tot_loss[loss=0.165, simple_loss=0.2643, pruned_loss=0.03279, over 1419425.43 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:45:08,044 INFO [train.py:763] (3/8) Epoch 27, batch 2400, loss[loss=0.1728, simple_loss=0.2762, pruned_loss=0.0347, over 7207.00 frames.], tot_loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03287, over 1422540.49 frames.], batch size: 23, lr: 2.78e-04
2022-04-30 05:46:14,164 INFO [train.py:763] (3/8) Epoch 27, batch 2450, loss[loss=0.1767, simple_loss=0.2677, pruned_loss=0.04281, over 6444.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2639, pruned_loss=0.03259, over 1423300.04 frames.], batch size: 38, lr: 2.78e-04
2022-04-30 05:47:19,802 INFO [train.py:763] (3/8) Epoch 27, batch 2500, loss[loss=0.156, simple_loss=0.2517, pruned_loss=0.03016, over 6771.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2638, pruned_loss=0.03268, over 1420393.94 frames.], batch size: 15, lr: 2.78e-04
2022-04-30 05:48:25,889 INFO [train.py:763] (3/8) Epoch 27, batch 2550, loss[loss=0.1572, simple_loss=0.2526, pruned_loss=0.03089, over 7256.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2635, pruned_loss=0.03241, over 1421658.29 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:49:31,724 INFO [train.py:763] (3/8) Epoch 27, batch 2600, loss[loss=0.1716, simple_loss=0.2709, pruned_loss=0.03612, over 7231.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.03242, over 1421556.68 frames.], batch size: 20, lr: 2.78e-04
2022-04-30 05:50:37,400 INFO [train.py:763] (3/8) Epoch 27, batch 2650, loss[loss=0.1558, simple_loss=0.2401, pruned_loss=0.0357, over 7006.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2639, pruned_loss=0.03223, over 1420246.89 frames.], batch size: 16, lr: 2.78e-04
2022-04-30 05:51:42,956 INFO [train.py:763] (3/8) Epoch 27, batch 2700, loss[loss=0.1745, simple_loss=0.2722, pruned_loss=0.03837, over 7324.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2641, pruned_loss=0.0321, over 1421881.30 frames.], batch size: 21, lr: 2.78e-04
2022-04-30 05:52:49,036 INFO [train.py:763] (3/8) Epoch 27, batch 2750, loss[loss=0.1605, simple_loss=0.2724, pruned_loss=0.02428, over 7249.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2644, pruned_loss=0.03221, over 1420642.80 frames.], batch size: 19, lr: 2.78e-04
2022-04-30 05:53:54,760 INFO [train.py:763] (3/8) Epoch 27, batch 2800, loss[loss=0.1539, simple_loss=0.2576, pruned_loss=0.02514, over 7231.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2643, pruned_loss=0.03224, over 1416766.48 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 05:55:00,519 INFO [train.py:763] (3/8) Epoch 27, batch 2850, loss[loss=0.1557, simple_loss=0.258, pruned_loss=0.02673, over 7144.00 frames.], tot_loss[loss=0.164, simple_loss=0.2641, pruned_loss=0.03199, over 1420894.78 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 05:56:06,158 INFO [train.py:763] (3/8) Epoch 27, batch 2900, loss[loss=0.1815, simple_loss=0.2858, pruned_loss=0.03862, over 7283.00 frames.], tot_loss[loss=0.165, simple_loss=0.265, pruned_loss=0.03246, over 1420592.57 frames.], batch size: 25, lr: 2.77e-04
2022-04-30 05:57:11,710 INFO [train.py:763] (3/8) Epoch 27, batch 2950, loss[loss=0.1789, simple_loss=0.2785, pruned_loss=0.03969, over 7197.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2652, pruned_loss=0.03284, over 1423148.79 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 05:58:18,058 INFO [train.py:763] (3/8) Epoch 27, batch 3000, loss[loss=0.1603, simple_loss=0.2611, pruned_loss=0.0297, over 7013.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2649, pruned_loss=0.03263, over 1425379.76 frames.], batch size: 28, lr: 2.77e-04
2022-04-30 05:58:18,059 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 05:58:33,165 INFO [train.py:792] (3/8) Epoch 27, validation: loss=0.1686, simple_loss=0.2648, pruned_loss=0.03621, over 698248.00 frames.
2022-04-30 05:59:40,077 INFO [train.py:763] (3/8) Epoch 27, batch 3050, loss[loss=0.153, simple_loss=0.2468, pruned_loss=0.02958, over 7123.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2645, pruned_loss=0.03258, over 1426398.82 frames.], batch size: 17, lr: 2.77e-04
2022-04-30 06:00:45,834 INFO [train.py:763] (3/8) Epoch 27, batch 3100, loss[loss=0.1745, simple_loss=0.2714, pruned_loss=0.03883, over 7371.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03212, over 1425523.99 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:01:51,941 INFO [train.py:763] (3/8) Epoch 27, batch 3150, loss[loss=0.1594, simple_loss=0.261, pruned_loss=0.02886, over 7421.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03233, over 1424707.88 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:02:58,130 INFO [train.py:763] (3/8) Epoch 27, batch 3200, loss[loss=0.1639, simple_loss=0.2599, pruned_loss=0.03397, over 7324.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03206, over 1424983.65 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:04:04,076 INFO [train.py:763] (3/8) Epoch 27, batch 3250, loss[loss=0.1466, simple_loss=0.2428, pruned_loss=0.02522, over 7160.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2623, pruned_loss=0.03205, over 1425652.52 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:05:10,045 INFO [train.py:763] (3/8) Epoch 27, batch 3300, loss[loss=0.146, simple_loss=0.2405, pruned_loss=0.02575, over 7000.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03186, over 1424391.65 frames.], batch size: 16, lr: 2.77e-04
2022-04-30 06:06:16,455 INFO [train.py:763] (3/8) Epoch 27, batch 3350, loss[loss=0.1663, simple_loss=0.268, pruned_loss=0.03228, over 7368.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2633, pruned_loss=0.03228, over 1421150.49 frames.], batch size: 23, lr: 2.77e-04
2022-04-30 06:07:23,074 INFO [train.py:763] (3/8) Epoch 27, batch 3400, loss[loss=0.147, simple_loss=0.2413, pruned_loss=0.02638, over 7318.00 frames.], tot_loss[loss=0.165, simple_loss=0.2643, pruned_loss=0.03282, over 1422912.20 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:08:29,074 INFO [train.py:763] (3/8) Epoch 27, batch 3450, loss[loss=0.1735, simple_loss=0.2721, pruned_loss=0.03747, over 7193.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2637, pruned_loss=0.03226, over 1424323.99 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:09:34,967 INFO [train.py:763] (3/8) Epoch 27, batch 3500, loss[loss=0.1571, simple_loss=0.2504, pruned_loss=0.03193, over 7064.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2628, pruned_loss=0.03199, over 1423085.65 frames.], batch size: 18, lr: 2.77e-04
2022-04-30 06:10:40,826 INFO [train.py:763] (3/8) Epoch 27, batch 3550, loss[loss=0.1646, simple_loss=0.2711, pruned_loss=0.0291, over 7340.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2634, pruned_loss=0.03211, over 1423572.18 frames.], batch size: 22, lr: 2.77e-04
2022-04-30 06:11:46,447 INFO [train.py:763] (3/8) Epoch 27, batch 3600, loss[loss=0.1537, simple_loss=0.2438, pruned_loss=0.03182, over 7452.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03224, over 1423072.48 frames.], batch size: 19, lr: 2.77e-04
2022-04-30 06:12:52,025 INFO [train.py:763] (3/8) Epoch 27, batch 3650, loss[loss=0.1857, simple_loss=0.2851, pruned_loss=0.04315, over 7417.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2633, pruned_loss=0.03222, over 1424263.83 frames.], batch size: 21, lr: 2.77e-04
2022-04-30 06:13:58,380 INFO [train.py:763] (3/8) Epoch 27, batch 3700, loss[loss=0.1599, simple_loss=0.2649, pruned_loss=0.02747, over 7427.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03233, over 1424397.56 frames.], batch size: 20, lr: 2.77e-04
2022-04-30 06:15:04,062 INFO [train.py:763] (3/8) Epoch 27, batch 3750, loss[loss=0.1788, simple_loss=0.2806, pruned_loss=0.03848, over 4883.00 frames.], tot_loss[loss=0.164, simple_loss=0.2636, pruned_loss=0.03217, over 1418685.95 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:16:10,307 INFO [train.py:763] (3/8) Epoch 27, batch 3800, loss[loss=0.1441, simple_loss=0.2415, pruned_loss=0.0234, over 7263.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2631, pruned_loss=0.03166, over 1421740.59 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:17:16,530 INFO [train.py:763] (3/8) Epoch 27, batch 3850, loss[loss=0.1542, simple_loss=0.2591, pruned_loss=0.02465, over 7153.00 frames.], tot_loss[loss=0.163, simple_loss=0.2633, pruned_loss=0.03142, over 1426493.09 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:18:22,911 INFO [train.py:763] (3/8) Epoch 27, batch 3900, loss[loss=0.1819, simple_loss=0.2773, pruned_loss=0.04329, over 7214.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2637, pruned_loss=0.03175, over 1425404.80 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:19:28,539 INFO [train.py:763] (3/8) Epoch 27, batch 3950, loss[loss=0.1765, simple_loss=0.2851, pruned_loss=0.03394, over 7202.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2634, pruned_loss=0.03161, over 1426409.96 frames.], batch size: 22, lr: 2.76e-04
2022-04-30 06:20:34,797 INFO [train.py:763] (3/8) Epoch 27, batch 4000, loss[loss=0.1604, simple_loss=0.2636, pruned_loss=0.02859, over 6662.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03125, over 1422953.78 frames.], batch size: 31, lr: 2.76e-04
2022-04-30 06:21:40,918 INFO [train.py:763] (3/8) Epoch 27, batch 4050, loss[loss=0.19, simple_loss=0.2819, pruned_loss=0.04904, over 5058.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2635, pruned_loss=0.03207, over 1417394.19 frames.], batch size: 52, lr: 2.76e-04
2022-04-30 06:22:47,108 INFO [train.py:763] (3/8) Epoch 27, batch 4100, loss[loss=0.1459, simple_loss=0.2313, pruned_loss=0.03026, over 7137.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2629, pruned_loss=0.03218, over 1419724.71 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:24:03,944 INFO [train.py:763] (3/8) Epoch 27, batch 4150, loss[loss=0.1531, simple_loss=0.2465, pruned_loss=0.02987, over 7165.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2633, pruned_loss=0.03253, over 1424991.65 frames.], batch size: 19, lr: 2.76e-04
2022-04-30 06:25:09,375 INFO [train.py:763] (3/8) Epoch 27, batch 4200, loss[loss=0.1779, simple_loss=0.275, pruned_loss=0.04037, over 5022.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2637, pruned_loss=0.03246, over 1418126.72 frames.], batch size: 54, lr: 2.76e-04
2022-04-30 06:26:15,106 INFO [train.py:763] (3/8) Epoch 27, batch 4250, loss[loss=0.1388, simple_loss=0.2286, pruned_loss=0.0245, over 7070.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2637, pruned_loss=0.03233, over 1416106.81 frames.], batch size: 18, lr: 2.76e-04
2022-04-30 06:27:21,139 INFO [train.py:763] (3/8) Epoch 27, batch 4300, loss[loss=0.1667, simple_loss=0.2627, pruned_loss=0.03538, over 7136.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03193, over 1417466.68 frames.], batch size: 17, lr: 2.76e-04
2022-04-30 06:28:27,401 INFO [train.py:763] (3/8) Epoch 27, batch 4350, loss[loss=0.1693, simple_loss=0.2813, pruned_loss=0.02861, over 7212.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2636, pruned_loss=0.03182, over 1417697.67 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:29:33,356 INFO [train.py:763] (3/8) Epoch 27, batch 4400, loss[loss=0.1608, simple_loss=0.2685, pruned_loss=0.02656, over 6411.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2631, pruned_loss=0.03189, over 1409549.45 frames.], batch size: 38, lr: 2.76e-04
2022-04-30 06:30:39,368 INFO [train.py:763] (3/8) Epoch 27, batch 4450, loss[loss=0.1301, simple_loss=0.2253, pruned_loss=0.01745, over 6830.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2639, pruned_loss=0.03252, over 1403163.91 frames.], batch size: 15, lr: 2.76e-04
2022-04-30 06:31:44,898 INFO [train.py:763] (3/8) Epoch 27, batch 4500, loss[loss=0.1728, simple_loss=0.2761, pruned_loss=0.03475, over 7215.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2646, pruned_loss=0.03279, over 1391049.47 frames.], batch size: 21, lr: 2.76e-04
2022-04-30 06:32:50,035 INFO [train.py:763] (3/8) Epoch 27, batch 4550, loss[loss=0.1534, simple_loss=0.2608, pruned_loss=0.02299, over 6450.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2651, pruned_loss=0.03312, over 1361387.22 frames.], batch size: 38, lr: 2.76e-04
2022-04-30 06:34:19,191 INFO [train.py:763] (3/8) Epoch 28, batch 0, loss[loss=0.1656, simple_loss=0.2679, pruned_loss=0.03169, over 6986.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2679, pruned_loss=0.03169, over 6986.00 frames.], batch size: 28, lr: 2.71e-04
2022-04-30 06:35:24,833 INFO [train.py:763] (3/8) Epoch 28, batch 50, loss[loss=0.1921, simple_loss=0.292, pruned_loss=0.04612, over 7282.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2628, pruned_loss=0.03082, over 323098.20 frames.], batch size: 24, lr: 2.71e-04
2022-04-30 06:36:31,682 INFO [train.py:763] (3/8) Epoch 28, batch 100, loss[loss=0.1742, simple_loss=0.2809, pruned_loss=0.03377, over 7309.00 frames.], tot_loss[loss=0.164, simple_loss=0.2632, pruned_loss=0.03238, over 568899.43 frames.], batch size: 21, lr: 2.71e-04
2022-04-30 06:37:37,371 INFO [train.py:763] (3/8) Epoch 28, batch 150, loss[loss=0.1696, simple_loss=0.2697, pruned_loss=0.03473, over 7233.00 frames.], tot_loss[loss=0.1638, simple_loss=0.263, pruned_loss=0.03228, over 759328.41 frames.], batch size: 20, lr: 2.71e-04
2022-04-30 06:38:43,639 INFO [train.py:763] (3/8) Epoch 28, batch 200, loss[loss=0.1532, simple_loss=0.2503, pruned_loss=0.02803, over 7071.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2623, pruned_loss=0.03212, over 909211.70 frames.], batch size: 18, lr: 2.71e-04
2022-04-30 06:39:49,239 INFO [train.py:763] (3/8) Epoch 28, batch 250, loss[loss=0.1797, simple_loss=0.268, pruned_loss=0.0457, over 4886.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2622, pruned_loss=0.03201, over 1020028.34 frames.], batch size: 53, lr: 2.71e-04
2022-04-30 06:40:54,482 INFO [train.py:763] (3/8) Epoch 28, batch 300, loss[loss=0.1718, simple_loss=0.2577, pruned_loss=0.04296, over 7159.00 frames.], tot_loss[loss=0.163, simple_loss=0.2627, pruned_loss=0.03167, over 1109589.45 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:41:59,622 INFO [train.py:763] (3/8) Epoch 28, batch 350, loss[loss=0.1543, simple_loss=0.2652, pruned_loss=0.02171, over 7065.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2633, pruned_loss=0.03153, over 1181051.67 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:43:05,886 INFO [train.py:763] (3/8) Epoch 28, batch 400, loss[loss=0.1757, simple_loss=0.2838, pruned_loss=0.03384, over 7129.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2636, pruned_loss=0.03163, over 1236960.41 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:44:12,420 INFO [train.py:763] (3/8) Epoch 28, batch 450, loss[loss=0.1828, simple_loss=0.285, pruned_loss=0.04034, over 7118.00 frames.], tot_loss[loss=0.1639, simple_loss=0.264, pruned_loss=0.03184, over 1282646.52 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:45:17,936 INFO [train.py:763] (3/8) Epoch 28, batch 500, loss[loss=0.1633, simple_loss=0.2664, pruned_loss=0.03015, over 5264.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03186, over 1309240.86 frames.], batch size: 52, lr: 2.70e-04
2022-04-30 06:46:23,647 INFO [train.py:763] (3/8) Epoch 28, batch 550, loss[loss=0.1587, simple_loss=0.2606, pruned_loss=0.02843, over 7218.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03168, over 1331613.66 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:47:29,778 INFO [train.py:763] (3/8) Epoch 28, batch 600, loss[loss=0.16, simple_loss=0.2528, pruned_loss=0.03362, over 7273.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2626, pruned_loss=0.03139, over 1347834.00 frames.], batch size: 19, lr: 2.70e-04
2022-04-30 06:48:35,459 INFO [train.py:763] (3/8) Epoch 28, batch 650, loss[loss=0.1394, simple_loss=0.2293, pruned_loss=0.02476, over 7055.00 frames.], tot_loss[loss=0.1626, simple_loss=0.262, pruned_loss=0.03157, over 1367172.39 frames.], batch size: 18, lr: 2.70e-04
2022-04-30 06:49:42,649 INFO [train.py:763] (3/8) Epoch 28, batch 700, loss[loss=0.1717, simple_loss=0.2812, pruned_loss=0.03112, over 5169.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2627, pruned_loss=0.03188, over 1375163.46 frames.], batch size: 52, lr: 2.70e-04
2022-04-30 06:50:48,227 INFO [train.py:763] (3/8) Epoch 28, batch 750, loss[loss=0.1394, simple_loss=0.2352, pruned_loss=0.02175, over 7433.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03199, over 1381401.73 frames.], batch size: 20, lr: 2.70e-04
2022-04-30 06:51:53,703 INFO [train.py:763] (3/8) Epoch 28, batch 800, loss[loss=0.1709, simple_loss=0.2748, pruned_loss=0.03347, over 7114.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2633, pruned_loss=0.03209, over 1387512.70 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:52:59,916 INFO [train.py:763] (3/8) Epoch 28, batch 850, loss[loss=0.1739, simple_loss=0.2763, pruned_loss=0.03578, over 6278.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03172, over 1392177.70 frames.], batch size: 37, lr: 2.70e-04
2022-04-30 06:54:06,450 INFO [train.py:763] (3/8) Epoch 28, batch 900, loss[loss=0.1453, simple_loss=0.253, pruned_loss=0.0188, over 6729.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03178, over 1399355.42 frames.], batch size: 31, lr: 2.70e-04
2022-04-30 06:55:12,063 INFO [train.py:763] (3/8) Epoch 28, batch 950, loss[loss=0.1823, simple_loss=0.2768, pruned_loss=0.04389, over 7202.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2631, pruned_loss=0.03183, over 1408583.61 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 06:56:17,977 INFO [train.py:763] (3/8) Epoch 28, batch 1000, loss[loss=0.1471, simple_loss=0.2323, pruned_loss=0.031, over 6827.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2623, pruned_loss=0.03171, over 1414320.77 frames.], batch size: 15, lr: 2.70e-04
2022-04-30 06:57:23,496 INFO [train.py:763] (3/8) Epoch 28, batch 1050, loss[loss=0.1656, simple_loss=0.2843, pruned_loss=0.02344, over 7406.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.0318, over 1419767.55 frames.], batch size: 21, lr: 2.70e-04
2022-04-30 06:58:29,248 INFO [train.py:763] (3/8) Epoch 28, batch 1100, loss[loss=0.1524, simple_loss=0.25, pruned_loss=0.02735, over 7276.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03182, over 1422589.04 frames.], batch size: 17, lr: 2.70e-04
2022-04-30 06:59:35,656 INFO [train.py:763] (3/8) Epoch 28, batch 1150, loss[loss=0.1749, simple_loss=0.2809, pruned_loss=0.03447, over 7101.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2632, pruned_loss=0.03186, over 1421328.77 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:00:40,811 INFO [train.py:763] (3/8) Epoch 28, batch 1200, loss[loss=0.1677, simple_loss=0.2708, pruned_loss=0.03229, over 7093.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2641, pruned_loss=0.03176, over 1423193.74 frames.], batch size: 28, lr: 2.70e-04
2022-04-30 07:01:47,022 INFO [train.py:763] (3/8) Epoch 28, batch 1250, loss[loss=0.1724, simple_loss=0.2742, pruned_loss=0.03528, over 7217.00 frames.], tot_loss[loss=0.1643, simple_loss=0.264, pruned_loss=0.03231, over 1417083.12 frames.], batch size: 22, lr: 2.70e-04
2022-04-30 07:02:52,926 INFO [train.py:763] (3/8) Epoch 28, batch 1300, loss[loss=0.1686, simple_loss=0.2814, pruned_loss=0.02791, over 7148.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.0322, over 1420193.30 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:03:58,473 INFO [train.py:763] (3/8) Epoch 28, batch 1350, loss[loss=0.1552, simple_loss=0.2663, pruned_loss=0.02199, over 7110.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03174, over 1426073.67 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:05:04,525 INFO [train.py:763] (3/8) Epoch 28, batch 1400, loss[loss=0.1366, simple_loss=0.2311, pruned_loss=0.02103, over 7289.00 frames.], tot_loss[loss=0.163, simple_loss=0.2626, pruned_loss=0.03169, over 1427051.33 frames.], batch size: 17, lr: 2.69e-04
2022-04-30 07:06:10,007 INFO [train.py:763] (3/8) Epoch 28, batch 1450, loss[loss=0.1568, simple_loss=0.2577, pruned_loss=0.02798, over 7282.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2621, pruned_loss=0.03161, over 1431117.48 frames.], batch size: 24, lr: 2.69e-04
2022-04-30 07:07:16,028 INFO [train.py:763] (3/8) Epoch 28, batch 1500, loss[loss=0.1485, simple_loss=0.2576, pruned_loss=0.01971, over 7332.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03138, over 1427654.13 frames.], batch size: 20, lr: 2.69e-04
2022-04-30 07:08:21,693 INFO [train.py:763] (3/8) Epoch 28, batch 1550, loss[loss=0.1525, simple_loss=0.2514, pruned_loss=0.02675, over 7220.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.03154, over 1430243.58 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:09:26,978 INFO [train.py:763] (3/8) Epoch 28, batch 1600, loss[loss=0.1504, simple_loss=0.2429, pruned_loss=0.02895, over 6827.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03161, over 1427449.99 frames.], batch size: 15, lr: 2.69e-04
2022-04-30 07:10:32,955 INFO [train.py:763] (3/8) Epoch 28, batch 1650, loss[loss=0.1426, simple_loss=0.2368, pruned_loss=0.02416, over 7220.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03143, over 1429325.15 frames.], batch size: 16, lr: 2.69e-04
2022-04-30 07:11:39,860 INFO [train.py:763] (3/8) Epoch 28, batch 1700, loss[loss=0.1634, simple_loss=0.2643, pruned_loss=0.03127, over 7267.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2624, pruned_loss=0.03119, over 1431611.50 frames.], batch size: 19, lr: 2.69e-04
2022-04-30 07:12:45,211 INFO [train.py:763] (3/8) Epoch 28, batch 1750, loss[loss=0.1678, simple_loss=0.2739, pruned_loss=0.03089, over 7115.00 frames.], tot_loss[loss=0.1629, simple_loss=0.263, pruned_loss=0.03144, over 1433145.28 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:13:50,836 INFO [train.py:763] (3/8) Epoch 28, batch 1800, loss[loss=0.1363, simple_loss=0.2242, pruned_loss=0.02424, over 6991.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03128, over 1423246.41 frames.], batch size: 16, lr: 2.69e-04
2022-04-30 07:14:56,956 INFO [train.py:763] (3/8) Epoch 28, batch 1850, loss[loss=0.1494, simple_loss=0.2366, pruned_loss=0.03112, over 7410.00 frames.], tot_loss[loss=0.1635, simple_loss=0.263, pruned_loss=0.03196, over 1425477.83 frames.], batch size: 18, lr: 2.69e-04
2022-04-30 07:16:02,989 INFO [train.py:763] (3/8) Epoch 28, batch 1900, loss[loss=0.1675, simple_loss=0.2711, pruned_loss=0.03195, over 7177.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2632, pruned_loss=0.03166, over 1425866.44 frames.], batch size: 26, lr: 2.69e-04
2022-04-30 07:17:09,676 INFO [train.py:763] (3/8) Epoch 28, batch 1950, loss[loss=0.1738, simple_loss=0.2797, pruned_loss=0.03393, over 7286.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2633, pruned_loss=0.03186, over 1428986.90 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:18:15,509 INFO [train.py:763] (3/8) Epoch 28, batch 2000, loss[loss=0.1463, simple_loss=0.2573, pruned_loss=0.01763, over 7195.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2628, pruned_loss=0.03173, over 1431282.26 frames.], batch size: 23, lr: 2.69e-04
2022-04-30 07:19:21,141 INFO [train.py:763] (3/8) Epoch 28, batch 2050, loss[loss=0.1589, simple_loss=0.2564, pruned_loss=0.03075, over 7320.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2632, pruned_loss=0.03204, over 1423669.19 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:20:26,743 INFO [train.py:763] (3/8) Epoch 28, batch 2100, loss[loss=0.1761, simple_loss=0.2702, pruned_loss=0.04103, over 7336.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03165, over 1425408.42 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:21:33,842 INFO [train.py:763] (3/8) Epoch 28, batch 2150, loss[loss=0.1551, simple_loss=0.2732, pruned_loss=0.01857, over 7226.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03151, over 1426421.36 frames.], batch size: 21, lr: 2.69e-04
2022-04-30 07:22:48,758 INFO [train.py:763] (3/8) Epoch 28, batch 2200, loss[loss=0.1651, simple_loss=0.2728, pruned_loss=0.02867, over 7265.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2621, pruned_loss=0.03149, over 1420707.30 frames.], batch size: 25, lr: 2.69e-04
2022-04-30 07:23:56,113 INFO [train.py:763] (3/8) Epoch 28, batch 2250, loss[loss=0.164, simple_loss=0.2649, pruned_loss=0.03157, over 7123.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03156, over 1424770.21 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:25:01,838 INFO [train.py:763] (3/8) Epoch 28, batch 2300, loss[loss=0.1821, simple_loss=0.2801, pruned_loss=0.04212, over 7279.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03141, over 1426308.44 frames.], batch size: 24, lr: 2.68e-04
2022-04-30 07:26:07,548 INFO [train.py:763] (3/8) Epoch 28, batch 2350, loss[loss=0.149, simple_loss=0.2424, pruned_loss=0.02778, over 7055.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2624, pruned_loss=0.03164, over 1423885.01 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:27:14,914 INFO [train.py:763] (3/8) Epoch 28, batch 2400, loss[loss=0.1612, simple_loss=0.2619, pruned_loss=0.03028, over 7368.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2618, pruned_loss=0.03172, over 1425854.66 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:28:20,437 INFO [train.py:763] (3/8) Epoch 28, batch 2450, loss[loss=0.1826, simple_loss=0.294, pruned_loss=0.03559, over 7099.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2627, pruned_loss=0.03211, over 1416701.31 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:29:26,088 INFO [train.py:763] (3/8) Epoch 28, batch 2500, loss[loss=0.1302, simple_loss=0.2262, pruned_loss=0.01712, over 7401.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2615, pruned_loss=0.03153, over 1419629.60 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:30:32,240 INFO [train.py:763] (3/8) Epoch 28, batch 2550, loss[loss=0.1383, simple_loss=0.2245, pruned_loss=0.02608, over 7167.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2612, pruned_loss=0.03156, over 1417197.53 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:31:37,898 INFO [train.py:763] (3/8) Epoch 28, batch 2600, loss[loss=0.1646, simple_loss=0.2715, pruned_loss=0.02885, over 7212.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2616, pruned_loss=0.03187, over 1415308.56 frames.], batch size: 23, lr: 2.68e-04
2022-04-30 07:32:43,455 INFO [train.py:763] (3/8) Epoch 28, batch 2650, loss[loss=0.1474, simple_loss=0.2395, pruned_loss=0.02769, over 7419.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2613, pruned_loss=0.03172, over 1417840.29 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:33:59,643 INFO [train.py:763] (3/8) Epoch 28, batch 2700, loss[loss=0.1768, simple_loss=0.266, pruned_loss=0.04379, over 5085.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2613, pruned_loss=0.03181, over 1418133.13 frames.], batch size: 53, lr: 2.68e-04
2022-04-30 07:35:13,952 INFO [train.py:763] (3/8) Epoch 28, batch 2750, loss[loss=0.158, simple_loss=0.2626, pruned_loss=0.02672, over 7325.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2619, pruned_loss=0.03163, over 1414619.45 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:36:28,354 INFO [train.py:763] (3/8) Epoch 28, batch 2800, loss[loss=0.1627, simple_loss=0.2595, pruned_loss=0.03297, over 7330.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2624, pruned_loss=0.03168, over 1417221.07 frames.], batch size: 22, lr: 2.68e-04
2022-04-30 07:37:44,241 INFO [train.py:763] (3/8) Epoch 28, batch 2850, loss[loss=0.1765, simple_loss=0.2788, pruned_loss=0.03709, over 7268.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2625, pruned_loss=0.03204, over 1418247.12 frames.], batch size: 19, lr: 2.68e-04
2022-04-30 07:38:58,497 INFO [train.py:763] (3/8) Epoch 28, batch 2900, loss[loss=0.1645, simple_loss=0.2505, pruned_loss=0.0392, over 7275.00 frames.], tot_loss[loss=0.163, simple_loss=0.2623, pruned_loss=0.03183, over 1417238.87 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:40:13,606 INFO [train.py:763] (3/8) Epoch 28, batch 2950, loss[loss=0.1456, simple_loss=0.2381, pruned_loss=0.02653, over 7136.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2614, pruned_loss=0.03158, over 1418219.95 frames.], batch size: 17, lr: 2.68e-04
2022-04-30 07:41:27,528 INFO [train.py:763] (3/8) Epoch 28, batch 3000, loss[loss=0.1638, simple_loss=0.259, pruned_loss=0.03427, over 7239.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2625, pruned_loss=0.03167, over 1419683.60 frames.], batch size: 20, lr: 2.68e-04
2022-04-30 07:41:27,529 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 07:41:44,121 INFO [train.py:792] (3/8) Epoch 28, validation: loss=0.1685, simple_loss=0.2656, pruned_loss=0.03573, over 698248.00 frames.
2022-04-30 07:42:49,822 INFO [train.py:763] (3/8) Epoch 28, batch 3050, loss[loss=0.1521, simple_loss=0.2474, pruned_loss=0.02841, over 7161.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03163, over 1422190.44 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:43:55,530 INFO [train.py:763] (3/8) Epoch 28, batch 3100, loss[loss=0.1553, simple_loss=0.2412, pruned_loss=0.03471, over 7289.00 frames.], tot_loss[loss=0.1627, simple_loss=0.262, pruned_loss=0.03166, over 1419361.12 frames.], batch size: 18, lr: 2.68e-04
2022-04-30 07:45:01,628 INFO [train.py:763] (3/8) Epoch 28, batch 3150, loss[loss=0.1877, simple_loss=0.2808, pruned_loss=0.04729, over 7221.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2629, pruned_loss=0.03188, over 1422807.29 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:46:07,723 INFO [train.py:763] (3/8) Epoch 28, batch 3200, loss[loss=0.1568, simple_loss=0.2672, pruned_loss=0.02321, over 7109.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.0313, over 1422554.82 frames.], batch size: 21, lr: 2.68e-04
2022-04-30 07:47:14,370 INFO [train.py:763] (3/8) Epoch 28, batch 3250, loss[loss=0.1379, simple_loss=0.228, pruned_loss=0.02391, over 6790.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03111, over 1421692.54 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:48:20,827 INFO [train.py:763] (3/8) Epoch 28, batch 3300, loss[loss=0.1634, simple_loss=0.2683, pruned_loss=0.02919, over 7222.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2628, pruned_loss=0.0318, over 1421650.58 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 07:49:26,929 INFO [train.py:763] (3/8) Epoch 28, batch 3350, loss[loss=0.1704, simple_loss=0.264, pruned_loss=0.03833, over 7020.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2619, pruned_loss=0.03177, over 1419766.83 frames.], batch size: 28, lr: 2.67e-04
2022-04-30 07:50:33,793 INFO [train.py:763] (3/8) Epoch 28, batch 3400, loss[loss=0.1644, simple_loss=0.2548, pruned_loss=0.03703, over 7067.00 frames.], tot_loss[loss=0.163, simple_loss=0.2621, pruned_loss=0.03191, over 1416853.11 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:51:39,844 INFO [train.py:763] (3/8) Epoch 28, batch 3450, loss[loss=0.1337, simple_loss=0.2239, pruned_loss=0.02177, over 7275.00 frames.], tot_loss[loss=0.163, simple_loss=0.2621, pruned_loss=0.03192, over 1419722.57 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 07:52:45,405 INFO [train.py:763] (3/8) Epoch 28, batch 3500, loss[loss=0.1744, simple_loss=0.2869, pruned_loss=0.03097, over 6810.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03168, over 1418996.38 frames.], batch size: 31, lr: 2.67e-04
2022-04-30 07:53:50,880 INFO [train.py:763] (3/8) Epoch 28, batch 3550, loss[loss=0.1526, simple_loss=0.2593, pruned_loss=0.023, over 7285.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2621, pruned_loss=0.03159, over 1422522.36 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 07:54:56,701 INFO [train.py:763] (3/8) Epoch 28, batch 3600, loss[loss=0.1376, simple_loss=0.2326, pruned_loss=0.02132, over 6792.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.0317, over 1422889.58 frames.], batch size: 15, lr: 2.67e-04
2022-04-30 07:56:02,360 INFO [train.py:763] (3/8) Epoch 28, batch 3650, loss[loss=0.1623, simple_loss=0.2687, pruned_loss=0.028, over 7321.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2615, pruned_loss=0.03133, over 1426505.28 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 07:57:08,116 INFO [train.py:763] (3/8) Epoch 28, batch 3700, loss[loss=0.1825, simple_loss=0.283, pruned_loss=0.04101, over 7210.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.03134, over 1425992.62 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 07:58:13,560 INFO [train.py:763] (3/8) Epoch 28, batch 3750, loss[loss=0.1926, simple_loss=0.289, pruned_loss=0.0481, over 4543.00 frames.], tot_loss[loss=0.1624, simple_loss=0.262, pruned_loss=0.03139, over 1424608.68 frames.], batch size: 52, lr: 2.67e-04
2022-04-30 07:59:19,061 INFO [train.py:763] (3/8) Epoch 28, batch 3800, loss[loss=0.1696, simple_loss=0.2626, pruned_loss=0.03833, over 7432.00 frames.], tot_loss[loss=0.163, simple_loss=0.2627, pruned_loss=0.03161, over 1425200.33 frames.], batch size: 20, lr: 2.67e-04
2022-04-30 08:00:24,609 INFO [train.py:763] (3/8) Epoch 28, batch 3850, loss[loss=0.1674, simple_loss=0.2726, pruned_loss=0.03113, over 7389.00 frames.], tot_loss[loss=0.163, simple_loss=0.2629, pruned_loss=0.03151, over 1426285.95 frames.], batch size: 23, lr: 2.67e-04
2022-04-30 08:01:31,043 INFO [train.py:763] (3/8) Epoch 28, batch 3900, loss[loss=0.186, simple_loss=0.284, pruned_loss=0.04395, over 7315.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2639, pruned_loss=0.03168, over 1429404.36 frames.], batch size: 24, lr: 2.67e-04
2022-04-30 08:02:37,690 INFO [train.py:763] (3/8) Epoch 28, batch 3950, loss[loss=0.1437, simple_loss=0.2359, pruned_loss=0.02579, over 7408.00 frames.], tot_loss[loss=0.1645, simple_loss=0.265, pruned_loss=0.03199, over 1430936.39 frames.], batch size: 18, lr: 2.67e-04
2022-04-30 08:03:44,063 INFO [train.py:763] (3/8) Epoch 28, batch 4000, loss[loss=0.1791, simple_loss=0.2769, pruned_loss=0.04065, over 7324.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2651, pruned_loss=0.03194, over 1430125.21 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:04:50,783 INFO [train.py:763] (3/8) Epoch 28, batch 4050, loss[loss=0.1369, simple_loss=0.2326, pruned_loss=0.02059, over 7266.00 frames.], tot_loss[loss=0.1644, simple_loss=0.265, pruned_loss=0.03187, over 1429756.12 frames.], batch size: 17, lr: 2.67e-04
2022-04-30 08:05:55,978 INFO [train.py:763] (3/8) Epoch 28, batch 4100, loss[loss=0.168, simple_loss=0.2713, pruned_loss=0.03237, over 7357.00 frames.], tot_loss[loss=0.1636, simple_loss=0.264, pruned_loss=0.03162, over 1430224.34 frames.], batch size: 22, lr: 2.67e-04
2022-04-30 08:07:02,630 INFO [train.py:763] (3/8) Epoch 28, batch 4150, loss[loss=0.1496, simple_loss=0.2493, pruned_loss=0.02493, over 7320.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2633, pruned_loss=0.03143, over 1424566.04 frames.], batch size: 21, lr: 2.67e-04
2022-04-30 08:08:09,142 INFO [train.py:763] (3/8) Epoch 28, batch 4200, loss[loss=0.1555, simple_loss=0.2624, pruned_loss=0.02426, over 7252.00 frames.], tot_loss[loss=0.164, simple_loss=0.2647, pruned_loss=0.03166, over 1421520.47 frames.], batch size: 19, lr: 2.66e-04
2022-04-30 08:09:14,666 INFO [train.py:763] (3/8) Epoch 28, batch 4250, loss[loss=0.157, simple_loss=0.2714, pruned_loss=0.02128, over 6725.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2638, pruned_loss=0.0313, over 1421695.37 frames.], batch size: 31, lr: 2.66e-04
2022-04-30 08:10:19,663 INFO [train.py:763] (3/8) Epoch 28, batch 4300, loss[loss=0.1511, simple_loss=0.2531, pruned_loss=0.02454, over 7170.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2631, pruned_loss=0.0309, over 1417458.16 frames.], batch size: 18, lr: 2.66e-04
2022-04-30 08:11:24,965 INFO [train.py:763] (3/8) Epoch 28, batch 4350, loss[loss=0.1517, simple_loss=0.2619, pruned_loss=0.02074, over 7318.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03072, over 1417972.15 frames.], batch size: 21, lr: 2.66e-04
2022-04-30 08:12:30,142 INFO [train.py:763] (3/8) Epoch 28, batch 4400, loss[loss=0.1867, simple_loss=0.277, pruned_loss=0.04818, over 7292.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2628, pruned_loss=0.03134, over 1410148.79 frames.], batch size: 24, lr: 2.66e-04
2022-04-30 08:13:35,272 INFO [train.py:763] (3/8) Epoch 28, batch 4450, loss[loss=0.1815, simple_loss=0.2859, pruned_loss=0.03852, over 6443.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2625, pruned_loss=0.03152, over 1401273.94 frames.], batch size: 38, lr: 2.66e-04
2022-04-30 08:14:40,128 INFO [train.py:763] (3/8) Epoch 28, batch 4500, loss[loss=0.1759, simple_loss=0.2846, pruned_loss=0.03358, over 7197.00 frames.], tot_loss[loss=0.164, simple_loss=0.2635, pruned_loss=0.03229, over 1378330.86 frames.], batch size: 22, lr: 2.66e-04
2022-04-30 08:15:45,361 INFO [train.py:763] (3/8) Epoch 28, batch 4550, loss[loss=0.1874, simple_loss=0.2767, pruned_loss=0.049, over 4873.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2655, pruned_loss=0.03294, over 1359749.28 frames.], batch size: 52, lr: 2.66e-04
2022-04-30 08:17:05,887 INFO [train.py:763] (3/8) Epoch 29, batch 0, loss[loss=0.1692, simple_loss=0.2687, pruned_loss=0.03485, over 7326.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2687, pruned_loss=0.03485, over 7326.00 frames.], batch size: 20, lr: 2.62e-04
2022-04-30 08:18:11,688 INFO [train.py:763] (3/8) Epoch 29, batch 50, loss[loss=0.1664, simple_loss=0.2542, pruned_loss=0.03927, over 7270.00 frames.], tot_loss[loss=0.1615, simple_loss=0.261, pruned_loss=0.03098, over 323547.71 frames.], batch size: 18, lr: 2.62e-04
2022-04-30 08:19:17,258 INFO [train.py:763] (3/8) Epoch 29, batch 100, loss[loss=0.1383, simple_loss=0.2314, pruned_loss=0.02261, over 7275.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03011, over 571714.68 frames.], batch size: 17, lr: 2.62e-04
2022-04-30 08:20:22,569 INFO [train.py:763] (3/8) Epoch 29, batch 150, loss[loss=0.1713, simple_loss=0.2754, pruned_loss=0.03358, over 7309.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2603, pruned_loss=0.03049, over 750140.42 frames.], batch size: 24, lr: 2.62e-04
2022-04-30 08:21:28,003 INFO [train.py:763] (3/8) Epoch 29, batch 200, loss[loss=0.1557, simple_loss=0.2518, pruned_loss=0.02985, over 7351.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03108, over 900510.66 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:22:33,078 INFO [train.py:763] (3/8) Epoch 29, batch 250, loss[loss=0.149, simple_loss=0.236, pruned_loss=0.03097, over 6813.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2624, pruned_loss=0.03135, over 1016507.13 frames.], batch size: 15, lr: 2.61e-04
2022-04-30 08:23:39,496 INFO [train.py:763] (3/8) Epoch 29, batch 300, loss[loss=0.1733, simple_loss=0.2631, pruned_loss=0.04172, over 7289.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03203, over 1108820.18 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:24:46,637 INFO [train.py:763] (3/8) Epoch 29, batch 350, loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03202, over 7327.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2627, pruned_loss=0.03198, over 1181539.21 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:25:52,370 INFO [train.py:763] (3/8) Epoch 29, batch 400, loss[loss=0.1826, simple_loss=0.2812, pruned_loss=0.04194, over 7292.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2622, pruned_loss=0.03195, over 1237498.55 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:26:57,828 INFO [train.py:763] (3/8) Epoch 29, batch 450, loss[loss=0.1778, simple_loss=0.2764, pruned_loss=0.0396, over 7416.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2619, pruned_loss=0.03182, over 1280002.96 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:28:03,213 INFO [train.py:763] (3/8) Epoch 29, batch 500, loss[loss=0.1644, simple_loss=0.2638, pruned_loss=0.03251, over 7323.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03183, over 1309453.78 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:29:08,669 INFO [train.py:763] (3/8) Epoch 29, batch 550, loss[loss=0.146, simple_loss=0.2519, pruned_loss=0.02006, over 7271.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03154, over 1337193.75 frames.], batch size: 24, lr: 2.61e-04
2022-04-30 08:30:14,685 INFO [train.py:763] (3/8) Epoch 29, batch 600, loss[loss=0.1759, simple_loss=0.2733, pruned_loss=0.03922, over 7208.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2627, pruned_loss=0.03139, over 1352098.24 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:31:20,872 INFO [train.py:763] (3/8) Epoch 29, batch 650, loss[loss=0.1507, simple_loss=0.2489, pruned_loss=0.02626, over 7062.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03135, over 1366830.76 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:32:27,046 INFO [train.py:763] (3/8) Epoch 29, batch 700, loss[loss=0.1747, simple_loss=0.2741, pruned_loss=0.03768, over 7333.00 frames.], tot_loss[loss=0.163, simple_loss=0.2628, pruned_loss=0.03155, over 1375298.61 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:33:32,281 INFO [train.py:763] (3/8) Epoch 29, batch 750, loss[loss=0.1693, simple_loss=0.2757, pruned_loss=0.03147, over 7232.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.03217, over 1381240.51 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:34:37,539 INFO [train.py:763] (3/8) Epoch 29, batch 800, loss[loss=0.1793, simple_loss=0.2877, pruned_loss=0.03538, over 7334.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03196, over 1387692.17 frames.], batch size: 22, lr: 2.61e-04
2022-04-30 08:35:43,021 INFO [train.py:763] (3/8) Epoch 29, batch 850, loss[loss=0.1519, simple_loss=0.2487, pruned_loss=0.02749, over 7070.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2618, pruned_loss=0.03139, over 1397129.72 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:36:48,529 INFO [train.py:763] (3/8) Epoch 29, batch 900, loss[loss=0.1603, simple_loss=0.2695, pruned_loss=0.02549, over 7214.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03133, over 1400761.79 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:37:53,908 INFO [train.py:763] (3/8) Epoch 29, batch 950, loss[loss=0.1769, simple_loss=0.2798, pruned_loss=0.03704, over 7113.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2634, pruned_loss=0.03183, over 1407167.06 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:38:59,973 INFO [train.py:763] (3/8) Epoch 29, batch 1000, loss[loss=0.1712, simple_loss=0.28, pruned_loss=0.0312, over 7149.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2648, pruned_loss=0.03219, over 1410395.07 frames.], batch size: 20, lr: 2.61e-04
2022-04-30 08:40:06,269 INFO [train.py:763] (3/8) Epoch 29, batch 1050, loss[loss=0.1581, simple_loss=0.2535, pruned_loss=0.03135, over 7295.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2651, pruned_loss=0.03232, over 1406145.44 frames.], batch size: 18, lr: 2.61e-04
2022-04-30 08:41:11,504 INFO [train.py:763] (3/8) Epoch 29, batch 1100, loss[loss=0.1628, simple_loss=0.2704, pruned_loss=0.02756, over 7319.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2652, pruned_loss=0.03226, over 1415835.74 frames.], batch size: 21, lr: 2.61e-04
2022-04-30 08:42:16,630 INFO [train.py:763] (3/8) Epoch 29, batch 1150, loss[loss=0.1352, simple_loss=0.2275, pruned_loss=0.02141, over 6991.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2645, pruned_loss=0.03208, over 1416572.06 frames.], batch size: 16, lr: 2.61e-04
2022-04-30 08:43:21,910 INFO [train.py:763] (3/8) Epoch 29, batch 1200, loss[loss=0.1981, simple_loss=0.2922, pruned_loss=0.05197, over 7160.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2641, pruned_loss=0.03213, over 1421277.23 frames.], batch size: 19, lr: 2.61e-04
2022-04-30 08:44:27,477 INFO [train.py:763] (3/8) Epoch 29, batch 1250, loss[loss=0.1774, simple_loss=0.2787, pruned_loss=0.03803, over 4693.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2626, pruned_loss=0.03189, over 1416464.38 frames.], batch size: 53, lr: 2.60e-04
2022-04-30 08:45:34,623 INFO [train.py:763] (3/8) Epoch 29, batch 1300, loss[loss=0.1534, simple_loss=0.2685, pruned_loss=0.01915, over 7344.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2627, pruned_loss=0.03181, over 1417499.57 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 08:46:42,213 INFO [train.py:763] (3/8) Epoch 29, batch 1350, loss[loss=0.1516, simple_loss=0.2458, pruned_loss=0.02873, over 6457.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2629, pruned_loss=0.03201, over 1418603.68 frames.], batch size: 37, lr: 2.60e-04
2022-04-30 08:47:48,990 INFO [train.py:763] (3/8) Epoch 29, batch 1400, loss[loss=0.1697, simple_loss=0.2593, pruned_loss=0.04002, over 6790.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03175, over 1419442.51 frames.], batch size: 15, lr: 2.60e-04
2022-04-30 08:48:56,273 INFO [train.py:763] (3/8) Epoch 29, batch 1450, loss[loss=0.1783, simple_loss=0.2786, pruned_loss=0.03905, over 7122.00 frames.], tot_loss[loss=0.163, simple_loss=0.2625, pruned_loss=0.03175, over 1417628.99 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:50:03,376 INFO [train.py:763] (3/8) Epoch 29, batch 1500, loss[loss=0.1749, simple_loss=0.2679, pruned_loss=0.041, over 7251.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2628, pruned_loss=0.03212, over 1416674.73 frames.], batch size: 19, lr: 2.60e-04
2022-04-30 08:51:09,976 INFO [train.py:763] (3/8) Epoch 29, batch 1550, loss[loss=0.1678, simple_loss=0.2736, pruned_loss=0.03102, over 7206.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2632, pruned_loss=0.03215, over 1417330.69 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 08:52:16,970 INFO [train.py:763] (3/8) Epoch 29, batch 1600, loss[loss=0.1614, simple_loss=0.2592, pruned_loss=0.03182, over 7317.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2639, pruned_loss=0.03246, over 1418459.31 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:53:22,973 INFO [train.py:763] (3/8) Epoch 29, batch 1650, loss[loss=0.1696, simple_loss=0.2665, pruned_loss=0.03632, over 7142.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2621, pruned_loss=0.03176, over 1422317.53 frames.], batch size: 26, lr: 2.60e-04
2022-04-30 08:54:28,291 INFO [train.py:763] (3/8) Epoch 29, batch 1700, loss[loss=0.1652, simple_loss=0.2594, pruned_loss=0.03557, over 7135.00 frames.], tot_loss[loss=0.1625, simple_loss=0.262, pruned_loss=0.03148, over 1425435.10 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 08:55:35,255 INFO [train.py:763] (3/8) Epoch 29, batch 1750, loss[loss=0.165, simple_loss=0.267, pruned_loss=0.03154, over 7144.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.03104, over 1422420.62 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 08:56:42,194 INFO [train.py:763] (3/8) Epoch 29, batch 1800, loss[loss=0.2387, simple_loss=0.3235, pruned_loss=0.07693, over 5192.00 frames.], tot_loss[loss=0.162, simple_loss=0.2614, pruned_loss=0.03125, over 1419572.45 frames.], batch size: 53, lr: 2.60e-04
2022-04-30 08:57:49,262 INFO [train.py:763] (3/8) Epoch 29, batch 1850, loss[loss=0.1682, simple_loss=0.2786, pruned_loss=0.02895, over 7129.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03093, over 1423864.58 frames.], batch size: 21, lr: 2.60e-04
2022-04-30 08:58:55,865 INFO [train.py:763] (3/8) Epoch 29, batch 1900, loss[loss=0.1256, simple_loss=0.2212, pruned_loss=0.01503, over 7234.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.03094, over 1426872.87 frames.], batch size: 16, lr: 2.60e-04
2022-04-30 09:00:01,479 INFO [train.py:763] (3/8) Epoch 29, batch 1950, loss[loss=0.1503, simple_loss=0.2491, pruned_loss=0.02576, over 7279.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.03103, over 1428349.46 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:01:06,697 INFO [train.py:763] (3/8) Epoch 29, batch 2000, loss[loss=0.1613, simple_loss=0.27, pruned_loss=0.02627, over 7334.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03118, over 1430126.75 frames.], batch size: 22, lr: 2.60e-04
2022-04-30 09:02:12,105 INFO [train.py:763] (3/8) Epoch 29, batch 2050, loss[loss=0.173, simple_loss=0.2753, pruned_loss=0.0353, over 7223.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03092, over 1430670.49 frames.], batch size: 23, lr: 2.60e-04
2022-04-30 09:03:17,246 INFO [train.py:763] (3/8) Epoch 29, batch 2100, loss[loss=0.1627, simple_loss=0.2687, pruned_loss=0.02832, over 7146.00 frames.], tot_loss[loss=0.1619, simple_loss=0.262, pruned_loss=0.03087, over 1429811.69 frames.], batch size: 20, lr: 2.60e-04
2022-04-30 09:04:22,315 INFO [train.py:763] (3/8) Epoch 29, batch 2150, loss[loss=0.1556, simple_loss=0.2389, pruned_loss=0.03617, over 7135.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03126, over 1427990.68 frames.], batch size: 17, lr: 2.60e-04
2022-04-30 09:05:27,759 INFO [train.py:763] (3/8) Epoch 29, batch 2200, loss[loss=0.1844, simple_loss=0.2952, pruned_loss=0.03677, over 7293.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03136, over 1423342.67 frames.], batch size: 24, lr: 2.60e-04
2022-04-30 09:06:32,912 INFO [train.py:763] (3/8) Epoch 29, batch 2250, loss[loss=0.1758, simple_loss=0.2803, pruned_loss=0.03564, over 7215.00 frames.], tot_loss[loss=0.1623, simple_loss=0.262, pruned_loss=0.03129, over 1422255.00 frames.], batch size: 26, lr: 2.59e-04
2022-04-30 09:07:38,516 INFO [train.py:763] (3/8) Epoch 29, batch 2300, loss[loss=0.167, simple_loss=0.2674, pruned_loss=0.03327, over 7327.00 frames.], tot_loss[loss=0.1622, simple_loss=0.262, pruned_loss=0.03124, over 1418977.07 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:08:43,786 INFO [train.py:763] (3/8) Epoch 29, batch 2350, loss[loss=0.1712, simple_loss=0.279, pruned_loss=0.03171, over 7341.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2619, pruned_loss=0.03129, over 1420229.93 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:09:49,527 INFO [train.py:763] (3/8) Epoch 29, batch 2400, loss[loss=0.1944, simple_loss=0.2892, pruned_loss=0.04985, over 7276.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2629, pruned_loss=0.03146, over 1421630.33 frames.], batch size: 25, lr: 2.59e-04
2022-04-30 09:10:55,175 INFO [train.py:763] (3/8) Epoch 29, batch 2450, loss[loss=0.1688, simple_loss=0.2772, pruned_loss=0.03021, over 7157.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03128, over 1426171.32 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:12:00,711 INFO [train.py:763] (3/8) Epoch 29, batch 2500, loss[loss=0.1702, simple_loss=0.2552, pruned_loss=0.04261, over 6763.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2614, pruned_loss=0.03138, over 1430031.53 frames.], batch size: 15, lr: 2.59e-04
2022-04-30 09:13:06,079 INFO [train.py:763] (3/8) Epoch 29, batch 2550, loss[loss=0.1498, simple_loss=0.2376, pruned_loss=0.03098, over 7433.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.03158, over 1428028.98 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:14:11,173 INFO [train.py:763] (3/8) Epoch 29, batch 2600, loss[loss=0.1925, simple_loss=0.2925, pruned_loss=0.04627, over 7113.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2618, pruned_loss=0.03157, over 1427906.06 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:15:16,453 INFO [train.py:763] (3/8) Epoch 29, batch 2650, loss[loss=0.156, simple_loss=0.258, pruned_loss=0.02703, over 7145.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2622, pruned_loss=0.03165, over 1429398.64 frames.], batch size: 17, lr: 2.59e-04
2022-04-30 09:16:21,500 INFO [train.py:763] (3/8) Epoch 29, batch 2700, loss[loss=0.1529, simple_loss=0.2601, pruned_loss=0.02288, over 7114.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2631, pruned_loss=0.03171, over 1429370.37 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:17:27,765 INFO [train.py:763] (3/8) Epoch 29, batch 2750, loss[loss=0.2244, simple_loss=0.3112, pruned_loss=0.06879, over 7236.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2636, pruned_loss=0.03205, over 1426224.75 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:18:33,542 INFO [train.py:763] (3/8) Epoch 29, batch 2800, loss[loss=0.1644, simple_loss=0.2696, pruned_loss=0.02962, over 7329.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2634, pruned_loss=0.03196, over 1424835.92 frames.], batch size: 22, lr: 2.59e-04
2022-04-30 09:19:39,944 INFO [train.py:763] (3/8) Epoch 29, batch 2850, loss[loss=0.1593, simple_loss=0.2633, pruned_loss=0.02758, over 7239.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2623, pruned_loss=0.03163, over 1419239.64 frames.], batch size: 20, lr: 2.59e-04
2022-04-30 09:20:45,379 INFO [train.py:763] (3/8) Epoch 29, batch 2900, loss[loss=0.1358, simple_loss=0.231, pruned_loss=0.02028, over 6988.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03099, over 1421633.50 frames.], batch size: 16, lr: 2.59e-04
2022-04-30 09:22:01,683 INFO [train.py:763] (3/8) Epoch 29, batch 2950, loss[loss=0.1646, simple_loss=0.2716, pruned_loss=0.0288, over 6239.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03091, over 1422607.02 frames.], batch size: 37, lr: 2.59e-04
2022-04-30 09:23:07,150 INFO [train.py:763] (3/8) Epoch 29, batch 3000, loss[loss=0.165, simple_loss=0.2611, pruned_loss=0.03447, over 7108.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2608, pruned_loss=0.031, over 1425072.08 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:23:07,151 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 09:23:22,371 INFO [train.py:792] (3/8) Epoch 29, validation: loss=0.1693, simple_loss=0.2664, pruned_loss=0.03606, over 698248.00 frames.
2022-04-30 09:24:27,449 INFO [train.py:763] (3/8) Epoch 29, batch 3050, loss[loss=0.1776, simple_loss=0.2753, pruned_loss=0.03996, over 7113.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2616, pruned_loss=0.03148, over 1427003.80 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:25:32,593 INFO [train.py:763] (3/8) Epoch 29, batch 3100, loss[loss=0.1607, simple_loss=0.2684, pruned_loss=0.02654, over 7422.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03139, over 1427216.51 frames.], batch size: 21, lr: 2.59e-04
2022-04-30 09:26:38,421 INFO [train.py:763] (3/8) Epoch 29, batch 3150, loss[loss=0.1529, simple_loss=0.2466, pruned_loss=0.02963, over 7152.00 frames.], tot_loss[loss=0.162, simple_loss=0.2618, pruned_loss=0.03112, over 1423129.90 frames.], batch size: 18, lr: 2.59e-04
2022-04-30 09:27:44,832 INFO [train.py:763] (3/8) Epoch 29, batch 3200, loss[loss=0.1611, simple_loss=0.2615, pruned_loss=0.03035, over 7263.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.0308, over 1425481.64 frames.], batch size: 19, lr: 2.59e-04
2022-04-30 09:28:51,940 INFO [train.py:763] (3/8) Epoch 29, batch 3250, loss[loss=0.1512, simple_loss=0.2592, pruned_loss=0.02162, over 7049.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2608, pruned_loss=0.03107, over 1420433.82 frames.], batch size: 28, lr: 2.59e-04
2022-04-30 09:29:57,730 INFO [train.py:763] (3/8) Epoch 29, batch 3300, loss[loss=0.1529, simple_loss=0.254, pruned_loss=0.02595, over 7326.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03087, over 1423605.68 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:31:03,710 INFO [train.py:763] (3/8) Epoch 29, batch 3350, loss[loss=0.1457, simple_loss=0.2393, pruned_loss=0.02608, over 7278.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03093, over 1427552.26 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:32:09,339 INFO [train.py:763] (3/8) Epoch 29, batch 3400, loss[loss=0.2079, simple_loss=0.2869, pruned_loss=0.06441, over 4910.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2611, pruned_loss=0.03128, over 1424829.47 frames.], batch size: 52, lr: 2.58e-04
2022-04-30 09:33:15,079 INFO [train.py:763] (3/8) Epoch 29, batch 3450, loss[loss=0.1788, simple_loss=0.2736, pruned_loss=0.04199, over 7306.00 frames.], tot_loss[loss=0.1617, simple_loss=0.261, pruned_loss=0.03125, over 1420925.46 frames.], batch size: 24, lr: 2.58e-04
2022-04-30 09:34:21,148 INFO [train.py:763] (3/8) Epoch 29, batch 3500, loss[loss=0.1881, simple_loss=0.2931, pruned_loss=0.04156, over 7150.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.0316, over 1423008.69 frames.], batch size: 26, lr: 2.58e-04
2022-04-30 09:35:26,535 INFO [train.py:763] (3/8) Epoch 29, batch 3550, loss[loss=0.1499, simple_loss=0.2521, pruned_loss=0.02385, over 7150.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2618, pruned_loss=0.03151, over 1422527.78 frames.], batch size: 18, lr: 2.58e-04
2022-04-30 09:36:32,237 INFO [train.py:763] (3/8) Epoch 29, batch 3600, loss[loss=0.1426, simple_loss=0.2404, pruned_loss=0.02241, over 7247.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2615, pruned_loss=0.03145, over 1427081.41 frames.], batch size: 19, lr: 2.58e-04
2022-04-30 09:37:46,876 INFO [train.py:763] (3/8) Epoch 29, batch 3650, loss[loss=0.1849, simple_loss=0.2849, pruned_loss=0.04246, over 6742.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2624, pruned_loss=0.03186, over 1429030.37 frames.], batch size: 31, lr: 2.58e-04
2022-04-30 09:38:52,211 INFO [train.py:763] (3/8) Epoch 29, batch 3700, loss[loss=0.1491, simple_loss=0.2405, pruned_loss=0.02889, over 7262.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2618, pruned_loss=0.03166, over 1429693.79 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:39:59,119 INFO [train.py:763] (3/8) Epoch 29, batch 3750, loss[loss=0.179, simple_loss=0.288, pruned_loss=0.03503, over 7121.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2615, pruned_loss=0.03129, over 1432779.41 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:41:05,832 INFO [train.py:763] (3/8) Epoch 29, batch 3800, loss[loss=0.1857, simple_loss=0.2914, pruned_loss=0.04003, over 7203.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03141, over 1424999.14 frames.], batch size: 22, lr: 2.58e-04
2022-04-30 09:42:11,177 INFO [train.py:763] (3/8) Epoch 29, batch 3850, loss[loss=0.1613, simple_loss=0.2553, pruned_loss=0.03364, over 6838.00 frames.], tot_loss[loss=0.162, simple_loss=0.2617, pruned_loss=0.0312, over 1425909.15 frames.], batch size: 15, lr: 2.58e-04
2022-04-30 09:43:16,814 INFO [train.py:763] (3/8) Epoch 29, batch 3900, loss[loss=0.16, simple_loss=0.2509, pruned_loss=0.03462, over 7150.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03131, over 1426725.75 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:44:22,547 INFO [train.py:763] (3/8) Epoch 29, batch 3950, loss[loss=0.1731, simple_loss=0.2747, pruned_loss=0.03579, over 7378.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2626, pruned_loss=0.03121, over 1420635.68 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:45:27,972 INFO [train.py:763] (3/8) Epoch 29, batch 4000, loss[loss=0.162, simple_loss=0.2627, pruned_loss=0.03064, over 7284.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2636, pruned_loss=0.0314, over 1419378.99 frames.], batch size: 25, lr: 2.58e-04
2022-04-30 09:46:33,248 INFO [train.py:763] (3/8) Epoch 29, batch 4050, loss[loss=0.1789, simple_loss=0.2844, pruned_loss=0.03671, over 7039.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2626, pruned_loss=0.0315, over 1418832.49 frames.], batch size: 28, lr: 2.58e-04
2022-04-30 09:47:39,263 INFO [train.py:763] (3/8) Epoch 29, batch 4100, loss[loss=0.1705, simple_loss=0.2708, pruned_loss=0.03511, over 7323.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03155, over 1420871.97 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:48:45,601 INFO [train.py:763] (3/8) Epoch 29, batch 4150, loss[loss=0.164, simple_loss=0.2736, pruned_loss=0.0272, over 7226.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03138, over 1421031.05 frames.], batch size: 21, lr: 2.58e-04
2022-04-30 09:50:00,121 INFO [train.py:763] (3/8) Epoch 29, batch 4200, loss[loss=0.1561, simple_loss=0.2602, pruned_loss=0.02598, over 7439.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2621, pruned_loss=0.0314, over 1421356.30 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:51:13,963 INFO [train.py:763] (3/8) Epoch 29, batch 4250, loss[loss=0.1829, simple_loss=0.2973, pruned_loss=0.03428, over 7372.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2639, pruned_loss=0.03183, over 1415650.40 frames.], batch size: 23, lr: 2.58e-04
2022-04-30 09:52:28,882 INFO [train.py:763] (3/8) Epoch 29, batch 4300, loss[loss=0.1496, simple_loss=0.2414, pruned_loss=0.0289, over 7277.00 frames.], tot_loss[loss=0.1631, simple_loss=0.263, pruned_loss=0.03155, over 1420087.02 frames.], batch size: 17, lr: 2.58e-04
2022-04-30 09:53:43,987 INFO [train.py:763] (3/8) Epoch 29, batch 4350, loss[loss=0.1641, simple_loss=0.2638, pruned_loss=0.03219, over 7243.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2627, pruned_loss=0.03155, over 1421739.79 frames.], batch size: 20, lr: 2.58e-04
2022-04-30 09:54:58,497 INFO [train.py:763] (3/8) Epoch 29, batch 4400, loss[loss=0.154, simple_loss=0.2707, pruned_loss=0.01869, over 7226.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03096, over 1418613.34 frames.], batch size: 20, lr: 2.57e-04
2022-04-30 09:56:12,786 INFO [train.py:763] (3/8) Epoch 29, batch 4450, loss[loss=0.1657, simple_loss=0.2758, pruned_loss=0.02781, over 6547.00 frames.], tot_loss[loss=0.1612, simple_loss=0.261, pruned_loss=0.03069, over 1413533.32 frames.], batch size: 38, lr: 2.57e-04
2022-04-30 09:57:17,982 INFO [train.py:763] (3/8) Epoch 29, batch 4500, loss[loss=0.1949, simple_loss=0.2993, pruned_loss=0.04528, over 4836.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03142, over 1399151.63 frames.], batch size: 52, lr: 2.57e-04
2022-04-30 09:58:32,303 INFO [train.py:763] (3/8) Epoch 29, batch 4550, loss[loss=0.181, simple_loss=0.2719, pruned_loss=0.04505, over 5247.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2648, pruned_loss=0.03251, over 1359713.84 frames.], batch size: 52, lr: 2.57e-04
2022-04-30 10:00:01,318 INFO [train.py:763] (3/8) Epoch 30, batch 0, loss[loss=0.1592, simple_loss=0.2623, pruned_loss=0.02804, over 7328.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2623, pruned_loss=0.02804, over 7328.00 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:01:06,992 INFO [train.py:763] (3/8) Epoch 30, batch 50, loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02975, over 7249.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2597, pruned_loss=0.03145, over 317286.77 frames.], batch size: 19, lr: 2.53e-04
2022-04-30 10:02:12,184 INFO [train.py:763] (3/8) Epoch 30, batch 100, loss[loss=0.1765, simple_loss=0.2831, pruned_loss=0.03499, over 7384.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03215, over 561743.99 frames.], batch size: 23, lr: 2.53e-04
2022-04-30 10:03:17,805 INFO [train.py:763] (3/8) Epoch 30, batch 150, loss[loss=0.1692, simple_loss=0.2752, pruned_loss=0.03161, over 7217.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2616, pruned_loss=0.03165, over 756903.69 frames.], batch size: 22, lr: 2.53e-04
2022-04-30 10:04:23,869 INFO [train.py:763] (3/8) Epoch 30, batch 200, loss[loss=0.1958, simple_loss=0.2883, pruned_loss=0.05166, over 5058.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2606, pruned_loss=0.03158, over 902018.28 frames.], batch size: 53, lr: 2.53e-04
2022-04-30 10:05:29,994 INFO [train.py:763] (3/8) Epoch 30, batch 250, loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03197, over 7294.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2624, pruned_loss=0.03211, over 1016303.14 frames.], batch size: 25, lr: 2.53e-04
2022-04-30 10:06:35,954 INFO [train.py:763] (3/8) Epoch 30, batch 300, loss[loss=0.1725, simple_loss=0.275, pruned_loss=0.03499, over 7335.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2626, pruned_loss=0.03242, over 1107841.85 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:07:41,450 INFO [train.py:763] (3/8) Epoch 30, batch 350, loss[loss=0.1488, simple_loss=0.2389, pruned_loss=0.02937, over 7176.00 frames.], tot_loss[loss=0.1629, simple_loss=0.262, pruned_loss=0.03188, over 1175590.59 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:08:46,854 INFO [train.py:763] (3/8) Epoch 30, batch 400, loss[loss=0.1433, simple_loss=0.2529, pruned_loss=0.01687, over 7213.00 frames.], tot_loss[loss=0.163, simple_loss=0.2624, pruned_loss=0.03182, over 1225669.29 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:09:52,320 INFO [train.py:763] (3/8) Epoch 30, batch 450, loss[loss=0.2151, simple_loss=0.3078, pruned_loss=0.06124, over 7186.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2625, pruned_loss=0.03149, over 1266826.21 frames.], batch size: 26, lr: 2.53e-04
2022-04-30 10:10:57,857 INFO [train.py:763] (3/8) Epoch 30, batch 500, loss[loss=0.1398, simple_loss=0.2368, pruned_loss=0.02137, over 7286.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2622, pruned_loss=0.03166, over 1302053.70 frames.], batch size: 17, lr: 2.53e-04
2022-04-30 10:12:03,591 INFO [train.py:763] (3/8) Epoch 30, batch 550, loss[loss=0.17, simple_loss=0.2817, pruned_loss=0.02917, over 7407.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03173, over 1328144.66 frames.], batch size: 21, lr: 2.53e-04
2022-04-30 10:13:09,439 INFO [train.py:763] (3/8) Epoch 30, batch 600, loss[loss=0.1483, simple_loss=0.2392, pruned_loss=0.02875, over 7057.00 frames.], tot_loss[loss=0.1633, simple_loss=0.263, pruned_loss=0.03181, over 1348160.17 frames.], batch size: 18, lr: 2.53e-04
2022-04-30 10:14:15,862 INFO [train.py:763] (3/8) Epoch 30, batch 650, loss[loss=0.1724, simple_loss=0.2859, pruned_loss=0.02943, over 7140.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2628, pruned_loss=0.03155, over 1369636.52 frames.], batch size: 20, lr: 2.53e-04
2022-04-30 10:15:21,893 INFO [train.py:763] (3/8) Epoch 30, batch 700, loss[loss=0.1328, simple_loss=0.2208, pruned_loss=0.02241, over 7183.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2622, pruned_loss=0.0314, over 1379252.37 frames.], batch size: 16, lr: 2.52e-04
2022-04-30 10:16:28,668 INFO [train.py:763] (3/8) Epoch 30, batch 750, loss[loss=0.1595, simple_loss=0.2609, pruned_loss=0.02904, over 7232.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2618, pruned_loss=0.03117, over 1387389.52 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:17:34,225 INFO [train.py:763] (3/8) Epoch 30, batch 800, loss[loss=0.1691, simple_loss=0.2752, pruned_loss=0.0315, over 7340.00 frames.], tot_loss[loss=0.162, simple_loss=0.2621, pruned_loss=0.03097, over 1396496.90 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:18:39,959 INFO [train.py:763] (3/8) Epoch 30, batch 850, loss[loss=0.1591, simple_loss=0.2675, pruned_loss=0.02533, over 7435.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03042, over 1399769.42 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:19:45,739 INFO [train.py:763] (3/8) Epoch 30, batch 900, loss[loss=0.1326, simple_loss=0.2255, pruned_loss=0.0199, over 6808.00 frames.], tot_loss[loss=0.1612, simple_loss=0.261, pruned_loss=0.03068, over 1404351.64 frames.], batch size: 15, lr: 2.52e-04
2022-04-30 10:20:52,496 INFO [train.py:763] (3/8) Epoch 30, batch 950, loss[loss=0.1518, simple_loss=0.2534, pruned_loss=0.02512, over 7124.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03065, over 1405456.03 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:21:58,499 INFO [train.py:763] (3/8) Epoch 30, batch 1000, loss[loss=0.1553, simple_loss=0.2649, pruned_loss=0.02281, over 7342.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03087, over 1408546.36 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:23:03,971 INFO [train.py:763] (3/8) Epoch 30, batch 1050, loss[loss=0.1645, simple_loss=0.2604, pruned_loss=0.03435, over 7119.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03099, over 1410538.09 frames.], batch size: 28, lr: 2.52e-04
2022-04-30 10:24:09,736 INFO [train.py:763] (3/8) Epoch 30, batch 1100, loss[loss=0.1442, simple_loss=0.2379, pruned_loss=0.02523, over 7072.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03067, over 1414756.45 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:25:15,758 INFO [train.py:763] (3/8) Epoch 30, batch 1150, loss[loss=0.1485, simple_loss=0.2537, pruned_loss=0.02159, over 7065.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03073, over 1416979.29 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:26:21,663 INFO [train.py:763] (3/8) Epoch 30, batch 1200, loss[loss=0.1703, simple_loss=0.2704, pruned_loss=0.03503, over 7192.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.03085, over 1419633.27 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:27:27,464 INFO [train.py:763] (3/8) Epoch 30, batch 1250, loss[loss=0.1311, simple_loss=0.2304, pruned_loss=0.01594, over 7410.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03058, over 1418674.25 frames.], batch size: 18, lr: 2.52e-04
2022-04-30 10:28:33,935 INFO [train.py:763] (3/8) Epoch 30, batch 1300, loss[loss=0.1792, simple_loss=0.2799, pruned_loss=0.03924, over 7164.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03076, over 1418775.65 frames.], batch size: 26, lr: 2.52e-04
2022-04-30 10:29:40,214 INFO [train.py:763] (3/8) Epoch 30, batch 1350, loss[loss=0.1545, simple_loss=0.2455, pruned_loss=0.03175, over 7149.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2625, pruned_loss=0.03109, over 1415631.22 frames.], batch size: 17, lr: 2.52e-04
2022-04-30 10:30:45,701 INFO [train.py:763] (3/8) Epoch 30, batch 1400, loss[loss=0.2039, simple_loss=0.3021, pruned_loss=0.05286, over 7339.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2631, pruned_loss=0.03116, over 1419608.78 frames.], batch size: 22, lr: 2.52e-04
2022-04-30 10:31:51,066 INFO [train.py:763] (3/8) Epoch 30, batch 1450, loss[loss=0.1567, simple_loss=0.265, pruned_loss=0.02415, over 7145.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2626, pruned_loss=0.03106, over 1420612.47 frames.], batch size: 20, lr: 2.52e-04
2022-04-30 10:32:56,516 INFO [train.py:763] (3/8) Epoch 30, batch 1500, loss[loss=0.1663, simple_loss=0.2689, pruned_loss=0.03183, over 7325.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2636, pruned_loss=0.03111, over 1426167.17 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:34:02,179 INFO [train.py:763] (3/8) Epoch 30, batch 1550, loss[loss=0.188, simple_loss=0.2904, pruned_loss=0.04284, over 7331.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03129, over 1427422.56 frames.], batch size: 25, lr: 2.52e-04
2022-04-30 10:35:07,677 INFO [train.py:763] (3/8) Epoch 30, batch 1600, loss[loss=0.133, simple_loss=0.2309, pruned_loss=0.01748, over 7251.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2619, pruned_loss=0.03097, over 1428534.36 frames.], batch size: 19, lr: 2.52e-04
2022-04-30 10:36:13,950 INFO [train.py:763] (3/8) Epoch 30, batch 1650, loss[loss=0.1614, simple_loss=0.2662, pruned_loss=0.02837, over 7122.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03099, over 1428765.89 frames.], batch size: 21, lr: 2.52e-04
2022-04-30 10:37:20,415 INFO [train.py:763] (3/8) Epoch 30, batch 1700, loss[loss=0.1768, simple_loss=0.2794, pruned_loss=0.03705, over 7312.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2605, pruned_loss=0.03094, over 1426445.69 frames.], batch size: 24, lr: 2.52e-04
2022-04-30 10:38:27,155 INFO [train.py:763] (3/8) Epoch 30, batch 1750, loss[loss=0.1621, simple_loss=0.2603, pruned_loss=0.03201, over 7375.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.0309, over 1428678.93 frames.], batch size: 23, lr: 2.52e-04
2022-04-30 10:39:33,031 INFO [train.py:763] (3/8) Epoch 30, batch 1800, loss[loss=0.1449, simple_loss=0.2424, pruned_loss=0.02373, over 7424.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2611, pruned_loss=0.03074, over 1425483.26 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:40:38,992 INFO [train.py:763] (3/8) Epoch 30, batch 1850, loss[loss=0.139, simple_loss=0.2381, pruned_loss=0.02, over 7141.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03091, over 1423587.01 frames.], batch size: 17, lr: 2.51e-04
2022-04-30 10:41:45,826 INFO [train.py:763] (3/8) Epoch 30, batch 1900, loss[loss=0.1629, simple_loss=0.261, pruned_loss=0.03241, over 7336.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03101, over 1426453.20 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 10:42:51,809 INFO [train.py:763] (3/8) Epoch 30, batch 1950, loss[loss=0.1855, simple_loss=0.2856, pruned_loss=0.04263, over 7369.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2611, pruned_loss=0.03083, over 1426806.44 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:43:59,475 INFO [train.py:763] (3/8) Epoch 30, batch 2000, loss[loss=0.1615, simple_loss=0.2564, pruned_loss=0.03325, over 7161.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2604, pruned_loss=0.03072, over 1428749.08 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:45:05,770 INFO [train.py:763] (3/8) Epoch 30, batch 2050, loss[loss=0.1887, simple_loss=0.2872, pruned_loss=0.04506, over 7190.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2598, pruned_loss=0.03056, over 1426417.03 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:46:11,292 INFO [train.py:763] (3/8) Epoch 30, batch 2100, loss[loss=0.164, simple_loss=0.2604, pruned_loss=0.03381, over 7148.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2607, pruned_loss=0.0309, over 1424322.37 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:47:17,301 INFO [train.py:763] (3/8) Epoch 30, batch 2150, loss[loss=0.1668, simple_loss=0.2627, pruned_loss=0.03551, over 7158.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2605, pruned_loss=0.03065, over 1427567.03 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:48:22,848 INFO [train.py:763] (3/8) Epoch 30, batch 2200, loss[loss=0.1567, simple_loss=0.2439, pruned_loss=0.03477, over 7064.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2621, pruned_loss=0.03117, over 1429325.70 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:49:28,454 INFO [train.py:763] (3/8) Epoch 30, batch 2250, loss[loss=0.1667, simple_loss=0.2746, pruned_loss=0.02936, over 7208.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2636, pruned_loss=0.03173, over 1428324.43 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:50:34,514 INFO [train.py:763] (3/8) Epoch 30, batch 2300, loss[loss=0.1446, simple_loss=0.245, pruned_loss=0.02217, over 7251.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2638, pruned_loss=0.03171, over 1431095.71 frames.], batch size: 19, lr: 2.51e-04
2022-04-30 10:51:40,502 INFO [train.py:763] (3/8) Epoch 30, batch 2350, loss[loss=0.1536, simple_loss=0.2459, pruned_loss=0.03064, over 7063.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2633, pruned_loss=0.03191, over 1430369.99 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:52:46,203 INFO [train.py:763] (3/8) Epoch 30, batch 2400, loss[loss=0.1699, simple_loss=0.2756, pruned_loss=0.03207, over 7220.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2637, pruned_loss=0.03193, over 1428935.44 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:53:51,753 INFO [train.py:763] (3/8) Epoch 30, batch 2450, loss[loss=0.1558, simple_loss=0.269, pruned_loss=0.02124, over 7225.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2635, pruned_loss=0.03181, over 1425101.17 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:54:57,032 INFO [train.py:763] (3/8) Epoch 30, batch 2500, loss[loss=0.1617, simple_loss=0.2748, pruned_loss=0.02432, over 7340.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2622, pruned_loss=0.03143, over 1427562.95 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 10:56:03,557 INFO [train.py:763] (3/8) Epoch 30, batch 2550, loss[loss=0.1718, simple_loss=0.2662, pruned_loss=0.0387, over 7169.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2619, pruned_loss=0.03138, over 1429170.60 frames.], batch size: 23, lr: 2.51e-04
2022-04-30 10:57:09,406 INFO [train.py:763] (3/8) Epoch 30, batch 2600, loss[loss=0.1485, simple_loss=0.2432, pruned_loss=0.02695, over 7402.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2617, pruned_loss=0.03134, over 1428530.53 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 10:58:15,103 INFO [train.py:763] (3/8) Epoch 30, batch 2650, loss[loss=0.1788, simple_loss=0.2682, pruned_loss=0.04474, over 7400.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2621, pruned_loss=0.03126, over 1425859.72 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 10:59:20,429 INFO [train.py:763] (3/8) Epoch 30, batch 2700, loss[loss=0.1564, simple_loss=0.26, pruned_loss=0.02641, over 7235.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03108, over 1419626.90 frames.], batch size: 25, lr: 2.51e-04
2022-04-30 11:00:26,175 INFO [train.py:763] (3/8) Epoch 30, batch 2750, loss[loss=0.1709, simple_loss=0.2836, pruned_loss=0.02911, over 7145.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03118, over 1420189.84 frames.], batch size: 20, lr: 2.51e-04
2022-04-30 11:01:31,734 INFO [train.py:763] (3/8) Epoch 30, batch 2800, loss[loss=0.1607, simple_loss=0.2425, pruned_loss=0.03939, over 7163.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2617, pruned_loss=0.03105, over 1422166.57 frames.], batch size: 18, lr: 2.51e-04
2022-04-30 11:02:36,836 INFO [train.py:763] (3/8) Epoch 30, batch 2850, loss[loss=0.1812, simple_loss=0.2827, pruned_loss=0.03985, over 7187.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2623, pruned_loss=0.03095, over 1419737.09 frames.], batch size: 22, lr: 2.51e-04
2022-04-30 11:03:42,111 INFO [train.py:763] (3/8) Epoch 30, batch 2900, loss[loss=0.1643, simple_loss=0.2736, pruned_loss=0.02748, over 7119.00 frames.], tot_loss[loss=0.1627, simple_loss=0.263, pruned_loss=0.03121, over 1423546.89 frames.], batch size: 21, lr: 2.51e-04
2022-04-30 11:04:47,458 INFO [train.py:763] (3/8) Epoch 30, batch 2950, loss[loss=0.1527, simple_loss=0.2535, pruned_loss=0.02591, over 7266.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03093, over 1422825.57 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:05:53,065 INFO [train.py:763] (3/8) Epoch 30, batch 3000, loss[loss=0.1501, simple_loss=0.2475, pruned_loss=0.02639, over 7332.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2618, pruned_loss=0.03071, over 1422380.46 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:05:53,065 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 11:06:08,153 INFO [train.py:792] (3/8) Epoch 30, validation: loss=0.1701, simple_loss=0.2661, pruned_loss=0.03704, over 698248.00 frames.
2022-04-30 11:07:13,672 INFO [train.py:763] (3/8) Epoch 30, batch 3050, loss[loss=0.1373, simple_loss=0.2281, pruned_loss=0.02324, over 7001.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2624, pruned_loss=0.03141, over 1422286.71 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:08:19,231 INFO [train.py:763] (3/8) Epoch 30, batch 3100, loss[loss=0.1736, simple_loss=0.2742, pruned_loss=0.03646, over 7313.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2618, pruned_loss=0.03099, over 1425379.89 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:09:24,926 INFO [train.py:763] (3/8) Epoch 30, batch 3150, loss[loss=0.141, simple_loss=0.2397, pruned_loss=0.02118, over 6991.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2612, pruned_loss=0.03089, over 1424248.62 frames.], batch size: 16, lr: 2.50e-04
2022-04-30 11:10:31,193 INFO [train.py:763] (3/8) Epoch 30, batch 3200, loss[loss=0.1569, simple_loss=0.2633, pruned_loss=0.0252, over 7205.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.03059, over 1416361.59 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:11:37,935 INFO [train.py:763] (3/8) Epoch 30, batch 3250, loss[loss=0.1597, simple_loss=0.2674, pruned_loss=0.02603, over 7145.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2614, pruned_loss=0.03077, over 1415935.33 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:12:45,386 INFO [train.py:763] (3/8) Epoch 30, batch 3300, loss[loss=0.1168, simple_loss=0.2064, pruned_loss=0.01361, over 7270.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.031, over 1422257.02 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:13:51,984 INFO [train.py:763] (3/8) Epoch 30, batch 3350, loss[loss=0.1629, simple_loss=0.2724, pruned_loss=0.02676, over 7217.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2606, pruned_loss=0.03087, over 1421451.40 frames.], batch size: 21, lr: 2.50e-04
2022-04-30 11:14:57,140 INFO [train.py:763] (3/8) Epoch 30, batch 3400, loss[loss=0.1645, simple_loss=0.2719, pruned_loss=0.02858, over 7289.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2607, pruned_loss=0.03102, over 1420942.10 frames.], batch size: 25, lr: 2.50e-04
2022-04-30 11:16:02,380 INFO [train.py:763] (3/8) Epoch 30, batch 3450, loss[loss=0.145, simple_loss=0.2509, pruned_loss=0.01953, over 6255.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03059, over 1424996.64 frames.], batch size: 37, lr: 2.50e-04
2022-04-30 11:17:08,605 INFO [train.py:763] (3/8) Epoch 30, batch 3500, loss[loss=0.1951, simple_loss=0.2844, pruned_loss=0.0529, over 7380.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2601, pruned_loss=0.03051, over 1427191.45 frames.], batch size: 23, lr: 2.50e-04
2022-04-30 11:18:14,699 INFO [train.py:763] (3/8) Epoch 30, batch 3550, loss[loss=0.1485, simple_loss=0.2532, pruned_loss=0.02188, over 7432.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2609, pruned_loss=0.03088, over 1428377.46 frames.], batch size: 20, lr: 2.50e-04
2022-04-30 11:19:20,436 INFO [train.py:763] (3/8) Epoch 30, batch 3600, loss[loss=0.1597, simple_loss=0.2645, pruned_loss=0.02748, over 7278.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2622, pruned_loss=0.03124, over 1422909.19 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:20:25,886 INFO [train.py:763] (3/8) Epoch 30, batch 3650, loss[loss=0.1415, simple_loss=0.2384, pruned_loss=0.02234, over 7135.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03063, over 1421839.72 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:21:32,099 INFO [train.py:763] (3/8) Epoch 30, batch 3700, loss[loss=0.1559, simple_loss=0.2535, pruned_loss=0.02918, over 7302.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.0309, over 1425497.01 frames.], batch size: 17, lr: 2.50e-04
2022-04-30 11:22:38,023 INFO [train.py:763] (3/8) Epoch 30, batch 3750, loss[loss=0.1591, simple_loss=0.2583, pruned_loss=0.02992, over 7255.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03097, over 1423470.91 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:23:45,244 INFO [train.py:763] (3/8) Epoch 30, batch 3800, loss[loss=0.1399, simple_loss=0.2319, pruned_loss=0.02394, over 7286.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03066, over 1425985.14 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:24:50,558 INFO [train.py:763] (3/8) Epoch 30, batch 3850, loss[loss=0.1459, simple_loss=0.2414, pruned_loss=0.02522, over 7064.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2625, pruned_loss=0.03135, over 1425126.76 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:25:56,095 INFO [train.py:763] (3/8) Epoch 30, batch 3900, loss[loss=0.1638, simple_loss=0.2753, pruned_loss=0.02613, over 7280.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2623, pruned_loss=0.03146, over 1428309.79 frames.], batch size: 24, lr: 2.50e-04
2022-04-30 11:27:01,585 INFO [train.py:763] (3/8) Epoch 30, batch 3950, loss[loss=0.1482, simple_loss=0.2549, pruned_loss=0.02073, over 7343.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2619, pruned_loss=0.03146, over 1428616.24 frames.], batch size: 19, lr: 2.50e-04
2022-04-30 11:28:06,971 INFO [train.py:763] (3/8) Epoch 30, batch 4000, loss[loss=0.1551, simple_loss=0.2553, pruned_loss=0.02748, over 7167.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2626, pruned_loss=0.03161, over 1426301.96 frames.], batch size: 18, lr: 2.50e-04
2022-04-30 11:29:11,957 INFO [train.py:763] (3/8) Epoch 30, batch 4050, loss[loss=0.1904, simple_loss=0.291, pruned_loss=0.04488, over 7280.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2629, pruned_loss=0.03165, over 1425521.07 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:30:18,166 INFO [train.py:763] (3/8) Epoch 30, batch 4100, loss[loss=0.1458, simple_loss=0.2489, pruned_loss=0.02133, over 7160.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2631, pruned_loss=0.03159, over 1427747.73 frames.], batch size: 19, lr: 2.49e-04
2022-04-30 11:31:24,158 INFO [train.py:763] (3/8) Epoch 30, batch 4150, loss[loss=0.1735, simple_loss=0.2769, pruned_loss=0.03498, over 7113.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03106, over 1430205.48 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:32:29,729 INFO [train.py:763] (3/8) Epoch 30, batch 4200, loss[loss=0.1506, simple_loss=0.2396, pruned_loss=0.03085, over 6810.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03086, over 1431141.41 frames.], batch size: 15, lr: 2.49e-04
2022-04-30 11:33:35,005 INFO [train.py:763] (3/8) Epoch 30, batch 4250, loss[loss=0.1757, simple_loss=0.2784, pruned_loss=0.03646, over 7154.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2616, pruned_loss=0.03082, over 1427628.07 frames.], batch size: 26, lr: 2.49e-04
2022-04-30 11:34:41,234 INFO [train.py:763] (3/8) Epoch 30, batch 4300, loss[loss=0.1703, simple_loss=0.2653, pruned_loss=0.03765, over 7303.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2614, pruned_loss=0.03089, over 1431155.24 frames.], batch size: 24, lr: 2.49e-04
2022-04-30 11:35:46,140 INFO [train.py:763] (3/8) Epoch 30, batch 4350, loss[loss=0.1587, simple_loss=0.2671, pruned_loss=0.02518, over 7109.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2617, pruned_loss=0.03088, over 1422053.87 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:36:51,029 INFO [train.py:763] (3/8) Epoch 30, batch 4400, loss[loss=0.1722, simple_loss=0.2635, pruned_loss=0.04046, over 7111.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2621, pruned_loss=0.03106, over 1412296.46 frames.], batch size: 21, lr: 2.49e-04
2022-04-30 11:37:56,306 INFO [train.py:763] (3/8) Epoch 30, batch 4450, loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02998, over 6402.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.0311, over 1411769.77 frames.], batch size: 38, lr: 2.49e-04
2022-04-30 11:39:02,208 INFO [train.py:763] (3/8) Epoch 30, batch 4500, loss[loss=0.1674, simple_loss=0.2657, pruned_loss=0.03456, over 6563.00 frames.], tot_loss[loss=0.1632, simple_loss=0.263, pruned_loss=0.03172, over 1385931.15 frames.], batch size: 38, lr: 2.49e-04
2022-04-30 11:40:07,227 INFO [train.py:763] (3/8) Epoch 30, batch 4550, loss[loss=0.1901, simple_loss=0.299, pruned_loss=0.04061, over 4918.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2642, pruned_loss=0.03238, over 1355358.28 frames.], batch size: 52, lr: 2.49e-04
2022-04-30 11:41:35,691 INFO [train.py:763] (3/8) Epoch 31, batch 0, loss[loss=0.1694, simple_loss=0.2666, pruned_loss=0.03613, over 5085.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2666, pruned_loss=0.03613, over 5085.00 frames.], batch size: 52, lr: 2.45e-04
2022-04-30 11:42:41,157 INFO [train.py:763] (3/8) Epoch 31, batch 50, loss[loss=0.1685, simple_loss=0.2711, pruned_loss=0.03294, over 6428.00 frames.], tot_loss[loss=0.1664, simple_loss=0.267, pruned_loss=0.03286, over 319323.88 frames.], batch size: 38, lr: 2.45e-04
2022-04-30 11:43:46,469 INFO [train.py:763] (3/8) Epoch 31, batch 100, loss[loss=0.1828, simple_loss=0.2871, pruned_loss=0.03929, over 7288.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2651, pruned_loss=0.0322, over 566393.36 frames.], batch size: 25, lr: 2.45e-04
2022-04-30 11:44:52,570 INFO [train.py:763] (3/8) Epoch 31, batch 150, loss[loss=0.1761, simple_loss=0.2894, pruned_loss=0.03136, over 7154.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2634, pruned_loss=0.03121, over 758174.47 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:45:58,814 INFO [train.py:763] (3/8) Epoch 31, batch 200, loss[loss=0.113, simple_loss=0.2065, pruned_loss=0.009729, over 7011.00 frames.], tot_loss[loss=0.1617, simple_loss=0.262, pruned_loss=0.03071, over 902865.58 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:47:04,081 INFO [train.py:763] (3/8) Epoch 31, batch 250, loss[loss=0.1668, simple_loss=0.2636, pruned_loss=0.035, over 7285.00 frames.], tot_loss[loss=0.1621, simple_loss=0.262, pruned_loss=0.0311, over 1022567.77 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:48:09,433 INFO [train.py:763] (3/8) Epoch 31, batch 300, loss[loss=0.1846, simple_loss=0.2792, pruned_loss=0.04495, over 7305.00 frames.], tot_loss[loss=0.162, simple_loss=0.2622, pruned_loss=0.03086, over 1113333.35 frames.], batch size: 24, lr: 2.45e-04
2022-04-30 11:49:14,695 INFO [train.py:763] (3/8) Epoch 31, batch 350, loss[loss=0.1692, simple_loss=0.2713, pruned_loss=0.0335, over 7111.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2616, pruned_loss=0.03046, over 1181025.33 frames.], batch size: 28, lr: 2.45e-04
2022-04-30 11:50:20,235 INFO [train.py:763] (3/8) Epoch 31, batch 400, loss[loss=0.181, simple_loss=0.2755, pruned_loss=0.04326, over 7170.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2619, pruned_loss=0.03076, over 1236141.77 frames.], batch size: 26, lr: 2.45e-04
2022-04-30 11:51:25,626 INFO [train.py:763] (3/8) Epoch 31, batch 450, loss[loss=0.1465, simple_loss=0.2522, pruned_loss=0.02041, over 7323.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03048, over 1276432.13 frames.], batch size: 21, lr: 2.45e-04
2022-04-30 11:52:41,061 INFO [train.py:763] (3/8) Epoch 31, batch 500, loss[loss=0.1596, simple_loss=0.2684, pruned_loss=0.02542, over 7330.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03019, over 1312758.48 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:53:47,761 INFO [train.py:763] (3/8) Epoch 31, batch 550, loss[loss=0.1628, simple_loss=0.2608, pruned_loss=0.03238, over 7335.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03025, over 1340992.30 frames.], batch size: 22, lr: 2.45e-04
2022-04-30 11:54:53,976 INFO [train.py:763] (3/8) Epoch 31, batch 600, loss[loss=0.1463, simple_loss=0.2335, pruned_loss=0.02955, over 7134.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03028, over 1363936.42 frames.], batch size: 17, lr: 2.45e-04
2022-04-30 11:55:59,914 INFO [train.py:763] (3/8) Epoch 31, batch 650, loss[loss=0.1487, simple_loss=0.2384, pruned_loss=0.02949, over 6997.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2602, pruned_loss=0.03066, over 1379345.87 frames.], batch size: 16, lr: 2.45e-04
2022-04-30 11:57:06,461 INFO [train.py:763] (3/8) Epoch 31, batch 700, loss[loss=0.176, simple_loss=0.2737, pruned_loss=0.0392, over 7208.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2606, pruned_loss=0.03084, over 1387659.79 frames.], batch size: 23, lr: 2.45e-04
2022-04-30 11:58:13,269 INFO [train.py:763] (3/8) Epoch 31, batch 750, loss[loss=0.1607, simple_loss=0.2613, pruned_loss=0.03005, over 7114.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03075, over 1395391.87 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 11:59:18,735 INFO [train.py:763] (3/8) Epoch 31, batch 800, loss[loss=0.1414, simple_loss=0.2383, pruned_loss=0.02224, over 7270.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2607, pruned_loss=0.03062, over 1400094.42 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:00:24,035 INFO [train.py:763] (3/8) Epoch 31, batch 850, loss[loss=0.1942, simple_loss=0.2949, pruned_loss=0.04681, over 7290.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2615, pruned_loss=0.0309, over 1407604.67 frames.], batch size: 25, lr: 2.44e-04
2022-04-30 12:01:28,729 INFO [train.py:763] (3/8) Epoch 31, batch 900, loss[loss=0.146, simple_loss=0.2526, pruned_loss=0.01971, over 7338.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2621, pruned_loss=0.03044, over 1410010.21 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:02:34,057 INFO [train.py:763] (3/8) Epoch 31, batch 950, loss[loss=0.1411, simple_loss=0.2346, pruned_loss=0.02379, over 6831.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2609, pruned_loss=0.03041, over 1412214.49 frames.], batch size: 15, lr: 2.44e-04
2022-04-30 12:03:39,303 INFO [train.py:763] (3/8) Epoch 31, batch 1000, loss[loss=0.1467, simple_loss=0.2508, pruned_loss=0.02135, over 7430.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03061, over 1415717.33 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:04:53,738 INFO [train.py:763] (3/8) Epoch 31, batch 1050, loss[loss=0.1836, simple_loss=0.2912, pruned_loss=0.03799, over 7236.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2603, pruned_loss=0.03061, over 1419760.01 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:05:59,155 INFO [train.py:763] (3/8) Epoch 31, batch 1100, loss[loss=0.1754, simple_loss=0.272, pruned_loss=0.03939, over 7202.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03033, over 1418541.86 frames.], batch size: 22, lr: 2.44e-04
2022-04-30 12:07:23,561 INFO [train.py:763] (3/8) Epoch 31, batch 1150, loss[loss=0.1451, simple_loss=0.2402, pruned_loss=0.02501, over 7133.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03033, over 1421920.69 frames.], batch size: 17, lr: 2.44e-04
2022-04-30 12:08:30,098 INFO [train.py:763] (3/8) Epoch 31, batch 1200, loss[loss=0.1601, simple_loss=0.2685, pruned_loss=0.02588, over 7407.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2595, pruned_loss=0.03032, over 1423640.22 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:09:54,553 INFO [train.py:763] (3/8) Epoch 31, batch 1250, loss[loss=0.1624, simple_loss=0.2676, pruned_loss=0.02863, over 7213.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2603, pruned_loss=0.03061, over 1417464.82 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:11:00,226 INFO [train.py:763] (3/8) Epoch 31, batch 1300, loss[loss=0.1708, simple_loss=0.2788, pruned_loss=0.03145, over 7141.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2611, pruned_loss=0.03059, over 1422961.96 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:12:14,866 INFO [train.py:763] (3/8) Epoch 31, batch 1350, loss[loss=0.1711, simple_loss=0.2611, pruned_loss=0.04051, over 7333.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03062, over 1421559.22 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:13:22,476 INFO [train.py:763] (3/8) Epoch 31, batch 1400, loss[loss=0.155, simple_loss=0.2489, pruned_loss=0.03058, over 7248.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03034, over 1422054.87 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:14:38,780 INFO [train.py:763] (3/8) Epoch 31, batch 1450, loss[loss=0.16, simple_loss=0.25, pruned_loss=0.03502, over 7335.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03034, over 1423840.23 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:15:46,110 INFO [train.py:763] (3/8) Epoch 31, batch 1500, loss[loss=0.1976, simple_loss=0.2866, pruned_loss=0.05432, over 4964.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2605, pruned_loss=0.03046, over 1422527.37 frames.], batch size: 52, lr: 2.44e-04
2022-04-30 12:16:51,627 INFO [train.py:763] (3/8) Epoch 31, batch 1550, loss[loss=0.1446, simple_loss=0.2371, pruned_loss=0.026, over 7397.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2603, pruned_loss=0.03032, over 1421741.51 frames.], batch size: 18, lr: 2.44e-04
2022-04-30 12:17:56,937 INFO [train.py:763] (3/8) Epoch 31, batch 1600, loss[loss=0.1867, simple_loss=0.279, pruned_loss=0.04719, over 7207.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03057, over 1417571.25 frames.], batch size: 23, lr: 2.44e-04
2022-04-30 12:19:02,303 INFO [train.py:763] (3/8) Epoch 31, batch 1650, loss[loss=0.1817, simple_loss=0.2836, pruned_loss=0.03994, over 7413.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2612, pruned_loss=0.03079, over 1416974.32 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:20:07,949 INFO [train.py:763] (3/8) Epoch 31, batch 1700, loss[loss=0.1714, simple_loss=0.2703, pruned_loss=0.03621, over 7126.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2603, pruned_loss=0.03048, over 1412668.80 frames.], batch size: 21, lr: 2.44e-04
2022-04-30 12:21:14,750 INFO [train.py:763] (3/8) Epoch 31, batch 1750, loss[loss=0.2048, simple_loss=0.2969, pruned_loss=0.05629, over 5093.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.03047, over 1410449.60 frames.], batch size: 52, lr: 2.44e-04
2022-04-30 12:22:33,259 INFO [train.py:763] (3/8) Epoch 31, batch 1800, loss[loss=0.1528, simple_loss=0.2469, pruned_loss=0.0293, over 7234.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2622, pruned_loss=0.03074, over 1411986.72 frames.], batch size: 20, lr: 2.44e-04
2022-04-30 12:23:40,150 INFO [train.py:763] (3/8) Epoch 31, batch 1850, loss[loss=0.1381, simple_loss=0.2249, pruned_loss=0.02565, over 6990.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03102, over 1405802.28 frames.], batch size: 16, lr: 2.44e-04
2022-04-30 12:24:46,002 INFO [train.py:763] (3/8) Epoch 31, batch 1900, loss[loss=0.151, simple_loss=0.2478, pruned_loss=0.02714, over 7360.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2613, pruned_loss=0.03084, over 1412510.09 frames.], batch size: 19, lr: 2.44e-04
2022-04-30 12:25:51,348 INFO [train.py:763] (3/8) Epoch 31, batch 1950, loss[loss=0.1483, simple_loss=0.2472, pruned_loss=0.02473, over 7360.00 frames.], tot_loss[loss=0.161, simple_loss=0.2607, pruned_loss=0.03069, over 1418294.72 frames.], batch size: 19, lr: 2.43e-04
2022-04-30 12:26:56,756 INFO [train.py:763] (3/8) Epoch 31, batch 2000, loss[loss=0.1514, simple_loss=0.2487, pruned_loss=0.027, over 7281.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2607, pruned_loss=0.03071, over 1420207.03 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:28:01,918 INFO [train.py:763] (3/8) Epoch 31, batch 2050, loss[loss=0.1731, simple_loss=0.2676, pruned_loss=0.03925, over 7155.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2612, pruned_loss=0.03105, over 1416722.88 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:29:07,872 INFO [train.py:763] (3/8) Epoch 31, batch 2100, loss[loss=0.1534, simple_loss=0.2446, pruned_loss=0.03108, over 7264.00 frames.], tot_loss[loss=0.162, simple_loss=0.2619, pruned_loss=0.03105, over 1417055.60 frames.], batch size: 16, lr: 2.43e-04
2022-04-30 12:30:13,151 INFO [train.py:763] (3/8) Epoch 31, batch 2150, loss[loss=0.1678, simple_loss=0.2726, pruned_loss=0.03156, over 7225.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2627, pruned_loss=0.03139, over 1420727.91 frames.], batch size: 21, lr: 2.43e-04
2022-04-30 12:31:18,646 INFO [train.py:763] (3/8) Epoch 31, batch 2200, loss[loss=0.171, simple_loss=0.2776, pruned_loss=0.03214, over 7184.00 frames.], tot_loss[loss=0.1612, simple_loss=0.261, pruned_loss=0.03071, over 1423234.92 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:32:23,989 INFO [train.py:763] (3/8) Epoch 31, batch 2250, loss[loss=0.1446, simple_loss=0.2466, pruned_loss=0.02133, over 7056.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03073, over 1424934.81 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:33:30,742 INFO [train.py:763] (3/8) Epoch 31, batch 2300, loss[loss=0.1745, simple_loss=0.2743, pruned_loss=0.03739, over 7338.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03124, over 1421178.14 frames.], batch size: 22, lr: 2.43e-04
2022-04-30 12:34:36,634 INFO [train.py:763] (3/8) Epoch 31, batch 2350, loss[loss=0.1527, simple_loss=0.2432, pruned_loss=0.03107, over 7279.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03128, over 1425004.79 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:35:41,755 INFO [train.py:763] (3/8) Epoch 31, batch 2400, loss[loss=0.1595, simple_loss=0.2578, pruned_loss=0.03063, over 7328.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2625, pruned_loss=0.03122, over 1420601.12 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:36:47,280 INFO [train.py:763] (3/8) Epoch 31, batch 2450, loss[loss=0.1894, simple_loss=0.2918, pruned_loss=0.04348, over 7145.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03109, over 1422338.74 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:37:52,779 INFO [train.py:763] (3/8) Epoch 31, batch 2500, loss[loss=0.1345, simple_loss=0.229, pruned_loss=0.02003, over 7279.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03067, over 1424620.02 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:38:58,016 INFO [train.py:763] (3/8) Epoch 31, batch 2550, loss[loss=0.1606, simple_loss=0.2653, pruned_loss=0.0279, over 7327.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03101, over 1423259.31 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:40:03,278 INFO [train.py:763] (3/8) Epoch 31, batch 2600, loss[loss=0.1367, simple_loss=0.2373, pruned_loss=0.01803, over 7139.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2606, pruned_loss=0.03059, over 1421347.40 frames.], batch size: 17, lr: 2.43e-04
2022-04-30 12:41:08,491 INFO [train.py:763] (3/8) Epoch 31, batch 2650, loss[loss=0.1751, simple_loss=0.2838, pruned_loss=0.0332, over 7162.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.0304, over 1423809.43 frames.], batch size: 26, lr: 2.43e-04
2022-04-30 12:42:15,310 INFO [train.py:763] (3/8) Epoch 31, batch 2700, loss[loss=0.1443, simple_loss=0.2444, pruned_loss=0.02203, over 7321.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03013, over 1422553.36 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:43:20,588 INFO [train.py:763] (3/8) Epoch 31, batch 2750, loss[loss=0.1522, simple_loss=0.2555, pruned_loss=0.02445, over 7118.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2601, pruned_loss=0.02977, over 1424588.89 frames.], batch size: 28, lr: 2.43e-04
2022-04-30 12:44:27,120 INFO [train.py:763] (3/8) Epoch 31, batch 2800, loss[loss=0.1402, simple_loss=0.2309, pruned_loss=0.02471, over 7418.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02998, over 1424338.10 frames.], batch size: 18, lr: 2.43e-04
2022-04-30 12:45:34,094 INFO [train.py:763] (3/8) Epoch 31, batch 2850, loss[loss=0.1677, simple_loss=0.2743, pruned_loss=0.0305, over 6486.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02971, over 1421318.64 frames.], batch size: 38, lr: 2.43e-04
2022-04-30 12:46:39,725 INFO [train.py:763] (3/8) Epoch 31, batch 2900, loss[loss=0.1566, simple_loss=0.2691, pruned_loss=0.02208, over 7226.00 frames.], tot_loss[loss=0.16, simple_loss=0.2604, pruned_loss=0.02982, over 1425353.90 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:47:44,745 INFO [train.py:763] (3/8) Epoch 31, batch 2950, loss[loss=0.1686, simple_loss=0.2682, pruned_loss=0.03448, over 7205.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2601, pruned_loss=0.02985, over 1418143.66 frames.], batch size: 23, lr: 2.43e-04
2022-04-30 12:48:50,665 INFO [train.py:763] (3/8) Epoch 31, batch 3000, loss[loss=0.1366, simple_loss=0.2383, pruned_loss=0.01746, over 7414.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.02994, over 1419465.25 frames.], batch size: 20, lr: 2.43e-04
2022-04-30 12:48:50,666 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 12:49:05,876 INFO [train.py:792] (3/8) Epoch 31, validation: loss=0.1686, simple_loss=0.2652, pruned_loss=0.03603, over 698248.00 frames.
2022-04-30 12:50:12,208 INFO [train.py:763] (3/8) Epoch 31, batch 3050, loss[loss=0.1751, simple_loss=0.2818, pruned_loss=0.03418, over 7293.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.03012, over 1423013.05 frames.], batch size: 25, lr: 2.43e-04
2022-04-30 12:51:18,204 INFO [train.py:763] (3/8) Epoch 31, batch 3100, loss[loss=0.1863, simple_loss=0.2963, pruned_loss=0.03817, over 7102.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03045, over 1426500.63 frames.], batch size: 28, lr: 2.42e-04
2022-04-30 12:52:23,638 INFO [train.py:763] (3/8) Epoch 31, batch 3150, loss[loss=0.1546, simple_loss=0.2389, pruned_loss=0.03512, over 7294.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.03049, over 1423957.18 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 12:53:29,084 INFO [train.py:763] (3/8) Epoch 31, batch 3200, loss[loss=0.1735, simple_loss=0.2855, pruned_loss=0.03079, over 7120.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2616, pruned_loss=0.03038, over 1426136.13 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:54:36,152 INFO [train.py:763] (3/8) Epoch 31, batch 3250, loss[loss=0.1528, simple_loss=0.2574, pruned_loss=0.02412, over 7331.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2616, pruned_loss=0.03037, over 1428125.74 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 12:55:42,935 INFO [train.py:763] (3/8) Epoch 31, batch 3300, loss[loss=0.1728, simple_loss=0.2683, pruned_loss=0.03864, over 7435.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.03002, over 1424326.70 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:56:50,142 INFO [train.py:763] (3/8) Epoch 31, batch 3350, loss[loss=0.1585, simple_loss=0.2689, pruned_loss=0.02405, over 7313.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02977, over 1425846.39 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 12:57:56,831 INFO [train.py:763] (3/8) Epoch 31, batch 3400, loss[loss=0.1449, simple_loss=0.2379, pruned_loss=0.02596, over 7333.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.0304, over 1422670.94 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 12:59:03,244 INFO [train.py:763] (3/8) Epoch 31, batch 3450, loss[loss=0.1879, simple_loss=0.2967, pruned_loss=0.03951, over 7219.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2621, pruned_loss=0.03082, over 1425913.93 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:00:08,922 INFO [train.py:763] (3/8) Epoch 31, batch 3500, loss[loss=0.1955, simple_loss=0.2995, pruned_loss=0.04574, over 7302.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2619, pruned_loss=0.03063, over 1428708.07 frames.], batch size: 24, lr: 2.42e-04
2022-04-30 13:01:14,841 INFO [train.py:763] (3/8) Epoch 31, batch 3550, loss[loss=0.1803, simple_loss=0.2687, pruned_loss=0.04594, over 7367.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03073, over 1431882.00 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:02:21,336 INFO [train.py:763] (3/8) Epoch 31, batch 3600, loss[loss=0.1713, simple_loss=0.2721, pruned_loss=0.03525, over 6290.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2609, pruned_loss=0.03088, over 1428321.63 frames.], batch size: 37, lr: 2.42e-04
2022-04-30 13:03:26,536 INFO [train.py:763] (3/8) Epoch 31, batch 3650, loss[loss=0.1628, simple_loss=0.2606, pruned_loss=0.03252, over 7243.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2613, pruned_loss=0.03048, over 1427994.51 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:04:32,082 INFO [train.py:763] (3/8) Epoch 31, batch 3700, loss[loss=0.1502, simple_loss=0.2432, pruned_loss=0.02854, over 7133.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.03052, over 1430043.73 frames.], batch size: 17, lr: 2.42e-04
2022-04-30 13:05:36,814 INFO [train.py:763] (3/8) Epoch 31, batch 3750, loss[loss=0.1716, simple_loss=0.2706, pruned_loss=0.03633, over 7193.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2607, pruned_loss=0.03037, over 1424616.25 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:06:42,585 INFO [train.py:763] (3/8) Epoch 31, batch 3800, loss[loss=0.1675, simple_loss=0.2661, pruned_loss=0.03445, over 7370.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03041, over 1425948.24 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:07:47,976 INFO [train.py:763] (3/8) Epoch 31, batch 3850, loss[loss=0.1606, simple_loss=0.2642, pruned_loss=0.02849, over 7437.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.0301, over 1428616.04 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:08:53,257 INFO [train.py:763] (3/8) Epoch 31, batch 3900, loss[loss=0.1342, simple_loss=0.2343, pruned_loss=0.01705, over 7162.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.0297, over 1429610.71 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:09:58,648 INFO [train.py:763] (3/8) Epoch 31, batch 3950, loss[loss=0.157, simple_loss=0.2733, pruned_loss=0.02031, over 7214.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.02998, over 1425958.03 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:11:04,247 INFO [train.py:763] (3/8) Epoch 31, batch 4000, loss[loss=0.1414, simple_loss=0.2344, pruned_loss=0.02417, over 7408.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02966, over 1421624.30 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:12:09,631 INFO [train.py:763] (3/8) Epoch 31, batch 4050, loss[loss=0.1951, simple_loss=0.3006, pruned_loss=0.04477, over 7368.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.02989, over 1419293.73 frames.], batch size: 23, lr: 2.42e-04
2022-04-30 13:13:15,759 INFO [train.py:763] (3/8) Epoch 31, batch 4100, loss[loss=0.1685, simple_loss=0.2735, pruned_loss=0.03175, over 7193.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2608, pruned_loss=0.03002, over 1417525.48 frames.], batch size: 22, lr: 2.42e-04
2022-04-30 13:14:21,773 INFO [train.py:763] (3/8) Epoch 31, batch 4150, loss[loss=0.1435, simple_loss=0.2447, pruned_loss=0.02114, over 7224.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2607, pruned_loss=0.03003, over 1420903.53 frames.], batch size: 21, lr: 2.42e-04
2022-04-30 13:15:28,686 INFO [train.py:763] (3/8) Epoch 31, batch 4200, loss[loss=0.1461, simple_loss=0.2488, pruned_loss=0.02175, over 7323.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02975, over 1419934.69 frames.], batch size: 20, lr: 2.42e-04
2022-04-30 13:16:35,572 INFO [train.py:763] (3/8) Epoch 31, batch 4250, loss[loss=0.1389, simple_loss=0.2264, pruned_loss=0.02566, over 7255.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02987, over 1418869.29 frames.], batch size: 19, lr: 2.42e-04
2022-04-30 13:17:40,851 INFO [train.py:763] (3/8) Epoch 31, batch 4300, loss[loss=0.1535, simple_loss=0.2377, pruned_loss=0.03464, over 7411.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2595, pruned_loss=0.02994, over 1418369.97 frames.], batch size: 18, lr: 2.42e-04
2022-04-30 13:18:46,141 INFO [train.py:763] (3/8) Epoch 31, batch 4350, loss[loss=0.1571, simple_loss=0.2563, pruned_loss=0.02893, over 7166.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2604, pruned_loss=0.03065, over 1418296.14 frames.], batch size: 18, lr: 2.41e-04
2022-04-30 13:19:51,341 INFO [train.py:763] (3/8) Epoch 31, batch 4400, loss[loss=0.1607, simple_loss=0.2631, pruned_loss=0.02911, over 7354.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2607, pruned_loss=0.03093, over 1405054.96 frames.], batch size: 25, lr: 2.41e-04
2022-04-30 13:20:56,965 INFO [train.py:763] (3/8) Epoch 31, batch 4450, loss[loss=0.1474, simple_loss=0.233, pruned_loss=0.03094, over 7239.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2617, pruned_loss=0.03122, over 1402864.20 frames.], batch size: 16, lr: 2.41e-04
2022-04-30 13:22:02,214 INFO [train.py:763] (3/8) Epoch 31, batch 4500, loss[loss=0.1618, simple_loss=0.2704, pruned_loss=0.02664, over 6917.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2618, pruned_loss=0.03129, over 1395687.03 frames.], batch size: 31, lr: 2.41e-04
2022-04-30 13:23:07,076 INFO [train.py:763] (3/8) Epoch 31, batch 4550, loss[loss=0.1769, simple_loss=0.2738, pruned_loss=0.03997, over 5276.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2615, pruned_loss=0.03167, over 1357340.76 frames.], batch size: 52, lr: 2.41e-04
2022-04-30 13:24:35,148 INFO [train.py:763] (3/8) Epoch 32, batch 0, loss[loss=0.1736, simple_loss=0.2625, pruned_loss=0.04234, over 6808.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2625, pruned_loss=0.04234, over 6808.00 frames.], batch size: 31, lr: 2.38e-04
2022-04-30 13:25:38,923 INFO [train.py:763] (3/8) Epoch 32, batch 50, loss[loss=0.1644, simple_loss=0.2604, pruned_loss=0.03415, over 5272.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2642, pruned_loss=0.03103, over 314604.74 frames.], batch size: 52, lr: 2.38e-04
2022-04-30 13:26:41,319 INFO [train.py:763] (3/8) Epoch 32, batch 100, loss[loss=0.143, simple_loss=0.2389, pruned_loss=0.02354, over 6242.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2629, pruned_loss=0.0306, over 559147.43 frames.], batch size: 37, lr: 2.38e-04
2022-04-30 13:27:47,090 INFO [train.py:763] (3/8) Epoch 32, batch 150, loss[loss=0.1853, simple_loss=0.2909, pruned_loss=0.03984, over 7219.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2638, pruned_loss=0.03027, over 751233.82 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:28:52,458 INFO [train.py:763] (3/8) Epoch 32, batch 200, loss[loss=0.1527, simple_loss=0.2322, pruned_loss=0.03657, over 7002.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2622, pruned_loss=0.03055, over 893860.67 frames.], batch size: 16, lr: 2.37e-04
2022-04-30 13:29:57,592 INFO [train.py:763] (3/8) Epoch 32, batch 250, loss[loss=0.1589, simple_loss=0.2746, pruned_loss=0.0216, over 7232.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2622, pruned_loss=0.03025, over 1008740.05 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:31:03,086 INFO [train.py:763] (3/8) Epoch 32, batch 300, loss[loss=0.1613, simple_loss=0.2674, pruned_loss=0.02764, over 6929.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2633, pruned_loss=0.03104, over 1091911.52 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:32:10,106 INFO [train.py:763] (3/8) Epoch 32, batch 350, loss[loss=0.1381, simple_loss=0.23, pruned_loss=0.02312, over 7398.00 frames.], tot_loss[loss=0.1626, simple_loss=0.263, pruned_loss=0.03107, over 1162832.65 frames.], batch size: 18, lr: 2.37e-04
2022-04-30 13:33:15,981 INFO [train.py:763] (3/8) Epoch 32, batch 400, loss[loss=0.1453, simple_loss=0.2492, pruned_loss=0.02073, over 7423.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2615, pruned_loss=0.03077, over 1220170.06 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:34:21,563 INFO [train.py:763] (3/8) Epoch 32, batch 450, loss[loss=0.153, simple_loss=0.2624, pruned_loss=0.02178, over 6804.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2612, pruned_loss=0.03066, over 1262714.79 frames.], batch size: 31, lr: 2.37e-04
2022-04-30 13:35:26,873 INFO [train.py:763] (3/8) Epoch 32, batch 500, loss[loss=0.1565, simple_loss=0.2577, pruned_loss=0.02771, over 7189.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2612, pruned_loss=0.03097, over 1300763.65 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:36:32,825 INFO [train.py:763] (3/8) Epoch 32, batch 550, loss[loss=0.1745, simple_loss=0.265, pruned_loss=0.04197, over 7317.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2627, pruned_loss=0.03116, over 1329641.82 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:37:38,142 INFO [train.py:763] (3/8) Epoch 32, batch 600, loss[loss=0.1568, simple_loss=0.2638, pruned_loss=0.02494, over 7298.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2631, pruned_loss=0.03133, over 1347892.17 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:38:43,401 INFO [train.py:763] (3/8) Epoch 32, batch 650, loss[loss=0.1771, simple_loss=0.2728, pruned_loss=0.04066, over 7167.00 frames.], tot_loss[loss=0.163, simple_loss=0.2635, pruned_loss=0.03128, over 1364675.19 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:39:48,620 INFO [train.py:763] (3/8) Epoch 32, batch 700, loss[loss=0.1371, simple_loss=0.2275, pruned_loss=0.02336, over 7121.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2631, pruned_loss=0.03115, over 1375088.65 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:40:55,073 INFO [train.py:763] (3/8) Epoch 32, batch 750, loss[loss=0.1604, simple_loss=0.2639, pruned_loss=0.02842, over 7206.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2626, pruned_loss=0.03103, over 1380671.88 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:42:02,249 INFO [train.py:763] (3/8) Epoch 32, batch 800, loss[loss=0.1489, simple_loss=0.2413, pruned_loss=0.02829, over 7424.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2617, pruned_loss=0.03149, over 1392656.65 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:43:08,537 INFO [train.py:763] (3/8) Epoch 32, batch 850, loss[loss=0.1863, simple_loss=0.2806, pruned_loss=0.04604, over 7366.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2613, pruned_loss=0.031, over 1399711.19 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:44:14,308 INFO [train.py:763] (3/8) Epoch 32, batch 900, loss[loss=0.1664, simple_loss=0.2588, pruned_loss=0.03702, over 7170.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2603, pruned_loss=0.03065, over 1409705.06 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:45:21,094 INFO [train.py:763] (3/8) Epoch 32, batch 950, loss[loss=0.1668, simple_loss=0.2625, pruned_loss=0.03553, over 7429.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03045, over 1413959.18 frames.], batch size: 20, lr: 2.37e-04
2022-04-30 13:46:27,362 INFO [train.py:763] (3/8) Epoch 32, batch 1000, loss[loss=0.185, simple_loss=0.2844, pruned_loss=0.04279, over 7227.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2597, pruned_loss=0.03032, over 1413536.04 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:47:33,311 INFO [train.py:763] (3/8) Epoch 32, batch 1050, loss[loss=0.1813, simple_loss=0.2753, pruned_loss=0.04364, over 7117.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2593, pruned_loss=0.03, over 1412457.08 frames.], batch size: 28, lr: 2.37e-04
2022-04-30 13:48:38,617 INFO [train.py:763] (3/8) Epoch 32, batch 1100, loss[loss=0.1711, simple_loss=0.2732, pruned_loss=0.03448, over 7271.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2592, pruned_loss=0.02978, over 1417385.87 frames.], batch size: 24, lr: 2.37e-04
2022-04-30 13:49:45,240 INFO [train.py:763] (3/8) Epoch 32, batch 1150, loss[loss=0.2008, simple_loss=0.3042, pruned_loss=0.04868, over 7223.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02954, over 1418951.82 frames.], batch size: 23, lr: 2.37e-04
2022-04-30 13:50:50,720 INFO [train.py:763] (3/8) Epoch 32, batch 1200, loss[loss=0.1673, simple_loss=0.2694, pruned_loss=0.03261, over 7177.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02988, over 1421436.77 frames.], batch size: 26, lr: 2.37e-04
2022-04-30 13:51:56,747 INFO [train.py:763] (3/8) Epoch 32, batch 1250, loss[loss=0.1631, simple_loss=0.2696, pruned_loss=0.02828, over 6542.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03021, over 1420401.97 frames.], batch size: 38, lr: 2.37e-04
2022-04-30 13:53:02,500 INFO [train.py:763] (3/8) Epoch 32, batch 1300, loss[loss=0.1668, simple_loss=0.2688, pruned_loss=0.03236, over 7221.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03041, over 1421163.68 frames.], batch size: 21, lr: 2.37e-04
2022-04-30 13:54:10,199 INFO [train.py:763] (3/8) Epoch 32, batch 1350, loss[loss=0.1338, simple_loss=0.2181, pruned_loss=0.02481, over 7286.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2604, pruned_loss=0.03053, over 1420763.64 frames.], batch size: 17, lr: 2.37e-04
2022-04-30 13:55:17,150 INFO [train.py:763] (3/8) Epoch 32, batch 1400, loss[loss=0.1488, simple_loss=0.2666, pruned_loss=0.01554, over 7142.00 frames.], tot_loss[loss=0.16, simple_loss=0.2597, pruned_loss=0.03013, over 1422309.34 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 13:56:22,420 INFO [train.py:763] (3/8) Epoch 32, batch 1450, loss[loss=0.1612, simple_loss=0.2706, pruned_loss=0.02589, over 6690.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2601, pruned_loss=0.03016, over 1425343.76 frames.], batch size: 31, lr: 2.36e-04
2022-04-30 13:57:27,825 INFO [train.py:763] (3/8) Epoch 32, batch 1500, loss[loss=0.1751, simple_loss=0.2676, pruned_loss=0.04137, over 5027.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2613, pruned_loss=0.03089, over 1422369.69 frames.], batch size: 52, lr: 2.36e-04
2022-04-30 13:58:33,078 INFO [train.py:763] (3/8) Epoch 32, batch 1550, loss[loss=0.1565, simple_loss=0.258, pruned_loss=0.0275, over 7219.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2615, pruned_loss=0.03083, over 1419017.27 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 13:59:38,326 INFO [train.py:763] (3/8) Epoch 32, batch 1600, loss[loss=0.1822, simple_loss=0.2897, pruned_loss=0.03734, over 7408.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2613, pruned_loss=0.03075, over 1420892.07 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:00:43,685 INFO [train.py:763] (3/8) Epoch 32, batch 1650, loss[loss=0.1715, simple_loss=0.2774, pruned_loss=0.03281, over 7219.00 frames.], tot_loss[loss=0.1611, simple_loss=0.261, pruned_loss=0.0306, over 1421824.72 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:01:48,787 INFO [train.py:763] (3/8) Epoch 32, batch 1700, loss[loss=0.1696, simple_loss=0.2798, pruned_loss=0.0297, over 7299.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2616, pruned_loss=0.03039, over 1423516.72 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:02:54,184 INFO [train.py:763] (3/8) Epoch 32, batch 1750, loss[loss=0.1909, simple_loss=0.2888, pruned_loss=0.04653, over 6956.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2624, pruned_loss=0.03097, over 1416726.22 frames.], batch size: 28, lr: 2.36e-04
2022-04-30 14:03:59,640 INFO [train.py:763] (3/8) Epoch 32, batch 1800, loss[loss=0.1524, simple_loss=0.2455, pruned_loss=0.02963, over 7251.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2617, pruned_loss=0.03077, over 1420376.62 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:05:06,115 INFO [train.py:763] (3/8) Epoch 32, batch 1850, loss[loss=0.1777, simple_loss=0.281, pruned_loss=0.03722, over 7309.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2613, pruned_loss=0.03065, over 1422766.47 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:06:21,242 INFO [train.py:763] (3/8) Epoch 32, batch 1900, loss[loss=0.1951, simple_loss=0.2882, pruned_loss=0.05097, over 7376.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03058, over 1425357.57 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:07:26,671 INFO [train.py:763] (3/8) Epoch 32, batch 1950, loss[loss=0.1701, simple_loss=0.265, pruned_loss=0.03765, over 7273.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2609, pruned_loss=0.03076, over 1424119.53 frames.], batch size: 24, lr: 2.36e-04
2022-04-30 14:08:33,678 INFO [train.py:763] (3/8) Epoch 32, batch 2000, loss[loss=0.1734, simple_loss=0.2741, pruned_loss=0.03637, over 6407.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2612, pruned_loss=0.03121, over 1425163.67 frames.], batch size: 37, lr: 2.36e-04
2022-04-30 14:09:39,827 INFO [train.py:763] (3/8) Epoch 32, batch 2050, loss[loss=0.1609, simple_loss=0.2524, pruned_loss=0.03467, over 7166.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2606, pruned_loss=0.03082, over 1426019.26 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:10:45,530 INFO [train.py:763] (3/8) Epoch 32, batch 2100, loss[loss=0.1663, simple_loss=0.2651, pruned_loss=0.0338, over 7148.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2606, pruned_loss=0.03102, over 1427558.33 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:11:52,555 INFO [train.py:763] (3/8) Epoch 32, batch 2150, loss[loss=0.1319, simple_loss=0.2299, pruned_loss=0.01695, over 7413.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03083, over 1429253.12 frames.], batch size: 18, lr: 2.36e-04
2022-04-30 14:12:58,733 INFO [train.py:763] (3/8) Epoch 32, batch 2200, loss[loss=0.1683, simple_loss=0.2813, pruned_loss=0.02761, over 5250.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.0306, over 1423239.60 frames.], batch size: 52, lr: 2.36e-04
2022-04-30 14:14:05,700 INFO [train.py:763] (3/8) Epoch 32, batch 2250, loss[loss=0.1962, simple_loss=0.3008, pruned_loss=0.04582, over 7222.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03115, over 1421401.41 frames.], batch size: 26, lr: 2.36e-04
2022-04-30 14:15:12,722 INFO [train.py:763] (3/8) Epoch 32, batch 2300, loss[loss=0.1787, simple_loss=0.2789, pruned_loss=0.03927, over 7194.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2609, pruned_loss=0.03114, over 1419994.27 frames.], batch size: 22, lr: 2.36e-04
2022-04-30 14:16:18,546 INFO [train.py:763] (3/8) Epoch 32, batch 2350, loss[loss=0.1848, simple_loss=0.2712, pruned_loss=0.04922, over 6775.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2592, pruned_loss=0.0305, over 1422649.81 frames.], batch size: 15, lr: 2.36e-04
2022-04-30 14:17:25,996 INFO [train.py:763] (3/8) Epoch 32, batch 2400, loss[loss=0.1678, simple_loss=0.2672, pruned_loss=0.03422, over 7446.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2587, pruned_loss=0.03059, over 1424260.87 frames.], batch size: 20, lr: 2.36e-04
2022-04-30 14:18:32,877 INFO [train.py:763] (3/8) Epoch 32, batch 2450, loss[loss=0.1711, simple_loss=0.2622, pruned_loss=0.03994, over 7261.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2588, pruned_loss=0.03077, over 1427026.39 frames.], batch size: 19, lr: 2.36e-04
2022-04-30 14:19:38,453 INFO [train.py:763] (3/8) Epoch 32, batch 2500, loss[loss=0.1774, simple_loss=0.2696, pruned_loss=0.04257, over 7316.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2588, pruned_loss=0.03027, over 1428093.33 frames.], batch size: 21, lr: 2.36e-04
2022-04-30 14:20:45,069 INFO [train.py:763] (3/8) Epoch 32, batch 2550, loss[loss=0.1763, simple_loss=0.2705, pruned_loss=0.04105, over 7368.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2583, pruned_loss=0.02998, over 1427336.68 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:21:59,921 INFO [train.py:763] (3/8) Epoch 32, batch 2600, loss[loss=0.1585, simple_loss=0.2653, pruned_loss=0.0259, over 7205.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2588, pruned_loss=0.0299, over 1427450.63 frames.], batch size: 23, lr: 2.36e-04
2022-04-30 14:23:23,009 INFO [train.py:763] (3/8) Epoch 32, batch 2650, loss[loss=0.1506, simple_loss=0.2447, pruned_loss=0.02822, over 7215.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02966, over 1423515.32 frames.], batch size: 16, lr: 2.35e-04
2022-04-30 14:24:36,937 INFO [train.py:763] (3/8) Epoch 32, batch 2700, loss[loss=0.1559, simple_loss=0.2544, pruned_loss=0.0287, over 7423.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02984, over 1425453.23 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:25:51,353 INFO [train.py:763] (3/8) Epoch 32, batch 2750, loss[loss=0.1372, simple_loss=0.2189, pruned_loss=0.02771, over 7278.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2604, pruned_loss=0.03024, over 1426383.81 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:26:57,660 INFO [train.py:763] (3/8) Epoch 32, batch 2800, loss[loss=0.1845, simple_loss=0.2842, pruned_loss=0.04241, over 7207.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2607, pruned_loss=0.03048, over 1425565.77 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:28:12,042 INFO [train.py:763] (3/8) Epoch 32, batch 2850, loss[loss=0.176, simple_loss=0.2857, pruned_loss=0.03318, over 7331.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2612, pruned_loss=0.0305, over 1427225.23 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:29:27,081 INFO [train.py:763] (3/8) Epoch 32, batch 2900, loss[loss=0.1616, simple_loss=0.2692, pruned_loss=0.02701, over 7286.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2616, pruned_loss=0.03059, over 1425992.05 frames.], batch size: 25, lr: 2.35e-04
2022-04-30 14:30:33,973 INFO [train.py:763] (3/8) Epoch 32, batch 2950, loss[loss=0.1594, simple_loss=0.2558, pruned_loss=0.03148, over 7433.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2622, pruned_loss=0.03075, over 1428586.76 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:31:40,119 INFO [train.py:763] (3/8) Epoch 32, batch 3000, loss[loss=0.1365, simple_loss=0.237, pruned_loss=0.01806, over 7062.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.0307, over 1427080.05 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:31:40,120 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 14:31:55,318 INFO [train.py:792] (3/8) 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] (3/8) Epoch 32, batch 3050, loss[loss=0.1511, simple_loss=0.2549, pruned_loss=0.02364, over 6556.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2608, pruned_loss=0.03086, over 1423343.68 frames.], batch size: 38, lr: 2.35e-04
2022-04-30 14:34:07,505 INFO [train.py:763] (3/8) Epoch 32, batch 3100, loss[loss=0.1868, simple_loss=0.2905, pruned_loss=0.04151, over 7360.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03038, over 1423527.99 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:35:13,884 INFO [train.py:763] (3/8) Epoch 32, batch 3150, loss[loss=0.1456, simple_loss=0.2478, pruned_loss=0.02168, over 7070.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03018, over 1421771.96 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:36:20,354 INFO [train.py:763] (3/8) Epoch 32, batch 3200, loss[loss=0.1425, simple_loss=0.2262, pruned_loss=0.02943, over 7184.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03022, over 1421751.88 frames.], batch size: 16, lr: 2.35e-04
2022-04-30 14:37:25,785 INFO [train.py:763] (3/8) Epoch 32, batch 3250, loss[loss=0.1411, simple_loss=0.2395, pruned_loss=0.02136, over 7268.00 frames.], tot_loss[loss=0.1606, simple_loss=0.26, pruned_loss=0.03058, over 1419412.70 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:38:31,355 INFO [train.py:763] (3/8) Epoch 32, batch 3300, loss[loss=0.1634, simple_loss=0.2663, pruned_loss=0.03022, over 7226.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2589, pruned_loss=0.03041, over 1424171.57 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:39:37,083 INFO [train.py:763] (3/8) Epoch 32, batch 3350, loss[loss=0.1503, simple_loss=0.2576, pruned_loss=0.02151, over 7319.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2595, pruned_loss=0.03061, over 1428080.44 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:40:43,411 INFO [train.py:763] (3/8) Epoch 32, batch 3400, loss[loss=0.152, simple_loss=0.2425, pruned_loss=0.03072, over 7276.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2599, pruned_loss=0.03072, over 1427974.01 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:41:50,116 INFO [train.py:763] (3/8) Epoch 32, batch 3450, loss[loss=0.191, simple_loss=0.2847, pruned_loss=0.04864, over 7329.00 frames.], tot_loss[loss=0.1614, simple_loss=0.261, pruned_loss=0.0309, over 1432277.31 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:42:56,323 INFO [train.py:763] (3/8) Epoch 32, batch 3500, loss[loss=0.1844, simple_loss=0.2798, pruned_loss=0.04445, over 7389.00 frames.], tot_loss[loss=0.162, simple_loss=0.2615, pruned_loss=0.03125, over 1428799.34 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:44:01,645 INFO [train.py:763] (3/8) Epoch 32, batch 3550, loss[loss=0.1628, simple_loss=0.2548, pruned_loss=0.03535, over 7416.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2614, pruned_loss=0.03109, over 1427264.86 frames.], batch size: 18, lr: 2.35e-04
2022-04-30 14:45:06,993 INFO [train.py:763] (3/8) Epoch 32, batch 3600, loss[loss=0.1562, simple_loss=0.2584, pruned_loss=0.02698, over 7332.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2614, pruned_loss=0.03117, over 1423033.14 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:46:12,675 INFO [train.py:763] (3/8) Epoch 32, batch 3650, loss[loss=0.1504, simple_loss=0.2499, pruned_loss=0.02547, over 7333.00 frames.], tot_loss[loss=0.1614, simple_loss=0.261, pruned_loss=0.03088, over 1422646.83 frames.], batch size: 20, lr: 2.35e-04
2022-04-30 14:47:18,399 INFO [train.py:763] (3/8) Epoch 32, batch 3700, loss[loss=0.1481, simple_loss=0.2451, pruned_loss=0.02558, over 7282.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03056, over 1426123.51 frames.], batch size: 17, lr: 2.35e-04
2022-04-30 14:48:25,076 INFO [train.py:763] (3/8) Epoch 32, batch 3750, loss[loss=0.1766, simple_loss=0.2777, pruned_loss=0.03775, over 7222.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03018, over 1426797.59 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:49:30,590 INFO [train.py:763] (3/8) Epoch 32, batch 3800, loss[loss=0.1703, simple_loss=0.2782, pruned_loss=0.03117, over 7208.00 frames.], tot_loss[loss=0.1596, simple_loss=0.259, pruned_loss=0.03011, over 1427478.37 frames.], batch size: 23, lr: 2.35e-04
2022-04-30 14:50:35,844 INFO [train.py:763] (3/8) Epoch 32, batch 3850, loss[loss=0.1723, simple_loss=0.2753, pruned_loss=0.03466, over 7324.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2598, pruned_loss=0.03059, over 1428275.31 frames.], batch size: 21, lr: 2.35e-04
2022-04-30 14:51:41,190 INFO [train.py:763] (3/8) Epoch 32, batch 3900, loss[loss=0.1451, simple_loss=0.2353, pruned_loss=0.02742, over 6817.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2615, pruned_loss=0.03106, over 1428517.88 frames.], batch size: 15, lr: 2.35e-04
2022-04-30 14:52:46,606 INFO [train.py:763] (3/8) Epoch 32, batch 3950, loss[loss=0.1419, simple_loss=0.2367, pruned_loss=0.0236, over 7412.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2627, pruned_loss=0.03137, over 1431378.23 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:53:52,265 INFO [train.py:763] (3/8) Epoch 32, batch 4000, loss[loss=0.1609, simple_loss=0.2659, pruned_loss=0.02795, over 6324.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03063, over 1430887.82 frames.], batch size: 37, lr: 2.34e-04
2022-04-30 14:54:57,658 INFO [train.py:763] (3/8) Epoch 32, batch 4050, loss[loss=0.1448, simple_loss=0.2338, pruned_loss=0.02787, over 7278.00 frames.], tot_loss[loss=0.1613, simple_loss=0.261, pruned_loss=0.03082, over 1427406.60 frames.], batch size: 18, lr: 2.34e-04
2022-04-30 14:56:02,793 INFO [train.py:763] (3/8) Epoch 32, batch 4100, loss[loss=0.1733, simple_loss=0.2691, pruned_loss=0.03874, over 7138.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2608, pruned_loss=0.03087, over 1421007.53 frames.], batch size: 26, lr: 2.34e-04
2022-04-30 14:57:08,460 INFO [train.py:763] (3/8) Epoch 32, batch 4150, loss[loss=0.1438, simple_loss=0.2332, pruned_loss=0.02718, over 6828.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03026, over 1420960.87 frames.], batch size: 15, lr: 2.34e-04
2022-04-30 14:58:14,264 INFO [train.py:763] (3/8) Epoch 32, batch 4200, loss[loss=0.1704, simple_loss=0.2669, pruned_loss=0.03698, over 7259.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03007, over 1418595.84 frames.], batch size: 19, lr: 2.34e-04
2022-04-30 14:59:19,680 INFO [train.py:763] (3/8) Epoch 32, batch 4250, loss[loss=0.1707, simple_loss=0.2638, pruned_loss=0.03884, over 7423.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03019, over 1420008.19 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:00:26,350 INFO [train.py:763] (3/8) Epoch 32, batch 4300, loss[loss=0.1697, simple_loss=0.2678, pruned_loss=0.03581, over 6722.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02994, over 1418717.64 frames.], batch size: 31, lr: 2.34e-04
2022-04-30 15:01:32,993 INFO [train.py:763] (3/8) Epoch 32, batch 4350, loss[loss=0.1504, simple_loss=0.2607, pruned_loss=0.02006, over 7224.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02997, over 1414632.29 frames.], batch size: 21, lr: 2.34e-04
2022-04-30 15:02:38,277 INFO [train.py:763] (3/8) Epoch 32, batch 4400, loss[loss=0.1549, simple_loss=0.2627, pruned_loss=0.02358, over 7142.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03002, over 1413886.70 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:03:43,363 INFO [train.py:763] (3/8) Epoch 32, batch 4450, loss[loss=0.1487, simple_loss=0.254, pruned_loss=0.0217, over 7322.00 frames.], tot_loss[loss=0.1599, simple_loss=0.26, pruned_loss=0.02989, over 1406141.10 frames.], batch size: 22, lr: 2.34e-04
2022-04-30 15:04:48,246 INFO [train.py:763] (3/8) Epoch 32, batch 4500, loss[loss=0.1518, simple_loss=0.2555, pruned_loss=0.02408, over 7147.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03041, over 1396594.52 frames.], batch size: 20, lr: 2.34e-04
2022-04-30 15:05:53,072 INFO [train.py:763] (3/8) Epoch 32, batch 4550, loss[loss=0.1728, simple_loss=0.2697, pruned_loss=0.03799, over 4859.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2618, pruned_loss=0.03078, over 1373994.71 frames.], batch size: 52, lr: 2.34e-04
2022-04-30 15:07:21,084 INFO [train.py:763] (3/8) Epoch 33, batch 0, loss[loss=0.1675, simple_loss=0.2634, pruned_loss=0.03578, over 7436.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2634, pruned_loss=0.03578, over 7436.00 frames.], batch size: 20, lr: 2.31e-04
2022-04-30 15:08:26,672 INFO [train.py:763] (3/8) Epoch 33, batch 50, loss[loss=0.1746, simple_loss=0.2832, pruned_loss=0.03305, over 7077.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2611, pruned_loss=0.03116, over 324499.02 frames.], batch size: 28, lr: 2.30e-04
2022-04-30 15:09:31,881 INFO [train.py:763] (3/8) Epoch 33, batch 100, loss[loss=0.1823, simple_loss=0.2894, pruned_loss=0.03765, over 7106.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2625, pruned_loss=0.03097, over 565487.94 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:10:37,373 INFO [train.py:763] (3/8) Epoch 33, batch 150, loss[loss=0.1328, simple_loss=0.2293, pruned_loss=0.01811, over 7055.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2606, pruned_loss=0.02991, over 755519.82 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:11:42,897 INFO [train.py:763] (3/8) Epoch 33, batch 200, loss[loss=0.1426, simple_loss=0.2306, pruned_loss=0.02731, over 7250.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02935, over 906248.30 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:12:48,573 INFO [train.py:763] (3/8) Epoch 33, batch 250, loss[loss=0.1768, simple_loss=0.277, pruned_loss=0.03824, over 5147.00 frames.], tot_loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.02959, over 1013330.07 frames.], batch size: 53, lr: 2.30e-04
2022-04-30 15:13:55,817 INFO [train.py:763] (3/8) Epoch 33, batch 300, loss[loss=0.1624, simple_loss=0.2602, pruned_loss=0.03224, over 7390.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2588, pruned_loss=0.02999, over 1103297.29 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:15:01,946 INFO [train.py:763] (3/8) Epoch 33, batch 350, loss[loss=0.1288, simple_loss=0.2203, pruned_loss=0.01864, over 7150.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03037, over 1168529.39 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:16:08,893 INFO [train.py:763] (3/8) Epoch 33, batch 400, loss[loss=0.1668, simple_loss=0.282, pruned_loss=0.02583, over 7404.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2592, pruned_loss=0.03007, over 1229032.79 frames.], batch size: 21, lr: 2.30e-04
2022-04-30 15:17:14,698 INFO [train.py:763] (3/8) Epoch 33, batch 450, loss[loss=0.1507, simple_loss=0.2421, pruned_loss=0.0296, over 7423.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2597, pruned_loss=0.03027, over 1273903.45 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:18:21,051 INFO [train.py:763] (3/8) Epoch 33, batch 500, loss[loss=0.199, simple_loss=0.2941, pruned_loss=0.05199, over 7310.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2602, pruned_loss=0.03072, over 1307309.63 frames.], batch size: 24, lr: 2.30e-04
2022-04-30 15:19:26,287 INFO [train.py:763] (3/8) Epoch 33, batch 550, loss[loss=0.1602, simple_loss=0.2751, pruned_loss=0.0227, over 6468.00 frames.], tot_loss[loss=0.161, simple_loss=0.2609, pruned_loss=0.03056, over 1331424.37 frames.], batch size: 38, lr: 2.30e-04
2022-04-30 15:20:43,084 INFO [train.py:763] (3/8) Epoch 33, batch 600, loss[loss=0.17, simple_loss=0.2721, pruned_loss=0.034, over 7297.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03025, over 1353004.77 frames.], batch size: 25, lr: 2.30e-04
2022-04-30 15:21:48,329 INFO [train.py:763] (3/8) Epoch 33, batch 650, loss[loss=0.1499, simple_loss=0.2507, pruned_loss=0.02452, over 7163.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2608, pruned_loss=0.03036, over 1371227.19 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:22:53,611 INFO [train.py:763] (3/8) Epoch 33, batch 700, loss[loss=0.1375, simple_loss=0.2272, pruned_loss=0.02384, over 7117.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2599, pruned_loss=0.03023, over 1378541.49 frames.], batch size: 17, lr: 2.30e-04
2022-04-30 15:23:58,783 INFO [train.py:763] (3/8) Epoch 33, batch 750, loss[loss=0.176, simple_loss=0.2796, pruned_loss=0.03617, over 7204.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03028, over 1390252.52 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:25:05,620 INFO [train.py:763] (3/8) Epoch 33, batch 800, loss[loss=0.139, simple_loss=0.2419, pruned_loss=0.01811, over 7272.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03012, over 1395514.32 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:26:11,924 INFO [train.py:763] (3/8) Epoch 33, batch 850, loss[loss=0.1694, simple_loss=0.2734, pruned_loss=0.03271, over 6414.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03013, over 1404332.64 frames.], batch size: 37, lr: 2.30e-04
2022-04-30 15:27:17,420 INFO [train.py:763] (3/8) Epoch 33, batch 900, loss[loss=0.1862, simple_loss=0.272, pruned_loss=0.05024, over 4980.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03009, over 1409172.79 frames.], batch size: 53, lr: 2.30e-04
2022-04-30 15:28:22,822 INFO [train.py:763] (3/8) Epoch 33, batch 950, loss[loss=0.1632, simple_loss=0.2613, pruned_loss=0.03252, over 7274.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2595, pruned_loss=0.03014, over 1407957.69 frames.], batch size: 18, lr: 2.30e-04
2022-04-30 15:29:28,253 INFO [train.py:763] (3/8) Epoch 33, batch 1000, loss[loss=0.1528, simple_loss=0.2578, pruned_loss=0.0239, over 7426.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.03025, over 1409108.20 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:30:33,670 INFO [train.py:763] (3/8) Epoch 33, batch 1050, loss[loss=0.1646, simple_loss=0.2667, pruned_loss=0.03129, over 7169.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2602, pruned_loss=0.03008, over 1415030.16 frames.], batch size: 19, lr: 2.30e-04
2022-04-30 15:31:40,468 INFO [train.py:763] (3/8) Epoch 33, batch 1100, loss[loss=0.1631, simple_loss=0.2685, pruned_loss=0.02882, over 6354.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03012, over 1413162.76 frames.], batch size: 38, lr: 2.30e-04
2022-04-30 15:32:45,927 INFO [train.py:763] (3/8) Epoch 33, batch 1150, loss[loss=0.154, simple_loss=0.2594, pruned_loss=0.02433, over 7437.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2599, pruned_loss=0.03014, over 1416372.32 frames.], batch size: 20, lr: 2.30e-04
2022-04-30 15:33:51,343 INFO [train.py:763] (3/8) Epoch 33, batch 1200, loss[loss=0.1706, simple_loss=0.278, pruned_loss=0.03164, over 7191.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03028, over 1420235.43 frames.], batch size: 23, lr: 2.30e-04
2022-04-30 15:34:56,632 INFO [train.py:763] (3/8) Epoch 33, batch 1250, loss[loss=0.1557, simple_loss=0.2583, pruned_loss=0.02658, over 7336.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03041, over 1417082.18 frames.], batch size: 22, lr: 2.30e-04
2022-04-30 15:36:02,616 INFO [train.py:763] (3/8) Epoch 33, batch 1300, loss[loss=0.1685, simple_loss=0.2767, pruned_loss=0.03011, over 7182.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03051, over 1417638.24 frames.], batch size: 26, lr: 2.30e-04
2022-04-30 15:37:09,763 INFO [train.py:763] (3/8) Epoch 33, batch 1350, loss[loss=0.1638, simple_loss=0.2684, pruned_loss=0.02963, over 7217.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2596, pruned_loss=0.03034, over 1418651.07 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:38:16,826 INFO [train.py:763] (3/8) Epoch 33, batch 1400, loss[loss=0.1621, simple_loss=0.2586, pruned_loss=0.03283, over 7261.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2597, pruned_loss=0.03056, over 1421570.31 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:39:22,842 INFO [train.py:763] (3/8) Epoch 33, batch 1450, loss[loss=0.1882, simple_loss=0.2994, pruned_loss=0.03847, over 7415.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.0302, over 1425622.51 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:40:28,338 INFO [train.py:763] (3/8) Epoch 33, batch 1500, loss[loss=0.1773, simple_loss=0.2756, pruned_loss=0.03944, over 7373.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2602, pruned_loss=0.03035, over 1423894.07 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:41:33,824 INFO [train.py:763] (3/8) Epoch 33, batch 1550, loss[loss=0.152, simple_loss=0.2617, pruned_loss=0.02115, over 7310.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2604, pruned_loss=0.03035, over 1420992.99 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:42:39,066 INFO [train.py:763] (3/8) Epoch 33, batch 1600, loss[loss=0.1698, simple_loss=0.2683, pruned_loss=0.03562, over 7328.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2601, pruned_loss=0.03039, over 1422340.23 frames.], batch size: 20, lr: 2.29e-04
2022-04-30 15:43:46,168 INFO [train.py:763] (3/8) Epoch 33, batch 1650, loss[loss=0.1836, simple_loss=0.288, pruned_loss=0.03961, over 7198.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2609, pruned_loss=0.03028, over 1421959.24 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 15:44:53,518 INFO [train.py:763] (3/8) Epoch 33, batch 1700, loss[loss=0.1817, simple_loss=0.2852, pruned_loss=0.03909, over 7385.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03014, over 1425981.29 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:46:00,131 INFO [train.py:763] (3/8) Epoch 33, batch 1750, loss[loss=0.1584, simple_loss=0.2575, pruned_loss=0.02965, over 7054.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03011, over 1421511.13 frames.], batch size: 28, lr: 2.29e-04
2022-04-30 15:47:05,296 INFO [train.py:763] (3/8) Epoch 33, batch 1800, loss[loss=0.149, simple_loss=0.237, pruned_loss=0.03051, over 7266.00 frames.], tot_loss[loss=0.1603, simple_loss=0.26, pruned_loss=0.03031, over 1423259.85 frames.], batch size: 17, lr: 2.29e-04
2022-04-30 15:48:11,896 INFO [train.py:763] (3/8) Epoch 33, batch 1850, loss[loss=0.1578, simple_loss=0.2709, pruned_loss=0.02236, over 7310.00 frames.], tot_loss[loss=0.1604, simple_loss=0.26, pruned_loss=0.03044, over 1416106.03 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:49:17,341 INFO [train.py:763] (3/8) Epoch 33, batch 1900, loss[loss=0.1501, simple_loss=0.2573, pruned_loss=0.02149, over 6752.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2596, pruned_loss=0.03001, over 1410572.99 frames.], batch size: 31, lr: 2.29e-04
2022-04-30 15:50:23,826 INFO [train.py:763] (3/8) Epoch 33, batch 1950, loss[loss=0.1569, simple_loss=0.2476, pruned_loss=0.03311, over 7004.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2592, pruned_loss=0.03005, over 1416267.36 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 15:51:31,073 INFO [train.py:763] (3/8) Epoch 33, batch 2000, loss[loss=0.1498, simple_loss=0.2426, pruned_loss=0.0285, over 7418.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02967, over 1421975.00 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:52:37,441 INFO [train.py:763] (3/8) Epoch 33, batch 2050, loss[loss=0.1722, simple_loss=0.2719, pruned_loss=0.03626, over 7122.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02981, over 1421068.62 frames.], batch size: 26, lr: 2.29e-04
2022-04-30 15:53:42,712 INFO [train.py:763] (3/8) Epoch 33, batch 2100, loss[loss=0.173, simple_loss=0.2808, pruned_loss=0.03262, over 7202.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2596, pruned_loss=0.02964, over 1423794.39 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 15:54:47,941 INFO [train.py:763] (3/8) Epoch 33, batch 2150, loss[loss=0.1769, simple_loss=0.2808, pruned_loss=0.03651, over 7297.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2594, pruned_loss=0.02964, over 1423446.97 frames.], batch size: 24, lr: 2.29e-04
2022-04-30 15:55:53,179 INFO [train.py:763] (3/8) Epoch 33, batch 2200, loss[loss=0.166, simple_loss=0.2747, pruned_loss=0.02865, over 7314.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02985, over 1426020.69 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 15:56:58,873 INFO [train.py:763] (3/8) Epoch 33, batch 2250, loss[loss=0.147, simple_loss=0.2428, pruned_loss=0.02564, over 7278.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.02999, over 1423225.25 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 15:58:05,270 INFO [train.py:763] (3/8) Epoch 33, batch 2300, loss[loss=0.1456, simple_loss=0.2359, pruned_loss=0.02767, over 7159.00 frames.], tot_loss[loss=0.161, simple_loss=0.2613, pruned_loss=0.03033, over 1424619.20 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 15:59:10,707 INFO [train.py:763] (3/8) Epoch 33, batch 2350, loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02956, over 7173.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2601, pruned_loss=0.02979, over 1426297.95 frames.], batch size: 19, lr: 2.29e-04
2022-04-30 16:00:16,787 INFO [train.py:763] (3/8) Epoch 33, batch 2400, loss[loss=0.1545, simple_loss=0.2583, pruned_loss=0.02539, over 7386.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2596, pruned_loss=0.03002, over 1427055.01 frames.], batch size: 23, lr: 2.29e-04
2022-04-30 16:01:22,890 INFO [train.py:763] (3/8) Epoch 33, batch 2450, loss[loss=0.1703, simple_loss=0.2806, pruned_loss=0.03002, over 7218.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2605, pruned_loss=0.03031, over 1421050.53 frames.], batch size: 21, lr: 2.29e-04
2022-04-30 16:02:28,045 INFO [train.py:763] (3/8) Epoch 33, batch 2500, loss[loss=0.1292, simple_loss=0.2238, pruned_loss=0.01727, over 6998.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2607, pruned_loss=0.03026, over 1418831.79 frames.], batch size: 16, lr: 2.29e-04
2022-04-30 16:03:33,223 INFO [train.py:763] (3/8) Epoch 33, batch 2550, loss[loss=0.1525, simple_loss=0.2562, pruned_loss=0.02444, over 7337.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03044, over 1420915.27 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:04:38,851 INFO [train.py:763] (3/8) Epoch 33, batch 2600, loss[loss=0.1423, simple_loss=0.2443, pruned_loss=0.02014, over 7083.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03062, over 1420373.07 frames.], batch size: 18, lr: 2.29e-04
2022-04-30 16:05:45,688 INFO [train.py:763] (3/8) Epoch 33, batch 2650, loss[loss=0.1504, simple_loss=0.2513, pruned_loss=0.02475, over 7346.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2599, pruned_loss=0.03048, over 1421504.28 frames.], batch size: 22, lr: 2.29e-04
2022-04-30 16:06:52,532 INFO [train.py:763] (3/8) Epoch 33, batch 2700, loss[loss=0.1456, simple_loss=0.2381, pruned_loss=0.02654, over 7265.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2602, pruned_loss=0.0305, over 1426076.43 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:07:59,667 INFO [train.py:763] (3/8) Epoch 33, batch 2750, loss[loss=0.1538, simple_loss=0.2548, pruned_loss=0.02644, over 7320.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2599, pruned_loss=0.03038, over 1424197.69 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:09:06,752 INFO [train.py:763] (3/8) Epoch 33, batch 2800, loss[loss=0.1424, simple_loss=0.2345, pruned_loss=0.02511, over 7400.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2609, pruned_loss=0.03064, over 1429463.51 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:10:13,295 INFO [train.py:763] (3/8) Epoch 33, batch 2850, loss[loss=0.1633, simple_loss=0.262, pruned_loss=0.03228, over 7195.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03045, over 1430941.74 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:11:18,328 INFO [train.py:763] (3/8) Epoch 33, batch 2900, loss[loss=0.15, simple_loss=0.2498, pruned_loss=0.02511, over 7143.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03004, over 1427289.12 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:12:24,335 INFO [train.py:763] (3/8) Epoch 33, batch 2950, loss[loss=0.1679, simple_loss=0.2731, pruned_loss=0.03133, over 7147.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2601, pruned_loss=0.03037, over 1427308.39 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:13:31,370 INFO [train.py:763] (3/8) Epoch 33, batch 3000, loss[loss=0.1478, simple_loss=0.2445, pruned_loss=0.02556, over 7351.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03035, over 1428013.34 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:13:31,371 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 16:13:46,765 INFO [train.py:792] (3/8) Epoch 33, validation: loss=0.1701, simple_loss=0.2653, pruned_loss=0.03746, over 698248.00 frames.
2022-04-30 16:14:51,745 INFO [train.py:763] (3/8) Epoch 33, batch 3050, loss[loss=0.1525, simple_loss=0.2593, pruned_loss=0.02281, over 7358.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2606, pruned_loss=0.03049, over 1428036.30 frames.], batch size: 19, lr: 2.28e-04
2022-04-30 16:15:58,064 INFO [train.py:763] (3/8) Epoch 33, batch 3100, loss[loss=0.1365, simple_loss=0.2331, pruned_loss=0.01992, over 6806.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2608, pruned_loss=0.03069, over 1428802.01 frames.], batch size: 15, lr: 2.28e-04
2022-04-30 16:17:04,951 INFO [train.py:763] (3/8) Epoch 33, batch 3150, loss[loss=0.126, simple_loss=0.2226, pruned_loss=0.01465, over 7280.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03026, over 1428146.47 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:18:11,843 INFO [train.py:763] (3/8) Epoch 33, batch 3200, loss[loss=0.2109, simple_loss=0.3001, pruned_loss=0.06091, over 4774.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2593, pruned_loss=0.02996, over 1423628.79 frames.], batch size: 52, lr: 2.28e-04
2022-04-30 16:19:17,472 INFO [train.py:763] (3/8) Epoch 33, batch 3250, loss[loss=0.1425, simple_loss=0.2331, pruned_loss=0.02592, over 7131.00 frames.], tot_loss[loss=0.16, simple_loss=0.2594, pruned_loss=0.0303, over 1421093.31 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:20:22,898 INFO [train.py:763] (3/8) Epoch 33, batch 3300, loss[loss=0.1639, simple_loss=0.2736, pruned_loss=0.02716, over 7104.00 frames.], tot_loss[loss=0.16, simple_loss=0.2594, pruned_loss=0.03026, over 1417799.06 frames.], batch size: 28, lr: 2.28e-04
2022-04-30 16:21:28,690 INFO [train.py:763] (3/8) Epoch 33, batch 3350, loss[loss=0.1541, simple_loss=0.2577, pruned_loss=0.02526, over 7145.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2582, pruned_loss=0.0297, over 1420557.36 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:22:44,380 INFO [train.py:763] (3/8) Epoch 33, batch 3400, loss[loss=0.1584, simple_loss=0.2604, pruned_loss=0.02824, over 7206.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2586, pruned_loss=0.0299, over 1421595.46 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:23:50,295 INFO [train.py:763] (3/8) Epoch 33, batch 3450, loss[loss=0.1479, simple_loss=0.2407, pruned_loss=0.02755, over 7000.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2588, pruned_loss=0.02966, over 1427258.71 frames.], batch size: 16, lr: 2.28e-04
2022-04-30 16:24:55,492 INFO [train.py:763] (3/8) Epoch 33, batch 3500, loss[loss=0.1708, simple_loss=0.2766, pruned_loss=0.03252, over 7198.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02963, over 1429052.40 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:26:01,143 INFO [train.py:763] (3/8) Epoch 33, batch 3550, loss[loss=0.1307, simple_loss=0.2235, pruned_loss=0.01898, over 7276.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02938, over 1431002.53 frames.], batch size: 17, lr: 2.28e-04
2022-04-30 16:27:06,626 INFO [train.py:763] (3/8) Epoch 33, batch 3600, loss[loss=0.1786, simple_loss=0.2804, pruned_loss=0.0384, over 7320.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02962, over 1432512.74 frames.], batch size: 21, lr: 2.28e-04
2022-04-30 16:28:13,475 INFO [train.py:763] (3/8) Epoch 33, batch 3650, loss[loss=0.1676, simple_loss=0.2788, pruned_loss=0.02818, over 6418.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02985, over 1427365.81 frames.], batch size: 38, lr: 2.28e-04
2022-04-30 16:29:20,523 INFO [train.py:763] (3/8) Epoch 33, batch 3700, loss[loss=0.1682, simple_loss=0.2617, pruned_loss=0.03736, over 7241.00 frames.], tot_loss[loss=0.159, simple_loss=0.2584, pruned_loss=0.02979, over 1423014.05 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:30:26,039 INFO [train.py:763] (3/8) Epoch 33, batch 3750, loss[loss=0.1551, simple_loss=0.262, pruned_loss=0.02413, over 7278.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2587, pruned_loss=0.03001, over 1420463.69 frames.], batch size: 24, lr: 2.28e-04
2022-04-30 16:31:31,699 INFO [train.py:763] (3/8) Epoch 33, batch 3800, loss[loss=0.1646, simple_loss=0.2721, pruned_loss=0.02859, over 7142.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2591, pruned_loss=0.02962, over 1424895.05 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:32:38,580 INFO [train.py:763] (3/8) Epoch 33, batch 3850, loss[loss=0.1804, simple_loss=0.2758, pruned_loss=0.04247, over 7220.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2589, pruned_loss=0.02999, over 1427445.03 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:33:45,460 INFO [train.py:763] (3/8) Epoch 33, batch 3900, loss[loss=0.1816, simple_loss=0.2811, pruned_loss=0.04109, over 7198.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2596, pruned_loss=0.03027, over 1425365.19 frames.], batch size: 23, lr: 2.28e-04
2022-04-30 16:34:52,420 INFO [train.py:763] (3/8) Epoch 33, batch 3950, loss[loss=0.1441, simple_loss=0.2573, pruned_loss=0.01543, over 7326.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2595, pruned_loss=0.02999, over 1422624.54 frames.], batch size: 20, lr: 2.28e-04
2022-04-30 16:35:59,190 INFO [train.py:763] (3/8) Epoch 33, batch 4000, loss[loss=0.1699, simple_loss=0.2601, pruned_loss=0.03979, over 7075.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2598, pruned_loss=0.03033, over 1423098.46 frames.], batch size: 18, lr: 2.28e-04
2022-04-30 16:37:13,141 INFO [train.py:763] (3/8) Epoch 33, batch 4050, loss[loss=0.1762, simple_loss=0.2782, pruned_loss=0.03711, over 7205.00 frames.], tot_loss[loss=0.161, simple_loss=0.2608, pruned_loss=0.03065, over 1417280.04 frames.], batch size: 26, lr: 2.27e-04
2022-04-30 16:38:27,100 INFO [train.py:763] (3/8) Epoch 33, batch 4100, loss[loss=0.1773, simple_loss=0.2823, pruned_loss=0.03619, over 6342.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2608, pruned_loss=0.03085, over 1417799.14 frames.], batch size: 37, lr: 2.27e-04
2022-04-30 16:39:41,392 INFO [train.py:763] (3/8) Epoch 33, batch 4150, loss[loss=0.1474, simple_loss=0.2471, pruned_loss=0.02381, over 7404.00 frames.], tot_loss[loss=0.161, simple_loss=0.2606, pruned_loss=0.03073, over 1417525.86 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:40:55,329 INFO [train.py:763] (3/8) Epoch 33, batch 4200, loss[loss=0.148, simple_loss=0.2529, pruned_loss=0.02156, over 7234.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2614, pruned_loss=0.03062, over 1419982.01 frames.], batch size: 20, lr: 2.27e-04
2022-04-30 16:42:02,047 INFO [train.py:763] (3/8) Epoch 33, batch 4250, loss[loss=0.1364, simple_loss=0.2257, pruned_loss=0.02362, over 7146.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2612, pruned_loss=0.03071, over 1420065.98 frames.], batch size: 17, lr: 2.27e-04
2022-04-30 16:43:17,917 INFO [train.py:763] (3/8) Epoch 33, batch 4300, loss[loss=0.1419, simple_loss=0.2312, pruned_loss=0.02631, over 6990.00 frames.], tot_loss[loss=0.1617, simple_loss=0.262, pruned_loss=0.03071, over 1420887.39 frames.], batch size: 16, lr: 2.27e-04
2022-04-30 16:44:24,670 INFO [train.py:763] (3/8) Epoch 33, batch 4350, loss[loss=0.1261, simple_loss=0.2165, pruned_loss=0.01789, over 6762.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2627, pruned_loss=0.03097, over 1415794.42 frames.], batch size: 15, lr: 2.27e-04
2022-04-30 16:45:48,493 INFO [train.py:763] (3/8) Epoch 33, batch 4400, loss[loss=0.1376, simple_loss=0.2364, pruned_loss=0.01938, over 7150.00 frames.], tot_loss[loss=0.162, simple_loss=0.2623, pruned_loss=0.03089, over 1415965.52 frames.], batch size: 18, lr: 2.27e-04
2022-04-30 16:46:53,553 INFO [train.py:763] (3/8) Epoch 33, batch 4450, loss[loss=0.1586, simple_loss=0.2611, pruned_loss=0.02803, over 7208.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2627, pruned_loss=0.03124, over 1402176.61 frames.], batch size: 23, lr: 2.27e-04
2022-04-30 16:48:00,201 INFO [train.py:763] (3/8) Epoch 33, batch 4500, loss[loss=0.2092, simple_loss=0.3009, pruned_loss=0.05869, over 5156.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2621, pruned_loss=0.03136, over 1393300.05 frames.], batch size: 52, lr: 2.27e-04
2022-04-30 16:49:05,829 INFO [train.py:763] (3/8) Epoch 33, batch 4550, loss[loss=0.1779, simple_loss=0.2822, pruned_loss=0.03683, over 5116.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2638, pruned_loss=0.03197, over 1351844.91 frames.], batch size: 52, lr: 2.27e-04
2022-04-30 16:50:25,381 INFO [train.py:763] (3/8) Epoch 34, batch 0, loss[loss=0.1635, simple_loss=0.2693, pruned_loss=0.02883, over 7229.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2693, pruned_loss=0.02883, over 7229.00 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:51:31,603 INFO [train.py:763] (3/8) Epoch 34, batch 50, loss[loss=0.1894, simple_loss=0.287, pruned_loss=0.04591, over 7289.00 frames.], tot_loss[loss=0.1634, simple_loss=0.264, pruned_loss=0.03143, over 318876.94 frames.], batch size: 24, lr: 2.24e-04
2022-04-30 16:52:37,603 INFO [train.py:763] (3/8) Epoch 34, batch 100, loss[loss=0.1807, simple_loss=0.2787, pruned_loss=0.04136, over 7137.00 frames.], tot_loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03037, over 567564.95 frames.], batch size: 26, lr: 2.24e-04
2022-04-30 16:53:43,310 INFO [train.py:763] (3/8) Epoch 34, batch 150, loss[loss=0.1811, simple_loss=0.2744, pruned_loss=0.04391, over 7374.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2596, pruned_loss=0.02991, over 760678.01 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:54:49,445 INFO [train.py:763] (3/8) Epoch 34, batch 200, loss[loss=0.137, simple_loss=0.2322, pruned_loss=0.0209, over 7073.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2588, pruned_loss=0.0298, over 910699.16 frames.], batch size: 18, lr: 2.24e-04
2022-04-30 16:55:56,557 INFO [train.py:763] (3/8) Epoch 34, batch 250, loss[loss=0.1578, simple_loss=0.269, pruned_loss=0.02329, over 7236.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02965, over 1027695.26 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 16:57:03,054 INFO [train.py:763] (3/8) Epoch 34, batch 300, loss[loss=0.1503, simple_loss=0.2628, pruned_loss=0.01887, over 7161.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02965, over 1113716.00 frames.], batch size: 19, lr: 2.24e-04
2022-04-30 16:58:08,943 INFO [train.py:763] (3/8) Epoch 34, batch 350, loss[loss=0.1948, simple_loss=0.287, pruned_loss=0.05132, over 7194.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2592, pruned_loss=0.02924, over 1185518.35 frames.], batch size: 23, lr: 2.24e-04
2022-04-30 16:59:14,464 INFO [train.py:763] (3/8) Epoch 34, batch 400, loss[loss=0.16, simple_loss=0.2665, pruned_loss=0.02677, over 7320.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02936, over 1239665.22 frames.], batch size: 20, lr: 2.24e-04
2022-04-30 17:00:20,067 INFO [train.py:763] (3/8) Epoch 34, batch 450, loss[loss=0.1725, simple_loss=0.2757, pruned_loss=0.03464, over 6864.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02951, over 1284190.53 frames.], batch size: 31, lr: 2.24e-04
2022-04-30 17:01:26,967 INFO [train.py:763] (3/8) Epoch 34, batch 500, loss[loss=0.1534, simple_loss=0.2569, pruned_loss=0.02494, over 7323.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2586, pruned_loss=0.02935, over 1314408.97 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:02:32,703 INFO [train.py:763] (3/8) Epoch 34, batch 550, loss[loss=0.1525, simple_loss=0.2404, pruned_loss=0.03228, over 7057.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2576, pruned_loss=0.0291, over 1335239.30 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:03:38,761 INFO [train.py:763] (3/8) Epoch 34, batch 600, loss[loss=0.1616, simple_loss=0.2725, pruned_loss=0.02542, over 7333.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02974, over 1353613.03 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:04:44,665 INFO [train.py:763] (3/8) Epoch 34, batch 650, loss[loss=0.1457, simple_loss=0.2427, pruned_loss=0.02441, over 7167.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02933, over 1372259.00 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:05:50,798 INFO [train.py:763] (3/8) Epoch 34, batch 700, loss[loss=0.1486, simple_loss=0.2392, pruned_loss=0.02906, over 7285.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.0296, over 1386476.42 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:06:58,021 INFO [train.py:763] (3/8) Epoch 34, batch 750, loss[loss=0.1471, simple_loss=0.2386, pruned_loss=0.02782, over 7255.00 frames.], tot_loss[loss=0.159, simple_loss=0.2587, pruned_loss=0.02967, over 1394503.44 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:08:04,369 INFO [train.py:763] (3/8) Epoch 34, batch 800, loss[loss=0.1604, simple_loss=0.2689, pruned_loss=0.02591, over 7211.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.02971, over 1403251.50 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:09:09,694 INFO [train.py:763] (3/8) Epoch 34, batch 850, loss[loss=0.1734, simple_loss=0.2788, pruned_loss=0.03396, over 7286.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02947, over 1403716.61 frames.], batch size: 24, lr: 2.23e-04
2022-04-30 17:10:15,267 INFO [train.py:763] (3/8) Epoch 34, batch 900, loss[loss=0.1712, simple_loss=0.2756, pruned_loss=0.03337, over 5062.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2597, pruned_loss=0.02933, over 1407283.18 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:11:21,215 INFO [train.py:763] (3/8) Epoch 34, batch 950, loss[loss=0.1665, simple_loss=0.26, pruned_loss=0.03646, over 7252.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02934, over 1410282.32 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:12:27,417 INFO [train.py:763] (3/8) Epoch 34, batch 1000, loss[loss=0.1903, simple_loss=0.2876, pruned_loss=0.04646, over 6739.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02966, over 1411710.04 frames.], batch size: 31, lr: 2.23e-04
2022-04-30 17:13:34,598 INFO [train.py:763] (3/8) Epoch 34, batch 1050, loss[loss=0.1622, simple_loss=0.2576, pruned_loss=0.03336, over 7416.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02947, over 1416122.99 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:14:40,067 INFO [train.py:763] (3/8) Epoch 34, batch 1100, loss[loss=0.1619, simple_loss=0.2616, pruned_loss=0.03115, over 7363.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02957, over 1420143.48 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:15:45,150 INFO [train.py:763] (3/8) Epoch 34, batch 1150, loss[loss=0.1628, simple_loss=0.2619, pruned_loss=0.03188, over 7225.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02937, over 1422465.94 frames.], batch size: 23, lr: 2.23e-04
2022-04-30 17:16:50,471 INFO [train.py:763] (3/8) Epoch 34, batch 1200, loss[loss=0.1381, simple_loss=0.2365, pruned_loss=0.01988, over 7280.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02924, over 1425488.16 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:17:56,081 INFO [train.py:763] (3/8) Epoch 34, batch 1250, loss[loss=0.1786, simple_loss=0.2875, pruned_loss=0.03488, over 7332.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02959, over 1424333.70 frames.], batch size: 22, lr: 2.23e-04
2022-04-30 17:19:02,072 INFO [train.py:763] (3/8) Epoch 34, batch 1300, loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02985, over 7038.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03007, over 1419850.78 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:20:07,320 INFO [train.py:763] (3/8) Epoch 34, batch 1350, loss[loss=0.1628, simple_loss=0.2687, pruned_loss=0.02841, over 7182.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2617, pruned_loss=0.03052, over 1423281.46 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:21:12,465 INFO [train.py:763] (3/8) Epoch 34, batch 1400, loss[loss=0.144, simple_loss=0.2569, pruned_loss=0.0156, over 7321.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2617, pruned_loss=0.03061, over 1421380.39 frames.], batch size: 20, lr: 2.23e-04
2022-04-30 17:22:17,959 INFO [train.py:763] (3/8) Epoch 34, batch 1450, loss[loss=0.1672, simple_loss=0.2585, pruned_loss=0.03797, over 7254.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2616, pruned_loss=0.0309, over 1419473.00 frames.], batch size: 19, lr: 2.23e-04
2022-04-30 17:23:24,434 INFO [train.py:763] (3/8) Epoch 34, batch 1500, loss[loss=0.1487, simple_loss=0.2453, pruned_loss=0.02607, over 7147.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2611, pruned_loss=0.03033, over 1420425.32 frames.], batch size: 17, lr: 2.23e-04
2022-04-30 17:24:29,698 INFO [train.py:763] (3/8) Epoch 34, batch 1550, loss[loss=0.1789, simple_loss=0.286, pruned_loss=0.03585, over 7220.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2615, pruned_loss=0.03013, over 1420549.05 frames.], batch size: 21, lr: 2.23e-04
2022-04-30 17:25:36,476 INFO [train.py:763] (3/8) Epoch 34, batch 1600, loss[loss=0.1622, simple_loss=0.2659, pruned_loss=0.0292, over 7081.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2611, pruned_loss=0.02992, over 1422993.39 frames.], batch size: 28, lr: 2.23e-04
2022-04-30 17:26:43,359 INFO [train.py:763] (3/8) Epoch 34, batch 1650, loss[loss=0.148, simple_loss=0.2474, pruned_loss=0.02429, over 7408.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02944, over 1427716.01 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:27:48,837 INFO [train.py:763] (3/8) Epoch 34, batch 1700, loss[loss=0.1791, simple_loss=0.2739, pruned_loss=0.04215, over 5049.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2601, pruned_loss=0.02965, over 1426289.22 frames.], batch size: 52, lr: 2.23e-04
2022-04-30 17:28:54,322 INFO [train.py:763] (3/8) Epoch 34, batch 1750, loss[loss=0.1535, simple_loss=0.2454, pruned_loss=0.0308, over 7161.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.02959, over 1426149.01 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:29:59,723 INFO [train.py:763] (3/8) Epoch 34, batch 1800, loss[loss=0.1559, simple_loss=0.258, pruned_loss=0.0269, over 7274.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2588, pruned_loss=0.02918, over 1430465.44 frames.], batch size: 25, lr: 2.23e-04
2022-04-30 17:31:04,985 INFO [train.py:763] (3/8) Epoch 34, batch 1850, loss[loss=0.1632, simple_loss=0.2531, pruned_loss=0.03661, over 7053.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02926, over 1426356.18 frames.], batch size: 18, lr: 2.23e-04
2022-04-30 17:32:10,318 INFO [train.py:763] (3/8) Epoch 34, batch 1900, loss[loss=0.1924, simple_loss=0.2854, pruned_loss=0.04965, over 7377.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.02922, over 1425880.47 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:33:15,841 INFO [train.py:763] (3/8) Epoch 34, batch 1950, loss[loss=0.1413, simple_loss=0.2393, pruned_loss=0.02166, over 7180.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2586, pruned_loss=0.0294, over 1424544.27 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:34:22,079 INFO [train.py:763] (3/8) Epoch 34, batch 2000, loss[loss=0.1731, simple_loss=0.2801, pruned_loss=0.03301, over 6502.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2588, pruned_loss=0.0295, over 1420236.95 frames.], batch size: 38, lr: 2.22e-04
2022-04-30 17:35:27,875 INFO [train.py:763] (3/8) Epoch 34, batch 2050, loss[loss=0.1736, simple_loss=0.2696, pruned_loss=0.03883, over 7115.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2591, pruned_loss=0.02987, over 1421169.97 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:36:33,093 INFO [train.py:763] (3/8) Epoch 34, batch 2100, loss[loss=0.1827, simple_loss=0.2842, pruned_loss=0.04061, over 7410.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.02989, over 1424779.34 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:37:40,125 INFO [train.py:763] (3/8) Epoch 34, batch 2150, loss[loss=0.168, simple_loss=0.2794, pruned_loss=0.02833, over 6118.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2594, pruned_loss=0.02974, over 1428074.04 frames.], batch size: 37, lr: 2.22e-04
2022-04-30 17:38:46,195 INFO [train.py:763] (3/8) Epoch 34, batch 2200, loss[loss=0.1683, simple_loss=0.2646, pruned_loss=0.03603, over 7439.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02967, over 1424647.65 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:39:51,384 INFO [train.py:763] (3/8) Epoch 34, batch 2250, loss[loss=0.1783, simple_loss=0.2725, pruned_loss=0.04201, over 7276.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2597, pruned_loss=0.0299, over 1422568.69 frames.], batch size: 18, lr: 2.22e-04
2022-04-30 17:40:56,557 INFO [train.py:763] (3/8) Epoch 34, batch 2300, loss[loss=0.1791, simple_loss=0.2698, pruned_loss=0.04415, over 7112.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2583, pruned_loss=0.02956, over 1419459.09 frames.], batch size: 26, lr: 2.22e-04
2022-04-30 17:42:01,778 INFO [train.py:763] (3/8) Epoch 34, batch 2350, loss[loss=0.1691, simple_loss=0.2746, pruned_loss=0.03178, over 7009.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2586, pruned_loss=0.02962, over 1416956.29 frames.], batch size: 28, lr: 2.22e-04
2022-04-30 17:43:08,020 INFO [train.py:763] (3/8) Epoch 34, batch 2400, loss[loss=0.1515, simple_loss=0.2378, pruned_loss=0.03262, over 7006.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2594, pruned_loss=0.03009, over 1423028.49 frames.], batch size: 16, lr: 2.22e-04
2022-04-30 17:44:15,063 INFO [train.py:763] (3/8) Epoch 34, batch 2450, loss[loss=0.1493, simple_loss=0.255, pruned_loss=0.0218, over 7428.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2585, pruned_loss=0.02949, over 1422804.53 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:45:22,380 INFO [train.py:763] (3/8) Epoch 34, batch 2500, loss[loss=0.1712, simple_loss=0.2821, pruned_loss=0.03013, over 6334.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2592, pruned_loss=0.03019, over 1424453.76 frames.], batch size: 37, lr: 2.22e-04
2022-04-30 17:46:28,712 INFO [train.py:763] (3/8) Epoch 34, batch 2550, loss[loss=0.1578, simple_loss=0.2618, pruned_loss=0.02693, over 7115.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2593, pruned_loss=0.03009, over 1423993.11 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:47:35,756 INFO [train.py:763] (3/8) Epoch 34, batch 2600, loss[loss=0.1676, simple_loss=0.2708, pruned_loss=0.03214, over 7209.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2582, pruned_loss=0.02956, over 1423893.63 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 17:48:40,938 INFO [train.py:763] (3/8) Epoch 34, batch 2650, loss[loss=0.1724, simple_loss=0.2764, pruned_loss=0.03418, over 7194.00 frames.], tot_loss[loss=0.159, simple_loss=0.2585, pruned_loss=0.02973, over 1422751.93 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:49:46,282 INFO [train.py:763] (3/8) Epoch 34, batch 2700, loss[loss=0.165, simple_loss=0.27, pruned_loss=0.03003, over 7116.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2581, pruned_loss=0.02936, over 1424606.70 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:50:51,542 INFO [train.py:763] (3/8) Epoch 34, batch 2750, loss[loss=0.1561, simple_loss=0.2631, pruned_loss=0.02456, over 7310.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2584, pruned_loss=0.0292, over 1424670.36 frames.], batch size: 21, lr: 2.22e-04
2022-04-30 17:51:57,728 INFO [train.py:763] (3/8) Epoch 34, batch 2800, loss[loss=0.1622, simple_loss=0.267, pruned_loss=0.02867, over 7335.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02953, over 1425838.64 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:53:04,498 INFO [train.py:763] (3/8) Epoch 34, batch 2850, loss[loss=0.1768, simple_loss=0.2714, pruned_loss=0.04106, over 7159.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02932, over 1424253.22 frames.], batch size: 19, lr: 2.22e-04
2022-04-30 17:54:11,624 INFO [train.py:763] (3/8) Epoch 34, batch 2900, loss[loss=0.1747, simple_loss=0.2722, pruned_loss=0.03855, over 6347.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2595, pruned_loss=0.02955, over 1423122.79 frames.], batch size: 37, lr: 2.22e-04
2022-04-30 17:55:17,492 INFO [train.py:763] (3/8) Epoch 34, batch 2950, loss[loss=0.1504, simple_loss=0.2437, pruned_loss=0.02852, over 7209.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2604, pruned_loss=0.02966, over 1416940.65 frames.], batch size: 16, lr: 2.22e-04
2022-04-30 17:56:22,955 INFO [train.py:763] (3/8) Epoch 34, batch 3000, loss[loss=0.1844, simple_loss=0.2758, pruned_loss=0.04656, over 7377.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02978, over 1420607.06 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:56:22,956 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 17:56:38,271 INFO [train.py:792] (3/8) Epoch 34, validation: loss=0.1686, simple_loss=0.2638, pruned_loss=0.03669, over 698248.00 frames.
2022-04-30 17:57:44,332 INFO [train.py:763] (3/8) Epoch 34, batch 3050, loss[loss=0.161, simple_loss=0.2612, pruned_loss=0.03041, over 7234.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02996, over 1423449.88 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 17:58:51,170 INFO [train.py:763] (3/8) Epoch 34, batch 3100, loss[loss=0.1807, simple_loss=0.2797, pruned_loss=0.04088, over 7389.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.03, over 1419640.64 frames.], batch size: 23, lr: 2.22e-04
2022-04-30 17:59:56,668 INFO [train.py:763] (3/8) Epoch 34, batch 3150, loss[loss=0.1907, simple_loss=0.2849, pruned_loss=0.04828, over 7215.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2595, pruned_loss=0.03001, over 1422160.35 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:01:02,258 INFO [train.py:763] (3/8) Epoch 34, batch 3200, loss[loss=0.1692, simple_loss=0.2646, pruned_loss=0.03693, over 7198.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2608, pruned_loss=0.03014, over 1427259.20 frames.], batch size: 22, lr: 2.22e-04
2022-04-30 18:02:09,378 INFO [train.py:763] (3/8) Epoch 34, batch 3250, loss[loss=0.153, simple_loss=0.2553, pruned_loss=0.02541, over 7428.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2605, pruned_loss=0.03023, over 1425110.63 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:03:15,760 INFO [train.py:763] (3/8) Epoch 34, batch 3300, loss[loss=0.1571, simple_loss=0.2566, pruned_loss=0.02877, over 7424.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2606, pruned_loss=0.02996, over 1425962.85 frames.], batch size: 20, lr: 2.22e-04
2022-04-30 18:04:21,125 INFO [train.py:763] (3/8) Epoch 34, batch 3350, loss[loss=0.1503, simple_loss=0.2544, pruned_loss=0.02308, over 7428.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03023, over 1429352.29 frames.], batch size: 20, lr: 2.21e-04
2022-04-30 18:05:26,506 INFO [train.py:763] (3/8) Epoch 34, batch 3400, loss[loss=0.1477, simple_loss=0.2475, pruned_loss=0.02391, over 7278.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03017, over 1425674.26 frames.], batch size: 18, lr: 2.21e-04
2022-04-30 18:06:31,935 INFO [train.py:763] (3/8) Epoch 34, batch 3450, loss[loss=0.1308, simple_loss=0.2172, pruned_loss=0.02218, over 6990.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2604, pruned_loss=0.02998, over 1428732.71 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:07:37,464 INFO [train.py:763] (3/8) Epoch 34, batch 3500, loss[loss=0.1568, simple_loss=0.2585, pruned_loss=0.02755, over 7339.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2597, pruned_loss=0.02961, over 1427666.97 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:08:42,509 INFO [train.py:763] (3/8) Epoch 34, batch 3550, loss[loss=0.1624, simple_loss=0.2679, pruned_loss=0.02848, over 6851.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02984, over 1419949.88 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:09:48,190 INFO [train.py:763] (3/8) Epoch 34, batch 3600, loss[loss=0.1601, simple_loss=0.2649, pruned_loss=0.02766, over 7215.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2591, pruned_loss=0.0296, over 1419701.99 frames.], batch size: 22, lr: 2.21e-04
2022-04-30 18:10:55,325 INFO [train.py:763] (3/8) Epoch 34, batch 3650, loss[loss=0.1797, simple_loss=0.285, pruned_loss=0.03722, over 7300.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2605, pruned_loss=0.03, over 1421576.36 frames.], batch size: 25, lr: 2.21e-04
2022-04-30 18:12:01,493 INFO [train.py:763] (3/8) Epoch 34, batch 3700, loss[loss=0.1511, simple_loss=0.2592, pruned_loss=0.02151, over 6334.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2599, pruned_loss=0.02989, over 1421021.68 frames.], batch size: 37, lr: 2.21e-04
2022-04-30 18:13:06,700 INFO [train.py:763] (3/8) Epoch 34, batch 3750, loss[loss=0.1678, simple_loss=0.2596, pruned_loss=0.03803, over 5106.00 frames.], tot_loss[loss=0.16, simple_loss=0.26, pruned_loss=0.02994, over 1418290.97 frames.], batch size: 52, lr: 2.21e-04
2022-04-30 18:14:11,984 INFO [train.py:763] (3/8) Epoch 34, batch 3800, loss[loss=0.1658, simple_loss=0.264, pruned_loss=0.03384, over 6794.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2604, pruned_loss=0.03013, over 1418648.70 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:15:17,334 INFO [train.py:763] (3/8) Epoch 34, batch 3850, loss[loss=0.1771, simple_loss=0.2842, pruned_loss=0.03499, over 7289.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02976, over 1420870.97 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:16:23,810 INFO [train.py:763] (3/8) Epoch 34, batch 3900, loss[loss=0.156, simple_loss=0.2459, pruned_loss=0.03301, over 6808.00 frames.], tot_loss[loss=0.16, simple_loss=0.2603, pruned_loss=0.0299, over 1417288.90 frames.], batch size: 15, lr: 2.21e-04
2022-04-30 18:17:30,967 INFO [train.py:763] (3/8) Epoch 34, batch 3950, loss[loss=0.1372, simple_loss=0.2347, pruned_loss=0.01989, over 7125.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02977, over 1418236.71 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:18:37,952 INFO [train.py:763] (3/8) Epoch 34, batch 4000, loss[loss=0.1549, simple_loss=0.2541, pruned_loss=0.02781, over 6978.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2603, pruned_loss=0.03008, over 1417558.03 frames.], batch size: 16, lr: 2.21e-04
2022-04-30 18:19:54,711 INFO [train.py:763] (3/8) Epoch 34, batch 4050, loss[loss=0.1586, simple_loss=0.274, pruned_loss=0.02164, over 6353.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2605, pruned_loss=0.02966, over 1420150.22 frames.], batch size: 38, lr: 2.21e-04
2022-04-30 18:21:01,772 INFO [train.py:763] (3/8) Epoch 34, batch 4100, loss[loss=0.1519, simple_loss=0.2596, pruned_loss=0.02211, over 7227.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2598, pruned_loss=0.02925, over 1425101.00 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:22:08,649 INFO [train.py:763] (3/8) Epoch 34, batch 4150, loss[loss=0.1834, simple_loss=0.2889, pruned_loss=0.03895, over 7312.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02951, over 1423932.85 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:23:15,039 INFO [train.py:763] (3/8) Epoch 34, batch 4200, loss[loss=0.1733, simple_loss=0.2763, pruned_loss=0.03515, over 7326.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02969, over 1422620.53 frames.], batch size: 21, lr: 2.21e-04
2022-04-30 18:24:20,537 INFO [train.py:763] (3/8) Epoch 34, batch 4250, loss[loss=0.1433, simple_loss=0.2407, pruned_loss=0.02294, over 7273.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2591, pruned_loss=0.02978, over 1427182.20 frames.], batch size: 17, lr: 2.21e-04
2022-04-30 18:25:25,961 INFO [train.py:763] (3/8) Epoch 34, batch 4300, loss[loss=0.1744, simple_loss=0.2685, pruned_loss=0.04017, over 7138.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2585, pruned_loss=0.02987, over 1418246.89 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:26:32,708 INFO [train.py:763] (3/8) Epoch 34, batch 4350, loss[loss=0.1943, simple_loss=0.2993, pruned_loss=0.04459, over 7301.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2588, pruned_loss=0.03028, over 1413608.53 frames.], batch size: 24, lr: 2.21e-04
2022-04-30 18:27:38,204 INFO [train.py:763] (3/8) Epoch 34, batch 4400, loss[loss=0.1421, simple_loss=0.2532, pruned_loss=0.01553, over 7157.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02996, over 1408393.29 frames.], batch size: 19, lr: 2.21e-04
2022-04-30 18:28:42,656 INFO [train.py:763] (3/8) Epoch 34, batch 4450, loss[loss=0.1696, simple_loss=0.282, pruned_loss=0.02859, over 6794.00 frames.], tot_loss[loss=0.1602, simple_loss=0.26, pruned_loss=0.03023, over 1392681.75 frames.], batch size: 31, lr: 2.21e-04
2022-04-30 18:29:47,243 INFO [train.py:763] (3/8) Epoch 34, batch 4500, loss[loss=0.1617, simple_loss=0.2728, pruned_loss=0.02532, over 7166.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2598, pruned_loss=0.02985, over 1378846.70 frames.], batch size: 26, lr: 2.21e-04
2022-04-30 18:30:51,773 INFO [train.py:763] (3/8) Epoch 34, batch 4550, loss[loss=0.193, simple_loss=0.2866, pruned_loss=0.04972, over 4761.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2628, pruned_loss=0.03102, over 1355288.04 frames.], batch size: 52, lr: 2.21e-04
2022-04-30 18:32:11,386 INFO [train.py:763] (3/8) Epoch 35, batch 0, loss[loss=0.1645, simple_loss=0.2697, pruned_loss=0.0297, over 7328.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2697, pruned_loss=0.0297, over 7328.00 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:33:17,373 INFO [train.py:763] (3/8) Epoch 35, batch 50, loss[loss=0.1597, simple_loss=0.2673, pruned_loss=0.02605, over 7433.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2619, pruned_loss=0.03119, over 316265.55 frames.], batch size: 20, lr: 2.18e-04
2022-04-30 18:34:22,751 INFO [train.py:763] (3/8) Epoch 35, batch 100, loss[loss=0.1706, simple_loss=0.2685, pruned_loss=0.03633, over 5436.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02983, over 562432.93 frames.], batch size: 54, lr: 2.17e-04
2022-04-30 18:35:28,401 INFO [train.py:763] (3/8) Epoch 35, batch 150, loss[loss=0.1422, simple_loss=0.2373, pruned_loss=0.02357, over 7232.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2583, pruned_loss=0.02954, over 751609.70 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:36:34,091 INFO [train.py:763] (3/8) Epoch 35, batch 200, loss[loss=0.1562, simple_loss=0.2619, pruned_loss=0.02522, over 7315.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02923, over 901705.24 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:37:50,842 INFO [train.py:763] (3/8) Epoch 35, batch 250, loss[loss=0.1761, simple_loss=0.2674, pruned_loss=0.0424, over 7165.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2583, pruned_loss=0.02918, over 1020418.36 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:38:58,247 INFO [train.py:763] (3/8) Epoch 35, batch 300, loss[loss=0.1584, simple_loss=0.2631, pruned_loss=0.02687, over 7192.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02929, over 1105604.73 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:40:05,544 INFO [train.py:763] (3/8) Epoch 35, batch 350, loss[loss=0.1765, simple_loss=0.2615, pruned_loss=0.04576, over 6821.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02934, over 1174810.45 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:41:12,760 INFO [train.py:763] (3/8) Epoch 35, batch 400, loss[loss=0.1809, simple_loss=0.2789, pruned_loss=0.04145, over 7214.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2606, pruned_loss=0.02952, over 1230852.86 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:42:19,853 INFO [train.py:763] (3/8) Epoch 35, batch 450, loss[loss=0.1886, simple_loss=0.2886, pruned_loss=0.04433, over 7158.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2617, pruned_loss=0.03009, over 1278731.70 frames.], batch size: 26, lr: 2.17e-04
2022-04-30 18:43:25,153 INFO [train.py:763] (3/8) Epoch 35, batch 500, loss[loss=0.1758, simple_loss=0.2868, pruned_loss=0.03239, over 7195.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2619, pruned_loss=0.0299, over 1309313.19 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:44:30,966 INFO [train.py:763] (3/8) Epoch 35, batch 550, loss[loss=0.1676, simple_loss=0.2621, pruned_loss=0.0366, over 7433.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2618, pruned_loss=0.02972, over 1335690.52 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:45:37,226 INFO [train.py:763] (3/8) Epoch 35, batch 600, loss[loss=0.1733, simple_loss=0.2906, pruned_loss=0.028, over 7215.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2614, pruned_loss=0.02958, over 1357913.93 frames.], batch size: 23, lr: 2.17e-04
2022-04-30 18:46:44,898 INFO [train.py:763] (3/8) Epoch 35, batch 650, loss[loss=0.1699, simple_loss=0.2689, pruned_loss=0.0354, over 7144.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02929, over 1372614.58 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:47:52,735 INFO [train.py:763] (3/8) Epoch 35, batch 700, loss[loss=0.164, simple_loss=0.2566, pruned_loss=0.03571, over 7247.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2592, pruned_loss=0.02933, over 1384085.47 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:48:58,271 INFO [train.py:763] (3/8) Epoch 35, batch 750, loss[loss=0.1475, simple_loss=0.2437, pruned_loss=0.02568, over 7330.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2597, pruned_loss=0.02989, over 1385327.83 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 18:50:03,740 INFO [train.py:763] (3/8) Epoch 35, batch 800, loss[loss=0.1719, simple_loss=0.277, pruned_loss=0.03338, over 7401.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02983, over 1392955.30 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:51:09,201 INFO [train.py:763] (3/8) Epoch 35, batch 850, loss[loss=0.1717, simple_loss=0.283, pruned_loss=0.03015, over 7225.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2602, pruned_loss=0.02979, over 1393141.63 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 18:52:23,433 INFO [train.py:763] (3/8) Epoch 35, batch 900, loss[loss=0.1639, simple_loss=0.2627, pruned_loss=0.03256, over 6756.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.0298, over 1400356.90 frames.], batch size: 31, lr: 2.17e-04
2022-04-30 18:53:37,765 INFO [train.py:763] (3/8) Epoch 35, batch 950, loss[loss=0.1393, simple_loss=0.2295, pruned_loss=0.02456, over 6998.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2608, pruned_loss=0.03018, over 1404272.75 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 18:54:42,875 INFO [train.py:763] (3/8) Epoch 35, batch 1000, loss[loss=0.1426, simple_loss=0.2266, pruned_loss=0.0293, over 7281.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2605, pruned_loss=0.03011, over 1406734.61 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 18:55:57,243 INFO [train.py:763] (3/8) Epoch 35, batch 1050, loss[loss=0.1559, simple_loss=0.2546, pruned_loss=0.02865, over 7365.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03019, over 1406432.40 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 18:57:20,298 INFO [train.py:763] (3/8) Epoch 35, batch 1100, loss[loss=0.1848, simple_loss=0.2942, pruned_loss=0.03769, over 7207.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2612, pruned_loss=0.03014, over 1407006.92 frames.], batch size: 22, lr: 2.17e-04
2022-04-30 18:58:25,985 INFO [train.py:763] (3/8) Epoch 35, batch 1150, loss[loss=0.1715, simple_loss=0.2734, pruned_loss=0.03475, over 7265.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2605, pruned_loss=0.02991, over 1412114.08 frames.], batch size: 24, lr: 2.17e-04
2022-04-30 18:59:32,075 INFO [train.py:763] (3/8) Epoch 35, batch 1200, loss[loss=0.1438, simple_loss=0.2357, pruned_loss=0.0259, over 7300.00 frames.], tot_loss[loss=0.161, simple_loss=0.261, pruned_loss=0.0305, over 1408113.15 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:00:55,254 INFO [train.py:763] (3/8) Epoch 35, batch 1250, loss[loss=0.1365, simple_loss=0.2243, pruned_loss=0.0244, over 7011.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2602, pruned_loss=0.03031, over 1410158.39 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:02:00,727 INFO [train.py:763] (3/8) Epoch 35, batch 1300, loss[loss=0.1474, simple_loss=0.2278, pruned_loss=0.03351, over 7143.00 frames.], tot_loss[loss=0.16, simple_loss=0.2598, pruned_loss=0.03008, over 1414546.46 frames.], batch size: 17, lr: 2.17e-04
2022-04-30 19:03:07,765 INFO [train.py:763] (3/8) Epoch 35, batch 1350, loss[loss=0.1525, simple_loss=0.2479, pruned_loss=0.02855, over 7260.00 frames.], tot_loss[loss=0.16, simple_loss=0.2596, pruned_loss=0.03018, over 1419550.22 frames.], batch size: 19, lr: 2.17e-04
2022-04-30 19:04:12,913 INFO [train.py:763] (3/8) Epoch 35, batch 1400, loss[loss=0.1333, simple_loss=0.2276, pruned_loss=0.01946, over 7001.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03004, over 1417806.57 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:05:18,834 INFO [train.py:763] (3/8) Epoch 35, batch 1450, loss[loss=0.1603, simple_loss=0.2463, pruned_loss=0.03714, over 7206.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2595, pruned_loss=0.02975, over 1415492.22 frames.], batch size: 16, lr: 2.17e-04
2022-04-30 19:06:24,726 INFO [train.py:763] (3/8) Epoch 35, batch 1500, loss[loss=0.1476, simple_loss=0.2495, pruned_loss=0.02285, over 7314.00 frames.], tot_loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.02957, over 1418878.75 frames.], batch size: 21, lr: 2.17e-04
2022-04-30 19:07:30,579 INFO [train.py:763] (3/8) Epoch 35, batch 1550, loss[loss=0.1803, simple_loss=0.2836, pruned_loss=0.03855, over 7241.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02915, over 1420657.56 frames.], batch size: 20, lr: 2.17e-04
2022-04-30 19:08:36,017 INFO [train.py:763] (3/8) Epoch 35, batch 1600, loss[loss=0.1832, simple_loss=0.2803, pruned_loss=0.04302, over 7372.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2577, pruned_loss=0.02902, over 1420491.79 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:09:42,622 INFO [train.py:763] (3/8) Epoch 35, batch 1650, loss[loss=0.1477, simple_loss=0.2533, pruned_loss=0.02106, over 7150.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02888, over 1422479.67 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:10:49,570 INFO [train.py:763] (3/8) Epoch 35, batch 1700, loss[loss=0.1871, simple_loss=0.2885, pruned_loss=0.04285, over 7291.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02923, over 1424319.77 frames.], batch size: 25, lr: 2.16e-04
2022-04-30 19:11:56,503 INFO [train.py:763] (3/8) Epoch 35, batch 1750, loss[loss=0.154, simple_loss=0.2451, pruned_loss=0.03145, over 7290.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02945, over 1420572.89 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:13:03,548 INFO [train.py:763] (3/8) Epoch 35, batch 1800, loss[loss=0.1794, simple_loss=0.2878, pruned_loss=0.0355, over 7190.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02971, over 1422077.75 frames.], batch size: 23, lr: 2.16e-04
2022-04-30 19:14:09,379 INFO [train.py:763] (3/8) Epoch 35, batch 1850, loss[loss=0.1729, simple_loss=0.2801, pruned_loss=0.03289, over 7118.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2599, pruned_loss=0.02964, over 1425164.10 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:15:15,198 INFO [train.py:763] (3/8) Epoch 35, batch 1900, loss[loss=0.1758, simple_loss=0.2746, pruned_loss=0.03851, over 6938.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2593, pruned_loss=0.0297, over 1426603.52 frames.], batch size: 32, lr: 2.16e-04
2022-04-30 19:16:21,440 INFO [train.py:763] (3/8) Epoch 35, batch 1950, loss[loss=0.1526, simple_loss=0.2506, pruned_loss=0.02735, over 7232.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2589, pruned_loss=0.02991, over 1424273.05 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:17:27,460 INFO [train.py:763] (3/8) Epoch 35, batch 2000, loss[loss=0.139, simple_loss=0.2313, pruned_loss=0.02341, over 7010.00 frames.], tot_loss[loss=0.16, simple_loss=0.2601, pruned_loss=0.02998, over 1421089.06 frames.], batch size: 16, lr: 2.16e-04
2022-04-30 19:18:34,497 INFO [train.py:763] (3/8) Epoch 35, batch 2050, loss[loss=0.1807, simple_loss=0.2859, pruned_loss=0.03769, over 7312.00 frames.], tot_loss[loss=0.16, simple_loss=0.2605, pruned_loss=0.02978, over 1425593.75 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:19:40,351 INFO [train.py:763] (3/8) Epoch 35, batch 2100, loss[loss=0.1575, simple_loss=0.2585, pruned_loss=0.02823, over 7419.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2594, pruned_loss=0.02939, over 1423932.13 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:20:47,377 INFO [train.py:763] (3/8) Epoch 35, batch 2150, loss[loss=0.1365, simple_loss=0.2335, pruned_loss=0.01979, over 7259.00 frames.], tot_loss[loss=0.159, simple_loss=0.2593, pruned_loss=0.02929, over 1425965.48 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:21:54,059 INFO [train.py:763] (3/8) Epoch 35, batch 2200, loss[loss=0.1319, simple_loss=0.2306, pruned_loss=0.01656, over 7411.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02938, over 1425601.65 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:23:01,264 INFO [train.py:763] (3/8) Epoch 35, batch 2250, loss[loss=0.1598, simple_loss=0.2702, pruned_loss=0.02471, over 7337.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2605, pruned_loss=0.02928, over 1421984.52 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:24:07,985 INFO [train.py:763] (3/8) Epoch 35, batch 2300, loss[loss=0.143, simple_loss=0.2363, pruned_loss=0.02485, over 7127.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.02951, over 1424835.32 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:25:12,949 INFO [train.py:763] (3/8) Epoch 35, batch 2350, loss[loss=0.1871, simple_loss=0.2788, pruned_loss=0.04771, over 5330.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2599, pruned_loss=0.02928, over 1422920.48 frames.], batch size: 53, lr: 2.16e-04
2022-04-30 19:26:18,888 INFO [train.py:763] (3/8) Epoch 35, batch 2400, loss[loss=0.145, simple_loss=0.2299, pruned_loss=0.03003, over 7405.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2593, pruned_loss=0.02901, over 1426243.75 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:27:24,047 INFO [train.py:763] (3/8) Epoch 35, batch 2450, loss[loss=0.1459, simple_loss=0.2491, pruned_loss=0.02133, over 7158.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02909, over 1422382.89 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:28:30,197 INFO [train.py:763] (3/8) Epoch 35, batch 2500, loss[loss=0.15, simple_loss=0.2458, pruned_loss=0.02716, over 7144.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2589, pruned_loss=0.02937, over 1425669.76 frames.], batch size: 20, lr: 2.16e-04
2022-04-30 19:29:36,785 INFO [train.py:763] (3/8) Epoch 35, batch 2550, loss[loss=0.1553, simple_loss=0.2592, pruned_loss=0.02566, over 7349.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2598, pruned_loss=0.02963, over 1422055.51 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:30:41,921 INFO [train.py:763] (3/8) Epoch 35, batch 2600, loss[loss=0.1486, simple_loss=0.2404, pruned_loss=0.02841, over 7155.00 frames.], tot_loss[loss=0.1597, simple_loss=0.26, pruned_loss=0.02969, over 1423282.02 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:31:47,694 INFO [train.py:763] (3/8) Epoch 35, batch 2650, loss[loss=0.2062, simple_loss=0.2964, pruned_loss=0.05805, over 5158.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2605, pruned_loss=0.03019, over 1422209.30 frames.], batch size: 52, lr: 2.16e-04
2022-04-30 19:32:53,212 INFO [train.py:763] (3/8) Epoch 35, batch 2700, loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02974, over 7302.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2603, pruned_loss=0.03032, over 1422520.90 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:33:59,267 INFO [train.py:763] (3/8) Epoch 35, batch 2750, loss[loss=0.1686, simple_loss=0.2741, pruned_loss=0.03161, over 7113.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2597, pruned_loss=0.03007, over 1425479.38 frames.], batch size: 21, lr: 2.16e-04
2022-04-30 19:35:05,456 INFO [train.py:763] (3/8) Epoch 35, batch 2800, loss[loss=0.1677, simple_loss=0.2778, pruned_loss=0.02884, over 7202.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2588, pruned_loss=0.02971, over 1426771.41 frames.], batch size: 22, lr: 2.16e-04
2022-04-30 19:36:12,139 INFO [train.py:763] (3/8) Epoch 35, batch 2850, loss[loss=0.1567, simple_loss=0.2489, pruned_loss=0.03221, over 7263.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2585, pruned_loss=0.02964, over 1427958.84 frames.], batch size: 17, lr: 2.16e-04
2022-04-30 19:37:18,075 INFO [train.py:763] (3/8) Epoch 35, batch 2900, loss[loss=0.148, simple_loss=0.2473, pruned_loss=0.02438, over 7254.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2576, pruned_loss=0.02955, over 1426008.75 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:38:23,360 INFO [train.py:763] (3/8) Epoch 35, batch 2950, loss[loss=0.159, simple_loss=0.2589, pruned_loss=0.0295, over 7162.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2586, pruned_loss=0.02981, over 1424156.14 frames.], batch size: 18, lr: 2.16e-04
2022-04-30 19:39:28,871 INFO [train.py:763] (3/8) Epoch 35, batch 3000, loss[loss=0.1488, simple_loss=0.2482, pruned_loss=0.02472, over 7171.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2596, pruned_loss=0.03005, over 1421832.25 frames.], batch size: 19, lr: 2.16e-04
2022-04-30 19:39:28,872 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 19:39:43,929 INFO [train.py:792] (3/8) Epoch 35, validation: loss=0.1681, simple_loss=0.2634, pruned_loss=0.03644, over 698248.00 frames.
2022-04-30 19:40:49,422 INFO [train.py:763] (3/8) Epoch 35, batch 3050, loss[loss=0.1645, simple_loss=0.2646, pruned_loss=0.03214, over 7306.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2601, pruned_loss=0.03025, over 1424345.60 frames.], batch size: 24, lr: 2.16e-04
2022-04-30 19:41:55,472 INFO [train.py:763] (3/8) Epoch 35, batch 3100, loss[loss=0.1853, simple_loss=0.2864, pruned_loss=0.04206, over 7284.00 frames.], tot_loss[loss=0.1606, simple_loss=0.261, pruned_loss=0.03011, over 1428582.03 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:43:02,576 INFO [train.py:763] (3/8) Epoch 35, batch 3150, loss[loss=0.1614, simple_loss=0.2693, pruned_loss=0.02673, over 7392.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02959, over 1425800.35 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:44:09,427 INFO [train.py:763] (3/8) Epoch 35, batch 3200, loss[loss=0.1576, simple_loss=0.2399, pruned_loss=0.0377, over 7137.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2607, pruned_loss=0.02997, over 1419959.30 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:45:15,566 INFO [train.py:763] (3/8) Epoch 35, batch 3250, loss[loss=0.1746, simple_loss=0.2785, pruned_loss=0.0353, over 5303.00 frames.], tot_loss[loss=0.1607, simple_loss=0.261, pruned_loss=0.03023, over 1417183.25 frames.], batch size: 53, lr: 2.15e-04
2022-04-30 19:46:21,012 INFO [train.py:763] (3/8) Epoch 35, batch 3300, loss[loss=0.1825, simple_loss=0.2874, pruned_loss=0.03884, over 7191.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2611, pruned_loss=0.03017, over 1421059.59 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:47:26,298 INFO [train.py:763] (3/8) Epoch 35, batch 3350, loss[loss=0.1553, simple_loss=0.2526, pruned_loss=0.02899, over 7194.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03044, over 1425307.81 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 19:48:32,226 INFO [train.py:763] (3/8) Epoch 35, batch 3400, loss[loss=0.1451, simple_loss=0.2349, pruned_loss=0.0276, over 7256.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2603, pruned_loss=0.03014, over 1424443.71 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:49:37,621 INFO [train.py:763] (3/8) Epoch 35, batch 3450, loss[loss=0.1271, simple_loss=0.2209, pruned_loss=0.01664, over 7282.00 frames.], tot_loss[loss=0.1603, simple_loss=0.26, pruned_loss=0.03024, over 1422185.56 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 19:50:43,216 INFO [train.py:763] (3/8) Epoch 35, batch 3500, loss[loss=0.1489, simple_loss=0.2499, pruned_loss=0.02395, over 7416.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2593, pruned_loss=0.0298, over 1418737.20 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:51:48,955 INFO [train.py:763] (3/8) Epoch 35, batch 3550, loss[loss=0.157, simple_loss=0.266, pruned_loss=0.024, over 6999.00 frames.], tot_loss[loss=0.159, simple_loss=0.259, pruned_loss=0.02949, over 1421897.16 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 19:52:54,516 INFO [train.py:763] (3/8) Epoch 35, batch 3600, loss[loss=0.1818, simple_loss=0.2767, pruned_loss=0.04342, over 7336.00 frames.], tot_loss[loss=0.1596, simple_loss=0.26, pruned_loss=0.02966, over 1420861.00 frames.], batch size: 25, lr: 2.15e-04
2022-04-30 19:54:00,481 INFO [train.py:763] (3/8) Epoch 35, batch 3650, loss[loss=0.1656, simple_loss=0.2738, pruned_loss=0.02872, over 7291.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02978, over 1422400.57 frames.], batch size: 24, lr: 2.15e-04
2022-04-30 19:55:05,899 INFO [train.py:763] (3/8) Epoch 35, batch 3700, loss[loss=0.1492, simple_loss=0.2569, pruned_loss=0.02076, over 7107.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.0298, over 1425164.83 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 19:56:11,431 INFO [train.py:763] (3/8) Epoch 35, batch 3750, loss[loss=0.163, simple_loss=0.2703, pruned_loss=0.02787, over 7332.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2597, pruned_loss=0.02979, over 1424568.56 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 19:57:16,644 INFO [train.py:763] (3/8) Epoch 35, batch 3800, loss[loss=0.1483, simple_loss=0.2481, pruned_loss=0.02423, over 7358.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2606, pruned_loss=0.03007, over 1426791.12 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 19:58:21,845 INFO [train.py:763] (3/8) Epoch 35, batch 3850, loss[loss=0.1561, simple_loss=0.2495, pruned_loss=0.03129, over 6997.00 frames.], tot_loss[loss=0.1609, simple_loss=0.261, pruned_loss=0.03037, over 1423640.06 frames.], batch size: 16, lr: 2.15e-04
2022-04-30 19:59:27,366 INFO [train.py:763] (3/8) Epoch 35, batch 3900, loss[loss=0.1691, simple_loss=0.275, pruned_loss=0.03158, over 7205.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2602, pruned_loss=0.03015, over 1425166.82 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:00:33,656 INFO [train.py:763] (3/8) Epoch 35, batch 3950, loss[loss=0.1786, simple_loss=0.2842, pruned_loss=0.0365, over 6795.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2607, pruned_loss=0.03019, over 1423405.70 frames.], batch size: 31, lr: 2.15e-04
2022-04-30 20:01:41,042 INFO [train.py:763] (3/8) Epoch 35, batch 4000, loss[loss=0.167, simple_loss=0.2676, pruned_loss=0.03325, over 7044.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.0304, over 1423676.68 frames.], batch size: 28, lr: 2.15e-04
2022-04-30 20:02:46,170 INFO [train.py:763] (3/8) Epoch 35, batch 4050, loss[loss=0.1747, simple_loss=0.2793, pruned_loss=0.03502, over 7216.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2613, pruned_loss=0.0302, over 1426331.82 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:03:51,645 INFO [train.py:763] (3/8) Epoch 35, batch 4100, loss[loss=0.1397, simple_loss=0.2362, pruned_loss=0.02161, over 7126.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2608, pruned_loss=0.02993, over 1426277.05 frames.], batch size: 17, lr: 2.15e-04
2022-04-30 20:04:57,464 INFO [train.py:763] (3/8) Epoch 35, batch 4150, loss[loss=0.1739, simple_loss=0.2901, pruned_loss=0.02882, over 7199.00 frames.], tot_loss[loss=0.1598, simple_loss=0.26, pruned_loss=0.02981, over 1418597.31 frames.], batch size: 23, lr: 2.15e-04
2022-04-30 20:06:03,149 INFO [train.py:763] (3/8) Epoch 35, batch 4200, loss[loss=0.1515, simple_loss=0.243, pruned_loss=0.03007, over 7242.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02948, over 1416658.84 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:07:09,099 INFO [train.py:763] (3/8) Epoch 35, batch 4250, loss[loss=0.1721, simple_loss=0.271, pruned_loss=0.0366, over 7218.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2598, pruned_loss=0.0298, over 1415988.29 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:08:14,296 INFO [train.py:763] (3/8) Epoch 35, batch 4300, loss[loss=0.1606, simple_loss=0.2576, pruned_loss=0.03184, over 7201.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2594, pruned_loss=0.02994, over 1411796.02 frames.], batch size: 22, lr: 2.15e-04
2022-04-30 20:09:20,406 INFO [train.py:763] (3/8) Epoch 35, batch 4350, loss[loss=0.1654, simple_loss=0.265, pruned_loss=0.03292, over 7439.00 frames.], tot_loss[loss=0.159, simple_loss=0.2584, pruned_loss=0.02977, over 1410400.34 frames.], batch size: 20, lr: 2.15e-04
2022-04-30 20:10:26,456 INFO [train.py:763] (3/8) Epoch 35, batch 4400, loss[loss=0.1357, simple_loss=0.2272, pruned_loss=0.02215, over 7351.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2573, pruned_loss=0.02925, over 1414809.52 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:11:33,064 INFO [train.py:763] (3/8) Epoch 35, batch 4450, loss[loss=0.1507, simple_loss=0.2534, pruned_loss=0.02405, over 7213.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2571, pruned_loss=0.02921, over 1405657.58 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:12:39,697 INFO [train.py:763] (3/8) Epoch 35, batch 4500, loss[loss=0.1864, simple_loss=0.2845, pruned_loss=0.04417, over 7228.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2578, pruned_loss=0.02953, over 1394622.77 frames.], batch size: 21, lr: 2.15e-04
2022-04-30 20:13:46,221 INFO [train.py:763] (3/8) Epoch 35, batch 4550, loss[loss=0.1352, simple_loss=0.2381, pruned_loss=0.01613, over 7255.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2587, pruned_loss=0.03011, over 1355543.76 frames.], batch size: 19, lr: 2.15e-04
2022-04-30 20:15:13,845 INFO [train.py:763] (3/8) Epoch 36, batch 0, loss[loss=0.1573, simple_loss=0.2615, pruned_loss=0.02661, over 7328.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2615, pruned_loss=0.02661, over 7328.00 frames.], batch size: 22, lr: 2.12e-04
2022-04-30 20:16:19,179 INFO [train.py:763] (3/8) Epoch 36, batch 50, loss[loss=0.1588, simple_loss=0.2628, pruned_loss=0.02743, over 7070.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2618, pruned_loss=0.03178, over 321531.10 frames.], batch size: 18, lr: 2.12e-04
2022-04-30 20:17:24,380 INFO [train.py:763] (3/8) Epoch 36, batch 100, loss[loss=0.1367, simple_loss=0.242, pruned_loss=0.01564, over 7348.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2623, pruned_loss=0.03127, over 566770.16 frames.], batch size: 20, lr: 2.12e-04
2022-04-30 20:18:29,496 INFO [train.py:763] (3/8) Epoch 36, batch 150, loss[loss=0.1913, simple_loss=0.2908, pruned_loss=0.04596, over 7035.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2618, pruned_loss=0.03017, over 753994.98 frames.], batch size: 28, lr: 2.11e-04
2022-04-30 20:19:34,474 INFO [train.py:763] (3/8) Epoch 36, batch 200, loss[loss=0.1419, simple_loss=0.248, pruned_loss=0.01791, over 7317.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2638, pruned_loss=0.03021, over 905753.24 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:20:39,730 INFO [train.py:763] (3/8) Epoch 36, batch 250, loss[loss=0.1521, simple_loss=0.2454, pruned_loss=0.02941, over 7253.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2621, pruned_loss=0.03012, over 1017295.48 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:21:45,225 INFO [train.py:763] (3/8) Epoch 36, batch 300, loss[loss=0.1834, simple_loss=0.2915, pruned_loss=0.03761, over 7317.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2618, pruned_loss=0.03001, over 1103815.24 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:22:50,516 INFO [train.py:763] (3/8) Epoch 36, batch 350, loss[loss=0.1485, simple_loss=0.2459, pruned_loss=0.0256, over 7179.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2617, pruned_loss=0.02995, over 1172276.81 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:23:55,933 INFO [train.py:763] (3/8) Epoch 36, batch 400, loss[loss=0.1655, simple_loss=0.273, pruned_loss=0.02896, over 7222.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2609, pruned_loss=0.0299, over 1231807.61 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:25:01,047 INFO [train.py:763] (3/8) Epoch 36, batch 450, loss[loss=0.1724, simple_loss=0.2757, pruned_loss=0.03454, over 7145.00 frames.], tot_loss[loss=0.1601, simple_loss=0.261, pruned_loss=0.02963, over 1276152.85 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:26:07,075 INFO [train.py:763] (3/8) Epoch 36, batch 500, loss[loss=0.1593, simple_loss=0.2637, pruned_loss=0.02747, over 7232.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2603, pruned_loss=0.0296, over 1306329.71 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:27:14,406 INFO [train.py:763] (3/8) Epoch 36, batch 550, loss[loss=0.1578, simple_loss=0.2567, pruned_loss=0.02946, over 7071.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2609, pruned_loss=0.02979, over 1321757.82 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:28:22,077 INFO [train.py:763] (3/8) Epoch 36, batch 600, loss[loss=0.1599, simple_loss=0.2592, pruned_loss=0.03028, over 7433.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2595, pruned_loss=0.02945, over 1346692.51 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:29:29,897 INFO [train.py:763] (3/8) Epoch 36, batch 650, loss[loss=0.1373, simple_loss=0.2296, pruned_loss=0.02249, over 7114.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02884, over 1366551.43 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:30:35,969 INFO [train.py:763] (3/8) Epoch 36, batch 700, loss[loss=0.1602, simple_loss=0.2532, pruned_loss=0.03362, over 7235.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2586, pruned_loss=0.02905, over 1380100.00 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:31:41,363 INFO [train.py:763] (3/8) Epoch 36, batch 750, loss[loss=0.1417, simple_loss=0.2388, pruned_loss=0.02226, over 7141.00 frames.], tot_loss[loss=0.1585, simple_loss=0.259, pruned_loss=0.02897, over 1389141.08 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:32:47,557 INFO [train.py:763] (3/8) Epoch 36, batch 800, loss[loss=0.14, simple_loss=0.2321, pruned_loss=0.02393, over 7397.00 frames.], tot_loss[loss=0.1588, simple_loss=0.259, pruned_loss=0.02928, over 1399181.31 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:33:53,517 INFO [train.py:763] (3/8) Epoch 36, batch 850, loss[loss=0.154, simple_loss=0.241, pruned_loss=0.03352, over 7265.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2599, pruned_loss=0.02974, over 1398518.99 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:34:59,125 INFO [train.py:763] (3/8) Epoch 36, batch 900, loss[loss=0.138, simple_loss=0.2438, pruned_loss=0.01604, over 7063.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02909, over 1407184.13 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:36:04,437 INFO [train.py:763] (3/8) Epoch 36, batch 950, loss[loss=0.1464, simple_loss=0.2337, pruned_loss=0.02956, over 7281.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02876, over 1411003.00 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:37:09,731 INFO [train.py:763] (3/8) Epoch 36, batch 1000, loss[loss=0.1816, simple_loss=0.2924, pruned_loss=0.03541, over 6741.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02857, over 1413212.03 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:38:15,275 INFO [train.py:763] (3/8) Epoch 36, batch 1050, loss[loss=0.1572, simple_loss=0.2561, pruned_loss=0.02918, over 7371.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02861, over 1417486.88 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:39:20,504 INFO [train.py:763] (3/8) Epoch 36, batch 1100, loss[loss=0.1615, simple_loss=0.269, pruned_loss=0.02704, over 7221.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02883, over 1419792.70 frames.], batch size: 21, lr: 2.11e-04
2022-04-30 20:40:26,422 INFO [train.py:763] (3/8) Epoch 36, batch 1150, loss[loss=0.1818, simple_loss=0.2775, pruned_loss=0.04307, over 5355.00 frames.], tot_loss[loss=0.158, simple_loss=0.2582, pruned_loss=0.02887, over 1419639.49 frames.], batch size: 52, lr: 2.11e-04
2022-04-30 20:41:32,753 INFO [train.py:763] (3/8) Epoch 36, batch 1200, loss[loss=0.1612, simple_loss=0.2701, pruned_loss=0.02617, over 7143.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2593, pruned_loss=0.02887, over 1421994.96 frames.], batch size: 20, lr: 2.11e-04
2022-04-30 20:42:37,806 INFO [train.py:763] (3/8) Epoch 36, batch 1250, loss[loss=0.1551, simple_loss=0.2575, pruned_loss=0.02632, over 7199.00 frames.], tot_loss[loss=0.159, simple_loss=0.2599, pruned_loss=0.02907, over 1421287.46 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:43:42,980 INFO [train.py:763] (3/8) Epoch 36, batch 1300, loss[loss=0.1465, simple_loss=0.2423, pruned_loss=0.02533, over 7130.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.02941, over 1423852.20 frames.], batch size: 17, lr: 2.11e-04
2022-04-30 20:44:48,209 INFO [train.py:763] (3/8) Epoch 36, batch 1350, loss[loss=0.1544, simple_loss=0.2597, pruned_loss=0.02456, over 7072.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2602, pruned_loss=0.02944, over 1418450.75 frames.], batch size: 18, lr: 2.11e-04
2022-04-30 20:45:54,980 INFO [train.py:763] (3/8) Epoch 36, batch 1400, loss[loss=0.1394, simple_loss=0.2351, pruned_loss=0.0219, over 6988.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2591, pruned_loss=0.02909, over 1417936.17 frames.], batch size: 16, lr: 2.11e-04
2022-04-30 20:47:00,116 INFO [train.py:763] (3/8) Epoch 36, batch 1450, loss[loss=0.1862, simple_loss=0.2786, pruned_loss=0.0469, over 7312.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2598, pruned_loss=0.02937, over 1420447.63 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:48:05,227 INFO [train.py:763] (3/8) Epoch 36, batch 1500, loss[loss=0.1631, simple_loss=0.268, pruned_loss=0.02909, over 7302.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02985, over 1416613.41 frames.], batch size: 24, lr: 2.11e-04
2022-04-30 20:49:10,953 INFO [train.py:763] (3/8) Epoch 36, batch 1550, loss[loss=0.1727, simple_loss=0.2786, pruned_loss=0.03335, over 6838.00 frames.], tot_loss[loss=0.161, simple_loss=0.2611, pruned_loss=0.03046, over 1411561.68 frames.], batch size: 31, lr: 2.11e-04
2022-04-30 20:50:16,847 INFO [train.py:763] (3/8) Epoch 36, batch 1600, loss[loss=0.1844, simple_loss=0.2881, pruned_loss=0.04041, over 7388.00 frames.], tot_loss[loss=0.16, simple_loss=0.2599, pruned_loss=0.03009, over 1412398.16 frames.], batch size: 23, lr: 2.11e-04
2022-04-30 20:51:24,011 INFO [train.py:763] (3/8) Epoch 36, batch 1650, loss[loss=0.1673, simple_loss=0.2649, pruned_loss=0.03489, over 7196.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02978, over 1415428.21 frames.], batch size: 22, lr: 2.11e-04
2022-04-30 20:52:38,229 INFO [train.py:763] (3/8) Epoch 36, batch 1700, loss[loss=0.1597, simple_loss=0.2564, pruned_loss=0.03153, over 7156.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2606, pruned_loss=0.03036, over 1414208.92 frames.], batch size: 19, lr: 2.11e-04
2022-04-30 20:53:43,582 INFO [train.py:763] (3/8) Epoch 36, batch 1750, loss[loss=0.1423, simple_loss=0.2377, pruned_loss=0.02345, over 7355.00 frames.], tot_loss[loss=0.16, simple_loss=0.2595, pruned_loss=0.03025, over 1409412.24 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:54:48,730 INFO [train.py:763] (3/8) Epoch 36, batch 1800, loss[loss=0.1663, simple_loss=0.2705, pruned_loss=0.03108, over 7305.00 frames.], tot_loss[loss=0.1601, simple_loss=0.26, pruned_loss=0.03017, over 1411040.57 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 20:55:54,036 INFO [train.py:763] (3/8) Epoch 36, batch 1850, loss[loss=0.1446, simple_loss=0.2442, pruned_loss=0.02253, over 7269.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2593, pruned_loss=0.0302, over 1411341.25 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 20:56:59,658 INFO [train.py:763] (3/8) Epoch 36, batch 1900, loss[loss=0.1673, simple_loss=0.2859, pruned_loss=0.02433, over 6856.00 frames.], tot_loss[loss=0.16, simple_loss=0.2602, pruned_loss=0.02992, over 1417288.52 frames.], batch size: 31, lr: 2.10e-04
2022-04-30 20:58:07,233 INFO [train.py:763] (3/8) Epoch 36, batch 1950, loss[loss=0.1582, simple_loss=0.2665, pruned_loss=0.02494, over 7210.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02937, over 1420337.93 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 20:59:14,630 INFO [train.py:763] (3/8) Epoch 36, batch 2000, loss[loss=0.1703, simple_loss=0.28, pruned_loss=0.03031, over 7422.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2593, pruned_loss=0.02982, over 1417456.08 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:00:22,193 INFO [train.py:763] (3/8) Epoch 36, batch 2050, loss[loss=0.176, simple_loss=0.2819, pruned_loss=0.03506, over 7238.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2587, pruned_loss=0.02977, over 1420421.59 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:01:28,530 INFO [train.py:763] (3/8) Epoch 36, batch 2100, loss[loss=0.1593, simple_loss=0.268, pruned_loss=0.0253, over 7158.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2592, pruned_loss=0.02975, over 1419916.00 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:02:35,085 INFO [train.py:763] (3/8) Epoch 36, batch 2150, loss[loss=0.1493, simple_loss=0.2533, pruned_loss=0.02268, over 7417.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02939, over 1417589.29 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:03:42,383 INFO [train.py:763] (3/8) Epoch 36, batch 2200, loss[loss=0.1403, simple_loss=0.2344, pruned_loss=0.02311, over 7266.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02892, over 1418910.67 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:04:49,052 INFO [train.py:763] (3/8) Epoch 36, batch 2250, loss[loss=0.1647, simple_loss=0.2742, pruned_loss=0.02762, over 7143.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02923, over 1419878.25 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:05:54,014 INFO [train.py:763] (3/8) Epoch 36, batch 2300, loss[loss=0.1884, simple_loss=0.2854, pruned_loss=0.04566, over 7214.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02899, over 1419315.68 frames.], batch size: 23, lr: 2.10e-04
2022-04-30 21:06:59,112 INFO [train.py:763] (3/8) Epoch 36, batch 2350, loss[loss=0.1465, simple_loss=0.2343, pruned_loss=0.02937, over 7276.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2595, pruned_loss=0.02967, over 1413442.75 frames.], batch size: 17, lr: 2.10e-04
2022-04-30 21:08:06,479 INFO [train.py:763] (3/8) Epoch 36, batch 2400, loss[loss=0.1829, simple_loss=0.2947, pruned_loss=0.03554, over 7334.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02959, over 1419533.36 frames.], batch size: 25, lr: 2.10e-04
2022-04-30 21:09:12,590 INFO [train.py:763] (3/8) Epoch 36, batch 2450, loss[loss=0.1616, simple_loss=0.2585, pruned_loss=0.03236, over 7100.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2585, pruned_loss=0.02938, over 1424876.52 frames.], batch size: 26, lr: 2.10e-04
2022-04-30 21:10:36,029 INFO [train.py:763] (3/8) Epoch 36, batch 2500, loss[loss=0.1392, simple_loss=0.2358, pruned_loss=0.02131, over 7152.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02892, over 1427769.58 frames.], batch size: 19, lr: 2.10e-04
2022-04-30 21:11:41,252 INFO [train.py:763] (3/8) Epoch 36, batch 2550, loss[loss=0.2083, simple_loss=0.3058, pruned_loss=0.05539, over 7290.00 frames.], tot_loss[loss=0.1589, simple_loss=0.259, pruned_loss=0.02935, over 1428918.49 frames.], batch size: 24, lr: 2.10e-04
2022-04-30 21:12:55,222 INFO [train.py:763] (3/8) Epoch 36, batch 2600, loss[loss=0.1476, simple_loss=0.2386, pruned_loss=0.02833, over 7300.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02942, over 1426074.63 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:14:18,382 INFO [train.py:763] (3/8) Epoch 36, batch 2650, loss[loss=0.1818, simple_loss=0.2776, pruned_loss=0.04302, over 7204.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2592, pruned_loss=0.02954, over 1429603.00 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:15:32,420 INFO [train.py:763] (3/8) Epoch 36, batch 2700, loss[loss=0.1441, simple_loss=0.2563, pruned_loss=0.01596, over 6235.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2593, pruned_loss=0.02955, over 1425424.73 frames.], batch size: 37, lr: 2.10e-04
2022-04-30 21:16:46,241 INFO [train.py:763] (3/8) Epoch 36, batch 2750, loss[loss=0.1869, simple_loss=0.2769, pruned_loss=0.04839, over 4999.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02914, over 1425528.53 frames.], batch size: 52, lr: 2.10e-04
2022-04-30 21:17:52,033 INFO [train.py:763] (3/8) Epoch 36, batch 2800, loss[loss=0.1403, simple_loss=0.2329, pruned_loss=0.02389, over 7281.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2591, pruned_loss=0.02935, over 1430444.95 frames.], batch size: 18, lr: 2.10e-04
2022-04-30 21:19:07,513 INFO [train.py:763] (3/8) Epoch 36, batch 2850, loss[loss=0.1616, simple_loss=0.2699, pruned_loss=0.0267, over 6564.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02907, over 1429168.10 frames.], batch size: 37, lr: 2.10e-04
2022-04-30 21:20:12,992 INFO [train.py:763] (3/8) Epoch 36, batch 2900, loss[loss=0.1332, simple_loss=0.2269, pruned_loss=0.01978, over 6998.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.02889, over 1429485.87 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:21:20,751 INFO [train.py:763] (3/8) Epoch 36, batch 2950, loss[loss=0.134, simple_loss=0.2309, pruned_loss=0.01849, over 7430.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02848, over 1425728.89 frames.], batch size: 20, lr: 2.10e-04
2022-04-30 21:22:27,898 INFO [train.py:763] (3/8) Epoch 36, batch 3000, loss[loss=0.1624, simple_loss=0.2683, pruned_loss=0.0282, over 7214.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.0287, over 1422623.08 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:22:27,899 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 21:22:43,065 INFO [train.py:792] (3/8) Epoch 36, validation: loss=0.1683, simple_loss=0.2628, pruned_loss=0.03692, over 698248.00 frames.
2022-04-30 21:23:48,279 INFO [train.py:763] (3/8) Epoch 36, batch 3050, loss[loss=0.1449, simple_loss=0.2307, pruned_loss=0.0296, over 7223.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2588, pruned_loss=0.02896, over 1422226.75 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:24:54,039 INFO [train.py:763] (3/8) Epoch 36, batch 3100, loss[loss=0.1688, simple_loss=0.2683, pruned_loss=0.03464, over 7070.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02935, over 1419562.59 frames.], batch size: 18, lr: 2.10e-04
2022-04-30 21:26:01,266 INFO [train.py:763] (3/8) Epoch 36, batch 3150, loss[loss=0.1298, simple_loss=0.2262, pruned_loss=0.01666, over 6995.00 frames.], tot_loss[loss=0.1587, simple_loss=0.259, pruned_loss=0.02923, over 1418134.28 frames.], batch size: 16, lr: 2.10e-04
2022-04-30 21:27:07,746 INFO [train.py:763] (3/8) Epoch 36, batch 3200, loss[loss=0.1934, simple_loss=0.2799, pruned_loss=0.05344, over 4958.00 frames.], tot_loss[loss=0.1586, simple_loss=0.259, pruned_loss=0.02913, over 1418597.73 frames.], batch size: 52, lr: 2.10e-04
2022-04-30 21:28:14,747 INFO [train.py:763] (3/8) Epoch 36, batch 3250, loss[loss=0.178, simple_loss=0.2813, pruned_loss=0.03733, over 7201.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.0291, over 1417939.40 frames.], batch size: 22, lr: 2.10e-04
2022-04-30 21:29:20,184 INFO [train.py:763] (3/8) Epoch 36, batch 3300, loss[loss=0.1646, simple_loss=0.266, pruned_loss=0.03163, over 7408.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2591, pruned_loss=0.02929, over 1415214.28 frames.], batch size: 21, lr: 2.10e-04
2022-04-30 21:30:25,143 INFO [train.py:763] (3/8) Epoch 36, batch 3350, loss[loss=0.193, simple_loss=0.2817, pruned_loss=0.05213, over 7384.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2602, pruned_loss=0.02956, over 1411407.64 frames.], batch size: 23, lr: 2.09e-04
2022-04-30 21:31:31,784 INFO [train.py:763] (3/8) Epoch 36, batch 3400, loss[loss=0.1481, simple_loss=0.2373, pruned_loss=0.02945, over 7125.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2603, pruned_loss=0.02979, over 1416753.43 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:32:37,218 INFO [train.py:763] (3/8) Epoch 36, batch 3450, loss[loss=0.1364, simple_loss=0.2222, pruned_loss=0.02534, over 7294.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2589, pruned_loss=0.02927, over 1419785.05 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:33:42,449 INFO [train.py:763] (3/8) Epoch 36, batch 3500, loss[loss=0.1511, simple_loss=0.2528, pruned_loss=0.02463, over 7351.00 frames.], tot_loss[loss=0.159, simple_loss=0.2592, pruned_loss=0.02947, over 1417102.91 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:34:47,628 INFO [train.py:763] (3/8) Epoch 36, batch 3550, loss[loss=0.1611, simple_loss=0.2549, pruned_loss=0.03368, over 6826.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02927, over 1414005.13 frames.], batch size: 15, lr: 2.09e-04
2022-04-30 21:35:54,817 INFO [train.py:763] (3/8) Epoch 36, batch 3600, loss[loss=0.1421, simple_loss=0.2355, pruned_loss=0.02432, over 7008.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2579, pruned_loss=0.02902, over 1420337.99 frames.], batch size: 16, lr: 2.09e-04
2022-04-30 21:37:01,773 INFO [train.py:763] (3/8) Epoch 36, batch 3650, loss[loss=0.153, simple_loss=0.2525, pruned_loss=0.02672, over 7151.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02843, over 1422643.51 frames.], batch size: 19, lr: 2.09e-04
2022-04-30 21:38:08,983 INFO [train.py:763] (3/8) Epoch 36, batch 3700, loss[loss=0.1556, simple_loss=0.2559, pruned_loss=0.02766, over 7245.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2578, pruned_loss=0.02876, over 1426011.85 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:39:14,210 INFO [train.py:763] (3/8) Epoch 36, batch 3750, loss[loss=0.1792, simple_loss=0.2692, pruned_loss=0.04458, over 7302.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02906, over 1423449.81 frames.], batch size: 24, lr: 2.09e-04
2022-04-30 21:40:19,602 INFO [train.py:763] (3/8) Epoch 36, batch 3800, loss[loss=0.1472, simple_loss=0.2302, pruned_loss=0.03213, over 7268.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2589, pruned_loss=0.02911, over 1425423.98 frames.], batch size: 17, lr: 2.09e-04
2022-04-30 21:41:25,003 INFO [train.py:763] (3/8) Epoch 36, batch 3850, loss[loss=0.1992, simple_loss=0.2908, pruned_loss=0.05382, over 5271.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2595, pruned_loss=0.02937, over 1424878.29 frames.], batch size: 54, lr: 2.09e-04
2022-04-30 21:42:30,256 INFO [train.py:763] (3/8) Epoch 36, batch 3900, loss[loss=0.1576, simple_loss=0.2704, pruned_loss=0.02246, over 7316.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2586, pruned_loss=0.02919, over 1426814.54 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:43:35,818 INFO [train.py:763] (3/8) Epoch 36, batch 3950, loss[loss=0.1505, simple_loss=0.2421, pruned_loss=0.02942, over 7275.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2589, pruned_loss=0.02943, over 1428451.87 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:44:41,518 INFO [train.py:763] (3/8) Epoch 36, batch 4000, loss[loss=0.1765, simple_loss=0.2742, pruned_loss=0.0394, over 7148.00 frames.], tot_loss[loss=0.159, simple_loss=0.2591, pruned_loss=0.02949, over 1428669.36 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:45:48,399 INFO [train.py:763] (3/8) Epoch 36, batch 4050, loss[loss=0.1604, simple_loss=0.2707, pruned_loss=0.02506, over 7148.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2594, pruned_loss=0.02948, over 1428131.66 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:46:54,632 INFO [train.py:763] (3/8) Epoch 36, batch 4100, loss[loss=0.1822, simple_loss=0.2859, pruned_loss=0.03922, over 7282.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2603, pruned_loss=0.02945, over 1425593.62 frames.], batch size: 25, lr: 2.09e-04
2022-04-30 21:48:00,280 INFO [train.py:763] (3/8) Epoch 36, batch 4150, loss[loss=0.1514, simple_loss=0.2591, pruned_loss=0.02179, over 7213.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2593, pruned_loss=0.02916, over 1426817.02 frames.], batch size: 21, lr: 2.09e-04
2022-04-30 21:49:06,725 INFO [train.py:763] (3/8) Epoch 36, batch 4200, loss[loss=0.1701, simple_loss=0.2826, pruned_loss=0.02876, over 7339.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2588, pruned_loss=0.02887, over 1429022.05 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:50:13,178 INFO [train.py:763] (3/8) Epoch 36, batch 4250, loss[loss=0.1739, simple_loss=0.2791, pruned_loss=0.03434, over 7193.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02885, over 1431533.32 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:51:18,747 INFO [train.py:763] (3/8) Epoch 36, batch 4300, loss[loss=0.1529, simple_loss=0.2615, pruned_loss=0.02222, over 7315.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2594, pruned_loss=0.02881, over 1425320.26 frames.], batch size: 20, lr: 2.09e-04
2022-04-30 21:52:24,304 INFO [train.py:763] (3/8) Epoch 36, batch 4350, loss[loss=0.1606, simple_loss=0.2739, pruned_loss=0.02371, over 7326.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.02892, over 1429536.43 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:53:30,947 INFO [train.py:763] (3/8) Epoch 36, batch 4400, loss[loss=0.173, simple_loss=0.2826, pruned_loss=0.03171, over 7331.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2602, pruned_loss=0.02903, over 1421561.22 frames.], batch size: 22, lr: 2.09e-04
2022-04-30 21:54:38,267 INFO [train.py:763] (3/8) Epoch 36, batch 4450, loss[loss=0.1414, simple_loss=0.2316, pruned_loss=0.02559, over 7416.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2601, pruned_loss=0.02902, over 1420370.03 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:55:43,445 INFO [train.py:763] (3/8) Epoch 36, batch 4500, loss[loss=0.1454, simple_loss=0.2421, pruned_loss=0.02437, over 7292.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02884, over 1415284.81 frames.], batch size: 18, lr: 2.09e-04
2022-04-30 21:56:47,988 INFO [train.py:763] (3/8) Epoch 36, batch 4550, loss[loss=0.1681, simple_loss=0.2707, pruned_loss=0.03274, over 6453.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2608, pruned_loss=0.02972, over 1391457.19 frames.], batch size: 37, lr: 2.09e-04
2022-04-30 21:58:07,231 INFO [train.py:763] (3/8) Epoch 37, batch 0, loss[loss=0.1727, simple_loss=0.2736, pruned_loss=0.03595, over 7357.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2736, pruned_loss=0.03595, over 7357.00 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 21:59:13,879 INFO [train.py:763] (3/8) Epoch 37, batch 50, loss[loss=0.151, simple_loss=0.2578, pruned_loss=0.02213, over 6355.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2558, pruned_loss=0.02754, over 322423.02 frames.], batch size: 37, lr: 2.06e-04
2022-04-30 22:00:20,503 INFO [train.py:763] (3/8) Epoch 37, batch 100, loss[loss=0.1302, simple_loss=0.2315, pruned_loss=0.01443, over 7255.00 frames.], tot_loss[loss=0.156, simple_loss=0.256, pruned_loss=0.02798, over 559896.72 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:01:27,280 INFO [train.py:763] (3/8) Epoch 37, batch 150, loss[loss=0.2041, simple_loss=0.2951, pruned_loss=0.0566, over 7383.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02888, over 747820.24 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:02:34,174 INFO [train.py:763] (3/8) Epoch 37, batch 200, loss[loss=0.152, simple_loss=0.2637, pruned_loss=0.02014, over 7405.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.0286, over 896490.77 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:03:39,629 INFO [train.py:763] (3/8) Epoch 37, batch 250, loss[loss=0.1565, simple_loss=0.247, pruned_loss=0.03302, over 7358.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.0284, over 1015283.67 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:04:45,206 INFO [train.py:763] (3/8) Epoch 37, batch 300, loss[loss=0.1662, simple_loss=0.2723, pruned_loss=0.03008, over 7236.00 frames.], tot_loss[loss=0.158, simple_loss=0.2586, pruned_loss=0.02868, over 1104712.77 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:05:51,655 INFO [train.py:763] (3/8) Epoch 37, batch 350, loss[loss=0.1501, simple_loss=0.2487, pruned_loss=0.02572, over 7259.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2591, pruned_loss=0.02892, over 1172031.12 frames.], batch size: 19, lr: 2.06e-04
2022-04-30 22:06:57,560 INFO [train.py:763] (3/8) Epoch 37, batch 400, loss[loss=0.1396, simple_loss=0.229, pruned_loss=0.02512, over 7279.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2598, pruned_loss=0.02879, over 1232192.49 frames.], batch size: 17, lr: 2.06e-04
2022-04-30 22:08:03,013 INFO [train.py:763] (3/8) Epoch 37, batch 450, loss[loss=0.177, simple_loss=0.2801, pruned_loss=0.03702, over 7106.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2582, pruned_loss=0.02812, over 1275110.27 frames.], batch size: 21, lr: 2.06e-04
2022-04-30 22:09:09,216 INFO [train.py:763] (3/8) Epoch 37, batch 500, loss[loss=0.14, simple_loss=0.2458, pruned_loss=0.01713, over 7288.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02848, over 1311756.58 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:10:16,143 INFO [train.py:763] (3/8) Epoch 37, batch 550, loss[loss=0.1576, simple_loss=0.2588, pruned_loss=0.02821, over 7333.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.0289, over 1335979.40 frames.], batch size: 20, lr: 2.06e-04
2022-04-30 22:11:22,961 INFO [train.py:763] (3/8) Epoch 37, batch 600, loss[loss=0.1645, simple_loss=0.2679, pruned_loss=0.03055, over 7388.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02911, over 1357366.04 frames.], batch size: 23, lr: 2.06e-04
2022-04-30 22:12:30,631 INFO [train.py:763] (3/8) Epoch 37, batch 650, loss[loss=0.1654, simple_loss=0.2789, pruned_loss=0.02598, over 7343.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02909, over 1374174.89 frames.], batch size: 22, lr: 2.06e-04
2022-04-30 22:13:38,153 INFO [train.py:763] (3/8) Epoch 37, batch 700, loss[loss=0.1419, simple_loss=0.244, pruned_loss=0.01993, over 7170.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02878, over 1386843.87 frames.], batch size: 18, lr: 2.06e-04
2022-04-30 22:14:45,728 INFO [train.py:763] (3/8) Epoch 37, batch 750, loss[loss=0.1798, simple_loss=0.2772, pruned_loss=0.04125, over 7397.00 frames.], tot_loss[loss=0.1589, simple_loss=0.26, pruned_loss=0.02893, over 1401265.29 frames.], batch size: 23, lr: 2.05e-04
2022-04-30 22:15:51,453 INFO [train.py:763] (3/8) Epoch 37, batch 800, loss[loss=0.1291, simple_loss=0.2248, pruned_loss=0.01675, over 7402.00 frames.], tot_loss[loss=0.1585, simple_loss=0.26, pruned_loss=0.0285, over 1409107.05 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:16:56,736 INFO [train.py:763] (3/8) Epoch 37, batch 850, loss[loss=0.1417, simple_loss=0.2333, pruned_loss=0.02502, over 7366.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2597, pruned_loss=0.02848, over 1411556.32 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:18:02,418 INFO [train.py:763] (3/8) Epoch 37, batch 900, loss[loss=0.1833, simple_loss=0.2853, pruned_loss=0.04064, over 7292.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2593, pruned_loss=0.02845, over 1413045.61 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:19:07,694 INFO [train.py:763] (3/8) Epoch 37, batch 950, loss[loss=0.1447, simple_loss=0.2379, pruned_loss=0.02576, over 7253.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2602, pruned_loss=0.02898, over 1418169.83 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:20:12,874 INFO [train.py:763] (3/8) Epoch 37, batch 1000, loss[loss=0.1475, simple_loss=0.2551, pruned_loss=0.01989, over 7203.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2604, pruned_loss=0.02943, over 1421200.31 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:21:18,157 INFO [train.py:763] (3/8) Epoch 37, batch 1050, loss[loss=0.1592, simple_loss=0.2589, pruned_loss=0.02972, over 7334.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2607, pruned_loss=0.02946, over 1422162.61 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:22:25,732 INFO [train.py:763] (3/8) Epoch 37, batch 1100, loss[loss=0.1422, simple_loss=0.2356, pruned_loss=0.02435, over 7226.00 frames.], tot_loss[loss=0.16, simple_loss=0.2609, pruned_loss=0.02953, over 1426477.29 frames.], batch size: 16, lr: 2.05e-04
2022-04-30 22:23:31,641 INFO [train.py:763] (3/8) Epoch 37, batch 1150, loss[loss=0.1438, simple_loss=0.2398, pruned_loss=0.02385, over 7256.00 frames.], tot_loss[loss=0.159, simple_loss=0.26, pruned_loss=0.02904, over 1423410.64 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:24:36,965 INFO [train.py:763] (3/8) Epoch 37, batch 1200, loss[loss=0.1606, simple_loss=0.2702, pruned_loss=0.02549, over 7204.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2595, pruned_loss=0.02859, over 1425256.09 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:25:43,865 INFO [train.py:763] (3/8) Epoch 37, batch 1250, loss[loss=0.2086, simple_loss=0.3126, pruned_loss=0.05224, over 6319.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2597, pruned_loss=0.02902, over 1428530.06 frames.], batch size: 37, lr: 2.05e-04
2022-04-30 22:26:50,671 INFO [train.py:763] (3/8) Epoch 37, batch 1300, loss[loss=0.1434, simple_loss=0.2269, pruned_loss=0.02993, over 7281.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2596, pruned_loss=0.02896, over 1427398.29 frames.], batch size: 17, lr: 2.05e-04
2022-04-30 22:27:56,059 INFO [train.py:763] (3/8) Epoch 37, batch 1350, loss[loss=0.1599, simple_loss=0.2652, pruned_loss=0.02735, over 7115.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02882, over 1421532.29 frames.], batch size: 21, lr: 2.05e-04
2022-04-30 22:29:02,059 INFO [train.py:763] (3/8) Epoch 37, batch 1400, loss[loss=0.1593, simple_loss=0.2589, pruned_loss=0.02988, over 7313.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2585, pruned_loss=0.02923, over 1421657.56 frames.], batch size: 24, lr: 2.05e-04
2022-04-30 22:30:07,327 INFO [train.py:763] (3/8) Epoch 37, batch 1450, loss[loss=0.1816, simple_loss=0.2817, pruned_loss=0.04072, over 7189.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2599, pruned_loss=0.02983, over 1425855.30 frames.], batch size: 22, lr: 2.05e-04
2022-04-30 22:31:13,181 INFO [train.py:763] (3/8) Epoch 37, batch 1500, loss[loss=0.1662, simple_loss=0.2709, pruned_loss=0.03073, over 7274.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2593, pruned_loss=0.02946, over 1425683.65 frames.], batch size: 25, lr: 2.05e-04
2022-04-30 22:32:18,520 INFO [train.py:763] (3/8) Epoch 37, batch 1550, loss[loss=0.1637, simple_loss=0.2613, pruned_loss=0.033, over 7231.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2597, pruned_loss=0.02959, over 1422925.90 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:33:23,882 INFO [train.py:763] (3/8) Epoch 37, batch 1600, loss[loss=0.1665, simple_loss=0.2535, pruned_loss=0.03972, over 7267.00 frames.], tot_loss[loss=0.159, simple_loss=0.2595, pruned_loss=0.02919, over 1425799.69 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:34:29,219 INFO [train.py:763] (3/8) Epoch 37, batch 1650, loss[loss=0.1667, simple_loss=0.2689, pruned_loss=0.03224, over 7109.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2594, pruned_loss=0.02905, over 1425491.94 frames.], batch size: 28, lr: 2.05e-04
2022-04-30 22:35:34,591 INFO [train.py:763] (3/8) Epoch 37, batch 1700, loss[loss=0.1407, simple_loss=0.2365, pruned_loss=0.02246, over 7164.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02894, over 1424310.89 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:36:40,244 INFO [train.py:763] (3/8) Epoch 37, batch 1750, loss[loss=0.1717, simple_loss=0.27, pruned_loss=0.03672, over 5103.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02872, over 1422859.98 frames.], batch size: 52, lr: 2.05e-04
2022-04-30 22:37:45,568 INFO [train.py:763] (3/8) Epoch 37, batch 1800, loss[loss=0.1619, simple_loss=0.2638, pruned_loss=0.02999, over 7335.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2572, pruned_loss=0.0283, over 1419690.39 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:38:50,828 INFO [train.py:763] (3/8) Epoch 37, batch 1850, loss[loss=0.1646, simple_loss=0.2704, pruned_loss=0.02943, over 7271.00 frames.], tot_loss[loss=0.1564, simple_loss=0.257, pruned_loss=0.02793, over 1422395.83 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:39:57,179 INFO [train.py:763] (3/8) Epoch 37, batch 1900, loss[loss=0.1595, simple_loss=0.2532, pruned_loss=0.03286, over 6885.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2578, pruned_loss=0.02816, over 1424952.94 frames.], batch size: 15, lr: 2.05e-04
2022-04-30 22:41:04,597 INFO [train.py:763] (3/8) Epoch 37, batch 1950, loss[loss=0.1498, simple_loss=0.2494, pruned_loss=0.02511, over 7259.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2592, pruned_loss=0.02876, over 1427761.63 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:42:12,273 INFO [train.py:763] (3/8) Epoch 37, batch 2000, loss[loss=0.141, simple_loss=0.246, pruned_loss=0.01802, over 7395.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2589, pruned_loss=0.02874, over 1426362.91 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:43:17,401 INFO [train.py:763] (3/8) Epoch 37, batch 2050, loss[loss=0.1587, simple_loss=0.2634, pruned_loss=0.02699, over 7246.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02909, over 1423246.04 frames.], batch size: 19, lr: 2.05e-04
2022-04-30 22:44:22,377 INFO [train.py:763] (3/8) Epoch 37, batch 2100, loss[loss=0.1685, simple_loss=0.2662, pruned_loss=0.03543, over 7182.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2606, pruned_loss=0.02939, over 1418094.64 frames.], batch size: 26, lr: 2.05e-04
2022-04-30 22:45:27,586 INFO [train.py:763] (3/8) Epoch 37, batch 2150, loss[loss=0.1423, simple_loss=0.2374, pruned_loss=0.0236, over 7059.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2603, pruned_loss=0.02928, over 1418239.96 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:46:32,463 INFO [train.py:763] (3/8) Epoch 37, batch 2200, loss[loss=0.1427, simple_loss=0.2361, pruned_loss=0.02468, over 7077.00 frames.], tot_loss[loss=0.1603, simple_loss=0.261, pruned_loss=0.02975, over 1419698.48 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:47:37,561 INFO [train.py:763] (3/8) Epoch 37, batch 2250, loss[loss=0.1579, simple_loss=0.2617, pruned_loss=0.02698, over 6490.00 frames.], tot_loss[loss=0.16, simple_loss=0.2608, pruned_loss=0.0296, over 1418672.76 frames.], batch size: 38, lr: 2.05e-04
2022-04-30 22:48:44,664 INFO [train.py:763] (3/8) Epoch 37, batch 2300, loss[loss=0.1577, simple_loss=0.2439, pruned_loss=0.03575, over 7063.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2608, pruned_loss=0.02954, over 1422756.39 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:49:50,008 INFO [train.py:763] (3/8) Epoch 37, batch 2350, loss[loss=0.1643, simple_loss=0.2644, pruned_loss=0.03209, over 7329.00 frames.], tot_loss[loss=0.16, simple_loss=0.2608, pruned_loss=0.02956, over 1421008.12 frames.], batch size: 20, lr: 2.05e-04
2022-04-30 22:50:55,500 INFO [train.py:763] (3/8) Epoch 37, batch 2400, loss[loss=0.138, simple_loss=0.232, pruned_loss=0.02197, over 7410.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2599, pruned_loss=0.02915, over 1425857.86 frames.], batch size: 18, lr: 2.05e-04
2022-04-30 22:52:02,204 INFO [train.py:763] (3/8) Epoch 37, batch 2450, loss[loss=0.1837, simple_loss=0.2743, pruned_loss=0.0466, over 7326.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2599, pruned_loss=0.0286, over 1428246.96 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:53:07,499 INFO [train.py:763] (3/8) Epoch 37, batch 2500, loss[loss=0.1439, simple_loss=0.2409, pruned_loss=0.02348, over 7168.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2594, pruned_loss=0.02845, over 1428059.21 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:54:13,275 INFO [train.py:763] (3/8) Epoch 37, batch 2550, loss[loss=0.146, simple_loss=0.2399, pruned_loss=0.02608, over 7169.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2589, pruned_loss=0.02833, over 1425310.84 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 22:55:19,537 INFO [train.py:763] (3/8) Epoch 37, batch 2600, loss[loss=0.1462, simple_loss=0.2512, pruned_loss=0.02058, over 7429.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2582, pruned_loss=0.02796, over 1424309.69 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:56:24,704 INFO [train.py:763] (3/8) Epoch 37, batch 2650, loss[loss=0.1659, simple_loss=0.2695, pruned_loss=0.03117, over 7203.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2588, pruned_loss=0.02818, over 1425285.76 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 22:57:30,427 INFO [train.py:763] (3/8) Epoch 37, batch 2700, loss[loss=0.1402, simple_loss=0.2486, pruned_loss=0.01593, over 7231.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2583, pruned_loss=0.02804, over 1424685.05 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 22:58:35,693 INFO [train.py:763] (3/8) Epoch 37, batch 2750, loss[loss=0.1496, simple_loss=0.2471, pruned_loss=0.02605, over 7353.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2584, pruned_loss=0.02821, over 1425909.84 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 22:59:42,057 INFO [train.py:763] (3/8) Epoch 37, batch 2800, loss[loss=0.1934, simple_loss=0.2919, pruned_loss=0.04742, over 7295.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2591, pruned_loss=0.02866, over 1423919.34 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:00:49,137 INFO [train.py:763] (3/8) Epoch 37, batch 2850, loss[loss=0.1424, simple_loss=0.2431, pruned_loss=0.02091, over 7414.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2584, pruned_loss=0.02839, over 1424046.62 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:01:56,134 INFO [train.py:763] (3/8) Epoch 37, batch 2900, loss[loss=0.1349, simple_loss=0.2308, pruned_loss=0.01953, over 7144.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2575, pruned_loss=0.02833, over 1424262.64 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:03:03,258 INFO [train.py:763] (3/8) Epoch 37, batch 2950, loss[loss=0.1293, simple_loss=0.2178, pruned_loss=0.02038, over 7415.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2575, pruned_loss=0.02814, over 1428692.15 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:04:10,181 INFO [train.py:763] (3/8) Epoch 37, batch 3000, loss[loss=0.1928, simple_loss=0.2884, pruned_loss=0.04865, over 7224.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2579, pruned_loss=0.02815, over 1428402.19 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:04:10,182 INFO [train.py:783] (3/8) Computing validation loss
2022-04-30 23:04:25,432 INFO [train.py:792] (3/8) Epoch 37, validation: loss=0.1692, simple_loss=0.2632, pruned_loss=0.03757, over 698248.00 frames.
2022-04-30 23:05:32,515 INFO [train.py:763] (3/8) Epoch 37, batch 3050, loss[loss=0.1396, simple_loss=0.2379, pruned_loss=0.02068, over 7166.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02831, over 1428490.12 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:06:38,292 INFO [train.py:763] (3/8) Epoch 37, batch 3100, loss[loss=0.1637, simple_loss=0.2631, pruned_loss=0.03216, over 7206.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2587, pruned_loss=0.02848, over 1421955.82 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:07:53,027 INFO [train.py:763] (3/8) Epoch 37, batch 3150, loss[loss=0.1887, simple_loss=0.2828, pruned_loss=0.04728, over 7381.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02879, over 1421290.82 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:08:58,933 INFO [train.py:763] (3/8) Epoch 37, batch 3200, loss[loss=0.1642, simple_loss=0.2728, pruned_loss=0.02773, over 7121.00 frames.], tot_loss[loss=0.158, simple_loss=0.2591, pruned_loss=0.02852, over 1425441.10 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:10:06,287 INFO [train.py:763] (3/8) Epoch 37, batch 3250, loss[loss=0.1385, simple_loss=0.2291, pruned_loss=0.02391, over 7302.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2585, pruned_loss=0.02861, over 1426434.58 frames.], batch size: 18, lr: 2.04e-04
2022-04-30 23:11:13,123 INFO [train.py:763] (3/8) Epoch 37, batch 3300, loss[loss=0.1576, simple_loss=0.2614, pruned_loss=0.02689, over 7233.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2582, pruned_loss=0.0287, over 1425789.99 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:12:18,273 INFO [train.py:763] (3/8) Epoch 37, batch 3350, loss[loss=0.1708, simple_loss=0.2786, pruned_loss=0.03144, over 7190.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2595, pruned_loss=0.02911, over 1426325.52 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:13:23,565 INFO [train.py:763] (3/8) Epoch 37, batch 3400, loss[loss=0.1614, simple_loss=0.2646, pruned_loss=0.02908, over 6815.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2591, pruned_loss=0.02879, over 1430310.03 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:14:28,969 INFO [train.py:763] (3/8) Epoch 37, batch 3450, loss[loss=0.1498, simple_loss=0.2583, pruned_loss=0.02065, over 7430.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2592, pruned_loss=0.02882, over 1431417.60 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:15:34,295 INFO [train.py:763] (3/8) Epoch 37, batch 3500, loss[loss=0.1486, simple_loss=0.2506, pruned_loss=0.02327, over 7227.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02863, over 1430596.39 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:16:39,546 INFO [train.py:763] (3/8) Epoch 37, batch 3550, loss[loss=0.1713, simple_loss=0.2739, pruned_loss=0.03438, over 7141.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2593, pruned_loss=0.02856, over 1430871.40 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:17:44,639 INFO [train.py:763] (3/8) Epoch 37, batch 3600, loss[loss=0.1968, simple_loss=0.2913, pruned_loss=0.05113, over 6659.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2601, pruned_loss=0.02907, over 1428919.40 frames.], batch size: 31, lr: 2.04e-04
2022-04-30 23:18:50,217 INFO [train.py:763] (3/8) Epoch 37, batch 3650, loss[loss=0.1694, simple_loss=0.2716, pruned_loss=0.0336, over 7149.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2593, pruned_loss=0.02872, over 1431359.99 frames.], batch size: 28, lr: 2.04e-04
2022-04-30 23:19:55,911 INFO [train.py:763] (3/8) Epoch 37, batch 3700, loss[loss=0.1702, simple_loss=0.2844, pruned_loss=0.02796, over 7278.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02896, over 1422844.46 frames.], batch size: 24, lr: 2.04e-04
2022-04-30 23:21:00,946 INFO [train.py:763] (3/8) Epoch 37, batch 3750, loss[loss=0.1382, simple_loss=0.2425, pruned_loss=0.01699, over 7164.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02883, over 1418805.62 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:22:07,063 INFO [train.py:763] (3/8) Epoch 37, batch 3800, loss[loss=0.144, simple_loss=0.2533, pruned_loss=0.01736, over 7374.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02881, over 1419530.54 frames.], batch size: 23, lr: 2.04e-04
2022-04-30 23:23:12,317 INFO [train.py:763] (3/8) Epoch 37, batch 3850, loss[loss=0.1827, simple_loss=0.2869, pruned_loss=0.03925, over 7111.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02865, over 1422210.25 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:24:18,020 INFO [train.py:763] (3/8) Epoch 37, batch 3900, loss[loss=0.1398, simple_loss=0.2417, pruned_loss=0.01897, over 7328.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.02879, over 1423560.19 frames.], batch size: 20, lr: 2.04e-04
2022-04-30 23:25:32,658 INFO [train.py:763] (3/8) Epoch 37, batch 3950, loss[loss=0.1713, simple_loss=0.2688, pruned_loss=0.03695, over 7214.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2577, pruned_loss=0.02872, over 1418886.63 frames.], batch size: 22, lr: 2.04e-04
2022-04-30 23:26:37,875 INFO [train.py:763] (3/8) Epoch 37, batch 4000, loss[loss=0.1523, simple_loss=0.2548, pruned_loss=0.02485, over 7163.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2576, pruned_loss=0.02859, over 1419402.47 frames.], batch size: 19, lr: 2.04e-04
2022-04-30 23:28:01,969 INFO [train.py:763] (3/8) Epoch 37, batch 4050, loss[loss=0.1419, simple_loss=0.2328, pruned_loss=0.02552, over 7264.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2573, pruned_loss=0.02853, over 1413208.03 frames.], batch size: 17, lr: 2.04e-04
2022-04-30 23:29:07,113 INFO [train.py:763] (3/8) Epoch 37, batch 4100, loss[loss=0.1612, simple_loss=0.2695, pruned_loss=0.02648, over 7212.00 frames.], tot_loss[loss=0.1573, simple_loss=0.258, pruned_loss=0.02835, over 1414994.12 frames.], batch size: 21, lr: 2.04e-04
2022-04-30 23:30:21,706 INFO [train.py:763] (3/8) Epoch 37, batch 4150, loss[loss=0.1458, simple_loss=0.2481, pruned_loss=0.02175, over 7255.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2569, pruned_loss=0.02821, over 1414485.32 frames.], batch size: 19, lr: 2.03e-04
2022-04-30 23:31:36,375 INFO [train.py:763] (3/8) Epoch 37, batch 4200, loss[loss=0.1723, simple_loss=0.2722, pruned_loss=0.03627, over 7289.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2566, pruned_loss=0.02791, over 1415632.61 frames.], batch size: 24, lr: 2.03e-04
2022-04-30 23:32:51,955 INFO [train.py:763] (3/8) Epoch 37, batch 4250, loss[loss=0.1682, simple_loss=0.2756, pruned_loss=0.03036, over 7242.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2575, pruned_loss=0.02851, over 1416191.82 frames.], batch size: 20, lr: 2.03e-04
2022-04-30 23:33:58,664 INFO [train.py:763] (3/8) Epoch 37, batch 4300, loss[loss=0.1824, simple_loss=0.2786, pruned_loss=0.04307, over 4777.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2565, pruned_loss=0.0284, over 1413715.55 frames.], batch size: 52, lr: 2.03e-04
2022-04-30 23:35:04,834 INFO [train.py:763] (3/8) Epoch 37, batch 4350, loss[loss=0.1613, simple_loss=0.2476, pruned_loss=0.03753, over 6998.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2554, pruned_loss=0.02818, over 1415631.46 frames.], batch size: 16, lr: 2.03e-04
2022-04-30 23:36:10,337 INFO [train.py:763] (3/8) Epoch 37, batch 4400, loss[loss=0.1392, simple_loss=0.2328, pruned_loss=0.02282, over 6771.00 frames.], tot_loss[loss=0.155, simple_loss=0.255, pruned_loss=0.0275, over 1416061.03 frames.], batch size: 15, lr: 2.03e-04
2022-04-30 23:37:17,175 INFO [train.py:763] (3/8) Epoch 37, batch 4450, loss[loss=0.1566, simple_loss=0.2531, pruned_loss=0.03006, over 6857.00 frames.], tot_loss[loss=0.1546, simple_loss=0.254, pruned_loss=0.02765, over 1407966.87 frames.], batch size: 15, lr: 2.03e-04
2022-04-30 23:38:22,785 INFO [train.py:763] (3/8) Epoch 37, batch 4500, loss[loss=0.1533, simple_loss=0.2614, pruned_loss=0.0226, over 6401.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2543, pruned_loss=0.02809, over 1382590.92 frames.], batch size: 37, lr: 2.03e-04
2022-04-30 23:39:28,655 INFO [train.py:763] (3/8) Epoch 37, batch 4550, loss[loss=0.1771, simple_loss=0.2696, pruned_loss=0.04225, over 5026.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2539, pruned_loss=0.02852, over 1356862.25 frames.], batch size: 53, lr: 2.03e-04
2022-04-30 23:40:56,595 INFO [train.py:763] (3/8) Epoch 38, batch 0, loss[loss=0.1544, simple_loss=0.2537, pruned_loss=0.0276, over 7266.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2537, pruned_loss=0.0276, over 7266.00 frames.], batch size: 19, lr: 2.01e-04
2022-04-30 23:42:03,204 INFO [train.py:763] (3/8) Epoch 38, batch 50, loss[loss=0.1774, simple_loss=0.2834, pruned_loss=0.03569, over 7151.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2611, pruned_loss=0.02916, over 320683.32 frames.], batch size: 20, lr: 2.01e-04
2022-04-30 23:43:10,050 INFO [train.py:763] (3/8) Epoch 38, batch 100, loss[loss=0.1629, simple_loss=0.2713, pruned_loss=0.02721, over 6725.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2603, pruned_loss=0.02878, over 565749.13 frames.], batch size: 31, lr: 2.01e-04
2022-04-30 23:44:16,790 INFO [train.py:763] (3/8) Epoch 38, batch 150, loss[loss=0.1418, simple_loss=0.2397, pruned_loss=0.02199, over 7159.00 frames.], tot_loss[loss=0.1575, simple_loss=0.258, pruned_loss=0.02847, over 754410.52 frames.], batch size: 18, lr: 2.01e-04
2022-04-30 23:45:22,772 INFO [train.py:763] (3/8) Epoch 38, batch 200, loss[loss=0.16, simple_loss=0.262, pruned_loss=0.02899, over 7444.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2599, pruned_loss=0.02958, over 901541.45 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:46:29,135 INFO [train.py:763] (3/8) Epoch 38, batch 250, loss[loss=0.1576, simple_loss=0.2628, pruned_loss=0.02624, over 6378.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02905, over 1017062.11 frames.], batch size: 37, lr: 2.00e-04
2022-04-30 23:47:35,364 INFO [train.py:763] (3/8) Epoch 38, batch 300, loss[loss=0.1638, simple_loss=0.2583, pruned_loss=0.03461, over 7436.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2588, pruned_loss=0.0289, over 1111971.16 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:48:41,445 INFO [train.py:763] (3/8) Epoch 38, batch 350, loss[loss=0.1667, simple_loss=0.2694, pruned_loss=0.03202, over 7308.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02862, over 1178370.31 frames.], batch size: 24, lr: 2.00e-04
2022-04-30 23:49:47,443 INFO [train.py:763] (3/8) Epoch 38, batch 400, loss[loss=0.1578, simple_loss=0.2689, pruned_loss=0.02335, over 7221.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2592, pruned_loss=0.02906, over 1227908.15 frames.], batch size: 21, lr: 2.00e-04
2022-04-30 23:50:53,870 INFO [train.py:763] (3/8) Epoch 38, batch 450, loss[loss=0.1794, simple_loss=0.2819, pruned_loss=0.03843, over 7190.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2589, pruned_loss=0.02892, over 1273219.62 frames.], batch size: 23, lr: 2.00e-04
2022-04-30 23:52:00,161 INFO [train.py:763] (3/8) Epoch 38, batch 500, loss[loss=0.1703, simple_loss=0.2738, pruned_loss=0.03341, over 7146.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2586, pruned_loss=0.02899, over 1300184.55 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:53:06,413 INFO [train.py:763] (3/8) Epoch 38, batch 550, loss[loss=0.1726, simple_loss=0.2699, pruned_loss=0.03762, over 7432.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02887, over 1325802.79 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:54:12,148 INFO [train.py:763] (3/8) Epoch 38, batch 600, loss[loss=0.1455, simple_loss=0.2482, pruned_loss=0.02139, over 7160.00 frames.], tot_loss[loss=0.158, simple_loss=0.2587, pruned_loss=0.02864, over 1344600.90 frames.], batch size: 18, lr: 2.00e-04
2022-04-30 23:55:17,887 INFO [train.py:763] (3/8) Epoch 38, batch 650, loss[loss=0.1305, simple_loss=0.2178, pruned_loss=0.02157, over 7271.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2579, pruned_loss=0.02825, over 1364330.05 frames.], batch size: 17, lr: 2.00e-04
2022-04-30 23:56:23,409 INFO [train.py:763] (3/8) Epoch 38, batch 700, loss[loss=0.14, simple_loss=0.2246, pruned_loss=0.02775, over 6800.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2571, pruned_loss=0.02836, over 1377018.08 frames.], batch size: 15, lr: 2.00e-04
2022-04-30 23:57:28,960 INFO [train.py:763] (3/8) Epoch 38, batch 750, loss[loss=0.1478, simple_loss=0.2531, pruned_loss=0.02126, over 6350.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2568, pruned_loss=0.02788, over 1386249.83 frames.], batch size: 38, lr: 2.00e-04
2022-04-30 23:58:35,117 INFO [train.py:763] (3/8) Epoch 38, batch 800, loss[loss=0.1691, simple_loss=0.2643, pruned_loss=0.03697, over 7247.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2571, pruned_loss=0.02809, over 1399477.52 frames.], batch size: 20, lr: 2.00e-04
2022-04-30 23:59:41,181 INFO [train.py:763] (3/8) Epoch 38, batch 850, loss[loss=0.1792, simple_loss=0.2877, pruned_loss=0.03538, over 7117.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2568, pruned_loss=0.02797, over 1405484.09 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:00:47,047 INFO [train.py:763] (3/8) Epoch 38, batch 900, loss[loss=0.1507, simple_loss=0.261, pruned_loss=0.02015, over 7413.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.02839, over 1404450.82 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:01:52,979 INFO [train.py:763] (3/8) Epoch 38, batch 950, loss[loss=0.1502, simple_loss=0.2409, pruned_loss=0.02973, over 7127.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2583, pruned_loss=0.02891, over 1405765.68 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:02:58,568 INFO [train.py:763] (3/8) Epoch 38, batch 1000, loss[loss=0.1542, simple_loss=0.2566, pruned_loss=0.02588, over 7352.00 frames.], tot_loss[loss=0.1577, simple_loss=0.258, pruned_loss=0.02871, over 1408728.05 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:04:03,995 INFO [train.py:763] (3/8) Epoch 38, batch 1050, loss[loss=0.1688, simple_loss=0.2725, pruned_loss=0.03253, over 6686.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2574, pruned_loss=0.02875, over 1411522.84 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:05:09,982 INFO [train.py:763] (3/8) Epoch 38, batch 1100, loss[loss=0.1823, simple_loss=0.2853, pruned_loss=0.0396, over 7387.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2577, pruned_loss=0.02921, over 1415597.17 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:06:15,677 INFO [train.py:763] (3/8) Epoch 38, batch 1150, loss[loss=0.1388, simple_loss=0.2378, pruned_loss=0.01988, over 7290.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2567, pruned_loss=0.02881, over 1418933.52 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:07:21,224 INFO [train.py:763] (3/8) Epoch 38, batch 1200, loss[loss=0.1895, simple_loss=0.2912, pruned_loss=0.0439, over 6823.00 frames.], tot_loss[loss=0.158, simple_loss=0.2577, pruned_loss=0.02917, over 1420426.95 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:08:27,091 INFO [train.py:763] (3/8) Epoch 38, batch 1250, loss[loss=0.1602, simple_loss=0.2572, pruned_loss=0.03155, over 7432.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2575, pruned_loss=0.02887, over 1421323.09 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:09:34,184 INFO [train.py:763] (3/8) Epoch 38, batch 1300, loss[loss=0.1369, simple_loss=0.2297, pruned_loss=0.02211, over 7286.00 frames.], tot_loss[loss=0.1572, simple_loss=0.257, pruned_loss=0.02869, over 1425576.84 frames.], batch size: 17, lr: 2.00e-04
2022-05-01 00:10:39,850 INFO [train.py:763] (3/8) Epoch 38, batch 1350, loss[loss=0.1519, simple_loss=0.2548, pruned_loss=0.02453, over 7334.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2574, pruned_loss=0.02868, over 1425530.31 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:11:45,175 INFO [train.py:763] (3/8) Epoch 38, batch 1400, loss[loss=0.1763, simple_loss=0.2687, pruned_loss=0.0419, over 7156.00 frames.], tot_loss[loss=0.157, simple_loss=0.257, pruned_loss=0.02849, over 1425032.02 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:12:50,402 INFO [train.py:763] (3/8) Epoch 38, batch 1450, loss[loss=0.1569, simple_loss=0.2621, pruned_loss=0.02586, over 7294.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02836, over 1425565.95 frames.], batch size: 25, lr: 2.00e-04
2022-05-01 00:13:55,955 INFO [train.py:763] (3/8) Epoch 38, batch 1500, loss[loss=0.1626, simple_loss=0.2711, pruned_loss=0.02706, over 7108.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2572, pruned_loss=0.02854, over 1424164.36 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:15:03,015 INFO [train.py:763] (3/8) Epoch 38, batch 1550, loss[loss=0.173, simple_loss=0.2848, pruned_loss=0.0306, over 7210.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2567, pruned_loss=0.02858, over 1423729.43 frames.], batch size: 22, lr: 2.00e-04
2022-05-01 00:16:09,258 INFO [train.py:763] (3/8) Epoch 38, batch 1600, loss[loss=0.1507, simple_loss=0.2576, pruned_loss=0.02192, over 6748.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2563, pruned_loss=0.02835, over 1426019.39 frames.], batch size: 31, lr: 2.00e-04
2022-05-01 00:17:15,070 INFO [train.py:763] (3/8) Epoch 38, batch 1650, loss[loss=0.148, simple_loss=0.2468, pruned_loss=0.02466, over 7214.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2566, pruned_loss=0.02853, over 1425184.16 frames.], batch size: 21, lr: 2.00e-04
2022-05-01 00:18:31,383 INFO [train.py:763] (3/8) Epoch 38, batch 1700, loss[loss=0.1529, simple_loss=0.2581, pruned_loss=0.02387, over 7062.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02878, over 1427184.93 frames.], batch size: 28, lr: 2.00e-04
2022-05-01 00:19:36,538 INFO [train.py:763] (3/8) Epoch 38, batch 1750, loss[loss=0.1674, simple_loss=0.2725, pruned_loss=0.03113, over 7425.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02892, over 1427693.29 frames.], batch size: 20, lr: 2.00e-04
2022-05-01 00:20:42,262 INFO [train.py:763] (3/8) Epoch 38, batch 1800, loss[loss=0.1557, simple_loss=0.2613, pruned_loss=0.02507, over 7193.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2587, pruned_loss=0.02907, over 1425208.41 frames.], batch size: 23, lr: 2.00e-04
2022-05-01 00:21:47,720 INFO [train.py:763] (3/8) Epoch 38, batch 1850, loss[loss=0.1462, simple_loss=0.2418, pruned_loss=0.02534, over 7155.00 frames.], tot_loss[loss=0.158, simple_loss=0.2581, pruned_loss=0.02889, over 1421870.70 frames.], batch size: 19, lr: 2.00e-04
2022-05-01 00:22:54,646 INFO [train.py:763] (3/8) Epoch 38, batch 1900, loss[loss=0.1452, simple_loss=0.2478, pruned_loss=0.0213, over 7269.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2578, pruned_loss=0.02884, over 1424751.59 frames.], batch size: 18, lr: 2.00e-04
2022-05-01 00:24:00,345 INFO [train.py:763] (3/8) Epoch 38, batch 1950, loss[loss=0.1464, simple_loss=0.2554, pruned_loss=0.01871, over 7318.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02885, over 1424684.75 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:25:06,438 INFO [train.py:763] (3/8) Epoch 38, batch 2000, loss[loss=0.142, simple_loss=0.2435, pruned_loss=0.02023, over 7271.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2585, pruned_loss=0.02914, over 1423762.59 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:26:13,052 INFO [train.py:763] (3/8) Epoch 38, batch 2050, loss[loss=0.1494, simple_loss=0.2478, pruned_loss=0.02552, over 7320.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2597, pruned_loss=0.0294, over 1421709.30 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:27:18,297 INFO [train.py:763] (3/8) Epoch 38, batch 2100, loss[loss=0.1608, simple_loss=0.2544, pruned_loss=0.03361, over 6803.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2589, pruned_loss=0.02899, over 1422278.99 frames.], batch size: 15, lr: 1.99e-04
2022-05-01 00:28:25,362 INFO [train.py:763] (3/8) Epoch 38, batch 2150, loss[loss=0.1442, simple_loss=0.253, pruned_loss=0.01772, over 7271.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2585, pruned_loss=0.029, over 1420255.54 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:29:31,357 INFO [train.py:763] (3/8) Epoch 38, batch 2200, loss[loss=0.1835, simple_loss=0.2845, pruned_loss=0.04119, over 7198.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2588, pruned_loss=0.02909, over 1420788.24 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:30:38,810 INFO [train.py:763] (3/8) Epoch 38, batch 2250, loss[loss=0.1829, simple_loss=0.2855, pruned_loss=0.04018, over 7149.00 frames.], tot_loss[loss=0.158, simple_loss=0.258, pruned_loss=0.02904, over 1423827.03 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:31:44,022 INFO [train.py:763] (3/8) Epoch 38, batch 2300, loss[loss=0.1513, simple_loss=0.2531, pruned_loss=0.02477, over 7162.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2587, pruned_loss=0.02936, over 1423843.80 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:32:50,157 INFO [train.py:763] (3/8) Epoch 38, batch 2350, loss[loss=0.174, simple_loss=0.2729, pruned_loss=0.03761, over 7235.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02888, over 1425884.04 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:33:55,523 INFO [train.py:763] (3/8) Epoch 38, batch 2400, loss[loss=0.1687, simple_loss=0.275, pruned_loss=0.03119, over 7151.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02863, over 1428251.99 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:35:01,018 INFO [train.py:763] (3/8) Epoch 38, batch 2450, loss[loss=0.1256, simple_loss=0.2267, pruned_loss=0.01222, over 7418.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02849, over 1428426.22 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:36:06,993 INFO [train.py:763] (3/8) Epoch 38, batch 2500, loss[loss=0.137, simple_loss=0.2326, pruned_loss=0.02071, over 7403.00 frames.], tot_loss[loss=0.157, simple_loss=0.2574, pruned_loss=0.02826, over 1426594.43 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 00:37:12,684 INFO [train.py:763] (3/8) Epoch 38, batch 2550, loss[loss=0.1534, simple_loss=0.2573, pruned_loss=0.02476, over 7435.00 frames.], tot_loss[loss=0.157, simple_loss=0.2572, pruned_loss=0.02838, over 1431217.28 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:38:18,035 INFO [train.py:763] (3/8) Epoch 38, batch 2600, loss[loss=0.1658, simple_loss=0.2685, pruned_loss=0.03149, over 7152.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2579, pruned_loss=0.02843, over 1429545.60 frames.], batch size: 26, lr: 1.99e-04
2022-05-01 00:39:23,368 INFO [train.py:763] (3/8) Epoch 38, batch 2650, loss[loss=0.1751, simple_loss=0.2796, pruned_loss=0.03535, over 7069.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2582, pruned_loss=0.0288, over 1429982.49 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 00:40:27,511 INFO [train.py:763] (3/8) Epoch 38, batch 2700, loss[loss=0.1645, simple_loss=0.2739, pruned_loss=0.02754, over 7354.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2578, pruned_loss=0.02833, over 1428529.49 frames.], batch size: 25, lr: 1.99e-04
2022-05-01 00:41:33,241 INFO [train.py:763] (3/8) Epoch 38, batch 2750, loss[loss=0.1605, simple_loss=0.2606, pruned_loss=0.03014, over 7158.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02861, over 1428605.95 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:42:38,765 INFO [train.py:763] (3/8) Epoch 38, batch 2800, loss[loss=0.1768, simple_loss=0.2812, pruned_loss=0.03618, over 7335.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2589, pruned_loss=0.02864, over 1425732.62 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:43:44,126 INFO [train.py:763] (3/8) Epoch 38, batch 2850, loss[loss=0.1586, simple_loss=0.2626, pruned_loss=0.02727, over 6345.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2584, pruned_loss=0.02846, over 1425792.91 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:44:49,673 INFO [train.py:763] (3/8) Epoch 38, batch 2900, loss[loss=0.1574, simple_loss=0.2692, pruned_loss=0.0228, over 7321.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02838, over 1425233.84 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:45:55,139 INFO [train.py:763] (3/8) Epoch 38, batch 2950, loss[loss=0.1625, simple_loss=0.258, pruned_loss=0.03355, over 7330.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02844, over 1428485.23 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 00:47:00,414 INFO [train.py:763] (3/8) Epoch 38, batch 3000, loss[loss=0.1581, simple_loss=0.2597, pruned_loss=0.02827, over 7222.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2581, pruned_loss=0.02838, over 1428862.67 frames.], batch size: 20, lr: 1.99e-04
2022-05-01 00:47:00,415 INFO [train.py:783] (3/8) Computing validation loss
2022-05-01 00:47:15,873 INFO [train.py:792] (3/8) Epoch 38, validation: loss=0.1707, simple_loss=0.2648, pruned_loss=0.03834, over 698248.00 frames.
2022-05-01 00:48:21,029 INFO [train.py:763] (3/8) Epoch 38, batch 3050, loss[loss=0.1506, simple_loss=0.2417, pruned_loss=0.02977, over 7125.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2574, pruned_loss=0.02819, over 1426227.32 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:49:26,203 INFO [train.py:763] (3/8) Epoch 38, batch 3100, loss[loss=0.1593, simple_loss=0.2688, pruned_loss=0.0249, over 6456.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02844, over 1418310.65 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:50:31,505 INFO [train.py:763] (3/8) Epoch 38, batch 3150, loss[loss=0.1769, simple_loss=0.2792, pruned_loss=0.03732, over 7416.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2581, pruned_loss=0.02842, over 1423850.82 frames.], batch size: 21, lr: 1.99e-04
2022-05-01 00:51:36,873 INFO [train.py:763] (3/8) Epoch 38, batch 3200, loss[loss=0.1648, simple_loss=0.2651, pruned_loss=0.03226, over 6427.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.0283, over 1424018.22 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:52:42,220 INFO [train.py:763] (3/8) Epoch 38, batch 3250, loss[loss=0.1581, simple_loss=0.2723, pruned_loss=0.02191, over 6437.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2586, pruned_loss=0.02849, over 1423901.62 frames.], batch size: 38, lr: 1.99e-04
2022-05-01 00:53:47,529 INFO [train.py:763] (3/8) Epoch 38, batch 3300, loss[loss=0.1649, simple_loss=0.2687, pruned_loss=0.03051, over 7160.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2584, pruned_loss=0.02832, over 1423746.87 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:54:52,919 INFO [train.py:763] (3/8) Epoch 38, batch 3350, loss[loss=0.1397, simple_loss=0.246, pruned_loss=0.01663, over 7135.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2574, pruned_loss=0.02779, over 1426353.65 frames.], batch size: 17, lr: 1.99e-04
2022-05-01 00:55:59,018 INFO [train.py:763] (3/8) Epoch 38, batch 3400, loss[loss=0.1458, simple_loss=0.2435, pruned_loss=0.02411, over 7364.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2568, pruned_loss=0.02792, over 1427057.24 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:57:06,510 INFO [train.py:763] (3/8) Epoch 38, batch 3450, loss[loss=0.185, simple_loss=0.2856, pruned_loss=0.04218, over 7196.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2573, pruned_loss=0.02842, over 1418597.55 frames.], batch size: 23, lr: 1.99e-04
2022-05-01 00:58:13,607 INFO [train.py:763] (3/8) Epoch 38, batch 3500, loss[loss=0.153, simple_loss=0.2626, pruned_loss=0.02164, over 7153.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2581, pruned_loss=0.02872, over 1419895.00 frames.], batch size: 19, lr: 1.99e-04
2022-05-01 00:59:19,212 INFO [train.py:763] (3/8) Epoch 38, batch 3550, loss[loss=0.1737, simple_loss=0.2821, pruned_loss=0.03265, over 7331.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2582, pruned_loss=0.02898, over 1422387.92 frames.], batch size: 22, lr: 1.99e-04
2022-05-01 01:00:25,362 INFO [train.py:763] (3/8) Epoch 38, batch 3600, loss[loss=0.1413, simple_loss=0.2333, pruned_loss=0.02462, over 7287.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2584, pruned_loss=0.02907, over 1423160.16 frames.], batch size: 18, lr: 1.99e-04
2022-05-01 01:01:30,572 INFO [train.py:763] (3/8) Epoch 38, batch 3650, loss[loss=0.1792, simple_loss=0.2818, pruned_loss=0.03835, over 7021.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2586, pruned_loss=0.02889, over 1425062.29 frames.], batch size: 28, lr: 1.99e-04
2022-05-01 01:02:35,701 INFO [train.py:763] (3/8) Epoch 38, batch 3700, loss[loss=0.1821, simple_loss=0.2866, pruned_loss=0.03876, over 6310.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2585, pruned_loss=0.02864, over 1421763.69 frames.], batch size: 37, lr: 1.99e-04
2022-05-01 01:03:41,345 INFO [train.py:763] (3/8) Epoch 38, batch 3750, loss[loss=0.1689, simple_loss=0.2758, pruned_loss=0.03095, over 7204.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2584, pruned_loss=0.02891, over 1416646.11 frames.], batch size: 23, lr: 1.98e-04
2022-05-01 01:04:46,826 INFO [train.py:763] (3/8) Epoch 38, batch 3800, loss[loss=0.1707, simple_loss=0.2737, pruned_loss=0.03384, over 7359.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02846, over 1422637.93 frames.], batch size: 19, lr: 1.98e-04
2022-05-01 01:05:52,024 INFO [train.py:763] (3/8) Epoch 38, batch 3850, loss[loss=0.2105, simple_loss=0.2915, pruned_loss=0.06473, over 5167.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02849, over 1419467.77 frames.], batch size: 52, lr: 1.98e-04
2022-05-01 01:06:57,232 INFO [train.py:763] (3/8) Epoch 38, batch 3900, loss[loss=0.1776, simple_loss=0.2852, pruned_loss=0.03502, over 7094.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2574, pruned_loss=0.02844, over 1420316.65 frames.], batch size: 28, lr: 1.98e-04
2022-05-01 01:08:02,831 INFO [train.py:763] (3/8) Epoch 38, batch 3950, loss[loss=0.1881, simple_loss=0.2838, pruned_loss=0.04619, over 7339.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02845, over 1422508.85 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:09:08,084 INFO [train.py:763] (3/8) Epoch 38, batch 4000, loss[loss=0.171, simple_loss=0.2762, pruned_loss=0.0329, over 6702.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2576, pruned_loss=0.02842, over 1425165.30 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:10:13,451 INFO [train.py:763] (3/8) Epoch 38, batch 4050, loss[loss=0.1626, simple_loss=0.253, pruned_loss=0.03608, over 6863.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.0285, over 1424221.03 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:11:18,887 INFO [train.py:763] (3/8) Epoch 38, batch 4100, loss[loss=0.1509, simple_loss=0.2557, pruned_loss=0.02305, over 7211.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02872, over 1422695.04 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:12:24,227 INFO [train.py:763] (3/8) Epoch 38, batch 4150, loss[loss=0.1657, simple_loss=0.2734, pruned_loss=0.02902, over 7216.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2575, pruned_loss=0.02865, over 1420787.92 frames.], batch size: 21, lr: 1.98e-04
2022-05-01 01:13:30,534 INFO [train.py:763] (3/8) Epoch 38, batch 4200, loss[loss=0.1761, simple_loss=0.2832, pruned_loss=0.03447, over 6714.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2578, pruned_loss=0.0286, over 1419333.40 frames.], batch size: 31, lr: 1.98e-04
2022-05-01 01:14:35,833 INFO [train.py:763] (3/8) Epoch 38, batch 4250, loss[loss=0.1555, simple_loss=0.2536, pruned_loss=0.02871, over 7154.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2577, pruned_loss=0.02846, over 1416252.71 frames.], batch size: 17, lr: 1.98e-04
2022-05-01 01:15:41,256 INFO [train.py:763] (3/8) Epoch 38, batch 4300, loss[loss=0.1775, simple_loss=0.2782, pruned_loss=0.03835, over 7295.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02877, over 1417296.77 frames.], batch size: 25, lr: 1.98e-04
2022-05-01 01:16:46,654 INFO [train.py:763] (3/8) Epoch 38, batch 4350, loss[loss=0.1597, simple_loss=0.2586, pruned_loss=0.0304, over 7445.00 frames.], tot_loss[loss=0.159, simple_loss=0.2598, pruned_loss=0.02909, over 1413534.62 frames.], batch size: 20, lr: 1.98e-04
2022-05-01 01:17:51,727 INFO [train.py:763] (3/8) Epoch 38, batch 4400, loss[loss=0.1791, simple_loss=0.2882, pruned_loss=0.035, over 7348.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2609, pruned_loss=0.02946, over 1410636.95 frames.], batch size: 22, lr: 1.98e-04
2022-05-01 01:18:57,802 INFO [train.py:763] (3/8) Epoch 38, batch 4450, loss[loss=0.1404, simple_loss=0.2293, pruned_loss=0.02578, over 7401.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2616, pruned_loss=0.02981, over 1398972.29 frames.], batch size: 17, lr: 1.98e-04
2022-05-01 01:20:03,887 INFO [train.py:763] (3/8) Epoch 38, batch 4500, loss[loss=0.1633, simple_loss=0.2575, pruned_loss=0.03461, over 7166.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2623, pruned_loss=0.03014, over 1388161.17 frames.], batch size: 18, lr: 1.98e-04
2022-05-01 01:21:09,321 INFO [train.py:763] (3/8) Epoch 38, batch 4550, loss[loss=0.2226, simple_loss=0.3134, pruned_loss=0.06588, over 5190.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2645, pruned_loss=0.0314, over 1349998.29 frames.], batch size: 52, lr: 1.98e-04
2022-05-01 01:22:39,305 INFO [train.py:763] (3/8) Epoch 39, batch 0, loss[loss=0.2013, simple_loss=0.3123, pruned_loss=0.0451, over 7286.00 frames.], tot_loss[loss=0.2013, simple_loss=0.3123, pruned_loss=0.0451, over 7286.00 frames.], batch size: 24, lr: 1.96e-04
2022-05-01 01:23:45,000 INFO [train.py:763] (3/8) Epoch 39, batch 50, loss[loss=0.1167, simple_loss=0.2082, pruned_loss=0.01264, over 7273.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2611, pruned_loss=0.03094, over 316480.18 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:24:50,353 INFO [train.py:763] (3/8) Epoch 39, batch 100, loss[loss=0.1723, simple_loss=0.2674, pruned_loss=0.03858, over 7355.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2587, pruned_loss=0.02918, over 562105.99 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:25:56,216 INFO [train.py:763] (3/8) Epoch 39, batch 150, loss[loss=0.1692, simple_loss=0.2824, pruned_loss=0.02799, over 7234.00 frames.], tot_loss[loss=0.1574, simple_loss=0.257, pruned_loss=0.02886, over 754518.24 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:27:01,294 INFO [train.py:763] (3/8) Epoch 39, batch 200, loss[loss=0.1451, simple_loss=0.2408, pruned_loss=0.02465, over 7418.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2587, pruned_loss=0.02872, over 903543.54 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:28:06,658 INFO [train.py:763] (3/8) Epoch 39, batch 250, loss[loss=0.1837, simple_loss=0.2786, pruned_loss=0.04438, over 7113.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02863, over 1017189.48 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:29:11,531 INFO [train.py:763] (3/8) Epoch 39, batch 300, loss[loss=0.1608, simple_loss=0.2676, pruned_loss=0.02698, over 7288.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2581, pruned_loss=0.02826, over 1107918.14 frames.], batch size: 24, lr: 1.95e-04
2022-05-01 01:30:16,874 INFO [train.py:763] (3/8) Epoch 39, batch 350, loss[loss=0.1728, simple_loss=0.28, pruned_loss=0.03282, over 7140.00 frames.], tot_loss[loss=0.157, simple_loss=0.2578, pruned_loss=0.02814, over 1171657.01 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:31:22,219 INFO [train.py:763] (3/8) Epoch 39, batch 400, loss[loss=0.1643, simple_loss=0.2671, pruned_loss=0.03074, over 7165.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2589, pruned_loss=0.0285, over 1228455.78 frames.], batch size: 26, lr: 1.95e-04
2022-05-01 01:32:27,453 INFO [train.py:763] (3/8) Epoch 39, batch 450, loss[loss=0.1827, simple_loss=0.2749, pruned_loss=0.04531, over 7307.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2579, pruned_loss=0.02816, over 1272660.16 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:33:32,866 INFO [train.py:763] (3/8) Epoch 39, batch 500, loss[loss=0.1589, simple_loss=0.2636, pruned_loss=0.02713, over 7321.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2575, pruned_loss=0.02797, over 1304841.52 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:34:38,279 INFO [train.py:763] (3/8) Epoch 39, batch 550, loss[loss=0.1528, simple_loss=0.2551, pruned_loss=0.02527, over 7223.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02832, over 1326054.36 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:35:43,497 INFO [train.py:763] (3/8) Epoch 39, batch 600, loss[loss=0.1503, simple_loss=0.2493, pruned_loss=0.02562, over 7256.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2577, pruned_loss=0.02836, over 1348255.80 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:36:48,736 INFO [train.py:763] (3/8) Epoch 39, batch 650, loss[loss=0.1557, simple_loss=0.266, pruned_loss=0.02274, over 7228.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2576, pruned_loss=0.02853, over 1367393.43 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:37:53,923 INFO [train.py:763] (3/8) Epoch 39, batch 700, loss[loss=0.1556, simple_loss=0.2416, pruned_loss=0.03474, over 7293.00 frames.], tot_loss[loss=0.158, simple_loss=0.2583, pruned_loss=0.02885, over 1380293.36 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:38:59,262 INFO [train.py:763] (3/8) Epoch 39, batch 750, loss[loss=0.1519, simple_loss=0.2446, pruned_loss=0.0296, over 7349.00 frames.], tot_loss[loss=0.1578, simple_loss=0.258, pruned_loss=0.02877, over 1385564.79 frames.], batch size: 19, lr: 1.95e-04
2022-05-01 01:40:04,491 INFO [train.py:763] (3/8) Epoch 39, batch 800, loss[loss=0.1629, simple_loss=0.2671, pruned_loss=0.02934, over 7111.00 frames.], tot_loss[loss=0.157, simple_loss=0.2573, pruned_loss=0.02831, over 1394542.77 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:41:18,500 INFO [train.py:763] (3/8) Epoch 39, batch 850, loss[loss=0.1251, simple_loss=0.2187, pruned_loss=0.01571, over 7126.00 frames.], tot_loss[loss=0.157, simple_loss=0.2576, pruned_loss=0.02827, over 1400747.87 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:42:32,264 INFO [train.py:763] (3/8) Epoch 39, batch 900, loss[loss=0.185, simple_loss=0.2921, pruned_loss=0.03892, over 7190.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2585, pruned_loss=0.02836, over 1407436.40 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:43:55,210 INFO [train.py:763] (3/8) Epoch 39, batch 950, loss[loss=0.1615, simple_loss=0.2674, pruned_loss=0.02785, over 5005.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2588, pruned_loss=0.02839, over 1410609.87 frames.], batch size: 52, lr: 1.95e-04
2022-05-01 01:45:01,221 INFO [train.py:763] (3/8) Epoch 39, batch 1000, loss[loss=0.1411, simple_loss=0.2423, pruned_loss=0.01992, over 7112.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2586, pruned_loss=0.0283, over 1409119.19 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:46:06,274 INFO [train.py:763] (3/8) Epoch 39, batch 1050, loss[loss=0.1616, simple_loss=0.2671, pruned_loss=0.02808, over 7212.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2589, pruned_loss=0.02814, over 1408021.28 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 01:47:29,492 INFO [train.py:763] (3/8) Epoch 39, batch 1100, loss[loss=0.1345, simple_loss=0.2331, pruned_loss=0.01796, over 7169.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2589, pruned_loss=0.02827, over 1407158.66 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 01:48:43,941 INFO [train.py:763] (3/8) Epoch 39, batch 1150, loss[loss=0.148, simple_loss=0.2533, pruned_loss=0.02136, over 6732.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2587, pruned_loss=0.02798, over 1414380.09 frames.], batch size: 31, lr: 1.95e-04
2022-05-01 01:49:48,902 INFO [train.py:763] (3/8) Epoch 39, batch 1200, loss[loss=0.1684, simple_loss=0.2761, pruned_loss=0.03036, over 6475.00 frames.], tot_loss[loss=0.158, simple_loss=0.2593, pruned_loss=0.02831, over 1417472.49 frames.], batch size: 38, lr: 1.95e-04
2022-05-01 01:50:54,368 INFO [train.py:763] (3/8) Epoch 39, batch 1250, loss[loss=0.1668, simple_loss=0.274, pruned_loss=0.02979, over 7304.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2588, pruned_loss=0.02832, over 1421820.33 frames.], batch size: 25, lr: 1.95e-04
2022-05-01 01:51:59,439 INFO [train.py:763] (3/8) Epoch 39, batch 1300, loss[loss=0.1723, simple_loss=0.2797, pruned_loss=0.03244, over 7435.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2587, pruned_loss=0.0284, over 1422400.36 frames.], batch size: 20, lr: 1.95e-04
2022-05-01 01:53:04,814 INFO [train.py:763] (3/8) Epoch 39, batch 1350, loss[loss=0.1469, simple_loss=0.2445, pruned_loss=0.02466, over 6286.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2581, pruned_loss=0.02864, over 1421591.83 frames.], batch size: 37, lr: 1.95e-04
2022-05-01 01:54:11,088 INFO [train.py:763] (3/8) Epoch 39, batch 1400, loss[loss=0.1584, simple_loss=0.2679, pruned_loss=0.02443, over 6452.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02862, over 1423261.67 frames.], batch size: 38, lr: 1.95e-04
2022-05-01 01:55:16,351 INFO [train.py:763] (3/8) Epoch 39, batch 1450, loss[loss=0.1714, simple_loss=0.2736, pruned_loss=0.0346, over 7180.00 frames.], tot_loss[loss=0.158, simple_loss=0.2584, pruned_loss=0.0288, over 1424670.21 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:56:21,443 INFO [train.py:763] (3/8) Epoch 39, batch 1500, loss[loss=0.1698, simple_loss=0.2599, pruned_loss=0.03984, over 7142.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2586, pruned_loss=0.02881, over 1425719.46 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 01:57:28,665 INFO [train.py:763] (3/8) Epoch 39, batch 1550, loss[loss=0.1689, simple_loss=0.2783, pruned_loss=0.02974, over 7189.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02866, over 1423492.66 frames.], batch size: 23, lr: 1.95e-04
2022-05-01 01:58:35,228 INFO [train.py:763] (3/8) Epoch 39, batch 1600, loss[loss=0.1629, simple_loss=0.2631, pruned_loss=0.03137, over 7098.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2584, pruned_loss=0.02857, over 1427060.72 frames.], batch size: 28, lr: 1.95e-04
2022-05-01 01:59:41,355 INFO [train.py:763] (3/8) Epoch 39, batch 1650, loss[loss=0.2118, simple_loss=0.2935, pruned_loss=0.06507, over 5002.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2581, pruned_loss=0.02881, over 1421589.77 frames.], batch size: 53, lr: 1.95e-04
2022-05-01 02:00:47,162 INFO [train.py:763] (3/8) Epoch 39, batch 1700, loss[loss=0.1451, simple_loss=0.2359, pruned_loss=0.0272, over 7428.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2588, pruned_loss=0.02926, over 1415145.47 frames.], batch size: 17, lr: 1.95e-04
2022-05-01 02:01:53,359 INFO [train.py:763] (3/8) Epoch 39, batch 1750, loss[loss=0.1667, simple_loss=0.2592, pruned_loss=0.03712, over 7320.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2577, pruned_loss=0.02886, over 1416947.91 frames.], batch size: 21, lr: 1.95e-04
2022-05-01 02:02:58,280 INFO [train.py:763] (3/8) Epoch 39, batch 1800, loss[loss=0.1722, simple_loss=0.2758, pruned_loss=0.0343, over 7350.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2584, pruned_loss=0.02872, over 1418996.96 frames.], batch size: 22, lr: 1.95e-04
2022-05-01 02:04:03,601 INFO [train.py:763] (3/8) Epoch 39, batch 1850, loss[loss=0.1633, simple_loss=0.2575, pruned_loss=0.03448, over 7065.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2582, pruned_loss=0.02852, over 1421898.49 frames.], batch size: 18, lr: 1.95e-04
2022-05-01 02:05:08,883 INFO [train.py:763] (3/8) Epoch 39, batch 1900, loss[loss=0.1663, simple_loss=0.271, pruned_loss=0.03078, over 7175.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2592, pruned_loss=0.02895, over 1425044.45 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:06:14,309 INFO [train.py:763] (3/8) Epoch 39, batch 1950, loss[loss=0.1815, simple_loss=0.2809, pruned_loss=0.04101, over 5053.00 frames.], tot_loss[loss=0.1594, simple_loss=0.26, pruned_loss=0.02947, over 1418894.23 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:07:19,645 INFO [train.py:763] (3/8) Epoch 39, batch 2000, loss[loss=0.1434, simple_loss=0.2387, pruned_loss=0.02404, over 7077.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.02887, over 1422245.93 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:08:24,808 INFO [train.py:763] (3/8) Epoch 39, batch 2050, loss[loss=0.1579, simple_loss=0.2549, pruned_loss=0.03046, over 7426.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2591, pruned_loss=0.02906, over 1426795.19 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:09:30,529 INFO [train.py:763] (3/8) Epoch 39, batch 2100, loss[loss=0.1441, simple_loss=0.2501, pruned_loss=0.01906, over 7386.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2589, pruned_loss=0.02887, over 1424892.22 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:10:35,928 INFO [train.py:763] (3/8) Epoch 39, batch 2150, loss[loss=0.1492, simple_loss=0.254, pruned_loss=0.02216, over 7148.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2599, pruned_loss=0.02944, over 1429008.25 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:11:43,127 INFO [train.py:763] (3/8) Epoch 39, batch 2200, loss[loss=0.188, simple_loss=0.2949, pruned_loss=0.04058, over 7238.00 frames.], tot_loss[loss=0.1584, simple_loss=0.259, pruned_loss=0.0289, over 1431521.35 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:12:48,269 INFO [train.py:763] (3/8) Epoch 39, batch 2250, loss[loss=0.1749, simple_loss=0.2768, pruned_loss=0.03654, over 7191.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2585, pruned_loss=0.02881, over 1429600.59 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:13:53,527 INFO [train.py:763] (3/8) Epoch 39, batch 2300, loss[loss=0.1441, simple_loss=0.2379, pruned_loss=0.02515, over 7444.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2573, pruned_loss=0.02861, over 1425937.65 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:15:00,684 INFO [train.py:763] (3/8) Epoch 39, batch 2350, loss[loss=0.1473, simple_loss=0.2544, pruned_loss=0.02014, over 7337.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2555, pruned_loss=0.0279, over 1426006.81 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:16:07,733 INFO [train.py:763] (3/8) Epoch 39, batch 2400, loss[loss=0.1757, simple_loss=0.2775, pruned_loss=0.03701, over 7194.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2557, pruned_loss=0.02825, over 1427637.58 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:17:13,327 INFO [train.py:763] (3/8) Epoch 39, batch 2450, loss[loss=0.1722, simple_loss=0.2744, pruned_loss=0.03501, over 7029.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2572, pruned_loss=0.02863, over 1422639.85 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:18:19,517 INFO [train.py:763] (3/8) Epoch 39, batch 2500, loss[loss=0.1386, simple_loss=0.242, pruned_loss=0.01759, over 7412.00 frames.], tot_loss[loss=0.157, simple_loss=0.2568, pruned_loss=0.0286, over 1419852.79 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:19:24,721 INFO [train.py:763] (3/8) Epoch 39, batch 2550, loss[loss=0.1648, simple_loss=0.2664, pruned_loss=0.0316, over 7023.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2576, pruned_loss=0.02893, over 1419531.23 frames.], batch size: 28, lr: 1.94e-04
2022-05-01 02:20:31,561 INFO [train.py:763] (3/8) Epoch 39, batch 2600, loss[loss=0.1473, simple_loss=0.2513, pruned_loss=0.02164, over 7334.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2569, pruned_loss=0.02873, over 1419500.74 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:21:37,532 INFO [train.py:763] (3/8) Epoch 39, batch 2650, loss[loss=0.1574, simple_loss=0.2561, pruned_loss=0.02933, over 7157.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2575, pruned_loss=0.02894, over 1421703.99 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:22:43,385 INFO [train.py:763] (3/8) Epoch 39, batch 2700, loss[loss=0.169, simple_loss=0.2681, pruned_loss=0.03498, over 7211.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2583, pruned_loss=0.02929, over 1423331.26 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:23:48,610 INFO [train.py:763] (3/8) Epoch 39, batch 2750, loss[loss=0.1939, simple_loss=0.2945, pruned_loss=0.04667, over 7281.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2579, pruned_loss=0.02871, over 1426418.90 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:24:53,688 INFO [train.py:763] (3/8) Epoch 39, batch 2800, loss[loss=0.156, simple_loss=0.2539, pruned_loss=0.02901, over 7446.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02879, over 1423809.19 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:25:58,654 INFO [train.py:763] (3/8) Epoch 39, batch 2850, loss[loss=0.1483, simple_loss=0.2492, pruned_loss=0.02368, over 6207.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2591, pruned_loss=0.02891, over 1420161.60 frames.], batch size: 37, lr: 1.94e-04
2022-05-01 02:27:03,579 INFO [train.py:763] (3/8) Epoch 39, batch 2900, loss[loss=0.1321, simple_loss=0.2254, pruned_loss=0.01943, over 7059.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2584, pruned_loss=0.02837, over 1420392.32 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:28:08,499 INFO [train.py:763] (3/8) Epoch 39, batch 2950, loss[loss=0.1692, simple_loss=0.2712, pruned_loss=0.0336, over 7272.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2596, pruned_loss=0.02848, over 1420358.81 frames.], batch size: 24, lr: 1.94e-04
2022-05-01 02:29:13,387 INFO [train.py:763] (3/8) Epoch 39, batch 3000, loss[loss=0.1883, simple_loss=0.293, pruned_loss=0.04185, over 7337.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2606, pruned_loss=0.02925, over 1414262.11 frames.], batch size: 22, lr: 1.94e-04
2022-05-01 02:29:13,388 INFO [train.py:783] (3/8) Computing validation loss
2022-05-01 02:29:28,415 INFO [train.py:792] (3/8) Epoch 39, validation: loss=0.1688, simple_loss=0.2638, pruned_loss=0.03694, over 698248.00 frames.
2022-05-01 02:30:33,956 INFO [train.py:763] (3/8) Epoch 39, batch 3050, loss[loss=0.1544, simple_loss=0.2555, pruned_loss=0.02666, over 7354.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2599, pruned_loss=0.0289, over 1416498.66 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:31:41,152 INFO [train.py:763] (3/8) Epoch 39, batch 3100, loss[loss=0.1753, simple_loss=0.2754, pruned_loss=0.03757, over 7205.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2605, pruned_loss=0.02908, over 1418318.01 frames.], batch size: 26, lr: 1.94e-04
2022-05-01 02:32:47,801 INFO [train.py:763] (3/8) Epoch 39, batch 3150, loss[loss=0.1621, simple_loss=0.2743, pruned_loss=0.02498, over 7140.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2604, pruned_loss=0.02916, over 1421845.30 frames.], batch size: 20, lr: 1.94e-04
2022-05-01 02:33:53,385 INFO [train.py:763] (3/8) Epoch 39, batch 3200, loss[loss=0.1616, simple_loss=0.2528, pruned_loss=0.03522, over 4938.00 frames.], tot_loss[loss=0.159, simple_loss=0.26, pruned_loss=0.02896, over 1421749.70 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:34:58,487 INFO [train.py:763] (3/8) Epoch 39, batch 3250, loss[loss=0.1804, simple_loss=0.2838, pruned_loss=0.03849, over 7391.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2604, pruned_loss=0.02868, over 1420649.12 frames.], batch size: 23, lr: 1.94e-04
2022-05-01 02:36:03,618 INFO [train.py:763] (3/8) Epoch 39, batch 3300, loss[loss=0.1731, simple_loss=0.2794, pruned_loss=0.03339, over 7121.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2593, pruned_loss=0.02873, over 1419692.84 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:37:08,799 INFO [train.py:763] (3/8) Epoch 39, batch 3350, loss[loss=0.1633, simple_loss=0.2665, pruned_loss=0.02999, over 7127.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2593, pruned_loss=0.0287, over 1417770.21 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:38:14,797 INFO [train.py:763] (3/8) Epoch 39, batch 3400, loss[loss=0.1535, simple_loss=0.2588, pruned_loss=0.0241, over 7162.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2579, pruned_loss=0.02832, over 1418769.83 frames.], batch size: 19, lr: 1.94e-04
2022-05-01 02:39:20,469 INFO [train.py:763] (3/8) Epoch 39, batch 3450, loss[loss=0.1181, simple_loss=0.2069, pruned_loss=0.01462, over 7270.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2586, pruned_loss=0.02863, over 1417213.60 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:40:25,650 INFO [train.py:763] (3/8) Epoch 39, batch 3500, loss[loss=0.1597, simple_loss=0.2647, pruned_loss=0.02737, over 7325.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2594, pruned_loss=0.02886, over 1418675.41 frames.], batch size: 21, lr: 1.94e-04
2022-05-01 02:41:31,487 INFO [train.py:763] (3/8) Epoch 39, batch 3550, loss[loss=0.1376, simple_loss=0.2356, pruned_loss=0.01977, over 7056.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2582, pruned_loss=0.02861, over 1420502.99 frames.], batch size: 18, lr: 1.94e-04
2022-05-01 02:42:37,765 INFO [train.py:763] (3/8) Epoch 39, batch 3600, loss[loss=0.1564, simple_loss=0.2553, pruned_loss=0.02879, over 5134.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.02833, over 1416756.44 frames.], batch size: 52, lr: 1.94e-04
2022-05-01 02:43:44,822 INFO [train.py:763] (3/8) Epoch 39, batch 3650, loss[loss=0.1713, simple_loss=0.2721, pruned_loss=0.03521, over 6328.00 frames.], tot_loss[loss=0.157, simple_loss=0.2578, pruned_loss=0.02812, over 1418601.39 frames.], batch size: 37, lr: 1.94e-04
2022-05-01 02:44:50,053 INFO [train.py:763] (3/8) Epoch 39, batch 3700, loss[loss=0.1546, simple_loss=0.2476, pruned_loss=0.03079, over 7130.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2582, pruned_loss=0.02813, over 1422702.79 frames.], batch size: 17, lr: 1.94e-04
2022-05-01 02:45:55,095 INFO [train.py:763] (3/8) Epoch 39, batch 3750, loss[loss=0.1692, simple_loss=0.2604, pruned_loss=0.03903, over 7345.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2591, pruned_loss=0.0286, over 1420050.77 frames.], batch size: 19, lr: 1.93e-04
2022-05-01 02:47:00,705 INFO [train.py:763] (3/8) Epoch 39, batch 3800, loss[loss=0.148, simple_loss=0.2435, pruned_loss=0.02627, over 6996.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2592, pruned_loss=0.02866, over 1424154.47 frames.], batch size: 16, lr: 1.93e-04
2022-05-01 02:48:07,767 INFO [train.py:763] (3/8) Epoch 39, batch 3850, loss[loss=0.164, simple_loss=0.2756, pruned_loss=0.02625, over 7418.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2583, pruned_loss=0.02847, over 1420293.51 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:49:13,630 INFO [train.py:763] (3/8) Epoch 39, batch 3900, loss[loss=0.1776, simple_loss=0.2764, pruned_loss=0.03943, over 7199.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2588, pruned_loss=0.02867, over 1421035.98 frames.], batch size: 23, lr: 1.93e-04
2022-05-01 02:50:20,006 INFO [train.py:763] (3/8) Epoch 39, batch 3950, loss[loss=0.1454, simple_loss=0.2367, pruned_loss=0.02703, over 7057.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2583, pruned_loss=0.02878, over 1416631.30 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:51:25,345 INFO [train.py:763] (3/8) Epoch 39, batch 4000, loss[loss=0.1432, simple_loss=0.2314, pruned_loss=0.02745, over 7147.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2581, pruned_loss=0.02856, over 1416198.52 frames.], batch size: 17, lr: 1.93e-04
2022-05-01 02:52:30,794 INFO [train.py:763] (3/8) Epoch 39, batch 4050, loss[loss=0.15, simple_loss=0.2589, pruned_loss=0.02057, over 7214.00 frames.], tot_loss[loss=0.158, simple_loss=0.2585, pruned_loss=0.02877, over 1420752.86 frames.], batch size: 22, lr: 1.93e-04
2022-05-01 02:53:35,944 INFO [train.py:763] (3/8) Epoch 39, batch 4100, loss[loss=0.1572, simple_loss=0.2597, pruned_loss=0.0273, over 7224.00 frames.], tot_loss[loss=0.1574, simple_loss=0.258, pruned_loss=0.02842, over 1421163.02 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 02:54:41,369 INFO [train.py:763] (3/8) Epoch 39, batch 4150, loss[loss=0.1519, simple_loss=0.2467, pruned_loss=0.02859, over 7266.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2578, pruned_loss=0.0284, over 1423140.76 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:55:46,808 INFO [train.py:763] (3/8) Epoch 39, batch 4200, loss[loss=0.1519, simple_loss=0.248, pruned_loss=0.02785, over 7163.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2579, pruned_loss=0.02854, over 1423945.93 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:56:52,115 INFO [train.py:763] (3/8) Epoch 39, batch 4250, loss[loss=0.1527, simple_loss=0.2582, pruned_loss=0.02357, over 7317.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2578, pruned_loss=0.02847, over 1419379.12 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 02:57:57,422 INFO [train.py:763] (3/8) Epoch 39, batch 4300, loss[loss=0.1304, simple_loss=0.229, pruned_loss=0.01588, over 7169.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2577, pruned_loss=0.02871, over 1419000.58 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 02:59:02,811 INFO [train.py:763] (3/8) Epoch 39, batch 4350, loss[loss=0.1576, simple_loss=0.2507, pruned_loss=0.03226, over 7328.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2572, pruned_loss=0.02844, over 1420377.66 frames.], batch size: 20, lr: 1.93e-04
2022-05-01 03:00:09,027 INFO [train.py:763] (3/8) Epoch 39, batch 4400, loss[loss=0.154, simple_loss=0.2604, pruned_loss=0.0238, over 6684.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2578, pruned_loss=0.0283, over 1420320.41 frames.], batch size: 31, lr: 1.93e-04
2022-05-01 03:01:14,004 INFO [train.py:763] (3/8) Epoch 39, batch 4450, loss[loss=0.1611, simple_loss=0.256, pruned_loss=0.03313, over 7159.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2577, pruned_loss=0.02832, over 1408928.97 frames.], batch size: 18, lr: 1.93e-04
2022-05-01 03:02:19,220 INFO [train.py:763] (3/8) Epoch 39, batch 4500, loss[loss=0.1713, simple_loss=0.2817, pruned_loss=0.03041, over 7223.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2584, pruned_loss=0.02857, over 1401367.61 frames.], batch size: 21, lr: 1.93e-04
2022-05-01 03:03:25,868 INFO [train.py:763] (3/8) Epoch 39, batch 4550, loss[loss=0.1364, simple_loss=0.2311, pruned_loss=0.02087, over 7259.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2558, pruned_loss=0.02835, over 1392088.26 frames.], batch size: 16, lr: 1.93e-04
2022-05-01 03:04:15,427 INFO [train.py:971] (3/8) Done!